{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 18108, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 5.52242102937928e-05, "grad_norm": 7.185103893280029, "learning_rate": 7.352941176470589e-08, "loss": 0.6199, "step": 1 }, { "epoch": 0.0001104484205875856, "grad_norm": 6.075882911682129, "learning_rate": 1.4705882352941178e-07, "loss": 0.5208, "step": 2 }, { "epoch": 0.0001656726308813784, "grad_norm": 3.92409348487854, "learning_rate": 2.2058823529411768e-07, "loss": 0.3802, "step": 3 }, { "epoch": 0.0002208968411751712, "grad_norm": 3.860447645187378, "learning_rate": 2.9411764705882356e-07, "loss": 0.3971, "step": 4 }, { "epoch": 0.000276121051468964, "grad_norm": 3.1068801879882812, "learning_rate": 3.6764705882352943e-07, "loss": 0.286, "step": 5 }, { "epoch": 0.0003313452617627568, "grad_norm": 4.920706748962402, "learning_rate": 4.4117647058823536e-07, "loss": 0.7312, "step": 6 }, { "epoch": 0.0003865694720565496, "grad_norm": 3.401787042617798, "learning_rate": 5.147058823529412e-07, "loss": 1.1555, "step": 7 }, { "epoch": 0.0004417936823503424, "grad_norm": 6.140610694885254, "learning_rate": 5.882352941176471e-07, "loss": 1.5254, "step": 8 }, { "epoch": 0.0004970178926441351, "grad_norm": 4.104187965393066, "learning_rate": 6.61764705882353e-07, "loss": 1.627, "step": 9 }, { "epoch": 0.000552242102937928, "grad_norm": 6.185025215148926, "learning_rate": 7.352941176470589e-07, "loss": 1.6809, "step": 10 }, { "epoch": 0.0006074663132317208, "grad_norm": 3.5377869606018066, "learning_rate": 8.088235294117648e-07, "loss": 0.5687, "step": 11 }, { "epoch": 0.0006626905235255136, "grad_norm": 4.640303134918213, "learning_rate": 8.823529411764707e-07, "loss": 1.784, "step": 12 }, { "epoch": 0.0007179147338193064, "grad_norm": 4.100270748138428, "learning_rate": 9.558823529411764e-07, "loss": 1.4605, "step": 13 }, { "epoch": 0.0007731389441130992, "grad_norm": 4.901978969573975, "learning_rate": 1.0294117647058825e-06, "loss": 0.5033, "step": 14 }, { "epoch": 0.0008283631544068919, "grad_norm": 4.802917003631592, "learning_rate": 1.1029411764705884e-06, "loss": 0.7745, "step": 15 }, { "epoch": 0.0008835873647006848, "grad_norm": 4.6057658195495605, "learning_rate": 1.1764705882352942e-06, "loss": 0.5419, "step": 16 }, { "epoch": 0.0009388115749944776, "grad_norm": 5.7863383293151855, "learning_rate": 1.25e-06, "loss": 0.8109, "step": 17 }, { "epoch": 0.0009940357852882703, "grad_norm": 6.686889171600342, "learning_rate": 1.323529411764706e-06, "loss": 0.6503, "step": 18 }, { "epoch": 0.0010492599955820633, "grad_norm": 5.7965803146362305, "learning_rate": 1.3970588235294119e-06, "loss": 0.8258, "step": 19 }, { "epoch": 0.001104484205875856, "grad_norm": 3.1672096252441406, "learning_rate": 1.4705882352941177e-06, "loss": 0.4565, "step": 20 }, { "epoch": 0.0011597084161696488, "grad_norm": 4.9186177253723145, "learning_rate": 1.5441176470588238e-06, "loss": 0.3353, "step": 21 }, { "epoch": 0.0012149326264634416, "grad_norm": 4.652125835418701, "learning_rate": 1.6176470588235297e-06, "loss": 0.4815, "step": 22 }, { "epoch": 0.0012701568367572344, "grad_norm": 4.1798529624938965, "learning_rate": 1.6911764705882356e-06, "loss": 0.484, "step": 23 }, { "epoch": 0.0013253810470510272, "grad_norm": 4.800864219665527, "learning_rate": 1.7647058823529414e-06, "loss": 0.9208, "step": 24 }, { "epoch": 0.00138060525734482, "grad_norm": 3.7994601726531982, "learning_rate": 1.8382352941176473e-06, "loss": 0.3603, "step": 25 }, { "epoch": 0.0014358294676386127, "grad_norm": 3.1788876056671143, "learning_rate": 1.9117647058823528e-06, "loss": 0.2718, "step": 26 }, { "epoch": 0.0014910536779324055, "grad_norm": 4.6528754234313965, "learning_rate": 1.985294117647059e-06, "loss": 0.3066, "step": 27 }, { "epoch": 0.0015462778882261983, "grad_norm": 7.097536087036133, "learning_rate": 2.058823529411765e-06, "loss": 1.6165, "step": 28 }, { "epoch": 0.001601502098519991, "grad_norm": 3.394015312194824, "learning_rate": 2.132352941176471e-06, "loss": 0.4067, "step": 29 }, { "epoch": 0.0016567263088137839, "grad_norm": 4.035543441772461, "learning_rate": 2.2058823529411767e-06, "loss": 1.2274, "step": 30 }, { "epoch": 0.0017119505191075769, "grad_norm": 3.5352439880371094, "learning_rate": 2.2794117647058826e-06, "loss": 0.5162, "step": 31 }, { "epoch": 0.0017671747294013696, "grad_norm": 4.931080341339111, "learning_rate": 2.3529411764705885e-06, "loss": 1.1093, "step": 32 }, { "epoch": 0.0018223989396951624, "grad_norm": 4.919506072998047, "learning_rate": 2.4264705882352943e-06, "loss": 0.4265, "step": 33 }, { "epoch": 0.0018776231499889552, "grad_norm": 4.03858757019043, "learning_rate": 2.5e-06, "loss": 1.4025, "step": 34 }, { "epoch": 0.001932847360282748, "grad_norm": 4.724118232727051, "learning_rate": 2.5735294117647057e-06, "loss": 0.3802, "step": 35 }, { "epoch": 0.0019880715705765406, "grad_norm": 3.9996142387390137, "learning_rate": 2.647058823529412e-06, "loss": 0.434, "step": 36 }, { "epoch": 0.0020432957808703338, "grad_norm": 6.570043563842773, "learning_rate": 2.720588235294118e-06, "loss": 1.3737, "step": 37 }, { "epoch": 0.0020985199911641265, "grad_norm": 3.157809257507324, "learning_rate": 2.7941176470588237e-06, "loss": 0.2944, "step": 38 }, { "epoch": 0.0021537442014579193, "grad_norm": 3.7383971214294434, "learning_rate": 2.8676470588235296e-06, "loss": 0.417, "step": 39 }, { "epoch": 0.002208968411751712, "grad_norm": 6.754633903503418, "learning_rate": 2.9411764705882355e-06, "loss": 1.6148, "step": 40 }, { "epoch": 0.002264192622045505, "grad_norm": 4.791891574859619, "learning_rate": 3.0147058823529413e-06, "loss": 0.5909, "step": 41 }, { "epoch": 0.0023194168323392977, "grad_norm": 4.574460506439209, "learning_rate": 3.0882352941176476e-06, "loss": 0.4421, "step": 42 }, { "epoch": 0.0023746410426330905, "grad_norm": 5.159701824188232, "learning_rate": 3.161764705882353e-06, "loss": 1.4162, "step": 43 }, { "epoch": 0.0024298652529268832, "grad_norm": 3.024709701538086, "learning_rate": 3.2352941176470594e-06, "loss": 0.3052, "step": 44 }, { "epoch": 0.002485089463220676, "grad_norm": 3.3240230083465576, "learning_rate": 3.308823529411765e-06, "loss": 0.5621, "step": 45 }, { "epoch": 0.002540313673514469, "grad_norm": 3.7516844272613525, "learning_rate": 3.382352941176471e-06, "loss": 0.2826, "step": 46 }, { "epoch": 0.0025955378838082616, "grad_norm": 3.8965439796447754, "learning_rate": 3.4558823529411766e-06, "loss": 0.5144, "step": 47 }, { "epoch": 0.0026507620941020544, "grad_norm": 5.551485061645508, "learning_rate": 3.529411764705883e-06, "loss": 0.4078, "step": 48 }, { "epoch": 0.002705986304395847, "grad_norm": 4.8652663230896, "learning_rate": 3.6029411764705883e-06, "loss": 0.5128, "step": 49 }, { "epoch": 0.00276121051468964, "grad_norm": 3.032909393310547, "learning_rate": 3.6764705882352946e-06, "loss": 0.2814, "step": 50 }, { "epoch": 0.0028164347249834327, "grad_norm": 4.808829307556152, "learning_rate": 3.7500000000000005e-06, "loss": 1.3292, "step": 51 }, { "epoch": 0.0028716589352772255, "grad_norm": 5.708749294281006, "learning_rate": 3.8235294117647055e-06, "loss": 1.0979, "step": 52 }, { "epoch": 0.0029268831455710183, "grad_norm": 4.589022636413574, "learning_rate": 3.897058823529412e-06, "loss": 0.781, "step": 53 }, { "epoch": 0.002982107355864811, "grad_norm": 4.0772786140441895, "learning_rate": 3.970588235294118e-06, "loss": 0.4404, "step": 54 }, { "epoch": 0.003037331566158604, "grad_norm": 5.9156904220581055, "learning_rate": 4.044117647058824e-06, "loss": 0.7209, "step": 55 }, { "epoch": 0.0030925557764523966, "grad_norm": 5.278625011444092, "learning_rate": 4.11764705882353e-06, "loss": 1.3623, "step": 56 }, { "epoch": 0.0031477799867461894, "grad_norm": 4.468790054321289, "learning_rate": 4.191176470588236e-06, "loss": 0.3371, "step": 57 }, { "epoch": 0.003203004197039982, "grad_norm": 3.634439468383789, "learning_rate": 4.264705882352942e-06, "loss": 1.1993, "step": 58 }, { "epoch": 0.003258228407333775, "grad_norm": 4.527961730957031, "learning_rate": 4.3382352941176475e-06, "loss": 0.7812, "step": 59 }, { "epoch": 0.0033134526176275677, "grad_norm": 6.374586582183838, "learning_rate": 4.411764705882353e-06, "loss": 0.5385, "step": 60 }, { "epoch": 0.0033686768279213605, "grad_norm": 2.5894031524658203, "learning_rate": 4.485294117647059e-06, "loss": 0.3727, "step": 61 }, { "epoch": 0.0034239010382151537, "grad_norm": 3.413083076477051, "learning_rate": 4.558823529411765e-06, "loss": 0.4695, "step": 62 }, { "epoch": 0.0034791252485089465, "grad_norm": 2.953282356262207, "learning_rate": 4.632352941176471e-06, "loss": 0.2496, "step": 63 }, { "epoch": 0.0035343494588027393, "grad_norm": 7.167604923248291, "learning_rate": 4.705882352941177e-06, "loss": 1.2937, "step": 64 }, { "epoch": 0.003589573669096532, "grad_norm": 4.2563862800598145, "learning_rate": 4.779411764705883e-06, "loss": 1.7625, "step": 65 }, { "epoch": 0.003644797879390325, "grad_norm": 4.583209037780762, "learning_rate": 4.852941176470589e-06, "loss": 1.8654, "step": 66 }, { "epoch": 0.0037000220896841176, "grad_norm": 3.7925589084625244, "learning_rate": 4.9264705882352945e-06, "loss": 0.4241, "step": 67 }, { "epoch": 0.0037552462999779104, "grad_norm": 3.1555702686309814, "learning_rate": 5e-06, "loss": 0.3097, "step": 68 }, { "epoch": 0.003810470510271703, "grad_norm": 6.959343910217285, "learning_rate": 5.073529411764706e-06, "loss": 1.7208, "step": 69 }, { "epoch": 0.003865694720565496, "grad_norm": 3.6634302139282227, "learning_rate": 5.147058823529411e-06, "loss": 0.5848, "step": 70 }, { "epoch": 0.003920918930859289, "grad_norm": 3.077915668487549, "learning_rate": 5.220588235294118e-06, "loss": 0.2395, "step": 71 }, { "epoch": 0.003976143141153081, "grad_norm": 5.469890594482422, "learning_rate": 5.294117647058824e-06, "loss": 1.6765, "step": 72 }, { "epoch": 0.004031367351446874, "grad_norm": 2.9641292095184326, "learning_rate": 5.36764705882353e-06, "loss": 0.3897, "step": 73 }, { "epoch": 0.0040865915617406675, "grad_norm": 1.5399712324142456, "learning_rate": 5.441176470588236e-06, "loss": 0.0663, "step": 74 }, { "epoch": 0.00414181577203446, "grad_norm": 2.3528342247009277, "learning_rate": 5.514705882352942e-06, "loss": 0.3451, "step": 75 }, { "epoch": 0.004197039982328253, "grad_norm": 4.420608043670654, "learning_rate": 5.588235294117647e-06, "loss": 1.3597, "step": 76 }, { "epoch": 0.0042522641926220454, "grad_norm": 2.3507041931152344, "learning_rate": 5.661764705882353e-06, "loss": 0.1205, "step": 77 }, { "epoch": 0.004307488402915839, "grad_norm": 3.863997459411621, "learning_rate": 5.735294117647059e-06, "loss": 1.1559, "step": 78 }, { "epoch": 0.004362712613209631, "grad_norm": 4.353459358215332, "learning_rate": 5.808823529411766e-06, "loss": 1.7913, "step": 79 }, { "epoch": 0.004417936823503424, "grad_norm": 4.060234069824219, "learning_rate": 5.882352941176471e-06, "loss": 1.5731, "step": 80 }, { "epoch": 0.0044731610337972166, "grad_norm": 4.0535478591918945, "learning_rate": 5.955882352941177e-06, "loss": 0.5416, "step": 81 }, { "epoch": 0.00452838524409101, "grad_norm": 3.3052978515625, "learning_rate": 6.029411764705883e-06, "loss": 0.4611, "step": 82 }, { "epoch": 0.004583609454384802, "grad_norm": 3.382111072540283, "learning_rate": 6.102941176470589e-06, "loss": 0.4744, "step": 83 }, { "epoch": 0.004638833664678595, "grad_norm": 2.2392210960388184, "learning_rate": 6.176470588235295e-06, "loss": 0.7418, "step": 84 }, { "epoch": 0.004694057874972388, "grad_norm": 2.5303988456726074, "learning_rate": 6.25e-06, "loss": 0.2112, "step": 85 }, { "epoch": 0.004749282085266181, "grad_norm": 3.653113842010498, "learning_rate": 6.323529411764706e-06, "loss": 0.9932, "step": 86 }, { "epoch": 0.004804506295559973, "grad_norm": 1.803563117980957, "learning_rate": 6.397058823529412e-06, "loss": 0.086, "step": 87 }, { "epoch": 0.0048597305058537665, "grad_norm": 3.5912880897521973, "learning_rate": 6.470588235294119e-06, "loss": 0.438, "step": 88 }, { "epoch": 0.004914954716147559, "grad_norm": 4.187110424041748, "learning_rate": 6.544117647058824e-06, "loss": 0.7156, "step": 89 }, { "epoch": 0.004970178926441352, "grad_norm": 3.76251220703125, "learning_rate": 6.61764705882353e-06, "loss": 2.0689, "step": 90 }, { "epoch": 0.005025403136735144, "grad_norm": 4.655309200286865, "learning_rate": 6.6911764705882356e-06, "loss": 2.1136, "step": 91 }, { "epoch": 0.005080627347028938, "grad_norm": 4.040733337402344, "learning_rate": 6.764705882352942e-06, "loss": 1.6301, "step": 92 }, { "epoch": 0.00513585155732273, "grad_norm": 5.455841541290283, "learning_rate": 6.838235294117648e-06, "loss": 1.5756, "step": 93 }, { "epoch": 0.005191075767616523, "grad_norm": 1.1844278573989868, "learning_rate": 6.911764705882353e-06, "loss": 0.1889, "step": 94 }, { "epoch": 0.0052462999779103155, "grad_norm": 5.6567535400390625, "learning_rate": 6.985294117647059e-06, "loss": 1.5317, "step": 95 }, { "epoch": 0.005301524188204109, "grad_norm": 2.720909833908081, "learning_rate": 7.058823529411766e-06, "loss": 0.3311, "step": 96 }, { "epoch": 0.005356748398497901, "grad_norm": 2.994654655456543, "learning_rate": 7.132352941176472e-06, "loss": 0.1356, "step": 97 }, { "epoch": 0.005411972608791694, "grad_norm": 3.657548427581787, "learning_rate": 7.205882352941177e-06, "loss": 1.1528, "step": 98 }, { "epoch": 0.0054671968190854875, "grad_norm": 5.02553129196167, "learning_rate": 7.2794117647058826e-06, "loss": 0.3024, "step": 99 }, { "epoch": 0.00552242102937928, "grad_norm": 1.7824978828430176, "learning_rate": 7.352941176470589e-06, "loss": 0.1885, "step": 100 }, { "epoch": 0.005577645239673073, "grad_norm": 4.360881805419922, "learning_rate": 7.426470588235295e-06, "loss": 0.936, "step": 101 }, { "epoch": 0.005632869449966865, "grad_norm": 1.7617028951644897, "learning_rate": 7.500000000000001e-06, "loss": 0.2216, "step": 102 }, { "epoch": 0.005688093660260659, "grad_norm": 3.810939073562622, "learning_rate": 7.573529411764706e-06, "loss": 1.1293, "step": 103 }, { "epoch": 0.005743317870554451, "grad_norm": 2.4641339778900146, "learning_rate": 7.647058823529411e-06, "loss": 0.8423, "step": 104 }, { "epoch": 0.005798542080848244, "grad_norm": 3.9343886375427246, "learning_rate": 7.720588235294119e-06, "loss": 0.2751, "step": 105 }, { "epoch": 0.0058537662911420365, "grad_norm": 2.0482125282287598, "learning_rate": 7.794117647058825e-06, "loss": 0.1658, "step": 106 }, { "epoch": 0.00590899050143583, "grad_norm": 3.312620162963867, "learning_rate": 7.86764705882353e-06, "loss": 0.5082, "step": 107 }, { "epoch": 0.005964214711729622, "grad_norm": 2.6958558559417725, "learning_rate": 7.941176470588236e-06, "loss": 0.506, "step": 108 }, { "epoch": 0.006019438922023415, "grad_norm": 3.2435264587402344, "learning_rate": 8.014705882352942e-06, "loss": 0.8821, "step": 109 }, { "epoch": 0.006074663132317208, "grad_norm": 2.361140251159668, "learning_rate": 8.088235294117648e-06, "loss": 0.3173, "step": 110 }, { "epoch": 0.006129887342611001, "grad_norm": 1.1956065893173218, "learning_rate": 8.161764705882354e-06, "loss": 0.084, "step": 111 }, { "epoch": 0.006185111552904793, "grad_norm": 4.538455486297607, "learning_rate": 8.23529411764706e-06, "loss": 0.9273, "step": 112 }, { "epoch": 0.006240335763198586, "grad_norm": 5.548904895782471, "learning_rate": 8.308823529411766e-06, "loss": 1.7378, "step": 113 }, { "epoch": 0.006295559973492379, "grad_norm": 1.3338254690170288, "learning_rate": 8.382352941176472e-06, "loss": 0.0857, "step": 114 }, { "epoch": 0.006350784183786172, "grad_norm": 3.1061530113220215, "learning_rate": 8.455882352941177e-06, "loss": 0.5469, "step": 115 }, { "epoch": 0.006406008394079964, "grad_norm": 1.3656977415084839, "learning_rate": 8.529411764705883e-06, "loss": 0.1003, "step": 116 }, { "epoch": 0.0064612326043737576, "grad_norm": 1.8070666790008545, "learning_rate": 8.60294117647059e-06, "loss": 0.2372, "step": 117 }, { "epoch": 0.00651645681466755, "grad_norm": 0.913676917552948, "learning_rate": 8.676470588235295e-06, "loss": 0.1162, "step": 118 }, { "epoch": 0.006571681024961343, "grad_norm": 1.5408262014389038, "learning_rate": 8.750000000000001e-06, "loss": 0.1894, "step": 119 }, { "epoch": 0.0066269052352551355, "grad_norm": 6.546752452850342, "learning_rate": 8.823529411764707e-06, "loss": 2.3959, "step": 120 }, { "epoch": 0.006682129445548929, "grad_norm": 5.237849235534668, "learning_rate": 8.897058823529413e-06, "loss": 1.4746, "step": 121 }, { "epoch": 0.006737353655842721, "grad_norm": 6.887173652648926, "learning_rate": 8.970588235294119e-06, "loss": 1.7185, "step": 122 }, { "epoch": 0.006792577866136514, "grad_norm": 1.900303602218628, "learning_rate": 9.044117647058824e-06, "loss": 0.0992, "step": 123 }, { "epoch": 0.0068478020764303075, "grad_norm": 2.6286559104919434, "learning_rate": 9.11764705882353e-06, "loss": 0.3576, "step": 124 }, { "epoch": 0.0069030262867241, "grad_norm": 4.483473777770996, "learning_rate": 9.191176470588236e-06, "loss": 0.358, "step": 125 }, { "epoch": 0.006958250497017893, "grad_norm": 0.8281896710395813, "learning_rate": 9.264705882352942e-06, "loss": 0.0362, "step": 126 }, { "epoch": 0.007013474707311685, "grad_norm": 2.950624942779541, "learning_rate": 9.338235294117648e-06, "loss": 0.3322, "step": 127 }, { "epoch": 0.007068698917605479, "grad_norm": 2.100003719329834, "learning_rate": 9.411764705882354e-06, "loss": 0.1364, "step": 128 }, { "epoch": 0.007123923127899271, "grad_norm": 4.4532999992370605, "learning_rate": 9.48529411764706e-06, "loss": 1.374, "step": 129 }, { "epoch": 0.007179147338193064, "grad_norm": 5.910168647766113, "learning_rate": 9.558823529411766e-06, "loss": 1.4577, "step": 130 }, { "epoch": 0.0072343715484868565, "grad_norm": 3.925241470336914, "learning_rate": 9.632352941176471e-06, "loss": 0.9142, "step": 131 }, { "epoch": 0.00728959575878065, "grad_norm": 3.1207339763641357, "learning_rate": 9.705882352941177e-06, "loss": 0.2524, "step": 132 }, { "epoch": 0.007344819969074442, "grad_norm": 1.0592808723449707, "learning_rate": 9.779411764705883e-06, "loss": 0.0753, "step": 133 }, { "epoch": 0.007400044179368235, "grad_norm": 2.9456117153167725, "learning_rate": 9.852941176470589e-06, "loss": 0.2446, "step": 134 }, { "epoch": 0.007455268389662028, "grad_norm": 3.6732194423675537, "learning_rate": 9.926470588235295e-06, "loss": 1.3204, "step": 135 }, { "epoch": 0.007510492599955821, "grad_norm": 0.7980672717094421, "learning_rate": 1e-05, "loss": 0.0336, "step": 136 }, { "epoch": 0.007565716810249613, "grad_norm": 5.064492702484131, "learning_rate": 1.0073529411764707e-05, "loss": 0.7117, "step": 137 }, { "epoch": 0.007620941020543406, "grad_norm": 5.834199905395508, "learning_rate": 1.0147058823529413e-05, "loss": 1.257, "step": 138 }, { "epoch": 0.007676165230837199, "grad_norm": 6.355549335479736, "learning_rate": 1.0220588235294118e-05, "loss": 0.3307, "step": 139 }, { "epoch": 0.007731389441130992, "grad_norm": 1.2656056880950928, "learning_rate": 1.0294117647058823e-05, "loss": 0.0764, "step": 140 }, { "epoch": 0.007786613651424784, "grad_norm": 3.055590867996216, "learning_rate": 1.0367647058823532e-05, "loss": 0.8106, "step": 141 }, { "epoch": 0.007841837861718578, "grad_norm": 4.919241428375244, "learning_rate": 1.0441176470588236e-05, "loss": 1.1358, "step": 142 }, { "epoch": 0.00789706207201237, "grad_norm": 2.258880376815796, "learning_rate": 1.0514705882352942e-05, "loss": 0.6085, "step": 143 }, { "epoch": 0.007952286282306162, "grad_norm": 1.0733081102371216, "learning_rate": 1.0588235294117648e-05, "loss": 0.0975, "step": 144 }, { "epoch": 0.008007510492599956, "grad_norm": 1.8443397283554077, "learning_rate": 1.0661764705882354e-05, "loss": 0.0855, "step": 145 }, { "epoch": 0.008062734702893749, "grad_norm": 2.5034561157226562, "learning_rate": 1.073529411764706e-05, "loss": 0.2873, "step": 146 }, { "epoch": 0.008117958913187541, "grad_norm": 2.5130715370178223, "learning_rate": 1.0808823529411765e-05, "loss": 0.1818, "step": 147 }, { "epoch": 0.008173183123481335, "grad_norm": 1.414775013923645, "learning_rate": 1.0882352941176471e-05, "loss": 0.2082, "step": 148 }, { "epoch": 0.008228407333775127, "grad_norm": 2.6998980045318604, "learning_rate": 1.0955882352941179e-05, "loss": 0.381, "step": 149 }, { "epoch": 0.00828363154406892, "grad_norm": 1.2449547052383423, "learning_rate": 1.1029411764705885e-05, "loss": 0.0766, "step": 150 }, { "epoch": 0.008338855754362712, "grad_norm": 1.3590264320373535, "learning_rate": 1.1102941176470589e-05, "loss": 0.1425, "step": 151 }, { "epoch": 0.008394079964656506, "grad_norm": 1.8503589630126953, "learning_rate": 1.1176470588235295e-05, "loss": 0.1386, "step": 152 }, { "epoch": 0.008449304174950299, "grad_norm": 2.8077547550201416, "learning_rate": 1.125e-05, "loss": 0.7339, "step": 153 }, { "epoch": 0.008504528385244091, "grad_norm": 1.2422325611114502, "learning_rate": 1.1323529411764707e-05, "loss": 0.2533, "step": 154 }, { "epoch": 0.008559752595537883, "grad_norm": 1.6314365863800049, "learning_rate": 1.1397058823529412e-05, "loss": 0.2054, "step": 155 }, { "epoch": 0.008614976805831677, "grad_norm": 1.9651319980621338, "learning_rate": 1.1470588235294118e-05, "loss": 0.1923, "step": 156 }, { "epoch": 0.00867020101612547, "grad_norm": 3.7227513790130615, "learning_rate": 1.1544117647058824e-05, "loss": 0.5652, "step": 157 }, { "epoch": 0.008725425226419262, "grad_norm": 1.0320912599563599, "learning_rate": 1.1617647058823532e-05, "loss": 0.1274, "step": 158 }, { "epoch": 0.008780649436713054, "grad_norm": 4.085603713989258, "learning_rate": 1.1691176470588238e-05, "loss": 0.9671, "step": 159 }, { "epoch": 0.008835873647006848, "grad_norm": 2.849208116531372, "learning_rate": 1.1764705882352942e-05, "loss": 0.2854, "step": 160 }, { "epoch": 0.00889109785730064, "grad_norm": 5.495087146759033, "learning_rate": 1.1838235294117648e-05, "loss": 1.0212, "step": 161 }, { "epoch": 0.008946322067594433, "grad_norm": 1.7230602502822876, "learning_rate": 1.1911764705882354e-05, "loss": 0.208, "step": 162 }, { "epoch": 0.009001546277888225, "grad_norm": 5.194159030914307, "learning_rate": 1.198529411764706e-05, "loss": 0.9429, "step": 163 }, { "epoch": 0.00905677048818202, "grad_norm": 0.5359808206558228, "learning_rate": 1.2058823529411765e-05, "loss": 0.0228, "step": 164 }, { "epoch": 0.009111994698475812, "grad_norm": 6.397045612335205, "learning_rate": 1.2132352941176471e-05, "loss": 0.5984, "step": 165 }, { "epoch": 0.009167218908769604, "grad_norm": 3.956895112991333, "learning_rate": 1.2205882352941179e-05, "loss": 1.6676, "step": 166 }, { "epoch": 0.009222443119063397, "grad_norm": 2.4118995666503906, "learning_rate": 1.2279411764705885e-05, "loss": 0.1935, "step": 167 }, { "epoch": 0.00927766732935719, "grad_norm": 1.3944555521011353, "learning_rate": 1.235294117647059e-05, "loss": 0.1363, "step": 168 }, { "epoch": 0.009332891539650983, "grad_norm": 2.197812557220459, "learning_rate": 1.2426470588235295e-05, "loss": 0.1772, "step": 169 }, { "epoch": 0.009388115749944775, "grad_norm": 0.9259921312332153, "learning_rate": 1.25e-05, "loss": 0.0817, "step": 170 }, { "epoch": 0.009443339960238568, "grad_norm": 1.7296556234359741, "learning_rate": 1.2573529411764706e-05, "loss": 0.1019, "step": 171 }, { "epoch": 0.009498564170532362, "grad_norm": 6.420588970184326, "learning_rate": 1.2647058823529412e-05, "loss": 0.5682, "step": 172 }, { "epoch": 0.009553788380826154, "grad_norm": 1.7961820363998413, "learning_rate": 1.2720588235294118e-05, "loss": 0.152, "step": 173 }, { "epoch": 0.009609012591119947, "grad_norm": 3.8713817596435547, "learning_rate": 1.2794117647058824e-05, "loss": 0.5965, "step": 174 }, { "epoch": 0.00966423680141374, "grad_norm": 1.8929321765899658, "learning_rate": 1.2867647058823532e-05, "loss": 0.1592, "step": 175 }, { "epoch": 0.009719461011707533, "grad_norm": 2.2648777961730957, "learning_rate": 1.2941176470588238e-05, "loss": 0.1911, "step": 176 }, { "epoch": 0.009774685222001325, "grad_norm": 2.385037660598755, "learning_rate": 1.3014705882352943e-05, "loss": 0.1396, "step": 177 }, { "epoch": 0.009829909432295118, "grad_norm": 3.7196972370147705, "learning_rate": 1.3088235294117648e-05, "loss": 0.7871, "step": 178 }, { "epoch": 0.009885133642588912, "grad_norm": 3.8967127799987793, "learning_rate": 1.3161764705882353e-05, "loss": 1.2062, "step": 179 }, { "epoch": 0.009940357852882704, "grad_norm": 2.121436357498169, "learning_rate": 1.323529411764706e-05, "loss": 0.2925, "step": 180 }, { "epoch": 0.009995582063176496, "grad_norm": 3.2448558807373047, "learning_rate": 1.3308823529411765e-05, "loss": 0.7736, "step": 181 }, { "epoch": 0.010050806273470289, "grad_norm": 6.812372207641602, "learning_rate": 1.3382352941176471e-05, "loss": 2.1131, "step": 182 }, { "epoch": 0.010106030483764083, "grad_norm": 4.968837738037109, "learning_rate": 1.3455882352941179e-05, "loss": 1.434, "step": 183 }, { "epoch": 0.010161254694057875, "grad_norm": 2.576615333557129, "learning_rate": 1.3529411764705885e-05, "loss": 0.6613, "step": 184 }, { "epoch": 0.010216478904351668, "grad_norm": 1.8582721948623657, "learning_rate": 1.360294117647059e-05, "loss": 0.1242, "step": 185 }, { "epoch": 0.01027170311464546, "grad_norm": 3.7582645416259766, "learning_rate": 1.3676470588235296e-05, "loss": 0.7157, "step": 186 }, { "epoch": 0.010326927324939254, "grad_norm": 2.650296211242676, "learning_rate": 1.375e-05, "loss": 0.18, "step": 187 }, { "epoch": 0.010382151535233046, "grad_norm": 4.153003215789795, "learning_rate": 1.3823529411764706e-05, "loss": 1.2317, "step": 188 }, { "epoch": 0.010437375745526839, "grad_norm": 3.0986573696136475, "learning_rate": 1.3897058823529412e-05, "loss": 0.6727, "step": 189 }, { "epoch": 0.010492599955820631, "grad_norm": 3.920989513397217, "learning_rate": 1.3970588235294118e-05, "loss": 1.0301, "step": 190 }, { "epoch": 0.010547824166114425, "grad_norm": 1.4791523218154907, "learning_rate": 1.4044117647058824e-05, "loss": 0.1278, "step": 191 }, { "epoch": 0.010603048376408217, "grad_norm": 2.81077241897583, "learning_rate": 1.4117647058823532e-05, "loss": 0.207, "step": 192 }, { "epoch": 0.01065827258670201, "grad_norm": 1.8613735437393188, "learning_rate": 1.4191176470588237e-05, "loss": 0.1541, "step": 193 }, { "epoch": 0.010713496796995802, "grad_norm": 2.884692430496216, "learning_rate": 1.4264705882352943e-05, "loss": 0.6505, "step": 194 }, { "epoch": 0.010768721007289596, "grad_norm": 1.4313912391662598, "learning_rate": 1.433823529411765e-05, "loss": 0.0867, "step": 195 }, { "epoch": 0.010823945217583389, "grad_norm": 3.9066619873046875, "learning_rate": 1.4411764705882353e-05, "loss": 0.7359, "step": 196 }, { "epoch": 0.010879169427877181, "grad_norm": 5.705310821533203, "learning_rate": 1.448529411764706e-05, "loss": 1.7208, "step": 197 }, { "epoch": 0.010934393638170975, "grad_norm": 0.8749362826347351, "learning_rate": 1.4558823529411765e-05, "loss": 0.0978, "step": 198 }, { "epoch": 0.010989617848464767, "grad_norm": 3.6093220710754395, "learning_rate": 1.4632352941176471e-05, "loss": 1.0594, "step": 199 }, { "epoch": 0.01104484205875856, "grad_norm": 2.8567869663238525, "learning_rate": 1.4705882352941179e-05, "loss": 0.5243, "step": 200 }, { "epoch": 0.011100066269052352, "grad_norm": 0.9458705186843872, "learning_rate": 1.4779411764705884e-05, "loss": 0.0758, "step": 201 }, { "epoch": 0.011155290479346146, "grad_norm": 5.233914375305176, "learning_rate": 1.485294117647059e-05, "loss": 0.8534, "step": 202 }, { "epoch": 0.011210514689639938, "grad_norm": 2.6427111625671387, "learning_rate": 1.4926470588235296e-05, "loss": 0.1666, "step": 203 }, { "epoch": 0.01126573889993373, "grad_norm": 1.1599160432815552, "learning_rate": 1.5000000000000002e-05, "loss": 0.085, "step": 204 }, { "epoch": 0.011320963110227523, "grad_norm": 4.023028373718262, "learning_rate": 1.5073529411764706e-05, "loss": 0.7691, "step": 205 }, { "epoch": 0.011376187320521317, "grad_norm": 1.8867590427398682, "learning_rate": 1.5147058823529412e-05, "loss": 0.1681, "step": 206 }, { "epoch": 0.01143141153081511, "grad_norm": 4.9077324867248535, "learning_rate": 1.5220588235294118e-05, "loss": 0.666, "step": 207 }, { "epoch": 0.011486635741108902, "grad_norm": 6.877908706665039, "learning_rate": 1.5294117647058822e-05, "loss": 0.6771, "step": 208 }, { "epoch": 0.011541859951402694, "grad_norm": 4.352974891662598, "learning_rate": 1.536764705882353e-05, "loss": 1.3806, "step": 209 }, { "epoch": 0.011597084161696488, "grad_norm": 1.6009525060653687, "learning_rate": 1.5441176470588237e-05, "loss": 0.1186, "step": 210 }, { "epoch": 0.01165230837199028, "grad_norm": 1.7582907676696777, "learning_rate": 1.5514705882352943e-05, "loss": 0.1176, "step": 211 }, { "epoch": 0.011707532582284073, "grad_norm": 1.7525469064712524, "learning_rate": 1.558823529411765e-05, "loss": 0.139, "step": 212 }, { "epoch": 0.011762756792577865, "grad_norm": 1.5220608711242676, "learning_rate": 1.5661764705882355e-05, "loss": 0.0966, "step": 213 }, { "epoch": 0.01181798100287166, "grad_norm": 1.9360203742980957, "learning_rate": 1.573529411764706e-05, "loss": 0.1344, "step": 214 }, { "epoch": 0.011873205213165452, "grad_norm": 1.4453799724578857, "learning_rate": 1.5808823529411767e-05, "loss": 0.0982, "step": 215 }, { "epoch": 0.011928429423459244, "grad_norm": 2.292337417602539, "learning_rate": 1.5882352941176473e-05, "loss": 0.1642, "step": 216 }, { "epoch": 0.011983653633753037, "grad_norm": 3.8290719985961914, "learning_rate": 1.595588235294118e-05, "loss": 0.7808, "step": 217 }, { "epoch": 0.01203887784404683, "grad_norm": 5.626047134399414, "learning_rate": 1.6029411764705884e-05, "loss": 0.8537, "step": 218 }, { "epoch": 0.012094102054340623, "grad_norm": 0.738060474395752, "learning_rate": 1.610294117647059e-05, "loss": 0.0262, "step": 219 }, { "epoch": 0.012149326264634415, "grad_norm": 1.9009205102920532, "learning_rate": 1.6176470588235296e-05, "loss": 0.1458, "step": 220 }, { "epoch": 0.01220455047492821, "grad_norm": 3.1606218814849854, "learning_rate": 1.6250000000000002e-05, "loss": 0.7657, "step": 221 }, { "epoch": 0.012259774685222002, "grad_norm": 1.4142979383468628, "learning_rate": 1.6323529411764708e-05, "loss": 0.0865, "step": 222 }, { "epoch": 0.012314998895515794, "grad_norm": 2.0591623783111572, "learning_rate": 1.6397058823529414e-05, "loss": 0.0602, "step": 223 }, { "epoch": 0.012370223105809586, "grad_norm": 1.340735673904419, "learning_rate": 1.647058823529412e-05, "loss": 0.0617, "step": 224 }, { "epoch": 0.01242544731610338, "grad_norm": 9.034049034118652, "learning_rate": 1.6544117647058825e-05, "loss": 0.3488, "step": 225 }, { "epoch": 0.012480671526397173, "grad_norm": 3.2883808612823486, "learning_rate": 1.661764705882353e-05, "loss": 0.8886, "step": 226 }, { "epoch": 0.012535895736690965, "grad_norm": 3.548686981201172, "learning_rate": 1.6691176470588237e-05, "loss": 0.2992, "step": 227 }, { "epoch": 0.012591119946984758, "grad_norm": 0.6434389352798462, "learning_rate": 1.6764705882352943e-05, "loss": 0.0336, "step": 228 }, { "epoch": 0.012646344157278552, "grad_norm": 6.009524822235107, "learning_rate": 1.683823529411765e-05, "loss": 1.1654, "step": 229 }, { "epoch": 0.012701568367572344, "grad_norm": 1.5884506702423096, "learning_rate": 1.6911764705882355e-05, "loss": 0.0998, "step": 230 }, { "epoch": 0.012756792577866136, "grad_norm": 2.88767671585083, "learning_rate": 1.698529411764706e-05, "loss": 0.2726, "step": 231 }, { "epoch": 0.012812016788159929, "grad_norm": 1.0223500728607178, "learning_rate": 1.7058823529411767e-05, "loss": 0.0566, "step": 232 }, { "epoch": 0.012867240998453723, "grad_norm": 5.716360569000244, "learning_rate": 1.7132352941176472e-05, "loss": 1.8722, "step": 233 }, { "epoch": 0.012922465208747515, "grad_norm": 5.00970983505249, "learning_rate": 1.720588235294118e-05, "loss": 1.9527, "step": 234 }, { "epoch": 0.012977689419041307, "grad_norm": 5.377320289611816, "learning_rate": 1.7279411764705884e-05, "loss": 0.8156, "step": 235 }, { "epoch": 0.0130329136293351, "grad_norm": 7.2957892417907715, "learning_rate": 1.735294117647059e-05, "loss": 0.2114, "step": 236 }, { "epoch": 0.013088137839628894, "grad_norm": 0.8459374904632568, "learning_rate": 1.7426470588235296e-05, "loss": 0.0298, "step": 237 }, { "epoch": 0.013143362049922686, "grad_norm": 6.261492729187012, "learning_rate": 1.7500000000000002e-05, "loss": 1.1785, "step": 238 }, { "epoch": 0.013198586260216479, "grad_norm": 3.086216688156128, "learning_rate": 1.7573529411764708e-05, "loss": 0.5246, "step": 239 }, { "epoch": 0.013253810470510271, "grad_norm": 3.8147356510162354, "learning_rate": 1.7647058823529414e-05, "loss": 0.5619, "step": 240 }, { "epoch": 0.013309034680804065, "grad_norm": 2.271653652191162, "learning_rate": 1.772058823529412e-05, "loss": 0.1283, "step": 241 }, { "epoch": 0.013364258891097857, "grad_norm": 1.962079405784607, "learning_rate": 1.7794117647058825e-05, "loss": 0.2127, "step": 242 }, { "epoch": 0.01341948310139165, "grad_norm": 4.903008460998535, "learning_rate": 1.786764705882353e-05, "loss": 1.2795, "step": 243 }, { "epoch": 0.013474707311685442, "grad_norm": 4.624261856079102, "learning_rate": 1.7941176470588237e-05, "loss": 0.6919, "step": 244 }, { "epoch": 0.013529931521979236, "grad_norm": 3.0656685829162598, "learning_rate": 1.8014705882352943e-05, "loss": 0.1384, "step": 245 }, { "epoch": 0.013585155732273028, "grad_norm": 2.0833635330200195, "learning_rate": 1.808823529411765e-05, "loss": 0.0852, "step": 246 }, { "epoch": 0.01364037994256682, "grad_norm": 4.010784149169922, "learning_rate": 1.8161764705882355e-05, "loss": 0.6268, "step": 247 }, { "epoch": 0.013695604152860615, "grad_norm": 1.468897819519043, "learning_rate": 1.823529411764706e-05, "loss": 0.059, "step": 248 }, { "epoch": 0.013750828363154407, "grad_norm": 2.0847277641296387, "learning_rate": 1.8308823529411766e-05, "loss": 0.1582, "step": 249 }, { "epoch": 0.0138060525734482, "grad_norm": 4.739665985107422, "learning_rate": 1.8382352941176472e-05, "loss": 0.1699, "step": 250 }, { "epoch": 0.013861276783741992, "grad_norm": 2.9844212532043457, "learning_rate": 1.8455882352941178e-05, "loss": 0.1649, "step": 251 }, { "epoch": 0.013916500994035786, "grad_norm": 2.4805588722229004, "learning_rate": 1.8529411764705884e-05, "loss": 0.1222, "step": 252 }, { "epoch": 0.013971725204329578, "grad_norm": 3.1422064304351807, "learning_rate": 1.860294117647059e-05, "loss": 0.0934, "step": 253 }, { "epoch": 0.01402694941462337, "grad_norm": 1.6967849731445312, "learning_rate": 1.8676470588235296e-05, "loss": 0.0606, "step": 254 }, { "epoch": 0.014082173624917163, "grad_norm": 0.6228529810905457, "learning_rate": 1.8750000000000002e-05, "loss": 0.0289, "step": 255 }, { "epoch": 0.014137397835210957, "grad_norm": 3.778024673461914, "learning_rate": 1.8823529411764708e-05, "loss": 0.8323, "step": 256 }, { "epoch": 0.01419262204550475, "grad_norm": 0.4765104055404663, "learning_rate": 1.8897058823529413e-05, "loss": 0.008, "step": 257 }, { "epoch": 0.014247846255798542, "grad_norm": 0.7078060507774353, "learning_rate": 1.897058823529412e-05, "loss": 0.0162, "step": 258 }, { "epoch": 0.014303070466092334, "grad_norm": 2.5727317333221436, "learning_rate": 1.9044117647058825e-05, "loss": 0.115, "step": 259 }, { "epoch": 0.014358294676386128, "grad_norm": 1.0237265825271606, "learning_rate": 1.911764705882353e-05, "loss": 0.0442, "step": 260 }, { "epoch": 0.01441351888667992, "grad_norm": 4.269442558288574, "learning_rate": 1.9191176470588237e-05, "loss": 0.83, "step": 261 }, { "epoch": 0.014468743096973713, "grad_norm": 1.4193402528762817, "learning_rate": 1.9264705882352943e-05, "loss": 0.0473, "step": 262 }, { "epoch": 0.014523967307267505, "grad_norm": 0.8617112636566162, "learning_rate": 1.933823529411765e-05, "loss": 0.0345, "step": 263 }, { "epoch": 0.0145791915175613, "grad_norm": 5.385477066040039, "learning_rate": 1.9411764705882355e-05, "loss": 0.6455, "step": 264 }, { "epoch": 0.014634415727855092, "grad_norm": 3.3829660415649414, "learning_rate": 1.948529411764706e-05, "loss": 0.3172, "step": 265 }, { "epoch": 0.014689639938148884, "grad_norm": 4.953531742095947, "learning_rate": 1.9558823529411766e-05, "loss": 1.4244, "step": 266 }, { "epoch": 0.014744864148442676, "grad_norm": 0.3544113039970398, "learning_rate": 1.9632352941176472e-05, "loss": 0.0071, "step": 267 }, { "epoch": 0.01480008835873647, "grad_norm": 3.1246159076690674, "learning_rate": 1.9705882352941178e-05, "loss": 0.1503, "step": 268 }, { "epoch": 0.014855312569030263, "grad_norm": 1.497964859008789, "learning_rate": 1.9779411764705884e-05, "loss": 0.0647, "step": 269 }, { "epoch": 0.014910536779324055, "grad_norm": 6.373353481292725, "learning_rate": 1.985294117647059e-05, "loss": 0.57, "step": 270 }, { "epoch": 0.01496576098961785, "grad_norm": 4.934869766235352, "learning_rate": 1.9926470588235296e-05, "loss": 1.6724, "step": 271 }, { "epoch": 0.015020985199911642, "grad_norm": 1.6650230884552002, "learning_rate": 2e-05, "loss": 0.1027, "step": 272 }, { "epoch": 0.015076209410205434, "grad_norm": 0.9400707483291626, "learning_rate": 2.0073529411764708e-05, "loss": 0.0251, "step": 273 }, { "epoch": 0.015131433620499226, "grad_norm": 4.201505661010742, "learning_rate": 2.0147058823529413e-05, "loss": 0.4829, "step": 274 }, { "epoch": 0.01518665783079302, "grad_norm": 4.8944525718688965, "learning_rate": 2.022058823529412e-05, "loss": 1.1383, "step": 275 }, { "epoch": 0.015241882041086813, "grad_norm": 6.0761189460754395, "learning_rate": 2.0294117647058825e-05, "loss": 1.2695, "step": 276 }, { "epoch": 0.015297106251380605, "grad_norm": 2.063555955886841, "learning_rate": 2.036764705882353e-05, "loss": 0.0679, "step": 277 }, { "epoch": 0.015352330461674397, "grad_norm": 3.987555742263794, "learning_rate": 2.0441176470588237e-05, "loss": 0.8865, "step": 278 }, { "epoch": 0.015407554671968192, "grad_norm": 5.520766735076904, "learning_rate": 2.051470588235294e-05, "loss": 1.2365, "step": 279 }, { "epoch": 0.015462778882261984, "grad_norm": 7.1682209968566895, "learning_rate": 2.0588235294117645e-05, "loss": 0.6487, "step": 280 }, { "epoch": 0.015518003092555776, "grad_norm": 6.153450965881348, "learning_rate": 2.0661764705882358e-05, "loss": 0.3892, "step": 281 }, { "epoch": 0.015573227302849569, "grad_norm": 5.047737121582031, "learning_rate": 2.0735294117647064e-05, "loss": 0.5162, "step": 282 }, { "epoch": 0.015628451513143363, "grad_norm": 4.847700119018555, "learning_rate": 2.080882352941177e-05, "loss": 0.2962, "step": 283 }, { "epoch": 0.015683675723437155, "grad_norm": 3.99705171585083, "learning_rate": 2.0882352941176472e-05, "loss": 0.2012, "step": 284 }, { "epoch": 0.015738899933730947, "grad_norm": 0.77045738697052, "learning_rate": 2.0955882352941178e-05, "loss": 0.0262, "step": 285 }, { "epoch": 0.01579412414402474, "grad_norm": 6.26143741607666, "learning_rate": 2.1029411764705884e-05, "loss": 1.3936, "step": 286 }, { "epoch": 0.015849348354318532, "grad_norm": 0.5331801176071167, "learning_rate": 2.110294117647059e-05, "loss": 0.014, "step": 287 }, { "epoch": 0.015904572564612324, "grad_norm": 5.719887733459473, "learning_rate": 2.1176470588235296e-05, "loss": 1.4296, "step": 288 }, { "epoch": 0.01595979677490612, "grad_norm": 0.5666600465774536, "learning_rate": 2.125e-05, "loss": 0.015, "step": 289 }, { "epoch": 0.016015020985199913, "grad_norm": 0.7674341797828674, "learning_rate": 2.1323529411764707e-05, "loss": 0.0299, "step": 290 }, { "epoch": 0.016070245195493705, "grad_norm": 5.211278438568115, "learning_rate": 2.1397058823529413e-05, "loss": 1.5854, "step": 291 }, { "epoch": 0.016125469405787497, "grad_norm": 8.410686492919922, "learning_rate": 2.147058823529412e-05, "loss": 0.4636, "step": 292 }, { "epoch": 0.01618069361608129, "grad_norm": 9.061305046081543, "learning_rate": 2.1544117647058825e-05, "loss": 1.2537, "step": 293 }, { "epoch": 0.016235917826375082, "grad_norm": 6.625141143798828, "learning_rate": 2.161764705882353e-05, "loss": 0.8454, "step": 294 }, { "epoch": 0.016291142036668874, "grad_norm": 1.3952410221099854, "learning_rate": 2.1691176470588237e-05, "loss": 0.0413, "step": 295 }, { "epoch": 0.01634636624696267, "grad_norm": 4.4889631271362305, "learning_rate": 2.1764705882352943e-05, "loss": 0.5029, "step": 296 }, { "epoch": 0.016401590457256462, "grad_norm": 0.2698691189289093, "learning_rate": 2.1838235294117645e-05, "loss": 0.0074, "step": 297 }, { "epoch": 0.016456814667550255, "grad_norm": 6.846498489379883, "learning_rate": 2.1911764705882358e-05, "loss": 1.0098, "step": 298 }, { "epoch": 0.016512038877844047, "grad_norm": 7.481047630310059, "learning_rate": 2.1985294117647064e-05, "loss": 0.9815, "step": 299 }, { "epoch": 0.01656726308813784, "grad_norm": 0.7396265268325806, "learning_rate": 2.205882352941177e-05, "loss": 0.0171, "step": 300 }, { "epoch": 0.016622487298431632, "grad_norm": 5.644479274749756, "learning_rate": 2.2132352941176472e-05, "loss": 1.0918, "step": 301 }, { "epoch": 0.016677711508725424, "grad_norm": 1.9274805784225464, "learning_rate": 2.2205882352941178e-05, "loss": 0.0992, "step": 302 }, { "epoch": 0.016732935719019217, "grad_norm": 4.397257328033447, "learning_rate": 2.2279411764705884e-05, "loss": 0.8303, "step": 303 }, { "epoch": 0.016788159929313012, "grad_norm": 0.9634764790534973, "learning_rate": 2.235294117647059e-05, "loss": 0.0272, "step": 304 }, { "epoch": 0.016843384139606805, "grad_norm": 3.7630062103271484, "learning_rate": 2.2426470588235296e-05, "loss": 0.6814, "step": 305 }, { "epoch": 0.016898608349900597, "grad_norm": 1.5614534616470337, "learning_rate": 2.25e-05, "loss": 0.0679, "step": 306 }, { "epoch": 0.01695383256019439, "grad_norm": 9.06970500946045, "learning_rate": 2.2573529411764707e-05, "loss": 0.9057, "step": 307 }, { "epoch": 0.017009056770488182, "grad_norm": 6.353118419647217, "learning_rate": 2.2647058823529413e-05, "loss": 0.6531, "step": 308 }, { "epoch": 0.017064280980781974, "grad_norm": 6.318681716918945, "learning_rate": 2.272058823529412e-05, "loss": 1.0162, "step": 309 }, { "epoch": 0.017119505191075766, "grad_norm": 0.4528250992298126, "learning_rate": 2.2794117647058825e-05, "loss": 0.0135, "step": 310 }, { "epoch": 0.01717472940136956, "grad_norm": 0.7840650677680969, "learning_rate": 2.286764705882353e-05, "loss": 0.0235, "step": 311 }, { "epoch": 0.017229953611663355, "grad_norm": 4.0859198570251465, "learning_rate": 2.2941176470588237e-05, "loss": 0.0772, "step": 312 }, { "epoch": 0.017285177821957147, "grad_norm": 4.648564338684082, "learning_rate": 2.3014705882352943e-05, "loss": 0.4622, "step": 313 }, { "epoch": 0.01734040203225094, "grad_norm": 4.350358963012695, "learning_rate": 2.308823529411765e-05, "loss": 1.4679, "step": 314 }, { "epoch": 0.01739562624254473, "grad_norm": 0.27118393778800964, "learning_rate": 2.3161764705882358e-05, "loss": 0.0098, "step": 315 }, { "epoch": 0.017450850452838524, "grad_norm": 1.4944849014282227, "learning_rate": 2.3235294117647064e-05, "loss": 0.0867, "step": 316 }, { "epoch": 0.017506074663132316, "grad_norm": 2.7394235134124756, "learning_rate": 2.330882352941177e-05, "loss": 0.0758, "step": 317 }, { "epoch": 0.01756129887342611, "grad_norm": 2.7116875648498535, "learning_rate": 2.3382352941176475e-05, "loss": 0.0655, "step": 318 }, { "epoch": 0.017616523083719905, "grad_norm": 1.192162036895752, "learning_rate": 2.3455882352941178e-05, "loss": 0.0297, "step": 319 }, { "epoch": 0.017671747294013697, "grad_norm": 4.051255226135254, "learning_rate": 2.3529411764705884e-05, "loss": 1.1192, "step": 320 }, { "epoch": 0.01772697150430749, "grad_norm": 5.202613353729248, "learning_rate": 2.360294117647059e-05, "loss": 1.0445, "step": 321 }, { "epoch": 0.01778219571460128, "grad_norm": 3.2312495708465576, "learning_rate": 2.3676470588235295e-05, "loss": 0.109, "step": 322 }, { "epoch": 0.017837419924895074, "grad_norm": 5.034701824188232, "learning_rate": 2.375e-05, "loss": 0.9351, "step": 323 }, { "epoch": 0.017892644135188866, "grad_norm": 4.372800827026367, "learning_rate": 2.3823529411764707e-05, "loss": 0.7108, "step": 324 }, { "epoch": 0.01794786834548266, "grad_norm": 6.233377933502197, "learning_rate": 2.3897058823529413e-05, "loss": 1.011, "step": 325 }, { "epoch": 0.01800309255577645, "grad_norm": 4.015389442443848, "learning_rate": 2.397058823529412e-05, "loss": 0.5256, "step": 326 }, { "epoch": 0.018058316766070247, "grad_norm": 4.021751880645752, "learning_rate": 2.4044117647058825e-05, "loss": 0.1806, "step": 327 }, { "epoch": 0.01811354097636404, "grad_norm": 0.41553401947021484, "learning_rate": 2.411764705882353e-05, "loss": 0.013, "step": 328 }, { "epoch": 0.01816876518665783, "grad_norm": 2.944943904876709, "learning_rate": 2.4191176470588237e-05, "loss": 0.0731, "step": 329 }, { "epoch": 0.018223989396951624, "grad_norm": 0.39521315693855286, "learning_rate": 2.4264705882352942e-05, "loss": 0.0112, "step": 330 }, { "epoch": 0.018279213607245416, "grad_norm": 1.7769852876663208, "learning_rate": 2.433823529411765e-05, "loss": 0.073, "step": 331 }, { "epoch": 0.01833443781753921, "grad_norm": 2.2362444400787354, "learning_rate": 2.4411764705882358e-05, "loss": 0.0708, "step": 332 }, { "epoch": 0.018389662027833, "grad_norm": 1.2011122703552246, "learning_rate": 2.4485294117647063e-05, "loss": 0.0345, "step": 333 }, { "epoch": 0.018444886238126793, "grad_norm": 2.4740917682647705, "learning_rate": 2.455882352941177e-05, "loss": 0.1421, "step": 334 }, { "epoch": 0.01850011044842059, "grad_norm": 2.140263795852661, "learning_rate": 2.4632352941176475e-05, "loss": 0.0989, "step": 335 }, { "epoch": 0.01855533465871438, "grad_norm": 3.7683064937591553, "learning_rate": 2.470588235294118e-05, "loss": 0.2322, "step": 336 }, { "epoch": 0.018610558869008174, "grad_norm": 4.61720085144043, "learning_rate": 2.4779411764705884e-05, "loss": 0.4364, "step": 337 }, { "epoch": 0.018665783079301966, "grad_norm": 3.2000298500061035, "learning_rate": 2.485294117647059e-05, "loss": 0.5964, "step": 338 }, { "epoch": 0.01872100728959576, "grad_norm": 2.6742758750915527, "learning_rate": 2.4926470588235295e-05, "loss": 0.082, "step": 339 }, { "epoch": 0.01877623149988955, "grad_norm": 3.9628548622131348, "learning_rate": 2.5e-05, "loss": 1.738, "step": 340 }, { "epoch": 0.018831455710183343, "grad_norm": 6.107083797454834, "learning_rate": 2.5073529411764707e-05, "loss": 0.3863, "step": 341 }, { "epoch": 0.018886679920477135, "grad_norm": 7.0268025398254395, "learning_rate": 2.5147058823529413e-05, "loss": 2.4745, "step": 342 }, { "epoch": 0.01894190413077093, "grad_norm": 4.234157085418701, "learning_rate": 2.522058823529412e-05, "loss": 0.3275, "step": 343 }, { "epoch": 0.018997128341064724, "grad_norm": 1.093874216079712, "learning_rate": 2.5294117647058825e-05, "loss": 0.0494, "step": 344 }, { "epoch": 0.019052352551358516, "grad_norm": 1.913493275642395, "learning_rate": 2.536764705882353e-05, "loss": 0.0926, "step": 345 }, { "epoch": 0.01910757676165231, "grad_norm": 0.9106028079986572, "learning_rate": 2.5441176470588236e-05, "loss": 0.0259, "step": 346 }, { "epoch": 0.0191628009719461, "grad_norm": 4.387288570404053, "learning_rate": 2.5514705882352942e-05, "loss": 0.8474, "step": 347 }, { "epoch": 0.019218025182239893, "grad_norm": 1.0246256589889526, "learning_rate": 2.5588235294117648e-05, "loss": 0.0159, "step": 348 }, { "epoch": 0.019273249392533685, "grad_norm": 1.6517624855041504, "learning_rate": 2.5661764705882357e-05, "loss": 0.0457, "step": 349 }, { "epoch": 0.01932847360282748, "grad_norm": 3.731339454650879, "learning_rate": 2.5735294117647063e-05, "loss": 0.6271, "step": 350 }, { "epoch": 0.019383697813121274, "grad_norm": 0.9247974157333374, "learning_rate": 2.580882352941177e-05, "loss": 0.0187, "step": 351 }, { "epoch": 0.019438922023415066, "grad_norm": 2.612698554992676, "learning_rate": 2.5882352941176475e-05, "loss": 0.0388, "step": 352 }, { "epoch": 0.019494146233708858, "grad_norm": 4.510993480682373, "learning_rate": 2.595588235294118e-05, "loss": 0.6171, "step": 353 }, { "epoch": 0.01954937044400265, "grad_norm": 0.5690004229545593, "learning_rate": 2.6029411764705887e-05, "loss": 0.0159, "step": 354 }, { "epoch": 0.019604594654296443, "grad_norm": 0.4854104518890381, "learning_rate": 2.610294117647059e-05, "loss": 0.0132, "step": 355 }, { "epoch": 0.019659818864590235, "grad_norm": 2.015963077545166, "learning_rate": 2.6176470588235295e-05, "loss": 0.115, "step": 356 }, { "epoch": 0.019715043074884028, "grad_norm": 5.840193748474121, "learning_rate": 2.625e-05, "loss": 1.5124, "step": 357 }, { "epoch": 0.019770267285177823, "grad_norm": 0.22214117646217346, "learning_rate": 2.6323529411764707e-05, "loss": 0.0058, "step": 358 }, { "epoch": 0.019825491495471616, "grad_norm": 3.0864346027374268, "learning_rate": 2.6397058823529413e-05, "loss": 0.0618, "step": 359 }, { "epoch": 0.019880715705765408, "grad_norm": 0.26539334654808044, "learning_rate": 2.647058823529412e-05, "loss": 0.0064, "step": 360 }, { "epoch": 0.0199359399160592, "grad_norm": 3.266493320465088, "learning_rate": 2.6544117647058825e-05, "loss": 0.081, "step": 361 }, { "epoch": 0.019991164126352993, "grad_norm": 1.662179708480835, "learning_rate": 2.661764705882353e-05, "loss": 0.0327, "step": 362 }, { "epoch": 0.020046388336646785, "grad_norm": 4.567314147949219, "learning_rate": 2.6691176470588236e-05, "loss": 1.5002, "step": 363 }, { "epoch": 0.020101612546940578, "grad_norm": 5.0696330070495605, "learning_rate": 2.6764705882352942e-05, "loss": 0.7061, "step": 364 }, { "epoch": 0.02015683675723437, "grad_norm": 0.9468331933021545, "learning_rate": 2.6838235294117648e-05, "loss": 0.0196, "step": 365 }, { "epoch": 0.020212060967528166, "grad_norm": 4.571047782897949, "learning_rate": 2.6911764705882357e-05, "loss": 0.3284, "step": 366 }, { "epoch": 0.020267285177821958, "grad_norm": 0.31906476616859436, "learning_rate": 2.6985294117647063e-05, "loss": 0.0072, "step": 367 }, { "epoch": 0.02032250938811575, "grad_norm": 0.6961895823478699, "learning_rate": 2.705882352941177e-05, "loss": 0.0125, "step": 368 }, { "epoch": 0.020377733598409543, "grad_norm": 7.386866092681885, "learning_rate": 2.7132352941176475e-05, "loss": 0.9946, "step": 369 }, { "epoch": 0.020432957808703335, "grad_norm": 4.232499599456787, "learning_rate": 2.720588235294118e-05, "loss": 0.4794, "step": 370 }, { "epoch": 0.020488182018997127, "grad_norm": 0.16127610206604004, "learning_rate": 2.7279411764705887e-05, "loss": 0.0024, "step": 371 }, { "epoch": 0.02054340622929092, "grad_norm": 7.5632123947143555, "learning_rate": 2.7352941176470593e-05, "loss": 0.4716, "step": 372 }, { "epoch": 0.020598630439584716, "grad_norm": 0.31277963519096375, "learning_rate": 2.7426470588235295e-05, "loss": 0.0078, "step": 373 }, { "epoch": 0.020653854649878508, "grad_norm": 0.3074933886528015, "learning_rate": 2.75e-05, "loss": 0.0049, "step": 374 }, { "epoch": 0.0207090788601723, "grad_norm": 5.159824848175049, "learning_rate": 2.7573529411764707e-05, "loss": 0.9211, "step": 375 }, { "epoch": 0.020764303070466093, "grad_norm": 5.982489585876465, "learning_rate": 2.7647058823529413e-05, "loss": 0.1189, "step": 376 }, { "epoch": 0.020819527280759885, "grad_norm": 0.32522261142730713, "learning_rate": 2.772058823529412e-05, "loss": 0.0081, "step": 377 }, { "epoch": 0.020874751491053677, "grad_norm": 0.7400128245353699, "learning_rate": 2.7794117647058824e-05, "loss": 0.0249, "step": 378 }, { "epoch": 0.02092997570134747, "grad_norm": 0.24857397377490997, "learning_rate": 2.786764705882353e-05, "loss": 0.0058, "step": 379 }, { "epoch": 0.020985199911641262, "grad_norm": 4.345304012298584, "learning_rate": 2.7941176470588236e-05, "loss": 0.1738, "step": 380 }, { "epoch": 0.021040424121935058, "grad_norm": 1.9369651079177856, "learning_rate": 2.8014705882352942e-05, "loss": 0.0324, "step": 381 }, { "epoch": 0.02109564833222885, "grad_norm": 3.7126951217651367, "learning_rate": 2.8088235294117648e-05, "loss": 0.4375, "step": 382 }, { "epoch": 0.021150872542522643, "grad_norm": 5.284471035003662, "learning_rate": 2.8161764705882357e-05, "loss": 0.6826, "step": 383 }, { "epoch": 0.021206096752816435, "grad_norm": 3.5934698581695557, "learning_rate": 2.8235294117647063e-05, "loss": 0.0753, "step": 384 }, { "epoch": 0.021261320963110227, "grad_norm": 0.09543141722679138, "learning_rate": 2.830882352941177e-05, "loss": 0.0015, "step": 385 }, { "epoch": 0.02131654517340402, "grad_norm": 1.358591079711914, "learning_rate": 2.8382352941176475e-05, "loss": 0.0307, "step": 386 }, { "epoch": 0.021371769383697812, "grad_norm": 4.155521869659424, "learning_rate": 2.845588235294118e-05, "loss": 0.9043, "step": 387 }, { "epoch": 0.021426993593991604, "grad_norm": 5.6654253005981445, "learning_rate": 2.8529411764705887e-05, "loss": 0.6361, "step": 388 }, { "epoch": 0.0214822178042854, "grad_norm": 3.6392924785614014, "learning_rate": 2.8602941176470593e-05, "loss": 0.4909, "step": 389 }, { "epoch": 0.021537442014579192, "grad_norm": 6.269838333129883, "learning_rate": 2.86764705882353e-05, "loss": 1.4363, "step": 390 }, { "epoch": 0.021592666224872985, "grad_norm": 6.487565040588379, "learning_rate": 2.875e-05, "loss": 1.254, "step": 391 }, { "epoch": 0.021647890435166777, "grad_norm": 4.32818603515625, "learning_rate": 2.8823529411764707e-05, "loss": 1.0515, "step": 392 }, { "epoch": 0.02170311464546057, "grad_norm": 1.2763035297393799, "learning_rate": 2.8897058823529413e-05, "loss": 0.0147, "step": 393 }, { "epoch": 0.021758338855754362, "grad_norm": 5.525787353515625, "learning_rate": 2.897058823529412e-05, "loss": 0.915, "step": 394 }, { "epoch": 0.021813563066048154, "grad_norm": 0.4385192394256592, "learning_rate": 2.9044117647058824e-05, "loss": 0.0065, "step": 395 }, { "epoch": 0.02186878727634195, "grad_norm": 0.5614654421806335, "learning_rate": 2.911764705882353e-05, "loss": 0.0108, "step": 396 }, { "epoch": 0.021924011486635742, "grad_norm": 0.336515337228775, "learning_rate": 2.9191176470588236e-05, "loss": 0.0048, "step": 397 }, { "epoch": 0.021979235696929535, "grad_norm": 0.44494765996932983, "learning_rate": 2.9264705882352942e-05, "loss": 0.0073, "step": 398 }, { "epoch": 0.022034459907223327, "grad_norm": 0.9118404388427734, "learning_rate": 2.9338235294117648e-05, "loss": 0.017, "step": 399 }, { "epoch": 0.02208968411751712, "grad_norm": 4.358837127685547, "learning_rate": 2.9411764705882357e-05, "loss": 0.555, "step": 400 }, { "epoch": 0.02214490832781091, "grad_norm": 3.7980289459228516, "learning_rate": 2.9485294117647063e-05, "loss": 0.0629, "step": 401 }, { "epoch": 0.022200132538104704, "grad_norm": 6.975796222686768, "learning_rate": 2.955882352941177e-05, "loss": 0.2283, "step": 402 }, { "epoch": 0.022255356748398496, "grad_norm": 3.7817375659942627, "learning_rate": 2.9632352941176475e-05, "loss": 0.0544, "step": 403 }, { "epoch": 0.022310580958692292, "grad_norm": 6.893856525421143, "learning_rate": 2.970588235294118e-05, "loss": 0.5806, "step": 404 }, { "epoch": 0.022365805168986085, "grad_norm": 4.029657363891602, "learning_rate": 2.9779411764705887e-05, "loss": 0.61, "step": 405 }, { "epoch": 0.022421029379279877, "grad_norm": 7.5142903327941895, "learning_rate": 2.9852941176470592e-05, "loss": 1.5398, "step": 406 }, { "epoch": 0.02247625358957367, "grad_norm": 0.35187405347824097, "learning_rate": 2.9926470588235298e-05, "loss": 0.0067, "step": 407 }, { "epoch": 0.02253147779986746, "grad_norm": 4.0492262840271, "learning_rate": 3.0000000000000004e-05, "loss": 0.3182, "step": 408 }, { "epoch": 0.022586702010161254, "grad_norm": 6.528915882110596, "learning_rate": 3.0073529411764707e-05, "loss": 0.1277, "step": 409 }, { "epoch": 0.022641926220455046, "grad_norm": 3.8416924476623535, "learning_rate": 3.0147058823529413e-05, "loss": 0.1257, "step": 410 }, { "epoch": 0.02269715043074884, "grad_norm": 6.960031509399414, "learning_rate": 3.022058823529412e-05, "loss": 0.1901, "step": 411 }, { "epoch": 0.022752374641042634, "grad_norm": 7.10014009475708, "learning_rate": 3.0294117647058824e-05, "loss": 1.1314, "step": 412 }, { "epoch": 0.022807598851336427, "grad_norm": 2.59033203125, "learning_rate": 3.036764705882353e-05, "loss": 0.2255, "step": 413 }, { "epoch": 0.02286282306163022, "grad_norm": 4.772641181945801, "learning_rate": 3.0441176470588236e-05, "loss": 0.2219, "step": 414 }, { "epoch": 0.02291804727192401, "grad_norm": 3.457597255706787, "learning_rate": 3.0514705882352942e-05, "loss": 0.4768, "step": 415 }, { "epoch": 0.022973271482217804, "grad_norm": 4.312600612640381, "learning_rate": 3.0588235294117644e-05, "loss": 0.1265, "step": 416 }, { "epoch": 0.023028495692511596, "grad_norm": 2.881443977355957, "learning_rate": 3.066176470588236e-05, "loss": 0.0679, "step": 417 }, { "epoch": 0.02308371990280539, "grad_norm": 3.1859657764434814, "learning_rate": 3.073529411764706e-05, "loss": 0.1026, "step": 418 }, { "epoch": 0.023138944113099184, "grad_norm": 3.598214864730835, "learning_rate": 3.080882352941177e-05, "loss": 0.6389, "step": 419 }, { "epoch": 0.023194168323392977, "grad_norm": 3.5698401927948, "learning_rate": 3.0882352941176475e-05, "loss": 0.7273, "step": 420 }, { "epoch": 0.02324939253368677, "grad_norm": 8.257476806640625, "learning_rate": 3.095588235294118e-05, "loss": 0.9289, "step": 421 }, { "epoch": 0.02330461674398056, "grad_norm": 4.16469144821167, "learning_rate": 3.1029411764705886e-05, "loss": 0.8978, "step": 422 }, { "epoch": 0.023359840954274354, "grad_norm": 3.885716438293457, "learning_rate": 3.110294117647059e-05, "loss": 0.5365, "step": 423 }, { "epoch": 0.023415065164568146, "grad_norm": 0.3642376959323883, "learning_rate": 3.11764705882353e-05, "loss": 0.0118, "step": 424 }, { "epoch": 0.02347028937486194, "grad_norm": 6.821834087371826, "learning_rate": 3.125e-05, "loss": 0.8642, "step": 425 }, { "epoch": 0.02352551358515573, "grad_norm": 1.9876446723937988, "learning_rate": 3.132352941176471e-05, "loss": 0.0608, "step": 426 }, { "epoch": 0.023580737795449527, "grad_norm": 2.7361083030700684, "learning_rate": 3.139705882352941e-05, "loss": 0.0563, "step": 427 }, { "epoch": 0.02363596200574332, "grad_norm": 5.742252826690674, "learning_rate": 3.147058823529412e-05, "loss": 2.0609, "step": 428 }, { "epoch": 0.02369118621603711, "grad_norm": 0.33838987350463867, "learning_rate": 3.1544117647058824e-05, "loss": 0.008, "step": 429 }, { "epoch": 0.023746410426330904, "grad_norm": 2.353090763092041, "learning_rate": 3.1617647058823533e-05, "loss": 0.1534, "step": 430 }, { "epoch": 0.023801634636624696, "grad_norm": 7.181396484375, "learning_rate": 3.1691176470588236e-05, "loss": 0.2, "step": 431 }, { "epoch": 0.02385685884691849, "grad_norm": 0.6294129490852356, "learning_rate": 3.1764705882352945e-05, "loss": 0.0151, "step": 432 }, { "epoch": 0.02391208305721228, "grad_norm": 5.0471343994140625, "learning_rate": 3.183823529411765e-05, "loss": 0.1952, "step": 433 }, { "epoch": 0.023967307267506073, "grad_norm": 0.9891933798789978, "learning_rate": 3.191176470588236e-05, "loss": 0.0315, "step": 434 }, { "epoch": 0.02402253147779987, "grad_norm": 3.282895088195801, "learning_rate": 3.1985294117647066e-05, "loss": 0.2292, "step": 435 }, { "epoch": 0.02407775568809366, "grad_norm": 0.26842519640922546, "learning_rate": 3.205882352941177e-05, "loss": 0.0072, "step": 436 }, { "epoch": 0.024132979898387454, "grad_norm": 5.518017292022705, "learning_rate": 3.213235294117647e-05, "loss": 0.0445, "step": 437 }, { "epoch": 0.024188204108681246, "grad_norm": 3.018923759460449, "learning_rate": 3.220588235294118e-05, "loss": 0.2667, "step": 438 }, { "epoch": 0.024243428318975038, "grad_norm": 3.963533639907837, "learning_rate": 3.227941176470588e-05, "loss": 0.1232, "step": 439 }, { "epoch": 0.02429865252926883, "grad_norm": 4.5815815925598145, "learning_rate": 3.235294117647059e-05, "loss": 0.5786, "step": 440 }, { "epoch": 0.024353876739562623, "grad_norm": 0.6328360438346863, "learning_rate": 3.2426470588235295e-05, "loss": 0.0199, "step": 441 }, { "epoch": 0.02440910094985642, "grad_norm": 5.497945308685303, "learning_rate": 3.2500000000000004e-05, "loss": 0.6839, "step": 442 }, { "epoch": 0.02446432516015021, "grad_norm": 3.3829312324523926, "learning_rate": 3.2573529411764706e-05, "loss": 0.3558, "step": 443 }, { "epoch": 0.024519549370444003, "grad_norm": 5.388258457183838, "learning_rate": 3.2647058823529416e-05, "loss": 1.0474, "step": 444 }, { "epoch": 0.024574773580737796, "grad_norm": 4.09397029876709, "learning_rate": 3.272058823529412e-05, "loss": 0.5895, "step": 445 }, { "epoch": 0.024629997791031588, "grad_norm": 5.795022487640381, "learning_rate": 3.279411764705883e-05, "loss": 0.198, "step": 446 }, { "epoch": 0.02468522200132538, "grad_norm": 4.503425121307373, "learning_rate": 3.286764705882353e-05, "loss": 1.2663, "step": 447 }, { "epoch": 0.024740446211619173, "grad_norm": 5.004148006439209, "learning_rate": 3.294117647058824e-05, "loss": 0.4779, "step": 448 }, { "epoch": 0.024795670421912965, "grad_norm": 0.054085616022348404, "learning_rate": 3.301470588235294e-05, "loss": 0.0017, "step": 449 }, { "epoch": 0.02485089463220676, "grad_norm": 4.138420581817627, "learning_rate": 3.308823529411765e-05, "loss": 0.8978, "step": 450 }, { "epoch": 0.024906118842500553, "grad_norm": 2.4874298572540283, "learning_rate": 3.316176470588236e-05, "loss": 0.2365, "step": 451 }, { "epoch": 0.024961343052794346, "grad_norm": 0.20889997482299805, "learning_rate": 3.323529411764706e-05, "loss": 0.0085, "step": 452 }, { "epoch": 0.025016567263088138, "grad_norm": 0.44466832280158997, "learning_rate": 3.330882352941177e-05, "loss": 0.0191, "step": 453 }, { "epoch": 0.02507179147338193, "grad_norm": 3.307723045349121, "learning_rate": 3.3382352941176474e-05, "loss": 0.3114, "step": 454 }, { "epoch": 0.025127015683675723, "grad_norm": 0.4353792369365692, "learning_rate": 3.345588235294118e-05, "loss": 0.0072, "step": 455 }, { "epoch": 0.025182239893969515, "grad_norm": 3.721048593521118, "learning_rate": 3.3529411764705886e-05, "loss": 0.2607, "step": 456 }, { "epoch": 0.025237464104263307, "grad_norm": 0.13869716227054596, "learning_rate": 3.360294117647059e-05, "loss": 0.0041, "step": 457 }, { "epoch": 0.025292688314557103, "grad_norm": 7.822288513183594, "learning_rate": 3.36764705882353e-05, "loss": 0.1415, "step": 458 }, { "epoch": 0.025347912524850896, "grad_norm": 0.12269444763660431, "learning_rate": 3.375e-05, "loss": 0.0047, "step": 459 }, { "epoch": 0.025403136735144688, "grad_norm": 3.4460835456848145, "learning_rate": 3.382352941176471e-05, "loss": 0.0982, "step": 460 }, { "epoch": 0.02545836094543848, "grad_norm": 7.1414055824279785, "learning_rate": 3.389705882352941e-05, "loss": 1.7347, "step": 461 }, { "epoch": 0.025513585155732273, "grad_norm": 6.629969120025635, "learning_rate": 3.397058823529412e-05, "loss": 1.4526, "step": 462 }, { "epoch": 0.025568809366026065, "grad_norm": 3.6714158058166504, "learning_rate": 3.4044117647058824e-05, "loss": 0.9497, "step": 463 }, { "epoch": 0.025624033576319857, "grad_norm": 5.636823654174805, "learning_rate": 3.411764705882353e-05, "loss": 0.8266, "step": 464 }, { "epoch": 0.025679257786613653, "grad_norm": 0.09867200255393982, "learning_rate": 3.4191176470588236e-05, "loss": 0.0032, "step": 465 }, { "epoch": 0.025734481996907446, "grad_norm": 0.18228818476200104, "learning_rate": 3.4264705882352945e-05, "loss": 0.0049, "step": 466 }, { "epoch": 0.025789706207201238, "grad_norm": 3.7138068675994873, "learning_rate": 3.433823529411765e-05, "loss": 0.7251, "step": 467 }, { "epoch": 0.02584493041749503, "grad_norm": 4.384453773498535, "learning_rate": 3.441176470588236e-05, "loss": 0.4177, "step": 468 }, { "epoch": 0.025900154627788823, "grad_norm": 4.9796462059021, "learning_rate": 3.4485294117647066e-05, "loss": 0.7783, "step": 469 }, { "epoch": 0.025955378838082615, "grad_norm": 0.7884670495986938, "learning_rate": 3.455882352941177e-05, "loss": 0.0159, "step": 470 }, { "epoch": 0.026010603048376407, "grad_norm": 3.9222452640533447, "learning_rate": 3.463235294117648e-05, "loss": 0.7479, "step": 471 }, { "epoch": 0.0260658272586702, "grad_norm": 3.7433316707611084, "learning_rate": 3.470588235294118e-05, "loss": 0.5481, "step": 472 }, { "epoch": 0.026121051468963995, "grad_norm": 0.9089195728302002, "learning_rate": 3.477941176470588e-05, "loss": 0.0233, "step": 473 }, { "epoch": 0.026176275679257788, "grad_norm": 4.512223243713379, "learning_rate": 3.485294117647059e-05, "loss": 1.0413, "step": 474 }, { "epoch": 0.02623149988955158, "grad_norm": 2.3850924968719482, "learning_rate": 3.4926470588235294e-05, "loss": 0.1235, "step": 475 }, { "epoch": 0.026286724099845372, "grad_norm": 4.684517860412598, "learning_rate": 3.5000000000000004e-05, "loss": 0.9131, "step": 476 }, { "epoch": 0.026341948310139165, "grad_norm": 3.658905506134033, "learning_rate": 3.5073529411764706e-05, "loss": 0.1631, "step": 477 }, { "epoch": 0.026397172520432957, "grad_norm": 3.34297251701355, "learning_rate": 3.5147058823529415e-05, "loss": 0.2163, "step": 478 }, { "epoch": 0.02645239673072675, "grad_norm": 5.445257186889648, "learning_rate": 3.522058823529412e-05, "loss": 0.7282, "step": 479 }, { "epoch": 0.026507620941020542, "grad_norm": 1.7133256196975708, "learning_rate": 3.529411764705883e-05, "loss": 0.0883, "step": 480 }, { "epoch": 0.026562845151314338, "grad_norm": 3.3327887058258057, "learning_rate": 3.536764705882353e-05, "loss": 0.1605, "step": 481 }, { "epoch": 0.02661806936160813, "grad_norm": 4.1416192054748535, "learning_rate": 3.544117647058824e-05, "loss": 0.6363, "step": 482 }, { "epoch": 0.026673293571901922, "grad_norm": 1.226915955543518, "learning_rate": 3.551470588235294e-05, "loss": 0.0452, "step": 483 }, { "epoch": 0.026728517782195715, "grad_norm": 3.7566025257110596, "learning_rate": 3.558823529411765e-05, "loss": 0.2602, "step": 484 }, { "epoch": 0.026783741992489507, "grad_norm": 0.5719228982925415, "learning_rate": 3.566176470588236e-05, "loss": 0.0144, "step": 485 }, { "epoch": 0.0268389662027833, "grad_norm": 0.3152928352355957, "learning_rate": 3.573529411764706e-05, "loss": 0.0107, "step": 486 }, { "epoch": 0.026894190413077092, "grad_norm": 5.585684299468994, "learning_rate": 3.580882352941177e-05, "loss": 0.4287, "step": 487 }, { "epoch": 0.026949414623370884, "grad_norm": 4.36761999130249, "learning_rate": 3.5882352941176474e-05, "loss": 0.6266, "step": 488 }, { "epoch": 0.02700463883366468, "grad_norm": 0.49481889605522156, "learning_rate": 3.5955882352941183e-05, "loss": 0.0104, "step": 489 }, { "epoch": 0.027059863043958472, "grad_norm": 0.18823808431625366, "learning_rate": 3.6029411764705886e-05, "loss": 0.006, "step": 490 }, { "epoch": 0.027115087254252265, "grad_norm": 0.19897757470607758, "learning_rate": 3.610294117647059e-05, "loss": 0.0049, "step": 491 }, { "epoch": 0.027170311464546057, "grad_norm": 2.5122127532958984, "learning_rate": 3.61764705882353e-05, "loss": 0.2356, "step": 492 }, { "epoch": 0.02722553567483985, "grad_norm": 0.2278033047914505, "learning_rate": 3.625e-05, "loss": 0.0071, "step": 493 }, { "epoch": 0.02728075988513364, "grad_norm": 0.365024596452713, "learning_rate": 3.632352941176471e-05, "loss": 0.0118, "step": 494 }, { "epoch": 0.027335984095427434, "grad_norm": 5.593668460845947, "learning_rate": 3.639705882352941e-05, "loss": 0.8115, "step": 495 }, { "epoch": 0.02739120830572123, "grad_norm": 1.892519474029541, "learning_rate": 3.647058823529412e-05, "loss": 0.097, "step": 496 }, { "epoch": 0.027446432516015022, "grad_norm": 6.435330390930176, "learning_rate": 3.6544117647058824e-05, "loss": 0.6724, "step": 497 }, { "epoch": 0.027501656726308814, "grad_norm": 1.5971133708953857, "learning_rate": 3.661764705882353e-05, "loss": 0.1006, "step": 498 }, { "epoch": 0.027556880936602607, "grad_norm": 3.565869092941284, "learning_rate": 3.6691176470588235e-05, "loss": 0.4929, "step": 499 }, { "epoch": 0.0276121051468964, "grad_norm": 6.451878070831299, "learning_rate": 3.6764705882352945e-05, "loss": 2.1705, "step": 500 }, { "epoch": 0.02766732935719019, "grad_norm": 0.40949687361717224, "learning_rate": 3.683823529411765e-05, "loss": 0.0125, "step": 501 }, { "epoch": 0.027722553567483984, "grad_norm": 5.888401985168457, "learning_rate": 3.6911764705882356e-05, "loss": 1.0534, "step": 502 }, { "epoch": 0.027777777777777776, "grad_norm": 0.7621806263923645, "learning_rate": 3.6985294117647066e-05, "loss": 0.0272, "step": 503 }, { "epoch": 0.027833001988071572, "grad_norm": 0.09555760025978088, "learning_rate": 3.705882352941177e-05, "loss": 0.003, "step": 504 }, { "epoch": 0.027888226198365364, "grad_norm": 3.6422712802886963, "learning_rate": 3.713235294117648e-05, "loss": 0.607, "step": 505 }, { "epoch": 0.027943450408659157, "grad_norm": 1.314074158668518, "learning_rate": 3.720588235294118e-05, "loss": 0.0485, "step": 506 }, { "epoch": 0.02799867461895295, "grad_norm": 0.7201856970787048, "learning_rate": 3.727941176470589e-05, "loss": 0.0191, "step": 507 }, { "epoch": 0.02805389882924674, "grad_norm": 6.08767557144165, "learning_rate": 3.735294117647059e-05, "loss": 0.8055, "step": 508 }, { "epoch": 0.028109123039540534, "grad_norm": 1.773444652557373, "learning_rate": 3.7426470588235294e-05, "loss": 0.0734, "step": 509 }, { "epoch": 0.028164347249834326, "grad_norm": 4.458462238311768, "learning_rate": 3.7500000000000003e-05, "loss": 0.9514, "step": 510 }, { "epoch": 0.02821957146012812, "grad_norm": 0.627357006072998, "learning_rate": 3.7573529411764706e-05, "loss": 0.025, "step": 511 }, { "epoch": 0.028274795670421914, "grad_norm": 3.847482919692993, "learning_rate": 3.7647058823529415e-05, "loss": 0.2076, "step": 512 }, { "epoch": 0.028330019880715707, "grad_norm": 4.803913593292236, "learning_rate": 3.772058823529412e-05, "loss": 1.0607, "step": 513 }, { "epoch": 0.0283852440910095, "grad_norm": 0.7816783785820007, "learning_rate": 3.779411764705883e-05, "loss": 0.0111, "step": 514 }, { "epoch": 0.02844046830130329, "grad_norm": 1.7512190341949463, "learning_rate": 3.786764705882353e-05, "loss": 0.0206, "step": 515 }, { "epoch": 0.028495692511597084, "grad_norm": 0.16074638068675995, "learning_rate": 3.794117647058824e-05, "loss": 0.0035, "step": 516 }, { "epoch": 0.028550916721890876, "grad_norm": 3.782531261444092, "learning_rate": 3.801470588235294e-05, "loss": 0.1015, "step": 517 }, { "epoch": 0.02860614093218467, "grad_norm": 4.361739158630371, "learning_rate": 3.808823529411765e-05, "loss": 0.8381, "step": 518 }, { "epoch": 0.028661365142478464, "grad_norm": 2.8056845664978027, "learning_rate": 3.816176470588236e-05, "loss": 0.4601, "step": 519 }, { "epoch": 0.028716589352772257, "grad_norm": 2.3346810340881348, "learning_rate": 3.823529411764706e-05, "loss": 0.058, "step": 520 }, { "epoch": 0.02877181356306605, "grad_norm": 0.15225617587566376, "learning_rate": 3.830882352941177e-05, "loss": 0.0041, "step": 521 }, { "epoch": 0.02882703777335984, "grad_norm": 1.8616901636123657, "learning_rate": 3.8382352941176474e-05, "loss": 0.0794, "step": 522 }, { "epoch": 0.028882261983653634, "grad_norm": 0.47739550471305847, "learning_rate": 3.845588235294118e-05, "loss": 0.014, "step": 523 }, { "epoch": 0.028937486193947426, "grad_norm": 0.48372936248779297, "learning_rate": 3.8529411764705886e-05, "loss": 0.0152, "step": 524 }, { "epoch": 0.02899271040424122, "grad_norm": 0.42803192138671875, "learning_rate": 3.8602941176470595e-05, "loss": 0.0085, "step": 525 }, { "epoch": 0.02904793461453501, "grad_norm": 1.221701979637146, "learning_rate": 3.86764705882353e-05, "loss": 0.0228, "step": 526 }, { "epoch": 0.029103158824828806, "grad_norm": 3.121659278869629, "learning_rate": 3.875e-05, "loss": 0.1918, "step": 527 }, { "epoch": 0.0291583830351226, "grad_norm": 2.1221976280212402, "learning_rate": 3.882352941176471e-05, "loss": 0.2095, "step": 528 }, { "epoch": 0.02921360724541639, "grad_norm": 0.28085607290267944, "learning_rate": 3.889705882352941e-05, "loss": 0.0067, "step": 529 }, { "epoch": 0.029268831455710183, "grad_norm": 4.173842430114746, "learning_rate": 3.897058823529412e-05, "loss": 0.1502, "step": 530 }, { "epoch": 0.029324055666003976, "grad_norm": 4.766704559326172, "learning_rate": 3.9044117647058823e-05, "loss": 0.8185, "step": 531 }, { "epoch": 0.029379279876297768, "grad_norm": 4.227066993713379, "learning_rate": 3.911764705882353e-05, "loss": 0.6175, "step": 532 }, { "epoch": 0.02943450408659156, "grad_norm": 7.871342182159424, "learning_rate": 3.9191176470588235e-05, "loss": 0.9484, "step": 533 }, { "epoch": 0.029489728296885353, "grad_norm": 2.73220157623291, "learning_rate": 3.9264705882352945e-05, "loss": 0.1024, "step": 534 }, { "epoch": 0.02954495250717915, "grad_norm": 3.9812633991241455, "learning_rate": 3.933823529411765e-05, "loss": 0.3492, "step": 535 }, { "epoch": 0.02960017671747294, "grad_norm": 8.165245056152344, "learning_rate": 3.9411764705882356e-05, "loss": 0.9744, "step": 536 }, { "epoch": 0.029655400927766733, "grad_norm": 3.9198875427246094, "learning_rate": 3.9485294117647066e-05, "loss": 0.5269, "step": 537 }, { "epoch": 0.029710625138060526, "grad_norm": 0.05020437389612198, "learning_rate": 3.955882352941177e-05, "loss": 0.0013, "step": 538 }, { "epoch": 0.029765849348354318, "grad_norm": 0.1487279087305069, "learning_rate": 3.963235294117648e-05, "loss": 0.0016, "step": 539 }, { "epoch": 0.02982107355864811, "grad_norm": 0.3594907820224762, "learning_rate": 3.970588235294118e-05, "loss": 0.0047, "step": 540 }, { "epoch": 0.029876297768941903, "grad_norm": 7.978976726531982, "learning_rate": 3.977941176470589e-05, "loss": 0.7731, "step": 541 }, { "epoch": 0.0299315219792357, "grad_norm": 3.648479700088501, "learning_rate": 3.985294117647059e-05, "loss": 0.1974, "step": 542 }, { "epoch": 0.02998674618952949, "grad_norm": 5.770876884460449, "learning_rate": 3.99264705882353e-05, "loss": 1.4645, "step": 543 }, { "epoch": 0.030041970399823283, "grad_norm": 0.1687716543674469, "learning_rate": 4e-05, "loss": 0.005, "step": 544 }, { "epoch": 0.030097194610117076, "grad_norm": 0.1542622447013855, "learning_rate": 3.999999968007154e-05, "loss": 0.0046, "step": 545 }, { "epoch": 0.030152418820410868, "grad_norm": 2.889434337615967, "learning_rate": 3.999999872028614e-05, "loss": 0.902, "step": 546 }, { "epoch": 0.03020764303070466, "grad_norm": 0.7511751651763916, "learning_rate": 3.9999997120643846e-05, "loss": 0.0166, "step": 547 }, { "epoch": 0.030262867240998453, "grad_norm": 1.0718570947647095, "learning_rate": 3.9999994881144706e-05, "loss": 0.0151, "step": 548 }, { "epoch": 0.030318091451292245, "grad_norm": 4.834776401519775, "learning_rate": 3.99999920017888e-05, "loss": 1.3423, "step": 549 }, { "epoch": 0.03037331566158604, "grad_norm": 4.707091808319092, "learning_rate": 3.999998848257621e-05, "loss": 0.9007, "step": 550 }, { "epoch": 0.030428539871879833, "grad_norm": 4.03314733505249, "learning_rate": 3.999998432350704e-05, "loss": 0.6854, "step": 551 }, { "epoch": 0.030483764082173626, "grad_norm": 3.898287773132324, "learning_rate": 3.999997952458144e-05, "loss": 0.7988, "step": 552 }, { "epoch": 0.030538988292467418, "grad_norm": 1.902355670928955, "learning_rate": 3.9999974085799564e-05, "loss": 0.082, "step": 553 }, { "epoch": 0.03059421250276121, "grad_norm": 2.7490224838256836, "learning_rate": 3.999996800716157e-05, "loss": 0.1226, "step": 554 }, { "epoch": 0.030649436713055003, "grad_norm": 0.4830743074417114, "learning_rate": 3.9999961288667666e-05, "loss": 0.014, "step": 555 }, { "epoch": 0.030704660923348795, "grad_norm": 2.1375646591186523, "learning_rate": 3.9999953930318066e-05, "loss": 0.1066, "step": 556 }, { "epoch": 0.030759885133642587, "grad_norm": 3.109513282775879, "learning_rate": 3.9999945932113e-05, "loss": 0.6915, "step": 557 }, { "epoch": 0.030815109343936383, "grad_norm": 5.357973098754883, "learning_rate": 3.999993729405273e-05, "loss": 0.3973, "step": 558 }, { "epoch": 0.030870333554230175, "grad_norm": 0.12584322690963745, "learning_rate": 3.999992801613752e-05, "loss": 0.0031, "step": 559 }, { "epoch": 0.030925557764523968, "grad_norm": 3.863642454147339, "learning_rate": 3.999991809836769e-05, "loss": 0.2167, "step": 560 }, { "epoch": 0.03098078197481776, "grad_norm": 5.856204509735107, "learning_rate": 3.999990754074353e-05, "loss": 1.7225, "step": 561 }, { "epoch": 0.031036006185111552, "grad_norm": 5.95374059677124, "learning_rate": 3.999989634326539e-05, "loss": 2.6474, "step": 562 }, { "epoch": 0.031091230395405345, "grad_norm": 2.9686994552612305, "learning_rate": 3.999988450593364e-05, "loss": 0.656, "step": 563 }, { "epoch": 0.031146454605699137, "grad_norm": 1.4189704656600952, "learning_rate": 3.999987202874864e-05, "loss": 0.0418, "step": 564 }, { "epoch": 0.031201678815992933, "grad_norm": 0.5834767818450928, "learning_rate": 3.99998589117108e-05, "loss": 0.0238, "step": 565 }, { "epoch": 0.031256903026286725, "grad_norm": 3.4557559490203857, "learning_rate": 3.999984515482053e-05, "loss": 0.641, "step": 566 }, { "epoch": 0.031312127236580514, "grad_norm": 4.539731025695801, "learning_rate": 3.9999830758078284e-05, "loss": 1.3576, "step": 567 }, { "epoch": 0.03136735144687431, "grad_norm": 4.321095943450928, "learning_rate": 3.999981572148451e-05, "loss": 0.4855, "step": 568 }, { "epoch": 0.031422575657168106, "grad_norm": 1.9050424098968506, "learning_rate": 3.999980004503969e-05, "loss": 0.0919, "step": 569 }, { "epoch": 0.031477799867461895, "grad_norm": 2.9321446418762207, "learning_rate": 3.999978372874434e-05, "loss": 0.0319, "step": 570 }, { "epoch": 0.03153302407775569, "grad_norm": 1.0445032119750977, "learning_rate": 3.999976677259897e-05, "loss": 0.0286, "step": 571 }, { "epoch": 0.03158824828804948, "grad_norm": 1.09619140625, "learning_rate": 3.9999749176604116e-05, "loss": 0.0375, "step": 572 }, { "epoch": 0.031643472498343275, "grad_norm": 0.2813814580440521, "learning_rate": 3.999973094076035e-05, "loss": 0.0112, "step": 573 }, { "epoch": 0.031698696708637064, "grad_norm": 0.1788533329963684, "learning_rate": 3.999971206506827e-05, "loss": 0.006, "step": 574 }, { "epoch": 0.03175392091893086, "grad_norm": 0.3896792232990265, "learning_rate": 3.999969254952845e-05, "loss": 0.0097, "step": 575 }, { "epoch": 0.03180914512922465, "grad_norm": 3.754034996032715, "learning_rate": 3.9999672394141526e-05, "loss": 0.9722, "step": 576 }, { "epoch": 0.031864369339518445, "grad_norm": 0.7358993887901306, "learning_rate": 3.999965159890815e-05, "loss": 0.024, "step": 577 }, { "epoch": 0.03191959354981224, "grad_norm": 0.20373192429542542, "learning_rate": 3.9999630163828984e-05, "loss": 0.0071, "step": 578 }, { "epoch": 0.03197481776010603, "grad_norm": 0.28524982929229736, "learning_rate": 3.999960808890472e-05, "loss": 0.005, "step": 579 }, { "epoch": 0.032030041970399825, "grad_norm": 4.070048809051514, "learning_rate": 3.999958537413604e-05, "loss": 0.8231, "step": 580 }, { "epoch": 0.032085266180693614, "grad_norm": 5.93355655670166, "learning_rate": 3.99995620195237e-05, "loss": 0.4599, "step": 581 }, { "epoch": 0.03214049039098741, "grad_norm": 0.13519339263439178, "learning_rate": 3.9999538025068434e-05, "loss": 0.0034, "step": 582 }, { "epoch": 0.0321957146012812, "grad_norm": 0.11714769899845123, "learning_rate": 3.9999513390771004e-05, "loss": 0.0034, "step": 583 }, { "epoch": 0.032250938811574995, "grad_norm": 0.8064020872116089, "learning_rate": 3.999948811663221e-05, "loss": 0.017, "step": 584 }, { "epoch": 0.03230616302186879, "grad_norm": 6.1967363357543945, "learning_rate": 3.999946220265286e-05, "loss": 1.0296, "step": 585 }, { "epoch": 0.03236138723216258, "grad_norm": 2.694467782974243, "learning_rate": 3.999943564883377e-05, "loss": 0.4309, "step": 586 }, { "epoch": 0.032416611442456375, "grad_norm": 7.773660182952881, "learning_rate": 3.99994084551758e-05, "loss": 1.4671, "step": 587 }, { "epoch": 0.032471835652750164, "grad_norm": 2.7070980072021484, "learning_rate": 3.999938062167982e-05, "loss": 0.0969, "step": 588 }, { "epoch": 0.03252705986304396, "grad_norm": 3.3194546699523926, "learning_rate": 3.999935214834671e-05, "loss": 0.3707, "step": 589 }, { "epoch": 0.03258228407333775, "grad_norm": 0.09370524436235428, "learning_rate": 3.99993230351774e-05, "loss": 0.0025, "step": 590 }, { "epoch": 0.032637508283631544, "grad_norm": 7.337200164794922, "learning_rate": 3.99992932821728e-05, "loss": 0.8832, "step": 591 }, { "epoch": 0.03269273249392534, "grad_norm": 2.5685365200042725, "learning_rate": 3.999926288933388e-05, "loss": 0.1377, "step": 592 }, { "epoch": 0.03274795670421913, "grad_norm": 0.1792830228805542, "learning_rate": 3.99992318566616e-05, "loss": 0.005, "step": 593 }, { "epoch": 0.032803180914512925, "grad_norm": 0.37777820229530334, "learning_rate": 3.9999200184156965e-05, "loss": 0.0083, "step": 594 }, { "epoch": 0.032858405124806714, "grad_norm": 0.653424084186554, "learning_rate": 3.999916787182097e-05, "loss": 0.0115, "step": 595 }, { "epoch": 0.03291362933510051, "grad_norm": 5.488597393035889, "learning_rate": 3.999913491965467e-05, "loss": 0.289, "step": 596 }, { "epoch": 0.0329688535453943, "grad_norm": 2.358213186264038, "learning_rate": 3.999910132765911e-05, "loss": 0.752, "step": 597 }, { "epoch": 0.033024077755688094, "grad_norm": 4.537961959838867, "learning_rate": 3.999906709583536e-05, "loss": 1.1643, "step": 598 }, { "epoch": 0.03307930196598188, "grad_norm": 1.9503862857818604, "learning_rate": 3.999903222418451e-05, "loss": 0.1344, "step": 599 }, { "epoch": 0.03313452617627568, "grad_norm": 0.18938176333904266, "learning_rate": 3.9998996712707694e-05, "loss": 0.005, "step": 600 }, { "epoch": 0.033189750386569475, "grad_norm": 1.3755193948745728, "learning_rate": 3.9998960561406036e-05, "loss": 0.0428, "step": 601 }, { "epoch": 0.033244974596863264, "grad_norm": 0.3801460266113281, "learning_rate": 3.9998923770280694e-05, "loss": 0.0098, "step": 602 }, { "epoch": 0.03330019880715706, "grad_norm": 0.3463192284107208, "learning_rate": 3.9998886339332846e-05, "loss": 0.008, "step": 603 }, { "epoch": 0.03335542301745085, "grad_norm": 2.1178739070892334, "learning_rate": 3.9998848268563694e-05, "loss": 0.0917, "step": 604 }, { "epoch": 0.033410647227744644, "grad_norm": 2.1834638118743896, "learning_rate": 3.999880955797445e-05, "loss": 0.2812, "step": 605 }, { "epoch": 0.03346587143803843, "grad_norm": 5.116266250610352, "learning_rate": 3.999877020756635e-05, "loss": 0.518, "step": 606 }, { "epoch": 0.03352109564833223, "grad_norm": 2.171694278717041, "learning_rate": 3.999873021734066e-05, "loss": 0.1151, "step": 607 }, { "epoch": 0.033576319858626025, "grad_norm": 0.9855673313140869, "learning_rate": 3.999868958729866e-05, "loss": 0.0156, "step": 608 }, { "epoch": 0.033631544068919814, "grad_norm": 3.4880712032318115, "learning_rate": 3.999864831744164e-05, "loss": 0.7879, "step": 609 }, { "epoch": 0.03368676827921361, "grad_norm": 2.888979434967041, "learning_rate": 3.999860640777093e-05, "loss": 0.2376, "step": 610 }, { "epoch": 0.0337419924895074, "grad_norm": 5.489663124084473, "learning_rate": 3.9998563858287866e-05, "loss": 1.0357, "step": 611 }, { "epoch": 0.033797216699801194, "grad_norm": 4.021475315093994, "learning_rate": 3.999852066899381e-05, "loss": 0.4813, "step": 612 }, { "epoch": 0.03385244091009498, "grad_norm": 1.575195550918579, "learning_rate": 3.999847683989015e-05, "loss": 0.0506, "step": 613 }, { "epoch": 0.03390766512038878, "grad_norm": 7.926339149475098, "learning_rate": 3.999843237097828e-05, "loss": 0.2584, "step": 614 }, { "epoch": 0.033962889330682575, "grad_norm": 0.4336821436882019, "learning_rate": 3.9998387262259626e-05, "loss": 0.018, "step": 615 }, { "epoch": 0.034018113540976364, "grad_norm": 2.3343632221221924, "learning_rate": 3.9998341513735625e-05, "loss": 0.192, "step": 616 }, { "epoch": 0.03407333775127016, "grad_norm": 2.4178335666656494, "learning_rate": 3.9998295125407754e-05, "loss": 0.1463, "step": 617 }, { "epoch": 0.03412856196156395, "grad_norm": 5.09498929977417, "learning_rate": 3.999824809727748e-05, "loss": 0.2376, "step": 618 }, { "epoch": 0.034183786171857744, "grad_norm": 1.6400419473648071, "learning_rate": 3.999820042934633e-05, "loss": 0.1431, "step": 619 }, { "epoch": 0.03423901038215153, "grad_norm": 3.94073748588562, "learning_rate": 3.9998152121615806e-05, "loss": 0.804, "step": 620 }, { "epoch": 0.03429423459244533, "grad_norm": 1.103832483291626, "learning_rate": 3.999810317408747e-05, "loss": 0.048, "step": 621 }, { "epoch": 0.03434945880273912, "grad_norm": 3.6944217681884766, "learning_rate": 3.9998053586762874e-05, "loss": 0.8597, "step": 622 }, { "epoch": 0.03440468301303291, "grad_norm": 2.011974811553955, "learning_rate": 3.999800335964361e-05, "loss": 0.2725, "step": 623 }, { "epoch": 0.03445990722332671, "grad_norm": 4.2653303146362305, "learning_rate": 3.999795249273129e-05, "loss": 0.2933, "step": 624 }, { "epoch": 0.0345151314336205, "grad_norm": 1.3542368412017822, "learning_rate": 3.999790098602755e-05, "loss": 0.0487, "step": 625 }, { "epoch": 0.034570355643914294, "grad_norm": 4.487484455108643, "learning_rate": 3.999784883953401e-05, "loss": 1.8167, "step": 626 }, { "epoch": 0.03462557985420808, "grad_norm": 2.665616750717163, "learning_rate": 3.999779605325236e-05, "loss": 0.1021, "step": 627 }, { "epoch": 0.03468080406450188, "grad_norm": 4.115176200866699, "learning_rate": 3.9997742627184285e-05, "loss": 0.5996, "step": 628 }, { "epoch": 0.03473602827479567, "grad_norm": 0.5027790069580078, "learning_rate": 3.999768856133149e-05, "loss": 0.021, "step": 629 }, { "epoch": 0.03479125248508946, "grad_norm": 3.2128326892852783, "learning_rate": 3.999763385569571e-05, "loss": 0.603, "step": 630 }, { "epoch": 0.03484647669538326, "grad_norm": 1.689087986946106, "learning_rate": 3.9997578510278686e-05, "loss": 0.1053, "step": 631 }, { "epoch": 0.03490170090567705, "grad_norm": 2.697904109954834, "learning_rate": 3.99975225250822e-05, "loss": 0.3239, "step": 632 }, { "epoch": 0.034956925115970844, "grad_norm": 3.6798925399780273, "learning_rate": 3.999746590010804e-05, "loss": 0.2831, "step": 633 }, { "epoch": 0.03501214932626463, "grad_norm": 5.196535110473633, "learning_rate": 3.999740863535802e-05, "loss": 1.1089, "step": 634 }, { "epoch": 0.03506737353655843, "grad_norm": 1.8372538089752197, "learning_rate": 3.999735073083395e-05, "loss": 0.0532, "step": 635 }, { "epoch": 0.03512259774685222, "grad_norm": 0.46699967980384827, "learning_rate": 3.999729218653771e-05, "loss": 0.0138, "step": 636 }, { "epoch": 0.03517782195714601, "grad_norm": 6.76269006729126, "learning_rate": 3.999723300247117e-05, "loss": 0.5254, "step": 637 }, { "epoch": 0.03523304616743981, "grad_norm": 0.9602828025817871, "learning_rate": 3.999717317863621e-05, "loss": 0.033, "step": 638 }, { "epoch": 0.0352882703777336, "grad_norm": 3.6963577270507812, "learning_rate": 3.9997112715034744e-05, "loss": 0.5298, "step": 639 }, { "epoch": 0.035343494588027394, "grad_norm": 1.2003594636917114, "learning_rate": 3.9997051611668725e-05, "loss": 0.0213, "step": 640 }, { "epoch": 0.03539871879832118, "grad_norm": 4.305522441864014, "learning_rate": 3.999698986854009e-05, "loss": 1.0076, "step": 641 }, { "epoch": 0.03545394300861498, "grad_norm": 2.7851977348327637, "learning_rate": 3.9996927485650816e-05, "loss": 0.1876, "step": 642 }, { "epoch": 0.03550916721890877, "grad_norm": 0.11298496276140213, "learning_rate": 3.999686446300291e-05, "loss": 0.003, "step": 643 }, { "epoch": 0.03556439142920256, "grad_norm": 4.571480751037598, "learning_rate": 3.999680080059838e-05, "loss": 0.6804, "step": 644 }, { "epoch": 0.03561961563949635, "grad_norm": 3.2173373699188232, "learning_rate": 3.999673649843926e-05, "loss": 0.3068, "step": 645 }, { "epoch": 0.03567483984979015, "grad_norm": 1.6341303586959839, "learning_rate": 3.999667155652762e-05, "loss": 0.1407, "step": 646 }, { "epoch": 0.035730064060083944, "grad_norm": 0.12583200633525848, "learning_rate": 3.999660597486552e-05, "loss": 0.0031, "step": 647 }, { "epoch": 0.03578528827037773, "grad_norm": 0.7347983717918396, "learning_rate": 3.9996539753455074e-05, "loss": 0.0378, "step": 648 }, { "epoch": 0.03584051248067153, "grad_norm": 5.745443820953369, "learning_rate": 3.999647289229839e-05, "loss": 0.1473, "step": 649 }, { "epoch": 0.03589573669096532, "grad_norm": 1.6895979642868042, "learning_rate": 3.999640539139761e-05, "loss": 0.1557, "step": 650 }, { "epoch": 0.03595096090125911, "grad_norm": 3.7245306968688965, "learning_rate": 3.999633725075489e-05, "loss": 0.5476, "step": 651 }, { "epoch": 0.0360061851115529, "grad_norm": 6.08723783493042, "learning_rate": 3.999626847037242e-05, "loss": 1.1261, "step": 652 }, { "epoch": 0.0360614093218467, "grad_norm": 0.10598932951688766, "learning_rate": 3.99961990502524e-05, "loss": 0.0038, "step": 653 }, { "epoch": 0.036116633532140494, "grad_norm": 3.8076539039611816, "learning_rate": 3.999612899039703e-05, "loss": 0.3756, "step": 654 }, { "epoch": 0.03617185774243428, "grad_norm": 4.912800312042236, "learning_rate": 3.999605829080858e-05, "loss": 0.5697, "step": 655 }, { "epoch": 0.03622708195272808, "grad_norm": 0.1622360199689865, "learning_rate": 3.99959869514893e-05, "loss": 0.0051, "step": 656 }, { "epoch": 0.03628230616302187, "grad_norm": 0.11798544973134995, "learning_rate": 3.999591497244146e-05, "loss": 0.0025, "step": 657 }, { "epoch": 0.03633753037331566, "grad_norm": 6.6510233879089355, "learning_rate": 3.999584235366738e-05, "loss": 1.3275, "step": 658 }, { "epoch": 0.03639275458360945, "grad_norm": 3.641657590866089, "learning_rate": 3.9995769095169386e-05, "loss": 0.0983, "step": 659 }, { "epoch": 0.03644797879390325, "grad_norm": 3.0441269874572754, "learning_rate": 3.999569519694981e-05, "loss": 0.3177, "step": 660 }, { "epoch": 0.03650320300419704, "grad_norm": 3.300096035003662, "learning_rate": 3.999562065901101e-05, "loss": 0.3473, "step": 661 }, { "epoch": 0.03655842721449083, "grad_norm": 3.137479543685913, "learning_rate": 3.999554548135539e-05, "loss": 0.07, "step": 662 }, { "epoch": 0.03661365142478463, "grad_norm": 0.21455450356006622, "learning_rate": 3.9995469663985335e-05, "loss": 0.0052, "step": 663 }, { "epoch": 0.03666887563507842, "grad_norm": 3.601362943649292, "learning_rate": 3.9995393206903296e-05, "loss": 0.7399, "step": 664 }, { "epoch": 0.03672409984537221, "grad_norm": 7.187249183654785, "learning_rate": 3.999531611011169e-05, "loss": 1.5969, "step": 665 }, { "epoch": 0.036779324055666, "grad_norm": 6.131557464599609, "learning_rate": 3.9995238373613e-05, "loss": 0.3902, "step": 666 }, { "epoch": 0.0368345482659598, "grad_norm": 6.363812446594238, "learning_rate": 3.9995159997409716e-05, "loss": 0.9015, "step": 667 }, { "epoch": 0.036889772476253586, "grad_norm": 3.021794080734253, "learning_rate": 3.999508098150434e-05, "loss": 0.3585, "step": 668 }, { "epoch": 0.03694499668654738, "grad_norm": 1.6206190586090088, "learning_rate": 3.999500132589939e-05, "loss": 0.0529, "step": 669 }, { "epoch": 0.03700022089684118, "grad_norm": 3.1729626655578613, "learning_rate": 3.9994921030597435e-05, "loss": 0.1147, "step": 670 }, { "epoch": 0.03705544510713497, "grad_norm": 4.0572733879089355, "learning_rate": 3.9994840095601026e-05, "loss": 0.5109, "step": 671 }, { "epoch": 0.03711066931742876, "grad_norm": 0.789972186088562, "learning_rate": 3.9994758520912764e-05, "loss": 0.0246, "step": 672 }, { "epoch": 0.03716589352772255, "grad_norm": 2.099026679992676, "learning_rate": 3.999467630653525e-05, "loss": 0.1203, "step": 673 }, { "epoch": 0.03722111773801635, "grad_norm": 6.612025737762451, "learning_rate": 3.999459345247112e-05, "loss": 1.2627, "step": 674 }, { "epoch": 0.037276341948310136, "grad_norm": 3.526801824569702, "learning_rate": 3.999450995872303e-05, "loss": 0.5174, "step": 675 }, { "epoch": 0.03733156615860393, "grad_norm": 3.7623653411865234, "learning_rate": 3.9994425825293636e-05, "loss": 1.1903, "step": 676 }, { "epoch": 0.03738679036889773, "grad_norm": 2.5590755939483643, "learning_rate": 3.999434105218565e-05, "loss": 0.448, "step": 677 }, { "epoch": 0.03744201457919152, "grad_norm": 3.480994462966919, "learning_rate": 3.999425563940176e-05, "loss": 0.5353, "step": 678 }, { "epoch": 0.03749723878948531, "grad_norm": 3.466991901397705, "learning_rate": 3.999416958694472e-05, "loss": 0.2595, "step": 679 }, { "epoch": 0.0375524629997791, "grad_norm": 4.479564666748047, "learning_rate": 3.999408289481727e-05, "loss": 0.506, "step": 680 }, { "epoch": 0.0376076872100729, "grad_norm": 1.1617695093154907, "learning_rate": 3.999399556302218e-05, "loss": 0.0452, "step": 681 }, { "epoch": 0.037662911420366686, "grad_norm": 4.084585666656494, "learning_rate": 3.999390759156226e-05, "loss": 0.5117, "step": 682 }, { "epoch": 0.03771813563066048, "grad_norm": 1.4882510900497437, "learning_rate": 3.999381898044032e-05, "loss": 0.0828, "step": 683 }, { "epoch": 0.03777335984095427, "grad_norm": 1.5541726350784302, "learning_rate": 3.999372972965918e-05, "loss": 0.097, "step": 684 }, { "epoch": 0.03782858405124807, "grad_norm": 2.6177947521209717, "learning_rate": 3.9993639839221714e-05, "loss": 0.2221, "step": 685 }, { "epoch": 0.03788380826154186, "grad_norm": 3.8159921169281006, "learning_rate": 3.999354930913079e-05, "loss": 0.8462, "step": 686 }, { "epoch": 0.03793903247183565, "grad_norm": 3.3373942375183105, "learning_rate": 3.99934581393893e-05, "loss": 0.7464, "step": 687 }, { "epoch": 0.03799425668212945, "grad_norm": 1.6812465190887451, "learning_rate": 3.999336633000017e-05, "loss": 0.0637, "step": 688 }, { "epoch": 0.038049480892423236, "grad_norm": 2.736255168914795, "learning_rate": 3.999327388096633e-05, "loss": 0.7195, "step": 689 }, { "epoch": 0.03810470510271703, "grad_norm": 0.8863444328308105, "learning_rate": 3.999318079229074e-05, "loss": 0.0501, "step": 690 }, { "epoch": 0.03815992931301082, "grad_norm": 4.236536026000977, "learning_rate": 3.999308706397638e-05, "loss": 1.5966, "step": 691 }, { "epoch": 0.03821515352330462, "grad_norm": 0.2991679608821869, "learning_rate": 3.9992992696026244e-05, "loss": 0.0084, "step": 692 }, { "epoch": 0.03827037773359841, "grad_norm": 0.9007558226585388, "learning_rate": 3.9992897688443354e-05, "loss": 0.0183, "step": 693 }, { "epoch": 0.0383256019438922, "grad_norm": 1.9035793542861938, "learning_rate": 3.999280204123075e-05, "loss": 0.0548, "step": 694 }, { "epoch": 0.038380826154186, "grad_norm": 1.4529067277908325, "learning_rate": 3.99927057543915e-05, "loss": 0.0305, "step": 695 }, { "epoch": 0.038436050364479786, "grad_norm": 2.8446578979492188, "learning_rate": 3.9992608827928664e-05, "loss": 0.2968, "step": 696 }, { "epoch": 0.03849127457477358, "grad_norm": 3.4752213954925537, "learning_rate": 3.999251126184536e-05, "loss": 0.5012, "step": 697 }, { "epoch": 0.03854649878506737, "grad_norm": 0.6667559742927551, "learning_rate": 3.999241305614471e-05, "loss": 0.0142, "step": 698 }, { "epoch": 0.038601722995361167, "grad_norm": 0.09123341739177704, "learning_rate": 3.9992314210829846e-05, "loss": 0.0019, "step": 699 }, { "epoch": 0.03865694720565496, "grad_norm": 3.2398295402526855, "learning_rate": 3.9992214725903934e-05, "loss": 0.3741, "step": 700 }, { "epoch": 0.03871217141594875, "grad_norm": 4.159255027770996, "learning_rate": 3.9992114601370155e-05, "loss": 0.0972, "step": 701 }, { "epoch": 0.03876739562624255, "grad_norm": 2.569976329803467, "learning_rate": 3.999201383723172e-05, "loss": 0.0705, "step": 702 }, { "epoch": 0.038822619836536336, "grad_norm": 0.5093204379081726, "learning_rate": 3.9991912433491844e-05, "loss": 0.0171, "step": 703 }, { "epoch": 0.03887784404683013, "grad_norm": 5.871143341064453, "learning_rate": 3.9991810390153783e-05, "loss": 1.0143, "step": 704 }, { "epoch": 0.03893306825712392, "grad_norm": 5.857358932495117, "learning_rate": 3.999170770722078e-05, "loss": 0.2653, "step": 705 }, { "epoch": 0.038988292467417716, "grad_norm": 3.2478678226470947, "learning_rate": 3.999160438469614e-05, "loss": 0.2757, "step": 706 }, { "epoch": 0.039043516677711505, "grad_norm": 1.1662334203720093, "learning_rate": 3.9991500422583163e-05, "loss": 0.0256, "step": 707 }, { "epoch": 0.0390987408880053, "grad_norm": 3.031404972076416, "learning_rate": 3.999139582088518e-05, "loss": 0.6792, "step": 708 }, { "epoch": 0.0391539650982991, "grad_norm": 2.554959535598755, "learning_rate": 3.999129057960552e-05, "loss": 0.137, "step": 709 }, { "epoch": 0.039209189308592886, "grad_norm": 1.6353319883346558, "learning_rate": 3.999118469874757e-05, "loss": 0.0761, "step": 710 }, { "epoch": 0.03926441351888668, "grad_norm": 1.4338150024414062, "learning_rate": 3.999107817831471e-05, "loss": 0.0608, "step": 711 }, { "epoch": 0.03931963772918047, "grad_norm": 4.5015058517456055, "learning_rate": 3.9990971018310336e-05, "loss": 1.6262, "step": 712 }, { "epoch": 0.039374861939474266, "grad_norm": 3.214651584625244, "learning_rate": 3.99908632187379e-05, "loss": 0.2525, "step": 713 }, { "epoch": 0.039430086149768055, "grad_norm": 3.6700024604797363, "learning_rate": 3.999075477960083e-05, "loss": 0.6303, "step": 714 }, { "epoch": 0.03948531036006185, "grad_norm": 0.5177813172340393, "learning_rate": 3.9990645700902606e-05, "loss": 0.0208, "step": 715 }, { "epoch": 0.03954053457035565, "grad_norm": 0.18655671179294586, "learning_rate": 3.999053598264672e-05, "loss": 0.0042, "step": 716 }, { "epoch": 0.039595758780649436, "grad_norm": 1.804479718208313, "learning_rate": 3.9990425624836674e-05, "loss": 0.138, "step": 717 }, { "epoch": 0.03965098299094323, "grad_norm": 0.2519471347332001, "learning_rate": 3.9990314627476e-05, "loss": 0.0105, "step": 718 }, { "epoch": 0.03970620720123702, "grad_norm": 1.089036464691162, "learning_rate": 3.9990202990568244e-05, "loss": 0.019, "step": 719 }, { "epoch": 0.039761431411530816, "grad_norm": 1.3826956748962402, "learning_rate": 3.9990090714117e-05, "loss": 0.0579, "step": 720 }, { "epoch": 0.039816655621824605, "grad_norm": 3.7365031242370605, "learning_rate": 3.998997779812584e-05, "loss": 0.4866, "step": 721 }, { "epoch": 0.0398718798321184, "grad_norm": 0.9895696640014648, "learning_rate": 3.998986424259838e-05, "loss": 0.0362, "step": 722 }, { "epoch": 0.0399271040424122, "grad_norm": 3.2472102642059326, "learning_rate": 3.998975004753825e-05, "loss": 0.2891, "step": 723 }, { "epoch": 0.039982328252705986, "grad_norm": 4.974280834197998, "learning_rate": 3.998963521294911e-05, "loss": 1.3471, "step": 724 }, { "epoch": 0.04003755246299978, "grad_norm": 0.11942251771688461, "learning_rate": 3.998951973883463e-05, "loss": 0.0023, "step": 725 }, { "epoch": 0.04009277667329357, "grad_norm": 4.2454118728637695, "learning_rate": 3.998940362519851e-05, "loss": 0.7197, "step": 726 }, { "epoch": 0.040148000883587366, "grad_norm": 3.385560989379883, "learning_rate": 3.9989286872044456e-05, "loss": 0.4307, "step": 727 }, { "epoch": 0.040203225093881155, "grad_norm": 0.662775456905365, "learning_rate": 3.998916947937622e-05, "loss": 0.0214, "step": 728 }, { "epoch": 0.04025844930417495, "grad_norm": 5.169105052947998, "learning_rate": 3.998905144719753e-05, "loss": 1.1377, "step": 729 }, { "epoch": 0.04031367351446874, "grad_norm": 1.1271390914916992, "learning_rate": 3.998893277551219e-05, "loss": 0.0416, "step": 730 }, { "epoch": 0.040368897724762536, "grad_norm": 0.13262739777565002, "learning_rate": 3.9988813464323974e-05, "loss": 0.0049, "step": 731 }, { "epoch": 0.04042412193505633, "grad_norm": 1.9215145111083984, "learning_rate": 3.998869351363672e-05, "loss": 0.072, "step": 732 }, { "epoch": 0.04047934614535012, "grad_norm": 2.9409596920013428, "learning_rate": 3.998857292345425e-05, "loss": 0.212, "step": 733 }, { "epoch": 0.040534570355643916, "grad_norm": 3.416779041290283, "learning_rate": 3.9988451693780426e-05, "loss": 0.5556, "step": 734 }, { "epoch": 0.040589794565937705, "grad_norm": 0.21939124166965485, "learning_rate": 3.9988329824619125e-05, "loss": 0.0088, "step": 735 }, { "epoch": 0.0406450187762315, "grad_norm": 0.4128265380859375, "learning_rate": 3.9988207315974254e-05, "loss": 0.0132, "step": 736 }, { "epoch": 0.04070024298652529, "grad_norm": 4.025622367858887, "learning_rate": 3.998808416784972e-05, "loss": 0.7735, "step": 737 }, { "epoch": 0.040755467196819085, "grad_norm": 3.2163968086242676, "learning_rate": 3.998796038024948e-05, "loss": 0.5722, "step": 738 }, { "epoch": 0.04081069140711288, "grad_norm": 4.166391849517822, "learning_rate": 3.9987835953177484e-05, "loss": 0.791, "step": 739 }, { "epoch": 0.04086591561740667, "grad_norm": 1.824569821357727, "learning_rate": 3.9987710886637705e-05, "loss": 0.083, "step": 740 }, { "epoch": 0.040921139827700466, "grad_norm": 2.446152687072754, "learning_rate": 3.998758518063416e-05, "loss": 0.2413, "step": 741 }, { "epoch": 0.040976364037994255, "grad_norm": 1.888787865638733, "learning_rate": 3.998745883517086e-05, "loss": 0.0592, "step": 742 }, { "epoch": 0.04103158824828805, "grad_norm": 3.9180235862731934, "learning_rate": 3.998733185025184e-05, "loss": 0.3871, "step": 743 }, { "epoch": 0.04108681245858184, "grad_norm": 3.7644100189208984, "learning_rate": 3.998720422588119e-05, "loss": 0.4452, "step": 744 }, { "epoch": 0.041142036668875635, "grad_norm": 2.3117127418518066, "learning_rate": 3.998707596206297e-05, "loss": 0.061, "step": 745 }, { "epoch": 0.04119726087916943, "grad_norm": 3.363022804260254, "learning_rate": 3.998694705880128e-05, "loss": 1.1184, "step": 746 }, { "epoch": 0.04125248508946322, "grad_norm": 3.676121711730957, "learning_rate": 3.9986817516100266e-05, "loss": 1.0987, "step": 747 }, { "epoch": 0.041307709299757016, "grad_norm": 0.8502395153045654, "learning_rate": 3.9986687333964057e-05, "loss": 0.0339, "step": 748 }, { "epoch": 0.041362933510050805, "grad_norm": 3.7776336669921875, "learning_rate": 3.9986556512396814e-05, "loss": 0.6219, "step": 749 }, { "epoch": 0.0414181577203446, "grad_norm": 0.07410918921232224, "learning_rate": 3.998642505140273e-05, "loss": 0.0025, "step": 750 }, { "epoch": 0.04147338193063839, "grad_norm": 2.2701292037963867, "learning_rate": 3.998629295098601e-05, "loss": 0.2304, "step": 751 }, { "epoch": 0.041528606140932185, "grad_norm": 0.43612220883369446, "learning_rate": 3.998616021115089e-05, "loss": 0.02, "step": 752 }, { "epoch": 0.041583830351225974, "grad_norm": 4.02420711517334, "learning_rate": 3.9986026831901596e-05, "loss": 0.6932, "step": 753 }, { "epoch": 0.04163905456151977, "grad_norm": 5.328437805175781, "learning_rate": 3.998589281324241e-05, "loss": 0.3351, "step": 754 }, { "epoch": 0.041694278771813566, "grad_norm": 2.6906018257141113, "learning_rate": 3.998575815517761e-05, "loss": 0.4222, "step": 755 }, { "epoch": 0.041749502982107355, "grad_norm": 2.057176113128662, "learning_rate": 3.998562285771152e-05, "loss": 0.1218, "step": 756 }, { "epoch": 0.04180472719240115, "grad_norm": 0.9486302733421326, "learning_rate": 3.9985486920848454e-05, "loss": 0.0306, "step": 757 }, { "epoch": 0.04185995140269494, "grad_norm": 0.29750198125839233, "learning_rate": 3.9985350344592764e-05, "loss": 0.0128, "step": 758 }, { "epoch": 0.041915175612988735, "grad_norm": 1.7827051877975464, "learning_rate": 3.998521312894882e-05, "loss": 0.3033, "step": 759 }, { "epoch": 0.041970399823282524, "grad_norm": 2.0169968605041504, "learning_rate": 3.998507527392101e-05, "loss": 0.0438, "step": 760 }, { "epoch": 0.04202562403357632, "grad_norm": 2.6628355979919434, "learning_rate": 3.998493677951375e-05, "loss": 0.2357, "step": 761 }, { "epoch": 0.042080848243870116, "grad_norm": 3.585953950881958, "learning_rate": 3.998479764573147e-05, "loss": 1.0171, "step": 762 }, { "epoch": 0.042136072454163905, "grad_norm": 0.1451287865638733, "learning_rate": 3.998465787257862e-05, "loss": 0.0058, "step": 763 }, { "epoch": 0.0421912966644577, "grad_norm": 0.2473389208316803, "learning_rate": 3.998451746005967e-05, "loss": 0.0113, "step": 764 }, { "epoch": 0.04224652087475149, "grad_norm": 4.585443019866943, "learning_rate": 3.998437640817911e-05, "loss": 0.8442, "step": 765 }, { "epoch": 0.042301745085045285, "grad_norm": 3.818136215209961, "learning_rate": 3.9984234716941455e-05, "loss": 0.4658, "step": 766 }, { "epoch": 0.042356969295339074, "grad_norm": 5.3118896484375, "learning_rate": 3.998409238635124e-05, "loss": 0.3865, "step": 767 }, { "epoch": 0.04241219350563287, "grad_norm": 0.28253456950187683, "learning_rate": 3.9983949416413014e-05, "loss": 0.0062, "step": 768 }, { "epoch": 0.042467417715926666, "grad_norm": 0.22107237577438354, "learning_rate": 3.998380580713136e-05, "loss": 0.0066, "step": 769 }, { "epoch": 0.042522641926220454, "grad_norm": 4.274048805236816, "learning_rate": 3.998366155851087e-05, "loss": 0.7937, "step": 770 }, { "epoch": 0.04257786613651425, "grad_norm": 2.667595148086548, "learning_rate": 3.998351667055615e-05, "loss": 0.1631, "step": 771 }, { "epoch": 0.04263309034680804, "grad_norm": 0.7493966221809387, "learning_rate": 3.9983371143271837e-05, "loss": 0.0154, "step": 772 }, { "epoch": 0.042688314557101835, "grad_norm": 3.0365843772888184, "learning_rate": 3.99832249766626e-05, "loss": 0.1565, "step": 773 }, { "epoch": 0.042743538767395624, "grad_norm": 0.5442637205123901, "learning_rate": 3.9983078170733104e-05, "loss": 0.007, "step": 774 }, { "epoch": 0.04279876297768942, "grad_norm": 3.9904897212982178, "learning_rate": 3.9982930725488044e-05, "loss": 0.9562, "step": 775 }, { "epoch": 0.04285398718798321, "grad_norm": 0.12439526617527008, "learning_rate": 3.998278264093214e-05, "loss": 0.0041, "step": 776 }, { "epoch": 0.042909211398277004, "grad_norm": 2.4145781993865967, "learning_rate": 3.998263391707014e-05, "loss": 0.2316, "step": 777 }, { "epoch": 0.0429644356085708, "grad_norm": 0.3076343536376953, "learning_rate": 3.998248455390679e-05, "loss": 0.0146, "step": 778 }, { "epoch": 0.04301965981886459, "grad_norm": 0.08936579525470734, "learning_rate": 3.9982334551446866e-05, "loss": 0.0032, "step": 779 }, { "epoch": 0.043074884029158385, "grad_norm": 0.8952546119689941, "learning_rate": 3.9982183909695176e-05, "loss": 0.0327, "step": 780 }, { "epoch": 0.043130108239452174, "grad_norm": 0.42235568165779114, "learning_rate": 3.9982032628656536e-05, "loss": 0.0196, "step": 781 }, { "epoch": 0.04318533244974597, "grad_norm": 0.8251855373382568, "learning_rate": 3.9981880708335784e-05, "loss": 0.0227, "step": 782 }, { "epoch": 0.04324055666003976, "grad_norm": 0.41301465034484863, "learning_rate": 3.9981728148737786e-05, "loss": 0.0114, "step": 783 }, { "epoch": 0.043295780870333554, "grad_norm": 0.28594255447387695, "learning_rate": 3.9981574949867415e-05, "loss": 0.0098, "step": 784 }, { "epoch": 0.04335100508062735, "grad_norm": 6.0038371086120605, "learning_rate": 3.998142111172958e-05, "loss": 0.9641, "step": 785 }, { "epoch": 0.04340622929092114, "grad_norm": 4.800288200378418, "learning_rate": 3.9981266634329195e-05, "loss": 1.0411, "step": 786 }, { "epoch": 0.043461453501214935, "grad_norm": 3.2449300289154053, "learning_rate": 3.9981111517671205e-05, "loss": 0.7197, "step": 787 }, { "epoch": 0.043516677711508724, "grad_norm": 3.8848724365234375, "learning_rate": 3.998095576176058e-05, "loss": 1.8499, "step": 788 }, { "epoch": 0.04357190192180252, "grad_norm": 2.977872610092163, "learning_rate": 3.9980799366602296e-05, "loss": 0.3744, "step": 789 }, { "epoch": 0.04362712613209631, "grad_norm": 0.14446575939655304, "learning_rate": 3.998064233220135e-05, "loss": 0.0051, "step": 790 }, { "epoch": 0.043682350342390104, "grad_norm": 0.10349533706903458, "learning_rate": 3.998048465856278e-05, "loss": 0.0033, "step": 791 }, { "epoch": 0.0437375745526839, "grad_norm": 0.4589765965938568, "learning_rate": 3.998032634569163e-05, "loss": 0.0125, "step": 792 }, { "epoch": 0.04379279876297769, "grad_norm": 3.410773277282715, "learning_rate": 3.998016739359295e-05, "loss": 0.1228, "step": 793 }, { "epoch": 0.043848022973271485, "grad_norm": 2.0786707401275635, "learning_rate": 3.9980007802271836e-05, "loss": 0.0678, "step": 794 }, { "epoch": 0.043903247183565274, "grad_norm": 0.049180060625076294, "learning_rate": 3.997984757173339e-05, "loss": 0.001, "step": 795 }, { "epoch": 0.04395847139385907, "grad_norm": 0.10096517950296402, "learning_rate": 3.9979686701982744e-05, "loss": 0.0031, "step": 796 }, { "epoch": 0.04401369560415286, "grad_norm": 3.250683069229126, "learning_rate": 3.997952519302503e-05, "loss": 0.6067, "step": 797 }, { "epoch": 0.044068919814446654, "grad_norm": 3.4135990142822266, "learning_rate": 3.997936304486544e-05, "loss": 0.5085, "step": 798 }, { "epoch": 0.04412414402474044, "grad_norm": 2.7334744930267334, "learning_rate": 3.997920025750914e-05, "loss": 0.9169, "step": 799 }, { "epoch": 0.04417936823503424, "grad_norm": 6.850595474243164, "learning_rate": 3.997903683096135e-05, "loss": 1.7714, "step": 800 }, { "epoch": 0.044234592445328035, "grad_norm": 3.8184995651245117, "learning_rate": 3.997887276522729e-05, "loss": 0.4898, "step": 801 }, { "epoch": 0.04428981665562182, "grad_norm": 3.409151554107666, "learning_rate": 3.9978708060312214e-05, "loss": 0.0582, "step": 802 }, { "epoch": 0.04434504086591562, "grad_norm": 0.1774301826953888, "learning_rate": 3.9978542716221385e-05, "loss": 0.0046, "step": 803 }, { "epoch": 0.04440026507620941, "grad_norm": 4.565890312194824, "learning_rate": 3.997837673296011e-05, "loss": 0.9162, "step": 804 }, { "epoch": 0.044455489286503204, "grad_norm": 4.648644924163818, "learning_rate": 3.9978210110533676e-05, "loss": 0.7643, "step": 805 }, { "epoch": 0.04451071349679699, "grad_norm": 2.4284777641296387, "learning_rate": 3.997804284894743e-05, "loss": 0.0642, "step": 806 }, { "epoch": 0.04456593770709079, "grad_norm": 3.9995222091674805, "learning_rate": 3.997787494820672e-05, "loss": 0.1158, "step": 807 }, { "epoch": 0.044621161917384584, "grad_norm": 1.9016016721725464, "learning_rate": 3.997770640831692e-05, "loss": 0.1031, "step": 808 }, { "epoch": 0.04467638612767837, "grad_norm": 3.101395606994629, "learning_rate": 3.997753722928341e-05, "loss": 0.1562, "step": 809 }, { "epoch": 0.04473161033797217, "grad_norm": 0.24049443006515503, "learning_rate": 3.997736741111161e-05, "loss": 0.0068, "step": 810 }, { "epoch": 0.04478683454826596, "grad_norm": 4.764894962310791, "learning_rate": 3.9977196953806956e-05, "loss": 0.5519, "step": 811 }, { "epoch": 0.044842058758559754, "grad_norm": 4.046773433685303, "learning_rate": 3.99770258573749e-05, "loss": 0.3739, "step": 812 }, { "epoch": 0.04489728296885354, "grad_norm": 5.744151592254639, "learning_rate": 3.997685412182091e-05, "loss": 0.7027, "step": 813 }, { "epoch": 0.04495250717914734, "grad_norm": 5.35287618637085, "learning_rate": 3.997668174715049e-05, "loss": 0.6411, "step": 814 }, { "epoch": 0.045007731389441134, "grad_norm": 4.5431742668151855, "learning_rate": 3.997650873336915e-05, "loss": 1.4374, "step": 815 }, { "epoch": 0.04506295559973492, "grad_norm": 2.014324903488159, "learning_rate": 3.997633508048242e-05, "loss": 0.0394, "step": 816 }, { "epoch": 0.04511817981002872, "grad_norm": 2.7360239028930664, "learning_rate": 3.997616078849587e-05, "loss": 0.4654, "step": 817 }, { "epoch": 0.04517340402032251, "grad_norm": 4.470723628997803, "learning_rate": 3.997598585741506e-05, "loss": 0.3949, "step": 818 }, { "epoch": 0.045228628230616304, "grad_norm": 0.15006564557552338, "learning_rate": 3.9975810287245595e-05, "loss": 0.0037, "step": 819 }, { "epoch": 0.04528385244091009, "grad_norm": 6.13006067276001, "learning_rate": 3.997563407799309e-05, "loss": 1.4003, "step": 820 }, { "epoch": 0.04533907665120389, "grad_norm": 0.744400680065155, "learning_rate": 3.9975457229663185e-05, "loss": 0.0121, "step": 821 }, { "epoch": 0.04539430086149768, "grad_norm": 5.707660675048828, "learning_rate": 3.997527974226153e-05, "loss": 0.3958, "step": 822 }, { "epoch": 0.04544952507179147, "grad_norm": 1.0235503911972046, "learning_rate": 3.997510161579381e-05, "loss": 0.0383, "step": 823 }, { "epoch": 0.04550474928208527, "grad_norm": 2.1000583171844482, "learning_rate": 3.997492285026573e-05, "loss": 0.1244, "step": 824 }, { "epoch": 0.04555997349237906, "grad_norm": 4.004913330078125, "learning_rate": 3.9974743445682993e-05, "loss": 0.4739, "step": 825 }, { "epoch": 0.045615197702672854, "grad_norm": 0.849504828453064, "learning_rate": 3.997456340205135e-05, "loss": 0.0247, "step": 826 }, { "epoch": 0.04567042191296664, "grad_norm": 4.0912604331970215, "learning_rate": 3.997438271937656e-05, "loss": 0.6649, "step": 827 }, { "epoch": 0.04572564612326044, "grad_norm": 0.34909310936927795, "learning_rate": 3.997420139766441e-05, "loss": 0.0072, "step": 828 }, { "epoch": 0.04578087033355423, "grad_norm": 2.692392587661743, "learning_rate": 3.997401943692068e-05, "loss": 0.241, "step": 829 }, { "epoch": 0.04583609454384802, "grad_norm": 2.0842583179473877, "learning_rate": 3.9973836837151215e-05, "loss": 0.4205, "step": 830 }, { "epoch": 0.04589131875414182, "grad_norm": 3.1085174083709717, "learning_rate": 3.997365359836184e-05, "loss": 0.4647, "step": 831 }, { "epoch": 0.04594654296443561, "grad_norm": 1.807054042816162, "learning_rate": 3.997346972055843e-05, "loss": 0.2133, "step": 832 }, { "epoch": 0.046001767174729404, "grad_norm": 1.2842299938201904, "learning_rate": 3.9973285203746855e-05, "loss": 0.0499, "step": 833 }, { "epoch": 0.04605699138502319, "grad_norm": 0.07620476186275482, "learning_rate": 3.9973100047933024e-05, "loss": 0.0019, "step": 834 }, { "epoch": 0.04611221559531699, "grad_norm": 3.9993224143981934, "learning_rate": 3.997291425312287e-05, "loss": 0.7076, "step": 835 }, { "epoch": 0.04616743980561078, "grad_norm": 2.4137165546417236, "learning_rate": 3.997272781932232e-05, "loss": 0.3024, "step": 836 }, { "epoch": 0.04622266401590457, "grad_norm": 1.0316705703735352, "learning_rate": 3.997254074653735e-05, "loss": 0.0331, "step": 837 }, { "epoch": 0.04627788822619837, "grad_norm": 2.8233683109283447, "learning_rate": 3.997235303477394e-05, "loss": 0.2773, "step": 838 }, { "epoch": 0.04633311243649216, "grad_norm": 0.357971727848053, "learning_rate": 3.9972164684038104e-05, "loss": 0.0138, "step": 839 }, { "epoch": 0.04638833664678595, "grad_norm": 1.216271162033081, "learning_rate": 3.997197569433586e-05, "loss": 0.0432, "step": 840 }, { "epoch": 0.04644356085707974, "grad_norm": 3.26739764213562, "learning_rate": 3.9971786065673254e-05, "loss": 0.3372, "step": 841 }, { "epoch": 0.04649878506737354, "grad_norm": 0.34659093618392944, "learning_rate": 3.997159579805635e-05, "loss": 0.0101, "step": 842 }, { "epoch": 0.04655400927766733, "grad_norm": 0.9313758611679077, "learning_rate": 3.997140489149125e-05, "loss": 0.0397, "step": 843 }, { "epoch": 0.04660923348796112, "grad_norm": 2.0510482788085938, "learning_rate": 3.997121334598404e-05, "loss": 0.1542, "step": 844 }, { "epoch": 0.04666445769825491, "grad_norm": 5.207319259643555, "learning_rate": 3.9971021161540863e-05, "loss": 0.6162, "step": 845 }, { "epoch": 0.04671968190854871, "grad_norm": 6.460243225097656, "learning_rate": 3.997082833816787e-05, "loss": 1.8135, "step": 846 }, { "epoch": 0.0467749061188425, "grad_norm": 0.16507649421691895, "learning_rate": 3.997063487587123e-05, "loss": 0.0066, "step": 847 }, { "epoch": 0.04683013032913629, "grad_norm": 4.806826591491699, "learning_rate": 3.9970440774657115e-05, "loss": 0.7201, "step": 848 }, { "epoch": 0.04688535453943009, "grad_norm": 0.6820359826087952, "learning_rate": 3.997024603453174e-05, "loss": 0.0142, "step": 849 }, { "epoch": 0.04694057874972388, "grad_norm": 4.3064656257629395, "learning_rate": 3.997005065550135e-05, "loss": 0.6487, "step": 850 }, { "epoch": 0.04699580296001767, "grad_norm": 3.899000644683838, "learning_rate": 3.9969854637572195e-05, "loss": 0.1656, "step": 851 }, { "epoch": 0.04705102717031146, "grad_norm": 5.97811222076416, "learning_rate": 3.996965798075053e-05, "loss": 0.8354, "step": 852 }, { "epoch": 0.04710625138060526, "grad_norm": 3.138399362564087, "learning_rate": 3.9969460685042654e-05, "loss": 0.8697, "step": 853 }, { "epoch": 0.04716147559089905, "grad_norm": 0.9447166919708252, "learning_rate": 3.996926275045488e-05, "loss": 0.0234, "step": 854 }, { "epoch": 0.04721669980119284, "grad_norm": 4.963366985321045, "learning_rate": 3.996906417699354e-05, "loss": 0.3397, "step": 855 }, { "epoch": 0.04727192401148664, "grad_norm": 0.25247836112976074, "learning_rate": 3.996886496466499e-05, "loss": 0.0072, "step": 856 }, { "epoch": 0.04732714822178043, "grad_norm": 1.4437631368637085, "learning_rate": 3.99686651134756e-05, "loss": 0.0726, "step": 857 }, { "epoch": 0.04738237243207422, "grad_norm": 0.3311542272567749, "learning_rate": 3.996846462343177e-05, "loss": 0.01, "step": 858 }, { "epoch": 0.04743759664236801, "grad_norm": 0.19500216841697693, "learning_rate": 3.99682634945399e-05, "loss": 0.0039, "step": 859 }, { "epoch": 0.04749282085266181, "grad_norm": 3.8547275066375732, "learning_rate": 3.996806172680645e-05, "loss": 1.0199, "step": 860 }, { "epoch": 0.0475480450629556, "grad_norm": 3.658318281173706, "learning_rate": 3.996785932023784e-05, "loss": 0.1459, "step": 861 }, { "epoch": 0.04760326927324939, "grad_norm": 5.060117244720459, "learning_rate": 3.9967656274840575e-05, "loss": 0.542, "step": 862 }, { "epoch": 0.04765849348354319, "grad_norm": 2.9275014400482178, "learning_rate": 3.9967452590621134e-05, "loss": 0.407, "step": 863 }, { "epoch": 0.04771371769383698, "grad_norm": 4.87360954284668, "learning_rate": 3.996724826758605e-05, "loss": 1.2476, "step": 864 }, { "epoch": 0.04776894190413077, "grad_norm": 2.924557685852051, "learning_rate": 3.996704330574184e-05, "loss": 0.1913, "step": 865 }, { "epoch": 0.04782416611442456, "grad_norm": 3.6591556072235107, "learning_rate": 3.996683770509507e-05, "loss": 0.5011, "step": 866 }, { "epoch": 0.04787939032471836, "grad_norm": 0.6188504099845886, "learning_rate": 3.996663146565232e-05, "loss": 0.0115, "step": 867 }, { "epoch": 0.047934614535012146, "grad_norm": 2.7947428226470947, "learning_rate": 3.996642458742019e-05, "loss": 0.1168, "step": 868 }, { "epoch": 0.04798983874530594, "grad_norm": 3.2835583686828613, "learning_rate": 3.99662170704053e-05, "loss": 0.4211, "step": 869 }, { "epoch": 0.04804506295559974, "grad_norm": 6.108421802520752, "learning_rate": 3.9966008914614276e-05, "loss": 1.3972, "step": 870 }, { "epoch": 0.04810028716589353, "grad_norm": 0.5671759843826294, "learning_rate": 3.996580012005379e-05, "loss": 0.0236, "step": 871 }, { "epoch": 0.04815551137618732, "grad_norm": 2.2736451625823975, "learning_rate": 3.996559068673052e-05, "loss": 0.3259, "step": 872 }, { "epoch": 0.04821073558648111, "grad_norm": 1.0749894380569458, "learning_rate": 3.996538061465116e-05, "loss": 0.1143, "step": 873 }, { "epoch": 0.04826595979677491, "grad_norm": 1.53611421585083, "learning_rate": 3.996516990382244e-05, "loss": 0.0988, "step": 874 }, { "epoch": 0.048321184007068696, "grad_norm": 4.039351940155029, "learning_rate": 3.996495855425109e-05, "loss": 0.4964, "step": 875 }, { "epoch": 0.04837640821736249, "grad_norm": 4.30972957611084, "learning_rate": 3.9964746565943884e-05, "loss": 0.1624, "step": 876 }, { "epoch": 0.04843163242765629, "grad_norm": 4.445703029632568, "learning_rate": 3.99645339389076e-05, "loss": 1.2365, "step": 877 }, { "epoch": 0.048486856637950076, "grad_norm": 1.445859432220459, "learning_rate": 3.996432067314903e-05, "loss": 0.0509, "step": 878 }, { "epoch": 0.04854208084824387, "grad_norm": 4.5128655433654785, "learning_rate": 3.996410676867501e-05, "loss": 0.543, "step": 879 }, { "epoch": 0.04859730505853766, "grad_norm": 4.678088188171387, "learning_rate": 3.9963892225492385e-05, "loss": 0.6373, "step": 880 }, { "epoch": 0.04865252926883146, "grad_norm": 4.631839752197266, "learning_rate": 3.9963677043608e-05, "loss": 0.2356, "step": 881 }, { "epoch": 0.048707753479125246, "grad_norm": 0.28841033577919006, "learning_rate": 3.996346122302877e-05, "loss": 0.0101, "step": 882 }, { "epoch": 0.04876297768941904, "grad_norm": 3.1216790676116943, "learning_rate": 3.996324476376157e-05, "loss": 0.7605, "step": 883 }, { "epoch": 0.04881820189971284, "grad_norm": 2.667604684829712, "learning_rate": 3.9963027665813335e-05, "loss": 0.2259, "step": 884 }, { "epoch": 0.048873426110006626, "grad_norm": 4.963838577270508, "learning_rate": 3.996280992919102e-05, "loss": 1.4867, "step": 885 }, { "epoch": 0.04892865032030042, "grad_norm": 1.6407465934753418, "learning_rate": 3.996259155390158e-05, "loss": 0.073, "step": 886 }, { "epoch": 0.04898387453059421, "grad_norm": 0.4384150505065918, "learning_rate": 3.996237253995201e-05, "loss": 0.0113, "step": 887 }, { "epoch": 0.04903909874088801, "grad_norm": 1.3631527423858643, "learning_rate": 3.996215288734931e-05, "loss": 0.0696, "step": 888 }, { "epoch": 0.049094322951181796, "grad_norm": 4.144669532775879, "learning_rate": 3.99619325961005e-05, "loss": 1.2701, "step": 889 }, { "epoch": 0.04914954716147559, "grad_norm": 0.6310134530067444, "learning_rate": 3.996171166621265e-05, "loss": 0.0224, "step": 890 }, { "epoch": 0.04920477137176938, "grad_norm": 2.9092857837677, "learning_rate": 3.996149009769281e-05, "loss": 0.0457, "step": 891 }, { "epoch": 0.049259995582063176, "grad_norm": 1.4754695892333984, "learning_rate": 3.996126789054807e-05, "loss": 0.0471, "step": 892 }, { "epoch": 0.04931521979235697, "grad_norm": 2.6252028942108154, "learning_rate": 3.9961045044785555e-05, "loss": 0.1754, "step": 893 }, { "epoch": 0.04937044400265076, "grad_norm": 0.07049255073070526, "learning_rate": 3.996082156041237e-05, "loss": 0.0023, "step": 894 }, { "epoch": 0.04942566821294456, "grad_norm": 0.3622780740261078, "learning_rate": 3.996059743743568e-05, "loss": 0.0074, "step": 895 }, { "epoch": 0.049480892423238346, "grad_norm": 1.3846954107284546, "learning_rate": 3.996037267586266e-05, "loss": 0.1264, "step": 896 }, { "epoch": 0.04953611663353214, "grad_norm": 0.4465561509132385, "learning_rate": 3.996014727570048e-05, "loss": 0.008, "step": 897 }, { "epoch": 0.04959134084382593, "grad_norm": 3.399282932281494, "learning_rate": 3.995992123695638e-05, "loss": 0.5096, "step": 898 }, { "epoch": 0.049646565054119726, "grad_norm": 2.625319480895996, "learning_rate": 3.995969455963757e-05, "loss": 0.2079, "step": 899 }, { "epoch": 0.04970178926441352, "grad_norm": 3.1444754600524902, "learning_rate": 3.99594672437513e-05, "loss": 0.1182, "step": 900 }, { "epoch": 0.04975701347470731, "grad_norm": 5.388269901275635, "learning_rate": 3.9959239289304864e-05, "loss": 1.503, "step": 901 }, { "epoch": 0.04981223768500111, "grad_norm": 2.671337842941284, "learning_rate": 3.995901069630553e-05, "loss": 0.5972, "step": 902 }, { "epoch": 0.049867461895294896, "grad_norm": 3.7155582904815674, "learning_rate": 3.995878146476063e-05, "loss": 0.9655, "step": 903 }, { "epoch": 0.04992268610558869, "grad_norm": 3.0550036430358887, "learning_rate": 3.9958551594677485e-05, "loss": 0.2627, "step": 904 }, { "epoch": 0.04997791031588248, "grad_norm": 0.230698361992836, "learning_rate": 3.9958321086063464e-05, "loss": 0.0047, "step": 905 }, { "epoch": 0.050033134526176276, "grad_norm": 2.6633095741271973, "learning_rate": 3.995808993892593e-05, "loss": 0.7664, "step": 906 }, { "epoch": 0.05008835873647007, "grad_norm": 3.180316925048828, "learning_rate": 3.9957858153272276e-05, "loss": 0.445, "step": 907 }, { "epoch": 0.05014358294676386, "grad_norm": 3.5768446922302246, "learning_rate": 3.995762572910993e-05, "loss": 0.2872, "step": 908 }, { "epoch": 0.05019880715705766, "grad_norm": 3.6449339389801025, "learning_rate": 3.995739266644631e-05, "loss": 1.0897, "step": 909 }, { "epoch": 0.050254031367351445, "grad_norm": 2.2884721755981445, "learning_rate": 3.995715896528889e-05, "loss": 0.0455, "step": 910 }, { "epoch": 0.05030925557764524, "grad_norm": 0.4147081673145294, "learning_rate": 3.9956924625645134e-05, "loss": 0.0142, "step": 911 }, { "epoch": 0.05036447978793903, "grad_norm": 5.329318523406982, "learning_rate": 3.995668964752255e-05, "loss": 0.9411, "step": 912 }, { "epoch": 0.050419703998232826, "grad_norm": 0.06815004348754883, "learning_rate": 3.9956454030928646e-05, "loss": 0.0015, "step": 913 }, { "epoch": 0.050474928208526615, "grad_norm": 2.7812345027923584, "learning_rate": 3.995621777587096e-05, "loss": 0.3154, "step": 914 }, { "epoch": 0.05053015241882041, "grad_norm": 0.1438557654619217, "learning_rate": 3.995598088235706e-05, "loss": 0.0047, "step": 915 }, { "epoch": 0.050585376629114207, "grad_norm": 2.104663610458374, "learning_rate": 3.9955743350394523e-05, "loss": 0.2368, "step": 916 }, { "epoch": 0.050640600839407995, "grad_norm": 0.4393625557422638, "learning_rate": 3.9955505179990945e-05, "loss": 0.0164, "step": 917 }, { "epoch": 0.05069582504970179, "grad_norm": 6.003518104553223, "learning_rate": 3.9955266371153934e-05, "loss": 0.6121, "step": 918 }, { "epoch": 0.05075104925999558, "grad_norm": 0.1804838925600052, "learning_rate": 3.9955026923891156e-05, "loss": 0.0056, "step": 919 }, { "epoch": 0.050806273470289376, "grad_norm": 4.634797096252441, "learning_rate": 3.9954786838210246e-05, "loss": 0.2657, "step": 920 }, { "epoch": 0.050861497680583165, "grad_norm": 6.1246795654296875, "learning_rate": 3.9954546114118897e-05, "loss": 0.7201, "step": 921 }, { "epoch": 0.05091672189087696, "grad_norm": 5.854478359222412, "learning_rate": 3.995430475162482e-05, "loss": 0.4867, "step": 922 }, { "epoch": 0.050971946101170756, "grad_norm": 4.7110114097595215, "learning_rate": 3.9954062750735717e-05, "loss": 1.0601, "step": 923 }, { "epoch": 0.051027170311464545, "grad_norm": 1.0635104179382324, "learning_rate": 3.995382011145934e-05, "loss": 0.0249, "step": 924 }, { "epoch": 0.05108239452175834, "grad_norm": 2.8127968311309814, "learning_rate": 3.9953576833803456e-05, "loss": 0.848, "step": 925 }, { "epoch": 0.05113761873205213, "grad_norm": 3.345319986343384, "learning_rate": 3.995333291777584e-05, "loss": 0.1438, "step": 926 }, { "epoch": 0.051192842942345926, "grad_norm": 4.716004848480225, "learning_rate": 3.9953088363384306e-05, "loss": 0.6675, "step": 927 }, { "epoch": 0.051248067152639715, "grad_norm": 5.221681594848633, "learning_rate": 3.995284317063666e-05, "loss": 2.0711, "step": 928 }, { "epoch": 0.05130329136293351, "grad_norm": 0.5599204301834106, "learning_rate": 3.9952597339540766e-05, "loss": 0.0214, "step": 929 }, { "epoch": 0.051358515573227306, "grad_norm": 1.918765664100647, "learning_rate": 3.995235087010448e-05, "loss": 0.0732, "step": 930 }, { "epoch": 0.051413739783521095, "grad_norm": 3.484396457672119, "learning_rate": 3.995210376233569e-05, "loss": 0.1917, "step": 931 }, { "epoch": 0.05146896399381489, "grad_norm": 1.2125277519226074, "learning_rate": 3.9951856016242296e-05, "loss": 0.0355, "step": 932 }, { "epoch": 0.05152418820410868, "grad_norm": 0.8008686900138855, "learning_rate": 3.995160763183223e-05, "loss": 0.0882, "step": 933 }, { "epoch": 0.051579412414402476, "grad_norm": 1.7095073461532593, "learning_rate": 3.995135860911343e-05, "loss": 0.0647, "step": 934 }, { "epoch": 0.051634636624696265, "grad_norm": 4.298102855682373, "learning_rate": 3.995110894809387e-05, "loss": 0.4582, "step": 935 }, { "epoch": 0.05168986083499006, "grad_norm": 4.432285785675049, "learning_rate": 3.995085864878155e-05, "loss": 0.1768, "step": 936 }, { "epoch": 0.05174508504528385, "grad_norm": 4.332840919494629, "learning_rate": 3.995060771118445e-05, "loss": 0.6968, "step": 937 }, { "epoch": 0.051800309255577645, "grad_norm": 3.323201894760132, "learning_rate": 3.9950356135310616e-05, "loss": 0.4722, "step": 938 }, { "epoch": 0.05185553346587144, "grad_norm": 1.5306339263916016, "learning_rate": 3.9950103921168094e-05, "loss": 0.0552, "step": 939 }, { "epoch": 0.05191075767616523, "grad_norm": 0.869091808795929, "learning_rate": 3.9949851068764955e-05, "loss": 0.0208, "step": 940 }, { "epoch": 0.051965981886459026, "grad_norm": 4.509561061859131, "learning_rate": 3.9949597578109276e-05, "loss": 0.1495, "step": 941 }, { "epoch": 0.052021206096752814, "grad_norm": 4.60536527633667, "learning_rate": 3.994934344920918e-05, "loss": 0.8386, "step": 942 }, { "epoch": 0.05207643030704661, "grad_norm": 0.46750590205192566, "learning_rate": 3.99490886820728e-05, "loss": 0.0106, "step": 943 }, { "epoch": 0.0521316545173404, "grad_norm": 1.25382399559021, "learning_rate": 3.9948833276708286e-05, "loss": 0.0447, "step": 944 }, { "epoch": 0.052186878727634195, "grad_norm": 2.106243371963501, "learning_rate": 3.994857723312379e-05, "loss": 0.1677, "step": 945 }, { "epoch": 0.05224210293792799, "grad_norm": 2.240572452545166, "learning_rate": 3.9948320551327524e-05, "loss": 0.1628, "step": 946 }, { "epoch": 0.05229732714822178, "grad_norm": 0.1526757925748825, "learning_rate": 3.994806323132769e-05, "loss": 0.0032, "step": 947 }, { "epoch": 0.052352551358515576, "grad_norm": 1.26038658618927, "learning_rate": 3.994780527313253e-05, "loss": 0.0399, "step": 948 }, { "epoch": 0.052407775568809364, "grad_norm": 3.1712701320648193, "learning_rate": 3.994754667675028e-05, "loss": 0.0752, "step": 949 }, { "epoch": 0.05246299977910316, "grad_norm": 3.1660401821136475, "learning_rate": 3.994728744218923e-05, "loss": 0.4459, "step": 950 }, { "epoch": 0.05251822398939695, "grad_norm": 3.998673915863037, "learning_rate": 3.9947027569457665e-05, "loss": 0.8075, "step": 951 }, { "epoch": 0.052573448199690745, "grad_norm": 0.8838708996772766, "learning_rate": 3.9946767058563904e-05, "loss": 0.0238, "step": 952 }, { "epoch": 0.052628672409984534, "grad_norm": 0.3001108765602112, "learning_rate": 3.994650590951627e-05, "loss": 0.0126, "step": 953 }, { "epoch": 0.05268389662027833, "grad_norm": 0.1939816176891327, "learning_rate": 3.994624412232314e-05, "loss": 0.0068, "step": 954 }, { "epoch": 0.052739120830572125, "grad_norm": 3.7900748252868652, "learning_rate": 3.9945981696992866e-05, "loss": 0.5102, "step": 955 }, { "epoch": 0.052794345040865914, "grad_norm": 5.74921989440918, "learning_rate": 3.994571863353386e-05, "loss": 0.1836, "step": 956 }, { "epoch": 0.05284956925115971, "grad_norm": 3.9574129581451416, "learning_rate": 3.994545493195453e-05, "loss": 0.5176, "step": 957 }, { "epoch": 0.0529047934614535, "grad_norm": 5.485291481018066, "learning_rate": 3.994519059226332e-05, "loss": 0.4476, "step": 958 }, { "epoch": 0.052960017671747295, "grad_norm": 2.1191086769104004, "learning_rate": 3.9944925614468674e-05, "loss": 0.1713, "step": 959 }, { "epoch": 0.053015241882041084, "grad_norm": 0.6315130591392517, "learning_rate": 3.994465999857908e-05, "loss": 0.014, "step": 960 }, { "epoch": 0.05307046609233488, "grad_norm": 3.4069464206695557, "learning_rate": 3.994439374460303e-05, "loss": 0.6293, "step": 961 }, { "epoch": 0.053125690302628675, "grad_norm": 3.882960319519043, "learning_rate": 3.994412685254905e-05, "loss": 0.4458, "step": 962 }, { "epoch": 0.053180914512922464, "grad_norm": 1.7842763662338257, "learning_rate": 3.994385932242567e-05, "loss": 0.1335, "step": 963 }, { "epoch": 0.05323613872321626, "grad_norm": 4.601657867431641, "learning_rate": 3.994359115424146e-05, "loss": 0.9565, "step": 964 }, { "epoch": 0.05329136293351005, "grad_norm": 2.2913875579833984, "learning_rate": 3.994332234800498e-05, "loss": 0.1664, "step": 965 }, { "epoch": 0.053346587143803845, "grad_norm": 4.399823188781738, "learning_rate": 3.9943052903724845e-05, "loss": 0.8705, "step": 966 }, { "epoch": 0.053401811354097634, "grad_norm": 1.323108434677124, "learning_rate": 3.9942782821409676e-05, "loss": 0.1145, "step": 967 }, { "epoch": 0.05345703556439143, "grad_norm": 0.9024590253829956, "learning_rate": 3.9942512101068105e-05, "loss": 0.0298, "step": 968 }, { "epoch": 0.053512259774685225, "grad_norm": 1.2398524284362793, "learning_rate": 3.9942240742708806e-05, "loss": 0.0408, "step": 969 }, { "epoch": 0.053567483984979014, "grad_norm": 0.5220991373062134, "learning_rate": 3.9941968746340446e-05, "loss": 0.0135, "step": 970 }, { "epoch": 0.05362270819527281, "grad_norm": 3.48657488822937, "learning_rate": 3.994169611197174e-05, "loss": 0.3281, "step": 971 }, { "epoch": 0.0536779324055666, "grad_norm": 1.6167975664138794, "learning_rate": 3.99414228396114e-05, "loss": 0.0813, "step": 972 }, { "epoch": 0.053733156615860395, "grad_norm": 0.7777401208877563, "learning_rate": 3.9941148929268165e-05, "loss": 0.029, "step": 973 }, { "epoch": 0.053788380826154183, "grad_norm": 1.118245244026184, "learning_rate": 3.9940874380950816e-05, "loss": 0.0422, "step": 974 }, { "epoch": 0.05384360503644798, "grad_norm": 0.13159410655498505, "learning_rate": 3.994059919466812e-05, "loss": 0.0038, "step": 975 }, { "epoch": 0.05389882924674177, "grad_norm": 0.8545509576797485, "learning_rate": 3.994032337042889e-05, "loss": 0.0134, "step": 976 }, { "epoch": 0.053954053457035564, "grad_norm": 0.03597402200102806, "learning_rate": 3.9940046908241946e-05, "loss": 0.0008, "step": 977 }, { "epoch": 0.05400927766732936, "grad_norm": 1.0347614288330078, "learning_rate": 3.993976980811614e-05, "loss": 0.0387, "step": 978 }, { "epoch": 0.05406450187762315, "grad_norm": 0.3556990325450897, "learning_rate": 3.993949207006033e-05, "loss": 0.0073, "step": 979 }, { "epoch": 0.054119726087916945, "grad_norm": 0.504631519317627, "learning_rate": 3.99392136940834e-05, "loss": 0.0111, "step": 980 }, { "epoch": 0.05417495029821073, "grad_norm": 4.4485650062561035, "learning_rate": 3.993893468019426e-05, "loss": 0.7445, "step": 981 }, { "epoch": 0.05423017450850453, "grad_norm": 0.5671532154083252, "learning_rate": 3.993865502840184e-05, "loss": 0.0093, "step": 982 }, { "epoch": 0.05428539871879832, "grad_norm": 2.8837087154388428, "learning_rate": 3.9938374738715085e-05, "loss": 0.0817, "step": 983 }, { "epoch": 0.054340622929092114, "grad_norm": 0.3313210606575012, "learning_rate": 3.993809381114295e-05, "loss": 0.0083, "step": 984 }, { "epoch": 0.05439584713938591, "grad_norm": 11.07579517364502, "learning_rate": 3.993781224569444e-05, "loss": 1.8939, "step": 985 }, { "epoch": 0.0544510713496797, "grad_norm": 3.6560590267181396, "learning_rate": 3.993753004237855e-05, "loss": 0.0863, "step": 986 }, { "epoch": 0.054506295559973494, "grad_norm": 0.05369526520371437, "learning_rate": 3.9937247201204325e-05, "loss": 0.0011, "step": 987 }, { "epoch": 0.05456151977026728, "grad_norm": 1.163712501525879, "learning_rate": 3.99369637221808e-05, "loss": 0.0272, "step": 988 }, { "epoch": 0.05461674398056108, "grad_norm": 0.1337786167860031, "learning_rate": 3.993667960531704e-05, "loss": 0.0023, "step": 989 }, { "epoch": 0.05467196819085487, "grad_norm": 3.194761037826538, "learning_rate": 3.993639485062215e-05, "loss": 0.3416, "step": 990 }, { "epoch": 0.054727192401148664, "grad_norm": 0.01457290630787611, "learning_rate": 3.993610945810522e-05, "loss": 0.0004, "step": 991 }, { "epoch": 0.05478241661144246, "grad_norm": 0.1268981695175171, "learning_rate": 3.993582342777541e-05, "loss": 0.004, "step": 992 }, { "epoch": 0.05483764082173625, "grad_norm": 1.8439058065414429, "learning_rate": 3.9935536759641843e-05, "loss": 0.1221, "step": 993 }, { "epoch": 0.054892865032030044, "grad_norm": 4.3617777824401855, "learning_rate": 3.9935249453713704e-05, "loss": 0.478, "step": 994 }, { "epoch": 0.05494808924232383, "grad_norm": 0.15415093302726746, "learning_rate": 3.993496151000018e-05, "loss": 0.0044, "step": 995 }, { "epoch": 0.05500331345261763, "grad_norm": 3.4988510608673096, "learning_rate": 3.993467292851048e-05, "loss": 0.9191, "step": 996 }, { "epoch": 0.05505853766291142, "grad_norm": 2.747988224029541, "learning_rate": 3.993438370925386e-05, "loss": 0.1897, "step": 997 }, { "epoch": 0.055113761873205214, "grad_norm": 0.11326351016759872, "learning_rate": 3.993409385223954e-05, "loss": 0.002, "step": 998 }, { "epoch": 0.055168986083499, "grad_norm": 3.9442851543426514, "learning_rate": 3.9933803357476806e-05, "loss": 0.64, "step": 999 }, { "epoch": 0.0552242102937928, "grad_norm": 5.123285293579102, "learning_rate": 3.993351222497496e-05, "loss": 0.954, "step": 1000 }, { "epoch": 0.055279434504086594, "grad_norm": 3.451770782470703, "learning_rate": 3.9933220454743306e-05, "loss": 0.5017, "step": 1001 }, { "epoch": 0.05533465871438038, "grad_norm": 3.453977346420288, "learning_rate": 3.9932928046791186e-05, "loss": 0.2211, "step": 1002 }, { "epoch": 0.05538988292467418, "grad_norm": 2.0126125812530518, "learning_rate": 3.993263500112795e-05, "loss": 0.0463, "step": 1003 }, { "epoch": 0.05544510713496797, "grad_norm": 0.04294798895716667, "learning_rate": 3.993234131776297e-05, "loss": 0.0014, "step": 1004 }, { "epoch": 0.055500331345261764, "grad_norm": 2.7735836505889893, "learning_rate": 3.993204699670565e-05, "loss": 0.22, "step": 1005 }, { "epoch": 0.05555555555555555, "grad_norm": 1.5444329977035522, "learning_rate": 3.993175203796541e-05, "loss": 0.04, "step": 1006 }, { "epoch": 0.05561077976584935, "grad_norm": 7.789406776428223, "learning_rate": 3.9931456441551664e-05, "loss": 1.1946, "step": 1007 }, { "epoch": 0.055666003976143144, "grad_norm": 2.4603114128112793, "learning_rate": 3.9931160207473895e-05, "loss": 0.2002, "step": 1008 }, { "epoch": 0.05572122818643693, "grad_norm": 2.7667746543884277, "learning_rate": 3.9930863335741566e-05, "loss": 0.895, "step": 1009 }, { "epoch": 0.05577645239673073, "grad_norm": 5.1480393409729, "learning_rate": 3.9930565826364176e-05, "loss": 1.7103, "step": 1010 }, { "epoch": 0.05583167660702452, "grad_norm": 6.531047821044922, "learning_rate": 3.993026767935125e-05, "loss": 0.9513, "step": 1011 }, { "epoch": 0.055886900817318313, "grad_norm": 4.0059967041015625, "learning_rate": 3.992996889471232e-05, "loss": 0.8318, "step": 1012 }, { "epoch": 0.0559421250276121, "grad_norm": 0.3592488765716553, "learning_rate": 3.9929669472456946e-05, "loss": 0.0083, "step": 1013 }, { "epoch": 0.0559973492379059, "grad_norm": 4.498117923736572, "learning_rate": 3.992936941259471e-05, "loss": 0.1285, "step": 1014 }, { "epoch": 0.056052573448199694, "grad_norm": 7.847482204437256, "learning_rate": 3.992906871513521e-05, "loss": 1.5411, "step": 1015 }, { "epoch": 0.05610779765849348, "grad_norm": 4.626918315887451, "learning_rate": 3.9928767380088064e-05, "loss": 1.0321, "step": 1016 }, { "epoch": 0.05616302186878728, "grad_norm": 3.2585129737854004, "learning_rate": 3.9928465407462916e-05, "loss": 0.0873, "step": 1017 }, { "epoch": 0.05621824607908107, "grad_norm": 4.690016746520996, "learning_rate": 3.992816279726943e-05, "loss": 1.0093, "step": 1018 }, { "epoch": 0.05627347028937486, "grad_norm": 0.8927239179611206, "learning_rate": 3.9927859549517275e-05, "loss": 0.0135, "step": 1019 }, { "epoch": 0.05632869449966865, "grad_norm": 0.14004158973693848, "learning_rate": 3.992755566421617e-05, "loss": 0.0031, "step": 1020 }, { "epoch": 0.05638391870996245, "grad_norm": 5.75179386138916, "learning_rate": 3.992725114137582e-05, "loss": 1.0872, "step": 1021 }, { "epoch": 0.05643914292025624, "grad_norm": 4.065658092498779, "learning_rate": 3.992694598100598e-05, "loss": 1.4894, "step": 1022 }, { "epoch": 0.05649436713055003, "grad_norm": 1.013122797012329, "learning_rate": 3.992664018311641e-05, "loss": 0.0212, "step": 1023 }, { "epoch": 0.05654959134084383, "grad_norm": 3.941538095474243, "learning_rate": 3.9926333747716885e-05, "loss": 0.8141, "step": 1024 }, { "epoch": 0.05660481555113762, "grad_norm": 0.18116775155067444, "learning_rate": 3.9926026674817225e-05, "loss": 0.0053, "step": 1025 }, { "epoch": 0.05666003976143141, "grad_norm": 2.4982073307037354, "learning_rate": 3.992571896442724e-05, "loss": 0.2795, "step": 1026 }, { "epoch": 0.0567152639717252, "grad_norm": 2.243253469467163, "learning_rate": 3.9925410616556776e-05, "loss": 0.0455, "step": 1027 }, { "epoch": 0.056770488182019, "grad_norm": 3.152198076248169, "learning_rate": 3.9925101631215706e-05, "loss": 0.4979, "step": 1028 }, { "epoch": 0.05682571239231279, "grad_norm": 3.655123472213745, "learning_rate": 3.992479200841391e-05, "loss": 0.2461, "step": 1029 }, { "epoch": 0.05688093660260658, "grad_norm": 0.26797524094581604, "learning_rate": 3.9924481748161293e-05, "loss": 0.0068, "step": 1030 }, { "epoch": 0.05693616081290038, "grad_norm": 2.6674766540527344, "learning_rate": 3.992417085046778e-05, "loss": 0.257, "step": 1031 }, { "epoch": 0.05699138502319417, "grad_norm": 3.959073543548584, "learning_rate": 3.9923859315343326e-05, "loss": 0.5412, "step": 1032 }, { "epoch": 0.05704660923348796, "grad_norm": 0.7430267930030823, "learning_rate": 3.992354714279788e-05, "loss": 0.0191, "step": 1033 }, { "epoch": 0.05710183344378175, "grad_norm": 1.4832243919372559, "learning_rate": 3.992323433284146e-05, "loss": 0.0331, "step": 1034 }, { "epoch": 0.05715705765407555, "grad_norm": 0.6655465960502625, "learning_rate": 3.992292088548404e-05, "loss": 0.0252, "step": 1035 }, { "epoch": 0.05721228186436934, "grad_norm": 5.290635108947754, "learning_rate": 3.9922606800735664e-05, "loss": 0.3586, "step": 1036 }, { "epoch": 0.05726750607466313, "grad_norm": 0.0324680395424366, "learning_rate": 3.9922292078606386e-05, "loss": 0.0009, "step": 1037 }, { "epoch": 0.05732273028495693, "grad_norm": 0.5513284802436829, "learning_rate": 3.992197671910626e-05, "loss": 0.0219, "step": 1038 }, { "epoch": 0.05737795449525072, "grad_norm": 5.051188945770264, "learning_rate": 3.9921660722245395e-05, "loss": 1.1141, "step": 1039 }, { "epoch": 0.05743317870554451, "grad_norm": 4.508037567138672, "learning_rate": 3.992134408803388e-05, "loss": 1.0352, "step": 1040 }, { "epoch": 0.0574884029158383, "grad_norm": 4.435494422912598, "learning_rate": 3.9921026816481855e-05, "loss": 0.5884, "step": 1041 }, { "epoch": 0.0575436271261321, "grad_norm": 5.689024448394775, "learning_rate": 3.992070890759947e-05, "loss": 1.1189, "step": 1042 }, { "epoch": 0.05759885133642589, "grad_norm": 3.2419798374176025, "learning_rate": 3.99203903613969e-05, "loss": 0.5852, "step": 1043 }, { "epoch": 0.05765407554671968, "grad_norm": 4.4219136238098145, "learning_rate": 3.9920071177884324e-05, "loss": 0.9049, "step": 1044 }, { "epoch": 0.05770929975701347, "grad_norm": 3.8891654014587402, "learning_rate": 3.991975135707196e-05, "loss": 0.1786, "step": 1045 }, { "epoch": 0.05776452396730727, "grad_norm": 4.409847259521484, "learning_rate": 3.991943089897005e-05, "loss": 1.4372, "step": 1046 }, { "epoch": 0.05781974817760106, "grad_norm": 3.5717430114746094, "learning_rate": 3.991910980358883e-05, "loss": 0.2701, "step": 1047 }, { "epoch": 0.05787497238789485, "grad_norm": 2.3355064392089844, "learning_rate": 3.9918788070938584e-05, "loss": 0.2004, "step": 1048 }, { "epoch": 0.05793019659818865, "grad_norm": 3.9884374141693115, "learning_rate": 3.99184657010296e-05, "loss": 1.1638, "step": 1049 }, { "epoch": 0.05798542080848244, "grad_norm": 5.0294270515441895, "learning_rate": 3.9918142693872194e-05, "loss": 0.2418, "step": 1050 }, { "epoch": 0.05804064501877623, "grad_norm": 0.2813260555267334, "learning_rate": 3.99178190494767e-05, "loss": 0.0082, "step": 1051 }, { "epoch": 0.05809586922907002, "grad_norm": 0.31675270199775696, "learning_rate": 3.991749476785347e-05, "loss": 0.0101, "step": 1052 }, { "epoch": 0.05815109343936382, "grad_norm": 0.5560124516487122, "learning_rate": 3.9917169849012876e-05, "loss": 0.0161, "step": 1053 }, { "epoch": 0.05820631764965761, "grad_norm": 0.7048330307006836, "learning_rate": 3.991684429296532e-05, "loss": 0.0178, "step": 1054 }, { "epoch": 0.0582615418599514, "grad_norm": 0.3235352337360382, "learning_rate": 3.9916518099721215e-05, "loss": 0.011, "step": 1055 }, { "epoch": 0.0583167660702452, "grad_norm": 1.8129993677139282, "learning_rate": 3.9916191269290996e-05, "loss": 0.1354, "step": 1056 }, { "epoch": 0.058371990280538986, "grad_norm": 2.0878021717071533, "learning_rate": 3.991586380168512e-05, "loss": 0.0319, "step": 1057 }, { "epoch": 0.05842721449083278, "grad_norm": 3.900786876678467, "learning_rate": 3.991553569691406e-05, "loss": 1.3417, "step": 1058 }, { "epoch": 0.05848243870112657, "grad_norm": 3.946230888366699, "learning_rate": 3.9915206954988316e-05, "loss": 0.5972, "step": 1059 }, { "epoch": 0.05853766291142037, "grad_norm": 0.3104817569255829, "learning_rate": 3.991487757591841e-05, "loss": 0.0095, "step": 1060 }, { "epoch": 0.05859288712171416, "grad_norm": 4.369722366333008, "learning_rate": 3.991454755971487e-05, "loss": 1.6031, "step": 1061 }, { "epoch": 0.05864811133200795, "grad_norm": 3.6336610317230225, "learning_rate": 3.991421690638826e-05, "loss": 0.0973, "step": 1062 }, { "epoch": 0.05870333554230175, "grad_norm": 2.8792905807495117, "learning_rate": 3.991388561594916e-05, "loss": 0.6139, "step": 1063 }, { "epoch": 0.058758559752595536, "grad_norm": 3.3574376106262207, "learning_rate": 3.9913553688408174e-05, "loss": 0.2375, "step": 1064 }, { "epoch": 0.05881378396288933, "grad_norm": 0.12733930349349976, "learning_rate": 3.991322112377591e-05, "loss": 0.0041, "step": 1065 }, { "epoch": 0.05886900817318312, "grad_norm": 0.44360506534576416, "learning_rate": 3.9912887922063e-05, "loss": 0.0145, "step": 1066 }, { "epoch": 0.05892423238347692, "grad_norm": 4.642817497253418, "learning_rate": 3.9912554083280126e-05, "loss": 0.8562, "step": 1067 }, { "epoch": 0.058979456593770706, "grad_norm": 3.1252939701080322, "learning_rate": 3.9912219607437954e-05, "loss": 0.5514, "step": 1068 }, { "epoch": 0.0590346808040645, "grad_norm": 5.903061866760254, "learning_rate": 3.9911884494547196e-05, "loss": 1.7762, "step": 1069 }, { "epoch": 0.0590899050143583, "grad_norm": 0.7068168520927429, "learning_rate": 3.991154874461856e-05, "loss": 0.0138, "step": 1070 }, { "epoch": 0.059145129224652086, "grad_norm": 2.7558624744415283, "learning_rate": 3.99112123576628e-05, "loss": 0.443, "step": 1071 }, { "epoch": 0.05920035343494588, "grad_norm": 0.177461177110672, "learning_rate": 3.9910875333690665e-05, "loss": 0.005, "step": 1072 }, { "epoch": 0.05925557764523967, "grad_norm": 1.7146811485290527, "learning_rate": 3.991053767271295e-05, "loss": 0.1827, "step": 1073 }, { "epoch": 0.05931080185553347, "grad_norm": 1.192099928855896, "learning_rate": 3.991019937474045e-05, "loss": 0.0293, "step": 1074 }, { "epoch": 0.059366026065827256, "grad_norm": 1.591260313987732, "learning_rate": 3.9909860439783985e-05, "loss": 0.0698, "step": 1075 }, { "epoch": 0.05942125027612105, "grad_norm": 0.05363635718822479, "learning_rate": 3.9909520867854416e-05, "loss": 0.0014, "step": 1076 }, { "epoch": 0.05947647448641485, "grad_norm": 0.20470580458641052, "learning_rate": 3.990918065896258e-05, "loss": 0.0051, "step": 1077 }, { "epoch": 0.059531698696708636, "grad_norm": 1.2962511777877808, "learning_rate": 3.990883981311939e-05, "loss": 0.0363, "step": 1078 }, { "epoch": 0.05958692290700243, "grad_norm": 4.715026378631592, "learning_rate": 3.990849833033573e-05, "loss": 0.6268, "step": 1079 }, { "epoch": 0.05964214711729622, "grad_norm": 2.370182514190674, "learning_rate": 3.9908156210622526e-05, "loss": 0.1681, "step": 1080 }, { "epoch": 0.05969737132759002, "grad_norm": 1.7625969648361206, "learning_rate": 3.9907813453990734e-05, "loss": 0.0168, "step": 1081 }, { "epoch": 0.059752595537883806, "grad_norm": 4.524224758148193, "learning_rate": 3.990747006045131e-05, "loss": 0.6971, "step": 1082 }, { "epoch": 0.0598078197481776, "grad_norm": 1.5874170064926147, "learning_rate": 3.990712603001525e-05, "loss": 0.0903, "step": 1083 }, { "epoch": 0.0598630439584714, "grad_norm": 2.299295663833618, "learning_rate": 3.9906781362693555e-05, "loss": 0.2883, "step": 1084 }, { "epoch": 0.059918268168765186, "grad_norm": 1.0181854963302612, "learning_rate": 3.9906436058497254e-05, "loss": 0.007, "step": 1085 }, { "epoch": 0.05997349237905898, "grad_norm": 4.607043743133545, "learning_rate": 3.990609011743739e-05, "loss": 0.7989, "step": 1086 }, { "epoch": 0.06002871658935277, "grad_norm": 0.828240156173706, "learning_rate": 3.9905743539525026e-05, "loss": 0.0151, "step": 1087 }, { "epoch": 0.06008394079964657, "grad_norm": 0.22552527487277985, "learning_rate": 3.990539632477127e-05, "loss": 0.0043, "step": 1088 }, { "epoch": 0.060139165009940355, "grad_norm": 5.972438812255859, "learning_rate": 3.990504847318721e-05, "loss": 0.5199, "step": 1089 }, { "epoch": 0.06019438922023415, "grad_norm": 2.14081072807312, "learning_rate": 3.990469998478398e-05, "loss": 0.1085, "step": 1090 }, { "epoch": 0.06024961343052794, "grad_norm": 4.556530475616455, "learning_rate": 3.9904350859572735e-05, "loss": 1.1233, "step": 1091 }, { "epoch": 0.060304837640821736, "grad_norm": 6.465964317321777, "learning_rate": 3.990400109756464e-05, "loss": 0.4622, "step": 1092 }, { "epoch": 0.06036006185111553, "grad_norm": 3.034860610961914, "learning_rate": 3.990365069877089e-05, "loss": 0.7735, "step": 1093 }, { "epoch": 0.06041528606140932, "grad_norm": 2.753777027130127, "learning_rate": 3.9903299663202686e-05, "loss": 0.2769, "step": 1094 }, { "epoch": 0.060470510271703116, "grad_norm": 0.13979676365852356, "learning_rate": 3.990294799087127e-05, "loss": 0.0044, "step": 1095 }, { "epoch": 0.060525734481996905, "grad_norm": 1.4803653955459595, "learning_rate": 3.990259568178788e-05, "loss": 0.0483, "step": 1096 }, { "epoch": 0.0605809586922907, "grad_norm": 5.653712749481201, "learning_rate": 3.9902242735963794e-05, "loss": 1.2737, "step": 1097 }, { "epoch": 0.06063618290258449, "grad_norm": 2.7890520095825195, "learning_rate": 3.99018891534103e-05, "loss": 1.0777, "step": 1098 }, { "epoch": 0.060691407112878286, "grad_norm": 4.003922462463379, "learning_rate": 3.990153493413872e-05, "loss": 0.0986, "step": 1099 }, { "epoch": 0.06074663132317208, "grad_norm": 0.09029761701822281, "learning_rate": 3.990118007816038e-05, "loss": 0.0022, "step": 1100 }, { "epoch": 0.06080185553346587, "grad_norm": 1.0966061353683472, "learning_rate": 3.990082458548664e-05, "loss": 0.0369, "step": 1101 }, { "epoch": 0.060857079743759666, "grad_norm": 0.14572134613990784, "learning_rate": 3.9900468456128856e-05, "loss": 0.0036, "step": 1102 }, { "epoch": 0.060912303954053455, "grad_norm": 0.7457638382911682, "learning_rate": 3.990011169009843e-05, "loss": 0.0175, "step": 1103 }, { "epoch": 0.06096752816434725, "grad_norm": 0.3012082874774933, "learning_rate": 3.9899754287406784e-05, "loss": 0.0102, "step": 1104 }, { "epoch": 0.06102275237464104, "grad_norm": 4.373849391937256, "learning_rate": 3.9899396248065344e-05, "loss": 0.6235, "step": 1105 }, { "epoch": 0.061077976584934836, "grad_norm": 0.37671002745628357, "learning_rate": 3.9899037572085565e-05, "loss": 0.0075, "step": 1106 }, { "epoch": 0.06113320079522863, "grad_norm": 3.669910430908203, "learning_rate": 3.9898678259478926e-05, "loss": 0.2252, "step": 1107 }, { "epoch": 0.06118842500552242, "grad_norm": 4.2530975341796875, "learning_rate": 3.989831831025692e-05, "loss": 0.7466, "step": 1108 }, { "epoch": 0.061243649215816216, "grad_norm": 0.13201546669006348, "learning_rate": 3.9897957724431066e-05, "loss": 0.0044, "step": 1109 }, { "epoch": 0.061298873426110005, "grad_norm": 3.896620035171509, "learning_rate": 3.98975965020129e-05, "loss": 0.5068, "step": 1110 }, { "epoch": 0.0613540976364038, "grad_norm": 0.3916216194629669, "learning_rate": 3.989723464301397e-05, "loss": 0.0075, "step": 1111 }, { "epoch": 0.06140932184669759, "grad_norm": 2.0911478996276855, "learning_rate": 3.989687214744586e-05, "loss": 0.2922, "step": 1112 }, { "epoch": 0.061464546056991386, "grad_norm": 0.19486312568187714, "learning_rate": 3.989650901532017e-05, "loss": 0.0049, "step": 1113 }, { "epoch": 0.061519770267285175, "grad_norm": 1.1755684614181519, "learning_rate": 3.989614524664851e-05, "loss": 0.0308, "step": 1114 }, { "epoch": 0.06157499447757897, "grad_norm": 2.9870996475219727, "learning_rate": 3.989578084144252e-05, "loss": 0.7803, "step": 1115 }, { "epoch": 0.061630218687872766, "grad_norm": 2.1599795818328857, "learning_rate": 3.989541579971386e-05, "loss": 0.1233, "step": 1116 }, { "epoch": 0.061685442898166555, "grad_norm": 0.09050968289375305, "learning_rate": 3.9895050121474215e-05, "loss": 0.0035, "step": 1117 }, { "epoch": 0.06174066710846035, "grad_norm": 4.077508449554443, "learning_rate": 3.989468380673527e-05, "loss": 0.5007, "step": 1118 }, { "epoch": 0.06179589131875414, "grad_norm": 3.756500005722046, "learning_rate": 3.989431685550876e-05, "loss": 0.5676, "step": 1119 }, { "epoch": 0.061851115529047936, "grad_norm": 0.22523707151412964, "learning_rate": 3.9893949267806415e-05, "loss": 0.0066, "step": 1120 }, { "epoch": 0.061906339739341724, "grad_norm": 0.0682818666100502, "learning_rate": 3.989358104363999e-05, "loss": 0.0028, "step": 1121 }, { "epoch": 0.06196156394963552, "grad_norm": 1.8223505020141602, "learning_rate": 3.989321218302128e-05, "loss": 0.0462, "step": 1122 }, { "epoch": 0.062016788159929316, "grad_norm": 0.6971144080162048, "learning_rate": 3.9892842685962084e-05, "loss": 0.0265, "step": 1123 }, { "epoch": 0.062072012370223105, "grad_norm": 0.6629753708839417, "learning_rate": 3.9892472552474205e-05, "loss": 0.026, "step": 1124 }, { "epoch": 0.0621272365805169, "grad_norm": 0.5829541087150574, "learning_rate": 3.9892101782569505e-05, "loss": 0.0262, "step": 1125 }, { "epoch": 0.06218246079081069, "grad_norm": 3.2763609886169434, "learning_rate": 3.989173037625984e-05, "loss": 0.4112, "step": 1126 }, { "epoch": 0.062237685001104485, "grad_norm": 3.327906608581543, "learning_rate": 3.989135833355709e-05, "loss": 0.4088, "step": 1127 }, { "epoch": 0.062292909211398274, "grad_norm": 0.14020609855651855, "learning_rate": 3.989098565447316e-05, "loss": 0.0043, "step": 1128 }, { "epoch": 0.06234813342169207, "grad_norm": 1.786937952041626, "learning_rate": 3.989061233901997e-05, "loss": 0.0576, "step": 1129 }, { "epoch": 0.062403357631985866, "grad_norm": 2.150486946105957, "learning_rate": 3.989023838720946e-05, "loss": 0.2965, "step": 1130 }, { "epoch": 0.062458581842279655, "grad_norm": 0.8478527069091797, "learning_rate": 3.9889863799053604e-05, "loss": 0.0217, "step": 1131 }, { "epoch": 0.06251380605257345, "grad_norm": 1.3163045644760132, "learning_rate": 3.988948857456438e-05, "loss": 0.0786, "step": 1132 }, { "epoch": 0.06256903026286724, "grad_norm": 3.388608455657959, "learning_rate": 3.9889112713753794e-05, "loss": 0.2344, "step": 1133 }, { "epoch": 0.06262425447316103, "grad_norm": 4.518100738525391, "learning_rate": 3.9888736216633875e-05, "loss": 0.798, "step": 1134 }, { "epoch": 0.06267947868345483, "grad_norm": 1.872055172920227, "learning_rate": 3.988835908321666e-05, "loss": 0.1535, "step": 1135 }, { "epoch": 0.06273470289374862, "grad_norm": 1.916717290878296, "learning_rate": 3.988798131351422e-05, "loss": 0.0146, "step": 1136 }, { "epoch": 0.06278992710404241, "grad_norm": 4.06143045425415, "learning_rate": 3.988760290753864e-05, "loss": 0.4193, "step": 1137 }, { "epoch": 0.06284515131433621, "grad_norm": 2.7788455486297607, "learning_rate": 3.988722386530202e-05, "loss": 0.1596, "step": 1138 }, { "epoch": 0.06290037552463, "grad_norm": 0.8343958854675293, "learning_rate": 3.988684418681649e-05, "loss": 0.0142, "step": 1139 }, { "epoch": 0.06295559973492379, "grad_norm": 0.1043207049369812, "learning_rate": 3.98864638720942e-05, "loss": 0.0034, "step": 1140 }, { "epoch": 0.06301082394521758, "grad_norm": 2.022364616394043, "learning_rate": 3.988608292114733e-05, "loss": 0.0583, "step": 1141 }, { "epoch": 0.06306604815551138, "grad_norm": 2.0741002559661865, "learning_rate": 3.9885701333988045e-05, "loss": 0.1607, "step": 1142 }, { "epoch": 0.06312127236580517, "grad_norm": 1.6325653791427612, "learning_rate": 3.9885319110628555e-05, "loss": 0.0339, "step": 1143 }, { "epoch": 0.06317649657609896, "grad_norm": 0.11073146760463715, "learning_rate": 3.9884936251081104e-05, "loss": 0.0027, "step": 1144 }, { "epoch": 0.06323172078639275, "grad_norm": 0.17533838748931885, "learning_rate": 3.988455275535794e-05, "loss": 0.0055, "step": 1145 }, { "epoch": 0.06328694499668655, "grad_norm": 3.9269258975982666, "learning_rate": 3.9884168623471306e-05, "loss": 1.1991, "step": 1146 }, { "epoch": 0.06334216920698034, "grad_norm": 4.887935638427734, "learning_rate": 3.988378385543352e-05, "loss": 0.872, "step": 1147 }, { "epoch": 0.06339739341727413, "grad_norm": 1.6917099952697754, "learning_rate": 3.988339845125689e-05, "loss": 0.0567, "step": 1148 }, { "epoch": 0.06345261762756793, "grad_norm": 3.491633653640747, "learning_rate": 3.9883012410953725e-05, "loss": 0.4926, "step": 1149 }, { "epoch": 0.06350784183786172, "grad_norm": 3.538761854171753, "learning_rate": 3.988262573453639e-05, "loss": 0.7888, "step": 1150 }, { "epoch": 0.06356306604815551, "grad_norm": 4.151082992553711, "learning_rate": 3.988223842201726e-05, "loss": 0.361, "step": 1151 }, { "epoch": 0.0636182902584493, "grad_norm": 2.734548568725586, "learning_rate": 3.988185047340872e-05, "loss": 0.2298, "step": 1152 }, { "epoch": 0.0636735144687431, "grad_norm": 5.1301188468933105, "learning_rate": 3.988146188872318e-05, "loss": 0.6967, "step": 1153 }, { "epoch": 0.06372873867903689, "grad_norm": 2.4511289596557617, "learning_rate": 3.988107266797307e-05, "loss": 0.4256, "step": 1154 }, { "epoch": 0.06378396288933068, "grad_norm": 2.1803247928619385, "learning_rate": 3.9880682811170856e-05, "loss": 0.5005, "step": 1155 }, { "epoch": 0.06383918709962448, "grad_norm": 0.3087855279445648, "learning_rate": 3.9880292318329e-05, "loss": 0.0117, "step": 1156 }, { "epoch": 0.06389441130991827, "grad_norm": 0.06320586055517197, "learning_rate": 3.987990118945999e-05, "loss": 0.0015, "step": 1157 }, { "epoch": 0.06394963552021206, "grad_norm": 1.6846082210540771, "learning_rate": 3.9879509424576343e-05, "loss": 0.0621, "step": 1158 }, { "epoch": 0.06400485973050585, "grad_norm": 0.7336466312408447, "learning_rate": 3.98791170236906e-05, "loss": 0.1047, "step": 1159 }, { "epoch": 0.06406008394079965, "grad_norm": 0.2667078673839569, "learning_rate": 3.987872398681531e-05, "loss": 0.0058, "step": 1160 }, { "epoch": 0.06411530815109344, "grad_norm": 4.812572002410889, "learning_rate": 3.9878330313963044e-05, "loss": 0.7618, "step": 1161 }, { "epoch": 0.06417053236138723, "grad_norm": 3.5454201698303223, "learning_rate": 3.987793600514641e-05, "loss": 0.2923, "step": 1162 }, { "epoch": 0.06422575657168103, "grad_norm": 2.8407442569732666, "learning_rate": 3.9877541060378004e-05, "loss": 1.1817, "step": 1163 }, { "epoch": 0.06428098078197482, "grad_norm": 0.17105761170387268, "learning_rate": 3.987714547967048e-05, "loss": 0.0034, "step": 1164 }, { "epoch": 0.06433620499226861, "grad_norm": 0.2658592760562897, "learning_rate": 3.987674926303647e-05, "loss": 0.0071, "step": 1165 }, { "epoch": 0.0643914292025624, "grad_norm": 0.07906611263751984, "learning_rate": 3.987635241048867e-05, "loss": 0.0025, "step": 1166 }, { "epoch": 0.0644466534128562, "grad_norm": 7.043942451477051, "learning_rate": 3.987595492203978e-05, "loss": 0.2572, "step": 1167 }, { "epoch": 0.06450187762314999, "grad_norm": 0.22865255177021027, "learning_rate": 3.9875556797702495e-05, "loss": 0.0071, "step": 1168 }, { "epoch": 0.06455710183344378, "grad_norm": 3.979989528656006, "learning_rate": 3.987515803748957e-05, "loss": 1.1323, "step": 1169 }, { "epoch": 0.06461232604373758, "grad_norm": 0.24101200699806213, "learning_rate": 3.987475864141376e-05, "loss": 0.0041, "step": 1170 }, { "epoch": 0.06466755025403137, "grad_norm": 3.037844181060791, "learning_rate": 3.987435860948784e-05, "loss": 0.8994, "step": 1171 }, { "epoch": 0.06472277446432516, "grad_norm": 5.313023567199707, "learning_rate": 3.9873957941724604e-05, "loss": 1.062, "step": 1172 }, { "epoch": 0.06477799867461895, "grad_norm": 4.9598541259765625, "learning_rate": 3.987355663813688e-05, "loss": 0.327, "step": 1173 }, { "epoch": 0.06483322288491275, "grad_norm": 0.7488822340965271, "learning_rate": 3.98731546987375e-05, "loss": 0.0151, "step": 1174 }, { "epoch": 0.06488844709520654, "grad_norm": 0.643640398979187, "learning_rate": 3.987275212353932e-05, "loss": 0.0235, "step": 1175 }, { "epoch": 0.06494367130550033, "grad_norm": 0.12247393280267715, "learning_rate": 3.987234891255523e-05, "loss": 0.0038, "step": 1176 }, { "epoch": 0.06499889551579413, "grad_norm": 2.634155035018921, "learning_rate": 3.987194506579812e-05, "loss": 0.3243, "step": 1177 }, { "epoch": 0.06505411972608792, "grad_norm": 2.519629955291748, "learning_rate": 3.9871540583280916e-05, "loss": 0.4976, "step": 1178 }, { "epoch": 0.06510934393638171, "grad_norm": 2.761286497116089, "learning_rate": 3.9871135465016556e-05, "loss": 0.3437, "step": 1179 }, { "epoch": 0.0651645681466755, "grad_norm": 1.3637665510177612, "learning_rate": 3.9870729711018006e-05, "loss": 0.036, "step": 1180 }, { "epoch": 0.0652197923569693, "grad_norm": 0.7762202620506287, "learning_rate": 3.987032332129824e-05, "loss": 0.0367, "step": 1181 }, { "epoch": 0.06527501656726309, "grad_norm": 0.32349029183387756, "learning_rate": 3.986991629587026e-05, "loss": 0.0109, "step": 1182 }, { "epoch": 0.06533024077755688, "grad_norm": 3.4066824913024902, "learning_rate": 3.9869508634747094e-05, "loss": 0.5899, "step": 1183 }, { "epoch": 0.06538546498785068, "grad_norm": 1.5491796731948853, "learning_rate": 3.9869100337941786e-05, "loss": 0.0771, "step": 1184 }, { "epoch": 0.06544068919814447, "grad_norm": 3.6334660053253174, "learning_rate": 3.986869140546738e-05, "loss": 0.2395, "step": 1185 }, { "epoch": 0.06549591340843826, "grad_norm": 0.21484199166297913, "learning_rate": 3.986828183733698e-05, "loss": 0.007, "step": 1186 }, { "epoch": 0.06555113761873205, "grad_norm": 3.397306203842163, "learning_rate": 3.986787163356368e-05, "loss": 0.3119, "step": 1187 }, { "epoch": 0.06560636182902585, "grad_norm": 0.8817563652992249, "learning_rate": 3.986746079416061e-05, "loss": 0.02, "step": 1188 }, { "epoch": 0.06566158603931964, "grad_norm": 0.13686132431030273, "learning_rate": 3.986704931914091e-05, "loss": 0.0038, "step": 1189 }, { "epoch": 0.06571681024961343, "grad_norm": 3.2118356227874756, "learning_rate": 3.9866637208517736e-05, "loss": 0.4433, "step": 1190 }, { "epoch": 0.06577203445990722, "grad_norm": 0.24584996700286865, "learning_rate": 3.986622446230429e-05, "loss": 0.0079, "step": 1191 }, { "epoch": 0.06582725867020102, "grad_norm": 0.3169926702976227, "learning_rate": 3.986581108051375e-05, "loss": 0.0078, "step": 1192 }, { "epoch": 0.06588248288049481, "grad_norm": 0.9067599773406982, "learning_rate": 3.9865397063159376e-05, "loss": 0.0341, "step": 1193 }, { "epoch": 0.0659377070907886, "grad_norm": 0.15471704304218292, "learning_rate": 3.986498241025438e-05, "loss": 0.0033, "step": 1194 }, { "epoch": 0.0659929313010824, "grad_norm": 0.22214345633983612, "learning_rate": 3.986456712181205e-05, "loss": 0.0062, "step": 1195 }, { "epoch": 0.06604815551137619, "grad_norm": 5.384189128875732, "learning_rate": 3.986415119784567e-05, "loss": 0.7171, "step": 1196 }, { "epoch": 0.06610337972166998, "grad_norm": 0.4011514186859131, "learning_rate": 3.986373463836854e-05, "loss": 0.0118, "step": 1197 }, { "epoch": 0.06615860393196377, "grad_norm": 3.7271828651428223, "learning_rate": 3.9863317443393994e-05, "loss": 0.8215, "step": 1198 }, { "epoch": 0.06621382814225757, "grad_norm": 4.607470512390137, "learning_rate": 3.9862899612935366e-05, "loss": 0.4675, "step": 1199 }, { "epoch": 0.06626905235255136, "grad_norm": 1.2677836418151855, "learning_rate": 3.986248114700603e-05, "loss": 0.0532, "step": 1200 }, { "epoch": 0.06632427656284515, "grad_norm": 3.415229320526123, "learning_rate": 3.986206204561939e-05, "loss": 1.1526, "step": 1201 }, { "epoch": 0.06637950077313895, "grad_norm": 0.19633857905864716, "learning_rate": 3.986164230878883e-05, "loss": 0.0038, "step": 1202 }, { "epoch": 0.06643472498343274, "grad_norm": 2.605668306350708, "learning_rate": 3.986122193652779e-05, "loss": 0.4121, "step": 1203 }, { "epoch": 0.06648994919372653, "grad_norm": 0.4450037479400635, "learning_rate": 3.986080092884972e-05, "loss": 0.0117, "step": 1204 }, { "epoch": 0.06654517340402032, "grad_norm": 5.197742938995361, "learning_rate": 3.9860379285768084e-05, "loss": 1.5655, "step": 1205 }, { "epoch": 0.06660039761431412, "grad_norm": 1.021962285041809, "learning_rate": 3.985995700729638e-05, "loss": 0.0462, "step": 1206 }, { "epoch": 0.06665562182460791, "grad_norm": 0.32968902587890625, "learning_rate": 3.985953409344811e-05, "loss": 0.0134, "step": 1207 }, { "epoch": 0.0667108460349017, "grad_norm": 3.910064935684204, "learning_rate": 3.98591105442368e-05, "loss": 1.2073, "step": 1208 }, { "epoch": 0.0667660702451955, "grad_norm": 1.9442204236984253, "learning_rate": 3.9858686359676014e-05, "loss": 0.0732, "step": 1209 }, { "epoch": 0.06682129445548929, "grad_norm": 3.411043882369995, "learning_rate": 3.985826153977931e-05, "loss": 0.2162, "step": 1210 }, { "epoch": 0.06687651866578308, "grad_norm": 4.8491902351379395, "learning_rate": 3.98578360845603e-05, "loss": 1.0041, "step": 1211 }, { "epoch": 0.06693174287607687, "grad_norm": 0.21873323619365692, "learning_rate": 3.9857409994032575e-05, "loss": 0.0056, "step": 1212 }, { "epoch": 0.06698696708637067, "grad_norm": 2.0725440979003906, "learning_rate": 3.985698326820976e-05, "loss": 0.0999, "step": 1213 }, { "epoch": 0.06704219129666446, "grad_norm": 2.0019006729125977, "learning_rate": 3.985655590710553e-05, "loss": 0.1681, "step": 1214 }, { "epoch": 0.06709741550695825, "grad_norm": 0.9518677592277527, "learning_rate": 3.985612791073355e-05, "loss": 0.0424, "step": 1215 }, { "epoch": 0.06715263971725205, "grad_norm": 2.6068761348724365, "learning_rate": 3.985569927910751e-05, "loss": 0.0498, "step": 1216 }, { "epoch": 0.06720786392754584, "grad_norm": 2.134632110595703, "learning_rate": 3.985527001224112e-05, "loss": 0.109, "step": 1217 }, { "epoch": 0.06726308813783963, "grad_norm": 4.5192766189575195, "learning_rate": 3.9854840110148116e-05, "loss": 0.438, "step": 1218 }, { "epoch": 0.06731831234813342, "grad_norm": 1.928462028503418, "learning_rate": 3.985440957284225e-05, "loss": 0.0344, "step": 1219 }, { "epoch": 0.06737353655842722, "grad_norm": 3.1170220375061035, "learning_rate": 3.985397840033731e-05, "loss": 0.3988, "step": 1220 }, { "epoch": 0.06742876076872101, "grad_norm": 5.347994804382324, "learning_rate": 3.985354659264707e-05, "loss": 0.4977, "step": 1221 }, { "epoch": 0.0674839849790148, "grad_norm": 0.925474226474762, "learning_rate": 3.9853114149785354e-05, "loss": 0.0447, "step": 1222 }, { "epoch": 0.0675392091893086, "grad_norm": 3.3194849491119385, "learning_rate": 3.9852681071766e-05, "loss": 0.3654, "step": 1223 }, { "epoch": 0.06759443339960239, "grad_norm": 3.8768417835235596, "learning_rate": 3.985224735860286e-05, "loss": 0.7205, "step": 1224 }, { "epoch": 0.06764965760989618, "grad_norm": 4.197778701782227, "learning_rate": 3.9851813010309806e-05, "loss": 0.577, "step": 1225 }, { "epoch": 0.06770488182018997, "grad_norm": 0.21007785201072693, "learning_rate": 3.9851378026900746e-05, "loss": 0.0102, "step": 1226 }, { "epoch": 0.06776010603048377, "grad_norm": 0.40165603160858154, "learning_rate": 3.985094240838958e-05, "loss": 0.0155, "step": 1227 }, { "epoch": 0.06781533024077756, "grad_norm": 2.286241054534912, "learning_rate": 3.985050615479026e-05, "loss": 0.0721, "step": 1228 }, { "epoch": 0.06787055445107135, "grad_norm": 3.9950547218322754, "learning_rate": 3.9850069266116734e-05, "loss": 0.1802, "step": 1229 }, { "epoch": 0.06792577866136515, "grad_norm": 3.688547372817993, "learning_rate": 3.9849631742382986e-05, "loss": 0.3305, "step": 1230 }, { "epoch": 0.06798100287165894, "grad_norm": 8.421310424804688, "learning_rate": 3.9849193583603e-05, "loss": 0.2327, "step": 1231 }, { "epoch": 0.06803622708195273, "grad_norm": 2.1866252422332764, "learning_rate": 3.984875478979081e-05, "loss": 0.1056, "step": 1232 }, { "epoch": 0.06809145129224652, "grad_norm": 4.148032188415527, "learning_rate": 3.984831536096044e-05, "loss": 0.2128, "step": 1233 }, { "epoch": 0.06814667550254032, "grad_norm": 1.8702278137207031, "learning_rate": 3.9847875297125965e-05, "loss": 0.2552, "step": 1234 }, { "epoch": 0.06820189971283411, "grad_norm": 0.721813976764679, "learning_rate": 3.984743459830145e-05, "loss": 0.0248, "step": 1235 }, { "epoch": 0.0682571239231279, "grad_norm": 3.7778329849243164, "learning_rate": 3.9846993264501e-05, "loss": 0.7402, "step": 1236 }, { "epoch": 0.06831234813342169, "grad_norm": 1.1902483701705933, "learning_rate": 3.984655129573873e-05, "loss": 0.0432, "step": 1237 }, { "epoch": 0.06836757234371549, "grad_norm": 3.6154303550720215, "learning_rate": 3.984610869202879e-05, "loss": 0.5212, "step": 1238 }, { "epoch": 0.06842279655400928, "grad_norm": 3.1933999061584473, "learning_rate": 3.984566545338533e-05, "loss": 0.3277, "step": 1239 }, { "epoch": 0.06847802076430307, "grad_norm": 3.2094368934631348, "learning_rate": 3.984522157982253e-05, "loss": 0.4912, "step": 1240 }, { "epoch": 0.06853324497459687, "grad_norm": 4.940793514251709, "learning_rate": 3.984477707135461e-05, "loss": 0.4409, "step": 1241 }, { "epoch": 0.06858846918489066, "grad_norm": 0.30530110001564026, "learning_rate": 3.984433192799576e-05, "loss": 0.0103, "step": 1242 }, { "epoch": 0.06864369339518445, "grad_norm": 0.6371400356292725, "learning_rate": 3.9843886149760245e-05, "loss": 0.0214, "step": 1243 }, { "epoch": 0.06869891760547824, "grad_norm": 3.7309844493865967, "learning_rate": 3.984343973666232e-05, "loss": 0.4736, "step": 1244 }, { "epoch": 0.06875414181577204, "grad_norm": 1.1870375871658325, "learning_rate": 3.984299268871626e-05, "loss": 0.0306, "step": 1245 }, { "epoch": 0.06880936602606583, "grad_norm": 3.4694437980651855, "learning_rate": 3.984254500593637e-05, "loss": 0.2876, "step": 1246 }, { "epoch": 0.06886459023635962, "grad_norm": 0.6025034785270691, "learning_rate": 3.9842096688336986e-05, "loss": 0.0237, "step": 1247 }, { "epoch": 0.06891981444665342, "grad_norm": 1.0150201320648193, "learning_rate": 3.984164773593244e-05, "loss": 0.0255, "step": 1248 }, { "epoch": 0.06897503865694721, "grad_norm": 2.007266044616699, "learning_rate": 3.984119814873709e-05, "loss": 0.2464, "step": 1249 }, { "epoch": 0.069030262867241, "grad_norm": 2.715656042098999, "learning_rate": 3.9840747926765326e-05, "loss": 0.2638, "step": 1250 }, { "epoch": 0.06908548707753479, "grad_norm": 0.2319595366716385, "learning_rate": 3.9840297070031556e-05, "loss": 0.0071, "step": 1251 }, { "epoch": 0.06914071128782859, "grad_norm": 4.414709091186523, "learning_rate": 3.9839845578550195e-05, "loss": 1.1966, "step": 1252 }, { "epoch": 0.06919593549812238, "grad_norm": 1.4210718870162964, "learning_rate": 3.98393934523357e-05, "loss": 0.1475, "step": 1253 }, { "epoch": 0.06925115970841617, "grad_norm": 4.364850997924805, "learning_rate": 3.983894069140252e-05, "loss": 0.5628, "step": 1254 }, { "epoch": 0.06930638391870997, "grad_norm": 2.653671979904175, "learning_rate": 3.983848729576516e-05, "loss": 0.9787, "step": 1255 }, { "epoch": 0.06936160812900376, "grad_norm": 5.776923656463623, "learning_rate": 3.983803326543811e-05, "loss": 0.9962, "step": 1256 }, { "epoch": 0.06941683233929755, "grad_norm": 0.7896462678909302, "learning_rate": 3.983757860043589e-05, "loss": 0.0299, "step": 1257 }, { "epoch": 0.06947205654959134, "grad_norm": 0.9246507287025452, "learning_rate": 3.983712330077306e-05, "loss": 0.0144, "step": 1258 }, { "epoch": 0.06952728075988514, "grad_norm": 3.173081636428833, "learning_rate": 3.9836667366464184e-05, "loss": 0.506, "step": 1259 }, { "epoch": 0.06958250497017893, "grad_norm": 0.02994207851588726, "learning_rate": 3.983621079752385e-05, "loss": 0.0012, "step": 1260 }, { "epoch": 0.06963772918047272, "grad_norm": 5.195211410522461, "learning_rate": 3.9835753593966656e-05, "loss": 1.7179, "step": 1261 }, { "epoch": 0.06969295339076652, "grad_norm": 0.32529518008232117, "learning_rate": 3.9835295755807235e-05, "loss": 0.0098, "step": 1262 }, { "epoch": 0.06974817760106031, "grad_norm": 3.5698156356811523, "learning_rate": 3.983483728306023e-05, "loss": 0.3427, "step": 1263 }, { "epoch": 0.0698034018113541, "grad_norm": 0.07506479322910309, "learning_rate": 3.983437817574032e-05, "loss": 0.0016, "step": 1264 }, { "epoch": 0.06985862602164788, "grad_norm": 0.08993864804506302, "learning_rate": 3.983391843386219e-05, "loss": 0.0023, "step": 1265 }, { "epoch": 0.06991385023194169, "grad_norm": 6.333981037139893, "learning_rate": 3.983345805744053e-05, "loss": 1.363, "step": 1266 }, { "epoch": 0.06996907444223548, "grad_norm": 0.09327961504459381, "learning_rate": 3.9832997046490096e-05, "loss": 0.0028, "step": 1267 }, { "epoch": 0.07002429865252927, "grad_norm": 3.2468416690826416, "learning_rate": 3.9832535401025625e-05, "loss": 0.4039, "step": 1268 }, { "epoch": 0.07007952286282307, "grad_norm": 4.996281623840332, "learning_rate": 3.983207312106187e-05, "loss": 0.1497, "step": 1269 }, { "epoch": 0.07013474707311686, "grad_norm": 0.09988682717084885, "learning_rate": 3.983161020661365e-05, "loss": 0.0024, "step": 1270 }, { "epoch": 0.07018997128341065, "grad_norm": 3.2678427696228027, "learning_rate": 3.9831146657695765e-05, "loss": 0.8204, "step": 1271 }, { "epoch": 0.07024519549370443, "grad_norm": 0.12776033580303192, "learning_rate": 3.9830682474323037e-05, "loss": 0.0044, "step": 1272 }, { "epoch": 0.07030041970399824, "grad_norm": 3.409123659133911, "learning_rate": 3.983021765651032e-05, "loss": 0.1983, "step": 1273 }, { "epoch": 0.07035564391429203, "grad_norm": 0.8901656866073608, "learning_rate": 3.982975220427249e-05, "loss": 0.0535, "step": 1274 }, { "epoch": 0.07041086812458582, "grad_norm": 3.4862217903137207, "learning_rate": 3.9829286117624426e-05, "loss": 0.1547, "step": 1275 }, { "epoch": 0.07046609233487962, "grad_norm": 3.3477063179016113, "learning_rate": 3.9828819396581055e-05, "loss": 0.7503, "step": 1276 }, { "epoch": 0.07052131654517341, "grad_norm": 1.7750130891799927, "learning_rate": 3.98283520411573e-05, "loss": 0.1892, "step": 1277 }, { "epoch": 0.0705765407554672, "grad_norm": 2.6144754886627197, "learning_rate": 3.982788405136811e-05, "loss": 0.2052, "step": 1278 }, { "epoch": 0.07063176496576098, "grad_norm": 3.85229754447937, "learning_rate": 3.982741542722846e-05, "loss": 0.798, "step": 1279 }, { "epoch": 0.07068698917605479, "grad_norm": 0.5790649056434631, "learning_rate": 3.982694616875335e-05, "loss": 0.0205, "step": 1280 }, { "epoch": 0.07074221338634858, "grad_norm": 0.33653250336647034, "learning_rate": 3.982647627595779e-05, "loss": 0.0116, "step": 1281 }, { "epoch": 0.07079743759664237, "grad_norm": 1.6758774518966675, "learning_rate": 3.98260057488568e-05, "loss": 0.0929, "step": 1282 }, { "epoch": 0.07085266180693615, "grad_norm": 2.2789242267608643, "learning_rate": 3.9825534587465453e-05, "loss": 0.1744, "step": 1283 }, { "epoch": 0.07090788601722996, "grad_norm": 2.2662692070007324, "learning_rate": 3.982506279179881e-05, "loss": 0.2496, "step": 1284 }, { "epoch": 0.07096311022752375, "grad_norm": 0.6191771030426025, "learning_rate": 3.982459036187197e-05, "loss": 0.0196, "step": 1285 }, { "epoch": 0.07101833443781753, "grad_norm": 3.5989956855773926, "learning_rate": 3.9824117297700046e-05, "loss": 0.7075, "step": 1286 }, { "epoch": 0.07107355864811134, "grad_norm": 0.08817692846059799, "learning_rate": 3.982364359929817e-05, "loss": 0.0028, "step": 1287 }, { "epoch": 0.07112878285840513, "grad_norm": 4.234983444213867, "learning_rate": 3.982316926668151e-05, "loss": 0.6163, "step": 1288 }, { "epoch": 0.07118400706869892, "grad_norm": 4.220340728759766, "learning_rate": 3.9822694299865226e-05, "loss": 0.8706, "step": 1289 }, { "epoch": 0.0712392312789927, "grad_norm": 5.1168742179870605, "learning_rate": 3.982221869886451e-05, "loss": 0.6778, "step": 1290 }, { "epoch": 0.0712944554892865, "grad_norm": 2.030020236968994, "learning_rate": 3.98217424636946e-05, "loss": 0.1153, "step": 1291 }, { "epoch": 0.0713496796995803, "grad_norm": 3.886523723602295, "learning_rate": 3.982126559437071e-05, "loss": 0.3829, "step": 1292 }, { "epoch": 0.07140490390987408, "grad_norm": 4.336799621582031, "learning_rate": 3.9820788090908106e-05, "loss": 0.5259, "step": 1293 }, { "epoch": 0.07146012812016789, "grad_norm": 0.3191574215888977, "learning_rate": 3.9820309953322064e-05, "loss": 0.0122, "step": 1294 }, { "epoch": 0.07151535233046168, "grad_norm": 1.6039706468582153, "learning_rate": 3.981983118162788e-05, "loss": 0.061, "step": 1295 }, { "epoch": 0.07157057654075547, "grad_norm": 3.338435649871826, "learning_rate": 3.981935177584087e-05, "loss": 1.0487, "step": 1296 }, { "epoch": 0.07162580075104925, "grad_norm": 3.8176016807556152, "learning_rate": 3.9818871735976384e-05, "loss": 0.2865, "step": 1297 }, { "epoch": 0.07168102496134306, "grad_norm": 5.391349792480469, "learning_rate": 3.981839106204976e-05, "loss": 1.3128, "step": 1298 }, { "epoch": 0.07173624917163685, "grad_norm": 2.6436002254486084, "learning_rate": 3.981790975407639e-05, "loss": 0.121, "step": 1299 }, { "epoch": 0.07179147338193063, "grad_norm": 1.991057276725769, "learning_rate": 3.9817427812071666e-05, "loss": 0.1051, "step": 1300 }, { "epoch": 0.07184669759222444, "grad_norm": 3.6657562255859375, "learning_rate": 3.9816945236051004e-05, "loss": 0.5305, "step": 1301 }, { "epoch": 0.07190192180251823, "grad_norm": 2.614729404449463, "learning_rate": 3.981646202602985e-05, "loss": 0.3058, "step": 1302 }, { "epoch": 0.07195714601281201, "grad_norm": 1.9739298820495605, "learning_rate": 3.9815978182023666e-05, "loss": 0.2758, "step": 1303 }, { "epoch": 0.0720123702231058, "grad_norm": 3.182425022125244, "learning_rate": 3.981549370404792e-05, "loss": 0.3516, "step": 1304 }, { "epoch": 0.0720675944333996, "grad_norm": 4.457700729370117, "learning_rate": 3.981500859211812e-05, "loss": 1.0624, "step": 1305 }, { "epoch": 0.0721228186436934, "grad_norm": 0.07829438894987106, "learning_rate": 3.9814522846249784e-05, "loss": 0.003, "step": 1306 }, { "epoch": 0.07217804285398718, "grad_norm": 1.1483160257339478, "learning_rate": 3.9814036466458456e-05, "loss": 0.0422, "step": 1307 }, { "epoch": 0.07223326706428099, "grad_norm": 2.0502636432647705, "learning_rate": 3.981354945275969e-05, "loss": 0.3045, "step": 1308 }, { "epoch": 0.07228849127457478, "grad_norm": 1.0386810302734375, "learning_rate": 3.9813061805169076e-05, "loss": 0.0321, "step": 1309 }, { "epoch": 0.07234371548486856, "grad_norm": 1.9316154718399048, "learning_rate": 3.98125735237022e-05, "loss": 0.0976, "step": 1310 }, { "epoch": 0.07239893969516235, "grad_norm": 3.626800775527954, "learning_rate": 3.981208460837471e-05, "loss": 0.2462, "step": 1311 }, { "epoch": 0.07245416390545616, "grad_norm": 2.8113949298858643, "learning_rate": 3.981159505920221e-05, "loss": 0.2555, "step": 1312 }, { "epoch": 0.07250938811574995, "grad_norm": 6.674103736877441, "learning_rate": 3.981110487620039e-05, "loss": 1.3856, "step": 1313 }, { "epoch": 0.07256461232604373, "grad_norm": 0.4879158139228821, "learning_rate": 3.981061405938493e-05, "loss": 0.0114, "step": 1314 }, { "epoch": 0.07261983653633754, "grad_norm": 0.3887441158294678, "learning_rate": 3.9810122608771524e-05, "loss": 0.0124, "step": 1315 }, { "epoch": 0.07267506074663133, "grad_norm": 1.0802942514419556, "learning_rate": 3.98096305243759e-05, "loss": 0.0471, "step": 1316 }, { "epoch": 0.07273028495692511, "grad_norm": 4.612740516662598, "learning_rate": 3.98091378062138e-05, "loss": 0.6756, "step": 1317 }, { "epoch": 0.0727855091672189, "grad_norm": 0.2017732411623001, "learning_rate": 3.980864445430099e-05, "loss": 0.0073, "step": 1318 }, { "epoch": 0.0728407333775127, "grad_norm": 0.2636902332305908, "learning_rate": 3.9808150468653246e-05, "loss": 0.0084, "step": 1319 }, { "epoch": 0.0728959575878065, "grad_norm": 2.8546338081359863, "learning_rate": 3.980765584928638e-05, "loss": 0.1626, "step": 1320 }, { "epoch": 0.07295118179810028, "grad_norm": 2.93522047996521, "learning_rate": 3.9807160596216217e-05, "loss": 0.8115, "step": 1321 }, { "epoch": 0.07300640600839409, "grad_norm": 5.382437705993652, "learning_rate": 3.980666470945859e-05, "loss": 0.6154, "step": 1322 }, { "epoch": 0.07306163021868788, "grad_norm": 1.6313397884368896, "learning_rate": 3.980616818902938e-05, "loss": 0.1598, "step": 1323 }, { "epoch": 0.07311685442898166, "grad_norm": 0.75703364610672, "learning_rate": 3.980567103494446e-05, "loss": 0.0927, "step": 1324 }, { "epoch": 0.07317207863927545, "grad_norm": 4.598731994628906, "learning_rate": 3.980517324721974e-05, "loss": 0.7971, "step": 1325 }, { "epoch": 0.07322730284956926, "grad_norm": 5.364561080932617, "learning_rate": 3.980467482587115e-05, "loss": 1.3168, "step": 1326 }, { "epoch": 0.07328252705986305, "grad_norm": 0.1607721745967865, "learning_rate": 3.980417577091462e-05, "loss": 0.0052, "step": 1327 }, { "epoch": 0.07333775127015683, "grad_norm": 2.8620378971099854, "learning_rate": 3.980367608236613e-05, "loss": 0.1828, "step": 1328 }, { "epoch": 0.07339297548045062, "grad_norm": 0.2983260452747345, "learning_rate": 3.9803175760241666e-05, "loss": 0.0109, "step": 1329 }, { "epoch": 0.07344819969074443, "grad_norm": 0.0897439643740654, "learning_rate": 3.980267480455723e-05, "loss": 0.0028, "step": 1330 }, { "epoch": 0.07350342390103821, "grad_norm": 0.32562255859375, "learning_rate": 3.9802173215328856e-05, "loss": 0.0073, "step": 1331 }, { "epoch": 0.073558648111332, "grad_norm": 5.0035481452941895, "learning_rate": 3.980167099257259e-05, "loss": 0.9767, "step": 1332 }, { "epoch": 0.0736138723216258, "grad_norm": 3.9133460521698, "learning_rate": 3.980116813630448e-05, "loss": 1.075, "step": 1333 }, { "epoch": 0.0736690965319196, "grad_norm": 4.327705383300781, "learning_rate": 3.980066464654065e-05, "loss": 0.6226, "step": 1334 }, { "epoch": 0.07372432074221338, "grad_norm": 3.4711267948150635, "learning_rate": 3.9800160523297174e-05, "loss": 0.5276, "step": 1335 }, { "epoch": 0.07377954495250717, "grad_norm": 4.263747692108154, "learning_rate": 3.97996557665902e-05, "loss": 0.8791, "step": 1336 }, { "epoch": 0.07383476916280098, "grad_norm": 0.49107328057289124, "learning_rate": 3.979915037643587e-05, "loss": 0.0162, "step": 1337 }, { "epoch": 0.07388999337309476, "grad_norm": 6.411668300628662, "learning_rate": 3.9798644352850354e-05, "loss": 0.3215, "step": 1338 }, { "epoch": 0.07394521758338855, "grad_norm": 3.7973995208740234, "learning_rate": 3.9798137695849833e-05, "loss": 0.4279, "step": 1339 }, { "epoch": 0.07400044179368236, "grad_norm": 0.8515478372573853, "learning_rate": 3.9797630405450544e-05, "loss": 0.0229, "step": 1340 }, { "epoch": 0.07405566600397614, "grad_norm": 4.283430099487305, "learning_rate": 3.979712248166868e-05, "loss": 1.1639, "step": 1341 }, { "epoch": 0.07411089021426993, "grad_norm": 4.65943717956543, "learning_rate": 3.979661392452051e-05, "loss": 0.4113, "step": 1342 }, { "epoch": 0.07416611442456372, "grad_norm": 4.1251702308654785, "learning_rate": 3.979610473402231e-05, "loss": 0.5679, "step": 1343 }, { "epoch": 0.07422133863485753, "grad_norm": 1.6685729026794434, "learning_rate": 3.979559491019035e-05, "loss": 0.0267, "step": 1344 }, { "epoch": 0.07427656284515131, "grad_norm": 0.4706588089466095, "learning_rate": 3.979508445304096e-05, "loss": 0.0209, "step": 1345 }, { "epoch": 0.0743317870554451, "grad_norm": 2.1604835987091064, "learning_rate": 3.9794573362590464e-05, "loss": 0.1313, "step": 1346 }, { "epoch": 0.0743870112657389, "grad_norm": 1.5080102682113647, "learning_rate": 3.979406163885521e-05, "loss": 0.0754, "step": 1347 }, { "epoch": 0.0744422354760327, "grad_norm": 0.6858462691307068, "learning_rate": 3.979354928185158e-05, "loss": 0.0207, "step": 1348 }, { "epoch": 0.07449745968632648, "grad_norm": 4.188544750213623, "learning_rate": 3.979303629159596e-05, "loss": 0.9788, "step": 1349 }, { "epoch": 0.07455268389662027, "grad_norm": 0.7523908615112305, "learning_rate": 3.9792522668104755e-05, "loss": 0.0304, "step": 1350 }, { "epoch": 0.07460790810691408, "grad_norm": 6.103738784790039, "learning_rate": 3.9792008411394405e-05, "loss": 0.7096, "step": 1351 }, { "epoch": 0.07466313231720786, "grad_norm": 3.0306849479675293, "learning_rate": 3.9791493521481364e-05, "loss": 0.7026, "step": 1352 }, { "epoch": 0.07471835652750165, "grad_norm": 2.5239975452423096, "learning_rate": 3.97909779983821e-05, "loss": 0.3575, "step": 1353 }, { "epoch": 0.07477358073779546, "grad_norm": 2.4108498096466064, "learning_rate": 3.97904618421131e-05, "loss": 0.5199, "step": 1354 }, { "epoch": 0.07482880494808924, "grad_norm": 3.7305033206939697, "learning_rate": 3.978994505269089e-05, "loss": 0.307, "step": 1355 }, { "epoch": 0.07488402915838303, "grad_norm": 0.42584994435310364, "learning_rate": 3.9789427630132e-05, "loss": 0.0153, "step": 1356 }, { "epoch": 0.07493925336867682, "grad_norm": 6.118645191192627, "learning_rate": 3.9788909574452973e-05, "loss": 1.3735, "step": 1357 }, { "epoch": 0.07499447757897063, "grad_norm": 2.8899457454681396, "learning_rate": 3.97883908856704e-05, "loss": 0.5623, "step": 1358 }, { "epoch": 0.07504970178926441, "grad_norm": 3.8604090213775635, "learning_rate": 3.978787156380087e-05, "loss": 0.515, "step": 1359 }, { "epoch": 0.0751049259995582, "grad_norm": 3.8398728370666504, "learning_rate": 3.978735160886099e-05, "loss": 0.4371, "step": 1360 }, { "epoch": 0.075160150209852, "grad_norm": 1.24146568775177, "learning_rate": 3.9786831020867403e-05, "loss": 0.0586, "step": 1361 }, { "epoch": 0.0752153744201458, "grad_norm": 0.055073853582143784, "learning_rate": 3.978630979983676e-05, "loss": 0.0022, "step": 1362 }, { "epoch": 0.07527059863043958, "grad_norm": 0.5084033608436584, "learning_rate": 3.978578794578574e-05, "loss": 0.0095, "step": 1363 }, { "epoch": 0.07532582284073337, "grad_norm": 3.7918615341186523, "learning_rate": 3.978526545873103e-05, "loss": 0.8655, "step": 1364 }, { "epoch": 0.07538104705102718, "grad_norm": 0.20535579323768616, "learning_rate": 3.9784742338689357e-05, "loss": 0.0064, "step": 1365 }, { "epoch": 0.07543627126132096, "grad_norm": 4.261562347412109, "learning_rate": 3.978421858567745e-05, "loss": 0.4153, "step": 1366 }, { "epoch": 0.07549149547161475, "grad_norm": 0.23964925110340118, "learning_rate": 3.9783694199712066e-05, "loss": 0.0062, "step": 1367 }, { "epoch": 0.07554671968190854, "grad_norm": 0.1291307657957077, "learning_rate": 3.978316918080999e-05, "loss": 0.0044, "step": 1368 }, { "epoch": 0.07560194389220234, "grad_norm": 0.1979065239429474, "learning_rate": 3.9782643528988e-05, "loss": 0.008, "step": 1369 }, { "epoch": 0.07565716810249613, "grad_norm": 3.305109977722168, "learning_rate": 3.978211724426293e-05, "loss": 0.6405, "step": 1370 }, { "epoch": 0.07571239231278992, "grad_norm": 3.4361226558685303, "learning_rate": 3.9781590326651613e-05, "loss": 0.3557, "step": 1371 }, { "epoch": 0.07576761652308373, "grad_norm": 0.17269675433635712, "learning_rate": 3.97810627761709e-05, "loss": 0.005, "step": 1372 }, { "epoch": 0.07582284073337751, "grad_norm": 4.304938793182373, "learning_rate": 3.9780534592837685e-05, "loss": 0.9089, "step": 1373 }, { "epoch": 0.0758780649436713, "grad_norm": 3.3522965908050537, "learning_rate": 3.978000577666885e-05, "loss": 0.5199, "step": 1374 }, { "epoch": 0.07593328915396509, "grad_norm": 0.21021243929862976, "learning_rate": 3.977947632768132e-05, "loss": 0.0063, "step": 1375 }, { "epoch": 0.0759885133642589, "grad_norm": 3.8700966835021973, "learning_rate": 3.977894624589204e-05, "loss": 0.5678, "step": 1376 }, { "epoch": 0.07604373757455268, "grad_norm": 0.07116584479808807, "learning_rate": 3.977841553131795e-05, "loss": 0.0025, "step": 1377 }, { "epoch": 0.07609896178484647, "grad_norm": 2.9215333461761475, "learning_rate": 3.9777884183976044e-05, "loss": 0.2586, "step": 1378 }, { "epoch": 0.07615418599514027, "grad_norm": 0.7797048687934875, "learning_rate": 3.9777352203883316e-05, "loss": 0.0162, "step": 1379 }, { "epoch": 0.07620941020543406, "grad_norm": 0.3131551444530487, "learning_rate": 3.977681959105679e-05, "loss": 0.0122, "step": 1380 }, { "epoch": 0.07626463441572785, "grad_norm": 2.378950834274292, "learning_rate": 3.97762863455135e-05, "loss": 0.196, "step": 1381 }, { "epoch": 0.07631985862602164, "grad_norm": 5.267537593841553, "learning_rate": 3.977575246727051e-05, "loss": 1.3557, "step": 1382 }, { "epoch": 0.07637508283631544, "grad_norm": 5.6923441886901855, "learning_rate": 3.9775217956344905e-05, "loss": 1.4741, "step": 1383 }, { "epoch": 0.07643030704660923, "grad_norm": 2.1319220066070557, "learning_rate": 3.9774682812753776e-05, "loss": 0.323, "step": 1384 }, { "epoch": 0.07648553125690302, "grad_norm": 0.10691026598215103, "learning_rate": 3.977414703651425e-05, "loss": 0.0035, "step": 1385 }, { "epoch": 0.07654075546719682, "grad_norm": 2.6011855602264404, "learning_rate": 3.977361062764346e-05, "loss": 0.2774, "step": 1386 }, { "epoch": 0.07659597967749061, "grad_norm": 0.0918043926358223, "learning_rate": 3.9773073586158577e-05, "loss": 0.0027, "step": 1387 }, { "epoch": 0.0766512038877844, "grad_norm": 2.9222989082336426, "learning_rate": 3.977253591207678e-05, "loss": 0.1873, "step": 1388 }, { "epoch": 0.07670642809807819, "grad_norm": 3.8985795974731445, "learning_rate": 3.9771997605415264e-05, "loss": 0.6184, "step": 1389 }, { "epoch": 0.076761652308372, "grad_norm": 1.3367844820022583, "learning_rate": 3.9771458666191266e-05, "loss": 0.0485, "step": 1390 }, { "epoch": 0.07681687651866578, "grad_norm": 3.443516492843628, "learning_rate": 3.9770919094422016e-05, "loss": 0.4007, "step": 1391 }, { "epoch": 0.07687210072895957, "grad_norm": 2.95772647857666, "learning_rate": 3.9770378890124774e-05, "loss": 0.2795, "step": 1392 }, { "epoch": 0.07692732493925337, "grad_norm": 0.5354994535446167, "learning_rate": 3.9769838053316825e-05, "loss": 0.0119, "step": 1393 }, { "epoch": 0.07698254914954716, "grad_norm": 1.7270545959472656, "learning_rate": 3.976929658401548e-05, "loss": 0.1062, "step": 1394 }, { "epoch": 0.07703777335984095, "grad_norm": 0.12453657388687134, "learning_rate": 3.9768754482238055e-05, "loss": 0.0029, "step": 1395 }, { "epoch": 0.07709299757013474, "grad_norm": 0.31799426674842834, "learning_rate": 3.9768211748001894e-05, "loss": 0.0073, "step": 1396 }, { "epoch": 0.07714822178042854, "grad_norm": 3.0007786750793457, "learning_rate": 3.976766838132436e-05, "loss": 0.7817, "step": 1397 }, { "epoch": 0.07720344599072233, "grad_norm": 1.1751775741577148, "learning_rate": 3.9767124382222845e-05, "loss": 0.0623, "step": 1398 }, { "epoch": 0.07725867020101612, "grad_norm": 3.195197582244873, "learning_rate": 3.976657975071474e-05, "loss": 0.1146, "step": 1399 }, { "epoch": 0.07731389441130992, "grad_norm": 0.3925759494304657, "learning_rate": 3.976603448681748e-05, "loss": 0.0076, "step": 1400 }, { "epoch": 0.07736911862160371, "grad_norm": 2.973825216293335, "learning_rate": 3.97654885905485e-05, "loss": 0.6695, "step": 1401 }, { "epoch": 0.0774243428318975, "grad_norm": 2.3936543464660645, "learning_rate": 3.976494206192528e-05, "loss": 0.1057, "step": 1402 }, { "epoch": 0.07747956704219129, "grad_norm": 2.940091133117676, "learning_rate": 3.976439490096529e-05, "loss": 0.4041, "step": 1403 }, { "epoch": 0.0775347912524851, "grad_norm": 1.654747486114502, "learning_rate": 3.976384710768604e-05, "loss": 0.0966, "step": 1404 }, { "epoch": 0.07759001546277888, "grad_norm": 0.16953037679195404, "learning_rate": 3.9763298682105055e-05, "loss": 0.0056, "step": 1405 }, { "epoch": 0.07764523967307267, "grad_norm": 3.6430976390838623, "learning_rate": 3.976274962423988e-05, "loss": 0.371, "step": 1406 }, { "epoch": 0.07770046388336647, "grad_norm": 2.9542236328125, "learning_rate": 3.9762199934108084e-05, "loss": 0.4484, "step": 1407 }, { "epoch": 0.07775568809366026, "grad_norm": 2.3859214782714844, "learning_rate": 3.976164961172725e-05, "loss": 0.24, "step": 1408 }, { "epoch": 0.07781091230395405, "grad_norm": 0.07725350558757782, "learning_rate": 3.976109865711498e-05, "loss": 0.0025, "step": 1409 }, { "epoch": 0.07786613651424784, "grad_norm": 3.2204947471618652, "learning_rate": 3.9760547070288924e-05, "loss": 0.3743, "step": 1410 }, { "epoch": 0.07792136072454164, "grad_norm": 2.5005762577056885, "learning_rate": 3.97599948512667e-05, "loss": 0.2208, "step": 1411 }, { "epoch": 0.07797658493483543, "grad_norm": 2.0006744861602783, "learning_rate": 3.9759442000065986e-05, "loss": 0.073, "step": 1412 }, { "epoch": 0.07803180914512922, "grad_norm": 0.40829354524612427, "learning_rate": 3.9758888516704474e-05, "loss": 0.016, "step": 1413 }, { "epoch": 0.07808703335542301, "grad_norm": 2.3669681549072266, "learning_rate": 3.975833440119987e-05, "loss": 0.2961, "step": 1414 }, { "epoch": 0.07814225756571681, "grad_norm": 3.1033143997192383, "learning_rate": 3.9757779653569894e-05, "loss": 0.4432, "step": 1415 }, { "epoch": 0.0781974817760106, "grad_norm": 0.6881954073905945, "learning_rate": 3.97572242738323e-05, "loss": 0.0298, "step": 1416 }, { "epoch": 0.07825270598630439, "grad_norm": 4.2127814292907715, "learning_rate": 3.9756668262004845e-05, "loss": 0.8881, "step": 1417 }, { "epoch": 0.0783079301965982, "grad_norm": 0.30769672989845276, "learning_rate": 3.975611161810534e-05, "loss": 0.0069, "step": 1418 }, { "epoch": 0.07836315440689198, "grad_norm": 0.495012491941452, "learning_rate": 3.975555434215158e-05, "loss": 0.0123, "step": 1419 }, { "epoch": 0.07841837861718577, "grad_norm": 3.3710830211639404, "learning_rate": 3.97549964341614e-05, "loss": 0.6511, "step": 1420 }, { "epoch": 0.07847360282747956, "grad_norm": 3.342825174331665, "learning_rate": 3.975443789415263e-05, "loss": 0.3399, "step": 1421 }, { "epoch": 0.07852882703777336, "grad_norm": 1.1251589059829712, "learning_rate": 3.975387872214316e-05, "loss": 0.0338, "step": 1422 }, { "epoch": 0.07858405124806715, "grad_norm": 1.478514552116394, "learning_rate": 3.975331891815088e-05, "loss": 0.0591, "step": 1423 }, { "epoch": 0.07863927545836094, "grad_norm": 3.243185043334961, "learning_rate": 3.975275848219368e-05, "loss": 0.3687, "step": 1424 }, { "epoch": 0.07869449966865474, "grad_norm": 0.14061573147773743, "learning_rate": 3.9752197414289514e-05, "loss": 0.0051, "step": 1425 }, { "epoch": 0.07874972387894853, "grad_norm": 0.046781208366155624, "learning_rate": 3.9751635714456316e-05, "loss": 0.0014, "step": 1426 }, { "epoch": 0.07880494808924232, "grad_norm": 0.17247933149337769, "learning_rate": 3.9751073382712056e-05, "loss": 0.005, "step": 1427 }, { "epoch": 0.07886017229953611, "grad_norm": 7.523706912994385, "learning_rate": 3.9750510419074733e-05, "loss": 1.6143, "step": 1428 }, { "epoch": 0.07891539650982991, "grad_norm": 4.0228776931762695, "learning_rate": 3.974994682356236e-05, "loss": 0.5224, "step": 1429 }, { "epoch": 0.0789706207201237, "grad_norm": 1.120262861251831, "learning_rate": 3.9749382596192956e-05, "loss": 0.0405, "step": 1430 }, { "epoch": 0.07902584493041749, "grad_norm": 0.020160339772701263, "learning_rate": 3.9748817736984585e-05, "loss": 0.0008, "step": 1431 }, { "epoch": 0.0790810691407113, "grad_norm": 0.11125826835632324, "learning_rate": 3.9748252245955304e-05, "loss": 0.0035, "step": 1432 }, { "epoch": 0.07913629335100508, "grad_norm": 4.327603816986084, "learning_rate": 3.974768612312322e-05, "loss": 1.1043, "step": 1433 }, { "epoch": 0.07919151756129887, "grad_norm": 0.597133219242096, "learning_rate": 3.974711936850643e-05, "loss": 0.0172, "step": 1434 }, { "epoch": 0.07924674177159266, "grad_norm": 3.5529394149780273, "learning_rate": 3.9746551982123084e-05, "loss": 0.3973, "step": 1435 }, { "epoch": 0.07930196598188646, "grad_norm": 0.15091554820537567, "learning_rate": 3.974598396399132e-05, "loss": 0.0053, "step": 1436 }, { "epoch": 0.07935719019218025, "grad_norm": 2.906919240951538, "learning_rate": 3.974541531412931e-05, "loss": 0.12, "step": 1437 }, { "epoch": 0.07941241440247404, "grad_norm": 0.15567825734615326, "learning_rate": 3.9744846032555256e-05, "loss": 0.0042, "step": 1438 }, { "epoch": 0.07946763861276784, "grad_norm": 1.9119007587432861, "learning_rate": 3.9744276119287365e-05, "loss": 0.5632, "step": 1439 }, { "epoch": 0.07952286282306163, "grad_norm": 4.699851989746094, "learning_rate": 3.9743705574343874e-05, "loss": 0.5057, "step": 1440 }, { "epoch": 0.07957808703335542, "grad_norm": 3.465322971343994, "learning_rate": 3.974313439774303e-05, "loss": 0.4973, "step": 1441 }, { "epoch": 0.07963331124364921, "grad_norm": 5.8192009925842285, "learning_rate": 3.974256258950311e-05, "loss": 1.4704, "step": 1442 }, { "epoch": 0.07968853545394301, "grad_norm": 0.6998622417449951, "learning_rate": 3.974199014964241e-05, "loss": 0.016, "step": 1443 }, { "epoch": 0.0797437596642368, "grad_norm": 3.256756067276001, "learning_rate": 3.974141707817924e-05, "loss": 0.808, "step": 1444 }, { "epoch": 0.07979898387453059, "grad_norm": 1.8899840116500854, "learning_rate": 3.974084337513194e-05, "loss": 0.0285, "step": 1445 }, { "epoch": 0.0798542080848244, "grad_norm": 3.1286799907684326, "learning_rate": 3.974026904051886e-05, "loss": 0.1411, "step": 1446 }, { "epoch": 0.07990943229511818, "grad_norm": 0.1121460348367691, "learning_rate": 3.973969407435838e-05, "loss": 0.0035, "step": 1447 }, { "epoch": 0.07996465650541197, "grad_norm": 2.1001713275909424, "learning_rate": 3.9739118476668885e-05, "loss": 0.3515, "step": 1448 }, { "epoch": 0.08001988071570576, "grad_norm": 0.06549635529518127, "learning_rate": 3.973854224746879e-05, "loss": 0.0017, "step": 1449 }, { "epoch": 0.08007510492599956, "grad_norm": 0.23248516023159027, "learning_rate": 3.973796538677654e-05, "loss": 0.0058, "step": 1450 }, { "epoch": 0.08013032913629335, "grad_norm": 1.6828689575195312, "learning_rate": 3.9737387894610586e-05, "loss": 0.0748, "step": 1451 }, { "epoch": 0.08018555334658714, "grad_norm": 0.3398086130619049, "learning_rate": 3.9736809770989406e-05, "loss": 0.0072, "step": 1452 }, { "epoch": 0.08024077755688094, "grad_norm": 1.94965398311615, "learning_rate": 3.973623101593149e-05, "loss": 0.1096, "step": 1453 }, { "epoch": 0.08029600176717473, "grad_norm": 2.4594576358795166, "learning_rate": 3.9735651629455356e-05, "loss": 0.232, "step": 1454 }, { "epoch": 0.08035122597746852, "grad_norm": 0.3326868712902069, "learning_rate": 3.9735071611579546e-05, "loss": 0.0096, "step": 1455 }, { "epoch": 0.08040645018776231, "grad_norm": 0.33011138439178467, "learning_rate": 3.973449096232261e-05, "loss": 0.0078, "step": 1456 }, { "epoch": 0.08046167439805611, "grad_norm": 0.7898361086845398, "learning_rate": 3.973390968170312e-05, "loss": 0.0198, "step": 1457 }, { "epoch": 0.0805168986083499, "grad_norm": 2.099257469177246, "learning_rate": 3.973332776973969e-05, "loss": 0.4253, "step": 1458 }, { "epoch": 0.08057212281864369, "grad_norm": 0.6952028870582581, "learning_rate": 3.973274522645092e-05, "loss": 0.0181, "step": 1459 }, { "epoch": 0.08062734702893748, "grad_norm": 2.8278870582580566, "learning_rate": 3.9732162051855453e-05, "loss": 0.4565, "step": 1460 }, { "epoch": 0.08068257123923128, "grad_norm": 3.278449535369873, "learning_rate": 3.9731578245971955e-05, "loss": 0.2751, "step": 1461 }, { "epoch": 0.08073779544952507, "grad_norm": 1.6681894063949585, "learning_rate": 3.973099380881909e-05, "loss": 0.0637, "step": 1462 }, { "epoch": 0.08079301965981886, "grad_norm": 3.1512887477874756, "learning_rate": 3.973040874041556e-05, "loss": 0.3441, "step": 1463 }, { "epoch": 0.08084824387011266, "grad_norm": 2.824183225631714, "learning_rate": 3.9729823040780086e-05, "loss": 0.4951, "step": 1464 }, { "epoch": 0.08090346808040645, "grad_norm": 2.6849935054779053, "learning_rate": 3.9729236709931406e-05, "loss": 0.0629, "step": 1465 }, { "epoch": 0.08095869229070024, "grad_norm": 1.03694748878479, "learning_rate": 3.9728649747888275e-05, "loss": 0.029, "step": 1466 }, { "epoch": 0.08101391650099403, "grad_norm": 1.9184489250183105, "learning_rate": 3.972806215466947e-05, "loss": 0.0552, "step": 1467 }, { "epoch": 0.08106914071128783, "grad_norm": 5.541787147521973, "learning_rate": 3.97274739302938e-05, "loss": 0.9253, "step": 1468 }, { "epoch": 0.08112436492158162, "grad_norm": 2.875868320465088, "learning_rate": 3.972688507478007e-05, "loss": 0.5118, "step": 1469 }, { "epoch": 0.08117958913187541, "grad_norm": 1.4101743698120117, "learning_rate": 3.972629558814713e-05, "loss": 0.0444, "step": 1470 }, { "epoch": 0.08123481334216921, "grad_norm": 0.02975352853536606, "learning_rate": 3.972570547041384e-05, "loss": 0.001, "step": 1471 }, { "epoch": 0.081290037552463, "grad_norm": 0.22694408893585205, "learning_rate": 3.972511472159907e-05, "loss": 0.0093, "step": 1472 }, { "epoch": 0.08134526176275679, "grad_norm": 4.558101654052734, "learning_rate": 3.972452334172173e-05, "loss": 0.2999, "step": 1473 }, { "epoch": 0.08140048597305058, "grad_norm": 0.1374627947807312, "learning_rate": 3.9723931330800734e-05, "loss": 0.0035, "step": 1474 }, { "epoch": 0.08145571018334438, "grad_norm": 0.2816200256347656, "learning_rate": 3.972333868885502e-05, "loss": 0.0068, "step": 1475 }, { "epoch": 0.08151093439363817, "grad_norm": 0.05495207756757736, "learning_rate": 3.972274541590355e-05, "loss": 0.0019, "step": 1476 }, { "epoch": 0.08156615860393196, "grad_norm": 0.3246457278728485, "learning_rate": 3.972215151196532e-05, "loss": 0.0067, "step": 1477 }, { "epoch": 0.08162138281422576, "grad_norm": 3.2727460861206055, "learning_rate": 3.97215569770593e-05, "loss": 0.3505, "step": 1478 }, { "epoch": 0.08167660702451955, "grad_norm": 2.8016953468322754, "learning_rate": 3.972096181120453e-05, "loss": 0.4376, "step": 1479 }, { "epoch": 0.08173183123481334, "grad_norm": 0.40529561042785645, "learning_rate": 3.972036601442005e-05, "loss": 0.0136, "step": 1480 }, { "epoch": 0.08178705544510713, "grad_norm": 2.111955404281616, "learning_rate": 3.9719769586724924e-05, "loss": 0.7433, "step": 1481 }, { "epoch": 0.08184227965540093, "grad_norm": 0.32340583205223083, "learning_rate": 3.971917252813823e-05, "loss": 0.0072, "step": 1482 }, { "epoch": 0.08189750386569472, "grad_norm": 3.599544048309326, "learning_rate": 3.9718574838679066e-05, "loss": 0.2033, "step": 1483 }, { "epoch": 0.08195272807598851, "grad_norm": 1.5466628074645996, "learning_rate": 3.9717976518366555e-05, "loss": 0.1596, "step": 1484 }, { "epoch": 0.08200795228628231, "grad_norm": 1.2547768354415894, "learning_rate": 3.971737756721984e-05, "loss": 0.0271, "step": 1485 }, { "epoch": 0.0820631764965761, "grad_norm": 0.42667168378829956, "learning_rate": 3.971677798525809e-05, "loss": 0.0139, "step": 1486 }, { "epoch": 0.08211840070686989, "grad_norm": 2.138856887817383, "learning_rate": 3.971617777250047e-05, "loss": 0.0717, "step": 1487 }, { "epoch": 0.08217362491716368, "grad_norm": 3.802551031112671, "learning_rate": 3.9715576928966204e-05, "loss": 0.428, "step": 1488 }, { "epoch": 0.08222884912745748, "grad_norm": 1.456695556640625, "learning_rate": 3.9714975454674506e-05, "loss": 0.0461, "step": 1489 }, { "epoch": 0.08228407333775127, "grad_norm": 2.086275100708008, "learning_rate": 3.971437334964461e-05, "loss": 0.1918, "step": 1490 }, { "epoch": 0.08233929754804506, "grad_norm": 4.4473958015441895, "learning_rate": 3.9713770613895786e-05, "loss": 0.5803, "step": 1491 }, { "epoch": 0.08239452175833886, "grad_norm": 3.2359302043914795, "learning_rate": 3.971316724744732e-05, "loss": 0.4051, "step": 1492 }, { "epoch": 0.08244974596863265, "grad_norm": 3.3652610778808594, "learning_rate": 3.971256325031851e-05, "loss": 0.5726, "step": 1493 }, { "epoch": 0.08250497017892644, "grad_norm": 3.320509433746338, "learning_rate": 3.971195862252868e-05, "loss": 0.4709, "step": 1494 }, { "epoch": 0.08256019438922023, "grad_norm": 0.8219838738441467, "learning_rate": 3.9711353364097186e-05, "loss": 0.022, "step": 1495 }, { "epoch": 0.08261541859951403, "grad_norm": 2.577561855316162, "learning_rate": 3.971074747504338e-05, "loss": 0.1407, "step": 1496 }, { "epoch": 0.08267064280980782, "grad_norm": 3.428755760192871, "learning_rate": 3.971014095538665e-05, "loss": 0.271, "step": 1497 }, { "epoch": 0.08272586702010161, "grad_norm": 2.265068531036377, "learning_rate": 3.970953380514638e-05, "loss": 0.3016, "step": 1498 }, { "epoch": 0.08278109123039541, "grad_norm": 2.0085976123809814, "learning_rate": 3.970892602434203e-05, "loss": 0.1194, "step": 1499 }, { "epoch": 0.0828363154406892, "grad_norm": 0.46292972564697266, "learning_rate": 3.970831761299303e-05, "loss": 0.0139, "step": 1500 }, { "epoch": 0.08289153965098299, "grad_norm": 0.11679669469594955, "learning_rate": 3.970770857111884e-05, "loss": 0.0037, "step": 1501 }, { "epoch": 0.08294676386127678, "grad_norm": 3.681626081466675, "learning_rate": 3.970709889873894e-05, "loss": 0.7921, "step": 1502 }, { "epoch": 0.08300198807157058, "grad_norm": 4.080471038818359, "learning_rate": 3.970648859587285e-05, "loss": 0.9235, "step": 1503 }, { "epoch": 0.08305721228186437, "grad_norm": 0.41872021555900574, "learning_rate": 3.9705877662540084e-05, "loss": 0.0128, "step": 1504 }, { "epoch": 0.08311243649215816, "grad_norm": 1.6218287944793701, "learning_rate": 3.970526609876019e-05, "loss": 0.0452, "step": 1505 }, { "epoch": 0.08316766070245195, "grad_norm": 5.066619396209717, "learning_rate": 3.9704653904552736e-05, "loss": 1.1423, "step": 1506 }, { "epoch": 0.08322288491274575, "grad_norm": 3.188305139541626, "learning_rate": 3.970404107993731e-05, "loss": 0.3518, "step": 1507 }, { "epoch": 0.08327810912303954, "grad_norm": 1.4000545740127563, "learning_rate": 3.970342762493351e-05, "loss": 0.0606, "step": 1508 }, { "epoch": 0.08333333333333333, "grad_norm": 0.0864645317196846, "learning_rate": 3.9702813539560974e-05, "loss": 0.0026, "step": 1509 }, { "epoch": 0.08338855754362713, "grad_norm": 3.6076571941375732, "learning_rate": 3.970219882383934e-05, "loss": 0.5036, "step": 1510 }, { "epoch": 0.08344378175392092, "grad_norm": 1.9512337446212769, "learning_rate": 3.970158347778827e-05, "loss": 0.2174, "step": 1511 }, { "epoch": 0.08349900596421471, "grad_norm": 3.8962433338165283, "learning_rate": 3.970096750142746e-05, "loss": 0.3128, "step": 1512 }, { "epoch": 0.0835542301745085, "grad_norm": 0.37885862588882446, "learning_rate": 3.970035089477662e-05, "loss": 0.0111, "step": 1513 }, { "epoch": 0.0836094543848023, "grad_norm": 3.8624398708343506, "learning_rate": 3.969973365785546e-05, "loss": 0.5987, "step": 1514 }, { "epoch": 0.08366467859509609, "grad_norm": 0.9848747849464417, "learning_rate": 3.9699115790683743e-05, "loss": 0.2456, "step": 1515 }, { "epoch": 0.08371990280538988, "grad_norm": 3.710306167602539, "learning_rate": 3.969849729328123e-05, "loss": 0.4896, "step": 1516 }, { "epoch": 0.08377512701568368, "grad_norm": 0.6966831088066101, "learning_rate": 3.969787816566771e-05, "loss": 0.0275, "step": 1517 }, { "epoch": 0.08383035122597747, "grad_norm": 1.6926612854003906, "learning_rate": 3.969725840786299e-05, "loss": 0.2835, "step": 1518 }, { "epoch": 0.08388557543627126, "grad_norm": 1.7607192993164062, "learning_rate": 3.9696638019886896e-05, "loss": 0.0787, "step": 1519 }, { "epoch": 0.08394079964656505, "grad_norm": 3.216068744659424, "learning_rate": 3.969601700175928e-05, "loss": 0.4352, "step": 1520 }, { "epoch": 0.08399602385685885, "grad_norm": 4.455437183380127, "learning_rate": 3.969539535350001e-05, "loss": 0.7993, "step": 1521 }, { "epoch": 0.08405124806715264, "grad_norm": 2.291058301925659, "learning_rate": 3.9694773075128974e-05, "loss": 0.1229, "step": 1522 }, { "epoch": 0.08410647227744643, "grad_norm": 5.261338233947754, "learning_rate": 3.969415016666607e-05, "loss": 1.1736, "step": 1523 }, { "epoch": 0.08416169648774023, "grad_norm": 0.14117994904518127, "learning_rate": 3.969352662813125e-05, "loss": 0.0045, "step": 1524 }, { "epoch": 0.08421692069803402, "grad_norm": 2.250131607055664, "learning_rate": 3.969290245954443e-05, "loss": 0.1095, "step": 1525 }, { "epoch": 0.08427214490832781, "grad_norm": 1.515552282333374, "learning_rate": 3.96922776609256e-05, "loss": 0.1778, "step": 1526 }, { "epoch": 0.0843273691186216, "grad_norm": 1.4352905750274658, "learning_rate": 3.9691652232294754e-05, "loss": 0.0565, "step": 1527 }, { "epoch": 0.0843825933289154, "grad_norm": 1.765211582183838, "learning_rate": 3.969102617367189e-05, "loss": 0.2725, "step": 1528 }, { "epoch": 0.08443781753920919, "grad_norm": 3.7154321670532227, "learning_rate": 3.9690399485077045e-05, "loss": 0.8057, "step": 1529 }, { "epoch": 0.08449304174950298, "grad_norm": 0.9770424365997314, "learning_rate": 3.968977216653026e-05, "loss": 0.0507, "step": 1530 }, { "epoch": 0.08454826595979678, "grad_norm": 1.513079047203064, "learning_rate": 3.968914421805161e-05, "loss": 0.0682, "step": 1531 }, { "epoch": 0.08460349017009057, "grad_norm": 0.5856451392173767, "learning_rate": 3.968851563966119e-05, "loss": 0.0191, "step": 1532 }, { "epoch": 0.08465871438038436, "grad_norm": 3.069575548171997, "learning_rate": 3.968788643137909e-05, "loss": 0.8004, "step": 1533 }, { "epoch": 0.08471393859067815, "grad_norm": 4.280239105224609, "learning_rate": 3.968725659322547e-05, "loss": 0.7516, "step": 1534 }, { "epoch": 0.08476916280097195, "grad_norm": 5.9409613609313965, "learning_rate": 3.968662612522046e-05, "loss": 1.4271, "step": 1535 }, { "epoch": 0.08482438701126574, "grad_norm": 0.030189648270606995, "learning_rate": 3.968599502738423e-05, "loss": 0.001, "step": 1536 }, { "epoch": 0.08487961122155953, "grad_norm": 2.159362316131592, "learning_rate": 3.968536329973698e-05, "loss": 0.1285, "step": 1537 }, { "epoch": 0.08493483543185333, "grad_norm": 1.2101136445999146, "learning_rate": 3.968473094229891e-05, "loss": 0.1058, "step": 1538 }, { "epoch": 0.08499005964214712, "grad_norm": 4.758050441741943, "learning_rate": 3.968409795509026e-05, "loss": 0.7283, "step": 1539 }, { "epoch": 0.08504528385244091, "grad_norm": 3.3695085048675537, "learning_rate": 3.968346433813127e-05, "loss": 0.4329, "step": 1540 }, { "epoch": 0.0851005080627347, "grad_norm": 3.3631248474121094, "learning_rate": 3.968283009144224e-05, "loss": 0.7312, "step": 1541 }, { "epoch": 0.0851557322730285, "grad_norm": 5.475940227508545, "learning_rate": 3.968219521504343e-05, "loss": 2.211, "step": 1542 }, { "epoch": 0.08521095648332229, "grad_norm": 0.8627938628196716, "learning_rate": 3.9681559708955156e-05, "loss": 0.0401, "step": 1543 }, { "epoch": 0.08526618069361608, "grad_norm": 0.11072546988725662, "learning_rate": 3.9680923573197764e-05, "loss": 0.0044, "step": 1544 }, { "epoch": 0.08532140490390988, "grad_norm": 0.0713108479976654, "learning_rate": 3.968028680779159e-05, "loss": 0.0021, "step": 1545 }, { "epoch": 0.08537662911420367, "grad_norm": 2.3113882541656494, "learning_rate": 3.967964941275703e-05, "loss": 0.1717, "step": 1546 }, { "epoch": 0.08543185332449746, "grad_norm": 4.139764308929443, "learning_rate": 3.967901138811444e-05, "loss": 0.6698, "step": 1547 }, { "epoch": 0.08548707753479125, "grad_norm": 1.8065440654754639, "learning_rate": 3.967837273388426e-05, "loss": 0.127, "step": 1548 }, { "epoch": 0.08554230174508505, "grad_norm": 0.8419360518455505, "learning_rate": 3.967773345008692e-05, "loss": 0.0355, "step": 1549 }, { "epoch": 0.08559752595537884, "grad_norm": 2.1880621910095215, "learning_rate": 3.9677093536742865e-05, "loss": 0.1898, "step": 1550 }, { "epoch": 0.08565275016567263, "grad_norm": 0.05566111207008362, "learning_rate": 3.967645299387257e-05, "loss": 0.002, "step": 1551 }, { "epoch": 0.08570797437596642, "grad_norm": 0.09461508691310883, "learning_rate": 3.9675811821496524e-05, "loss": 0.0029, "step": 1552 }, { "epoch": 0.08576319858626022, "grad_norm": 6.073918342590332, "learning_rate": 3.967517001963524e-05, "loss": 0.6713, "step": 1553 }, { "epoch": 0.08581842279655401, "grad_norm": 1.4745250940322876, "learning_rate": 3.9674527588309256e-05, "loss": 0.0843, "step": 1554 }, { "epoch": 0.0858736470068478, "grad_norm": 3.2759013175964355, "learning_rate": 3.967388452753913e-05, "loss": 0.8207, "step": 1555 }, { "epoch": 0.0859288712171416, "grad_norm": 2.748300790786743, "learning_rate": 3.967324083734542e-05, "loss": 0.1328, "step": 1556 }, { "epoch": 0.08598409542743539, "grad_norm": 2.604501962661743, "learning_rate": 3.967259651774873e-05, "loss": 0.6225, "step": 1557 }, { "epoch": 0.08603931963772918, "grad_norm": 4.39169979095459, "learning_rate": 3.967195156876968e-05, "loss": 0.8078, "step": 1558 }, { "epoch": 0.08609454384802297, "grad_norm": 3.7665398120880127, "learning_rate": 3.967130599042889e-05, "loss": 0.5889, "step": 1559 }, { "epoch": 0.08614976805831677, "grad_norm": 0.20469491183757782, "learning_rate": 3.9670659782747016e-05, "loss": 0.006, "step": 1560 }, { "epoch": 0.08620499226861056, "grad_norm": 2.547062873840332, "learning_rate": 3.967001294574474e-05, "loss": 0.1204, "step": 1561 }, { "epoch": 0.08626021647890435, "grad_norm": 0.778881311416626, "learning_rate": 3.966936547944275e-05, "loss": 0.0241, "step": 1562 }, { "epoch": 0.08631544068919815, "grad_norm": 2.3747398853302, "learning_rate": 3.966871738386177e-05, "loss": 0.1711, "step": 1563 }, { "epoch": 0.08637066489949194, "grad_norm": 4.2961649894714355, "learning_rate": 3.966806865902252e-05, "loss": 0.6911, "step": 1564 }, { "epoch": 0.08642588910978573, "grad_norm": 4.855388164520264, "learning_rate": 3.966741930494576e-05, "loss": 0.6421, "step": 1565 }, { "epoch": 0.08648111332007952, "grad_norm": 1.9806406497955322, "learning_rate": 3.966676932165227e-05, "loss": 0.2043, "step": 1566 }, { "epoch": 0.08653633753037332, "grad_norm": 0.1384546011686325, "learning_rate": 3.9666118709162837e-05, "loss": 0.0036, "step": 1567 }, { "epoch": 0.08659156174066711, "grad_norm": 0.5045193433761597, "learning_rate": 3.966546746749828e-05, "loss": 0.015, "step": 1568 }, { "epoch": 0.0866467859509609, "grad_norm": 1.0608904361724854, "learning_rate": 3.966481559667943e-05, "loss": 0.0303, "step": 1569 }, { "epoch": 0.0867020101612547, "grad_norm": 0.8226733207702637, "learning_rate": 3.966416309672715e-05, "loss": 0.0277, "step": 1570 }, { "epoch": 0.08675723437154849, "grad_norm": 0.22999908030033112, "learning_rate": 3.966350996766231e-05, "loss": 0.0096, "step": 1571 }, { "epoch": 0.08681245858184228, "grad_norm": 0.7130586504936218, "learning_rate": 3.966285620950581e-05, "loss": 0.0271, "step": 1572 }, { "epoch": 0.08686768279213607, "grad_norm": 0.4420055150985718, "learning_rate": 3.966220182227856e-05, "loss": 0.0264, "step": 1573 }, { "epoch": 0.08692290700242987, "grad_norm": 1.2254916429519653, "learning_rate": 3.96615468060015e-05, "loss": 0.0448, "step": 1574 }, { "epoch": 0.08697813121272366, "grad_norm": 3.06107759475708, "learning_rate": 3.966089116069558e-05, "loss": 0.337, "step": 1575 }, { "epoch": 0.08703335542301745, "grad_norm": 6.055077075958252, "learning_rate": 3.966023488638178e-05, "loss": 1.0707, "step": 1576 }, { "epoch": 0.08708857963331125, "grad_norm": 2.201706886291504, "learning_rate": 3.9659577983081095e-05, "loss": 0.3438, "step": 1577 }, { "epoch": 0.08714380384360504, "grad_norm": 3.2530205249786377, "learning_rate": 3.9658920450814545e-05, "loss": 0.4551, "step": 1578 }, { "epoch": 0.08719902805389883, "grad_norm": 2.8790829181671143, "learning_rate": 3.965826228960317e-05, "loss": 0.6268, "step": 1579 }, { "epoch": 0.08725425226419262, "grad_norm": 1.9088997840881348, "learning_rate": 3.9657603499468e-05, "loss": 0.0587, "step": 1580 }, { "epoch": 0.08730947647448642, "grad_norm": 4.406550884246826, "learning_rate": 3.9656944080430146e-05, "loss": 0.6801, "step": 1581 }, { "epoch": 0.08736470068478021, "grad_norm": 2.550374746322632, "learning_rate": 3.965628403251069e-05, "loss": 0.3067, "step": 1582 }, { "epoch": 0.087419924895074, "grad_norm": 2.4320836067199707, "learning_rate": 3.965562335573075e-05, "loss": 0.2424, "step": 1583 }, { "epoch": 0.0874751491053678, "grad_norm": 0.5040801763534546, "learning_rate": 3.9654962050111453e-05, "loss": 0.0221, "step": 1584 }, { "epoch": 0.08753037331566159, "grad_norm": 3.4232146739959717, "learning_rate": 3.9654300115673974e-05, "loss": 0.6256, "step": 1585 }, { "epoch": 0.08758559752595538, "grad_norm": 3.939523220062256, "learning_rate": 3.965363755243948e-05, "loss": 0.4762, "step": 1586 }, { "epoch": 0.08764082173624917, "grad_norm": 0.7582346796989441, "learning_rate": 3.965297436042916e-05, "loss": 0.0243, "step": 1587 }, { "epoch": 0.08769604594654297, "grad_norm": 0.062292344868183136, "learning_rate": 3.965231053966425e-05, "loss": 0.0017, "step": 1588 }, { "epoch": 0.08775127015683676, "grad_norm": 1.4850248098373413, "learning_rate": 3.965164609016597e-05, "loss": 0.3151, "step": 1589 }, { "epoch": 0.08780649436713055, "grad_norm": 3.8307156562805176, "learning_rate": 3.965098101195559e-05, "loss": 0.589, "step": 1590 }, { "epoch": 0.08786171857742435, "grad_norm": 0.13611355423927307, "learning_rate": 3.9650315305054386e-05, "loss": 0.0042, "step": 1591 }, { "epoch": 0.08791694278771814, "grad_norm": 0.5026236772537231, "learning_rate": 3.964964896948365e-05, "loss": 0.0186, "step": 1592 }, { "epoch": 0.08797216699801193, "grad_norm": 0.7566234469413757, "learning_rate": 3.9648982005264706e-05, "loss": 0.0267, "step": 1593 }, { "epoch": 0.08802739120830572, "grad_norm": 2.9786124229431152, "learning_rate": 3.964831441241889e-05, "loss": 0.1359, "step": 1594 }, { "epoch": 0.08808261541859952, "grad_norm": 0.39013147354125977, "learning_rate": 3.964764619096756e-05, "loss": 0.018, "step": 1595 }, { "epoch": 0.08813783962889331, "grad_norm": 1.1312017440795898, "learning_rate": 3.964697734093209e-05, "loss": 0.0361, "step": 1596 }, { "epoch": 0.0881930638391871, "grad_norm": 0.14618246257305145, "learning_rate": 3.9646307862333885e-05, "loss": 0.0062, "step": 1597 }, { "epoch": 0.08824828804948089, "grad_norm": 2.850069999694824, "learning_rate": 3.9645637755194355e-05, "loss": 0.452, "step": 1598 }, { "epoch": 0.08830351225977469, "grad_norm": 0.09825848788022995, "learning_rate": 3.964496701953495e-05, "loss": 0.0025, "step": 1599 }, { "epoch": 0.08835873647006848, "grad_norm": 0.13654232025146484, "learning_rate": 3.964429565537713e-05, "loss": 0.0047, "step": 1600 }, { "epoch": 0.08841396068036227, "grad_norm": 3.5139708518981934, "learning_rate": 3.964362366274236e-05, "loss": 0.6446, "step": 1601 }, { "epoch": 0.08846918489065607, "grad_norm": 2.7385034561157227, "learning_rate": 3.9642951041652146e-05, "loss": 0.756, "step": 1602 }, { "epoch": 0.08852440910094986, "grad_norm": 0.3862329125404358, "learning_rate": 3.9642277792128e-05, "loss": 0.0123, "step": 1603 }, { "epoch": 0.08857963331124365, "grad_norm": 0.2420700639486313, "learning_rate": 3.9641603914191484e-05, "loss": 0.0081, "step": 1604 }, { "epoch": 0.08863485752153744, "grad_norm": 1.8734772205352783, "learning_rate": 3.964092940786413e-05, "loss": 0.055, "step": 1605 }, { "epoch": 0.08869008173183124, "grad_norm": 3.6363608837127686, "learning_rate": 3.964025427316753e-05, "loss": 1.062, "step": 1606 }, { "epoch": 0.08874530594212503, "grad_norm": 3.0588691234588623, "learning_rate": 3.9639578510123294e-05, "loss": 0.2571, "step": 1607 }, { "epoch": 0.08880053015241882, "grad_norm": 0.48702746629714966, "learning_rate": 3.963890211875302e-05, "loss": 0.0189, "step": 1608 }, { "epoch": 0.08885575436271262, "grad_norm": 4.9849019050598145, "learning_rate": 3.9638225099078356e-05, "loss": 0.7671, "step": 1609 }, { "epoch": 0.08891097857300641, "grad_norm": 0.18422968685626984, "learning_rate": 3.963754745112097e-05, "loss": 0.0054, "step": 1610 }, { "epoch": 0.0889662027833002, "grad_norm": 2.1738979816436768, "learning_rate": 3.963686917490253e-05, "loss": 0.1162, "step": 1611 }, { "epoch": 0.08902142699359399, "grad_norm": 4.411866188049316, "learning_rate": 3.963619027044474e-05, "loss": 0.9468, "step": 1612 }, { "epoch": 0.08907665120388779, "grad_norm": 2.6036055088043213, "learning_rate": 3.9635510737769333e-05, "loss": 0.4075, "step": 1613 }, { "epoch": 0.08913187541418158, "grad_norm": 4.562314987182617, "learning_rate": 3.9634830576898024e-05, "loss": 0.6117, "step": 1614 }, { "epoch": 0.08918709962447537, "grad_norm": 0.18289059400558472, "learning_rate": 3.963414978785259e-05, "loss": 0.0052, "step": 1615 }, { "epoch": 0.08924232383476917, "grad_norm": 0.1579829603433609, "learning_rate": 3.963346837065482e-05, "loss": 0.0051, "step": 1616 }, { "epoch": 0.08929754804506296, "grad_norm": 6.690621376037598, "learning_rate": 3.963278632532649e-05, "loss": 1.1111, "step": 1617 }, { "epoch": 0.08935277225535675, "grad_norm": 2.828979730606079, "learning_rate": 3.9632103651889436e-05, "loss": 0.7808, "step": 1618 }, { "epoch": 0.08940799646565054, "grad_norm": 0.7445110082626343, "learning_rate": 3.96314203503655e-05, "loss": 0.0242, "step": 1619 }, { "epoch": 0.08946322067594434, "grad_norm": 0.1150372326374054, "learning_rate": 3.963073642077653e-05, "loss": 0.0049, "step": 1620 }, { "epoch": 0.08951844488623813, "grad_norm": 3.323819160461426, "learning_rate": 3.963005186314442e-05, "loss": 0.3862, "step": 1621 }, { "epoch": 0.08957366909653192, "grad_norm": 1.991970181465149, "learning_rate": 3.962936667749107e-05, "loss": 0.1445, "step": 1622 }, { "epoch": 0.08962889330682572, "grad_norm": 0.6145743131637573, "learning_rate": 3.96286808638384e-05, "loss": 0.0207, "step": 1623 }, { "epoch": 0.08968411751711951, "grad_norm": 1.952437400817871, "learning_rate": 3.962799442220834e-05, "loss": 0.5153, "step": 1624 }, { "epoch": 0.0897393417274133, "grad_norm": 2.5001816749572754, "learning_rate": 3.9627307352622864e-05, "loss": 0.3828, "step": 1625 }, { "epoch": 0.08979456593770709, "grad_norm": 2.3387959003448486, "learning_rate": 3.962661965510395e-05, "loss": 0.328, "step": 1626 }, { "epoch": 0.08984979014800089, "grad_norm": 1.6372532844543457, "learning_rate": 3.96259313296736e-05, "loss": 0.0566, "step": 1627 }, { "epoch": 0.08990501435829468, "grad_norm": 1.9930057525634766, "learning_rate": 3.962524237635384e-05, "loss": 0.1045, "step": 1628 }, { "epoch": 0.08996023856858847, "grad_norm": 2.1492223739624023, "learning_rate": 3.9624552795166696e-05, "loss": 0.0901, "step": 1629 }, { "epoch": 0.09001546277888227, "grad_norm": 0.13839855790138245, "learning_rate": 3.962386258613424e-05, "loss": 0.0053, "step": 1630 }, { "epoch": 0.09007068698917606, "grad_norm": 5.4850754737854, "learning_rate": 3.962317174927856e-05, "loss": 0.9495, "step": 1631 }, { "epoch": 0.09012591119946985, "grad_norm": 0.40024176239967346, "learning_rate": 3.962248028462174e-05, "loss": 0.0128, "step": 1632 }, { "epoch": 0.09018113540976364, "grad_norm": 2.2890524864196777, "learning_rate": 3.962178819218592e-05, "loss": 0.7561, "step": 1633 }, { "epoch": 0.09023635962005744, "grad_norm": 0.24152112007141113, "learning_rate": 3.962109547199323e-05, "loss": 0.01, "step": 1634 }, { "epoch": 0.09029158383035123, "grad_norm": 3.9335358142852783, "learning_rate": 3.9620402124065854e-05, "loss": 0.9291, "step": 1635 }, { "epoch": 0.09034680804064502, "grad_norm": 1.6748377084732056, "learning_rate": 3.961970814842594e-05, "loss": 0.0605, "step": 1636 }, { "epoch": 0.0904020322509388, "grad_norm": 5.9019012451171875, "learning_rate": 3.961901354509572e-05, "loss": 0.3318, "step": 1637 }, { "epoch": 0.09045725646123261, "grad_norm": 1.4260703325271606, "learning_rate": 3.961831831409739e-05, "loss": 0.0498, "step": 1638 }, { "epoch": 0.0905124806715264, "grad_norm": 0.996099054813385, "learning_rate": 3.961762245545321e-05, "loss": 0.0548, "step": 1639 }, { "epoch": 0.09056770488182019, "grad_norm": 4.327800750732422, "learning_rate": 3.961692596918544e-05, "loss": 1.0296, "step": 1640 }, { "epoch": 0.09062292909211399, "grad_norm": 2.1230289936065674, "learning_rate": 3.961622885531636e-05, "loss": 0.0743, "step": 1641 }, { "epoch": 0.09067815330240778, "grad_norm": 4.124722480773926, "learning_rate": 3.961553111386828e-05, "loss": 0.9175, "step": 1642 }, { "epoch": 0.09073337751270157, "grad_norm": 1.3530722856521606, "learning_rate": 3.9614832744863514e-05, "loss": 0.0904, "step": 1643 }, { "epoch": 0.09078860172299535, "grad_norm": 3.096574306488037, "learning_rate": 3.9614133748324404e-05, "loss": 0.9222, "step": 1644 }, { "epoch": 0.09084382593328916, "grad_norm": 2.3204963207244873, "learning_rate": 3.961343412427332e-05, "loss": 0.2773, "step": 1645 }, { "epoch": 0.09089905014358295, "grad_norm": 1.1677640676498413, "learning_rate": 3.9612733872732636e-05, "loss": 0.0545, "step": 1646 }, { "epoch": 0.09095427435387674, "grad_norm": 0.4038540720939636, "learning_rate": 3.961203299372477e-05, "loss": 0.0124, "step": 1647 }, { "epoch": 0.09100949856417054, "grad_norm": 2.249890089035034, "learning_rate": 3.961133148727213e-05, "loss": 0.047, "step": 1648 }, { "epoch": 0.09106472277446433, "grad_norm": 4.795877456665039, "learning_rate": 3.9610629353397164e-05, "loss": 0.6408, "step": 1649 }, { "epoch": 0.09111994698475812, "grad_norm": 0.969131350517273, "learning_rate": 3.960992659212234e-05, "loss": 0.0397, "step": 1650 }, { "epoch": 0.0911751711950519, "grad_norm": 3.0265421867370605, "learning_rate": 3.960922320347013e-05, "loss": 0.3075, "step": 1651 }, { "epoch": 0.09123039540534571, "grad_norm": 0.14341145753860474, "learning_rate": 3.960851918746305e-05, "loss": 0.004, "step": 1652 }, { "epoch": 0.0912856196156395, "grad_norm": 1.1775572299957275, "learning_rate": 3.960781454412362e-05, "loss": 0.0483, "step": 1653 }, { "epoch": 0.09134084382593328, "grad_norm": 3.4445064067840576, "learning_rate": 3.960710927347438e-05, "loss": 0.7533, "step": 1654 }, { "epoch": 0.09139606803622709, "grad_norm": 1.0183085203170776, "learning_rate": 3.9606403375537894e-05, "loss": 0.0268, "step": 1655 }, { "epoch": 0.09145129224652088, "grad_norm": 2.226609468460083, "learning_rate": 3.960569685033675e-05, "loss": 0.2493, "step": 1656 }, { "epoch": 0.09150651645681467, "grad_norm": 0.1525602787733078, "learning_rate": 3.9604989697893547e-05, "loss": 0.004, "step": 1657 }, { "epoch": 0.09156174066710845, "grad_norm": 0.36345040798187256, "learning_rate": 3.960428191823091e-05, "loss": 0.0084, "step": 1658 }, { "epoch": 0.09161696487740226, "grad_norm": 2.7217559814453125, "learning_rate": 3.9603573511371484e-05, "loss": 0.3796, "step": 1659 }, { "epoch": 0.09167218908769605, "grad_norm": 1.0995630025863647, "learning_rate": 3.960286447733793e-05, "loss": 0.0526, "step": 1660 }, { "epoch": 0.09172741329798983, "grad_norm": 0.9625577926635742, "learning_rate": 3.960215481615294e-05, "loss": 0.0426, "step": 1661 }, { "epoch": 0.09178263750828364, "grad_norm": 1.7386606931686401, "learning_rate": 3.96014445278392e-05, "loss": 0.2148, "step": 1662 }, { "epoch": 0.09183786171857743, "grad_norm": 0.4109165370464325, "learning_rate": 3.960073361241946e-05, "loss": 0.014, "step": 1663 }, { "epoch": 0.09189308592887122, "grad_norm": 3.132199287414551, "learning_rate": 3.960002206991645e-05, "loss": 0.3032, "step": 1664 }, { "epoch": 0.091948310139165, "grad_norm": 3.6013941764831543, "learning_rate": 3.959930990035293e-05, "loss": 0.5065, "step": 1665 }, { "epoch": 0.09200353434945881, "grad_norm": 1.204622745513916, "learning_rate": 3.959859710375169e-05, "loss": 0.0411, "step": 1666 }, { "epoch": 0.0920587585597526, "grad_norm": 0.7763097286224365, "learning_rate": 3.9597883680135536e-05, "loss": 0.041, "step": 1667 }, { "epoch": 0.09211398277004638, "grad_norm": 4.816957473754883, "learning_rate": 3.959716962952729e-05, "loss": 1.0795, "step": 1668 }, { "epoch": 0.09216920698034019, "grad_norm": 2.581818103790283, "learning_rate": 3.9596454951949796e-05, "loss": 0.2091, "step": 1669 }, { "epoch": 0.09222443119063398, "grad_norm": 0.2502744197845459, "learning_rate": 3.9595739647425924e-05, "loss": 0.0103, "step": 1670 }, { "epoch": 0.09227965540092777, "grad_norm": 0.33036595582962036, "learning_rate": 3.959502371597855e-05, "loss": 0.0098, "step": 1671 }, { "epoch": 0.09233487961122155, "grad_norm": 2.411400556564331, "learning_rate": 3.959430715763058e-05, "loss": 0.1662, "step": 1672 }, { "epoch": 0.09239010382151536, "grad_norm": 3.1283023357391357, "learning_rate": 3.9593589972404946e-05, "loss": 0.2515, "step": 1673 }, { "epoch": 0.09244532803180915, "grad_norm": 5.958460807800293, "learning_rate": 3.959287216032459e-05, "loss": 1.576, "step": 1674 }, { "epoch": 0.09250055224210293, "grad_norm": 0.9291479587554932, "learning_rate": 3.9592153721412474e-05, "loss": 0.0331, "step": 1675 }, { "epoch": 0.09255577645239674, "grad_norm": 0.4455602765083313, "learning_rate": 3.959143465569158e-05, "loss": 0.0076, "step": 1676 }, { "epoch": 0.09261100066269053, "grad_norm": 4.570846080780029, "learning_rate": 3.959071496318492e-05, "loss": 1.0938, "step": 1677 }, { "epoch": 0.09266622487298432, "grad_norm": 3.3478100299835205, "learning_rate": 3.958999464391551e-05, "loss": 0.9878, "step": 1678 }, { "epoch": 0.0927214490832781, "grad_norm": 2.977404832839966, "learning_rate": 3.958927369790641e-05, "loss": 0.4306, "step": 1679 }, { "epoch": 0.0927766732935719, "grad_norm": 2.6259305477142334, "learning_rate": 3.958855212518067e-05, "loss": 0.1074, "step": 1680 }, { "epoch": 0.0928318975038657, "grad_norm": 0.6852043867111206, "learning_rate": 3.958782992576138e-05, "loss": 0.0238, "step": 1681 }, { "epoch": 0.09288712171415948, "grad_norm": 5.18745756149292, "learning_rate": 3.958710709967165e-05, "loss": 1.2858, "step": 1682 }, { "epoch": 0.09294234592445327, "grad_norm": 3.467479944229126, "learning_rate": 3.958638364693461e-05, "loss": 0.6731, "step": 1683 }, { "epoch": 0.09299757013474708, "grad_norm": 0.06022796034812927, "learning_rate": 3.9585659567573384e-05, "loss": 0.0012, "step": 1684 }, { "epoch": 0.09305279434504087, "grad_norm": 2.4043262004852295, "learning_rate": 3.958493486161116e-05, "loss": 0.1963, "step": 1685 }, { "epoch": 0.09310801855533465, "grad_norm": 0.9734740853309631, "learning_rate": 3.958420952907111e-05, "loss": 0.0535, "step": 1686 }, { "epoch": 0.09316324276562846, "grad_norm": 0.8474118709564209, "learning_rate": 3.9583483569976444e-05, "loss": 0.0284, "step": 1687 }, { "epoch": 0.09321846697592225, "grad_norm": 4.306432723999023, "learning_rate": 3.958275698435039e-05, "loss": 0.2982, "step": 1688 }, { "epoch": 0.09327369118621603, "grad_norm": 3.85347580909729, "learning_rate": 3.958202977221619e-05, "loss": 0.5206, "step": 1689 }, { "epoch": 0.09332891539650982, "grad_norm": 4.430119037628174, "learning_rate": 3.95813019335971e-05, "loss": 0.855, "step": 1690 }, { "epoch": 0.09338413960680363, "grad_norm": 0.8218241930007935, "learning_rate": 3.958057346851642e-05, "loss": 0.0251, "step": 1691 }, { "epoch": 0.09343936381709742, "grad_norm": 5.987943172454834, "learning_rate": 3.9579844376997455e-05, "loss": 0.6663, "step": 1692 }, { "epoch": 0.0934945880273912, "grad_norm": 2.0171961784362793, "learning_rate": 3.957911465906353e-05, "loss": 0.3053, "step": 1693 }, { "epoch": 0.093549812237685, "grad_norm": 1.6894716024398804, "learning_rate": 3.957838431473798e-05, "loss": 0.1385, "step": 1694 }, { "epoch": 0.0936050364479788, "grad_norm": 0.05575387924909592, "learning_rate": 3.957765334404419e-05, "loss": 0.0025, "step": 1695 }, { "epoch": 0.09366026065827258, "grad_norm": 4.71719217300415, "learning_rate": 3.957692174700552e-05, "loss": 0.1608, "step": 1696 }, { "epoch": 0.09371548486856637, "grad_norm": 0.3820231258869171, "learning_rate": 3.9576189523645396e-05, "loss": 0.0111, "step": 1697 }, { "epoch": 0.09377070907886018, "grad_norm": 3.8067731857299805, "learning_rate": 3.957545667398724e-05, "loss": 1.3178, "step": 1698 }, { "epoch": 0.09382593328915396, "grad_norm": 0.17576442658901215, "learning_rate": 3.957472319805449e-05, "loss": 0.0071, "step": 1699 }, { "epoch": 0.09388115749944775, "grad_norm": 3.12349534034729, "learning_rate": 3.9573989095870625e-05, "loss": 0.3322, "step": 1700 }, { "epoch": 0.09393638170974156, "grad_norm": 2.904250383377075, "learning_rate": 3.9573254367459125e-05, "loss": 0.9497, "step": 1701 }, { "epoch": 0.09399160592003535, "grad_norm": 5.172834873199463, "learning_rate": 3.957251901284349e-05, "loss": 1.1187, "step": 1702 }, { "epoch": 0.09404683013032913, "grad_norm": 4.274576187133789, "learning_rate": 3.9571783032047254e-05, "loss": 0.6744, "step": 1703 }, { "epoch": 0.09410205434062292, "grad_norm": 0.10399606823921204, "learning_rate": 3.9571046425093964e-05, "loss": 0.0034, "step": 1704 }, { "epoch": 0.09415727855091673, "grad_norm": 4.679492950439453, "learning_rate": 3.957030919200718e-05, "loss": 0.1314, "step": 1705 }, { "epoch": 0.09421250276121051, "grad_norm": 0.08757317811250687, "learning_rate": 3.956957133281049e-05, "loss": 0.003, "step": 1706 }, { "epoch": 0.0942677269715043, "grad_norm": 1.85794997215271, "learning_rate": 3.95688328475275e-05, "loss": 0.0663, "step": 1707 }, { "epoch": 0.0943229511817981, "grad_norm": 0.08794226497411728, "learning_rate": 3.956809373618184e-05, "loss": 0.0032, "step": 1708 }, { "epoch": 0.0943781753920919, "grad_norm": 5.17275333404541, "learning_rate": 3.956735399879715e-05, "loss": 0.2362, "step": 1709 }, { "epoch": 0.09443339960238568, "grad_norm": 0.08416518568992615, "learning_rate": 3.95666136353971e-05, "loss": 0.0025, "step": 1710 }, { "epoch": 0.09448862381267947, "grad_norm": 3.4518849849700928, "learning_rate": 3.9565872646005375e-05, "loss": 0.9139, "step": 1711 }, { "epoch": 0.09454384802297328, "grad_norm": 1.722957730293274, "learning_rate": 3.956513103064568e-05, "loss": 0.3943, "step": 1712 }, { "epoch": 0.09459907223326706, "grad_norm": 1.0579006671905518, "learning_rate": 3.9564388789341754e-05, "loss": 0.0515, "step": 1713 }, { "epoch": 0.09465429644356085, "grad_norm": 0.07928198575973511, "learning_rate": 3.9563645922117334e-05, "loss": 0.0031, "step": 1714 }, { "epoch": 0.09470952065385466, "grad_norm": 3.8048593997955322, "learning_rate": 3.956290242899617e-05, "loss": 0.4077, "step": 1715 }, { "epoch": 0.09476474486414845, "grad_norm": 2.6447107791900635, "learning_rate": 3.956215831000208e-05, "loss": 0.2629, "step": 1716 }, { "epoch": 0.09481996907444223, "grad_norm": 0.7696117758750916, "learning_rate": 3.956141356515885e-05, "loss": 0.0244, "step": 1717 }, { "epoch": 0.09487519328473602, "grad_norm": 0.9886699318885803, "learning_rate": 3.9560668194490306e-05, "loss": 0.0305, "step": 1718 }, { "epoch": 0.09493041749502983, "grad_norm": 0.10239847749471664, "learning_rate": 3.9559922198020305e-05, "loss": 0.0052, "step": 1719 }, { "epoch": 0.09498564170532361, "grad_norm": 0.2880316972732544, "learning_rate": 3.95591755757727e-05, "loss": 0.0077, "step": 1720 }, { "epoch": 0.0950408659156174, "grad_norm": 0.7657171487808228, "learning_rate": 3.9558428327771393e-05, "loss": 0.0273, "step": 1721 }, { "epoch": 0.0950960901259112, "grad_norm": 9.095829963684082, "learning_rate": 3.955768045404028e-05, "loss": 0.7494, "step": 1722 }, { "epoch": 0.095151314336205, "grad_norm": 2.38744854927063, "learning_rate": 3.9556931954603305e-05, "loss": 0.0385, "step": 1723 }, { "epoch": 0.09520653854649878, "grad_norm": 0.2275877743959427, "learning_rate": 3.9556182829484386e-05, "loss": 0.0042, "step": 1724 }, { "epoch": 0.09526176275679257, "grad_norm": 1.8768521547317505, "learning_rate": 3.955543307870751e-05, "loss": 0.1679, "step": 1725 }, { "epoch": 0.09531698696708638, "grad_norm": 3.8102290630340576, "learning_rate": 3.955468270229665e-05, "loss": 0.723, "step": 1726 }, { "epoch": 0.09537221117738016, "grad_norm": 0.9230690598487854, "learning_rate": 3.955393170027583e-05, "loss": 0.0334, "step": 1727 }, { "epoch": 0.09542743538767395, "grad_norm": 2.520219564437866, "learning_rate": 3.955318007266906e-05, "loss": 0.3843, "step": 1728 }, { "epoch": 0.09548265959796774, "grad_norm": 0.5958617329597473, "learning_rate": 3.9552427819500404e-05, "loss": 0.0223, "step": 1729 }, { "epoch": 0.09553788380826155, "grad_norm": 4.141596794128418, "learning_rate": 3.955167494079391e-05, "loss": 0.6695, "step": 1730 }, { "epoch": 0.09559310801855533, "grad_norm": 0.15574009716510773, "learning_rate": 3.9550921436573675e-05, "loss": 0.005, "step": 1731 }, { "epoch": 0.09564833222884912, "grad_norm": 1.1113197803497314, "learning_rate": 3.955016730686381e-05, "loss": 0.0509, "step": 1732 }, { "epoch": 0.09570355643914293, "grad_norm": 2.006068229675293, "learning_rate": 3.9549412551688426e-05, "loss": 0.4148, "step": 1733 }, { "epoch": 0.09575878064943671, "grad_norm": 0.0899488553404808, "learning_rate": 3.9548657171071685e-05, "loss": 0.0025, "step": 1734 }, { "epoch": 0.0958140048597305, "grad_norm": 0.11261143535375595, "learning_rate": 3.954790116503775e-05, "loss": 0.003, "step": 1735 }, { "epoch": 0.09586922907002429, "grad_norm": 0.10627256333827972, "learning_rate": 3.954714453361081e-05, "loss": 0.0047, "step": 1736 }, { "epoch": 0.0959244532803181, "grad_norm": 5.053688049316406, "learning_rate": 3.954638727681506e-05, "loss": 1.771, "step": 1737 }, { "epoch": 0.09597967749061188, "grad_norm": 4.014666557312012, "learning_rate": 3.954562939467473e-05, "loss": 1.0522, "step": 1738 }, { "epoch": 0.09603490170090567, "grad_norm": 0.4757901728153229, "learning_rate": 3.954487088721409e-05, "loss": 0.0176, "step": 1739 }, { "epoch": 0.09609012591119948, "grad_norm": 0.12398957461118698, "learning_rate": 3.954411175445737e-05, "loss": 0.0036, "step": 1740 }, { "epoch": 0.09614535012149326, "grad_norm": 0.014280086383223534, "learning_rate": 3.954335199642889e-05, "loss": 0.0005, "step": 1741 }, { "epoch": 0.09620057433178705, "grad_norm": 0.850051999092102, "learning_rate": 3.954259161315293e-05, "loss": 0.0333, "step": 1742 }, { "epoch": 0.09625579854208084, "grad_norm": 0.18621373176574707, "learning_rate": 3.9541830604653836e-05, "loss": 0.0056, "step": 1743 }, { "epoch": 0.09631102275237464, "grad_norm": 3.4285576343536377, "learning_rate": 3.954106897095595e-05, "loss": 0.7418, "step": 1744 }, { "epoch": 0.09636624696266843, "grad_norm": 0.917230486869812, "learning_rate": 3.954030671208363e-05, "loss": 0.0336, "step": 1745 }, { "epoch": 0.09642147117296222, "grad_norm": 0.0894661620259285, "learning_rate": 3.9539543828061273e-05, "loss": 0.0046, "step": 1746 }, { "epoch": 0.09647669538325603, "grad_norm": 3.6285085678100586, "learning_rate": 3.9538780318913285e-05, "loss": 0.4342, "step": 1747 }, { "epoch": 0.09653191959354981, "grad_norm": 3.8307459354400635, "learning_rate": 3.953801618466408e-05, "loss": 0.3773, "step": 1748 }, { "epoch": 0.0965871438038436, "grad_norm": 1.2564431428909302, "learning_rate": 3.953725142533813e-05, "loss": 0.0143, "step": 1749 }, { "epoch": 0.09664236801413739, "grad_norm": 3.036212921142578, "learning_rate": 3.9536486040959876e-05, "loss": 0.3365, "step": 1750 }, { "epoch": 0.0966975922244312, "grad_norm": 4.29620361328125, "learning_rate": 3.953572003155382e-05, "loss": 1.0811, "step": 1751 }, { "epoch": 0.09675281643472498, "grad_norm": 6.132455825805664, "learning_rate": 3.953495339714447e-05, "loss": 2.3011, "step": 1752 }, { "epoch": 0.09680804064501877, "grad_norm": 1.589255928993225, "learning_rate": 3.9534186137756336e-05, "loss": 0.3658, "step": 1753 }, { "epoch": 0.09686326485531258, "grad_norm": 2.6233229637145996, "learning_rate": 3.9533418253413975e-05, "loss": 0.5737, "step": 1754 }, { "epoch": 0.09691848906560636, "grad_norm": 3.006251573562622, "learning_rate": 3.953264974414196e-05, "loss": 0.8991, "step": 1755 }, { "epoch": 0.09697371327590015, "grad_norm": 4.544569969177246, "learning_rate": 3.953188060996488e-05, "loss": 0.3582, "step": 1756 }, { "epoch": 0.09702893748619394, "grad_norm": 5.952131271362305, "learning_rate": 3.953111085090732e-05, "loss": 0.3518, "step": 1757 }, { "epoch": 0.09708416169648774, "grad_norm": 5.159146308898926, "learning_rate": 3.9530340466993936e-05, "loss": 0.0932, "step": 1758 }, { "epoch": 0.09713938590678153, "grad_norm": 0.45276325941085815, "learning_rate": 3.952956945824935e-05, "loss": 0.011, "step": 1759 }, { "epoch": 0.09719461011707532, "grad_norm": 3.4293243885040283, "learning_rate": 3.952879782469824e-05, "loss": 0.3628, "step": 1760 }, { "epoch": 0.09724983432736913, "grad_norm": 3.5160157680511475, "learning_rate": 3.9528025566365294e-05, "loss": 1.0209, "step": 1761 }, { "epoch": 0.09730505853766291, "grad_norm": 4.425302982330322, "learning_rate": 3.952725268327521e-05, "loss": 1.198, "step": 1762 }, { "epoch": 0.0973602827479567, "grad_norm": 1.3268077373504639, "learning_rate": 3.9526479175452735e-05, "loss": 0.0321, "step": 1763 }, { "epoch": 0.09741550695825049, "grad_norm": 4.552794933319092, "learning_rate": 3.952570504292259e-05, "loss": 2.2176, "step": 1764 }, { "epoch": 0.0974707311685443, "grad_norm": 1.5412719249725342, "learning_rate": 3.952493028570956e-05, "loss": 0.0535, "step": 1765 }, { "epoch": 0.09752595537883808, "grad_norm": 0.4105844795703888, "learning_rate": 3.9524154903838423e-05, "loss": 0.0166, "step": 1766 }, { "epoch": 0.09758117958913187, "grad_norm": 1.257757544517517, "learning_rate": 3.952337889733399e-05, "loss": 0.0395, "step": 1767 }, { "epoch": 0.09763640379942568, "grad_norm": 0.2759515643119812, "learning_rate": 3.952260226622108e-05, "loss": 0.0099, "step": 1768 }, { "epoch": 0.09769162800971946, "grad_norm": 0.16007816791534424, "learning_rate": 3.952182501052455e-05, "loss": 0.0036, "step": 1769 }, { "epoch": 0.09774685222001325, "grad_norm": 3.5914485454559326, "learning_rate": 3.9521047130269254e-05, "loss": 0.2049, "step": 1770 }, { "epoch": 0.09780207643030704, "grad_norm": 3.7395102977752686, "learning_rate": 3.95202686254801e-05, "loss": 0.6581, "step": 1771 }, { "epoch": 0.09785730064060084, "grad_norm": 5.2745819091796875, "learning_rate": 3.951948949618196e-05, "loss": 0.914, "step": 1772 }, { "epoch": 0.09791252485089463, "grad_norm": 0.07830572873353958, "learning_rate": 3.95187097423998e-05, "loss": 0.0027, "step": 1773 }, { "epoch": 0.09796774906118842, "grad_norm": 5.0487751960754395, "learning_rate": 3.9517929364158535e-05, "loss": 0.5478, "step": 1774 }, { "epoch": 0.09802297327148221, "grad_norm": 1.5030220746994019, "learning_rate": 3.9517148361483155e-05, "loss": 0.0927, "step": 1775 }, { "epoch": 0.09807819748177601, "grad_norm": 0.377191424369812, "learning_rate": 3.951636673439863e-05, "loss": 0.0134, "step": 1776 }, { "epoch": 0.0981334216920698, "grad_norm": 4.658609390258789, "learning_rate": 3.951558448292998e-05, "loss": 1.1776, "step": 1777 }, { "epoch": 0.09818864590236359, "grad_norm": 1.2807648181915283, "learning_rate": 3.951480160710222e-05, "loss": 0.045, "step": 1778 }, { "epoch": 0.0982438701126574, "grad_norm": 0.46222636103630066, "learning_rate": 3.95140181069404e-05, "loss": 0.0134, "step": 1779 }, { "epoch": 0.09829909432295118, "grad_norm": 6.088967323303223, "learning_rate": 3.951323398246958e-05, "loss": 0.5458, "step": 1780 }, { "epoch": 0.09835431853324497, "grad_norm": 0.3743405044078827, "learning_rate": 3.951244923371486e-05, "loss": 0.0107, "step": 1781 }, { "epoch": 0.09840954274353876, "grad_norm": 1.5326555967330933, "learning_rate": 3.9511663860701344e-05, "loss": 0.0367, "step": 1782 }, { "epoch": 0.09846476695383256, "grad_norm": 0.22864940762519836, "learning_rate": 3.951087786345415e-05, "loss": 0.0083, "step": 1783 }, { "epoch": 0.09851999116412635, "grad_norm": 0.6273927092552185, "learning_rate": 3.9510091241998426e-05, "loss": 0.0269, "step": 1784 }, { "epoch": 0.09857521537442014, "grad_norm": 0.06877343356609344, "learning_rate": 3.950930399635934e-05, "loss": 0.0026, "step": 1785 }, { "epoch": 0.09863043958471394, "grad_norm": 0.10298381745815277, "learning_rate": 3.950851612656208e-05, "loss": 0.0034, "step": 1786 }, { "epoch": 0.09868566379500773, "grad_norm": 0.07977601885795593, "learning_rate": 3.9507727632631854e-05, "loss": 0.0029, "step": 1787 }, { "epoch": 0.09874088800530152, "grad_norm": 2.7114791870117188, "learning_rate": 3.950693851459388e-05, "loss": 0.4589, "step": 1788 }, { "epoch": 0.09879611221559531, "grad_norm": 3.507638931274414, "learning_rate": 3.950614877247341e-05, "loss": 0.6471, "step": 1789 }, { "epoch": 0.09885133642588911, "grad_norm": 0.06869431585073471, "learning_rate": 3.950535840629571e-05, "loss": 0.0021, "step": 1790 }, { "epoch": 0.0989065606361829, "grad_norm": 1.3439109325408936, "learning_rate": 3.950456741608607e-05, "loss": 0.0618, "step": 1791 }, { "epoch": 0.09896178484647669, "grad_norm": 3.779801368713379, "learning_rate": 3.9503775801869785e-05, "loss": 0.0628, "step": 1792 }, { "epoch": 0.0990170090567705, "grad_norm": 0.3785991966724396, "learning_rate": 3.950298356367219e-05, "loss": 0.0121, "step": 1793 }, { "epoch": 0.09907223326706428, "grad_norm": 0.23933500051498413, "learning_rate": 3.950219070151862e-05, "loss": 0.0081, "step": 1794 }, { "epoch": 0.09912745747735807, "grad_norm": 0.0699283704161644, "learning_rate": 3.950139721543446e-05, "loss": 0.002, "step": 1795 }, { "epoch": 0.09918268168765186, "grad_norm": 4.848519802093506, "learning_rate": 3.9500603105445086e-05, "loss": 1.1687, "step": 1796 }, { "epoch": 0.09923790589794566, "grad_norm": 0.7515017986297607, "learning_rate": 3.94998083715759e-05, "loss": 0.0116, "step": 1797 }, { "epoch": 0.09929313010823945, "grad_norm": 3.0577986240386963, "learning_rate": 3.949901301385232e-05, "loss": 0.7856, "step": 1798 }, { "epoch": 0.09934835431853324, "grad_norm": 1.1591882705688477, "learning_rate": 3.949821703229982e-05, "loss": 0.037, "step": 1799 }, { "epoch": 0.09940357852882704, "grad_norm": 0.8873463273048401, "learning_rate": 3.949742042694384e-05, "loss": 0.0352, "step": 1800 }, { "epoch": 0.09945880273912083, "grad_norm": 0.8027803897857666, "learning_rate": 3.949662319780987e-05, "loss": 0.0975, "step": 1801 }, { "epoch": 0.09951402694941462, "grad_norm": 2.9251797199249268, "learning_rate": 3.949582534492343e-05, "loss": 0.1355, "step": 1802 }, { "epoch": 0.09956925115970841, "grad_norm": 4.30219841003418, "learning_rate": 3.949502686831002e-05, "loss": 0.5141, "step": 1803 }, { "epoch": 0.09962447537000221, "grad_norm": 1.98258638381958, "learning_rate": 3.949422776799521e-05, "loss": 0.0748, "step": 1804 }, { "epoch": 0.099679699580296, "grad_norm": 1.1854650974273682, "learning_rate": 3.9493428044004555e-05, "loss": 0.1209, "step": 1805 }, { "epoch": 0.09973492379058979, "grad_norm": 1.4037429094314575, "learning_rate": 3.9492627696363644e-05, "loss": 0.1095, "step": 1806 }, { "epoch": 0.0997901480008836, "grad_norm": 1.9930312633514404, "learning_rate": 3.949182672509808e-05, "loss": 0.203, "step": 1807 }, { "epoch": 0.09984537221117738, "grad_norm": 2.016266345977783, "learning_rate": 3.9491025130233484e-05, "loss": 0.0625, "step": 1808 }, { "epoch": 0.09990059642147117, "grad_norm": 0.3425273597240448, "learning_rate": 3.9490222911795504e-05, "loss": 0.0101, "step": 1809 }, { "epoch": 0.09995582063176496, "grad_norm": 6.444084167480469, "learning_rate": 3.948942006980981e-05, "loss": 1.447, "step": 1810 }, { "epoch": 0.10001104484205876, "grad_norm": 2.5517423152923584, "learning_rate": 3.948861660430209e-05, "loss": 0.3518, "step": 1811 }, { "epoch": 0.10006626905235255, "grad_norm": 4.889651775360107, "learning_rate": 3.9487812515298034e-05, "loss": 0.6417, "step": 1812 }, { "epoch": 0.10012149326264634, "grad_norm": 3.315183401107788, "learning_rate": 3.948700780282338e-05, "loss": 0.0999, "step": 1813 }, { "epoch": 0.10017671747294014, "grad_norm": 5.450104713439941, "learning_rate": 3.9486202466903866e-05, "loss": 1.884, "step": 1814 }, { "epoch": 0.10023194168323393, "grad_norm": 0.07789051532745361, "learning_rate": 3.9485396507565265e-05, "loss": 0.0028, "step": 1815 }, { "epoch": 0.10028716589352772, "grad_norm": 0.4040836691856384, "learning_rate": 3.948458992483335e-05, "loss": 0.0162, "step": 1816 }, { "epoch": 0.10034239010382151, "grad_norm": 3.8166449069976807, "learning_rate": 3.9483782718733945e-05, "loss": 0.5621, "step": 1817 }, { "epoch": 0.10039761431411531, "grad_norm": 4.7843451499938965, "learning_rate": 3.948297488929286e-05, "loss": 0.7317, "step": 1818 }, { "epoch": 0.1004528385244091, "grad_norm": 0.05491849407553673, "learning_rate": 3.948216643653594e-05, "loss": 0.0018, "step": 1819 }, { "epoch": 0.10050806273470289, "grad_norm": 0.4479728639125824, "learning_rate": 3.948135736048905e-05, "loss": 0.013, "step": 1820 }, { "epoch": 0.10056328694499668, "grad_norm": 1.7518436908721924, "learning_rate": 3.948054766117808e-05, "loss": 0.0739, "step": 1821 }, { "epoch": 0.10061851115529048, "grad_norm": 0.5012490153312683, "learning_rate": 3.947973733862893e-05, "loss": 0.0115, "step": 1822 }, { "epoch": 0.10067373536558427, "grad_norm": 0.7279697060585022, "learning_rate": 3.9478926392867525e-05, "loss": 0.0222, "step": 1823 }, { "epoch": 0.10072895957587806, "grad_norm": 3.7595267295837402, "learning_rate": 3.947811482391981e-05, "loss": 0.2832, "step": 1824 }, { "epoch": 0.10078418378617186, "grad_norm": 0.274069607257843, "learning_rate": 3.9477302631811756e-05, "loss": 0.0059, "step": 1825 }, { "epoch": 0.10083940799646565, "grad_norm": 0.9618537425994873, "learning_rate": 3.947648981656934e-05, "loss": 0.0323, "step": 1826 }, { "epoch": 0.10089463220675944, "grad_norm": 2.1447885036468506, "learning_rate": 3.947567637821856e-05, "loss": 0.1252, "step": 1827 }, { "epoch": 0.10094985641705323, "grad_norm": 0.08979836851358414, "learning_rate": 3.947486231678546e-05, "loss": 0.0029, "step": 1828 }, { "epoch": 0.10100508062734703, "grad_norm": 0.7130630016326904, "learning_rate": 3.9474047632296065e-05, "loss": 0.018, "step": 1829 }, { "epoch": 0.10106030483764082, "grad_norm": 3.8942415714263916, "learning_rate": 3.947323232477645e-05, "loss": 0.6128, "step": 1830 }, { "epoch": 0.10111552904793461, "grad_norm": 1.8521581888198853, "learning_rate": 3.947241639425269e-05, "loss": 0.2245, "step": 1831 }, { "epoch": 0.10117075325822841, "grad_norm": 4.2162628173828125, "learning_rate": 3.947159984075089e-05, "loss": 0.6615, "step": 1832 }, { "epoch": 0.1012259774685222, "grad_norm": 2.8282337188720703, "learning_rate": 3.947078266429718e-05, "loss": 0.0675, "step": 1833 }, { "epoch": 0.10128120167881599, "grad_norm": 2.789801597595215, "learning_rate": 3.946996486491771e-05, "loss": 0.1858, "step": 1834 }, { "epoch": 0.10133642588910978, "grad_norm": 3.158433198928833, "learning_rate": 3.946914644263863e-05, "loss": 0.4521, "step": 1835 }, { "epoch": 0.10139165009940358, "grad_norm": 0.07611402869224548, "learning_rate": 3.946832739748613e-05, "loss": 0.003, "step": 1836 }, { "epoch": 0.10144687430969737, "grad_norm": 0.04331730678677559, "learning_rate": 3.946750772948641e-05, "loss": 0.0016, "step": 1837 }, { "epoch": 0.10150209851999116, "grad_norm": 5.121640682220459, "learning_rate": 3.94666874386657e-05, "loss": 0.615, "step": 1838 }, { "epoch": 0.10155732273028496, "grad_norm": 0.05991014465689659, "learning_rate": 3.946586652505024e-05, "loss": 0.0021, "step": 1839 }, { "epoch": 0.10161254694057875, "grad_norm": 0.712252140045166, "learning_rate": 3.946504498866629e-05, "loss": 0.0299, "step": 1840 }, { "epoch": 0.10166777115087254, "grad_norm": 1.2131134271621704, "learning_rate": 3.946422282954014e-05, "loss": 0.0543, "step": 1841 }, { "epoch": 0.10172299536116633, "grad_norm": 0.271463006734848, "learning_rate": 3.946340004769809e-05, "loss": 0.0071, "step": 1842 }, { "epoch": 0.10177821957146013, "grad_norm": 2.529690980911255, "learning_rate": 3.9462576643166454e-05, "loss": 0.1827, "step": 1843 }, { "epoch": 0.10183344378175392, "grad_norm": 1.7711390256881714, "learning_rate": 3.946175261597159e-05, "loss": 0.2634, "step": 1844 }, { "epoch": 0.10188866799204771, "grad_norm": 3.2469894886016846, "learning_rate": 3.946092796613986e-05, "loss": 0.1537, "step": 1845 }, { "epoch": 0.10194389220234151, "grad_norm": 1.6659448146820068, "learning_rate": 3.946010269369763e-05, "loss": 0.0688, "step": 1846 }, { "epoch": 0.1019991164126353, "grad_norm": 2.9996604919433594, "learning_rate": 3.945927679867132e-05, "loss": 0.1249, "step": 1847 }, { "epoch": 0.10205434062292909, "grad_norm": 0.1336989849805832, "learning_rate": 3.945845028108735e-05, "loss": 0.0054, "step": 1848 }, { "epoch": 0.10210956483322288, "grad_norm": 1.9456725120544434, "learning_rate": 3.945762314097216e-05, "loss": 0.2261, "step": 1849 }, { "epoch": 0.10216478904351668, "grad_norm": 3.5483837127685547, "learning_rate": 3.945679537835221e-05, "loss": 1.1412, "step": 1850 }, { "epoch": 0.10222001325381047, "grad_norm": 1.8849297761917114, "learning_rate": 3.945596699325398e-05, "loss": 0.1106, "step": 1851 }, { "epoch": 0.10227523746410426, "grad_norm": 3.9947056770324707, "learning_rate": 3.945513798570398e-05, "loss": 0.9221, "step": 1852 }, { "epoch": 0.10233046167439806, "grad_norm": 1.5961984395980835, "learning_rate": 3.945430835572873e-05, "loss": 0.2639, "step": 1853 }, { "epoch": 0.10238568588469185, "grad_norm": 4.096810340881348, "learning_rate": 3.9453478103354775e-05, "loss": 0.9031, "step": 1854 }, { "epoch": 0.10244091009498564, "grad_norm": 2.323713779449463, "learning_rate": 3.9452647228608674e-05, "loss": 0.6196, "step": 1855 }, { "epoch": 0.10249613430527943, "grad_norm": 0.03996570408344269, "learning_rate": 3.945181573151701e-05, "loss": 0.0013, "step": 1856 }, { "epoch": 0.10255135851557323, "grad_norm": 1.9866610765457153, "learning_rate": 3.945098361210637e-05, "loss": 0.1826, "step": 1857 }, { "epoch": 0.10260658272586702, "grad_norm": 0.09724926948547363, "learning_rate": 3.94501508704034e-05, "loss": 0.0026, "step": 1858 }, { "epoch": 0.10266180693616081, "grad_norm": 0.7513957619667053, "learning_rate": 3.944931750643473e-05, "loss": 0.026, "step": 1859 }, { "epoch": 0.10271703114645461, "grad_norm": 5.404149055480957, "learning_rate": 3.944848352022703e-05, "loss": 0.6159, "step": 1860 }, { "epoch": 0.1027722553567484, "grad_norm": 0.30348169803619385, "learning_rate": 3.944764891180697e-05, "loss": 0.0129, "step": 1861 }, { "epoch": 0.10282747956704219, "grad_norm": 3.2898876667022705, "learning_rate": 3.944681368120126e-05, "loss": 0.2574, "step": 1862 }, { "epoch": 0.10288270377733598, "grad_norm": 2.1525063514709473, "learning_rate": 3.9445977828436615e-05, "loss": 0.2609, "step": 1863 }, { "epoch": 0.10293792798762978, "grad_norm": 2.4026811122894287, "learning_rate": 3.944514135353977e-05, "loss": 0.6281, "step": 1864 }, { "epoch": 0.10299315219792357, "grad_norm": 0.5025554299354553, "learning_rate": 3.94443042565375e-05, "loss": 0.0186, "step": 1865 }, { "epoch": 0.10304837640821736, "grad_norm": 3.0614211559295654, "learning_rate": 3.944346653745659e-05, "loss": 0.5009, "step": 1866 }, { "epoch": 0.10310360061851115, "grad_norm": 3.344888210296631, "learning_rate": 3.944262819632383e-05, "loss": 0.3701, "step": 1867 }, { "epoch": 0.10315882482880495, "grad_norm": 3.1452231407165527, "learning_rate": 3.944178923316604e-05, "loss": 0.7046, "step": 1868 }, { "epoch": 0.10321404903909874, "grad_norm": 1.796409249305725, "learning_rate": 3.9440949648010065e-05, "loss": 0.1076, "step": 1869 }, { "epoch": 0.10326927324939253, "grad_norm": 1.7252880334854126, "learning_rate": 3.9440109440882756e-05, "loss": 0.0667, "step": 1870 }, { "epoch": 0.10332449745968633, "grad_norm": 0.1437634825706482, "learning_rate": 3.943926861181101e-05, "loss": 0.0048, "step": 1871 }, { "epoch": 0.10337972166998012, "grad_norm": 2.3563687801361084, "learning_rate": 3.9438427160821726e-05, "loss": 0.5358, "step": 1872 }, { "epoch": 0.10343494588027391, "grad_norm": 0.17338915169239044, "learning_rate": 3.943758508794181e-05, "loss": 0.0052, "step": 1873 }, { "epoch": 0.1034901700905677, "grad_norm": 3.5067200660705566, "learning_rate": 3.943674239319822e-05, "loss": 0.3403, "step": 1874 }, { "epoch": 0.1035453943008615, "grad_norm": 1.3040796518325806, "learning_rate": 3.9435899076617895e-05, "loss": 0.0375, "step": 1875 }, { "epoch": 0.10360061851115529, "grad_norm": 7.666818141937256, "learning_rate": 3.943505513822783e-05, "loss": 2.476, "step": 1876 }, { "epoch": 0.10365584272144908, "grad_norm": 0.05824222415685654, "learning_rate": 3.943421057805503e-05, "loss": 0.0019, "step": 1877 }, { "epoch": 0.10371106693174288, "grad_norm": 0.050482749938964844, "learning_rate": 3.9433365396126496e-05, "loss": 0.0018, "step": 1878 }, { "epoch": 0.10376629114203667, "grad_norm": 0.1645081341266632, "learning_rate": 3.943251959246929e-05, "loss": 0.0046, "step": 1879 }, { "epoch": 0.10382151535233046, "grad_norm": 0.29751163721084595, "learning_rate": 3.943167316711045e-05, "loss": 0.0117, "step": 1880 }, { "epoch": 0.10387673956262425, "grad_norm": 0.21231690049171448, "learning_rate": 3.9430826120077064e-05, "loss": 0.0064, "step": 1881 }, { "epoch": 0.10393196377291805, "grad_norm": 3.2932233810424805, "learning_rate": 3.9429978451396245e-05, "loss": 0.7412, "step": 1882 }, { "epoch": 0.10398718798321184, "grad_norm": 0.3262636661529541, "learning_rate": 3.9429130161095096e-05, "loss": 0.0109, "step": 1883 }, { "epoch": 0.10404241219350563, "grad_norm": 3.6398508548736572, "learning_rate": 3.942828124920076e-05, "loss": 0.7392, "step": 1884 }, { "epoch": 0.10409763640379943, "grad_norm": 1.9821598529815674, "learning_rate": 3.9427431715740394e-05, "loss": 0.3438, "step": 1885 }, { "epoch": 0.10415286061409322, "grad_norm": 0.3809322714805603, "learning_rate": 3.942658156074118e-05, "loss": 0.0124, "step": 1886 }, { "epoch": 0.10420808482438701, "grad_norm": 0.07032771408557892, "learning_rate": 3.9425730784230326e-05, "loss": 0.0018, "step": 1887 }, { "epoch": 0.1042633090346808, "grad_norm": 4.249593257904053, "learning_rate": 3.942487938623503e-05, "loss": 0.0662, "step": 1888 }, { "epoch": 0.1043185332449746, "grad_norm": 2.9493839740753174, "learning_rate": 3.9424027366782554e-05, "loss": 0.3345, "step": 1889 }, { "epoch": 0.10437375745526839, "grad_norm": 4.653048515319824, "learning_rate": 3.9423174725900135e-05, "loss": 0.6989, "step": 1890 }, { "epoch": 0.10442898166556218, "grad_norm": 0.6197544932365417, "learning_rate": 3.942232146361506e-05, "loss": 0.0095, "step": 1891 }, { "epoch": 0.10448420587585598, "grad_norm": 1.1095075607299805, "learning_rate": 3.9421467579954635e-05, "loss": 0.023, "step": 1892 }, { "epoch": 0.10453943008614977, "grad_norm": 0.9942349195480347, "learning_rate": 3.942061307494617e-05, "loss": 0.0403, "step": 1893 }, { "epoch": 0.10459465429644356, "grad_norm": 4.598077297210693, "learning_rate": 3.9419757948617006e-05, "loss": 1.0562, "step": 1894 }, { "epoch": 0.10464987850673735, "grad_norm": 0.3658573031425476, "learning_rate": 3.9418902200994496e-05, "loss": 0.0099, "step": 1895 }, { "epoch": 0.10470510271703115, "grad_norm": 0.5681367516517639, "learning_rate": 3.941804583210602e-05, "loss": 0.0215, "step": 1896 }, { "epoch": 0.10476032692732494, "grad_norm": 1.248726487159729, "learning_rate": 3.941718884197898e-05, "loss": 0.0532, "step": 1897 }, { "epoch": 0.10481555113761873, "grad_norm": 0.18330980837345123, "learning_rate": 3.94163312306408e-05, "loss": 0.005, "step": 1898 }, { "epoch": 0.10487077534791253, "grad_norm": 2.0649642944335938, "learning_rate": 3.941547299811889e-05, "loss": 0.1941, "step": 1899 }, { "epoch": 0.10492599955820632, "grad_norm": 2.0507004261016846, "learning_rate": 3.941461414444073e-05, "loss": 0.2483, "step": 1900 }, { "epoch": 0.10498122376850011, "grad_norm": 0.09635133296251297, "learning_rate": 3.94137546696338e-05, "loss": 0.0044, "step": 1901 }, { "epoch": 0.1050364479787939, "grad_norm": 0.7285335659980774, "learning_rate": 3.941289457372559e-05, "loss": 0.0115, "step": 1902 }, { "epoch": 0.1050916721890877, "grad_norm": 0.3548639118671417, "learning_rate": 3.9412033856743616e-05, "loss": 0.0084, "step": 1903 }, { "epoch": 0.10514689639938149, "grad_norm": 2.3390564918518066, "learning_rate": 3.941117251871541e-05, "loss": 0.0938, "step": 1904 }, { "epoch": 0.10520212060967528, "grad_norm": 0.6077074408531189, "learning_rate": 3.9410310559668534e-05, "loss": 0.0059, "step": 1905 }, { "epoch": 0.10525734481996907, "grad_norm": 4.140383243560791, "learning_rate": 3.9409447979630566e-05, "loss": 0.4372, "step": 1906 }, { "epoch": 0.10531256903026287, "grad_norm": 0.22554099559783936, "learning_rate": 3.940858477862911e-05, "loss": 0.006, "step": 1907 }, { "epoch": 0.10536779324055666, "grad_norm": 1.3993537425994873, "learning_rate": 3.940772095669176e-05, "loss": 0.1447, "step": 1908 }, { "epoch": 0.10542301745085045, "grad_norm": 1.4448028802871704, "learning_rate": 3.940685651384617e-05, "loss": 0.0579, "step": 1909 }, { "epoch": 0.10547824166114425, "grad_norm": 1.4079291820526123, "learning_rate": 3.9405991450119993e-05, "loss": 0.0684, "step": 1910 }, { "epoch": 0.10553346587143804, "grad_norm": 1.122917890548706, "learning_rate": 3.94051257655409e-05, "loss": 0.0187, "step": 1911 }, { "epoch": 0.10558869008173183, "grad_norm": 0.30588915944099426, "learning_rate": 3.9404259460136594e-05, "loss": 0.0068, "step": 1912 }, { "epoch": 0.10564391429202562, "grad_norm": 4.197123050689697, "learning_rate": 3.940339253393478e-05, "loss": 0.4782, "step": 1913 }, { "epoch": 0.10569913850231942, "grad_norm": 0.06393325328826904, "learning_rate": 3.9402524986963203e-05, "loss": 0.0019, "step": 1914 }, { "epoch": 0.10575436271261321, "grad_norm": 4.503447532653809, "learning_rate": 3.9401656819249615e-05, "loss": 1.2471, "step": 1915 }, { "epoch": 0.105809586922907, "grad_norm": 0.3886789381504059, "learning_rate": 3.940078803082179e-05, "loss": 0.0098, "step": 1916 }, { "epoch": 0.1058648111332008, "grad_norm": 2.6403450965881348, "learning_rate": 3.939991862170753e-05, "loss": 0.071, "step": 1917 }, { "epoch": 0.10592003534349459, "grad_norm": 2.2269489765167236, "learning_rate": 3.939904859193465e-05, "loss": 0.184, "step": 1918 }, { "epoch": 0.10597525955378838, "grad_norm": 4.341691493988037, "learning_rate": 3.939817794153096e-05, "loss": 0.6888, "step": 1919 }, { "epoch": 0.10603048376408217, "grad_norm": 0.6092293858528137, "learning_rate": 3.9397306670524345e-05, "loss": 0.0133, "step": 1920 }, { "epoch": 0.10608570797437597, "grad_norm": 5.209187984466553, "learning_rate": 3.9396434778942666e-05, "loss": 0.6524, "step": 1921 }, { "epoch": 0.10614093218466976, "grad_norm": 0.8807324767112732, "learning_rate": 3.939556226681382e-05, "loss": 0.0242, "step": 1922 }, { "epoch": 0.10619615639496355, "grad_norm": 4.7748799324035645, "learning_rate": 3.9394689134165717e-05, "loss": 0.3517, "step": 1923 }, { "epoch": 0.10625138060525735, "grad_norm": 4.840809345245361, "learning_rate": 3.93938153810263e-05, "loss": 0.5312, "step": 1924 }, { "epoch": 0.10630660481555114, "grad_norm": 1.4773788452148438, "learning_rate": 3.939294100742351e-05, "loss": 0.0164, "step": 1925 }, { "epoch": 0.10636182902584493, "grad_norm": 0.6676299571990967, "learning_rate": 3.9392066013385335e-05, "loss": 0.0252, "step": 1926 }, { "epoch": 0.10641705323613872, "grad_norm": 3.6398448944091797, "learning_rate": 3.939119039893976e-05, "loss": 0.3121, "step": 1927 }, { "epoch": 0.10647227744643252, "grad_norm": 0.10346715897321701, "learning_rate": 3.9390314164114795e-05, "loss": 0.0041, "step": 1928 }, { "epoch": 0.10652750165672631, "grad_norm": 4.036705017089844, "learning_rate": 3.938943730893848e-05, "loss": 0.1542, "step": 1929 }, { "epoch": 0.1065827258670201, "grad_norm": 3.802316665649414, "learning_rate": 3.938855983343887e-05, "loss": 0.0595, "step": 1930 }, { "epoch": 0.1066379500773139, "grad_norm": 2.828401803970337, "learning_rate": 3.938768173764403e-05, "loss": 0.2932, "step": 1931 }, { "epoch": 0.10669317428760769, "grad_norm": 0.9266706109046936, "learning_rate": 3.938680302158206e-05, "loss": 0.0256, "step": 1932 }, { "epoch": 0.10674839849790148, "grad_norm": 0.051079776138067245, "learning_rate": 3.938592368528107e-05, "loss": 0.0015, "step": 1933 }, { "epoch": 0.10680362270819527, "grad_norm": 0.013793976046144962, "learning_rate": 3.938504372876919e-05, "loss": 0.0005, "step": 1934 }, { "epoch": 0.10685884691848907, "grad_norm": 0.21030853688716888, "learning_rate": 3.938416315207457e-05, "loss": 0.0059, "step": 1935 }, { "epoch": 0.10691407112878286, "grad_norm": 0.699682354927063, "learning_rate": 3.9383281955225395e-05, "loss": 0.0994, "step": 1936 }, { "epoch": 0.10696929533907665, "grad_norm": 0.3763364851474762, "learning_rate": 3.938240013824985e-05, "loss": 0.0068, "step": 1937 }, { "epoch": 0.10702451954937045, "grad_norm": 3.0465822219848633, "learning_rate": 3.938151770117613e-05, "loss": 0.9378, "step": 1938 }, { "epoch": 0.10707974375966424, "grad_norm": 5.455670356750488, "learning_rate": 3.9380634644032496e-05, "loss": 0.6856, "step": 1939 }, { "epoch": 0.10713496796995803, "grad_norm": 0.6536770462989807, "learning_rate": 3.937975096684718e-05, "loss": 0.0191, "step": 1940 }, { "epoch": 0.10719019218025182, "grad_norm": 3.2475898265838623, "learning_rate": 3.937886666964846e-05, "loss": 0.3627, "step": 1941 }, { "epoch": 0.10724541639054562, "grad_norm": 3.1465132236480713, "learning_rate": 3.937798175246463e-05, "loss": 0.3742, "step": 1942 }, { "epoch": 0.10730064060083941, "grad_norm": 3.2691643238067627, "learning_rate": 3.937709621532399e-05, "loss": 0.5437, "step": 1943 }, { "epoch": 0.1073558648111332, "grad_norm": 0.5987614393234253, "learning_rate": 3.937621005825488e-05, "loss": 0.0118, "step": 1944 }, { "epoch": 0.107411089021427, "grad_norm": 0.07965444773435593, "learning_rate": 3.9375323281285654e-05, "loss": 0.0026, "step": 1945 }, { "epoch": 0.10746631323172079, "grad_norm": 3.643406867980957, "learning_rate": 3.9374435884444674e-05, "loss": 0.944, "step": 1946 }, { "epoch": 0.10752153744201458, "grad_norm": 2.3406097888946533, "learning_rate": 3.937354786776033e-05, "loss": 0.1156, "step": 1947 }, { "epoch": 0.10757676165230837, "grad_norm": 0.3022637665271759, "learning_rate": 3.937265923126104e-05, "loss": 0.0087, "step": 1948 }, { "epoch": 0.10763198586260217, "grad_norm": 5.690565586090088, "learning_rate": 3.9371769974975224e-05, "loss": 0.6862, "step": 1949 }, { "epoch": 0.10768721007289596, "grad_norm": 0.5736353993415833, "learning_rate": 3.9370880098931346e-05, "loss": 0.0187, "step": 1950 }, { "epoch": 0.10774243428318975, "grad_norm": 2.7851195335388184, "learning_rate": 3.9369989603157865e-05, "loss": 0.3398, "step": 1951 }, { "epoch": 0.10779765849348354, "grad_norm": 2.452800750732422, "learning_rate": 3.936909848768327e-05, "loss": 0.1179, "step": 1952 }, { "epoch": 0.10785288270377734, "grad_norm": 0.1486882120370865, "learning_rate": 3.936820675253607e-05, "loss": 0.0052, "step": 1953 }, { "epoch": 0.10790810691407113, "grad_norm": 0.08145109564065933, "learning_rate": 3.93673143977448e-05, "loss": 0.0026, "step": 1954 }, { "epoch": 0.10796333112436492, "grad_norm": 0.5387272238731384, "learning_rate": 3.936642142333801e-05, "loss": 0.0084, "step": 1955 }, { "epoch": 0.10801855533465872, "grad_norm": 5.009909152984619, "learning_rate": 3.936552782934426e-05, "loss": 1.3182, "step": 1956 }, { "epoch": 0.10807377954495251, "grad_norm": 3.6153321266174316, "learning_rate": 3.936463361579214e-05, "loss": 1.1421, "step": 1957 }, { "epoch": 0.1081290037552463, "grad_norm": 1.213976502418518, "learning_rate": 3.936373878271027e-05, "loss": 0.1057, "step": 1958 }, { "epoch": 0.10818422796554009, "grad_norm": 0.8105581402778625, "learning_rate": 3.936284333012727e-05, "loss": 0.0251, "step": 1959 }, { "epoch": 0.10823945217583389, "grad_norm": 0.6936259269714355, "learning_rate": 3.9361947258071784e-05, "loss": 0.0236, "step": 1960 }, { "epoch": 0.10829467638612768, "grad_norm": 4.93407678604126, "learning_rate": 3.9361050566572486e-05, "loss": 0.5501, "step": 1961 }, { "epoch": 0.10834990059642147, "grad_norm": 1.5062968730926514, "learning_rate": 3.936015325565806e-05, "loss": 0.2956, "step": 1962 }, { "epoch": 0.10840512480671527, "grad_norm": 3.64762282371521, "learning_rate": 3.935925532535722e-05, "loss": 0.4019, "step": 1963 }, { "epoch": 0.10846034901700906, "grad_norm": 1.3638916015625, "learning_rate": 3.9358356775698684e-05, "loss": 0.0652, "step": 1964 }, { "epoch": 0.10851557322730285, "grad_norm": 5.615677833557129, "learning_rate": 3.935745760671121e-05, "loss": 1.1048, "step": 1965 }, { "epoch": 0.10857079743759664, "grad_norm": 4.3947248458862305, "learning_rate": 3.9356557818423546e-05, "loss": 1.8735, "step": 1966 }, { "epoch": 0.10862602164789044, "grad_norm": 1.608216404914856, "learning_rate": 3.93556574108645e-05, "loss": 0.0663, "step": 1967 }, { "epoch": 0.10868124585818423, "grad_norm": 6.1971211433410645, "learning_rate": 3.9354756384062876e-05, "loss": 1.3323, "step": 1968 }, { "epoch": 0.10873647006847802, "grad_norm": 3.6635851860046387, "learning_rate": 3.9353854738047485e-05, "loss": 0.3782, "step": 1969 }, { "epoch": 0.10879169427877182, "grad_norm": 2.0414552688598633, "learning_rate": 3.9352952472847194e-05, "loss": 0.1124, "step": 1970 }, { "epoch": 0.10884691848906561, "grad_norm": 0.07825314998626709, "learning_rate": 3.9352049588490844e-05, "loss": 0.003, "step": 1971 }, { "epoch": 0.1089021426993594, "grad_norm": 2.575861692428589, "learning_rate": 3.935114608500735e-05, "loss": 0.2386, "step": 1972 }, { "epoch": 0.10895736690965319, "grad_norm": 3.8007566928863525, "learning_rate": 3.935024196242559e-05, "loss": 0.6007, "step": 1973 }, { "epoch": 0.10901259111994699, "grad_norm": 6.7813873291015625, "learning_rate": 3.9349337220774503e-05, "loss": 0.4098, "step": 1974 }, { "epoch": 0.10906781533024078, "grad_norm": 5.627842903137207, "learning_rate": 3.9348431860083044e-05, "loss": 1.5677, "step": 1975 }, { "epoch": 0.10912303954053457, "grad_norm": 2.262047290802002, "learning_rate": 3.934752588038016e-05, "loss": 0.1077, "step": 1976 }, { "epoch": 0.10917826375082837, "grad_norm": 0.20957335829734802, "learning_rate": 3.934661928169484e-05, "loss": 0.0077, "step": 1977 }, { "epoch": 0.10923348796112216, "grad_norm": 2.237584114074707, "learning_rate": 3.934571206405609e-05, "loss": 0.2439, "step": 1978 }, { "epoch": 0.10928871217141595, "grad_norm": 3.0966615676879883, "learning_rate": 3.9344804227492945e-05, "loss": 0.9534, "step": 1979 }, { "epoch": 0.10934393638170974, "grad_norm": 0.5631508827209473, "learning_rate": 3.934389577203444e-05, "loss": 0.0135, "step": 1980 }, { "epoch": 0.10939916059200354, "grad_norm": 3.2899587154388428, "learning_rate": 3.934298669770963e-05, "loss": 0.1951, "step": 1981 }, { "epoch": 0.10945438480229733, "grad_norm": 0.11134575307369232, "learning_rate": 3.934207700454762e-05, "loss": 0.0029, "step": 1982 }, { "epoch": 0.10950960901259112, "grad_norm": 1.129962682723999, "learning_rate": 3.9341166692577495e-05, "loss": 0.056, "step": 1983 }, { "epoch": 0.10956483322288492, "grad_norm": 4.228122234344482, "learning_rate": 3.934025576182839e-05, "loss": 1.1084, "step": 1984 }, { "epoch": 0.10962005743317871, "grad_norm": 0.38095715641975403, "learning_rate": 3.933934421232944e-05, "loss": 0.0141, "step": 1985 }, { "epoch": 0.1096752816434725, "grad_norm": 0.6027636528015137, "learning_rate": 3.9338432044109814e-05, "loss": 0.0126, "step": 1986 }, { "epoch": 0.10973050585376629, "grad_norm": 1.2676960229873657, "learning_rate": 3.933751925719869e-05, "loss": 0.0656, "step": 1987 }, { "epoch": 0.10978573006406009, "grad_norm": 0.10033253580331802, "learning_rate": 3.933660585162528e-05, "loss": 0.0028, "step": 1988 }, { "epoch": 0.10984095427435388, "grad_norm": 3.1086997985839844, "learning_rate": 3.9335691827418794e-05, "loss": 1.0546, "step": 1989 }, { "epoch": 0.10989617848464767, "grad_norm": 0.162535160779953, "learning_rate": 3.9334777184608485e-05, "loss": 0.0061, "step": 1990 }, { "epoch": 0.10995140269494147, "grad_norm": 1.3476511240005493, "learning_rate": 3.933386192322361e-05, "loss": 0.0344, "step": 1991 }, { "epoch": 0.11000662690523526, "grad_norm": 0.39040932059288025, "learning_rate": 3.933294604329344e-05, "loss": 0.0132, "step": 1992 }, { "epoch": 0.11006185111552905, "grad_norm": 3.07742977142334, "learning_rate": 3.93320295448473e-05, "loss": 1.241, "step": 1993 }, { "epoch": 0.11011707532582284, "grad_norm": 0.012350708246231079, "learning_rate": 3.93311124279145e-05, "loss": 0.0004, "step": 1994 }, { "epoch": 0.11017229953611664, "grad_norm": 2.817699670791626, "learning_rate": 3.933019469252437e-05, "loss": 0.4708, "step": 1995 }, { "epoch": 0.11022752374641043, "grad_norm": 0.39298391342163086, "learning_rate": 3.932927633870629e-05, "loss": 0.0164, "step": 1996 }, { "epoch": 0.11028274795670422, "grad_norm": 0.03060661442577839, "learning_rate": 3.9328357366489625e-05, "loss": 0.0011, "step": 1997 }, { "epoch": 0.110337972166998, "grad_norm": 0.19093690812587738, "learning_rate": 3.932743777590378e-05, "loss": 0.0074, "step": 1998 }, { "epoch": 0.11039319637729181, "grad_norm": 4.604796409606934, "learning_rate": 3.932651756697819e-05, "loss": 0.6402, "step": 1999 }, { "epoch": 0.1104484205875856, "grad_norm": 5.713490962982178, "learning_rate": 3.9325596739742276e-05, "loss": 0.8022, "step": 2000 }, { "epoch": 0.11050364479787939, "grad_norm": 2.1049721240997314, "learning_rate": 3.9324675294225505e-05, "loss": 0.0874, "step": 2001 }, { "epoch": 0.11055886900817319, "grad_norm": 1.2566555738449097, "learning_rate": 3.932375323045736e-05, "loss": 0.0702, "step": 2002 }, { "epoch": 0.11061409321846698, "grad_norm": 3.0696091651916504, "learning_rate": 3.932283054846733e-05, "loss": 0.762, "step": 2003 }, { "epoch": 0.11066931742876077, "grad_norm": 2.8819422721862793, "learning_rate": 3.932190724828494e-05, "loss": 0.5926, "step": 2004 }, { "epoch": 0.11072454163905456, "grad_norm": 0.4215995669364929, "learning_rate": 3.932098332993974e-05, "loss": 0.0143, "step": 2005 }, { "epoch": 0.11077976584934836, "grad_norm": 2.705817699432373, "learning_rate": 3.932005879346127e-05, "loss": 0.2192, "step": 2006 }, { "epoch": 0.11083499005964215, "grad_norm": 4.942155361175537, "learning_rate": 3.931913363887912e-05, "loss": 1.2558, "step": 2007 }, { "epoch": 0.11089021426993594, "grad_norm": 2.9915881156921387, "learning_rate": 3.9318207866222883e-05, "loss": 0.3504, "step": 2008 }, { "epoch": 0.11094543848022974, "grad_norm": 0.479024201631546, "learning_rate": 3.931728147552219e-05, "loss": 0.014, "step": 2009 }, { "epoch": 0.11100066269052353, "grad_norm": 1.2219794988632202, "learning_rate": 3.931635446680666e-05, "loss": 0.1516, "step": 2010 }, { "epoch": 0.11105588690081732, "grad_norm": 1.0091062784194946, "learning_rate": 3.9315426840105963e-05, "loss": 0.021, "step": 2011 }, { "epoch": 0.1111111111111111, "grad_norm": 2.5980894565582275, "learning_rate": 3.931449859544977e-05, "loss": 0.1358, "step": 2012 }, { "epoch": 0.11116633532140491, "grad_norm": 0.04772442206740379, "learning_rate": 3.9313569732867784e-05, "loss": 0.0016, "step": 2013 }, { "epoch": 0.1112215595316987, "grad_norm": 0.39924660325050354, "learning_rate": 3.931264025238972e-05, "loss": 0.0099, "step": 2014 }, { "epoch": 0.11127678374199249, "grad_norm": 4.6270270347595215, "learning_rate": 3.931171015404531e-05, "loss": 1.1749, "step": 2015 }, { "epoch": 0.11133200795228629, "grad_norm": 0.138471782207489, "learning_rate": 3.931077943786431e-05, "loss": 0.0043, "step": 2016 }, { "epoch": 0.11138723216258008, "grad_norm": 3.8224592208862305, "learning_rate": 3.930984810387651e-05, "loss": 0.1931, "step": 2017 }, { "epoch": 0.11144245637287387, "grad_norm": 3.9880714416503906, "learning_rate": 3.930891615211169e-05, "loss": 1.1683, "step": 2018 }, { "epoch": 0.11149768058316765, "grad_norm": 0.24547624588012695, "learning_rate": 3.9307983582599673e-05, "loss": 0.0072, "step": 2019 }, { "epoch": 0.11155290479346146, "grad_norm": 3.3876426219940186, "learning_rate": 3.93070503953703e-05, "loss": 0.1163, "step": 2020 }, { "epoch": 0.11160812900375525, "grad_norm": 2.587327003479004, "learning_rate": 3.930611659045341e-05, "loss": 0.2136, "step": 2021 }, { "epoch": 0.11166335321404904, "grad_norm": 1.5574883222579956, "learning_rate": 3.9305182167878896e-05, "loss": 0.1175, "step": 2022 }, { "epoch": 0.11171857742434284, "grad_norm": 0.781639039516449, "learning_rate": 3.930424712767664e-05, "loss": 0.0214, "step": 2023 }, { "epoch": 0.11177380163463663, "grad_norm": 2.5939102172851562, "learning_rate": 3.930331146987657e-05, "loss": 0.2576, "step": 2024 }, { "epoch": 0.11182902584493042, "grad_norm": 0.8604514002799988, "learning_rate": 3.9302375194508604e-05, "loss": 0.0191, "step": 2025 }, { "epoch": 0.1118842500552242, "grad_norm": 3.970440149307251, "learning_rate": 3.93014383016027e-05, "loss": 0.9896, "step": 2026 }, { "epoch": 0.11193947426551801, "grad_norm": 3.7811944484710693, "learning_rate": 3.9300500791188845e-05, "loss": 0.9729, "step": 2027 }, { "epoch": 0.1119946984758118, "grad_norm": 1.7312474250793457, "learning_rate": 3.929956266329702e-05, "loss": 0.0625, "step": 2028 }, { "epoch": 0.11204992268610559, "grad_norm": 0.09103800356388092, "learning_rate": 3.929862391795724e-05, "loss": 0.003, "step": 2029 }, { "epoch": 0.11210514689639939, "grad_norm": 2.0668749809265137, "learning_rate": 3.929768455519955e-05, "loss": 0.09, "step": 2030 }, { "epoch": 0.11216037110669318, "grad_norm": 0.04345275089144707, "learning_rate": 3.929674457505398e-05, "loss": 0.0011, "step": 2031 }, { "epoch": 0.11221559531698697, "grad_norm": 2.8565213680267334, "learning_rate": 3.929580397755063e-05, "loss": 0.234, "step": 2032 }, { "epoch": 0.11227081952728075, "grad_norm": 0.3095290958881378, "learning_rate": 3.9294862762719564e-05, "loss": 0.0068, "step": 2033 }, { "epoch": 0.11232604373757456, "grad_norm": 2.387166976928711, "learning_rate": 3.929392093059091e-05, "loss": 0.1264, "step": 2034 }, { "epoch": 0.11238126794786835, "grad_norm": 5.960535526275635, "learning_rate": 3.929297848119481e-05, "loss": 1.6503, "step": 2035 }, { "epoch": 0.11243649215816214, "grad_norm": 0.1380433291196823, "learning_rate": 3.929203541456139e-05, "loss": 0.0035, "step": 2036 }, { "epoch": 0.11249171636845594, "grad_norm": 1.4793821573257446, "learning_rate": 3.929109173072084e-05, "loss": 0.2629, "step": 2037 }, { "epoch": 0.11254694057874973, "grad_norm": 8.317129135131836, "learning_rate": 3.929014742970335e-05, "loss": 0.9422, "step": 2038 }, { "epoch": 0.11260216478904352, "grad_norm": 5.945246696472168, "learning_rate": 3.9289202511539116e-05, "loss": 0.5749, "step": 2039 }, { "epoch": 0.1126573889993373, "grad_norm": 4.061450481414795, "learning_rate": 3.9288256976258395e-05, "loss": 0.5353, "step": 2040 }, { "epoch": 0.11271261320963111, "grad_norm": 2.4389281272888184, "learning_rate": 3.928731082389141e-05, "loss": 0.2887, "step": 2041 }, { "epoch": 0.1127678374199249, "grad_norm": 3.6479647159576416, "learning_rate": 3.928636405446845e-05, "loss": 1.3318, "step": 2042 }, { "epoch": 0.11282306163021869, "grad_norm": 0.09515677392482758, "learning_rate": 3.92854166680198e-05, "loss": 0.0033, "step": 2043 }, { "epoch": 0.11287828584051247, "grad_norm": 0.14639833569526672, "learning_rate": 3.928446866457576e-05, "loss": 0.0049, "step": 2044 }, { "epoch": 0.11293351005080628, "grad_norm": 0.12269757688045502, "learning_rate": 3.9283520044166675e-05, "loss": 0.0034, "step": 2045 }, { "epoch": 0.11298873426110007, "grad_norm": 3.0016183853149414, "learning_rate": 3.9282570806822884e-05, "loss": 0.2483, "step": 2046 }, { "epoch": 0.11304395847139385, "grad_norm": 2.4739530086517334, "learning_rate": 3.928162095257475e-05, "loss": 0.2828, "step": 2047 }, { "epoch": 0.11309918268168766, "grad_norm": 3.1913626194000244, "learning_rate": 3.9280670481452676e-05, "loss": 1.0091, "step": 2048 }, { "epoch": 0.11315440689198145, "grad_norm": 0.16019128262996674, "learning_rate": 3.927971939348706e-05, "loss": 0.0056, "step": 2049 }, { "epoch": 0.11320963110227523, "grad_norm": 1.796942114830017, "learning_rate": 3.927876768870834e-05, "loss": 0.0723, "step": 2050 }, { "epoch": 0.11326485531256902, "grad_norm": 0.3777771294116974, "learning_rate": 3.927781536714695e-05, "loss": 0.0072, "step": 2051 }, { "epoch": 0.11332007952286283, "grad_norm": 3.660306215286255, "learning_rate": 3.927686242883337e-05, "loss": 1.2312, "step": 2052 }, { "epoch": 0.11337530373315662, "grad_norm": 0.047808777540922165, "learning_rate": 3.927590887379808e-05, "loss": 0.0016, "step": 2053 }, { "epoch": 0.1134305279434504, "grad_norm": 4.601268291473389, "learning_rate": 3.927495470207159e-05, "loss": 0.3763, "step": 2054 }, { "epoch": 0.11348575215374421, "grad_norm": 0.06284767389297485, "learning_rate": 3.9273999913684426e-05, "loss": 0.0016, "step": 2055 }, { "epoch": 0.113540976364038, "grad_norm": 2.465862274169922, "learning_rate": 3.927304450866713e-05, "loss": 0.28, "step": 2056 }, { "epoch": 0.11359620057433178, "grad_norm": 1.3322480916976929, "learning_rate": 3.9272088487050274e-05, "loss": 0.0611, "step": 2057 }, { "epoch": 0.11365142478462557, "grad_norm": 1.5737409591674805, "learning_rate": 3.927113184886445e-05, "loss": 0.0597, "step": 2058 }, { "epoch": 0.11370664899491938, "grad_norm": 0.5319113731384277, "learning_rate": 3.927017459414025e-05, "loss": 0.017, "step": 2059 }, { "epoch": 0.11376187320521317, "grad_norm": 3.758873462677002, "learning_rate": 3.92692167229083e-05, "loss": 0.8263, "step": 2060 }, { "epoch": 0.11381709741550695, "grad_norm": 0.21605882048606873, "learning_rate": 3.926825823519926e-05, "loss": 0.005, "step": 2061 }, { "epoch": 0.11387232162580076, "grad_norm": 0.9711660742759705, "learning_rate": 3.926729913104378e-05, "loss": 0.0422, "step": 2062 }, { "epoch": 0.11392754583609455, "grad_norm": 0.14367106556892395, "learning_rate": 3.9266339410472546e-05, "loss": 0.0025, "step": 2063 }, { "epoch": 0.11398277004638833, "grad_norm": 3.887784242630005, "learning_rate": 3.926537907351627e-05, "loss": 0.3988, "step": 2064 }, { "epoch": 0.11403799425668212, "grad_norm": 1.7851237058639526, "learning_rate": 3.926441812020567e-05, "loss": 0.0231, "step": 2065 }, { "epoch": 0.11409321846697593, "grad_norm": 0.2141779363155365, "learning_rate": 3.926345655057149e-05, "loss": 0.0052, "step": 2066 }, { "epoch": 0.11414844267726972, "grad_norm": 0.11102790385484695, "learning_rate": 3.9262494364644495e-05, "loss": 0.0033, "step": 2067 }, { "epoch": 0.1142036668875635, "grad_norm": 3.857069492340088, "learning_rate": 3.9261531562455466e-05, "loss": 0.3225, "step": 2068 }, { "epoch": 0.1142588910978573, "grad_norm": 0.00996030680835247, "learning_rate": 3.926056814403521e-05, "loss": 0.0002, "step": 2069 }, { "epoch": 0.1143141153081511, "grad_norm": 0.8465242981910706, "learning_rate": 3.925960410941454e-05, "loss": 0.0214, "step": 2070 }, { "epoch": 0.11436933951844488, "grad_norm": 4.8941264152526855, "learning_rate": 3.925863945862431e-05, "loss": 0.6731, "step": 2071 }, { "epoch": 0.11442456372873867, "grad_norm": 2.9690263271331787, "learning_rate": 3.925767419169538e-05, "loss": 0.4714, "step": 2072 }, { "epoch": 0.11447978793903248, "grad_norm": 1.5984153747558594, "learning_rate": 3.9256708308658625e-05, "loss": 0.019, "step": 2073 }, { "epoch": 0.11453501214932627, "grad_norm": 1.6995606422424316, "learning_rate": 3.9255741809544946e-05, "loss": 0.1544, "step": 2074 }, { "epoch": 0.11459023635962005, "grad_norm": 0.26880455017089844, "learning_rate": 3.9254774694385275e-05, "loss": 0.0096, "step": 2075 }, { "epoch": 0.11464546056991386, "grad_norm": 0.6633351445198059, "learning_rate": 3.925380696321054e-05, "loss": 0.0119, "step": 2076 }, { "epoch": 0.11470068478020765, "grad_norm": 0.2968516945838928, "learning_rate": 3.9252838616051706e-05, "loss": 0.0073, "step": 2077 }, { "epoch": 0.11475590899050143, "grad_norm": 6.159264087677002, "learning_rate": 3.9251869652939763e-05, "loss": 0.1478, "step": 2078 }, { "epoch": 0.11481113320079522, "grad_norm": 3.2505276203155518, "learning_rate": 3.925090007390569e-05, "loss": 0.2199, "step": 2079 }, { "epoch": 0.11486635741108903, "grad_norm": 3.0483791828155518, "learning_rate": 3.924992987898053e-05, "loss": 0.2893, "step": 2080 }, { "epoch": 0.11492158162138282, "grad_norm": 0.045998457819223404, "learning_rate": 3.9248959068195305e-05, "loss": 0.0014, "step": 2081 }, { "epoch": 0.1149768058316766, "grad_norm": 2.933145046234131, "learning_rate": 3.9247987641581086e-05, "loss": 0.4287, "step": 2082 }, { "epoch": 0.1150320300419704, "grad_norm": 6.977573871612549, "learning_rate": 3.924701559916894e-05, "loss": 1.8826, "step": 2083 }, { "epoch": 0.1150872542522642, "grad_norm": 1.509488582611084, "learning_rate": 3.9246042940989973e-05, "loss": 0.0693, "step": 2084 }, { "epoch": 0.11514247846255798, "grad_norm": 1.1868289709091187, "learning_rate": 3.92450696670753e-05, "loss": 0.1048, "step": 2085 }, { "epoch": 0.11519770267285177, "grad_norm": 3.6203062534332275, "learning_rate": 3.924409577745606e-05, "loss": 0.5084, "step": 2086 }, { "epoch": 0.11525292688314558, "grad_norm": 1.4455673694610596, "learning_rate": 3.924312127216342e-05, "loss": 0.2096, "step": 2087 }, { "epoch": 0.11530815109343936, "grad_norm": 0.6241396069526672, "learning_rate": 3.924214615122853e-05, "loss": 0.0135, "step": 2088 }, { "epoch": 0.11536337530373315, "grad_norm": 3.919318675994873, "learning_rate": 3.9241170414682615e-05, "loss": 0.3847, "step": 2089 }, { "epoch": 0.11541859951402694, "grad_norm": 0.5859614610671997, "learning_rate": 3.924019406255688e-05, "loss": 0.0113, "step": 2090 }, { "epoch": 0.11547382372432075, "grad_norm": 0.08905240893363953, "learning_rate": 3.923921709488256e-05, "loss": 0.0023, "step": 2091 }, { "epoch": 0.11552904793461453, "grad_norm": 0.8244495987892151, "learning_rate": 3.9238239511690916e-05, "loss": 0.0348, "step": 2092 }, { "epoch": 0.11558427214490832, "grad_norm": 4.853574275970459, "learning_rate": 3.9237261313013224e-05, "loss": 0.6048, "step": 2093 }, { "epoch": 0.11563949635520213, "grad_norm": 2.445251703262329, "learning_rate": 3.9236282498880776e-05, "loss": 0.2087, "step": 2094 }, { "epoch": 0.11569472056549591, "grad_norm": 0.34605249762535095, "learning_rate": 3.9235303069324885e-05, "loss": 0.0098, "step": 2095 }, { "epoch": 0.1157499447757897, "grad_norm": 2.5199809074401855, "learning_rate": 3.9234323024376884e-05, "loss": 0.3825, "step": 2096 }, { "epoch": 0.11580516898608349, "grad_norm": 0.13852882385253906, "learning_rate": 3.923334236406814e-05, "loss": 0.0033, "step": 2097 }, { "epoch": 0.1158603931963773, "grad_norm": 0.11478191614151001, "learning_rate": 3.923236108843002e-05, "loss": 0.0042, "step": 2098 }, { "epoch": 0.11591561740667108, "grad_norm": 1.6367541551589966, "learning_rate": 3.923137919749391e-05, "loss": 0.1107, "step": 2099 }, { "epoch": 0.11597084161696487, "grad_norm": 3.6498770713806152, "learning_rate": 3.9230396691291234e-05, "loss": 0.2509, "step": 2100 }, { "epoch": 0.11602606582725868, "grad_norm": 0.050308603793382645, "learning_rate": 3.922941356985342e-05, "loss": 0.0017, "step": 2101 }, { "epoch": 0.11608129003755246, "grad_norm": 0.37068286538124084, "learning_rate": 3.922842983321192e-05, "loss": 0.0086, "step": 2102 }, { "epoch": 0.11613651424784625, "grad_norm": 0.0274717565625906, "learning_rate": 3.9227445481398205e-05, "loss": 0.0009, "step": 2103 }, { "epoch": 0.11619173845814004, "grad_norm": 2.880479097366333, "learning_rate": 3.9226460514443785e-05, "loss": 0.4619, "step": 2104 }, { "epoch": 0.11624696266843385, "grad_norm": 2.14764666557312, "learning_rate": 3.9225474932380144e-05, "loss": 0.1886, "step": 2105 }, { "epoch": 0.11630218687872763, "grad_norm": 0.1399279534816742, "learning_rate": 3.922448873523883e-05, "loss": 0.004, "step": 2106 }, { "epoch": 0.11635741108902142, "grad_norm": 3.950789451599121, "learning_rate": 3.92235019230514e-05, "loss": 1.2122, "step": 2107 }, { "epoch": 0.11641263529931523, "grad_norm": 3.2925572395324707, "learning_rate": 3.9222514495849405e-05, "loss": 0.9239, "step": 2108 }, { "epoch": 0.11646785950960901, "grad_norm": 2.2796497344970703, "learning_rate": 3.922152645366446e-05, "loss": 0.3404, "step": 2109 }, { "epoch": 0.1165230837199028, "grad_norm": 3.5579941272735596, "learning_rate": 3.922053779652815e-05, "loss": 0.8867, "step": 2110 }, { "epoch": 0.11657830793019659, "grad_norm": 0.0907893180847168, "learning_rate": 3.921954852447212e-05, "loss": 0.0026, "step": 2111 }, { "epoch": 0.1166335321404904, "grad_norm": 0.2711176872253418, "learning_rate": 3.921855863752803e-05, "loss": 0.007, "step": 2112 }, { "epoch": 0.11668875635078418, "grad_norm": 3.7509844303131104, "learning_rate": 3.921756813572752e-05, "loss": 0.3353, "step": 2113 }, { "epoch": 0.11674398056107797, "grad_norm": 0.1981082260608673, "learning_rate": 3.9216577019102304e-05, "loss": 0.0072, "step": 2114 }, { "epoch": 0.11679920477137178, "grad_norm": 3.309068202972412, "learning_rate": 3.921558528768408e-05, "loss": 0.0871, "step": 2115 }, { "epoch": 0.11685442898166556, "grad_norm": 3.4078867435455322, "learning_rate": 3.921459294150458e-05, "loss": 0.3049, "step": 2116 }, { "epoch": 0.11690965319195935, "grad_norm": 1.3084908723831177, "learning_rate": 3.9213599980595546e-05, "loss": 0.0326, "step": 2117 }, { "epoch": 0.11696487740225314, "grad_norm": 0.9443795680999756, "learning_rate": 3.9212606404988754e-05, "loss": 0.0293, "step": 2118 }, { "epoch": 0.11702010161254695, "grad_norm": 2.5088958740234375, "learning_rate": 3.921161221471598e-05, "loss": 0.1145, "step": 2119 }, { "epoch": 0.11707532582284073, "grad_norm": 4.580027103424072, "learning_rate": 3.921061740980905e-05, "loss": 0.5721, "step": 2120 }, { "epoch": 0.11713055003313452, "grad_norm": 3.1246533393859863, "learning_rate": 3.920962199029977e-05, "loss": 0.1264, "step": 2121 }, { "epoch": 0.11718577424342833, "grad_norm": 7.334140300750732, "learning_rate": 3.920862595622e-05, "loss": 1.3456, "step": 2122 }, { "epoch": 0.11724099845372211, "grad_norm": 1.5104156732559204, "learning_rate": 3.92076293076016e-05, "loss": 0.0351, "step": 2123 }, { "epoch": 0.1172962226640159, "grad_norm": 0.32562774419784546, "learning_rate": 3.920663204447645e-05, "loss": 0.0117, "step": 2124 }, { "epoch": 0.11735144687430969, "grad_norm": 0.11659111827611923, "learning_rate": 3.920563416687647e-05, "loss": 0.004, "step": 2125 }, { "epoch": 0.1174066710846035, "grad_norm": 2.4458765983581543, "learning_rate": 3.920463567483357e-05, "loss": 0.249, "step": 2126 }, { "epoch": 0.11746189529489728, "grad_norm": 6.988078594207764, "learning_rate": 3.920363656837971e-05, "loss": 2.3221, "step": 2127 }, { "epoch": 0.11751711950519107, "grad_norm": 1.8249212503433228, "learning_rate": 3.920263684754685e-05, "loss": 0.0411, "step": 2128 }, { "epoch": 0.11757234371548488, "grad_norm": 3.121480941772461, "learning_rate": 3.9201636512366956e-05, "loss": 0.4838, "step": 2129 }, { "epoch": 0.11762756792577866, "grad_norm": 2.568833589553833, "learning_rate": 3.920063556287205e-05, "loss": 0.3839, "step": 2130 }, { "epoch": 0.11768279213607245, "grad_norm": 3.793463945388794, "learning_rate": 3.919963399909415e-05, "loss": 1.7868, "step": 2131 }, { "epoch": 0.11773801634636624, "grad_norm": 0.5842819213867188, "learning_rate": 3.919863182106531e-05, "loss": 0.0161, "step": 2132 }, { "epoch": 0.11779324055666004, "grad_norm": 1.2121500968933105, "learning_rate": 3.919762902881757e-05, "loss": 0.1691, "step": 2133 }, { "epoch": 0.11784846476695383, "grad_norm": 2.4279773235321045, "learning_rate": 3.919662562238302e-05, "loss": 0.7283, "step": 2134 }, { "epoch": 0.11790368897724762, "grad_norm": 3.8476054668426514, "learning_rate": 3.919562160179378e-05, "loss": 0.7184, "step": 2135 }, { "epoch": 0.11795891318754141, "grad_norm": 0.6169946193695068, "learning_rate": 3.9194616967081954e-05, "loss": 0.0199, "step": 2136 }, { "epoch": 0.11801413739783521, "grad_norm": 0.04748325049877167, "learning_rate": 3.919361171827968e-05, "loss": 0.0011, "step": 2137 }, { "epoch": 0.118069361608129, "grad_norm": 0.48687630891799927, "learning_rate": 3.9192605855419124e-05, "loss": 0.0117, "step": 2138 }, { "epoch": 0.11812458581842279, "grad_norm": 0.30250269174575806, "learning_rate": 3.9191599378532475e-05, "loss": 0.0075, "step": 2139 }, { "epoch": 0.1181798100287166, "grad_norm": 2.1361379623413086, "learning_rate": 3.919059228765193e-05, "loss": 0.4252, "step": 2140 }, { "epoch": 0.11823503423901038, "grad_norm": 2.11272931098938, "learning_rate": 3.91895845828097e-05, "loss": 0.1506, "step": 2141 }, { "epoch": 0.11829025844930417, "grad_norm": 2.04701828956604, "learning_rate": 3.918857626403802e-05, "loss": 0.0538, "step": 2142 }, { "epoch": 0.11834548265959796, "grad_norm": 2.906902313232422, "learning_rate": 3.918756733136916e-05, "loss": 0.492, "step": 2143 }, { "epoch": 0.11840070686989176, "grad_norm": 3.237255334854126, "learning_rate": 3.9186557784835404e-05, "loss": 0.9396, "step": 2144 }, { "epoch": 0.11845593108018555, "grad_norm": 3.6501200199127197, "learning_rate": 3.9185547624469045e-05, "loss": 0.4765, "step": 2145 }, { "epoch": 0.11851115529047934, "grad_norm": 3.326669692993164, "learning_rate": 3.918453685030239e-05, "loss": 0.1486, "step": 2146 }, { "epoch": 0.11856637950077314, "grad_norm": 2.4497175216674805, "learning_rate": 3.918352546236779e-05, "loss": 0.214, "step": 2147 }, { "epoch": 0.11862160371106693, "grad_norm": 1.872397541999817, "learning_rate": 3.91825134606976e-05, "loss": 0.0537, "step": 2148 }, { "epoch": 0.11867682792136072, "grad_norm": 0.19363820552825928, "learning_rate": 3.918150084532419e-05, "loss": 0.0062, "step": 2149 }, { "epoch": 0.11873205213165451, "grad_norm": 0.2893035113811493, "learning_rate": 3.9180487616279956e-05, "loss": 0.007, "step": 2150 }, { "epoch": 0.11878727634194831, "grad_norm": 0.533419668674469, "learning_rate": 3.9179473773597325e-05, "loss": 0.0145, "step": 2151 }, { "epoch": 0.1188425005522421, "grad_norm": 2.843478202819824, "learning_rate": 3.9178459317308726e-05, "loss": 0.1335, "step": 2152 }, { "epoch": 0.11889772476253589, "grad_norm": 1.9924156665802002, "learning_rate": 3.917744424744661e-05, "loss": 0.0665, "step": 2153 }, { "epoch": 0.1189529489728297, "grad_norm": 0.19509746134281158, "learning_rate": 3.9176428564043464e-05, "loss": 0.0086, "step": 2154 }, { "epoch": 0.11900817318312348, "grad_norm": 0.21197958290576935, "learning_rate": 3.917541226713177e-05, "loss": 0.006, "step": 2155 }, { "epoch": 0.11906339739341727, "grad_norm": 1.1290034055709839, "learning_rate": 3.917439535674405e-05, "loss": 0.0392, "step": 2156 }, { "epoch": 0.11911862160371106, "grad_norm": 0.07328838855028152, "learning_rate": 3.917337783291284e-05, "loss": 0.0024, "step": 2157 }, { "epoch": 0.11917384581400486, "grad_norm": 3.2198119163513184, "learning_rate": 3.917235969567068e-05, "loss": 1.0333, "step": 2158 }, { "epoch": 0.11922907002429865, "grad_norm": 0.9867509007453918, "learning_rate": 3.9171340945050155e-05, "loss": 0.0274, "step": 2159 }, { "epoch": 0.11928429423459244, "grad_norm": 0.18692129850387573, "learning_rate": 3.917032158108386e-05, "loss": 0.0052, "step": 2160 }, { "epoch": 0.11933951844488624, "grad_norm": 1.9910813570022583, "learning_rate": 3.9169301603804395e-05, "loss": 0.0733, "step": 2161 }, { "epoch": 0.11939474265518003, "grad_norm": 2.005375862121582, "learning_rate": 3.916828101324441e-05, "loss": 0.2365, "step": 2162 }, { "epoch": 0.11944996686547382, "grad_norm": 5.097100734710693, "learning_rate": 3.916725980943653e-05, "loss": 0.7184, "step": 2163 }, { "epoch": 0.11950519107576761, "grad_norm": 4.05974006652832, "learning_rate": 3.9166237992413446e-05, "loss": 0.1269, "step": 2164 }, { "epoch": 0.11956041528606141, "grad_norm": 2.9807541370391846, "learning_rate": 3.916521556220785e-05, "loss": 0.4323, "step": 2165 }, { "epoch": 0.1196156394963552, "grad_norm": 3.1649057865142822, "learning_rate": 3.916419251885245e-05, "loss": 0.6372, "step": 2166 }, { "epoch": 0.11967086370664899, "grad_norm": 0.14057275652885437, "learning_rate": 3.916316886237997e-05, "loss": 0.0048, "step": 2167 }, { "epoch": 0.1197260879169428, "grad_norm": 0.14410701394081116, "learning_rate": 3.9162144592823157e-05, "loss": 0.0043, "step": 2168 }, { "epoch": 0.11978131212723658, "grad_norm": 0.11195740103721619, "learning_rate": 3.91611197102148e-05, "loss": 0.0025, "step": 2169 }, { "epoch": 0.11983653633753037, "grad_norm": 2.688009262084961, "learning_rate": 3.916009421458766e-05, "loss": 0.2046, "step": 2170 }, { "epoch": 0.11989176054782416, "grad_norm": 0.046515949070453644, "learning_rate": 3.9159068105974564e-05, "loss": 0.0009, "step": 2171 }, { "epoch": 0.11994698475811796, "grad_norm": 0.40756961703300476, "learning_rate": 3.915804138440834e-05, "loss": 0.011, "step": 2172 }, { "epoch": 0.12000220896841175, "grad_norm": 3.2046608924865723, "learning_rate": 3.915701404992183e-05, "loss": 0.455, "step": 2173 }, { "epoch": 0.12005743317870554, "grad_norm": 4.427392959594727, "learning_rate": 3.91559861025479e-05, "loss": 1.2969, "step": 2174 }, { "epoch": 0.12011265738899933, "grad_norm": 3.9538869857788086, "learning_rate": 3.915495754231944e-05, "loss": 1.2028, "step": 2175 }, { "epoch": 0.12016788159929313, "grad_norm": 0.8295421600341797, "learning_rate": 3.915392836926936e-05, "loss": 0.0215, "step": 2176 }, { "epoch": 0.12022310580958692, "grad_norm": 0.0801016092300415, "learning_rate": 3.915289858343058e-05, "loss": 0.0019, "step": 2177 }, { "epoch": 0.12027833001988071, "grad_norm": 5.071850299835205, "learning_rate": 3.9151868184836046e-05, "loss": 1.1449, "step": 2178 }, { "epoch": 0.12033355423017451, "grad_norm": 0.5127970576286316, "learning_rate": 3.915083717351873e-05, "loss": 0.0089, "step": 2179 }, { "epoch": 0.1203887784404683, "grad_norm": 0.43292099237442017, "learning_rate": 3.914980554951161e-05, "loss": 0.0131, "step": 2180 }, { "epoch": 0.12044400265076209, "grad_norm": 4.729193210601807, "learning_rate": 3.9148773312847695e-05, "loss": 0.549, "step": 2181 }, { "epoch": 0.12049922686105588, "grad_norm": 1.557460904121399, "learning_rate": 3.9147740463560004e-05, "loss": 0.0374, "step": 2182 }, { "epoch": 0.12055445107134968, "grad_norm": 0.054369907826185226, "learning_rate": 3.914670700168159e-05, "loss": 0.0019, "step": 2183 }, { "epoch": 0.12060967528164347, "grad_norm": 0.05665351077914238, "learning_rate": 3.914567292724551e-05, "loss": 0.0017, "step": 2184 }, { "epoch": 0.12066489949193726, "grad_norm": 2.835639476776123, "learning_rate": 3.9144638240284845e-05, "loss": 0.2948, "step": 2185 }, { "epoch": 0.12072012370223106, "grad_norm": 0.5746424198150635, "learning_rate": 3.9143602940832706e-05, "loss": 0.0193, "step": 2186 }, { "epoch": 0.12077534791252485, "grad_norm": 4.561875343322754, "learning_rate": 3.91425670289222e-05, "loss": 0.7077, "step": 2187 }, { "epoch": 0.12083057212281864, "grad_norm": 0.22517284750938416, "learning_rate": 3.914153050458649e-05, "loss": 0.0066, "step": 2188 }, { "epoch": 0.12088579633311243, "grad_norm": 1.4681273698806763, "learning_rate": 3.914049336785872e-05, "loss": 0.2398, "step": 2189 }, { "epoch": 0.12094102054340623, "grad_norm": 3.249634265899658, "learning_rate": 3.913945561877207e-05, "loss": 0.3389, "step": 2190 }, { "epoch": 0.12099624475370002, "grad_norm": 3.575258493423462, "learning_rate": 3.913841725735975e-05, "loss": 0.1087, "step": 2191 }, { "epoch": 0.12105146896399381, "grad_norm": 3.7338972091674805, "learning_rate": 3.9137378283654985e-05, "loss": 0.8203, "step": 2192 }, { "epoch": 0.12110669317428761, "grad_norm": 1.228758692741394, "learning_rate": 3.913633869769101e-05, "loss": 0.0417, "step": 2193 }, { "epoch": 0.1211619173845814, "grad_norm": 3.151331901550293, "learning_rate": 3.913529849950107e-05, "loss": 0.2615, "step": 2194 }, { "epoch": 0.12121714159487519, "grad_norm": 0.018965626135468483, "learning_rate": 3.913425768911846e-05, "loss": 0.0006, "step": 2195 }, { "epoch": 0.12127236580516898, "grad_norm": 1.0852632522583008, "learning_rate": 3.913321626657647e-05, "loss": 0.0321, "step": 2196 }, { "epoch": 0.12132759001546278, "grad_norm": 0.7394475936889648, "learning_rate": 3.913217423190842e-05, "loss": 0.0259, "step": 2197 }, { "epoch": 0.12138281422575657, "grad_norm": 2.7773890495300293, "learning_rate": 3.913113158514765e-05, "loss": 0.5819, "step": 2198 }, { "epoch": 0.12143803843605036, "grad_norm": 1.613861322402954, "learning_rate": 3.913008832632753e-05, "loss": 0.1528, "step": 2199 }, { "epoch": 0.12149326264634416, "grad_norm": 6.076051235198975, "learning_rate": 3.912904445548141e-05, "loss": 1.103, "step": 2200 }, { "epoch": 0.12154848685663795, "grad_norm": 1.5672591924667358, "learning_rate": 3.91279999726427e-05, "loss": 0.0639, "step": 2201 }, { "epoch": 0.12160371106693174, "grad_norm": 1.2263078689575195, "learning_rate": 3.912695487784482e-05, "loss": 0.1004, "step": 2202 }, { "epoch": 0.12165893527722553, "grad_norm": 2.986365795135498, "learning_rate": 3.91259091711212e-05, "loss": 0.0922, "step": 2203 }, { "epoch": 0.12171415948751933, "grad_norm": 2.6165778636932373, "learning_rate": 3.91248628525053e-05, "loss": 0.3025, "step": 2204 }, { "epoch": 0.12176938369781312, "grad_norm": 0.6001619100570679, "learning_rate": 3.9123815922030594e-05, "loss": 0.0146, "step": 2205 }, { "epoch": 0.12182460790810691, "grad_norm": 0.03638472780585289, "learning_rate": 3.9122768379730566e-05, "loss": 0.0011, "step": 2206 }, { "epoch": 0.12187983211840071, "grad_norm": 4.935224533081055, "learning_rate": 3.912172022563874e-05, "loss": 0.6071, "step": 2207 }, { "epoch": 0.1219350563286945, "grad_norm": 2.161062002182007, "learning_rate": 3.912067145978864e-05, "loss": 0.1929, "step": 2208 }, { "epoch": 0.12199028053898829, "grad_norm": 3.6020724773406982, "learning_rate": 3.911962208221384e-05, "loss": 0.4642, "step": 2209 }, { "epoch": 0.12204550474928208, "grad_norm": 4.755600452423096, "learning_rate": 3.911857209294789e-05, "loss": 1.135, "step": 2210 }, { "epoch": 0.12210072895957588, "grad_norm": 0.055362943559885025, "learning_rate": 3.9117521492024394e-05, "loss": 0.0016, "step": 2211 }, { "epoch": 0.12215595316986967, "grad_norm": 2.2741715908050537, "learning_rate": 3.911647027947696e-05, "loss": 0.1205, "step": 2212 }, { "epoch": 0.12221117738016346, "grad_norm": 1.4275381565093994, "learning_rate": 3.9115418455339214e-05, "loss": 0.0405, "step": 2213 }, { "epoch": 0.12226640159045726, "grad_norm": 1.7249946594238281, "learning_rate": 3.9114366019644815e-05, "loss": 0.2053, "step": 2214 }, { "epoch": 0.12232162580075105, "grad_norm": 6.181752681732178, "learning_rate": 3.911331297242743e-05, "loss": 1.4687, "step": 2215 }, { "epoch": 0.12237685001104484, "grad_norm": 1.3710333108901978, "learning_rate": 3.911225931372075e-05, "loss": 0.0486, "step": 2216 }, { "epoch": 0.12243207422133863, "grad_norm": 1.1556425094604492, "learning_rate": 3.9111205043558486e-05, "loss": 0.1228, "step": 2217 }, { "epoch": 0.12248729843163243, "grad_norm": 2.749818801879883, "learning_rate": 3.911015016197437e-05, "loss": 0.725, "step": 2218 }, { "epoch": 0.12254252264192622, "grad_norm": 2.1868197917938232, "learning_rate": 3.9109094669002144e-05, "loss": 0.1188, "step": 2219 }, { "epoch": 0.12259774685222001, "grad_norm": 4.080347537994385, "learning_rate": 3.9108038564675574e-05, "loss": 1.1761, "step": 2220 }, { "epoch": 0.1226529710625138, "grad_norm": 0.26090869307518005, "learning_rate": 3.910698184902845e-05, "loss": 0.0055, "step": 2221 }, { "epoch": 0.1227081952728076, "grad_norm": 1.6064774990081787, "learning_rate": 3.910592452209459e-05, "loss": 0.0731, "step": 2222 }, { "epoch": 0.12276341948310139, "grad_norm": 6.159585952758789, "learning_rate": 3.9104866583907806e-05, "loss": 0.5312, "step": 2223 }, { "epoch": 0.12281864369339518, "grad_norm": 0.7672664523124695, "learning_rate": 3.9103808034501954e-05, "loss": 0.0292, "step": 2224 }, { "epoch": 0.12287386790368898, "grad_norm": 2.24308443069458, "learning_rate": 3.9102748873910894e-05, "loss": 0.1685, "step": 2225 }, { "epoch": 0.12292909211398277, "grad_norm": 0.5019701719284058, "learning_rate": 3.910168910216851e-05, "loss": 0.0111, "step": 2226 }, { "epoch": 0.12298431632427656, "grad_norm": 0.6718278527259827, "learning_rate": 3.910062871930873e-05, "loss": 0.0095, "step": 2227 }, { "epoch": 0.12303954053457035, "grad_norm": 1.0727440118789673, "learning_rate": 3.9099567725365444e-05, "loss": 0.0352, "step": 2228 }, { "epoch": 0.12309476474486415, "grad_norm": 1.763104796409607, "learning_rate": 3.909850612037262e-05, "loss": 0.0885, "step": 2229 }, { "epoch": 0.12314998895515794, "grad_norm": 2.278696060180664, "learning_rate": 3.90974439043642e-05, "loss": 0.332, "step": 2230 }, { "epoch": 0.12320521316545173, "grad_norm": 1.2605727910995483, "learning_rate": 3.909638107737419e-05, "loss": 0.0336, "step": 2231 }, { "epoch": 0.12326043737574553, "grad_norm": 0.09476625174283981, "learning_rate": 3.9095317639436595e-05, "loss": 0.0024, "step": 2232 }, { "epoch": 0.12331566158603932, "grad_norm": 0.24064120650291443, "learning_rate": 3.9094253590585416e-05, "loss": 0.0057, "step": 2233 }, { "epoch": 0.12337088579633311, "grad_norm": 3.1868739128112793, "learning_rate": 3.9093188930854705e-05, "loss": 0.1674, "step": 2234 }, { "epoch": 0.1234261100066269, "grad_norm": 0.09597703814506531, "learning_rate": 3.909212366027853e-05, "loss": 0.0019, "step": 2235 }, { "epoch": 0.1234813342169207, "grad_norm": 0.23743204772472382, "learning_rate": 3.909105777889096e-05, "loss": 0.0088, "step": 2236 }, { "epoch": 0.12353655842721449, "grad_norm": 3.0815484523773193, "learning_rate": 3.908999128672611e-05, "loss": 0.4305, "step": 2237 }, { "epoch": 0.12359178263750828, "grad_norm": 0.9801818132400513, "learning_rate": 3.9088924183818086e-05, "loss": 0.0428, "step": 2238 }, { "epoch": 0.12364700684780208, "grad_norm": 6.264251232147217, "learning_rate": 3.9087856470201035e-05, "loss": 0.1419, "step": 2239 }, { "epoch": 0.12370223105809587, "grad_norm": 2.5853116512298584, "learning_rate": 3.908678814590911e-05, "loss": 0.6442, "step": 2240 }, { "epoch": 0.12375745526838966, "grad_norm": 2.3868298530578613, "learning_rate": 3.90857192109765e-05, "loss": 0.153, "step": 2241 }, { "epoch": 0.12381267947868345, "grad_norm": 2.000652551651001, "learning_rate": 3.90846496654374e-05, "loss": 0.1542, "step": 2242 }, { "epoch": 0.12386790368897725, "grad_norm": 0.0721600279211998, "learning_rate": 3.908357950932602e-05, "loss": 0.0019, "step": 2243 }, { "epoch": 0.12392312789927104, "grad_norm": 0.046012263745069504, "learning_rate": 3.9082508742676603e-05, "loss": 0.0013, "step": 2244 }, { "epoch": 0.12397835210956483, "grad_norm": 3.985947608947754, "learning_rate": 3.908143736552341e-05, "loss": 0.5893, "step": 2245 }, { "epoch": 0.12403357631985863, "grad_norm": 3.7199673652648926, "learning_rate": 3.908036537790071e-05, "loss": 0.4973, "step": 2246 }, { "epoch": 0.12408880053015242, "grad_norm": 3.1283843517303467, "learning_rate": 3.9079292779842806e-05, "loss": 1.0527, "step": 2247 }, { "epoch": 0.12414402474044621, "grad_norm": 1.867223858833313, "learning_rate": 3.9078219571384005e-05, "loss": 0.1427, "step": 2248 }, { "epoch": 0.12419924895074, "grad_norm": 1.8418128490447998, "learning_rate": 3.907714575255865e-05, "loss": 0.062, "step": 2249 }, { "epoch": 0.1242544731610338, "grad_norm": 2.6522436141967773, "learning_rate": 3.907607132340109e-05, "loss": 0.4785, "step": 2250 }, { "epoch": 0.12430969737132759, "grad_norm": 0.885205090045929, "learning_rate": 3.90749962839457e-05, "loss": 0.0214, "step": 2251 }, { "epoch": 0.12436492158162138, "grad_norm": 0.1444489061832428, "learning_rate": 3.9073920634226877e-05, "loss": 0.0037, "step": 2252 }, { "epoch": 0.12442014579191518, "grad_norm": 3.643263339996338, "learning_rate": 3.9072844374279035e-05, "loss": 0.8524, "step": 2253 }, { "epoch": 0.12447537000220897, "grad_norm": 4.345881938934326, "learning_rate": 3.90717675041366e-05, "loss": 0.6772, "step": 2254 }, { "epoch": 0.12453059421250276, "grad_norm": 4.635126113891602, "learning_rate": 3.907069002383403e-05, "loss": 0.5682, "step": 2255 }, { "epoch": 0.12458581842279655, "grad_norm": 1.0603080987930298, "learning_rate": 3.906961193340579e-05, "loss": 0.0441, "step": 2256 }, { "epoch": 0.12464104263309035, "grad_norm": 0.47240641713142395, "learning_rate": 3.906853323288638e-05, "loss": 0.0104, "step": 2257 }, { "epoch": 0.12469626684338414, "grad_norm": 0.3821825683116913, "learning_rate": 3.90674539223103e-05, "loss": 0.0071, "step": 2258 }, { "epoch": 0.12475149105367793, "grad_norm": 2.2570090293884277, "learning_rate": 3.9066374001712096e-05, "loss": 0.3709, "step": 2259 }, { "epoch": 0.12480671526397173, "grad_norm": 0.07493030279874802, "learning_rate": 3.906529347112629e-05, "loss": 0.0027, "step": 2260 }, { "epoch": 0.12486193947426552, "grad_norm": 5.0072221755981445, "learning_rate": 3.906421233058748e-05, "loss": 0.786, "step": 2261 }, { "epoch": 0.12491716368455931, "grad_norm": 2.538639545440674, "learning_rate": 3.9063130580130254e-05, "loss": 0.1599, "step": 2262 }, { "epoch": 0.1249723878948531, "grad_norm": 2.2333834171295166, "learning_rate": 3.9062048219789205e-05, "loss": 0.1803, "step": 2263 }, { "epoch": 0.1250276121051469, "grad_norm": 3.61991548538208, "learning_rate": 3.906096524959896e-05, "loss": 0.648, "step": 2264 }, { "epoch": 0.12508283631544068, "grad_norm": 0.014440096914768219, "learning_rate": 3.905988166959418e-05, "loss": 0.0004, "step": 2265 }, { "epoch": 0.12513806052573448, "grad_norm": 0.3771447539329529, "learning_rate": 3.9058797479809515e-05, "loss": 0.0056, "step": 2266 }, { "epoch": 0.12519328473602828, "grad_norm": 0.3231365978717804, "learning_rate": 3.905771268027967e-05, "loss": 0.0069, "step": 2267 }, { "epoch": 0.12524850894632206, "grad_norm": 0.7997879385948181, "learning_rate": 3.905662727103933e-05, "loss": 0.1197, "step": 2268 }, { "epoch": 0.12530373315661586, "grad_norm": 0.24019339680671692, "learning_rate": 3.9055541252123244e-05, "loss": 0.0052, "step": 2269 }, { "epoch": 0.12535895736690966, "grad_norm": 0.02135932818055153, "learning_rate": 3.905445462356614e-05, "loss": 0.0007, "step": 2270 }, { "epoch": 0.12541418157720344, "grad_norm": 2.51166033744812, "learning_rate": 3.905336738540279e-05, "loss": 0.1952, "step": 2271 }, { "epoch": 0.12546940578749724, "grad_norm": 2.0700459480285645, "learning_rate": 3.905227953766797e-05, "loss": 0.0387, "step": 2272 }, { "epoch": 0.12552462999779104, "grad_norm": 4.872467994689941, "learning_rate": 3.905119108039649e-05, "loss": 0.9113, "step": 2273 }, { "epoch": 0.12557985420808482, "grad_norm": 0.06632815301418304, "learning_rate": 3.905010201362317e-05, "loss": 0.0022, "step": 2274 }, { "epoch": 0.12563507841837862, "grad_norm": 4.687907695770264, "learning_rate": 3.904901233738285e-05, "loss": 0.2845, "step": 2275 }, { "epoch": 0.12569030262867242, "grad_norm": 3.2547035217285156, "learning_rate": 3.90479220517104e-05, "loss": 0.8141, "step": 2276 }, { "epoch": 0.1257455268389662, "grad_norm": 0.33748751878738403, "learning_rate": 3.90468311566407e-05, "loss": 0.0066, "step": 2277 }, { "epoch": 0.12580075104926, "grad_norm": 2.793046236038208, "learning_rate": 3.904573965220864e-05, "loss": 0.5831, "step": 2278 }, { "epoch": 0.12585597525955378, "grad_norm": 0.4502725601196289, "learning_rate": 3.904464753844915e-05, "loss": 0.0126, "step": 2279 }, { "epoch": 0.12591119946984758, "grad_norm": 0.38183844089508057, "learning_rate": 3.904355481539717e-05, "loss": 0.0116, "step": 2280 }, { "epoch": 0.12596642368014138, "grad_norm": 0.04168691113591194, "learning_rate": 3.9042461483087655e-05, "loss": 0.0012, "step": 2281 }, { "epoch": 0.12602164789043516, "grad_norm": 0.6241477727890015, "learning_rate": 3.904136754155559e-05, "loss": 0.0183, "step": 2282 }, { "epoch": 0.12607687210072896, "grad_norm": 2.1196258068084717, "learning_rate": 3.904027299083596e-05, "loss": 0.2555, "step": 2283 }, { "epoch": 0.12613209631102276, "grad_norm": 4.124336242675781, "learning_rate": 3.90391778309638e-05, "loss": 1.4905, "step": 2284 }, { "epoch": 0.12618732052131654, "grad_norm": 0.24343474209308624, "learning_rate": 3.9038082061974133e-05, "loss": 0.0062, "step": 2285 }, { "epoch": 0.12624254473161034, "grad_norm": 2.2323012351989746, "learning_rate": 3.903698568390202e-05, "loss": 0.075, "step": 2286 }, { "epoch": 0.12629776894190414, "grad_norm": 2.6796810626983643, "learning_rate": 3.9035888696782554e-05, "loss": 0.2126, "step": 2287 }, { "epoch": 0.12635299315219792, "grad_norm": 0.07872536778450012, "learning_rate": 3.90347911006508e-05, "loss": 0.0021, "step": 2288 }, { "epoch": 0.12640821736249172, "grad_norm": 1.2783374786376953, "learning_rate": 3.90336928955419e-05, "loss": 0.0448, "step": 2289 }, { "epoch": 0.1264634415727855, "grad_norm": 0.4541742205619812, "learning_rate": 3.9032594081490966e-05, "loss": 0.0201, "step": 2290 }, { "epoch": 0.1265186657830793, "grad_norm": 1.7954148054122925, "learning_rate": 3.903149465853317e-05, "loss": 0.0967, "step": 2291 }, { "epoch": 0.1265738899933731, "grad_norm": 0.2605820894241333, "learning_rate": 3.903039462670368e-05, "loss": 0.0088, "step": 2292 }, { "epoch": 0.12662911420366688, "grad_norm": 0.7396826148033142, "learning_rate": 3.902929398603769e-05, "loss": 0.0254, "step": 2293 }, { "epoch": 0.12668433841396068, "grad_norm": 6.541845321655273, "learning_rate": 3.902819273657041e-05, "loss": 1.1764, "step": 2294 }, { "epoch": 0.12673956262425448, "grad_norm": 1.4492210149765015, "learning_rate": 3.902709087833707e-05, "loss": 0.1574, "step": 2295 }, { "epoch": 0.12679478683454826, "grad_norm": 3.574061632156372, "learning_rate": 3.902598841137293e-05, "loss": 0.4204, "step": 2296 }, { "epoch": 0.12685001104484206, "grad_norm": 0.015244712121784687, "learning_rate": 3.9024885335713254e-05, "loss": 0.0005, "step": 2297 }, { "epoch": 0.12690523525513586, "grad_norm": 1.0829073190689087, "learning_rate": 3.902378165139334e-05, "loss": 0.019, "step": 2298 }, { "epoch": 0.12696045946542964, "grad_norm": 3.2277815341949463, "learning_rate": 3.9022677358448485e-05, "loss": 0.3443, "step": 2299 }, { "epoch": 0.12701568367572344, "grad_norm": 2.850733757019043, "learning_rate": 3.902157245691403e-05, "loss": 0.742, "step": 2300 }, { "epoch": 0.12707090788601724, "grad_norm": 4.056323051452637, "learning_rate": 3.902046694682532e-05, "loss": 0.7615, "step": 2301 }, { "epoch": 0.12712613209631102, "grad_norm": 0.09650598466396332, "learning_rate": 3.901936082821772e-05, "loss": 0.0018, "step": 2302 }, { "epoch": 0.12718135630660482, "grad_norm": 3.410909414291382, "learning_rate": 3.9018254101126626e-05, "loss": 1.0207, "step": 2303 }, { "epoch": 0.1272365805168986, "grad_norm": 5.898458003997803, "learning_rate": 3.901714676558744e-05, "loss": 0.7925, "step": 2304 }, { "epoch": 0.1272918047271924, "grad_norm": 3.563366413116455, "learning_rate": 3.9016038821635584e-05, "loss": 0.9508, "step": 2305 }, { "epoch": 0.1273470289374862, "grad_norm": 5.303065776824951, "learning_rate": 3.9014930269306516e-05, "loss": 0.2655, "step": 2306 }, { "epoch": 0.12740225314777998, "grad_norm": 0.01203797198832035, "learning_rate": 3.9013821108635696e-05, "loss": 0.0004, "step": 2307 }, { "epoch": 0.12745747735807378, "grad_norm": 0.45931413769721985, "learning_rate": 3.90127113396586e-05, "loss": 0.0062, "step": 2308 }, { "epoch": 0.12751270156836758, "grad_norm": 2.4997503757476807, "learning_rate": 3.901160096241075e-05, "loss": 0.4114, "step": 2309 }, { "epoch": 0.12756792577866136, "grad_norm": 1.4739514589309692, "learning_rate": 3.9010489976927664e-05, "loss": 0.0634, "step": 2310 }, { "epoch": 0.12762314998895516, "grad_norm": 1.955829381942749, "learning_rate": 3.9009378383244874e-05, "loss": 0.2477, "step": 2311 }, { "epoch": 0.12767837419924896, "grad_norm": 1.7182468175888062, "learning_rate": 3.900826618139796e-05, "loss": 0.0238, "step": 2312 }, { "epoch": 0.12773359840954274, "grad_norm": 3.3696999549865723, "learning_rate": 3.90071533714225e-05, "loss": 0.2539, "step": 2313 }, { "epoch": 0.12778882261983654, "grad_norm": 0.11434125900268555, "learning_rate": 3.900603995335408e-05, "loss": 0.0032, "step": 2314 }, { "epoch": 0.12784404683013034, "grad_norm": 3.1202149391174316, "learning_rate": 3.900492592722834e-05, "loss": 0.4788, "step": 2315 }, { "epoch": 0.12789927104042412, "grad_norm": 0.05411480367183685, "learning_rate": 3.900381129308091e-05, "loss": 0.0016, "step": 2316 }, { "epoch": 0.12795449525071792, "grad_norm": 3.1078543663024902, "learning_rate": 3.900269605094747e-05, "loss": 0.6435, "step": 2317 }, { "epoch": 0.1280097194610117, "grad_norm": 1.3437670469284058, "learning_rate": 3.9001580200863667e-05, "loss": 0.0619, "step": 2318 }, { "epoch": 0.1280649436713055, "grad_norm": 1.378001093864441, "learning_rate": 3.9000463742865234e-05, "loss": 0.0295, "step": 2319 }, { "epoch": 0.1281201678815993, "grad_norm": 3.09470534324646, "learning_rate": 3.899934667698786e-05, "loss": 0.2475, "step": 2320 }, { "epoch": 0.12817539209189308, "grad_norm": 2.872864007949829, "learning_rate": 3.899822900326731e-05, "loss": 1.049, "step": 2321 }, { "epoch": 0.12823061630218688, "grad_norm": 4.166329383850098, "learning_rate": 3.899711072173932e-05, "loss": 0.137, "step": 2322 }, { "epoch": 0.12828584051248068, "grad_norm": 4.174127101898193, "learning_rate": 3.899599183243968e-05, "loss": 0.5169, "step": 2323 }, { "epoch": 0.12834106472277446, "grad_norm": 0.07875800877809525, "learning_rate": 3.899487233540418e-05, "loss": 0.0026, "step": 2324 }, { "epoch": 0.12839628893306826, "grad_norm": 0.37917327880859375, "learning_rate": 3.899375223066864e-05, "loss": 0.0148, "step": 2325 }, { "epoch": 0.12845151314336206, "grad_norm": 0.15068678557872772, "learning_rate": 3.8992631518268894e-05, "loss": 0.0062, "step": 2326 }, { "epoch": 0.12850673735365584, "grad_norm": 2.9230990409851074, "learning_rate": 3.899151019824079e-05, "loss": 0.3356, "step": 2327 }, { "epoch": 0.12856196156394964, "grad_norm": 0.9475106596946716, "learning_rate": 3.8990388270620216e-05, "loss": 0.0325, "step": 2328 }, { "epoch": 0.12861718577424344, "grad_norm": 0.23996785283088684, "learning_rate": 3.898926573544305e-05, "loss": 0.0051, "step": 2329 }, { "epoch": 0.12867240998453722, "grad_norm": 0.26570644974708557, "learning_rate": 3.898814259274522e-05, "loss": 0.0073, "step": 2330 }, { "epoch": 0.12872763419483102, "grad_norm": 1.178086519241333, "learning_rate": 3.898701884256265e-05, "loss": 0.0325, "step": 2331 }, { "epoch": 0.1287828584051248, "grad_norm": 2.729412794113159, "learning_rate": 3.898589448493129e-05, "loss": 0.2549, "step": 2332 }, { "epoch": 0.1288380826154186, "grad_norm": 0.30598196387290955, "learning_rate": 3.898476951988712e-05, "loss": 0.009, "step": 2333 }, { "epoch": 0.1288933068257124, "grad_norm": 2.408010959625244, "learning_rate": 3.898364394746612e-05, "loss": 0.2957, "step": 2334 }, { "epoch": 0.12894853103600618, "grad_norm": 2.8418197631835938, "learning_rate": 3.898251776770431e-05, "loss": 0.361, "step": 2335 }, { "epoch": 0.12900375524629998, "grad_norm": 0.7093974351882935, "learning_rate": 3.898139098063771e-05, "loss": 0.0258, "step": 2336 }, { "epoch": 0.12905897945659378, "grad_norm": 2.444059371948242, "learning_rate": 3.8980263586302385e-05, "loss": 0.5686, "step": 2337 }, { "epoch": 0.12911420366688756, "grad_norm": 0.038272757083177567, "learning_rate": 3.8979135584734386e-05, "loss": 0.0011, "step": 2338 }, { "epoch": 0.12916942787718136, "grad_norm": 0.15990294516086578, "learning_rate": 3.8978006975969815e-05, "loss": 0.0039, "step": 2339 }, { "epoch": 0.12922465208747516, "grad_norm": 3.2177376747131348, "learning_rate": 3.8976877760044764e-05, "loss": 0.4562, "step": 2340 }, { "epoch": 0.12927987629776894, "grad_norm": 2.0832359790802, "learning_rate": 3.897574793699538e-05, "loss": 0.2364, "step": 2341 }, { "epoch": 0.12933510050806274, "grad_norm": 2.26570725440979, "learning_rate": 3.8974617506857784e-05, "loss": 0.1109, "step": 2342 }, { "epoch": 0.12939032471835651, "grad_norm": 5.822092533111572, "learning_rate": 3.8973486469668165e-05, "loss": 1.2475, "step": 2343 }, { "epoch": 0.12944554892865032, "grad_norm": 2.9719841480255127, "learning_rate": 3.89723548254627e-05, "loss": 0.4295, "step": 2344 }, { "epoch": 0.12950077313894412, "grad_norm": 1.9918005466461182, "learning_rate": 3.897122257427759e-05, "loss": 0.3104, "step": 2345 }, { "epoch": 0.1295559973492379, "grad_norm": 2.532952308654785, "learning_rate": 3.8970089716149055e-05, "loss": 0.2551, "step": 2346 }, { "epoch": 0.1296112215595317, "grad_norm": 2.1768581867218018, "learning_rate": 3.896895625111335e-05, "loss": 0.1034, "step": 2347 }, { "epoch": 0.1296664457698255, "grad_norm": 0.06412916630506516, "learning_rate": 3.896782217920673e-05, "loss": 0.0015, "step": 2348 }, { "epoch": 0.12972166998011928, "grad_norm": 4.920044422149658, "learning_rate": 3.8966687500465485e-05, "loss": 0.4709, "step": 2349 }, { "epoch": 0.12977689419041308, "grad_norm": 4.078677177429199, "learning_rate": 3.896555221492591e-05, "loss": 0.3225, "step": 2350 }, { "epoch": 0.12983211840070688, "grad_norm": 1.2932305335998535, "learning_rate": 3.8964416322624326e-05, "loss": 0.0325, "step": 2351 }, { "epoch": 0.12988734261100066, "grad_norm": 0.5766744017601013, "learning_rate": 3.896327982359707e-05, "loss": 0.0196, "step": 2352 }, { "epoch": 0.12994256682129446, "grad_norm": 3.5171167850494385, "learning_rate": 3.8962142717880514e-05, "loss": 0.7771, "step": 2353 }, { "epoch": 0.12999779103158826, "grad_norm": 1.8041632175445557, "learning_rate": 3.896100500551102e-05, "loss": 0.1327, "step": 2354 }, { "epoch": 0.13005301524188204, "grad_norm": 0.36909496784210205, "learning_rate": 3.895986668652501e-05, "loss": 0.0137, "step": 2355 }, { "epoch": 0.13010823945217584, "grad_norm": 0.07430115342140198, "learning_rate": 3.895872776095887e-05, "loss": 0.003, "step": 2356 }, { "epoch": 0.13016346366246961, "grad_norm": 3.443702459335327, "learning_rate": 3.895758822884907e-05, "loss": 1.4285, "step": 2357 }, { "epoch": 0.13021868787276342, "grad_norm": 4.88512659072876, "learning_rate": 3.8956448090232045e-05, "loss": 0.6124, "step": 2358 }, { "epoch": 0.13027391208305722, "grad_norm": 2.9029624462127686, "learning_rate": 3.8955307345144285e-05, "loss": 0.4394, "step": 2359 }, { "epoch": 0.130329136293351, "grad_norm": 3.0548458099365234, "learning_rate": 3.8954165993622276e-05, "loss": 0.7435, "step": 2360 }, { "epoch": 0.1303843605036448, "grad_norm": 0.8288192749023438, "learning_rate": 3.895302403570254e-05, "loss": 0.0242, "step": 2361 }, { "epoch": 0.1304395847139386, "grad_norm": 4.3673787117004395, "learning_rate": 3.8951881471421605e-05, "loss": 0.4442, "step": 2362 }, { "epoch": 0.13049480892423237, "grad_norm": 2.7108194828033447, "learning_rate": 3.895073830081603e-05, "loss": 0.0682, "step": 2363 }, { "epoch": 0.13055003313452618, "grad_norm": 0.07968098670244217, "learning_rate": 3.8949594523922384e-05, "loss": 0.0033, "step": 2364 }, { "epoch": 0.13060525734481998, "grad_norm": 2.2748329639434814, "learning_rate": 3.894845014077726e-05, "loss": 0.3623, "step": 2365 }, { "epoch": 0.13066048155511376, "grad_norm": 3.641130208969116, "learning_rate": 3.8947305151417276e-05, "loss": 0.9761, "step": 2366 }, { "epoch": 0.13071570576540756, "grad_norm": 0.5820630192756653, "learning_rate": 3.894615955587906e-05, "loss": 0.019, "step": 2367 }, { "epoch": 0.13077092997570136, "grad_norm": 3.1405835151672363, "learning_rate": 3.8945013354199264e-05, "loss": 0.518, "step": 2368 }, { "epoch": 0.13082615418599514, "grad_norm": 1.06771719455719, "learning_rate": 3.8943866546414556e-05, "loss": 0.1664, "step": 2369 }, { "epoch": 0.13088137839628894, "grad_norm": 5.787936210632324, "learning_rate": 3.8942719132561626e-05, "loss": 1.1662, "step": 2370 }, { "epoch": 0.1309366026065827, "grad_norm": 2.997547149658203, "learning_rate": 3.894157111267718e-05, "loss": 0.0751, "step": 2371 }, { "epoch": 0.13099182681687652, "grad_norm": 0.8958227634429932, "learning_rate": 3.894042248679795e-05, "loss": 0.0336, "step": 2372 }, { "epoch": 0.13104705102717032, "grad_norm": 2.632200241088867, "learning_rate": 3.8939273254960686e-05, "loss": 0.7507, "step": 2373 }, { "epoch": 0.1311022752374641, "grad_norm": 0.44402116537094116, "learning_rate": 3.893812341720216e-05, "loss": 0.0114, "step": 2374 }, { "epoch": 0.1311574994477579, "grad_norm": 0.3379916846752167, "learning_rate": 3.893697297355914e-05, "loss": 0.0088, "step": 2375 }, { "epoch": 0.1312127236580517, "grad_norm": 0.6609836220741272, "learning_rate": 3.893582192406845e-05, "loss": 0.0213, "step": 2376 }, { "epoch": 0.13126794786834547, "grad_norm": 0.2985250949859619, "learning_rate": 3.8934670268766905e-05, "loss": 0.0083, "step": 2377 }, { "epoch": 0.13132317207863928, "grad_norm": 0.8446754813194275, "learning_rate": 3.8933518007691356e-05, "loss": 0.0247, "step": 2378 }, { "epoch": 0.13137839628893308, "grad_norm": 2.8416593074798584, "learning_rate": 3.893236514087866e-05, "loss": 0.3235, "step": 2379 }, { "epoch": 0.13143362049922686, "grad_norm": 0.2346186339855194, "learning_rate": 3.893121166836571e-05, "loss": 0.0076, "step": 2380 }, { "epoch": 0.13148884470952066, "grad_norm": 0.05324840545654297, "learning_rate": 3.89300575901894e-05, "loss": 0.0018, "step": 2381 }, { "epoch": 0.13154406891981443, "grad_norm": 2.8612542152404785, "learning_rate": 3.892890290638666e-05, "loss": 0.2708, "step": 2382 }, { "epoch": 0.13159929313010824, "grad_norm": 4.399971008300781, "learning_rate": 3.892774761699443e-05, "loss": 0.6538, "step": 2383 }, { "epoch": 0.13165451734040204, "grad_norm": 2.7971460819244385, "learning_rate": 3.892659172204966e-05, "loss": 0.285, "step": 2384 }, { "epoch": 0.1317097415506958, "grad_norm": 0.3482910394668579, "learning_rate": 3.892543522158935e-05, "loss": 0.012, "step": 2385 }, { "epoch": 0.13176496576098962, "grad_norm": 0.13557247817516327, "learning_rate": 3.892427811565048e-05, "loss": 0.0059, "step": 2386 }, { "epoch": 0.13182018997128342, "grad_norm": 0.08459052443504333, "learning_rate": 3.8923120404270084e-05, "loss": 0.0029, "step": 2387 }, { "epoch": 0.1318754141815772, "grad_norm": 4.427348613739014, "learning_rate": 3.892196208748519e-05, "loss": 0.6214, "step": 2388 }, { "epoch": 0.131930638391871, "grad_norm": 0.369628369808197, "learning_rate": 3.892080316533286e-05, "loss": 0.0065, "step": 2389 }, { "epoch": 0.1319858626021648, "grad_norm": 1.754515290260315, "learning_rate": 3.8919643637850175e-05, "loss": 0.0692, "step": 2390 }, { "epoch": 0.13204108681245857, "grad_norm": 1.8990912437438965, "learning_rate": 3.891848350507423e-05, "loss": 0.7522, "step": 2391 }, { "epoch": 0.13209631102275238, "grad_norm": 3.513953685760498, "learning_rate": 3.891732276704213e-05, "loss": 1.1427, "step": 2392 }, { "epoch": 0.13215153523304618, "grad_norm": 2.353550672531128, "learning_rate": 3.891616142379103e-05, "loss": 0.9475, "step": 2393 }, { "epoch": 0.13220675944333996, "grad_norm": 2.277519464492798, "learning_rate": 3.891499947535807e-05, "loss": 0.5203, "step": 2394 }, { "epoch": 0.13226198365363376, "grad_norm": 0.05739772319793701, "learning_rate": 3.8913836921780425e-05, "loss": 0.0024, "step": 2395 }, { "epoch": 0.13231720786392753, "grad_norm": 4.3862104415893555, "learning_rate": 3.89126737630953e-05, "loss": 0.7328, "step": 2396 }, { "epoch": 0.13237243207422134, "grad_norm": 3.470463991165161, "learning_rate": 3.8911509999339886e-05, "loss": 1.0179, "step": 2397 }, { "epoch": 0.13242765628451514, "grad_norm": 0.1524105668067932, "learning_rate": 3.891034563055145e-05, "loss": 0.0084, "step": 2398 }, { "epoch": 0.1324828804948089, "grad_norm": 4.051578998565674, "learning_rate": 3.89091806567672e-05, "loss": 1.1385, "step": 2399 }, { "epoch": 0.13253810470510272, "grad_norm": 1.1595087051391602, "learning_rate": 3.8908015078024435e-05, "loss": 0.0296, "step": 2400 }, { "epoch": 0.13259332891539652, "grad_norm": 2.2610580921173096, "learning_rate": 3.890684889436044e-05, "loss": 0.1781, "step": 2401 }, { "epoch": 0.1326485531256903, "grad_norm": 0.5171661376953125, "learning_rate": 3.890568210581253e-05, "loss": 0.0146, "step": 2402 }, { "epoch": 0.1327037773359841, "grad_norm": 0.18855537474155426, "learning_rate": 3.890451471241802e-05, "loss": 0.0068, "step": 2403 }, { "epoch": 0.1327590015462779, "grad_norm": 0.07460687309503555, "learning_rate": 3.890334671421427e-05, "loss": 0.0026, "step": 2404 }, { "epoch": 0.13281422575657167, "grad_norm": 2.174488067626953, "learning_rate": 3.8902178111238636e-05, "loss": 0.2431, "step": 2405 }, { "epoch": 0.13286944996686548, "grad_norm": 2.7896533012390137, "learning_rate": 3.8901008903528514e-05, "loss": 0.2327, "step": 2406 }, { "epoch": 0.13292467417715928, "grad_norm": 0.33440300822257996, "learning_rate": 3.8899839091121314e-05, "loss": 0.0073, "step": 2407 }, { "epoch": 0.13297989838745305, "grad_norm": 0.1085163801908493, "learning_rate": 3.8898668674054454e-05, "loss": 0.004, "step": 2408 }, { "epoch": 0.13303512259774686, "grad_norm": 0.04531131312251091, "learning_rate": 3.889749765236538e-05, "loss": 0.0017, "step": 2409 }, { "epoch": 0.13309034680804063, "grad_norm": 0.24984034895896912, "learning_rate": 3.8896326026091556e-05, "loss": 0.0082, "step": 2410 }, { "epoch": 0.13314557101833444, "grad_norm": 0.9546232223510742, "learning_rate": 3.889515379527047e-05, "loss": 0.0173, "step": 2411 }, { "epoch": 0.13320079522862824, "grad_norm": 0.48798978328704834, "learning_rate": 3.889398095993962e-05, "loss": 0.0119, "step": 2412 }, { "epoch": 0.133256019438922, "grad_norm": 4.636463165283203, "learning_rate": 3.8892807520136526e-05, "loss": 1.4256, "step": 2413 }, { "epoch": 0.13331124364921582, "grad_norm": 3.0740067958831787, "learning_rate": 3.889163347589874e-05, "loss": 0.5619, "step": 2414 }, { "epoch": 0.13336646785950962, "grad_norm": 3.4318442344665527, "learning_rate": 3.8890458827263816e-05, "loss": 0.3098, "step": 2415 }, { "epoch": 0.1334216920698034, "grad_norm": 3.3000566959381104, "learning_rate": 3.888928357426934e-05, "loss": 1.1701, "step": 2416 }, { "epoch": 0.1334769162800972, "grad_norm": 1.643687129020691, "learning_rate": 3.88881077169529e-05, "loss": 0.1265, "step": 2417 }, { "epoch": 0.133532140490391, "grad_norm": 1.3199101686477661, "learning_rate": 3.888693125535213e-05, "loss": 0.0528, "step": 2418 }, { "epoch": 0.13358736470068477, "grad_norm": 2.4072368144989014, "learning_rate": 3.888575418950465e-05, "loss": 0.1851, "step": 2419 }, { "epoch": 0.13364258891097858, "grad_norm": 0.10298038274049759, "learning_rate": 3.888457651944813e-05, "loss": 0.0033, "step": 2420 }, { "epoch": 0.13369781312127235, "grad_norm": 3.9939186573028564, "learning_rate": 3.888339824522025e-05, "loss": 0.9194, "step": 2421 }, { "epoch": 0.13375303733156615, "grad_norm": 1.8561433553695679, "learning_rate": 3.88822193668587e-05, "loss": 0.1439, "step": 2422 }, { "epoch": 0.13380826154185996, "grad_norm": 0.17668263614177704, "learning_rate": 3.88810398844012e-05, "loss": 0.006, "step": 2423 }, { "epoch": 0.13386348575215373, "grad_norm": 2.5179665088653564, "learning_rate": 3.8879859797885475e-05, "loss": 0.0935, "step": 2424 }, { "epoch": 0.13391870996244754, "grad_norm": 4.293405055999756, "learning_rate": 3.887867910734929e-05, "loss": 0.4546, "step": 2425 }, { "epoch": 0.13397393417274134, "grad_norm": 3.6355974674224854, "learning_rate": 3.8877497812830414e-05, "loss": 0.2298, "step": 2426 }, { "epoch": 0.1340291583830351, "grad_norm": 0.14758865535259247, "learning_rate": 3.8876315914366646e-05, "loss": 0.003, "step": 2427 }, { "epoch": 0.13408438259332892, "grad_norm": 0.717481791973114, "learning_rate": 3.887513341199578e-05, "loss": 0.0167, "step": 2428 }, { "epoch": 0.13413960680362272, "grad_norm": 2.8872568607330322, "learning_rate": 3.8873950305755676e-05, "loss": 0.4239, "step": 2429 }, { "epoch": 0.1341948310139165, "grad_norm": 1.18752121925354, "learning_rate": 3.887276659568417e-05, "loss": 0.0441, "step": 2430 }, { "epoch": 0.1342500552242103, "grad_norm": 0.05503864213824272, "learning_rate": 3.8871582281819123e-05, "loss": 0.0015, "step": 2431 }, { "epoch": 0.1343052794345041, "grad_norm": 1.5958082675933838, "learning_rate": 3.887039736419844e-05, "loss": 0.0657, "step": 2432 }, { "epoch": 0.13436050364479787, "grad_norm": 4.3888115882873535, "learning_rate": 3.8869211842860016e-05, "loss": 0.0998, "step": 2433 }, { "epoch": 0.13441572785509168, "grad_norm": 0.32782071828842163, "learning_rate": 3.88680257178418e-05, "loss": 0.0085, "step": 2434 }, { "epoch": 0.13447095206538545, "grad_norm": 3.759427547454834, "learning_rate": 3.886683898918172e-05, "loss": 0.5343, "step": 2435 }, { "epoch": 0.13452617627567925, "grad_norm": 0.026490069925785065, "learning_rate": 3.8865651656917746e-05, "loss": 0.0009, "step": 2436 }, { "epoch": 0.13458140048597306, "grad_norm": 3.920696496963501, "learning_rate": 3.886446372108787e-05, "loss": 0.2722, "step": 2437 }, { "epoch": 0.13463662469626683, "grad_norm": 3.348619222640991, "learning_rate": 3.8863275181730095e-05, "loss": 0.4047, "step": 2438 }, { "epoch": 0.13469184890656064, "grad_norm": 0.33953842520713806, "learning_rate": 3.886208603888244e-05, "loss": 0.0103, "step": 2439 }, { "epoch": 0.13474707311685444, "grad_norm": 4.013564109802246, "learning_rate": 3.886089629258296e-05, "loss": 0.6954, "step": 2440 }, { "epoch": 0.1348022973271482, "grad_norm": 0.2120758444070816, "learning_rate": 3.8859705942869715e-05, "loss": 0.0075, "step": 2441 }, { "epoch": 0.13485752153744202, "grad_norm": 0.2810676693916321, "learning_rate": 3.885851498978078e-05, "loss": 0.0084, "step": 2442 }, { "epoch": 0.13491274574773582, "grad_norm": 3.389859676361084, "learning_rate": 3.885732343335427e-05, "loss": 0.0628, "step": 2443 }, { "epoch": 0.1349679699580296, "grad_norm": 3.9817826747894287, "learning_rate": 3.8856131273628295e-05, "loss": 0.188, "step": 2444 }, { "epoch": 0.1350231941683234, "grad_norm": 3.486015796661377, "learning_rate": 3.8854938510641e-05, "loss": 0.8101, "step": 2445 }, { "epoch": 0.1350784183786172, "grad_norm": 5.013569355010986, "learning_rate": 3.885374514443054e-05, "loss": 1.4814, "step": 2446 }, { "epoch": 0.13513364258891097, "grad_norm": 1.7755390405654907, "learning_rate": 3.8852551175035104e-05, "loss": 0.0916, "step": 2447 }, { "epoch": 0.13518886679920478, "grad_norm": 0.17790581285953522, "learning_rate": 3.885135660249289e-05, "loss": 0.0043, "step": 2448 }, { "epoch": 0.13524409100949855, "grad_norm": 3.3887951374053955, "learning_rate": 3.88501614268421e-05, "loss": 0.3113, "step": 2449 }, { "epoch": 0.13529931521979235, "grad_norm": 0.2289057821035385, "learning_rate": 3.884896564812098e-05, "loss": 0.0048, "step": 2450 }, { "epoch": 0.13535453943008616, "grad_norm": 0.1468169093132019, "learning_rate": 3.88477692663678e-05, "loss": 0.0048, "step": 2451 }, { "epoch": 0.13540976364037993, "grad_norm": 2.3447420597076416, "learning_rate": 3.8846572281620815e-05, "loss": 0.1724, "step": 2452 }, { "epoch": 0.13546498785067373, "grad_norm": 0.1563718616962433, "learning_rate": 3.884537469391833e-05, "loss": 0.0024, "step": 2453 }, { "epoch": 0.13552021206096754, "grad_norm": 0.22693867981433868, "learning_rate": 3.884417650329866e-05, "loss": 0.0056, "step": 2454 }, { "epoch": 0.1355754362712613, "grad_norm": 3.1401143074035645, "learning_rate": 3.8842977709800136e-05, "loss": 0.5944, "step": 2455 }, { "epoch": 0.13563066048155512, "grad_norm": 0.08862324804067612, "learning_rate": 3.8841778313461115e-05, "loss": 0.0036, "step": 2456 }, { "epoch": 0.13568588469184892, "grad_norm": 0.389178991317749, "learning_rate": 3.884057831431996e-05, "loss": 0.0173, "step": 2457 }, { "epoch": 0.1357411089021427, "grad_norm": 2.634552478790283, "learning_rate": 3.8839377712415075e-05, "loss": 0.2012, "step": 2458 }, { "epoch": 0.1357963331124365, "grad_norm": 0.21722576022148132, "learning_rate": 3.883817650778486e-05, "loss": 0.0067, "step": 2459 }, { "epoch": 0.1358515573227303, "grad_norm": 4.713653564453125, "learning_rate": 3.883697470046775e-05, "loss": 0.441, "step": 2460 }, { "epoch": 0.13590678153302407, "grad_norm": 4.875687599182129, "learning_rate": 3.883577229050219e-05, "loss": 1.8751, "step": 2461 }, { "epoch": 0.13596200574331788, "grad_norm": 4.68801212310791, "learning_rate": 3.883456927792665e-05, "loss": 0.7318, "step": 2462 }, { "epoch": 0.13601722995361165, "grad_norm": 1.8350118398666382, "learning_rate": 3.883336566277962e-05, "loss": 0.3402, "step": 2463 }, { "epoch": 0.13607245416390545, "grad_norm": 2.3466134071350098, "learning_rate": 3.883216144509961e-05, "loss": 0.3828, "step": 2464 }, { "epoch": 0.13612767837419926, "grad_norm": 4.470776081085205, "learning_rate": 3.883095662492515e-05, "loss": 1.1868, "step": 2465 }, { "epoch": 0.13618290258449303, "grad_norm": 0.35319551825523376, "learning_rate": 3.882975120229476e-05, "loss": 0.0111, "step": 2466 }, { "epoch": 0.13623812679478683, "grad_norm": 2.6750543117523193, "learning_rate": 3.882854517724704e-05, "loss": 0.2887, "step": 2467 }, { "epoch": 0.13629335100508064, "grad_norm": 2.1141369342803955, "learning_rate": 3.882733854982054e-05, "loss": 0.103, "step": 2468 }, { "epoch": 0.1363485752153744, "grad_norm": 4.3484206199646, "learning_rate": 3.8826131320053895e-05, "loss": 0.5849, "step": 2469 }, { "epoch": 0.13640379942566822, "grad_norm": 5.894852161407471, "learning_rate": 3.882492348798571e-05, "loss": 1.0309, "step": 2470 }, { "epoch": 0.13645902363596202, "grad_norm": 0.097833052277565, "learning_rate": 3.8823715053654624e-05, "loss": 0.0033, "step": 2471 }, { "epoch": 0.1365142478462558, "grad_norm": 5.040555477142334, "learning_rate": 3.882250601709931e-05, "loss": 0.0753, "step": 2472 }, { "epoch": 0.1365694720565496, "grad_norm": 0.106836698949337, "learning_rate": 3.882129637835844e-05, "loss": 0.0025, "step": 2473 }, { "epoch": 0.13662469626684337, "grad_norm": 1.6248538494110107, "learning_rate": 3.882008613747072e-05, "loss": 0.2841, "step": 2474 }, { "epoch": 0.13667992047713717, "grad_norm": 1.3099710941314697, "learning_rate": 3.881887529447487e-05, "loss": 0.0425, "step": 2475 }, { "epoch": 0.13673514468743098, "grad_norm": 0.03406586870551109, "learning_rate": 3.881766384940962e-05, "loss": 0.001, "step": 2476 }, { "epoch": 0.13679036889772475, "grad_norm": 3.8228237628936768, "learning_rate": 3.881645180231373e-05, "loss": 0.8157, "step": 2477 }, { "epoch": 0.13684559310801855, "grad_norm": 4.445845603942871, "learning_rate": 3.8815239153225984e-05, "loss": 0.8546, "step": 2478 }, { "epoch": 0.13690081731831236, "grad_norm": 5.470333576202393, "learning_rate": 3.8814025902185166e-05, "loss": 0.7789, "step": 2479 }, { "epoch": 0.13695604152860613, "grad_norm": 2.8904621601104736, "learning_rate": 3.88128120492301e-05, "loss": 0.1608, "step": 2480 }, { "epoch": 0.13701126573889993, "grad_norm": 3.5701305866241455, "learning_rate": 3.881159759439962e-05, "loss": 0.147, "step": 2481 }, { "epoch": 0.13706648994919374, "grad_norm": 1.9221768379211426, "learning_rate": 3.881038253773258e-05, "loss": 0.3235, "step": 2482 }, { "epoch": 0.1371217141594875, "grad_norm": 1.3356572389602661, "learning_rate": 3.880916687926785e-05, "loss": 0.0524, "step": 2483 }, { "epoch": 0.13717693836978131, "grad_norm": 0.8975638151168823, "learning_rate": 3.880795061904433e-05, "loss": 0.025, "step": 2484 }, { "epoch": 0.13723216258007512, "grad_norm": 3.6997594833374023, "learning_rate": 3.880673375710092e-05, "loss": 0.6993, "step": 2485 }, { "epoch": 0.1372873867903689, "grad_norm": 4.373580455780029, "learning_rate": 3.880551629347656e-05, "loss": 1.4928, "step": 2486 }, { "epoch": 0.1373426110006627, "grad_norm": 1.6735411882400513, "learning_rate": 3.88042982282102e-05, "loss": 0.1417, "step": 2487 }, { "epoch": 0.13739783521095647, "grad_norm": 0.30836156010627747, "learning_rate": 3.880307956134079e-05, "loss": 0.0091, "step": 2488 }, { "epoch": 0.13745305942125027, "grad_norm": 0.9823681712150574, "learning_rate": 3.880186029290735e-05, "loss": 0.0375, "step": 2489 }, { "epoch": 0.13750828363154408, "grad_norm": 0.4398544132709503, "learning_rate": 3.880064042294887e-05, "loss": 0.0179, "step": 2490 }, { "epoch": 0.13756350784183785, "grad_norm": 1.9794437885284424, "learning_rate": 3.879941995150438e-05, "loss": 0.1911, "step": 2491 }, { "epoch": 0.13761873205213165, "grad_norm": 5.844122886657715, "learning_rate": 3.879819887861293e-05, "loss": 1.1506, "step": 2492 }, { "epoch": 0.13767395626242546, "grad_norm": 0.14763550460338593, "learning_rate": 3.879697720431357e-05, "loss": 0.0042, "step": 2493 }, { "epoch": 0.13772918047271923, "grad_norm": 2.9542245864868164, "learning_rate": 3.8795754928645405e-05, "loss": 1.0106, "step": 2494 }, { "epoch": 0.13778440468301303, "grad_norm": 1.4299242496490479, "learning_rate": 3.8794532051647526e-05, "loss": 0.2448, "step": 2495 }, { "epoch": 0.13783962889330684, "grad_norm": 0.1556997448205948, "learning_rate": 3.8793308573359064e-05, "loss": 0.0043, "step": 2496 }, { "epoch": 0.1378948531036006, "grad_norm": 0.19819436967372894, "learning_rate": 3.8792084493819165e-05, "loss": 0.005, "step": 2497 }, { "epoch": 0.13795007731389441, "grad_norm": 0.14765986800193787, "learning_rate": 3.8790859813066976e-05, "loss": 0.0043, "step": 2498 }, { "epoch": 0.13800530152418822, "grad_norm": 3.3018813133239746, "learning_rate": 3.8789634531141684e-05, "loss": 0.6571, "step": 2499 }, { "epoch": 0.138060525734482, "grad_norm": 1.1229538917541504, "learning_rate": 3.87884086480825e-05, "loss": 0.0428, "step": 2500 }, { "epoch": 0.1381157499447758, "grad_norm": 0.2237352877855301, "learning_rate": 3.878718216392863e-05, "loss": 0.0084, "step": 2501 }, { "epoch": 0.13817097415506957, "grad_norm": 2.656686544418335, "learning_rate": 3.878595507871931e-05, "loss": 0.2262, "step": 2502 }, { "epoch": 0.13822619836536337, "grad_norm": 2.3110318183898926, "learning_rate": 3.878472739249382e-05, "loss": 0.4661, "step": 2503 }, { "epoch": 0.13828142257565718, "grad_norm": 0.5705171823501587, "learning_rate": 3.8783499105291416e-05, "loss": 0.0179, "step": 2504 }, { "epoch": 0.13833664678595095, "grad_norm": 3.642406463623047, "learning_rate": 3.8782270217151405e-05, "loss": 0.256, "step": 2505 }, { "epoch": 0.13839187099624475, "grad_norm": 0.3157048523426056, "learning_rate": 3.8781040728113096e-05, "loss": 0.0108, "step": 2506 }, { "epoch": 0.13844709520653856, "grad_norm": 0.05131111666560173, "learning_rate": 3.877981063821583e-05, "loss": 0.0013, "step": 2507 }, { "epoch": 0.13850231941683233, "grad_norm": 2.051640272140503, "learning_rate": 3.8778579947498953e-05, "loss": 0.0585, "step": 2508 }, { "epoch": 0.13855754362712613, "grad_norm": 0.6084541082382202, "learning_rate": 3.877734865600185e-05, "loss": 0.0266, "step": 2509 }, { "epoch": 0.13861276783741994, "grad_norm": 3.2635202407836914, "learning_rate": 3.8776116763763896e-05, "loss": 0.4445, "step": 2510 }, { "epoch": 0.1386679920477137, "grad_norm": 1.4473978281021118, "learning_rate": 3.877488427082452e-05, "loss": 0.181, "step": 2511 }, { "epoch": 0.13872321625800751, "grad_norm": 0.3330337107181549, "learning_rate": 3.877365117722315e-05, "loss": 0.007, "step": 2512 }, { "epoch": 0.1387784404683013, "grad_norm": 1.833125352859497, "learning_rate": 3.877241748299923e-05, "loss": 0.1067, "step": 2513 }, { "epoch": 0.1388336646785951, "grad_norm": 2.7206876277923584, "learning_rate": 3.8771183188192234e-05, "loss": 0.3337, "step": 2514 }, { "epoch": 0.1388888888888889, "grad_norm": 2.451134204864502, "learning_rate": 3.876994829284164e-05, "loss": 0.0955, "step": 2515 }, { "epoch": 0.13894411309918267, "grad_norm": 0.8388774394989014, "learning_rate": 3.876871279698697e-05, "loss": 0.0185, "step": 2516 }, { "epoch": 0.13899933730947647, "grad_norm": 0.3298887610435486, "learning_rate": 3.8767476700667747e-05, "loss": 0.0088, "step": 2517 }, { "epoch": 0.13905456151977028, "grad_norm": 2.697164535522461, "learning_rate": 3.876624000392352e-05, "loss": 0.6779, "step": 2518 }, { "epoch": 0.13910978573006405, "grad_norm": 4.191402435302734, "learning_rate": 3.876500270679384e-05, "loss": 1.5016, "step": 2519 }, { "epoch": 0.13916500994035785, "grad_norm": 2.033935546875, "learning_rate": 3.876376480931831e-05, "loss": 0.5868, "step": 2520 }, { "epoch": 0.13922023415065166, "grad_norm": 0.7384020090103149, "learning_rate": 3.876252631153652e-05, "loss": 0.0219, "step": 2521 }, { "epoch": 0.13927545836094543, "grad_norm": 2.5532658100128174, "learning_rate": 3.87612872134881e-05, "loss": 0.2277, "step": 2522 }, { "epoch": 0.13933068257123923, "grad_norm": 2.1424524784088135, "learning_rate": 3.876004751521269e-05, "loss": 0.984, "step": 2523 }, { "epoch": 0.13938590678153304, "grad_norm": 0.17880868911743164, "learning_rate": 3.8758807216749956e-05, "loss": 0.0037, "step": 2524 }, { "epoch": 0.1394411309918268, "grad_norm": 1.022171139717102, "learning_rate": 3.875756631813957e-05, "loss": 0.0175, "step": 2525 }, { "epoch": 0.13949635520212061, "grad_norm": 0.024853551760315895, "learning_rate": 3.8756324819421244e-05, "loss": 0.0008, "step": 2526 }, { "epoch": 0.1395515794124144, "grad_norm": 3.545914649963379, "learning_rate": 3.875508272063469e-05, "loss": 0.7707, "step": 2527 }, { "epoch": 0.1396068036227082, "grad_norm": 3.2807116508483887, "learning_rate": 3.875384002181964e-05, "loss": 0.2888, "step": 2528 }, { "epoch": 0.139662027833002, "grad_norm": 0.2601708769798279, "learning_rate": 3.875259672301586e-05, "loss": 0.0079, "step": 2529 }, { "epoch": 0.13971725204329577, "grad_norm": 1.3795592784881592, "learning_rate": 3.875135282426313e-05, "loss": 0.0652, "step": 2530 }, { "epoch": 0.13977247625358957, "grad_norm": 0.06522412598133087, "learning_rate": 3.875010832560123e-05, "loss": 0.0023, "step": 2531 }, { "epoch": 0.13982770046388338, "grad_norm": 0.32733243703842163, "learning_rate": 3.8748863227069994e-05, "loss": 0.0062, "step": 2532 }, { "epoch": 0.13988292467417715, "grad_norm": 3.6581621170043945, "learning_rate": 3.8747617528709246e-05, "loss": 0.2763, "step": 2533 }, { "epoch": 0.13993814888447095, "grad_norm": 2.9367330074310303, "learning_rate": 3.874637123055884e-05, "loss": 0.1526, "step": 2534 }, { "epoch": 0.13999337309476476, "grad_norm": 3.0328850746154785, "learning_rate": 3.874512433265865e-05, "loss": 1.444, "step": 2535 }, { "epoch": 0.14004859730505853, "grad_norm": 0.09599880874156952, "learning_rate": 3.874387683504857e-05, "loss": 0.0028, "step": 2536 }, { "epoch": 0.14010382151535233, "grad_norm": 0.015351631678640842, "learning_rate": 3.87426287377685e-05, "loss": 0.0004, "step": 2537 }, { "epoch": 0.14015904572564614, "grad_norm": 3.3701910972595215, "learning_rate": 3.874138004085839e-05, "loss": 0.9388, "step": 2538 }, { "epoch": 0.1402142699359399, "grad_norm": 0.6586227416992188, "learning_rate": 3.8740130744358176e-05, "loss": 0.0197, "step": 2539 }, { "epoch": 0.14026949414623371, "grad_norm": 1.0348581075668335, "learning_rate": 3.873888084830782e-05, "loss": 0.0599, "step": 2540 }, { "epoch": 0.1403247183565275, "grad_norm": 0.34290122985839844, "learning_rate": 3.873763035274733e-05, "loss": 0.0101, "step": 2541 }, { "epoch": 0.1403799425668213, "grad_norm": 3.780447483062744, "learning_rate": 3.873637925771669e-05, "loss": 0.2381, "step": 2542 }, { "epoch": 0.1404351667771151, "grad_norm": 1.0081748962402344, "learning_rate": 3.8735127563255946e-05, "loss": 0.0357, "step": 2543 }, { "epoch": 0.14049039098740887, "grad_norm": 2.857222557067871, "learning_rate": 3.873387526940513e-05, "loss": 0.5766, "step": 2544 }, { "epoch": 0.14054561519770267, "grad_norm": 0.6853592395782471, "learning_rate": 3.873262237620432e-05, "loss": 0.0204, "step": 2545 }, { "epoch": 0.14060083940799648, "grad_norm": 0.052453406155109406, "learning_rate": 3.8731368883693576e-05, "loss": 0.0013, "step": 2546 }, { "epoch": 0.14065606361829025, "grad_norm": 2.7495741844177246, "learning_rate": 3.8730114791913026e-05, "loss": 0.1232, "step": 2547 }, { "epoch": 0.14071128782858405, "grad_norm": 2.4977779388427734, "learning_rate": 3.872886010090278e-05, "loss": 0.1439, "step": 2548 }, { "epoch": 0.14076651203887786, "grad_norm": 3.0379984378814697, "learning_rate": 3.872760481070298e-05, "loss": 0.5359, "step": 2549 }, { "epoch": 0.14082173624917163, "grad_norm": 0.03357686474919319, "learning_rate": 3.872634892135379e-05, "loss": 0.001, "step": 2550 }, { "epoch": 0.14087696045946543, "grad_norm": 0.46033939719200134, "learning_rate": 3.8725092432895376e-05, "loss": 0.0137, "step": 2551 }, { "epoch": 0.14093218466975924, "grad_norm": 0.11301866918802261, "learning_rate": 3.872383534536796e-05, "loss": 0.0051, "step": 2552 }, { "epoch": 0.140987408880053, "grad_norm": 0.03494885563850403, "learning_rate": 3.8722577658811735e-05, "loss": 0.0013, "step": 2553 }, { "epoch": 0.14104263309034681, "grad_norm": 4.89113187789917, "learning_rate": 3.872131937326696e-05, "loss": 0.1447, "step": 2554 }, { "epoch": 0.1410978573006406, "grad_norm": 0.04098102077841759, "learning_rate": 3.872006048877388e-05, "loss": 0.0012, "step": 2555 }, { "epoch": 0.1411530815109344, "grad_norm": 0.0347733236849308, "learning_rate": 3.8718801005372766e-05, "loss": 0.0012, "step": 2556 }, { "epoch": 0.1412083057212282, "grad_norm": 0.037299711257219315, "learning_rate": 3.871754092310392e-05, "loss": 0.0011, "step": 2557 }, { "epoch": 0.14126352993152197, "grad_norm": 3.4407958984375, "learning_rate": 3.871628024200765e-05, "loss": 0.967, "step": 2558 }, { "epoch": 0.14131875414181577, "grad_norm": 9.476284980773926, "learning_rate": 3.8715018962124295e-05, "loss": 0.3835, "step": 2559 }, { "epoch": 0.14137397835210957, "grad_norm": 2.9192888736724854, "learning_rate": 3.871375708349421e-05, "loss": 0.7844, "step": 2560 }, { "epoch": 0.14142920256240335, "grad_norm": 1.7209874391555786, "learning_rate": 3.8712494606157746e-05, "loss": 0.1131, "step": 2561 }, { "epoch": 0.14148442677269715, "grad_norm": 3.649007797241211, "learning_rate": 3.871123153015532e-05, "loss": 0.4861, "step": 2562 }, { "epoch": 0.14153965098299096, "grad_norm": 4.414297103881836, "learning_rate": 3.870996785552732e-05, "loss": 0.3588, "step": 2563 }, { "epoch": 0.14159487519328473, "grad_norm": 0.5018669366836548, "learning_rate": 3.87087035823142e-05, "loss": 0.0141, "step": 2564 }, { "epoch": 0.14165009940357853, "grad_norm": 0.6616705656051636, "learning_rate": 3.8707438710556375e-05, "loss": 0.0205, "step": 2565 }, { "epoch": 0.1417053236138723, "grad_norm": 0.007588190957903862, "learning_rate": 3.8706173240294335e-05, "loss": 0.0003, "step": 2566 }, { "epoch": 0.1417605478241661, "grad_norm": 3.7223012447357178, "learning_rate": 3.870490717156855e-05, "loss": 0.6465, "step": 2567 }, { "epoch": 0.1418157720344599, "grad_norm": 0.5650807619094849, "learning_rate": 3.870364050441954e-05, "loss": 0.0155, "step": 2568 }, { "epoch": 0.1418709962447537, "grad_norm": 3.249128818511963, "learning_rate": 3.870237323888783e-05, "loss": 0.6151, "step": 2569 }, { "epoch": 0.1419262204550475, "grad_norm": 1.1820104122161865, "learning_rate": 3.870110537501395e-05, "loss": 0.1342, "step": 2570 }, { "epoch": 0.1419814446653413, "grad_norm": 0.5048978328704834, "learning_rate": 3.8699836912838466e-05, "loss": 0.0247, "step": 2571 }, { "epoch": 0.14203666887563507, "grad_norm": 0.028424696996808052, "learning_rate": 3.869856785240197e-05, "loss": 0.0009, "step": 2572 }, { "epoch": 0.14209189308592887, "grad_norm": 2.8924999237060547, "learning_rate": 3.869729819374505e-05, "loss": 0.0616, "step": 2573 }, { "epoch": 0.14214711729622267, "grad_norm": 0.6191950440406799, "learning_rate": 3.869602793690834e-05, "loss": 0.0109, "step": 2574 }, { "epoch": 0.14220234150651645, "grad_norm": 0.1389778107404709, "learning_rate": 3.8694757081932464e-05, "loss": 0.0032, "step": 2575 }, { "epoch": 0.14225756571681025, "grad_norm": 6.057955265045166, "learning_rate": 3.869348562885809e-05, "loss": 1.1526, "step": 2576 }, { "epoch": 0.14231278992710406, "grad_norm": 8.668196678161621, "learning_rate": 3.8692213577725894e-05, "loss": 0.1558, "step": 2577 }, { "epoch": 0.14236801413739783, "grad_norm": 3.3785030841827393, "learning_rate": 3.869094092857657e-05, "loss": 0.4537, "step": 2578 }, { "epoch": 0.14242323834769163, "grad_norm": 0.8600090742111206, "learning_rate": 3.868966768145083e-05, "loss": 0.036, "step": 2579 }, { "epoch": 0.1424784625579854, "grad_norm": 2.525714635848999, "learning_rate": 3.8688393836389424e-05, "loss": 0.6678, "step": 2580 }, { "epoch": 0.1425336867682792, "grad_norm": 0.44258803129196167, "learning_rate": 3.8687119393433085e-05, "loss": 0.0105, "step": 2581 }, { "epoch": 0.142588910978573, "grad_norm": 0.07997240871191025, "learning_rate": 3.86858443526226e-05, "loss": 0.001, "step": 2582 }, { "epoch": 0.1426441351888668, "grad_norm": 4.715931415557861, "learning_rate": 3.8684568713998764e-05, "loss": 0.8507, "step": 2583 }, { "epoch": 0.1426993593991606, "grad_norm": 0.021024109795689583, "learning_rate": 3.8683292477602374e-05, "loss": 0.0007, "step": 2584 }, { "epoch": 0.1427545836094544, "grad_norm": 0.047800302505493164, "learning_rate": 3.8682015643474275e-05, "loss": 0.0013, "step": 2585 }, { "epoch": 0.14280980781974817, "grad_norm": 0.7499178051948547, "learning_rate": 3.8680738211655306e-05, "loss": 0.0323, "step": 2586 }, { "epoch": 0.14286503203004197, "grad_norm": 3.2942240238189697, "learning_rate": 3.867946018218634e-05, "loss": 0.5811, "step": 2587 }, { "epoch": 0.14292025624033577, "grad_norm": 7.4721598625183105, "learning_rate": 3.8678181555108266e-05, "loss": 1.2897, "step": 2588 }, { "epoch": 0.14297548045062955, "grad_norm": 0.9004323482513428, "learning_rate": 3.867690233046199e-05, "loss": 0.0204, "step": 2589 }, { "epoch": 0.14303070466092335, "grad_norm": 2.080768585205078, "learning_rate": 3.867562250828844e-05, "loss": 0.237, "step": 2590 }, { "epoch": 0.14308592887121716, "grad_norm": 0.919366180896759, "learning_rate": 3.867434208862856e-05, "loss": 0.0332, "step": 2591 }, { "epoch": 0.14314115308151093, "grad_norm": 3.678800582885742, "learning_rate": 3.867306107152331e-05, "loss": 0.5269, "step": 2592 }, { "epoch": 0.14319637729180473, "grad_norm": 2.3999109268188477, "learning_rate": 3.867177945701367e-05, "loss": 0.3068, "step": 2593 }, { "epoch": 0.1432516015020985, "grad_norm": 2.4120993614196777, "learning_rate": 3.867049724514066e-05, "loss": 0.1556, "step": 2594 }, { "epoch": 0.1433068257123923, "grad_norm": 0.27988895773887634, "learning_rate": 3.8669214435945283e-05, "loss": 0.0058, "step": 2595 }, { "epoch": 0.1433620499226861, "grad_norm": 0.3138928711414337, "learning_rate": 3.866793102946859e-05, "loss": 0.0105, "step": 2596 }, { "epoch": 0.1434172741329799, "grad_norm": 2.68849515914917, "learning_rate": 3.866664702575164e-05, "loss": 0.1026, "step": 2597 }, { "epoch": 0.1434724983432737, "grad_norm": 2.6803529262542725, "learning_rate": 3.866536242483551e-05, "loss": 0.6488, "step": 2598 }, { "epoch": 0.1435277225535675, "grad_norm": 4.511563777923584, "learning_rate": 3.866407722676129e-05, "loss": 1.363, "step": 2599 }, { "epoch": 0.14358294676386127, "grad_norm": 2.9518847465515137, "learning_rate": 3.866279143157012e-05, "loss": 0.4003, "step": 2600 }, { "epoch": 0.14363817097415507, "grad_norm": 4.68499755859375, "learning_rate": 3.8661505039303104e-05, "loss": 1.0416, "step": 2601 }, { "epoch": 0.14369339518444887, "grad_norm": 2.8489582538604736, "learning_rate": 3.866021805000142e-05, "loss": 0.296, "step": 2602 }, { "epoch": 0.14374861939474265, "grad_norm": 0.2584573030471802, "learning_rate": 3.865893046370625e-05, "loss": 0.0055, "step": 2603 }, { "epoch": 0.14380384360503645, "grad_norm": 0.061650242656469345, "learning_rate": 3.8657642280458764e-05, "loss": 0.0026, "step": 2604 }, { "epoch": 0.14385906781533023, "grad_norm": 1.1063220500946045, "learning_rate": 3.865635350030019e-05, "loss": 0.0254, "step": 2605 }, { "epoch": 0.14391429202562403, "grad_norm": 0.564426600933075, "learning_rate": 3.865506412327175e-05, "loss": 0.015, "step": 2606 }, { "epoch": 0.14396951623591783, "grad_norm": 2.126678228378296, "learning_rate": 3.86537741494147e-05, "loss": 0.135, "step": 2607 }, { "epoch": 0.1440247404462116, "grad_norm": 0.44285646080970764, "learning_rate": 3.865248357877032e-05, "loss": 0.0166, "step": 2608 }, { "epoch": 0.1440799646565054, "grad_norm": 0.07055578380823135, "learning_rate": 3.865119241137988e-05, "loss": 0.0017, "step": 2609 }, { "epoch": 0.1441351888667992, "grad_norm": 4.742039203643799, "learning_rate": 3.86499006472847e-05, "loss": 1.2108, "step": 2610 }, { "epoch": 0.144190413077093, "grad_norm": 0.06879287958145142, "learning_rate": 3.86486082865261e-05, "loss": 0.0024, "step": 2611 }, { "epoch": 0.1442456372873868, "grad_norm": 3.08280348777771, "learning_rate": 3.864731532914543e-05, "loss": 0.6143, "step": 2612 }, { "epoch": 0.1443008614976806, "grad_norm": 1.951586127281189, "learning_rate": 3.864602177518406e-05, "loss": 0.2879, "step": 2613 }, { "epoch": 0.14435608570797437, "grad_norm": 0.019187666475772858, "learning_rate": 3.864472762468338e-05, "loss": 0.0007, "step": 2614 }, { "epoch": 0.14441130991826817, "grad_norm": 1.34005606174469, "learning_rate": 3.864343287768477e-05, "loss": 0.0312, "step": 2615 }, { "epoch": 0.14446653412856197, "grad_norm": 3.9195191860198975, "learning_rate": 3.864213753422967e-05, "loss": 0.8741, "step": 2616 }, { "epoch": 0.14452175833885575, "grad_norm": 0.09477679431438446, "learning_rate": 3.864084159435952e-05, "loss": 0.0024, "step": 2617 }, { "epoch": 0.14457698254914955, "grad_norm": 0.08432142436504364, "learning_rate": 3.8639545058115776e-05, "loss": 0.0028, "step": 2618 }, { "epoch": 0.14463220675944333, "grad_norm": 4.71885347366333, "learning_rate": 3.8638247925539926e-05, "loss": 0.7736, "step": 2619 }, { "epoch": 0.14468743096973713, "grad_norm": 5.952374458312988, "learning_rate": 3.863695019667346e-05, "loss": 0.7091, "step": 2620 }, { "epoch": 0.14474265518003093, "grad_norm": 3.6468169689178467, "learning_rate": 3.8635651871557905e-05, "loss": 0.727, "step": 2621 }, { "epoch": 0.1447978793903247, "grad_norm": 1.9117164611816406, "learning_rate": 3.863435295023479e-05, "loss": 0.0686, "step": 2622 }, { "epoch": 0.1448531036006185, "grad_norm": 3.2951738834381104, "learning_rate": 3.8633053432745676e-05, "loss": 0.1478, "step": 2623 }, { "epoch": 0.1449083278109123, "grad_norm": 1.2187821865081787, "learning_rate": 3.8631753319132134e-05, "loss": 0.0249, "step": 2624 }, { "epoch": 0.1449635520212061, "grad_norm": 5.930171966552734, "learning_rate": 3.8630452609435765e-05, "loss": 0.0765, "step": 2625 }, { "epoch": 0.1450187762314999, "grad_norm": 0.3556579351425171, "learning_rate": 3.862915130369817e-05, "loss": 0.0079, "step": 2626 }, { "epoch": 0.1450740004417937, "grad_norm": 3.106412649154663, "learning_rate": 3.862784940196101e-05, "loss": 0.421, "step": 2627 }, { "epoch": 0.14512922465208747, "grad_norm": 3.973555088043213, "learning_rate": 3.86265469042659e-05, "loss": 0.5813, "step": 2628 }, { "epoch": 0.14518444886238127, "grad_norm": 5.627493381500244, "learning_rate": 3.862524381065453e-05, "loss": 0.3994, "step": 2629 }, { "epoch": 0.14523967307267507, "grad_norm": 2.3766231536865234, "learning_rate": 3.862394012116858e-05, "loss": 0.4313, "step": 2630 }, { "epoch": 0.14529489728296885, "grad_norm": 1.70556640625, "learning_rate": 3.8622635835849775e-05, "loss": 0.1128, "step": 2631 }, { "epoch": 0.14535012149326265, "grad_norm": 4.048344135284424, "learning_rate": 3.862133095473983e-05, "loss": 0.6436, "step": 2632 }, { "epoch": 0.14540534570355643, "grad_norm": 0.48558521270751953, "learning_rate": 3.86200254778805e-05, "loss": 0.0121, "step": 2633 }, { "epoch": 0.14546056991385023, "grad_norm": 3.8407275676727295, "learning_rate": 3.861871940531354e-05, "loss": 0.9819, "step": 2634 }, { "epoch": 0.14551579412414403, "grad_norm": 2.84883451461792, "learning_rate": 3.8617412737080746e-05, "loss": 0.1346, "step": 2635 }, { "epoch": 0.1455710183344378, "grad_norm": 3.4110989570617676, "learning_rate": 3.861610547322391e-05, "loss": 0.7939, "step": 2636 }, { "epoch": 0.1456262425447316, "grad_norm": 0.01843898370862007, "learning_rate": 3.861479761378487e-05, "loss": 0.0006, "step": 2637 }, { "epoch": 0.1456814667550254, "grad_norm": 0.021502623334527016, "learning_rate": 3.861348915880545e-05, "loss": 0.0007, "step": 2638 }, { "epoch": 0.1457366909653192, "grad_norm": 1.2321295738220215, "learning_rate": 3.861218010832753e-05, "loss": 0.1598, "step": 2639 }, { "epoch": 0.145791915175613, "grad_norm": 0.3391202390193939, "learning_rate": 3.8610870462392987e-05, "loss": 0.0091, "step": 2640 }, { "epoch": 0.1458471393859068, "grad_norm": 0.0495452955365181, "learning_rate": 3.8609560221043704e-05, "loss": 0.0022, "step": 2641 }, { "epoch": 0.14590236359620057, "grad_norm": 0.12188808619976044, "learning_rate": 3.860824938432162e-05, "loss": 0.0032, "step": 2642 }, { "epoch": 0.14595758780649437, "grad_norm": 3.5367813110351562, "learning_rate": 3.860693795226865e-05, "loss": 0.5885, "step": 2643 }, { "epoch": 0.14601281201678817, "grad_norm": 0.12232127040624619, "learning_rate": 3.860562592492677e-05, "loss": 0.0033, "step": 2644 }, { "epoch": 0.14606803622708195, "grad_norm": 0.037424761801958084, "learning_rate": 3.8604313302337956e-05, "loss": 0.0012, "step": 2645 }, { "epoch": 0.14612326043737575, "grad_norm": 2.2214410305023193, "learning_rate": 3.8603000084544184e-05, "loss": 0.5361, "step": 2646 }, { "epoch": 0.14617848464766953, "grad_norm": 3.644916296005249, "learning_rate": 3.860168627158749e-05, "loss": 0.44, "step": 2647 }, { "epoch": 0.14623370885796333, "grad_norm": 0.0447719506919384, "learning_rate": 3.8600371863509884e-05, "loss": 0.0015, "step": 2648 }, { "epoch": 0.14628893306825713, "grad_norm": 0.058689672499895096, "learning_rate": 3.8599056860353436e-05, "loss": 0.0019, "step": 2649 }, { "epoch": 0.1463441572785509, "grad_norm": 0.12231819331645966, "learning_rate": 3.859774126216021e-05, "loss": 0.0035, "step": 2650 }, { "epoch": 0.1463993814888447, "grad_norm": 0.48895958065986633, "learning_rate": 3.85964250689723e-05, "loss": 0.0181, "step": 2651 }, { "epoch": 0.1464546056991385, "grad_norm": 0.7011481523513794, "learning_rate": 3.8595108280831796e-05, "loss": 0.0151, "step": 2652 }, { "epoch": 0.1465098299094323, "grad_norm": 0.5622438788414001, "learning_rate": 3.8593790897780855e-05, "loss": 0.02, "step": 2653 }, { "epoch": 0.1465650541197261, "grad_norm": 2.6826047897338867, "learning_rate": 3.8592472919861596e-05, "loss": 0.3271, "step": 2654 }, { "epoch": 0.1466202783300199, "grad_norm": 2.7817437648773193, "learning_rate": 3.859115434711621e-05, "loss": 0.1731, "step": 2655 }, { "epoch": 0.14667550254031367, "grad_norm": 4.006106853485107, "learning_rate": 3.8589835179586865e-05, "loss": 0.3441, "step": 2656 }, { "epoch": 0.14673072675060747, "grad_norm": 1.319091558456421, "learning_rate": 3.858851541731577e-05, "loss": 0.0373, "step": 2657 }, { "epoch": 0.14678595096090125, "grad_norm": 2.15191912651062, "learning_rate": 3.8587195060345136e-05, "loss": 0.1057, "step": 2658 }, { "epoch": 0.14684117517119505, "grad_norm": 0.2194184511899948, "learning_rate": 3.8585874108717236e-05, "loss": 0.005, "step": 2659 }, { "epoch": 0.14689639938148885, "grad_norm": 2.1895534992218018, "learning_rate": 3.85845525624743e-05, "loss": 0.0549, "step": 2660 }, { "epoch": 0.14695162359178263, "grad_norm": 6.139169216156006, "learning_rate": 3.858323042165863e-05, "loss": 1.1842, "step": 2661 }, { "epoch": 0.14700684780207643, "grad_norm": 3.338073492050171, "learning_rate": 3.85819076863125e-05, "loss": 0.219, "step": 2662 }, { "epoch": 0.14706207201237023, "grad_norm": 3.658600091934204, "learning_rate": 3.858058435647825e-05, "loss": 0.8829, "step": 2663 }, { "epoch": 0.147117296222664, "grad_norm": 2.779327869415283, "learning_rate": 3.857926043219821e-05, "loss": 0.0664, "step": 2664 }, { "epoch": 0.1471725204329578, "grad_norm": 1.1072783470153809, "learning_rate": 3.857793591351474e-05, "loss": 0.1887, "step": 2665 }, { "epoch": 0.1472277446432516, "grad_norm": 0.18033531308174133, "learning_rate": 3.8576610800470204e-05, "loss": 0.004, "step": 2666 }, { "epoch": 0.1472829688535454, "grad_norm": 3.2496211528778076, "learning_rate": 3.8575285093107e-05, "loss": 0.1235, "step": 2667 }, { "epoch": 0.1473381930638392, "grad_norm": 1.3874573707580566, "learning_rate": 3.857395879146756e-05, "loss": 0.0178, "step": 2668 }, { "epoch": 0.147393417274133, "grad_norm": 2.9936294555664062, "learning_rate": 3.857263189559428e-05, "loss": 0.5224, "step": 2669 }, { "epoch": 0.14744864148442677, "grad_norm": 3.6132872104644775, "learning_rate": 3.8571304405529646e-05, "loss": 0.3841, "step": 2670 }, { "epoch": 0.14750386569472057, "grad_norm": 5.978461265563965, "learning_rate": 3.8569976321316114e-05, "loss": 0.926, "step": 2671 }, { "epoch": 0.14755908990501435, "grad_norm": 3.7878122329711914, "learning_rate": 3.856864764299617e-05, "loss": 0.5585, "step": 2672 }, { "epoch": 0.14761431411530815, "grad_norm": 0.4566546380519867, "learning_rate": 3.856731837061232e-05, "loss": 0.0151, "step": 2673 }, { "epoch": 0.14766953832560195, "grad_norm": 3.4240546226501465, "learning_rate": 3.856598850420711e-05, "loss": 0.1324, "step": 2674 }, { "epoch": 0.14772476253589573, "grad_norm": 0.054526738822460175, "learning_rate": 3.856465804382306e-05, "loss": 0.001, "step": 2675 }, { "epoch": 0.14777998674618953, "grad_norm": 0.6515992283821106, "learning_rate": 3.856332698950275e-05, "loss": 0.014, "step": 2676 }, { "epoch": 0.14783521095648333, "grad_norm": 5.3044657707214355, "learning_rate": 3.8561995341288766e-05, "loss": 0.1033, "step": 2677 }, { "epoch": 0.1478904351667771, "grad_norm": 2.443225622177124, "learning_rate": 3.8560663099223707e-05, "loss": 0.1722, "step": 2678 }, { "epoch": 0.1479456593770709, "grad_norm": 4.110834121704102, "learning_rate": 3.85593302633502e-05, "loss": 1.6037, "step": 2679 }, { "epoch": 0.1480008835873647, "grad_norm": 0.4336942732334137, "learning_rate": 3.8557996833710876e-05, "loss": 0.0138, "step": 2680 }, { "epoch": 0.1480561077976585, "grad_norm": 2.970550537109375, "learning_rate": 3.8556662810348397e-05, "loss": 0.9481, "step": 2681 }, { "epoch": 0.1481113320079523, "grad_norm": 0.027336427941918373, "learning_rate": 3.855532819330545e-05, "loss": 0.0008, "step": 2682 }, { "epoch": 0.1481665562182461, "grad_norm": 0.5197135210037231, "learning_rate": 3.855399298262473e-05, "loss": 0.0092, "step": 2683 }, { "epoch": 0.14822178042853987, "grad_norm": 4.350478649139404, "learning_rate": 3.855265717834895e-05, "loss": 1.0705, "step": 2684 }, { "epoch": 0.14827700463883367, "grad_norm": 1.0616364479064941, "learning_rate": 3.855132078052086e-05, "loss": 0.0269, "step": 2685 }, { "epoch": 0.14833222884912745, "grad_norm": 0.2991809546947479, "learning_rate": 3.8549983789183194e-05, "loss": 0.0115, "step": 2686 }, { "epoch": 0.14838745305942125, "grad_norm": 1.9335901737213135, "learning_rate": 3.854864620437874e-05, "loss": 0.0873, "step": 2687 }, { "epoch": 0.14844267726971505, "grad_norm": 0.04315965250134468, "learning_rate": 3.854730802615029e-05, "loss": 0.0014, "step": 2688 }, { "epoch": 0.14849790148000883, "grad_norm": 0.14002586901187897, "learning_rate": 3.854596925454065e-05, "loss": 0.003, "step": 2689 }, { "epoch": 0.14855312569030263, "grad_norm": 1.40626060962677, "learning_rate": 3.854462988959267e-05, "loss": 0.0463, "step": 2690 }, { "epoch": 0.14860834990059643, "grad_norm": 1.6970950365066528, "learning_rate": 3.854328993134917e-05, "loss": 0.2163, "step": 2691 }, { "epoch": 0.1486635741108902, "grad_norm": 4.2441911697387695, "learning_rate": 3.854194937985304e-05, "loss": 1.2162, "step": 2692 }, { "epoch": 0.148718798321184, "grad_norm": 2.4409475326538086, "learning_rate": 3.8540608235147165e-05, "loss": 0.2645, "step": 2693 }, { "epoch": 0.1487740225314778, "grad_norm": 0.35242438316345215, "learning_rate": 3.853926649727445e-05, "loss": 0.0127, "step": 2694 }, { "epoch": 0.1488292467417716, "grad_norm": 0.34988924860954285, "learning_rate": 3.8537924166277814e-05, "loss": 0.0071, "step": 2695 }, { "epoch": 0.1488844709520654, "grad_norm": 0.02178729884326458, "learning_rate": 3.8536581242200216e-05, "loss": 0.0007, "step": 2696 }, { "epoch": 0.14893969516235916, "grad_norm": 0.06142336130142212, "learning_rate": 3.853523772508461e-05, "loss": 0.0018, "step": 2697 }, { "epoch": 0.14899491937265297, "grad_norm": 0.36436283588409424, "learning_rate": 3.8533893614973975e-05, "loss": 0.0107, "step": 2698 }, { "epoch": 0.14905014358294677, "grad_norm": 1.3082066774368286, "learning_rate": 3.853254891191133e-05, "loss": 0.027, "step": 2699 }, { "epoch": 0.14910536779324055, "grad_norm": 3.232489824295044, "learning_rate": 3.853120361593968e-05, "loss": 0.5353, "step": 2700 }, { "epoch": 0.14916059200353435, "grad_norm": 0.8377676606178284, "learning_rate": 3.8529857727102075e-05, "loss": 0.0171, "step": 2701 }, { "epoch": 0.14921581621382815, "grad_norm": 0.1623038351535797, "learning_rate": 3.8528511245441565e-05, "loss": 0.005, "step": 2702 }, { "epoch": 0.14927104042412193, "grad_norm": 0.005998457781970501, "learning_rate": 3.8527164171001235e-05, "loss": 0.0002, "step": 2703 }, { "epoch": 0.14932626463441573, "grad_norm": 3.492847204208374, "learning_rate": 3.8525816503824176e-05, "loss": 0.9759, "step": 2704 }, { "epoch": 0.14938148884470953, "grad_norm": 0.8302115201950073, "learning_rate": 3.8524468243953504e-05, "loss": 0.014, "step": 2705 }, { "epoch": 0.1494367130550033, "grad_norm": 0.7715540528297424, "learning_rate": 3.852311939143236e-05, "loss": 0.0223, "step": 2706 }, { "epoch": 0.1494919372652971, "grad_norm": 0.2168501913547516, "learning_rate": 3.852176994630389e-05, "loss": 0.0041, "step": 2707 }, { "epoch": 0.1495471614755909, "grad_norm": 1.2524365186691284, "learning_rate": 3.852041990861128e-05, "loss": 0.0391, "step": 2708 }, { "epoch": 0.1496023856858847, "grad_norm": 0.035427965223789215, "learning_rate": 3.8519069278397704e-05, "loss": 0.0012, "step": 2709 }, { "epoch": 0.1496576098961785, "grad_norm": 0.1849707067012787, "learning_rate": 3.851771805570638e-05, "loss": 0.0032, "step": 2710 }, { "epoch": 0.14971283410647226, "grad_norm": 3.1571991443634033, "learning_rate": 3.8516366240580535e-05, "loss": 0.4989, "step": 2711 }, { "epoch": 0.14976805831676607, "grad_norm": 1.4626810550689697, "learning_rate": 3.8515013833063424e-05, "loss": 0.0727, "step": 2712 }, { "epoch": 0.14982328252705987, "grad_norm": 2.986124038696289, "learning_rate": 3.851366083319831e-05, "loss": 0.6505, "step": 2713 }, { "epoch": 0.14987850673735365, "grad_norm": 0.34716400504112244, "learning_rate": 3.851230724102848e-05, "loss": 0.0092, "step": 2714 }, { "epoch": 0.14993373094764745, "grad_norm": 2.629772901535034, "learning_rate": 3.8510953056597247e-05, "loss": 0.1964, "step": 2715 }, { "epoch": 0.14998895515794125, "grad_norm": 0.27314308285713196, "learning_rate": 3.8509598279947915e-05, "loss": 0.0082, "step": 2716 }, { "epoch": 0.15004417936823503, "grad_norm": 3.4319887161254883, "learning_rate": 3.8508242911123844e-05, "loss": 0.2465, "step": 2717 }, { "epoch": 0.15009940357852883, "grad_norm": 0.030651958659291267, "learning_rate": 3.8506886950168394e-05, "loss": 0.001, "step": 2718 }, { "epoch": 0.15015462778882263, "grad_norm": 0.10220352560281754, "learning_rate": 3.850553039712494e-05, "loss": 0.0038, "step": 2719 }, { "epoch": 0.1502098519991164, "grad_norm": 3.053307056427002, "learning_rate": 3.850417325203689e-05, "loss": 0.1063, "step": 2720 }, { "epoch": 0.1502650762094102, "grad_norm": 3.4570860862731934, "learning_rate": 3.850281551494766e-05, "loss": 0.0578, "step": 2721 }, { "epoch": 0.150320300419704, "grad_norm": 1.41713285446167, "learning_rate": 3.850145718590068e-05, "loss": 0.1139, "step": 2722 }, { "epoch": 0.1503755246299978, "grad_norm": 0.02796037867665291, "learning_rate": 3.850009826493942e-05, "loss": 0.0011, "step": 2723 }, { "epoch": 0.1504307488402916, "grad_norm": 0.1938277930021286, "learning_rate": 3.849873875210734e-05, "loss": 0.004, "step": 2724 }, { "epoch": 0.15048597305058536, "grad_norm": 1.8909279108047485, "learning_rate": 3.849737864744795e-05, "loss": 0.1113, "step": 2725 }, { "epoch": 0.15054119726087917, "grad_norm": 1.6873224973678589, "learning_rate": 3.8496017951004756e-05, "loss": 0.0837, "step": 2726 }, { "epoch": 0.15059642147117297, "grad_norm": 0.8910025358200073, "learning_rate": 3.8494656662821295e-05, "loss": 0.023, "step": 2727 }, { "epoch": 0.15065164568146674, "grad_norm": 0.08384183794260025, "learning_rate": 3.849329478294111e-05, "loss": 0.0026, "step": 2728 }, { "epoch": 0.15070686989176055, "grad_norm": 4.209063529968262, "learning_rate": 3.849193231140778e-05, "loss": 0.3003, "step": 2729 }, { "epoch": 0.15076209410205435, "grad_norm": 1.726230263710022, "learning_rate": 3.849056924826489e-05, "loss": 0.1216, "step": 2730 }, { "epoch": 0.15081731831234813, "grad_norm": 0.10338570177555084, "learning_rate": 3.848920559355605e-05, "loss": 0.0037, "step": 2731 }, { "epoch": 0.15087254252264193, "grad_norm": 3.586383581161499, "learning_rate": 3.848784134732489e-05, "loss": 1.0453, "step": 2732 }, { "epoch": 0.15092776673293573, "grad_norm": 2.4178824424743652, "learning_rate": 3.848647650961505e-05, "loss": 0.0248, "step": 2733 }, { "epoch": 0.1509829909432295, "grad_norm": 4.8095293045043945, "learning_rate": 3.8485111080470195e-05, "loss": 1.0908, "step": 2734 }, { "epoch": 0.1510382151535233, "grad_norm": 2.0529050827026367, "learning_rate": 3.848374505993401e-05, "loss": 0.2426, "step": 2735 }, { "epoch": 0.15109343936381708, "grad_norm": 2.8824193477630615, "learning_rate": 3.84823784480502e-05, "loss": 0.2139, "step": 2736 }, { "epoch": 0.1511486635741109, "grad_norm": 0.142131969332695, "learning_rate": 3.84810112448625e-05, "loss": 0.0021, "step": 2737 }, { "epoch": 0.1512038877844047, "grad_norm": 0.04444578289985657, "learning_rate": 3.847964345041462e-05, "loss": 0.0013, "step": 2738 }, { "epoch": 0.15125911199469846, "grad_norm": 3.352590322494507, "learning_rate": 3.847827506475035e-05, "loss": 1.0781, "step": 2739 }, { "epoch": 0.15131433620499227, "grad_norm": 0.7551371455192566, "learning_rate": 3.847690608791345e-05, "loss": 0.0251, "step": 2740 }, { "epoch": 0.15136956041528607, "grad_norm": 5.39739990234375, "learning_rate": 3.847553651994772e-05, "loss": 0.5888, "step": 2741 }, { "epoch": 0.15142478462557984, "grad_norm": 3.238009214401245, "learning_rate": 3.847416636089698e-05, "loss": 0.0368, "step": 2742 }, { "epoch": 0.15148000883587365, "grad_norm": 0.7882015705108643, "learning_rate": 3.847279561080507e-05, "loss": 0.0196, "step": 2743 }, { "epoch": 0.15153523304616745, "grad_norm": 0.14037981629371643, "learning_rate": 3.8471424269715834e-05, "loss": 0.005, "step": 2744 }, { "epoch": 0.15159045725646123, "grad_norm": 2.63702654838562, "learning_rate": 3.8470052337673145e-05, "loss": 0.7288, "step": 2745 }, { "epoch": 0.15164568146675503, "grad_norm": 3.7057383060455322, "learning_rate": 3.846867981472091e-05, "loss": 0.4528, "step": 2746 }, { "epoch": 0.15170090567704883, "grad_norm": 4.592367172241211, "learning_rate": 3.846730670090302e-05, "loss": 0.6239, "step": 2747 }, { "epoch": 0.1517561298873426, "grad_norm": 3.4703927040100098, "learning_rate": 3.846593299626342e-05, "loss": 1.2099, "step": 2748 }, { "epoch": 0.1518113540976364, "grad_norm": 3.2457010746002197, "learning_rate": 3.8464558700846054e-05, "loss": 0.6394, "step": 2749 }, { "epoch": 0.15186657830793018, "grad_norm": 0.33638206124305725, "learning_rate": 3.846318381469489e-05, "loss": 0.0064, "step": 2750 }, { "epoch": 0.151921802518224, "grad_norm": 0.08986467868089676, "learning_rate": 3.846180833785391e-05, "loss": 0.0035, "step": 2751 }, { "epoch": 0.1519770267285178, "grad_norm": 0.11624900251626968, "learning_rate": 3.8460432270367126e-05, "loss": 0.0039, "step": 2752 }, { "epoch": 0.15203225093881156, "grad_norm": 0.049205854535102844, "learning_rate": 3.8459055612278555e-05, "loss": 0.0017, "step": 2753 }, { "epoch": 0.15208747514910537, "grad_norm": 2.691898822784424, "learning_rate": 3.845767836363225e-05, "loss": 0.2654, "step": 2754 }, { "epoch": 0.15214269935939917, "grad_norm": 0.08248666673898697, "learning_rate": 3.8456300524472264e-05, "loss": 0.0027, "step": 2755 }, { "epoch": 0.15219792356969294, "grad_norm": 2.462247610092163, "learning_rate": 3.8454922094842676e-05, "loss": 0.6675, "step": 2756 }, { "epoch": 0.15225314777998675, "grad_norm": 7.265903949737549, "learning_rate": 3.845354307478759e-05, "loss": 0.5462, "step": 2757 }, { "epoch": 0.15230837199028055, "grad_norm": 0.05857459455728531, "learning_rate": 3.845216346435114e-05, "loss": 0.0021, "step": 2758 }, { "epoch": 0.15236359620057432, "grad_norm": 0.43313273787498474, "learning_rate": 3.8450783263577444e-05, "loss": 0.0149, "step": 2759 }, { "epoch": 0.15241882041086813, "grad_norm": 0.33800584077835083, "learning_rate": 3.8449402472510666e-05, "loss": 0.01, "step": 2760 }, { "epoch": 0.15247404462116193, "grad_norm": 1.5735527276992798, "learning_rate": 3.8448021091194975e-05, "loss": 0.2969, "step": 2761 }, { "epoch": 0.1525292688314557, "grad_norm": 1.3499224185943604, "learning_rate": 3.8446639119674573e-05, "loss": 0.0255, "step": 2762 }, { "epoch": 0.1525844930417495, "grad_norm": 0.03417374566197395, "learning_rate": 3.844525655799367e-05, "loss": 0.001, "step": 2763 }, { "epoch": 0.15263971725204328, "grad_norm": 0.08598405122756958, "learning_rate": 3.844387340619649e-05, "loss": 0.0022, "step": 2764 }, { "epoch": 0.15269494146233709, "grad_norm": 0.8043197393417358, "learning_rate": 3.8442489664327303e-05, "loss": 0.0241, "step": 2765 }, { "epoch": 0.1527501656726309, "grad_norm": 0.07638709992170334, "learning_rate": 3.8441105332430366e-05, "loss": 0.002, "step": 2766 }, { "epoch": 0.15280538988292466, "grad_norm": 0.7292903661727905, "learning_rate": 3.843972041054997e-05, "loss": 0.0243, "step": 2767 }, { "epoch": 0.15286061409321847, "grad_norm": 0.06581991910934448, "learning_rate": 3.843833489873042e-05, "loss": 0.0019, "step": 2768 }, { "epoch": 0.15291583830351227, "grad_norm": 0.729128360748291, "learning_rate": 3.843694879701605e-05, "loss": 0.0212, "step": 2769 }, { "epoch": 0.15297106251380604, "grad_norm": 4.737536907196045, "learning_rate": 3.8435562105451195e-05, "loss": 0.4494, "step": 2770 }, { "epoch": 0.15302628672409985, "grad_norm": 0.07936309278011322, "learning_rate": 3.8434174824080226e-05, "loss": 0.0031, "step": 2771 }, { "epoch": 0.15308151093439365, "grad_norm": 3.285884380340576, "learning_rate": 3.843278695294752e-05, "loss": 0.9189, "step": 2772 }, { "epoch": 0.15313673514468742, "grad_norm": 1.5972334146499634, "learning_rate": 3.84313984920975e-05, "loss": 0.0616, "step": 2773 }, { "epoch": 0.15319195935498123, "grad_norm": 2.8011319637298584, "learning_rate": 3.843000944157455e-05, "loss": 0.2552, "step": 2774 }, { "epoch": 0.15324718356527503, "grad_norm": 0.10426388680934906, "learning_rate": 3.842861980142314e-05, "loss": 0.0023, "step": 2775 }, { "epoch": 0.1533024077755688, "grad_norm": 0.2194894552230835, "learning_rate": 3.842722957168772e-05, "loss": 0.0023, "step": 2776 }, { "epoch": 0.1533576319858626, "grad_norm": 0.7533344030380249, "learning_rate": 3.8425838752412765e-05, "loss": 0.0443, "step": 2777 }, { "epoch": 0.15341285619615638, "grad_norm": 0.46681031584739685, "learning_rate": 3.842444734364277e-05, "loss": 0.0112, "step": 2778 }, { "epoch": 0.15346808040645019, "grad_norm": 0.3105134963989258, "learning_rate": 3.842305534542226e-05, "loss": 0.007, "step": 2779 }, { "epoch": 0.153523304616744, "grad_norm": 4.348452568054199, "learning_rate": 3.842166275779575e-05, "loss": 1.0468, "step": 2780 }, { "epoch": 0.15357852882703776, "grad_norm": 0.4571149945259094, "learning_rate": 3.842026958080781e-05, "loss": 0.0106, "step": 2781 }, { "epoch": 0.15363375303733157, "grad_norm": 2.037954092025757, "learning_rate": 3.8418875814503e-05, "loss": 0.4749, "step": 2782 }, { "epoch": 0.15368897724762537, "grad_norm": 0.2974337041378021, "learning_rate": 3.8417481458925924e-05, "loss": 0.0106, "step": 2783 }, { "epoch": 0.15374420145791914, "grad_norm": 4.290207862854004, "learning_rate": 3.8416086514121184e-05, "loss": 0.4032, "step": 2784 }, { "epoch": 0.15379942566821295, "grad_norm": 2.0084099769592285, "learning_rate": 3.84146909801334e-05, "loss": 0.1928, "step": 2785 }, { "epoch": 0.15385464987850675, "grad_norm": 3.0918169021606445, "learning_rate": 3.841329485700723e-05, "loss": 0.5438, "step": 2786 }, { "epoch": 0.15390987408880052, "grad_norm": 4.106349945068359, "learning_rate": 3.8411898144787345e-05, "loss": 0.5193, "step": 2787 }, { "epoch": 0.15396509829909433, "grad_norm": 2.897273540496826, "learning_rate": 3.841050084351841e-05, "loss": 0.3073, "step": 2788 }, { "epoch": 0.1540203225093881, "grad_norm": 4.319255828857422, "learning_rate": 3.8409102953245156e-05, "loss": 0.4312, "step": 2789 }, { "epoch": 0.1540755467196819, "grad_norm": 0.36257845163345337, "learning_rate": 3.840770447401228e-05, "loss": 0.0086, "step": 2790 }, { "epoch": 0.1541307709299757, "grad_norm": 1.4793195724487305, "learning_rate": 3.840630540586453e-05, "loss": 0.0265, "step": 2791 }, { "epoch": 0.15418599514026948, "grad_norm": 2.654392719268799, "learning_rate": 3.840490574884668e-05, "loss": 0.0316, "step": 2792 }, { "epoch": 0.15424121935056329, "grad_norm": 5.287543296813965, "learning_rate": 3.8403505503003495e-05, "loss": 1.1015, "step": 2793 }, { "epoch": 0.1542964435608571, "grad_norm": 2.934786796569824, "learning_rate": 3.8402104668379774e-05, "loss": 0.4236, "step": 2794 }, { "epoch": 0.15435166777115086, "grad_norm": 2.628977060317993, "learning_rate": 3.8400703245020334e-05, "loss": 0.3559, "step": 2795 }, { "epoch": 0.15440689198144467, "grad_norm": 0.5432642102241516, "learning_rate": 3.8399301232970015e-05, "loss": 0.0169, "step": 2796 }, { "epoch": 0.15446211619173847, "grad_norm": 2.697479724884033, "learning_rate": 3.839789863227367e-05, "loss": 0.7749, "step": 2797 }, { "epoch": 0.15451734040203224, "grad_norm": 0.20685414969921112, "learning_rate": 3.839649544297618e-05, "loss": 0.004, "step": 2798 }, { "epoch": 0.15457256461232605, "grad_norm": 1.3255677223205566, "learning_rate": 3.839509166512241e-05, "loss": 0.0619, "step": 2799 }, { "epoch": 0.15462778882261985, "grad_norm": 0.14975544810295105, "learning_rate": 3.8393687298757305e-05, "loss": 0.003, "step": 2800 }, { "epoch": 0.15468301303291362, "grad_norm": 0.08298121392726898, "learning_rate": 3.8392282343925774e-05, "loss": 0.0026, "step": 2801 }, { "epoch": 0.15473823724320743, "grad_norm": 3.9157371520996094, "learning_rate": 3.839087680067276e-05, "loss": 0.9798, "step": 2802 }, { "epoch": 0.1547934614535012, "grad_norm": 2.9806673526763916, "learning_rate": 3.838947066904325e-05, "loss": 0.25, "step": 2803 }, { "epoch": 0.154848685663795, "grad_norm": 0.18478861451148987, "learning_rate": 3.838806394908222e-05, "loss": 0.0036, "step": 2804 }, { "epoch": 0.1549039098740888, "grad_norm": 1.8080328702926636, "learning_rate": 3.838665664083468e-05, "loss": 0.1081, "step": 2805 }, { "epoch": 0.15495913408438258, "grad_norm": 2.577113628387451, "learning_rate": 3.838524874434564e-05, "loss": 0.7047, "step": 2806 }, { "epoch": 0.15501435829467639, "grad_norm": 1.5686428546905518, "learning_rate": 3.838384025966016e-05, "loss": 0.0226, "step": 2807 }, { "epoch": 0.1550695825049702, "grad_norm": 0.46156811714172363, "learning_rate": 3.838243118682329e-05, "loss": 0.008, "step": 2808 }, { "epoch": 0.15512480671526396, "grad_norm": 0.023546893149614334, "learning_rate": 3.838102152588012e-05, "loss": 0.0006, "step": 2809 }, { "epoch": 0.15518003092555777, "grad_norm": 2.3190150260925293, "learning_rate": 3.8379611276875735e-05, "loss": 0.6796, "step": 2810 }, { "epoch": 0.15523525513585157, "grad_norm": 1.3839385509490967, "learning_rate": 3.837820043985526e-05, "loss": 0.0665, "step": 2811 }, { "epoch": 0.15529047934614534, "grad_norm": 0.09761656820774078, "learning_rate": 3.837678901486384e-05, "loss": 0.0016, "step": 2812 }, { "epoch": 0.15534570355643915, "grad_norm": 0.03577953204512596, "learning_rate": 3.837537700194662e-05, "loss": 0.0009, "step": 2813 }, { "epoch": 0.15540092776673295, "grad_norm": 0.023325158283114433, "learning_rate": 3.837396440114877e-05, "loss": 0.0006, "step": 2814 }, { "epoch": 0.15545615197702672, "grad_norm": 2.3403539657592773, "learning_rate": 3.83725512125155e-05, "loss": 0.2976, "step": 2815 }, { "epoch": 0.15551137618732053, "grad_norm": 2.4453184604644775, "learning_rate": 3.8371137436092017e-05, "loss": 0.7652, "step": 2816 }, { "epoch": 0.1555666003976143, "grad_norm": 4.501852512359619, "learning_rate": 3.836972307192354e-05, "loss": 0.6858, "step": 2817 }, { "epoch": 0.1556218246079081, "grad_norm": 1.7650580406188965, "learning_rate": 3.8368308120055325e-05, "loss": 0.0896, "step": 2818 }, { "epoch": 0.1556770488182019, "grad_norm": 0.13648413121700287, "learning_rate": 3.8366892580532636e-05, "loss": 0.0021, "step": 2819 }, { "epoch": 0.15573227302849568, "grad_norm": 1.3237215280532837, "learning_rate": 3.836547645340077e-05, "loss": 0.0384, "step": 2820 }, { "epoch": 0.15578749723878949, "grad_norm": 0.1879568099975586, "learning_rate": 3.836405973870503e-05, "loss": 0.0048, "step": 2821 }, { "epoch": 0.1558427214490833, "grad_norm": 6.296457767486572, "learning_rate": 3.8362642436490734e-05, "loss": 1.8629, "step": 2822 }, { "epoch": 0.15589794565937706, "grad_norm": 1.9899420738220215, "learning_rate": 3.836122454680324e-05, "loss": 0.6499, "step": 2823 }, { "epoch": 0.15595316986967087, "grad_norm": 0.016311347484588623, "learning_rate": 3.835980606968789e-05, "loss": 0.0005, "step": 2824 }, { "epoch": 0.15600839407996467, "grad_norm": 2.4396958351135254, "learning_rate": 3.835838700519008e-05, "loss": 0.7938, "step": 2825 }, { "epoch": 0.15606361829025844, "grad_norm": 2.1170170307159424, "learning_rate": 3.8356967353355205e-05, "loss": 0.2364, "step": 2826 }, { "epoch": 0.15611884250055225, "grad_norm": 5.909397602081299, "learning_rate": 3.8355547114228686e-05, "loss": 1.2198, "step": 2827 }, { "epoch": 0.15617406671084602, "grad_norm": 2.439854860305786, "learning_rate": 3.835412628785596e-05, "loss": 0.8817, "step": 2828 }, { "epoch": 0.15622929092113982, "grad_norm": 3.7171261310577393, "learning_rate": 3.835270487428248e-05, "loss": 0.4297, "step": 2829 }, { "epoch": 0.15628451513143363, "grad_norm": 1.9316296577453613, "learning_rate": 3.835128287355372e-05, "loss": 0.2906, "step": 2830 }, { "epoch": 0.1563397393417274, "grad_norm": 0.07289710640907288, "learning_rate": 3.8349860285715185e-05, "loss": 0.0024, "step": 2831 }, { "epoch": 0.1563949635520212, "grad_norm": 0.11041015386581421, "learning_rate": 3.834843711081237e-05, "loss": 0.0036, "step": 2832 }, { "epoch": 0.156450187762315, "grad_norm": 0.08755131810903549, "learning_rate": 3.8347013348890824e-05, "loss": 0.0028, "step": 2833 }, { "epoch": 0.15650541197260878, "grad_norm": 0.04660749062895775, "learning_rate": 3.834558899999609e-05, "loss": 0.0015, "step": 2834 }, { "epoch": 0.15656063618290258, "grad_norm": 1.5326688289642334, "learning_rate": 3.834416406417373e-05, "loss": 0.0948, "step": 2835 }, { "epoch": 0.1566158603931964, "grad_norm": 0.07109581679105759, "learning_rate": 3.834273854146935e-05, "loss": 0.0026, "step": 2836 }, { "epoch": 0.15667108460349016, "grad_norm": 3.1678385734558105, "learning_rate": 3.834131243192853e-05, "loss": 0.2814, "step": 2837 }, { "epoch": 0.15672630881378397, "grad_norm": 0.0363820344209671, "learning_rate": 3.8339885735596914e-05, "loss": 0.0011, "step": 2838 }, { "epoch": 0.15678153302407777, "grad_norm": 0.4242400527000427, "learning_rate": 3.833845845252014e-05, "loss": 0.0093, "step": 2839 }, { "epoch": 0.15683675723437154, "grad_norm": 1.430067777633667, "learning_rate": 3.833703058274388e-05, "loss": 0.1289, "step": 2840 }, { "epoch": 0.15689198144466535, "grad_norm": 0.3198033571243286, "learning_rate": 3.833560212631381e-05, "loss": 0.0097, "step": 2841 }, { "epoch": 0.15694720565495912, "grad_norm": 1.8193553686141968, "learning_rate": 3.833417308327562e-05, "loss": 0.4054, "step": 2842 }, { "epoch": 0.15700242986525292, "grad_norm": 2.9691786766052246, "learning_rate": 3.833274345367504e-05, "loss": 0.2526, "step": 2843 }, { "epoch": 0.15705765407554673, "grad_norm": 3.691380262374878, "learning_rate": 3.833131323755781e-05, "loss": 0.1788, "step": 2844 }, { "epoch": 0.1571128782858405, "grad_norm": 2.2981059551239014, "learning_rate": 3.832988243496968e-05, "loss": 0.7935, "step": 2845 }, { "epoch": 0.1571681024961343, "grad_norm": 0.12182281166315079, "learning_rate": 3.8328451045956426e-05, "loss": 0.004, "step": 2846 }, { "epoch": 0.1572233267064281, "grad_norm": 0.5331194400787354, "learning_rate": 3.832701907056385e-05, "loss": 0.0142, "step": 2847 }, { "epoch": 0.15727855091672188, "grad_norm": 0.013166045770049095, "learning_rate": 3.8325586508837756e-05, "loss": 0.0004, "step": 2848 }, { "epoch": 0.15733377512701568, "grad_norm": 0.16361652314662933, "learning_rate": 3.832415336082397e-05, "loss": 0.0072, "step": 2849 }, { "epoch": 0.1573889993373095, "grad_norm": 0.7045726180076599, "learning_rate": 3.832271962656837e-05, "loss": 0.0352, "step": 2850 }, { "epoch": 0.15744422354760326, "grad_norm": 3.3315770626068115, "learning_rate": 3.832128530611679e-05, "loss": 0.5122, "step": 2851 }, { "epoch": 0.15749944775789707, "grad_norm": 1.344751000404358, "learning_rate": 3.831985039951515e-05, "loss": 0.2175, "step": 2852 }, { "epoch": 0.15755467196819087, "grad_norm": 0.7364709973335266, "learning_rate": 3.831841490680932e-05, "loss": 0.0233, "step": 2853 }, { "epoch": 0.15760989617848464, "grad_norm": 2.1742444038391113, "learning_rate": 3.8316978828045266e-05, "loss": 0.9205, "step": 2854 }, { "epoch": 0.15766512038877845, "grad_norm": 1.2344716787338257, "learning_rate": 3.8315542163268905e-05, "loss": 0.0274, "step": 2855 }, { "epoch": 0.15772034459907222, "grad_norm": 1.2697663307189941, "learning_rate": 3.831410491252621e-05, "loss": 0.0221, "step": 2856 }, { "epoch": 0.15777556880936602, "grad_norm": 4.257533550262451, "learning_rate": 3.8312667075863164e-05, "loss": 1.099, "step": 2857 }, { "epoch": 0.15783079301965983, "grad_norm": 2.970094680786133, "learning_rate": 3.8311228653325765e-05, "loss": 0.1681, "step": 2858 }, { "epoch": 0.1578860172299536, "grad_norm": 0.3097939193248749, "learning_rate": 3.8309789644960024e-05, "loss": 0.0148, "step": 2859 }, { "epoch": 0.1579412414402474, "grad_norm": 3.1723899841308594, "learning_rate": 3.8308350050811986e-05, "loss": 0.327, "step": 2860 }, { "epoch": 0.1579964656505412, "grad_norm": 3.770876884460449, "learning_rate": 3.830690987092772e-05, "loss": 0.8838, "step": 2861 }, { "epoch": 0.15805168986083498, "grad_norm": 0.9142929911613464, "learning_rate": 3.8305469105353277e-05, "loss": 0.0495, "step": 2862 }, { "epoch": 0.15810691407112878, "grad_norm": 4.166353702545166, "learning_rate": 3.830402775413477e-05, "loss": 0.5109, "step": 2863 }, { "epoch": 0.1581621382814226, "grad_norm": 0.08356271684169769, "learning_rate": 3.830258581731831e-05, "loss": 0.0033, "step": 2864 }, { "epoch": 0.15821736249171636, "grad_norm": 4.360375881195068, "learning_rate": 3.830114329495002e-05, "loss": 0.6036, "step": 2865 }, { "epoch": 0.15827258670201017, "grad_norm": 0.3608594834804535, "learning_rate": 3.829970018707605e-05, "loss": 0.0119, "step": 2866 }, { "epoch": 0.15832781091230397, "grad_norm": 2.9962074756622314, "learning_rate": 3.8298256493742585e-05, "loss": 0.1427, "step": 2867 }, { "epoch": 0.15838303512259774, "grad_norm": 0.01750052534043789, "learning_rate": 3.8296812214995795e-05, "loss": 0.0006, "step": 2868 }, { "epoch": 0.15843825933289155, "grad_norm": 4.303750038146973, "learning_rate": 3.8295367350881896e-05, "loss": 0.6043, "step": 2869 }, { "epoch": 0.15849348354318532, "grad_norm": 0.019558431580662727, "learning_rate": 3.82939219014471e-05, "loss": 0.0006, "step": 2870 }, { "epoch": 0.15854870775347912, "grad_norm": 1.029413104057312, "learning_rate": 3.8292475866737676e-05, "loss": 0.0495, "step": 2871 }, { "epoch": 0.15860393196377293, "grad_norm": 0.16817693412303925, "learning_rate": 3.829102924679987e-05, "loss": 0.0059, "step": 2872 }, { "epoch": 0.1586591561740667, "grad_norm": 0.8160267472267151, "learning_rate": 3.828958204167997e-05, "loss": 0.0283, "step": 2873 }, { "epoch": 0.1587143803843605, "grad_norm": 3.4473190307617188, "learning_rate": 3.828813425142426e-05, "loss": 0.2459, "step": 2874 }, { "epoch": 0.1587696045946543, "grad_norm": 1.173777461051941, "learning_rate": 3.828668587607908e-05, "loss": 0.1483, "step": 2875 }, { "epoch": 0.15882482880494808, "grad_norm": 1.5069327354431152, "learning_rate": 3.828523691569076e-05, "loss": 0.0666, "step": 2876 }, { "epoch": 0.15888005301524188, "grad_norm": 0.7236358523368835, "learning_rate": 3.8283787370305646e-05, "loss": 0.0187, "step": 2877 }, { "epoch": 0.1589352772255357, "grad_norm": 0.13286486268043518, "learning_rate": 3.828233723997013e-05, "loss": 0.0031, "step": 2878 }, { "epoch": 0.15899050143582946, "grad_norm": 2.028379201889038, "learning_rate": 3.82808865247306e-05, "loss": 0.519, "step": 2879 }, { "epoch": 0.15904572564612326, "grad_norm": 2.9930520057678223, "learning_rate": 3.8279435224633463e-05, "loss": 0.2675, "step": 2880 }, { "epoch": 0.15910094985641704, "grad_norm": 2.0396533012390137, "learning_rate": 3.827798333972515e-05, "loss": 0.1945, "step": 2881 }, { "epoch": 0.15915617406671084, "grad_norm": 0.04268522933125496, "learning_rate": 3.827653087005212e-05, "loss": 0.0013, "step": 2882 }, { "epoch": 0.15921139827700465, "grad_norm": 0.1593775749206543, "learning_rate": 3.827507781566083e-05, "loss": 0.0039, "step": 2883 }, { "epoch": 0.15926662248729842, "grad_norm": 1.115541696548462, "learning_rate": 3.827362417659779e-05, "loss": 0.0215, "step": 2884 }, { "epoch": 0.15932184669759222, "grad_norm": 3.4867746829986572, "learning_rate": 3.8272169952909475e-05, "loss": 1.0772, "step": 2885 }, { "epoch": 0.15937707090788603, "grad_norm": 3.188737630844116, "learning_rate": 3.827071514464243e-05, "loss": 0.4072, "step": 2886 }, { "epoch": 0.1594322951181798, "grad_norm": 0.09147543460130692, "learning_rate": 3.826925975184319e-05, "loss": 0.0038, "step": 2887 }, { "epoch": 0.1594875193284736, "grad_norm": 0.053295303136110306, "learning_rate": 3.826780377455832e-05, "loss": 0.0015, "step": 2888 }, { "epoch": 0.1595427435387674, "grad_norm": 0.2731882333755493, "learning_rate": 3.826634721283441e-05, "loss": 0.0078, "step": 2889 }, { "epoch": 0.15959796774906118, "grad_norm": 0.0696086660027504, "learning_rate": 3.826489006671804e-05, "loss": 0.0012, "step": 2890 }, { "epoch": 0.15965319195935498, "grad_norm": 0.574799656867981, "learning_rate": 3.826343233625585e-05, "loss": 0.0196, "step": 2891 }, { "epoch": 0.1597084161696488, "grad_norm": 0.007290512323379517, "learning_rate": 3.826197402149445e-05, "loss": 0.0003, "step": 2892 }, { "epoch": 0.15976364037994256, "grad_norm": 1.2623449563980103, "learning_rate": 3.826051512248052e-05, "loss": 0.012, "step": 2893 }, { "epoch": 0.15981886459023636, "grad_norm": 3.9354326725006104, "learning_rate": 3.825905563926073e-05, "loss": 1.0587, "step": 2894 }, { "epoch": 0.15987408880053014, "grad_norm": 6.638800144195557, "learning_rate": 3.8257595571881766e-05, "loss": 0.6032, "step": 2895 }, { "epoch": 0.15992931301082394, "grad_norm": 4.223890781402588, "learning_rate": 3.825613492039034e-05, "loss": 1.0051, "step": 2896 }, { "epoch": 0.15998453722111775, "grad_norm": 1.6802008152008057, "learning_rate": 3.825467368483318e-05, "loss": 0.0539, "step": 2897 }, { "epoch": 0.16003976143141152, "grad_norm": 1.6878859996795654, "learning_rate": 3.825321186525705e-05, "loss": 0.1416, "step": 2898 }, { "epoch": 0.16009498564170532, "grad_norm": 0.8160326480865479, "learning_rate": 3.825174946170871e-05, "loss": 0.0242, "step": 2899 }, { "epoch": 0.16015020985199913, "grad_norm": 2.6001718044281006, "learning_rate": 3.825028647423493e-05, "loss": 0.0763, "step": 2900 }, { "epoch": 0.1602054340622929, "grad_norm": 3.747037649154663, "learning_rate": 3.8248822902882545e-05, "loss": 1.02, "step": 2901 }, { "epoch": 0.1602606582725867, "grad_norm": 3.262899160385132, "learning_rate": 3.824735874769836e-05, "loss": 0.2987, "step": 2902 }, { "epoch": 0.1603158824828805, "grad_norm": 0.26342085003852844, "learning_rate": 3.824589400872921e-05, "loss": 0.0053, "step": 2903 }, { "epoch": 0.16037110669317428, "grad_norm": 5.04193115234375, "learning_rate": 3.824442868602198e-05, "loss": 0.3333, "step": 2904 }, { "epoch": 0.16042633090346808, "grad_norm": 0.3916192054748535, "learning_rate": 3.8242962779623527e-05, "loss": 0.0129, "step": 2905 }, { "epoch": 0.1604815551137619, "grad_norm": 2.0999362468719482, "learning_rate": 3.824149628958076e-05, "loss": 0.0795, "step": 2906 }, { "epoch": 0.16053677932405566, "grad_norm": 0.3104234039783478, "learning_rate": 3.82400292159406e-05, "loss": 0.0087, "step": 2907 }, { "epoch": 0.16059200353434946, "grad_norm": 0.6713646650314331, "learning_rate": 3.823856155874998e-05, "loss": 0.0246, "step": 2908 }, { "epoch": 0.16064722774464324, "grad_norm": 0.1307343691587448, "learning_rate": 3.823709331805585e-05, "loss": 0.0029, "step": 2909 }, { "epoch": 0.16070245195493704, "grad_norm": 2.7379987239837646, "learning_rate": 3.8235624493905185e-05, "loss": 0.1873, "step": 2910 }, { "epoch": 0.16075767616523085, "grad_norm": 2.0961804389953613, "learning_rate": 3.8234155086344984e-05, "loss": 0.1258, "step": 2911 }, { "epoch": 0.16081290037552462, "grad_norm": 5.335219860076904, "learning_rate": 3.823268509542224e-05, "loss": 1.002, "step": 2912 }, { "epoch": 0.16086812458581842, "grad_norm": 0.24069201946258545, "learning_rate": 3.8231214521184007e-05, "loss": 0.0058, "step": 2913 }, { "epoch": 0.16092334879611223, "grad_norm": 2.5309553146362305, "learning_rate": 3.8229743363677304e-05, "loss": 0.2269, "step": 2914 }, { "epoch": 0.160978573006406, "grad_norm": 2.830596685409546, "learning_rate": 3.822827162294923e-05, "loss": 0.6597, "step": 2915 }, { "epoch": 0.1610337972166998, "grad_norm": 0.7082881331443787, "learning_rate": 3.822679929904684e-05, "loss": 0.0149, "step": 2916 }, { "epoch": 0.1610890214269936, "grad_norm": 3.885296106338501, "learning_rate": 3.8225326392017256e-05, "loss": 0.8068, "step": 2917 }, { "epoch": 0.16114424563728738, "grad_norm": 2.0111494064331055, "learning_rate": 3.82238529019076e-05, "loss": 0.4028, "step": 2918 }, { "epoch": 0.16119946984758118, "grad_norm": 4.060841083526611, "learning_rate": 3.8222378828765e-05, "loss": 1.3326, "step": 2919 }, { "epoch": 0.16125469405787496, "grad_norm": 3.9258313179016113, "learning_rate": 3.822090417263663e-05, "loss": 0.4344, "step": 2920 }, { "epoch": 0.16130991826816876, "grad_norm": 1.44380784034729, "learning_rate": 3.821942893356966e-05, "loss": 0.0793, "step": 2921 }, { "epoch": 0.16136514247846256, "grad_norm": 0.8488371968269348, "learning_rate": 3.821795311161129e-05, "loss": 0.0281, "step": 2922 }, { "epoch": 0.16142036668875634, "grad_norm": 2.546351909637451, "learning_rate": 3.821647670680874e-05, "loss": 0.5814, "step": 2923 }, { "epoch": 0.16147559089905014, "grad_norm": 2.5917155742645264, "learning_rate": 3.821499971920924e-05, "loss": 0.425, "step": 2924 }, { "epoch": 0.16153081510934394, "grad_norm": 3.4975194931030273, "learning_rate": 3.821352214886003e-05, "loss": 1.0485, "step": 2925 }, { "epoch": 0.16158603931963772, "grad_norm": 4.050629138946533, "learning_rate": 3.821204399580841e-05, "loss": 0.102, "step": 2926 }, { "epoch": 0.16164126352993152, "grad_norm": 4.5678629875183105, "learning_rate": 3.8210565260101654e-05, "loss": 0.951, "step": 2927 }, { "epoch": 0.16169648774022533, "grad_norm": 0.1862793266773224, "learning_rate": 3.8209085941787066e-05, "loss": 0.0048, "step": 2928 }, { "epoch": 0.1617517119505191, "grad_norm": 0.24984517693519592, "learning_rate": 3.820760604091198e-05, "loss": 0.0056, "step": 2929 }, { "epoch": 0.1618069361608129, "grad_norm": 0.6578459739685059, "learning_rate": 3.820612555752375e-05, "loss": 0.0244, "step": 2930 }, { "epoch": 0.1618621603711067, "grad_norm": 3.4611032009124756, "learning_rate": 3.8204644491669724e-05, "loss": 0.7576, "step": 2931 }, { "epoch": 0.16191738458140048, "grad_norm": 0.07308090478181839, "learning_rate": 3.82031628433973e-05, "loss": 0.0024, "step": 2932 }, { "epoch": 0.16197260879169428, "grad_norm": 0.2087973654270172, "learning_rate": 3.820168061275387e-05, "loss": 0.0069, "step": 2933 }, { "epoch": 0.16202783300198806, "grad_norm": 4.4933881759643555, "learning_rate": 3.820019779978686e-05, "loss": 1.0489, "step": 2934 }, { "epoch": 0.16208305721228186, "grad_norm": 0.34913796186447144, "learning_rate": 3.819871440454371e-05, "loss": 0.0073, "step": 2935 }, { "epoch": 0.16213828142257566, "grad_norm": 3.9226016998291016, "learning_rate": 3.819723042707188e-05, "loss": 0.6931, "step": 2936 }, { "epoch": 0.16219350563286944, "grad_norm": 2.829193115234375, "learning_rate": 3.819574586741884e-05, "loss": 0.305, "step": 2937 }, { "epoch": 0.16224872984316324, "grad_norm": 1.4575139284133911, "learning_rate": 3.8194260725632084e-05, "loss": 0.0364, "step": 2938 }, { "epoch": 0.16230395405345704, "grad_norm": 5.664032936096191, "learning_rate": 3.819277500175914e-05, "loss": 1.0755, "step": 2939 }, { "epoch": 0.16235917826375082, "grad_norm": 0.030632860958576202, "learning_rate": 3.819128869584753e-05, "loss": 0.0009, "step": 2940 }, { "epoch": 0.16241440247404462, "grad_norm": 2.8658032417297363, "learning_rate": 3.81898018079448e-05, "loss": 0.3595, "step": 2941 }, { "epoch": 0.16246962668433843, "grad_norm": 3.577214241027832, "learning_rate": 3.818831433809853e-05, "loss": 0.3849, "step": 2942 }, { "epoch": 0.1625248508946322, "grad_norm": 1.9399362802505493, "learning_rate": 3.81868262863563e-05, "loss": 0.4802, "step": 2943 }, { "epoch": 0.162580075104926, "grad_norm": 3.241428852081299, "learning_rate": 3.818533765276573e-05, "loss": 0.1997, "step": 2944 }, { "epoch": 0.1626352993152198, "grad_norm": 3.2734501361846924, "learning_rate": 3.818384843737443e-05, "loss": 0.5082, "step": 2945 }, { "epoch": 0.16269052352551358, "grad_norm": 1.2445096969604492, "learning_rate": 3.818235864023005e-05, "loss": 0.0514, "step": 2946 }, { "epoch": 0.16274574773580738, "grad_norm": 1.0447226762771606, "learning_rate": 3.818086826138026e-05, "loss": 0.0428, "step": 2947 }, { "epoch": 0.16280097194610116, "grad_norm": 1.608523964881897, "learning_rate": 3.8179377300872736e-05, "loss": 0.0322, "step": 2948 }, { "epoch": 0.16285619615639496, "grad_norm": 4.865279674530029, "learning_rate": 3.817788575875518e-05, "loss": 1.3597, "step": 2949 }, { "epoch": 0.16291142036668876, "grad_norm": 1.0467514991760254, "learning_rate": 3.81763936350753e-05, "loss": 0.0427, "step": 2950 }, { "epoch": 0.16296664457698254, "grad_norm": 0.05918343737721443, "learning_rate": 3.8174900929880846e-05, "loss": 0.0016, "step": 2951 }, { "epoch": 0.16302186878727634, "grad_norm": 1.7126843929290771, "learning_rate": 3.817340764321956e-05, "loss": 0.2213, "step": 2952 }, { "epoch": 0.16307709299757014, "grad_norm": 1.8338463306427002, "learning_rate": 3.817191377513924e-05, "loss": 0.2172, "step": 2953 }, { "epoch": 0.16313231720786392, "grad_norm": 0.7969985604286194, "learning_rate": 3.817041932568766e-05, "loss": 0.0199, "step": 2954 }, { "epoch": 0.16318754141815772, "grad_norm": 0.23027849197387695, "learning_rate": 3.816892429491263e-05, "loss": 0.0059, "step": 2955 }, { "epoch": 0.16324276562845152, "grad_norm": 0.3520999550819397, "learning_rate": 3.8167428682862004e-05, "loss": 0.0071, "step": 2956 }, { "epoch": 0.1632979898387453, "grad_norm": 2.537501335144043, "learning_rate": 3.81659324895836e-05, "loss": 0.3749, "step": 2957 }, { "epoch": 0.1633532140490391, "grad_norm": 3.9959259033203125, "learning_rate": 3.8164435715125305e-05, "loss": 1.0866, "step": 2958 }, { "epoch": 0.16340843825933288, "grad_norm": 3.6834425926208496, "learning_rate": 3.8162938359535e-05, "loss": 1.2826, "step": 2959 }, { "epoch": 0.16346366246962668, "grad_norm": 2.9954116344451904, "learning_rate": 3.816144042286059e-05, "loss": 0.2901, "step": 2960 }, { "epoch": 0.16351888667992048, "grad_norm": 1.5448036193847656, "learning_rate": 3.815994190515e-05, "loss": 0.1208, "step": 2961 }, { "epoch": 0.16357411089021426, "grad_norm": 0.3913552463054657, "learning_rate": 3.815844280645116e-05, "loss": 0.0107, "step": 2962 }, { "epoch": 0.16362933510050806, "grad_norm": 2.1366376876831055, "learning_rate": 3.8156943126812045e-05, "loss": 0.199, "step": 2963 }, { "epoch": 0.16368455931080186, "grad_norm": 0.36137086153030396, "learning_rate": 3.815544286628063e-05, "loss": 0.0129, "step": 2964 }, { "epoch": 0.16373978352109564, "grad_norm": 3.7291464805603027, "learning_rate": 3.8153942024904905e-05, "loss": 0.223, "step": 2965 }, { "epoch": 0.16379500773138944, "grad_norm": 2.204153060913086, "learning_rate": 3.81524406027329e-05, "loss": 0.1318, "step": 2966 }, { "epoch": 0.16385023194168324, "grad_norm": 0.03665401041507721, "learning_rate": 3.815093859981264e-05, "loss": 0.0015, "step": 2967 }, { "epoch": 0.16390545615197702, "grad_norm": 4.032263278961182, "learning_rate": 3.814943601619218e-05, "loss": 0.9333, "step": 2968 }, { "epoch": 0.16396068036227082, "grad_norm": 1.2571464776992798, "learning_rate": 3.814793285191959e-05, "loss": 0.2578, "step": 2969 }, { "epoch": 0.16401590457256462, "grad_norm": 0.8012239933013916, "learning_rate": 3.814642910704297e-05, "loss": 0.0396, "step": 2970 }, { "epoch": 0.1640711287828584, "grad_norm": 3.6643621921539307, "learning_rate": 3.814492478161042e-05, "loss": 1.2978, "step": 2971 }, { "epoch": 0.1641263529931522, "grad_norm": 3.3690345287323, "learning_rate": 3.814341987567007e-05, "loss": 0.4849, "step": 2972 }, { "epoch": 0.16418157720344598, "grad_norm": 2.773129463195801, "learning_rate": 3.8141914389270064e-05, "loss": 0.3088, "step": 2973 }, { "epoch": 0.16423680141373978, "grad_norm": 1.06939697265625, "learning_rate": 3.8140408322458565e-05, "loss": 0.0905, "step": 2974 }, { "epoch": 0.16429202562403358, "grad_norm": 0.23153600096702576, "learning_rate": 3.813890167528377e-05, "loss": 0.0071, "step": 2975 }, { "epoch": 0.16434724983432736, "grad_norm": 5.210019588470459, "learning_rate": 3.813739444779387e-05, "loss": 0.762, "step": 2976 }, { "epoch": 0.16440247404462116, "grad_norm": 0.12439955025911331, "learning_rate": 3.813588664003708e-05, "loss": 0.004, "step": 2977 }, { "epoch": 0.16445769825491496, "grad_norm": 0.42986127734184265, "learning_rate": 3.813437825206165e-05, "loss": 0.0131, "step": 2978 }, { "epoch": 0.16451292246520874, "grad_norm": 4.728750705718994, "learning_rate": 3.813286928391583e-05, "loss": 0.5711, "step": 2979 }, { "epoch": 0.16456814667550254, "grad_norm": 0.9621712565422058, "learning_rate": 3.8131359735647905e-05, "loss": 0.0182, "step": 2980 }, { "epoch": 0.16462337088579634, "grad_norm": 2.897756576538086, "learning_rate": 3.812984960730616e-05, "loss": 0.7424, "step": 2981 }, { "epoch": 0.16467859509609012, "grad_norm": 2.5226216316223145, "learning_rate": 3.812833889893892e-05, "loss": 0.5682, "step": 2982 }, { "epoch": 0.16473381930638392, "grad_norm": 3.6164519786834717, "learning_rate": 3.8126827610594504e-05, "loss": 0.9671, "step": 2983 }, { "epoch": 0.16478904351667772, "grad_norm": 2.730015993118286, "learning_rate": 3.812531574232126e-05, "loss": 0.6559, "step": 2984 }, { "epoch": 0.1648442677269715, "grad_norm": 4.573452472686768, "learning_rate": 3.8123803294167574e-05, "loss": 1.0844, "step": 2985 }, { "epoch": 0.1648994919372653, "grad_norm": 0.18489906191825867, "learning_rate": 3.812229026618182e-05, "loss": 0.0057, "step": 2986 }, { "epoch": 0.16495471614755908, "grad_norm": 0.047339752316474915, "learning_rate": 3.8120776658412415e-05, "loss": 0.0015, "step": 2987 }, { "epoch": 0.16500994035785288, "grad_norm": 4.777512550354004, "learning_rate": 3.811926247090777e-05, "loss": 0.8071, "step": 2988 }, { "epoch": 0.16506516456814668, "grad_norm": 4.466504096984863, "learning_rate": 3.811774770371634e-05, "loss": 2.1961, "step": 2989 }, { "epoch": 0.16512038877844046, "grad_norm": 0.10302697867155075, "learning_rate": 3.8116232356886585e-05, "loss": 0.0033, "step": 2990 }, { "epoch": 0.16517561298873426, "grad_norm": 0.618943452835083, "learning_rate": 3.811471643046698e-05, "loss": 0.0242, "step": 2991 }, { "epoch": 0.16523083719902806, "grad_norm": 0.36567264795303345, "learning_rate": 3.811319992450602e-05, "loss": 0.0116, "step": 2992 }, { "epoch": 0.16528606140932184, "grad_norm": 3.4849720001220703, "learning_rate": 3.811168283905224e-05, "loss": 1.3472, "step": 2993 }, { "epoch": 0.16534128561961564, "grad_norm": 0.045655135065317154, "learning_rate": 3.811016517415415e-05, "loss": 0.0017, "step": 2994 }, { "epoch": 0.16539650982990944, "grad_norm": 2.6126708984375, "learning_rate": 3.810864692986033e-05, "loss": 0.3623, "step": 2995 }, { "epoch": 0.16545173404020322, "grad_norm": 2.0569722652435303, "learning_rate": 3.810712810621934e-05, "loss": 0.0582, "step": 2996 }, { "epoch": 0.16550695825049702, "grad_norm": 1.0439444780349731, "learning_rate": 3.8105608703279765e-05, "loss": 0.0251, "step": 2997 }, { "epoch": 0.16556218246079082, "grad_norm": 1.9098995923995972, "learning_rate": 3.810408872109023e-05, "loss": 0.4455, "step": 2998 }, { "epoch": 0.1656174066710846, "grad_norm": 3.6824045181274414, "learning_rate": 3.810256815969935e-05, "loss": 1.5925, "step": 2999 }, { "epoch": 0.1656726308813784, "grad_norm": 0.08011122792959213, "learning_rate": 3.8101047019155794e-05, "loss": 0.0019, "step": 3000 }, { "epoch": 0.16572785509167218, "grad_norm": 0.6601334810256958, "learning_rate": 3.809952529950819e-05, "loss": 0.0155, "step": 3001 }, { "epoch": 0.16578307930196598, "grad_norm": 0.05031552165746689, "learning_rate": 3.8098003000805266e-05, "loss": 0.0023, "step": 3002 }, { "epoch": 0.16583830351225978, "grad_norm": 4.131770610809326, "learning_rate": 3.8096480123095695e-05, "loss": 0.4283, "step": 3003 }, { "epoch": 0.16589352772255356, "grad_norm": 1.5045517683029175, "learning_rate": 3.80949566664282e-05, "loss": 0.0832, "step": 3004 }, { "epoch": 0.16594875193284736, "grad_norm": 0.4789910614490509, "learning_rate": 3.809343263085154e-05, "loss": 0.0112, "step": 3005 }, { "epoch": 0.16600397614314116, "grad_norm": 3.4966537952423096, "learning_rate": 3.809190801641445e-05, "loss": 1.1987, "step": 3006 }, { "epoch": 0.16605920035343494, "grad_norm": 2.809992551803589, "learning_rate": 3.809038282316572e-05, "loss": 0.5004, "step": 3007 }, { "epoch": 0.16611442456372874, "grad_norm": 2.2770564556121826, "learning_rate": 3.8088857051154145e-05, "loss": 0.1335, "step": 3008 }, { "epoch": 0.16616964877402254, "grad_norm": 0.18747837841510773, "learning_rate": 3.808733070042854e-05, "loss": 0.0051, "step": 3009 }, { "epoch": 0.16622487298431632, "grad_norm": 0.5510467886924744, "learning_rate": 3.808580377103773e-05, "loss": 0.0151, "step": 3010 }, { "epoch": 0.16628009719461012, "grad_norm": 0.6779239773750305, "learning_rate": 3.808427626303056e-05, "loss": 0.0286, "step": 3011 }, { "epoch": 0.1663353214049039, "grad_norm": 2.509394884109497, "learning_rate": 3.808274817645592e-05, "loss": 0.1334, "step": 3012 }, { "epoch": 0.1663905456151977, "grad_norm": 0.15469573438167572, "learning_rate": 3.808121951136268e-05, "loss": 0.0053, "step": 3013 }, { "epoch": 0.1664457698254915, "grad_norm": 2.4759459495544434, "learning_rate": 3.807969026779976e-05, "loss": 0.1683, "step": 3014 }, { "epoch": 0.16650099403578528, "grad_norm": 0.14344802498817444, "learning_rate": 3.807816044581607e-05, "loss": 0.0048, "step": 3015 }, { "epoch": 0.16655621824607908, "grad_norm": 0.12615665793418884, "learning_rate": 3.807663004546057e-05, "loss": 0.0029, "step": 3016 }, { "epoch": 0.16661144245637288, "grad_norm": 0.246821790933609, "learning_rate": 3.807509906678221e-05, "loss": 0.009, "step": 3017 }, { "epoch": 0.16666666666666666, "grad_norm": 0.12974616885185242, "learning_rate": 3.807356750982997e-05, "loss": 0.0031, "step": 3018 }, { "epoch": 0.16672189087696046, "grad_norm": 4.9427032470703125, "learning_rate": 3.807203537465285e-05, "loss": 0.7902, "step": 3019 }, { "epoch": 0.16677711508725426, "grad_norm": 0.5337782502174377, "learning_rate": 3.807050266129987e-05, "loss": 0.0212, "step": 3020 }, { "epoch": 0.16683233929754804, "grad_norm": 2.314324140548706, "learning_rate": 3.806896936982007e-05, "loss": 0.3582, "step": 3021 }, { "epoch": 0.16688756350784184, "grad_norm": 0.3134874403476715, "learning_rate": 3.80674355002625e-05, "loss": 0.0075, "step": 3022 }, { "epoch": 0.16694278771813564, "grad_norm": 3.152813673019409, "learning_rate": 3.806590105267623e-05, "loss": 0.2105, "step": 3023 }, { "epoch": 0.16699801192842942, "grad_norm": 3.6460788249969482, "learning_rate": 3.806436602711035e-05, "loss": 0.513, "step": 3024 }, { "epoch": 0.16705323613872322, "grad_norm": 3.1270248889923096, "learning_rate": 3.806283042361398e-05, "loss": 0.5639, "step": 3025 }, { "epoch": 0.167108460349017, "grad_norm": 2.1153414249420166, "learning_rate": 3.806129424223624e-05, "loss": 0.8221, "step": 3026 }, { "epoch": 0.1671636845593108, "grad_norm": 0.23663809895515442, "learning_rate": 3.8059757483026285e-05, "loss": 0.0095, "step": 3027 }, { "epoch": 0.1672189087696046, "grad_norm": 0.07147303223609924, "learning_rate": 3.8058220146033267e-05, "loss": 0.0025, "step": 3028 }, { "epoch": 0.16727413297989838, "grad_norm": 0.2938774526119232, "learning_rate": 3.805668223130638e-05, "loss": 0.0092, "step": 3029 }, { "epoch": 0.16732935719019218, "grad_norm": 1.664447546005249, "learning_rate": 3.805514373889482e-05, "loss": 0.1028, "step": 3030 }, { "epoch": 0.16738458140048598, "grad_norm": 0.16248652338981628, "learning_rate": 3.805360466884781e-05, "loss": 0.0054, "step": 3031 }, { "epoch": 0.16743980561077976, "grad_norm": 0.11272541433572769, "learning_rate": 3.8052065021214596e-05, "loss": 0.003, "step": 3032 }, { "epoch": 0.16749502982107356, "grad_norm": 3.734846830368042, "learning_rate": 3.805052479604443e-05, "loss": 0.7158, "step": 3033 }, { "epoch": 0.16755025403136736, "grad_norm": 1.584171175956726, "learning_rate": 3.804898399338658e-05, "loss": 0.2575, "step": 3034 }, { "epoch": 0.16760547824166114, "grad_norm": 3.3401107788085938, "learning_rate": 3.8047442613290356e-05, "loss": 1.481, "step": 3035 }, { "epoch": 0.16766070245195494, "grad_norm": 1.0725408792495728, "learning_rate": 3.804590065580506e-05, "loss": 0.0452, "step": 3036 }, { "epoch": 0.16771592666224874, "grad_norm": 0.061650607734918594, "learning_rate": 3.804435812098003e-05, "loss": 0.0025, "step": 3037 }, { "epoch": 0.16777115087254252, "grad_norm": 1.4533733129501343, "learning_rate": 3.804281500886462e-05, "loss": 0.1247, "step": 3038 }, { "epoch": 0.16782637508283632, "grad_norm": 0.5122219920158386, "learning_rate": 3.8041271319508185e-05, "loss": 0.0121, "step": 3039 }, { "epoch": 0.1678815992931301, "grad_norm": 0.11472732573747635, "learning_rate": 3.803972705296012e-05, "loss": 0.0032, "step": 3040 }, { "epoch": 0.1679368235034239, "grad_norm": 0.10114732384681702, "learning_rate": 3.803818220926983e-05, "loss": 0.0036, "step": 3041 }, { "epoch": 0.1679920477137177, "grad_norm": 0.38056710362434387, "learning_rate": 3.803663678848674e-05, "loss": 0.0041, "step": 3042 }, { "epoch": 0.16804727192401148, "grad_norm": 2.174997091293335, "learning_rate": 3.8035090790660286e-05, "loss": 0.4127, "step": 3043 }, { "epoch": 0.16810249613430528, "grad_norm": 1.370209813117981, "learning_rate": 3.803354421583994e-05, "loss": 0.0624, "step": 3044 }, { "epoch": 0.16815772034459908, "grad_norm": 1.7286585569381714, "learning_rate": 3.803199706407517e-05, "loss": 0.3985, "step": 3045 }, { "epoch": 0.16821294455489286, "grad_norm": 0.6612453460693359, "learning_rate": 3.803044933541548e-05, "loss": 0.0143, "step": 3046 }, { "epoch": 0.16826816876518666, "grad_norm": 4.337963581085205, "learning_rate": 3.8028901029910394e-05, "loss": 0.7389, "step": 3047 }, { "epoch": 0.16832339297548046, "grad_norm": 0.8164913654327393, "learning_rate": 3.8027352147609426e-05, "loss": 0.0206, "step": 3048 }, { "epoch": 0.16837861718577424, "grad_norm": 3.983471632003784, "learning_rate": 3.802580268856215e-05, "loss": 0.4456, "step": 3049 }, { "epoch": 0.16843384139606804, "grad_norm": 0.3443731963634491, "learning_rate": 3.802425265281813e-05, "loss": 0.0076, "step": 3050 }, { "epoch": 0.16848906560636182, "grad_norm": 2.5143556594848633, "learning_rate": 3.802270204042695e-05, "loss": 0.202, "step": 3051 }, { "epoch": 0.16854428981665562, "grad_norm": 2.930736541748047, "learning_rate": 3.802115085143822e-05, "loss": 1.1247, "step": 3052 }, { "epoch": 0.16859951402694942, "grad_norm": 0.0521966814994812, "learning_rate": 3.801959908590158e-05, "loss": 0.0021, "step": 3053 }, { "epoch": 0.1686547382372432, "grad_norm": 2.4514060020446777, "learning_rate": 3.801804674386666e-05, "loss": 0.1472, "step": 3054 }, { "epoch": 0.168709962447537, "grad_norm": 0.04772314056754112, "learning_rate": 3.801649382538313e-05, "loss": 0.002, "step": 3055 }, { "epoch": 0.1687651866578308, "grad_norm": 2.6523237228393555, "learning_rate": 3.801494033050067e-05, "loss": 0.2386, "step": 3056 }, { "epoch": 0.16882041086812458, "grad_norm": 1.328858733177185, "learning_rate": 3.8013386259268985e-05, "loss": 0.0324, "step": 3057 }, { "epoch": 0.16887563507841838, "grad_norm": 4.671551704406738, "learning_rate": 3.8011831611737785e-05, "loss": 0.6645, "step": 3058 }, { "epoch": 0.16893085928871218, "grad_norm": 0.8715988993644714, "learning_rate": 3.801027638795682e-05, "loss": 0.0258, "step": 3059 }, { "epoch": 0.16898608349900596, "grad_norm": 5.663049697875977, "learning_rate": 3.800872058797584e-05, "loss": 0.5568, "step": 3060 }, { "epoch": 0.16904130770929976, "grad_norm": 0.6887264251708984, "learning_rate": 3.800716421184462e-05, "loss": 0.0285, "step": 3061 }, { "epoch": 0.16909653191959356, "grad_norm": 0.17475593090057373, "learning_rate": 3.8005607259612956e-05, "loss": 0.0031, "step": 3062 }, { "epoch": 0.16915175612988734, "grad_norm": 0.7095703482627869, "learning_rate": 3.800404973133066e-05, "loss": 0.0125, "step": 3063 }, { "epoch": 0.16920698034018114, "grad_norm": 4.243083477020264, "learning_rate": 3.800249162704754e-05, "loss": 0.6925, "step": 3064 }, { "epoch": 0.16926220455047492, "grad_norm": 0.040149908512830734, "learning_rate": 3.8000932946813474e-05, "loss": 0.0013, "step": 3065 }, { "epoch": 0.16931742876076872, "grad_norm": 0.9442363977432251, "learning_rate": 3.799937369067832e-05, "loss": 0.0166, "step": 3066 }, { "epoch": 0.16937265297106252, "grad_norm": 0.02008737437427044, "learning_rate": 3.7997813858691956e-05, "loss": 0.0008, "step": 3067 }, { "epoch": 0.1694278771813563, "grad_norm": 4.046328544616699, "learning_rate": 3.799625345090429e-05, "loss": 1.2908, "step": 3068 }, { "epoch": 0.1694831013916501, "grad_norm": 1.8615344762802124, "learning_rate": 3.7994692467365244e-05, "loss": 0.1453, "step": 3069 }, { "epoch": 0.1695383256019439, "grad_norm": 1.789185643196106, "learning_rate": 3.799313090812475e-05, "loss": 0.1887, "step": 3070 }, { "epoch": 0.16959354981223768, "grad_norm": 1.3930623531341553, "learning_rate": 3.799156877323278e-05, "loss": 0.4036, "step": 3071 }, { "epoch": 0.16964877402253148, "grad_norm": 0.047806013375520706, "learning_rate": 3.799000606273931e-05, "loss": 0.0019, "step": 3072 }, { "epoch": 0.16970399823282528, "grad_norm": 2.2188661098480225, "learning_rate": 3.7988442776694313e-05, "loss": 0.7718, "step": 3073 }, { "epoch": 0.16975922244311906, "grad_norm": 0.678575873374939, "learning_rate": 3.798687891514784e-05, "loss": 0.0212, "step": 3074 }, { "epoch": 0.16981444665341286, "grad_norm": 0.044333141297101974, "learning_rate": 3.79853144781499e-05, "loss": 0.0013, "step": 3075 }, { "epoch": 0.16986967086370666, "grad_norm": 0.7786058783531189, "learning_rate": 3.798374946575054e-05, "loss": 0.0191, "step": 3076 }, { "epoch": 0.16992489507400044, "grad_norm": 6.644892692565918, "learning_rate": 3.798218387799984e-05, "loss": 0.8529, "step": 3077 }, { "epoch": 0.16998011928429424, "grad_norm": 3.056668996810913, "learning_rate": 3.798061771494789e-05, "loss": 0.2538, "step": 3078 }, { "epoch": 0.17003534349458801, "grad_norm": 0.7600423693656921, "learning_rate": 3.7979050976644784e-05, "loss": 0.0356, "step": 3079 }, { "epoch": 0.17009056770488182, "grad_norm": 2.880659818649292, "learning_rate": 3.797748366314066e-05, "loss": 0.1344, "step": 3080 }, { "epoch": 0.17014579191517562, "grad_norm": 0.09384139627218246, "learning_rate": 3.7975915774485644e-05, "loss": 0.0026, "step": 3081 }, { "epoch": 0.1702010161254694, "grad_norm": 4.0169453620910645, "learning_rate": 3.797434731072992e-05, "loss": 0.9219, "step": 3082 }, { "epoch": 0.1702562403357632, "grad_norm": 0.1273472011089325, "learning_rate": 3.797277827192365e-05, "loss": 0.0034, "step": 3083 }, { "epoch": 0.170311464546057, "grad_norm": 0.03760476037859917, "learning_rate": 3.797120865811703e-05, "loss": 0.0014, "step": 3084 }, { "epoch": 0.17036668875635078, "grad_norm": 1.3038779497146606, "learning_rate": 3.796963846936029e-05, "loss": 0.0668, "step": 3085 }, { "epoch": 0.17042191296664458, "grad_norm": 3.041065216064453, "learning_rate": 3.796806770570366e-05, "loss": 0.4914, "step": 3086 }, { "epoch": 0.17047713717693838, "grad_norm": 3.1471424102783203, "learning_rate": 3.796649636719739e-05, "loss": 0.3513, "step": 3087 }, { "epoch": 0.17053236138723216, "grad_norm": 2.1943917274475098, "learning_rate": 3.7964924453891745e-05, "loss": 0.4232, "step": 3088 }, { "epoch": 0.17058758559752596, "grad_norm": 2.3841161727905273, "learning_rate": 3.796335196583703e-05, "loss": 0.4154, "step": 3089 }, { "epoch": 0.17064280980781976, "grad_norm": 1.737858533859253, "learning_rate": 3.796177890308354e-05, "loss": 0.0854, "step": 3090 }, { "epoch": 0.17069803401811354, "grad_norm": 1.583889126777649, "learning_rate": 3.796020526568162e-05, "loss": 0.0954, "step": 3091 }, { "epoch": 0.17075325822840734, "grad_norm": 2.3161702156066895, "learning_rate": 3.79586310536816e-05, "loss": 0.1639, "step": 3092 }, { "epoch": 0.17080848243870111, "grad_norm": 1.1057896614074707, "learning_rate": 3.795705626713384e-05, "loss": 0.1197, "step": 3093 }, { "epoch": 0.17086370664899492, "grad_norm": 0.49025729298591614, "learning_rate": 3.7955480906088726e-05, "loss": 0.0063, "step": 3094 }, { "epoch": 0.17091893085928872, "grad_norm": 2.3931939601898193, "learning_rate": 3.795390497059667e-05, "loss": 0.2029, "step": 3095 }, { "epoch": 0.1709741550695825, "grad_norm": 2.523202657699585, "learning_rate": 3.795232846070808e-05, "loss": 0.5258, "step": 3096 }, { "epoch": 0.1710293792798763, "grad_norm": 2.159165143966675, "learning_rate": 3.795075137647339e-05, "loss": 0.5787, "step": 3097 }, { "epoch": 0.1710846034901701, "grad_norm": 0.9183998703956604, "learning_rate": 3.794917371794306e-05, "loss": 0.0387, "step": 3098 }, { "epoch": 0.17113982770046388, "grad_norm": 2.209153652191162, "learning_rate": 3.7947595485167565e-05, "loss": 0.0799, "step": 3099 }, { "epoch": 0.17119505191075768, "grad_norm": 0.031664472073316574, "learning_rate": 3.7946016678197396e-05, "loss": 0.0013, "step": 3100 }, { "epoch": 0.17125027612105148, "grad_norm": 1.3718960285186768, "learning_rate": 3.794443729708307e-05, "loss": 0.1845, "step": 3101 }, { "epoch": 0.17130550033134526, "grad_norm": 2.5215940475463867, "learning_rate": 3.7942857341875096e-05, "loss": 0.444, "step": 3102 }, { "epoch": 0.17136072454163906, "grad_norm": 0.8347992897033691, "learning_rate": 3.7941276812624046e-05, "loss": 0.03, "step": 3103 }, { "epoch": 0.17141594875193283, "grad_norm": 2.1942262649536133, "learning_rate": 3.793969570938047e-05, "loss": 0.053, "step": 3104 }, { "epoch": 0.17147117296222664, "grad_norm": 2.379831075668335, "learning_rate": 3.793811403219495e-05, "loss": 0.2928, "step": 3105 }, { "epoch": 0.17152639717252044, "grad_norm": 0.06295669823884964, "learning_rate": 3.793653178111811e-05, "loss": 0.0017, "step": 3106 }, { "epoch": 0.17158162138281421, "grad_norm": 2.0947139263153076, "learning_rate": 3.7934948956200545e-05, "loss": 0.5661, "step": 3107 }, { "epoch": 0.17163684559310802, "grad_norm": 0.11295844614505768, "learning_rate": 3.7933365557492904e-05, "loss": 0.0031, "step": 3108 }, { "epoch": 0.17169206980340182, "grad_norm": 0.2066117823123932, "learning_rate": 3.793178158504584e-05, "loss": 0.0073, "step": 3109 }, { "epoch": 0.1717472940136956, "grad_norm": 2.7115769386291504, "learning_rate": 3.793019703891005e-05, "loss": 0.4528, "step": 3110 }, { "epoch": 0.1718025182239894, "grad_norm": 0.07728248089551926, "learning_rate": 3.79286119191362e-05, "loss": 0.002, "step": 3111 }, { "epoch": 0.1718577424342832, "grad_norm": 4.117190361022949, "learning_rate": 3.7927026225775015e-05, "loss": 0.6697, "step": 3112 }, { "epoch": 0.17191296664457698, "grad_norm": 3.666018009185791, "learning_rate": 3.792543995887722e-05, "loss": 0.233, "step": 3113 }, { "epoch": 0.17196819085487078, "grad_norm": 1.0883009433746338, "learning_rate": 3.7923853118493576e-05, "loss": 0.019, "step": 3114 }, { "epoch": 0.17202341506516458, "grad_norm": 0.2885138690471649, "learning_rate": 3.792226570467484e-05, "loss": 0.007, "step": 3115 }, { "epoch": 0.17207863927545836, "grad_norm": 0.03932248428463936, "learning_rate": 3.792067771747181e-05, "loss": 0.0014, "step": 3116 }, { "epoch": 0.17213386348575216, "grad_norm": 1.735484004020691, "learning_rate": 3.791908915693528e-05, "loss": 0.2188, "step": 3117 }, { "epoch": 0.17218908769604593, "grad_norm": 2.2584004402160645, "learning_rate": 3.791750002311607e-05, "loss": 0.3275, "step": 3118 }, { "epoch": 0.17224431190633974, "grad_norm": 3.8110365867614746, "learning_rate": 3.7915910316065026e-05, "loss": 0.325, "step": 3119 }, { "epoch": 0.17229953611663354, "grad_norm": 0.05945170298218727, "learning_rate": 3.7914320035833e-05, "loss": 0.002, "step": 3120 }, { "epoch": 0.17235476032692731, "grad_norm": 0.24272824823856354, "learning_rate": 3.791272918247089e-05, "loss": 0.0027, "step": 3121 }, { "epoch": 0.17240998453722112, "grad_norm": 0.2264515906572342, "learning_rate": 3.7911137756029575e-05, "loss": 0.006, "step": 3122 }, { "epoch": 0.17246520874751492, "grad_norm": 0.09188386052846909, "learning_rate": 3.7909545756559966e-05, "loss": 0.003, "step": 3123 }, { "epoch": 0.1725204329578087, "grad_norm": 4.897784233093262, "learning_rate": 3.790795318411301e-05, "loss": 0.791, "step": 3124 }, { "epoch": 0.1725756571681025, "grad_norm": 2.6568455696105957, "learning_rate": 3.790636003873964e-05, "loss": 0.3954, "step": 3125 }, { "epoch": 0.1726308813783963, "grad_norm": 0.442062646150589, "learning_rate": 3.790476632049084e-05, "loss": 0.0161, "step": 3126 }, { "epoch": 0.17268610558869008, "grad_norm": 2.45265793800354, "learning_rate": 3.790317202941759e-05, "loss": 0.2127, "step": 3127 }, { "epoch": 0.17274132979898388, "grad_norm": 2.7874250411987305, "learning_rate": 3.79015771655709e-05, "loss": 0.2631, "step": 3128 }, { "epoch": 0.17279655400927768, "grad_norm": 1.1809669733047485, "learning_rate": 3.78999817290018e-05, "loss": 0.0406, "step": 3129 }, { "epoch": 0.17285177821957146, "grad_norm": 0.019683456048369408, "learning_rate": 3.789838571976132e-05, "loss": 0.0006, "step": 3130 }, { "epoch": 0.17290700242986526, "grad_norm": 0.17480234801769257, "learning_rate": 3.7896789137900524e-05, "loss": 0.0053, "step": 3131 }, { "epoch": 0.17296222664015903, "grad_norm": 0.9774436354637146, "learning_rate": 3.78951919834705e-05, "loss": 0.0242, "step": 3132 }, { "epoch": 0.17301745085045284, "grad_norm": 3.794278144836426, "learning_rate": 3.789359425652233e-05, "loss": 0.6006, "step": 3133 }, { "epoch": 0.17307267506074664, "grad_norm": 2.4433460235595703, "learning_rate": 3.789199595710715e-05, "loss": 0.4911, "step": 3134 }, { "epoch": 0.17312789927104041, "grad_norm": 2.522378921508789, "learning_rate": 3.7890397085276076e-05, "loss": 0.4187, "step": 3135 }, { "epoch": 0.17318312348133422, "grad_norm": 0.45998597145080566, "learning_rate": 3.788879764108027e-05, "loss": 0.0191, "step": 3136 }, { "epoch": 0.17323834769162802, "grad_norm": 3.602634906768799, "learning_rate": 3.7887197624570895e-05, "loss": 0.3502, "step": 3137 }, { "epoch": 0.1732935719019218, "grad_norm": 0.07318385690450668, "learning_rate": 3.788559703579915e-05, "loss": 0.004, "step": 3138 }, { "epoch": 0.1733487961122156, "grad_norm": 4.684863567352295, "learning_rate": 3.7883995874816236e-05, "loss": 0.4825, "step": 3139 }, { "epoch": 0.1734040203225094, "grad_norm": 0.538313090801239, "learning_rate": 3.788239414167338e-05, "loss": 0.0134, "step": 3140 }, { "epoch": 0.17345924453280318, "grad_norm": 2.136888265609741, "learning_rate": 3.7880791836421834e-05, "loss": 0.1134, "step": 3141 }, { "epoch": 0.17351446874309698, "grad_norm": 3.493922233581543, "learning_rate": 3.7879188959112844e-05, "loss": 0.2276, "step": 3142 }, { "epoch": 0.17356969295339075, "grad_norm": 0.6277145743370056, "learning_rate": 3.7877585509797706e-05, "loss": 0.0273, "step": 3143 }, { "epoch": 0.17362491716368456, "grad_norm": 0.7649189829826355, "learning_rate": 3.7875981488527705e-05, "loss": 0.0276, "step": 3144 }, { "epoch": 0.17368014137397836, "grad_norm": 2.4484989643096924, "learning_rate": 3.787437689535417e-05, "loss": 0.378, "step": 3145 }, { "epoch": 0.17373536558427213, "grad_norm": 0.2138228714466095, "learning_rate": 3.787277173032843e-05, "loss": 0.0075, "step": 3146 }, { "epoch": 0.17379058979456594, "grad_norm": 0.02576463297009468, "learning_rate": 3.787116599350184e-05, "loss": 0.0009, "step": 3147 }, { "epoch": 0.17384581400485974, "grad_norm": 4.948095798492432, "learning_rate": 3.786955968492578e-05, "loss": 1.5765, "step": 3148 }, { "epoch": 0.17390103821515351, "grad_norm": 3.05295467376709, "learning_rate": 3.786795280465163e-05, "loss": 0.3644, "step": 3149 }, { "epoch": 0.17395626242544732, "grad_norm": 1.3271037340164185, "learning_rate": 3.78663453527308e-05, "loss": 0.0606, "step": 3150 }, { "epoch": 0.17401148663574112, "grad_norm": 6.474555015563965, "learning_rate": 3.7864737329214715e-05, "loss": 1.0097, "step": 3151 }, { "epoch": 0.1740667108460349, "grad_norm": 0.932054340839386, "learning_rate": 3.786312873415483e-05, "loss": 0.0627, "step": 3152 }, { "epoch": 0.1741219350563287, "grad_norm": 2.272632360458374, "learning_rate": 3.78615195676026e-05, "loss": 0.1833, "step": 3153 }, { "epoch": 0.1741771592666225, "grad_norm": 5.268199443817139, "learning_rate": 3.785990982960951e-05, "loss": 1.8443, "step": 3154 }, { "epoch": 0.17423238347691627, "grad_norm": 1.266868233680725, "learning_rate": 3.7858299520227064e-05, "loss": 0.0208, "step": 3155 }, { "epoch": 0.17428760768721008, "grad_norm": 0.02797415480017662, "learning_rate": 3.785668863950677e-05, "loss": 0.001, "step": 3156 }, { "epoch": 0.17434283189750385, "grad_norm": 3.5132012367248535, "learning_rate": 3.7855077187500175e-05, "loss": 0.8494, "step": 3157 }, { "epoch": 0.17439805610779766, "grad_norm": 3.544187307357788, "learning_rate": 3.785346516425882e-05, "loss": 0.3208, "step": 3158 }, { "epoch": 0.17445328031809146, "grad_norm": 2.7010879516601562, "learning_rate": 3.7851852569834305e-05, "loss": 0.2735, "step": 3159 }, { "epoch": 0.17450850452838523, "grad_norm": 0.41031259298324585, "learning_rate": 3.785023940427819e-05, "loss": 0.0205, "step": 3160 }, { "epoch": 0.17456372873867904, "grad_norm": 1.080229640007019, "learning_rate": 3.7848625667642107e-05, "loss": 0.0487, "step": 3161 }, { "epoch": 0.17461895294897284, "grad_norm": 0.2233811914920807, "learning_rate": 3.7847011359977675e-05, "loss": 0.0054, "step": 3162 }, { "epoch": 0.1746741771592666, "grad_norm": 1.6313601732254028, "learning_rate": 3.784539648133653e-05, "loss": 0.0725, "step": 3163 }, { "epoch": 0.17472940136956042, "grad_norm": 0.8857250213623047, "learning_rate": 3.784378103177036e-05, "loss": 0.0296, "step": 3164 }, { "epoch": 0.17478462557985422, "grad_norm": 3.61372447013855, "learning_rate": 3.7842165011330833e-05, "loss": 0.388, "step": 3165 }, { "epoch": 0.174839849790148, "grad_norm": 1.9300824403762817, "learning_rate": 3.784054842006966e-05, "loss": 0.4272, "step": 3166 }, { "epoch": 0.1748950740004418, "grad_norm": 0.36502811312675476, "learning_rate": 3.7838931258038544e-05, "loss": 0.0108, "step": 3167 }, { "epoch": 0.1749502982107356, "grad_norm": 2.1491894721984863, "learning_rate": 3.783731352528923e-05, "loss": 0.278, "step": 3168 }, { "epoch": 0.17500552242102937, "grad_norm": 0.259831964969635, "learning_rate": 3.7835695221873485e-05, "loss": 0.0079, "step": 3169 }, { "epoch": 0.17506074663132318, "grad_norm": 0.7480794787406921, "learning_rate": 3.783407634784307e-05, "loss": 0.0145, "step": 3170 }, { "epoch": 0.17511597084161695, "grad_norm": 2.6395530700683594, "learning_rate": 3.783245690324978e-05, "loss": 0.3176, "step": 3171 }, { "epoch": 0.17517119505191076, "grad_norm": 0.8996037244796753, "learning_rate": 3.783083688814543e-05, "loss": 0.013, "step": 3172 }, { "epoch": 0.17522641926220456, "grad_norm": 1.7327288389205933, "learning_rate": 3.7829216302581837e-05, "loss": 0.2373, "step": 3173 }, { "epoch": 0.17528164347249833, "grad_norm": 0.00970807671546936, "learning_rate": 3.782759514661086e-05, "loss": 0.0005, "step": 3174 }, { "epoch": 0.17533686768279214, "grad_norm": 0.5690028667449951, "learning_rate": 3.782597342028437e-05, "loss": 0.0193, "step": 3175 }, { "epoch": 0.17539209189308594, "grad_norm": 4.966973304748535, "learning_rate": 3.7824351123654236e-05, "loss": 0.2925, "step": 3176 }, { "epoch": 0.1754473161033797, "grad_norm": 3.6076056957244873, "learning_rate": 3.782272825677236e-05, "loss": 0.6488, "step": 3177 }, { "epoch": 0.17550254031367352, "grad_norm": 2.0838265419006348, "learning_rate": 3.782110481969068e-05, "loss": 0.1516, "step": 3178 }, { "epoch": 0.17555776452396732, "grad_norm": 0.37439271807670593, "learning_rate": 3.781948081246111e-05, "loss": 0.0106, "step": 3179 }, { "epoch": 0.1756129887342611, "grad_norm": 2.867537021636963, "learning_rate": 3.781785623513563e-05, "loss": 0.5575, "step": 3180 }, { "epoch": 0.1756682129445549, "grad_norm": 0.056468378752470016, "learning_rate": 3.78162310877662e-05, "loss": 0.0017, "step": 3181 }, { "epoch": 0.1757234371548487, "grad_norm": 4.018270492553711, "learning_rate": 3.781460537040482e-05, "loss": 0.6826, "step": 3182 }, { "epoch": 0.17577866136514247, "grad_norm": 0.1926974505186081, "learning_rate": 3.781297908310349e-05, "loss": 0.0042, "step": 3183 }, { "epoch": 0.17583388557543628, "grad_norm": 1.1954342126846313, "learning_rate": 3.7811352225914255e-05, "loss": 0.0331, "step": 3184 }, { "epoch": 0.17588910978573005, "grad_norm": 1.1371389627456665, "learning_rate": 3.780972479888915e-05, "loss": 0.1623, "step": 3185 }, { "epoch": 0.17594433399602386, "grad_norm": 2.363783359527588, "learning_rate": 3.780809680208025e-05, "loss": 0.5731, "step": 3186 }, { "epoch": 0.17599955820631766, "grad_norm": 0.2028711438179016, "learning_rate": 3.780646823553963e-05, "loss": 0.0056, "step": 3187 }, { "epoch": 0.17605478241661143, "grad_norm": 2.2027361392974854, "learning_rate": 3.780483909931941e-05, "loss": 0.2794, "step": 3188 }, { "epoch": 0.17611000662690524, "grad_norm": 1.6545778512954712, "learning_rate": 3.780320939347169e-05, "loss": 0.063, "step": 3189 }, { "epoch": 0.17616523083719904, "grad_norm": 0.06842547655105591, "learning_rate": 3.780157911804862e-05, "loss": 0.0028, "step": 3190 }, { "epoch": 0.1762204550474928, "grad_norm": 0.03891279920935631, "learning_rate": 3.7799948273102364e-05, "loss": 0.0015, "step": 3191 }, { "epoch": 0.17627567925778662, "grad_norm": 0.009626578539609909, "learning_rate": 3.7798316858685075e-05, "loss": 0.0004, "step": 3192 }, { "epoch": 0.17633090346808042, "grad_norm": 0.043807175010442734, "learning_rate": 3.779668487484896e-05, "loss": 0.0009, "step": 3193 }, { "epoch": 0.1763861276783742, "grad_norm": 3.453885316848755, "learning_rate": 3.779505232164624e-05, "loss": 1.0523, "step": 3194 }, { "epoch": 0.176441351888668, "grad_norm": 1.4707953929901123, "learning_rate": 3.779341919912914e-05, "loss": 0.2546, "step": 3195 }, { "epoch": 0.17649657609896177, "grad_norm": 0.2361091822385788, "learning_rate": 3.779178550734989e-05, "loss": 0.0081, "step": 3196 }, { "epoch": 0.17655180030925557, "grad_norm": 1.5067037343978882, "learning_rate": 3.779015124636078e-05, "loss": 0.0437, "step": 3197 }, { "epoch": 0.17660702451954938, "grad_norm": 0.3426976203918457, "learning_rate": 3.7788516416214084e-05, "loss": 0.0038, "step": 3198 }, { "epoch": 0.17666224872984315, "grad_norm": 3.4477970600128174, "learning_rate": 3.778688101696211e-05, "loss": 0.2812, "step": 3199 }, { "epoch": 0.17671747294013695, "grad_norm": 0.11003236472606659, "learning_rate": 3.7785245048657166e-05, "loss": 0.0033, "step": 3200 }, { "epoch": 0.17677269715043076, "grad_norm": 2.8675615787506104, "learning_rate": 3.77836085113516e-05, "loss": 0.4182, "step": 3201 }, { "epoch": 0.17682792136072453, "grad_norm": 0.20598727464675903, "learning_rate": 3.778197140509778e-05, "loss": 0.0067, "step": 3202 }, { "epoch": 0.17688314557101834, "grad_norm": 0.009149239398539066, "learning_rate": 3.778033372994807e-05, "loss": 0.0004, "step": 3203 }, { "epoch": 0.17693836978131214, "grad_norm": 0.5850933790206909, "learning_rate": 3.7778695485954854e-05, "loss": 0.0102, "step": 3204 }, { "epoch": 0.1769935939916059, "grad_norm": 0.1478039026260376, "learning_rate": 3.7777056673170566e-05, "loss": 0.0055, "step": 3205 }, { "epoch": 0.17704881820189972, "grad_norm": 6.190684795379639, "learning_rate": 3.7775417291647624e-05, "loss": 1.2149, "step": 3206 }, { "epoch": 0.17710404241219352, "grad_norm": 3.4744224548339844, "learning_rate": 3.777377734143848e-05, "loss": 0.7536, "step": 3207 }, { "epoch": 0.1771592666224873, "grad_norm": 2.414278268814087, "learning_rate": 3.77721368225956e-05, "loss": 0.0781, "step": 3208 }, { "epoch": 0.1772144908327811, "grad_norm": 0.05602720379829407, "learning_rate": 3.777049573517146e-05, "loss": 0.0017, "step": 3209 }, { "epoch": 0.17726971504307487, "grad_norm": 0.07116395980119705, "learning_rate": 3.776885407921858e-05, "loss": 0.0022, "step": 3210 }, { "epoch": 0.17732493925336867, "grad_norm": 3.716121196746826, "learning_rate": 3.776721185478946e-05, "loss": 0.9656, "step": 3211 }, { "epoch": 0.17738016346366248, "grad_norm": 0.05052698776125908, "learning_rate": 3.776556906193667e-05, "loss": 0.0014, "step": 3212 }, { "epoch": 0.17743538767395625, "grad_norm": 5.094519138336182, "learning_rate": 3.7763925700712737e-05, "loss": 0.4483, "step": 3213 }, { "epoch": 0.17749061188425005, "grad_norm": 4.070674419403076, "learning_rate": 3.776228177117025e-05, "loss": 0.4002, "step": 3214 }, { "epoch": 0.17754583609454386, "grad_norm": 5.835549354553223, "learning_rate": 3.7760637273361805e-05, "loss": 0.7785, "step": 3215 }, { "epoch": 0.17760106030483763, "grad_norm": 3.1266489028930664, "learning_rate": 3.775899220734001e-05, "loss": 0.8263, "step": 3216 }, { "epoch": 0.17765628451513144, "grad_norm": 1.8335851430892944, "learning_rate": 3.77573465731575e-05, "loss": 0.179, "step": 3217 }, { "epoch": 0.17771150872542524, "grad_norm": 0.036649368703365326, "learning_rate": 3.775570037086692e-05, "loss": 0.0015, "step": 3218 }, { "epoch": 0.177766732935719, "grad_norm": 2.4543511867523193, "learning_rate": 3.775405360052093e-05, "loss": 0.5935, "step": 3219 }, { "epoch": 0.17782195714601282, "grad_norm": 1.8895214796066284, "learning_rate": 3.775240626217223e-05, "loss": 0.0274, "step": 3220 }, { "epoch": 0.17787718135630662, "grad_norm": 1.4919275045394897, "learning_rate": 3.775075835587351e-05, "loss": 0.0445, "step": 3221 }, { "epoch": 0.1779324055666004, "grad_norm": 0.12269487231969833, "learning_rate": 3.77491098816775e-05, "loss": 0.0046, "step": 3222 }, { "epoch": 0.1779876297768942, "grad_norm": 2.122971773147583, "learning_rate": 3.7747460839636935e-05, "loss": 0.193, "step": 3223 }, { "epoch": 0.17804285398718797, "grad_norm": 4.001572132110596, "learning_rate": 3.774581122980457e-05, "loss": 0.4565, "step": 3224 }, { "epoch": 0.17809807819748177, "grad_norm": 0.11799819022417068, "learning_rate": 3.774416105223318e-05, "loss": 0.0053, "step": 3225 }, { "epoch": 0.17815330240777558, "grad_norm": 2.6953728199005127, "learning_rate": 3.774251030697556e-05, "loss": 0.1524, "step": 3226 }, { "epoch": 0.17820852661806935, "grad_norm": 5.424408912658691, "learning_rate": 3.7740858994084536e-05, "loss": 0.3055, "step": 3227 }, { "epoch": 0.17826375082836315, "grad_norm": 0.4270258843898773, "learning_rate": 3.773920711361292e-05, "loss": 0.0117, "step": 3228 }, { "epoch": 0.17831897503865696, "grad_norm": 1.7239537239074707, "learning_rate": 3.773755466561357e-05, "loss": 0.1039, "step": 3229 }, { "epoch": 0.17837419924895073, "grad_norm": 3.2190651893615723, "learning_rate": 3.7735901650139354e-05, "loss": 0.7237, "step": 3230 }, { "epoch": 0.17842942345924453, "grad_norm": 3.576200246810913, "learning_rate": 3.773424806724315e-05, "loss": 0.6648, "step": 3231 }, { "epoch": 0.17848464766953834, "grad_norm": 3.8286702632904053, "learning_rate": 3.773259391697786e-05, "loss": 0.8371, "step": 3232 }, { "epoch": 0.1785398718798321, "grad_norm": 4.302521705627441, "learning_rate": 3.773093919939641e-05, "loss": 0.4499, "step": 3233 }, { "epoch": 0.17859509609012592, "grad_norm": 3.3452253341674805, "learning_rate": 3.772928391455173e-05, "loss": 0.3434, "step": 3234 }, { "epoch": 0.1786503203004197, "grad_norm": 0.09332001209259033, "learning_rate": 3.772762806249679e-05, "loss": 0.0038, "step": 3235 }, { "epoch": 0.1787055445107135, "grad_norm": 2.561077117919922, "learning_rate": 3.7725971643284564e-05, "loss": 0.1967, "step": 3236 }, { "epoch": 0.1787607687210073, "grad_norm": 0.39418551325798035, "learning_rate": 3.7724314656968036e-05, "loss": 0.0075, "step": 3237 }, { "epoch": 0.17881599293130107, "grad_norm": 1.9600095748901367, "learning_rate": 3.772265710360023e-05, "loss": 0.197, "step": 3238 }, { "epoch": 0.17887121714159487, "grad_norm": 3.2636678218841553, "learning_rate": 3.772099898323416e-05, "loss": 0.3925, "step": 3239 }, { "epoch": 0.17892644135188868, "grad_norm": 0.048222433775663376, "learning_rate": 3.7719340295922886e-05, "loss": 0.0016, "step": 3240 }, { "epoch": 0.17898166556218245, "grad_norm": 2.460574150085449, "learning_rate": 3.771768104171947e-05, "loss": 0.4308, "step": 3241 }, { "epoch": 0.17903688977247625, "grad_norm": 0.045314252376556396, "learning_rate": 3.7716021220677e-05, "loss": 0.0019, "step": 3242 }, { "epoch": 0.17909211398277006, "grad_norm": 1.342727780342102, "learning_rate": 3.771436083284858e-05, "loss": 0.0313, "step": 3243 }, { "epoch": 0.17914733819306383, "grad_norm": 0.22508886456489563, "learning_rate": 3.7712699878287324e-05, "loss": 0.0093, "step": 3244 }, { "epoch": 0.17920256240335763, "grad_norm": 2.9666521549224854, "learning_rate": 3.7711038357046365e-05, "loss": 0.5528, "step": 3245 }, { "epoch": 0.17925778661365144, "grad_norm": 0.4279783368110657, "learning_rate": 3.7709376269178874e-05, "loss": 0.0248, "step": 3246 }, { "epoch": 0.1793130108239452, "grad_norm": 3.6814050674438477, "learning_rate": 3.7707713614738024e-05, "loss": 0.5016, "step": 3247 }, { "epoch": 0.17936823503423902, "grad_norm": 2.6633689403533936, "learning_rate": 3.7706050393776996e-05, "loss": 0.4059, "step": 3248 }, { "epoch": 0.1794234592445328, "grad_norm": 1.1271649599075317, "learning_rate": 3.7704386606349016e-05, "loss": 0.0485, "step": 3249 }, { "epoch": 0.1794786834548266, "grad_norm": 0.24522723257541656, "learning_rate": 3.7702722252507306e-05, "loss": 0.0058, "step": 3250 }, { "epoch": 0.1795339076651204, "grad_norm": 0.05138007178902626, "learning_rate": 3.7701057332305106e-05, "loss": 0.002, "step": 3251 }, { "epoch": 0.17958913187541417, "grad_norm": 1.1223366260528564, "learning_rate": 3.76993918457957e-05, "loss": 0.0646, "step": 3252 }, { "epoch": 0.17964435608570797, "grad_norm": 2.838641405105591, "learning_rate": 3.769772579303235e-05, "loss": 0.298, "step": 3253 }, { "epoch": 0.17969958029600178, "grad_norm": 3.234616756439209, "learning_rate": 3.7696059174068375e-05, "loss": 0.4459, "step": 3254 }, { "epoch": 0.17975480450629555, "grad_norm": 0.21934816241264343, "learning_rate": 3.769439198895708e-05, "loss": 0.0073, "step": 3255 }, { "epoch": 0.17981002871658935, "grad_norm": 2.9234695434570312, "learning_rate": 3.7692724237751826e-05, "loss": 0.2369, "step": 3256 }, { "epoch": 0.17986525292688316, "grad_norm": 0.213897243142128, "learning_rate": 3.7691055920505946e-05, "loss": 0.0103, "step": 3257 }, { "epoch": 0.17992047713717693, "grad_norm": 5.437581539154053, "learning_rate": 3.768938703727283e-05, "loss": 0.5123, "step": 3258 }, { "epoch": 0.17997570134747073, "grad_norm": 0.5967790484428406, "learning_rate": 3.768771758810585e-05, "loss": 0.0244, "step": 3259 }, { "epoch": 0.18003092555776454, "grad_norm": 2.59763503074646, "learning_rate": 3.768604757305844e-05, "loss": 0.4185, "step": 3260 }, { "epoch": 0.1800861497680583, "grad_norm": 0.09016183763742447, "learning_rate": 3.768437699218402e-05, "loss": 0.0041, "step": 3261 }, { "epoch": 0.18014137397835212, "grad_norm": 0.3897949457168579, "learning_rate": 3.768270584553603e-05, "loss": 0.0118, "step": 3262 }, { "epoch": 0.1801965981886459, "grad_norm": 0.19213628768920898, "learning_rate": 3.768103413316794e-05, "loss": 0.0084, "step": 3263 }, { "epoch": 0.1802518223989397, "grad_norm": 3.3847413063049316, "learning_rate": 3.767936185513323e-05, "loss": 0.6156, "step": 3264 }, { "epoch": 0.1803070466092335, "grad_norm": 0.06373989582061768, "learning_rate": 3.7677689011485404e-05, "loss": 0.0023, "step": 3265 }, { "epoch": 0.18036227081952727, "grad_norm": 2.993877649307251, "learning_rate": 3.7676015602277984e-05, "loss": 0.2694, "step": 3266 }, { "epoch": 0.18041749502982107, "grad_norm": 5.540035724639893, "learning_rate": 3.76743416275645e-05, "loss": 0.9911, "step": 3267 }, { "epoch": 0.18047271924011488, "grad_norm": 2.824690580368042, "learning_rate": 3.767266708739851e-05, "loss": 0.7923, "step": 3268 }, { "epoch": 0.18052794345040865, "grad_norm": 1.7217806577682495, "learning_rate": 3.767099198183359e-05, "loss": 0.0981, "step": 3269 }, { "epoch": 0.18058316766070245, "grad_norm": 4.534872055053711, "learning_rate": 3.766931631092333e-05, "loss": 1.0756, "step": 3270 }, { "epoch": 0.18063839187099626, "grad_norm": 1.2190544605255127, "learning_rate": 3.7667640074721345e-05, "loss": 0.035, "step": 3271 }, { "epoch": 0.18069361608129003, "grad_norm": 3.479490041732788, "learning_rate": 3.766596327328125e-05, "loss": 0.3765, "step": 3272 }, { "epoch": 0.18074884029158383, "grad_norm": 4.803794860839844, "learning_rate": 3.76642859066567e-05, "loss": 1.2345, "step": 3273 }, { "epoch": 0.1808040645018776, "grad_norm": 0.2851541042327881, "learning_rate": 3.7662607974901346e-05, "loss": 0.0099, "step": 3274 }, { "epoch": 0.1808592887121714, "grad_norm": 2.362678289413452, "learning_rate": 3.766092947806889e-05, "loss": 0.1495, "step": 3275 }, { "epoch": 0.18091451292246521, "grad_norm": 3.6316049098968506, "learning_rate": 3.7659250416213014e-05, "loss": 0.5587, "step": 3276 }, { "epoch": 0.180969737132759, "grad_norm": 1.7355636358261108, "learning_rate": 3.765757078938745e-05, "loss": 0.0456, "step": 3277 }, { "epoch": 0.1810249613430528, "grad_norm": 0.9504139423370361, "learning_rate": 3.765589059764593e-05, "loss": 0.0321, "step": 3278 }, { "epoch": 0.1810801855533466, "grad_norm": 0.1331428438425064, "learning_rate": 3.7654209841042196e-05, "loss": 0.0031, "step": 3279 }, { "epoch": 0.18113540976364037, "grad_norm": 3.416928291320801, "learning_rate": 3.7652528519630036e-05, "loss": 0.8152, "step": 3280 }, { "epoch": 0.18119063397393417, "grad_norm": 3.6219897270202637, "learning_rate": 3.7650846633463233e-05, "loss": 0.3883, "step": 3281 }, { "epoch": 0.18124585818422798, "grad_norm": 3.9510498046875, "learning_rate": 3.76491641825956e-05, "loss": 0.5029, "step": 3282 }, { "epoch": 0.18130108239452175, "grad_norm": 0.33236679434776306, "learning_rate": 3.764748116708095e-05, "loss": 0.0144, "step": 3283 }, { "epoch": 0.18135630660481555, "grad_norm": 3.5516927242279053, "learning_rate": 3.764579758697315e-05, "loss": 1.1487, "step": 3284 }, { "epoch": 0.18141153081510936, "grad_norm": 3.504129648208618, "learning_rate": 3.764411344232604e-05, "loss": 0.9816, "step": 3285 }, { "epoch": 0.18146675502540313, "grad_norm": 0.07967696338891983, "learning_rate": 3.7642428733193515e-05, "loss": 0.0032, "step": 3286 }, { "epoch": 0.18152197923569693, "grad_norm": 0.048185236752033234, "learning_rate": 3.7640743459629464e-05, "loss": 0.0022, "step": 3287 }, { "epoch": 0.1815772034459907, "grad_norm": 2.905787944793701, "learning_rate": 3.763905762168781e-05, "loss": 0.5003, "step": 3288 }, { "epoch": 0.1816324276562845, "grad_norm": 1.6371921300888062, "learning_rate": 3.7637371219422496e-05, "loss": 0.0763, "step": 3289 }, { "epoch": 0.18168765186657831, "grad_norm": 2.4402670860290527, "learning_rate": 3.763568425288746e-05, "loss": 0.1655, "step": 3290 }, { "epoch": 0.1817428760768721, "grad_norm": 1.1568853855133057, "learning_rate": 3.763399672213668e-05, "loss": 0.0567, "step": 3291 }, { "epoch": 0.1817981002871659, "grad_norm": 2.497349500656128, "learning_rate": 3.7632308627224134e-05, "loss": 0.2043, "step": 3292 }, { "epoch": 0.1818533244974597, "grad_norm": 0.4307144284248352, "learning_rate": 3.763061996820384e-05, "loss": 0.0105, "step": 3293 }, { "epoch": 0.18190854870775347, "grad_norm": 0.017414428293704987, "learning_rate": 3.7628930745129825e-05, "loss": 0.0008, "step": 3294 }, { "epoch": 0.18196377291804727, "grad_norm": 2.3561768531799316, "learning_rate": 3.762724095805613e-05, "loss": 0.2854, "step": 3295 }, { "epoch": 0.18201899712834108, "grad_norm": 2.423081159591675, "learning_rate": 3.762555060703681e-05, "loss": 0.4081, "step": 3296 }, { "epoch": 0.18207422133863485, "grad_norm": 0.3116375505924225, "learning_rate": 3.762385969212596e-05, "loss": 0.0076, "step": 3297 }, { "epoch": 0.18212944554892865, "grad_norm": 2.9901411533355713, "learning_rate": 3.7622168213377655e-05, "loss": 0.1922, "step": 3298 }, { "epoch": 0.18218466975922246, "grad_norm": 0.681406557559967, "learning_rate": 3.762047617084602e-05, "loss": 0.096, "step": 3299 }, { "epoch": 0.18223989396951623, "grad_norm": 5.669151782989502, "learning_rate": 3.7618783564585196e-05, "loss": 1.052, "step": 3300 }, { "epoch": 0.18229511817981003, "grad_norm": 2.6431708335876465, "learning_rate": 3.7617090394649315e-05, "loss": 0.1475, "step": 3301 }, { "epoch": 0.1823503423901038, "grad_norm": 5.067481994628906, "learning_rate": 3.761539666109257e-05, "loss": 1.0887, "step": 3302 }, { "epoch": 0.1824055666003976, "grad_norm": 5.774160385131836, "learning_rate": 3.761370236396914e-05, "loss": 1.1979, "step": 3303 }, { "epoch": 0.18246079081069141, "grad_norm": 0.19098521769046783, "learning_rate": 3.761200750333321e-05, "loss": 0.0057, "step": 3304 }, { "epoch": 0.1825160150209852, "grad_norm": 3.8861258029937744, "learning_rate": 3.761031207923903e-05, "loss": 0.3815, "step": 3305 }, { "epoch": 0.182571239231279, "grad_norm": 1.5491989850997925, "learning_rate": 3.760861609174084e-05, "loss": 0.2258, "step": 3306 }, { "epoch": 0.1826264634415728, "grad_norm": 4.4822773933410645, "learning_rate": 3.7606919540892885e-05, "loss": 1.029, "step": 3307 }, { "epoch": 0.18268168765186657, "grad_norm": 3.003540277481079, "learning_rate": 3.7605222426749446e-05, "loss": 0.9965, "step": 3308 }, { "epoch": 0.18273691186216037, "grad_norm": 0.4016566276550293, "learning_rate": 3.760352474936482e-05, "loss": 0.0089, "step": 3309 }, { "epoch": 0.18279213607245418, "grad_norm": 1.3611215353012085, "learning_rate": 3.760182650879333e-05, "loss": 0.0577, "step": 3310 }, { "epoch": 0.18284736028274795, "grad_norm": 1.881744623184204, "learning_rate": 3.760012770508931e-05, "loss": 0.3403, "step": 3311 }, { "epoch": 0.18290258449304175, "grad_norm": 4.083560943603516, "learning_rate": 3.759842833830708e-05, "loss": 1.2502, "step": 3312 }, { "epoch": 0.18295780870333556, "grad_norm": 1.3577263355255127, "learning_rate": 3.759672840850103e-05, "loss": 0.0547, "step": 3313 }, { "epoch": 0.18301303291362933, "grad_norm": 1.4449554681777954, "learning_rate": 3.7595027915725546e-05, "loss": 0.3352, "step": 3314 }, { "epoch": 0.18306825712392313, "grad_norm": 3.3405601978302, "learning_rate": 3.759332686003503e-05, "loss": 0.7504, "step": 3315 }, { "epoch": 0.1831234813342169, "grad_norm": 0.14341790974140167, "learning_rate": 3.75916252414839e-05, "loss": 0.0075, "step": 3316 }, { "epoch": 0.1831787055445107, "grad_norm": 0.5616919994354248, "learning_rate": 3.7589923060126593e-05, "loss": 0.0259, "step": 3317 }, { "epoch": 0.18323392975480451, "grad_norm": 2.003044843673706, "learning_rate": 3.758822031601758e-05, "loss": 0.124, "step": 3318 }, { "epoch": 0.1832891539650983, "grad_norm": 3.9330246448516846, "learning_rate": 3.7586517009211324e-05, "loss": 1.2085, "step": 3319 }, { "epoch": 0.1833443781753921, "grad_norm": 3.853761672973633, "learning_rate": 3.7584813139762315e-05, "loss": 0.2725, "step": 3320 }, { "epoch": 0.1833996023856859, "grad_norm": 0.1346174031496048, "learning_rate": 3.758310870772508e-05, "loss": 0.0053, "step": 3321 }, { "epoch": 0.18345482659597967, "grad_norm": 0.4036332964897156, "learning_rate": 3.7581403713154146e-05, "loss": 0.0131, "step": 3322 }, { "epoch": 0.18351005080627347, "grad_norm": 4.566810131072998, "learning_rate": 3.757969815610404e-05, "loss": 1.23, "step": 3323 }, { "epoch": 0.18356527501656728, "grad_norm": 0.6807793378829956, "learning_rate": 3.7577992036629353e-05, "loss": 0.0353, "step": 3324 }, { "epoch": 0.18362049922686105, "grad_norm": 1.402963638305664, "learning_rate": 3.7576285354784656e-05, "loss": 0.0639, "step": 3325 }, { "epoch": 0.18367572343715485, "grad_norm": 0.9398419260978699, "learning_rate": 3.7574578110624554e-05, "loss": 0.0403, "step": 3326 }, { "epoch": 0.18373094764744863, "grad_norm": 0.1128392294049263, "learning_rate": 3.757287030420367e-05, "loss": 0.004, "step": 3327 }, { "epoch": 0.18378617185774243, "grad_norm": 3.046485185623169, "learning_rate": 3.757116193557663e-05, "loss": 0.3455, "step": 3328 }, { "epoch": 0.18384139606803623, "grad_norm": 0.4209185838699341, "learning_rate": 3.75694530047981e-05, "loss": 0.0111, "step": 3329 }, { "epoch": 0.18389662027833, "grad_norm": 1.0309579372406006, "learning_rate": 3.7567743511922746e-05, "loss": 0.0365, "step": 3330 }, { "epoch": 0.1839518444886238, "grad_norm": 5.690656661987305, "learning_rate": 3.7566033457005266e-05, "loss": 1.0246, "step": 3331 }, { "epoch": 0.18400706869891761, "grad_norm": 0.2110253870487213, "learning_rate": 3.756432284010037e-05, "loss": 0.0054, "step": 3332 }, { "epoch": 0.1840622929092114, "grad_norm": 2.053306818008423, "learning_rate": 3.756261166126278e-05, "loss": 0.8034, "step": 3333 }, { "epoch": 0.1841175171195052, "grad_norm": 0.7056519985198975, "learning_rate": 3.7560899920547254e-05, "loss": 0.0203, "step": 3334 }, { "epoch": 0.184172741329799, "grad_norm": 4.242204666137695, "learning_rate": 3.7559187618008536e-05, "loss": 1.5211, "step": 3335 }, { "epoch": 0.18422796554009277, "grad_norm": 0.06941311061382294, "learning_rate": 3.755747475370141e-05, "loss": 0.0029, "step": 3336 }, { "epoch": 0.18428318975038657, "grad_norm": 0.16424262523651123, "learning_rate": 3.7555761327680696e-05, "loss": 0.0057, "step": 3337 }, { "epoch": 0.18433841396068038, "grad_norm": 2.248220205307007, "learning_rate": 3.7554047340001195e-05, "loss": 0.101, "step": 3338 }, { "epoch": 0.18439363817097415, "grad_norm": 0.4589572548866272, "learning_rate": 3.755233279071774e-05, "loss": 0.0162, "step": 3339 }, { "epoch": 0.18444886238126795, "grad_norm": 2.885664939880371, "learning_rate": 3.75506176798852e-05, "loss": 0.2787, "step": 3340 }, { "epoch": 0.18450408659156173, "grad_norm": 0.2987355589866638, "learning_rate": 3.754890200755843e-05, "loss": 0.0116, "step": 3341 }, { "epoch": 0.18455931080185553, "grad_norm": 4.152364253997803, "learning_rate": 3.754718577379232e-05, "loss": 0.4288, "step": 3342 }, { "epoch": 0.18461453501214933, "grad_norm": 2.585318088531494, "learning_rate": 3.754546897864179e-05, "loss": 0.3086, "step": 3343 }, { "epoch": 0.1846697592224431, "grad_norm": 0.02356918342411518, "learning_rate": 3.754375162216176e-05, "loss": 0.001, "step": 3344 }, { "epoch": 0.1847249834327369, "grad_norm": 0.8959758877754211, "learning_rate": 3.7542033704407166e-05, "loss": 0.0242, "step": 3345 }, { "epoch": 0.18478020764303071, "grad_norm": 0.07071267813444138, "learning_rate": 3.754031522543297e-05, "loss": 0.0024, "step": 3346 }, { "epoch": 0.1848354318533245, "grad_norm": 1.4437015056610107, "learning_rate": 3.7538596185294165e-05, "loss": 0.2563, "step": 3347 }, { "epoch": 0.1848906560636183, "grad_norm": 0.14821922779083252, "learning_rate": 3.7536876584045735e-05, "loss": 0.0051, "step": 3348 }, { "epoch": 0.1849458802739121, "grad_norm": 1.2040016651153564, "learning_rate": 3.753515642174269e-05, "loss": 0.0971, "step": 3349 }, { "epoch": 0.18500110448420587, "grad_norm": 0.22064454853534698, "learning_rate": 3.7533435698440076e-05, "loss": 0.007, "step": 3350 }, { "epoch": 0.18505632869449967, "grad_norm": 2.5545735359191895, "learning_rate": 3.7531714414192935e-05, "loss": 0.1501, "step": 3351 }, { "epoch": 0.18511155290479347, "grad_norm": 6.330078601837158, "learning_rate": 3.7529992569056344e-05, "loss": 2.4335, "step": 3352 }, { "epoch": 0.18516677711508725, "grad_norm": 4.53007698059082, "learning_rate": 3.752827016308538e-05, "loss": 0.5157, "step": 3353 }, { "epoch": 0.18522200132538105, "grad_norm": 0.377718061208725, "learning_rate": 3.752654719633516e-05, "loss": 0.0137, "step": 3354 }, { "epoch": 0.18527722553567483, "grad_norm": 3.99387788772583, "learning_rate": 3.75248236688608e-05, "loss": 0.5621, "step": 3355 }, { "epoch": 0.18533244974596863, "grad_norm": 0.9820428490638733, "learning_rate": 3.752309958071743e-05, "loss": 0.0283, "step": 3356 }, { "epoch": 0.18538767395626243, "grad_norm": 4.515352725982666, "learning_rate": 3.752137493196022e-05, "loss": 0.8582, "step": 3357 }, { "epoch": 0.1854428981665562, "grad_norm": 1.4378798007965088, "learning_rate": 3.7519649722644356e-05, "loss": 0.0518, "step": 3358 }, { "epoch": 0.18549812237685, "grad_norm": 3.104031562805176, "learning_rate": 3.7517923952825016e-05, "loss": 0.2181, "step": 3359 }, { "epoch": 0.1855533465871438, "grad_norm": 2.828110694885254, "learning_rate": 3.751619762255741e-05, "loss": 0.7682, "step": 3360 }, { "epoch": 0.1856085707974376, "grad_norm": 0.33514726161956787, "learning_rate": 3.751447073189678e-05, "loss": 0.0148, "step": 3361 }, { "epoch": 0.1856637950077314, "grad_norm": 5.36073637008667, "learning_rate": 3.751274328089837e-05, "loss": 1.4985, "step": 3362 }, { "epoch": 0.1857190192180252, "grad_norm": 3.1212236881256104, "learning_rate": 3.7511015269617446e-05, "loss": 0.7313, "step": 3363 }, { "epoch": 0.18577424342831897, "grad_norm": 5.105349540710449, "learning_rate": 3.750928669810929e-05, "loss": 0.369, "step": 3364 }, { "epoch": 0.18582946763861277, "grad_norm": 2.221099376678467, "learning_rate": 3.750755756642921e-05, "loss": 0.1013, "step": 3365 }, { "epoch": 0.18588469184890655, "grad_norm": 3.189288854598999, "learning_rate": 3.7505827874632516e-05, "loss": 0.9878, "step": 3366 }, { "epoch": 0.18593991605920035, "grad_norm": 3.606943130493164, "learning_rate": 3.750409762277456e-05, "loss": 0.1073, "step": 3367 }, { "epoch": 0.18599514026949415, "grad_norm": 2.273904323577881, "learning_rate": 3.750236681091069e-05, "loss": 0.2523, "step": 3368 }, { "epoch": 0.18605036447978793, "grad_norm": 0.14154884219169617, "learning_rate": 3.750063543909626e-05, "loss": 0.0042, "step": 3369 }, { "epoch": 0.18610558869008173, "grad_norm": 2.4207663536071777, "learning_rate": 3.7498903507386704e-05, "loss": 0.196, "step": 3370 }, { "epoch": 0.18616081290037553, "grad_norm": 0.07312901318073273, "learning_rate": 3.749717101583739e-05, "loss": 0.0035, "step": 3371 }, { "epoch": 0.1862160371106693, "grad_norm": 0.18338392674922943, "learning_rate": 3.7495437964503774e-05, "loss": 0.0068, "step": 3372 }, { "epoch": 0.1862712613209631, "grad_norm": 1.018775224685669, "learning_rate": 3.749370435344128e-05, "loss": 0.0327, "step": 3373 }, { "epoch": 0.1863264855312569, "grad_norm": 4.493326187133789, "learning_rate": 3.749197018270539e-05, "loss": 0.1542, "step": 3374 }, { "epoch": 0.1863817097415507, "grad_norm": 0.3214269280433655, "learning_rate": 3.7490235452351574e-05, "loss": 0.0108, "step": 3375 }, { "epoch": 0.1864369339518445, "grad_norm": 1.5338349342346191, "learning_rate": 3.748850016243533e-05, "loss": 0.1087, "step": 3376 }, { "epoch": 0.1864921581621383, "grad_norm": 3.252448558807373, "learning_rate": 3.7486764313012186e-05, "loss": 0.6669, "step": 3377 }, { "epoch": 0.18654738237243207, "grad_norm": 0.11835962533950806, "learning_rate": 3.7485027904137664e-05, "loss": 0.0039, "step": 3378 }, { "epoch": 0.18660260658272587, "grad_norm": 1.9262322187423706, "learning_rate": 3.748329093586732e-05, "loss": 0.1754, "step": 3379 }, { "epoch": 0.18665783079301965, "grad_norm": 0.5460940003395081, "learning_rate": 3.748155340825672e-05, "loss": 0.0195, "step": 3380 }, { "epoch": 0.18671305500331345, "grad_norm": 2.550715923309326, "learning_rate": 3.7479815321361475e-05, "loss": 0.2622, "step": 3381 }, { "epoch": 0.18676827921360725, "grad_norm": 1.2879340648651123, "learning_rate": 3.7478076675237166e-05, "loss": 0.0571, "step": 3382 }, { "epoch": 0.18682350342390103, "grad_norm": 0.321888267993927, "learning_rate": 3.747633746993943e-05, "loss": 0.014, "step": 3383 }, { "epoch": 0.18687872763419483, "grad_norm": 3.384249210357666, "learning_rate": 3.74745977055239e-05, "loss": 0.4546, "step": 3384 }, { "epoch": 0.18693395184448863, "grad_norm": 0.13489669561386108, "learning_rate": 3.747285738204624e-05, "loss": 0.0059, "step": 3385 }, { "epoch": 0.1869891760547824, "grad_norm": 7.20947265625, "learning_rate": 3.747111649956214e-05, "loss": 0.7792, "step": 3386 }, { "epoch": 0.1870444002650762, "grad_norm": 1.2108166217803955, "learning_rate": 3.746937505812728e-05, "loss": 0.0506, "step": 3387 }, { "epoch": 0.18709962447537, "grad_norm": 3.352776288986206, "learning_rate": 3.746763305779737e-05, "loss": 0.4013, "step": 3388 }, { "epoch": 0.1871548486856638, "grad_norm": 0.6297839283943176, "learning_rate": 3.746589049862816e-05, "loss": 0.0228, "step": 3389 }, { "epoch": 0.1872100728959576, "grad_norm": 1.3875699043273926, "learning_rate": 3.7464147380675385e-05, "loss": 0.0279, "step": 3390 }, { "epoch": 0.1872652971062514, "grad_norm": 1.3216220140457153, "learning_rate": 3.746240370399482e-05, "loss": 0.0528, "step": 3391 }, { "epoch": 0.18732052131654517, "grad_norm": 1.175917148590088, "learning_rate": 3.7460659468642255e-05, "loss": 0.0302, "step": 3392 }, { "epoch": 0.18737574552683897, "grad_norm": 5.213515758514404, "learning_rate": 3.745891467467347e-05, "loss": 0.629, "step": 3393 }, { "epoch": 0.18743096973713275, "grad_norm": 0.22587478160858154, "learning_rate": 3.745716932214431e-05, "loss": 0.005, "step": 3394 }, { "epoch": 0.18748619394742655, "grad_norm": 1.9700589179992676, "learning_rate": 3.74554234111106e-05, "loss": 0.7384, "step": 3395 }, { "epoch": 0.18754141815772035, "grad_norm": 2.3837738037109375, "learning_rate": 3.745367694162821e-05, "loss": 0.2975, "step": 3396 }, { "epoch": 0.18759664236801413, "grad_norm": 2.4061875343322754, "learning_rate": 3.7451929913753e-05, "loss": 0.2675, "step": 3397 }, { "epoch": 0.18765186657830793, "grad_norm": 1.2696170806884766, "learning_rate": 3.745018232754087e-05, "loss": 0.024, "step": 3398 }, { "epoch": 0.18770709078860173, "grad_norm": 3.2011308670043945, "learning_rate": 3.744843418304773e-05, "loss": 0.6126, "step": 3399 }, { "epoch": 0.1877623149988955, "grad_norm": 0.07919320464134216, "learning_rate": 3.74466854803295e-05, "loss": 0.0025, "step": 3400 }, { "epoch": 0.1878175392091893, "grad_norm": 1.103842854499817, "learning_rate": 3.744493621944214e-05, "loss": 0.0526, "step": 3401 }, { "epoch": 0.1878727634194831, "grad_norm": 1.1071542501449585, "learning_rate": 3.744318640044161e-05, "loss": 0.0581, "step": 3402 }, { "epoch": 0.1879279876297769, "grad_norm": 0.18680211901664734, "learning_rate": 3.744143602338388e-05, "loss": 0.0033, "step": 3403 }, { "epoch": 0.1879832118400707, "grad_norm": 3.9435012340545654, "learning_rate": 3.743968508832496e-05, "loss": 0.4911, "step": 3404 }, { "epoch": 0.1880384360503645, "grad_norm": 1.53438138961792, "learning_rate": 3.743793359532087e-05, "loss": 0.3046, "step": 3405 }, { "epoch": 0.18809366026065827, "grad_norm": 1.3521671295166016, "learning_rate": 3.7436181544427636e-05, "loss": 0.0199, "step": 3406 }, { "epoch": 0.18814888447095207, "grad_norm": 1.8400263786315918, "learning_rate": 3.743442893570132e-05, "loss": 0.0673, "step": 3407 }, { "epoch": 0.18820410868124585, "grad_norm": 3.5447616577148438, "learning_rate": 3.743267576919799e-05, "loss": 0.5629, "step": 3408 }, { "epoch": 0.18825933289153965, "grad_norm": 4.239013195037842, "learning_rate": 3.743092204497373e-05, "loss": 0.354, "step": 3409 }, { "epoch": 0.18831455710183345, "grad_norm": 7.211368560791016, "learning_rate": 3.742916776308465e-05, "loss": 1.0586, "step": 3410 }, { "epoch": 0.18836978131212723, "grad_norm": 1.8119345903396606, "learning_rate": 3.742741292358688e-05, "loss": 0.0946, "step": 3411 }, { "epoch": 0.18842500552242103, "grad_norm": 1.0216953754425049, "learning_rate": 3.742565752653654e-05, "loss": 0.1891, "step": 3412 }, { "epoch": 0.18848022973271483, "grad_norm": 1.2821756601333618, "learning_rate": 3.7423901571989825e-05, "loss": 0.1082, "step": 3413 }, { "epoch": 0.1885354539430086, "grad_norm": 2.675213575363159, "learning_rate": 3.742214506000289e-05, "loss": 0.2683, "step": 3414 }, { "epoch": 0.1885906781533024, "grad_norm": 2.607715129852295, "learning_rate": 3.742038799063193e-05, "loss": 0.4807, "step": 3415 }, { "epoch": 0.1886459023635962, "grad_norm": 1.9206193685531616, "learning_rate": 3.741863036393318e-05, "loss": 0.1689, "step": 3416 }, { "epoch": 0.18870112657389, "grad_norm": 0.22054950892925262, "learning_rate": 3.741687217996284e-05, "loss": 0.0066, "step": 3417 }, { "epoch": 0.1887563507841838, "grad_norm": 0.4745156764984131, "learning_rate": 3.741511343877718e-05, "loss": 0.0185, "step": 3418 }, { "epoch": 0.18881157499447757, "grad_norm": 2.462557554244995, "learning_rate": 3.741335414043246e-05, "loss": 0.3124, "step": 3419 }, { "epoch": 0.18886679920477137, "grad_norm": 0.30377912521362305, "learning_rate": 3.741159428498497e-05, "loss": 0.0087, "step": 3420 }, { "epoch": 0.18892202341506517, "grad_norm": 1.5082917213439941, "learning_rate": 3.7409833872491016e-05, "loss": 0.0857, "step": 3421 }, { "epoch": 0.18897724762535895, "grad_norm": 0.21958908438682556, "learning_rate": 3.7408072903006906e-05, "loss": 0.0071, "step": 3422 }, { "epoch": 0.18903247183565275, "grad_norm": 3.329242706298828, "learning_rate": 3.740631137658898e-05, "loss": 0.6134, "step": 3423 }, { "epoch": 0.18908769604594655, "grad_norm": 2.4434783458709717, "learning_rate": 3.740454929329361e-05, "loss": 0.2411, "step": 3424 }, { "epoch": 0.18914292025624033, "grad_norm": 0.2003079652786255, "learning_rate": 3.740278665317716e-05, "loss": 0.0066, "step": 3425 }, { "epoch": 0.18919814446653413, "grad_norm": 1.0238808393478394, "learning_rate": 3.740102345629602e-05, "loss": 0.0408, "step": 3426 }, { "epoch": 0.18925336867682793, "grad_norm": 0.7212167978286743, "learning_rate": 3.739925970270659e-05, "loss": 0.0221, "step": 3427 }, { "epoch": 0.1893085928871217, "grad_norm": 1.1743433475494385, "learning_rate": 3.739749539246532e-05, "loss": 0.0414, "step": 3428 }, { "epoch": 0.1893638170974155, "grad_norm": 1.5494287014007568, "learning_rate": 3.739573052562864e-05, "loss": 0.1695, "step": 3429 }, { "epoch": 0.1894190413077093, "grad_norm": 2.6532444953918457, "learning_rate": 3.7393965102253024e-05, "loss": 0.6099, "step": 3430 }, { "epoch": 0.1894742655180031, "grad_norm": 0.7069112658500671, "learning_rate": 3.7392199122394934e-05, "loss": 0.0098, "step": 3431 }, { "epoch": 0.1895294897282969, "grad_norm": 1.2907668352127075, "learning_rate": 3.7390432586110887e-05, "loss": 0.067, "step": 3432 }, { "epoch": 0.18958471393859067, "grad_norm": 0.11522175371646881, "learning_rate": 3.7388665493457394e-05, "loss": 0.0034, "step": 3433 }, { "epoch": 0.18963993814888447, "grad_norm": 4.462729454040527, "learning_rate": 3.7386897844490986e-05, "loss": 0.6748, "step": 3434 }, { "epoch": 0.18969516235917827, "grad_norm": 0.055746890604496, "learning_rate": 3.738512963926822e-05, "loss": 0.0018, "step": 3435 }, { "epoch": 0.18975038656947205, "grad_norm": 4.183952808380127, "learning_rate": 3.7383360877845664e-05, "loss": 0.6574, "step": 3436 }, { "epoch": 0.18980561077976585, "grad_norm": 0.26407361030578613, "learning_rate": 3.73815915602799e-05, "loss": 0.0084, "step": 3437 }, { "epoch": 0.18986083499005965, "grad_norm": 2.710016965866089, "learning_rate": 3.737982168662755e-05, "loss": 0.0433, "step": 3438 }, { "epoch": 0.18991605920035343, "grad_norm": 0.08505846560001373, "learning_rate": 3.7378051256945215e-05, "loss": 0.0034, "step": 3439 }, { "epoch": 0.18997128341064723, "grad_norm": 1.7530814409255981, "learning_rate": 3.737628027128955e-05, "loss": 0.4527, "step": 3440 }, { "epoch": 0.19002650762094103, "grad_norm": 2.021545648574829, "learning_rate": 3.737450872971721e-05, "loss": 0.7773, "step": 3441 }, { "epoch": 0.1900817318312348, "grad_norm": 1.384080410003662, "learning_rate": 3.7372736632284875e-05, "loss": 0.0309, "step": 3442 }, { "epoch": 0.1901369560415286, "grad_norm": 1.9622547626495361, "learning_rate": 3.7370963979049236e-05, "loss": 0.5605, "step": 3443 }, { "epoch": 0.1901921802518224, "grad_norm": 1.093313217163086, "learning_rate": 3.7369190770067014e-05, "loss": 0.0456, "step": 3444 }, { "epoch": 0.1902474044621162, "grad_norm": 2.6110944747924805, "learning_rate": 3.736741700539492e-05, "loss": 0.2984, "step": 3445 }, { "epoch": 0.19030262867241, "grad_norm": 3.386126756668091, "learning_rate": 3.736564268508972e-05, "loss": 0.8421, "step": 3446 }, { "epoch": 0.19035785288270377, "grad_norm": 1.420131802558899, "learning_rate": 3.736386780920817e-05, "loss": 0.0672, "step": 3447 }, { "epoch": 0.19041307709299757, "grad_norm": 0.1715489625930786, "learning_rate": 3.7362092377807056e-05, "loss": 0.0043, "step": 3448 }, { "epoch": 0.19046830130329137, "grad_norm": 2.201117515563965, "learning_rate": 3.736031639094318e-05, "loss": 0.0993, "step": 3449 }, { "epoch": 0.19052352551358515, "grad_norm": 3.4226415157318115, "learning_rate": 3.7358539848673364e-05, "loss": 0.8745, "step": 3450 }, { "epoch": 0.19057874972387895, "grad_norm": 3.464773654937744, "learning_rate": 3.7356762751054435e-05, "loss": 0.2147, "step": 3451 }, { "epoch": 0.19063397393417275, "grad_norm": 2.365830183029175, "learning_rate": 3.735498509814325e-05, "loss": 0.1727, "step": 3452 }, { "epoch": 0.19068919814446653, "grad_norm": 5.2201337814331055, "learning_rate": 3.735320688999669e-05, "loss": 1.5221, "step": 3453 }, { "epoch": 0.19074442235476033, "grad_norm": 0.32388368248939514, "learning_rate": 3.7351428126671635e-05, "loss": 0.0094, "step": 3454 }, { "epoch": 0.19079964656505413, "grad_norm": 0.44122114777565, "learning_rate": 3.7349648808225005e-05, "loss": 0.0125, "step": 3455 }, { "epoch": 0.1908548707753479, "grad_norm": 1.0724568367004395, "learning_rate": 3.734786893471371e-05, "loss": 0.1265, "step": 3456 }, { "epoch": 0.1909100949856417, "grad_norm": 2.7732093334198, "learning_rate": 3.73460885061947e-05, "loss": 0.402, "step": 3457 }, { "epoch": 0.19096531919593548, "grad_norm": 2.29793643951416, "learning_rate": 3.734430752272494e-05, "loss": 0.1301, "step": 3458 }, { "epoch": 0.1910205434062293, "grad_norm": 1.078847885131836, "learning_rate": 3.734252598436141e-05, "loss": 0.0411, "step": 3459 }, { "epoch": 0.1910757676165231, "grad_norm": 1.07757568359375, "learning_rate": 3.73407438911611e-05, "loss": 0.0231, "step": 3460 }, { "epoch": 0.19113099182681687, "grad_norm": 2.30544114112854, "learning_rate": 3.7338961243181014e-05, "loss": 0.2094, "step": 3461 }, { "epoch": 0.19118621603711067, "grad_norm": 5.533844470977783, "learning_rate": 3.733717804047821e-05, "loss": 1.3301, "step": 3462 }, { "epoch": 0.19124144024740447, "grad_norm": 2.6071367263793945, "learning_rate": 3.7335394283109716e-05, "loss": 0.5266, "step": 3463 }, { "epoch": 0.19129666445769825, "grad_norm": 3.4038491249084473, "learning_rate": 3.733360997113261e-05, "loss": 1.3762, "step": 3464 }, { "epoch": 0.19135188866799205, "grad_norm": 4.8713555335998535, "learning_rate": 3.733182510460397e-05, "loss": 0.6272, "step": 3465 }, { "epoch": 0.19140711287828585, "grad_norm": 0.06773947179317474, "learning_rate": 3.733003968358091e-05, "loss": 0.0027, "step": 3466 }, { "epoch": 0.19146233708857963, "grad_norm": 1.2622383832931519, "learning_rate": 3.7328253708120545e-05, "loss": 0.0437, "step": 3467 }, { "epoch": 0.19151756129887343, "grad_norm": 2.5881824493408203, "learning_rate": 3.732646717828001e-05, "loss": 0.1788, "step": 3468 }, { "epoch": 0.19157278550916723, "grad_norm": 6.017989635467529, "learning_rate": 3.732468009411646e-05, "loss": 0.1307, "step": 3469 }, { "epoch": 0.191628009719461, "grad_norm": 6.377562999725342, "learning_rate": 3.732289245568707e-05, "loss": 1.1191, "step": 3470 }, { "epoch": 0.1916832339297548, "grad_norm": 3.8370065689086914, "learning_rate": 3.7321104263049045e-05, "loss": 1.1028, "step": 3471 }, { "epoch": 0.19173845814004858, "grad_norm": 3.1457698345184326, "learning_rate": 3.7319315516259576e-05, "loss": 0.4923, "step": 3472 }, { "epoch": 0.1917936823503424, "grad_norm": 0.08073097467422485, "learning_rate": 3.73175262153759e-05, "loss": 0.0031, "step": 3473 }, { "epoch": 0.1918489065606362, "grad_norm": 4.301811695098877, "learning_rate": 3.731573636045526e-05, "loss": 0.3734, "step": 3474 }, { "epoch": 0.19190413077092996, "grad_norm": 3.1124184131622314, "learning_rate": 3.7313945951554914e-05, "loss": 0.4982, "step": 3475 }, { "epoch": 0.19195935498122377, "grad_norm": 2.3212244510650635, "learning_rate": 3.731215498873215e-05, "loss": 0.3166, "step": 3476 }, { "epoch": 0.19201457919151757, "grad_norm": 2.2385241985321045, "learning_rate": 3.7310363472044265e-05, "loss": 0.2818, "step": 3477 }, { "epoch": 0.19206980340181135, "grad_norm": 0.1240178570151329, "learning_rate": 3.730857140154857e-05, "loss": 0.0047, "step": 3478 }, { "epoch": 0.19212502761210515, "grad_norm": 4.559281349182129, "learning_rate": 3.7306778777302396e-05, "loss": 0.5139, "step": 3479 }, { "epoch": 0.19218025182239895, "grad_norm": 0.6034799218177795, "learning_rate": 3.7304985599363104e-05, "loss": 0.0206, "step": 3480 }, { "epoch": 0.19223547603269273, "grad_norm": 0.2924584448337555, "learning_rate": 3.730319186778806e-05, "loss": 0.0103, "step": 3481 }, { "epoch": 0.19229070024298653, "grad_norm": 0.12185147404670715, "learning_rate": 3.730139758263464e-05, "loss": 0.0053, "step": 3482 }, { "epoch": 0.19234592445328033, "grad_norm": 1.0987825393676758, "learning_rate": 3.729960274396026e-05, "loss": 0.0458, "step": 3483 }, { "epoch": 0.1924011486635741, "grad_norm": 0.2917935252189636, "learning_rate": 3.7297807351822344e-05, "loss": 0.0071, "step": 3484 }, { "epoch": 0.1924563728738679, "grad_norm": 1.3679009675979614, "learning_rate": 3.729601140627832e-05, "loss": 0.1489, "step": 3485 }, { "epoch": 0.19251159708416168, "grad_norm": 0.1720404475927353, "learning_rate": 3.729421490738565e-05, "loss": 0.0072, "step": 3486 }, { "epoch": 0.1925668212944555, "grad_norm": 0.40279078483581543, "learning_rate": 3.7292417855201816e-05, "loss": 0.0092, "step": 3487 }, { "epoch": 0.1926220455047493, "grad_norm": 1.963032841682434, "learning_rate": 3.7290620249784304e-05, "loss": 0.4753, "step": 3488 }, { "epoch": 0.19267726971504306, "grad_norm": 0.5087659955024719, "learning_rate": 3.7288822091190627e-05, "loss": 0.0152, "step": 3489 }, { "epoch": 0.19273249392533687, "grad_norm": 0.16465826332569122, "learning_rate": 3.728702337947831e-05, "loss": 0.0059, "step": 3490 }, { "epoch": 0.19278771813563067, "grad_norm": 0.19352470338344574, "learning_rate": 3.7285224114704896e-05, "loss": 0.0067, "step": 3491 }, { "epoch": 0.19284294234592445, "grad_norm": 1.2492367029190063, "learning_rate": 3.728342429692796e-05, "loss": 0.0502, "step": 3492 }, { "epoch": 0.19289816655621825, "grad_norm": 0.9909612536430359, "learning_rate": 3.728162392620507e-05, "loss": 0.0381, "step": 3493 }, { "epoch": 0.19295339076651205, "grad_norm": 1.0147308111190796, "learning_rate": 3.727982300259385e-05, "loss": 0.0445, "step": 3494 }, { "epoch": 0.19300861497680583, "grad_norm": 2.1357827186584473, "learning_rate": 3.727802152615188e-05, "loss": 0.2518, "step": 3495 }, { "epoch": 0.19306383918709963, "grad_norm": 1.751929759979248, "learning_rate": 3.727621949693682e-05, "loss": 0.1252, "step": 3496 }, { "epoch": 0.1931190633973934, "grad_norm": 2.363953113555908, "learning_rate": 3.727441691500631e-05, "loss": 0.0474, "step": 3497 }, { "epoch": 0.1931742876076872, "grad_norm": 1.5112063884735107, "learning_rate": 3.7272613780418036e-05, "loss": 0.326, "step": 3498 }, { "epoch": 0.193229511817981, "grad_norm": 2.561889886856079, "learning_rate": 3.727081009322967e-05, "loss": 0.0916, "step": 3499 }, { "epoch": 0.19328473602827478, "grad_norm": 0.08573517203330994, "learning_rate": 3.726900585349892e-05, "loss": 0.0026, "step": 3500 }, { "epoch": 0.1933399602385686, "grad_norm": 2.2970707416534424, "learning_rate": 3.72672010612835e-05, "loss": 0.0819, "step": 3501 }, { "epoch": 0.1933951844488624, "grad_norm": 0.16842472553253174, "learning_rate": 3.7265395716641173e-05, "loss": 0.0061, "step": 3502 }, { "epoch": 0.19345040865915616, "grad_norm": 3.5415782928466797, "learning_rate": 3.7263589819629687e-05, "loss": 1.3862, "step": 3503 }, { "epoch": 0.19350563286944997, "grad_norm": 2.0377490520477295, "learning_rate": 3.72617833703068e-05, "loss": 0.4016, "step": 3504 }, { "epoch": 0.19356085707974377, "grad_norm": 4.897293567657471, "learning_rate": 3.7259976368730335e-05, "loss": 1.248, "step": 3505 }, { "epoch": 0.19361608129003754, "grad_norm": 0.14408618211746216, "learning_rate": 3.725816881495809e-05, "loss": 0.0044, "step": 3506 }, { "epoch": 0.19367130550033135, "grad_norm": 0.6244546175003052, "learning_rate": 3.725636070904789e-05, "loss": 0.0153, "step": 3507 }, { "epoch": 0.19372652971062515, "grad_norm": 1.7904956340789795, "learning_rate": 3.725455205105758e-05, "loss": 0.089, "step": 3508 }, { "epoch": 0.19378175392091893, "grad_norm": 0.06379915773868561, "learning_rate": 3.7252742841045026e-05, "loss": 0.0017, "step": 3509 }, { "epoch": 0.19383697813121273, "grad_norm": 0.06420043110847473, "learning_rate": 3.7250933079068116e-05, "loss": 0.002, "step": 3510 }, { "epoch": 0.1938922023415065, "grad_norm": 3.030391216278076, "learning_rate": 3.7249122765184745e-05, "loss": 0.1825, "step": 3511 }, { "epoch": 0.1939474265518003, "grad_norm": 2.988295078277588, "learning_rate": 3.724731189945283e-05, "loss": 0.2005, "step": 3512 }, { "epoch": 0.1940026507620941, "grad_norm": 2.41340970993042, "learning_rate": 3.724550048193031e-05, "loss": 0.2437, "step": 3513 }, { "epoch": 0.19405787497238788, "grad_norm": 0.264395147562027, "learning_rate": 3.724368851267513e-05, "loss": 0.0098, "step": 3514 }, { "epoch": 0.1941130991826817, "grad_norm": 3.2937188148498535, "learning_rate": 3.724187599174527e-05, "loss": 0.5968, "step": 3515 }, { "epoch": 0.1941683233929755, "grad_norm": 2.9252424240112305, "learning_rate": 3.72400629191987e-05, "loss": 0.1925, "step": 3516 }, { "epoch": 0.19422354760326926, "grad_norm": 2.7174324989318848, "learning_rate": 3.723824929509345e-05, "loss": 0.3252, "step": 3517 }, { "epoch": 0.19427877181356307, "grad_norm": 0.06385712325572968, "learning_rate": 3.723643511948752e-05, "loss": 0.003, "step": 3518 }, { "epoch": 0.19433399602385687, "grad_norm": 2.171921730041504, "learning_rate": 3.723462039243896e-05, "loss": 0.0907, "step": 3519 }, { "epoch": 0.19438922023415064, "grad_norm": 2.3760969638824463, "learning_rate": 3.7232805114005845e-05, "loss": 0.1397, "step": 3520 }, { "epoch": 0.19444444444444445, "grad_norm": 3.4440531730651855, "learning_rate": 3.723098928424622e-05, "loss": 0.3634, "step": 3521 }, { "epoch": 0.19449966865473825, "grad_norm": 1.6281341314315796, "learning_rate": 3.722917290321819e-05, "loss": 0.1854, "step": 3522 }, { "epoch": 0.19455489286503203, "grad_norm": 5.471370697021484, "learning_rate": 3.722735597097988e-05, "loss": 1.7921, "step": 3523 }, { "epoch": 0.19461011707532583, "grad_norm": 0.07999853044748306, "learning_rate": 3.72255384875894e-05, "loss": 0.0029, "step": 3524 }, { "epoch": 0.1946653412856196, "grad_norm": 3.937089681625366, "learning_rate": 3.7223720453104915e-05, "loss": 1.669, "step": 3525 }, { "epoch": 0.1947205654959134, "grad_norm": 1.8037289381027222, "learning_rate": 3.7221901867584575e-05, "loss": 0.1219, "step": 3526 }, { "epoch": 0.1947757897062072, "grad_norm": 0.3358179032802582, "learning_rate": 3.7220082731086555e-05, "loss": 0.0108, "step": 3527 }, { "epoch": 0.19483101391650098, "grad_norm": 3.844202995300293, "learning_rate": 3.721826304366908e-05, "loss": 0.4107, "step": 3528 }, { "epoch": 0.1948862381267948, "grad_norm": 1.0390477180480957, "learning_rate": 3.721644280539035e-05, "loss": 0.0365, "step": 3529 }, { "epoch": 0.1949414623370886, "grad_norm": 1.0127018690109253, "learning_rate": 3.721462201630859e-05, "loss": 0.0321, "step": 3530 }, { "epoch": 0.19499668654738236, "grad_norm": 0.3623516261577606, "learning_rate": 3.7212800676482074e-05, "loss": 0.011, "step": 3531 }, { "epoch": 0.19505191075767617, "grad_norm": 2.3729734420776367, "learning_rate": 3.721097878596906e-05, "loss": 0.6566, "step": 3532 }, { "epoch": 0.19510713496796997, "grad_norm": 0.27209851145744324, "learning_rate": 3.720915634482784e-05, "loss": 0.0095, "step": 3533 }, { "epoch": 0.19516235917826374, "grad_norm": 2.648106098175049, "learning_rate": 3.720733335311671e-05, "loss": 0.1181, "step": 3534 }, { "epoch": 0.19521758338855755, "grad_norm": 2.64201283454895, "learning_rate": 3.7205509810894e-05, "loss": 0.1791, "step": 3535 }, { "epoch": 0.19527280759885135, "grad_norm": 0.1645323932170868, "learning_rate": 3.720368571821805e-05, "loss": 0.0053, "step": 3536 }, { "epoch": 0.19532803180914513, "grad_norm": 7.291468143463135, "learning_rate": 3.720186107514722e-05, "loss": 0.4058, "step": 3537 }, { "epoch": 0.19538325601943893, "grad_norm": 2.108611583709717, "learning_rate": 3.7200035881739884e-05, "loss": 0.2469, "step": 3538 }, { "epoch": 0.1954384802297327, "grad_norm": 0.4104924499988556, "learning_rate": 3.7198210138054424e-05, "loss": 0.0064, "step": 3539 }, { "epoch": 0.1954937044400265, "grad_norm": 3.764518976211548, "learning_rate": 3.719638384414927e-05, "loss": 0.5152, "step": 3540 }, { "epoch": 0.1955489286503203, "grad_norm": 0.13314811885356903, "learning_rate": 3.719455700008283e-05, "loss": 0.0048, "step": 3541 }, { "epoch": 0.19560415286061408, "grad_norm": 0.09587662667036057, "learning_rate": 3.7192729605913574e-05, "loss": 0.0035, "step": 3542 }, { "epoch": 0.19565937707090789, "grad_norm": 1.4027148485183716, "learning_rate": 3.719090166169995e-05, "loss": 0.1241, "step": 3543 }, { "epoch": 0.1957146012812017, "grad_norm": 1.0034738779067993, "learning_rate": 3.718907316750044e-05, "loss": 0.1683, "step": 3544 }, { "epoch": 0.19576982549149546, "grad_norm": 0.6472395062446594, "learning_rate": 3.7187244123373536e-05, "loss": 0.036, "step": 3545 }, { "epoch": 0.19582504970178927, "grad_norm": 0.2942845821380615, "learning_rate": 3.7185414529377774e-05, "loss": 0.0053, "step": 3546 }, { "epoch": 0.19588027391208307, "grad_norm": 0.4651346504688263, "learning_rate": 3.718358438557167e-05, "loss": 0.0223, "step": 3547 }, { "epoch": 0.19593549812237684, "grad_norm": 0.29624828696250916, "learning_rate": 3.7181753692013783e-05, "loss": 0.0072, "step": 3548 }, { "epoch": 0.19599072233267065, "grad_norm": 1.5156333446502686, "learning_rate": 3.717992244876268e-05, "loss": 0.0525, "step": 3549 }, { "epoch": 0.19604594654296442, "grad_norm": 1.9921002388000488, "learning_rate": 3.717809065587695e-05, "loss": 0.0896, "step": 3550 }, { "epoch": 0.19610117075325822, "grad_norm": 1.795939564704895, "learning_rate": 3.7176258313415205e-05, "loss": 0.5772, "step": 3551 }, { "epoch": 0.19615639496355203, "grad_norm": 3.5748209953308105, "learning_rate": 3.717442542143604e-05, "loss": 0.6116, "step": 3552 }, { "epoch": 0.1962116191738458, "grad_norm": 2.635859727859497, "learning_rate": 3.7172591979998125e-05, "loss": 0.3288, "step": 3553 }, { "epoch": 0.1962668433841396, "grad_norm": 0.6475620269775391, "learning_rate": 3.7170757989160104e-05, "loss": 0.0232, "step": 3554 }, { "epoch": 0.1963220675944334, "grad_norm": 2.075709819793701, "learning_rate": 3.716892344898065e-05, "loss": 0.4874, "step": 3555 }, { "epoch": 0.19637729180472718, "grad_norm": 0.7110207676887512, "learning_rate": 3.716708835951846e-05, "loss": 0.0192, "step": 3556 }, { "epoch": 0.19643251601502099, "grad_norm": 0.12854672968387604, "learning_rate": 3.716525272083223e-05, "loss": 0.0032, "step": 3557 }, { "epoch": 0.1964877402253148, "grad_norm": 0.511879026889801, "learning_rate": 3.716341653298071e-05, "loss": 0.0132, "step": 3558 }, { "epoch": 0.19654296443560856, "grad_norm": 5.863277912139893, "learning_rate": 3.716157979602263e-05, "loss": 0.1922, "step": 3559 }, { "epoch": 0.19659818864590237, "grad_norm": 2.895707845687866, "learning_rate": 3.715974251001675e-05, "loss": 0.8064, "step": 3560 }, { "epoch": 0.19665341285619617, "grad_norm": 0.17513135075569153, "learning_rate": 3.7157904675021857e-05, "loss": 0.0041, "step": 3561 }, { "epoch": 0.19670863706648994, "grad_norm": 0.027273355051875114, "learning_rate": 3.715606629109675e-05, "loss": 0.0009, "step": 3562 }, { "epoch": 0.19676386127678375, "grad_norm": 1.5447955131530762, "learning_rate": 3.715422735830024e-05, "loss": 0.0576, "step": 3563 }, { "epoch": 0.19681908548707752, "grad_norm": 2.494462013244629, "learning_rate": 3.715238787669116e-05, "loss": 0.4923, "step": 3564 }, { "epoch": 0.19687430969737132, "grad_norm": 2.737485408782959, "learning_rate": 3.715054784632837e-05, "loss": 0.3222, "step": 3565 }, { "epoch": 0.19692953390766513, "grad_norm": 0.057439353317022324, "learning_rate": 3.714870726727072e-05, "loss": 0.002, "step": 3566 }, { "epoch": 0.1969847581179589, "grad_norm": 0.11565282940864563, "learning_rate": 3.71468661395771e-05, "loss": 0.0026, "step": 3567 }, { "epoch": 0.1970399823282527, "grad_norm": 6.407467842102051, "learning_rate": 3.714502446330643e-05, "loss": 0.4485, "step": 3568 }, { "epoch": 0.1970952065385465, "grad_norm": 3.932339668273926, "learning_rate": 3.714318223851761e-05, "loss": 2.0606, "step": 3569 }, { "epoch": 0.19715043074884028, "grad_norm": 0.2195935696363449, "learning_rate": 3.714133946526959e-05, "loss": 0.0056, "step": 3570 }, { "epoch": 0.19720565495913409, "grad_norm": 1.4911009073257446, "learning_rate": 3.7139496143621316e-05, "loss": 0.2917, "step": 3571 }, { "epoch": 0.1972608791694279, "grad_norm": 2.4635262489318848, "learning_rate": 3.713765227363177e-05, "loss": 0.0287, "step": 3572 }, { "epoch": 0.19731610337972166, "grad_norm": 6.234316349029541, "learning_rate": 3.7135807855359935e-05, "loss": 1.1191, "step": 3573 }, { "epoch": 0.19737132759001547, "grad_norm": 3.643890380859375, "learning_rate": 3.7133962888864825e-05, "loss": 0.9837, "step": 3574 }, { "epoch": 0.19742655180030927, "grad_norm": 4.256521224975586, "learning_rate": 3.7132117374205464e-05, "loss": 0.6215, "step": 3575 }, { "epoch": 0.19748177601060304, "grad_norm": 0.019815729930996895, "learning_rate": 3.7130271311440896e-05, "loss": 0.0006, "step": 3576 }, { "epoch": 0.19753700022089685, "grad_norm": 2.410076379776001, "learning_rate": 3.712842470063018e-05, "loss": 0.0896, "step": 3577 }, { "epoch": 0.19759222443119062, "grad_norm": 0.0799560397863388, "learning_rate": 3.7126577541832396e-05, "loss": 0.0022, "step": 3578 }, { "epoch": 0.19764744864148442, "grad_norm": 3.43285870552063, "learning_rate": 3.712472983510664e-05, "loss": 0.2746, "step": 3579 }, { "epoch": 0.19770267285177823, "grad_norm": 1.0307782888412476, "learning_rate": 3.712288158051202e-05, "loss": 0.0233, "step": 3580 }, { "epoch": 0.197757897062072, "grad_norm": 0.2691606283187866, "learning_rate": 3.712103277810768e-05, "loss": 0.0095, "step": 3581 }, { "epoch": 0.1978131212723658, "grad_norm": 0.6263423562049866, "learning_rate": 3.711918342795275e-05, "loss": 0.0221, "step": 3582 }, { "epoch": 0.1978683454826596, "grad_norm": 0.1415611356496811, "learning_rate": 3.711733353010641e-05, "loss": 0.0038, "step": 3583 }, { "epoch": 0.19792356969295338, "grad_norm": 3.718533515930176, "learning_rate": 3.711548308462785e-05, "loss": 0.3683, "step": 3584 }, { "epoch": 0.19797879390324719, "grad_norm": 3.8792777061462402, "learning_rate": 3.7113632091576246e-05, "loss": 1.6269, "step": 3585 }, { "epoch": 0.198034018113541, "grad_norm": 3.7837865352630615, "learning_rate": 3.711178055101084e-05, "loss": 0.9881, "step": 3586 }, { "epoch": 0.19808924232383476, "grad_norm": 2.449641466140747, "learning_rate": 3.710992846299086e-05, "loss": 0.8027, "step": 3587 }, { "epoch": 0.19814446653412857, "grad_norm": 0.13004857301712036, "learning_rate": 3.7108075827575546e-05, "loss": 0.006, "step": 3588 }, { "epoch": 0.19819969074442234, "grad_norm": 1.542942762374878, "learning_rate": 3.7106222644824195e-05, "loss": 0.1403, "step": 3589 }, { "epoch": 0.19825491495471614, "grad_norm": 3.865446090698242, "learning_rate": 3.7104368914796073e-05, "loss": 0.4646, "step": 3590 }, { "epoch": 0.19831013916500995, "grad_norm": 1.9857217073440552, "learning_rate": 3.71025146375505e-05, "loss": 0.313, "step": 3591 }, { "epoch": 0.19836536337530372, "grad_norm": 4.319082260131836, "learning_rate": 3.7100659813146794e-05, "loss": 0.5785, "step": 3592 }, { "epoch": 0.19842058758559752, "grad_norm": 1.883672833442688, "learning_rate": 3.70988044416443e-05, "loss": 0.1343, "step": 3593 }, { "epoch": 0.19847581179589133, "grad_norm": 0.15678493678569794, "learning_rate": 3.709694852310237e-05, "loss": 0.0057, "step": 3594 }, { "epoch": 0.1985310360061851, "grad_norm": 2.5064496994018555, "learning_rate": 3.709509205758039e-05, "loss": 0.2791, "step": 3595 }, { "epoch": 0.1985862602164789, "grad_norm": 1.5616716146469116, "learning_rate": 3.7093235045137744e-05, "loss": 0.077, "step": 3596 }, { "epoch": 0.1986414844267727, "grad_norm": 1.5849872827529907, "learning_rate": 3.709137748583384e-05, "loss": 0.3136, "step": 3597 }, { "epoch": 0.19869670863706648, "grad_norm": 1.1666970252990723, "learning_rate": 3.7089519379728126e-05, "loss": 0.0416, "step": 3598 }, { "epoch": 0.19875193284736029, "grad_norm": 3.8457212448120117, "learning_rate": 3.708766072688002e-05, "loss": 0.4175, "step": 3599 }, { "epoch": 0.1988071570576541, "grad_norm": 0.3067173957824707, "learning_rate": 3.708580152734902e-05, "loss": 0.0079, "step": 3600 }, { "epoch": 0.19886238126794786, "grad_norm": 1.4688912630081177, "learning_rate": 3.708394178119457e-05, "loss": 0.0302, "step": 3601 }, { "epoch": 0.19891760547824167, "grad_norm": 0.25731372833251953, "learning_rate": 3.70820814884762e-05, "loss": 0.0091, "step": 3602 }, { "epoch": 0.19897282968853544, "grad_norm": 0.05334223806858063, "learning_rate": 3.70802206492534e-05, "loss": 0.0024, "step": 3603 }, { "epoch": 0.19902805389882924, "grad_norm": 0.0887809470295906, "learning_rate": 3.7078359263585725e-05, "loss": 0.0036, "step": 3604 }, { "epoch": 0.19908327810912305, "grad_norm": 3.345489025115967, "learning_rate": 3.7076497331532716e-05, "loss": 0.1646, "step": 3605 }, { "epoch": 0.19913850231941682, "grad_norm": 0.5463494062423706, "learning_rate": 3.707463485315394e-05, "loss": 0.0154, "step": 3606 }, { "epoch": 0.19919372652971062, "grad_norm": 0.10561983287334442, "learning_rate": 3.707277182850899e-05, "loss": 0.0045, "step": 3607 }, { "epoch": 0.19924895074000443, "grad_norm": 3.108867645263672, "learning_rate": 3.707090825765746e-05, "loss": 0.7776, "step": 3608 }, { "epoch": 0.1993041749502982, "grad_norm": 2.915320873260498, "learning_rate": 3.706904414065898e-05, "loss": 0.5065, "step": 3609 }, { "epoch": 0.199359399160592, "grad_norm": 2.053164005279541, "learning_rate": 3.706717947757319e-05, "loss": 0.2581, "step": 3610 }, { "epoch": 0.1994146233708858, "grad_norm": 0.19336602091789246, "learning_rate": 3.7065314268459724e-05, "loss": 0.0075, "step": 3611 }, { "epoch": 0.19946984758117958, "grad_norm": 0.3735501170158386, "learning_rate": 3.706344851337829e-05, "loss": 0.0129, "step": 3612 }, { "epoch": 0.19952507179147339, "grad_norm": 2.262003183364868, "learning_rate": 3.7061582212388546e-05, "loss": 0.1522, "step": 3613 }, { "epoch": 0.1995802960017672, "grad_norm": 1.5654945373535156, "learning_rate": 3.705971536555022e-05, "loss": 0.0617, "step": 3614 }, { "epoch": 0.19963552021206096, "grad_norm": 1.2443888187408447, "learning_rate": 3.7057847972923034e-05, "loss": 0.0635, "step": 3615 }, { "epoch": 0.19969074442235477, "grad_norm": 3.5612947940826416, "learning_rate": 3.705598003456673e-05, "loss": 0.28, "step": 3616 }, { "epoch": 0.19974596863264854, "grad_norm": 0.059231050312519073, "learning_rate": 3.705411155054106e-05, "loss": 0.003, "step": 3617 }, { "epoch": 0.19980119284294234, "grad_norm": 1.7535210847854614, "learning_rate": 3.705224252090583e-05, "loss": 0.3412, "step": 3618 }, { "epoch": 0.19985641705323615, "grad_norm": 3.875131368637085, "learning_rate": 3.70503729457208e-05, "loss": 1.7237, "step": 3619 }, { "epoch": 0.19991164126352992, "grad_norm": 2.369875192642212, "learning_rate": 3.70485028250458e-05, "loss": 0.2914, "step": 3620 }, { "epoch": 0.19996686547382372, "grad_norm": 0.1412922590970993, "learning_rate": 3.7046632158940663e-05, "loss": 0.004, "step": 3621 }, { "epoch": 0.20002208968411753, "grad_norm": 4.322918891906738, "learning_rate": 3.7044760947465236e-05, "loss": 0.5934, "step": 3622 }, { "epoch": 0.2000773138944113, "grad_norm": 0.7707206010818481, "learning_rate": 3.704288919067938e-05, "loss": 0.0415, "step": 3623 }, { "epoch": 0.2001325381047051, "grad_norm": 0.04900537431240082, "learning_rate": 3.7041016888642984e-05, "loss": 0.0015, "step": 3624 }, { "epoch": 0.2001877623149989, "grad_norm": 0.46776485443115234, "learning_rate": 3.703914404141594e-05, "loss": 0.0175, "step": 3625 }, { "epoch": 0.20024298652529268, "grad_norm": 0.28577670454978943, "learning_rate": 3.703727064905817e-05, "loss": 0.0123, "step": 3626 }, { "epoch": 0.20029821073558648, "grad_norm": 0.022256717085838318, "learning_rate": 3.703539671162961e-05, "loss": 0.0008, "step": 3627 }, { "epoch": 0.2003534349458803, "grad_norm": 0.12026070803403854, "learning_rate": 3.703352222919021e-05, "loss": 0.0038, "step": 3628 }, { "epoch": 0.20040865915617406, "grad_norm": 1.422286868095398, "learning_rate": 3.703164720179994e-05, "loss": 0.0846, "step": 3629 }, { "epoch": 0.20046388336646787, "grad_norm": 3.408574342727661, "learning_rate": 3.702977162951879e-05, "loss": 0.1712, "step": 3630 }, { "epoch": 0.20051910757676164, "grad_norm": 0.06896265596151352, "learning_rate": 3.7027895512406765e-05, "loss": 0.0033, "step": 3631 }, { "epoch": 0.20057433178705544, "grad_norm": 2.6582226753234863, "learning_rate": 3.7026018850523885e-05, "loss": 0.1927, "step": 3632 }, { "epoch": 0.20062955599734925, "grad_norm": 0.4604801833629608, "learning_rate": 3.70241416439302e-05, "loss": 0.0123, "step": 3633 }, { "epoch": 0.20068478020764302, "grad_norm": 3.8750221729278564, "learning_rate": 3.7022263892685745e-05, "loss": 0.5658, "step": 3634 }, { "epoch": 0.20074000441793682, "grad_norm": 3.1366851329803467, "learning_rate": 3.7020385596850614e-05, "loss": 0.7928, "step": 3635 }, { "epoch": 0.20079522862823063, "grad_norm": 3.2137675285339355, "learning_rate": 3.7018506756484896e-05, "loss": 0.2723, "step": 3636 }, { "epoch": 0.2008504528385244, "grad_norm": 0.14281098544597626, "learning_rate": 3.701662737164869e-05, "loss": 0.0045, "step": 3637 }, { "epoch": 0.2009056770488182, "grad_norm": 0.3406079113483429, "learning_rate": 3.7014747442402135e-05, "loss": 0.0045, "step": 3638 }, { "epoch": 0.200960901259112, "grad_norm": 2.979271411895752, "learning_rate": 3.701286696880537e-05, "loss": 0.7215, "step": 3639 }, { "epoch": 0.20101612546940578, "grad_norm": 0.039443597197532654, "learning_rate": 3.701098595091856e-05, "loss": 0.0016, "step": 3640 }, { "epoch": 0.20107134967969958, "grad_norm": 0.7449967265129089, "learning_rate": 3.7009104388801874e-05, "loss": 0.0158, "step": 3641 }, { "epoch": 0.20112657388999336, "grad_norm": 0.04196307808160782, "learning_rate": 3.700722228251552e-05, "loss": 0.0011, "step": 3642 }, { "epoch": 0.20118179810028716, "grad_norm": 0.9341163635253906, "learning_rate": 3.7005339632119705e-05, "loss": 0.0284, "step": 3643 }, { "epoch": 0.20123702231058097, "grad_norm": 0.02016916498541832, "learning_rate": 3.700345643767467e-05, "loss": 0.001, "step": 3644 }, { "epoch": 0.20129224652087474, "grad_norm": 2.3730225563049316, "learning_rate": 3.7001572699240645e-05, "loss": 0.2111, "step": 3645 }, { "epoch": 0.20134747073116854, "grad_norm": 0.22457852959632874, "learning_rate": 3.699968841687792e-05, "loss": 0.0072, "step": 3646 }, { "epoch": 0.20140269494146235, "grad_norm": 2.4653685092926025, "learning_rate": 3.699780359064676e-05, "loss": 0.5501, "step": 3647 }, { "epoch": 0.20145791915175612, "grad_norm": 0.21428050100803375, "learning_rate": 3.699591822060747e-05, "loss": 0.0051, "step": 3648 }, { "epoch": 0.20151314336204992, "grad_norm": 0.02500256523489952, "learning_rate": 3.6994032306820385e-05, "loss": 0.0008, "step": 3649 }, { "epoch": 0.20156836757234373, "grad_norm": 0.10864947736263275, "learning_rate": 3.699214584934581e-05, "loss": 0.004, "step": 3650 }, { "epoch": 0.2016235917826375, "grad_norm": 3.738940477371216, "learning_rate": 3.6990258848244125e-05, "loss": 0.5287, "step": 3651 }, { "epoch": 0.2016788159929313, "grad_norm": 2.2442846298217773, "learning_rate": 3.698837130357569e-05, "loss": 0.2075, "step": 3652 }, { "epoch": 0.2017340402032251, "grad_norm": 0.09199479222297668, "learning_rate": 3.698648321540089e-05, "loss": 0.0031, "step": 3653 }, { "epoch": 0.20178926441351888, "grad_norm": 0.18225546181201935, "learning_rate": 3.698459458378013e-05, "loss": 0.0079, "step": 3654 }, { "epoch": 0.20184448862381268, "grad_norm": 3.65132474899292, "learning_rate": 3.698270540877384e-05, "loss": 0.4363, "step": 3655 }, { "epoch": 0.20189971283410646, "grad_norm": 3.8569886684417725, "learning_rate": 3.698081569044246e-05, "loss": 0.9366, "step": 3656 }, { "epoch": 0.20195493704440026, "grad_norm": 0.3469458818435669, "learning_rate": 3.697892542884644e-05, "loss": 0.0098, "step": 3657 }, { "epoch": 0.20201016125469407, "grad_norm": 0.3577621877193451, "learning_rate": 3.697703462404626e-05, "loss": 0.0105, "step": 3658 }, { "epoch": 0.20206538546498784, "grad_norm": 0.062419723719358444, "learning_rate": 3.697514327610241e-05, "loss": 0.0023, "step": 3659 }, { "epoch": 0.20212060967528164, "grad_norm": 1.9719346761703491, "learning_rate": 3.69732513850754e-05, "loss": 0.454, "step": 3660 }, { "epoch": 0.20217583388557545, "grad_norm": 3.8321542739868164, "learning_rate": 3.697135895102576e-05, "loss": 0.7187, "step": 3661 }, { "epoch": 0.20223105809586922, "grad_norm": 0.22433233261108398, "learning_rate": 3.696946597401403e-05, "loss": 0.0063, "step": 3662 }, { "epoch": 0.20228628230616302, "grad_norm": 0.997247576713562, "learning_rate": 3.696757245410077e-05, "loss": 0.0311, "step": 3663 }, { "epoch": 0.20234150651645683, "grad_norm": 4.200006484985352, "learning_rate": 3.6965678391346566e-05, "loss": 0.3313, "step": 3664 }, { "epoch": 0.2023967307267506, "grad_norm": 0.4403572082519531, "learning_rate": 3.696378378581201e-05, "loss": 0.0171, "step": 3665 }, { "epoch": 0.2024519549370444, "grad_norm": 3.402620315551758, "learning_rate": 3.6961888637557725e-05, "loss": 1.3096, "step": 3666 }, { "epoch": 0.2025071791473382, "grad_norm": 2.4687530994415283, "learning_rate": 3.695999294664432e-05, "loss": 0.1587, "step": 3667 }, { "epoch": 0.20256240335763198, "grad_norm": 1.4622594118118286, "learning_rate": 3.6958096713132465e-05, "loss": 0.4051, "step": 3668 }, { "epoch": 0.20261762756792578, "grad_norm": 0.08442669361829758, "learning_rate": 3.6956199937082817e-05, "loss": 0.0025, "step": 3669 }, { "epoch": 0.20267285177821956, "grad_norm": 0.13229624927043915, "learning_rate": 3.695430261855607e-05, "loss": 0.0051, "step": 3670 }, { "epoch": 0.20272807598851336, "grad_norm": 2.2215845584869385, "learning_rate": 3.6952404757612905e-05, "loss": 0.1229, "step": 3671 }, { "epoch": 0.20278330019880716, "grad_norm": 4.958470821380615, "learning_rate": 3.695050635431405e-05, "loss": 0.8157, "step": 3672 }, { "epoch": 0.20283852440910094, "grad_norm": 0.27891018986701965, "learning_rate": 3.6948607408720244e-05, "loss": 0.0052, "step": 3673 }, { "epoch": 0.20289374861939474, "grad_norm": 2.901477575302124, "learning_rate": 3.6946707920892244e-05, "loss": 0.3456, "step": 3674 }, { "epoch": 0.20294897282968855, "grad_norm": 1.542426586151123, "learning_rate": 3.69448078908908e-05, "loss": 0.0263, "step": 3675 }, { "epoch": 0.20300419703998232, "grad_norm": 0.13758575916290283, "learning_rate": 3.694290731877671e-05, "loss": 0.0037, "step": 3676 }, { "epoch": 0.20305942125027612, "grad_norm": 0.19643965363502502, "learning_rate": 3.69410062046108e-05, "loss": 0.0049, "step": 3677 }, { "epoch": 0.20311464546056993, "grad_norm": 0.1173163577914238, "learning_rate": 3.693910454845385e-05, "loss": 0.0028, "step": 3678 }, { "epoch": 0.2031698696708637, "grad_norm": 0.8709065914154053, "learning_rate": 3.693720235036674e-05, "loss": 0.0226, "step": 3679 }, { "epoch": 0.2032250938811575, "grad_norm": 2.7984778881073, "learning_rate": 3.69352996104103e-05, "loss": 0.2121, "step": 3680 }, { "epoch": 0.20328031809145128, "grad_norm": 6.725295543670654, "learning_rate": 3.693339632864541e-05, "loss": 1.6504, "step": 3681 }, { "epoch": 0.20333554230174508, "grad_norm": 2.9630541801452637, "learning_rate": 3.6931492505132965e-05, "loss": 0.1763, "step": 3682 }, { "epoch": 0.20339076651203888, "grad_norm": 2.6641693115234375, "learning_rate": 3.6929588139933875e-05, "loss": 0.2268, "step": 3683 }, { "epoch": 0.20344599072233266, "grad_norm": 1.2156161069869995, "learning_rate": 3.692768323310907e-05, "loss": 0.1082, "step": 3684 }, { "epoch": 0.20350121493262646, "grad_norm": 0.9716283082962036, "learning_rate": 3.692577778471948e-05, "loss": 0.0148, "step": 3685 }, { "epoch": 0.20355643914292026, "grad_norm": 3.064297914505005, "learning_rate": 3.692387179482608e-05, "loss": 0.3367, "step": 3686 }, { "epoch": 0.20361166335321404, "grad_norm": 2.1494715213775635, "learning_rate": 3.692196526348983e-05, "loss": 0.0721, "step": 3687 }, { "epoch": 0.20366688756350784, "grad_norm": 0.10619290173053741, "learning_rate": 3.6920058190771746e-05, "loss": 0.0031, "step": 3688 }, { "epoch": 0.20372211177380165, "grad_norm": 1.7007763385772705, "learning_rate": 3.6918150576732826e-05, "loss": 0.0133, "step": 3689 }, { "epoch": 0.20377733598409542, "grad_norm": 4.366104602813721, "learning_rate": 3.6916242421434106e-05, "loss": 1.3869, "step": 3690 }, { "epoch": 0.20383256019438922, "grad_norm": 3.341451644897461, "learning_rate": 3.6914333724936635e-05, "loss": 0.1245, "step": 3691 }, { "epoch": 0.20388778440468303, "grad_norm": 1.9074757099151611, "learning_rate": 3.691242448730148e-05, "loss": 0.061, "step": 3692 }, { "epoch": 0.2039430086149768, "grad_norm": 0.26059436798095703, "learning_rate": 3.6910514708589705e-05, "loss": 0.0035, "step": 3693 }, { "epoch": 0.2039982328252706, "grad_norm": 3.9768710136413574, "learning_rate": 3.690860438886243e-05, "loss": 0.2181, "step": 3694 }, { "epoch": 0.20405345703556438, "grad_norm": 5.788622856140137, "learning_rate": 3.690669352818076e-05, "loss": 0.699, "step": 3695 }, { "epoch": 0.20410868124585818, "grad_norm": 0.41241663694381714, "learning_rate": 3.690478212660584e-05, "loss": 0.0079, "step": 3696 }, { "epoch": 0.20416390545615198, "grad_norm": 1.414309024810791, "learning_rate": 3.6902870184198814e-05, "loss": 0.1141, "step": 3697 }, { "epoch": 0.20421912966644576, "grad_norm": 0.10932440310716629, "learning_rate": 3.690095770102084e-05, "loss": 0.0021, "step": 3698 }, { "epoch": 0.20427435387673956, "grad_norm": 1.5609902143478394, "learning_rate": 3.689904467713312e-05, "loss": 0.1343, "step": 3699 }, { "epoch": 0.20432957808703336, "grad_norm": 2.055527448654175, "learning_rate": 3.6897131112596856e-05, "loss": 0.2145, "step": 3700 }, { "epoch": 0.20438480229732714, "grad_norm": 0.20487502217292786, "learning_rate": 3.689521700747326e-05, "loss": 0.0063, "step": 3701 }, { "epoch": 0.20444002650762094, "grad_norm": 0.04541262239217758, "learning_rate": 3.6893302361823574e-05, "loss": 0.0014, "step": 3702 }, { "epoch": 0.20449525071791474, "grad_norm": 2.736778497695923, "learning_rate": 3.689138717570905e-05, "loss": 0.1746, "step": 3703 }, { "epoch": 0.20455047492820852, "grad_norm": 3.6948459148406982, "learning_rate": 3.688947144919097e-05, "loss": 0.702, "step": 3704 }, { "epoch": 0.20460569913850232, "grad_norm": 3.3396196365356445, "learning_rate": 3.688755518233061e-05, "loss": 0.391, "step": 3705 }, { "epoch": 0.20466092334879613, "grad_norm": 0.3161926567554474, "learning_rate": 3.688563837518928e-05, "loss": 0.0087, "step": 3706 }, { "epoch": 0.2047161475590899, "grad_norm": 0.6580511927604675, "learning_rate": 3.688372102782831e-05, "loss": 0.0199, "step": 3707 }, { "epoch": 0.2047713717693837, "grad_norm": 3.964535713195801, "learning_rate": 3.688180314030904e-05, "loss": 0.9011, "step": 3708 }, { "epoch": 0.20482659597967748, "grad_norm": 2.6033174991607666, "learning_rate": 3.6879884712692826e-05, "loss": 0.1407, "step": 3709 }, { "epoch": 0.20488182018997128, "grad_norm": 0.08255942165851593, "learning_rate": 3.6877965745041045e-05, "loss": 0.002, "step": 3710 }, { "epoch": 0.20493704440026508, "grad_norm": 0.7972579002380371, "learning_rate": 3.687604623741509e-05, "loss": 0.0628, "step": 3711 }, { "epoch": 0.20499226861055886, "grad_norm": 1.0769473314285278, "learning_rate": 3.687412618987638e-05, "loss": 0.1587, "step": 3712 }, { "epoch": 0.20504749282085266, "grad_norm": 1.8417507410049438, "learning_rate": 3.687220560248632e-05, "loss": 0.0772, "step": 3713 }, { "epoch": 0.20510271703114646, "grad_norm": 0.026415884494781494, "learning_rate": 3.687028447530637e-05, "loss": 0.0009, "step": 3714 }, { "epoch": 0.20515794124144024, "grad_norm": 1.425650954246521, "learning_rate": 3.6868362808398e-05, "loss": 0.0701, "step": 3715 }, { "epoch": 0.20521316545173404, "grad_norm": 0.4389306306838989, "learning_rate": 3.686644060182269e-05, "loss": 0.021, "step": 3716 }, { "epoch": 0.20526838966202784, "grad_norm": 2.856846809387207, "learning_rate": 3.686451785564192e-05, "loss": 0.4321, "step": 3717 }, { "epoch": 0.20532361387232162, "grad_norm": 0.12064506113529205, "learning_rate": 3.6862594569917206e-05, "loss": 0.0035, "step": 3718 }, { "epoch": 0.20537883808261542, "grad_norm": 0.4169185757637024, "learning_rate": 3.6860670744710096e-05, "loss": 0.0056, "step": 3719 }, { "epoch": 0.20543406229290923, "grad_norm": 2.604417562484741, "learning_rate": 3.685874638008213e-05, "loss": 0.7426, "step": 3720 }, { "epoch": 0.205489286503203, "grad_norm": 2.701936960220337, "learning_rate": 3.6856821476094865e-05, "loss": 0.2965, "step": 3721 }, { "epoch": 0.2055445107134968, "grad_norm": 0.05673924833536148, "learning_rate": 3.685489603280989e-05, "loss": 0.0013, "step": 3722 }, { "epoch": 0.20559973492379058, "grad_norm": 0.5655949115753174, "learning_rate": 3.685297005028881e-05, "loss": 0.0208, "step": 3723 }, { "epoch": 0.20565495913408438, "grad_norm": 0.5989162921905518, "learning_rate": 3.685104352859324e-05, "loss": 0.0234, "step": 3724 }, { "epoch": 0.20571018334437818, "grad_norm": 2.7321457862854004, "learning_rate": 3.684911646778482e-05, "loss": 0.6516, "step": 3725 }, { "epoch": 0.20576540755467196, "grad_norm": 0.010014065541327, "learning_rate": 3.684718886792519e-05, "loss": 0.0004, "step": 3726 }, { "epoch": 0.20582063176496576, "grad_norm": 6.024170398712158, "learning_rate": 3.684526072907603e-05, "loss": 0.8139, "step": 3727 }, { "epoch": 0.20587585597525956, "grad_norm": 4.279236316680908, "learning_rate": 3.684333205129902e-05, "loss": 0.99, "step": 3728 }, { "epoch": 0.20593108018555334, "grad_norm": 0.11338263005018234, "learning_rate": 3.684140283465587e-05, "loss": 0.0051, "step": 3729 }, { "epoch": 0.20598630439584714, "grad_norm": 5.057807922363281, "learning_rate": 3.683947307920829e-05, "loss": 1.132, "step": 3730 }, { "epoch": 0.20604152860614094, "grad_norm": 2.8284285068511963, "learning_rate": 3.6837542785018036e-05, "loss": 0.8271, "step": 3731 }, { "epoch": 0.20609675281643472, "grad_norm": 3.7545857429504395, "learning_rate": 3.6835611952146856e-05, "loss": 0.3827, "step": 3732 }, { "epoch": 0.20615197702672852, "grad_norm": 2.254088878631592, "learning_rate": 3.683368058065651e-05, "loss": 0.4627, "step": 3733 }, { "epoch": 0.2062072012370223, "grad_norm": 1.7799278497695923, "learning_rate": 3.683174867060881e-05, "loss": 0.3435, "step": 3734 }, { "epoch": 0.2062624254473161, "grad_norm": 0.027857545763254166, "learning_rate": 3.682981622206555e-05, "loss": 0.001, "step": 3735 }, { "epoch": 0.2063176496576099, "grad_norm": 5.737943172454834, "learning_rate": 3.6827883235088554e-05, "loss": 1.3993, "step": 3736 }, { "epoch": 0.20637287386790368, "grad_norm": 3.3700740337371826, "learning_rate": 3.682594970973966e-05, "loss": 0.3551, "step": 3737 }, { "epoch": 0.20642809807819748, "grad_norm": 0.035948652774095535, "learning_rate": 3.682401564608074e-05, "loss": 0.0011, "step": 3738 }, { "epoch": 0.20648332228849128, "grad_norm": 2.4027886390686035, "learning_rate": 3.6822081044173665e-05, "loss": 0.197, "step": 3739 }, { "epoch": 0.20653854649878506, "grad_norm": 3.786212921142578, "learning_rate": 3.6820145904080325e-05, "loss": 0.1143, "step": 3740 }, { "epoch": 0.20659377070907886, "grad_norm": 1.4295185804367065, "learning_rate": 3.681821022586263e-05, "loss": 0.2505, "step": 3741 }, { "epoch": 0.20664899491937266, "grad_norm": 0.028351131826639175, "learning_rate": 3.6816274009582515e-05, "loss": 0.001, "step": 3742 }, { "epoch": 0.20670421912966644, "grad_norm": 0.016039403155446053, "learning_rate": 3.681433725530192e-05, "loss": 0.0005, "step": 3743 }, { "epoch": 0.20675944333996024, "grad_norm": 0.3000010848045349, "learning_rate": 3.68123999630828e-05, "loss": 0.0077, "step": 3744 }, { "epoch": 0.20681466755025404, "grad_norm": 2.1261136531829834, "learning_rate": 3.681046213298715e-05, "loss": 0.2795, "step": 3745 }, { "epoch": 0.20686989176054782, "grad_norm": 0.4596744477748871, "learning_rate": 3.680852376507696e-05, "loss": 0.01, "step": 3746 }, { "epoch": 0.20692511597084162, "grad_norm": 0.22112499177455902, "learning_rate": 3.680658485941424e-05, "loss": 0.0089, "step": 3747 }, { "epoch": 0.2069803401811354, "grad_norm": 2.6758687496185303, "learning_rate": 3.680464541606103e-05, "loss": 0.1838, "step": 3748 }, { "epoch": 0.2070355643914292, "grad_norm": 1.5831563472747803, "learning_rate": 3.680270543507937e-05, "loss": 0.1279, "step": 3749 }, { "epoch": 0.207090788601723, "grad_norm": 1.923862099647522, "learning_rate": 3.6800764916531326e-05, "loss": 0.0734, "step": 3750 }, { "epoch": 0.20714601281201678, "grad_norm": 2.3277642726898193, "learning_rate": 3.679882386047898e-05, "loss": 0.2096, "step": 3751 }, { "epoch": 0.20720123702231058, "grad_norm": 2.1354150772094727, "learning_rate": 3.679688226698444e-05, "loss": 0.3707, "step": 3752 }, { "epoch": 0.20725646123260438, "grad_norm": 0.09370194375514984, "learning_rate": 3.679494013610981e-05, "loss": 0.0039, "step": 3753 }, { "epoch": 0.20731168544289816, "grad_norm": 1.3751152753829956, "learning_rate": 3.679299746791724e-05, "loss": 0.1316, "step": 3754 }, { "epoch": 0.20736690965319196, "grad_norm": 1.121496558189392, "learning_rate": 3.679105426246887e-05, "loss": 0.0239, "step": 3755 }, { "epoch": 0.20742213386348576, "grad_norm": 0.01251824852079153, "learning_rate": 3.6789110519826875e-05, "loss": 0.0004, "step": 3756 }, { "epoch": 0.20747735807377954, "grad_norm": 1.3168355226516724, "learning_rate": 3.6787166240053426e-05, "loss": 0.1767, "step": 3757 }, { "epoch": 0.20753258228407334, "grad_norm": 0.12599793076515198, "learning_rate": 3.6785221423210755e-05, "loss": 0.0038, "step": 3758 }, { "epoch": 0.20758780649436714, "grad_norm": 0.048490896821022034, "learning_rate": 3.678327606936105e-05, "loss": 0.0017, "step": 3759 }, { "epoch": 0.20764303070466092, "grad_norm": 0.1737765222787857, "learning_rate": 3.6781330178566575e-05, "loss": 0.0057, "step": 3760 }, { "epoch": 0.20769825491495472, "grad_norm": 3.1585896015167236, "learning_rate": 3.677938375088957e-05, "loss": 0.9023, "step": 3761 }, { "epoch": 0.2077534791252485, "grad_norm": 0.871593177318573, "learning_rate": 3.677743678639231e-05, "loss": 0.0286, "step": 3762 }, { "epoch": 0.2078087033355423, "grad_norm": 0.06704912334680557, "learning_rate": 3.677548928513708e-05, "loss": 0.0022, "step": 3763 }, { "epoch": 0.2078639275458361, "grad_norm": 5.054290294647217, "learning_rate": 3.67735412471862e-05, "loss": 1.0467, "step": 3764 }, { "epoch": 0.20791915175612988, "grad_norm": 3.3876466751098633, "learning_rate": 3.677159267260197e-05, "loss": 0.7413, "step": 3765 }, { "epoch": 0.20797437596642368, "grad_norm": 2.925941228866577, "learning_rate": 3.6769643561446755e-05, "loss": 0.184, "step": 3766 }, { "epoch": 0.20802960017671748, "grad_norm": 0.10346682369709015, "learning_rate": 3.6767693913782895e-05, "loss": 0.0044, "step": 3767 }, { "epoch": 0.20808482438701126, "grad_norm": 0.16144979000091553, "learning_rate": 3.6765743729672775e-05, "loss": 0.0062, "step": 3768 }, { "epoch": 0.20814004859730506, "grad_norm": 0.44612887501716614, "learning_rate": 3.6763793009178784e-05, "loss": 0.0051, "step": 3769 }, { "epoch": 0.20819527280759886, "grad_norm": 3.4801979064941406, "learning_rate": 3.6761841752363324e-05, "loss": 0.946, "step": 3770 }, { "epoch": 0.20825049701789264, "grad_norm": 0.026348542422056198, "learning_rate": 3.675988995928883e-05, "loss": 0.0008, "step": 3771 }, { "epoch": 0.20830572122818644, "grad_norm": 2.618417501449585, "learning_rate": 3.675793763001774e-05, "loss": 0.1867, "step": 3772 }, { "epoch": 0.20836094543848022, "grad_norm": 0.4399404525756836, "learning_rate": 3.675598476461253e-05, "loss": 0.0124, "step": 3773 }, { "epoch": 0.20841616964877402, "grad_norm": 0.12873001396656036, "learning_rate": 3.6754031363135654e-05, "loss": 0.0034, "step": 3774 }, { "epoch": 0.20847139385906782, "grad_norm": 2.6081533432006836, "learning_rate": 3.675207742564962e-05, "loss": 0.5045, "step": 3775 }, { "epoch": 0.2085266180693616, "grad_norm": 3.224787712097168, "learning_rate": 3.675012295221694e-05, "loss": 0.1444, "step": 3776 }, { "epoch": 0.2085818422796554, "grad_norm": 0.010619842447340488, "learning_rate": 3.674816794290014e-05, "loss": 0.0003, "step": 3777 }, { "epoch": 0.2086370664899492, "grad_norm": 2.792104959487915, "learning_rate": 3.674621239776177e-05, "loss": 0.201, "step": 3778 }, { "epoch": 0.20869229070024298, "grad_norm": 1.8929009437561035, "learning_rate": 3.6744256316864386e-05, "loss": 0.169, "step": 3779 }, { "epoch": 0.20874751491053678, "grad_norm": 1.2825838327407837, "learning_rate": 3.674229970027058e-05, "loss": 0.0215, "step": 3780 }, { "epoch": 0.20880273912083058, "grad_norm": 0.5448728799819946, "learning_rate": 3.674034254804294e-05, "loss": 0.0205, "step": 3781 }, { "epoch": 0.20885796333112436, "grad_norm": 0.7073938846588135, "learning_rate": 3.673838486024408e-05, "loss": 0.0222, "step": 3782 }, { "epoch": 0.20891318754141816, "grad_norm": 3.769559860229492, "learning_rate": 3.673642663693664e-05, "loss": 0.3376, "step": 3783 }, { "epoch": 0.20896841175171196, "grad_norm": 0.01910623535513878, "learning_rate": 3.673446787818326e-05, "loss": 0.0006, "step": 3784 }, { "epoch": 0.20902363596200574, "grad_norm": 0.7710670828819275, "learning_rate": 3.673250858404663e-05, "loss": 0.0185, "step": 3785 }, { "epoch": 0.20907886017229954, "grad_norm": 1.7553327083587646, "learning_rate": 3.67305487545894e-05, "loss": 0.0544, "step": 3786 }, { "epoch": 0.20913408438259332, "grad_norm": 2.98846435546875, "learning_rate": 3.672858838987428e-05, "loss": 0.2671, "step": 3787 }, { "epoch": 0.20918930859288712, "grad_norm": 1.0085656642913818, "learning_rate": 3.672662748996401e-05, "loss": 0.0477, "step": 3788 }, { "epoch": 0.20924453280318092, "grad_norm": 2.259432315826416, "learning_rate": 3.6724666054921296e-05, "loss": 0.6566, "step": 3789 }, { "epoch": 0.2092997570134747, "grad_norm": 0.030202142894268036, "learning_rate": 3.672270408480891e-05, "loss": 0.0011, "step": 3790 }, { "epoch": 0.2093549812237685, "grad_norm": 3.4792726039886475, "learning_rate": 3.6720741579689604e-05, "loss": 0.3045, "step": 3791 }, { "epoch": 0.2094102054340623, "grad_norm": 2.6848862171173096, "learning_rate": 3.6718778539626176e-05, "loss": 0.4669, "step": 3792 }, { "epoch": 0.20946542964435608, "grad_norm": 3.481339454650879, "learning_rate": 3.671681496468143e-05, "loss": 0.9415, "step": 3793 }, { "epoch": 0.20952065385464988, "grad_norm": 3.3899834156036377, "learning_rate": 3.671485085491817e-05, "loss": 0.6249, "step": 3794 }, { "epoch": 0.20957587806494368, "grad_norm": 0.13007313013076782, "learning_rate": 3.6712886210399264e-05, "loss": 0.0049, "step": 3795 }, { "epoch": 0.20963110227523746, "grad_norm": 0.30059006810188293, "learning_rate": 3.6710921031187535e-05, "loss": 0.0052, "step": 3796 }, { "epoch": 0.20968632648553126, "grad_norm": 4.047455310821533, "learning_rate": 3.670895531734588e-05, "loss": 0.1759, "step": 3797 }, { "epoch": 0.20974155069582506, "grad_norm": 1.8867506980895996, "learning_rate": 3.670698906893717e-05, "loss": 0.1508, "step": 3798 }, { "epoch": 0.20979677490611884, "grad_norm": 4.699065208435059, "learning_rate": 3.670502228602431e-05, "loss": 0.6424, "step": 3799 }, { "epoch": 0.20985199911641264, "grad_norm": 6.360843181610107, "learning_rate": 3.6703054968670245e-05, "loss": 0.6405, "step": 3800 }, { "epoch": 0.20990722332670642, "grad_norm": 2.6779818534851074, "learning_rate": 3.670108711693789e-05, "loss": 0.7224, "step": 3801 }, { "epoch": 0.20996244753700022, "grad_norm": 4.180028915405273, "learning_rate": 3.669911873089022e-05, "loss": 0.649, "step": 3802 }, { "epoch": 0.21001767174729402, "grad_norm": 3.750514268875122, "learning_rate": 3.6697149810590194e-05, "loss": 0.9678, "step": 3803 }, { "epoch": 0.2100728959575878, "grad_norm": 2.575455904006958, "learning_rate": 3.669518035610081e-05, "loss": 0.3299, "step": 3804 }, { "epoch": 0.2101281201678816, "grad_norm": 0.2363847941160202, "learning_rate": 3.669321036748508e-05, "loss": 0.0058, "step": 3805 }, { "epoch": 0.2101833443781754, "grad_norm": 1.1231015920639038, "learning_rate": 3.669123984480603e-05, "loss": 0.0277, "step": 3806 }, { "epoch": 0.21023856858846918, "grad_norm": 5.086604595184326, "learning_rate": 3.668926878812669e-05, "loss": 1.4457, "step": 3807 }, { "epoch": 0.21029379279876298, "grad_norm": 3.7343313694000244, "learning_rate": 3.6687297197510135e-05, "loss": 0.7732, "step": 3808 }, { "epoch": 0.21034901700905678, "grad_norm": 0.2575530409812927, "learning_rate": 3.668532507301944e-05, "loss": 0.005, "step": 3809 }, { "epoch": 0.21040424121935056, "grad_norm": 2.427598714828491, "learning_rate": 3.668335241471769e-05, "loss": 0.2473, "step": 3810 }, { "epoch": 0.21045946542964436, "grad_norm": 0.4165785014629364, "learning_rate": 3.668137922266801e-05, "loss": 0.0171, "step": 3811 }, { "epoch": 0.21051468963993814, "grad_norm": 1.5366023778915405, "learning_rate": 3.66794054969335e-05, "loss": 0.2371, "step": 3812 }, { "epoch": 0.21056991385023194, "grad_norm": 0.45892781019210815, "learning_rate": 3.667743123757734e-05, "loss": 0.0138, "step": 3813 }, { "epoch": 0.21062513806052574, "grad_norm": 2.6570804119110107, "learning_rate": 3.6675456444662676e-05, "loss": 0.6163, "step": 3814 }, { "epoch": 0.21068036227081952, "grad_norm": 3.830825090408325, "learning_rate": 3.667348111825268e-05, "loss": 0.2373, "step": 3815 }, { "epoch": 0.21073558648111332, "grad_norm": 0.5235438942909241, "learning_rate": 3.667150525841056e-05, "loss": 0.0205, "step": 3816 }, { "epoch": 0.21079081069140712, "grad_norm": 3.4333043098449707, "learning_rate": 3.666952886519952e-05, "loss": 0.8381, "step": 3817 }, { "epoch": 0.2108460349017009, "grad_norm": 2.7772748470306396, "learning_rate": 3.66675519386828e-05, "loss": 0.967, "step": 3818 }, { "epoch": 0.2109012591119947, "grad_norm": 2.798391342163086, "learning_rate": 3.666557447892364e-05, "loss": 0.2493, "step": 3819 }, { "epoch": 0.2109564833222885, "grad_norm": 3.184398651123047, "learning_rate": 3.666359648598532e-05, "loss": 0.2681, "step": 3820 }, { "epoch": 0.21101170753258228, "grad_norm": 2.220677137374878, "learning_rate": 3.66616179599311e-05, "loss": 0.2153, "step": 3821 }, { "epoch": 0.21106693174287608, "grad_norm": 2.9228906631469727, "learning_rate": 3.6659638900824284e-05, "loss": 0.4151, "step": 3822 }, { "epoch": 0.21112215595316988, "grad_norm": 3.6068694591522217, "learning_rate": 3.6657659308728196e-05, "loss": 0.7821, "step": 3823 }, { "epoch": 0.21117738016346366, "grad_norm": 0.07696476578712463, "learning_rate": 3.6655679183706164e-05, "loss": 0.0024, "step": 3824 }, { "epoch": 0.21123260437375746, "grad_norm": 0.5818743109703064, "learning_rate": 3.665369852582154e-05, "loss": 0.0174, "step": 3825 }, { "epoch": 0.21128782858405123, "grad_norm": 2.7681081295013428, "learning_rate": 3.665171733513768e-05, "loss": 0.4388, "step": 3826 }, { "epoch": 0.21134305279434504, "grad_norm": 0.05535002052783966, "learning_rate": 3.6649735611717984e-05, "loss": 0.0021, "step": 3827 }, { "epoch": 0.21139827700463884, "grad_norm": 4.44618558883667, "learning_rate": 3.664775335562585e-05, "loss": 0.8498, "step": 3828 }, { "epoch": 0.21145350121493262, "grad_norm": 5.154018878936768, "learning_rate": 3.6645770566924686e-05, "loss": 1.1964, "step": 3829 }, { "epoch": 0.21150872542522642, "grad_norm": 2.125979423522949, "learning_rate": 3.6643787245677936e-05, "loss": 0.3188, "step": 3830 }, { "epoch": 0.21156394963552022, "grad_norm": 3.0192387104034424, "learning_rate": 3.664180339194905e-05, "loss": 0.8923, "step": 3831 }, { "epoch": 0.211619173845814, "grad_norm": 0.17213179171085358, "learning_rate": 3.663981900580149e-05, "loss": 0.0045, "step": 3832 }, { "epoch": 0.2116743980561078, "grad_norm": 1.3504353761672974, "learning_rate": 3.6637834087298756e-05, "loss": 0.206, "step": 3833 }, { "epoch": 0.2117296222664016, "grad_norm": 0.13586920499801636, "learning_rate": 3.663584863650434e-05, "loss": 0.0059, "step": 3834 }, { "epoch": 0.21178484647669538, "grad_norm": 2.3022873401641846, "learning_rate": 3.663386265348177e-05, "loss": 0.5542, "step": 3835 }, { "epoch": 0.21184007068698918, "grad_norm": 2.080371379852295, "learning_rate": 3.663187613829457e-05, "loss": 0.6933, "step": 3836 }, { "epoch": 0.21189529489728298, "grad_norm": 2.5125622749328613, "learning_rate": 3.6629889091006314e-05, "loss": 0.7872, "step": 3837 }, { "epoch": 0.21195051910757676, "grad_norm": 0.1095917820930481, "learning_rate": 3.662790151168057e-05, "loss": 0.0036, "step": 3838 }, { "epoch": 0.21200574331787056, "grad_norm": 2.578641414642334, "learning_rate": 3.66259134003809e-05, "loss": 0.3716, "step": 3839 }, { "epoch": 0.21206096752816433, "grad_norm": 3.305480480194092, "learning_rate": 3.662392475717093e-05, "loss": 0.3113, "step": 3840 }, { "epoch": 0.21211619173845814, "grad_norm": 0.07295430451631546, "learning_rate": 3.662193558211429e-05, "loss": 0.0027, "step": 3841 }, { "epoch": 0.21217141594875194, "grad_norm": 0.13815230131149292, "learning_rate": 3.6619945875274606e-05, "loss": 0.004, "step": 3842 }, { "epoch": 0.21222664015904572, "grad_norm": 3.5198464393615723, "learning_rate": 3.6617955636715545e-05, "loss": 0.6064, "step": 3843 }, { "epoch": 0.21228186436933952, "grad_norm": 1.46337890625, "learning_rate": 3.6615964866500764e-05, "loss": 0.1815, "step": 3844 }, { "epoch": 0.21233708857963332, "grad_norm": 1.6960779428482056, "learning_rate": 3.6613973564693974e-05, "loss": 0.0699, "step": 3845 }, { "epoch": 0.2123923127899271, "grad_norm": 0.28986695408821106, "learning_rate": 3.6611981731358864e-05, "loss": 0.0117, "step": 3846 }, { "epoch": 0.2124475370002209, "grad_norm": 0.0383932963013649, "learning_rate": 3.6609989366559166e-05, "loss": 0.0015, "step": 3847 }, { "epoch": 0.2125027612105147, "grad_norm": 0.06879764050245285, "learning_rate": 3.6607996470358624e-05, "loss": 0.0017, "step": 3848 }, { "epoch": 0.21255798542080848, "grad_norm": 0.7092316746711731, "learning_rate": 3.6606003042820995e-05, "loss": 0.0379, "step": 3849 }, { "epoch": 0.21261320963110228, "grad_norm": 2.81325626373291, "learning_rate": 3.660400908401006e-05, "loss": 0.5636, "step": 3850 }, { "epoch": 0.21266843384139608, "grad_norm": 0.028612833470106125, "learning_rate": 3.660201459398959e-05, "loss": 0.0013, "step": 3851 }, { "epoch": 0.21272365805168986, "grad_norm": 5.237816333770752, "learning_rate": 3.660001957282341e-05, "loss": 1.0848, "step": 3852 }, { "epoch": 0.21277888226198366, "grad_norm": 0.2587968707084656, "learning_rate": 3.6598024020575355e-05, "loss": 0.0134, "step": 3853 }, { "epoch": 0.21283410647227743, "grad_norm": 3.292602062225342, "learning_rate": 3.6596027937309265e-05, "loss": 0.3784, "step": 3854 }, { "epoch": 0.21288933068257124, "grad_norm": 0.18552960455417633, "learning_rate": 3.6594031323088975e-05, "loss": 0.0058, "step": 3855 }, { "epoch": 0.21294455489286504, "grad_norm": 3.0188372135162354, "learning_rate": 3.65920341779784e-05, "loss": 0.2082, "step": 3856 }, { "epoch": 0.21299977910315882, "grad_norm": 0.009024449624121189, "learning_rate": 3.659003650204141e-05, "loss": 0.0003, "step": 3857 }, { "epoch": 0.21305500331345262, "grad_norm": 0.708537757396698, "learning_rate": 3.6588038295341917e-05, "loss": 0.0192, "step": 3858 }, { "epoch": 0.21311022752374642, "grad_norm": 0.02220042422413826, "learning_rate": 3.658603955794386e-05, "loss": 0.0007, "step": 3859 }, { "epoch": 0.2131654517340402, "grad_norm": 0.2171391099691391, "learning_rate": 3.658404028991118e-05, "loss": 0.0082, "step": 3860 }, { "epoch": 0.213220675944334, "grad_norm": 1.8124409914016724, "learning_rate": 3.658204049130783e-05, "loss": 0.1854, "step": 3861 }, { "epoch": 0.2132759001546278, "grad_norm": 0.40883198380470276, "learning_rate": 3.658004016219781e-05, "loss": 0.0113, "step": 3862 }, { "epoch": 0.21333112436492158, "grad_norm": 0.7246799468994141, "learning_rate": 3.65780393026451e-05, "loss": 0.1217, "step": 3863 }, { "epoch": 0.21338634857521538, "grad_norm": 4.933159351348877, "learning_rate": 3.6576037912713716e-05, "loss": 0.4561, "step": 3864 }, { "epoch": 0.21344157278550915, "grad_norm": 3.1735358238220215, "learning_rate": 3.6574035992467686e-05, "loss": 0.4395, "step": 3865 }, { "epoch": 0.21349679699580296, "grad_norm": 0.03641851246356964, "learning_rate": 3.657203354197107e-05, "loss": 0.0017, "step": 3866 }, { "epoch": 0.21355202120609676, "grad_norm": 3.5074479579925537, "learning_rate": 3.657003056128791e-05, "loss": 1.3867, "step": 3867 }, { "epoch": 0.21360724541639053, "grad_norm": 3.6373486518859863, "learning_rate": 3.65680270504823e-05, "loss": 0.2871, "step": 3868 }, { "epoch": 0.21366246962668434, "grad_norm": 3.845611095428467, "learning_rate": 3.656602300961835e-05, "loss": 0.2788, "step": 3869 }, { "epoch": 0.21371769383697814, "grad_norm": 0.2427813857793808, "learning_rate": 3.656401843876015e-05, "loss": 0.0035, "step": 3870 }, { "epoch": 0.21377291804727191, "grad_norm": 1.7793000936508179, "learning_rate": 3.6562013337971854e-05, "loss": 0.1757, "step": 3871 }, { "epoch": 0.21382814225756572, "grad_norm": 0.168949693441391, "learning_rate": 3.6560007707317595e-05, "loss": 0.0056, "step": 3872 }, { "epoch": 0.21388336646785952, "grad_norm": 0.5105208158493042, "learning_rate": 3.655800154686155e-05, "loss": 0.0236, "step": 3873 }, { "epoch": 0.2139385906781533, "grad_norm": 0.37442973256111145, "learning_rate": 3.65559948566679e-05, "loss": 0.0137, "step": 3874 }, { "epoch": 0.2139938148884471, "grad_norm": 3.3567628860473633, "learning_rate": 3.655398763680083e-05, "loss": 1.2756, "step": 3875 }, { "epoch": 0.2140490390987409, "grad_norm": 0.05679793283343315, "learning_rate": 3.655197988732457e-05, "loss": 0.0018, "step": 3876 }, { "epoch": 0.21410426330903468, "grad_norm": 2.7106876373291016, "learning_rate": 3.654997160830336e-05, "loss": 0.3882, "step": 3877 }, { "epoch": 0.21415948751932848, "grad_norm": 0.10670747607946396, "learning_rate": 3.654796279980145e-05, "loss": 0.0043, "step": 3878 }, { "epoch": 0.21421471172962225, "grad_norm": 1.9396369457244873, "learning_rate": 3.654595346188308e-05, "loss": 0.2053, "step": 3879 }, { "epoch": 0.21426993593991606, "grad_norm": 2.7726340293884277, "learning_rate": 3.654394359461257e-05, "loss": 0.6988, "step": 3880 }, { "epoch": 0.21432516015020986, "grad_norm": 1.4843670129776, "learning_rate": 3.654193319805419e-05, "loss": 0.0653, "step": 3881 }, { "epoch": 0.21438038436050363, "grad_norm": 7.247557163238525, "learning_rate": 3.653992227227229e-05, "loss": 0.8979, "step": 3882 }, { "epoch": 0.21443560857079744, "grad_norm": 0.1595117747783661, "learning_rate": 3.653791081733118e-05, "loss": 0.004, "step": 3883 }, { "epoch": 0.21449083278109124, "grad_norm": 1.4770561456680298, "learning_rate": 3.653589883329523e-05, "loss": 0.0146, "step": 3884 }, { "epoch": 0.21454605699138501, "grad_norm": 4.37962007522583, "learning_rate": 3.6533886320228796e-05, "loss": 0.4935, "step": 3885 }, { "epoch": 0.21460128120167882, "grad_norm": 2.620699167251587, "learning_rate": 3.653187327819626e-05, "loss": 0.2754, "step": 3886 }, { "epoch": 0.21465650541197262, "grad_norm": 3.3150739669799805, "learning_rate": 3.652985970726205e-05, "loss": 0.1942, "step": 3887 }, { "epoch": 0.2147117296222664, "grad_norm": 2.2466180324554443, "learning_rate": 3.652784560749056e-05, "loss": 0.4162, "step": 3888 }, { "epoch": 0.2147669538325602, "grad_norm": 2.207106828689575, "learning_rate": 3.652583097894624e-05, "loss": 0.0776, "step": 3889 }, { "epoch": 0.214822178042854, "grad_norm": 3.502654790878296, "learning_rate": 3.652381582169353e-05, "loss": 0.3143, "step": 3890 }, { "epoch": 0.21487740225314778, "grad_norm": 0.16205011308193207, "learning_rate": 3.6521800135796925e-05, "loss": 0.005, "step": 3891 }, { "epoch": 0.21493262646344158, "grad_norm": 1.5436046123504639, "learning_rate": 3.651978392132089e-05, "loss": 0.1699, "step": 3892 }, { "epoch": 0.21498785067373535, "grad_norm": 2.7132086753845215, "learning_rate": 3.651776717832994e-05, "loss": 1.0929, "step": 3893 }, { "epoch": 0.21504307488402916, "grad_norm": 4.897378921508789, "learning_rate": 3.651574990688859e-05, "loss": 2.4475, "step": 3894 }, { "epoch": 0.21509829909432296, "grad_norm": 0.9492200016975403, "learning_rate": 3.651373210706138e-05, "loss": 0.0331, "step": 3895 }, { "epoch": 0.21515352330461673, "grad_norm": 0.08784914016723633, "learning_rate": 3.651171377891288e-05, "loss": 0.0032, "step": 3896 }, { "epoch": 0.21520874751491054, "grad_norm": 2.2957184314727783, "learning_rate": 3.6509694922507646e-05, "loss": 0.6734, "step": 3897 }, { "epoch": 0.21526397172520434, "grad_norm": 7.381020545959473, "learning_rate": 3.6507675537910266e-05, "loss": 1.2508, "step": 3898 }, { "epoch": 0.21531919593549811, "grad_norm": 3.2416646480560303, "learning_rate": 3.650565562518535e-05, "loss": 0.1821, "step": 3899 }, { "epoch": 0.21537442014579192, "grad_norm": 0.6543154716491699, "learning_rate": 3.6503635184397524e-05, "loss": 0.0206, "step": 3900 }, { "epoch": 0.21542964435608572, "grad_norm": 4.12965726852417, "learning_rate": 3.6501614215611425e-05, "loss": 0.6338, "step": 3901 }, { "epoch": 0.2154848685663795, "grad_norm": 0.4928669333457947, "learning_rate": 3.64995927188917e-05, "loss": 0.0216, "step": 3902 }, { "epoch": 0.2155400927766733, "grad_norm": 1.445825457572937, "learning_rate": 3.649757069430304e-05, "loss": 0.0608, "step": 3903 }, { "epoch": 0.21559531698696707, "grad_norm": 0.688962459564209, "learning_rate": 3.6495548141910126e-05, "loss": 0.022, "step": 3904 }, { "epoch": 0.21565054119726088, "grad_norm": 0.08403361588716507, "learning_rate": 3.649352506177767e-05, "loss": 0.0033, "step": 3905 }, { "epoch": 0.21570576540755468, "grad_norm": 5.328737735748291, "learning_rate": 3.649150145397038e-05, "loss": 1.1112, "step": 3906 }, { "epoch": 0.21576098961784845, "grad_norm": 0.5933181047439575, "learning_rate": 3.6489477318553026e-05, "loss": 0.0259, "step": 3907 }, { "epoch": 0.21581621382814226, "grad_norm": 0.060353126376867294, "learning_rate": 3.6487452655590336e-05, "loss": 0.002, "step": 3908 }, { "epoch": 0.21587143803843606, "grad_norm": 2.2493228912353516, "learning_rate": 3.64854274651471e-05, "loss": 0.2653, "step": 3909 }, { "epoch": 0.21592666224872983, "grad_norm": 4.673791408538818, "learning_rate": 3.6483401747288116e-05, "loss": 0.628, "step": 3910 }, { "epoch": 0.21598188645902364, "grad_norm": 0.3602609932422638, "learning_rate": 3.6481375502078174e-05, "loss": 0.0063, "step": 3911 }, { "epoch": 0.21603711066931744, "grad_norm": 3.650251626968384, "learning_rate": 3.647934872958212e-05, "loss": 0.7265, "step": 3912 }, { "epoch": 0.21609233487961121, "grad_norm": 0.05402678623795509, "learning_rate": 3.647732142986478e-05, "loss": 0.0017, "step": 3913 }, { "epoch": 0.21614755908990502, "grad_norm": 3.048403024673462, "learning_rate": 3.647529360299101e-05, "loss": 0.8276, "step": 3914 }, { "epoch": 0.21620278330019882, "grad_norm": 1.520725131034851, "learning_rate": 3.64732652490257e-05, "loss": 0.06, "step": 3915 }, { "epoch": 0.2162580075104926, "grad_norm": 0.05025617033243179, "learning_rate": 3.6471236368033745e-05, "loss": 0.002, "step": 3916 }, { "epoch": 0.2163132317207864, "grad_norm": 2.1424801349639893, "learning_rate": 3.646920696008004e-05, "loss": 0.5742, "step": 3917 }, { "epoch": 0.21636845593108017, "grad_norm": 0.014594483189284801, "learning_rate": 3.646717702522952e-05, "loss": 0.0005, "step": 3918 }, { "epoch": 0.21642368014137398, "grad_norm": 2.1878223419189453, "learning_rate": 3.6465146563547124e-05, "loss": 0.1118, "step": 3919 }, { "epoch": 0.21647890435166778, "grad_norm": 3.5773744583129883, "learning_rate": 3.646311557509782e-05, "loss": 0.3138, "step": 3920 }, { "epoch": 0.21653412856196155, "grad_norm": 2.1949119567871094, "learning_rate": 3.646108405994657e-05, "loss": 0.0892, "step": 3921 }, { "epoch": 0.21658935277225536, "grad_norm": 0.1534864902496338, "learning_rate": 3.6459052018158394e-05, "loss": 0.0057, "step": 3922 }, { "epoch": 0.21664457698254916, "grad_norm": 0.06342720985412598, "learning_rate": 3.645701944979828e-05, "loss": 0.0011, "step": 3923 }, { "epoch": 0.21669980119284293, "grad_norm": 3.6652774810791016, "learning_rate": 3.6454986354931265e-05, "loss": 0.7833, "step": 3924 }, { "epoch": 0.21675502540313674, "grad_norm": 0.8294539451599121, "learning_rate": 3.645295273362239e-05, "loss": 0.0295, "step": 3925 }, { "epoch": 0.21681024961343054, "grad_norm": 1.2860400676727295, "learning_rate": 3.645091858593671e-05, "loss": 0.058, "step": 3926 }, { "epoch": 0.21686547382372431, "grad_norm": 1.988105297088623, "learning_rate": 3.644888391193932e-05, "loss": 0.1355, "step": 3927 }, { "epoch": 0.21692069803401812, "grad_norm": 3.8539645671844482, "learning_rate": 3.6446848711695306e-05, "loss": 1.1117, "step": 3928 }, { "epoch": 0.21697592224431192, "grad_norm": 0.8478796482086182, "learning_rate": 3.6444812985269774e-05, "loss": 0.0261, "step": 3929 }, { "epoch": 0.2170311464546057, "grad_norm": 2.4260969161987305, "learning_rate": 3.644277673272786e-05, "loss": 0.3404, "step": 3930 }, { "epoch": 0.2170863706648995, "grad_norm": 6.176457405090332, "learning_rate": 3.6440739954134705e-05, "loss": 1.0712, "step": 3931 }, { "epoch": 0.21714159487519327, "grad_norm": 5.175265312194824, "learning_rate": 3.643870264955548e-05, "loss": 0.6251, "step": 3932 }, { "epoch": 0.21719681908548708, "grad_norm": 3.5016894340515137, "learning_rate": 3.643666481905536e-05, "loss": 0.4287, "step": 3933 }, { "epoch": 0.21725204329578088, "grad_norm": 0.09589406102895737, "learning_rate": 3.6434626462699536e-05, "loss": 0.0049, "step": 3934 }, { "epoch": 0.21730726750607465, "grad_norm": 3.0619616508483887, "learning_rate": 3.643258758055322e-05, "loss": 0.2781, "step": 3935 }, { "epoch": 0.21736249171636846, "grad_norm": 0.057317305356264114, "learning_rate": 3.6430548172681653e-05, "loss": 0.0025, "step": 3936 }, { "epoch": 0.21741771592666226, "grad_norm": 0.10732956975698471, "learning_rate": 3.642850823915007e-05, "loss": 0.0039, "step": 3937 }, { "epoch": 0.21747294013695603, "grad_norm": 3.154364824295044, "learning_rate": 3.642646778002374e-05, "loss": 0.5531, "step": 3938 }, { "epoch": 0.21752816434724984, "grad_norm": 1.580501675605774, "learning_rate": 3.6424426795367936e-05, "loss": 0.0545, "step": 3939 }, { "epoch": 0.21758338855754364, "grad_norm": 0.02444637380540371, "learning_rate": 3.6422385285247965e-05, "loss": 0.001, "step": 3940 }, { "epoch": 0.2176386127678374, "grad_norm": 2.3032281398773193, "learning_rate": 3.642034324972914e-05, "loss": 0.124, "step": 3941 }, { "epoch": 0.21769383697813122, "grad_norm": 2.4633686542510986, "learning_rate": 3.641830068887679e-05, "loss": 0.6888, "step": 3942 }, { "epoch": 0.21774906118842502, "grad_norm": 0.22047364711761475, "learning_rate": 3.641625760275625e-05, "loss": 0.007, "step": 3943 }, { "epoch": 0.2178042853987188, "grad_norm": 0.060555677860975266, "learning_rate": 3.64142139914329e-05, "loss": 0.0018, "step": 3944 }, { "epoch": 0.2178595096090126, "grad_norm": 0.19546975195407867, "learning_rate": 3.641216985497211e-05, "loss": 0.0052, "step": 3945 }, { "epoch": 0.21791473381930637, "grad_norm": 0.2582070529460907, "learning_rate": 3.6410125193439287e-05, "loss": 0.0095, "step": 3946 }, { "epoch": 0.21796995802960017, "grad_norm": 1.2160940170288086, "learning_rate": 3.640808000689984e-05, "loss": 0.12, "step": 3947 }, { "epoch": 0.21802518223989398, "grad_norm": 1.2576481103897095, "learning_rate": 3.64060342954192e-05, "loss": 0.2118, "step": 3948 }, { "epoch": 0.21808040645018775, "grad_norm": 0.027847465127706528, "learning_rate": 3.640398805906283e-05, "loss": 0.0011, "step": 3949 }, { "epoch": 0.21813563066048156, "grad_norm": 3.0328896045684814, "learning_rate": 3.640194129789617e-05, "loss": 0.7089, "step": 3950 }, { "epoch": 0.21819085487077536, "grad_norm": 1.5306864976882935, "learning_rate": 3.639989401198471e-05, "loss": 0.0524, "step": 3951 }, { "epoch": 0.21824607908106913, "grad_norm": 0.9349351525306702, "learning_rate": 3.639784620139396e-05, "loss": 0.0234, "step": 3952 }, { "epoch": 0.21830130329136294, "grad_norm": 2.6690940856933594, "learning_rate": 3.639579786618943e-05, "loss": 0.4551, "step": 3953 }, { "epoch": 0.21835652750165674, "grad_norm": 0.09532321244478226, "learning_rate": 3.639374900643664e-05, "loss": 0.0039, "step": 3954 }, { "epoch": 0.2184117517119505, "grad_norm": 0.22661130130290985, "learning_rate": 3.639169962220115e-05, "loss": 0.0059, "step": 3955 }, { "epoch": 0.21846697592224432, "grad_norm": 0.5491451025009155, "learning_rate": 3.638964971354853e-05, "loss": 0.0159, "step": 3956 }, { "epoch": 0.2185222001325381, "grad_norm": 6.426131725311279, "learning_rate": 3.6387599280544354e-05, "loss": 1.4718, "step": 3957 }, { "epoch": 0.2185774243428319, "grad_norm": 0.5529657006263733, "learning_rate": 3.6385548323254224e-05, "loss": 0.0329, "step": 3958 }, { "epoch": 0.2186326485531257, "grad_norm": 0.11358239501714706, "learning_rate": 3.638349684174376e-05, "loss": 0.0048, "step": 3959 }, { "epoch": 0.21868787276341947, "grad_norm": 3.7705092430114746, "learning_rate": 3.6381444836078586e-05, "loss": 0.7407, "step": 3960 }, { "epoch": 0.21874309697371327, "grad_norm": 3.5055463314056396, "learning_rate": 3.6379392306324354e-05, "loss": 0.3469, "step": 3961 }, { "epoch": 0.21879832118400708, "grad_norm": 3.087660312652588, "learning_rate": 3.637733925254673e-05, "loss": 0.5247, "step": 3962 }, { "epoch": 0.21885354539430085, "grad_norm": 0.07722004503011703, "learning_rate": 3.63752856748114e-05, "loss": 0.0033, "step": 3963 }, { "epoch": 0.21890876960459466, "grad_norm": 0.1638961285352707, "learning_rate": 3.637323157318407e-05, "loss": 0.005, "step": 3964 }, { "epoch": 0.21896399381488846, "grad_norm": 2.900399923324585, "learning_rate": 3.637117694773044e-05, "loss": 0.102, "step": 3965 }, { "epoch": 0.21901921802518223, "grad_norm": 3.0821239948272705, "learning_rate": 3.636912179851626e-05, "loss": 0.4723, "step": 3966 }, { "epoch": 0.21907444223547604, "grad_norm": 1.0534791946411133, "learning_rate": 3.636706612560727e-05, "loss": 0.0418, "step": 3967 }, { "epoch": 0.21912966644576984, "grad_norm": 0.04860677942633629, "learning_rate": 3.636500992906924e-05, "loss": 0.0013, "step": 3968 }, { "epoch": 0.2191848906560636, "grad_norm": 0.1470823585987091, "learning_rate": 3.636295320896795e-05, "loss": 0.005, "step": 3969 }, { "epoch": 0.21924011486635742, "grad_norm": 1.231391191482544, "learning_rate": 3.636089596536921e-05, "loss": 0.1035, "step": 3970 }, { "epoch": 0.2192953390766512, "grad_norm": 1.7405614852905273, "learning_rate": 3.635883819833883e-05, "loss": 0.0774, "step": 3971 }, { "epoch": 0.219350563286945, "grad_norm": 0.03248779475688934, "learning_rate": 3.635677990794264e-05, "loss": 0.0012, "step": 3972 }, { "epoch": 0.2194057874972388, "grad_norm": 3.354433298110962, "learning_rate": 3.635472109424649e-05, "loss": 0.8248, "step": 3973 }, { "epoch": 0.21946101170753257, "grad_norm": 2.106436252593994, "learning_rate": 3.635266175731626e-05, "loss": 0.151, "step": 3974 }, { "epoch": 0.21951623591782637, "grad_norm": 0.11214051395654678, "learning_rate": 3.6350601897217827e-05, "loss": 0.0039, "step": 3975 }, { "epoch": 0.21957146012812018, "grad_norm": 0.3087846636772156, "learning_rate": 3.634854151401709e-05, "loss": 0.0123, "step": 3976 }, { "epoch": 0.21962668433841395, "grad_norm": 2.9947564601898193, "learning_rate": 3.634648060777997e-05, "loss": 0.8528, "step": 3977 }, { "epoch": 0.21968190854870775, "grad_norm": 0.22286748886108398, "learning_rate": 3.634441917857239e-05, "loss": 0.0107, "step": 3978 }, { "epoch": 0.21973713275900156, "grad_norm": 1.6026933193206787, "learning_rate": 3.634235722646032e-05, "loss": 0.0865, "step": 3979 }, { "epoch": 0.21979235696929533, "grad_norm": 0.03738226741552353, "learning_rate": 3.634029475150971e-05, "loss": 0.0011, "step": 3980 }, { "epoch": 0.21984758117958914, "grad_norm": 0.049553483724594116, "learning_rate": 3.633823175378656e-05, "loss": 0.0019, "step": 3981 }, { "epoch": 0.21990280538988294, "grad_norm": 0.254624605178833, "learning_rate": 3.6336168233356864e-05, "loss": 0.0067, "step": 3982 }, { "epoch": 0.2199580296001767, "grad_norm": 2.6398825645446777, "learning_rate": 3.6334104190286635e-05, "loss": 0.1942, "step": 3983 }, { "epoch": 0.22001325381047052, "grad_norm": 1.3066153526306152, "learning_rate": 3.633203962464191e-05, "loss": 0.0448, "step": 3984 }, { "epoch": 0.2200684780207643, "grad_norm": 4.339734077453613, "learning_rate": 3.6329974536488736e-05, "loss": 1.1733, "step": 3985 }, { "epoch": 0.2201237022310581, "grad_norm": 0.055393874645233154, "learning_rate": 3.63279089258932e-05, "loss": 0.0018, "step": 3986 }, { "epoch": 0.2201789264413519, "grad_norm": 0.18207316100597382, "learning_rate": 3.632584279292137e-05, "loss": 0.0061, "step": 3987 }, { "epoch": 0.22023415065164567, "grad_norm": 1.746427059173584, "learning_rate": 3.632377613763935e-05, "loss": 0.2591, "step": 3988 }, { "epoch": 0.22028937486193947, "grad_norm": 0.6107025146484375, "learning_rate": 3.6321708960113265e-05, "loss": 0.0173, "step": 3989 }, { "epoch": 0.22034459907223328, "grad_norm": 2.325751304626465, "learning_rate": 3.631964126040924e-05, "loss": 0.1543, "step": 3990 }, { "epoch": 0.22039982328252705, "grad_norm": 0.041253991425037384, "learning_rate": 3.631757303859343e-05, "loss": 0.0012, "step": 3991 }, { "epoch": 0.22045504749282085, "grad_norm": 3.114086389541626, "learning_rate": 3.6315504294732005e-05, "loss": 0.6765, "step": 3992 }, { "epoch": 0.22051027170311466, "grad_norm": 3.2988228797912598, "learning_rate": 3.631343502889115e-05, "loss": 0.4681, "step": 3993 }, { "epoch": 0.22056549591340843, "grad_norm": 0.06946256011724472, "learning_rate": 3.631136524113706e-05, "loss": 0.0021, "step": 3994 }, { "epoch": 0.22062072012370224, "grad_norm": 2.9017012119293213, "learning_rate": 3.630929493153597e-05, "loss": 0.2791, "step": 3995 }, { "epoch": 0.220675944333996, "grad_norm": 2.510664939880371, "learning_rate": 3.63072241001541e-05, "loss": 0.1777, "step": 3996 }, { "epoch": 0.2207311685442898, "grad_norm": 0.8264995813369751, "learning_rate": 3.6305152747057704e-05, "loss": 0.0342, "step": 3997 }, { "epoch": 0.22078639275458362, "grad_norm": 0.6041592359542847, "learning_rate": 3.630308087231305e-05, "loss": 0.0048, "step": 3998 }, { "epoch": 0.2208416169648774, "grad_norm": 3.2285821437835693, "learning_rate": 3.6301008475986437e-05, "loss": 0.3801, "step": 3999 }, { "epoch": 0.2208968411751712, "grad_norm": 4.879166126251221, "learning_rate": 3.629893555814415e-05, "loss": 0.7865, "step": 4000 }, { "epoch": 0.220952065385465, "grad_norm": 1.1562180519104004, "learning_rate": 3.6296862118852516e-05, "loss": 0.0272, "step": 4001 }, { "epoch": 0.22100728959575877, "grad_norm": 0.3428437113761902, "learning_rate": 3.629478815817786e-05, "loss": 0.0079, "step": 4002 }, { "epoch": 0.22106251380605257, "grad_norm": 2.8371570110321045, "learning_rate": 3.629271367618655e-05, "loss": 0.1599, "step": 4003 }, { "epoch": 0.22111773801634638, "grad_norm": 0.16577400267124176, "learning_rate": 3.629063867294494e-05, "loss": 0.0039, "step": 4004 }, { "epoch": 0.22117296222664015, "grad_norm": 0.3661280870437622, "learning_rate": 3.628856314851943e-05, "loss": 0.0124, "step": 4005 }, { "epoch": 0.22122818643693395, "grad_norm": 8.807859420776367, "learning_rate": 3.628648710297641e-05, "loss": 0.8804, "step": 4006 }, { "epoch": 0.22128341064722776, "grad_norm": 4.858043193817139, "learning_rate": 3.6284410536382294e-05, "loss": 1.1664, "step": 4007 }, { "epoch": 0.22133863485752153, "grad_norm": 1.9145727157592773, "learning_rate": 3.628233344880353e-05, "loss": 0.0905, "step": 4008 }, { "epoch": 0.22139385906781534, "grad_norm": 0.37908753752708435, "learning_rate": 3.628025584030657e-05, "loss": 0.0116, "step": 4009 }, { "epoch": 0.2214490832781091, "grad_norm": 2.623439073562622, "learning_rate": 3.627817771095787e-05, "loss": 0.6538, "step": 4010 }, { "epoch": 0.2215043074884029, "grad_norm": 2.5841877460479736, "learning_rate": 3.627609906082393e-05, "loss": 0.4721, "step": 4011 }, { "epoch": 0.22155953169869672, "grad_norm": 1.3741822242736816, "learning_rate": 3.627401988997125e-05, "loss": 0.0967, "step": 4012 }, { "epoch": 0.2216147559089905, "grad_norm": 0.13714171946048737, "learning_rate": 3.627194019846633e-05, "loss": 0.0042, "step": 4013 }, { "epoch": 0.2216699801192843, "grad_norm": 2.7182271480560303, "learning_rate": 3.6269859986375726e-05, "loss": 0.227, "step": 4014 }, { "epoch": 0.2217252043295781, "grad_norm": 0.6201121807098389, "learning_rate": 3.6267779253765976e-05, "loss": 0.0152, "step": 4015 }, { "epoch": 0.22178042853987187, "grad_norm": 3.6188645362854004, "learning_rate": 3.626569800070367e-05, "loss": 0.4108, "step": 4016 }, { "epoch": 0.22183565275016567, "grad_norm": 4.366286754608154, "learning_rate": 3.626361622725536e-05, "loss": 0.3467, "step": 4017 }, { "epoch": 0.22189087696045948, "grad_norm": 0.4871377646923065, "learning_rate": 3.626153393348768e-05, "loss": 0.0184, "step": 4018 }, { "epoch": 0.22194610117075325, "grad_norm": 0.49718889594078064, "learning_rate": 3.625945111946723e-05, "loss": 0.0172, "step": 4019 }, { "epoch": 0.22200132538104705, "grad_norm": 0.9169959425926208, "learning_rate": 3.625736778526065e-05, "loss": 0.028, "step": 4020 }, { "epoch": 0.22205654959134086, "grad_norm": 2.909234046936035, "learning_rate": 3.6255283930934595e-05, "loss": 0.2835, "step": 4021 }, { "epoch": 0.22211177380163463, "grad_norm": 0.3072788417339325, "learning_rate": 3.625319955655573e-05, "loss": 0.007, "step": 4022 }, { "epoch": 0.22216699801192843, "grad_norm": 0.05176467075943947, "learning_rate": 3.6251114662190735e-05, "loss": 0.0014, "step": 4023 }, { "epoch": 0.2222222222222222, "grad_norm": 4.964280128479004, "learning_rate": 3.624902924790633e-05, "loss": 1.666, "step": 4024 }, { "epoch": 0.222277446432516, "grad_norm": 0.21607381105422974, "learning_rate": 3.6246943313769204e-05, "loss": 0.0065, "step": 4025 }, { "epoch": 0.22233267064280982, "grad_norm": 0.08084776252508163, "learning_rate": 3.624485685984612e-05, "loss": 0.0023, "step": 4026 }, { "epoch": 0.2223878948531036, "grad_norm": 3.2110719680786133, "learning_rate": 3.624276988620381e-05, "loss": 0.4993, "step": 4027 }, { "epoch": 0.2224431190633974, "grad_norm": 0.0846121534705162, "learning_rate": 3.624068239290906e-05, "loss": 0.0029, "step": 4028 }, { "epoch": 0.2224983432736912, "grad_norm": 2.9004814624786377, "learning_rate": 3.623859438002863e-05, "loss": 0.0626, "step": 4029 }, { "epoch": 0.22255356748398497, "grad_norm": 0.48990148305892944, "learning_rate": 3.623650584762935e-05, "loss": 0.0118, "step": 4030 }, { "epoch": 0.22260879169427877, "grad_norm": 0.07373245805501938, "learning_rate": 3.623441679577802e-05, "loss": 0.0022, "step": 4031 }, { "epoch": 0.22266401590457258, "grad_norm": 0.06987898051738739, "learning_rate": 3.6232327224541484e-05, "loss": 0.0017, "step": 4032 }, { "epoch": 0.22271924011486635, "grad_norm": 7.081358909606934, "learning_rate": 3.623023713398658e-05, "loss": 0.1934, "step": 4033 }, { "epoch": 0.22277446432516015, "grad_norm": 0.796240508556366, "learning_rate": 3.622814652418019e-05, "loss": 0.0116, "step": 4034 }, { "epoch": 0.22282968853545393, "grad_norm": 1.717707872390747, "learning_rate": 3.622605539518919e-05, "loss": 0.1057, "step": 4035 }, { "epoch": 0.22288491274574773, "grad_norm": 0.16575613617897034, "learning_rate": 3.622396374708049e-05, "loss": 0.0049, "step": 4036 }, { "epoch": 0.22294013695604153, "grad_norm": 5.0960001945495605, "learning_rate": 3.622187157992099e-05, "loss": 1.1022, "step": 4037 }, { "epoch": 0.2229953611663353, "grad_norm": 3.2270336151123047, "learning_rate": 3.621977889377765e-05, "loss": 0.847, "step": 4038 }, { "epoch": 0.2230505853766291, "grad_norm": 3.9042086601257324, "learning_rate": 3.62176856887174e-05, "loss": 0.8217, "step": 4039 }, { "epoch": 0.22310580958692292, "grad_norm": 0.04507682844996452, "learning_rate": 3.621559196480722e-05, "loss": 0.0014, "step": 4040 }, { "epoch": 0.2231610337972167, "grad_norm": 4.300971031188965, "learning_rate": 3.621349772211409e-05, "loss": 0.4534, "step": 4041 }, { "epoch": 0.2232162580075105, "grad_norm": 2.8212027549743652, "learning_rate": 3.6211402960705e-05, "loss": 0.2521, "step": 4042 }, { "epoch": 0.2232714822178043, "grad_norm": 1.7945656776428223, "learning_rate": 3.620930768064699e-05, "loss": 0.2321, "step": 4043 }, { "epoch": 0.22332670642809807, "grad_norm": 1.885766625404358, "learning_rate": 3.620721188200707e-05, "loss": 0.2585, "step": 4044 }, { "epoch": 0.22338193063839187, "grad_norm": 2.7481534481048584, "learning_rate": 3.6205115564852314e-05, "loss": 0.2161, "step": 4045 }, { "epoch": 0.22343715484868568, "grad_norm": 0.031909652054309845, "learning_rate": 3.620301872924977e-05, "loss": 0.0012, "step": 4046 }, { "epoch": 0.22349237905897945, "grad_norm": 0.010946090333163738, "learning_rate": 3.6200921375266534e-05, "loss": 0.0004, "step": 4047 }, { "epoch": 0.22354760326927325, "grad_norm": 3.339367628097534, "learning_rate": 3.61988235029697e-05, "loss": 0.4194, "step": 4048 }, { "epoch": 0.22360282747956703, "grad_norm": 3.7796905040740967, "learning_rate": 3.6196725112426385e-05, "loss": 1.2712, "step": 4049 }, { "epoch": 0.22365805168986083, "grad_norm": 0.09181790053844452, "learning_rate": 3.619462620370372e-05, "loss": 0.0028, "step": 4050 }, { "epoch": 0.22371327590015463, "grad_norm": 0.08146917074918747, "learning_rate": 3.619252677686886e-05, "loss": 0.0033, "step": 4051 }, { "epoch": 0.2237685001104484, "grad_norm": 0.1600736528635025, "learning_rate": 3.6190426831988974e-05, "loss": 0.0048, "step": 4052 }, { "epoch": 0.2238237243207422, "grad_norm": 2.7617337703704834, "learning_rate": 3.618832636913124e-05, "loss": 0.2002, "step": 4053 }, { "epoch": 0.22387894853103602, "grad_norm": 0.007745318580418825, "learning_rate": 3.6186225388362856e-05, "loss": 0.0002, "step": 4054 }, { "epoch": 0.2239341727413298, "grad_norm": 0.9238251447677612, "learning_rate": 3.618412388975104e-05, "loss": 0.0423, "step": 4055 }, { "epoch": 0.2239893969516236, "grad_norm": 0.06512048840522766, "learning_rate": 3.618202187336303e-05, "loss": 0.0028, "step": 4056 }, { "epoch": 0.2240446211619174, "grad_norm": 1.5804377794265747, "learning_rate": 3.617991933926607e-05, "loss": 0.2225, "step": 4057 }, { "epoch": 0.22409984537221117, "grad_norm": 0.029111206531524658, "learning_rate": 3.6177816287527436e-05, "loss": 0.0009, "step": 4058 }, { "epoch": 0.22415506958250497, "grad_norm": 5.8687615394592285, "learning_rate": 3.6175712718214394e-05, "loss": 1.8184, "step": 4059 }, { "epoch": 0.22421029379279878, "grad_norm": 4.5281081199646, "learning_rate": 3.617360863139426e-05, "loss": 0.234, "step": 4060 }, { "epoch": 0.22426551800309255, "grad_norm": 1.7835414409637451, "learning_rate": 3.617150402713433e-05, "loss": 0.049, "step": 4061 }, { "epoch": 0.22432074221338635, "grad_norm": 3.4207658767700195, "learning_rate": 3.616939890550196e-05, "loss": 0.8993, "step": 4062 }, { "epoch": 0.22437596642368013, "grad_norm": 6.3983869552612305, "learning_rate": 3.616729326656448e-05, "loss": 1.0011, "step": 4063 }, { "epoch": 0.22443119063397393, "grad_norm": 5.173095703125, "learning_rate": 3.6165187110389266e-05, "loss": 1.4751, "step": 4064 }, { "epoch": 0.22448641484426773, "grad_norm": 0.12420687824487686, "learning_rate": 3.6163080437043696e-05, "loss": 0.006, "step": 4065 }, { "epoch": 0.2245416390545615, "grad_norm": 1.7465183734893799, "learning_rate": 3.6160973246595165e-05, "loss": 0.0848, "step": 4066 }, { "epoch": 0.2245968632648553, "grad_norm": 4.101992130279541, "learning_rate": 3.615886553911109e-05, "loss": 1.5029, "step": 4067 }, { "epoch": 0.22465208747514911, "grad_norm": 0.1716349720954895, "learning_rate": 3.615675731465891e-05, "loss": 0.0048, "step": 4068 }, { "epoch": 0.2247073116854429, "grad_norm": 5.3936686515808105, "learning_rate": 3.6154648573306064e-05, "loss": 1.7332, "step": 4069 }, { "epoch": 0.2247625358957367, "grad_norm": 2.224064588546753, "learning_rate": 3.6152539315120024e-05, "loss": 0.1074, "step": 4070 }, { "epoch": 0.2248177601060305, "grad_norm": 0.0665498599410057, "learning_rate": 3.615042954016826e-05, "loss": 0.002, "step": 4071 }, { "epoch": 0.22487298431632427, "grad_norm": 1.6638559103012085, "learning_rate": 3.614831924851828e-05, "loss": 0.0479, "step": 4072 }, { "epoch": 0.22492820852661807, "grad_norm": 1.9203635454177856, "learning_rate": 3.614620844023759e-05, "loss": 0.2943, "step": 4073 }, { "epoch": 0.22498343273691188, "grad_norm": 3.7062833309173584, "learning_rate": 3.6144097115393735e-05, "loss": 0.3878, "step": 4074 }, { "epoch": 0.22503865694720565, "grad_norm": 0.052532099187374115, "learning_rate": 3.6141985274054243e-05, "loss": 0.0011, "step": 4075 }, { "epoch": 0.22509388115749945, "grad_norm": 1.0863591432571411, "learning_rate": 3.61398729162867e-05, "loss": 0.0217, "step": 4076 }, { "epoch": 0.22514910536779323, "grad_norm": 2.196025848388672, "learning_rate": 3.613776004215867e-05, "loss": 0.3386, "step": 4077 }, { "epoch": 0.22520432957808703, "grad_norm": 0.11388497054576874, "learning_rate": 3.613564665173775e-05, "loss": 0.0029, "step": 4078 }, { "epoch": 0.22525955378838083, "grad_norm": 0.8074826002120972, "learning_rate": 3.613353274509156e-05, "loss": 0.1314, "step": 4079 }, { "epoch": 0.2253147779986746, "grad_norm": 6.366385459899902, "learning_rate": 3.613141832228773e-05, "loss": 1.9316, "step": 4080 }, { "epoch": 0.2253700022089684, "grad_norm": 0.1416725218296051, "learning_rate": 3.61293033833939e-05, "loss": 0.0062, "step": 4081 }, { "epoch": 0.22542522641926221, "grad_norm": 4.567753791809082, "learning_rate": 3.612718792847773e-05, "loss": 0.4848, "step": 4082 }, { "epoch": 0.225480450629556, "grad_norm": 0.23617549240589142, "learning_rate": 3.6125071957606923e-05, "loss": 0.0115, "step": 4083 }, { "epoch": 0.2255356748398498, "grad_norm": 0.13291716575622559, "learning_rate": 3.6122955470849145e-05, "loss": 0.0039, "step": 4084 }, { "epoch": 0.2255908990501436, "grad_norm": 1.3146904706954956, "learning_rate": 3.612083846827213e-05, "loss": 0.2389, "step": 4085 }, { "epoch": 0.22564612326043737, "grad_norm": 4.504310607910156, "learning_rate": 3.611872094994359e-05, "loss": 0.369, "step": 4086 }, { "epoch": 0.22570134747073117, "grad_norm": 0.5552065372467041, "learning_rate": 3.611660291593128e-05, "loss": 0.0132, "step": 4087 }, { "epoch": 0.22575657168102495, "grad_norm": 2.828016519546509, "learning_rate": 3.6114484366302967e-05, "loss": 0.1353, "step": 4088 }, { "epoch": 0.22581179589131875, "grad_norm": 0.3950662910938263, "learning_rate": 3.611236530112642e-05, "loss": 0.0091, "step": 4089 }, { "epoch": 0.22586702010161255, "grad_norm": 0.3263162672519684, "learning_rate": 3.6110245720469435e-05, "loss": 0.0102, "step": 4090 }, { "epoch": 0.22592224431190633, "grad_norm": 0.11362452805042267, "learning_rate": 3.610812562439983e-05, "loss": 0.0031, "step": 4091 }, { "epoch": 0.22597746852220013, "grad_norm": 0.021258797496557236, "learning_rate": 3.6106005012985425e-05, "loss": 0.0007, "step": 4092 }, { "epoch": 0.22603269273249393, "grad_norm": 6.143338680267334, "learning_rate": 3.610388388629407e-05, "loss": 1.6198, "step": 4093 }, { "epoch": 0.2260879169427877, "grad_norm": 0.2159993201494217, "learning_rate": 3.610176224439362e-05, "loss": 0.0043, "step": 4094 }, { "epoch": 0.2261431411530815, "grad_norm": 1.5407688617706299, "learning_rate": 3.609964008735196e-05, "loss": 0.0569, "step": 4095 }, { "epoch": 0.22619836536337531, "grad_norm": 5.488783359527588, "learning_rate": 3.6097517415236975e-05, "loss": 1.1497, "step": 4096 }, { "epoch": 0.2262535895736691, "grad_norm": 4.821946144104004, "learning_rate": 3.609539422811658e-05, "loss": 0.9584, "step": 4097 }, { "epoch": 0.2263088137839629, "grad_norm": 2.0007734298706055, "learning_rate": 3.609327052605871e-05, "loss": 0.1453, "step": 4098 }, { "epoch": 0.2263640379942567, "grad_norm": 0.672381579875946, "learning_rate": 3.60911463091313e-05, "loss": 0.0167, "step": 4099 }, { "epoch": 0.22641926220455047, "grad_norm": 0.7786780595779419, "learning_rate": 3.60890215774023e-05, "loss": 0.0274, "step": 4100 }, { "epoch": 0.22647448641484427, "grad_norm": 0.20311452448368073, "learning_rate": 3.608689633093971e-05, "loss": 0.0083, "step": 4101 }, { "epoch": 0.22652971062513805, "grad_norm": 0.8097642660140991, "learning_rate": 3.608477056981149e-05, "loss": 0.0305, "step": 4102 }, { "epoch": 0.22658493483543185, "grad_norm": 0.06862223148345947, "learning_rate": 3.6082644294085685e-05, "loss": 0.0016, "step": 4103 }, { "epoch": 0.22664015904572565, "grad_norm": 0.6035037636756897, "learning_rate": 3.60805175038303e-05, "loss": 0.0099, "step": 4104 }, { "epoch": 0.22669538325601943, "grad_norm": 5.279763698577881, "learning_rate": 3.607839019911338e-05, "loss": 1.0207, "step": 4105 }, { "epoch": 0.22675060746631323, "grad_norm": 3.315498113632202, "learning_rate": 3.607626238000298e-05, "loss": 0.2201, "step": 4106 }, { "epoch": 0.22680583167660703, "grad_norm": 0.39168500900268555, "learning_rate": 3.607413404656718e-05, "loss": 0.01, "step": 4107 }, { "epoch": 0.2268610558869008, "grad_norm": 2.096956729888916, "learning_rate": 3.6072005198874076e-05, "loss": 0.1058, "step": 4108 }, { "epoch": 0.2269162800971946, "grad_norm": 0.273524671792984, "learning_rate": 3.6069875836991775e-05, "loss": 0.0099, "step": 4109 }, { "epoch": 0.22697150430748841, "grad_norm": 3.1380701065063477, "learning_rate": 3.6067745960988386e-05, "loss": 0.2731, "step": 4110 }, { "epoch": 0.2270267285177822, "grad_norm": 3.907944917678833, "learning_rate": 3.6065615570932065e-05, "loss": 0.2091, "step": 4111 }, { "epoch": 0.227081952728076, "grad_norm": 0.07117018848657608, "learning_rate": 3.606348466689097e-05, "loss": 0.0024, "step": 4112 }, { "epoch": 0.2271371769383698, "grad_norm": 1.7593508958816528, "learning_rate": 3.6061353248933264e-05, "loss": 0.0489, "step": 4113 }, { "epoch": 0.22719240114866357, "grad_norm": 3.704085111618042, "learning_rate": 3.605922131712714e-05, "loss": 0.3766, "step": 4114 }, { "epoch": 0.22724762535895737, "grad_norm": 1.7075825929641724, "learning_rate": 3.605708887154082e-05, "loss": 0.2128, "step": 4115 }, { "epoch": 0.22730284956925115, "grad_norm": 3.304314136505127, "learning_rate": 3.60549559122425e-05, "loss": 0.5992, "step": 4116 }, { "epoch": 0.22735807377954495, "grad_norm": 1.9729474782943726, "learning_rate": 3.6052822439300446e-05, "loss": 0.1928, "step": 4117 }, { "epoch": 0.22741329798983875, "grad_norm": 4.44614315032959, "learning_rate": 3.6050688452782896e-05, "loss": 0.8473, "step": 4118 }, { "epoch": 0.22746852220013253, "grad_norm": 0.13873785734176636, "learning_rate": 3.6048553952758126e-05, "loss": 0.0031, "step": 4119 }, { "epoch": 0.22752374641042633, "grad_norm": 0.5903757214546204, "learning_rate": 3.604641893929443e-05, "loss": 0.019, "step": 4120 }, { "epoch": 0.22757897062072013, "grad_norm": 0.1281488835811615, "learning_rate": 3.604428341246011e-05, "loss": 0.0041, "step": 4121 }, { "epoch": 0.2276341948310139, "grad_norm": 1.2210685014724731, "learning_rate": 3.604214737232348e-05, "loss": 0.0352, "step": 4122 }, { "epoch": 0.2276894190413077, "grad_norm": 1.7743583917617798, "learning_rate": 3.604001081895289e-05, "loss": 0.5208, "step": 4123 }, { "epoch": 0.22774464325160151, "grad_norm": 3.963101625442505, "learning_rate": 3.60378737524167e-05, "loss": 1.0666, "step": 4124 }, { "epoch": 0.2277998674618953, "grad_norm": 0.38113927841186523, "learning_rate": 3.6035736172783266e-05, "loss": 0.0088, "step": 4125 }, { "epoch": 0.2278550916721891, "grad_norm": 2.4190738201141357, "learning_rate": 3.603359808012097e-05, "loss": 0.2362, "step": 4126 }, { "epoch": 0.22791031588248287, "grad_norm": 0.023177143186330795, "learning_rate": 3.603145947449823e-05, "loss": 0.0007, "step": 4127 }, { "epoch": 0.22796554009277667, "grad_norm": 0.19153133034706116, "learning_rate": 3.602932035598347e-05, "loss": 0.0048, "step": 4128 }, { "epoch": 0.22802076430307047, "grad_norm": 3.938514232635498, "learning_rate": 3.6027180724645114e-05, "loss": 1.0073, "step": 4129 }, { "epoch": 0.22807598851336425, "grad_norm": 0.5012977123260498, "learning_rate": 3.6025040580551616e-05, "loss": 0.0098, "step": 4130 }, { "epoch": 0.22813121272365805, "grad_norm": 3.5801594257354736, "learning_rate": 3.602289992377145e-05, "loss": 0.9379, "step": 4131 }, { "epoch": 0.22818643693395185, "grad_norm": 8.812979698181152, "learning_rate": 3.6020758754373104e-05, "loss": 1.1957, "step": 4132 }, { "epoch": 0.22824166114424563, "grad_norm": 4.981518745422363, "learning_rate": 3.601861707242507e-05, "loss": 0.8511, "step": 4133 }, { "epoch": 0.22829688535453943, "grad_norm": 3.2451741695404053, "learning_rate": 3.601647487799588e-05, "loss": 0.6874, "step": 4134 }, { "epoch": 0.22835210956483323, "grad_norm": 0.02434919960796833, "learning_rate": 3.601433217115406e-05, "loss": 0.0009, "step": 4135 }, { "epoch": 0.228407333775127, "grad_norm": 5.067685127258301, "learning_rate": 3.601218895196816e-05, "loss": 0.7544, "step": 4136 }, { "epoch": 0.2284625579854208, "grad_norm": 1.2514785528182983, "learning_rate": 3.601004522050676e-05, "loss": 0.1635, "step": 4137 }, { "epoch": 0.2285177821957146, "grad_norm": 0.07169736176729202, "learning_rate": 3.600790097683842e-05, "loss": 0.0024, "step": 4138 }, { "epoch": 0.2285730064060084, "grad_norm": 1.5089809894561768, "learning_rate": 3.600575622103176e-05, "loss": 0.0579, "step": 4139 }, { "epoch": 0.2286282306163022, "grad_norm": 3.5333235263824463, "learning_rate": 3.60036109531554e-05, "loss": 0.3863, "step": 4140 }, { "epoch": 0.22868345482659597, "grad_norm": 3.2504587173461914, "learning_rate": 3.600146517327796e-05, "loss": 0.524, "step": 4141 }, { "epoch": 0.22873867903688977, "grad_norm": 3.2763562202453613, "learning_rate": 3.59993188814681e-05, "loss": 0.7216, "step": 4142 }, { "epoch": 0.22879390324718357, "grad_norm": 0.04955065995454788, "learning_rate": 3.5997172077794465e-05, "loss": 0.0012, "step": 4143 }, { "epoch": 0.22884912745747735, "grad_norm": 1.5563862323760986, "learning_rate": 3.5995024762325765e-05, "loss": 0.1064, "step": 4144 }, { "epoch": 0.22890435166777115, "grad_norm": 0.2160668969154358, "learning_rate": 3.599287693513069e-05, "loss": 0.008, "step": 4145 }, { "epoch": 0.22895957587806495, "grad_norm": 4.104889392852783, "learning_rate": 3.599072859627795e-05, "loss": 0.9915, "step": 4146 }, { "epoch": 0.22901480008835873, "grad_norm": 0.07487580925226212, "learning_rate": 3.598857974583627e-05, "loss": 0.002, "step": 4147 }, { "epoch": 0.22907002429865253, "grad_norm": 2.739262580871582, "learning_rate": 3.598643038387442e-05, "loss": 0.4357, "step": 4148 }, { "epoch": 0.22912524850894633, "grad_norm": 3.277088165283203, "learning_rate": 3.598428051046114e-05, "loss": 0.7161, "step": 4149 }, { "epoch": 0.2291804727192401, "grad_norm": 0.4477201998233795, "learning_rate": 3.598213012566523e-05, "loss": 0.0136, "step": 4150 }, { "epoch": 0.2292356969295339, "grad_norm": 4.419613361358643, "learning_rate": 3.597997922955547e-05, "loss": 0.3167, "step": 4151 }, { "epoch": 0.2292909211398277, "grad_norm": 3.4631710052490234, "learning_rate": 3.597782782220068e-05, "loss": 0.19, "step": 4152 }, { "epoch": 0.2293461453501215, "grad_norm": 2.603241443634033, "learning_rate": 3.59756759036697e-05, "loss": 0.2788, "step": 4153 }, { "epoch": 0.2294013695604153, "grad_norm": 6.090237617492676, "learning_rate": 3.5973523474031364e-05, "loss": 0.551, "step": 4154 }, { "epoch": 0.22945659377070907, "grad_norm": 0.13445788621902466, "learning_rate": 3.597137053335454e-05, "loss": 0.0045, "step": 4155 }, { "epoch": 0.22951181798100287, "grad_norm": 3.664905309677124, "learning_rate": 3.596921708170809e-05, "loss": 0.2909, "step": 4156 }, { "epoch": 0.22956704219129667, "grad_norm": 2.408703327178955, "learning_rate": 3.5967063119160936e-05, "loss": 0.2328, "step": 4157 }, { "epoch": 0.22962226640159045, "grad_norm": 0.03843081742525101, "learning_rate": 3.596490864578198e-05, "loss": 0.0017, "step": 4158 }, { "epoch": 0.22967749061188425, "grad_norm": 2.5610411167144775, "learning_rate": 3.5962753661640134e-05, "loss": 0.1008, "step": 4159 }, { "epoch": 0.22973271482217805, "grad_norm": 0.08876381814479828, "learning_rate": 3.5960598166804366e-05, "loss": 0.0027, "step": 4160 }, { "epoch": 0.22978793903247183, "grad_norm": 3.158669948577881, "learning_rate": 3.595844216134362e-05, "loss": 0.49, "step": 4161 }, { "epoch": 0.22984316324276563, "grad_norm": 3.1093931198120117, "learning_rate": 3.5956285645326876e-05, "loss": 0.7695, "step": 4162 }, { "epoch": 0.22989838745305943, "grad_norm": 0.4329175651073456, "learning_rate": 3.595412861882313e-05, "loss": 0.0117, "step": 4163 }, { "epoch": 0.2299536116633532, "grad_norm": 3.564815044403076, "learning_rate": 3.595197108190139e-05, "loss": 0.4961, "step": 4164 }, { "epoch": 0.230008835873647, "grad_norm": 2.0158207416534424, "learning_rate": 3.594981303463068e-05, "loss": 0.119, "step": 4165 }, { "epoch": 0.2300640600839408, "grad_norm": 0.1866401880979538, "learning_rate": 3.594765447708005e-05, "loss": 0.0083, "step": 4166 }, { "epoch": 0.2301192842942346, "grad_norm": 0.08838117867708206, "learning_rate": 3.594549540931855e-05, "loss": 0.0029, "step": 4167 }, { "epoch": 0.2301745085045284, "grad_norm": 0.08458582311868668, "learning_rate": 3.594333583141525e-05, "loss": 0.0013, "step": 4168 }, { "epoch": 0.23022973271482217, "grad_norm": 2.4344115257263184, "learning_rate": 3.594117574343926e-05, "loss": 0.1179, "step": 4169 }, { "epoch": 0.23028495692511597, "grad_norm": 5.261387348175049, "learning_rate": 3.593901514545967e-05, "loss": 1.0352, "step": 4170 }, { "epoch": 0.23034018113540977, "grad_norm": 0.15930067002773285, "learning_rate": 3.593685403754561e-05, "loss": 0.0035, "step": 4171 }, { "epoch": 0.23039540534570355, "grad_norm": 5.289316654205322, "learning_rate": 3.593469241976621e-05, "loss": 1.1986, "step": 4172 }, { "epoch": 0.23045062955599735, "grad_norm": 1.1647039651870728, "learning_rate": 3.5932530292190646e-05, "loss": 0.0519, "step": 4173 }, { "epoch": 0.23050585376629115, "grad_norm": 0.4296027421951294, "learning_rate": 3.593036765488808e-05, "loss": 0.0083, "step": 4174 }, { "epoch": 0.23056107797658493, "grad_norm": 1.0359318256378174, "learning_rate": 3.5928204507927695e-05, "loss": 0.1096, "step": 4175 }, { "epoch": 0.23061630218687873, "grad_norm": 3.0848541259765625, "learning_rate": 3.59260408513787e-05, "loss": 0.1437, "step": 4176 }, { "epoch": 0.23067152639717253, "grad_norm": 3.069749116897583, "learning_rate": 3.592387668531033e-05, "loss": 0.5982, "step": 4177 }, { "epoch": 0.2307267506074663, "grad_norm": 0.1939985454082489, "learning_rate": 3.59217120097918e-05, "loss": 0.0045, "step": 4178 }, { "epoch": 0.2307819748177601, "grad_norm": 3.1613316535949707, "learning_rate": 3.591954682489238e-05, "loss": 0.5726, "step": 4179 }, { "epoch": 0.23083719902805389, "grad_norm": 1.7385891675949097, "learning_rate": 3.591738113068134e-05, "loss": 0.2385, "step": 4180 }, { "epoch": 0.2308924232383477, "grad_norm": 0.8816854953765869, "learning_rate": 3.5915214927227956e-05, "loss": 0.0149, "step": 4181 }, { "epoch": 0.2309476474486415, "grad_norm": 0.026323841884732246, "learning_rate": 3.591304821460155e-05, "loss": 0.0012, "step": 4182 }, { "epoch": 0.23100287165893527, "grad_norm": 0.10188917815685272, "learning_rate": 3.5910880992871415e-05, "loss": 0.0041, "step": 4183 }, { "epoch": 0.23105809586922907, "grad_norm": 0.2442004680633545, "learning_rate": 3.5908713262106905e-05, "loss": 0.0098, "step": 4184 }, { "epoch": 0.23111332007952287, "grad_norm": 0.027928996831178665, "learning_rate": 3.590654502237737e-05, "loss": 0.001, "step": 4185 }, { "epoch": 0.23116854428981665, "grad_norm": 3.579242467880249, "learning_rate": 3.5904376273752174e-05, "loss": 0.6298, "step": 4186 }, { "epoch": 0.23122376850011045, "grad_norm": 5.197432041168213, "learning_rate": 3.5902207016300704e-05, "loss": 1.035, "step": 4187 }, { "epoch": 0.23127899271040425, "grad_norm": 1.105331540107727, "learning_rate": 3.5900037250092366e-05, "loss": 0.1023, "step": 4188 }, { "epoch": 0.23133421692069803, "grad_norm": 0.19686004519462585, "learning_rate": 3.589786697519657e-05, "loss": 0.0059, "step": 4189 }, { "epoch": 0.23138944113099183, "grad_norm": 3.2819812297821045, "learning_rate": 3.589569619168274e-05, "loss": 0.4653, "step": 4190 }, { "epoch": 0.23144466534128563, "grad_norm": 2.540698766708374, "learning_rate": 3.589352489962034e-05, "loss": 0.3718, "step": 4191 }, { "epoch": 0.2314998895515794, "grad_norm": 0.07077180594205856, "learning_rate": 3.589135309907883e-05, "loss": 0.0024, "step": 4192 }, { "epoch": 0.2315551137618732, "grad_norm": 0.4393142759799957, "learning_rate": 3.58891807901277e-05, "loss": 0.0123, "step": 4193 }, { "epoch": 0.23161033797216699, "grad_norm": 1.888399362564087, "learning_rate": 3.588700797283644e-05, "loss": 0.2252, "step": 4194 }, { "epoch": 0.2316655621824608, "grad_norm": 3.35302996635437, "learning_rate": 3.5884834647274564e-05, "loss": 1.0783, "step": 4195 }, { "epoch": 0.2317207863927546, "grad_norm": 0.4000615179538727, "learning_rate": 3.588266081351161e-05, "loss": 0.0088, "step": 4196 }, { "epoch": 0.23177601060304837, "grad_norm": 0.9640556573867798, "learning_rate": 3.5880486471617115e-05, "loss": 0.0397, "step": 4197 }, { "epoch": 0.23183123481334217, "grad_norm": 1.8725122213363647, "learning_rate": 3.587831162166065e-05, "loss": 0.2463, "step": 4198 }, { "epoch": 0.23188645902363597, "grad_norm": 0.055481962859630585, "learning_rate": 3.5876136263711794e-05, "loss": 0.0018, "step": 4199 }, { "epoch": 0.23194168323392975, "grad_norm": 0.03781228885054588, "learning_rate": 3.587396039784014e-05, "loss": 0.0016, "step": 4200 }, { "epoch": 0.23199690744422355, "grad_norm": 6.788931369781494, "learning_rate": 3.5871784024115306e-05, "loss": 0.5278, "step": 4201 }, { "epoch": 0.23205213165451735, "grad_norm": 4.708362579345703, "learning_rate": 3.586960714260691e-05, "loss": 1.4048, "step": 4202 }, { "epoch": 0.23210735586481113, "grad_norm": 9.204291343688965, "learning_rate": 3.586742975338461e-05, "loss": 1.9601, "step": 4203 }, { "epoch": 0.23216258007510493, "grad_norm": 5.916568756103516, "learning_rate": 3.586525185651805e-05, "loss": 1.641, "step": 4204 }, { "epoch": 0.23221780428539873, "grad_norm": 0.1727411448955536, "learning_rate": 3.5863073452076925e-05, "loss": 0.0049, "step": 4205 }, { "epoch": 0.2322730284956925, "grad_norm": 0.09550273418426514, "learning_rate": 3.586089454013092e-05, "loss": 0.0039, "step": 4206 }, { "epoch": 0.2323282527059863, "grad_norm": 1.4147496223449707, "learning_rate": 3.585871512074974e-05, "loss": 0.0841, "step": 4207 }, { "epoch": 0.23238347691628009, "grad_norm": 3.6131465435028076, "learning_rate": 3.585653519400311e-05, "loss": 0.4843, "step": 4208 }, { "epoch": 0.2324387011265739, "grad_norm": 0.6166078448295593, "learning_rate": 3.585435475996079e-05, "loss": 0.0195, "step": 4209 }, { "epoch": 0.2324939253368677, "grad_norm": 0.80058354139328, "learning_rate": 3.585217381869252e-05, "loss": 0.0211, "step": 4210 }, { "epoch": 0.23254914954716147, "grad_norm": 0.11066249758005142, "learning_rate": 3.584999237026808e-05, "loss": 0.0036, "step": 4211 }, { "epoch": 0.23260437375745527, "grad_norm": 1.02034592628479, "learning_rate": 3.5847810414757265e-05, "loss": 0.021, "step": 4212 }, { "epoch": 0.23265959796774907, "grad_norm": 0.1450939178466797, "learning_rate": 3.5845627952229874e-05, "loss": 0.0038, "step": 4213 }, { "epoch": 0.23271482217804285, "grad_norm": 0.07255443930625916, "learning_rate": 3.584344498275574e-05, "loss": 0.0029, "step": 4214 }, { "epoch": 0.23277004638833665, "grad_norm": 3.112440347671509, "learning_rate": 3.584126150640469e-05, "loss": 0.5841, "step": 4215 }, { "epoch": 0.23282527059863045, "grad_norm": 0.029297206550836563, "learning_rate": 3.583907752324659e-05, "loss": 0.001, "step": 4216 }, { "epoch": 0.23288049480892423, "grad_norm": 0.15050695836544037, "learning_rate": 3.58368930333513e-05, "loss": 0.0074, "step": 4217 }, { "epoch": 0.23293571901921803, "grad_norm": 0.5418540835380554, "learning_rate": 3.583470803678872e-05, "loss": 0.0206, "step": 4218 }, { "epoch": 0.2329909432295118, "grad_norm": 1.740671992301941, "learning_rate": 3.583252253362876e-05, "loss": 0.0176, "step": 4219 }, { "epoch": 0.2330461674398056, "grad_norm": 1.9830988645553589, "learning_rate": 3.583033652394132e-05, "loss": 0.2559, "step": 4220 }, { "epoch": 0.2331013916500994, "grad_norm": 0.056077565997838974, "learning_rate": 3.5828150007796356e-05, "loss": 0.0022, "step": 4221 }, { "epoch": 0.23315661586039318, "grad_norm": 1.140370488166809, "learning_rate": 3.5825962985263806e-05, "loss": 0.1473, "step": 4222 }, { "epoch": 0.233211840070687, "grad_norm": 3.670243501663208, "learning_rate": 3.5823775456413653e-05, "loss": 0.0957, "step": 4223 }, { "epoch": 0.2332670642809808, "grad_norm": 4.009696006774902, "learning_rate": 3.582158742131587e-05, "loss": 0.5442, "step": 4224 }, { "epoch": 0.23332228849127457, "grad_norm": 0.6200041770935059, "learning_rate": 3.581939888004046e-05, "loss": 0.0228, "step": 4225 }, { "epoch": 0.23337751270156837, "grad_norm": 4.420703411102295, "learning_rate": 3.581720983265745e-05, "loss": 0.477, "step": 4226 }, { "epoch": 0.23343273691186217, "grad_norm": 2.226435422897339, "learning_rate": 3.581502027923686e-05, "loss": 0.2627, "step": 4227 }, { "epoch": 0.23348796112215595, "grad_norm": 3.3972859382629395, "learning_rate": 3.5812830219848756e-05, "loss": 0.4631, "step": 4228 }, { "epoch": 0.23354318533244975, "grad_norm": 2.9730100631713867, "learning_rate": 3.5810639654563195e-05, "loss": 0.3753, "step": 4229 }, { "epoch": 0.23359840954274355, "grad_norm": 0.5031595826148987, "learning_rate": 3.580844858345026e-05, "loss": 0.0147, "step": 4230 }, { "epoch": 0.23365363375303733, "grad_norm": 1.988415241241455, "learning_rate": 3.580625700658005e-05, "loss": 0.2618, "step": 4231 }, { "epoch": 0.23370885796333113, "grad_norm": 0.6022909283638, "learning_rate": 3.580406492402268e-05, "loss": 0.0184, "step": 4232 }, { "epoch": 0.2337640821736249, "grad_norm": 2.2353458404541016, "learning_rate": 3.5801872335848276e-05, "loss": 0.4653, "step": 4233 }, { "epoch": 0.2338193063839187, "grad_norm": 2.597710609436035, "learning_rate": 3.5799679242126995e-05, "loss": 0.4104, "step": 4234 }, { "epoch": 0.2338745305942125, "grad_norm": 0.21585330367088318, "learning_rate": 3.579748564292899e-05, "loss": 0.0056, "step": 4235 }, { "epoch": 0.23392975480450628, "grad_norm": 0.23636452853679657, "learning_rate": 3.579529153832446e-05, "loss": 0.0071, "step": 4236 }, { "epoch": 0.2339849790148001, "grad_norm": 0.2694976031780243, "learning_rate": 3.579309692838357e-05, "loss": 0.0105, "step": 4237 }, { "epoch": 0.2340402032250939, "grad_norm": 3.9351248741149902, "learning_rate": 3.579090181317655e-05, "loss": 0.6317, "step": 4238 }, { "epoch": 0.23409542743538767, "grad_norm": 2.716991424560547, "learning_rate": 3.5788706192773635e-05, "loss": 0.2223, "step": 4239 }, { "epoch": 0.23415065164568147, "grad_norm": 3.418898820877075, "learning_rate": 3.578651006724505e-05, "loss": 0.3681, "step": 4240 }, { "epoch": 0.23420587585597527, "grad_norm": 2.9505422115325928, "learning_rate": 3.578431343666108e-05, "loss": 0.359, "step": 4241 }, { "epoch": 0.23426110006626905, "grad_norm": 3.303668975830078, "learning_rate": 3.578211630109198e-05, "loss": 0.6815, "step": 4242 }, { "epoch": 0.23431632427656285, "grad_norm": 0.051341041922569275, "learning_rate": 3.5779918660608045e-05, "loss": 0.0015, "step": 4243 }, { "epoch": 0.23437154848685665, "grad_norm": 3.0496408939361572, "learning_rate": 3.5777720515279594e-05, "loss": 0.7882, "step": 4244 }, { "epoch": 0.23442677269715043, "grad_norm": 0.013205936178565025, "learning_rate": 3.577552186517695e-05, "loss": 0.0005, "step": 4245 }, { "epoch": 0.23448199690744423, "grad_norm": 1.737571358680725, "learning_rate": 3.577332271037044e-05, "loss": 0.3145, "step": 4246 }, { "epoch": 0.234537221117738, "grad_norm": 1.0052014589309692, "learning_rate": 3.577112305093044e-05, "loss": 0.034, "step": 4247 }, { "epoch": 0.2345924453280318, "grad_norm": 0.024143770337104797, "learning_rate": 3.5768922886927314e-05, "loss": 0.0012, "step": 4248 }, { "epoch": 0.2346476695383256, "grad_norm": 3.2486298084259033, "learning_rate": 3.576672221843145e-05, "loss": 0.5905, "step": 4249 }, { "epoch": 0.23470289374861938, "grad_norm": 0.8200429081916809, "learning_rate": 3.576452104551326e-05, "loss": 0.0229, "step": 4250 }, { "epoch": 0.2347581179589132, "grad_norm": 3.2328577041625977, "learning_rate": 3.576231936824316e-05, "loss": 0.1523, "step": 4251 }, { "epoch": 0.234813342169207, "grad_norm": 0.9316455721855164, "learning_rate": 3.5760117186691594e-05, "loss": 0.0295, "step": 4252 }, { "epoch": 0.23486856637950076, "grad_norm": 0.5499038100242615, "learning_rate": 3.575791450092901e-05, "loss": 0.0187, "step": 4253 }, { "epoch": 0.23492379058979457, "grad_norm": 0.1291338950395584, "learning_rate": 3.575571131102588e-05, "loss": 0.0034, "step": 4254 }, { "epoch": 0.23497901480008837, "grad_norm": 2.1938910484313965, "learning_rate": 3.575350761705268e-05, "loss": 0.2539, "step": 4255 }, { "epoch": 0.23503423901038215, "grad_norm": 0.9543353319168091, "learning_rate": 3.575130341907994e-05, "loss": 0.1405, "step": 4256 }, { "epoch": 0.23508946322067595, "grad_norm": 0.08036485314369202, "learning_rate": 3.5749098717178156e-05, "loss": 0.0023, "step": 4257 }, { "epoch": 0.23514468743096975, "grad_norm": 0.08441752195358276, "learning_rate": 3.574689351141786e-05, "loss": 0.0025, "step": 4258 }, { "epoch": 0.23519991164126353, "grad_norm": 0.03772495314478874, "learning_rate": 3.574468780186962e-05, "loss": 0.0009, "step": 4259 }, { "epoch": 0.23525513585155733, "grad_norm": 3.6338837146759033, "learning_rate": 3.5742481588603995e-05, "loss": 0.5289, "step": 4260 }, { "epoch": 0.2353103600618511, "grad_norm": 0.025425581261515617, "learning_rate": 3.574027487169156e-05, "loss": 0.0009, "step": 4261 }, { "epoch": 0.2353655842721449, "grad_norm": 0.035141706466674805, "learning_rate": 3.573806765120293e-05, "loss": 0.0011, "step": 4262 }, { "epoch": 0.2354208084824387, "grad_norm": 5.030677318572998, "learning_rate": 3.573585992720871e-05, "loss": 0.9273, "step": 4263 }, { "epoch": 0.23547603269273248, "grad_norm": 2.429217576980591, "learning_rate": 3.573365169977953e-05, "loss": 0.1612, "step": 4264 }, { "epoch": 0.2355312569030263, "grad_norm": 4.558441162109375, "learning_rate": 3.573144296898604e-05, "loss": 0.246, "step": 4265 }, { "epoch": 0.2355864811133201, "grad_norm": 2.642063856124878, "learning_rate": 3.5729233734898904e-05, "loss": 0.1393, "step": 4266 }, { "epoch": 0.23564170532361386, "grad_norm": 0.7423669099807739, "learning_rate": 3.57270239975888e-05, "loss": 0.0884, "step": 4267 }, { "epoch": 0.23569692953390767, "grad_norm": 3.0117104053497314, "learning_rate": 3.572481375712643e-05, "loss": 0.5588, "step": 4268 }, { "epoch": 0.23575215374420147, "grad_norm": 3.547346830368042, "learning_rate": 3.5722603013582496e-05, "loss": 0.4176, "step": 4269 }, { "epoch": 0.23580737795449525, "grad_norm": 6.942080974578857, "learning_rate": 3.572039176702773e-05, "loss": 1.8342, "step": 4270 }, { "epoch": 0.23586260216478905, "grad_norm": 0.7556229829788208, "learning_rate": 3.571818001753288e-05, "loss": 0.0251, "step": 4271 }, { "epoch": 0.23591782637508282, "grad_norm": 1.4775923490524292, "learning_rate": 3.571596776516871e-05, "loss": 0.1124, "step": 4272 }, { "epoch": 0.23597305058537663, "grad_norm": 3.150066375732422, "learning_rate": 3.571375501000599e-05, "loss": 0.3987, "step": 4273 }, { "epoch": 0.23602827479567043, "grad_norm": 0.8045300245285034, "learning_rate": 3.5711541752115496e-05, "loss": 0.0343, "step": 4274 }, { "epoch": 0.2360834990059642, "grad_norm": 0.07818302512168884, "learning_rate": 3.570932799156807e-05, "loss": 0.0037, "step": 4275 }, { "epoch": 0.236138723216258, "grad_norm": 0.618537187576294, "learning_rate": 3.570711372843451e-05, "loss": 0.0259, "step": 4276 }, { "epoch": 0.2361939474265518, "grad_norm": 0.3660176992416382, "learning_rate": 3.570489896278566e-05, "loss": 0.0118, "step": 4277 }, { "epoch": 0.23624917163684558, "grad_norm": 0.09885133057832718, "learning_rate": 3.57026836946924e-05, "loss": 0.0026, "step": 4278 }, { "epoch": 0.2363043958471394, "grad_norm": 2.886939525604248, "learning_rate": 3.570046792422558e-05, "loss": 0.4063, "step": 4279 }, { "epoch": 0.2363596200574332, "grad_norm": 0.05222577229142189, "learning_rate": 3.5698251651456085e-05, "loss": 0.0021, "step": 4280 }, { "epoch": 0.23641484426772696, "grad_norm": 0.1665014624595642, "learning_rate": 3.569603487645483e-05, "loss": 0.0038, "step": 4281 }, { "epoch": 0.23647006847802077, "grad_norm": 0.04020398110151291, "learning_rate": 3.569381759929274e-05, "loss": 0.0015, "step": 4282 }, { "epoch": 0.23652529268831457, "grad_norm": 2.3201069831848145, "learning_rate": 3.5691599820040744e-05, "loss": 0.4352, "step": 4283 }, { "epoch": 0.23658051689860835, "grad_norm": 1.6020197868347168, "learning_rate": 3.56893815387698e-05, "loss": 0.0558, "step": 4284 }, { "epoch": 0.23663574110890215, "grad_norm": 0.03051205910742283, "learning_rate": 3.568716275555087e-05, "loss": 0.0011, "step": 4285 }, { "epoch": 0.23669096531919592, "grad_norm": 4.178577899932861, "learning_rate": 3.568494347045495e-05, "loss": 0.2267, "step": 4286 }, { "epoch": 0.23674618952948973, "grad_norm": 3.454028367996216, "learning_rate": 3.568272368355303e-05, "loss": 0.3749, "step": 4287 }, { "epoch": 0.23680141373978353, "grad_norm": 0.048125941306352615, "learning_rate": 3.5680503394916135e-05, "loss": 0.0015, "step": 4288 }, { "epoch": 0.2368566379500773, "grad_norm": 2.4291915893554688, "learning_rate": 3.5678282604615293e-05, "loss": 0.1271, "step": 4289 }, { "epoch": 0.2369118621603711, "grad_norm": 3.681246757507324, "learning_rate": 3.5676061312721564e-05, "loss": 1.7088, "step": 4290 }, { "epoch": 0.2369670863706649, "grad_norm": 2.507371187210083, "learning_rate": 3.5673839519306004e-05, "loss": 0.1743, "step": 4291 }, { "epoch": 0.23702231058095868, "grad_norm": 1.485144853591919, "learning_rate": 3.5671617224439695e-05, "loss": 0.0504, "step": 4292 }, { "epoch": 0.2370775347912525, "grad_norm": 2.6219940185546875, "learning_rate": 3.566939442819373e-05, "loss": 0.5573, "step": 4293 }, { "epoch": 0.2371327590015463, "grad_norm": 0.19376710057258606, "learning_rate": 3.566717113063924e-05, "loss": 0.008, "step": 4294 }, { "epoch": 0.23718798321184006, "grad_norm": 3.8585517406463623, "learning_rate": 3.5664947331847336e-05, "loss": 0.8942, "step": 4295 }, { "epoch": 0.23724320742213387, "grad_norm": 0.08005454391241074, "learning_rate": 3.566272303188917e-05, "loss": 0.0027, "step": 4296 }, { "epoch": 0.23729843163242767, "grad_norm": 3.090367555618286, "learning_rate": 3.56604982308359e-05, "loss": 0.3552, "step": 4297 }, { "epoch": 0.23735365584272144, "grad_norm": 3.6349103450775146, "learning_rate": 3.565827292875871e-05, "loss": 0.1203, "step": 4298 }, { "epoch": 0.23740888005301525, "grad_norm": 0.24935641884803772, "learning_rate": 3.56560471257288e-05, "loss": 0.0109, "step": 4299 }, { "epoch": 0.23746410426330902, "grad_norm": 4.644767761230469, "learning_rate": 3.565382082181737e-05, "loss": 1.1428, "step": 4300 }, { "epoch": 0.23751932847360283, "grad_norm": 0.10438613593578339, "learning_rate": 3.565159401709564e-05, "loss": 0.0028, "step": 4301 }, { "epoch": 0.23757455268389663, "grad_norm": 1.807239055633545, "learning_rate": 3.5649366711634864e-05, "loss": 0.4096, "step": 4302 }, { "epoch": 0.2376297768941904, "grad_norm": 0.10675454139709473, "learning_rate": 3.564713890550629e-05, "loss": 0.0049, "step": 4303 }, { "epoch": 0.2376850011044842, "grad_norm": 0.10212329030036926, "learning_rate": 3.5644910598781206e-05, "loss": 0.0032, "step": 4304 }, { "epoch": 0.237740225314778, "grad_norm": 0.9250826835632324, "learning_rate": 3.5642681791530895e-05, "loss": 0.0294, "step": 4305 }, { "epoch": 0.23779544952507178, "grad_norm": 3.3891851902008057, "learning_rate": 3.564045248382665e-05, "loss": 0.8599, "step": 4306 }, { "epoch": 0.2378506737353656, "grad_norm": 4.044816970825195, "learning_rate": 3.5638222675739806e-05, "loss": 0.4944, "step": 4307 }, { "epoch": 0.2379058979456594, "grad_norm": 0.18577080965042114, "learning_rate": 3.56359923673417e-05, "loss": 0.0061, "step": 4308 }, { "epoch": 0.23796112215595316, "grad_norm": 3.556098699569702, "learning_rate": 3.563376155870369e-05, "loss": 0.4909, "step": 4309 }, { "epoch": 0.23801634636624697, "grad_norm": 0.920471727848053, "learning_rate": 3.563153024989714e-05, "loss": 0.0336, "step": 4310 }, { "epoch": 0.23807157057654074, "grad_norm": 0.2100995033979416, "learning_rate": 3.562929844099342e-05, "loss": 0.0065, "step": 4311 }, { "epoch": 0.23812679478683454, "grad_norm": 1.8975417613983154, "learning_rate": 3.5627066132063966e-05, "loss": 0.0721, "step": 4312 }, { "epoch": 0.23818201899712835, "grad_norm": 1.235483169555664, "learning_rate": 3.562483332318017e-05, "loss": 0.056, "step": 4313 }, { "epoch": 0.23823724320742212, "grad_norm": 1.8544625043869019, "learning_rate": 3.562260001441348e-05, "loss": 0.204, "step": 4314 }, { "epoch": 0.23829246741771593, "grad_norm": 0.07239578664302826, "learning_rate": 3.562036620583533e-05, "loss": 0.0021, "step": 4315 }, { "epoch": 0.23834769162800973, "grad_norm": 4.149805545806885, "learning_rate": 3.561813189751721e-05, "loss": 0.7429, "step": 4316 }, { "epoch": 0.2384029158383035, "grad_norm": 0.09689129889011383, "learning_rate": 3.5615897089530574e-05, "loss": 0.0048, "step": 4317 }, { "epoch": 0.2384581400485973, "grad_norm": 1.2960634231567383, "learning_rate": 3.561366178194694e-05, "loss": 0.1982, "step": 4318 }, { "epoch": 0.2385133642588911, "grad_norm": 0.07328646630048752, "learning_rate": 3.5611425974837816e-05, "loss": 0.0028, "step": 4319 }, { "epoch": 0.23856858846918488, "grad_norm": 0.5854148864746094, "learning_rate": 3.560918966827473e-05, "loss": 0.0161, "step": 4320 }, { "epoch": 0.2386238126794787, "grad_norm": 3.4161465167999268, "learning_rate": 3.560695286232923e-05, "loss": 0.4891, "step": 4321 }, { "epoch": 0.2386790368897725, "grad_norm": 1.0125895738601685, "learning_rate": 3.560471555707288e-05, "loss": 0.0266, "step": 4322 }, { "epoch": 0.23873426110006626, "grad_norm": 0.047985777258872986, "learning_rate": 3.560247775257725e-05, "loss": 0.0012, "step": 4323 }, { "epoch": 0.23878948531036007, "grad_norm": 2.6911590099334717, "learning_rate": 3.560023944891394e-05, "loss": 0.0389, "step": 4324 }, { "epoch": 0.23884470952065384, "grad_norm": 1.381659746170044, "learning_rate": 3.559800064615456e-05, "loss": 0.0169, "step": 4325 }, { "epoch": 0.23889993373094764, "grad_norm": 0.2746438980102539, "learning_rate": 3.559576134437073e-05, "loss": 0.012, "step": 4326 }, { "epoch": 0.23895515794124145, "grad_norm": 0.11406034976243973, "learning_rate": 3.559352154363409e-05, "loss": 0.0031, "step": 4327 }, { "epoch": 0.23901038215153522, "grad_norm": 2.2167365550994873, "learning_rate": 3.559128124401631e-05, "loss": 0.2219, "step": 4328 }, { "epoch": 0.23906560636182903, "grad_norm": 0.06416116654872894, "learning_rate": 3.5589040445589065e-05, "loss": 0.0021, "step": 4329 }, { "epoch": 0.23912083057212283, "grad_norm": 0.21254928410053253, "learning_rate": 3.5586799148424025e-05, "loss": 0.0063, "step": 4330 }, { "epoch": 0.2391760547824166, "grad_norm": 2.5738742351531982, "learning_rate": 3.558455735259291e-05, "loss": 0.1398, "step": 4331 }, { "epoch": 0.2392312789927104, "grad_norm": 1.7152401208877563, "learning_rate": 3.5582315058167434e-05, "loss": 0.0356, "step": 4332 }, { "epoch": 0.2392865032030042, "grad_norm": 1.9750014543533325, "learning_rate": 3.5580072265219336e-05, "loss": 0.2359, "step": 4333 }, { "epoch": 0.23934172741329798, "grad_norm": 3.41560435295105, "learning_rate": 3.5577828973820376e-05, "loss": 0.8332, "step": 4334 }, { "epoch": 0.23939695162359179, "grad_norm": 2.4829623699188232, "learning_rate": 3.557558518404233e-05, "loss": 0.2271, "step": 4335 }, { "epoch": 0.2394521758338856, "grad_norm": 0.05303018540143967, "learning_rate": 3.557334089595696e-05, "loss": 0.0021, "step": 4336 }, { "epoch": 0.23950740004417936, "grad_norm": 0.20303915441036224, "learning_rate": 3.5571096109636073e-05, "loss": 0.0062, "step": 4337 }, { "epoch": 0.23956262425447317, "grad_norm": 0.05583176389336586, "learning_rate": 3.5568850825151505e-05, "loss": 0.0018, "step": 4338 }, { "epoch": 0.23961784846476694, "grad_norm": 0.83052659034729, "learning_rate": 3.5566605042575074e-05, "loss": 0.0247, "step": 4339 }, { "epoch": 0.23967307267506074, "grad_norm": 0.9771982431411743, "learning_rate": 3.5564358761978635e-05, "loss": 0.0243, "step": 4340 }, { "epoch": 0.23972829688535455, "grad_norm": 0.4590972065925598, "learning_rate": 3.5562111983434044e-05, "loss": 0.0094, "step": 4341 }, { "epoch": 0.23978352109564832, "grad_norm": 0.2577248513698578, "learning_rate": 3.555986470701319e-05, "loss": 0.0072, "step": 4342 }, { "epoch": 0.23983874530594212, "grad_norm": 4.989217758178711, "learning_rate": 3.555761693278796e-05, "loss": 2.0432, "step": 4343 }, { "epoch": 0.23989396951623593, "grad_norm": 0.9055227637290955, "learning_rate": 3.555536866083028e-05, "loss": 0.0253, "step": 4344 }, { "epoch": 0.2399491937265297, "grad_norm": 3.555260419845581, "learning_rate": 3.5553119891212074e-05, "loss": 1.2444, "step": 4345 }, { "epoch": 0.2400044179368235, "grad_norm": 0.14724665880203247, "learning_rate": 3.555087062400528e-05, "loss": 0.0037, "step": 4346 }, { "epoch": 0.2400596421471173, "grad_norm": 0.8353533744812012, "learning_rate": 3.5548620859281865e-05, "loss": 0.1295, "step": 4347 }, { "epoch": 0.24011486635741108, "grad_norm": 0.358844518661499, "learning_rate": 3.55463705971138e-05, "loss": 0.0088, "step": 4348 }, { "epoch": 0.24017009056770489, "grad_norm": 0.12477673590183258, "learning_rate": 3.554411983757309e-05, "loss": 0.0029, "step": 4349 }, { "epoch": 0.24022531477799866, "grad_norm": 0.09904822707176208, "learning_rate": 3.554186858073173e-05, "loss": 0.003, "step": 4350 }, { "epoch": 0.24028053898829246, "grad_norm": 5.009559631347656, "learning_rate": 3.553961682666175e-05, "loss": 0.4093, "step": 4351 }, { "epoch": 0.24033576319858627, "grad_norm": 4.636260032653809, "learning_rate": 3.5537364575435185e-05, "loss": 0.6477, "step": 4352 }, { "epoch": 0.24039098740888004, "grad_norm": 5.156913757324219, "learning_rate": 3.5535111827124097e-05, "loss": 0.9299, "step": 4353 }, { "epoch": 0.24044621161917384, "grad_norm": 3.5657827854156494, "learning_rate": 3.553285858180055e-05, "loss": 0.678, "step": 4354 }, { "epoch": 0.24050143582946765, "grad_norm": 2.919926166534424, "learning_rate": 3.5530604839536644e-05, "loss": 0.163, "step": 4355 }, { "epoch": 0.24055666003976142, "grad_norm": 2.5036842823028564, "learning_rate": 3.552835060040448e-05, "loss": 0.4487, "step": 4356 }, { "epoch": 0.24061188425005522, "grad_norm": 0.07454082369804382, "learning_rate": 3.552609586447615e-05, "loss": 0.0027, "step": 4357 }, { "epoch": 0.24066710846034903, "grad_norm": 2.4253525733947754, "learning_rate": 3.5523840631823834e-05, "loss": 0.4596, "step": 4358 }, { "epoch": 0.2407223326706428, "grad_norm": 0.9276666641235352, "learning_rate": 3.552158490251966e-05, "loss": 0.0299, "step": 4359 }, { "epoch": 0.2407775568809366, "grad_norm": 2.4138522148132324, "learning_rate": 3.551932867663579e-05, "loss": 0.2091, "step": 4360 }, { "epoch": 0.2408327810912304, "grad_norm": 5.241978645324707, "learning_rate": 3.5517071954244414e-05, "loss": 1.7047, "step": 4361 }, { "epoch": 0.24088800530152418, "grad_norm": 0.08634354919195175, "learning_rate": 3.5514814735417734e-05, "loss": 0.0024, "step": 4362 }, { "epoch": 0.24094322951181799, "grad_norm": 1.6614595651626587, "learning_rate": 3.551255702022796e-05, "loss": 0.1028, "step": 4363 }, { "epoch": 0.24099845372211176, "grad_norm": 3.0313985347747803, "learning_rate": 3.5510298808747335e-05, "loss": 0.433, "step": 4364 }, { "epoch": 0.24105367793240556, "grad_norm": 0.16925975680351257, "learning_rate": 3.5508040101048085e-05, "loss": 0.0044, "step": 4365 }, { "epoch": 0.24110890214269937, "grad_norm": 2.758545398712158, "learning_rate": 3.5505780897202485e-05, "loss": 0.3211, "step": 4366 }, { "epoch": 0.24116412635299314, "grad_norm": 3.3123726844787598, "learning_rate": 3.5503521197282803e-05, "loss": 0.7136, "step": 4367 }, { "epoch": 0.24121935056328694, "grad_norm": 0.15787723660469055, "learning_rate": 3.550126100136135e-05, "loss": 0.0045, "step": 4368 }, { "epoch": 0.24127457477358075, "grad_norm": 1.7952088117599487, "learning_rate": 3.5499000309510427e-05, "loss": 0.1185, "step": 4369 }, { "epoch": 0.24132979898387452, "grad_norm": 1.6905062198638916, "learning_rate": 3.549673912180236e-05, "loss": 0.4652, "step": 4370 }, { "epoch": 0.24138502319416832, "grad_norm": 0.016903501003980637, "learning_rate": 3.549447743830949e-05, "loss": 0.0005, "step": 4371 }, { "epoch": 0.24144024740446213, "grad_norm": 0.6445388793945312, "learning_rate": 3.549221525910418e-05, "loss": 0.0166, "step": 4372 }, { "epoch": 0.2414954716147559, "grad_norm": 0.11472529917955399, "learning_rate": 3.548995258425879e-05, "loss": 0.0028, "step": 4373 }, { "epoch": 0.2415506958250497, "grad_norm": 2.026512861251831, "learning_rate": 3.548768941384573e-05, "loss": 0.2774, "step": 4374 }, { "epoch": 0.2416059200353435, "grad_norm": 0.5573537945747375, "learning_rate": 3.548542574793738e-05, "loss": 0.0214, "step": 4375 }, { "epoch": 0.24166114424563728, "grad_norm": 0.39156293869018555, "learning_rate": 3.548316158660619e-05, "loss": 0.0144, "step": 4376 }, { "epoch": 0.24171636845593109, "grad_norm": 0.04500587657094002, "learning_rate": 3.548089692992458e-05, "loss": 0.0013, "step": 4377 }, { "epoch": 0.24177159266622486, "grad_norm": 4.347908973693848, "learning_rate": 3.5478631777965e-05, "loss": 1.1854, "step": 4378 }, { "epoch": 0.24182681687651866, "grad_norm": 0.5361732244491577, "learning_rate": 3.5476366130799924e-05, "loss": 0.0156, "step": 4379 }, { "epoch": 0.24188204108681247, "grad_norm": 3.082134962081909, "learning_rate": 3.547409998850184e-05, "loss": 0.8767, "step": 4380 }, { "epoch": 0.24193726529710624, "grad_norm": 1.3430372476577759, "learning_rate": 3.5471833351143246e-05, "loss": 0.0609, "step": 4381 }, { "epoch": 0.24199248950740004, "grad_norm": 2.1205828189849854, "learning_rate": 3.546956621879665e-05, "loss": 0.2424, "step": 4382 }, { "epoch": 0.24204771371769385, "grad_norm": 1.6338869333267212, "learning_rate": 3.5467298591534586e-05, "loss": 0.2917, "step": 4383 }, { "epoch": 0.24210293792798762, "grad_norm": 0.1553889364004135, "learning_rate": 3.546503046942962e-05, "loss": 0.0037, "step": 4384 }, { "epoch": 0.24215816213828142, "grad_norm": 0.12690894305706024, "learning_rate": 3.5462761852554296e-05, "loss": 0.0037, "step": 4385 }, { "epoch": 0.24221338634857523, "grad_norm": 0.9991120100021362, "learning_rate": 3.5460492740981205e-05, "loss": 0.0288, "step": 4386 }, { "epoch": 0.242268610558869, "grad_norm": 0.8540899753570557, "learning_rate": 3.545822313478293e-05, "loss": 0.0513, "step": 4387 }, { "epoch": 0.2423238347691628, "grad_norm": 3.7962896823883057, "learning_rate": 3.545595303403209e-05, "loss": 0.5482, "step": 4388 }, { "epoch": 0.2423790589794566, "grad_norm": 4.339117527008057, "learning_rate": 3.545368243880131e-05, "loss": 0.6824, "step": 4389 }, { "epoch": 0.24243428318975038, "grad_norm": 0.1032332256436348, "learning_rate": 3.545141134916324e-05, "loss": 0.0037, "step": 4390 }, { "epoch": 0.24248950740004419, "grad_norm": 0.2679625153541565, "learning_rate": 3.544913976519053e-05, "loss": 0.0088, "step": 4391 }, { "epoch": 0.24254473161033796, "grad_norm": 0.9684996604919434, "learning_rate": 3.5446867686955854e-05, "loss": 0.025, "step": 4392 }, { "epoch": 0.24259995582063176, "grad_norm": 0.08328013867139816, "learning_rate": 3.544459511453191e-05, "loss": 0.0029, "step": 4393 }, { "epoch": 0.24265518003092557, "grad_norm": 3.9743666648864746, "learning_rate": 3.54423220479914e-05, "loss": 0.3612, "step": 4394 }, { "epoch": 0.24271040424121934, "grad_norm": 2.4337894916534424, "learning_rate": 3.544004848740704e-05, "loss": 0.229, "step": 4395 }, { "epoch": 0.24276562845151314, "grad_norm": 0.051156383007764816, "learning_rate": 3.543777443285158e-05, "loss": 0.0015, "step": 4396 }, { "epoch": 0.24282085266180695, "grad_norm": 1.8093085289001465, "learning_rate": 3.543549988439776e-05, "loss": 0.0766, "step": 4397 }, { "epoch": 0.24287607687210072, "grad_norm": 0.17849652469158173, "learning_rate": 3.5433224842118364e-05, "loss": 0.0038, "step": 4398 }, { "epoch": 0.24293130108239452, "grad_norm": 3.0564234256744385, "learning_rate": 3.5430949306086164e-05, "loss": 0.2445, "step": 4399 }, { "epoch": 0.24298652529268833, "grad_norm": 2.8730039596557617, "learning_rate": 3.542867327637396e-05, "loss": 0.0561, "step": 4400 }, { "epoch": 0.2430417495029821, "grad_norm": 1.84971022605896, "learning_rate": 3.542639675305459e-05, "loss": 0.1007, "step": 4401 }, { "epoch": 0.2430969737132759, "grad_norm": 1.9227814674377441, "learning_rate": 3.542411973620085e-05, "loss": 0.0912, "step": 4402 }, { "epoch": 0.24315219792356968, "grad_norm": 0.7263188362121582, "learning_rate": 3.542184222588562e-05, "loss": 0.0215, "step": 4403 }, { "epoch": 0.24320742213386348, "grad_norm": 2.783956289291382, "learning_rate": 3.5419564222181753e-05, "loss": 0.4883, "step": 4404 }, { "epoch": 0.24326264634415729, "grad_norm": 4.673562526702881, "learning_rate": 3.541728572516213e-05, "loss": 0.2201, "step": 4405 }, { "epoch": 0.24331787055445106, "grad_norm": 0.8258641362190247, "learning_rate": 3.5415006734899645e-05, "loss": 0.0254, "step": 4406 }, { "epoch": 0.24337309476474486, "grad_norm": 1.41645085811615, "learning_rate": 3.541272725146721e-05, "loss": 0.0299, "step": 4407 }, { "epoch": 0.24342831897503867, "grad_norm": 0.05197831243276596, "learning_rate": 3.541044727493775e-05, "loss": 0.0014, "step": 4408 }, { "epoch": 0.24348354318533244, "grad_norm": 1.1349135637283325, "learning_rate": 3.540816680538421e-05, "loss": 0.0434, "step": 4409 }, { "epoch": 0.24353876739562624, "grad_norm": 3.9585916996002197, "learning_rate": 3.540588584287955e-05, "loss": 0.7954, "step": 4410 }, { "epoch": 0.24359399160592005, "grad_norm": 0.100812628865242, "learning_rate": 3.540360438749675e-05, "loss": 0.003, "step": 4411 }, { "epoch": 0.24364921581621382, "grad_norm": 2.2846691608428955, "learning_rate": 3.540132243930878e-05, "loss": 0.2252, "step": 4412 }, { "epoch": 0.24370444002650762, "grad_norm": 2.639111280441284, "learning_rate": 3.5399039998388666e-05, "loss": 0.4333, "step": 4413 }, { "epoch": 0.24375966423680143, "grad_norm": 2.5916714668273926, "learning_rate": 3.539675706480943e-05, "loss": 0.3195, "step": 4414 }, { "epoch": 0.2438148884470952, "grad_norm": 0.8706675171852112, "learning_rate": 3.539447363864409e-05, "loss": 0.0348, "step": 4415 }, { "epoch": 0.243870112657389, "grad_norm": 0.08996684849262238, "learning_rate": 3.5392189719965726e-05, "loss": 0.0025, "step": 4416 }, { "epoch": 0.24392533686768278, "grad_norm": 4.003444194793701, "learning_rate": 3.538990530884738e-05, "loss": 1.3014, "step": 4417 }, { "epoch": 0.24398056107797658, "grad_norm": 1.1973202228546143, "learning_rate": 3.538762040536216e-05, "loss": 0.0329, "step": 4418 }, { "epoch": 0.24403578528827038, "grad_norm": 1.2747559547424316, "learning_rate": 3.538533500958315e-05, "loss": 0.0523, "step": 4419 }, { "epoch": 0.24409100949856416, "grad_norm": 3.4819109439849854, "learning_rate": 3.5383049121583486e-05, "loss": 0.3439, "step": 4420 }, { "epoch": 0.24414623370885796, "grad_norm": 1.9111356735229492, "learning_rate": 3.538076274143627e-05, "loss": 0.3587, "step": 4421 }, { "epoch": 0.24420145791915177, "grad_norm": 1.6482092142105103, "learning_rate": 3.537847586921467e-05, "loss": 0.172, "step": 4422 }, { "epoch": 0.24425668212944554, "grad_norm": 2.8259353637695312, "learning_rate": 3.537618850499185e-05, "loss": 0.3793, "step": 4423 }, { "epoch": 0.24431190633973934, "grad_norm": 0.04309055954217911, "learning_rate": 3.537390064884099e-05, "loss": 0.0014, "step": 4424 }, { "epoch": 0.24436713055003315, "grad_norm": 1.9201645851135254, "learning_rate": 3.5371612300835276e-05, "loss": 0.1206, "step": 4425 }, { "epoch": 0.24442235476032692, "grad_norm": 3.264359474182129, "learning_rate": 3.5369323461047924e-05, "loss": 0.7674, "step": 4426 }, { "epoch": 0.24447757897062072, "grad_norm": 2.341810941696167, "learning_rate": 3.536703412955216e-05, "loss": 0.1643, "step": 4427 }, { "epoch": 0.24453280318091453, "grad_norm": 0.5901448726654053, "learning_rate": 3.536474430642123e-05, "loss": 0.0174, "step": 4428 }, { "epoch": 0.2445880273912083, "grad_norm": 3.804131269454956, "learning_rate": 3.5362453991728384e-05, "loss": 0.7996, "step": 4429 }, { "epoch": 0.2446432516015021, "grad_norm": 0.0384121835231781, "learning_rate": 3.5360163185546897e-05, "loss": 0.0014, "step": 4430 }, { "epoch": 0.24469847581179588, "grad_norm": 0.13947196304798126, "learning_rate": 3.535787188795006e-05, "loss": 0.0047, "step": 4431 }, { "epoch": 0.24475370002208968, "grad_norm": 0.5614922642707825, "learning_rate": 3.535558009901119e-05, "loss": 0.0206, "step": 4432 }, { "epoch": 0.24480892423238348, "grad_norm": 1.8401411771774292, "learning_rate": 3.5353287818803586e-05, "loss": 0.1299, "step": 4433 }, { "epoch": 0.24486414844267726, "grad_norm": 0.13272498548030853, "learning_rate": 3.535099504740061e-05, "loss": 0.0045, "step": 4434 }, { "epoch": 0.24491937265297106, "grad_norm": 0.08566915988922119, "learning_rate": 3.534870178487558e-05, "loss": 0.0033, "step": 4435 }, { "epoch": 0.24497459686326487, "grad_norm": 3.396472215652466, "learning_rate": 3.53464080313019e-05, "loss": 0.4853, "step": 4436 }, { "epoch": 0.24502982107355864, "grad_norm": 0.2362608015537262, "learning_rate": 3.5344113786752934e-05, "loss": 0.0112, "step": 4437 }, { "epoch": 0.24508504528385244, "grad_norm": 1.1819744110107422, "learning_rate": 3.534181905130208e-05, "loss": 0.178, "step": 4438 }, { "epoch": 0.24514026949414625, "grad_norm": 3.415886640548706, "learning_rate": 3.533952382502277e-05, "loss": 0.9034, "step": 4439 }, { "epoch": 0.24519549370444002, "grad_norm": 1.208577036857605, "learning_rate": 3.533722810798841e-05, "loss": 0.0212, "step": 4440 }, { "epoch": 0.24525071791473382, "grad_norm": 1.416298747062683, "learning_rate": 3.533493190027247e-05, "loss": 0.031, "step": 4441 }, { "epoch": 0.2453059421250276, "grad_norm": 0.5094972848892212, "learning_rate": 3.533263520194839e-05, "loss": 0.0137, "step": 4442 }, { "epoch": 0.2453611663353214, "grad_norm": 0.9953457117080688, "learning_rate": 3.533033801308967e-05, "loss": 0.0238, "step": 4443 }, { "epoch": 0.2454163905456152, "grad_norm": 2.828728437423706, "learning_rate": 3.532804033376979e-05, "loss": 0.9139, "step": 4444 }, { "epoch": 0.24547161475590898, "grad_norm": 0.3040188252925873, "learning_rate": 3.532574216406226e-05, "loss": 0.0112, "step": 4445 }, { "epoch": 0.24552683896620278, "grad_norm": 0.06657597422599792, "learning_rate": 3.5323443504040615e-05, "loss": 0.0018, "step": 4446 }, { "epoch": 0.24558206317649658, "grad_norm": 0.2458307147026062, "learning_rate": 3.532114435377838e-05, "loss": 0.0092, "step": 4447 }, { "epoch": 0.24563728738679036, "grad_norm": 0.04387250170111656, "learning_rate": 3.5318844713349124e-05, "loss": 0.0018, "step": 4448 }, { "epoch": 0.24569251159708416, "grad_norm": 0.0808286964893341, "learning_rate": 3.531654458282642e-05, "loss": 0.003, "step": 4449 }, { "epoch": 0.24574773580737796, "grad_norm": 2.1355080604553223, "learning_rate": 3.531424396228384e-05, "loss": 0.1048, "step": 4450 }, { "epoch": 0.24580296001767174, "grad_norm": 1.2900047302246094, "learning_rate": 3.5311942851795005e-05, "loss": 0.047, "step": 4451 }, { "epoch": 0.24585818422796554, "grad_norm": 0.09103557467460632, "learning_rate": 3.530964125143352e-05, "loss": 0.0027, "step": 4452 }, { "epoch": 0.24591340843825935, "grad_norm": 3.340712785720825, "learning_rate": 3.530733916127304e-05, "loss": 0.7071, "step": 4453 }, { "epoch": 0.24596863264855312, "grad_norm": 2.4866676330566406, "learning_rate": 3.5305036581387186e-05, "loss": 0.1887, "step": 4454 }, { "epoch": 0.24602385685884692, "grad_norm": 1.9144049882888794, "learning_rate": 3.530273351184965e-05, "loss": 0.0716, "step": 4455 }, { "epoch": 0.2460790810691407, "grad_norm": 4.150104999542236, "learning_rate": 3.5300429952734105e-05, "loss": 0.6734, "step": 4456 }, { "epoch": 0.2461343052794345, "grad_norm": 2.747189521789551, "learning_rate": 3.529812590411424e-05, "loss": 0.3832, "step": 4457 }, { "epoch": 0.2461895294897283, "grad_norm": 0.6683241128921509, "learning_rate": 3.5295821366063787e-05, "loss": 0.0295, "step": 4458 }, { "epoch": 0.24624475370002208, "grad_norm": 4.454983711242676, "learning_rate": 3.529351633865645e-05, "loss": 0.1033, "step": 4459 }, { "epoch": 0.24629997791031588, "grad_norm": 0.4037010669708252, "learning_rate": 3.5291210821965996e-05, "loss": 0.0135, "step": 4460 }, { "epoch": 0.24635520212060968, "grad_norm": 0.2482403963804245, "learning_rate": 3.528890481606617e-05, "loss": 0.0062, "step": 4461 }, { "epoch": 0.24641042633090346, "grad_norm": 1.4737403392791748, "learning_rate": 3.5286598321030755e-05, "loss": 0.3165, "step": 4462 }, { "epoch": 0.24646565054119726, "grad_norm": 1.2250396013259888, "learning_rate": 3.5284291336933544e-05, "loss": 0.1364, "step": 4463 }, { "epoch": 0.24652087475149106, "grad_norm": 3.506439208984375, "learning_rate": 3.528198386384834e-05, "loss": 0.5439, "step": 4464 }, { "epoch": 0.24657609896178484, "grad_norm": 0.007627894636243582, "learning_rate": 3.527967590184896e-05, "loss": 0.0003, "step": 4465 }, { "epoch": 0.24663132317207864, "grad_norm": 1.5370919704437256, "learning_rate": 3.527736745100926e-05, "loss": 0.1038, "step": 4466 }, { "epoch": 0.24668654738237245, "grad_norm": 3.369706153869629, "learning_rate": 3.5275058511403076e-05, "loss": 0.6018, "step": 4467 }, { "epoch": 0.24674177159266622, "grad_norm": 2.6835052967071533, "learning_rate": 3.5272749083104286e-05, "loss": 0.8088, "step": 4468 }, { "epoch": 0.24679699580296002, "grad_norm": 2.7975399494171143, "learning_rate": 3.527043916618677e-05, "loss": 0.128, "step": 4469 }, { "epoch": 0.2468522200132538, "grad_norm": 0.04966822266578674, "learning_rate": 3.526812876072443e-05, "loss": 0.0015, "step": 4470 }, { "epoch": 0.2469074442235476, "grad_norm": 1.8021745681762695, "learning_rate": 3.526581786679119e-05, "loss": 0.0592, "step": 4471 }, { "epoch": 0.2469626684338414, "grad_norm": 1.752375602722168, "learning_rate": 3.526350648446097e-05, "loss": 0.0938, "step": 4472 }, { "epoch": 0.24701789264413518, "grad_norm": 0.2158084511756897, "learning_rate": 3.526119461380773e-05, "loss": 0.0079, "step": 4473 }, { "epoch": 0.24707311685442898, "grad_norm": 3.01935076713562, "learning_rate": 3.5258882254905424e-05, "loss": 0.5525, "step": 4474 }, { "epoch": 0.24712834106472278, "grad_norm": 3.1183669567108154, "learning_rate": 3.525656940782804e-05, "loss": 0.2113, "step": 4475 }, { "epoch": 0.24718356527501656, "grad_norm": 5.051856994628906, "learning_rate": 3.525425607264956e-05, "loss": 0.8202, "step": 4476 }, { "epoch": 0.24723878948531036, "grad_norm": 0.07910653203725815, "learning_rate": 3.525194224944401e-05, "loss": 0.0032, "step": 4477 }, { "epoch": 0.24729401369560416, "grad_norm": 0.1056508794426918, "learning_rate": 3.52496279382854e-05, "loss": 0.0038, "step": 4478 }, { "epoch": 0.24734923790589794, "grad_norm": 4.89409065246582, "learning_rate": 3.524731313924778e-05, "loss": 0.9705, "step": 4479 }, { "epoch": 0.24740446211619174, "grad_norm": 0.24041177332401276, "learning_rate": 3.524499785240521e-05, "loss": 0.0075, "step": 4480 }, { "epoch": 0.24745968632648555, "grad_norm": 1.8492850065231323, "learning_rate": 3.524268207783175e-05, "loss": 0.3601, "step": 4481 }, { "epoch": 0.24751491053677932, "grad_norm": 3.6618716716766357, "learning_rate": 3.5240365815601506e-05, "loss": 0.1638, "step": 4482 }, { "epoch": 0.24757013474707312, "grad_norm": 0.42323362827301025, "learning_rate": 3.523804906578856e-05, "loss": 0.0171, "step": 4483 }, { "epoch": 0.2476253589573669, "grad_norm": 1.2053035497665405, "learning_rate": 3.523573182846705e-05, "loss": 0.0539, "step": 4484 }, { "epoch": 0.2476805831676607, "grad_norm": 0.9241304397583008, "learning_rate": 3.523341410371111e-05, "loss": 0.0322, "step": 4485 }, { "epoch": 0.2477358073779545, "grad_norm": 5.73014497756958, "learning_rate": 3.523109589159488e-05, "loss": 0.3127, "step": 4486 }, { "epoch": 0.24779103158824828, "grad_norm": 0.4518206715583801, "learning_rate": 3.522877719219253e-05, "loss": 0.0143, "step": 4487 }, { "epoch": 0.24784625579854208, "grad_norm": 3.4558403491973877, "learning_rate": 3.5226458005578245e-05, "loss": 0.5661, "step": 4488 }, { "epoch": 0.24790148000883588, "grad_norm": 0.39331597089767456, "learning_rate": 3.522413833182622e-05, "loss": 0.0158, "step": 4489 }, { "epoch": 0.24795670421912966, "grad_norm": 0.7468076348304749, "learning_rate": 3.522181817101067e-05, "loss": 0.0211, "step": 4490 }, { "epoch": 0.24801192842942346, "grad_norm": 1.758270263671875, "learning_rate": 3.5219497523205816e-05, "loss": 0.0722, "step": 4491 }, { "epoch": 0.24806715263971726, "grad_norm": 0.25374311208724976, "learning_rate": 3.521717638848592e-05, "loss": 0.0101, "step": 4492 }, { "epoch": 0.24812237685001104, "grad_norm": 0.015072868205606937, "learning_rate": 3.521485476692522e-05, "loss": 0.0008, "step": 4493 }, { "epoch": 0.24817760106030484, "grad_norm": 0.12764164805412292, "learning_rate": 3.5212532658598e-05, "loss": 0.004, "step": 4494 }, { "epoch": 0.24823282527059862, "grad_norm": 0.5421246886253357, "learning_rate": 3.521021006357856e-05, "loss": 0.0089, "step": 4495 }, { "epoch": 0.24828804948089242, "grad_norm": 3.2945079803466797, "learning_rate": 3.52078869819412e-05, "loss": 0.4631, "step": 4496 }, { "epoch": 0.24834327369118622, "grad_norm": 0.0745805874466896, "learning_rate": 3.520556341376023e-05, "loss": 0.0018, "step": 4497 }, { "epoch": 0.24839849790148, "grad_norm": 2.7090401649475098, "learning_rate": 3.520323935911001e-05, "loss": 0.076, "step": 4498 }, { "epoch": 0.2484537221117738, "grad_norm": 0.13689830899238586, "learning_rate": 3.520091481806487e-05, "loss": 0.005, "step": 4499 }, { "epoch": 0.2485089463220676, "grad_norm": 0.2334236353635788, "learning_rate": 3.51985897906992e-05, "loss": 0.0067, "step": 4500 }, { "epoch": 0.24856417053236138, "grad_norm": 2.887388229370117, "learning_rate": 3.519626427708737e-05, "loss": 0.6228, "step": 4501 }, { "epoch": 0.24861939474265518, "grad_norm": 0.061290621757507324, "learning_rate": 3.519393827730378e-05, "loss": 0.0021, "step": 4502 }, { "epoch": 0.24867461895294898, "grad_norm": 0.00811474584043026, "learning_rate": 3.519161179142285e-05, "loss": 0.0003, "step": 4503 }, { "epoch": 0.24872984316324276, "grad_norm": 0.06460876017808914, "learning_rate": 3.5189284819519015e-05, "loss": 0.0023, "step": 4504 }, { "epoch": 0.24878506737353656, "grad_norm": 2.0241193771362305, "learning_rate": 3.518695736166671e-05, "loss": 0.0544, "step": 4505 }, { "epoch": 0.24884029158383036, "grad_norm": 2.799943208694458, "learning_rate": 3.518462941794041e-05, "loss": 0.474, "step": 4506 }, { "epoch": 0.24889551579412414, "grad_norm": 0.012209261767566204, "learning_rate": 3.518230098841458e-05, "loss": 0.0004, "step": 4507 }, { "epoch": 0.24895074000441794, "grad_norm": 2.479254961013794, "learning_rate": 3.5179972073163726e-05, "loss": 0.309, "step": 4508 }, { "epoch": 0.24900596421471172, "grad_norm": 0.02681136503815651, "learning_rate": 3.517764267226235e-05, "loss": 0.0011, "step": 4509 }, { "epoch": 0.24906118842500552, "grad_norm": 2.517143487930298, "learning_rate": 3.517531278578497e-05, "loss": 0.1681, "step": 4510 }, { "epoch": 0.24911641263529932, "grad_norm": 0.7622615098953247, "learning_rate": 3.5172982413806136e-05, "loss": 0.0209, "step": 4511 }, { "epoch": 0.2491716368455931, "grad_norm": 3.3332607746124268, "learning_rate": 3.5170651556400396e-05, "loss": 1.1706, "step": 4512 }, { "epoch": 0.2492268610558869, "grad_norm": 0.14736433327198029, "learning_rate": 3.5168320213642324e-05, "loss": 0.0038, "step": 4513 }, { "epoch": 0.2492820852661807, "grad_norm": 2.0252203941345215, "learning_rate": 3.5165988385606513e-05, "loss": 0.4143, "step": 4514 }, { "epoch": 0.24933730947647448, "grad_norm": 0.2648889720439911, "learning_rate": 3.516365607236755e-05, "loss": 0.0048, "step": 4515 }, { "epoch": 0.24939253368676828, "grad_norm": 1.5505963563919067, "learning_rate": 3.516132327400006e-05, "loss": 0.2473, "step": 4516 }, { "epoch": 0.24944775789706208, "grad_norm": 0.0246557779610157, "learning_rate": 3.515898999057868e-05, "loss": 0.0005, "step": 4517 }, { "epoch": 0.24950298210735586, "grad_norm": 0.011439851485192776, "learning_rate": 3.515665622217806e-05, "loss": 0.0005, "step": 4518 }, { "epoch": 0.24955820631764966, "grad_norm": 3.3498950004577637, "learning_rate": 3.515432196887285e-05, "loss": 0.5652, "step": 4519 }, { "epoch": 0.24961343052794346, "grad_norm": 0.04060469567775726, "learning_rate": 3.5151987230737734e-05, "loss": 0.0013, "step": 4520 }, { "epoch": 0.24966865473823724, "grad_norm": 0.015486513264477253, "learning_rate": 3.5149652007847423e-05, "loss": 0.0006, "step": 4521 }, { "epoch": 0.24972387894853104, "grad_norm": 0.19190505146980286, "learning_rate": 3.514731630027661e-05, "loss": 0.004, "step": 4522 }, { "epoch": 0.24977910315882482, "grad_norm": 2.651068687438965, "learning_rate": 3.514498010810002e-05, "loss": 0.5225, "step": 4523 }, { "epoch": 0.24983432736911862, "grad_norm": 1.6981645822525024, "learning_rate": 3.5142643431392405e-05, "loss": 0.2012, "step": 4524 }, { "epoch": 0.24988955157941242, "grad_norm": 0.0244753435254097, "learning_rate": 3.514030627022852e-05, "loss": 0.0006, "step": 4525 }, { "epoch": 0.2499447757897062, "grad_norm": 4.99307107925415, "learning_rate": 3.513796862468313e-05, "loss": 1.2201, "step": 4526 }, { "epoch": 0.25, "grad_norm": 1.5554790496826172, "learning_rate": 3.513563049483103e-05, "loss": 0.0133, "step": 4527 }, { "epoch": 0.2500552242102938, "grad_norm": 0.03380828723311424, "learning_rate": 3.513329188074702e-05, "loss": 0.0012, "step": 4528 }, { "epoch": 0.2501104484205876, "grad_norm": 0.898796796798706, "learning_rate": 3.5130952782505925e-05, "loss": 0.0161, "step": 4529 }, { "epoch": 0.25016567263088135, "grad_norm": 1.289319396018982, "learning_rate": 3.5128613200182566e-05, "loss": 0.1655, "step": 4530 }, { "epoch": 0.25022089684117516, "grad_norm": 2.2173781394958496, "learning_rate": 3.5126273133851815e-05, "loss": 0.264, "step": 4531 }, { "epoch": 0.25027612105146896, "grad_norm": 5.894022464752197, "learning_rate": 3.5123932583588514e-05, "loss": 1.4889, "step": 4532 }, { "epoch": 0.25033134526176276, "grad_norm": 6.938827991485596, "learning_rate": 3.512159154946755e-05, "loss": 1.0722, "step": 4533 }, { "epoch": 0.25038656947205656, "grad_norm": 4.945138931274414, "learning_rate": 3.5119250031563826e-05, "loss": 0.7998, "step": 4534 }, { "epoch": 0.25044179368235037, "grad_norm": 4.349050998687744, "learning_rate": 3.511690802995226e-05, "loss": 0.8728, "step": 4535 }, { "epoch": 0.2504970178926441, "grad_norm": 4.387031078338623, "learning_rate": 3.511456554470776e-05, "loss": 0.519, "step": 4536 }, { "epoch": 0.2505522421029379, "grad_norm": 0.0953378975391388, "learning_rate": 3.5112222575905276e-05, "loss": 0.003, "step": 4537 }, { "epoch": 0.2506074663132317, "grad_norm": 3.6213150024414062, "learning_rate": 3.5109879123619786e-05, "loss": 0.444, "step": 4538 }, { "epoch": 0.2506626905235255, "grad_norm": 3.8972668647766113, "learning_rate": 3.510753518792624e-05, "loss": 0.7824, "step": 4539 }, { "epoch": 0.2507179147338193, "grad_norm": 0.2594887614250183, "learning_rate": 3.510519076889963e-05, "loss": 0.0055, "step": 4540 }, { "epoch": 0.25077313894411307, "grad_norm": 1.09901762008667, "learning_rate": 3.510284586661496e-05, "loss": 0.0407, "step": 4541 }, { "epoch": 0.2508283631544069, "grad_norm": 0.029095981270074844, "learning_rate": 3.5100500481147254e-05, "loss": 0.0011, "step": 4542 }, { "epoch": 0.2508835873647007, "grad_norm": 2.840421199798584, "learning_rate": 3.509815461257156e-05, "loss": 0.4855, "step": 4543 }, { "epoch": 0.2509388115749945, "grad_norm": 2.225733757019043, "learning_rate": 3.509580826096291e-05, "loss": 0.1339, "step": 4544 }, { "epoch": 0.2509940357852883, "grad_norm": 0.1693112850189209, "learning_rate": 3.509346142639638e-05, "loss": 0.0049, "step": 4545 }, { "epoch": 0.2510492599955821, "grad_norm": 1.7875244617462158, "learning_rate": 3.509111410894705e-05, "loss": 0.1085, "step": 4546 }, { "epoch": 0.25110448420587583, "grad_norm": 2.565324306488037, "learning_rate": 3.508876630869002e-05, "loss": 0.1833, "step": 4547 }, { "epoch": 0.25115970841616964, "grad_norm": 0.05758001282811165, "learning_rate": 3.508641802570039e-05, "loss": 0.0015, "step": 4548 }, { "epoch": 0.25121493262646344, "grad_norm": 4.700821876525879, "learning_rate": 3.508406926005331e-05, "loss": 1.1595, "step": 4549 }, { "epoch": 0.25127015683675724, "grad_norm": 1.2115485668182373, "learning_rate": 3.5081720011823904e-05, "loss": 0.0292, "step": 4550 }, { "epoch": 0.25132538104705104, "grad_norm": 2.0847134590148926, "learning_rate": 3.507937028108734e-05, "loss": 0.2605, "step": 4551 }, { "epoch": 0.25138060525734485, "grad_norm": 0.1819605976343155, "learning_rate": 3.507702006791879e-05, "loss": 0.0045, "step": 4552 }, { "epoch": 0.2514358294676386, "grad_norm": 0.9414523839950562, "learning_rate": 3.5074669372393455e-05, "loss": 0.048, "step": 4553 }, { "epoch": 0.2514910536779324, "grad_norm": 2.096142292022705, "learning_rate": 3.507231819458652e-05, "loss": 0.183, "step": 4554 }, { "epoch": 0.2515462778882262, "grad_norm": 0.021863939240574837, "learning_rate": 3.506996653457323e-05, "loss": 0.0008, "step": 4555 }, { "epoch": 0.25160150209852, "grad_norm": 0.5536490082740784, "learning_rate": 3.50676143924288e-05, "loss": 0.0137, "step": 4556 }, { "epoch": 0.2516567263088138, "grad_norm": 0.09030813723802567, "learning_rate": 3.506526176822849e-05, "loss": 0.0032, "step": 4557 }, { "epoch": 0.25171195051910755, "grad_norm": 0.08091144263744354, "learning_rate": 3.5062908662047566e-05, "loss": 0.0027, "step": 4558 }, { "epoch": 0.25176717472940136, "grad_norm": 0.6635076999664307, "learning_rate": 3.5060555073961316e-05, "loss": 0.0193, "step": 4559 }, { "epoch": 0.25182239893969516, "grad_norm": 0.1535048484802246, "learning_rate": 3.505820100404503e-05, "loss": 0.0073, "step": 4560 }, { "epoch": 0.25187762314998896, "grad_norm": 0.0924675390124321, "learning_rate": 3.505584645237403e-05, "loss": 0.0025, "step": 4561 }, { "epoch": 0.25193284736028276, "grad_norm": 4.300772666931152, "learning_rate": 3.505349141902363e-05, "loss": 0.5004, "step": 4562 }, { "epoch": 0.25198807157057657, "grad_norm": 0.10652391612529755, "learning_rate": 3.505113590406919e-05, "loss": 0.0043, "step": 4563 }, { "epoch": 0.2520432957808703, "grad_norm": 0.04309973120689392, "learning_rate": 3.5048779907586064e-05, "loss": 0.0017, "step": 4564 }, { "epoch": 0.2520985199911641, "grad_norm": 2.517829656600952, "learning_rate": 3.504642342964963e-05, "loss": 0.2558, "step": 4565 }, { "epoch": 0.2521537442014579, "grad_norm": 3.4288997650146484, "learning_rate": 3.504406647033527e-05, "loss": 0.8811, "step": 4566 }, { "epoch": 0.2522089684117517, "grad_norm": 2.5468978881835938, "learning_rate": 3.504170902971839e-05, "loss": 0.3458, "step": 4567 }, { "epoch": 0.2522641926220455, "grad_norm": 4.783572673797607, "learning_rate": 3.503935110787443e-05, "loss": 0.819, "step": 4568 }, { "epoch": 0.25231941683233927, "grad_norm": 4.923304557800293, "learning_rate": 3.5036992704878804e-05, "loss": 0.5465, "step": 4569 }, { "epoch": 0.2523746410426331, "grad_norm": 0.11160557717084885, "learning_rate": 3.503463382080698e-05, "loss": 0.0035, "step": 4570 }, { "epoch": 0.2524298652529269, "grad_norm": 0.3732012212276459, "learning_rate": 3.503227445573441e-05, "loss": 0.007, "step": 4571 }, { "epoch": 0.2524850894632207, "grad_norm": 0.8119865655899048, "learning_rate": 3.5029914609736586e-05, "loss": 0.0183, "step": 4572 }, { "epoch": 0.2525403136735145, "grad_norm": 2.705968141555786, "learning_rate": 3.502755428288901e-05, "loss": 0.4203, "step": 4573 }, { "epoch": 0.2525955378838083, "grad_norm": 3.7370290756225586, "learning_rate": 3.502519347526719e-05, "loss": 1.0703, "step": 4574 }, { "epoch": 0.25265076209410203, "grad_norm": 3.5325841903686523, "learning_rate": 3.502283218694666e-05, "loss": 0.3877, "step": 4575 }, { "epoch": 0.25270598630439584, "grad_norm": 2.6802735328674316, "learning_rate": 3.502047041800295e-05, "loss": 0.3851, "step": 4576 }, { "epoch": 0.25276121051468964, "grad_norm": 3.388629913330078, "learning_rate": 3.501810816851164e-05, "loss": 0.9837, "step": 4577 }, { "epoch": 0.25281643472498344, "grad_norm": 0.4434855282306671, "learning_rate": 3.501574543854829e-05, "loss": 0.0108, "step": 4578 }, { "epoch": 0.25287165893527724, "grad_norm": 1.0790218114852905, "learning_rate": 3.501338222818849e-05, "loss": 0.0365, "step": 4579 }, { "epoch": 0.252926883145571, "grad_norm": 3.182852029800415, "learning_rate": 3.501101853750786e-05, "loss": 0.5131, "step": 4580 }, { "epoch": 0.2529821073558648, "grad_norm": 1.5887930393218994, "learning_rate": 3.5008654366582005e-05, "loss": 0.5002, "step": 4581 }, { "epoch": 0.2530373315661586, "grad_norm": 0.9634966254234314, "learning_rate": 3.5006289715486576e-05, "loss": 0.0605, "step": 4582 }, { "epoch": 0.2530925557764524, "grad_norm": 0.04794105514883995, "learning_rate": 3.5003924584297216e-05, "loss": 0.002, "step": 4583 }, { "epoch": 0.2531477799867462, "grad_norm": 2.630216360092163, "learning_rate": 3.5001558973089595e-05, "loss": 0.2942, "step": 4584 }, { "epoch": 0.25320300419704, "grad_norm": 1.7710590362548828, "learning_rate": 3.499919288193939e-05, "loss": 0.0988, "step": 4585 }, { "epoch": 0.25325822840733375, "grad_norm": 2.0990355014801025, "learning_rate": 3.499682631092231e-05, "loss": 0.4556, "step": 4586 }, { "epoch": 0.25331345261762755, "grad_norm": 2.00827693939209, "learning_rate": 3.499445926011406e-05, "loss": 0.0613, "step": 4587 }, { "epoch": 0.25336867682792136, "grad_norm": 0.22269350290298462, "learning_rate": 3.4992091729590374e-05, "loss": 0.0067, "step": 4588 }, { "epoch": 0.25342390103821516, "grad_norm": 0.03454698249697685, "learning_rate": 3.4989723719426984e-05, "loss": 0.0015, "step": 4589 }, { "epoch": 0.25347912524850896, "grad_norm": 0.343931645154953, "learning_rate": 3.498735522969966e-05, "loss": 0.0096, "step": 4590 }, { "epoch": 0.25353434945880277, "grad_norm": 0.5447636842727661, "learning_rate": 3.4984986260484186e-05, "loss": 0.0164, "step": 4591 }, { "epoch": 0.2535895736690965, "grad_norm": 1.3046729564666748, "learning_rate": 3.4982616811856336e-05, "loss": 0.2526, "step": 4592 }, { "epoch": 0.2536447978793903, "grad_norm": 0.71827632188797, "learning_rate": 3.498024688389191e-05, "loss": 0.0184, "step": 4593 }, { "epoch": 0.2537000220896841, "grad_norm": 1.0092979669570923, "learning_rate": 3.497787647666675e-05, "loss": 0.0598, "step": 4594 }, { "epoch": 0.2537552462999779, "grad_norm": 0.1865849494934082, "learning_rate": 3.497550559025668e-05, "loss": 0.0063, "step": 4595 }, { "epoch": 0.2538104705102717, "grad_norm": 3.5494258403778076, "learning_rate": 3.497313422473755e-05, "loss": 0.3625, "step": 4596 }, { "epoch": 0.25386569472056547, "grad_norm": 0.06338898837566376, "learning_rate": 3.497076238018524e-05, "loss": 0.0024, "step": 4597 }, { "epoch": 0.2539209189308593, "grad_norm": 1.0875612497329712, "learning_rate": 3.496839005667561e-05, "loss": 0.024, "step": 4598 }, { "epoch": 0.2539761431411531, "grad_norm": 1.542659044265747, "learning_rate": 3.496601725428457e-05, "loss": 0.0708, "step": 4599 }, { "epoch": 0.2540313673514469, "grad_norm": 4.17022180557251, "learning_rate": 3.4963643973088034e-05, "loss": 0.513, "step": 4600 }, { "epoch": 0.2540865915617407, "grad_norm": 0.013174300082027912, "learning_rate": 3.496127021316193e-05, "loss": 0.0005, "step": 4601 }, { "epoch": 0.2541418157720345, "grad_norm": 2.569695234298706, "learning_rate": 3.49588959745822e-05, "loss": 0.3331, "step": 4602 }, { "epoch": 0.25419703998232823, "grad_norm": 0.8604515194892883, "learning_rate": 3.49565212574248e-05, "loss": 0.0215, "step": 4603 }, { "epoch": 0.25425226419262204, "grad_norm": 0.028593670576810837, "learning_rate": 3.49541460617657e-05, "loss": 0.0009, "step": 4604 }, { "epoch": 0.25430748840291584, "grad_norm": 0.3872019946575165, "learning_rate": 3.49517703876809e-05, "loss": 0.0109, "step": 4605 }, { "epoch": 0.25436271261320964, "grad_norm": 2.902287721633911, "learning_rate": 3.4949394235246404e-05, "loss": 0.7664, "step": 4606 }, { "epoch": 0.25441793682350344, "grad_norm": 2.0459694862365723, "learning_rate": 3.494701760453822e-05, "loss": 0.279, "step": 4607 }, { "epoch": 0.2544731610337972, "grad_norm": 0.01264536939561367, "learning_rate": 3.494464049563239e-05, "loss": 0.0004, "step": 4608 }, { "epoch": 0.254528385244091, "grad_norm": 0.08480453491210938, "learning_rate": 3.494226290860497e-05, "loss": 0.0033, "step": 4609 }, { "epoch": 0.2545836094543848, "grad_norm": 0.03628856688737869, "learning_rate": 3.4939884843532015e-05, "loss": 0.0013, "step": 4610 }, { "epoch": 0.2546388336646786, "grad_norm": 3.2523882389068604, "learning_rate": 3.493750630048961e-05, "loss": 0.1443, "step": 4611 }, { "epoch": 0.2546940578749724, "grad_norm": 1.821150302886963, "learning_rate": 3.4935127279553864e-05, "loss": 0.09, "step": 4612 }, { "epoch": 0.2547492820852662, "grad_norm": 5.9674973487854, "learning_rate": 3.493274778080087e-05, "loss": 2.0537, "step": 4613 }, { "epoch": 0.25480450629555995, "grad_norm": 0.8947548866271973, "learning_rate": 3.4930367804306766e-05, "loss": 0.0158, "step": 4614 }, { "epoch": 0.25485973050585375, "grad_norm": 3.1092679500579834, "learning_rate": 3.492798735014769e-05, "loss": 0.8049, "step": 4615 }, { "epoch": 0.25491495471614756, "grad_norm": 2.6743342876434326, "learning_rate": 3.4925606418399805e-05, "loss": 0.1057, "step": 4616 }, { "epoch": 0.25497017892644136, "grad_norm": 3.065291404724121, "learning_rate": 3.4923225009139275e-05, "loss": 0.8175, "step": 4617 }, { "epoch": 0.25502540313673516, "grad_norm": 3.09598970413208, "learning_rate": 3.492084312244229e-05, "loss": 0.2704, "step": 4618 }, { "epoch": 0.2550806273470289, "grad_norm": 2.1783273220062256, "learning_rate": 3.491846075838506e-05, "loss": 0.1667, "step": 4619 }, { "epoch": 0.2551358515573227, "grad_norm": 3.320401191711426, "learning_rate": 3.49160779170438e-05, "loss": 1.0448, "step": 4620 }, { "epoch": 0.2551910757676165, "grad_norm": 4.106770992279053, "learning_rate": 3.491369459849474e-05, "loss": 0.7695, "step": 4621 }, { "epoch": 0.2552462999779103, "grad_norm": 3.174117088317871, "learning_rate": 3.4911310802814134e-05, "loss": 0.2993, "step": 4622 }, { "epoch": 0.2553015241882041, "grad_norm": 0.7134305834770203, "learning_rate": 3.4908926530078245e-05, "loss": 0.0248, "step": 4623 }, { "epoch": 0.2553567483984979, "grad_norm": 2.762085437774658, "learning_rate": 3.4906541780363344e-05, "loss": 0.5762, "step": 4624 }, { "epoch": 0.25541197260879167, "grad_norm": 5.336458206176758, "learning_rate": 3.4904156553745746e-05, "loss": 0.2802, "step": 4625 }, { "epoch": 0.2554671968190855, "grad_norm": 0.35476404428482056, "learning_rate": 3.4901770850301745e-05, "loss": 0.0089, "step": 4626 }, { "epoch": 0.2555224210293793, "grad_norm": 2.1238675117492676, "learning_rate": 3.4899384670107676e-05, "loss": 0.0524, "step": 4627 }, { "epoch": 0.2555776452396731, "grad_norm": 2.6662654876708984, "learning_rate": 3.4896998013239866e-05, "loss": 0.6212, "step": 4628 }, { "epoch": 0.2556328694499669, "grad_norm": 1.5636990070343018, "learning_rate": 3.4894610879774684e-05, "loss": 0.0295, "step": 4629 }, { "epoch": 0.2556880936602607, "grad_norm": 4.762506008148193, "learning_rate": 3.48922232697885e-05, "loss": 0.9652, "step": 4630 }, { "epoch": 0.25574331787055443, "grad_norm": 1.3056230545043945, "learning_rate": 3.488983518335769e-05, "loss": 0.0385, "step": 4631 }, { "epoch": 0.25579854208084823, "grad_norm": 0.09566034376621246, "learning_rate": 3.488744662055867e-05, "loss": 0.0025, "step": 4632 }, { "epoch": 0.25585376629114204, "grad_norm": 0.07615894824266434, "learning_rate": 3.488505758146785e-05, "loss": 0.0021, "step": 4633 }, { "epoch": 0.25590899050143584, "grad_norm": 0.23732221126556396, "learning_rate": 3.488266806616166e-05, "loss": 0.0072, "step": 4634 }, { "epoch": 0.25596421471172964, "grad_norm": 2.3907551765441895, "learning_rate": 3.488027807471655e-05, "loss": 0.3705, "step": 4635 }, { "epoch": 0.2560194389220234, "grad_norm": 0.16220928728580475, "learning_rate": 3.4877887607208976e-05, "loss": 0.0045, "step": 4636 }, { "epoch": 0.2560746631323172, "grad_norm": 0.016687141731381416, "learning_rate": 3.4875496663715425e-05, "loss": 0.0006, "step": 4637 }, { "epoch": 0.256129887342611, "grad_norm": 2.595721483230591, "learning_rate": 3.487310524431239e-05, "loss": 0.4382, "step": 4638 }, { "epoch": 0.2561851115529048, "grad_norm": 0.12247294932603836, "learning_rate": 3.487071334907638e-05, "loss": 0.0045, "step": 4639 }, { "epoch": 0.2562403357631986, "grad_norm": 0.08866560459136963, "learning_rate": 3.486832097808391e-05, "loss": 0.002, "step": 4640 }, { "epoch": 0.2562955599734924, "grad_norm": 2.612044095993042, "learning_rate": 3.486592813141152e-05, "loss": 0.8933, "step": 4641 }, { "epoch": 0.25635078418378615, "grad_norm": 0.468879759311676, "learning_rate": 3.4863534809135774e-05, "loss": 0.0144, "step": 4642 }, { "epoch": 0.25640600839407995, "grad_norm": 2.026005506515503, "learning_rate": 3.486114101133323e-05, "loss": 0.4413, "step": 4643 }, { "epoch": 0.25646123260437376, "grad_norm": 0.07119274139404297, "learning_rate": 3.485874673808048e-05, "loss": 0.0015, "step": 4644 }, { "epoch": 0.25651645681466756, "grad_norm": 3.3849172592163086, "learning_rate": 3.4856351989454124e-05, "loss": 0.8079, "step": 4645 }, { "epoch": 0.25657168102496136, "grad_norm": 2.6215384006500244, "learning_rate": 3.485395676553077e-05, "loss": 0.271, "step": 4646 }, { "epoch": 0.2566269052352551, "grad_norm": 3.7376997470855713, "learning_rate": 3.485156106638705e-05, "loss": 0.8197, "step": 4647 }, { "epoch": 0.2566821294455489, "grad_norm": 2.2600350379943848, "learning_rate": 3.484916489209961e-05, "loss": 0.0345, "step": 4648 }, { "epoch": 0.2567373536558427, "grad_norm": 0.5418235063552856, "learning_rate": 3.484676824274511e-05, "loss": 0.0161, "step": 4649 }, { "epoch": 0.2567925778661365, "grad_norm": 2.6031739711761475, "learning_rate": 3.484437111840024e-05, "loss": 0.1665, "step": 4650 }, { "epoch": 0.2568478020764303, "grad_norm": 0.13153260946273804, "learning_rate": 3.484197351914167e-05, "loss": 0.0035, "step": 4651 }, { "epoch": 0.2569030262867241, "grad_norm": 1.9276814460754395, "learning_rate": 3.4839575445046116e-05, "loss": 0.1082, "step": 4652 }, { "epoch": 0.25695825049701787, "grad_norm": 0.05599045008420944, "learning_rate": 3.4837176896190294e-05, "loss": 0.002, "step": 4653 }, { "epoch": 0.2570134747073117, "grad_norm": 1.3906201124191284, "learning_rate": 3.483477787265094e-05, "loss": 0.1171, "step": 4654 }, { "epoch": 0.2570686989176055, "grad_norm": 0.018543226644396782, "learning_rate": 3.483237837450482e-05, "loss": 0.0006, "step": 4655 }, { "epoch": 0.2571239231278993, "grad_norm": 3.692232847213745, "learning_rate": 3.482997840182868e-05, "loss": 0.2677, "step": 4656 }, { "epoch": 0.2571791473381931, "grad_norm": 1.720474123954773, "learning_rate": 3.4827577954699314e-05, "loss": 0.3114, "step": 4657 }, { "epoch": 0.2572343715484869, "grad_norm": 3.0820693969726562, "learning_rate": 3.482517703319352e-05, "loss": 0.087, "step": 4658 }, { "epoch": 0.25728959575878063, "grad_norm": 3.3631460666656494, "learning_rate": 3.4822775637388105e-05, "loss": 1.0896, "step": 4659 }, { "epoch": 0.25734481996907443, "grad_norm": 4.850876331329346, "learning_rate": 3.482037376735989e-05, "loss": 0.3727, "step": 4660 }, { "epoch": 0.25740004417936824, "grad_norm": 0.740145742893219, "learning_rate": 3.481797142318574e-05, "loss": 0.0294, "step": 4661 }, { "epoch": 0.25745526838966204, "grad_norm": 0.04698788374662399, "learning_rate": 3.48155686049425e-05, "loss": 0.0015, "step": 4662 }, { "epoch": 0.25751049259995584, "grad_norm": 2.642272710800171, "learning_rate": 3.481316531270703e-05, "loss": 0.2742, "step": 4663 }, { "epoch": 0.2575657168102496, "grad_norm": 0.025843001902103424, "learning_rate": 3.481076154655624e-05, "loss": 0.0008, "step": 4664 }, { "epoch": 0.2576209410205434, "grad_norm": 1.4142683744430542, "learning_rate": 3.480835730656702e-05, "loss": 0.1509, "step": 4665 }, { "epoch": 0.2576761652308372, "grad_norm": 0.09871308505535126, "learning_rate": 3.48059525928163e-05, "loss": 0.003, "step": 4666 }, { "epoch": 0.257731389441131, "grad_norm": 0.042941171675920486, "learning_rate": 3.480354740538099e-05, "loss": 0.0014, "step": 4667 }, { "epoch": 0.2577866136514248, "grad_norm": 3.115215539932251, "learning_rate": 3.480114174433807e-05, "loss": 0.6787, "step": 4668 }, { "epoch": 0.2578418378617186, "grad_norm": 0.2441786527633667, "learning_rate": 3.4798735609764475e-05, "loss": 0.009, "step": 4669 }, { "epoch": 0.25789706207201235, "grad_norm": 5.54763650894165, "learning_rate": 3.479632900173721e-05, "loss": 0.9231, "step": 4670 }, { "epoch": 0.25795228628230615, "grad_norm": 1.2028437852859497, "learning_rate": 3.479392192033325e-05, "loss": 0.046, "step": 4671 }, { "epoch": 0.25800751049259996, "grad_norm": 1.215960144996643, "learning_rate": 3.479151436562962e-05, "loss": 0.0315, "step": 4672 }, { "epoch": 0.25806273470289376, "grad_norm": 0.10937197506427765, "learning_rate": 3.478910633770333e-05, "loss": 0.0038, "step": 4673 }, { "epoch": 0.25811795891318756, "grad_norm": 0.9703243374824524, "learning_rate": 3.478669783663142e-05, "loss": 0.0311, "step": 4674 }, { "epoch": 0.2581731831234813, "grad_norm": 0.019162509590387344, "learning_rate": 3.478428886249095e-05, "loss": 0.0006, "step": 4675 }, { "epoch": 0.2582284073337751, "grad_norm": 0.13522766530513763, "learning_rate": 3.4781879415359e-05, "loss": 0.0051, "step": 4676 }, { "epoch": 0.2582836315440689, "grad_norm": 0.9597538113594055, "learning_rate": 3.4779469495312636e-05, "loss": 0.0338, "step": 4677 }, { "epoch": 0.2583388557543627, "grad_norm": 0.6689589023590088, "learning_rate": 3.4777059102428974e-05, "loss": 0.0177, "step": 4678 }, { "epoch": 0.2583940799646565, "grad_norm": 0.1110115796327591, "learning_rate": 3.477464823678512e-05, "loss": 0.0034, "step": 4679 }, { "epoch": 0.2584493041749503, "grad_norm": 2.22666335105896, "learning_rate": 3.477223689845821e-05, "loss": 0.5866, "step": 4680 }, { "epoch": 0.25850452838524407, "grad_norm": 0.047283802181482315, "learning_rate": 3.4769825087525394e-05, "loss": 0.0014, "step": 4681 }, { "epoch": 0.2585597525955379, "grad_norm": 0.02745114080607891, "learning_rate": 3.4767412804063814e-05, "loss": 0.0009, "step": 4682 }, { "epoch": 0.2586149768058317, "grad_norm": 0.1502571702003479, "learning_rate": 3.4765000048150655e-05, "loss": 0.0051, "step": 4683 }, { "epoch": 0.2586702010161255, "grad_norm": 5.202617168426514, "learning_rate": 3.476258681986312e-05, "loss": 1.0601, "step": 4684 }, { "epoch": 0.2587254252264193, "grad_norm": 0.3303237557411194, "learning_rate": 3.47601731192784e-05, "loss": 0.0126, "step": 4685 }, { "epoch": 0.25878064943671303, "grad_norm": 6.159916400909424, "learning_rate": 3.475775894647373e-05, "loss": 1.905, "step": 4686 }, { "epoch": 0.25883587364700683, "grad_norm": 0.27719444036483765, "learning_rate": 3.4755344301526324e-05, "loss": 0.0053, "step": 4687 }, { "epoch": 0.25889109785730063, "grad_norm": 0.4736458659172058, "learning_rate": 3.475292918451345e-05, "loss": 0.0135, "step": 4688 }, { "epoch": 0.25894632206759444, "grad_norm": 0.18222220242023468, "learning_rate": 3.475051359551238e-05, "loss": 0.0059, "step": 4689 }, { "epoch": 0.25900154627788824, "grad_norm": 0.01218932494521141, "learning_rate": 3.4748097534600385e-05, "loss": 0.0003, "step": 4690 }, { "epoch": 0.25905677048818204, "grad_norm": 3.285338878631592, "learning_rate": 3.474568100185476e-05, "loss": 0.0788, "step": 4691 }, { "epoch": 0.2591119946984758, "grad_norm": 0.05506734549999237, "learning_rate": 3.4743263997352824e-05, "loss": 0.0014, "step": 4692 }, { "epoch": 0.2591672189087696, "grad_norm": 0.35312899947166443, "learning_rate": 3.4740846521171895e-05, "loss": 0.0073, "step": 4693 }, { "epoch": 0.2592224431190634, "grad_norm": 0.027336524799466133, "learning_rate": 3.473842857338933e-05, "loss": 0.0009, "step": 4694 }, { "epoch": 0.2592776673293572, "grad_norm": 6.04049825668335, "learning_rate": 3.473601015408247e-05, "loss": 0.9695, "step": 4695 }, { "epoch": 0.259332891539651, "grad_norm": 9.326558113098145, "learning_rate": 3.473359126332869e-05, "loss": 0.4009, "step": 4696 }, { "epoch": 0.2593881157499448, "grad_norm": 0.06605508178472519, "learning_rate": 3.4731171901205384e-05, "loss": 0.0021, "step": 4697 }, { "epoch": 0.25944333996023855, "grad_norm": 11.652702331542969, "learning_rate": 3.472875206778996e-05, "loss": 0.4841, "step": 4698 }, { "epoch": 0.25949856417053235, "grad_norm": 1.700684905052185, "learning_rate": 3.472633176315982e-05, "loss": 0.4047, "step": 4699 }, { "epoch": 0.25955378838082616, "grad_norm": 0.39503100514411926, "learning_rate": 3.47239109873924e-05, "loss": 0.0124, "step": 4700 }, { "epoch": 0.25960901259111996, "grad_norm": 0.031904079020023346, "learning_rate": 3.472148974056515e-05, "loss": 0.0009, "step": 4701 }, { "epoch": 0.25966423680141376, "grad_norm": 1.8208274841308594, "learning_rate": 3.471906802275554e-05, "loss": 0.3238, "step": 4702 }, { "epoch": 0.2597194610117075, "grad_norm": 0.02468913607299328, "learning_rate": 3.471664583404103e-05, "loss": 0.0012, "step": 4703 }, { "epoch": 0.2597746852220013, "grad_norm": 4.676607608795166, "learning_rate": 3.471422317449913e-05, "loss": 0.7474, "step": 4704 }, { "epoch": 0.2598299094322951, "grad_norm": 4.631119728088379, "learning_rate": 3.4711800044207336e-05, "loss": 1.1501, "step": 4705 }, { "epoch": 0.2598851336425889, "grad_norm": 2.0530080795288086, "learning_rate": 3.4709376443243184e-05, "loss": 0.6879, "step": 4706 }, { "epoch": 0.2599403578528827, "grad_norm": 0.6401739120483398, "learning_rate": 3.47069523716842e-05, "loss": 0.0181, "step": 4707 }, { "epoch": 0.2599955820631765, "grad_norm": 0.3853670656681061, "learning_rate": 3.470452782960794e-05, "loss": 0.0146, "step": 4708 }, { "epoch": 0.26005080627347027, "grad_norm": 0.013653390109539032, "learning_rate": 3.470210281709197e-05, "loss": 0.0006, "step": 4709 }, { "epoch": 0.2601060304837641, "grad_norm": 2.061929941177368, "learning_rate": 3.4699677334213884e-05, "loss": 0.0494, "step": 4710 }, { "epoch": 0.2601612546940579, "grad_norm": 3.99882435798645, "learning_rate": 3.469725138105127e-05, "loss": 0.0694, "step": 4711 }, { "epoch": 0.2602164789043517, "grad_norm": 2.647210121154785, "learning_rate": 3.469482495768174e-05, "loss": 0.3515, "step": 4712 }, { "epoch": 0.2602717031146455, "grad_norm": 0.07279973477125168, "learning_rate": 3.469239806418293e-05, "loss": 0.0029, "step": 4713 }, { "epoch": 0.26032692732493923, "grad_norm": 2.234382390975952, "learning_rate": 3.468997070063247e-05, "loss": 0.1869, "step": 4714 }, { "epoch": 0.26038215153523303, "grad_norm": 0.05501585453748703, "learning_rate": 3.468754286710803e-05, "loss": 0.002, "step": 4715 }, { "epoch": 0.26043737574552683, "grad_norm": 2.3910298347473145, "learning_rate": 3.468511456368728e-05, "loss": 0.2172, "step": 4716 }, { "epoch": 0.26049259995582064, "grad_norm": 6.3571624755859375, "learning_rate": 3.468268579044791e-05, "loss": 0.3725, "step": 4717 }, { "epoch": 0.26054782416611444, "grad_norm": 1.4810832738876343, "learning_rate": 3.4680256547467616e-05, "loss": 0.1547, "step": 4718 }, { "epoch": 0.26060304837640824, "grad_norm": 4.085110664367676, "learning_rate": 3.467782683482413e-05, "loss": 0.5977, "step": 4719 }, { "epoch": 0.260658272586702, "grad_norm": 1.792527675628662, "learning_rate": 3.467539665259518e-05, "loss": 0.0868, "step": 4720 }, { "epoch": 0.2607134967969958, "grad_norm": 0.14580507576465607, "learning_rate": 3.467296600085851e-05, "loss": 0.0053, "step": 4721 }, { "epoch": 0.2607687210072896, "grad_norm": 0.1334480196237564, "learning_rate": 3.467053487969188e-05, "loss": 0.005, "step": 4722 }, { "epoch": 0.2608239452175834, "grad_norm": 0.45372048020362854, "learning_rate": 3.466810328917307e-05, "loss": 0.0093, "step": 4723 }, { "epoch": 0.2608791694278772, "grad_norm": 2.5508570671081543, "learning_rate": 3.466567122937989e-05, "loss": 0.797, "step": 4724 }, { "epoch": 0.26093439363817095, "grad_norm": 4.000854969024658, "learning_rate": 3.466323870039013e-05, "loss": 0.7008, "step": 4725 }, { "epoch": 0.26098961784846475, "grad_norm": 4.4584503173828125, "learning_rate": 3.466080570228162e-05, "loss": 1.2269, "step": 4726 }, { "epoch": 0.26104484205875855, "grad_norm": 0.058617979288101196, "learning_rate": 3.4658372235132196e-05, "loss": 0.0025, "step": 4727 }, { "epoch": 0.26110006626905236, "grad_norm": 2.6175715923309326, "learning_rate": 3.465593829901972e-05, "loss": 0.1689, "step": 4728 }, { "epoch": 0.26115529047934616, "grad_norm": 0.018343402072787285, "learning_rate": 3.465350389402205e-05, "loss": 0.0009, "step": 4729 }, { "epoch": 0.26121051468963996, "grad_norm": 2.754776954650879, "learning_rate": 3.465106902021708e-05, "loss": 0.1184, "step": 4730 }, { "epoch": 0.2612657388999337, "grad_norm": 0.8647142052650452, "learning_rate": 3.464863367768269e-05, "loss": 0.0328, "step": 4731 }, { "epoch": 0.2613209631102275, "grad_norm": 3.1025924682617188, "learning_rate": 3.4646197866496815e-05, "loss": 0.3287, "step": 4732 }, { "epoch": 0.2613761873205213, "grad_norm": 2.850586175918579, "learning_rate": 3.4643761586737366e-05, "loss": 0.2684, "step": 4733 }, { "epoch": 0.2614314115308151, "grad_norm": 2.994039535522461, "learning_rate": 3.46413248384823e-05, "loss": 0.3337, "step": 4734 }, { "epoch": 0.2614866357411089, "grad_norm": 0.016903236508369446, "learning_rate": 3.463888762180957e-05, "loss": 0.0008, "step": 4735 }, { "epoch": 0.2615418599514027, "grad_norm": 0.6030492186546326, "learning_rate": 3.463644993679715e-05, "loss": 0.0213, "step": 4736 }, { "epoch": 0.26159708416169647, "grad_norm": 0.33366212248802185, "learning_rate": 3.463401178352303e-05, "loss": 0.0108, "step": 4737 }, { "epoch": 0.26165230837199027, "grad_norm": 3.9340085983276367, "learning_rate": 3.4631573162065214e-05, "loss": 0.1391, "step": 4738 }, { "epoch": 0.2617075325822841, "grad_norm": 0.5052974820137024, "learning_rate": 3.4629134072501714e-05, "loss": 0.0139, "step": 4739 }, { "epoch": 0.2617627567925779, "grad_norm": 4.313660621643066, "learning_rate": 3.462669451491057e-05, "loss": 1.6211, "step": 4740 }, { "epoch": 0.2618179810028717, "grad_norm": 4.508242130279541, "learning_rate": 3.462425448936982e-05, "loss": 0.7894, "step": 4741 }, { "epoch": 0.2618732052131654, "grad_norm": 0.1800365149974823, "learning_rate": 3.462181399595755e-05, "loss": 0.0061, "step": 4742 }, { "epoch": 0.26192842942345923, "grad_norm": 0.5128700733184814, "learning_rate": 3.461937303475182e-05, "loss": 0.0159, "step": 4743 }, { "epoch": 0.26198365363375303, "grad_norm": 0.6531338095664978, "learning_rate": 3.461693160583072e-05, "loss": 0.0152, "step": 4744 }, { "epoch": 0.26203887784404684, "grad_norm": 2.8691556453704834, "learning_rate": 3.461448970927237e-05, "loss": 0.6582, "step": 4745 }, { "epoch": 0.26209410205434064, "grad_norm": 1.4096500873565674, "learning_rate": 3.461204734515489e-05, "loss": 0.3032, "step": 4746 }, { "epoch": 0.26214932626463444, "grad_norm": 2.3686301708221436, "learning_rate": 3.4609604513556414e-05, "loss": 0.1691, "step": 4747 }, { "epoch": 0.2622045504749282, "grad_norm": 0.2123478502035141, "learning_rate": 3.4607161214555095e-05, "loss": 0.0058, "step": 4748 }, { "epoch": 0.262259774685222, "grad_norm": 0.009466638788580894, "learning_rate": 3.460471744822911e-05, "loss": 0.0004, "step": 4749 }, { "epoch": 0.2623149988955158, "grad_norm": 2.4641425609588623, "learning_rate": 3.460227321465663e-05, "loss": 0.1936, "step": 4750 }, { "epoch": 0.2623702231058096, "grad_norm": 1.5408456325531006, "learning_rate": 3.459982851391586e-05, "loss": 0.0449, "step": 4751 }, { "epoch": 0.2624254473161034, "grad_norm": 2.328936815261841, "learning_rate": 3.459738334608502e-05, "loss": 0.4431, "step": 4752 }, { "epoch": 0.26248067152639715, "grad_norm": 5.8535003662109375, "learning_rate": 3.459493771124232e-05, "loss": 1.8309, "step": 4753 }, { "epoch": 0.26253589573669095, "grad_norm": 0.2346535474061966, "learning_rate": 3.4592491609466016e-05, "loss": 0.0083, "step": 4754 }, { "epoch": 0.26259111994698475, "grad_norm": 2.763881206512451, "learning_rate": 3.459004504083436e-05, "loss": 0.5656, "step": 4755 }, { "epoch": 0.26264634415727856, "grad_norm": 2.3986361026763916, "learning_rate": 3.4587598005425634e-05, "loss": 0.7206, "step": 4756 }, { "epoch": 0.26270156836757236, "grad_norm": 2.9727182388305664, "learning_rate": 3.458515050331811e-05, "loss": 0.2367, "step": 4757 }, { "epoch": 0.26275679257786616, "grad_norm": 2.696791172027588, "learning_rate": 3.458270253459011e-05, "loss": 0.2888, "step": 4758 }, { "epoch": 0.2628120167881599, "grad_norm": 0.3150140941143036, "learning_rate": 3.458025409931994e-05, "loss": 0.0131, "step": 4759 }, { "epoch": 0.2628672409984537, "grad_norm": 1.9782353639602661, "learning_rate": 3.4577805197585925e-05, "loss": 0.1332, "step": 4760 }, { "epoch": 0.2629224652087475, "grad_norm": 0.07099713385105133, "learning_rate": 3.4575355829466424e-05, "loss": 0.0028, "step": 4761 }, { "epoch": 0.2629776894190413, "grad_norm": 1.5458234548568726, "learning_rate": 3.4572905995039794e-05, "loss": 0.0873, "step": 4762 }, { "epoch": 0.2630329136293351, "grad_norm": 0.950590968132019, "learning_rate": 3.457045569438442e-05, "loss": 0.0364, "step": 4763 }, { "epoch": 0.26308813783962887, "grad_norm": 2.200241804122925, "learning_rate": 3.456800492757868e-05, "loss": 0.1667, "step": 4764 }, { "epoch": 0.26314336204992267, "grad_norm": 0.6612810492515564, "learning_rate": 3.456555369470099e-05, "loss": 0.0204, "step": 4765 }, { "epoch": 0.26319858626021647, "grad_norm": 3.2490711212158203, "learning_rate": 3.456310199582978e-05, "loss": 0.5616, "step": 4766 }, { "epoch": 0.2632538104705103, "grad_norm": 3.871425151824951, "learning_rate": 3.456064983104347e-05, "loss": 0.779, "step": 4767 }, { "epoch": 0.2633090346808041, "grad_norm": 1.0530308485031128, "learning_rate": 3.455819720042052e-05, "loss": 0.0267, "step": 4768 }, { "epoch": 0.2633642588910979, "grad_norm": 3.220907211303711, "learning_rate": 3.45557441040394e-05, "loss": 0.9022, "step": 4769 }, { "epoch": 0.2634194831013916, "grad_norm": 0.04831717163324356, "learning_rate": 3.4553290541978584e-05, "loss": 0.0022, "step": 4770 }, { "epoch": 0.26347470731168543, "grad_norm": 2.0233476161956787, "learning_rate": 3.4550836514316576e-05, "loss": 0.1104, "step": 4771 }, { "epoch": 0.26352993152197923, "grad_norm": 0.4149476885795593, "learning_rate": 3.454838202113188e-05, "loss": 0.0175, "step": 4772 }, { "epoch": 0.26358515573227304, "grad_norm": 1.2792612314224243, "learning_rate": 3.4545927062503027e-05, "loss": 0.129, "step": 4773 }, { "epoch": 0.26364037994256684, "grad_norm": 2.853304147720337, "learning_rate": 3.454347163850855e-05, "loss": 0.6491, "step": 4774 }, { "epoch": 0.26369560415286064, "grad_norm": 3.616546392440796, "learning_rate": 3.454101574922702e-05, "loss": 0.7824, "step": 4775 }, { "epoch": 0.2637508283631544, "grad_norm": 1.4939696788787842, "learning_rate": 3.4538559394737e-05, "loss": 0.3813, "step": 4776 }, { "epoch": 0.2638060525734482, "grad_norm": 0.3018993139266968, "learning_rate": 3.453610257511708e-05, "loss": 0.0134, "step": 4777 }, { "epoch": 0.263861276783742, "grad_norm": 2.3877463340759277, "learning_rate": 3.453364529044584e-05, "loss": 0.4453, "step": 4778 }, { "epoch": 0.2639165009940358, "grad_norm": 0.13183575868606567, "learning_rate": 3.4531187540801924e-05, "loss": 0.0068, "step": 4779 }, { "epoch": 0.2639717252043296, "grad_norm": 1.6762973070144653, "learning_rate": 3.452872932626395e-05, "loss": 0.1201, "step": 4780 }, { "epoch": 0.26402694941462335, "grad_norm": 2.8642642498016357, "learning_rate": 3.452627064691056e-05, "loss": 0.5112, "step": 4781 }, { "epoch": 0.26408217362491715, "grad_norm": 2.349419116973877, "learning_rate": 3.452381150282042e-05, "loss": 0.334, "step": 4782 }, { "epoch": 0.26413739783521095, "grad_norm": 0.14889001846313477, "learning_rate": 3.45213518940722e-05, "loss": 0.0072, "step": 4783 }, { "epoch": 0.26419262204550475, "grad_norm": 3.1358649730682373, "learning_rate": 3.4518891820744597e-05, "loss": 0.6908, "step": 4784 }, { "epoch": 0.26424784625579856, "grad_norm": 0.15848839282989502, "learning_rate": 3.451643128291631e-05, "loss": 0.0075, "step": 4785 }, { "epoch": 0.26430307046609236, "grad_norm": 1.1466491222381592, "learning_rate": 3.4513970280666054e-05, "loss": 0.0476, "step": 4786 }, { "epoch": 0.2643582946763861, "grad_norm": 2.3926236629486084, "learning_rate": 3.451150881407257e-05, "loss": 0.4945, "step": 4787 }, { "epoch": 0.2644135188866799, "grad_norm": 3.380740165710449, "learning_rate": 3.450904688321461e-05, "loss": 0.5589, "step": 4788 }, { "epoch": 0.2644687430969737, "grad_norm": 0.10611094534397125, "learning_rate": 3.4506584488170934e-05, "loss": 0.0052, "step": 4789 }, { "epoch": 0.2645239673072675, "grad_norm": 3.1792688369750977, "learning_rate": 3.4504121629020326e-05, "loss": 0.5039, "step": 4790 }, { "epoch": 0.2645791915175613, "grad_norm": 3.893648386001587, "learning_rate": 3.450165830584157e-05, "loss": 0.61, "step": 4791 }, { "epoch": 0.26463441572785507, "grad_norm": 1.0779695510864258, "learning_rate": 3.4499194518713484e-05, "loss": 0.067, "step": 4792 }, { "epoch": 0.26468963993814887, "grad_norm": 0.07383324950933456, "learning_rate": 3.449673026771488e-05, "loss": 0.0035, "step": 4793 }, { "epoch": 0.26474486414844267, "grad_norm": 0.547254741191864, "learning_rate": 3.449426555292461e-05, "loss": 0.0198, "step": 4794 }, { "epoch": 0.2648000883587365, "grad_norm": 1.063507318496704, "learning_rate": 3.449180037442153e-05, "loss": 0.0494, "step": 4795 }, { "epoch": 0.2648553125690303, "grad_norm": 0.06094282492995262, "learning_rate": 3.448933473228449e-05, "loss": 0.0029, "step": 4796 }, { "epoch": 0.2649105367793241, "grad_norm": 0.06854923069477081, "learning_rate": 3.448686862659238e-05, "loss": 0.0034, "step": 4797 }, { "epoch": 0.2649657609896178, "grad_norm": 0.02791263721883297, "learning_rate": 3.448440205742411e-05, "loss": 0.0012, "step": 4798 }, { "epoch": 0.26502098519991163, "grad_norm": 2.771303176879883, "learning_rate": 3.4481935024858576e-05, "loss": 0.368, "step": 4799 }, { "epoch": 0.26507620941020543, "grad_norm": 11.441725730895996, "learning_rate": 3.4479467528974715e-05, "loss": 0.5742, "step": 4800 }, { "epoch": 0.26513143362049924, "grad_norm": 0.32750001549720764, "learning_rate": 3.4476999569851464e-05, "loss": 0.0191, "step": 4801 }, { "epoch": 0.26518665783079304, "grad_norm": 0.5900338292121887, "learning_rate": 3.447453114756779e-05, "loss": 0.0191, "step": 4802 }, { "epoch": 0.2652418820410868, "grad_norm": 0.4946543276309967, "learning_rate": 3.447206226220265e-05, "loss": 0.0239, "step": 4803 }, { "epoch": 0.2652971062513806, "grad_norm": 0.026690717786550522, "learning_rate": 3.446959291383504e-05, "loss": 0.0014, "step": 4804 }, { "epoch": 0.2653523304616744, "grad_norm": 1.5235592126846313, "learning_rate": 3.4467123102543954e-05, "loss": 0.2695, "step": 4805 }, { "epoch": 0.2654075546719682, "grad_norm": 4.186145782470703, "learning_rate": 3.4464652828408425e-05, "loss": 0.7521, "step": 4806 }, { "epoch": 0.265462778882262, "grad_norm": 2.987382173538208, "learning_rate": 3.4462182091507464e-05, "loss": 0.3337, "step": 4807 }, { "epoch": 0.2655180030925558, "grad_norm": 3.539292573928833, "learning_rate": 3.445971089192013e-05, "loss": 1.2499, "step": 4808 }, { "epoch": 0.26557322730284955, "grad_norm": 2.0460073947906494, "learning_rate": 3.445723922972548e-05, "loss": 1.0937, "step": 4809 }, { "epoch": 0.26562845151314335, "grad_norm": 0.23532384634017944, "learning_rate": 3.4454767105002586e-05, "loss": 0.0094, "step": 4810 }, { "epoch": 0.26568367572343715, "grad_norm": 0.07326781749725342, "learning_rate": 3.445229451783054e-05, "loss": 0.0033, "step": 4811 }, { "epoch": 0.26573889993373095, "grad_norm": 3.1700222492218018, "learning_rate": 3.4449821468288454e-05, "loss": 0.8059, "step": 4812 }, { "epoch": 0.26579412414402476, "grad_norm": 1.9047449827194214, "learning_rate": 3.444734795645544e-05, "loss": 0.0932, "step": 4813 }, { "epoch": 0.26584934835431856, "grad_norm": 0.02596326358616352, "learning_rate": 3.444487398241064e-05, "loss": 0.0014, "step": 4814 }, { "epoch": 0.2659045725646123, "grad_norm": 1.8708703517913818, "learning_rate": 3.444239954623319e-05, "loss": 0.1497, "step": 4815 }, { "epoch": 0.2659597967749061, "grad_norm": 0.5261595249176025, "learning_rate": 3.443992464800227e-05, "loss": 0.0181, "step": 4816 }, { "epoch": 0.2660150209851999, "grad_norm": 0.07346481829881668, "learning_rate": 3.443744928779704e-05, "loss": 0.0029, "step": 4817 }, { "epoch": 0.2660702451954937, "grad_norm": 0.15298667550086975, "learning_rate": 3.443497346569672e-05, "loss": 0.0056, "step": 4818 }, { "epoch": 0.2661254694057875, "grad_norm": 1.9448678493499756, "learning_rate": 3.44324971817805e-05, "loss": 0.2595, "step": 4819 }, { "epoch": 0.26618069361608127, "grad_norm": 0.03659292683005333, "learning_rate": 3.4430020436127604e-05, "loss": 0.0021, "step": 4820 }, { "epoch": 0.26623591782637507, "grad_norm": 3.770137310028076, "learning_rate": 3.442754322881727e-05, "loss": 0.2111, "step": 4821 }, { "epoch": 0.26629114203666887, "grad_norm": 3.452467203140259, "learning_rate": 3.4425065559928766e-05, "loss": 0.6061, "step": 4822 }, { "epoch": 0.2663463662469627, "grad_norm": 0.2158707231283188, "learning_rate": 3.442258742954134e-05, "loss": 0.0078, "step": 4823 }, { "epoch": 0.2664015904572565, "grad_norm": 0.28204864263534546, "learning_rate": 3.442010883773429e-05, "loss": 0.0105, "step": 4824 }, { "epoch": 0.2664568146675503, "grad_norm": 2.2156951427459717, "learning_rate": 3.44176297845869e-05, "loss": 0.191, "step": 4825 }, { "epoch": 0.266512038877844, "grad_norm": 3.6035211086273193, "learning_rate": 3.441515027017849e-05, "loss": 0.6404, "step": 4826 }, { "epoch": 0.26656726308813783, "grad_norm": 2.2421703338623047, "learning_rate": 3.4412670294588384e-05, "loss": 0.1635, "step": 4827 }, { "epoch": 0.26662248729843163, "grad_norm": 0.2448693811893463, "learning_rate": 3.441018985789593e-05, "loss": 0.007, "step": 4828 }, { "epoch": 0.26667771150872543, "grad_norm": 5.089130878448486, "learning_rate": 3.440770896018047e-05, "loss": 1.2559, "step": 4829 }, { "epoch": 0.26673293571901924, "grad_norm": 4.032748699188232, "learning_rate": 3.4405227601521384e-05, "loss": 0.3671, "step": 4830 }, { "epoch": 0.266788159929313, "grad_norm": 2.378751516342163, "learning_rate": 3.440274578199806e-05, "loss": 0.1838, "step": 4831 }, { "epoch": 0.2668433841396068, "grad_norm": 5.73467493057251, "learning_rate": 3.44002635016899e-05, "loss": 0.2597, "step": 4832 }, { "epoch": 0.2668986083499006, "grad_norm": 0.05211401730775833, "learning_rate": 3.439778076067631e-05, "loss": 0.0022, "step": 4833 }, { "epoch": 0.2669538325601944, "grad_norm": 2.8562865257263184, "learning_rate": 3.439529755903672e-05, "loss": 0.4406, "step": 4834 }, { "epoch": 0.2670090567704882, "grad_norm": 0.22343429923057556, "learning_rate": 3.439281389685059e-05, "loss": 0.0094, "step": 4835 }, { "epoch": 0.267064280980782, "grad_norm": 0.37817540764808655, "learning_rate": 3.4390329774197364e-05, "loss": 0.0133, "step": 4836 }, { "epoch": 0.26711950519107575, "grad_norm": 0.3131476938724518, "learning_rate": 3.4387845191156525e-05, "loss": 0.0121, "step": 4837 }, { "epoch": 0.26717472940136955, "grad_norm": 1.914597988128662, "learning_rate": 3.438536014780755e-05, "loss": 0.2663, "step": 4838 }, { "epoch": 0.26722995361166335, "grad_norm": 1.9849853515625, "learning_rate": 3.438287464422995e-05, "loss": 0.1867, "step": 4839 }, { "epoch": 0.26728517782195715, "grad_norm": 0.09632519632577896, "learning_rate": 3.438038868050325e-05, "loss": 0.003, "step": 4840 }, { "epoch": 0.26734040203225096, "grad_norm": 0.1429690420627594, "learning_rate": 3.437790225670697e-05, "loss": 0.0056, "step": 4841 }, { "epoch": 0.2673956262425447, "grad_norm": 0.05980958789587021, "learning_rate": 3.437541537292067e-05, "loss": 0.0029, "step": 4842 }, { "epoch": 0.2674508504528385, "grad_norm": 0.7736377120018005, "learning_rate": 3.437292802922391e-05, "loss": 0.0238, "step": 4843 }, { "epoch": 0.2675060746631323, "grad_norm": 0.9706251621246338, "learning_rate": 3.437044022569627e-05, "loss": 0.0947, "step": 4844 }, { "epoch": 0.2675612988734261, "grad_norm": 0.04511591047048569, "learning_rate": 3.436795196241732e-05, "loss": 0.0022, "step": 4845 }, { "epoch": 0.2676165230837199, "grad_norm": 1.6534043550491333, "learning_rate": 3.436546323946669e-05, "loss": 0.0672, "step": 4846 }, { "epoch": 0.2676717472940137, "grad_norm": 0.2698085606098175, "learning_rate": 3.4362974056923994e-05, "loss": 0.0069, "step": 4847 }, { "epoch": 0.26772697150430746, "grad_norm": 3.5915169715881348, "learning_rate": 3.436048441486887e-05, "loss": 0.8082, "step": 4848 }, { "epoch": 0.26778219571460127, "grad_norm": 0.059514280408620834, "learning_rate": 3.435799431338097e-05, "loss": 0.002, "step": 4849 }, { "epoch": 0.26783741992489507, "grad_norm": 0.10722415894269943, "learning_rate": 3.435550375253995e-05, "loss": 0.0032, "step": 4850 }, { "epoch": 0.2678926441351889, "grad_norm": 0.9425435066223145, "learning_rate": 3.43530127324255e-05, "loss": 0.0441, "step": 4851 }, { "epoch": 0.2679478683454827, "grad_norm": 2.6577188968658447, "learning_rate": 3.435052125311731e-05, "loss": 0.9061, "step": 4852 }, { "epoch": 0.2680030925557765, "grad_norm": 0.8338409662246704, "learning_rate": 3.434802931469509e-05, "loss": 0.0421, "step": 4853 }, { "epoch": 0.2680583167660702, "grad_norm": 0.09376384317874908, "learning_rate": 3.434553691723857e-05, "loss": 0.0037, "step": 4854 }, { "epoch": 0.26811354097636403, "grad_norm": 3.2943577766418457, "learning_rate": 3.434304406082748e-05, "loss": 0.9311, "step": 4855 }, { "epoch": 0.26816876518665783, "grad_norm": 3.0901031494140625, "learning_rate": 3.4340550745541586e-05, "loss": 0.3106, "step": 4856 }, { "epoch": 0.26822398939695163, "grad_norm": 0.016111720353364944, "learning_rate": 3.433805697146064e-05, "loss": 0.0008, "step": 4857 }, { "epoch": 0.26827921360724544, "grad_norm": 0.10394521057605743, "learning_rate": 3.433556273866443e-05, "loss": 0.0037, "step": 4858 }, { "epoch": 0.2683344378175392, "grad_norm": 1.987990140914917, "learning_rate": 3.4333068047232764e-05, "loss": 0.2291, "step": 4859 }, { "epoch": 0.268389662027833, "grad_norm": 2.0525217056274414, "learning_rate": 3.433057289724544e-05, "loss": 0.1879, "step": 4860 }, { "epoch": 0.2684448862381268, "grad_norm": 3.2813427448272705, "learning_rate": 3.4328077288782295e-05, "loss": 0.4159, "step": 4861 }, { "epoch": 0.2685001104484206, "grad_norm": 2.0924949645996094, "learning_rate": 3.432558122192317e-05, "loss": 0.0747, "step": 4862 }, { "epoch": 0.2685553346587144, "grad_norm": 0.06677120923995972, "learning_rate": 3.4323084696747916e-05, "loss": 0.0022, "step": 4863 }, { "epoch": 0.2686105588690082, "grad_norm": 0.6701928973197937, "learning_rate": 3.43205877133364e-05, "loss": 0.023, "step": 4864 }, { "epoch": 0.26866578307930195, "grad_norm": 0.0952998623251915, "learning_rate": 3.431809027176853e-05, "loss": 0.0031, "step": 4865 }, { "epoch": 0.26872100728959575, "grad_norm": 0.006353576667606831, "learning_rate": 3.431559237212418e-05, "loss": 0.0003, "step": 4866 }, { "epoch": 0.26877623149988955, "grad_norm": 0.021256737411022186, "learning_rate": 3.431309401448327e-05, "loss": 0.001, "step": 4867 }, { "epoch": 0.26883145571018335, "grad_norm": 0.19382832944393158, "learning_rate": 3.431059519892574e-05, "loss": 0.006, "step": 4868 }, { "epoch": 0.26888667992047716, "grad_norm": 1.9736535549163818, "learning_rate": 3.430809592553153e-05, "loss": 0.1911, "step": 4869 }, { "epoch": 0.2689419041307709, "grad_norm": 4.59653377532959, "learning_rate": 3.43055961943806e-05, "loss": 0.8981, "step": 4870 }, { "epoch": 0.2689971283410647, "grad_norm": 2.4884848594665527, "learning_rate": 3.430309600555292e-05, "loss": 0.3552, "step": 4871 }, { "epoch": 0.2690523525513585, "grad_norm": 4.904277801513672, "learning_rate": 3.430059535912848e-05, "loss": 0.2128, "step": 4872 }, { "epoch": 0.2691075767616523, "grad_norm": 0.3724669814109802, "learning_rate": 3.429809425518728e-05, "loss": 0.0134, "step": 4873 }, { "epoch": 0.2691628009719461, "grad_norm": 2.2389492988586426, "learning_rate": 3.429559269380934e-05, "loss": 0.7448, "step": 4874 }, { "epoch": 0.2692180251822399, "grad_norm": 1.6096572875976562, "learning_rate": 3.42930906750747e-05, "loss": 0.1555, "step": 4875 }, { "epoch": 0.26927324939253366, "grad_norm": 4.614478588104248, "learning_rate": 3.429058819906339e-05, "loss": 0.6721, "step": 4876 }, { "epoch": 0.26932847360282747, "grad_norm": 2.871497631072998, "learning_rate": 3.428808526585548e-05, "loss": 0.1463, "step": 4877 }, { "epoch": 0.26938369781312127, "grad_norm": 0.37533098459243774, "learning_rate": 3.428558187553105e-05, "loss": 0.0119, "step": 4878 }, { "epoch": 0.2694389220234151, "grad_norm": 0.15404647588729858, "learning_rate": 3.4283078028170185e-05, "loss": 0.0032, "step": 4879 }, { "epoch": 0.2694941462337089, "grad_norm": 0.035642821341753006, "learning_rate": 3.428057372385299e-05, "loss": 0.0009, "step": 4880 }, { "epoch": 0.2695493704440027, "grad_norm": 1.5515598058700562, "learning_rate": 3.427806896265959e-05, "loss": 0.0301, "step": 4881 }, { "epoch": 0.2696045946542964, "grad_norm": 1.8259130716323853, "learning_rate": 3.427556374467011e-05, "loss": 0.3538, "step": 4882 }, { "epoch": 0.26965981886459023, "grad_norm": 4.09838342666626, "learning_rate": 3.427305806996471e-05, "loss": 0.5012, "step": 4883 }, { "epoch": 0.26971504307488403, "grad_norm": 2.980293035507202, "learning_rate": 3.427055193862355e-05, "loss": 0.1483, "step": 4884 }, { "epoch": 0.26977026728517783, "grad_norm": 2.1428170204162598, "learning_rate": 3.426804535072681e-05, "loss": 0.2357, "step": 4885 }, { "epoch": 0.26982549149547164, "grad_norm": 2.5738589763641357, "learning_rate": 3.4265538306354676e-05, "loss": 0.1709, "step": 4886 }, { "epoch": 0.2698807157057654, "grad_norm": 2.8348567485809326, "learning_rate": 3.426303080558736e-05, "loss": 0.603, "step": 4887 }, { "epoch": 0.2699359399160592, "grad_norm": 0.009173592552542686, "learning_rate": 3.426052284850507e-05, "loss": 0.0004, "step": 4888 }, { "epoch": 0.269991164126353, "grad_norm": 1.3368635177612305, "learning_rate": 3.4258014435188074e-05, "loss": 0.0527, "step": 4889 }, { "epoch": 0.2700463883366468, "grad_norm": 0.054487910121679306, "learning_rate": 3.42555055657166e-05, "loss": 0.0015, "step": 4890 }, { "epoch": 0.2701016125469406, "grad_norm": 1.1007593870162964, "learning_rate": 3.425299624017092e-05, "loss": 0.1908, "step": 4891 }, { "epoch": 0.2701568367572344, "grad_norm": 1.2369574308395386, "learning_rate": 3.425048645863132e-05, "loss": 0.2819, "step": 4892 }, { "epoch": 0.27021206096752814, "grad_norm": 3.192476272583008, "learning_rate": 3.424797622117807e-05, "loss": 0.1216, "step": 4893 }, { "epoch": 0.27026728517782195, "grad_norm": 0.7977995276451111, "learning_rate": 3.424546552789151e-05, "loss": 0.04, "step": 4894 }, { "epoch": 0.27032250938811575, "grad_norm": 2.162288188934326, "learning_rate": 3.424295437885196e-05, "loss": 0.1571, "step": 4895 }, { "epoch": 0.27037773359840955, "grad_norm": 1.3453145027160645, "learning_rate": 3.4240442774139745e-05, "loss": 0.191, "step": 4896 }, { "epoch": 0.27043295780870336, "grad_norm": 0.8487066030502319, "learning_rate": 3.423793071383522e-05, "loss": 0.0402, "step": 4897 }, { "epoch": 0.2704881820189971, "grad_norm": 0.10946665704250336, "learning_rate": 3.423541819801876e-05, "loss": 0.0028, "step": 4898 }, { "epoch": 0.2705434062292909, "grad_norm": 2.1307053565979004, "learning_rate": 3.4232905226770746e-05, "loss": 0.0742, "step": 4899 }, { "epoch": 0.2705986304395847, "grad_norm": 1.683623194694519, "learning_rate": 3.423039180017158e-05, "loss": 0.159, "step": 4900 }, { "epoch": 0.2706538546498785, "grad_norm": 2.4669721126556396, "learning_rate": 3.4227877918301664e-05, "loss": 0.2701, "step": 4901 }, { "epoch": 0.2707090788601723, "grad_norm": 5.9912190437316895, "learning_rate": 3.4225363581241426e-05, "loss": 1.2742, "step": 4902 }, { "epoch": 0.2707643030704661, "grad_norm": 3.8165013790130615, "learning_rate": 3.4222848789071314e-05, "loss": 0.5817, "step": 4903 }, { "epoch": 0.27081952728075986, "grad_norm": 1.5942609310150146, "learning_rate": 3.4220333541871776e-05, "loss": 0.1105, "step": 4904 }, { "epoch": 0.27087475149105367, "grad_norm": 2.908576011657715, "learning_rate": 3.4217817839723286e-05, "loss": 0.4796, "step": 4905 }, { "epoch": 0.27092997570134747, "grad_norm": 0.056498877704143524, "learning_rate": 3.421530168270632e-05, "loss": 0.0026, "step": 4906 }, { "epoch": 0.2709851999116413, "grad_norm": 4.082444667816162, "learning_rate": 3.421278507090139e-05, "loss": 1.3778, "step": 4907 }, { "epoch": 0.2710404241219351, "grad_norm": 0.20555365085601807, "learning_rate": 3.4210268004389005e-05, "loss": 0.0055, "step": 4908 }, { "epoch": 0.2710956483322288, "grad_norm": 2.503659725189209, "learning_rate": 3.420775048324969e-05, "loss": 0.0982, "step": 4909 }, { "epoch": 0.2711508725425226, "grad_norm": 0.6912412047386169, "learning_rate": 3.420523250756399e-05, "loss": 0.0361, "step": 4910 }, { "epoch": 0.27120609675281643, "grad_norm": 0.16312333941459656, "learning_rate": 3.420271407741246e-05, "loss": 0.0091, "step": 4911 }, { "epoch": 0.27126132096311023, "grad_norm": 2.409153699874878, "learning_rate": 3.4200195192875675e-05, "loss": 0.71, "step": 4912 }, { "epoch": 0.27131654517340403, "grad_norm": 1.6508623361587524, "learning_rate": 3.419767585403422e-05, "loss": 0.0635, "step": 4913 }, { "epoch": 0.27137176938369784, "grad_norm": 0.9950856566429138, "learning_rate": 3.4195156060968693e-05, "loss": 0.0287, "step": 4914 }, { "epoch": 0.2714269935939916, "grad_norm": 2.2373719215393066, "learning_rate": 3.4192635813759715e-05, "loss": 0.5803, "step": 4915 }, { "epoch": 0.2714822178042854, "grad_norm": 3.118953227996826, "learning_rate": 3.419011511248791e-05, "loss": 0.8743, "step": 4916 }, { "epoch": 0.2715374420145792, "grad_norm": 2.2372803688049316, "learning_rate": 3.4187593957233925e-05, "loss": 0.0867, "step": 4917 }, { "epoch": 0.271592666224873, "grad_norm": 2.8511152267456055, "learning_rate": 3.418507234807842e-05, "loss": 0.2746, "step": 4918 }, { "epoch": 0.2716478904351668, "grad_norm": 0.2817327380180359, "learning_rate": 3.418255028510207e-05, "loss": 0.0092, "step": 4919 }, { "epoch": 0.2717031146454606, "grad_norm": 2.602815628051758, "learning_rate": 3.418002776838556e-05, "loss": 0.2605, "step": 4920 }, { "epoch": 0.27175833885575434, "grad_norm": 3.828526496887207, "learning_rate": 3.417750479800959e-05, "loss": 1.1218, "step": 4921 }, { "epoch": 0.27181356306604815, "grad_norm": 0.05440918356180191, "learning_rate": 3.4174981374054885e-05, "loss": 0.0024, "step": 4922 }, { "epoch": 0.27186878727634195, "grad_norm": 0.048761483281850815, "learning_rate": 3.4172457496602164e-05, "loss": 0.0023, "step": 4923 }, { "epoch": 0.27192401148663575, "grad_norm": 1.1659432649612427, "learning_rate": 3.4169933165732184e-05, "loss": 0.0483, "step": 4924 }, { "epoch": 0.27197923569692956, "grad_norm": 2.5742275714874268, "learning_rate": 3.41674083815257e-05, "loss": 0.0877, "step": 4925 }, { "epoch": 0.2720344599072233, "grad_norm": 4.481043338775635, "learning_rate": 3.4164883144063495e-05, "loss": 0.8958, "step": 4926 }, { "epoch": 0.2720896841175171, "grad_norm": 3.21303391456604, "learning_rate": 3.4162357453426345e-05, "loss": 1.1025, "step": 4927 }, { "epoch": 0.2721449083278109, "grad_norm": 1.3177443742752075, "learning_rate": 3.415983130969506e-05, "loss": 0.0554, "step": 4928 }, { "epoch": 0.2722001325381047, "grad_norm": 4.132437229156494, "learning_rate": 3.4157304712950474e-05, "loss": 1.064, "step": 4929 }, { "epoch": 0.2722553567483985, "grad_norm": 0.18211409449577332, "learning_rate": 3.4154777663273395e-05, "loss": 0.0079, "step": 4930 }, { "epoch": 0.2723105809586923, "grad_norm": 1.4738473892211914, "learning_rate": 3.4152250160744686e-05, "loss": 0.0942, "step": 4931 }, { "epoch": 0.27236580516898606, "grad_norm": 4.133862018585205, "learning_rate": 3.41497222054452e-05, "loss": 0.9292, "step": 4932 }, { "epoch": 0.27242102937927987, "grad_norm": 0.6095134615898132, "learning_rate": 3.414719379745582e-05, "loss": 0.0315, "step": 4933 }, { "epoch": 0.27247625358957367, "grad_norm": 2.40518856048584, "learning_rate": 3.414466493685744e-05, "loss": 0.3853, "step": 4934 }, { "epoch": 0.27253147779986747, "grad_norm": 0.33770108222961426, "learning_rate": 3.4142135623730954e-05, "loss": 0.0104, "step": 4935 }, { "epoch": 0.2725867020101613, "grad_norm": 3.1764965057373047, "learning_rate": 3.413960585815729e-05, "loss": 0.5342, "step": 4936 }, { "epoch": 0.272641926220455, "grad_norm": 0.7949164509773254, "learning_rate": 3.4137075640217385e-05, "loss": 0.0252, "step": 4937 }, { "epoch": 0.2726971504307488, "grad_norm": 1.8887856006622314, "learning_rate": 3.413454496999218e-05, "loss": 0.2837, "step": 4938 }, { "epoch": 0.2727523746410426, "grad_norm": 0.1454571634531021, "learning_rate": 3.413201384756264e-05, "loss": 0.0047, "step": 4939 }, { "epoch": 0.27280759885133643, "grad_norm": 0.19235876202583313, "learning_rate": 3.412948227300975e-05, "loss": 0.005, "step": 4940 }, { "epoch": 0.27286282306163023, "grad_norm": 0.19065949320793152, "learning_rate": 3.412695024641449e-05, "loss": 0.0092, "step": 4941 }, { "epoch": 0.27291804727192404, "grad_norm": 0.3264700472354889, "learning_rate": 3.4124417767857885e-05, "loss": 0.0079, "step": 4942 }, { "epoch": 0.2729732714822178, "grad_norm": 0.7643177509307861, "learning_rate": 3.4121884837420945e-05, "loss": 0.0316, "step": 4943 }, { "epoch": 0.2730284956925116, "grad_norm": 0.1878068745136261, "learning_rate": 3.4119351455184694e-05, "loss": 0.0097, "step": 4944 }, { "epoch": 0.2730837199028054, "grad_norm": 1.4509955644607544, "learning_rate": 3.41168176212302e-05, "loss": 0.1901, "step": 4945 }, { "epoch": 0.2731389441130992, "grad_norm": 2.5297021865844727, "learning_rate": 3.411428333563852e-05, "loss": 0.2228, "step": 4946 }, { "epoch": 0.273194168323393, "grad_norm": 1.229928970336914, "learning_rate": 3.411174859849074e-05, "loss": 0.0983, "step": 4947 }, { "epoch": 0.27324939253368674, "grad_norm": 4.261417388916016, "learning_rate": 3.4109213409867945e-05, "loss": 0.9442, "step": 4948 }, { "epoch": 0.27330461674398054, "grad_norm": 0.12897475063800812, "learning_rate": 3.4106677769851244e-05, "loss": 0.0034, "step": 4949 }, { "epoch": 0.27335984095427435, "grad_norm": 2.1164519786834717, "learning_rate": 3.410414167852176e-05, "loss": 0.4104, "step": 4950 }, { "epoch": 0.27341506516456815, "grad_norm": 0.8865818381309509, "learning_rate": 3.410160513596063e-05, "loss": 0.0387, "step": 4951 }, { "epoch": 0.27347028937486195, "grad_norm": 1.7108303308486938, "learning_rate": 3.409906814224901e-05, "loss": 0.0731, "step": 4952 }, { "epoch": 0.27352551358515576, "grad_norm": 0.9556367993354797, "learning_rate": 3.409653069746807e-05, "loss": 0.0583, "step": 4953 }, { "epoch": 0.2735807377954495, "grad_norm": 0.11426711082458496, "learning_rate": 3.409399280169897e-05, "loss": 0.0021, "step": 4954 }, { "epoch": 0.2736359620057433, "grad_norm": 2.4941656589508057, "learning_rate": 3.409145445502292e-05, "loss": 0.5259, "step": 4955 }, { "epoch": 0.2736911862160371, "grad_norm": 0.28333422541618347, "learning_rate": 3.408891565752112e-05, "loss": 0.0073, "step": 4956 }, { "epoch": 0.2737464104263309, "grad_norm": 2.1904382705688477, "learning_rate": 3.408637640927481e-05, "loss": 0.1517, "step": 4957 }, { "epoch": 0.2738016346366247, "grad_norm": 1.153733730316162, "learning_rate": 3.4083836710365203e-05, "loss": 0.0351, "step": 4958 }, { "epoch": 0.2738568588469185, "grad_norm": 2.9715819358825684, "learning_rate": 3.408129656087358e-05, "loss": 0.9043, "step": 4959 }, { "epoch": 0.27391208305721226, "grad_norm": 3.2928295135498047, "learning_rate": 3.407875596088118e-05, "loss": 0.4088, "step": 4960 }, { "epoch": 0.27396730726750607, "grad_norm": 1.852312684059143, "learning_rate": 3.40762149104693e-05, "loss": 0.328, "step": 4961 }, { "epoch": 0.27402253147779987, "grad_norm": 2.326573610305786, "learning_rate": 3.4073673409719233e-05, "loss": 0.1433, "step": 4962 }, { "epoch": 0.27407775568809367, "grad_norm": 0.7402355670928955, "learning_rate": 3.407113145871229e-05, "loss": 0.0304, "step": 4963 }, { "epoch": 0.2741329798983875, "grad_norm": 0.035697877407073975, "learning_rate": 3.406858905752979e-05, "loss": 0.0015, "step": 4964 }, { "epoch": 0.2741882041086812, "grad_norm": 0.030909568071365356, "learning_rate": 3.406604620625307e-05, "loss": 0.001, "step": 4965 }, { "epoch": 0.274243428318975, "grad_norm": 3.4918770790100098, "learning_rate": 3.40635029049635e-05, "loss": 0.2712, "step": 4966 }, { "epoch": 0.2742986525292688, "grad_norm": 1.8411682844161987, "learning_rate": 3.406095915374242e-05, "loss": 0.5742, "step": 4967 }, { "epoch": 0.27435387673956263, "grad_norm": 0.08781681954860687, "learning_rate": 3.405841495267124e-05, "loss": 0.0023, "step": 4968 }, { "epoch": 0.27440910094985643, "grad_norm": 4.255640506744385, "learning_rate": 3.405587030183134e-05, "loss": 0.7817, "step": 4969 }, { "epoch": 0.27446432516015024, "grad_norm": 2.978276252746582, "learning_rate": 3.4053325201304125e-05, "loss": 0.575, "step": 4970 }, { "epoch": 0.274519549370444, "grad_norm": 0.2906384766101837, "learning_rate": 3.405077965117104e-05, "loss": 0.0094, "step": 4971 }, { "epoch": 0.2745747735807378, "grad_norm": 0.720862090587616, "learning_rate": 3.4048233651513505e-05, "loss": 0.0341, "step": 4972 }, { "epoch": 0.2746299977910316, "grad_norm": 1.38336980342865, "learning_rate": 3.4045687202412986e-05, "loss": 0.1196, "step": 4973 }, { "epoch": 0.2746852220013254, "grad_norm": 1.2956507205963135, "learning_rate": 3.4043140303950945e-05, "loss": 0.0531, "step": 4974 }, { "epoch": 0.2747404462116192, "grad_norm": 0.04561960697174072, "learning_rate": 3.4040592956208866e-05, "loss": 0.0023, "step": 4975 }, { "epoch": 0.27479567042191294, "grad_norm": 0.7732374668121338, "learning_rate": 3.4038045159268254e-05, "loss": 0.0198, "step": 4976 }, { "epoch": 0.27485089463220674, "grad_norm": 2.9090657234191895, "learning_rate": 3.40354969132106e-05, "loss": 0.2737, "step": 4977 }, { "epoch": 0.27490611884250055, "grad_norm": 2.367978811264038, "learning_rate": 3.403294821811746e-05, "loss": 0.1421, "step": 4978 }, { "epoch": 0.27496134305279435, "grad_norm": 2.028911590576172, "learning_rate": 3.403039907407034e-05, "loss": 0.0953, "step": 4979 }, { "epoch": 0.27501656726308815, "grad_norm": 0.14102095365524292, "learning_rate": 3.402784948115081e-05, "loss": 0.0038, "step": 4980 }, { "epoch": 0.27507179147338195, "grad_norm": 2.0560569763183594, "learning_rate": 3.4025299439440454e-05, "loss": 0.2263, "step": 4981 }, { "epoch": 0.2751270156836757, "grad_norm": 3.748823404312134, "learning_rate": 3.402274894902083e-05, "loss": 1.0702, "step": 4982 }, { "epoch": 0.2751822398939695, "grad_norm": 0.255473256111145, "learning_rate": 3.402019800997355e-05, "loss": 0.0071, "step": 4983 }, { "epoch": 0.2752374641042633, "grad_norm": 4.796751499176025, "learning_rate": 3.401764662238022e-05, "loss": 0.8936, "step": 4984 }, { "epoch": 0.2752926883145571, "grad_norm": 0.05549433454871178, "learning_rate": 3.401509478632247e-05, "loss": 0.0015, "step": 4985 }, { "epoch": 0.2753479125248509, "grad_norm": 2.2434403896331787, "learning_rate": 3.401254250188194e-05, "loss": 0.2197, "step": 4986 }, { "epoch": 0.27540313673514466, "grad_norm": 2.1571850776672363, "learning_rate": 3.400998976914028e-05, "loss": 0.1292, "step": 4987 }, { "epoch": 0.27545836094543846, "grad_norm": 0.07228947430849075, "learning_rate": 3.4007436588179164e-05, "loss": 0.0035, "step": 4988 }, { "epoch": 0.27551358515573227, "grad_norm": 1.6361364126205444, "learning_rate": 3.4004882959080276e-05, "loss": 0.0857, "step": 4989 }, { "epoch": 0.27556880936602607, "grad_norm": 0.9029746651649475, "learning_rate": 3.4002328881925305e-05, "loss": 0.0374, "step": 4990 }, { "epoch": 0.27562403357631987, "grad_norm": 0.3442058563232422, "learning_rate": 3.399977435679598e-05, "loss": 0.0131, "step": 4991 }, { "epoch": 0.2756792577866137, "grad_norm": 0.05992010980844498, "learning_rate": 3.399721938377401e-05, "loss": 0.0025, "step": 4992 }, { "epoch": 0.2757344819969074, "grad_norm": 1.2530184984207153, "learning_rate": 3.399466396294115e-05, "loss": 0.0877, "step": 4993 }, { "epoch": 0.2757897062072012, "grad_norm": 2.753525495529175, "learning_rate": 3.3992108094379146e-05, "loss": 0.1774, "step": 4994 }, { "epoch": 0.275844930417495, "grad_norm": 5.007463455200195, "learning_rate": 3.398955177816976e-05, "loss": 0.8907, "step": 4995 }, { "epoch": 0.27590015462778883, "grad_norm": 2.081632137298584, "learning_rate": 3.39869950143948e-05, "loss": 0.2311, "step": 4996 }, { "epoch": 0.27595537883808263, "grad_norm": 1.3237476348876953, "learning_rate": 3.398443780313605e-05, "loss": 0.1307, "step": 4997 }, { "epoch": 0.27601060304837643, "grad_norm": 3.764305591583252, "learning_rate": 3.398188014447532e-05, "loss": 0.708, "step": 4998 }, { "epoch": 0.2760658272586702, "grad_norm": 3.656647205352783, "learning_rate": 3.397932203849444e-05, "loss": 0.4808, "step": 4999 }, { "epoch": 0.276121051468964, "grad_norm": 0.08325141668319702, "learning_rate": 3.397676348527525e-05, "loss": 0.003, "step": 5000 }, { "epoch": 0.2761762756792578, "grad_norm": 2.469468832015991, "learning_rate": 3.39742044848996e-05, "loss": 0.7603, "step": 5001 }, { "epoch": 0.2762314998895516, "grad_norm": 3.7862980365753174, "learning_rate": 3.3971645037449375e-05, "loss": 0.1928, "step": 5002 }, { "epoch": 0.2762867240998454, "grad_norm": 0.19174717366695404, "learning_rate": 3.396908514300644e-05, "loss": 0.0047, "step": 5003 }, { "epoch": 0.27634194831013914, "grad_norm": 2.6862261295318604, "learning_rate": 3.396652480165271e-05, "loss": 0.4021, "step": 5004 }, { "epoch": 0.27639717252043294, "grad_norm": 0.5769820809364319, "learning_rate": 3.396396401347009e-05, "loss": 0.0158, "step": 5005 }, { "epoch": 0.27645239673072675, "grad_norm": 1.0999752283096313, "learning_rate": 3.396140277854051e-05, "loss": 0.1107, "step": 5006 }, { "epoch": 0.27650762094102055, "grad_norm": 2.6219987869262695, "learning_rate": 3.3958841096945905e-05, "loss": 0.4448, "step": 5007 }, { "epoch": 0.27656284515131435, "grad_norm": 1.918226718902588, "learning_rate": 3.395627896876823e-05, "loss": 0.2131, "step": 5008 }, { "epoch": 0.27661806936160815, "grad_norm": 0.36590102314949036, "learning_rate": 3.395371639408946e-05, "loss": 0.0144, "step": 5009 }, { "epoch": 0.2766732935719019, "grad_norm": 1.8136993646621704, "learning_rate": 3.395115337299159e-05, "loss": 0.0453, "step": 5010 }, { "epoch": 0.2767285177821957, "grad_norm": 3.211447238922119, "learning_rate": 3.39485899055566e-05, "loss": 0.1377, "step": 5011 }, { "epoch": 0.2767837419924895, "grad_norm": 0.43085867166519165, "learning_rate": 3.39460259918665e-05, "loss": 0.0149, "step": 5012 }, { "epoch": 0.2768389662027833, "grad_norm": 4.475324630737305, "learning_rate": 3.394346163200334e-05, "loss": 1.5533, "step": 5013 }, { "epoch": 0.2768941904130771, "grad_norm": 0.5223763585090637, "learning_rate": 3.394089682604914e-05, "loss": 0.0218, "step": 5014 }, { "epoch": 0.27694941462337086, "grad_norm": 1.8873587846755981, "learning_rate": 3.393833157408596e-05, "loss": 0.31, "step": 5015 }, { "epoch": 0.27700463883366466, "grad_norm": 0.1703457087278366, "learning_rate": 3.393576587619588e-05, "loss": 0.0062, "step": 5016 }, { "epoch": 0.27705986304395847, "grad_norm": 0.13021427392959595, "learning_rate": 3.3933199732460966e-05, "loss": 0.0049, "step": 5017 }, { "epoch": 0.27711508725425227, "grad_norm": 0.3848894238471985, "learning_rate": 3.393063314296333e-05, "loss": 0.0137, "step": 5018 }, { "epoch": 0.27717031146454607, "grad_norm": 0.5933595895767212, "learning_rate": 3.392806610778509e-05, "loss": 0.0242, "step": 5019 }, { "epoch": 0.2772255356748399, "grad_norm": 0.7373307347297668, "learning_rate": 3.3925498627008353e-05, "loss": 0.0239, "step": 5020 }, { "epoch": 0.2772807598851336, "grad_norm": 0.05185164511203766, "learning_rate": 3.392293070071527e-05, "loss": 0.0019, "step": 5021 }, { "epoch": 0.2773359840954274, "grad_norm": 2.239102363586426, "learning_rate": 3.392036232898801e-05, "loss": 0.1089, "step": 5022 }, { "epoch": 0.2773912083057212, "grad_norm": 2.436548948287964, "learning_rate": 3.3917793511908715e-05, "loss": 0.9649, "step": 5023 }, { "epoch": 0.27744643251601503, "grad_norm": 2.748767852783203, "learning_rate": 3.391522424955959e-05, "loss": 0.5194, "step": 5024 }, { "epoch": 0.27750165672630883, "grad_norm": 2.0778567790985107, "learning_rate": 3.3912654542022826e-05, "loss": 0.2515, "step": 5025 }, { "epoch": 0.2775568809366026, "grad_norm": 0.01632150076329708, "learning_rate": 3.391008438938064e-05, "loss": 0.0006, "step": 5026 }, { "epoch": 0.2776121051468964, "grad_norm": 0.14514094591140747, "learning_rate": 3.390751379171525e-05, "loss": 0.0038, "step": 5027 }, { "epoch": 0.2776673293571902, "grad_norm": 0.27620434761047363, "learning_rate": 3.39049427491089e-05, "loss": 0.0064, "step": 5028 }, { "epoch": 0.277722553567484, "grad_norm": 0.013993697240948677, "learning_rate": 3.390237126164385e-05, "loss": 0.0006, "step": 5029 }, { "epoch": 0.2777777777777778, "grad_norm": 0.5048975348472595, "learning_rate": 3.389979932940236e-05, "loss": 0.0067, "step": 5030 }, { "epoch": 0.2778330019880716, "grad_norm": 0.03364218398928642, "learning_rate": 3.389722695246672e-05, "loss": 0.0011, "step": 5031 }, { "epoch": 0.27788822619836534, "grad_norm": 4.716180801391602, "learning_rate": 3.389465413091922e-05, "loss": 0.461, "step": 5032 }, { "epoch": 0.27794345040865914, "grad_norm": 3.385713577270508, "learning_rate": 3.3892080864842187e-05, "loss": 0.6613, "step": 5033 }, { "epoch": 0.27799867461895295, "grad_norm": 0.01645328290760517, "learning_rate": 3.388950715431794e-05, "loss": 0.0004, "step": 5034 }, { "epoch": 0.27805389882924675, "grad_norm": 0.020310454070568085, "learning_rate": 3.388693299942881e-05, "loss": 0.0006, "step": 5035 }, { "epoch": 0.27810912303954055, "grad_norm": 1.8882302045822144, "learning_rate": 3.388435840025716e-05, "loss": 0.1126, "step": 5036 }, { "epoch": 0.27816434724983435, "grad_norm": 2.6241300106048584, "learning_rate": 3.388178335688536e-05, "loss": 0.5085, "step": 5037 }, { "epoch": 0.2782195714601281, "grad_norm": 3.980334997177124, "learning_rate": 3.387920786939579e-05, "loss": 0.881, "step": 5038 }, { "epoch": 0.2782747956704219, "grad_norm": 1.153396487236023, "learning_rate": 3.3876631937870846e-05, "loss": 0.0453, "step": 5039 }, { "epoch": 0.2783300198807157, "grad_norm": 2.8796439170837402, "learning_rate": 3.3874055562392945e-05, "loss": 0.1968, "step": 5040 }, { "epoch": 0.2783852440910095, "grad_norm": 0.023195460438728333, "learning_rate": 3.387147874304451e-05, "loss": 0.0007, "step": 5041 }, { "epoch": 0.2784404683013033, "grad_norm": 2.41850209236145, "learning_rate": 3.3868901479907976e-05, "loss": 0.063, "step": 5042 }, { "epoch": 0.27849569251159706, "grad_norm": 2.128775119781494, "learning_rate": 3.3866323773065796e-05, "loss": 0.3975, "step": 5043 }, { "epoch": 0.27855091672189086, "grad_norm": 0.02166791260242462, "learning_rate": 3.386374562260045e-05, "loss": 0.0009, "step": 5044 }, { "epoch": 0.27860614093218466, "grad_norm": 0.5209009051322937, "learning_rate": 3.386116702859441e-05, "loss": 0.0131, "step": 5045 }, { "epoch": 0.27866136514247847, "grad_norm": 3.6606311798095703, "learning_rate": 3.385858799113018e-05, "loss": 0.8421, "step": 5046 }, { "epoch": 0.27871658935277227, "grad_norm": 4.014236927032471, "learning_rate": 3.385600851029027e-05, "loss": 1.2992, "step": 5047 }, { "epoch": 0.2787718135630661, "grad_norm": 0.05063556134700775, "learning_rate": 3.385342858615719e-05, "loss": 0.0024, "step": 5048 }, { "epoch": 0.2788270377733598, "grad_norm": 0.26213139295578003, "learning_rate": 3.38508482188135e-05, "loss": 0.0058, "step": 5049 }, { "epoch": 0.2788822619836536, "grad_norm": 2.0787551403045654, "learning_rate": 3.384826740834174e-05, "loss": 0.0821, "step": 5050 }, { "epoch": 0.2789374861939474, "grad_norm": 0.12361070513725281, "learning_rate": 3.384568615482448e-05, "loss": 0.0041, "step": 5051 }, { "epoch": 0.27899271040424123, "grad_norm": 2.7073681354522705, "learning_rate": 3.3843104458344306e-05, "loss": 0.1816, "step": 5052 }, { "epoch": 0.27904793461453503, "grad_norm": 0.2994658648967743, "learning_rate": 3.38405223189838e-05, "loss": 0.0069, "step": 5053 }, { "epoch": 0.2791031588248288, "grad_norm": 3.339238166809082, "learning_rate": 3.3837939736825596e-05, "loss": 0.4195, "step": 5054 }, { "epoch": 0.2791583830351226, "grad_norm": 3.2434017658233643, "learning_rate": 3.38353567119523e-05, "loss": 0.8806, "step": 5055 }, { "epoch": 0.2792136072454164, "grad_norm": 6.7327399253845215, "learning_rate": 3.383277324444656e-05, "loss": 1.8802, "step": 5056 }, { "epoch": 0.2792688314557102, "grad_norm": 4.878663063049316, "learning_rate": 3.383018933439101e-05, "loss": 0.4101, "step": 5057 }, { "epoch": 0.279324055666004, "grad_norm": 0.10594967007637024, "learning_rate": 3.3827604981868346e-05, "loss": 0.0044, "step": 5058 }, { "epoch": 0.2793792798762978, "grad_norm": 0.1830553561449051, "learning_rate": 3.382502018696123e-05, "loss": 0.0082, "step": 5059 }, { "epoch": 0.27943450408659154, "grad_norm": 0.04243141785264015, "learning_rate": 3.382243494975235e-05, "loss": 0.0017, "step": 5060 }, { "epoch": 0.27948972829688534, "grad_norm": 0.03333368897438049, "learning_rate": 3.381984927032444e-05, "loss": 0.0016, "step": 5061 }, { "epoch": 0.27954495250717915, "grad_norm": 1.182990312576294, "learning_rate": 3.38172631487602e-05, "loss": 0.0544, "step": 5062 }, { "epoch": 0.27960017671747295, "grad_norm": 0.22196069359779358, "learning_rate": 3.3814676585142375e-05, "loss": 0.0053, "step": 5063 }, { "epoch": 0.27965540092776675, "grad_norm": 5.4619832038879395, "learning_rate": 3.381208957955372e-05, "loss": 0.3791, "step": 5064 }, { "epoch": 0.2797106251380605, "grad_norm": 0.22314125299453735, "learning_rate": 3.3809502132076995e-05, "loss": 0.0084, "step": 5065 }, { "epoch": 0.2797658493483543, "grad_norm": 6.8934006690979, "learning_rate": 3.380691424279499e-05, "loss": 1.9672, "step": 5066 }, { "epoch": 0.2798210735586481, "grad_norm": 1.0830256938934326, "learning_rate": 3.380432591179048e-05, "loss": 0.0559, "step": 5067 }, { "epoch": 0.2798762977689419, "grad_norm": 0.5014088749885559, "learning_rate": 3.3801737139146297e-05, "loss": 0.0236, "step": 5068 }, { "epoch": 0.2799315219792357, "grad_norm": 6.740269184112549, "learning_rate": 3.379914792494524e-05, "loss": 1.2629, "step": 5069 }, { "epoch": 0.2799867461895295, "grad_norm": 6.088454723358154, "learning_rate": 3.379655826927017e-05, "loss": 1.8413, "step": 5070 }, { "epoch": 0.28004197039982326, "grad_norm": 0.12386991083621979, "learning_rate": 3.3793968172203914e-05, "loss": 0.0055, "step": 5071 }, { "epoch": 0.28009719461011706, "grad_norm": 1.7792609930038452, "learning_rate": 3.379137763382935e-05, "loss": 0.2724, "step": 5072 }, { "epoch": 0.28015241882041086, "grad_norm": 0.0849599838256836, "learning_rate": 3.378878665422935e-05, "loss": 0.0026, "step": 5073 }, { "epoch": 0.28020764303070467, "grad_norm": 0.10133234411478043, "learning_rate": 3.378619523348682e-05, "loss": 0.0038, "step": 5074 }, { "epoch": 0.28026286724099847, "grad_norm": 1.951894760131836, "learning_rate": 3.3783603371684645e-05, "loss": 0.1028, "step": 5075 }, { "epoch": 0.2803180914512923, "grad_norm": 0.04148232191801071, "learning_rate": 3.3781011068905755e-05, "loss": 0.0016, "step": 5076 }, { "epoch": 0.280373315661586, "grad_norm": 0.1696491241455078, "learning_rate": 3.3778418325233104e-05, "loss": 0.0026, "step": 5077 }, { "epoch": 0.2804285398718798, "grad_norm": 1.9315605163574219, "learning_rate": 3.377582514074961e-05, "loss": 0.1722, "step": 5078 }, { "epoch": 0.2804837640821736, "grad_norm": 4.927333831787109, "learning_rate": 3.3773231515538264e-05, "loss": 0.5916, "step": 5079 }, { "epoch": 0.28053898829246743, "grad_norm": 2.7521331310272217, "learning_rate": 3.3770637449682025e-05, "loss": 0.2997, "step": 5080 }, { "epoch": 0.28059421250276123, "grad_norm": 0.6863056421279907, "learning_rate": 3.376804294326389e-05, "loss": 0.0228, "step": 5081 }, { "epoch": 0.280649436713055, "grad_norm": 1.674516201019287, "learning_rate": 3.3765447996366864e-05, "loss": 0.0831, "step": 5082 }, { "epoch": 0.2807046609233488, "grad_norm": 1.6716623306274414, "learning_rate": 3.376285260907397e-05, "loss": 0.1857, "step": 5083 }, { "epoch": 0.2807598851336426, "grad_norm": 4.6033101081848145, "learning_rate": 3.376025678146824e-05, "loss": 0.5982, "step": 5084 }, { "epoch": 0.2808151093439364, "grad_norm": 3.40841007232666, "learning_rate": 3.375766051363272e-05, "loss": 0.1952, "step": 5085 }, { "epoch": 0.2808703335542302, "grad_norm": 0.0981677696108818, "learning_rate": 3.3755063805650485e-05, "loss": 0.0049, "step": 5086 }, { "epoch": 0.280925557764524, "grad_norm": 0.11427506804466248, "learning_rate": 3.3752466657604585e-05, "loss": 0.0042, "step": 5087 }, { "epoch": 0.28098078197481774, "grad_norm": 2.9183340072631836, "learning_rate": 3.374986906957814e-05, "loss": 0.7242, "step": 5088 }, { "epoch": 0.28103600618511154, "grad_norm": 1.2764328718185425, "learning_rate": 3.374727104165422e-05, "loss": 0.077, "step": 5089 }, { "epoch": 0.28109123039540534, "grad_norm": 0.5327197909355164, "learning_rate": 3.374467257391598e-05, "loss": 0.0159, "step": 5090 }, { "epoch": 0.28114645460569915, "grad_norm": 2.246992588043213, "learning_rate": 3.374207366644653e-05, "loss": 0.1319, "step": 5091 }, { "epoch": 0.28120167881599295, "grad_norm": 1.637245535850525, "learning_rate": 3.3739474319329016e-05, "loss": 0.2824, "step": 5092 }, { "epoch": 0.2812569030262867, "grad_norm": 1.5379011631011963, "learning_rate": 3.3736874532646614e-05, "loss": 0.1432, "step": 5093 }, { "epoch": 0.2813121272365805, "grad_norm": 0.08395295590162277, "learning_rate": 3.3734274306482476e-05, "loss": 0.0033, "step": 5094 }, { "epoch": 0.2813673514468743, "grad_norm": 1.4670023918151855, "learning_rate": 3.3731673640919806e-05, "loss": 0.0702, "step": 5095 }, { "epoch": 0.2814225756571681, "grad_norm": 3.0318171977996826, "learning_rate": 3.372907253604181e-05, "loss": 0.5628, "step": 5096 }, { "epoch": 0.2814777998674619, "grad_norm": 1.4999934434890747, "learning_rate": 3.3726470991931696e-05, "loss": 0.0776, "step": 5097 }, { "epoch": 0.2815330240777557, "grad_norm": 4.414520740509033, "learning_rate": 3.3723869008672695e-05, "loss": 0.3766, "step": 5098 }, { "epoch": 0.28158824828804946, "grad_norm": 0.20570699870586395, "learning_rate": 3.372126658634806e-05, "loss": 0.0063, "step": 5099 }, { "epoch": 0.28164347249834326, "grad_norm": 3.5598483085632324, "learning_rate": 3.371866372504104e-05, "loss": 1.018, "step": 5100 }, { "epoch": 0.28169869670863706, "grad_norm": 0.12886762619018555, "learning_rate": 3.3716060424834916e-05, "loss": 0.0033, "step": 5101 }, { "epoch": 0.28175392091893087, "grad_norm": 2.700695514678955, "learning_rate": 3.3713456685812966e-05, "loss": 0.5024, "step": 5102 }, { "epoch": 0.28180914512922467, "grad_norm": 6.555270195007324, "learning_rate": 3.37108525080585e-05, "loss": 0.1822, "step": 5103 }, { "epoch": 0.2818643693395185, "grad_norm": 2.0377306938171387, "learning_rate": 3.3708247891654825e-05, "loss": 0.1825, "step": 5104 }, { "epoch": 0.2819195935498122, "grad_norm": 4.165523052215576, "learning_rate": 3.370564283668528e-05, "loss": 0.9338, "step": 5105 }, { "epoch": 0.281974817760106, "grad_norm": 0.7162611484527588, "learning_rate": 3.3703037343233194e-05, "loss": 0.0213, "step": 5106 }, { "epoch": 0.2820300419703998, "grad_norm": 2.157435894012451, "learning_rate": 3.370043141138194e-05, "loss": 0.3354, "step": 5107 }, { "epoch": 0.28208526618069363, "grad_norm": 0.2880106568336487, "learning_rate": 3.369782504121488e-05, "loss": 0.0098, "step": 5108 }, { "epoch": 0.28214049039098743, "grad_norm": 1.9460886716842651, "learning_rate": 3.36952182328154e-05, "loss": 0.7862, "step": 5109 }, { "epoch": 0.2821957146012812, "grad_norm": 0.10252007097005844, "learning_rate": 3.36926109862669e-05, "loss": 0.0041, "step": 5110 }, { "epoch": 0.282250938811575, "grad_norm": 3.147923707962036, "learning_rate": 3.369000330165279e-05, "loss": 0.1721, "step": 5111 }, { "epoch": 0.2823061630218688, "grad_norm": 0.4114009439945221, "learning_rate": 3.368739517905651e-05, "loss": 0.0134, "step": 5112 }, { "epoch": 0.2823613872321626, "grad_norm": 0.052731845527887344, "learning_rate": 3.3684786618561485e-05, "loss": 0.0017, "step": 5113 }, { "epoch": 0.2824166114424564, "grad_norm": 3.2238776683807373, "learning_rate": 3.3682177620251176e-05, "loss": 0.6293, "step": 5114 }, { "epoch": 0.2824718356527502, "grad_norm": 3.486220121383667, "learning_rate": 3.367956818420906e-05, "loss": 0.6459, "step": 5115 }, { "epoch": 0.28252705986304394, "grad_norm": 0.9760128855705261, "learning_rate": 3.367695831051861e-05, "loss": 0.0209, "step": 5116 }, { "epoch": 0.28258228407333774, "grad_norm": 2.516049385070801, "learning_rate": 3.367434799926333e-05, "loss": 0.1465, "step": 5117 }, { "epoch": 0.28263750828363154, "grad_norm": 3.3867993354797363, "learning_rate": 3.3671737250526724e-05, "loss": 0.4305, "step": 5118 }, { "epoch": 0.28269273249392535, "grad_norm": 2.3419718742370605, "learning_rate": 3.366912606439232e-05, "loss": 0.2654, "step": 5119 }, { "epoch": 0.28274795670421915, "grad_norm": 2.4579761028289795, "learning_rate": 3.366651444094366e-05, "loss": 0.2724, "step": 5120 }, { "epoch": 0.2828031809145129, "grad_norm": 2.1763126850128174, "learning_rate": 3.36639023802643e-05, "loss": 0.6193, "step": 5121 }, { "epoch": 0.2828584051248067, "grad_norm": 0.17545193433761597, "learning_rate": 3.3661289882437805e-05, "loss": 0.0066, "step": 5122 }, { "epoch": 0.2829136293351005, "grad_norm": 1.181598424911499, "learning_rate": 3.365867694754775e-05, "loss": 0.0327, "step": 5123 }, { "epoch": 0.2829688535453943, "grad_norm": 0.45767128467559814, "learning_rate": 3.365606357567773e-05, "loss": 0.0174, "step": 5124 }, { "epoch": 0.2830240777556881, "grad_norm": 4.575396537780762, "learning_rate": 3.3653449766911375e-05, "loss": 1.0358, "step": 5125 }, { "epoch": 0.2830793019659819, "grad_norm": 1.6652873754501343, "learning_rate": 3.365083552133228e-05, "loss": 0.0748, "step": 5126 }, { "epoch": 0.28313452617627566, "grad_norm": 1.7957324981689453, "learning_rate": 3.36482208390241e-05, "loss": 0.0465, "step": 5127 }, { "epoch": 0.28318975038656946, "grad_norm": 0.053940486162900925, "learning_rate": 3.3645605720070476e-05, "loss": 0.0024, "step": 5128 }, { "epoch": 0.28324497459686326, "grad_norm": 0.4457190930843353, "learning_rate": 3.364299016455508e-05, "loss": 0.0117, "step": 5129 }, { "epoch": 0.28330019880715707, "grad_norm": 4.446030616760254, "learning_rate": 3.3640374172561583e-05, "loss": 0.767, "step": 5130 }, { "epoch": 0.28335542301745087, "grad_norm": 0.04618559032678604, "learning_rate": 3.363775774417369e-05, "loss": 0.0017, "step": 5131 }, { "epoch": 0.2834106472277446, "grad_norm": 0.109001524746418, "learning_rate": 3.3635140879475104e-05, "loss": 0.0037, "step": 5132 }, { "epoch": 0.2834658714380384, "grad_norm": 0.13501198589801788, "learning_rate": 3.363252357854954e-05, "loss": 0.006, "step": 5133 }, { "epoch": 0.2835210956483322, "grad_norm": 3.0195164680480957, "learning_rate": 3.362990584148074e-05, "loss": 0.2429, "step": 5134 }, { "epoch": 0.283576319858626, "grad_norm": 2.3673408031463623, "learning_rate": 3.3627287668352445e-05, "loss": 0.3336, "step": 5135 }, { "epoch": 0.2836315440689198, "grad_norm": 0.1553172767162323, "learning_rate": 3.362466905924842e-05, "loss": 0.0057, "step": 5136 }, { "epoch": 0.28368676827921363, "grad_norm": 4.532780170440674, "learning_rate": 3.3622050014252455e-05, "loss": 0.7233, "step": 5137 }, { "epoch": 0.2837419924895074, "grad_norm": 2.2401857376098633, "learning_rate": 3.361943053344832e-05, "loss": 0.1069, "step": 5138 }, { "epoch": 0.2837972166998012, "grad_norm": 1.2450816631317139, "learning_rate": 3.361681061691983e-05, "loss": 0.0387, "step": 5139 }, { "epoch": 0.283852440910095, "grad_norm": 0.014049665071070194, "learning_rate": 3.361419026475081e-05, "loss": 0.0007, "step": 5140 }, { "epoch": 0.2839076651203888, "grad_norm": 2.6355271339416504, "learning_rate": 3.361156947702508e-05, "loss": 0.6729, "step": 5141 }, { "epoch": 0.2839628893306826, "grad_norm": 0.2531284689903259, "learning_rate": 3.3608948253826495e-05, "loss": 0.006, "step": 5142 }, { "epoch": 0.2840181135409764, "grad_norm": 0.32509058713912964, "learning_rate": 3.360632659523891e-05, "loss": 0.0098, "step": 5143 }, { "epoch": 0.28407333775127014, "grad_norm": 0.20285676419734955, "learning_rate": 3.36037045013462e-05, "loss": 0.0054, "step": 5144 }, { "epoch": 0.28412856196156394, "grad_norm": 0.3337625563144684, "learning_rate": 3.360108197223226e-05, "loss": 0.0174, "step": 5145 }, { "epoch": 0.28418378617185774, "grad_norm": 1.5984983444213867, "learning_rate": 3.359845900798098e-05, "loss": 0.139, "step": 5146 }, { "epoch": 0.28423901038215155, "grad_norm": 3.433478593826294, "learning_rate": 3.359583560867629e-05, "loss": 0.8748, "step": 5147 }, { "epoch": 0.28429423459244535, "grad_norm": 1.385179042816162, "learning_rate": 3.3593211774402114e-05, "loss": 0.0298, "step": 5148 }, { "epoch": 0.2843494588027391, "grad_norm": 2.562378406524658, "learning_rate": 3.359058750524239e-05, "loss": 0.3942, "step": 5149 }, { "epoch": 0.2844046830130329, "grad_norm": 2.8605685234069824, "learning_rate": 3.3587962801281086e-05, "loss": 0.78, "step": 5150 }, { "epoch": 0.2844599072233267, "grad_norm": 0.12665556371212006, "learning_rate": 3.358533766260216e-05, "loss": 0.0046, "step": 5151 }, { "epoch": 0.2845151314336205, "grad_norm": 1.794264554977417, "learning_rate": 3.358271208928961e-05, "loss": 0.0482, "step": 5152 }, { "epoch": 0.2845703556439143, "grad_norm": 2.795974016189575, "learning_rate": 3.358008608142744e-05, "loss": 0.0517, "step": 5153 }, { "epoch": 0.2846255798542081, "grad_norm": 5.305349826812744, "learning_rate": 3.357745963909965e-05, "loss": 1.124, "step": 5154 }, { "epoch": 0.28468080406450186, "grad_norm": 2.815366506576538, "learning_rate": 3.357483276239027e-05, "loss": 0.1234, "step": 5155 }, { "epoch": 0.28473602827479566, "grad_norm": 0.19395534694194794, "learning_rate": 3.3572205451383347e-05, "loss": 0.0056, "step": 5156 }, { "epoch": 0.28479125248508946, "grad_norm": 0.5555679798126221, "learning_rate": 3.356957770616293e-05, "loss": 0.0216, "step": 5157 }, { "epoch": 0.28484647669538327, "grad_norm": 0.043713293969631195, "learning_rate": 3.3566949526813096e-05, "loss": 0.0014, "step": 5158 }, { "epoch": 0.28490170090567707, "grad_norm": 2.9585583209991455, "learning_rate": 3.356432091341792e-05, "loss": 0.2938, "step": 5159 }, { "epoch": 0.2849569251159708, "grad_norm": 0.9863617420196533, "learning_rate": 3.3561691866061505e-05, "loss": 0.0352, "step": 5160 }, { "epoch": 0.2850121493262646, "grad_norm": 0.24244581162929535, "learning_rate": 3.355906238482796e-05, "loss": 0.0061, "step": 5161 }, { "epoch": 0.2850673735365584, "grad_norm": 0.5854840278625488, "learning_rate": 3.35564324698014e-05, "loss": 0.0201, "step": 5162 }, { "epoch": 0.2851225977468522, "grad_norm": 0.9269518256187439, "learning_rate": 3.355380212106598e-05, "loss": 0.0185, "step": 5163 }, { "epoch": 0.285177821957146, "grad_norm": 2.6257288455963135, "learning_rate": 3.355117133870584e-05, "loss": 0.2359, "step": 5164 }, { "epoch": 0.28523304616743983, "grad_norm": 3.2581770420074463, "learning_rate": 3.3548540122805156e-05, "loss": 0.8087, "step": 5165 }, { "epoch": 0.2852882703777336, "grad_norm": 0.7257972359657288, "learning_rate": 3.35459084734481e-05, "loss": 0.0182, "step": 5166 }, { "epoch": 0.2853434945880274, "grad_norm": 0.1339261531829834, "learning_rate": 3.3543276390718865e-05, "loss": 0.004, "step": 5167 }, { "epoch": 0.2853987187983212, "grad_norm": 4.38944673538208, "learning_rate": 3.3540643874701664e-05, "loss": 1.1944, "step": 5168 }, { "epoch": 0.285453943008615, "grad_norm": 0.23450694978237152, "learning_rate": 3.353801092548072e-05, "loss": 0.0048, "step": 5169 }, { "epoch": 0.2855091672189088, "grad_norm": 3.3577332496643066, "learning_rate": 3.353537754314026e-05, "loss": 0.3062, "step": 5170 }, { "epoch": 0.28556439142920254, "grad_norm": 4.200155258178711, "learning_rate": 3.3532743727764545e-05, "loss": 0.3738, "step": 5171 }, { "epoch": 0.28561961563949634, "grad_norm": 1.231189250946045, "learning_rate": 3.353010947943783e-05, "loss": 0.0297, "step": 5172 }, { "epoch": 0.28567483984979014, "grad_norm": 2.8904309272766113, "learning_rate": 3.352747479824439e-05, "loss": 0.5982, "step": 5173 }, { "epoch": 0.28573006406008394, "grad_norm": 3.927804470062256, "learning_rate": 3.352483968426852e-05, "loss": 1.137, "step": 5174 }, { "epoch": 0.28578528827037775, "grad_norm": 0.01809975691139698, "learning_rate": 3.3522204137594526e-05, "loss": 0.0008, "step": 5175 }, { "epoch": 0.28584051248067155, "grad_norm": 1.6828699111938477, "learning_rate": 3.351956815830673e-05, "loss": 0.3786, "step": 5176 }, { "epoch": 0.2858957366909653, "grad_norm": 2.4799764156341553, "learning_rate": 3.351693174648946e-05, "loss": 0.2263, "step": 5177 }, { "epoch": 0.2859509609012591, "grad_norm": 0.4681633412837982, "learning_rate": 3.351429490222706e-05, "loss": 0.0189, "step": 5178 }, { "epoch": 0.2860061851115529, "grad_norm": 0.032392095774412155, "learning_rate": 3.3511657625603893e-05, "loss": 0.0013, "step": 5179 }, { "epoch": 0.2860614093218467, "grad_norm": 0.04837358370423317, "learning_rate": 3.3509019916704334e-05, "loss": 0.0017, "step": 5180 }, { "epoch": 0.2861166335321405, "grad_norm": 1.7920135259628296, "learning_rate": 3.3506381775612765e-05, "loss": 0.1426, "step": 5181 }, { "epoch": 0.2861718577424343, "grad_norm": 0.1406434327363968, "learning_rate": 3.350374320241359e-05, "loss": 0.0024, "step": 5182 }, { "epoch": 0.28622708195272806, "grad_norm": 0.13801483809947968, "learning_rate": 3.3501104197191236e-05, "loss": 0.0079, "step": 5183 }, { "epoch": 0.28628230616302186, "grad_norm": 0.03636482357978821, "learning_rate": 3.349846476003012e-05, "loss": 0.0014, "step": 5184 }, { "epoch": 0.28633753037331566, "grad_norm": 1.7636853456497192, "learning_rate": 3.3495824891014683e-05, "loss": 0.0577, "step": 5185 }, { "epoch": 0.28639275458360947, "grad_norm": 3.868307590484619, "learning_rate": 3.349318459022939e-05, "loss": 0.3431, "step": 5186 }, { "epoch": 0.28644797879390327, "grad_norm": 2.3950753211975098, "learning_rate": 3.349054385775871e-05, "loss": 0.2883, "step": 5187 }, { "epoch": 0.286503203004197, "grad_norm": 1.9532934427261353, "learning_rate": 3.348790269368712e-05, "loss": 0.2292, "step": 5188 }, { "epoch": 0.2865584272144908, "grad_norm": 1.465356469154358, "learning_rate": 3.348526109809913e-05, "loss": 0.0904, "step": 5189 }, { "epoch": 0.2866136514247846, "grad_norm": 0.456131249666214, "learning_rate": 3.348261907107925e-05, "loss": 0.0076, "step": 5190 }, { "epoch": 0.2866688756350784, "grad_norm": 0.13626693189144135, "learning_rate": 3.3479976612711995e-05, "loss": 0.0061, "step": 5191 }, { "epoch": 0.2867240998453722, "grad_norm": 0.26272785663604736, "learning_rate": 3.3477333723081916e-05, "loss": 0.0099, "step": 5192 }, { "epoch": 0.28677932405566603, "grad_norm": 2.1576321125030518, "learning_rate": 3.3474690402273564e-05, "loss": 0.174, "step": 5193 }, { "epoch": 0.2868345482659598, "grad_norm": 1.4762156009674072, "learning_rate": 3.347204665037151e-05, "loss": 0.2006, "step": 5194 }, { "epoch": 0.2868897724762536, "grad_norm": 3.0371103286743164, "learning_rate": 3.346940246746032e-05, "loss": 0.6935, "step": 5195 }, { "epoch": 0.2869449966865474, "grad_norm": 0.17694054543972015, "learning_rate": 3.3466757853624604e-05, "loss": 0.0047, "step": 5196 }, { "epoch": 0.2870002208968412, "grad_norm": 0.0567888543009758, "learning_rate": 3.346411280894896e-05, "loss": 0.0022, "step": 5197 }, { "epoch": 0.287055445107135, "grad_norm": 0.7328624725341797, "learning_rate": 3.3461467333518025e-05, "loss": 0.0193, "step": 5198 }, { "epoch": 0.28711066931742873, "grad_norm": 1.0088653564453125, "learning_rate": 3.3458821427416426e-05, "loss": 0.0243, "step": 5199 }, { "epoch": 0.28716589352772254, "grad_norm": 2.782482385635376, "learning_rate": 3.345617509072881e-05, "loss": 0.1611, "step": 5200 }, { "epoch": 0.28722111773801634, "grad_norm": 0.11242670565843582, "learning_rate": 3.345352832353985e-05, "loss": 0.0033, "step": 5201 }, { "epoch": 0.28727634194831014, "grad_norm": 3.622046947479248, "learning_rate": 3.345088112593422e-05, "loss": 0.1619, "step": 5202 }, { "epoch": 0.28733156615860395, "grad_norm": 2.76143479347229, "learning_rate": 3.3448233497996595e-05, "loss": 0.2517, "step": 5203 }, { "epoch": 0.28738679036889775, "grad_norm": 0.36787089705467224, "learning_rate": 3.344558543981171e-05, "loss": 0.0113, "step": 5204 }, { "epoch": 0.2874420145791915, "grad_norm": 1.7364287376403809, "learning_rate": 3.3442936951464266e-05, "loss": 0.0525, "step": 5205 }, { "epoch": 0.2874972387894853, "grad_norm": 2.2575149536132812, "learning_rate": 3.3440288033039e-05, "loss": 0.1046, "step": 5206 }, { "epoch": 0.2875524629997791, "grad_norm": 0.2673138976097107, "learning_rate": 3.343763868462065e-05, "loss": 0.0087, "step": 5207 }, { "epoch": 0.2876076872100729, "grad_norm": 2.188141107559204, "learning_rate": 3.343498890629399e-05, "loss": 0.3334, "step": 5208 }, { "epoch": 0.2876629114203667, "grad_norm": 0.33392640948295593, "learning_rate": 3.3432338698143785e-05, "loss": 0.0122, "step": 5209 }, { "epoch": 0.28771813563066045, "grad_norm": 0.6454695463180542, "learning_rate": 3.3429688060254824e-05, "loss": 0.0203, "step": 5210 }, { "epoch": 0.28777335984095426, "grad_norm": 0.20053261518478394, "learning_rate": 3.342703699271191e-05, "loss": 0.008, "step": 5211 }, { "epoch": 0.28782858405124806, "grad_norm": 0.17007946968078613, "learning_rate": 3.342438549559985e-05, "loss": 0.0045, "step": 5212 }, { "epoch": 0.28788380826154186, "grad_norm": 0.09392346441745758, "learning_rate": 3.342173356900349e-05, "loss": 0.0025, "step": 5213 }, { "epoch": 0.28793903247183567, "grad_norm": 3.290065288543701, "learning_rate": 3.341908121300766e-05, "loss": 0.1359, "step": 5214 }, { "epoch": 0.28799425668212947, "grad_norm": 0.40789541602134705, "learning_rate": 3.341642842769722e-05, "loss": 0.0065, "step": 5215 }, { "epoch": 0.2880494808924232, "grad_norm": 5.732456207275391, "learning_rate": 3.341377521315704e-05, "loss": 1.3468, "step": 5216 }, { "epoch": 0.288104705102717, "grad_norm": 0.4388214945793152, "learning_rate": 3.3411121569472e-05, "loss": 0.0063, "step": 5217 }, { "epoch": 0.2881599293130108, "grad_norm": 0.9335362315177917, "learning_rate": 3.340846749672701e-05, "loss": 0.0132, "step": 5218 }, { "epoch": 0.2882151535233046, "grad_norm": 0.07669305056333542, "learning_rate": 3.3405812995006965e-05, "loss": 0.0021, "step": 5219 }, { "epoch": 0.2882703777335984, "grad_norm": 3.044297933578491, "learning_rate": 3.34031580643968e-05, "loss": 0.7293, "step": 5220 }, { "epoch": 0.28832560194389223, "grad_norm": 0.21162979304790497, "learning_rate": 3.3400502704981455e-05, "loss": 0.0042, "step": 5221 }, { "epoch": 0.288380826154186, "grad_norm": 5.721880912780762, "learning_rate": 3.339784691684587e-05, "loss": 0.8056, "step": 5222 }, { "epoch": 0.2884360503644798, "grad_norm": 1.057442545890808, "learning_rate": 3.339519070007502e-05, "loss": 0.0443, "step": 5223 }, { "epoch": 0.2884912745747736, "grad_norm": 0.5526071786880493, "learning_rate": 3.33925340547539e-05, "loss": 0.0151, "step": 5224 }, { "epoch": 0.2885464987850674, "grad_norm": 0.03416881710290909, "learning_rate": 3.3389876980967475e-05, "loss": 0.0015, "step": 5225 }, { "epoch": 0.2886017229953612, "grad_norm": 11.596698760986328, "learning_rate": 3.338721947880077e-05, "loss": 0.3744, "step": 5226 }, { "epoch": 0.28865694720565493, "grad_norm": 0.07304288446903229, "learning_rate": 3.3384561548338805e-05, "loss": 0.0025, "step": 5227 }, { "epoch": 0.28871217141594874, "grad_norm": 5.566732406616211, "learning_rate": 3.338190318966661e-05, "loss": 0.9804, "step": 5228 }, { "epoch": 0.28876739562624254, "grad_norm": 0.35386785864830017, "learning_rate": 3.337924440286924e-05, "loss": 0.0071, "step": 5229 }, { "epoch": 0.28882261983653634, "grad_norm": 0.04545469582080841, "learning_rate": 3.337658518803174e-05, "loss": 0.0021, "step": 5230 }, { "epoch": 0.28887784404683015, "grad_norm": 0.451689213514328, "learning_rate": 3.3373925545239205e-05, "loss": 0.0146, "step": 5231 }, { "epoch": 0.28893306825712395, "grad_norm": 3.9479217529296875, "learning_rate": 3.337126547457672e-05, "loss": 0.4394, "step": 5232 }, { "epoch": 0.2889882924674177, "grad_norm": 0.02265971526503563, "learning_rate": 3.336860497612938e-05, "loss": 0.0007, "step": 5233 }, { "epoch": 0.2890435166777115, "grad_norm": 0.040017738938331604, "learning_rate": 3.3365944049982315e-05, "loss": 0.001, "step": 5234 }, { "epoch": 0.2890987408880053, "grad_norm": 0.03842468559741974, "learning_rate": 3.336328269622065e-05, "loss": 0.0014, "step": 5235 }, { "epoch": 0.2891539650982991, "grad_norm": 1.0062603950500488, "learning_rate": 3.3360620914929524e-05, "loss": 0.0288, "step": 5236 }, { "epoch": 0.2892091893085929, "grad_norm": 4.564253330230713, "learning_rate": 3.3357958706194096e-05, "loss": 0.1591, "step": 5237 }, { "epoch": 0.28926441351888665, "grad_norm": 0.14365215599536896, "learning_rate": 3.335529607009955e-05, "loss": 0.0054, "step": 5238 }, { "epoch": 0.28931963772918046, "grad_norm": 0.04054674506187439, "learning_rate": 3.335263300673105e-05, "loss": 0.0017, "step": 5239 }, { "epoch": 0.28937486193947426, "grad_norm": 0.018287230283021927, "learning_rate": 3.3349969516173814e-05, "loss": 0.0006, "step": 5240 }, { "epoch": 0.28943008614976806, "grad_norm": 2.720268726348877, "learning_rate": 3.3347305598513046e-05, "loss": 0.5814, "step": 5241 }, { "epoch": 0.28948531036006186, "grad_norm": 7.162306308746338, "learning_rate": 3.334464125383398e-05, "loss": 0.8628, "step": 5242 }, { "epoch": 0.28954053457035567, "grad_norm": 0.016932455822825432, "learning_rate": 3.334197648222184e-05, "loss": 0.0007, "step": 5243 }, { "epoch": 0.2895957587806494, "grad_norm": 1.4086816310882568, "learning_rate": 3.333931128376189e-05, "loss": 0.0519, "step": 5244 }, { "epoch": 0.2896509829909432, "grad_norm": 3.552752733230591, "learning_rate": 3.3336645658539404e-05, "loss": 0.045, "step": 5245 }, { "epoch": 0.289706207201237, "grad_norm": 0.023881087079644203, "learning_rate": 3.333397960663965e-05, "loss": 0.0011, "step": 5246 }, { "epoch": 0.2897614314115308, "grad_norm": 2.636802911758423, "learning_rate": 3.3331313128147926e-05, "loss": 0.3206, "step": 5247 }, { "epoch": 0.2898166556218246, "grad_norm": 3.119114637374878, "learning_rate": 3.332864622314955e-05, "loss": 0.0768, "step": 5248 }, { "epoch": 0.2898718798321184, "grad_norm": 0.9331822991371155, "learning_rate": 3.332597889172983e-05, "loss": 0.0228, "step": 5249 }, { "epoch": 0.2899271040424122, "grad_norm": 0.19191564619541168, "learning_rate": 3.3323311133974114e-05, "loss": 0.0063, "step": 5250 }, { "epoch": 0.289982328252706, "grad_norm": 2.6259593963623047, "learning_rate": 3.332064294996774e-05, "loss": 0.4207, "step": 5251 }, { "epoch": 0.2900375524629998, "grad_norm": 1.6032369136810303, "learning_rate": 3.331797433979608e-05, "loss": 0.1394, "step": 5252 }, { "epoch": 0.2900927766732936, "grad_norm": 2.737902879714966, "learning_rate": 3.3315305303544505e-05, "loss": 0.1284, "step": 5253 }, { "epoch": 0.2901480008835874, "grad_norm": 1.9185833930969238, "learning_rate": 3.3312635841298405e-05, "loss": 0.0343, "step": 5254 }, { "epoch": 0.29020322509388113, "grad_norm": 0.013991226442158222, "learning_rate": 3.330996595314318e-05, "loss": 0.0005, "step": 5255 }, { "epoch": 0.29025844930417494, "grad_norm": 1.259060025215149, "learning_rate": 3.330729563916426e-05, "loss": 0.4412, "step": 5256 }, { "epoch": 0.29031367351446874, "grad_norm": 0.6009324193000793, "learning_rate": 3.330462489944706e-05, "loss": 0.016, "step": 5257 }, { "epoch": 0.29036889772476254, "grad_norm": 2.43941330909729, "learning_rate": 3.3301953734077043e-05, "loss": 0.3023, "step": 5258 }, { "epoch": 0.29042412193505635, "grad_norm": 0.1403229832649231, "learning_rate": 3.3299282143139656e-05, "loss": 0.0046, "step": 5259 }, { "epoch": 0.29047934614535015, "grad_norm": 1.3656699657440186, "learning_rate": 3.329661012672036e-05, "loss": 0.0441, "step": 5260 }, { "epoch": 0.2905345703556439, "grad_norm": 3.658167600631714, "learning_rate": 3.3293937684904666e-05, "loss": 0.0776, "step": 5261 }, { "epoch": 0.2905897945659377, "grad_norm": 0.18920716643333435, "learning_rate": 3.329126481777805e-05, "loss": 0.0056, "step": 5262 }, { "epoch": 0.2906450187762315, "grad_norm": 0.0881686732172966, "learning_rate": 3.3288591525426044e-05, "loss": 0.0034, "step": 5263 }, { "epoch": 0.2907002429865253, "grad_norm": 0.065333291888237, "learning_rate": 3.3285917807934156e-05, "loss": 0.0021, "step": 5264 }, { "epoch": 0.2907554671968191, "grad_norm": 1.7823660373687744, "learning_rate": 3.3283243665387936e-05, "loss": 0.0284, "step": 5265 }, { "epoch": 0.29081069140711285, "grad_norm": 1.6806325912475586, "learning_rate": 3.328056909787294e-05, "loss": 0.0473, "step": 5266 }, { "epoch": 0.29086591561740666, "grad_norm": 0.4606272280216217, "learning_rate": 3.327789410547472e-05, "loss": 0.1029, "step": 5267 }, { "epoch": 0.29092113982770046, "grad_norm": 0.4700228273868561, "learning_rate": 3.327521868827887e-05, "loss": 0.0045, "step": 5268 }, { "epoch": 0.29097636403799426, "grad_norm": 2.5362188816070557, "learning_rate": 3.327254284637099e-05, "loss": 0.1828, "step": 5269 }, { "epoch": 0.29103158824828806, "grad_norm": 0.1321721076965332, "learning_rate": 3.3269866579836673e-05, "loss": 0.0035, "step": 5270 }, { "epoch": 0.29108681245858187, "grad_norm": 1.7895617485046387, "learning_rate": 3.326718988876155e-05, "loss": 0.0949, "step": 5271 }, { "epoch": 0.2911420366688756, "grad_norm": 1.3843146562576294, "learning_rate": 3.3264512773231244e-05, "loss": 0.1997, "step": 5272 }, { "epoch": 0.2911972608791694, "grad_norm": 3.6348965167999268, "learning_rate": 3.326183523333142e-05, "loss": 0.3854, "step": 5273 }, { "epoch": 0.2912524850894632, "grad_norm": 2.454413890838623, "learning_rate": 3.325915726914773e-05, "loss": 0.1527, "step": 5274 }, { "epoch": 0.291307709299757, "grad_norm": 1.9647457599639893, "learning_rate": 3.325647888076585e-05, "loss": 0.2562, "step": 5275 }, { "epoch": 0.2913629335100508, "grad_norm": 3.3711345195770264, "learning_rate": 3.325380006827147e-05, "loss": 0.6202, "step": 5276 }, { "epoch": 0.2914181577203446, "grad_norm": 0.052076440304517746, "learning_rate": 3.32511208317503e-05, "loss": 0.0017, "step": 5277 }, { "epoch": 0.2914733819306384, "grad_norm": 2.392167568206787, "learning_rate": 3.324844117128804e-05, "loss": 0.4228, "step": 5278 }, { "epoch": 0.2915286061409322, "grad_norm": 3.189621686935425, "learning_rate": 3.324576108697044e-05, "loss": 0.4081, "step": 5279 }, { "epoch": 0.291583830351226, "grad_norm": 3.3606085777282715, "learning_rate": 3.324308057888323e-05, "loss": 0.2642, "step": 5280 }, { "epoch": 0.2916390545615198, "grad_norm": 3.089930772781372, "learning_rate": 3.324039964711218e-05, "loss": 0.2264, "step": 5281 }, { "epoch": 0.2916942787718136, "grad_norm": 0.10210427641868591, "learning_rate": 3.323771829174304e-05, "loss": 0.0023, "step": 5282 }, { "epoch": 0.29174950298210733, "grad_norm": 2.580920457839966, "learning_rate": 3.323503651286161e-05, "loss": 0.7047, "step": 5283 }, { "epoch": 0.29180472719240114, "grad_norm": 3.2891788482666016, "learning_rate": 3.323235431055368e-05, "loss": 0.8206, "step": 5284 }, { "epoch": 0.29185995140269494, "grad_norm": 1.6595791578292847, "learning_rate": 3.3229671684905066e-05, "loss": 0.077, "step": 5285 }, { "epoch": 0.29191517561298874, "grad_norm": 0.34932151436805725, "learning_rate": 3.322698863600159e-05, "loss": 0.0064, "step": 5286 }, { "epoch": 0.29197039982328254, "grad_norm": 1.4320244789123535, "learning_rate": 3.32243051639291e-05, "loss": 0.0524, "step": 5287 }, { "epoch": 0.29202562403357635, "grad_norm": 0.18148669600486755, "learning_rate": 3.322162126877343e-05, "loss": 0.005, "step": 5288 }, { "epoch": 0.2920808482438701, "grad_norm": 0.026841318234801292, "learning_rate": 3.321893695062047e-05, "loss": 0.0009, "step": 5289 }, { "epoch": 0.2921360724541639, "grad_norm": 2.9427709579467773, "learning_rate": 3.321625220955607e-05, "loss": 0.6257, "step": 5290 }, { "epoch": 0.2921912966644577, "grad_norm": 2.2332139015197754, "learning_rate": 3.321356704566614e-05, "loss": 0.3165, "step": 5291 }, { "epoch": 0.2922465208747515, "grad_norm": 2.16499400138855, "learning_rate": 3.321088145903658e-05, "loss": 0.7387, "step": 5292 }, { "epoch": 0.2923017450850453, "grad_norm": 3.1055409908294678, "learning_rate": 3.320819544975332e-05, "loss": 0.602, "step": 5293 }, { "epoch": 0.29235696929533905, "grad_norm": 3.3265326023101807, "learning_rate": 3.320550901790228e-05, "loss": 1.0434, "step": 5294 }, { "epoch": 0.29241219350563286, "grad_norm": 0.15035682916641235, "learning_rate": 3.3202822163569415e-05, "loss": 0.0043, "step": 5295 }, { "epoch": 0.29246741771592666, "grad_norm": 4.859085559844971, "learning_rate": 3.320013488684068e-05, "loss": 0.6346, "step": 5296 }, { "epoch": 0.29252264192622046, "grad_norm": 0.193637877702713, "learning_rate": 3.3197447187802055e-05, "loss": 0.0045, "step": 5297 }, { "epoch": 0.29257786613651426, "grad_norm": 4.179060935974121, "learning_rate": 3.319475906653952e-05, "loss": 0.9004, "step": 5298 }, { "epoch": 0.29263309034680807, "grad_norm": 3.139859676361084, "learning_rate": 3.3192070523139076e-05, "loss": 0.405, "step": 5299 }, { "epoch": 0.2926883145571018, "grad_norm": 3.671733856201172, "learning_rate": 3.318938155768674e-05, "loss": 0.7411, "step": 5300 }, { "epoch": 0.2927435387673956, "grad_norm": 0.28775274753570557, "learning_rate": 3.318669217026855e-05, "loss": 0.0083, "step": 5301 }, { "epoch": 0.2927987629776894, "grad_norm": 0.23471400141716003, "learning_rate": 3.318400236097052e-05, "loss": 0.0086, "step": 5302 }, { "epoch": 0.2928539871879832, "grad_norm": 0.500240683555603, "learning_rate": 3.318131212987873e-05, "loss": 0.0123, "step": 5303 }, { "epoch": 0.292909211398277, "grad_norm": 2.1041464805603027, "learning_rate": 3.3178621477079244e-05, "loss": 0.0288, "step": 5304 }, { "epoch": 0.2929644356085708, "grad_norm": 2.139101505279541, "learning_rate": 3.317593040265813e-05, "loss": 0.418, "step": 5305 }, { "epoch": 0.2930196598188646, "grad_norm": 3.251854181289673, "learning_rate": 3.31732389067015e-05, "loss": 0.2555, "step": 5306 }, { "epoch": 0.2930748840291584, "grad_norm": 2.828378915786743, "learning_rate": 3.3170546989295454e-05, "loss": 0.343, "step": 5307 }, { "epoch": 0.2931301082394522, "grad_norm": 2.099898099899292, "learning_rate": 3.316785465052611e-05, "loss": 0.0915, "step": 5308 }, { "epoch": 0.293185332449746, "grad_norm": 2.9518027305603027, "learning_rate": 3.3165161890479604e-05, "loss": 0.0251, "step": 5309 }, { "epoch": 0.2932405566600398, "grad_norm": 0.21554730832576752, "learning_rate": 3.31624687092421e-05, "loss": 0.0054, "step": 5310 }, { "epoch": 0.29329578087033353, "grad_norm": 0.11688262969255447, "learning_rate": 3.315977510689975e-05, "loss": 0.0031, "step": 5311 }, { "epoch": 0.29335100508062734, "grad_norm": 0.061332959681749344, "learning_rate": 3.315708108353873e-05, "loss": 0.0022, "step": 5312 }, { "epoch": 0.29340622929092114, "grad_norm": 0.10470258444547653, "learning_rate": 3.315438663924522e-05, "loss": 0.0033, "step": 5313 }, { "epoch": 0.29346145350121494, "grad_norm": 3.293113946914673, "learning_rate": 3.315169177410544e-05, "loss": 0.8508, "step": 5314 }, { "epoch": 0.29351667771150874, "grad_norm": 1.417910099029541, "learning_rate": 3.31489964882056e-05, "loss": 0.137, "step": 5315 }, { "epoch": 0.2935719019218025, "grad_norm": 6.047929286956787, "learning_rate": 3.3146300781631925e-05, "loss": 0.8824, "step": 5316 }, { "epoch": 0.2936271261320963, "grad_norm": 0.18755267560482025, "learning_rate": 3.314360465447066e-05, "loss": 0.0044, "step": 5317 }, { "epoch": 0.2936823503423901, "grad_norm": 0.10219919681549072, "learning_rate": 3.314090810680807e-05, "loss": 0.0033, "step": 5318 }, { "epoch": 0.2937375745526839, "grad_norm": 2.014592170715332, "learning_rate": 3.313821113873042e-05, "loss": 0.2046, "step": 5319 }, { "epoch": 0.2937927987629777, "grad_norm": 4.160792350769043, "learning_rate": 3.313551375032399e-05, "loss": 0.5589, "step": 5320 }, { "epoch": 0.2938480229732715, "grad_norm": 0.5185306072235107, "learning_rate": 3.313281594167507e-05, "loss": 0.0118, "step": 5321 }, { "epoch": 0.29390324718356525, "grad_norm": 0.1462116837501526, "learning_rate": 3.313011771286999e-05, "loss": 0.004, "step": 5322 }, { "epoch": 0.29395847139385906, "grad_norm": 0.2954404056072235, "learning_rate": 3.312741906399507e-05, "loss": 0.0087, "step": 5323 }, { "epoch": 0.29401369560415286, "grad_norm": 0.22748270630836487, "learning_rate": 3.3124719995136635e-05, "loss": 0.0056, "step": 5324 }, { "epoch": 0.29406891981444666, "grad_norm": 0.9588721394538879, "learning_rate": 3.312202050638105e-05, "loss": 0.0208, "step": 5325 }, { "epoch": 0.29412414402474046, "grad_norm": 0.2072618007659912, "learning_rate": 3.3119320597814666e-05, "loss": 0.0054, "step": 5326 }, { "epoch": 0.29417936823503427, "grad_norm": 0.10294037312269211, "learning_rate": 3.3116620269523867e-05, "loss": 0.003, "step": 5327 }, { "epoch": 0.294234592445328, "grad_norm": 0.23368032276630402, "learning_rate": 3.311391952159505e-05, "loss": 0.0071, "step": 5328 }, { "epoch": 0.2942898166556218, "grad_norm": 0.815883457660675, "learning_rate": 3.3111218354114604e-05, "loss": 0.0107, "step": 5329 }, { "epoch": 0.2943450408659156, "grad_norm": 0.2553118169307709, "learning_rate": 3.310851676716897e-05, "loss": 0.012, "step": 5330 }, { "epoch": 0.2944002650762094, "grad_norm": 2.7826454639434814, "learning_rate": 3.310581476084455e-05, "loss": 1.0398, "step": 5331 }, { "epoch": 0.2944554892865032, "grad_norm": 0.06799263507127762, "learning_rate": 3.3103112335227815e-05, "loss": 0.0015, "step": 5332 }, { "epoch": 0.29451071349679697, "grad_norm": 1.056381344795227, "learning_rate": 3.310040949040521e-05, "loss": 0.0357, "step": 5333 }, { "epoch": 0.2945659377070908, "grad_norm": 0.24487939476966858, "learning_rate": 3.309770622646321e-05, "loss": 0.0066, "step": 5334 }, { "epoch": 0.2946211619173846, "grad_norm": 2.070611000061035, "learning_rate": 3.309500254348831e-05, "loss": 0.4597, "step": 5335 }, { "epoch": 0.2946763861276784, "grad_norm": 1.3981298208236694, "learning_rate": 3.3092298441566986e-05, "loss": 0.0509, "step": 5336 }, { "epoch": 0.2947316103379722, "grad_norm": 0.2928381562232971, "learning_rate": 3.308959392078577e-05, "loss": 0.0085, "step": 5337 }, { "epoch": 0.294786834548266, "grad_norm": 0.0660812109708786, "learning_rate": 3.308688898123117e-05, "loss": 0.0014, "step": 5338 }, { "epoch": 0.29484205875855973, "grad_norm": 2.0107104778289795, "learning_rate": 3.308418362298975e-05, "loss": 0.181, "step": 5339 }, { "epoch": 0.29489728296885354, "grad_norm": 0.38841548562049866, "learning_rate": 3.308147784614804e-05, "loss": 0.0112, "step": 5340 }, { "epoch": 0.29495250717914734, "grad_norm": 2.3435018062591553, "learning_rate": 3.307877165079261e-05, "loss": 0.2002, "step": 5341 }, { "epoch": 0.29500773138944114, "grad_norm": 0.02008332870900631, "learning_rate": 3.3076065037010045e-05, "loss": 0.0009, "step": 5342 }, { "epoch": 0.29506295559973494, "grad_norm": 0.01986096240580082, "learning_rate": 3.307335800488693e-05, "loss": 0.0007, "step": 5343 }, { "epoch": 0.2951181798100287, "grad_norm": 1.2694395780563354, "learning_rate": 3.307065055450988e-05, "loss": 0.0349, "step": 5344 }, { "epoch": 0.2951734040203225, "grad_norm": 0.4131297171115875, "learning_rate": 3.30679426859655e-05, "loss": 0.0063, "step": 5345 }, { "epoch": 0.2952286282306163, "grad_norm": 3.1351253986358643, "learning_rate": 3.3065234399340435e-05, "loss": 0.1957, "step": 5346 }, { "epoch": 0.2952838524409101, "grad_norm": 0.06888949871063232, "learning_rate": 3.3062525694721325e-05, "loss": 0.0013, "step": 5347 }, { "epoch": 0.2953390766512039, "grad_norm": 0.2380041629076004, "learning_rate": 3.3059816572194834e-05, "loss": 0.0064, "step": 5348 }, { "epoch": 0.2953943008614977, "grad_norm": 0.1847895085811615, "learning_rate": 3.305710703184763e-05, "loss": 0.0044, "step": 5349 }, { "epoch": 0.29544952507179145, "grad_norm": 0.4476305842399597, "learning_rate": 3.30543970737664e-05, "loss": 0.0098, "step": 5350 }, { "epoch": 0.29550474928208526, "grad_norm": 0.028323916718363762, "learning_rate": 3.305168669803784e-05, "loss": 0.0009, "step": 5351 }, { "epoch": 0.29555997349237906, "grad_norm": 2.0626144409179688, "learning_rate": 3.304897590474867e-05, "loss": 0.0691, "step": 5352 }, { "epoch": 0.29561519770267286, "grad_norm": 2.9611902236938477, "learning_rate": 3.304626469398561e-05, "loss": 0.1038, "step": 5353 }, { "epoch": 0.29567042191296666, "grad_norm": 4.802340984344482, "learning_rate": 3.30435530658354e-05, "loss": 0.5898, "step": 5354 }, { "epoch": 0.2957256461232604, "grad_norm": 0.025344202294945717, "learning_rate": 3.30408410203848e-05, "loss": 0.0008, "step": 5355 }, { "epoch": 0.2957808703335542, "grad_norm": 0.0738878846168518, "learning_rate": 3.3038128557720565e-05, "loss": 0.002, "step": 5356 }, { "epoch": 0.295836094543848, "grad_norm": 0.8597284555435181, "learning_rate": 3.303541567792948e-05, "loss": 0.0281, "step": 5357 }, { "epoch": 0.2958913187541418, "grad_norm": 1.363924264907837, "learning_rate": 3.303270238109834e-05, "loss": 0.0388, "step": 5358 }, { "epoch": 0.2959465429644356, "grad_norm": 0.5709383487701416, "learning_rate": 3.302998866731395e-05, "loss": 0.0161, "step": 5359 }, { "epoch": 0.2960017671747294, "grad_norm": 1.832747220993042, "learning_rate": 3.302727453666312e-05, "loss": 0.2121, "step": 5360 }, { "epoch": 0.29605699138502317, "grad_norm": 5.874688148498535, "learning_rate": 3.30245599892327e-05, "loss": 1.0182, "step": 5361 }, { "epoch": 0.296112215595317, "grad_norm": 0.10599660873413086, "learning_rate": 3.302184502510952e-05, "loss": 0.0038, "step": 5362 }, { "epoch": 0.2961674398056108, "grad_norm": 0.025844430550932884, "learning_rate": 3.301912964438045e-05, "loss": 0.0006, "step": 5363 }, { "epoch": 0.2962226640159046, "grad_norm": 0.05141126364469528, "learning_rate": 3.3016413847132355e-05, "loss": 0.0018, "step": 5364 }, { "epoch": 0.2962778882261984, "grad_norm": 0.8832306265830994, "learning_rate": 3.301369763345212e-05, "loss": 0.0198, "step": 5365 }, { "epoch": 0.2963331124364922, "grad_norm": 0.025506211444735527, "learning_rate": 3.301098100342666e-05, "loss": 0.0009, "step": 5366 }, { "epoch": 0.29638833664678593, "grad_norm": 0.3231744170188904, "learning_rate": 3.300826395714287e-05, "loss": 0.0051, "step": 5367 }, { "epoch": 0.29644356085707974, "grad_norm": 0.12076704204082489, "learning_rate": 3.3005546494687685e-05, "loss": 0.003, "step": 5368 }, { "epoch": 0.29649878506737354, "grad_norm": 2.2028913497924805, "learning_rate": 3.300282861614805e-05, "loss": 0.1653, "step": 5369 }, { "epoch": 0.29655400927766734, "grad_norm": 0.1250467598438263, "learning_rate": 3.3000110321610905e-05, "loss": 0.0037, "step": 5370 }, { "epoch": 0.29660923348796114, "grad_norm": 0.05309359356760979, "learning_rate": 3.299739161116322e-05, "loss": 0.0014, "step": 5371 }, { "epoch": 0.2966644576982549, "grad_norm": 1.8497250080108643, "learning_rate": 3.2994672484891974e-05, "loss": 0.361, "step": 5372 }, { "epoch": 0.2967196819085487, "grad_norm": 4.129190921783447, "learning_rate": 3.2991952942884165e-05, "loss": 0.3407, "step": 5373 }, { "epoch": 0.2967749061188425, "grad_norm": 0.06420926749706268, "learning_rate": 3.298923298522679e-05, "loss": 0.0017, "step": 5374 }, { "epoch": 0.2968301303291363, "grad_norm": 4.624621391296387, "learning_rate": 3.298651261200688e-05, "loss": 0.3963, "step": 5375 }, { "epoch": 0.2968853545394301, "grad_norm": 2.312256336212158, "learning_rate": 3.298379182331145e-05, "loss": 0.1506, "step": 5376 }, { "epoch": 0.2969405787497239, "grad_norm": 3.8596510887145996, "learning_rate": 3.298107061922756e-05, "loss": 0.0866, "step": 5377 }, { "epoch": 0.29699580296001765, "grad_norm": 4.742722988128662, "learning_rate": 3.297834899984227e-05, "loss": 0.9286, "step": 5378 }, { "epoch": 0.29705102717031145, "grad_norm": 2.674467086791992, "learning_rate": 3.2975626965242644e-05, "loss": 0.5197, "step": 5379 }, { "epoch": 0.29710625138060526, "grad_norm": 0.0975252315402031, "learning_rate": 3.297290451551577e-05, "loss": 0.0035, "step": 5380 }, { "epoch": 0.29716147559089906, "grad_norm": 1.5845385789871216, "learning_rate": 3.2970181650748755e-05, "loss": 0.3691, "step": 5381 }, { "epoch": 0.29721669980119286, "grad_norm": 1.542057991027832, "learning_rate": 3.2967458371028706e-05, "loss": 0.0278, "step": 5382 }, { "epoch": 0.2972719240114866, "grad_norm": 0.25398457050323486, "learning_rate": 3.2964734676442734e-05, "loss": 0.0065, "step": 5383 }, { "epoch": 0.2973271482217804, "grad_norm": 0.11127876490354538, "learning_rate": 3.2962010567078e-05, "loss": 0.0036, "step": 5384 }, { "epoch": 0.2973823724320742, "grad_norm": 5.09194278717041, "learning_rate": 3.295928604302165e-05, "loss": 0.9514, "step": 5385 }, { "epoch": 0.297437596642368, "grad_norm": 5.989198684692383, "learning_rate": 3.295656110436084e-05, "loss": 0.9194, "step": 5386 }, { "epoch": 0.2974928208526618, "grad_norm": 1.3292676210403442, "learning_rate": 3.295383575118276e-05, "loss": 0.0438, "step": 5387 }, { "epoch": 0.2975480450629556, "grad_norm": 0.01277939323335886, "learning_rate": 3.295110998357459e-05, "loss": 0.0004, "step": 5388 }, { "epoch": 0.29760326927324937, "grad_norm": 0.09851052612066269, "learning_rate": 3.294838380162354e-05, "loss": 0.0033, "step": 5389 }, { "epoch": 0.2976584934835432, "grad_norm": 0.3497007489204407, "learning_rate": 3.294565720541684e-05, "loss": 0.006, "step": 5390 }, { "epoch": 0.297713717693837, "grad_norm": 0.05921662226319313, "learning_rate": 3.29429301950417e-05, "loss": 0.0019, "step": 5391 }, { "epoch": 0.2977689419041308, "grad_norm": 2.5526459217071533, "learning_rate": 3.2940202770585383e-05, "loss": 0.3961, "step": 5392 }, { "epoch": 0.2978241661144246, "grad_norm": 1.0429320335388184, "learning_rate": 3.293747493213514e-05, "loss": 0.0373, "step": 5393 }, { "epoch": 0.29787939032471833, "grad_norm": 2.9792215824127197, "learning_rate": 3.2934746679778236e-05, "loss": 0.0967, "step": 5394 }, { "epoch": 0.29793461453501213, "grad_norm": 4.535846710205078, "learning_rate": 3.293201801360197e-05, "loss": 1.5299, "step": 5395 }, { "epoch": 0.29798983874530593, "grad_norm": 0.250423401594162, "learning_rate": 3.2929288933693624e-05, "loss": 0.0061, "step": 5396 }, { "epoch": 0.29804506295559974, "grad_norm": 0.22456976771354675, "learning_rate": 3.292655944014053e-05, "loss": 0.0069, "step": 5397 }, { "epoch": 0.29810028716589354, "grad_norm": 2.1862497329711914, "learning_rate": 3.2923829533029984e-05, "loss": 0.1359, "step": 5398 }, { "epoch": 0.29815551137618734, "grad_norm": 1.1755611896514893, "learning_rate": 3.292109921244935e-05, "loss": 0.0322, "step": 5399 }, { "epoch": 0.2982107355864811, "grad_norm": 4.425432205200195, "learning_rate": 3.291836847848596e-05, "loss": 0.4902, "step": 5400 }, { "epoch": 0.2982659597967749, "grad_norm": 0.04867809638381004, "learning_rate": 3.2915637331227194e-05, "loss": 0.0016, "step": 5401 }, { "epoch": 0.2983211840070687, "grad_norm": 0.1513219177722931, "learning_rate": 3.291290577076041e-05, "loss": 0.004, "step": 5402 }, { "epoch": 0.2983764082173625, "grad_norm": 1.439149260520935, "learning_rate": 3.291017379717301e-05, "loss": 0.0899, "step": 5403 }, { "epoch": 0.2984316324276563, "grad_norm": 4.511607646942139, "learning_rate": 3.2907441410552406e-05, "loss": 0.8054, "step": 5404 }, { "epoch": 0.2984868566379501, "grad_norm": 1.2457650899887085, "learning_rate": 3.2904708610986e-05, "loss": 0.014, "step": 5405 }, { "epoch": 0.29854208084824385, "grad_norm": 0.26961082220077515, "learning_rate": 3.2901975398561226e-05, "loss": 0.0095, "step": 5406 }, { "epoch": 0.29859730505853765, "grad_norm": 2.8520400524139404, "learning_rate": 3.2899241773365534e-05, "loss": 0.1907, "step": 5407 }, { "epoch": 0.29865252926883146, "grad_norm": 2.0473077297210693, "learning_rate": 3.289650773548637e-05, "loss": 0.1756, "step": 5408 }, { "epoch": 0.29870775347912526, "grad_norm": 0.09723170846700668, "learning_rate": 3.289377328501121e-05, "loss": 0.0023, "step": 5409 }, { "epoch": 0.29876297768941906, "grad_norm": 0.19660046696662903, "learning_rate": 3.289103842202754e-05, "loss": 0.004, "step": 5410 }, { "epoch": 0.2988182018997128, "grad_norm": 3.1720259189605713, "learning_rate": 3.288830314662284e-05, "loss": 0.4872, "step": 5411 }, { "epoch": 0.2988734261100066, "grad_norm": 2.5835721492767334, "learning_rate": 3.288556745888464e-05, "loss": 0.6975, "step": 5412 }, { "epoch": 0.2989286503203004, "grad_norm": 4.807100772857666, "learning_rate": 3.288283135890046e-05, "loss": 0.6839, "step": 5413 }, { "epoch": 0.2989838745305942, "grad_norm": 3.077915668487549, "learning_rate": 3.288009484675782e-05, "loss": 0.4155, "step": 5414 }, { "epoch": 0.299039098740888, "grad_norm": 2.3333747386932373, "learning_rate": 3.2877357922544275e-05, "loss": 0.6771, "step": 5415 }, { "epoch": 0.2990943229511818, "grad_norm": 3.7588307857513428, "learning_rate": 3.28746205863474e-05, "loss": 0.2659, "step": 5416 }, { "epoch": 0.29914954716147557, "grad_norm": 0.12345024943351746, "learning_rate": 3.287188283825475e-05, "loss": 0.0044, "step": 5417 }, { "epoch": 0.2992047713717694, "grad_norm": 1.3447396755218506, "learning_rate": 3.2869144678353926e-05, "loss": 0.0361, "step": 5418 }, { "epoch": 0.2992599955820632, "grad_norm": 6.20078706741333, "learning_rate": 3.286640610673253e-05, "loss": 0.4881, "step": 5419 }, { "epoch": 0.299315219792357, "grad_norm": 0.01818326860666275, "learning_rate": 3.2863667123478164e-05, "loss": 0.0007, "step": 5420 }, { "epoch": 0.2993704440026508, "grad_norm": 0.3882632255554199, "learning_rate": 3.286092772867848e-05, "loss": 0.0089, "step": 5421 }, { "epoch": 0.29942566821294453, "grad_norm": 0.1497868299484253, "learning_rate": 3.2858187922421096e-05, "loss": 0.0065, "step": 5422 }, { "epoch": 0.29948089242323833, "grad_norm": 0.44476014375686646, "learning_rate": 3.285544770479367e-05, "loss": 0.0129, "step": 5423 }, { "epoch": 0.29953611663353213, "grad_norm": 0.7456749081611633, "learning_rate": 3.285270707588389e-05, "loss": 0.0101, "step": 5424 }, { "epoch": 0.29959134084382594, "grad_norm": 2.177558422088623, "learning_rate": 3.284996603577941e-05, "loss": 0.3312, "step": 5425 }, { "epoch": 0.29964656505411974, "grad_norm": 3.095587968826294, "learning_rate": 3.284722458456793e-05, "loss": 0.2783, "step": 5426 }, { "epoch": 0.29970178926441354, "grad_norm": 1.8433886766433716, "learning_rate": 3.284448272233717e-05, "loss": 0.0438, "step": 5427 }, { "epoch": 0.2997570134747073, "grad_norm": 2.404344320297241, "learning_rate": 3.284174044917483e-05, "loss": 0.4253, "step": 5428 }, { "epoch": 0.2998122376850011, "grad_norm": 4.528120994567871, "learning_rate": 3.283899776516867e-05, "loss": 1.5909, "step": 5429 }, { "epoch": 0.2998674618952949, "grad_norm": 0.9528043866157532, "learning_rate": 3.2836254670406415e-05, "loss": 0.0205, "step": 5430 }, { "epoch": 0.2999226861055887, "grad_norm": 2.916459083557129, "learning_rate": 3.283351116497582e-05, "loss": 0.42, "step": 5431 }, { "epoch": 0.2999779103158825, "grad_norm": 3.3626222610473633, "learning_rate": 3.283076724896468e-05, "loss": 0.3334, "step": 5432 }, { "epoch": 0.30003313452617625, "grad_norm": 0.6833440661430359, "learning_rate": 3.2828022922460755e-05, "loss": 0.0232, "step": 5433 }, { "epoch": 0.30008835873647005, "grad_norm": 2.1664907932281494, "learning_rate": 3.2825278185551876e-05, "loss": 0.1167, "step": 5434 }, { "epoch": 0.30014358294676385, "grad_norm": 2.5820302963256836, "learning_rate": 3.2822533038325825e-05, "loss": 0.0818, "step": 5435 }, { "epoch": 0.30019880715705766, "grad_norm": 1.8540021181106567, "learning_rate": 3.2819787480870435e-05, "loss": 0.0859, "step": 5436 }, { "epoch": 0.30025403136735146, "grad_norm": 1.5520607233047485, "learning_rate": 3.2817041513273546e-05, "loss": 0.123, "step": 5437 }, { "epoch": 0.30030925557764526, "grad_norm": 3.5397863388061523, "learning_rate": 3.2814295135623014e-05, "loss": 0.4198, "step": 5438 }, { "epoch": 0.300364479787939, "grad_norm": 3.9025843143463135, "learning_rate": 3.2811548348006706e-05, "loss": 0.7929, "step": 5439 }, { "epoch": 0.3004197039982328, "grad_norm": 3.765221357345581, "learning_rate": 3.280880115051249e-05, "loss": 0.6604, "step": 5440 }, { "epoch": 0.3004749282085266, "grad_norm": 6.623061656951904, "learning_rate": 3.280605354322825e-05, "loss": 0.1459, "step": 5441 }, { "epoch": 0.3005301524188204, "grad_norm": 1.6461039781570435, "learning_rate": 3.280330552624191e-05, "loss": 0.3895, "step": 5442 }, { "epoch": 0.3005853766291142, "grad_norm": 7.615862846374512, "learning_rate": 3.280055709964137e-05, "loss": 1.3036, "step": 5443 }, { "epoch": 0.300640600839408, "grad_norm": 1.0425400733947754, "learning_rate": 3.2797808263514574e-05, "loss": 0.0304, "step": 5444 }, { "epoch": 0.30069582504970177, "grad_norm": 0.8673451542854309, "learning_rate": 3.2795059017949457e-05, "loss": 0.0222, "step": 5445 }, { "epoch": 0.3007510492599956, "grad_norm": 0.5258547067642212, "learning_rate": 3.279230936303398e-05, "loss": 0.0176, "step": 5446 }, { "epoch": 0.3008062734702894, "grad_norm": 0.3702016770839691, "learning_rate": 3.27895592988561e-05, "loss": 0.0099, "step": 5447 }, { "epoch": 0.3008614976805832, "grad_norm": 5.798868656158447, "learning_rate": 3.2786808825503814e-05, "loss": 0.7049, "step": 5448 }, { "epoch": 0.300916721890877, "grad_norm": 0.3986794352531433, "learning_rate": 3.278405794306511e-05, "loss": 0.0164, "step": 5449 }, { "epoch": 0.30097194610117073, "grad_norm": 0.44934290647506714, "learning_rate": 3.278130665162799e-05, "loss": 0.0154, "step": 5450 }, { "epoch": 0.30102717031146453, "grad_norm": 1.273398756980896, "learning_rate": 3.277855495128049e-05, "loss": 0.0486, "step": 5451 }, { "epoch": 0.30108239452175833, "grad_norm": 0.26836761832237244, "learning_rate": 3.277580284211064e-05, "loss": 0.0064, "step": 5452 }, { "epoch": 0.30113761873205214, "grad_norm": 6.188815593719482, "learning_rate": 3.277305032420648e-05, "loss": 0.5887, "step": 5453 }, { "epoch": 0.30119284294234594, "grad_norm": 0.6343863606452942, "learning_rate": 3.277029739765608e-05, "loss": 0.0214, "step": 5454 }, { "epoch": 0.30124806715263974, "grad_norm": 0.15544980764389038, "learning_rate": 3.2767544062547516e-05, "loss": 0.0041, "step": 5455 }, { "epoch": 0.3013032913629335, "grad_norm": 2.4966912269592285, "learning_rate": 3.276479031896886e-05, "loss": 0.3321, "step": 5456 }, { "epoch": 0.3013585155732273, "grad_norm": 0.09160986542701721, "learning_rate": 3.276203616700823e-05, "loss": 0.0027, "step": 5457 }, { "epoch": 0.3014137397835211, "grad_norm": 2.3827874660491943, "learning_rate": 3.275928160675373e-05, "loss": 0.8939, "step": 5458 }, { "epoch": 0.3014689639938149, "grad_norm": 3.110682725906372, "learning_rate": 3.275652663829348e-05, "loss": 0.3608, "step": 5459 }, { "epoch": 0.3015241882041087, "grad_norm": 3.7120487689971924, "learning_rate": 3.275377126171563e-05, "loss": 0.4576, "step": 5460 }, { "epoch": 0.30157941241440245, "grad_norm": 2.459712505340576, "learning_rate": 3.2751015477108336e-05, "loss": 0.5628, "step": 5461 }, { "epoch": 0.30163463662469625, "grad_norm": 3.7580931186676025, "learning_rate": 3.274825928455975e-05, "loss": 0.9868, "step": 5462 }, { "epoch": 0.30168986083499005, "grad_norm": 5.3553547859191895, "learning_rate": 3.274550268415806e-05, "loss": 1.0043, "step": 5463 }, { "epoch": 0.30174508504528386, "grad_norm": 0.7464867234230042, "learning_rate": 3.274274567599145e-05, "loss": 0.0267, "step": 5464 }, { "epoch": 0.30180030925557766, "grad_norm": 2.0968010425567627, "learning_rate": 3.273998826014813e-05, "loss": 0.0564, "step": 5465 }, { "epoch": 0.30185553346587146, "grad_norm": 4.006324291229248, "learning_rate": 3.273723043671632e-05, "loss": 0.2793, "step": 5466 }, { "epoch": 0.3019107576761652, "grad_norm": 0.2206597775220871, "learning_rate": 3.273447220578424e-05, "loss": 0.008, "step": 5467 }, { "epoch": 0.301965981886459, "grad_norm": 1.9482331275939941, "learning_rate": 3.2731713567440144e-05, "loss": 0.1792, "step": 5468 }, { "epoch": 0.3020212060967528, "grad_norm": 2.1009790897369385, "learning_rate": 3.2728954521772294e-05, "loss": 0.1872, "step": 5469 }, { "epoch": 0.3020764303070466, "grad_norm": 0.3535260260105133, "learning_rate": 3.272619506886894e-05, "loss": 0.0102, "step": 5470 }, { "epoch": 0.3021316545173404, "grad_norm": 0.035992544144392014, "learning_rate": 3.272343520881838e-05, "loss": 0.0012, "step": 5471 }, { "epoch": 0.30218687872763417, "grad_norm": 1.8198295831680298, "learning_rate": 3.2720674941708905e-05, "loss": 0.0511, "step": 5472 }, { "epoch": 0.30224210293792797, "grad_norm": 0.5868385434150696, "learning_rate": 3.271791426762883e-05, "loss": 0.0173, "step": 5473 }, { "epoch": 0.3022973271482218, "grad_norm": 2.0522520542144775, "learning_rate": 3.2715153186666464e-05, "loss": 0.12, "step": 5474 }, { "epoch": 0.3023525513585156, "grad_norm": 0.10209516435861588, "learning_rate": 3.271239169891015e-05, "loss": 0.0036, "step": 5475 }, { "epoch": 0.3024077755688094, "grad_norm": 0.9915471076965332, "learning_rate": 3.270962980444823e-05, "loss": 0.0254, "step": 5476 }, { "epoch": 0.3024629997791032, "grad_norm": 1.5525429248809814, "learning_rate": 3.270686750336908e-05, "loss": 0.187, "step": 5477 }, { "epoch": 0.30251822398939693, "grad_norm": 0.16830837726593018, "learning_rate": 3.270410479576106e-05, "loss": 0.0051, "step": 5478 }, { "epoch": 0.30257344819969073, "grad_norm": 1.8863564729690552, "learning_rate": 3.270134168171256e-05, "loss": 0.1273, "step": 5479 }, { "epoch": 0.30262867240998453, "grad_norm": 0.39622756838798523, "learning_rate": 3.269857816131198e-05, "loss": 0.0162, "step": 5480 }, { "epoch": 0.30268389662027834, "grad_norm": 0.02575700730085373, "learning_rate": 3.2695814234647735e-05, "loss": 0.0009, "step": 5481 }, { "epoch": 0.30273912083057214, "grad_norm": 1.1187156438827515, "learning_rate": 3.2693049901808245e-05, "loss": 0.0214, "step": 5482 }, { "epoch": 0.30279434504086594, "grad_norm": 2.354658603668213, "learning_rate": 3.269028516288196e-05, "loss": 0.4256, "step": 5483 }, { "epoch": 0.3028495692511597, "grad_norm": 0.14415493607521057, "learning_rate": 3.268752001795732e-05, "loss": 0.0047, "step": 5484 }, { "epoch": 0.3029047934614535, "grad_norm": 0.061186596751213074, "learning_rate": 3.26847544671228e-05, "loss": 0.0022, "step": 5485 }, { "epoch": 0.3029600176717473, "grad_norm": 0.3245415687561035, "learning_rate": 3.268198851046687e-05, "loss": 0.0094, "step": 5486 }, { "epoch": 0.3030152418820411, "grad_norm": 1.2491536140441895, "learning_rate": 3.267922214807802e-05, "loss": 0.0915, "step": 5487 }, { "epoch": 0.3030704660923349, "grad_norm": 0.6134395599365234, "learning_rate": 3.267645538004476e-05, "loss": 0.03, "step": 5488 }, { "epoch": 0.30312569030262865, "grad_norm": 0.2819408178329468, "learning_rate": 3.26736882064556e-05, "loss": 0.0087, "step": 5489 }, { "epoch": 0.30318091451292245, "grad_norm": 0.30074793100357056, "learning_rate": 3.267092062739909e-05, "loss": 0.01, "step": 5490 }, { "epoch": 0.30323613872321625, "grad_norm": 1.981899619102478, "learning_rate": 3.266815264296374e-05, "loss": 0.1407, "step": 5491 }, { "epoch": 0.30329136293351006, "grad_norm": 6.01317024230957, "learning_rate": 3.266538425323813e-05, "loss": 0.162, "step": 5492 }, { "epoch": 0.30334658714380386, "grad_norm": 3.8875908851623535, "learning_rate": 3.2662615458310814e-05, "loss": 0.2593, "step": 5493 }, { "epoch": 0.30340181135409766, "grad_norm": 2.428197145462036, "learning_rate": 3.265984625827038e-05, "loss": 0.2849, "step": 5494 }, { "epoch": 0.3034570355643914, "grad_norm": 4.10936164855957, "learning_rate": 3.2657076653205426e-05, "loss": 0.8658, "step": 5495 }, { "epoch": 0.3035122597746852, "grad_norm": 1.2881368398666382, "learning_rate": 3.265430664320456e-05, "loss": 0.1874, "step": 5496 }, { "epoch": 0.303567483984979, "grad_norm": 3.161503314971924, "learning_rate": 3.26515362283564e-05, "loss": 0.1047, "step": 5497 }, { "epoch": 0.3036227081952728, "grad_norm": 2.7652623653411865, "learning_rate": 3.2648765408749575e-05, "loss": 0.0646, "step": 5498 }, { "epoch": 0.3036779324055666, "grad_norm": 0.11963418126106262, "learning_rate": 3.264599418447274e-05, "loss": 0.0037, "step": 5499 }, { "epoch": 0.30373315661586037, "grad_norm": 0.020879080519080162, "learning_rate": 3.264322255561454e-05, "loss": 0.0011, "step": 5500 }, { "epoch": 0.30378838082615417, "grad_norm": 4.025273323059082, "learning_rate": 3.2640450522263666e-05, "loss": 0.4515, "step": 5501 }, { "epoch": 0.303843605036448, "grad_norm": 3.056502342224121, "learning_rate": 3.2637678084508796e-05, "loss": 0.2498, "step": 5502 }, { "epoch": 0.3038988292467418, "grad_norm": 4.763664722442627, "learning_rate": 3.263490524243862e-05, "loss": 0.4688, "step": 5503 }, { "epoch": 0.3039540534570356, "grad_norm": 0.0897056832909584, "learning_rate": 3.2632131996141856e-05, "loss": 0.0033, "step": 5504 }, { "epoch": 0.3040092776673294, "grad_norm": 0.8697341084480286, "learning_rate": 3.262935834570723e-05, "loss": 0.0272, "step": 5505 }, { "epoch": 0.30406450187762313, "grad_norm": 1.6786463260650635, "learning_rate": 3.2626584291223466e-05, "loss": 0.216, "step": 5506 }, { "epoch": 0.30411972608791693, "grad_norm": 2.398022174835205, "learning_rate": 3.2623809832779337e-05, "loss": 0.2707, "step": 5507 }, { "epoch": 0.30417495029821073, "grad_norm": 0.05210050195455551, "learning_rate": 3.262103497046359e-05, "loss": 0.0021, "step": 5508 }, { "epoch": 0.30423017450850454, "grad_norm": 1.1871635913848877, "learning_rate": 3.2618259704365006e-05, "loss": 0.0353, "step": 5509 }, { "epoch": 0.30428539871879834, "grad_norm": 0.03347044810652733, "learning_rate": 3.2615484034572364e-05, "loss": 0.001, "step": 5510 }, { "epoch": 0.30434062292909214, "grad_norm": 2.819512367248535, "learning_rate": 3.261270796117447e-05, "loss": 0.2792, "step": 5511 }, { "epoch": 0.3043958471393859, "grad_norm": 2.2438666820526123, "learning_rate": 3.260993148426016e-05, "loss": 0.2462, "step": 5512 }, { "epoch": 0.3044510713496797, "grad_norm": 6.195064544677734, "learning_rate": 3.260715460391823e-05, "loss": 1.327, "step": 5513 }, { "epoch": 0.3045062955599735, "grad_norm": 5.451083183288574, "learning_rate": 3.2604377320237536e-05, "loss": 0.5579, "step": 5514 }, { "epoch": 0.3045615197702673, "grad_norm": 0.048459429293870926, "learning_rate": 3.2601599633306924e-05, "loss": 0.0017, "step": 5515 }, { "epoch": 0.3046167439805611, "grad_norm": 3.1708126068115234, "learning_rate": 3.259882154321527e-05, "loss": 0.2064, "step": 5516 }, { "epoch": 0.30467196819085485, "grad_norm": 2.9300825595855713, "learning_rate": 3.259604305005144e-05, "loss": 0.6834, "step": 5517 }, { "epoch": 0.30472719240114865, "grad_norm": 2.5141232013702393, "learning_rate": 3.259326415390434e-05, "loss": 0.1439, "step": 5518 }, { "epoch": 0.30478241661144245, "grad_norm": 5.219560623168945, "learning_rate": 3.259048485486287e-05, "loss": 0.8656, "step": 5519 }, { "epoch": 0.30483764082173626, "grad_norm": 3.909464120864868, "learning_rate": 3.258770515301594e-05, "loss": 0.9277, "step": 5520 }, { "epoch": 0.30489286503203006, "grad_norm": 2.8285534381866455, "learning_rate": 3.258492504845249e-05, "loss": 0.7481, "step": 5521 }, { "epoch": 0.30494808924232386, "grad_norm": 2.488903284072876, "learning_rate": 3.258214454126146e-05, "loss": 0.3736, "step": 5522 }, { "epoch": 0.3050033134526176, "grad_norm": 0.43976399302482605, "learning_rate": 3.257936363153181e-05, "loss": 0.0157, "step": 5523 }, { "epoch": 0.3050585376629114, "grad_norm": 1.1185956001281738, "learning_rate": 3.2576582319352495e-05, "loss": 0.0588, "step": 5524 }, { "epoch": 0.3051137618732052, "grad_norm": 1.9271565675735474, "learning_rate": 3.2573800604812515e-05, "loss": 0.0886, "step": 5525 }, { "epoch": 0.305168986083499, "grad_norm": 4.428711891174316, "learning_rate": 3.2571018488000854e-05, "loss": 0.6733, "step": 5526 }, { "epoch": 0.3052242102937928, "grad_norm": 0.11239637434482574, "learning_rate": 3.2568235969006525e-05, "loss": 0.0031, "step": 5527 }, { "epoch": 0.30527943450408657, "grad_norm": 0.1453772932291031, "learning_rate": 3.2565453047918554e-05, "loss": 0.0048, "step": 5528 }, { "epoch": 0.30533465871438037, "grad_norm": 0.09588336199522018, "learning_rate": 3.256266972482596e-05, "loss": 0.0042, "step": 5529 }, { "epoch": 0.30538988292467417, "grad_norm": 0.16675762832164764, "learning_rate": 3.25598859998178e-05, "loss": 0.0043, "step": 5530 }, { "epoch": 0.305445107134968, "grad_norm": 3.721126079559326, "learning_rate": 3.2557101872983126e-05, "loss": 1.4469, "step": 5531 }, { "epoch": 0.3055003313452618, "grad_norm": 5.145079612731934, "learning_rate": 3.255431734441102e-05, "loss": 0.8326, "step": 5532 }, { "epoch": 0.3055555555555556, "grad_norm": 1.1162112951278687, "learning_rate": 3.255153241419056e-05, "loss": 0.0541, "step": 5533 }, { "epoch": 0.3056107797658493, "grad_norm": 0.0693264976143837, "learning_rate": 3.254874708241085e-05, "loss": 0.0025, "step": 5534 }, { "epoch": 0.30566600397614313, "grad_norm": 3.0782763957977295, "learning_rate": 3.254596134916099e-05, "loss": 0.9006, "step": 5535 }, { "epoch": 0.30572122818643693, "grad_norm": 0.6298828721046448, "learning_rate": 3.254317521453011e-05, "loss": 0.0153, "step": 5536 }, { "epoch": 0.30577645239673074, "grad_norm": 5.6151251792907715, "learning_rate": 3.254038867860735e-05, "loss": 0.5737, "step": 5537 }, { "epoch": 0.30583167660702454, "grad_norm": 2.3523895740509033, "learning_rate": 3.253760174148185e-05, "loss": 0.3373, "step": 5538 }, { "epoch": 0.3058869008173183, "grad_norm": 0.06322351843118668, "learning_rate": 3.253481440324278e-05, "loss": 0.0026, "step": 5539 }, { "epoch": 0.3059421250276121, "grad_norm": 1.2519663572311401, "learning_rate": 3.2532026663979306e-05, "loss": 0.0278, "step": 5540 }, { "epoch": 0.3059973492379059, "grad_norm": 3.555476665496826, "learning_rate": 3.252923852378063e-05, "loss": 1.1001, "step": 5541 }, { "epoch": 0.3060525734481997, "grad_norm": 0.40730613470077515, "learning_rate": 3.252644998273594e-05, "loss": 0.0154, "step": 5542 }, { "epoch": 0.3061077976584935, "grad_norm": 2.1140971183776855, "learning_rate": 3.252366104093446e-05, "loss": 0.191, "step": 5543 }, { "epoch": 0.3061630218687873, "grad_norm": 0.046149373054504395, "learning_rate": 3.2520871698465404e-05, "loss": 0.0021, "step": 5544 }, { "epoch": 0.30621824607908105, "grad_norm": 0.42734652757644653, "learning_rate": 3.251808195541802e-05, "loss": 0.0115, "step": 5545 }, { "epoch": 0.30627347028937485, "grad_norm": 0.08196339011192322, "learning_rate": 3.251529181188156e-05, "loss": 0.0024, "step": 5546 }, { "epoch": 0.30632869449966865, "grad_norm": 2.4626643657684326, "learning_rate": 3.251250126794528e-05, "loss": 0.5152, "step": 5547 }, { "epoch": 0.30638391870996246, "grad_norm": 1.755642056465149, "learning_rate": 3.2509710323698464e-05, "loss": 0.3963, "step": 5548 }, { "epoch": 0.30643914292025626, "grad_norm": 0.13669706881046295, "learning_rate": 3.25069189792304e-05, "loss": 0.0062, "step": 5549 }, { "epoch": 0.30649436713055006, "grad_norm": 0.07033191621303558, "learning_rate": 3.2504127234630396e-05, "loss": 0.0019, "step": 5550 }, { "epoch": 0.3065495913408438, "grad_norm": 3.564288854598999, "learning_rate": 3.250133508998776e-05, "loss": 0.2207, "step": 5551 }, { "epoch": 0.3066048155511376, "grad_norm": 1.372430443763733, "learning_rate": 3.249854254539183e-05, "loss": 0.0506, "step": 5552 }, { "epoch": 0.3066600397614314, "grad_norm": 0.0901591032743454, "learning_rate": 3.249574960093194e-05, "loss": 0.0035, "step": 5553 }, { "epoch": 0.3067152639717252, "grad_norm": 0.5680098533630371, "learning_rate": 3.249295625669744e-05, "loss": 0.0163, "step": 5554 }, { "epoch": 0.306770488182019, "grad_norm": 2.080740451812744, "learning_rate": 3.249016251277771e-05, "loss": 0.0885, "step": 5555 }, { "epoch": 0.30682571239231277, "grad_norm": 2.471627712249756, "learning_rate": 3.2487368369262125e-05, "loss": 0.1127, "step": 5556 }, { "epoch": 0.30688093660260657, "grad_norm": 0.03888799622654915, "learning_rate": 3.248457382624007e-05, "loss": 0.0011, "step": 5557 }, { "epoch": 0.30693616081290037, "grad_norm": 3.9857354164123535, "learning_rate": 3.248177888380096e-05, "loss": 0.522, "step": 5558 }, { "epoch": 0.3069913850231942, "grad_norm": 3.7971811294555664, "learning_rate": 3.247898354203421e-05, "loss": 0.677, "step": 5559 }, { "epoch": 0.307046609233488, "grad_norm": 0.04157840833067894, "learning_rate": 3.247618780102925e-05, "loss": 0.0014, "step": 5560 }, { "epoch": 0.3071018334437818, "grad_norm": 0.11172980070114136, "learning_rate": 3.2473391660875524e-05, "loss": 0.0044, "step": 5561 }, { "epoch": 0.3071570576540755, "grad_norm": 0.5917102098464966, "learning_rate": 3.2470595121662487e-05, "loss": 0.0253, "step": 5562 }, { "epoch": 0.30721228186436933, "grad_norm": 1.6682422161102295, "learning_rate": 3.246779818347961e-05, "loss": 0.0372, "step": 5563 }, { "epoch": 0.30726750607466313, "grad_norm": 2.1572113037109375, "learning_rate": 3.246500084641637e-05, "loss": 0.1367, "step": 5564 }, { "epoch": 0.30732273028495694, "grad_norm": 0.23424631357192993, "learning_rate": 3.246220311056227e-05, "loss": 0.0074, "step": 5565 }, { "epoch": 0.30737795449525074, "grad_norm": 3.1217222213745117, "learning_rate": 3.2459404976006826e-05, "loss": 0.1753, "step": 5566 }, { "epoch": 0.3074331787055445, "grad_norm": 0.08490046858787537, "learning_rate": 3.245660644283954e-05, "loss": 0.0026, "step": 5567 }, { "epoch": 0.3074884029158383, "grad_norm": 2.3267760276794434, "learning_rate": 3.245380751114994e-05, "loss": 0.2616, "step": 5568 }, { "epoch": 0.3075436271261321, "grad_norm": 0.13169477880001068, "learning_rate": 3.24510081810276e-05, "loss": 0.0046, "step": 5569 }, { "epoch": 0.3075988513364259, "grad_norm": 0.10559329390525818, "learning_rate": 3.2448208452562054e-05, "loss": 0.0036, "step": 5570 }, { "epoch": 0.3076540755467197, "grad_norm": 3.8437910079956055, "learning_rate": 3.2445408325842876e-05, "loss": 0.6218, "step": 5571 }, { "epoch": 0.3077092997570135, "grad_norm": 0.9186256527900696, "learning_rate": 3.244260780095967e-05, "loss": 0.0428, "step": 5572 }, { "epoch": 0.30776452396730725, "grad_norm": 0.07337494194507599, "learning_rate": 3.2439806878002e-05, "loss": 0.0025, "step": 5573 }, { "epoch": 0.30781974817760105, "grad_norm": 0.057318706065416336, "learning_rate": 3.24370055570595e-05, "loss": 0.0027, "step": 5574 }, { "epoch": 0.30787497238789485, "grad_norm": 2.0803065299987793, "learning_rate": 3.243420383822178e-05, "loss": 0.2051, "step": 5575 }, { "epoch": 0.30793019659818865, "grad_norm": 3.591202735900879, "learning_rate": 3.2431401721578496e-05, "loss": 0.373, "step": 5576 }, { "epoch": 0.30798542080848246, "grad_norm": 1.877054214477539, "learning_rate": 3.2428599207219266e-05, "loss": 0.2446, "step": 5577 }, { "epoch": 0.3080406450187762, "grad_norm": 3.8063812255859375, "learning_rate": 3.2425796295233774e-05, "loss": 0.6819, "step": 5578 }, { "epoch": 0.30809586922907, "grad_norm": 0.7127312421798706, "learning_rate": 3.242299298571168e-05, "loss": 0.026, "step": 5579 }, { "epoch": 0.3081510934393638, "grad_norm": 0.5353173017501831, "learning_rate": 3.2420189278742675e-05, "loss": 0.0112, "step": 5580 }, { "epoch": 0.3082063176496576, "grad_norm": 0.08313007652759552, "learning_rate": 3.241738517441645e-05, "loss": 0.0029, "step": 5581 }, { "epoch": 0.3082615418599514, "grad_norm": 0.975606381893158, "learning_rate": 3.241458067282273e-05, "loss": 0.0296, "step": 5582 }, { "epoch": 0.3083167660702452, "grad_norm": 0.019093651324510574, "learning_rate": 3.241177577405123e-05, "loss": 0.0008, "step": 5583 }, { "epoch": 0.30837199028053897, "grad_norm": 1.1109645366668701, "learning_rate": 3.240897047819169e-05, "loss": 0.0232, "step": 5584 }, { "epoch": 0.30842721449083277, "grad_norm": 0.05866904556751251, "learning_rate": 3.240616478533385e-05, "loss": 0.0025, "step": 5585 }, { "epoch": 0.30848243870112657, "grad_norm": 2.264834403991699, "learning_rate": 3.2403358695567485e-05, "loss": 0.1966, "step": 5586 }, { "epoch": 0.3085376629114204, "grad_norm": 2.1591076850891113, "learning_rate": 3.2400552208982366e-05, "loss": 0.3814, "step": 5587 }, { "epoch": 0.3085928871217142, "grad_norm": 3.999055862426758, "learning_rate": 3.239774532566828e-05, "loss": 1.3548, "step": 5588 }, { "epoch": 0.308648111332008, "grad_norm": 0.23686878383159637, "learning_rate": 3.2394938045715027e-05, "loss": 0.0097, "step": 5589 }, { "epoch": 0.3087033355423017, "grad_norm": 3.2832319736480713, "learning_rate": 3.239213036921241e-05, "loss": 0.3049, "step": 5590 }, { "epoch": 0.30875855975259553, "grad_norm": 2.604640245437622, "learning_rate": 3.2389322296250267e-05, "loss": 0.3842, "step": 5591 }, { "epoch": 0.30881378396288933, "grad_norm": 1.8000843524932861, "learning_rate": 3.238651382691844e-05, "loss": 0.1585, "step": 5592 }, { "epoch": 0.30886900817318313, "grad_norm": 12.990431785583496, "learning_rate": 3.238370496130677e-05, "loss": 0.03, "step": 5593 }, { "epoch": 0.30892423238347694, "grad_norm": 4.4641571044921875, "learning_rate": 3.238089569950512e-05, "loss": 0.4278, "step": 5594 }, { "epoch": 0.3089794565937707, "grad_norm": 0.11643418669700623, "learning_rate": 3.237808604160337e-05, "loss": 0.0042, "step": 5595 }, { "epoch": 0.3090346808040645, "grad_norm": 2.0682153701782227, "learning_rate": 3.2375275987691414e-05, "loss": 0.1796, "step": 5596 }, { "epoch": 0.3090899050143583, "grad_norm": 0.13450461626052856, "learning_rate": 3.237246553785914e-05, "loss": 0.0052, "step": 5597 }, { "epoch": 0.3091451292246521, "grad_norm": 0.0844578891992569, "learning_rate": 3.236965469219647e-05, "loss": 0.0033, "step": 5598 }, { "epoch": 0.3092003534349459, "grad_norm": 3.37153959274292, "learning_rate": 3.236684345079334e-05, "loss": 0.5564, "step": 5599 }, { "epoch": 0.3092555776452397, "grad_norm": 0.7041477560997009, "learning_rate": 3.2364031813739675e-05, "loss": 0.0233, "step": 5600 }, { "epoch": 0.30931080185553345, "grad_norm": 0.6356825828552246, "learning_rate": 3.236121978112544e-05, "loss": 0.023, "step": 5601 }, { "epoch": 0.30936602606582725, "grad_norm": 0.1782715618610382, "learning_rate": 3.235840735304059e-05, "loss": 0.0063, "step": 5602 }, { "epoch": 0.30942125027612105, "grad_norm": 3.662475824356079, "learning_rate": 3.2355594529575105e-05, "loss": 1.2556, "step": 5603 }, { "epoch": 0.30947647448641485, "grad_norm": 0.19319649040699005, "learning_rate": 3.235278131081898e-05, "loss": 0.0072, "step": 5604 }, { "epoch": 0.30953169869670866, "grad_norm": 1.0478019714355469, "learning_rate": 3.234996769686221e-05, "loss": 0.05, "step": 5605 }, { "epoch": 0.3095869229070024, "grad_norm": 1.4570114612579346, "learning_rate": 3.234715368779481e-05, "loss": 0.0451, "step": 5606 }, { "epoch": 0.3096421471172962, "grad_norm": 0.05037835240364075, "learning_rate": 3.234433928370682e-05, "loss": 0.0016, "step": 5607 }, { "epoch": 0.30969737132759, "grad_norm": 2.8133981227874756, "learning_rate": 3.234152448468827e-05, "loss": 1.0082, "step": 5608 }, { "epoch": 0.3097525955378838, "grad_norm": 2.0556697845458984, "learning_rate": 3.233870929082922e-05, "loss": 0.1792, "step": 5609 }, { "epoch": 0.3098078197481776, "grad_norm": 0.9297361373901367, "learning_rate": 3.233589370221973e-05, "loss": 0.0215, "step": 5610 }, { "epoch": 0.3098630439584714, "grad_norm": 0.23853936791419983, "learning_rate": 3.2333077718949884e-05, "loss": 0.0075, "step": 5611 }, { "epoch": 0.30991826816876517, "grad_norm": 0.3753701448440552, "learning_rate": 3.2330261341109774e-05, "loss": 0.0126, "step": 5612 }, { "epoch": 0.30997349237905897, "grad_norm": 4.08687686920166, "learning_rate": 3.2327444568789494e-05, "loss": 1.3084, "step": 5613 }, { "epoch": 0.31002871658935277, "grad_norm": 0.17578758299350739, "learning_rate": 3.2324627402079174e-05, "loss": 0.0032, "step": 5614 }, { "epoch": 0.3100839407996466, "grad_norm": 0.08600999414920807, "learning_rate": 3.232180984106893e-05, "loss": 0.0023, "step": 5615 }, { "epoch": 0.3101391650099404, "grad_norm": 4.338453769683838, "learning_rate": 3.231899188584891e-05, "loss": 1.2696, "step": 5616 }, { "epoch": 0.3101943892202341, "grad_norm": 0.4079049527645111, "learning_rate": 3.231617353650927e-05, "loss": 0.0118, "step": 5617 }, { "epoch": 0.3102496134305279, "grad_norm": 2.265881299972534, "learning_rate": 3.231335479314019e-05, "loss": 0.1692, "step": 5618 }, { "epoch": 0.31030483764082173, "grad_norm": 2.978496789932251, "learning_rate": 3.2310535655831825e-05, "loss": 0.2417, "step": 5619 }, { "epoch": 0.31036006185111553, "grad_norm": 3.248751163482666, "learning_rate": 3.230771612467437e-05, "loss": 0.8679, "step": 5620 }, { "epoch": 0.31041528606140933, "grad_norm": 3.7872061729431152, "learning_rate": 3.230489619975805e-05, "loss": 0.9324, "step": 5621 }, { "epoch": 0.31047051027170314, "grad_norm": 0.20536260306835175, "learning_rate": 3.2302075881173066e-05, "loss": 0.0048, "step": 5622 }, { "epoch": 0.3105257344819969, "grad_norm": 0.3030906617641449, "learning_rate": 3.229925516900965e-05, "loss": 0.0086, "step": 5623 }, { "epoch": 0.3105809586922907, "grad_norm": 2.779268980026245, "learning_rate": 3.229643406335805e-05, "loss": 0.79, "step": 5624 }, { "epoch": 0.3106361829025845, "grad_norm": 3.2363994121551514, "learning_rate": 3.229361256430851e-05, "loss": 0.8933, "step": 5625 }, { "epoch": 0.3106914071128783, "grad_norm": 2.0633597373962402, "learning_rate": 3.229079067195132e-05, "loss": 0.0512, "step": 5626 }, { "epoch": 0.3107466313231721, "grad_norm": 2.4605066776275635, "learning_rate": 3.2287968386376734e-05, "loss": 0.1986, "step": 5627 }, { "epoch": 0.3108018555334659, "grad_norm": 3.494014024734497, "learning_rate": 3.228514570767506e-05, "loss": 0.257, "step": 5628 }, { "epoch": 0.31085707974375965, "grad_norm": 0.1383412629365921, "learning_rate": 3.2282322635936603e-05, "loss": 0.004, "step": 5629 }, { "epoch": 0.31091230395405345, "grad_norm": 1.1775990724563599, "learning_rate": 3.227949917125168e-05, "loss": 0.1018, "step": 5630 }, { "epoch": 0.31096752816434725, "grad_norm": 0.24607320129871368, "learning_rate": 3.227667531371061e-05, "loss": 0.0056, "step": 5631 }, { "epoch": 0.31102275237464105, "grad_norm": 0.7476022839546204, "learning_rate": 3.227385106340376e-05, "loss": 0.0259, "step": 5632 }, { "epoch": 0.31107797658493486, "grad_norm": 0.06036160886287689, "learning_rate": 3.2271026420421464e-05, "loss": 0.0023, "step": 5633 }, { "epoch": 0.3111332007952286, "grad_norm": 0.12869229912757874, "learning_rate": 3.22682013848541e-05, "loss": 0.0039, "step": 5634 }, { "epoch": 0.3111884250055224, "grad_norm": 0.5583417415618896, "learning_rate": 3.2265375956792055e-05, "loss": 0.0195, "step": 5635 }, { "epoch": 0.3112436492158162, "grad_norm": 0.07453334331512451, "learning_rate": 3.2262550136325706e-05, "loss": 0.0026, "step": 5636 }, { "epoch": 0.31129887342611, "grad_norm": 1.9104139804840088, "learning_rate": 3.225972392354547e-05, "loss": 0.197, "step": 5637 }, { "epoch": 0.3113540976364038, "grad_norm": 5.012066841125488, "learning_rate": 3.225689731854177e-05, "loss": 0.2329, "step": 5638 }, { "epoch": 0.3114093218466976, "grad_norm": 2.5304088592529297, "learning_rate": 3.225407032140502e-05, "loss": 0.5444, "step": 5639 }, { "epoch": 0.31146454605699136, "grad_norm": 1.8072155714035034, "learning_rate": 3.225124293222569e-05, "loss": 0.0327, "step": 5640 }, { "epoch": 0.31151977026728517, "grad_norm": 6.143622875213623, "learning_rate": 3.22484151510942e-05, "loss": 2.3899, "step": 5641 }, { "epoch": 0.31157499447757897, "grad_norm": 0.2348558008670807, "learning_rate": 3.2245586978101054e-05, "loss": 0.0088, "step": 5642 }, { "epoch": 0.3116302186878728, "grad_norm": 0.14012457430362701, "learning_rate": 3.224275841333672e-05, "loss": 0.0036, "step": 5643 }, { "epoch": 0.3116854428981666, "grad_norm": 3.2638535499572754, "learning_rate": 3.223992945689168e-05, "loss": 0.8819, "step": 5644 }, { "epoch": 0.3117406671084603, "grad_norm": 2.2376461029052734, "learning_rate": 3.223710010885646e-05, "loss": 0.0446, "step": 5645 }, { "epoch": 0.3117958913187541, "grad_norm": 5.823675632476807, "learning_rate": 3.2234270369321566e-05, "loss": 1.2397, "step": 5646 }, { "epoch": 0.31185111552904793, "grad_norm": 0.3319191336631775, "learning_rate": 3.2231440238377535e-05, "loss": 0.0117, "step": 5647 }, { "epoch": 0.31190633973934173, "grad_norm": 0.024915922433137894, "learning_rate": 3.222860971611491e-05, "loss": 0.0009, "step": 5648 }, { "epoch": 0.31196156394963553, "grad_norm": 2.7540626525878906, "learning_rate": 3.222577880262425e-05, "loss": 0.2452, "step": 5649 }, { "epoch": 0.31201678815992934, "grad_norm": 0.12636762857437134, "learning_rate": 3.2222947497996116e-05, "loss": 0.0067, "step": 5650 }, { "epoch": 0.3120720123702231, "grad_norm": 4.502451419830322, "learning_rate": 3.2220115802321095e-05, "loss": 0.5143, "step": 5651 }, { "epoch": 0.3121272365805169, "grad_norm": 0.738509476184845, "learning_rate": 3.221728371568978e-05, "loss": 0.027, "step": 5652 }, { "epoch": 0.3121824607908107, "grad_norm": 0.5241484642028809, "learning_rate": 3.221445123819278e-05, "loss": 0.0174, "step": 5653 }, { "epoch": 0.3122376850011045, "grad_norm": 0.021906226873397827, "learning_rate": 3.221161836992071e-05, "loss": 0.0009, "step": 5654 }, { "epoch": 0.3122929092113983, "grad_norm": 2.8180301189422607, "learning_rate": 3.2208785110964204e-05, "loss": 0.419, "step": 5655 }, { "epoch": 0.31234813342169204, "grad_norm": 2.5203030109405518, "learning_rate": 3.220595146141391e-05, "loss": 0.4199, "step": 5656 }, { "epoch": 0.31240335763198585, "grad_norm": 2.417914867401123, "learning_rate": 3.220311742136048e-05, "loss": 0.2621, "step": 5657 }, { "epoch": 0.31245858184227965, "grad_norm": 0.07853241264820099, "learning_rate": 3.220028299089457e-05, "loss": 0.0021, "step": 5658 }, { "epoch": 0.31251380605257345, "grad_norm": 0.0584346204996109, "learning_rate": 3.2197448170106885e-05, "loss": 0.0015, "step": 5659 }, { "epoch": 0.31256903026286725, "grad_norm": 1.4875191450119019, "learning_rate": 3.2194612959088106e-05, "loss": 0.0423, "step": 5660 }, { "epoch": 0.31262425447316106, "grad_norm": 6.548969268798828, "learning_rate": 3.219177735792895e-05, "loss": 1.3814, "step": 5661 }, { "epoch": 0.3126794786834548, "grad_norm": 1.4191516637802124, "learning_rate": 3.2188941366720114e-05, "loss": 0.1431, "step": 5662 }, { "epoch": 0.3127347028937486, "grad_norm": 0.5132499933242798, "learning_rate": 3.218610498555235e-05, "loss": 0.0143, "step": 5663 }, { "epoch": 0.3127899271040424, "grad_norm": 6.378286361694336, "learning_rate": 3.218326821451639e-05, "loss": 1.4201, "step": 5664 }, { "epoch": 0.3128451513143362, "grad_norm": 1.954497218132019, "learning_rate": 3.2180431053703e-05, "loss": 0.3854, "step": 5665 }, { "epoch": 0.31290037552463, "grad_norm": 1.0452967882156372, "learning_rate": 3.217759350320295e-05, "loss": 0.0138, "step": 5666 }, { "epoch": 0.3129555997349238, "grad_norm": 1.8710601329803467, "learning_rate": 3.2174755563107015e-05, "loss": 0.0626, "step": 5667 }, { "epoch": 0.31301082394521756, "grad_norm": 2.2784478664398193, "learning_rate": 3.217191723350598e-05, "loss": 0.7508, "step": 5668 }, { "epoch": 0.31306604815551137, "grad_norm": 0.030187347903847694, "learning_rate": 3.216907851449066e-05, "loss": 0.0009, "step": 5669 }, { "epoch": 0.31312127236580517, "grad_norm": 1.5018465518951416, "learning_rate": 3.216623940615189e-05, "loss": 0.1579, "step": 5670 }, { "epoch": 0.313176496576099, "grad_norm": 0.07471849024295807, "learning_rate": 3.216339990858047e-05, "loss": 0.0029, "step": 5671 }, { "epoch": 0.3132317207863928, "grad_norm": 1.3918659687042236, "learning_rate": 3.216056002186727e-05, "loss": 0.0689, "step": 5672 }, { "epoch": 0.3132869449966865, "grad_norm": 2.9540977478027344, "learning_rate": 3.215771974610313e-05, "loss": 0.9165, "step": 5673 }, { "epoch": 0.3133421692069803, "grad_norm": 3.586925983428955, "learning_rate": 3.215487908137892e-05, "loss": 1.0186, "step": 5674 }, { "epoch": 0.31339739341727413, "grad_norm": 1.52903151512146, "learning_rate": 3.215203802778553e-05, "loss": 0.2257, "step": 5675 }, { "epoch": 0.31345261762756793, "grad_norm": 0.046921610832214355, "learning_rate": 3.214919658541385e-05, "loss": 0.0021, "step": 5676 }, { "epoch": 0.31350784183786173, "grad_norm": 2.056267499923706, "learning_rate": 3.2146354754354785e-05, "loss": 0.558, "step": 5677 }, { "epoch": 0.31356306604815554, "grad_norm": 0.17721498012542725, "learning_rate": 3.214351253469924e-05, "loss": 0.0055, "step": 5678 }, { "epoch": 0.3136182902584493, "grad_norm": 0.04380986467003822, "learning_rate": 3.214066992653817e-05, "loss": 0.0015, "step": 5679 }, { "epoch": 0.3136735144687431, "grad_norm": 0.38505101203918457, "learning_rate": 3.21378269299625e-05, "loss": 0.0086, "step": 5680 }, { "epoch": 0.3137287386790369, "grad_norm": 2.95357608795166, "learning_rate": 3.21349835450632e-05, "loss": 1.0818, "step": 5681 }, { "epoch": 0.3137839628893307, "grad_norm": 1.1908717155456543, "learning_rate": 3.213213977193122e-05, "loss": 0.1614, "step": 5682 }, { "epoch": 0.3138391870996245, "grad_norm": 0.0627065971493721, "learning_rate": 3.212929561065756e-05, "loss": 0.0023, "step": 5683 }, { "epoch": 0.31389441130991824, "grad_norm": 1.1960386037826538, "learning_rate": 3.212645106133319e-05, "loss": 0.1453, "step": 5684 }, { "epoch": 0.31394963552021204, "grad_norm": 3.640838384628296, "learning_rate": 3.212360612404914e-05, "loss": 0.3388, "step": 5685 }, { "epoch": 0.31400485973050585, "grad_norm": 1.1024601459503174, "learning_rate": 3.212076079889641e-05, "loss": 0.056, "step": 5686 }, { "epoch": 0.31406008394079965, "grad_norm": 0.17538051307201385, "learning_rate": 3.211791508596604e-05, "loss": 0.0063, "step": 5687 }, { "epoch": 0.31411530815109345, "grad_norm": 3.027435302734375, "learning_rate": 3.211506898534906e-05, "loss": 0.5152, "step": 5688 }, { "epoch": 0.31417053236138726, "grad_norm": 1.9444502592086792, "learning_rate": 3.211222249713654e-05, "loss": 0.2659, "step": 5689 }, { "epoch": 0.314225756571681, "grad_norm": 0.580706775188446, "learning_rate": 3.210937562141954e-05, "loss": 0.0129, "step": 5690 }, { "epoch": 0.3142809807819748, "grad_norm": 3.9677064418792725, "learning_rate": 3.2106528358289134e-05, "loss": 1.1577, "step": 5691 }, { "epoch": 0.3143362049922686, "grad_norm": 0.05170845985412598, "learning_rate": 3.2103680707836426e-05, "loss": 0.0019, "step": 5692 }, { "epoch": 0.3143914292025624, "grad_norm": 0.10909111797809601, "learning_rate": 3.210083267015251e-05, "loss": 0.0028, "step": 5693 }, { "epoch": 0.3144466534128562, "grad_norm": 0.13603125512599945, "learning_rate": 3.209798424532851e-05, "loss": 0.0051, "step": 5694 }, { "epoch": 0.31450187762314996, "grad_norm": 0.20103400945663452, "learning_rate": 3.209513543345556e-05, "loss": 0.0061, "step": 5695 }, { "epoch": 0.31455710183344376, "grad_norm": 2.1513724327087402, "learning_rate": 3.209228623462478e-05, "loss": 0.1839, "step": 5696 }, { "epoch": 0.31461232604373757, "grad_norm": 0.08888041973114014, "learning_rate": 3.208943664892735e-05, "loss": 0.0037, "step": 5697 }, { "epoch": 0.31466755025403137, "grad_norm": 0.11244214326143265, "learning_rate": 3.208658667645442e-05, "loss": 0.0042, "step": 5698 }, { "epoch": 0.3147227744643252, "grad_norm": 0.7158251404762268, "learning_rate": 3.2083736317297164e-05, "loss": 0.0108, "step": 5699 }, { "epoch": 0.314777998674619, "grad_norm": 0.058093152940273285, "learning_rate": 3.2080885571546796e-05, "loss": 0.0027, "step": 5700 }, { "epoch": 0.3148332228849127, "grad_norm": 4.029148101806641, "learning_rate": 3.20780344392945e-05, "loss": 0.5221, "step": 5701 }, { "epoch": 0.3148884470952065, "grad_norm": 3.212390661239624, "learning_rate": 3.20751829206315e-05, "loss": 0.419, "step": 5702 }, { "epoch": 0.31494367130550033, "grad_norm": 4.506152629852295, "learning_rate": 3.207233101564902e-05, "loss": 1.3146, "step": 5703 }, { "epoch": 0.31499889551579413, "grad_norm": 0.2738746106624603, "learning_rate": 3.2069478724438306e-05, "loss": 0.0097, "step": 5704 }, { "epoch": 0.31505411972608793, "grad_norm": 1.847302794456482, "learning_rate": 3.20666260470906e-05, "loss": 0.2024, "step": 5705 }, { "epoch": 0.31510934393638174, "grad_norm": 0.1327856481075287, "learning_rate": 3.206377298369718e-05, "loss": 0.0041, "step": 5706 }, { "epoch": 0.3151645681466755, "grad_norm": 0.30978283286094666, "learning_rate": 3.2060919534349314e-05, "loss": 0.0062, "step": 5707 }, { "epoch": 0.3152197923569693, "grad_norm": 1.4103301763534546, "learning_rate": 3.20580656991383e-05, "loss": 0.077, "step": 5708 }, { "epoch": 0.3152750165672631, "grad_norm": 3.245455026626587, "learning_rate": 3.205521147815544e-05, "loss": 0.3944, "step": 5709 }, { "epoch": 0.3153302407775569, "grad_norm": 1.7184202671051025, "learning_rate": 3.205235687149204e-05, "loss": 0.1713, "step": 5710 }, { "epoch": 0.3153854649878507, "grad_norm": 4.858918190002441, "learning_rate": 3.204950187923943e-05, "loss": 0.4506, "step": 5711 }, { "epoch": 0.31544068919814444, "grad_norm": 3.462355375289917, "learning_rate": 3.204664650148895e-05, "loss": 0.217, "step": 5712 }, { "epoch": 0.31549591340843824, "grad_norm": 2.2403717041015625, "learning_rate": 3.204379073833196e-05, "loss": 0.2182, "step": 5713 }, { "epoch": 0.31555113761873205, "grad_norm": 0.07330905646085739, "learning_rate": 3.204093458985982e-05, "loss": 0.003, "step": 5714 }, { "epoch": 0.31560636182902585, "grad_norm": 0.21087414026260376, "learning_rate": 3.2038078056163896e-05, "loss": 0.0063, "step": 5715 }, { "epoch": 0.31566158603931965, "grad_norm": 2.9358344078063965, "learning_rate": 3.203522113733558e-05, "loss": 0.2594, "step": 5716 }, { "epoch": 0.31571681024961346, "grad_norm": 0.04740680009126663, "learning_rate": 3.203236383346629e-05, "loss": 0.0014, "step": 5717 }, { "epoch": 0.3157720344599072, "grad_norm": 4.763319969177246, "learning_rate": 3.202950614464742e-05, "loss": 1.162, "step": 5718 }, { "epoch": 0.315827258670201, "grad_norm": 0.05819302052259445, "learning_rate": 3.20266480709704e-05, "loss": 0.002, "step": 5719 }, { "epoch": 0.3158824828804948, "grad_norm": 3.0219643115997314, "learning_rate": 3.202378961252667e-05, "loss": 0.4854, "step": 5720 }, { "epoch": 0.3159377070907886, "grad_norm": 0.05352926254272461, "learning_rate": 3.202093076940768e-05, "loss": 0.0016, "step": 5721 }, { "epoch": 0.3159929313010824, "grad_norm": 0.3112001121044159, "learning_rate": 3.20180715417049e-05, "loss": 0.0127, "step": 5722 }, { "epoch": 0.31604815551137616, "grad_norm": 3.0202865600585938, "learning_rate": 3.201521192950979e-05, "loss": 0.499, "step": 5723 }, { "epoch": 0.31610337972166996, "grad_norm": 2.7599949836730957, "learning_rate": 3.2012351932913846e-05, "loss": 1.1673, "step": 5724 }, { "epoch": 0.31615860393196377, "grad_norm": 1.0515836477279663, "learning_rate": 3.200949155200857e-05, "loss": 0.1871, "step": 5725 }, { "epoch": 0.31621382814225757, "grad_norm": 0.0535152293741703, "learning_rate": 3.2006630786885465e-05, "loss": 0.0025, "step": 5726 }, { "epoch": 0.31626905235255137, "grad_norm": 4.447188377380371, "learning_rate": 3.200376963763606e-05, "loss": 1.1272, "step": 5727 }, { "epoch": 0.3163242765628452, "grad_norm": 0.710269570350647, "learning_rate": 3.2000908104351887e-05, "loss": 0.0225, "step": 5728 }, { "epoch": 0.3163795007731389, "grad_norm": 0.39247453212738037, "learning_rate": 3.19980461871245e-05, "loss": 0.0121, "step": 5729 }, { "epoch": 0.3164347249834327, "grad_norm": 2.582301378250122, "learning_rate": 3.1995183886045464e-05, "loss": 0.4491, "step": 5730 }, { "epoch": 0.3164899491937265, "grad_norm": 4.340929985046387, "learning_rate": 3.199232120120635e-05, "loss": 0.5253, "step": 5731 }, { "epoch": 0.31654517340402033, "grad_norm": 0.07612941414117813, "learning_rate": 3.198945813269873e-05, "loss": 0.003, "step": 5732 }, { "epoch": 0.31660039761431413, "grad_norm": 2.446568012237549, "learning_rate": 3.1986594680614216e-05, "loss": 0.1347, "step": 5733 }, { "epoch": 0.31665562182460794, "grad_norm": 0.09477626532316208, "learning_rate": 3.198373084504441e-05, "loss": 0.0035, "step": 5734 }, { "epoch": 0.3167108460349017, "grad_norm": 0.1697208732366562, "learning_rate": 3.198086662608095e-05, "loss": 0.0062, "step": 5735 }, { "epoch": 0.3167660702451955, "grad_norm": 0.4680835008621216, "learning_rate": 3.1978002023815446e-05, "loss": 0.0153, "step": 5736 }, { "epoch": 0.3168212944554893, "grad_norm": 2.183260679244995, "learning_rate": 3.1975137038339563e-05, "loss": 0.3038, "step": 5737 }, { "epoch": 0.3168765186657831, "grad_norm": 0.018069790676236153, "learning_rate": 3.197227166974496e-05, "loss": 0.0007, "step": 5738 }, { "epoch": 0.3169317428760769, "grad_norm": 2.183148145675659, "learning_rate": 3.196940591812329e-05, "loss": 0.2477, "step": 5739 }, { "epoch": 0.31698696708637064, "grad_norm": 0.10039948672056198, "learning_rate": 3.196653978356626e-05, "loss": 0.0029, "step": 5740 }, { "epoch": 0.31704219129666444, "grad_norm": 0.42028772830963135, "learning_rate": 3.196367326616555e-05, "loss": 0.0159, "step": 5741 }, { "epoch": 0.31709741550695825, "grad_norm": 0.9665903449058533, "learning_rate": 3.1960806366012874e-05, "loss": 0.0348, "step": 5742 }, { "epoch": 0.31715263971725205, "grad_norm": 6.366614818572998, "learning_rate": 3.1957939083199955e-05, "loss": 0.8683, "step": 5743 }, { "epoch": 0.31720786392754585, "grad_norm": 3.896324872970581, "learning_rate": 3.195507141781851e-05, "loss": 0.6404, "step": 5744 }, { "epoch": 0.31726308813783966, "grad_norm": 0.856429934501648, "learning_rate": 3.1952203369960305e-05, "loss": 0.0208, "step": 5745 }, { "epoch": 0.3173183123481334, "grad_norm": 1.711230754852295, "learning_rate": 3.194933493971709e-05, "loss": 0.1475, "step": 5746 }, { "epoch": 0.3173735365584272, "grad_norm": 0.42116719484329224, "learning_rate": 3.194646612718063e-05, "loss": 0.0133, "step": 5747 }, { "epoch": 0.317428760768721, "grad_norm": 0.304411917924881, "learning_rate": 3.1943596932442714e-05, "loss": 0.009, "step": 5748 }, { "epoch": 0.3174839849790148, "grad_norm": 4.579833030700684, "learning_rate": 3.194072735559512e-05, "loss": 1.7222, "step": 5749 }, { "epoch": 0.3175392091893086, "grad_norm": 1.2173668146133423, "learning_rate": 3.193785739672967e-05, "loss": 0.1688, "step": 5750 }, { "epoch": 0.31759443339960236, "grad_norm": 3.9883782863616943, "learning_rate": 3.1934987055938174e-05, "loss": 0.3531, "step": 5751 }, { "epoch": 0.31764965760989616, "grad_norm": 0.5240965485572815, "learning_rate": 3.193211633331247e-05, "loss": 0.0119, "step": 5752 }, { "epoch": 0.31770488182018997, "grad_norm": 1.9331799745559692, "learning_rate": 3.192924522894439e-05, "loss": 0.1456, "step": 5753 }, { "epoch": 0.31776010603048377, "grad_norm": 0.15690937638282776, "learning_rate": 3.192637374292579e-05, "loss": 0.0059, "step": 5754 }, { "epoch": 0.31781533024077757, "grad_norm": 2.473299503326416, "learning_rate": 3.192350187534855e-05, "loss": 0.1149, "step": 5755 }, { "epoch": 0.3178705544510714, "grad_norm": 0.40247735381126404, "learning_rate": 3.192062962630453e-05, "loss": 0.0168, "step": 5756 }, { "epoch": 0.3179257786613651, "grad_norm": 0.6744105815887451, "learning_rate": 3.191775699588564e-05, "loss": 0.0175, "step": 5757 }, { "epoch": 0.3179810028716589, "grad_norm": 0.635242760181427, "learning_rate": 3.191488398418377e-05, "loss": 0.0259, "step": 5758 }, { "epoch": 0.3180362270819527, "grad_norm": 0.18464992940425873, "learning_rate": 3.191201059129085e-05, "loss": 0.0066, "step": 5759 }, { "epoch": 0.31809145129224653, "grad_norm": 1.8731200695037842, "learning_rate": 3.190913681729879e-05, "loss": 0.0656, "step": 5760 }, { "epoch": 0.31814667550254033, "grad_norm": 2.242128610610962, "learning_rate": 3.190626266229954e-05, "loss": 0.2896, "step": 5761 }, { "epoch": 0.3182018997128341, "grad_norm": 0.054086390882730484, "learning_rate": 3.190338812638506e-05, "loss": 0.0017, "step": 5762 }, { "epoch": 0.3182571239231279, "grad_norm": 2.808933973312378, "learning_rate": 3.1900513209647295e-05, "loss": 0.1171, "step": 5763 }, { "epoch": 0.3183123481334217, "grad_norm": 2.027923345565796, "learning_rate": 3.189763791217824e-05, "loss": 0.2158, "step": 5764 }, { "epoch": 0.3183675723437155, "grad_norm": 0.22430559992790222, "learning_rate": 3.189476223406988e-05, "loss": 0.0044, "step": 5765 }, { "epoch": 0.3184227965540093, "grad_norm": 4.878063678741455, "learning_rate": 3.189188617541421e-05, "loss": 1.2253, "step": 5766 }, { "epoch": 0.3184780207643031, "grad_norm": 2.714534282684326, "learning_rate": 3.188900973630325e-05, "loss": 0.436, "step": 5767 }, { "epoch": 0.31853324497459684, "grad_norm": 1.4857321977615356, "learning_rate": 3.188613291682901e-05, "loss": 0.0714, "step": 5768 }, { "epoch": 0.31858846918489064, "grad_norm": 3.446110963821411, "learning_rate": 3.188325571708355e-05, "loss": 0.8538, "step": 5769 }, { "epoch": 0.31864369339518445, "grad_norm": 2.736105442047119, "learning_rate": 3.188037813715891e-05, "loss": 0.3118, "step": 5770 }, { "epoch": 0.31869891760547825, "grad_norm": 2.7240500450134277, "learning_rate": 3.187750017714715e-05, "loss": 0.2287, "step": 5771 }, { "epoch": 0.31875414181577205, "grad_norm": 0.5345973968505859, "learning_rate": 3.187462183714033e-05, "loss": 0.0154, "step": 5772 }, { "epoch": 0.31880936602606585, "grad_norm": 0.8268933296203613, "learning_rate": 3.187174311723058e-05, "loss": 0.0165, "step": 5773 }, { "epoch": 0.3188645902363596, "grad_norm": 4.091949462890625, "learning_rate": 3.186886401750995e-05, "loss": 0.0403, "step": 5774 }, { "epoch": 0.3189198144466534, "grad_norm": 2.7265713214874268, "learning_rate": 3.186598453807058e-05, "loss": 0.267, "step": 5775 }, { "epoch": 0.3189750386569472, "grad_norm": 1.1162760257720947, "learning_rate": 3.1863104679004576e-05, "loss": 0.0386, "step": 5776 }, { "epoch": 0.319030262867241, "grad_norm": 0.5581704378128052, "learning_rate": 3.186022444040409e-05, "loss": 0.0243, "step": 5777 }, { "epoch": 0.3190854870775348, "grad_norm": 1.5792851448059082, "learning_rate": 3.185734382236126e-05, "loss": 0.3843, "step": 5778 }, { "epoch": 0.31914071128782856, "grad_norm": 2.12559175491333, "learning_rate": 3.1854462824968234e-05, "loss": 0.2061, "step": 5779 }, { "epoch": 0.31919593549812236, "grad_norm": 0.10387752205133438, "learning_rate": 3.18515814483172e-05, "loss": 0.0032, "step": 5780 }, { "epoch": 0.31925115970841617, "grad_norm": 1.2013055086135864, "learning_rate": 3.184869969250034e-05, "loss": 0.132, "step": 5781 }, { "epoch": 0.31930638391870997, "grad_norm": 1.884423017501831, "learning_rate": 3.184581755760983e-05, "loss": 0.0372, "step": 5782 }, { "epoch": 0.31936160812900377, "grad_norm": 0.19483432173728943, "learning_rate": 3.184293504373791e-05, "loss": 0.0041, "step": 5783 }, { "epoch": 0.3194168323392976, "grad_norm": 1.5840202569961548, "learning_rate": 3.1840052150976774e-05, "loss": 0.0851, "step": 5784 }, { "epoch": 0.3194720565495913, "grad_norm": 1.170795202255249, "learning_rate": 3.183716887941866e-05, "loss": 0.0323, "step": 5785 }, { "epoch": 0.3195272807598851, "grad_norm": 2.202683448791504, "learning_rate": 3.1834285229155826e-05, "loss": 0.4046, "step": 5786 }, { "epoch": 0.3195825049701789, "grad_norm": 4.596459865570068, "learning_rate": 3.1831401200280504e-05, "loss": 1.2866, "step": 5787 }, { "epoch": 0.31963772918047273, "grad_norm": 3.113081216812134, "learning_rate": 3.182851679288499e-05, "loss": 0.5821, "step": 5788 }, { "epoch": 0.31969295339076653, "grad_norm": 0.5430782437324524, "learning_rate": 3.182563200706154e-05, "loss": 0.0201, "step": 5789 }, { "epoch": 0.3197481776010603, "grad_norm": 1.7572888135910034, "learning_rate": 3.182274684290246e-05, "loss": 0.0684, "step": 5790 }, { "epoch": 0.3198034018113541, "grad_norm": 2.273357391357422, "learning_rate": 3.181986130050004e-05, "loss": 0.6322, "step": 5791 }, { "epoch": 0.3198586260216479, "grad_norm": 0.881747841835022, "learning_rate": 3.181697537994661e-05, "loss": 0.0228, "step": 5792 }, { "epoch": 0.3199138502319417, "grad_norm": 2.84985613822937, "learning_rate": 3.181408908133451e-05, "loss": 0.6133, "step": 5793 }, { "epoch": 0.3199690744422355, "grad_norm": 0.066128671169281, "learning_rate": 3.181120240475605e-05, "loss": 0.0021, "step": 5794 }, { "epoch": 0.3200242986525293, "grad_norm": 0.07354667037725449, "learning_rate": 3.1808315350303614e-05, "loss": 0.0033, "step": 5795 }, { "epoch": 0.32007952286282304, "grad_norm": 0.05411577969789505, "learning_rate": 3.180542791806955e-05, "loss": 0.0016, "step": 5796 }, { "epoch": 0.32013474707311684, "grad_norm": 2.6764066219329834, "learning_rate": 3.180254010814623e-05, "loss": 0.3315, "step": 5797 }, { "epoch": 0.32018997128341065, "grad_norm": 0.07280174642801285, "learning_rate": 3.1799651920626055e-05, "loss": 0.0025, "step": 5798 }, { "epoch": 0.32024519549370445, "grad_norm": 2.1177709102630615, "learning_rate": 3.1796763355601425e-05, "loss": 0.3834, "step": 5799 }, { "epoch": 0.32030041970399825, "grad_norm": 0.08990193903446198, "learning_rate": 3.179387441316475e-05, "loss": 0.0028, "step": 5800 }, { "epoch": 0.320355643914292, "grad_norm": 2.9927961826324463, "learning_rate": 3.179098509340846e-05, "loss": 0.2931, "step": 5801 }, { "epoch": 0.3204108681245858, "grad_norm": 0.062408484518527985, "learning_rate": 3.178809539642499e-05, "loss": 0.0031, "step": 5802 }, { "epoch": 0.3204660923348796, "grad_norm": 2.8503308296203613, "learning_rate": 3.1785205322306786e-05, "loss": 0.2434, "step": 5803 }, { "epoch": 0.3205213165451734, "grad_norm": 0.03769515082240105, "learning_rate": 3.1782314871146316e-05, "loss": 0.0016, "step": 5804 }, { "epoch": 0.3205765407554672, "grad_norm": 0.6637055277824402, "learning_rate": 3.1779424043036045e-05, "loss": 0.0154, "step": 5805 }, { "epoch": 0.320631764965761, "grad_norm": 0.2622688412666321, "learning_rate": 3.177653283806847e-05, "loss": 0.0064, "step": 5806 }, { "epoch": 0.32068698917605476, "grad_norm": 2.0684726238250732, "learning_rate": 3.177364125633608e-05, "loss": 0.176, "step": 5807 }, { "epoch": 0.32074221338634856, "grad_norm": 0.36911824345588684, "learning_rate": 3.177074929793139e-05, "loss": 0.0133, "step": 5808 }, { "epoch": 0.32079743759664237, "grad_norm": 1.8072923421859741, "learning_rate": 3.176785696294692e-05, "loss": 0.6372, "step": 5809 }, { "epoch": 0.32085266180693617, "grad_norm": 0.6548129916191101, "learning_rate": 3.1764964251475205e-05, "loss": 0.0252, "step": 5810 }, { "epoch": 0.32090788601722997, "grad_norm": 2.415879249572754, "learning_rate": 3.1762071163608784e-05, "loss": 0.202, "step": 5811 }, { "epoch": 0.3209631102275238, "grad_norm": 0.84562748670578, "learning_rate": 3.1759177699440224e-05, "loss": 0.0379, "step": 5812 }, { "epoch": 0.3210183344378175, "grad_norm": 2.4120631217956543, "learning_rate": 3.1756283859062095e-05, "loss": 0.0821, "step": 5813 }, { "epoch": 0.3210735586481113, "grad_norm": 0.11473345756530762, "learning_rate": 3.1753389642566976e-05, "loss": 0.0044, "step": 5814 }, { "epoch": 0.3211287828584051, "grad_norm": 3.0452418327331543, "learning_rate": 3.1750495050047463e-05, "loss": 0.4014, "step": 5815 }, { "epoch": 0.32118400706869893, "grad_norm": 0.04832223802804947, "learning_rate": 3.1747600081596155e-05, "loss": 0.0018, "step": 5816 }, { "epoch": 0.32123923127899273, "grad_norm": 3.110933542251587, "learning_rate": 3.174470473730568e-05, "loss": 0.3599, "step": 5817 }, { "epoch": 0.3212944554892865, "grad_norm": 0.07569359987974167, "learning_rate": 3.174180901726867e-05, "loss": 0.0021, "step": 5818 }, { "epoch": 0.3213496796995803, "grad_norm": 3.3001601696014404, "learning_rate": 3.173891292157776e-05, "loss": 0.2487, "step": 5819 }, { "epoch": 0.3214049039098741, "grad_norm": 0.13394653797149658, "learning_rate": 3.1736016450325594e-05, "loss": 0.0052, "step": 5820 }, { "epoch": 0.3214601281201679, "grad_norm": 0.2854173481464386, "learning_rate": 3.173311960360487e-05, "loss": 0.0084, "step": 5821 }, { "epoch": 0.3215153523304617, "grad_norm": 1.6707639694213867, "learning_rate": 3.173022238150824e-05, "loss": 0.0618, "step": 5822 }, { "epoch": 0.3215705765407555, "grad_norm": 0.21366438269615173, "learning_rate": 3.17273247841284e-05, "loss": 0.005, "step": 5823 }, { "epoch": 0.32162580075104924, "grad_norm": 0.19208481907844543, "learning_rate": 3.172442681155805e-05, "loss": 0.0057, "step": 5824 }, { "epoch": 0.32168102496134304, "grad_norm": 3.460029363632202, "learning_rate": 3.1721528463889914e-05, "loss": 0.2305, "step": 5825 }, { "epoch": 0.32173624917163685, "grad_norm": 0.02632022649049759, "learning_rate": 3.171862974121671e-05, "loss": 0.0008, "step": 5826 }, { "epoch": 0.32179147338193065, "grad_norm": 3.4542367458343506, "learning_rate": 3.171573064363118e-05, "loss": 0.5986, "step": 5827 }, { "epoch": 0.32184669759222445, "grad_norm": 1.5224449634552002, "learning_rate": 3.1712831171226074e-05, "loss": 0.0418, "step": 5828 }, { "epoch": 0.3219019218025182, "grad_norm": 3.6127614974975586, "learning_rate": 3.1709931324094156e-05, "loss": 0.3195, "step": 5829 }, { "epoch": 0.321957146012812, "grad_norm": 3.040900230407715, "learning_rate": 3.170703110232819e-05, "loss": 0.1454, "step": 5830 }, { "epoch": 0.3220123702231058, "grad_norm": 3.1114723682403564, "learning_rate": 3.1704130506020975e-05, "loss": 0.3076, "step": 5831 }, { "epoch": 0.3220675944333996, "grad_norm": 3.269481897354126, "learning_rate": 3.170122953526531e-05, "loss": 0.3946, "step": 5832 }, { "epoch": 0.3221228186436934, "grad_norm": 0.34939590096473694, "learning_rate": 3.1698328190153995e-05, "loss": 0.0128, "step": 5833 }, { "epoch": 0.3221780428539872, "grad_norm": 0.02146250568330288, "learning_rate": 3.169542647077986e-05, "loss": 0.0007, "step": 5834 }, { "epoch": 0.32223326706428096, "grad_norm": 2.911763906478882, "learning_rate": 3.169252437723573e-05, "loss": 1.1013, "step": 5835 }, { "epoch": 0.32228849127457476, "grad_norm": 3.4693872928619385, "learning_rate": 3.168962190961447e-05, "loss": 0.9489, "step": 5836 }, { "epoch": 0.32234371548486856, "grad_norm": 4.81598424911499, "learning_rate": 3.168671906800892e-05, "loss": 0.3101, "step": 5837 }, { "epoch": 0.32239893969516237, "grad_norm": 0.02256278693675995, "learning_rate": 3.1683815852511954e-05, "loss": 0.0006, "step": 5838 }, { "epoch": 0.32245416390545617, "grad_norm": 0.036101941019296646, "learning_rate": 3.168091226321646e-05, "loss": 0.0009, "step": 5839 }, { "epoch": 0.3225093881157499, "grad_norm": 0.08974217623472214, "learning_rate": 3.167800830021533e-05, "loss": 0.0019, "step": 5840 }, { "epoch": 0.3225646123260437, "grad_norm": 2.3382837772369385, "learning_rate": 3.1675103963601465e-05, "loss": 0.2015, "step": 5841 }, { "epoch": 0.3226198365363375, "grad_norm": 2.7837929725646973, "learning_rate": 3.167219925346779e-05, "loss": 0.1208, "step": 5842 }, { "epoch": 0.3226750607466313, "grad_norm": 2.9742610454559326, "learning_rate": 3.166929416990723e-05, "loss": 0.9114, "step": 5843 }, { "epoch": 0.32273028495692513, "grad_norm": 3.0068626403808594, "learning_rate": 3.1666388713012724e-05, "loss": 0.7405, "step": 5844 }, { "epoch": 0.32278550916721893, "grad_norm": 2.108076810836792, "learning_rate": 3.166348288287724e-05, "loss": 0.313, "step": 5845 }, { "epoch": 0.3228407333775127, "grad_norm": 3.027161121368408, "learning_rate": 3.1660576679593725e-05, "loss": 0.214, "step": 5846 }, { "epoch": 0.3228959575878065, "grad_norm": 2.9786386489868164, "learning_rate": 3.165767010325517e-05, "loss": 0.1273, "step": 5847 }, { "epoch": 0.3229511817981003, "grad_norm": 2.771282911300659, "learning_rate": 3.165476315395456e-05, "loss": 0.2688, "step": 5848 }, { "epoch": 0.3230064060083941, "grad_norm": 0.4569779932498932, "learning_rate": 3.1651855831784895e-05, "loss": 0.0115, "step": 5849 }, { "epoch": 0.3230616302186879, "grad_norm": 1.8881524801254272, "learning_rate": 3.164894813683919e-05, "loss": 0.0277, "step": 5850 }, { "epoch": 0.3231168544289817, "grad_norm": 2.6504743099212646, "learning_rate": 3.164604006921048e-05, "loss": 0.2258, "step": 5851 }, { "epoch": 0.32317207863927544, "grad_norm": 1.7313228845596313, "learning_rate": 3.1643131628991786e-05, "loss": 0.1025, "step": 5852 }, { "epoch": 0.32322730284956924, "grad_norm": 0.25883743166923523, "learning_rate": 3.164022281627616e-05, "loss": 0.0122, "step": 5853 }, { "epoch": 0.32328252705986305, "grad_norm": 1.050658106803894, "learning_rate": 3.163731363115668e-05, "loss": 0.0864, "step": 5854 }, { "epoch": 0.32333775127015685, "grad_norm": 0.07280947268009186, "learning_rate": 3.163440407372639e-05, "loss": 0.0026, "step": 5855 }, { "epoch": 0.32339297548045065, "grad_norm": 2.1413276195526123, "learning_rate": 3.163149414407841e-05, "loss": 0.2522, "step": 5856 }, { "epoch": 0.3234481996907444, "grad_norm": 0.5936740636825562, "learning_rate": 3.162858384230581e-05, "loss": 0.0182, "step": 5857 }, { "epoch": 0.3235034239010382, "grad_norm": 1.0868282318115234, "learning_rate": 3.162567316850171e-05, "loss": 0.0343, "step": 5858 }, { "epoch": 0.323558648111332, "grad_norm": 3.361773729324341, "learning_rate": 3.1622762122759226e-05, "loss": 0.4044, "step": 5859 }, { "epoch": 0.3236138723216258, "grad_norm": 2.5735414028167725, "learning_rate": 3.161985070517149e-05, "loss": 0.3637, "step": 5860 }, { "epoch": 0.3236690965319196, "grad_norm": 0.6702289581298828, "learning_rate": 3.1616938915831656e-05, "loss": 0.0846, "step": 5861 }, { "epoch": 0.3237243207422134, "grad_norm": 0.08615007996559143, "learning_rate": 3.161402675483288e-05, "loss": 0.003, "step": 5862 }, { "epoch": 0.32377954495250716, "grad_norm": 0.5348883271217346, "learning_rate": 3.1611114222268314e-05, "loss": 0.009, "step": 5863 }, { "epoch": 0.32383476916280096, "grad_norm": 1.4842493534088135, "learning_rate": 3.160820131823115e-05, "loss": 0.0632, "step": 5864 }, { "epoch": 0.32388999337309476, "grad_norm": 0.7911704778671265, "learning_rate": 3.160528804281458e-05, "loss": 0.0229, "step": 5865 }, { "epoch": 0.32394521758338857, "grad_norm": 0.15217192471027374, "learning_rate": 3.160237439611181e-05, "loss": 0.0033, "step": 5866 }, { "epoch": 0.32400044179368237, "grad_norm": 4.103496551513672, "learning_rate": 3.1599460378216046e-05, "loss": 1.2018, "step": 5867 }, { "epoch": 0.3240556660039761, "grad_norm": 5.764361381530762, "learning_rate": 3.159654598922053e-05, "loss": 0.2084, "step": 5868 }, { "epoch": 0.3241108902142699, "grad_norm": 0.013898792676627636, "learning_rate": 3.1593631229218486e-05, "loss": 0.0006, "step": 5869 }, { "epoch": 0.3241661144245637, "grad_norm": 3.107074737548828, "learning_rate": 3.159071609830318e-05, "loss": 0.4757, "step": 5870 }, { "epoch": 0.3242213386348575, "grad_norm": 3.080505132675171, "learning_rate": 3.158780059656787e-05, "loss": 0.8417, "step": 5871 }, { "epoch": 0.32427656284515133, "grad_norm": 0.9355429410934448, "learning_rate": 3.158488472410582e-05, "loss": 0.0166, "step": 5872 }, { "epoch": 0.32433178705544513, "grad_norm": 0.7314025163650513, "learning_rate": 3.1581968481010335e-05, "loss": 0.0268, "step": 5873 }, { "epoch": 0.3243870112657389, "grad_norm": 1.341086506843567, "learning_rate": 3.1579051867374704e-05, "loss": 0.1076, "step": 5874 }, { "epoch": 0.3244422354760327, "grad_norm": 3.1044163703918457, "learning_rate": 3.157613488329224e-05, "loss": 0.6805, "step": 5875 }, { "epoch": 0.3244974596863265, "grad_norm": 1.0154011249542236, "learning_rate": 3.157321752885627e-05, "loss": 0.0443, "step": 5876 }, { "epoch": 0.3245526838966203, "grad_norm": 1.6770551204681396, "learning_rate": 3.157029980416011e-05, "loss": 0.0832, "step": 5877 }, { "epoch": 0.3246079081069141, "grad_norm": 0.02294168621301651, "learning_rate": 3.156738170929713e-05, "loss": 0.0012, "step": 5878 }, { "epoch": 0.32466313231720784, "grad_norm": 0.5879694223403931, "learning_rate": 3.1564463244360675e-05, "loss": 0.0189, "step": 5879 }, { "epoch": 0.32471835652750164, "grad_norm": 0.03015780821442604, "learning_rate": 3.1561544409444125e-05, "loss": 0.001, "step": 5880 }, { "epoch": 0.32477358073779544, "grad_norm": 4.314718723297119, "learning_rate": 3.155862520464085e-05, "loss": 0.0743, "step": 5881 }, { "epoch": 0.32482880494808924, "grad_norm": 0.33597198128700256, "learning_rate": 3.155570563004425e-05, "loss": 0.0098, "step": 5882 }, { "epoch": 0.32488402915838305, "grad_norm": 1.2749364376068115, "learning_rate": 3.155278568574772e-05, "loss": 0.1514, "step": 5883 }, { "epoch": 0.32493925336867685, "grad_norm": 1.0806628465652466, "learning_rate": 3.15498653718447e-05, "loss": 0.0995, "step": 5884 }, { "epoch": 0.3249944775789706, "grad_norm": 0.14046454429626465, "learning_rate": 3.15469446884286e-05, "loss": 0.0039, "step": 5885 }, { "epoch": 0.3250497017892644, "grad_norm": 0.07971902936697006, "learning_rate": 3.1544023635592874e-05, "loss": 0.0025, "step": 5886 }, { "epoch": 0.3251049259995582, "grad_norm": 4.875367641448975, "learning_rate": 3.154110221343095e-05, "loss": 1.0559, "step": 5887 }, { "epoch": 0.325160150209852, "grad_norm": 0.44544103741645813, "learning_rate": 3.153818042203632e-05, "loss": 0.0187, "step": 5888 }, { "epoch": 0.3252153744201458, "grad_norm": 0.0405985452234745, "learning_rate": 3.153525826150246e-05, "loss": 0.0013, "step": 5889 }, { "epoch": 0.3252705986304396, "grad_norm": 0.05486907437443733, "learning_rate": 3.1532335731922835e-05, "loss": 0.0016, "step": 5890 }, { "epoch": 0.32532582284073336, "grad_norm": 0.2686600387096405, "learning_rate": 3.152941283339097e-05, "loss": 0.0039, "step": 5891 }, { "epoch": 0.32538104705102716, "grad_norm": 0.38629817962646484, "learning_rate": 3.152648956600036e-05, "loss": 0.013, "step": 5892 }, { "epoch": 0.32543627126132096, "grad_norm": 2.4652559757232666, "learning_rate": 3.152356592984453e-05, "loss": 0.662, "step": 5893 }, { "epoch": 0.32549149547161477, "grad_norm": 0.21910114586353302, "learning_rate": 3.1520641925017024e-05, "loss": 0.0107, "step": 5894 }, { "epoch": 0.32554671968190857, "grad_norm": 0.43716421723365784, "learning_rate": 3.151771755161139e-05, "loss": 0.0132, "step": 5895 }, { "epoch": 0.3256019438922023, "grad_norm": 0.011525134555995464, "learning_rate": 3.151479280972117e-05, "loss": 0.0004, "step": 5896 }, { "epoch": 0.3256571681024961, "grad_norm": 0.0071121202781796455, "learning_rate": 3.151186769943995e-05, "loss": 0.0002, "step": 5897 }, { "epoch": 0.3257123923127899, "grad_norm": 0.06410399824380875, "learning_rate": 3.150894222086132e-05, "loss": 0.0017, "step": 5898 }, { "epoch": 0.3257676165230837, "grad_norm": 3.1082935333251953, "learning_rate": 3.150601637407886e-05, "loss": 0.6004, "step": 5899 }, { "epoch": 0.32582284073337753, "grad_norm": 1.6120588779449463, "learning_rate": 3.150309015918617e-05, "loss": 0.1738, "step": 5900 }, { "epoch": 0.32587806494367133, "grad_norm": 0.0877910926938057, "learning_rate": 3.1500163576276886e-05, "loss": 0.003, "step": 5901 }, { "epoch": 0.3259332891539651, "grad_norm": 0.24634967744350433, "learning_rate": 3.149723662544463e-05, "loss": 0.0066, "step": 5902 }, { "epoch": 0.3259885133642589, "grad_norm": 2.265554666519165, "learning_rate": 3.149430930678304e-05, "loss": 0.0915, "step": 5903 }, { "epoch": 0.3260437375745527, "grad_norm": 0.06825606524944305, "learning_rate": 3.149138162038577e-05, "loss": 0.0025, "step": 5904 }, { "epoch": 0.3260989617848465, "grad_norm": 0.3718482553958893, "learning_rate": 3.1488453566346496e-05, "loss": 0.0106, "step": 5905 }, { "epoch": 0.3261541859951403, "grad_norm": 2.361182928085327, "learning_rate": 3.148552514475888e-05, "loss": 0.304, "step": 5906 }, { "epoch": 0.32620941020543404, "grad_norm": 2.104454278945923, "learning_rate": 3.148259635571662e-05, "loss": 0.7527, "step": 5907 }, { "epoch": 0.32626463441572784, "grad_norm": 1.6376887559890747, "learning_rate": 3.147966719931341e-05, "loss": 0.0586, "step": 5908 }, { "epoch": 0.32631985862602164, "grad_norm": 4.592957973480225, "learning_rate": 3.147673767564297e-05, "loss": 1.0563, "step": 5909 }, { "epoch": 0.32637508283631544, "grad_norm": 0.5156848430633545, "learning_rate": 3.147380778479902e-05, "loss": 0.0133, "step": 5910 }, { "epoch": 0.32643030704660925, "grad_norm": 0.9056285619735718, "learning_rate": 3.1470877526875284e-05, "loss": 0.0267, "step": 5911 }, { "epoch": 0.32648553125690305, "grad_norm": 0.1819830685853958, "learning_rate": 3.1467946901965524e-05, "loss": 0.0063, "step": 5912 }, { "epoch": 0.3265407554671968, "grad_norm": 6.942424774169922, "learning_rate": 3.1465015910163504e-05, "loss": 0.6895, "step": 5913 }, { "epoch": 0.3265959796774906, "grad_norm": 0.022340035066008568, "learning_rate": 3.1462084551562974e-05, "loss": 0.0008, "step": 5914 }, { "epoch": 0.3266512038877844, "grad_norm": 2.949974775314331, "learning_rate": 3.145915282625773e-05, "loss": 0.7404, "step": 5915 }, { "epoch": 0.3267064280980782, "grad_norm": 3.188469648361206, "learning_rate": 3.145622073434157e-05, "loss": 0.3721, "step": 5916 }, { "epoch": 0.326761652308372, "grad_norm": 0.09397441893815994, "learning_rate": 3.145328827590829e-05, "loss": 0.0036, "step": 5917 }, { "epoch": 0.32681687651866576, "grad_norm": 1.9070030450820923, "learning_rate": 3.145035545105172e-05, "loss": 0.114, "step": 5918 }, { "epoch": 0.32687210072895956, "grad_norm": 0.10972454398870468, "learning_rate": 3.144742225986567e-05, "loss": 0.0036, "step": 5919 }, { "epoch": 0.32692732493925336, "grad_norm": 3.9119858741760254, "learning_rate": 3.1444488702444004e-05, "loss": 0.0739, "step": 5920 }, { "epoch": 0.32698254914954716, "grad_norm": 0.09367921203374863, "learning_rate": 3.144155477888055e-05, "loss": 0.0034, "step": 5921 }, { "epoch": 0.32703777335984097, "grad_norm": 0.37599635124206543, "learning_rate": 3.143862048926919e-05, "loss": 0.0078, "step": 5922 }, { "epoch": 0.32709299757013477, "grad_norm": 4.460604190826416, "learning_rate": 3.14356858337038e-05, "loss": 0.4972, "step": 5923 }, { "epoch": 0.3271482217804285, "grad_norm": 3.8186705112457275, "learning_rate": 3.143275081227826e-05, "loss": 0.2612, "step": 5924 }, { "epoch": 0.3272034459907223, "grad_norm": 5.520651817321777, "learning_rate": 3.1429815425086476e-05, "loss": 0.1449, "step": 5925 }, { "epoch": 0.3272586702010161, "grad_norm": 5.6748199462890625, "learning_rate": 3.142687967222236e-05, "loss": 0.8287, "step": 5926 }, { "epoch": 0.3273138944113099, "grad_norm": 1.8831076622009277, "learning_rate": 3.1423943553779834e-05, "loss": 0.1915, "step": 5927 }, { "epoch": 0.3273691186216037, "grad_norm": 0.17855966091156006, "learning_rate": 3.142100706985283e-05, "loss": 0.0044, "step": 5928 }, { "epoch": 0.32742434283189753, "grad_norm": 0.016592014580965042, "learning_rate": 3.1418070220535295e-05, "loss": 0.0007, "step": 5929 }, { "epoch": 0.3274795670421913, "grad_norm": 4.597743034362793, "learning_rate": 3.141513300592118e-05, "loss": 0.5164, "step": 5930 }, { "epoch": 0.3275347912524851, "grad_norm": 2.191317319869995, "learning_rate": 3.141219542610447e-05, "loss": 0.4827, "step": 5931 }, { "epoch": 0.3275900154627789, "grad_norm": 0.4519445300102234, "learning_rate": 3.140925748117914e-05, "loss": 0.0177, "step": 5932 }, { "epoch": 0.3276452396730727, "grad_norm": 0.2657378613948822, "learning_rate": 3.1406319171239186e-05, "loss": 0.0089, "step": 5933 }, { "epoch": 0.3277004638833665, "grad_norm": 0.0055417027324438095, "learning_rate": 3.1403380496378604e-05, "loss": 0.0002, "step": 5934 }, { "epoch": 0.32775568809366024, "grad_norm": 2.5250983238220215, "learning_rate": 3.140044145669142e-05, "loss": 0.3305, "step": 5935 }, { "epoch": 0.32781091230395404, "grad_norm": 3.2413971424102783, "learning_rate": 3.139750205227165e-05, "loss": 0.3649, "step": 5936 }, { "epoch": 0.32786613651424784, "grad_norm": 2.502385139465332, "learning_rate": 3.139456228321335e-05, "loss": 0.032, "step": 5937 }, { "epoch": 0.32792136072454164, "grad_norm": 0.8513694405555725, "learning_rate": 3.1391622149610555e-05, "loss": 0.1335, "step": 5938 }, { "epoch": 0.32797658493483545, "grad_norm": 2.1930384635925293, "learning_rate": 3.138868165155734e-05, "loss": 0.2577, "step": 5939 }, { "epoch": 0.32803180914512925, "grad_norm": 0.006940440274775028, "learning_rate": 3.1385740789147776e-05, "loss": 0.0003, "step": 5940 }, { "epoch": 0.328087033355423, "grad_norm": 0.06649547815322876, "learning_rate": 3.138279956247596e-05, "loss": 0.002, "step": 5941 }, { "epoch": 0.3281422575657168, "grad_norm": 0.07828329503536224, "learning_rate": 3.137985797163597e-05, "loss": 0.0026, "step": 5942 }, { "epoch": 0.3281974817760106, "grad_norm": 1.2284400463104248, "learning_rate": 3.137691601672193e-05, "loss": 0.194, "step": 5943 }, { "epoch": 0.3282527059863044, "grad_norm": 1.015768051147461, "learning_rate": 3.137397369782796e-05, "loss": 0.0192, "step": 5944 }, { "epoch": 0.3283079301965982, "grad_norm": 0.1143888607621193, "learning_rate": 3.137103101504819e-05, "loss": 0.0046, "step": 5945 }, { "epoch": 0.32836315440689195, "grad_norm": 3.3457396030426025, "learning_rate": 3.1368087968476763e-05, "loss": 0.7994, "step": 5946 }, { "epoch": 0.32841837861718576, "grad_norm": 0.3541428744792938, "learning_rate": 3.136514455820784e-05, "loss": 0.012, "step": 5947 }, { "epoch": 0.32847360282747956, "grad_norm": 0.7233228087425232, "learning_rate": 3.1362200784335585e-05, "loss": 0.0205, "step": 5948 }, { "epoch": 0.32852882703777336, "grad_norm": 1.2748993635177612, "learning_rate": 3.1359256646954186e-05, "loss": 0.0661, "step": 5949 }, { "epoch": 0.32858405124806717, "grad_norm": 0.0257211085408926, "learning_rate": 3.135631214615782e-05, "loss": 0.0011, "step": 5950 }, { "epoch": 0.32863927545836097, "grad_norm": 2.03513765335083, "learning_rate": 3.1353367282040714e-05, "loss": 0.1589, "step": 5951 }, { "epoch": 0.3286944996686547, "grad_norm": 2.7533156871795654, "learning_rate": 3.1350422054697055e-05, "loss": 0.6848, "step": 5952 }, { "epoch": 0.3287497238789485, "grad_norm": 2.515615463256836, "learning_rate": 3.134747646422108e-05, "loss": 0.1322, "step": 5953 }, { "epoch": 0.3288049480892423, "grad_norm": 0.18095898628234863, "learning_rate": 3.134453051070703e-05, "loss": 0.0065, "step": 5954 }, { "epoch": 0.3288601722995361, "grad_norm": 0.03975692763924599, "learning_rate": 3.134158419424916e-05, "loss": 0.0013, "step": 5955 }, { "epoch": 0.3289153965098299, "grad_norm": 2.6364424228668213, "learning_rate": 3.133863751494171e-05, "loss": 0.2279, "step": 5956 }, { "epoch": 0.32897062072012373, "grad_norm": 0.0437919944524765, "learning_rate": 3.133569047287898e-05, "loss": 0.0012, "step": 5957 }, { "epoch": 0.3290258449304175, "grad_norm": 2.9609575271606445, "learning_rate": 3.1332743068155236e-05, "loss": 0.3693, "step": 5958 }, { "epoch": 0.3290810691407113, "grad_norm": 6.364819526672363, "learning_rate": 3.1329795300864774e-05, "loss": 1.1843, "step": 5959 }, { "epoch": 0.3291362933510051, "grad_norm": 0.48595550656318665, "learning_rate": 3.132684717110191e-05, "loss": 0.0112, "step": 5960 }, { "epoch": 0.3291915175612989, "grad_norm": 0.8179962635040283, "learning_rate": 3.132389867896096e-05, "loss": 0.0247, "step": 5961 }, { "epoch": 0.3292467417715927, "grad_norm": 7.7725653648376465, "learning_rate": 3.132094982453625e-05, "loss": 0.3629, "step": 5962 }, { "epoch": 0.32930196598188644, "grad_norm": 3.619891405105591, "learning_rate": 3.131800060792213e-05, "loss": 0.6412, "step": 5963 }, { "epoch": 0.32935719019218024, "grad_norm": 0.17762130498886108, "learning_rate": 3.131505102921294e-05, "loss": 0.0053, "step": 5964 }, { "epoch": 0.32941241440247404, "grad_norm": 5.862761497497559, "learning_rate": 3.131210108850306e-05, "loss": 0.6389, "step": 5965 }, { "epoch": 0.32946763861276784, "grad_norm": 2.116288423538208, "learning_rate": 3.130915078588687e-05, "loss": 0.3116, "step": 5966 }, { "epoch": 0.32952286282306165, "grad_norm": 2.983186960220337, "learning_rate": 3.130620012145874e-05, "loss": 0.8997, "step": 5967 }, { "epoch": 0.32957808703335545, "grad_norm": 1.6770228147506714, "learning_rate": 3.130324909531308e-05, "loss": 0.0443, "step": 5968 }, { "epoch": 0.3296333112436492, "grad_norm": 0.15673214197158813, "learning_rate": 3.1300297707544315e-05, "loss": 0.0045, "step": 5969 }, { "epoch": 0.329688535453943, "grad_norm": 5.528833389282227, "learning_rate": 3.129734595824685e-05, "loss": 1.5648, "step": 5970 }, { "epoch": 0.3297437596642368, "grad_norm": 5.14431619644165, "learning_rate": 3.1294393847515116e-05, "loss": 0.8423, "step": 5971 }, { "epoch": 0.3297989838745306, "grad_norm": 1.178220272064209, "learning_rate": 3.129144137544358e-05, "loss": 0.0311, "step": 5972 }, { "epoch": 0.3298542080848244, "grad_norm": 1.4073622226715088, "learning_rate": 3.1288488542126684e-05, "loss": 0.0755, "step": 5973 }, { "epoch": 0.32990943229511815, "grad_norm": 4.575790882110596, "learning_rate": 3.1285535347658906e-05, "loss": 0.4628, "step": 5974 }, { "epoch": 0.32996465650541196, "grad_norm": 0.11193545907735825, "learning_rate": 3.128258179213473e-05, "loss": 0.0033, "step": 5975 }, { "epoch": 0.33001988071570576, "grad_norm": 4.310881614685059, "learning_rate": 3.1279627875648626e-05, "loss": 0.6638, "step": 5976 }, { "epoch": 0.33007510492599956, "grad_norm": 1.055063009262085, "learning_rate": 3.127667359829513e-05, "loss": 0.0527, "step": 5977 }, { "epoch": 0.33013032913629337, "grad_norm": 4.109349250793457, "learning_rate": 3.1273718960168733e-05, "loss": 1.1502, "step": 5978 }, { "epoch": 0.33018555334658717, "grad_norm": 1.2807011604309082, "learning_rate": 3.1270763961363975e-05, "loss": 0.08, "step": 5979 }, { "epoch": 0.3302407775568809, "grad_norm": 0.5867488980293274, "learning_rate": 3.1267808601975386e-05, "loss": 0.0184, "step": 5980 }, { "epoch": 0.3302960017671747, "grad_norm": 1.2017472982406616, "learning_rate": 3.126485288209753e-05, "loss": 0.0786, "step": 5981 }, { "epoch": 0.3303512259774685, "grad_norm": 1.9953687191009521, "learning_rate": 3.126189680182496e-05, "loss": 0.161, "step": 5982 }, { "epoch": 0.3304064501877623, "grad_norm": 2.0853333473205566, "learning_rate": 3.125894036125224e-05, "loss": 0.5805, "step": 5983 }, { "epoch": 0.3304616743980561, "grad_norm": 5.101663112640381, "learning_rate": 3.125598356047398e-05, "loss": 1.5232, "step": 5984 }, { "epoch": 0.3305168986083499, "grad_norm": 1.6742581129074097, "learning_rate": 3.1253026399584755e-05, "loss": 0.2214, "step": 5985 }, { "epoch": 0.3305721228186437, "grad_norm": 0.03006325103342533, "learning_rate": 3.1250068878679176e-05, "loss": 0.0008, "step": 5986 }, { "epoch": 0.3306273470289375, "grad_norm": 3.4021143913269043, "learning_rate": 3.124711099785187e-05, "loss": 1.186, "step": 5987 }, { "epoch": 0.3306825712392313, "grad_norm": 2.2240378856658936, "learning_rate": 3.124415275719746e-05, "loss": 0.2558, "step": 5988 }, { "epoch": 0.3307377954495251, "grad_norm": 0.03368854522705078, "learning_rate": 3.12411941568106e-05, "loss": 0.0013, "step": 5989 }, { "epoch": 0.3307930196598189, "grad_norm": 0.16471080482006073, "learning_rate": 3.123823519678593e-05, "loss": 0.0051, "step": 5990 }, { "epoch": 0.33084824387011263, "grad_norm": 5.450992584228516, "learning_rate": 3.123527587721812e-05, "loss": 0.9145, "step": 5991 }, { "epoch": 0.33090346808040644, "grad_norm": 0.7792221903800964, "learning_rate": 3.123231619820186e-05, "loss": 0.0341, "step": 5992 }, { "epoch": 0.33095869229070024, "grad_norm": 0.8265570998191833, "learning_rate": 3.122935615983182e-05, "loss": 0.0332, "step": 5993 }, { "epoch": 0.33101391650099404, "grad_norm": 4.586453914642334, "learning_rate": 3.122639576220271e-05, "loss": 1.177, "step": 5994 }, { "epoch": 0.33106914071128785, "grad_norm": 1.0347031354904175, "learning_rate": 3.122343500540923e-05, "loss": 0.0233, "step": 5995 }, { "epoch": 0.33112436492158165, "grad_norm": 3.378143072128296, "learning_rate": 3.122047388954613e-05, "loss": 0.3289, "step": 5996 }, { "epoch": 0.3311795891318754, "grad_norm": 0.2488744705915451, "learning_rate": 3.121751241470812e-05, "loss": 0.0054, "step": 5997 }, { "epoch": 0.3312348133421692, "grad_norm": 1.9407302141189575, "learning_rate": 3.121455058098994e-05, "loss": 0.0927, "step": 5998 }, { "epoch": 0.331290037552463, "grad_norm": 3.1605265140533447, "learning_rate": 3.121158838848638e-05, "loss": 0.5561, "step": 5999 }, { "epoch": 0.3313452617627568, "grad_norm": 2.3043441772460938, "learning_rate": 3.1208625837292176e-05, "loss": 0.3756, "step": 6000 }, { "epoch": 0.3314004859730506, "grad_norm": 0.371614545583725, "learning_rate": 3.120566292750213e-05, "loss": 0.0115, "step": 6001 }, { "epoch": 0.33145571018334435, "grad_norm": 0.4530029892921448, "learning_rate": 3.1202699659211024e-05, "loss": 0.0125, "step": 6002 }, { "epoch": 0.33151093439363816, "grad_norm": 0.3682270050048828, "learning_rate": 3.119973603251366e-05, "loss": 0.0138, "step": 6003 }, { "epoch": 0.33156615860393196, "grad_norm": 0.097755566239357, "learning_rate": 3.119677204750486e-05, "loss": 0.0028, "step": 6004 }, { "epoch": 0.33162138281422576, "grad_norm": 1.9506545066833496, "learning_rate": 3.119380770427945e-05, "loss": 0.4469, "step": 6005 }, { "epoch": 0.33167660702451957, "grad_norm": 2.1039211750030518, "learning_rate": 3.119084300293225e-05, "loss": 0.1793, "step": 6006 }, { "epoch": 0.33173183123481337, "grad_norm": 0.03270323574542999, "learning_rate": 3.1187877943558136e-05, "loss": 0.0015, "step": 6007 }, { "epoch": 0.3317870554451071, "grad_norm": 3.8809964656829834, "learning_rate": 3.1184912526251954e-05, "loss": 0.9991, "step": 6008 }, { "epoch": 0.3318422796554009, "grad_norm": 0.20923787355422974, "learning_rate": 3.118194675110857e-05, "loss": 0.0051, "step": 6009 }, { "epoch": 0.3318975038656947, "grad_norm": 4.1424031257629395, "learning_rate": 3.1178980618222886e-05, "loss": 0.5557, "step": 6010 }, { "epoch": 0.3319527280759885, "grad_norm": 1.5678631067276, "learning_rate": 3.117601412768978e-05, "loss": 0.0833, "step": 6011 }, { "epoch": 0.3320079522862823, "grad_norm": 5.442885875701904, "learning_rate": 3.1173047279604176e-05, "loss": 1.2499, "step": 6012 }, { "epoch": 0.3320631764965761, "grad_norm": 0.630527675151825, "learning_rate": 3.117008007406097e-05, "loss": 0.0242, "step": 6013 }, { "epoch": 0.3321184007068699, "grad_norm": 1.3547943830490112, "learning_rate": 3.1167112511155105e-05, "loss": 0.2512, "step": 6014 }, { "epoch": 0.3321736249171637, "grad_norm": 0.9129177927970886, "learning_rate": 3.1164144590981524e-05, "loss": 0.1594, "step": 6015 }, { "epoch": 0.3322288491274575, "grad_norm": 4.606356620788574, "learning_rate": 3.1161176313635175e-05, "loss": 0.4171, "step": 6016 }, { "epoch": 0.3322840733377513, "grad_norm": 4.680988788604736, "learning_rate": 3.1158207679211016e-05, "loss": 0.3391, "step": 6017 }, { "epoch": 0.3323392975480451, "grad_norm": 0.3185402750968933, "learning_rate": 3.115523868780403e-05, "loss": 0.0054, "step": 6018 }, { "epoch": 0.33239452175833883, "grad_norm": 0.059644438326358795, "learning_rate": 3.1152269339509194e-05, "loss": 0.0024, "step": 6019 }, { "epoch": 0.33244974596863264, "grad_norm": 0.7751737833023071, "learning_rate": 3.114929963442152e-05, "loss": 0.0313, "step": 6020 }, { "epoch": 0.33250497017892644, "grad_norm": 0.027786502614617348, "learning_rate": 3.114632957263602e-05, "loss": 0.0012, "step": 6021 }, { "epoch": 0.33256019438922024, "grad_norm": 1.5099992752075195, "learning_rate": 3.1143359154247687e-05, "loss": 0.1303, "step": 6022 }, { "epoch": 0.33261541859951405, "grad_norm": 0.6071376800537109, "learning_rate": 3.114038837935157e-05, "loss": 0.0206, "step": 6023 }, { "epoch": 0.3326706428098078, "grad_norm": 1.5608339309692383, "learning_rate": 3.113741724804273e-05, "loss": 0.0529, "step": 6024 }, { "epoch": 0.3327258670201016, "grad_norm": 3.5018229484558105, "learning_rate": 3.113444576041619e-05, "loss": 1.1537, "step": 6025 }, { "epoch": 0.3327810912303954, "grad_norm": 3.7913832664489746, "learning_rate": 3.1131473916567045e-05, "loss": 0.7352, "step": 6026 }, { "epoch": 0.3328363154406892, "grad_norm": 5.416817665100098, "learning_rate": 3.112850171659035e-05, "loss": 0.8366, "step": 6027 }, { "epoch": 0.332891539650983, "grad_norm": 0.36796334385871887, "learning_rate": 3.11255291605812e-05, "loss": 0.0127, "step": 6028 }, { "epoch": 0.3329467638612768, "grad_norm": 2.110171318054199, "learning_rate": 3.112255624863471e-05, "loss": 0.7259, "step": 6029 }, { "epoch": 0.33300198807157055, "grad_norm": 2.4954121112823486, "learning_rate": 3.1119582980845976e-05, "loss": 0.2272, "step": 6030 }, { "epoch": 0.33305721228186436, "grad_norm": 3.741666316986084, "learning_rate": 3.1116609357310126e-05, "loss": 0.3667, "step": 6031 }, { "epoch": 0.33311243649215816, "grad_norm": 1.2739872932434082, "learning_rate": 3.111363537812229e-05, "loss": 0.0353, "step": 6032 }, { "epoch": 0.33316766070245196, "grad_norm": 1.2648504972457886, "learning_rate": 3.111066104337763e-05, "loss": 0.0703, "step": 6033 }, { "epoch": 0.33322288491274576, "grad_norm": 2.805379867553711, "learning_rate": 3.110768635317129e-05, "loss": 0.8577, "step": 6034 }, { "epoch": 0.33327810912303957, "grad_norm": 0.36235734820365906, "learning_rate": 3.110471130759843e-05, "loss": 0.008, "step": 6035 }, { "epoch": 0.3333333333333333, "grad_norm": 0.04237006604671478, "learning_rate": 3.1101735906754255e-05, "loss": 0.0017, "step": 6036 }, { "epoch": 0.3333885575436271, "grad_norm": 0.4138782322406769, "learning_rate": 3.109876015073394e-05, "loss": 0.0135, "step": 6037 }, { "epoch": 0.3334437817539209, "grad_norm": 3.637040853500366, "learning_rate": 3.109578403963269e-05, "loss": 0.282, "step": 6038 }, { "epoch": 0.3334990059642147, "grad_norm": 3.2736778259277344, "learning_rate": 3.109280757354572e-05, "loss": 0.7333, "step": 6039 }, { "epoch": 0.3335542301745085, "grad_norm": 0.08014152944087982, "learning_rate": 3.108983075256826e-05, "loss": 0.0031, "step": 6040 }, { "epoch": 0.3336094543848023, "grad_norm": 1.8226808309555054, "learning_rate": 3.1086853576795536e-05, "loss": 0.0711, "step": 6041 }, { "epoch": 0.3336646785950961, "grad_norm": 4.047458171844482, "learning_rate": 3.108387604632281e-05, "loss": 0.2487, "step": 6042 }, { "epoch": 0.3337199028053899, "grad_norm": 1.9775429964065552, "learning_rate": 3.108089816124533e-05, "loss": 0.3297, "step": 6043 }, { "epoch": 0.3337751270156837, "grad_norm": 1.597870111465454, "learning_rate": 3.107791992165837e-05, "loss": 0.2157, "step": 6044 }, { "epoch": 0.3338303512259775, "grad_norm": 4.232396125793457, "learning_rate": 3.1074941327657215e-05, "loss": 0.4021, "step": 6045 }, { "epoch": 0.3338855754362713, "grad_norm": 6.096053123474121, "learning_rate": 3.1071962379337166e-05, "loss": 1.5209, "step": 6046 }, { "epoch": 0.33394079964656503, "grad_norm": 3.319592237472534, "learning_rate": 3.106898307679351e-05, "loss": 0.1793, "step": 6047 }, { "epoch": 0.33399602385685884, "grad_norm": 2.370105504989624, "learning_rate": 3.1066003420121584e-05, "loss": 0.0639, "step": 6048 }, { "epoch": 0.33405124806715264, "grad_norm": 6.106571197509766, "learning_rate": 3.1063023409416696e-05, "loss": 0.8895, "step": 6049 }, { "epoch": 0.33410647227744644, "grad_norm": 0.03130955621600151, "learning_rate": 3.10600430447742e-05, "loss": 0.0013, "step": 6050 }, { "epoch": 0.33416169648774025, "grad_norm": 0.633269190788269, "learning_rate": 3.105706232628944e-05, "loss": 0.0288, "step": 6051 }, { "epoch": 0.334216920698034, "grad_norm": 0.037672434002161026, "learning_rate": 3.105408125405777e-05, "loss": 0.001, "step": 6052 }, { "epoch": 0.3342721449083278, "grad_norm": 0.04375237599015236, "learning_rate": 3.1051099828174574e-05, "loss": 0.002, "step": 6053 }, { "epoch": 0.3343273691186216, "grad_norm": 0.6197169423103333, "learning_rate": 3.1048118048735234e-05, "loss": 0.0211, "step": 6054 }, { "epoch": 0.3343825933289154, "grad_norm": 2.864624261856079, "learning_rate": 3.1045135915835144e-05, "loss": 0.6724, "step": 6055 }, { "epoch": 0.3344378175392092, "grad_norm": 3.215435266494751, "learning_rate": 3.104215342956972e-05, "loss": 0.7647, "step": 6056 }, { "epoch": 0.334493041749503, "grad_norm": 1.8418240547180176, "learning_rate": 3.1039170590034366e-05, "loss": 0.0669, "step": 6057 }, { "epoch": 0.33454826595979675, "grad_norm": 2.722935914993286, "learning_rate": 3.103618739732452e-05, "loss": 0.5508, "step": 6058 }, { "epoch": 0.33460349017009056, "grad_norm": 1.4680126905441284, "learning_rate": 3.103320385153562e-05, "loss": 0.2433, "step": 6059 }, { "epoch": 0.33465871438038436, "grad_norm": 3.747652292251587, "learning_rate": 3.1030219952763115e-05, "loss": 1.3204, "step": 6060 }, { "epoch": 0.33471393859067816, "grad_norm": 2.8012733459472656, "learning_rate": 3.1027235701102475e-05, "loss": 0.2247, "step": 6061 }, { "epoch": 0.33476916280097196, "grad_norm": 2.87428879737854, "learning_rate": 3.102425109664917e-05, "loss": 0.7038, "step": 6062 }, { "epoch": 0.3348243870112657, "grad_norm": 0.7625014185905457, "learning_rate": 3.102126613949869e-05, "loss": 0.0156, "step": 6063 }, { "epoch": 0.3348796112215595, "grad_norm": 1.39193856716156, "learning_rate": 3.101828082974653e-05, "loss": 0.0624, "step": 6064 }, { "epoch": 0.3349348354318533, "grad_norm": 0.1327531784772873, "learning_rate": 3.10152951674882e-05, "loss": 0.0039, "step": 6065 }, { "epoch": 0.3349900596421471, "grad_norm": 0.13102397322654724, "learning_rate": 3.101230915281922e-05, "loss": 0.0048, "step": 6066 }, { "epoch": 0.3350452838524409, "grad_norm": 0.5855098962783813, "learning_rate": 3.100932278583511e-05, "loss": 0.0206, "step": 6067 }, { "epoch": 0.3351005080627347, "grad_norm": 2.9999053478240967, "learning_rate": 3.100633606663143e-05, "loss": 0.4802, "step": 6068 }, { "epoch": 0.3351557322730285, "grad_norm": 3.024628162384033, "learning_rate": 3.1003348995303727e-05, "loss": 0.0474, "step": 6069 }, { "epoch": 0.3352109564833223, "grad_norm": 2.1967053413391113, "learning_rate": 3.1000361571947555e-05, "loss": 0.4538, "step": 6070 }, { "epoch": 0.3352661806936161, "grad_norm": 0.1058448925614357, "learning_rate": 3.099737379665851e-05, "loss": 0.0052, "step": 6071 }, { "epoch": 0.3353214049039099, "grad_norm": 0.04497108981013298, "learning_rate": 3.099438566953216e-05, "loss": 0.0016, "step": 6072 }, { "epoch": 0.3353766291142037, "grad_norm": 0.23138286173343658, "learning_rate": 3.099139719066412e-05, "loss": 0.0121, "step": 6073 }, { "epoch": 0.3354318533244975, "grad_norm": 2.901810646057129, "learning_rate": 3.098840836014999e-05, "loss": 0.2686, "step": 6074 }, { "epoch": 0.33548707753479123, "grad_norm": 3.7804250717163086, "learning_rate": 3.09854191780854e-05, "loss": 0.4696, "step": 6075 }, { "epoch": 0.33554230174508504, "grad_norm": 5.325677871704102, "learning_rate": 3.098242964456597e-05, "loss": 0.6013, "step": 6076 }, { "epoch": 0.33559752595537884, "grad_norm": 0.9744748473167419, "learning_rate": 3.097943975968735e-05, "loss": 0.0354, "step": 6077 }, { "epoch": 0.33565275016567264, "grad_norm": 0.07349183410406113, "learning_rate": 3.097644952354519e-05, "loss": 0.0029, "step": 6078 }, { "epoch": 0.33570797437596644, "grad_norm": 0.5900600552558899, "learning_rate": 3.097345893623517e-05, "loss": 0.0176, "step": 6079 }, { "epoch": 0.3357631985862602, "grad_norm": 0.5594265460968018, "learning_rate": 3.097046799785295e-05, "loss": 0.0172, "step": 6080 }, { "epoch": 0.335818422796554, "grad_norm": 2.6354777812957764, "learning_rate": 3.0967476708494236e-05, "loss": 0.3549, "step": 6081 }, { "epoch": 0.3358736470068478, "grad_norm": 4.282042980194092, "learning_rate": 3.096448506825471e-05, "loss": 0.2823, "step": 6082 }, { "epoch": 0.3359288712171416, "grad_norm": 0.6902381777763367, "learning_rate": 3.0961493077230105e-05, "loss": 0.1016, "step": 6083 }, { "epoch": 0.3359840954274354, "grad_norm": 0.2744576036930084, "learning_rate": 3.095850073551612e-05, "loss": 0.0095, "step": 6084 }, { "epoch": 0.3360393196377292, "grad_norm": 2.6695492267608643, "learning_rate": 3.0955508043208506e-05, "loss": 0.1977, "step": 6085 }, { "epoch": 0.33609454384802295, "grad_norm": 0.043983880430459976, "learning_rate": 3.095251500040299e-05, "loss": 0.0019, "step": 6086 }, { "epoch": 0.33614976805831676, "grad_norm": 0.04500700533390045, "learning_rate": 3.094952160719535e-05, "loss": 0.0014, "step": 6087 }, { "epoch": 0.33620499226861056, "grad_norm": 3.4781315326690674, "learning_rate": 3.094652786368134e-05, "loss": 0.3857, "step": 6088 }, { "epoch": 0.33626021647890436, "grad_norm": 2.8658909797668457, "learning_rate": 3.094353376995673e-05, "loss": 0.1957, "step": 6089 }, { "epoch": 0.33631544068919816, "grad_norm": 0.5118517875671387, "learning_rate": 3.0940539326117334e-05, "loss": 0.1235, "step": 6090 }, { "epoch": 0.3363706648994919, "grad_norm": 3.7413337230682373, "learning_rate": 3.093754453225893e-05, "loss": 0.5765, "step": 6091 }, { "epoch": 0.3364258891097857, "grad_norm": 2.43290638923645, "learning_rate": 3.0934549388477344e-05, "loss": 0.3493, "step": 6092 }, { "epoch": 0.3364811133200795, "grad_norm": 2.3933727741241455, "learning_rate": 3.0931553894868386e-05, "loss": 0.7216, "step": 6093 }, { "epoch": 0.3365363375303733, "grad_norm": 0.06137203052639961, "learning_rate": 3.0928558051527913e-05, "loss": 0.0031, "step": 6094 }, { "epoch": 0.3365915617406671, "grad_norm": 3.8793222904205322, "learning_rate": 3.092556185855174e-05, "loss": 1.0873, "step": 6095 }, { "epoch": 0.3366467859509609, "grad_norm": 1.8959583044052124, "learning_rate": 3.092256531603574e-05, "loss": 0.3447, "step": 6096 }, { "epoch": 0.3367020101612547, "grad_norm": 2.7608227729797363, "learning_rate": 3.0919568424075794e-05, "loss": 0.3213, "step": 6097 }, { "epoch": 0.3367572343715485, "grad_norm": 2.194643020629883, "learning_rate": 3.091657118276776e-05, "loss": 0.1208, "step": 6098 }, { "epoch": 0.3368124585818423, "grad_norm": 2.3199217319488525, "learning_rate": 3.091357359220753e-05, "loss": 0.5927, "step": 6099 }, { "epoch": 0.3368676827921361, "grad_norm": 3.4977142810821533, "learning_rate": 3.0910575652491014e-05, "loss": 0.4183, "step": 6100 }, { "epoch": 0.3369229070024299, "grad_norm": 0.040733661502599716, "learning_rate": 3.0907577363714124e-05, "loss": 0.0019, "step": 6101 }, { "epoch": 0.33697813121272363, "grad_norm": 1.6644076108932495, "learning_rate": 3.0904578725972785e-05, "loss": 0.1486, "step": 6102 }, { "epoch": 0.33703335542301743, "grad_norm": 0.9242804050445557, "learning_rate": 3.090157973936292e-05, "loss": 0.0518, "step": 6103 }, { "epoch": 0.33708857963331124, "grad_norm": 6.986702919006348, "learning_rate": 3.0898580403980493e-05, "loss": 0.9922, "step": 6104 }, { "epoch": 0.33714380384360504, "grad_norm": 0.0678783431649208, "learning_rate": 3.0895580719921445e-05, "loss": 0.0028, "step": 6105 }, { "epoch": 0.33719902805389884, "grad_norm": 2.441258668899536, "learning_rate": 3.0892580687281756e-05, "loss": 0.154, "step": 6106 }, { "epoch": 0.33725425226419264, "grad_norm": 0.7281455993652344, "learning_rate": 3.0889580306157404e-05, "loss": 0.0191, "step": 6107 }, { "epoch": 0.3373094764744864, "grad_norm": 2.357259750366211, "learning_rate": 3.0886579576644377e-05, "loss": 0.1446, "step": 6108 }, { "epoch": 0.3373647006847802, "grad_norm": 0.22114326059818268, "learning_rate": 3.088357849883867e-05, "loss": 0.0086, "step": 6109 }, { "epoch": 0.337419924895074, "grad_norm": 2.3605868816375732, "learning_rate": 3.08805770728363e-05, "loss": 0.3089, "step": 6110 }, { "epoch": 0.3374751491053678, "grad_norm": 1.491616129875183, "learning_rate": 3.0877575298733296e-05, "loss": 0.156, "step": 6111 }, { "epoch": 0.3375303733156616, "grad_norm": 0.21311967074871063, "learning_rate": 3.087457317662569e-05, "loss": 0.0062, "step": 6112 }, { "epoch": 0.3375855975259554, "grad_norm": 0.11654835939407349, "learning_rate": 3.0871570706609544e-05, "loss": 0.0037, "step": 6113 }, { "epoch": 0.33764082173624915, "grad_norm": 4.077518463134766, "learning_rate": 3.0868567888780885e-05, "loss": 0.7979, "step": 6114 }, { "epoch": 0.33769604594654296, "grad_norm": 0.08650094270706177, "learning_rate": 3.08655647232358e-05, "loss": 0.0033, "step": 6115 }, { "epoch": 0.33775127015683676, "grad_norm": 0.8298642039299011, "learning_rate": 3.086256121007037e-05, "loss": 0.0259, "step": 6116 }, { "epoch": 0.33780649436713056, "grad_norm": 0.026432722806930542, "learning_rate": 3.085955734938068e-05, "loss": 0.0011, "step": 6117 }, { "epoch": 0.33786171857742436, "grad_norm": 0.26216208934783936, "learning_rate": 3.085655314126284e-05, "loss": 0.0128, "step": 6118 }, { "epoch": 0.3379169427877181, "grad_norm": 4.339805603027344, "learning_rate": 3.085354858581296e-05, "loss": 1.0834, "step": 6119 }, { "epoch": 0.3379721669980119, "grad_norm": 2.714928150177002, "learning_rate": 3.085054368312715e-05, "loss": 0.4074, "step": 6120 }, { "epoch": 0.3380273912083057, "grad_norm": 0.17088042199611664, "learning_rate": 3.0847538433301564e-05, "loss": 0.0056, "step": 6121 }, { "epoch": 0.3380826154185995, "grad_norm": 2.2265262603759766, "learning_rate": 3.0844532836432344e-05, "loss": 0.4236, "step": 6122 }, { "epoch": 0.3381378396288933, "grad_norm": 0.10689754039049149, "learning_rate": 3.084152689261564e-05, "loss": 0.0053, "step": 6123 }, { "epoch": 0.3381930638391871, "grad_norm": 3.125065565109253, "learning_rate": 3.0838520601947624e-05, "loss": 0.2306, "step": 6124 }, { "epoch": 0.33824828804948087, "grad_norm": 2.841970443725586, "learning_rate": 3.083551396452449e-05, "loss": 0.4447, "step": 6125 }, { "epoch": 0.3383035122597747, "grad_norm": 3.7350590229034424, "learning_rate": 3.083250698044241e-05, "loss": 0.2071, "step": 6126 }, { "epoch": 0.3383587364700685, "grad_norm": 1.849521279335022, "learning_rate": 3.082949964979759e-05, "loss": 0.0866, "step": 6127 }, { "epoch": 0.3384139606803623, "grad_norm": 1.215706467628479, "learning_rate": 3.082649197268625e-05, "loss": 0.0418, "step": 6128 }, { "epoch": 0.3384691848906561, "grad_norm": 0.935502827167511, "learning_rate": 3.082348394920461e-05, "loss": 0.0479, "step": 6129 }, { "epoch": 0.33852440910094983, "grad_norm": 1.3597991466522217, "learning_rate": 3.082047557944891e-05, "loss": 0.0591, "step": 6130 }, { "epoch": 0.33857963331124363, "grad_norm": 0.7147231101989746, "learning_rate": 3.081746686351538e-05, "loss": 0.1972, "step": 6131 }, { "epoch": 0.33863485752153744, "grad_norm": 3.8913304805755615, "learning_rate": 3.0814457801500295e-05, "loss": 1.5594, "step": 6132 }, { "epoch": 0.33869008173183124, "grad_norm": 2.0162229537963867, "learning_rate": 3.081144839349992e-05, "loss": 0.1556, "step": 6133 }, { "epoch": 0.33874530594212504, "grad_norm": 1.7061845064163208, "learning_rate": 3.080843863961053e-05, "loss": 0.0577, "step": 6134 }, { "epoch": 0.33880053015241884, "grad_norm": 0.02694041281938553, "learning_rate": 3.080542853992842e-05, "loss": 0.0009, "step": 6135 }, { "epoch": 0.3388557543627126, "grad_norm": 2.1486856937408447, "learning_rate": 3.080241809454989e-05, "loss": 0.2715, "step": 6136 }, { "epoch": 0.3389109785730064, "grad_norm": 0.5029037594795227, "learning_rate": 3.079940730357124e-05, "loss": 0.0171, "step": 6137 }, { "epoch": 0.3389662027833002, "grad_norm": 6.936461448669434, "learning_rate": 3.079639616708882e-05, "loss": 0.2577, "step": 6138 }, { "epoch": 0.339021426993594, "grad_norm": 3.76849627494812, "learning_rate": 3.079338468519895e-05, "loss": 0.6551, "step": 6139 }, { "epoch": 0.3390766512038878, "grad_norm": 1.0918132066726685, "learning_rate": 3.079037285799797e-05, "loss": 0.0695, "step": 6140 }, { "epoch": 0.33913187541418155, "grad_norm": 0.03730400279164314, "learning_rate": 3.078736068558225e-05, "loss": 0.0014, "step": 6141 }, { "epoch": 0.33918709962447535, "grad_norm": 2.352372884750366, "learning_rate": 3.078434816804814e-05, "loss": 0.279, "step": 6142 }, { "epoch": 0.33924232383476915, "grad_norm": 0.1914108842611313, "learning_rate": 3.078133530549204e-05, "loss": 0.0076, "step": 6143 }, { "epoch": 0.33929754804506296, "grad_norm": 0.0207950621843338, "learning_rate": 3.077832209801033e-05, "loss": 0.0008, "step": 6144 }, { "epoch": 0.33935277225535676, "grad_norm": 2.075153112411499, "learning_rate": 3.077530854569941e-05, "loss": 0.4889, "step": 6145 }, { "epoch": 0.33940799646565056, "grad_norm": 3.5734126567840576, "learning_rate": 3.077229464865569e-05, "loss": 0.4776, "step": 6146 }, { "epoch": 0.3394632206759443, "grad_norm": 0.020571567118167877, "learning_rate": 3.0769280406975596e-05, "loss": 0.001, "step": 6147 }, { "epoch": 0.3395184448862381, "grad_norm": 0.6592673063278198, "learning_rate": 3.076626582075557e-05, "loss": 0.0278, "step": 6148 }, { "epoch": 0.3395736690965319, "grad_norm": 0.146543949842453, "learning_rate": 3.0763250890092044e-05, "loss": 0.0053, "step": 6149 }, { "epoch": 0.3396288933068257, "grad_norm": 3.662640333175659, "learning_rate": 3.0760235615081485e-05, "loss": 0.6472, "step": 6150 }, { "epoch": 0.3396841175171195, "grad_norm": 3.2120420932769775, "learning_rate": 3.075721999582036e-05, "loss": 0.1515, "step": 6151 }, { "epoch": 0.3397393417274133, "grad_norm": 0.3418933153152466, "learning_rate": 3.075420403240514e-05, "loss": 0.0067, "step": 6152 }, { "epoch": 0.33979456593770707, "grad_norm": 1.8681942224502563, "learning_rate": 3.07511877249323e-05, "loss": 0.1249, "step": 6153 }, { "epoch": 0.3398497901480009, "grad_norm": 3.336958885192871, "learning_rate": 3.074817107349838e-05, "loss": 0.4139, "step": 6154 }, { "epoch": 0.3399050143582947, "grad_norm": 1.3583780527114868, "learning_rate": 3.0745154078199856e-05, "loss": 0.0504, "step": 6155 }, { "epoch": 0.3399602385685885, "grad_norm": 1.5856109857559204, "learning_rate": 3.0742136739133266e-05, "loss": 0.4492, "step": 6156 }, { "epoch": 0.3400154627788823, "grad_norm": 0.953706681728363, "learning_rate": 3.0739119056395146e-05, "loss": 0.0516, "step": 6157 }, { "epoch": 0.34007068698917603, "grad_norm": 0.05123969167470932, "learning_rate": 3.0736101030082024e-05, "loss": 0.0014, "step": 6158 }, { "epoch": 0.34012591119946983, "grad_norm": 3.2631285190582275, "learning_rate": 3.0733082660290476e-05, "loss": 0.5778, "step": 6159 }, { "epoch": 0.34018113540976364, "grad_norm": 0.19056540727615356, "learning_rate": 3.073006394711706e-05, "loss": 0.0078, "step": 6160 }, { "epoch": 0.34023635962005744, "grad_norm": 5.8382134437561035, "learning_rate": 3.0727044890658335e-05, "loss": 0.887, "step": 6161 }, { "epoch": 0.34029158383035124, "grad_norm": 0.7884731292724609, "learning_rate": 3.072402549101092e-05, "loss": 0.0255, "step": 6162 }, { "epoch": 0.34034680804064504, "grad_norm": 1.959393858909607, "learning_rate": 3.072100574827139e-05, "loss": 0.109, "step": 6163 }, { "epoch": 0.3404020322509388, "grad_norm": 4.219195365905762, "learning_rate": 3.0717985662536376e-05, "loss": 0.3531, "step": 6164 }, { "epoch": 0.3404572564612326, "grad_norm": 1.9715112447738647, "learning_rate": 3.071496523390248e-05, "loss": 0.1892, "step": 6165 }, { "epoch": 0.3405124806715264, "grad_norm": 2.2099056243896484, "learning_rate": 3.071194446246634e-05, "loss": 0.6157, "step": 6166 }, { "epoch": 0.3405677048818202, "grad_norm": 0.576798677444458, "learning_rate": 3.07089233483246e-05, "loss": 0.0151, "step": 6167 }, { "epoch": 0.340622929092114, "grad_norm": 0.9271186590194702, "learning_rate": 3.070590189157393e-05, "loss": 0.2191, "step": 6168 }, { "epoch": 0.34067815330240775, "grad_norm": 4.062761306762695, "learning_rate": 3.0702880092310964e-05, "loss": 1.3406, "step": 6169 }, { "epoch": 0.34073337751270155, "grad_norm": 2.744605302810669, "learning_rate": 3.0699857950632405e-05, "loss": 0.0455, "step": 6170 }, { "epoch": 0.34078860172299535, "grad_norm": 2.127887725830078, "learning_rate": 3.0696835466634926e-05, "loss": 0.3051, "step": 6171 }, { "epoch": 0.34084382593328916, "grad_norm": 0.0815344750881195, "learning_rate": 3.0693812640415225e-05, "loss": 0.002, "step": 6172 }, { "epoch": 0.34089905014358296, "grad_norm": 0.21783646941184998, "learning_rate": 3.069078947207001e-05, "loss": 0.0049, "step": 6173 }, { "epoch": 0.34095427435387676, "grad_norm": 0.09575340151786804, "learning_rate": 3.068776596169601e-05, "loss": 0.003, "step": 6174 }, { "epoch": 0.3410094985641705, "grad_norm": 0.2394983172416687, "learning_rate": 3.068474210938996e-05, "loss": 0.0084, "step": 6175 }, { "epoch": 0.3410647227744643, "grad_norm": 3.4234418869018555, "learning_rate": 3.068171791524857e-05, "loss": 0.5376, "step": 6176 }, { "epoch": 0.3411199469847581, "grad_norm": 2.1985740661621094, "learning_rate": 3.0678693379368624e-05, "loss": 0.1257, "step": 6177 }, { "epoch": 0.3411751711950519, "grad_norm": 0.34879595041275024, "learning_rate": 3.067566850184688e-05, "loss": 0.0038, "step": 6178 }, { "epoch": 0.3412303954053457, "grad_norm": 2.6984453201293945, "learning_rate": 3.0672643282780106e-05, "loss": 0.8018, "step": 6179 }, { "epoch": 0.3412856196156395, "grad_norm": 0.9763562679290771, "learning_rate": 3.066961772226509e-05, "loss": 0.0864, "step": 6180 }, { "epoch": 0.34134084382593327, "grad_norm": 0.04136701300740242, "learning_rate": 3.0666591820398624e-05, "loss": 0.0014, "step": 6181 }, { "epoch": 0.3413960680362271, "grad_norm": 1.2030029296875, "learning_rate": 3.066356557727753e-05, "loss": 0.1011, "step": 6182 }, { "epoch": 0.3414512922465209, "grad_norm": 0.025436127558350563, "learning_rate": 3.0660538992998604e-05, "loss": 0.0011, "step": 6183 }, { "epoch": 0.3415065164568147, "grad_norm": 0.20288656651973724, "learning_rate": 3.065751206765869e-05, "loss": 0.0072, "step": 6184 }, { "epoch": 0.3415617406671085, "grad_norm": 2.027181625366211, "learning_rate": 3.065448480135463e-05, "loss": 0.2348, "step": 6185 }, { "epoch": 0.34161696487740223, "grad_norm": 0.02106316387653351, "learning_rate": 3.065145719418326e-05, "loss": 0.001, "step": 6186 }, { "epoch": 0.34167218908769603, "grad_norm": 0.5605273246765137, "learning_rate": 3.064842924624145e-05, "loss": 0.0127, "step": 6187 }, { "epoch": 0.34172741329798983, "grad_norm": 2.562983512878418, "learning_rate": 3.0645400957626085e-05, "loss": 0.2076, "step": 6188 }, { "epoch": 0.34178263750828364, "grad_norm": 0.3398435413837433, "learning_rate": 3.064237232843403e-05, "loss": 0.0072, "step": 6189 }, { "epoch": 0.34183786171857744, "grad_norm": 1.2643094062805176, "learning_rate": 3.063934335876218e-05, "loss": 0.1132, "step": 6190 }, { "epoch": 0.34189308592887124, "grad_norm": 0.031250596046447754, "learning_rate": 3.063631404870746e-05, "loss": 0.0012, "step": 6191 }, { "epoch": 0.341948310139165, "grad_norm": 3.108456611633301, "learning_rate": 3.063328439836677e-05, "loss": 0.3339, "step": 6192 }, { "epoch": 0.3420035343494588, "grad_norm": 5.452643394470215, "learning_rate": 3.063025440783704e-05, "loss": 0.4223, "step": 6193 }, { "epoch": 0.3420587585597526, "grad_norm": 2.1991584300994873, "learning_rate": 3.06272240772152e-05, "loss": 0.0277, "step": 6194 }, { "epoch": 0.3421139827700464, "grad_norm": 6.432344436645508, "learning_rate": 3.0624193406598215e-05, "loss": 1.3017, "step": 6195 }, { "epoch": 0.3421692069803402, "grad_norm": 0.30370980501174927, "learning_rate": 3.062116239608304e-05, "loss": 0.0055, "step": 6196 }, { "epoch": 0.34222443119063395, "grad_norm": 0.16496363282203674, "learning_rate": 3.061813104576664e-05, "loss": 0.0051, "step": 6197 }, { "epoch": 0.34227965540092775, "grad_norm": 0.17874477803707123, "learning_rate": 3.0615099355746e-05, "loss": 0.0044, "step": 6198 }, { "epoch": 0.34233487961122155, "grad_norm": 1.8426125049591064, "learning_rate": 3.061206732611811e-05, "loss": 0.0353, "step": 6199 }, { "epoch": 0.34239010382151536, "grad_norm": 0.015369007363915443, "learning_rate": 3.060903495697997e-05, "loss": 0.0006, "step": 6200 }, { "epoch": 0.34244532803180916, "grad_norm": 1.9096510410308838, "learning_rate": 3.060600224842861e-05, "loss": 0.0615, "step": 6201 }, { "epoch": 0.34250055224210296, "grad_norm": 0.07285895198583603, "learning_rate": 3.060296920056104e-05, "loss": 0.0028, "step": 6202 }, { "epoch": 0.3425557764523967, "grad_norm": 5.141624450683594, "learning_rate": 3.0599935813474295e-05, "loss": 0.4072, "step": 6203 }, { "epoch": 0.3426110006626905, "grad_norm": 4.276515960693359, "learning_rate": 3.059690208726544e-05, "loss": 0.6116, "step": 6204 }, { "epoch": 0.3426662248729843, "grad_norm": 0.7619537115097046, "learning_rate": 3.05938680220315e-05, "loss": 0.0201, "step": 6205 }, { "epoch": 0.3427214490832781, "grad_norm": 0.07729054987430573, "learning_rate": 3.0590833617869575e-05, "loss": 0.0015, "step": 6206 }, { "epoch": 0.3427766732935719, "grad_norm": 3.5719082355499268, "learning_rate": 3.058779887487672e-05, "loss": 0.7997, "step": 6207 }, { "epoch": 0.34283189750386567, "grad_norm": 0.03619185835123062, "learning_rate": 3.058476379315005e-05, "loss": 0.0014, "step": 6208 }, { "epoch": 0.34288712171415947, "grad_norm": 4.380975246429443, "learning_rate": 3.058172837278665e-05, "loss": 0.3771, "step": 6209 }, { "epoch": 0.3429423459244533, "grad_norm": 3.7917912006378174, "learning_rate": 3.0578692613883636e-05, "loss": 1.0148, "step": 6210 }, { "epoch": 0.3429975701347471, "grad_norm": 0.7356024384498596, "learning_rate": 3.0575656516538126e-05, "loss": 0.135, "step": 6211 }, { "epoch": 0.3430527943450409, "grad_norm": 0.017040938138961792, "learning_rate": 3.0572620080847256e-05, "loss": 0.0005, "step": 6212 }, { "epoch": 0.3431080185553347, "grad_norm": 0.0548478327691555, "learning_rate": 3.056958330690817e-05, "loss": 0.0018, "step": 6213 }, { "epoch": 0.34316324276562843, "grad_norm": 1.1364891529083252, "learning_rate": 3.056654619481803e-05, "loss": 0.0401, "step": 6214 }, { "epoch": 0.34321846697592223, "grad_norm": 0.19983147084712982, "learning_rate": 3.0563508744673984e-05, "loss": 0.0044, "step": 6215 }, { "epoch": 0.34327369118621603, "grad_norm": 0.6311490535736084, "learning_rate": 3.056047095657323e-05, "loss": 0.0135, "step": 6216 }, { "epoch": 0.34332891539650984, "grad_norm": 5.431786060333252, "learning_rate": 3.055743283061294e-05, "loss": 0.3854, "step": 6217 }, { "epoch": 0.34338413960680364, "grad_norm": 0.10599452257156372, "learning_rate": 3.0554394366890326e-05, "loss": 0.0036, "step": 6218 }, { "epoch": 0.34343936381709744, "grad_norm": 3.1708924770355225, "learning_rate": 3.0551355565502584e-05, "loss": 0.1829, "step": 6219 }, { "epoch": 0.3434945880273912, "grad_norm": 4.616937637329102, "learning_rate": 3.0548316426546945e-05, "loss": 0.9402, "step": 6220 }, { "epoch": 0.343549812237685, "grad_norm": 2.1640775203704834, "learning_rate": 3.054527695012062e-05, "loss": 0.1652, "step": 6221 }, { "epoch": 0.3436050364479788, "grad_norm": 0.033796582370996475, "learning_rate": 3.0542237136320874e-05, "loss": 0.0013, "step": 6222 }, { "epoch": 0.3436602606582726, "grad_norm": 0.06892506778240204, "learning_rate": 3.053919698524494e-05, "loss": 0.0029, "step": 6223 }, { "epoch": 0.3437154848685664, "grad_norm": 0.18632255494594574, "learning_rate": 3.0536156496990104e-05, "loss": 0.0048, "step": 6224 }, { "epoch": 0.34377070907886015, "grad_norm": 0.6007761359214783, "learning_rate": 3.0533115671653625e-05, "loss": 0.0264, "step": 6225 }, { "epoch": 0.34382593328915395, "grad_norm": 0.09146369248628616, "learning_rate": 3.0530074509332786e-05, "loss": 0.0032, "step": 6226 }, { "epoch": 0.34388115749944775, "grad_norm": 3.4519131183624268, "learning_rate": 3.052703301012488e-05, "loss": 0.6226, "step": 6227 }, { "epoch": 0.34393638170974156, "grad_norm": 3.574382781982422, "learning_rate": 3.052399117412723e-05, "loss": 0.8028, "step": 6228 }, { "epoch": 0.34399160592003536, "grad_norm": 0.4616222381591797, "learning_rate": 3.052094900143713e-05, "loss": 0.0188, "step": 6229 }, { "epoch": 0.34404683013032916, "grad_norm": 0.05345896631479263, "learning_rate": 3.051790649215194e-05, "loss": 0.0013, "step": 6230 }, { "epoch": 0.3441020543406229, "grad_norm": 7.647912979125977, "learning_rate": 3.0514863646368952e-05, "loss": 0.6224, "step": 6231 }, { "epoch": 0.3441572785509167, "grad_norm": 2.3648569583892822, "learning_rate": 3.0511820464185554e-05, "loss": 0.1667, "step": 6232 }, { "epoch": 0.3442125027612105, "grad_norm": 0.3867642879486084, "learning_rate": 3.050877694569909e-05, "loss": 0.0121, "step": 6233 }, { "epoch": 0.3442677269715043, "grad_norm": 0.29172101616859436, "learning_rate": 3.0505733091006936e-05, "loss": 0.0107, "step": 6234 }, { "epoch": 0.3443229511817981, "grad_norm": 1.032563328742981, "learning_rate": 3.0502688900206476e-05, "loss": 0.0215, "step": 6235 }, { "epoch": 0.34437817539209187, "grad_norm": 2.8378536701202393, "learning_rate": 3.0499644373395094e-05, "loss": 0.1892, "step": 6236 }, { "epoch": 0.34443339960238567, "grad_norm": 0.30226343870162964, "learning_rate": 3.04965995106702e-05, "loss": 0.0084, "step": 6237 }, { "epoch": 0.3444886238126795, "grad_norm": 2.8962652683258057, "learning_rate": 3.0493554312129205e-05, "loss": 0.8255, "step": 6238 }, { "epoch": 0.3445438480229733, "grad_norm": 4.316525936126709, "learning_rate": 3.049050877786953e-05, "loss": 0.455, "step": 6239 }, { "epoch": 0.3445990722332671, "grad_norm": 1.3659696578979492, "learning_rate": 3.048746290798862e-05, "loss": 0.1015, "step": 6240 }, { "epoch": 0.3446542964435609, "grad_norm": 3.983332633972168, "learning_rate": 3.048441670258391e-05, "loss": 0.2231, "step": 6241 }, { "epoch": 0.34470952065385463, "grad_norm": 2.6782124042510986, "learning_rate": 3.0481370161752858e-05, "loss": 0.0861, "step": 6242 }, { "epoch": 0.34476474486414843, "grad_norm": 1.833042860031128, "learning_rate": 3.0478323285592942e-05, "loss": 0.1014, "step": 6243 }, { "epoch": 0.34481996907444223, "grad_norm": 0.19728931784629822, "learning_rate": 3.0475276074201635e-05, "loss": 0.0048, "step": 6244 }, { "epoch": 0.34487519328473604, "grad_norm": 1.5297508239746094, "learning_rate": 3.0472228527676423e-05, "loss": 0.4281, "step": 6245 }, { "epoch": 0.34493041749502984, "grad_norm": 3.3696746826171875, "learning_rate": 3.0469180646114803e-05, "loss": 0.2481, "step": 6246 }, { "epoch": 0.3449856417053236, "grad_norm": 0.012776129879057407, "learning_rate": 3.0466132429614298e-05, "loss": 0.0005, "step": 6247 }, { "epoch": 0.3450408659156174, "grad_norm": 0.023075617849826813, "learning_rate": 3.0463083878272413e-05, "loss": 0.0008, "step": 6248 }, { "epoch": 0.3450960901259112, "grad_norm": 0.02144889533519745, "learning_rate": 3.0460034992186686e-05, "loss": 0.0006, "step": 6249 }, { "epoch": 0.345151314336205, "grad_norm": 6.54951810836792, "learning_rate": 3.0456985771454666e-05, "loss": 0.2681, "step": 6250 }, { "epoch": 0.3452065385464988, "grad_norm": 0.0065581295639276505, "learning_rate": 3.0453936216173906e-05, "loss": 0.0002, "step": 6251 }, { "epoch": 0.3452617627567926, "grad_norm": 2.8196849822998047, "learning_rate": 3.0450886326441956e-05, "loss": 0.336, "step": 6252 }, { "epoch": 0.34531698696708635, "grad_norm": 0.07212904840707779, "learning_rate": 3.044783610235641e-05, "loss": 0.0017, "step": 6253 }, { "epoch": 0.34537221117738015, "grad_norm": 0.13731764256954193, "learning_rate": 3.044478554401483e-05, "loss": 0.0031, "step": 6254 }, { "epoch": 0.34542743538767395, "grad_norm": 3.205404281616211, "learning_rate": 3.0441734651514836e-05, "loss": 0.2777, "step": 6255 }, { "epoch": 0.34548265959796776, "grad_norm": 0.0774344801902771, "learning_rate": 3.0438683424954025e-05, "loss": 0.0025, "step": 6256 }, { "epoch": 0.34553788380826156, "grad_norm": 4.2051520347595215, "learning_rate": 3.0435631864430006e-05, "loss": 0.5858, "step": 6257 }, { "epoch": 0.34559310801855536, "grad_norm": 3.901914596557617, "learning_rate": 3.043257997004042e-05, "loss": 0.8701, "step": 6258 }, { "epoch": 0.3456483322288491, "grad_norm": 0.33178016543388367, "learning_rate": 3.0429527741882902e-05, "loss": 0.0126, "step": 6259 }, { "epoch": 0.3457035564391429, "grad_norm": 1.1577246189117432, "learning_rate": 3.0426475180055094e-05, "loss": 0.2679, "step": 6260 }, { "epoch": 0.3457587806494367, "grad_norm": 4.833057403564453, "learning_rate": 3.042342228465467e-05, "loss": 0.1645, "step": 6261 }, { "epoch": 0.3458140048597305, "grad_norm": 0.1263544261455536, "learning_rate": 3.0420369055779284e-05, "loss": 0.0037, "step": 6262 }, { "epoch": 0.3458692290700243, "grad_norm": 0.03184860199689865, "learning_rate": 3.0417315493526632e-05, "loss": 0.0011, "step": 6263 }, { "epoch": 0.34592445328031807, "grad_norm": 0.1508859544992447, "learning_rate": 3.04142615979944e-05, "loss": 0.0044, "step": 6264 }, { "epoch": 0.34597967749061187, "grad_norm": 3.8420376777648926, "learning_rate": 3.041120736928029e-05, "loss": 0.482, "step": 6265 }, { "epoch": 0.3460349017009057, "grad_norm": 0.011683383025228977, "learning_rate": 3.040815280748202e-05, "loss": 0.0004, "step": 6266 }, { "epoch": 0.3460901259111995, "grad_norm": 0.031931061297655106, "learning_rate": 3.0405097912697306e-05, "loss": 0.0014, "step": 6267 }, { "epoch": 0.3461453501214933, "grad_norm": 0.4639071822166443, "learning_rate": 3.0402042685023892e-05, "loss": 0.0115, "step": 6268 }, { "epoch": 0.3462005743317871, "grad_norm": 0.06705059856176376, "learning_rate": 3.0398987124559518e-05, "loss": 0.0022, "step": 6269 }, { "epoch": 0.34625579854208083, "grad_norm": 4.036721706390381, "learning_rate": 3.0395931231401937e-05, "loss": 0.4035, "step": 6270 }, { "epoch": 0.34631102275237463, "grad_norm": 0.1126941442489624, "learning_rate": 3.0392875005648927e-05, "loss": 0.0054, "step": 6271 }, { "epoch": 0.34636624696266843, "grad_norm": 1.3041574954986572, "learning_rate": 3.0389818447398257e-05, "loss": 0.0588, "step": 6272 }, { "epoch": 0.34642147117296224, "grad_norm": 1.3301481008529663, "learning_rate": 3.0386761556747714e-05, "loss": 0.0211, "step": 6273 }, { "epoch": 0.34647669538325604, "grad_norm": 3.3683645725250244, "learning_rate": 3.0383704333795098e-05, "loss": 0.746, "step": 6274 }, { "epoch": 0.3465319195935498, "grad_norm": 0.27877432107925415, "learning_rate": 3.0380646778638216e-05, "loss": 0.0098, "step": 6275 }, { "epoch": 0.3465871438038436, "grad_norm": 5.274857521057129, "learning_rate": 3.0377588891374904e-05, "loss": 0.7825, "step": 6276 }, { "epoch": 0.3466423680141374, "grad_norm": 0.9516335129737854, "learning_rate": 3.0374530672102972e-05, "loss": 0.1308, "step": 6277 }, { "epoch": 0.3466975922244312, "grad_norm": 0.3122021555900574, "learning_rate": 3.0371472120920264e-05, "loss": 0.0096, "step": 6278 }, { "epoch": 0.346752816434725, "grad_norm": 0.18605449795722961, "learning_rate": 3.036841323792464e-05, "loss": 0.0063, "step": 6279 }, { "epoch": 0.3468080406450188, "grad_norm": 1.7139283418655396, "learning_rate": 3.0365354023213968e-05, "loss": 0.0387, "step": 6280 }, { "epoch": 0.34686326485531255, "grad_norm": 0.235137477517128, "learning_rate": 3.0362294476886098e-05, "loss": 0.006, "step": 6281 }, { "epoch": 0.34691848906560635, "grad_norm": 0.1612999141216278, "learning_rate": 3.0359234599038934e-05, "loss": 0.0054, "step": 6282 }, { "epoch": 0.34697371327590015, "grad_norm": 0.06627920269966125, "learning_rate": 3.0356174389770364e-05, "loss": 0.0018, "step": 6283 }, { "epoch": 0.34702893748619396, "grad_norm": 0.06436982750892639, "learning_rate": 3.0353113849178297e-05, "loss": 0.0025, "step": 6284 }, { "epoch": 0.34708416169648776, "grad_norm": 2.8626868724823, "learning_rate": 3.0350052977360636e-05, "loss": 0.1506, "step": 6285 }, { "epoch": 0.3471393859067815, "grad_norm": 0.04295070096850395, "learning_rate": 3.0346991774415317e-05, "loss": 0.0012, "step": 6286 }, { "epoch": 0.3471946101170753, "grad_norm": 0.444064199924469, "learning_rate": 3.034393024044027e-05, "loss": 0.0096, "step": 6287 }, { "epoch": 0.3472498343273691, "grad_norm": 3.1931142807006836, "learning_rate": 3.034086837553346e-05, "loss": 0.5125, "step": 6288 }, { "epoch": 0.3473050585376629, "grad_norm": 1.306086778640747, "learning_rate": 3.0337806179792822e-05, "loss": 0.1377, "step": 6289 }, { "epoch": 0.3473602827479567, "grad_norm": 1.7080765962600708, "learning_rate": 3.0334743653316336e-05, "loss": 0.1424, "step": 6290 }, { "epoch": 0.3474155069582505, "grad_norm": 0.03172171115875244, "learning_rate": 3.0331680796201977e-05, "loss": 0.0009, "step": 6291 }, { "epoch": 0.34747073116854427, "grad_norm": 4.573309421539307, "learning_rate": 3.032861760854774e-05, "loss": 1.6699, "step": 6292 }, { "epoch": 0.34752595537883807, "grad_norm": 2.2587738037109375, "learning_rate": 3.032555409045162e-05, "loss": 0.2061, "step": 6293 }, { "epoch": 0.3475811795891319, "grad_norm": 2.702916145324707, "learning_rate": 3.0322490242011624e-05, "loss": 0.8139, "step": 6294 }, { "epoch": 0.3476364037994257, "grad_norm": 4.306612968444824, "learning_rate": 3.031942606332579e-05, "loss": 0.3085, "step": 6295 }, { "epoch": 0.3476916280097195, "grad_norm": 0.4924981892108917, "learning_rate": 3.0316361554492128e-05, "loss": 0.0189, "step": 6296 }, { "epoch": 0.3477468522200133, "grad_norm": 5.392522811889648, "learning_rate": 3.031329671560869e-05, "loss": 1.6559, "step": 6297 }, { "epoch": 0.34780207643030703, "grad_norm": 1.7304295301437378, "learning_rate": 3.0310231546773535e-05, "loss": 0.1779, "step": 6298 }, { "epoch": 0.34785730064060083, "grad_norm": 0.28792718052864075, "learning_rate": 3.030716604808472e-05, "loss": 0.0096, "step": 6299 }, { "epoch": 0.34791252485089463, "grad_norm": 0.5738894939422607, "learning_rate": 3.0304100219640316e-05, "loss": 0.0123, "step": 6300 }, { "epoch": 0.34796774906118844, "grad_norm": 0.05761246383190155, "learning_rate": 3.030103406153841e-05, "loss": 0.0021, "step": 6301 }, { "epoch": 0.34802297327148224, "grad_norm": 0.5164591670036316, "learning_rate": 3.0297967573877104e-05, "loss": 0.011, "step": 6302 }, { "epoch": 0.348078197481776, "grad_norm": 3.3911232948303223, "learning_rate": 3.0294900756754502e-05, "loss": 0.288, "step": 6303 }, { "epoch": 0.3481334216920698, "grad_norm": 0.05297474563121796, "learning_rate": 3.0291833610268706e-05, "loss": 0.002, "step": 6304 }, { "epoch": 0.3481886459023636, "grad_norm": 1.2747204303741455, "learning_rate": 3.028876613451786e-05, "loss": 0.0407, "step": 6305 }, { "epoch": 0.3482438701126574, "grad_norm": 1.4593044519424438, "learning_rate": 3.028569832960009e-05, "loss": 0.0629, "step": 6306 }, { "epoch": 0.3482990943229512, "grad_norm": 0.05503084510564804, "learning_rate": 3.0282630195613554e-05, "loss": 0.0025, "step": 6307 }, { "epoch": 0.348354318533245, "grad_norm": 1.7579909563064575, "learning_rate": 3.0279561732656405e-05, "loss": 0.2478, "step": 6308 }, { "epoch": 0.34840954274353875, "grad_norm": 0.12188517302274704, "learning_rate": 3.0276492940826805e-05, "loss": 0.0032, "step": 6309 }, { "epoch": 0.34846476695383255, "grad_norm": 3.2596335411071777, "learning_rate": 3.027342382022295e-05, "loss": 0.166, "step": 6310 }, { "epoch": 0.34851999116412635, "grad_norm": 3.7348997592926025, "learning_rate": 3.027035437094301e-05, "loss": 0.047, "step": 6311 }, { "epoch": 0.34857521537442016, "grad_norm": 0.09581202268600464, "learning_rate": 3.02672845930852e-05, "loss": 0.0039, "step": 6312 }, { "epoch": 0.34863043958471396, "grad_norm": 0.30371975898742676, "learning_rate": 3.0264214486747723e-05, "loss": 0.008, "step": 6313 }, { "epoch": 0.3486856637950077, "grad_norm": 0.5136848092079163, "learning_rate": 3.02611440520288e-05, "loss": 0.0219, "step": 6314 }, { "epoch": 0.3487408880053015, "grad_norm": 0.8182233572006226, "learning_rate": 3.025807328902668e-05, "loss": 0.0206, "step": 6315 }, { "epoch": 0.3487961122155953, "grad_norm": 0.30793049931526184, "learning_rate": 3.0255002197839584e-05, "loss": 0.0071, "step": 6316 }, { "epoch": 0.3488513364258891, "grad_norm": 6.307381629943848, "learning_rate": 3.0251930778565773e-05, "loss": 0.3164, "step": 6317 }, { "epoch": 0.3489065606361829, "grad_norm": 2.7253737449645996, "learning_rate": 3.024885903130351e-05, "loss": 0.245, "step": 6318 }, { "epoch": 0.3489617848464767, "grad_norm": 0.04374607652425766, "learning_rate": 3.024578695615107e-05, "loss": 0.0014, "step": 6319 }, { "epoch": 0.34901700905677047, "grad_norm": 0.20479999482631683, "learning_rate": 3.0242714553206734e-05, "loss": 0.0061, "step": 6320 }, { "epoch": 0.34907223326706427, "grad_norm": 4.316276550292969, "learning_rate": 3.0239641822568803e-05, "loss": 1.039, "step": 6321 }, { "epoch": 0.34912745747735807, "grad_norm": 3.41243052482605, "learning_rate": 3.023656876433558e-05, "loss": 0.3844, "step": 6322 }, { "epoch": 0.3491826816876519, "grad_norm": 0.45702606439590454, "learning_rate": 3.023349537860538e-05, "loss": 0.0074, "step": 6323 }, { "epoch": 0.3492379058979457, "grad_norm": 2.668513774871826, "learning_rate": 3.023042166547653e-05, "loss": 0.3833, "step": 6324 }, { "epoch": 0.3492931301082394, "grad_norm": 0.05900608375668526, "learning_rate": 3.022734762504736e-05, "loss": 0.0013, "step": 6325 }, { "epoch": 0.3493483543185332, "grad_norm": 1.456494688987732, "learning_rate": 3.0224273257416227e-05, "loss": 0.056, "step": 6326 }, { "epoch": 0.34940357852882703, "grad_norm": 3.895779609680176, "learning_rate": 3.0221198562681492e-05, "loss": 1.2821, "step": 6327 }, { "epoch": 0.34945880273912083, "grad_norm": 3.2984092235565186, "learning_rate": 3.021812354094151e-05, "loss": 0.2858, "step": 6328 }, { "epoch": 0.34951402694941464, "grad_norm": 3.4496958255767822, "learning_rate": 3.021504819229467e-05, "loss": 0.7594, "step": 6329 }, { "epoch": 0.34956925115970844, "grad_norm": 2.301609754562378, "learning_rate": 3.0211972516839347e-05, "loss": 0.4372, "step": 6330 }, { "epoch": 0.3496244753700022, "grad_norm": 3.261291742324829, "learning_rate": 3.0208896514673963e-05, "loss": 0.7608, "step": 6331 }, { "epoch": 0.349679699580296, "grad_norm": 0.03201166167855263, "learning_rate": 3.020582018589691e-05, "loss": 0.001, "step": 6332 }, { "epoch": 0.3497349237905898, "grad_norm": 0.03749709203839302, "learning_rate": 3.0202743530606614e-05, "loss": 0.0013, "step": 6333 }, { "epoch": 0.3497901480008836, "grad_norm": 2.902094602584839, "learning_rate": 3.019966654890151e-05, "loss": 0.1923, "step": 6334 }, { "epoch": 0.3498453722111774, "grad_norm": 1.5441466569900513, "learning_rate": 3.0196589240880034e-05, "loss": 0.0819, "step": 6335 }, { "epoch": 0.3499005964214712, "grad_norm": 0.03809519112110138, "learning_rate": 3.019351160664064e-05, "loss": 0.0008, "step": 6336 }, { "epoch": 0.34995582063176495, "grad_norm": 0.19687394797801971, "learning_rate": 3.0190433646281794e-05, "loss": 0.0035, "step": 6337 }, { "epoch": 0.35001104484205875, "grad_norm": 1.354711890220642, "learning_rate": 3.0187355359901957e-05, "loss": 0.1026, "step": 6338 }, { "epoch": 0.35006626905235255, "grad_norm": 1.5890122652053833, "learning_rate": 3.0184276747599624e-05, "loss": 0.0385, "step": 6339 }, { "epoch": 0.35012149326264635, "grad_norm": 0.07102178037166595, "learning_rate": 3.0181197809473287e-05, "loss": 0.0019, "step": 6340 }, { "epoch": 0.35017671747294016, "grad_norm": 2.462724208831787, "learning_rate": 3.017811854562144e-05, "loss": 0.0907, "step": 6341 }, { "epoch": 0.3502319416832339, "grad_norm": 0.09208076447248459, "learning_rate": 3.0175038956142614e-05, "loss": 0.004, "step": 6342 }, { "epoch": 0.3502871658935277, "grad_norm": 0.23144063353538513, "learning_rate": 3.0171959041135318e-05, "loss": 0.0074, "step": 6343 }, { "epoch": 0.3503423901038215, "grad_norm": 2.7229466438293457, "learning_rate": 3.01688788006981e-05, "loss": 0.2293, "step": 6344 }, { "epoch": 0.3503976143141153, "grad_norm": 5.511796951293945, "learning_rate": 3.0165798234929497e-05, "loss": 0.0418, "step": 6345 }, { "epoch": 0.3504528385244091, "grad_norm": 1.0996936559677124, "learning_rate": 3.016271734392806e-05, "loss": 0.1133, "step": 6346 }, { "epoch": 0.3505080627347029, "grad_norm": 0.45499011874198914, "learning_rate": 3.0159636127792376e-05, "loss": 0.012, "step": 6347 }, { "epoch": 0.35056328694499667, "grad_norm": 0.48744288086891174, "learning_rate": 3.0156554586621002e-05, "loss": 0.0131, "step": 6348 }, { "epoch": 0.35061851115529047, "grad_norm": 0.6777094602584839, "learning_rate": 3.0153472720512536e-05, "loss": 0.0247, "step": 6349 }, { "epoch": 0.35067373536558427, "grad_norm": 0.9447500109672546, "learning_rate": 3.015039052956557e-05, "loss": 0.0139, "step": 6350 }, { "epoch": 0.3507289595758781, "grad_norm": 1.0331271886825562, "learning_rate": 3.014730801387871e-05, "loss": 0.0504, "step": 6351 }, { "epoch": 0.3507841837861719, "grad_norm": 0.06351291388273239, "learning_rate": 3.0144225173550583e-05, "loss": 0.0018, "step": 6352 }, { "epoch": 0.3508394079964656, "grad_norm": 1.4098950624465942, "learning_rate": 3.0141142008679814e-05, "loss": 0.0391, "step": 6353 }, { "epoch": 0.3508946322067594, "grad_norm": 0.06867541372776031, "learning_rate": 3.013805851936504e-05, "loss": 0.0015, "step": 6354 }, { "epoch": 0.35094985641705323, "grad_norm": 0.07620962709188461, "learning_rate": 3.0134974705704915e-05, "loss": 0.0024, "step": 6355 }, { "epoch": 0.35100508062734703, "grad_norm": 0.16107043623924255, "learning_rate": 3.0131890567798092e-05, "loss": 0.0044, "step": 6356 }, { "epoch": 0.35106030483764084, "grad_norm": 0.16971227526664734, "learning_rate": 3.0128806105743246e-05, "loss": 0.0047, "step": 6357 }, { "epoch": 0.35111552904793464, "grad_norm": 1.1593793630599976, "learning_rate": 3.0125721319639063e-05, "loss": 0.0568, "step": 6358 }, { "epoch": 0.3511707532582284, "grad_norm": 0.4761424660682678, "learning_rate": 3.012263620958422e-05, "loss": 0.0198, "step": 6359 }, { "epoch": 0.3512259774685222, "grad_norm": 0.8507242798805237, "learning_rate": 3.011955077567743e-05, "loss": 0.0674, "step": 6360 }, { "epoch": 0.351281201678816, "grad_norm": 2.422886371612549, "learning_rate": 3.0116465018017397e-05, "loss": 0.2327, "step": 6361 }, { "epoch": 0.3513364258891098, "grad_norm": 0.06799571961164474, "learning_rate": 3.011337893670286e-05, "loss": 0.0026, "step": 6362 }, { "epoch": 0.3513916500994036, "grad_norm": 0.07071388512849808, "learning_rate": 3.011029253183253e-05, "loss": 0.0029, "step": 6363 }, { "epoch": 0.3514468743096974, "grad_norm": 2.6429603099823, "learning_rate": 3.010720580350516e-05, "loss": 0.375, "step": 6364 }, { "epoch": 0.35150209851999115, "grad_norm": 0.012907379306852818, "learning_rate": 3.0104118751819506e-05, "loss": 0.0004, "step": 6365 }, { "epoch": 0.35155732273028495, "grad_norm": 3.364034652709961, "learning_rate": 3.0101031376874323e-05, "loss": 0.2427, "step": 6366 }, { "epoch": 0.35161254694057875, "grad_norm": 3.6012766361236572, "learning_rate": 3.009794367876839e-05, "loss": 0.2733, "step": 6367 }, { "epoch": 0.35166777115087255, "grad_norm": 2.364143133163452, "learning_rate": 3.0094855657600496e-05, "loss": 0.1877, "step": 6368 }, { "epoch": 0.35172299536116636, "grad_norm": 1.4063153266906738, "learning_rate": 3.0091767313469423e-05, "loss": 0.0307, "step": 6369 }, { "epoch": 0.3517782195714601, "grad_norm": 1.9564669132232666, "learning_rate": 3.0088678646473996e-05, "loss": 0.2059, "step": 6370 }, { "epoch": 0.3518334437817539, "grad_norm": 0.05430842190980911, "learning_rate": 3.008558965671301e-05, "loss": 0.0016, "step": 6371 }, { "epoch": 0.3518886679920477, "grad_norm": 0.022056741639971733, "learning_rate": 3.00825003442853e-05, "loss": 0.0008, "step": 6372 }, { "epoch": 0.3519438922023415, "grad_norm": 3.6248042583465576, "learning_rate": 3.0079410709289702e-05, "loss": 0.8327, "step": 6373 }, { "epoch": 0.3519991164126353, "grad_norm": 0.03647197410464287, "learning_rate": 3.0076320751825055e-05, "loss": 0.0013, "step": 6374 }, { "epoch": 0.3520543406229291, "grad_norm": 1.3718112707138062, "learning_rate": 3.0073230471990222e-05, "loss": 0.0443, "step": 6375 }, { "epoch": 0.35210956483322287, "grad_norm": 0.9717452526092529, "learning_rate": 3.0070139869884075e-05, "loss": 0.017, "step": 6376 }, { "epoch": 0.35216478904351667, "grad_norm": 0.325025737285614, "learning_rate": 3.0067048945605478e-05, "loss": 0.0086, "step": 6377 }, { "epoch": 0.35222001325381047, "grad_norm": 3.4748892784118652, "learning_rate": 3.006395769925333e-05, "loss": 0.4933, "step": 6378 }, { "epoch": 0.3522752374641043, "grad_norm": 0.8050622940063477, "learning_rate": 3.0060866130926526e-05, "loss": 0.0298, "step": 6379 }, { "epoch": 0.3523304616743981, "grad_norm": 0.7446155548095703, "learning_rate": 3.0057774240723973e-05, "loss": 0.0279, "step": 6380 }, { "epoch": 0.3523856858846918, "grad_norm": 0.12907510995864868, "learning_rate": 3.0054682028744584e-05, "loss": 0.0034, "step": 6381 }, { "epoch": 0.3524409100949856, "grad_norm": 0.052457891404628754, "learning_rate": 3.0051589495087294e-05, "loss": 0.0014, "step": 6382 }, { "epoch": 0.35249613430527943, "grad_norm": 1.1700832843780518, "learning_rate": 3.0048496639851037e-05, "loss": 0.1559, "step": 6383 }, { "epoch": 0.35255135851557323, "grad_norm": 2.009752035140991, "learning_rate": 3.0045403463134773e-05, "loss": 0.3538, "step": 6384 }, { "epoch": 0.35260658272586703, "grad_norm": 3.898789882659912, "learning_rate": 3.0042309965037454e-05, "loss": 0.3148, "step": 6385 }, { "epoch": 0.35266180693616084, "grad_norm": 0.2738400101661682, "learning_rate": 3.0039216145658045e-05, "loss": 0.004, "step": 6386 }, { "epoch": 0.3527170311464546, "grad_norm": 2.277860403060913, "learning_rate": 3.0036122005095536e-05, "loss": 0.1849, "step": 6387 }, { "epoch": 0.3527722553567484, "grad_norm": 0.5055126547813416, "learning_rate": 3.0033027543448905e-05, "loss": 0.0106, "step": 6388 }, { "epoch": 0.3528274795670422, "grad_norm": 5.014344215393066, "learning_rate": 3.0029932760817163e-05, "loss": 1.0064, "step": 6389 }, { "epoch": 0.352882703777336, "grad_norm": 0.04817621782422066, "learning_rate": 3.002683765729932e-05, "loss": 0.0011, "step": 6390 }, { "epoch": 0.3529379279876298, "grad_norm": 4.0026984214782715, "learning_rate": 3.0023742232994393e-05, "loss": 0.7732, "step": 6391 }, { "epoch": 0.35299315219792354, "grad_norm": 0.2077534943819046, "learning_rate": 3.002064648800142e-05, "loss": 0.0018, "step": 6392 }, { "epoch": 0.35304837640821735, "grad_norm": 3.138570785522461, "learning_rate": 3.0017550422419436e-05, "loss": 0.3278, "step": 6393 }, { "epoch": 0.35310360061851115, "grad_norm": 0.03469168394804001, "learning_rate": 3.0014454036347494e-05, "loss": 0.0014, "step": 6394 }, { "epoch": 0.35315882482880495, "grad_norm": 0.08076867461204529, "learning_rate": 3.001135732988466e-05, "loss": 0.0025, "step": 6395 }, { "epoch": 0.35321404903909875, "grad_norm": 0.014947311021387577, "learning_rate": 3.0008260303130004e-05, "loss": 0.0005, "step": 6396 }, { "epoch": 0.35326927324939256, "grad_norm": 0.19363659620285034, "learning_rate": 3.0005162956182604e-05, "loss": 0.0053, "step": 6397 }, { "epoch": 0.3533244974596863, "grad_norm": 3.228215456008911, "learning_rate": 3.0002065289141557e-05, "loss": 0.676, "step": 6398 }, { "epoch": 0.3533797216699801, "grad_norm": 5.3801374435424805, "learning_rate": 2.9998967302105978e-05, "loss": 0.4751, "step": 6399 }, { "epoch": 0.3534349458802739, "grad_norm": 1.0182873010635376, "learning_rate": 2.9995868995174962e-05, "loss": 0.0193, "step": 6400 }, { "epoch": 0.3534901700905677, "grad_norm": 0.6295552253723145, "learning_rate": 2.9992770368447636e-05, "loss": 0.0248, "step": 6401 }, { "epoch": 0.3535453943008615, "grad_norm": 0.20159149169921875, "learning_rate": 2.998967142202314e-05, "loss": 0.0044, "step": 6402 }, { "epoch": 0.3536006185111553, "grad_norm": 4.040841579437256, "learning_rate": 2.9986572156000618e-05, "loss": 0.3668, "step": 6403 }, { "epoch": 0.35365584272144907, "grad_norm": 6.171775817871094, "learning_rate": 2.9983472570479223e-05, "loss": 0.734, "step": 6404 }, { "epoch": 0.35371106693174287, "grad_norm": 0.04103269800543785, "learning_rate": 2.998037266555812e-05, "loss": 0.0016, "step": 6405 }, { "epoch": 0.35376629114203667, "grad_norm": 0.32870370149612427, "learning_rate": 2.9977272441336477e-05, "loss": 0.0103, "step": 6406 }, { "epoch": 0.3538215153523305, "grad_norm": 0.05491046607494354, "learning_rate": 2.9974171897913487e-05, "loss": 0.002, "step": 6407 }, { "epoch": 0.3538767395626243, "grad_norm": 2.839834451675415, "learning_rate": 2.9971071035388344e-05, "loss": 0.152, "step": 6408 }, { "epoch": 0.353931963772918, "grad_norm": 0.6450552344322205, "learning_rate": 2.9967969853860253e-05, "loss": 0.0259, "step": 6409 }, { "epoch": 0.3539871879832118, "grad_norm": 0.6877647638320923, "learning_rate": 2.9964868353428432e-05, "loss": 0.0844, "step": 6410 }, { "epoch": 0.35404241219350563, "grad_norm": 1.8874307870864868, "learning_rate": 2.9961766534192094e-05, "loss": 0.2372, "step": 6411 }, { "epoch": 0.35409763640379943, "grad_norm": 2.649892568588257, "learning_rate": 2.995866439625049e-05, "loss": 0.0806, "step": 6412 }, { "epoch": 0.35415286061409323, "grad_norm": 2.3738157749176025, "learning_rate": 2.995556193970286e-05, "loss": 0.0901, "step": 6413 }, { "epoch": 0.35420808482438704, "grad_norm": 0.04019714146852493, "learning_rate": 2.9952459164648463e-05, "loss": 0.0011, "step": 6414 }, { "epoch": 0.3542633090346808, "grad_norm": 0.14378608763217926, "learning_rate": 2.9949356071186564e-05, "loss": 0.0046, "step": 6415 }, { "epoch": 0.3543185332449746, "grad_norm": 1.6301342248916626, "learning_rate": 2.9946252659416434e-05, "loss": 0.0515, "step": 6416 }, { "epoch": 0.3543737574552684, "grad_norm": 4.54202127456665, "learning_rate": 2.994314892943737e-05, "loss": 0.3937, "step": 6417 }, { "epoch": 0.3544289816655622, "grad_norm": 3.6271910667419434, "learning_rate": 2.994004488134867e-05, "loss": 0.5194, "step": 6418 }, { "epoch": 0.354484205875856, "grad_norm": 8.142496109008789, "learning_rate": 2.9936940515249628e-05, "loss": 1.1246, "step": 6419 }, { "epoch": 0.35453943008614974, "grad_norm": 1.2892520427703857, "learning_rate": 2.9933835831239574e-05, "loss": 0.0477, "step": 6420 }, { "epoch": 0.35459465429644355, "grad_norm": 2.228134870529175, "learning_rate": 2.993073082941783e-05, "loss": 0.2499, "step": 6421 }, { "epoch": 0.35464987850673735, "grad_norm": 2.910423994064331, "learning_rate": 2.9927625509883734e-05, "loss": 0.9562, "step": 6422 }, { "epoch": 0.35470510271703115, "grad_norm": 0.10825459659099579, "learning_rate": 2.992451987273664e-05, "loss": 0.0023, "step": 6423 }, { "epoch": 0.35476032692732495, "grad_norm": 0.6343527436256409, "learning_rate": 2.9921413918075894e-05, "loss": 0.0125, "step": 6424 }, { "epoch": 0.35481555113761876, "grad_norm": 0.3462289869785309, "learning_rate": 2.9918307646000875e-05, "loss": 0.0082, "step": 6425 }, { "epoch": 0.3548707753479125, "grad_norm": 2.7099192142486572, "learning_rate": 2.991520105661096e-05, "loss": 0.6893, "step": 6426 }, { "epoch": 0.3549259995582063, "grad_norm": 0.20153890550136566, "learning_rate": 2.991209415000554e-05, "loss": 0.0063, "step": 6427 }, { "epoch": 0.3549812237685001, "grad_norm": 3.5508806705474854, "learning_rate": 2.9908986926284002e-05, "loss": 1.3056, "step": 6428 }, { "epoch": 0.3550364479787939, "grad_norm": 3.5657808780670166, "learning_rate": 2.9905879385545762e-05, "loss": 0.1996, "step": 6429 }, { "epoch": 0.3550916721890877, "grad_norm": 3.6704204082489014, "learning_rate": 2.9902771527890247e-05, "loss": 0.3522, "step": 6430 }, { "epoch": 0.35514689639938146, "grad_norm": 3.1243863105773926, "learning_rate": 2.9899663353416874e-05, "loss": 0.0556, "step": 6431 }, { "epoch": 0.35520212060967526, "grad_norm": 2.6190593242645264, "learning_rate": 2.9896554862225088e-05, "loss": 0.3324, "step": 6432 }, { "epoch": 0.35525734481996907, "grad_norm": 0.3113221228122711, "learning_rate": 2.989344605441434e-05, "loss": 0.0031, "step": 6433 }, { "epoch": 0.35531256903026287, "grad_norm": 0.8434111475944519, "learning_rate": 2.989033693008408e-05, "loss": 0.0149, "step": 6434 }, { "epoch": 0.3553677932405567, "grad_norm": 3.053593158721924, "learning_rate": 2.988722748933379e-05, "loss": 0.575, "step": 6435 }, { "epoch": 0.3554230174508505, "grad_norm": 2.5573017597198486, "learning_rate": 2.9884117732262948e-05, "loss": 0.2518, "step": 6436 }, { "epoch": 0.3554782416611442, "grad_norm": 3.8979573249816895, "learning_rate": 2.9881007658971036e-05, "loss": 0.1791, "step": 6437 }, { "epoch": 0.355533465871438, "grad_norm": 6.146097660064697, "learning_rate": 2.9877897269557562e-05, "loss": 0.9937, "step": 6438 }, { "epoch": 0.35558869008173183, "grad_norm": 1.262726902961731, "learning_rate": 2.9874786564122034e-05, "loss": 0.0454, "step": 6439 }, { "epoch": 0.35564391429202563, "grad_norm": 3.3742570877075195, "learning_rate": 2.987167554276397e-05, "loss": 0.3996, "step": 6440 }, { "epoch": 0.35569913850231943, "grad_norm": 0.09028594195842743, "learning_rate": 2.98685642055829e-05, "loss": 0.0032, "step": 6441 }, { "epoch": 0.35575436271261324, "grad_norm": 0.029864678159356117, "learning_rate": 2.9865452552678365e-05, "loss": 0.0009, "step": 6442 }, { "epoch": 0.355809586922907, "grad_norm": 5.593258380889893, "learning_rate": 2.9862340584149922e-05, "loss": 0.4895, "step": 6443 }, { "epoch": 0.3558648111332008, "grad_norm": 3.400973320007324, "learning_rate": 2.9859228300097126e-05, "loss": 0.8733, "step": 6444 }, { "epoch": 0.3559200353434946, "grad_norm": 3.1507458686828613, "learning_rate": 2.9856115700619546e-05, "loss": 0.4592, "step": 6445 }, { "epoch": 0.3559752595537884, "grad_norm": 2.8389039039611816, "learning_rate": 2.9853002785816767e-05, "loss": 0.2806, "step": 6446 }, { "epoch": 0.3560304837640822, "grad_norm": 2.839104413986206, "learning_rate": 2.984988955578838e-05, "loss": 0.8935, "step": 6447 }, { "epoch": 0.35608570797437594, "grad_norm": 2.559117078781128, "learning_rate": 2.9846776010633985e-05, "loss": 0.2812, "step": 6448 }, { "epoch": 0.35614093218466975, "grad_norm": 0.8032671213150024, "learning_rate": 2.9843662150453193e-05, "loss": 0.0171, "step": 6449 }, { "epoch": 0.35619615639496355, "grad_norm": 4.89303731918335, "learning_rate": 2.9840547975345623e-05, "loss": 0.6775, "step": 6450 }, { "epoch": 0.35625138060525735, "grad_norm": 1.3317227363586426, "learning_rate": 2.983743348541091e-05, "loss": 0.2215, "step": 6451 }, { "epoch": 0.35630660481555115, "grad_norm": 1.8462133407592773, "learning_rate": 2.9834318680748697e-05, "loss": 0.231, "step": 6452 }, { "epoch": 0.35636182902584496, "grad_norm": 0.15885555744171143, "learning_rate": 2.9831203561458623e-05, "loss": 0.005, "step": 6453 }, { "epoch": 0.3564170532361387, "grad_norm": 2.985790252685547, "learning_rate": 2.9828088127640368e-05, "loss": 0.8149, "step": 6454 }, { "epoch": 0.3564722774464325, "grad_norm": 4.058383464813232, "learning_rate": 2.9824972379393585e-05, "loss": 0.6172, "step": 6455 }, { "epoch": 0.3565275016567263, "grad_norm": 1.3787310123443604, "learning_rate": 2.9821856316817972e-05, "loss": 0.1409, "step": 6456 }, { "epoch": 0.3565827258670201, "grad_norm": 1.7592856884002686, "learning_rate": 2.9818739940013217e-05, "loss": 0.2097, "step": 6457 }, { "epoch": 0.3566379500773139, "grad_norm": 3.1108548641204834, "learning_rate": 2.9815623249079012e-05, "loss": 0.4326, "step": 6458 }, { "epoch": 0.35669317428760766, "grad_norm": 0.22756123542785645, "learning_rate": 2.9812506244115078e-05, "loss": 0.0078, "step": 6459 }, { "epoch": 0.35674839849790146, "grad_norm": 1.4744402170181274, "learning_rate": 2.9809388925221136e-05, "loss": 0.0638, "step": 6460 }, { "epoch": 0.35680362270819527, "grad_norm": 0.13549569249153137, "learning_rate": 2.9806271292496913e-05, "loss": 0.0057, "step": 6461 }, { "epoch": 0.35685884691848907, "grad_norm": 2.228087902069092, "learning_rate": 2.980315334604216e-05, "loss": 0.2058, "step": 6462 }, { "epoch": 0.3569140711287829, "grad_norm": 4.513979434967041, "learning_rate": 2.9800035085956614e-05, "loss": 0.5625, "step": 6463 }, { "epoch": 0.3569692953390767, "grad_norm": 0.20091643929481506, "learning_rate": 2.979691651234005e-05, "loss": 0.0078, "step": 6464 }, { "epoch": 0.3570245195493704, "grad_norm": 0.20315097272396088, "learning_rate": 2.979379762529224e-05, "loss": 0.0075, "step": 6465 }, { "epoch": 0.3570797437596642, "grad_norm": 0.9224437475204468, "learning_rate": 2.979067842491296e-05, "loss": 0.0501, "step": 6466 }, { "epoch": 0.35713496796995803, "grad_norm": 2.9827072620391846, "learning_rate": 2.9787558911302e-05, "loss": 0.5092, "step": 6467 }, { "epoch": 0.35719019218025183, "grad_norm": 3.7434301376342773, "learning_rate": 2.9784439084559173e-05, "loss": 0.9922, "step": 6468 }, { "epoch": 0.35724541639054563, "grad_norm": 1.7970820665359497, "learning_rate": 2.9781318944784285e-05, "loss": 0.1571, "step": 6469 }, { "epoch": 0.3573006406008394, "grad_norm": 0.7173104882240295, "learning_rate": 2.9778198492077153e-05, "loss": 0.2047, "step": 6470 }, { "epoch": 0.3573558648111332, "grad_norm": 0.062090568244457245, "learning_rate": 2.9775077726537614e-05, "loss": 0.0025, "step": 6471 }, { "epoch": 0.357411089021427, "grad_norm": 0.047859076410532, "learning_rate": 2.9771956648265514e-05, "loss": 0.0021, "step": 6472 }, { "epoch": 0.3574663132317208, "grad_norm": 3.8558449745178223, "learning_rate": 2.9768835257360696e-05, "loss": 0.8828, "step": 6473 }, { "epoch": 0.3575215374420146, "grad_norm": 0.3856315612792969, "learning_rate": 2.976571355392303e-05, "loss": 0.0064, "step": 6474 }, { "epoch": 0.3575767616523084, "grad_norm": 0.05925655737519264, "learning_rate": 2.9762591538052388e-05, "loss": 0.0022, "step": 6475 }, { "epoch": 0.35763198586260214, "grad_norm": 0.2136119157075882, "learning_rate": 2.9759469209848646e-05, "loss": 0.0109, "step": 6476 }, { "epoch": 0.35768721007289594, "grad_norm": 1.364107370376587, "learning_rate": 2.9756346569411706e-05, "loss": 0.0318, "step": 6477 }, { "epoch": 0.35774243428318975, "grad_norm": 0.8550430536270142, "learning_rate": 2.975322361684146e-05, "loss": 0.0317, "step": 6478 }, { "epoch": 0.35779765849348355, "grad_norm": 0.07124372571706772, "learning_rate": 2.975010035223782e-05, "loss": 0.002, "step": 6479 }, { "epoch": 0.35785288270377735, "grad_norm": 0.11739247292280197, "learning_rate": 2.9746976775700717e-05, "loss": 0.0033, "step": 6480 }, { "epoch": 0.35790810691407116, "grad_norm": 2.2271978855133057, "learning_rate": 2.974385288733008e-05, "loss": 0.2092, "step": 6481 }, { "epoch": 0.3579633311243649, "grad_norm": 0.04729009047150612, "learning_rate": 2.9740728687225848e-05, "loss": 0.002, "step": 6482 }, { "epoch": 0.3580185553346587, "grad_norm": 0.05898572504520416, "learning_rate": 2.9737604175487977e-05, "loss": 0.0025, "step": 6483 }, { "epoch": 0.3580737795449525, "grad_norm": 0.18150697648525238, "learning_rate": 2.973447935221642e-05, "loss": 0.0051, "step": 6484 }, { "epoch": 0.3581290037552463, "grad_norm": 3.2497661113739014, "learning_rate": 2.973135421751116e-05, "loss": 0.2627, "step": 6485 }, { "epoch": 0.3581842279655401, "grad_norm": 1.2181806564331055, "learning_rate": 2.972822877147217e-05, "loss": 0.1896, "step": 6486 }, { "epoch": 0.35823945217583386, "grad_norm": 0.14564737677574158, "learning_rate": 2.9725103014199453e-05, "loss": 0.0055, "step": 6487 }, { "epoch": 0.35829467638612766, "grad_norm": 1.7122325897216797, "learning_rate": 2.9721976945793007e-05, "loss": 0.0513, "step": 6488 }, { "epoch": 0.35834990059642147, "grad_norm": 0.1568344384431839, "learning_rate": 2.9718850566352836e-05, "loss": 0.006, "step": 6489 }, { "epoch": 0.35840512480671527, "grad_norm": 4.366529941558838, "learning_rate": 2.9715723875978967e-05, "loss": 0.48, "step": 6490 }, { "epoch": 0.3584603490170091, "grad_norm": 0.045070961117744446, "learning_rate": 2.9712596874771433e-05, "loss": 0.0013, "step": 6491 }, { "epoch": 0.3585155732273029, "grad_norm": 0.01690811477601528, "learning_rate": 2.9709469562830272e-05, "loss": 0.0008, "step": 6492 }, { "epoch": 0.3585707974375966, "grad_norm": 0.48582687973976135, "learning_rate": 2.9706341940255546e-05, "loss": 0.023, "step": 6493 }, { "epoch": 0.3586260216478904, "grad_norm": 2.2618014812469482, "learning_rate": 2.97032140071473e-05, "loss": 0.5851, "step": 6494 }, { "epoch": 0.35868124585818423, "grad_norm": 0.1592845320701599, "learning_rate": 2.9700085763605616e-05, "loss": 0.0046, "step": 6495 }, { "epoch": 0.35873647006847803, "grad_norm": 1.4664171934127808, "learning_rate": 2.969695720973058e-05, "loss": 0.0481, "step": 6496 }, { "epoch": 0.35879169427877183, "grad_norm": 1.7867616415023804, "learning_rate": 2.9693828345622263e-05, "loss": 0.2454, "step": 6497 }, { "epoch": 0.3588469184890656, "grad_norm": 0.0573226660490036, "learning_rate": 2.9690699171380794e-05, "loss": 0.0025, "step": 6498 }, { "epoch": 0.3589021426993594, "grad_norm": 0.9906662702560425, "learning_rate": 2.9687569687106265e-05, "loss": 0.0156, "step": 6499 }, { "epoch": 0.3589573669096532, "grad_norm": 5.138011932373047, "learning_rate": 2.96844398928988e-05, "loss": 0.8568, "step": 6500 }, { "epoch": 0.359012591119947, "grad_norm": 0.4295866787433624, "learning_rate": 2.9681309788858536e-05, "loss": 0.0105, "step": 6501 }, { "epoch": 0.3590678153302408, "grad_norm": 2.3743579387664795, "learning_rate": 2.9678179375085606e-05, "loss": 0.1697, "step": 6502 }, { "epoch": 0.3591230395405346, "grad_norm": 0.1344469040632248, "learning_rate": 2.9675048651680164e-05, "loss": 0.004, "step": 6503 }, { "epoch": 0.35917826375082834, "grad_norm": 3.744605302810669, "learning_rate": 2.9671917618742382e-05, "loss": 0.6506, "step": 6504 }, { "epoch": 0.35923348796112214, "grad_norm": 5.510336875915527, "learning_rate": 2.966878627637241e-05, "loss": 0.6811, "step": 6505 }, { "epoch": 0.35928871217141595, "grad_norm": 0.2505490183830261, "learning_rate": 2.9665654624670445e-05, "loss": 0.0069, "step": 6506 }, { "epoch": 0.35934393638170975, "grad_norm": 0.9533536434173584, "learning_rate": 2.9662522663736674e-05, "loss": 0.1305, "step": 6507 }, { "epoch": 0.35939916059200355, "grad_norm": 1.6541286706924438, "learning_rate": 2.965939039367129e-05, "loss": 0.1762, "step": 6508 }, { "epoch": 0.3594543848022973, "grad_norm": 4.256929397583008, "learning_rate": 2.965625781457451e-05, "loss": 0.728, "step": 6509 }, { "epoch": 0.3595096090125911, "grad_norm": 0.09132320433855057, "learning_rate": 2.965312492654655e-05, "loss": 0.003, "step": 6510 }, { "epoch": 0.3595648332228849, "grad_norm": 2.538919687271118, "learning_rate": 2.9649991729687647e-05, "loss": 0.1801, "step": 6511 }, { "epoch": 0.3596200574331787, "grad_norm": 3.1801223754882812, "learning_rate": 2.9646858224098034e-05, "loss": 0.1379, "step": 6512 }, { "epoch": 0.3596752816434725, "grad_norm": 5.5737457275390625, "learning_rate": 2.964372440987796e-05, "loss": 1.0567, "step": 6513 }, { "epoch": 0.3597305058537663, "grad_norm": 0.2739616334438324, "learning_rate": 2.964059028712769e-05, "loss": 0.0084, "step": 6514 }, { "epoch": 0.35978573006406006, "grad_norm": 0.061051420867443085, "learning_rate": 2.9637455855947494e-05, "loss": 0.0019, "step": 6515 }, { "epoch": 0.35984095427435386, "grad_norm": 0.03372374549508095, "learning_rate": 2.9634321116437648e-05, "loss": 0.0011, "step": 6516 }, { "epoch": 0.35989617848464767, "grad_norm": 2.429769277572632, "learning_rate": 2.963118606869844e-05, "loss": 0.1319, "step": 6517 }, { "epoch": 0.35995140269494147, "grad_norm": 2.0092074871063232, "learning_rate": 2.9628050712830167e-05, "loss": 0.1362, "step": 6518 }, { "epoch": 0.36000662690523527, "grad_norm": 0.2152406871318817, "learning_rate": 2.962491504893315e-05, "loss": 0.0034, "step": 6519 }, { "epoch": 0.3600618511155291, "grad_norm": 1.4579322338104248, "learning_rate": 2.9621779077107694e-05, "loss": 0.3213, "step": 6520 }, { "epoch": 0.3601170753258228, "grad_norm": 1.9030781984329224, "learning_rate": 2.961864279745413e-05, "loss": 0.2384, "step": 6521 }, { "epoch": 0.3601722995361166, "grad_norm": 2.3183975219726562, "learning_rate": 2.961550621007281e-05, "loss": 0.7968, "step": 6522 }, { "epoch": 0.3602275237464104, "grad_norm": 2.321890115737915, "learning_rate": 2.9612369315064066e-05, "loss": 0.165, "step": 6523 }, { "epoch": 0.36028274795670423, "grad_norm": 4.321560859680176, "learning_rate": 2.9609232112528265e-05, "loss": 0.2807, "step": 6524 }, { "epoch": 0.36033797216699803, "grad_norm": 1.773527979850769, "learning_rate": 2.960609460256577e-05, "loss": 0.1285, "step": 6525 }, { "epoch": 0.3603931963772918, "grad_norm": 0.1428326815366745, "learning_rate": 2.9602956785276958e-05, "loss": 0.0064, "step": 6526 }, { "epoch": 0.3604484205875856, "grad_norm": 0.04902173578739166, "learning_rate": 2.9599818660762227e-05, "loss": 0.0014, "step": 6527 }, { "epoch": 0.3605036447978794, "grad_norm": 0.922905445098877, "learning_rate": 2.9596680229121964e-05, "loss": 0.026, "step": 6528 }, { "epoch": 0.3605588690081732, "grad_norm": 0.12322608381509781, "learning_rate": 2.9593541490456582e-05, "loss": 0.0054, "step": 6529 }, { "epoch": 0.360614093218467, "grad_norm": 3.017904281616211, "learning_rate": 2.9590402444866497e-05, "loss": 0.5696, "step": 6530 }, { "epoch": 0.3606693174287608, "grad_norm": 0.011966672725975513, "learning_rate": 2.958726309245213e-05, "loss": 0.0006, "step": 6531 }, { "epoch": 0.36072454163905454, "grad_norm": 0.3191688060760498, "learning_rate": 2.958412343331393e-05, "loss": 0.0068, "step": 6532 }, { "epoch": 0.36077976584934834, "grad_norm": 0.1391047090291977, "learning_rate": 2.9580983467552328e-05, "loss": 0.0039, "step": 6533 }, { "epoch": 0.36083499005964215, "grad_norm": 1.9097439050674438, "learning_rate": 2.9577843195267797e-05, "loss": 0.1237, "step": 6534 }, { "epoch": 0.36089021426993595, "grad_norm": 0.19099093973636627, "learning_rate": 2.957470261656079e-05, "loss": 0.008, "step": 6535 }, { "epoch": 0.36094543848022975, "grad_norm": 0.30249127745628357, "learning_rate": 2.9571561731531785e-05, "loss": 0.012, "step": 6536 }, { "epoch": 0.3610006626905235, "grad_norm": 0.4086645841598511, "learning_rate": 2.956842054028128e-05, "loss": 0.0157, "step": 6537 }, { "epoch": 0.3610558869008173, "grad_norm": 1.5140646696090698, "learning_rate": 2.956527904290976e-05, "loss": 0.0982, "step": 6538 }, { "epoch": 0.3611111111111111, "grad_norm": 0.5571076273918152, "learning_rate": 2.956213723951773e-05, "loss": 0.0258, "step": 6539 }, { "epoch": 0.3611663353214049, "grad_norm": 2.7128100395202637, "learning_rate": 2.9558995130205707e-05, "loss": 0.4016, "step": 6540 }, { "epoch": 0.3612215595316987, "grad_norm": 0.017413077875971794, "learning_rate": 2.9555852715074214e-05, "loss": 0.0007, "step": 6541 }, { "epoch": 0.3612767837419925, "grad_norm": 2.6296675205230713, "learning_rate": 2.9552709994223794e-05, "loss": 0.4164, "step": 6542 }, { "epoch": 0.36133200795228626, "grad_norm": 1.4647859334945679, "learning_rate": 2.9549566967754986e-05, "loss": 0.0553, "step": 6543 }, { "epoch": 0.36138723216258006, "grad_norm": 6.297995090484619, "learning_rate": 2.954642363576834e-05, "loss": 1.0802, "step": 6544 }, { "epoch": 0.36144245637287387, "grad_norm": 0.3504623472690582, "learning_rate": 2.9543279998364424e-05, "loss": 0.0099, "step": 6545 }, { "epoch": 0.36149768058316767, "grad_norm": 4.132061004638672, "learning_rate": 2.9540136055643814e-05, "loss": 1.2724, "step": 6546 }, { "epoch": 0.36155290479346147, "grad_norm": 1.7932406663894653, "learning_rate": 2.9536991807707095e-05, "loss": 0.1518, "step": 6547 }, { "epoch": 0.3616081290037552, "grad_norm": 0.9324926733970642, "learning_rate": 2.9533847254654855e-05, "loss": 0.1741, "step": 6548 }, { "epoch": 0.361663353214049, "grad_norm": 0.17041902244091034, "learning_rate": 2.9530702396587698e-05, "loss": 0.0055, "step": 6549 }, { "epoch": 0.3617185774243428, "grad_norm": 3.4637298583984375, "learning_rate": 2.9527557233606243e-05, "loss": 0.3621, "step": 6550 }, { "epoch": 0.3617738016346366, "grad_norm": 0.08531566709280014, "learning_rate": 2.952441176581111e-05, "loss": 0.0025, "step": 6551 }, { "epoch": 0.36182902584493043, "grad_norm": 0.05816313996911049, "learning_rate": 2.9521265993302922e-05, "loss": 0.0017, "step": 6552 }, { "epoch": 0.36188425005522423, "grad_norm": 0.15835949778556824, "learning_rate": 2.951811991618233e-05, "loss": 0.0043, "step": 6553 }, { "epoch": 0.361939474265518, "grad_norm": 1.6189934015274048, "learning_rate": 2.9514973534549988e-05, "loss": 0.0743, "step": 6554 }, { "epoch": 0.3619946984758118, "grad_norm": 0.7301778197288513, "learning_rate": 2.9511826848506556e-05, "loss": 0.0302, "step": 6555 }, { "epoch": 0.3620499226861056, "grad_norm": 0.3967251777648926, "learning_rate": 2.95086798581527e-05, "loss": 0.0093, "step": 6556 }, { "epoch": 0.3621051468963994, "grad_norm": 1.834183931350708, "learning_rate": 2.9505532563589104e-05, "loss": 0.3196, "step": 6557 }, { "epoch": 0.3621603711066932, "grad_norm": 2.339653253555298, "learning_rate": 2.9502384964916468e-05, "loss": 0.2955, "step": 6558 }, { "epoch": 0.362215595316987, "grad_norm": 2.245370864868164, "learning_rate": 2.9499237062235483e-05, "loss": 0.1717, "step": 6559 }, { "epoch": 0.36227081952728074, "grad_norm": 3.433544397354126, "learning_rate": 2.949608885564686e-05, "loss": 0.316, "step": 6560 }, { "epoch": 0.36232604373757454, "grad_norm": 3.058387041091919, "learning_rate": 2.949294034525132e-05, "loss": 0.3583, "step": 6561 }, { "epoch": 0.36238126794786835, "grad_norm": 0.06944180279970169, "learning_rate": 2.9489791531149586e-05, "loss": 0.0038, "step": 6562 }, { "epoch": 0.36243649215816215, "grad_norm": 2.18234920501709, "learning_rate": 2.9486642413442417e-05, "loss": 0.5121, "step": 6563 }, { "epoch": 0.36249171636845595, "grad_norm": 3.920311450958252, "learning_rate": 2.9483492992230544e-05, "loss": 0.8784, "step": 6564 }, { "epoch": 0.3625469405787497, "grad_norm": 0.33854755759239197, "learning_rate": 2.948034326761473e-05, "loss": 0.0078, "step": 6565 }, { "epoch": 0.3626021647890435, "grad_norm": 1.6708519458770752, "learning_rate": 2.947719323969575e-05, "loss": 0.0451, "step": 6566 }, { "epoch": 0.3626573889993373, "grad_norm": 3.713327646255493, "learning_rate": 2.9474042908574378e-05, "loss": 0.5166, "step": 6567 }, { "epoch": 0.3627126132096311, "grad_norm": 5.018774032592773, "learning_rate": 2.9470892274351394e-05, "loss": 0.6156, "step": 6568 }, { "epoch": 0.3627678374199249, "grad_norm": 1.692883014678955, "learning_rate": 2.9467741337127612e-05, "loss": 0.0614, "step": 6569 }, { "epoch": 0.3628230616302187, "grad_norm": 0.10395719110965729, "learning_rate": 2.9464590097003824e-05, "loss": 0.0032, "step": 6570 }, { "epoch": 0.36287828584051246, "grad_norm": 0.3151048421859741, "learning_rate": 2.9461438554080862e-05, "loss": 0.0095, "step": 6571 }, { "epoch": 0.36293351005080626, "grad_norm": 0.2876589596271515, "learning_rate": 2.9458286708459543e-05, "loss": 0.0047, "step": 6572 }, { "epoch": 0.36298873426110007, "grad_norm": 0.06027938053011894, "learning_rate": 2.9455134560240705e-05, "loss": 0.0023, "step": 6573 }, { "epoch": 0.36304395847139387, "grad_norm": 0.12279415130615234, "learning_rate": 2.945198210952519e-05, "loss": 0.004, "step": 6574 }, { "epoch": 0.36309918268168767, "grad_norm": 0.018220366910099983, "learning_rate": 2.944882935641386e-05, "loss": 0.0008, "step": 6575 }, { "epoch": 0.3631544068919814, "grad_norm": 0.2166479229927063, "learning_rate": 2.9445676301007587e-05, "loss": 0.0065, "step": 6576 }, { "epoch": 0.3632096311022752, "grad_norm": 3.6068906784057617, "learning_rate": 2.9442522943407233e-05, "loss": 0.4572, "step": 6577 }, { "epoch": 0.363264855312569, "grad_norm": 0.2541685998439789, "learning_rate": 2.943936928371369e-05, "loss": 0.0083, "step": 6578 }, { "epoch": 0.3633200795228628, "grad_norm": 0.304878294467926, "learning_rate": 2.943621532202785e-05, "loss": 0.0136, "step": 6579 }, { "epoch": 0.36337530373315663, "grad_norm": 0.14475049078464508, "learning_rate": 2.9433061058450618e-05, "loss": 0.0058, "step": 6580 }, { "epoch": 0.36343052794345043, "grad_norm": 5.073364734649658, "learning_rate": 2.9429906493082904e-05, "loss": 0.6492, "step": 6581 }, { "epoch": 0.3634857521537442, "grad_norm": 0.2695869207382202, "learning_rate": 2.9426751626025646e-05, "loss": 0.0085, "step": 6582 }, { "epoch": 0.363540976364038, "grad_norm": 2.713265895843506, "learning_rate": 2.9423596457379756e-05, "loss": 0.3656, "step": 6583 }, { "epoch": 0.3635962005743318, "grad_norm": 0.06968222558498383, "learning_rate": 2.942044098724619e-05, "loss": 0.003, "step": 6584 }, { "epoch": 0.3636514247846256, "grad_norm": 1.8168237209320068, "learning_rate": 2.9417285215725905e-05, "loss": 0.1004, "step": 6585 }, { "epoch": 0.3637066489949194, "grad_norm": 0.019394248723983765, "learning_rate": 2.941412914291985e-05, "loss": 0.0007, "step": 6586 }, { "epoch": 0.3637618732052132, "grad_norm": 0.018200665712356567, "learning_rate": 2.9410972768929005e-05, "loss": 0.0008, "step": 6587 }, { "epoch": 0.36381709741550694, "grad_norm": 0.441795289516449, "learning_rate": 2.9407816093854348e-05, "loss": 0.0147, "step": 6588 }, { "epoch": 0.36387232162580074, "grad_norm": 3.1381237506866455, "learning_rate": 2.9404659117796866e-05, "loss": 0.4017, "step": 6589 }, { "epoch": 0.36392754583609455, "grad_norm": 0.08756522089242935, "learning_rate": 2.940150184085758e-05, "loss": 0.0028, "step": 6590 }, { "epoch": 0.36398277004638835, "grad_norm": 0.2869834005832672, "learning_rate": 2.939834426313747e-05, "loss": 0.0098, "step": 6591 }, { "epoch": 0.36403799425668215, "grad_norm": 3.3153059482574463, "learning_rate": 2.9395186384737582e-05, "loss": 0.1943, "step": 6592 }, { "epoch": 0.3640932184669759, "grad_norm": 1.2501776218414307, "learning_rate": 2.9392028205758925e-05, "loss": 0.078, "step": 6593 }, { "epoch": 0.3641484426772697, "grad_norm": 0.04958821460604668, "learning_rate": 2.9388869726302554e-05, "loss": 0.0019, "step": 6594 }, { "epoch": 0.3642036668875635, "grad_norm": 3.5073869228363037, "learning_rate": 2.938571094646951e-05, "loss": 0.0774, "step": 6595 }, { "epoch": 0.3642588910978573, "grad_norm": 6.451004981994629, "learning_rate": 2.9382551866360855e-05, "loss": 0.0477, "step": 6596 }, { "epoch": 0.3643141153081511, "grad_norm": 3.6733815670013428, "learning_rate": 2.937939248607765e-05, "loss": 1.176, "step": 6597 }, { "epoch": 0.3643693395184449, "grad_norm": 3.042041301727295, "learning_rate": 2.937623280572098e-05, "loss": 0.2115, "step": 6598 }, { "epoch": 0.36442456372873866, "grad_norm": 2.334822416305542, "learning_rate": 2.9373072825391928e-05, "loss": 0.2446, "step": 6599 }, { "epoch": 0.36447978793903246, "grad_norm": 0.10884854197502136, "learning_rate": 2.9369912545191595e-05, "loss": 0.0026, "step": 6600 }, { "epoch": 0.36453501214932627, "grad_norm": 0.9912770986557007, "learning_rate": 2.936675196522108e-05, "loss": 0.036, "step": 6601 }, { "epoch": 0.36459023635962007, "grad_norm": 3.93815541267395, "learning_rate": 2.9363591085581512e-05, "loss": 1.464, "step": 6602 }, { "epoch": 0.36464546056991387, "grad_norm": 1.8976620435714722, "learning_rate": 2.9360429906374002e-05, "loss": 0.1747, "step": 6603 }, { "epoch": 0.3647006847802076, "grad_norm": 0.6822468638420105, "learning_rate": 2.9357268427699695e-05, "loss": 0.0251, "step": 6604 }, { "epoch": 0.3647559089905014, "grad_norm": 1.0186935663223267, "learning_rate": 2.935410664965973e-05, "loss": 0.1451, "step": 6605 }, { "epoch": 0.3648111332007952, "grad_norm": 4.629251003265381, "learning_rate": 2.935094457235526e-05, "loss": 0.6799, "step": 6606 }, { "epoch": 0.364866357411089, "grad_norm": 0.6629597544670105, "learning_rate": 2.9347782195887456e-05, "loss": 0.0233, "step": 6607 }, { "epoch": 0.36492158162138283, "grad_norm": 3.388627290725708, "learning_rate": 2.934461952035749e-05, "loss": 0.3999, "step": 6608 }, { "epoch": 0.36497680583167663, "grad_norm": 3.113276720046997, "learning_rate": 2.9341456545866537e-05, "loss": 0.2807, "step": 6609 }, { "epoch": 0.3650320300419704, "grad_norm": 1.6254180669784546, "learning_rate": 2.9338293272515796e-05, "loss": 0.0229, "step": 6610 }, { "epoch": 0.3650872542522642, "grad_norm": 2.3466365337371826, "learning_rate": 2.9335129700406474e-05, "loss": 0.3758, "step": 6611 }, { "epoch": 0.365142478462558, "grad_norm": 2.39337158203125, "learning_rate": 2.933196582963977e-05, "loss": 0.1385, "step": 6612 }, { "epoch": 0.3651977026728518, "grad_norm": 0.5099785327911377, "learning_rate": 2.9328801660316917e-05, "loss": 0.0167, "step": 6613 }, { "epoch": 0.3652529268831456, "grad_norm": 0.4247860014438629, "learning_rate": 2.9325637192539134e-05, "loss": 0.0174, "step": 6614 }, { "epoch": 0.36530815109343934, "grad_norm": 0.11741901189088821, "learning_rate": 2.9322472426407674e-05, "loss": 0.0031, "step": 6615 }, { "epoch": 0.36536337530373314, "grad_norm": 0.4682888686656952, "learning_rate": 2.9319307362023784e-05, "loss": 0.0094, "step": 6616 }, { "epoch": 0.36541859951402694, "grad_norm": 1.5038830041885376, "learning_rate": 2.9316141999488718e-05, "loss": 0.0231, "step": 6617 }, { "epoch": 0.36547382372432075, "grad_norm": 3.450132131576538, "learning_rate": 2.9312976338903743e-05, "loss": 0.3173, "step": 6618 }, { "epoch": 0.36552904793461455, "grad_norm": 0.8833643198013306, "learning_rate": 2.9309810380370146e-05, "loss": 0.0223, "step": 6619 }, { "epoch": 0.36558427214490835, "grad_norm": 0.09988924860954285, "learning_rate": 2.9306644123989213e-05, "loss": 0.0041, "step": 6620 }, { "epoch": 0.3656394963552021, "grad_norm": 1.866320252418518, "learning_rate": 2.9303477569862234e-05, "loss": 0.7449, "step": 6621 }, { "epoch": 0.3656947205654959, "grad_norm": 0.08490236848592758, "learning_rate": 2.9300310718090526e-05, "loss": 0.0029, "step": 6622 }, { "epoch": 0.3657499447757897, "grad_norm": 5.109613418579102, "learning_rate": 2.9297143568775403e-05, "loss": 0.768, "step": 6623 }, { "epoch": 0.3658051689860835, "grad_norm": 0.10222350805997849, "learning_rate": 2.9293976122018185e-05, "loss": 0.0029, "step": 6624 }, { "epoch": 0.3658603931963773, "grad_norm": 1.0422130823135376, "learning_rate": 2.929080837792022e-05, "loss": 0.044, "step": 6625 }, { "epoch": 0.3659156174066711, "grad_norm": 1.18805992603302, "learning_rate": 2.9287640336582836e-05, "loss": 0.0379, "step": 6626 }, { "epoch": 0.36597084161696486, "grad_norm": 0.07329319417476654, "learning_rate": 2.92844719981074e-05, "loss": 0.0023, "step": 6627 }, { "epoch": 0.36602606582725866, "grad_norm": 0.0666486918926239, "learning_rate": 2.928130336259527e-05, "loss": 0.0021, "step": 6628 }, { "epoch": 0.36608129003755246, "grad_norm": 3.078462600708008, "learning_rate": 2.927813443014783e-05, "loss": 0.874, "step": 6629 }, { "epoch": 0.36613651424784627, "grad_norm": 2.3630847930908203, "learning_rate": 2.9274965200866448e-05, "loss": 0.055, "step": 6630 }, { "epoch": 0.36619173845814007, "grad_norm": 3.185177803039551, "learning_rate": 2.927179567485253e-05, "loss": 0.1961, "step": 6631 }, { "epoch": 0.3662469626684338, "grad_norm": 0.20107927918434143, "learning_rate": 2.9268625852207476e-05, "loss": 0.003, "step": 6632 }, { "epoch": 0.3663021868787276, "grad_norm": 0.12968981266021729, "learning_rate": 2.926545573303268e-05, "loss": 0.0045, "step": 6633 }, { "epoch": 0.3663574110890214, "grad_norm": 3.117800712585449, "learning_rate": 2.9262285317429593e-05, "loss": 0.6297, "step": 6634 }, { "epoch": 0.3664126352993152, "grad_norm": 0.0824391171336174, "learning_rate": 2.9259114605499623e-05, "loss": 0.0026, "step": 6635 }, { "epoch": 0.36646785950960903, "grad_norm": 0.17295673489570618, "learning_rate": 2.925594359734422e-05, "loss": 0.0057, "step": 6636 }, { "epoch": 0.36652308371990283, "grad_norm": 4.020904064178467, "learning_rate": 2.9252772293064827e-05, "loss": 0.3157, "step": 6637 }, { "epoch": 0.3665783079301966, "grad_norm": 2.050908088684082, "learning_rate": 2.9249600692762906e-05, "loss": 0.1807, "step": 6638 }, { "epoch": 0.3666335321404904, "grad_norm": 0.06668655574321747, "learning_rate": 2.9246428796539933e-05, "loss": 0.0022, "step": 6639 }, { "epoch": 0.3666887563507842, "grad_norm": 4.015318870544434, "learning_rate": 2.924325660449738e-05, "loss": 0.2528, "step": 6640 }, { "epoch": 0.366743980561078, "grad_norm": 0.17712074518203735, "learning_rate": 2.9240084116736723e-05, "loss": 0.0043, "step": 6641 }, { "epoch": 0.3667992047713718, "grad_norm": 0.4269487261772156, "learning_rate": 2.9236911333359477e-05, "loss": 0.0082, "step": 6642 }, { "epoch": 0.36685442898166554, "grad_norm": 1.6203954219818115, "learning_rate": 2.923373825446714e-05, "loss": 0.4297, "step": 6643 }, { "epoch": 0.36690965319195934, "grad_norm": 3.620393753051758, "learning_rate": 2.923056488016123e-05, "loss": 0.5015, "step": 6644 }, { "epoch": 0.36696487740225314, "grad_norm": 1.3745297193527222, "learning_rate": 2.9227391210543273e-05, "loss": 0.0406, "step": 6645 }, { "epoch": 0.36702010161254695, "grad_norm": 0.018033817410469055, "learning_rate": 2.92242172457148e-05, "loss": 0.0006, "step": 6646 }, { "epoch": 0.36707532582284075, "grad_norm": 0.029190512374043465, "learning_rate": 2.9221042985777356e-05, "loss": 0.0009, "step": 6647 }, { "epoch": 0.36713055003313455, "grad_norm": 0.020403454080224037, "learning_rate": 2.9217868430832496e-05, "loss": 0.0006, "step": 6648 }, { "epoch": 0.3671857742434283, "grad_norm": 0.9492003917694092, "learning_rate": 2.921469358098178e-05, "loss": 0.0441, "step": 6649 }, { "epoch": 0.3672409984537221, "grad_norm": 0.18235690891742706, "learning_rate": 2.9211518436326796e-05, "loss": 0.0066, "step": 6650 }, { "epoch": 0.3672962226640159, "grad_norm": 1.459948182106018, "learning_rate": 2.92083429969691e-05, "loss": 0.0175, "step": 6651 }, { "epoch": 0.3673514468743097, "grad_norm": 4.499504089355469, "learning_rate": 2.9205167263010302e-05, "loss": 0.3064, "step": 6652 }, { "epoch": 0.3674066710846035, "grad_norm": 2.585066556930542, "learning_rate": 2.9201991234551993e-05, "loss": 0.3838, "step": 6653 }, { "epoch": 0.36746189529489726, "grad_norm": 0.9771249294281006, "learning_rate": 2.9198814911695792e-05, "loss": 0.0273, "step": 6654 }, { "epoch": 0.36751711950519106, "grad_norm": 3.908599615097046, "learning_rate": 2.9195638294543313e-05, "loss": 1.384, "step": 6655 }, { "epoch": 0.36757234371548486, "grad_norm": 2.1661670207977295, "learning_rate": 2.9192461383196186e-05, "loss": 0.1233, "step": 6656 }, { "epoch": 0.36762756792577866, "grad_norm": 2.1185004711151123, "learning_rate": 2.918928417775605e-05, "loss": 0.0841, "step": 6657 }, { "epoch": 0.36768279213607247, "grad_norm": 0.6440451145172119, "learning_rate": 2.918610667832455e-05, "loss": 0.0122, "step": 6658 }, { "epoch": 0.36773801634636627, "grad_norm": 4.469414710998535, "learning_rate": 2.9182928885003345e-05, "loss": 1.3124, "step": 6659 }, { "epoch": 0.36779324055666, "grad_norm": 3.3441507816314697, "learning_rate": 2.9179750797894107e-05, "loss": 0.4347, "step": 6660 }, { "epoch": 0.3678484647669538, "grad_norm": 2.9267423152923584, "learning_rate": 2.9176572417098503e-05, "loss": 0.4025, "step": 6661 }, { "epoch": 0.3679036889772476, "grad_norm": 3.209118604660034, "learning_rate": 2.917339374271823e-05, "loss": 0.0898, "step": 6662 }, { "epoch": 0.3679589131875414, "grad_norm": 0.23102299869060516, "learning_rate": 2.9170214774854968e-05, "loss": 0.0063, "step": 6663 }, { "epoch": 0.36801413739783523, "grad_norm": 3.140000581741333, "learning_rate": 2.9167035513610428e-05, "loss": 0.3078, "step": 6664 }, { "epoch": 0.36806936160812903, "grad_norm": 3.6619884967803955, "learning_rate": 2.916385595908633e-05, "loss": 1.1736, "step": 6665 }, { "epoch": 0.3681245858184228, "grad_norm": 0.028472380712628365, "learning_rate": 2.9160676111384387e-05, "loss": 0.001, "step": 6666 }, { "epoch": 0.3681798100287166, "grad_norm": 0.05208588391542435, "learning_rate": 2.915749597060634e-05, "loss": 0.0011, "step": 6667 }, { "epoch": 0.3682350342390104, "grad_norm": 2.9667725563049316, "learning_rate": 2.9154315536853925e-05, "loss": 0.0498, "step": 6668 }, { "epoch": 0.3682902584493042, "grad_norm": 0.6455103754997253, "learning_rate": 2.915113481022889e-05, "loss": 0.0258, "step": 6669 }, { "epoch": 0.368345482659598, "grad_norm": 0.3254740834236145, "learning_rate": 2.9147953790833007e-05, "loss": 0.008, "step": 6670 }, { "epoch": 0.36840070686989174, "grad_norm": 2.0804522037506104, "learning_rate": 2.914477247876804e-05, "loss": 0.4816, "step": 6671 }, { "epoch": 0.36845593108018554, "grad_norm": 2.8480653762817383, "learning_rate": 2.9141590874135764e-05, "loss": 0.2422, "step": 6672 }, { "epoch": 0.36851115529047934, "grad_norm": 0.5367550849914551, "learning_rate": 2.9138408977037974e-05, "loss": 0.0178, "step": 6673 }, { "epoch": 0.36856637950077314, "grad_norm": 0.5453229546546936, "learning_rate": 2.913522678757646e-05, "loss": 0.0165, "step": 6674 }, { "epoch": 0.36862160371106695, "grad_norm": 0.3746502995491028, "learning_rate": 2.9132044305853035e-05, "loss": 0.0086, "step": 6675 }, { "epoch": 0.36867682792136075, "grad_norm": 0.3868195116519928, "learning_rate": 2.9128861531969517e-05, "loss": 0.0796, "step": 6676 }, { "epoch": 0.3687320521316545, "grad_norm": 0.020520078018307686, "learning_rate": 2.9125678466027727e-05, "loss": 0.0008, "step": 6677 }, { "epoch": 0.3687872763419483, "grad_norm": 1.9054629802703857, "learning_rate": 2.912249510812951e-05, "loss": 0.3189, "step": 6678 }, { "epoch": 0.3688425005522421, "grad_norm": 0.22827941179275513, "learning_rate": 2.9119311458376698e-05, "loss": 0.0089, "step": 6679 }, { "epoch": 0.3688977247625359, "grad_norm": 1.8315865993499756, "learning_rate": 2.9116127516871154e-05, "loss": 0.1248, "step": 6680 }, { "epoch": 0.3689529489728297, "grad_norm": 0.7033730149269104, "learning_rate": 2.9112943283714737e-05, "loss": 0.0143, "step": 6681 }, { "epoch": 0.36900817318312346, "grad_norm": 0.17624595761299133, "learning_rate": 2.9109758759009316e-05, "loss": 0.0039, "step": 6682 }, { "epoch": 0.36906339739341726, "grad_norm": 0.831415593624115, "learning_rate": 2.9106573942856785e-05, "loss": 0.0254, "step": 6683 }, { "epoch": 0.36911862160371106, "grad_norm": 2.3149490356445312, "learning_rate": 2.9103388835359028e-05, "loss": 0.3779, "step": 6684 }, { "epoch": 0.36917384581400486, "grad_norm": 0.1548437476158142, "learning_rate": 2.9100203436617937e-05, "loss": 0.0053, "step": 6685 }, { "epoch": 0.36922907002429867, "grad_norm": 0.13786689937114716, "learning_rate": 2.9097017746735443e-05, "loss": 0.0039, "step": 6686 }, { "epoch": 0.36928429423459247, "grad_norm": 3.034334897994995, "learning_rate": 2.909383176581345e-05, "loss": 0.2351, "step": 6687 }, { "epoch": 0.3693395184448862, "grad_norm": 0.1381697952747345, "learning_rate": 2.9090645493953886e-05, "loss": 0.0027, "step": 6688 }, { "epoch": 0.36939474265518, "grad_norm": 5.635626792907715, "learning_rate": 2.9087458931258692e-05, "loss": 0.783, "step": 6689 }, { "epoch": 0.3694499668654738, "grad_norm": 0.42577704787254333, "learning_rate": 2.9084272077829818e-05, "loss": 0.0096, "step": 6690 }, { "epoch": 0.3695051910757676, "grad_norm": 3.7868545055389404, "learning_rate": 2.908108493376922e-05, "loss": 1.0471, "step": 6691 }, { "epoch": 0.36956041528606143, "grad_norm": 0.20857921242713928, "learning_rate": 2.9077897499178864e-05, "loss": 0.0043, "step": 6692 }, { "epoch": 0.3696156394963552, "grad_norm": 0.0395674854516983, "learning_rate": 2.907470977416072e-05, "loss": 0.0014, "step": 6693 }, { "epoch": 0.369670863706649, "grad_norm": 3.9436440467834473, "learning_rate": 2.9071521758816775e-05, "loss": 0.7716, "step": 6694 }, { "epoch": 0.3697260879169428, "grad_norm": 2.6957857608795166, "learning_rate": 2.9068333453249025e-05, "loss": 0.5793, "step": 6695 }, { "epoch": 0.3697813121272366, "grad_norm": 0.04699874296784401, "learning_rate": 2.9065144857559474e-05, "loss": 0.0012, "step": 6696 }, { "epoch": 0.3698365363375304, "grad_norm": 0.5361711382865906, "learning_rate": 2.9061955971850127e-05, "loss": 0.0177, "step": 6697 }, { "epoch": 0.3698917605478242, "grad_norm": 0.7730131149291992, "learning_rate": 2.905876679622301e-05, "loss": 0.0198, "step": 6698 }, { "epoch": 0.36994698475811794, "grad_norm": 1.2372130155563354, "learning_rate": 2.905557733078016e-05, "loss": 0.0351, "step": 6699 }, { "epoch": 0.37000220896841174, "grad_norm": 2.1779987812042236, "learning_rate": 2.9052387575623605e-05, "loss": 0.4829, "step": 6700 }, { "epoch": 0.37005743317870554, "grad_norm": 0.07850755751132965, "learning_rate": 2.9049197530855404e-05, "loss": 0.0028, "step": 6701 }, { "epoch": 0.37011265738899934, "grad_norm": 1.783922553062439, "learning_rate": 2.904600719657761e-05, "loss": 0.3581, "step": 6702 }, { "epoch": 0.37016788159929315, "grad_norm": 0.34858179092407227, "learning_rate": 2.9042816572892292e-05, "loss": 0.0127, "step": 6703 }, { "epoch": 0.37022310580958695, "grad_norm": 2.7327616214752197, "learning_rate": 2.903962565990153e-05, "loss": 0.5551, "step": 6704 }, { "epoch": 0.3702783300198807, "grad_norm": 0.3912128508090973, "learning_rate": 2.903643445770741e-05, "loss": 0.0111, "step": 6705 }, { "epoch": 0.3703335542301745, "grad_norm": 3.036133289337158, "learning_rate": 2.903324296641202e-05, "loss": 0.5603, "step": 6706 }, { "epoch": 0.3703887784404683, "grad_norm": 2.663295030593872, "learning_rate": 2.903005118611748e-05, "loss": 0.3148, "step": 6707 }, { "epoch": 0.3704440026507621, "grad_norm": 2.0731709003448486, "learning_rate": 2.902685911692589e-05, "loss": 0.2726, "step": 6708 }, { "epoch": 0.3704992268610559, "grad_norm": 0.11394893378019333, "learning_rate": 2.9023666758939378e-05, "loss": 0.0043, "step": 6709 }, { "epoch": 0.37055445107134966, "grad_norm": 2.812737464904785, "learning_rate": 2.9020474112260085e-05, "loss": 0.3195, "step": 6710 }, { "epoch": 0.37060967528164346, "grad_norm": 4.258680820465088, "learning_rate": 2.9017281176990132e-05, "loss": 0.7801, "step": 6711 }, { "epoch": 0.37066489949193726, "grad_norm": 3.170928955078125, "learning_rate": 2.9014087953231694e-05, "loss": 0.7076, "step": 6712 }, { "epoch": 0.37072012370223106, "grad_norm": 1.2966388463974, "learning_rate": 2.9010894441086912e-05, "loss": 0.0369, "step": 6713 }, { "epoch": 0.37077534791252487, "grad_norm": 0.04046085849404335, "learning_rate": 2.900770064065797e-05, "loss": 0.0019, "step": 6714 }, { "epoch": 0.37083057212281867, "grad_norm": 0.13859273493289948, "learning_rate": 2.9004506552047038e-05, "loss": 0.0056, "step": 6715 }, { "epoch": 0.3708857963331124, "grad_norm": 0.8830586671829224, "learning_rate": 2.9001312175356307e-05, "loss": 0.0256, "step": 6716 }, { "epoch": 0.3709410205434062, "grad_norm": 1.8569406270980835, "learning_rate": 2.8998117510687974e-05, "loss": 0.0319, "step": 6717 }, { "epoch": 0.3709962447537, "grad_norm": 3.2437427043914795, "learning_rate": 2.8994922558144245e-05, "loss": 0.4792, "step": 6718 }, { "epoch": 0.3710514689639938, "grad_norm": 0.6039767861366272, "learning_rate": 2.8991727317827334e-05, "loss": 0.0169, "step": 6719 }, { "epoch": 0.3711066931742876, "grad_norm": 4.022526264190674, "learning_rate": 2.8988531789839474e-05, "loss": 0.7434, "step": 6720 }, { "epoch": 0.3711619173845814, "grad_norm": 0.6343451142311096, "learning_rate": 2.8985335974282887e-05, "loss": 0.0184, "step": 6721 }, { "epoch": 0.3712171415948752, "grad_norm": 4.63922119140625, "learning_rate": 2.8982139871259822e-05, "loss": 0.5563, "step": 6722 }, { "epoch": 0.371272365805169, "grad_norm": 0.05729634314775467, "learning_rate": 2.897894348087254e-05, "loss": 0.0017, "step": 6723 }, { "epoch": 0.3713275900154628, "grad_norm": 0.10299620777368546, "learning_rate": 2.8975746803223282e-05, "loss": 0.0037, "step": 6724 }, { "epoch": 0.3713828142257566, "grad_norm": 0.1242276057600975, "learning_rate": 2.8972549838414338e-05, "loss": 0.0048, "step": 6725 }, { "epoch": 0.3714380384360504, "grad_norm": 0.06695688515901566, "learning_rate": 2.8969352586547978e-05, "loss": 0.0022, "step": 6726 }, { "epoch": 0.37149326264634414, "grad_norm": 0.19323383271694183, "learning_rate": 2.89661550477265e-05, "loss": 0.0057, "step": 6727 }, { "epoch": 0.37154848685663794, "grad_norm": 0.0548861138522625, "learning_rate": 2.8962957222052187e-05, "loss": 0.0023, "step": 6728 }, { "epoch": 0.37160371106693174, "grad_norm": 0.026019692420959473, "learning_rate": 2.8959759109627362e-05, "loss": 0.001, "step": 6729 }, { "epoch": 0.37165893527722554, "grad_norm": 1.6362968683242798, "learning_rate": 2.8956560710554337e-05, "loss": 0.1695, "step": 6730 }, { "epoch": 0.37171415948751935, "grad_norm": 3.6640713214874268, "learning_rate": 2.8953362024935433e-05, "loss": 0.9324, "step": 6731 }, { "epoch": 0.3717693836978131, "grad_norm": 0.06235191598534584, "learning_rate": 2.8950163052872994e-05, "loss": 0.002, "step": 6732 }, { "epoch": 0.3718246079081069, "grad_norm": 1.3706285953521729, "learning_rate": 2.894696379446935e-05, "loss": 0.0943, "step": 6733 }, { "epoch": 0.3718798321184007, "grad_norm": 3.501972198486328, "learning_rate": 2.894376424982687e-05, "loss": 1.0645, "step": 6734 }, { "epoch": 0.3719350563286945, "grad_norm": 2.269958734512329, "learning_rate": 2.894056441904791e-05, "loss": 0.4943, "step": 6735 }, { "epoch": 0.3719902805389883, "grad_norm": 0.037643447518348694, "learning_rate": 2.8937364302234844e-05, "loss": 0.0012, "step": 6736 }, { "epoch": 0.3720455047492821, "grad_norm": 0.12420742958784103, "learning_rate": 2.8934163899490044e-05, "loss": 0.0028, "step": 6737 }, { "epoch": 0.37210072895957585, "grad_norm": 4.254518032073975, "learning_rate": 2.8930963210915907e-05, "loss": 0.8205, "step": 6738 }, { "epoch": 0.37215595316986966, "grad_norm": 3.9673757553100586, "learning_rate": 2.892776223661484e-05, "loss": 0.1151, "step": 6739 }, { "epoch": 0.37221117738016346, "grad_norm": 0.04659133777022362, "learning_rate": 2.892456097668923e-05, "loss": 0.0021, "step": 6740 }, { "epoch": 0.37226640159045726, "grad_norm": 3.357048511505127, "learning_rate": 2.8921359431241514e-05, "loss": 0.5173, "step": 6741 }, { "epoch": 0.37232162580075107, "grad_norm": 1.4780322313308716, "learning_rate": 2.8918157600374113e-05, "loss": 0.0597, "step": 6742 }, { "epoch": 0.37237685001104487, "grad_norm": 2.2977075576782227, "learning_rate": 2.891495548418946e-05, "loss": 0.1504, "step": 6743 }, { "epoch": 0.3724320742213386, "grad_norm": 0.5549628734588623, "learning_rate": 2.8911753082790005e-05, "loss": 0.02, "step": 6744 }, { "epoch": 0.3724872984316324, "grad_norm": 2.3558309078216553, "learning_rate": 2.8908550396278187e-05, "loss": 0.1741, "step": 6745 }, { "epoch": 0.3725425226419262, "grad_norm": 3.19816517829895, "learning_rate": 2.890534742475649e-05, "loss": 0.3902, "step": 6746 }, { "epoch": 0.37259774685222, "grad_norm": 0.048486728221178055, "learning_rate": 2.8902144168327377e-05, "loss": 0.002, "step": 6747 }, { "epoch": 0.3726529710625138, "grad_norm": 2.6911513805389404, "learning_rate": 2.8898940627093322e-05, "loss": 0.2332, "step": 6748 }, { "epoch": 0.3727081952728076, "grad_norm": 0.6201191544532776, "learning_rate": 2.889573680115683e-05, "loss": 0.0198, "step": 6749 }, { "epoch": 0.3727634194831014, "grad_norm": 0.05732714384794235, "learning_rate": 2.8892532690620388e-05, "loss": 0.0028, "step": 6750 }, { "epoch": 0.3728186436933952, "grad_norm": 5.5392746925354, "learning_rate": 2.888932829558651e-05, "loss": 1.1804, "step": 6751 }, { "epoch": 0.372873867903689, "grad_norm": 3.118682622909546, "learning_rate": 2.8886123616157716e-05, "loss": 0.255, "step": 6752 }, { "epoch": 0.3729290921139828, "grad_norm": 0.10677345097064972, "learning_rate": 2.8882918652436523e-05, "loss": 0.0036, "step": 6753 }, { "epoch": 0.3729843163242766, "grad_norm": 0.21896407008171082, "learning_rate": 2.887971340452548e-05, "loss": 0.0069, "step": 6754 }, { "epoch": 0.37303954053457034, "grad_norm": 5.84863805770874, "learning_rate": 2.887650787252712e-05, "loss": 0.9456, "step": 6755 }, { "epoch": 0.37309476474486414, "grad_norm": 0.21041862666606903, "learning_rate": 2.887330205654401e-05, "loss": 0.0067, "step": 6756 }, { "epoch": 0.37314998895515794, "grad_norm": 2.442124128341675, "learning_rate": 2.8870095956678702e-05, "loss": 0.1977, "step": 6757 }, { "epoch": 0.37320521316545174, "grad_norm": 2.004399538040161, "learning_rate": 2.886688957303377e-05, "loss": 0.0881, "step": 6758 }, { "epoch": 0.37326043737574555, "grad_norm": 2.0936551094055176, "learning_rate": 2.8863682905711802e-05, "loss": 0.2637, "step": 6759 }, { "epoch": 0.3733156615860393, "grad_norm": 0.14938724040985107, "learning_rate": 2.8860475954815387e-05, "loss": 0.0023, "step": 6760 }, { "epoch": 0.3733708857963331, "grad_norm": 6.384872913360596, "learning_rate": 2.8857268720447114e-05, "loss": 0.825, "step": 6761 }, { "epoch": 0.3734261100066269, "grad_norm": 0.7726407647132874, "learning_rate": 2.8854061202709603e-05, "loss": 0.035, "step": 6762 }, { "epoch": 0.3734813342169207, "grad_norm": 0.03759060427546501, "learning_rate": 2.8850853401705463e-05, "loss": 0.0011, "step": 6763 }, { "epoch": 0.3735365584272145, "grad_norm": 2.333951711654663, "learning_rate": 2.8847645317537335e-05, "loss": 0.832, "step": 6764 }, { "epoch": 0.3735917826375083, "grad_norm": 0.32066383957862854, "learning_rate": 2.8844436950307835e-05, "loss": 0.0115, "step": 6765 }, { "epoch": 0.37364700684780205, "grad_norm": 3.89121150970459, "learning_rate": 2.884122830011962e-05, "loss": 0.9792, "step": 6766 }, { "epoch": 0.37370223105809586, "grad_norm": 0.9938993453979492, "learning_rate": 2.883801936707535e-05, "loss": 0.0206, "step": 6767 }, { "epoch": 0.37375745526838966, "grad_norm": 0.08098293840885162, "learning_rate": 2.8834810151277673e-05, "loss": 0.0034, "step": 6768 }, { "epoch": 0.37381267947868346, "grad_norm": 1.9843642711639404, "learning_rate": 2.8831600652829265e-05, "loss": 0.1137, "step": 6769 }, { "epoch": 0.37386790368897727, "grad_norm": 0.04734933748841286, "learning_rate": 2.8828390871832818e-05, "loss": 0.0013, "step": 6770 }, { "epoch": 0.373923127899271, "grad_norm": 0.026461301371455193, "learning_rate": 2.882518080839101e-05, "loss": 0.0007, "step": 6771 }, { "epoch": 0.3739783521095648, "grad_norm": 1.2465180158615112, "learning_rate": 2.8821970462606543e-05, "loss": 0.0539, "step": 6772 }, { "epoch": 0.3740335763198586, "grad_norm": 0.0653664693236351, "learning_rate": 2.8818759834582122e-05, "loss": 0.0022, "step": 6773 }, { "epoch": 0.3740888005301524, "grad_norm": 1.0810527801513672, "learning_rate": 2.8815548924420476e-05, "loss": 0.1319, "step": 6774 }, { "epoch": 0.3741440247404462, "grad_norm": 1.4038910865783691, "learning_rate": 2.881233773222432e-05, "loss": 0.0476, "step": 6775 }, { "epoch": 0.37419924895074, "grad_norm": 2.6282572746276855, "learning_rate": 2.880912625809639e-05, "loss": 0.2806, "step": 6776 }, { "epoch": 0.3742544731610338, "grad_norm": 1.4204987287521362, "learning_rate": 2.8805914502139437e-05, "loss": 0.0527, "step": 6777 }, { "epoch": 0.3743096973713276, "grad_norm": 0.7207887768745422, "learning_rate": 2.8802702464456205e-05, "loss": 0.0289, "step": 6778 }, { "epoch": 0.3743649215816214, "grad_norm": 1.041733741760254, "learning_rate": 2.8799490145149457e-05, "loss": 0.0218, "step": 6779 }, { "epoch": 0.3744201457919152, "grad_norm": 3.362253427505493, "learning_rate": 2.879627754432198e-05, "loss": 0.2597, "step": 6780 }, { "epoch": 0.374475370002209, "grad_norm": 3.3090627193450928, "learning_rate": 2.879306466207653e-05, "loss": 0.8772, "step": 6781 }, { "epoch": 0.3745305942125028, "grad_norm": 0.8178420066833496, "learning_rate": 2.8789851498515918e-05, "loss": 0.2382, "step": 6782 }, { "epoch": 0.37458581842279653, "grad_norm": 1.3111881017684937, "learning_rate": 2.8786638053742933e-05, "loss": 0.2049, "step": 6783 }, { "epoch": 0.37464104263309034, "grad_norm": 0.07233383506536484, "learning_rate": 2.8783424327860374e-05, "loss": 0.0026, "step": 6784 }, { "epoch": 0.37469626684338414, "grad_norm": 0.8605263829231262, "learning_rate": 2.8780210320971074e-05, "loss": 0.0187, "step": 6785 }, { "epoch": 0.37475149105367794, "grad_norm": 1.7562859058380127, "learning_rate": 2.877699603317784e-05, "loss": 0.1339, "step": 6786 }, { "epoch": 0.37480671526397175, "grad_norm": 2.415376663208008, "learning_rate": 2.8773781464583525e-05, "loss": 0.4965, "step": 6787 }, { "epoch": 0.3748619394742655, "grad_norm": 2.351936101913452, "learning_rate": 2.8770566615290963e-05, "loss": 0.6095, "step": 6788 }, { "epoch": 0.3749171636845593, "grad_norm": 1.3369060754776, "learning_rate": 2.8767351485403e-05, "loss": 0.0484, "step": 6789 }, { "epoch": 0.3749723878948531, "grad_norm": 3.0497851371765137, "learning_rate": 2.8764136075022507e-05, "loss": 0.3773, "step": 6790 }, { "epoch": 0.3750276121051469, "grad_norm": 1.5749691724777222, "learning_rate": 2.8760920384252355e-05, "loss": 0.261, "step": 6791 }, { "epoch": 0.3750828363154407, "grad_norm": 0.06617290526628494, "learning_rate": 2.875770441319541e-05, "loss": 0.0032, "step": 6792 }, { "epoch": 0.3751380605257345, "grad_norm": 6.053613185882568, "learning_rate": 2.8754488161954578e-05, "loss": 0.1025, "step": 6793 }, { "epoch": 0.37519328473602825, "grad_norm": 0.1125057265162468, "learning_rate": 2.8751271630632734e-05, "loss": 0.003, "step": 6794 }, { "epoch": 0.37524850894632206, "grad_norm": 0.27483299374580383, "learning_rate": 2.8748054819332806e-05, "loss": 0.0034, "step": 6795 }, { "epoch": 0.37530373315661586, "grad_norm": 0.15233954787254333, "learning_rate": 2.8744837728157698e-05, "loss": 0.0046, "step": 6796 }, { "epoch": 0.37535895736690966, "grad_norm": 4.0457353591918945, "learning_rate": 2.8741620357210336e-05, "loss": 0.7307, "step": 6797 }, { "epoch": 0.37541418157720347, "grad_norm": 2.209763526916504, "learning_rate": 2.8738402706593653e-05, "loss": 0.1149, "step": 6798 }, { "epoch": 0.3754694057874972, "grad_norm": 0.774225652217865, "learning_rate": 2.873518477641059e-05, "loss": 0.0142, "step": 6799 }, { "epoch": 0.375524629997791, "grad_norm": 3.2797744274139404, "learning_rate": 2.8731966566764096e-05, "loss": 0.844, "step": 6800 }, { "epoch": 0.3755798542080848, "grad_norm": 6.468319892883301, "learning_rate": 2.8728748077757136e-05, "loss": 1.3716, "step": 6801 }, { "epoch": 0.3756350784183786, "grad_norm": 1.0948715209960938, "learning_rate": 2.872552930949267e-05, "loss": 0.0433, "step": 6802 }, { "epoch": 0.3756903026286724, "grad_norm": 1.5134119987487793, "learning_rate": 2.8722310262073686e-05, "loss": 0.0703, "step": 6803 }, { "epoch": 0.3757455268389662, "grad_norm": 4.581601619720459, "learning_rate": 2.8719090935603168e-05, "loss": 0.9739, "step": 6804 }, { "epoch": 0.37580075104926, "grad_norm": 0.0876225084066391, "learning_rate": 2.8715871330184103e-05, "loss": 0.0021, "step": 6805 }, { "epoch": 0.3758559752595538, "grad_norm": 0.816748857498169, "learning_rate": 2.8712651445919505e-05, "loss": 0.0293, "step": 6806 }, { "epoch": 0.3759111994698476, "grad_norm": 0.1528901904821396, "learning_rate": 2.870943128291238e-05, "loss": 0.0035, "step": 6807 }, { "epoch": 0.3759664236801414, "grad_norm": 0.05353468284010887, "learning_rate": 2.870621084126575e-05, "loss": 0.0019, "step": 6808 }, { "epoch": 0.3760216478904352, "grad_norm": 3.1451334953308105, "learning_rate": 2.870299012108266e-05, "loss": 0.43, "step": 6809 }, { "epoch": 0.376076872100729, "grad_norm": 1.673078179359436, "learning_rate": 2.869976912246613e-05, "loss": 0.0257, "step": 6810 }, { "epoch": 0.37613209631102273, "grad_norm": 5.616189479827881, "learning_rate": 2.8696547845519226e-05, "loss": 1.2086, "step": 6811 }, { "epoch": 0.37618732052131654, "grad_norm": 0.07296796143054962, "learning_rate": 2.8693326290344998e-05, "loss": 0.0022, "step": 6812 }, { "epoch": 0.37624254473161034, "grad_norm": 1.2150259017944336, "learning_rate": 2.8690104457046506e-05, "loss": 0.0379, "step": 6813 }, { "epoch": 0.37629776894190414, "grad_norm": 1.1802470684051514, "learning_rate": 2.868688234572684e-05, "loss": 0.0241, "step": 6814 }, { "epoch": 0.37635299315219795, "grad_norm": 0.033195242285728455, "learning_rate": 2.8683659956489075e-05, "loss": 0.0012, "step": 6815 }, { "epoch": 0.3764082173624917, "grad_norm": 1.6477938890457153, "learning_rate": 2.8680437289436303e-05, "loss": 0.1093, "step": 6816 }, { "epoch": 0.3764634415727855, "grad_norm": 0.5017552971839905, "learning_rate": 2.8677214344671637e-05, "loss": 0.0199, "step": 6817 }, { "epoch": 0.3765186657830793, "grad_norm": 2.300837755203247, "learning_rate": 2.8673991122298173e-05, "loss": 0.2652, "step": 6818 }, { "epoch": 0.3765738899933731, "grad_norm": 0.7620238661766052, "learning_rate": 2.867076762241905e-05, "loss": 0.0236, "step": 6819 }, { "epoch": 0.3766291142036669, "grad_norm": 2.1178529262542725, "learning_rate": 2.8667543845137376e-05, "loss": 0.3033, "step": 6820 }, { "epoch": 0.3766843384139607, "grad_norm": 0.8606855273246765, "learning_rate": 2.8664319790556302e-05, "loss": 0.0171, "step": 6821 }, { "epoch": 0.37673956262425445, "grad_norm": 4.683266639709473, "learning_rate": 2.8661095458778976e-05, "loss": 0.8135, "step": 6822 }, { "epoch": 0.37679478683454826, "grad_norm": 5.338189125061035, "learning_rate": 2.8657870849908543e-05, "loss": 1.2382, "step": 6823 }, { "epoch": 0.37685001104484206, "grad_norm": 5.850948333740234, "learning_rate": 2.8654645964048175e-05, "loss": 0.6406, "step": 6824 }, { "epoch": 0.37690523525513586, "grad_norm": 0.42427295446395874, "learning_rate": 2.8651420801301052e-05, "loss": 0.0106, "step": 6825 }, { "epoch": 0.37696045946542966, "grad_norm": 4.4758477210998535, "learning_rate": 2.8648195361770338e-05, "loss": 0.4999, "step": 6826 }, { "epoch": 0.3770156836757234, "grad_norm": 0.0668036937713623, "learning_rate": 2.864496964555924e-05, "loss": 0.0023, "step": 6827 }, { "epoch": 0.3770709078860172, "grad_norm": 0.03971630707383156, "learning_rate": 2.8641743652770947e-05, "loss": 0.0021, "step": 6828 }, { "epoch": 0.377126132096311, "grad_norm": 1.5208590030670166, "learning_rate": 2.863851738350867e-05, "loss": 0.1267, "step": 6829 }, { "epoch": 0.3771813563066048, "grad_norm": 2.0457589626312256, "learning_rate": 2.8635290837875643e-05, "loss": 0.0853, "step": 6830 }, { "epoch": 0.3772365805168986, "grad_norm": 2.7694308757781982, "learning_rate": 2.863206401597507e-05, "loss": 0.3108, "step": 6831 }, { "epoch": 0.3772918047271924, "grad_norm": 0.15945883095264435, "learning_rate": 2.8628836917910196e-05, "loss": 0.0054, "step": 6832 }, { "epoch": 0.3773470289374862, "grad_norm": 0.04785123094916344, "learning_rate": 2.8625609543784256e-05, "loss": 0.0015, "step": 6833 }, { "epoch": 0.37740225314778, "grad_norm": 2.926126003265381, "learning_rate": 2.862238189370052e-05, "loss": 0.8508, "step": 6834 }, { "epoch": 0.3774574773580738, "grad_norm": 0.13329611718654633, "learning_rate": 2.8619153967762237e-05, "loss": 0.0021, "step": 6835 }, { "epoch": 0.3775127015683676, "grad_norm": 1.1326637268066406, "learning_rate": 2.8615925766072684e-05, "loss": 0.135, "step": 6836 }, { "epoch": 0.3775679257786614, "grad_norm": 0.1292189061641693, "learning_rate": 2.8612697288735134e-05, "loss": 0.003, "step": 6837 }, { "epoch": 0.37762314998895513, "grad_norm": 3.6412272453308105, "learning_rate": 2.8609468535852884e-05, "loss": 0.0782, "step": 6838 }, { "epoch": 0.37767837419924893, "grad_norm": 0.1740296483039856, "learning_rate": 2.8606239507529214e-05, "loss": 0.0049, "step": 6839 }, { "epoch": 0.37773359840954274, "grad_norm": 0.05186976492404938, "learning_rate": 2.860301020386745e-05, "loss": 0.0017, "step": 6840 }, { "epoch": 0.37778882261983654, "grad_norm": 0.49712106585502625, "learning_rate": 2.8599780624970896e-05, "loss": 0.0209, "step": 6841 }, { "epoch": 0.37784404683013034, "grad_norm": 0.8405640125274658, "learning_rate": 2.8596550770942876e-05, "loss": 0.1854, "step": 6842 }, { "epoch": 0.37789927104042415, "grad_norm": 1.0630066394805908, "learning_rate": 2.8593320641886725e-05, "loss": 0.0523, "step": 6843 }, { "epoch": 0.3779544952507179, "grad_norm": 3.837608814239502, "learning_rate": 2.859009023790578e-05, "loss": 0.4748, "step": 6844 }, { "epoch": 0.3780097194610117, "grad_norm": 1.1683197021484375, "learning_rate": 2.85868595591034e-05, "loss": 0.1976, "step": 6845 }, { "epoch": 0.3780649436713055, "grad_norm": 0.3547234833240509, "learning_rate": 2.8583628605582928e-05, "loss": 0.0078, "step": 6846 }, { "epoch": 0.3781201678815993, "grad_norm": 0.026984579861164093, "learning_rate": 2.8580397377447748e-05, "loss": 0.0011, "step": 6847 }, { "epoch": 0.3781753920918931, "grad_norm": 2.290626287460327, "learning_rate": 2.8577165874801224e-05, "loss": 0.3134, "step": 6848 }, { "epoch": 0.3782306163021869, "grad_norm": 0.22682367265224457, "learning_rate": 2.8573934097746746e-05, "loss": 0.0079, "step": 6849 }, { "epoch": 0.37828584051248065, "grad_norm": 2.9703330993652344, "learning_rate": 2.8570702046387708e-05, "loss": 0.4171, "step": 6850 }, { "epoch": 0.37834106472277446, "grad_norm": 0.06976671516895294, "learning_rate": 2.8567469720827517e-05, "loss": 0.0025, "step": 6851 }, { "epoch": 0.37839628893306826, "grad_norm": 0.11517946422100067, "learning_rate": 2.8564237121169572e-05, "loss": 0.0033, "step": 6852 }, { "epoch": 0.37845151314336206, "grad_norm": 3.212613582611084, "learning_rate": 2.8561004247517302e-05, "loss": 0.5499, "step": 6853 }, { "epoch": 0.37850673735365586, "grad_norm": 1.6387829780578613, "learning_rate": 2.855777109997413e-05, "loss": 0.0382, "step": 6854 }, { "epoch": 0.3785619615639496, "grad_norm": 7.786330223083496, "learning_rate": 2.8554537678643502e-05, "loss": 2.4533, "step": 6855 }, { "epoch": 0.3786171857742434, "grad_norm": 0.4456309676170349, "learning_rate": 2.8551303983628865e-05, "loss": 0.0101, "step": 6856 }, { "epoch": 0.3786724099845372, "grad_norm": 0.03141437843441963, "learning_rate": 2.8548070015033662e-05, "loss": 0.0011, "step": 6857 }, { "epoch": 0.378727634194831, "grad_norm": 1.8360658884048462, "learning_rate": 2.8544835772961367e-05, "loss": 0.224, "step": 6858 }, { "epoch": 0.3787828584051248, "grad_norm": 0.07140962034463882, "learning_rate": 2.854160125751545e-05, "loss": 0.0027, "step": 6859 }, { "epoch": 0.3788380826154186, "grad_norm": 0.07801360636949539, "learning_rate": 2.8538366468799385e-05, "loss": 0.0022, "step": 6860 }, { "epoch": 0.3788933068257124, "grad_norm": 0.11906863749027252, "learning_rate": 2.853513140691668e-05, "loss": 0.0055, "step": 6861 }, { "epoch": 0.3789485310360062, "grad_norm": 0.13944083452224731, "learning_rate": 2.8531896071970813e-05, "loss": 0.0036, "step": 6862 }, { "epoch": 0.3790037552463, "grad_norm": 1.2322537899017334, "learning_rate": 2.852866046406531e-05, "loss": 0.0818, "step": 6863 }, { "epoch": 0.3790589794565938, "grad_norm": 0.5745251774787903, "learning_rate": 2.8525424583303674e-05, "loss": 0.0142, "step": 6864 }, { "epoch": 0.3791142036668876, "grad_norm": 0.22806914150714874, "learning_rate": 2.8522188429789434e-05, "loss": 0.0065, "step": 6865 }, { "epoch": 0.37916942787718133, "grad_norm": 5.054307460784912, "learning_rate": 2.851895200362613e-05, "loss": 0.3409, "step": 6866 }, { "epoch": 0.37922465208747513, "grad_norm": 2.3228745460510254, "learning_rate": 2.8515715304917292e-05, "loss": 0.1755, "step": 6867 }, { "epoch": 0.37927987629776894, "grad_norm": 2.7910470962524414, "learning_rate": 2.8512478333766477e-05, "loss": 0.3277, "step": 6868 }, { "epoch": 0.37933510050806274, "grad_norm": 0.9220260381698608, "learning_rate": 2.8509241090277256e-05, "loss": 0.0209, "step": 6869 }, { "epoch": 0.37939032471835654, "grad_norm": 0.03042151778936386, "learning_rate": 2.850600357455318e-05, "loss": 0.001, "step": 6870 }, { "epoch": 0.37944554892865034, "grad_norm": 2.584684133529663, "learning_rate": 2.8502765786697833e-05, "loss": 0.4861, "step": 6871 }, { "epoch": 0.3795007731389441, "grad_norm": 1.8165773153305054, "learning_rate": 2.849952772681481e-05, "loss": 0.1439, "step": 6872 }, { "epoch": 0.3795559973492379, "grad_norm": 0.6923748254776001, "learning_rate": 2.849628939500769e-05, "loss": 0.0139, "step": 6873 }, { "epoch": 0.3796112215595317, "grad_norm": 1.1157935857772827, "learning_rate": 2.849305079138009e-05, "loss": 0.1504, "step": 6874 }, { "epoch": 0.3796664457698255, "grad_norm": 0.11277131736278534, "learning_rate": 2.8489811916035612e-05, "loss": 0.0037, "step": 6875 }, { "epoch": 0.3797216699801193, "grad_norm": 1.4688689708709717, "learning_rate": 2.8486572769077885e-05, "loss": 0.2392, "step": 6876 }, { "epoch": 0.37977689419041305, "grad_norm": 1.1445375680923462, "learning_rate": 2.8483333350610534e-05, "loss": 0.041, "step": 6877 }, { "epoch": 0.37983211840070685, "grad_norm": 0.07544039189815521, "learning_rate": 2.8480093660737198e-05, "loss": 0.0024, "step": 6878 }, { "epoch": 0.37988734261100066, "grad_norm": 4.014171600341797, "learning_rate": 2.8476853699561523e-05, "loss": 0.567, "step": 6879 }, { "epoch": 0.37994256682129446, "grad_norm": 0.10203119367361069, "learning_rate": 2.8473613467187168e-05, "loss": 0.004, "step": 6880 }, { "epoch": 0.37999779103158826, "grad_norm": 4.9277119636535645, "learning_rate": 2.847037296371779e-05, "loss": 0.9091, "step": 6881 }, { "epoch": 0.38005301524188206, "grad_norm": 4.435093402862549, "learning_rate": 2.8467132189257076e-05, "loss": 0.434, "step": 6882 }, { "epoch": 0.3801082394521758, "grad_norm": 3.5776655673980713, "learning_rate": 2.8463891143908688e-05, "loss": 0.8202, "step": 6883 }, { "epoch": 0.3801634636624696, "grad_norm": 0.4089638292789459, "learning_rate": 2.846064982777633e-05, "loss": 0.0056, "step": 6884 }, { "epoch": 0.3802186878727634, "grad_norm": 4.574189186096191, "learning_rate": 2.84574082409637e-05, "loss": 0.6587, "step": 6885 }, { "epoch": 0.3802739120830572, "grad_norm": 1.8445736169815063, "learning_rate": 2.84541663835745e-05, "loss": 0.0483, "step": 6886 }, { "epoch": 0.380329136293351, "grad_norm": 0.3480546772480011, "learning_rate": 2.8450924255712455e-05, "loss": 0.0057, "step": 6887 }, { "epoch": 0.3803843605036448, "grad_norm": 0.050179243087768555, "learning_rate": 2.8447681857481285e-05, "loss": 0.0015, "step": 6888 }, { "epoch": 0.38043958471393857, "grad_norm": 0.10729081183671951, "learning_rate": 2.8444439188984714e-05, "loss": 0.003, "step": 6889 }, { "epoch": 0.3804948089242324, "grad_norm": 5.892533302307129, "learning_rate": 2.8441196250326504e-05, "loss": 0.947, "step": 6890 }, { "epoch": 0.3805500331345262, "grad_norm": 1.0237375497817993, "learning_rate": 2.8437953041610384e-05, "loss": 0.0731, "step": 6891 }, { "epoch": 0.38060525734482, "grad_norm": 0.29350751638412476, "learning_rate": 2.843470956294013e-05, "loss": 0.0097, "step": 6892 }, { "epoch": 0.3806604815551138, "grad_norm": 0.05555340275168419, "learning_rate": 2.8431465814419504e-05, "loss": 0.0026, "step": 6893 }, { "epoch": 0.38071570576540753, "grad_norm": 1.3159843683242798, "learning_rate": 2.8428221796152282e-05, "loss": 0.1893, "step": 6894 }, { "epoch": 0.38077092997570133, "grad_norm": 0.46642833948135376, "learning_rate": 2.8424977508242252e-05, "loss": 0.0156, "step": 6895 }, { "epoch": 0.38082615418599514, "grad_norm": 4.9620280265808105, "learning_rate": 2.8421732950793206e-05, "loss": 0.9147, "step": 6896 }, { "epoch": 0.38088137839628894, "grad_norm": 0.028988169506192207, "learning_rate": 2.841848812390895e-05, "loss": 0.0008, "step": 6897 }, { "epoch": 0.38093660260658274, "grad_norm": 0.1184988021850586, "learning_rate": 2.841524302769329e-05, "loss": 0.0033, "step": 6898 }, { "epoch": 0.38099182681687654, "grad_norm": 1.8115931749343872, "learning_rate": 2.8411997662250047e-05, "loss": 0.1486, "step": 6899 }, { "epoch": 0.3810470510271703, "grad_norm": 4.4859724044799805, "learning_rate": 2.840875202768305e-05, "loss": 1.2677, "step": 6900 }, { "epoch": 0.3811022752374641, "grad_norm": 3.940291166305542, "learning_rate": 2.8405506124096138e-05, "loss": 1.1412, "step": 6901 }, { "epoch": 0.3811574994477579, "grad_norm": 3.166513442993164, "learning_rate": 2.840225995159316e-05, "loss": 0.5785, "step": 6902 }, { "epoch": 0.3812127236580517, "grad_norm": 2.267247200012207, "learning_rate": 2.8399013510277966e-05, "loss": 0.1655, "step": 6903 }, { "epoch": 0.3812679478683455, "grad_norm": 2.753554105758667, "learning_rate": 2.839576680025441e-05, "loss": 0.3853, "step": 6904 }, { "epoch": 0.38132317207863925, "grad_norm": 0.7655849456787109, "learning_rate": 2.8392519821626382e-05, "loss": 0.0258, "step": 6905 }, { "epoch": 0.38137839628893305, "grad_norm": 1.68099844455719, "learning_rate": 2.8389272574497745e-05, "loss": 0.2298, "step": 6906 }, { "epoch": 0.38143362049922686, "grad_norm": 0.66907799243927, "learning_rate": 2.8386025058972403e-05, "loss": 0.021, "step": 6907 }, { "epoch": 0.38148884470952066, "grad_norm": 0.09360219538211823, "learning_rate": 2.8382777275154237e-05, "loss": 0.0042, "step": 6908 }, { "epoch": 0.38154406891981446, "grad_norm": 0.05360391363501549, "learning_rate": 2.837952922314717e-05, "loss": 0.0018, "step": 6909 }, { "epoch": 0.38159929313010826, "grad_norm": 0.4806254506111145, "learning_rate": 2.83762809030551e-05, "loss": 0.021, "step": 6910 }, { "epoch": 0.381654517340402, "grad_norm": 4.809262275695801, "learning_rate": 2.8373032314981963e-05, "loss": 0.6215, "step": 6911 }, { "epoch": 0.3817097415506958, "grad_norm": 0.030670488253235817, "learning_rate": 2.8369783459031678e-05, "loss": 0.0012, "step": 6912 }, { "epoch": 0.3817649657609896, "grad_norm": 5.352102756500244, "learning_rate": 2.8366534335308204e-05, "loss": 1.4032, "step": 6913 }, { "epoch": 0.3818201899712834, "grad_norm": 3.46380877494812, "learning_rate": 2.8363284943915464e-05, "loss": 0.1674, "step": 6914 }, { "epoch": 0.3818754141815772, "grad_norm": 0.01795358955860138, "learning_rate": 2.836003528495744e-05, "loss": 0.0006, "step": 6915 }, { "epoch": 0.38193063839187097, "grad_norm": 0.2052392065525055, "learning_rate": 2.8356785358538088e-05, "loss": 0.0057, "step": 6916 }, { "epoch": 0.38198586260216477, "grad_norm": 2.1835591793060303, "learning_rate": 2.8353535164761377e-05, "loss": 0.1541, "step": 6917 }, { "epoch": 0.3820410868124586, "grad_norm": 0.061779625713825226, "learning_rate": 2.8350284703731295e-05, "loss": 0.0025, "step": 6918 }, { "epoch": 0.3820963110227524, "grad_norm": 1.0983184576034546, "learning_rate": 2.834703397555184e-05, "loss": 0.0179, "step": 6919 }, { "epoch": 0.3821515352330462, "grad_norm": 4.035791397094727, "learning_rate": 2.8343782980326994e-05, "loss": 1.075, "step": 6920 }, { "epoch": 0.38220675944334, "grad_norm": 0.5662679672241211, "learning_rate": 2.8340531718160783e-05, "loss": 0.0155, "step": 6921 }, { "epoch": 0.38226198365363373, "grad_norm": 0.20832373201847076, "learning_rate": 2.8337280189157215e-05, "loss": 0.0042, "step": 6922 }, { "epoch": 0.38231720786392753, "grad_norm": 4.62034273147583, "learning_rate": 2.8334028393420322e-05, "loss": 0.3281, "step": 6923 }, { "epoch": 0.38237243207422134, "grad_norm": 0.37356245517730713, "learning_rate": 2.833077633105413e-05, "loss": 0.0117, "step": 6924 }, { "epoch": 0.38242765628451514, "grad_norm": 1.7396949529647827, "learning_rate": 2.832752400216269e-05, "loss": 0.0963, "step": 6925 }, { "epoch": 0.38248288049480894, "grad_norm": 1.0718728303909302, "learning_rate": 2.8324271406850053e-05, "loss": 0.0175, "step": 6926 }, { "epoch": 0.38253810470510274, "grad_norm": 0.20302703976631165, "learning_rate": 2.8321018545220273e-05, "loss": 0.0058, "step": 6927 }, { "epoch": 0.3825933289153965, "grad_norm": 2.828325033187866, "learning_rate": 2.8317765417377415e-05, "loss": 0.4902, "step": 6928 }, { "epoch": 0.3826485531256903, "grad_norm": 0.48399272561073303, "learning_rate": 2.8314512023425568e-05, "loss": 0.0123, "step": 6929 }, { "epoch": 0.3827037773359841, "grad_norm": 0.09572809189558029, "learning_rate": 2.8311258363468807e-05, "loss": 0.0038, "step": 6930 }, { "epoch": 0.3827590015462779, "grad_norm": 0.13061858713626862, "learning_rate": 2.8308004437611232e-05, "loss": 0.0053, "step": 6931 }, { "epoch": 0.3828142257565717, "grad_norm": 1.9538720846176147, "learning_rate": 2.8304750245956945e-05, "loss": 0.2294, "step": 6932 }, { "epoch": 0.38286944996686545, "grad_norm": 3.7882485389709473, "learning_rate": 2.8301495788610052e-05, "loss": 0.5161, "step": 6933 }, { "epoch": 0.38292467417715925, "grad_norm": 0.09203274548053741, "learning_rate": 2.8298241065674678e-05, "loss": 0.0023, "step": 6934 }, { "epoch": 0.38297989838745305, "grad_norm": 0.8018136024475098, "learning_rate": 2.8294986077254945e-05, "loss": 0.0252, "step": 6935 }, { "epoch": 0.38303512259774686, "grad_norm": 0.1682748943567276, "learning_rate": 2.8291730823454993e-05, "loss": 0.0051, "step": 6936 }, { "epoch": 0.38309034680804066, "grad_norm": 3.3211264610290527, "learning_rate": 2.8288475304378976e-05, "loss": 0.6157, "step": 6937 }, { "epoch": 0.38314557101833446, "grad_norm": 0.038700081408023834, "learning_rate": 2.8285219520131027e-05, "loss": 0.0016, "step": 6938 }, { "epoch": 0.3832007952286282, "grad_norm": 0.4145216643810272, "learning_rate": 2.828196347081532e-05, "loss": 0.0112, "step": 6939 }, { "epoch": 0.383256019438922, "grad_norm": 2.159385919570923, "learning_rate": 2.827870715653603e-05, "loss": 0.0525, "step": 6940 }, { "epoch": 0.3833112436492158, "grad_norm": 0.020256249234080315, "learning_rate": 2.8275450577397322e-05, "loss": 0.0008, "step": 6941 }, { "epoch": 0.3833664678595096, "grad_norm": 3.095794677734375, "learning_rate": 2.827219373350339e-05, "loss": 0.0944, "step": 6942 }, { "epoch": 0.3834216920698034, "grad_norm": 0.08329696953296661, "learning_rate": 2.8268936624958433e-05, "loss": 0.002, "step": 6943 }, { "epoch": 0.38347691628009717, "grad_norm": 0.15523411333560944, "learning_rate": 2.8265679251866662e-05, "loss": 0.005, "step": 6944 }, { "epoch": 0.38353214049039097, "grad_norm": 2.888035297393799, "learning_rate": 2.826242161433227e-05, "loss": 0.271, "step": 6945 }, { "epoch": 0.3835873647006848, "grad_norm": 0.09752944111824036, "learning_rate": 2.825916371245949e-05, "loss": 0.0033, "step": 6946 }, { "epoch": 0.3836425889109786, "grad_norm": 2.7084426879882812, "learning_rate": 2.8255905546352553e-05, "loss": 0.1657, "step": 6947 }, { "epoch": 0.3836978131212724, "grad_norm": 0.225302055478096, "learning_rate": 2.825264711611569e-05, "loss": 0.0088, "step": 6948 }, { "epoch": 0.3837530373315662, "grad_norm": 0.08229223638772964, "learning_rate": 2.8249388421853153e-05, "loss": 0.0031, "step": 6949 }, { "epoch": 0.38380826154185993, "grad_norm": 0.011301577091217041, "learning_rate": 2.82461294636692e-05, "loss": 0.0004, "step": 6950 }, { "epoch": 0.38386348575215373, "grad_norm": 2.771726608276367, "learning_rate": 2.8242870241668083e-05, "loss": 0.1844, "step": 6951 }, { "epoch": 0.38391870996244754, "grad_norm": 0.05691392347216606, "learning_rate": 2.823961075595409e-05, "loss": 0.0021, "step": 6952 }, { "epoch": 0.38397393417274134, "grad_norm": 2.2102949619293213, "learning_rate": 2.823635100663148e-05, "loss": 0.1127, "step": 6953 }, { "epoch": 0.38402915838303514, "grad_norm": 1.5826025009155273, "learning_rate": 2.823309099380456e-05, "loss": 0.2426, "step": 6954 }, { "epoch": 0.3840843825933289, "grad_norm": 4.524052143096924, "learning_rate": 2.822983071757762e-05, "loss": 0.8772, "step": 6955 }, { "epoch": 0.3841396068036227, "grad_norm": 2.264950752258301, "learning_rate": 2.8226570178054965e-05, "loss": 0.1704, "step": 6956 }, { "epoch": 0.3841948310139165, "grad_norm": 0.03143276646733284, "learning_rate": 2.822330937534091e-05, "loss": 0.0016, "step": 6957 }, { "epoch": 0.3842500552242103, "grad_norm": 0.24207527935504913, "learning_rate": 2.822004830953978e-05, "loss": 0.0079, "step": 6958 }, { "epoch": 0.3843052794345041, "grad_norm": 3.444768190383911, "learning_rate": 2.8216786980755898e-05, "loss": 0.2012, "step": 6959 }, { "epoch": 0.3843605036447979, "grad_norm": 1.4680715799331665, "learning_rate": 2.8213525389093616e-05, "loss": 0.0385, "step": 6960 }, { "epoch": 0.38441572785509165, "grad_norm": 0.4373779594898224, "learning_rate": 2.821026353465726e-05, "loss": 0.0133, "step": 6961 }, { "epoch": 0.38447095206538545, "grad_norm": 1.3141810894012451, "learning_rate": 2.8207001417551212e-05, "loss": 0.0539, "step": 6962 }, { "epoch": 0.38452617627567925, "grad_norm": 1.139947772026062, "learning_rate": 2.8203739037879824e-05, "loss": 0.2046, "step": 6963 }, { "epoch": 0.38458140048597306, "grad_norm": 0.8605776429176331, "learning_rate": 2.8200476395747464e-05, "loss": 0.0194, "step": 6964 }, { "epoch": 0.38463662469626686, "grad_norm": 3.9045233726501465, "learning_rate": 2.8197213491258524e-05, "loss": 0.4793, "step": 6965 }, { "epoch": 0.38469184890656066, "grad_norm": 2.220277786254883, "learning_rate": 2.819395032451738e-05, "loss": 0.4271, "step": 6966 }, { "epoch": 0.3847470731168544, "grad_norm": 0.1163514032959938, "learning_rate": 2.8190686895628446e-05, "loss": 0.0034, "step": 6967 }, { "epoch": 0.3848022973271482, "grad_norm": 1.365645408630371, "learning_rate": 2.8187423204696117e-05, "loss": 0.0598, "step": 6968 }, { "epoch": 0.384857521537442, "grad_norm": 1.4703176021575928, "learning_rate": 2.818415925182481e-05, "loss": 0.0564, "step": 6969 }, { "epoch": 0.3849127457477358, "grad_norm": 3.4815220832824707, "learning_rate": 2.8180895037118952e-05, "loss": 0.4527, "step": 6970 }, { "epoch": 0.3849679699580296, "grad_norm": 0.025644799694418907, "learning_rate": 2.817763056068297e-05, "loss": 0.0008, "step": 6971 }, { "epoch": 0.38502319416832337, "grad_norm": 2.127256155014038, "learning_rate": 2.8174365822621305e-05, "loss": 0.209, "step": 6972 }, { "epoch": 0.38507841837861717, "grad_norm": 1.9885480403900146, "learning_rate": 2.817110082303841e-05, "loss": 0.0405, "step": 6973 }, { "epoch": 0.385133642588911, "grad_norm": 2.8564910888671875, "learning_rate": 2.816783556203873e-05, "loss": 0.5419, "step": 6974 }, { "epoch": 0.3851888667992048, "grad_norm": 0.018582860007882118, "learning_rate": 2.8164570039726746e-05, "loss": 0.0008, "step": 6975 }, { "epoch": 0.3852440910094986, "grad_norm": 0.2354099601507187, "learning_rate": 2.816130425620692e-05, "loss": 0.005, "step": 6976 }, { "epoch": 0.3852993152197924, "grad_norm": 2.8224077224731445, "learning_rate": 2.8158038211583732e-05, "loss": 0.0951, "step": 6977 }, { "epoch": 0.38535453943008613, "grad_norm": 0.4442261755466461, "learning_rate": 2.8154771905961684e-05, "loss": 0.0147, "step": 6978 }, { "epoch": 0.38540976364037993, "grad_norm": 0.13091114163398743, "learning_rate": 2.8151505339445262e-05, "loss": 0.0054, "step": 6979 }, { "epoch": 0.38546498785067373, "grad_norm": 0.04006088897585869, "learning_rate": 2.814823851213898e-05, "loss": 0.0011, "step": 6980 }, { "epoch": 0.38552021206096754, "grad_norm": 0.3673169016838074, "learning_rate": 2.814497142414735e-05, "loss": 0.0045, "step": 6981 }, { "epoch": 0.38557543627126134, "grad_norm": 4.911279201507568, "learning_rate": 2.8141704075574895e-05, "loss": 0.4595, "step": 6982 }, { "epoch": 0.3856306604815551, "grad_norm": 4.0308518409729, "learning_rate": 2.813843646652615e-05, "loss": 0.3192, "step": 6983 }, { "epoch": 0.3856858846918489, "grad_norm": 1.402306079864502, "learning_rate": 2.8135168597105655e-05, "loss": 0.0633, "step": 6984 }, { "epoch": 0.3857411089021427, "grad_norm": 0.8621609807014465, "learning_rate": 2.813190046741795e-05, "loss": 0.0194, "step": 6985 }, { "epoch": 0.3857963331124365, "grad_norm": 0.03153199329972267, "learning_rate": 2.812863207756761e-05, "loss": 0.0008, "step": 6986 }, { "epoch": 0.3858515573227303, "grad_norm": 4.7565226554870605, "learning_rate": 2.8125363427659182e-05, "loss": 1.264, "step": 6987 }, { "epoch": 0.3859067815330241, "grad_norm": 1.4126611948013306, "learning_rate": 2.8122094517797244e-05, "loss": 0.0328, "step": 6988 }, { "epoch": 0.38596200574331785, "grad_norm": 8.735215187072754, "learning_rate": 2.811882534808638e-05, "loss": 0.1433, "step": 6989 }, { "epoch": 0.38601722995361165, "grad_norm": 2.7684595584869385, "learning_rate": 2.8115555918631185e-05, "loss": 0.3611, "step": 6990 }, { "epoch": 0.38607245416390545, "grad_norm": 1.9621226787567139, "learning_rate": 2.8112286229536252e-05, "loss": 0.1726, "step": 6991 }, { "epoch": 0.38612767837419926, "grad_norm": 0.10366911441087723, "learning_rate": 2.8109016280906183e-05, "loss": 0.003, "step": 6992 }, { "epoch": 0.38618290258449306, "grad_norm": 2.554478645324707, "learning_rate": 2.8105746072845603e-05, "loss": 0.1953, "step": 6993 }, { "epoch": 0.3862381267947868, "grad_norm": 3.6008780002593994, "learning_rate": 2.8102475605459126e-05, "loss": 0.2896, "step": 6994 }, { "epoch": 0.3862933510050806, "grad_norm": 2.5430474281311035, "learning_rate": 2.809920487885139e-05, "loss": 0.2565, "step": 6995 }, { "epoch": 0.3863485752153744, "grad_norm": 0.5337943434715271, "learning_rate": 2.8095933893127027e-05, "loss": 0.022, "step": 6996 }, { "epoch": 0.3864037994256682, "grad_norm": 0.13883350789546967, "learning_rate": 2.8092662648390696e-05, "loss": 0.0035, "step": 6997 }, { "epoch": 0.386459023635962, "grad_norm": 2.4914469718933105, "learning_rate": 2.8089391144747046e-05, "loss": 0.3945, "step": 6998 }, { "epoch": 0.3865142478462558, "grad_norm": 2.93900465965271, "learning_rate": 2.8086119382300746e-05, "loss": 0.1111, "step": 6999 }, { "epoch": 0.38656947205654957, "grad_norm": 1.3819938898086548, "learning_rate": 2.8082847361156468e-05, "loss": 0.1144, "step": 7000 }, { "epoch": 0.38662469626684337, "grad_norm": 0.10785513371229172, "learning_rate": 2.8079575081418887e-05, "loss": 0.0028, "step": 7001 }, { "epoch": 0.3866799204771372, "grad_norm": 0.3035268783569336, "learning_rate": 2.8076302543192705e-05, "loss": 0.0086, "step": 7002 }, { "epoch": 0.386735144687431, "grad_norm": 0.20818297564983368, "learning_rate": 2.80730297465826e-05, "loss": 0.0066, "step": 7003 }, { "epoch": 0.3867903688977248, "grad_norm": 0.04028428718447685, "learning_rate": 2.8069756691693305e-05, "loss": 0.0015, "step": 7004 }, { "epoch": 0.3868455931080186, "grad_norm": 0.06388850510120392, "learning_rate": 2.806648337862951e-05, "loss": 0.0025, "step": 7005 }, { "epoch": 0.38690081731831233, "grad_norm": 0.060693126171827316, "learning_rate": 2.806320980749595e-05, "loss": 0.0014, "step": 7006 }, { "epoch": 0.38695604152860613, "grad_norm": 0.027731461450457573, "learning_rate": 2.8059935978397354e-05, "loss": 0.0009, "step": 7007 }, { "epoch": 0.38701126573889993, "grad_norm": 2.0445728302001953, "learning_rate": 2.8056661891438462e-05, "loss": 0.1947, "step": 7008 }, { "epoch": 0.38706648994919374, "grad_norm": 1.6869425773620605, "learning_rate": 2.8053387546724015e-05, "loss": 0.1855, "step": 7009 }, { "epoch": 0.38712171415948754, "grad_norm": 1.3900138139724731, "learning_rate": 2.805011294435878e-05, "loss": 0.1079, "step": 7010 }, { "epoch": 0.3871769383697813, "grad_norm": 1.4799537658691406, "learning_rate": 2.8046838084447512e-05, "loss": 0.0851, "step": 7011 }, { "epoch": 0.3872321625800751, "grad_norm": 1.2166134119033813, "learning_rate": 2.8043562967094985e-05, "loss": 0.0331, "step": 7012 }, { "epoch": 0.3872873867903689, "grad_norm": 0.00830200407654047, "learning_rate": 2.8040287592405974e-05, "loss": 0.0003, "step": 7013 }, { "epoch": 0.3873426110006627, "grad_norm": 1.8408336639404297, "learning_rate": 2.8037011960485282e-05, "loss": 0.188, "step": 7014 }, { "epoch": 0.3873978352109565, "grad_norm": 2.6411473751068115, "learning_rate": 2.8033736071437692e-05, "loss": 0.1222, "step": 7015 }, { "epoch": 0.3874530594212503, "grad_norm": 3.056913375854492, "learning_rate": 2.8030459925368014e-05, "loss": 0.0386, "step": 7016 }, { "epoch": 0.38750828363154405, "grad_norm": 1.530282974243164, "learning_rate": 2.8027183522381067e-05, "loss": 0.1026, "step": 7017 }, { "epoch": 0.38756350784183785, "grad_norm": 0.00996343046426773, "learning_rate": 2.802390686258166e-05, "loss": 0.0004, "step": 7018 }, { "epoch": 0.38761873205213165, "grad_norm": 2.100365161895752, "learning_rate": 2.8020629946074633e-05, "loss": 0.3374, "step": 7019 }, { "epoch": 0.38767395626242546, "grad_norm": 3.2654130458831787, "learning_rate": 2.8017352772964818e-05, "loss": 0.4732, "step": 7020 }, { "epoch": 0.38772918047271926, "grad_norm": 3.8658111095428467, "learning_rate": 2.8014075343357058e-05, "loss": 0.1424, "step": 7021 }, { "epoch": 0.387784404683013, "grad_norm": 2.209568977355957, "learning_rate": 2.8010797657356224e-05, "loss": 0.204, "step": 7022 }, { "epoch": 0.3878396288933068, "grad_norm": 0.13419510424137115, "learning_rate": 2.8007519715067163e-05, "loss": 0.0032, "step": 7023 }, { "epoch": 0.3878948531036006, "grad_norm": 0.014935953542590141, "learning_rate": 2.8004241516594746e-05, "loss": 0.0005, "step": 7024 }, { "epoch": 0.3879500773138944, "grad_norm": 2.805493116378784, "learning_rate": 2.800096306204386e-05, "loss": 0.2284, "step": 7025 }, { "epoch": 0.3880053015241882, "grad_norm": 0.07496734708547592, "learning_rate": 2.799768435151939e-05, "loss": 0.0018, "step": 7026 }, { "epoch": 0.388060525734482, "grad_norm": 0.1516302227973938, "learning_rate": 2.7994405385126224e-05, "loss": 0.0046, "step": 7027 }, { "epoch": 0.38811574994477577, "grad_norm": 3.1709089279174805, "learning_rate": 2.7991126162969276e-05, "loss": 0.5249, "step": 7028 }, { "epoch": 0.38817097415506957, "grad_norm": 0.23291468620300293, "learning_rate": 2.798784668515344e-05, "loss": 0.007, "step": 7029 }, { "epoch": 0.3882261983653634, "grad_norm": 0.042415227741003036, "learning_rate": 2.7984566951783665e-05, "loss": 0.0014, "step": 7030 }, { "epoch": 0.3882814225756572, "grad_norm": 3.359602451324463, "learning_rate": 2.7981286962964854e-05, "loss": 0.0438, "step": 7031 }, { "epoch": 0.388336646785951, "grad_norm": 2.8998727798461914, "learning_rate": 2.797800671880195e-05, "loss": 0.5298, "step": 7032 }, { "epoch": 0.3883918709962448, "grad_norm": 2.721184730529785, "learning_rate": 2.79747262193999e-05, "loss": 0.5896, "step": 7033 }, { "epoch": 0.38844709520653853, "grad_norm": 1.4332154989242554, "learning_rate": 2.7971445464863653e-05, "loss": 0.0368, "step": 7034 }, { "epoch": 0.38850231941683233, "grad_norm": 0.3213782012462616, "learning_rate": 2.7968164455298176e-05, "loss": 0.0071, "step": 7035 }, { "epoch": 0.38855754362712613, "grad_norm": 0.04563773795962334, "learning_rate": 2.7964883190808433e-05, "loss": 0.0013, "step": 7036 }, { "epoch": 0.38861276783741994, "grad_norm": 2.9652369022369385, "learning_rate": 2.79616016714994e-05, "loss": 0.2954, "step": 7037 }, { "epoch": 0.38866799204771374, "grad_norm": 5.645912170410156, "learning_rate": 2.7958319897476065e-05, "loss": 0.9991, "step": 7038 }, { "epoch": 0.3887232162580075, "grad_norm": 0.15620893239974976, "learning_rate": 2.795503786884342e-05, "loss": 0.0041, "step": 7039 }, { "epoch": 0.3887784404683013, "grad_norm": 0.026953263208270073, "learning_rate": 2.7951755585706464e-05, "loss": 0.0012, "step": 7040 }, { "epoch": 0.3888336646785951, "grad_norm": 0.06487731635570526, "learning_rate": 2.7948473048170216e-05, "loss": 0.0027, "step": 7041 }, { "epoch": 0.3888888888888889, "grad_norm": 1.2672053575515747, "learning_rate": 2.794519025633968e-05, "loss": 0.0803, "step": 7042 }, { "epoch": 0.3889441130991827, "grad_norm": 1.2275922298431396, "learning_rate": 2.794190721031989e-05, "loss": 0.0412, "step": 7043 }, { "epoch": 0.3889993373094765, "grad_norm": 0.5383326411247253, "learning_rate": 2.7938623910215886e-05, "loss": 0.0098, "step": 7044 }, { "epoch": 0.38905456151977025, "grad_norm": 2.467365264892578, "learning_rate": 2.793534035613269e-05, "loss": 0.2558, "step": 7045 }, { "epoch": 0.38910978573006405, "grad_norm": 1.4953941106796265, "learning_rate": 2.7932056548175376e-05, "loss": 0.0435, "step": 7046 }, { "epoch": 0.38916500994035785, "grad_norm": 2.6178035736083984, "learning_rate": 2.7928772486448985e-05, "loss": 0.2445, "step": 7047 }, { "epoch": 0.38922023415065166, "grad_norm": 3.3202812671661377, "learning_rate": 2.792548817105859e-05, "loss": 0.3374, "step": 7048 }, { "epoch": 0.38927545836094546, "grad_norm": 0.07573480159044266, "learning_rate": 2.792220360210927e-05, "loss": 0.0022, "step": 7049 }, { "epoch": 0.3893306825712392, "grad_norm": 5.5828657150268555, "learning_rate": 2.79189187797061e-05, "loss": 1.3204, "step": 7050 }, { "epoch": 0.389385906781533, "grad_norm": 4.056040287017822, "learning_rate": 2.7915633703954176e-05, "loss": 0.9705, "step": 7051 }, { "epoch": 0.3894411309918268, "grad_norm": 3.859874725341797, "learning_rate": 2.7912348374958597e-05, "loss": 0.7914, "step": 7052 }, { "epoch": 0.3894963552021206, "grad_norm": 0.060696158558130264, "learning_rate": 2.790906279282446e-05, "loss": 0.0024, "step": 7053 }, { "epoch": 0.3895515794124144, "grad_norm": 2.686756134033203, "learning_rate": 2.7905776957656898e-05, "loss": 0.3417, "step": 7054 }, { "epoch": 0.3896068036227082, "grad_norm": 1.9939122200012207, "learning_rate": 2.7902490869561014e-05, "loss": 0.2949, "step": 7055 }, { "epoch": 0.38966202783300197, "grad_norm": 8.672536849975586, "learning_rate": 2.7899204528641956e-05, "loss": 1.9555, "step": 7056 }, { "epoch": 0.38971725204329577, "grad_norm": 2.7859303951263428, "learning_rate": 2.7895917935004862e-05, "loss": 0.5274, "step": 7057 }, { "epoch": 0.3897724762535896, "grad_norm": 0.14000004529953003, "learning_rate": 2.7892631088754866e-05, "loss": 0.0034, "step": 7058 }, { "epoch": 0.3898277004638834, "grad_norm": 2.9876608848571777, "learning_rate": 2.788934398999714e-05, "loss": 0.1631, "step": 7059 }, { "epoch": 0.3898829246741772, "grad_norm": 1.4492766857147217, "learning_rate": 2.7886056638836833e-05, "loss": 0.0553, "step": 7060 }, { "epoch": 0.3899381488844709, "grad_norm": 0.21851590275764465, "learning_rate": 2.788276903537912e-05, "loss": 0.0075, "step": 7061 }, { "epoch": 0.38999337309476473, "grad_norm": 0.37105798721313477, "learning_rate": 2.7879481179729195e-05, "loss": 0.0116, "step": 7062 }, { "epoch": 0.39004859730505853, "grad_norm": 0.7413000464439392, "learning_rate": 2.7876193071992227e-05, "loss": 0.0226, "step": 7063 }, { "epoch": 0.39010382151535233, "grad_norm": 3.8993804454803467, "learning_rate": 2.7872904712273424e-05, "loss": 0.0297, "step": 7064 }, { "epoch": 0.39015904572564614, "grad_norm": 0.471381813287735, "learning_rate": 2.786961610067799e-05, "loss": 0.0124, "step": 7065 }, { "epoch": 0.39021426993593994, "grad_norm": 3.426628351211548, "learning_rate": 2.7866327237311122e-05, "loss": 0.1293, "step": 7066 }, { "epoch": 0.3902694941462337, "grad_norm": 0.07449104636907578, "learning_rate": 2.786303812227806e-05, "loss": 0.0026, "step": 7067 }, { "epoch": 0.3903247183565275, "grad_norm": 2.587730646133423, "learning_rate": 2.7859748755684023e-05, "loss": 0.1989, "step": 7068 }, { "epoch": 0.3903799425668213, "grad_norm": 0.28167733550071716, "learning_rate": 2.7856459137634243e-05, "loss": 0.0104, "step": 7069 }, { "epoch": 0.3904351667771151, "grad_norm": 3.5734305381774902, "learning_rate": 2.7853169268233974e-05, "loss": 0.5134, "step": 7070 }, { "epoch": 0.3904903909874089, "grad_norm": 2.825695276260376, "learning_rate": 2.784987914758846e-05, "loss": 0.2278, "step": 7071 }, { "epoch": 0.3905456151977027, "grad_norm": 2.437077522277832, "learning_rate": 2.784658877580297e-05, "loss": 0.2355, "step": 7072 }, { "epoch": 0.39060083940799645, "grad_norm": 2.9600820541381836, "learning_rate": 2.784329815298276e-05, "loss": 0.2252, "step": 7073 }, { "epoch": 0.39065606361829025, "grad_norm": 1.5666404962539673, "learning_rate": 2.7840007279233115e-05, "loss": 0.1909, "step": 7074 }, { "epoch": 0.39071128782858405, "grad_norm": 0.2355869561433792, "learning_rate": 2.7836716154659317e-05, "loss": 0.0058, "step": 7075 }, { "epoch": 0.39076651203887786, "grad_norm": 3.4403774738311768, "learning_rate": 2.783342477936666e-05, "loss": 0.4758, "step": 7076 }, { "epoch": 0.39082173624917166, "grad_norm": 0.24585124850273132, "learning_rate": 2.7830133153460442e-05, "loss": 0.0068, "step": 7077 }, { "epoch": 0.3908769604594654, "grad_norm": 0.13993753492832184, "learning_rate": 2.7826841277045976e-05, "loss": 0.0048, "step": 7078 }, { "epoch": 0.3909321846697592, "grad_norm": 0.046831849962472916, "learning_rate": 2.782354915022857e-05, "loss": 0.0018, "step": 7079 }, { "epoch": 0.390987408880053, "grad_norm": 0.24816054105758667, "learning_rate": 2.782025677311356e-05, "loss": 0.008, "step": 7080 }, { "epoch": 0.3910426330903468, "grad_norm": 0.31215929985046387, "learning_rate": 2.7816964145806266e-05, "loss": 0.0105, "step": 7081 }, { "epoch": 0.3910978573006406, "grad_norm": 2.8945953845977783, "learning_rate": 2.7813671268412044e-05, "loss": 0.9328, "step": 7082 }, { "epoch": 0.3911530815109344, "grad_norm": 0.18083450198173523, "learning_rate": 2.781037814103623e-05, "loss": 0.0042, "step": 7083 }, { "epoch": 0.39120830572122817, "grad_norm": 2.9179327487945557, "learning_rate": 2.780708476378418e-05, "loss": 0.2442, "step": 7084 }, { "epoch": 0.39126352993152197, "grad_norm": 0.2581701874732971, "learning_rate": 2.780379113676127e-05, "loss": 0.0073, "step": 7085 }, { "epoch": 0.39131875414181577, "grad_norm": 0.14259816706180573, "learning_rate": 2.780049726007286e-05, "loss": 0.0046, "step": 7086 }, { "epoch": 0.3913739783521096, "grad_norm": 0.5973621010780334, "learning_rate": 2.779720313382433e-05, "loss": 0.0211, "step": 7087 }, { "epoch": 0.3914292025624034, "grad_norm": 0.11896013468503952, "learning_rate": 2.7793908758121085e-05, "loss": 0.0035, "step": 7088 }, { "epoch": 0.3914844267726971, "grad_norm": 2.2947990894317627, "learning_rate": 2.7790614133068506e-05, "loss": 0.0388, "step": 7089 }, { "epoch": 0.3915396509829909, "grad_norm": 0.25198742747306824, "learning_rate": 2.7787319258772e-05, "loss": 0.0102, "step": 7090 }, { "epoch": 0.39159487519328473, "grad_norm": 1.6652945280075073, "learning_rate": 2.778402413533699e-05, "loss": 0.0378, "step": 7091 }, { "epoch": 0.39165009940357853, "grad_norm": 2.9805498123168945, "learning_rate": 2.7780728762868877e-05, "loss": 0.1669, "step": 7092 }, { "epoch": 0.39170532361387234, "grad_norm": 1.1546140909194946, "learning_rate": 2.7777433141473106e-05, "loss": 0.0348, "step": 7093 }, { "epoch": 0.39176054782416614, "grad_norm": 3.6419167518615723, "learning_rate": 2.7774137271255105e-05, "loss": 1.0401, "step": 7094 }, { "epoch": 0.3918157720344599, "grad_norm": 0.12858274579048157, "learning_rate": 2.777084115232032e-05, "loss": 0.0033, "step": 7095 }, { "epoch": 0.3918709962447537, "grad_norm": 0.009302731603384018, "learning_rate": 2.776754478477421e-05, "loss": 0.0003, "step": 7096 }, { "epoch": 0.3919262204550475, "grad_norm": 7.304949760437012, "learning_rate": 2.776424816872222e-05, "loss": 1.6615, "step": 7097 }, { "epoch": 0.3919814446653413, "grad_norm": 0.06347193568944931, "learning_rate": 2.7760951304269834e-05, "loss": 0.0026, "step": 7098 }, { "epoch": 0.3920366688756351, "grad_norm": 2.808703660964966, "learning_rate": 2.775765419152252e-05, "loss": 0.2501, "step": 7099 }, { "epoch": 0.39209189308592884, "grad_norm": 4.555273532867432, "learning_rate": 2.775435683058576e-05, "loss": 0.7939, "step": 7100 }, { "epoch": 0.39214711729622265, "grad_norm": 1.8853965997695923, "learning_rate": 2.775105922156505e-05, "loss": 0.0689, "step": 7101 }, { "epoch": 0.39220234150651645, "grad_norm": 3.3446030616760254, "learning_rate": 2.774776136456589e-05, "loss": 0.1421, "step": 7102 }, { "epoch": 0.39225756571681025, "grad_norm": 2.421565532684326, "learning_rate": 2.774446325969379e-05, "loss": 0.0452, "step": 7103 }, { "epoch": 0.39231278992710406, "grad_norm": 2.272573232650757, "learning_rate": 2.7741164907054264e-05, "loss": 0.6517, "step": 7104 }, { "epoch": 0.39236801413739786, "grad_norm": 0.2966708540916443, "learning_rate": 2.7737866306752827e-05, "loss": 0.0113, "step": 7105 }, { "epoch": 0.3924232383476916, "grad_norm": 0.037316542118787766, "learning_rate": 2.7734567458895027e-05, "loss": 0.0015, "step": 7106 }, { "epoch": 0.3924784625579854, "grad_norm": 3.797764778137207, "learning_rate": 2.773126836358639e-05, "loss": 0.3458, "step": 7107 }, { "epoch": 0.3925336867682792, "grad_norm": 0.9360576868057251, "learning_rate": 2.7727969020932466e-05, "loss": 0.0614, "step": 7108 }, { "epoch": 0.392588910978573, "grad_norm": 1.0639774799346924, "learning_rate": 2.7724669431038815e-05, "loss": 0.0287, "step": 7109 }, { "epoch": 0.3926441351888668, "grad_norm": 0.08790243417024612, "learning_rate": 2.7721369594011e-05, "loss": 0.0032, "step": 7110 }, { "epoch": 0.3926993593991606, "grad_norm": 0.31469306349754333, "learning_rate": 2.7718069509954583e-05, "loss": 0.0095, "step": 7111 }, { "epoch": 0.39275458360945437, "grad_norm": 0.019784511998295784, "learning_rate": 2.7714769178975158e-05, "loss": 0.001, "step": 7112 }, { "epoch": 0.39280980781974817, "grad_norm": 2.8018221855163574, "learning_rate": 2.77114686011783e-05, "loss": 0.5991, "step": 7113 }, { "epoch": 0.39286503203004197, "grad_norm": 1.509810209274292, "learning_rate": 2.770816777666961e-05, "loss": 0.1091, "step": 7114 }, { "epoch": 0.3929202562403358, "grad_norm": 3.2495851516723633, "learning_rate": 2.7704866705554684e-05, "loss": 0.3937, "step": 7115 }, { "epoch": 0.3929754804506296, "grad_norm": 0.4275713860988617, "learning_rate": 2.7701565387939142e-05, "loss": 0.017, "step": 7116 }, { "epoch": 0.3930307046609233, "grad_norm": 1.3581212759017944, "learning_rate": 2.7698263823928596e-05, "loss": 0.2122, "step": 7117 }, { "epoch": 0.3930859288712171, "grad_norm": 0.1763390451669693, "learning_rate": 2.7694962013628673e-05, "loss": 0.0054, "step": 7118 }, { "epoch": 0.39314115308151093, "grad_norm": 4.914647579193115, "learning_rate": 2.769165995714501e-05, "loss": 0.9654, "step": 7119 }, { "epoch": 0.39319637729180473, "grad_norm": 1.424702525138855, "learning_rate": 2.768835765458325e-05, "loss": 0.0497, "step": 7120 }, { "epoch": 0.39325160150209854, "grad_norm": 0.04950644075870514, "learning_rate": 2.7685055106049037e-05, "loss": 0.0017, "step": 7121 }, { "epoch": 0.39330682571239234, "grad_norm": 3.112165927886963, "learning_rate": 2.7681752311648035e-05, "loss": 0.6468, "step": 7122 }, { "epoch": 0.3933620499226861, "grad_norm": 0.1584862619638443, "learning_rate": 2.7678449271485904e-05, "loss": 0.0048, "step": 7123 }, { "epoch": 0.3934172741329799, "grad_norm": 0.07061224430799484, "learning_rate": 2.7675145985668326e-05, "loss": 0.0029, "step": 7124 }, { "epoch": 0.3934724983432737, "grad_norm": 0.06626482307910919, "learning_rate": 2.7671842454300978e-05, "loss": 0.002, "step": 7125 }, { "epoch": 0.3935277225535675, "grad_norm": 0.048716358840465546, "learning_rate": 2.7668538677489543e-05, "loss": 0.002, "step": 7126 }, { "epoch": 0.3935829467638613, "grad_norm": 0.03919947147369385, "learning_rate": 2.7665234655339732e-05, "loss": 0.0016, "step": 7127 }, { "epoch": 0.39363817097415504, "grad_norm": 0.09467537701129913, "learning_rate": 2.766193038795724e-05, "loss": 0.0021, "step": 7128 }, { "epoch": 0.39369339518444885, "grad_norm": 2.8041129112243652, "learning_rate": 2.7658625875447777e-05, "loss": 0.1756, "step": 7129 }, { "epoch": 0.39374861939474265, "grad_norm": 1.6728304624557495, "learning_rate": 2.7655321117917076e-05, "loss": 0.0899, "step": 7130 }, { "epoch": 0.39380384360503645, "grad_norm": 1.8976325988769531, "learning_rate": 2.7652016115470858e-05, "loss": 0.2527, "step": 7131 }, { "epoch": 0.39385906781533025, "grad_norm": 1.450488567352295, "learning_rate": 2.7648710868214862e-05, "loss": 0.0824, "step": 7132 }, { "epoch": 0.39391429202562406, "grad_norm": 0.3227391242980957, "learning_rate": 2.7645405376254822e-05, "loss": 0.0109, "step": 7133 }, { "epoch": 0.3939695162359178, "grad_norm": 0.5579866170883179, "learning_rate": 2.7642099639696502e-05, "loss": 0.1028, "step": 7134 }, { "epoch": 0.3940247404462116, "grad_norm": 3.0335209369659424, "learning_rate": 2.7638793658645665e-05, "loss": 0.6555, "step": 7135 }, { "epoch": 0.3940799646565054, "grad_norm": 0.021262630820274353, "learning_rate": 2.7635487433208063e-05, "loss": 0.0009, "step": 7136 }, { "epoch": 0.3941351888667992, "grad_norm": 1.189216136932373, "learning_rate": 2.763218096348949e-05, "loss": 0.0478, "step": 7137 }, { "epoch": 0.394190413077093, "grad_norm": 0.7956220507621765, "learning_rate": 2.7628874249595708e-05, "loss": 0.0246, "step": 7138 }, { "epoch": 0.39424563728738676, "grad_norm": 1.384931206703186, "learning_rate": 2.7625567291632527e-05, "loss": 0.1608, "step": 7139 }, { "epoch": 0.39430086149768057, "grad_norm": 5.343575954437256, "learning_rate": 2.7622260089705738e-05, "loss": 0.4939, "step": 7140 }, { "epoch": 0.39435608570797437, "grad_norm": 5.2409892082214355, "learning_rate": 2.761895264392115e-05, "loss": 0.7652, "step": 7141 }, { "epoch": 0.39441130991826817, "grad_norm": 3.6123576164245605, "learning_rate": 2.761564495438458e-05, "loss": 0.8995, "step": 7142 }, { "epoch": 0.394466534128562, "grad_norm": 4.719988822937012, "learning_rate": 2.7612337021201846e-05, "loss": 0.3658, "step": 7143 }, { "epoch": 0.3945217583388558, "grad_norm": 1.613473653793335, "learning_rate": 2.7609028844478776e-05, "loss": 0.3604, "step": 7144 }, { "epoch": 0.3945769825491495, "grad_norm": 0.4299980103969574, "learning_rate": 2.7605720424321213e-05, "loss": 0.0075, "step": 7145 }, { "epoch": 0.3946322067594433, "grad_norm": 1.1334311962127686, "learning_rate": 2.7602411760835e-05, "loss": 0.0249, "step": 7146 }, { "epoch": 0.39468743096973713, "grad_norm": 0.014352594502270222, "learning_rate": 2.759910285412599e-05, "loss": 0.0006, "step": 7147 }, { "epoch": 0.39474265518003093, "grad_norm": 0.12403319776058197, "learning_rate": 2.759579370430005e-05, "loss": 0.0037, "step": 7148 }, { "epoch": 0.39479787939032474, "grad_norm": 2.1876959800720215, "learning_rate": 2.759248431146304e-05, "loss": 0.3752, "step": 7149 }, { "epoch": 0.39485310360061854, "grad_norm": 0.053455982357263565, "learning_rate": 2.758917467572085e-05, "loss": 0.0021, "step": 7150 }, { "epoch": 0.3949083278109123, "grad_norm": 3.1499717235565186, "learning_rate": 2.7585864797179357e-05, "loss": 0.3734, "step": 7151 }, { "epoch": 0.3949635520212061, "grad_norm": 3.528700351715088, "learning_rate": 2.7582554675944445e-05, "loss": 0.633, "step": 7152 }, { "epoch": 0.3950187762314999, "grad_norm": 0.7179049849510193, "learning_rate": 2.7579244312122028e-05, "loss": 0.0215, "step": 7153 }, { "epoch": 0.3950740004417937, "grad_norm": 0.11500726640224457, "learning_rate": 2.7575933705818e-05, "loss": 0.0037, "step": 7154 }, { "epoch": 0.3951292246520875, "grad_norm": 0.8208906650543213, "learning_rate": 2.7572622857138295e-05, "loss": 0.0719, "step": 7155 }, { "epoch": 0.39518444886238124, "grad_norm": 3.6795623302459717, "learning_rate": 2.7569311766188823e-05, "loss": 0.4121, "step": 7156 }, { "epoch": 0.39523967307267505, "grad_norm": 2.945152521133423, "learning_rate": 2.7566000433075518e-05, "loss": 0.3343, "step": 7157 }, { "epoch": 0.39529489728296885, "grad_norm": 0.01254427433013916, "learning_rate": 2.7562688857904317e-05, "loss": 0.0005, "step": 7158 }, { "epoch": 0.39535012149326265, "grad_norm": 0.12192549556493759, "learning_rate": 2.7559377040781177e-05, "loss": 0.0044, "step": 7159 }, { "epoch": 0.39540534570355645, "grad_norm": 3.5832479000091553, "learning_rate": 2.7556064981812037e-05, "loss": 0.8632, "step": 7160 }, { "epoch": 0.39546056991385026, "grad_norm": 0.10441816598176956, "learning_rate": 2.7552752681102873e-05, "loss": 0.0025, "step": 7161 }, { "epoch": 0.395515794124144, "grad_norm": 0.023985397070646286, "learning_rate": 2.7549440138759647e-05, "loss": 0.001, "step": 7162 }, { "epoch": 0.3955710183344378, "grad_norm": 3.7711126804351807, "learning_rate": 2.754612735488834e-05, "loss": 0.1924, "step": 7163 }, { "epoch": 0.3956262425447316, "grad_norm": 0.5480829477310181, "learning_rate": 2.754281432959493e-05, "loss": 0.0224, "step": 7164 }, { "epoch": 0.3956814667550254, "grad_norm": 0.6319460272789001, "learning_rate": 2.7539501062985423e-05, "loss": 0.0105, "step": 7165 }, { "epoch": 0.3957366909653192, "grad_norm": 2.856144666671753, "learning_rate": 2.753618755516581e-05, "loss": 0.184, "step": 7166 }, { "epoch": 0.39579191517561296, "grad_norm": 0.026183636859059334, "learning_rate": 2.7532873806242105e-05, "loss": 0.0008, "step": 7167 }, { "epoch": 0.39584713938590677, "grad_norm": 0.07861338555812836, "learning_rate": 2.7529559816320318e-05, "loss": 0.0031, "step": 7168 }, { "epoch": 0.39590236359620057, "grad_norm": 0.11816126853227615, "learning_rate": 2.7526245585506477e-05, "loss": 0.0034, "step": 7169 }, { "epoch": 0.39595758780649437, "grad_norm": 1.1495412588119507, "learning_rate": 2.752293111390661e-05, "loss": 0.0696, "step": 7170 }, { "epoch": 0.3960128120167882, "grad_norm": 1.0369296073913574, "learning_rate": 2.751961640162677e-05, "loss": 0.0438, "step": 7171 }, { "epoch": 0.396068036227082, "grad_norm": 5.351333141326904, "learning_rate": 2.7516301448772993e-05, "loss": 1.2125, "step": 7172 }, { "epoch": 0.3961232604373757, "grad_norm": 0.08456835895776749, "learning_rate": 2.7512986255451328e-05, "loss": 0.002, "step": 7173 }, { "epoch": 0.3961784846476695, "grad_norm": 3.0222065448760986, "learning_rate": 2.7509670821767845e-05, "loss": 0.4424, "step": 7174 }, { "epoch": 0.39623370885796333, "grad_norm": 1.2869713306427002, "learning_rate": 2.7506355147828613e-05, "loss": 0.0407, "step": 7175 }, { "epoch": 0.39628893306825713, "grad_norm": 0.09212347865104675, "learning_rate": 2.7503039233739715e-05, "loss": 0.0019, "step": 7176 }, { "epoch": 0.39634415727855093, "grad_norm": 2.818277359008789, "learning_rate": 2.749972307960723e-05, "loss": 0.7091, "step": 7177 }, { "epoch": 0.3963993814888447, "grad_norm": 0.11323344707489014, "learning_rate": 2.749640668553725e-05, "loss": 0.0032, "step": 7178 }, { "epoch": 0.3964546056991385, "grad_norm": 0.2651297152042389, "learning_rate": 2.7493090051635883e-05, "loss": 0.006, "step": 7179 }, { "epoch": 0.3965098299094323, "grad_norm": 3.379603862762451, "learning_rate": 2.7489773178009227e-05, "loss": 0.2437, "step": 7180 }, { "epoch": 0.3965650541197261, "grad_norm": 6.6098198890686035, "learning_rate": 2.7486456064763405e-05, "loss": 1.2522, "step": 7181 }, { "epoch": 0.3966202783300199, "grad_norm": 0.010955052450299263, "learning_rate": 2.7483138712004547e-05, "loss": 0.0003, "step": 7182 }, { "epoch": 0.3966755025403137, "grad_norm": 3.8357431888580322, "learning_rate": 2.7479821119838775e-05, "loss": 0.8522, "step": 7183 }, { "epoch": 0.39673072675060744, "grad_norm": 0.028582671657204628, "learning_rate": 2.7476503288372233e-05, "loss": 0.0007, "step": 7184 }, { "epoch": 0.39678595096090125, "grad_norm": 0.12364354729652405, "learning_rate": 2.7473185217711065e-05, "loss": 0.0045, "step": 7185 }, { "epoch": 0.39684117517119505, "grad_norm": 0.0903032124042511, "learning_rate": 2.7469866907961423e-05, "loss": 0.0035, "step": 7186 }, { "epoch": 0.39689639938148885, "grad_norm": 0.15672460198402405, "learning_rate": 2.7466548359229478e-05, "loss": 0.0055, "step": 7187 }, { "epoch": 0.39695162359178265, "grad_norm": 0.4755116105079651, "learning_rate": 2.746322957162139e-05, "loss": 0.0153, "step": 7188 }, { "epoch": 0.39700684780207646, "grad_norm": 0.2682223618030548, "learning_rate": 2.7459910545243347e-05, "loss": 0.0066, "step": 7189 }, { "epoch": 0.3970620720123702, "grad_norm": 2.4541382789611816, "learning_rate": 2.7456591280201524e-05, "loss": 0.2663, "step": 7190 }, { "epoch": 0.397117296222664, "grad_norm": 2.8958725929260254, "learning_rate": 2.745327177660212e-05, "loss": 0.23, "step": 7191 }, { "epoch": 0.3971725204329578, "grad_norm": 1.7988001108169556, "learning_rate": 2.7449952034551333e-05, "loss": 0.4667, "step": 7192 }, { "epoch": 0.3972277446432516, "grad_norm": 0.060006722807884216, "learning_rate": 2.744663205415537e-05, "loss": 0.0025, "step": 7193 }, { "epoch": 0.3972829688535454, "grad_norm": 3.6520066261291504, "learning_rate": 2.7443311835520447e-05, "loss": 1.2108, "step": 7194 }, { "epoch": 0.39733819306383916, "grad_norm": 3.1052889823913574, "learning_rate": 2.7439991378752795e-05, "loss": 0.0944, "step": 7195 }, { "epoch": 0.39739341727413297, "grad_norm": 3.0637834072113037, "learning_rate": 2.743667068395863e-05, "loss": 0.0919, "step": 7196 }, { "epoch": 0.39744864148442677, "grad_norm": 0.29945412278175354, "learning_rate": 2.7433349751244205e-05, "loss": 0.0118, "step": 7197 }, { "epoch": 0.39750386569472057, "grad_norm": 0.7211903929710388, "learning_rate": 2.7430028580715756e-05, "loss": 0.0337, "step": 7198 }, { "epoch": 0.3975590899050144, "grad_norm": 5.879300117492676, "learning_rate": 2.7426707172479536e-05, "loss": 0.9879, "step": 7199 }, { "epoch": 0.3976143141153082, "grad_norm": 3.204944133758545, "learning_rate": 2.7423385526641818e-05, "loss": 0.4091, "step": 7200 }, { "epoch": 0.3976695383256019, "grad_norm": 0.37613344192504883, "learning_rate": 2.7420063643308856e-05, "loss": 0.0072, "step": 7201 }, { "epoch": 0.3977247625358957, "grad_norm": 1.8460862636566162, "learning_rate": 2.7416741522586945e-05, "loss": 0.2761, "step": 7202 }, { "epoch": 0.39777998674618953, "grad_norm": 1.707005262374878, "learning_rate": 2.741341916458235e-05, "loss": 0.0717, "step": 7203 }, { "epoch": 0.39783521095648333, "grad_norm": 1.4094219207763672, "learning_rate": 2.741009656940137e-05, "loss": 0.3492, "step": 7204 }, { "epoch": 0.39789043516677713, "grad_norm": 5.086067199707031, "learning_rate": 2.740677373715031e-05, "loss": 1.1409, "step": 7205 }, { "epoch": 0.3979456593770709, "grad_norm": 0.012964299879968166, "learning_rate": 2.7403450667935474e-05, "loss": 0.0005, "step": 7206 }, { "epoch": 0.3980008835873647, "grad_norm": 0.03329973295331001, "learning_rate": 2.7400127361863167e-05, "loss": 0.0012, "step": 7207 }, { "epoch": 0.3980561077976585, "grad_norm": 3.225374698638916, "learning_rate": 2.739680381903972e-05, "loss": 0.1087, "step": 7208 }, { "epoch": 0.3981113320079523, "grad_norm": 0.11883470416069031, "learning_rate": 2.739348003957146e-05, "loss": 0.0029, "step": 7209 }, { "epoch": 0.3981665562182461, "grad_norm": 4.690496444702148, "learning_rate": 2.739015602356473e-05, "loss": 0.1555, "step": 7210 }, { "epoch": 0.3982217804285399, "grad_norm": 1.403307318687439, "learning_rate": 2.738683177112587e-05, "loss": 0.4005, "step": 7211 }, { "epoch": 0.39827700463883364, "grad_norm": 1.8455702066421509, "learning_rate": 2.7383507282361227e-05, "loss": 0.1267, "step": 7212 }, { "epoch": 0.39833222884912745, "grad_norm": 0.16362632811069489, "learning_rate": 2.7380182557377173e-05, "loss": 0.0066, "step": 7213 }, { "epoch": 0.39838745305942125, "grad_norm": 0.12376318126916885, "learning_rate": 2.737685759628006e-05, "loss": 0.0028, "step": 7214 }, { "epoch": 0.39844267726971505, "grad_norm": 0.3129456341266632, "learning_rate": 2.737353239917628e-05, "loss": 0.0084, "step": 7215 }, { "epoch": 0.39849790148000885, "grad_norm": 4.965508937835693, "learning_rate": 2.7370206966172205e-05, "loss": 0.1932, "step": 7216 }, { "epoch": 0.3985531256903026, "grad_norm": 0.2172355204820633, "learning_rate": 2.7366881297374225e-05, "loss": 0.0045, "step": 7217 }, { "epoch": 0.3986083499005964, "grad_norm": 0.17035479843616486, "learning_rate": 2.736355539288874e-05, "loss": 0.0082, "step": 7218 }, { "epoch": 0.3986635741108902, "grad_norm": 3.079167127609253, "learning_rate": 2.7360229252822156e-05, "loss": 0.9489, "step": 7219 }, { "epoch": 0.398718798321184, "grad_norm": 2.29640531539917, "learning_rate": 2.735690287728088e-05, "loss": 0.2536, "step": 7220 }, { "epoch": 0.3987740225314778, "grad_norm": 3.3673341274261475, "learning_rate": 2.7353576266371343e-05, "loss": 0.5179, "step": 7221 }, { "epoch": 0.3988292467417716, "grad_norm": 0.10496734827756882, "learning_rate": 2.7350249420199962e-05, "loss": 0.0044, "step": 7222 }, { "epoch": 0.39888447095206536, "grad_norm": 0.15465234220027924, "learning_rate": 2.734692233887318e-05, "loss": 0.0048, "step": 7223 }, { "epoch": 0.39893969516235916, "grad_norm": 1.1994268894195557, "learning_rate": 2.734359502249744e-05, "loss": 0.2637, "step": 7224 }, { "epoch": 0.39899491937265297, "grad_norm": 1.880998134613037, "learning_rate": 2.734026747117918e-05, "loss": 0.1402, "step": 7225 }, { "epoch": 0.39905014358294677, "grad_norm": 0.7477355003356934, "learning_rate": 2.733693968502487e-05, "loss": 0.1662, "step": 7226 }, { "epoch": 0.3991053677932406, "grad_norm": 0.19863030314445496, "learning_rate": 2.733361166414098e-05, "loss": 0.006, "step": 7227 }, { "epoch": 0.3991605920035344, "grad_norm": 0.03651103377342224, "learning_rate": 2.7330283408633964e-05, "loss": 0.0013, "step": 7228 }, { "epoch": 0.3992158162138281, "grad_norm": 0.5192597508430481, "learning_rate": 2.7326954918610316e-05, "loss": 0.0134, "step": 7229 }, { "epoch": 0.3992710404241219, "grad_norm": 0.061891961842775345, "learning_rate": 2.732362619417652e-05, "loss": 0.0032, "step": 7230 }, { "epoch": 0.39932626463441573, "grad_norm": 3.6866190433502197, "learning_rate": 2.732029723543908e-05, "loss": 1.2393, "step": 7231 }, { "epoch": 0.39938148884470953, "grad_norm": 2.9640133380889893, "learning_rate": 2.731696804250449e-05, "loss": 0.3558, "step": 7232 }, { "epoch": 0.39943671305500333, "grad_norm": 1.9311869144439697, "learning_rate": 2.7313638615479255e-05, "loss": 0.0186, "step": 7233 }, { "epoch": 0.3994919372652971, "grad_norm": 1.0790436267852783, "learning_rate": 2.7310308954469905e-05, "loss": 0.0864, "step": 7234 }, { "epoch": 0.3995471614755909, "grad_norm": 1.7951258420944214, "learning_rate": 2.7306979059582954e-05, "loss": 0.0668, "step": 7235 }, { "epoch": 0.3996023856858847, "grad_norm": 0.8046917915344238, "learning_rate": 2.7303648930924952e-05, "loss": 0.0323, "step": 7236 }, { "epoch": 0.3996576098961785, "grad_norm": 2.347573757171631, "learning_rate": 2.730031856860242e-05, "loss": 0.0423, "step": 7237 }, { "epoch": 0.3997128341064723, "grad_norm": 5.132033824920654, "learning_rate": 2.7296987972721914e-05, "loss": 1.2731, "step": 7238 }, { "epoch": 0.3997680583167661, "grad_norm": 2.563432216644287, "learning_rate": 2.7293657143389994e-05, "loss": 0.3735, "step": 7239 }, { "epoch": 0.39982328252705984, "grad_norm": 1.9351447820663452, "learning_rate": 2.7290326080713214e-05, "loss": 0.3588, "step": 7240 }, { "epoch": 0.39987850673735365, "grad_norm": 2.740462303161621, "learning_rate": 2.7286994784798145e-05, "loss": 0.4056, "step": 7241 }, { "epoch": 0.39993373094764745, "grad_norm": 2.3816404342651367, "learning_rate": 2.7283663255751373e-05, "loss": 0.0999, "step": 7242 }, { "epoch": 0.39998895515794125, "grad_norm": 0.7330580949783325, "learning_rate": 2.7280331493679474e-05, "loss": 0.0229, "step": 7243 }, { "epoch": 0.40004417936823505, "grad_norm": 0.017770111560821533, "learning_rate": 2.727699949868905e-05, "loss": 0.0007, "step": 7244 }, { "epoch": 0.4000994035785288, "grad_norm": 0.03212844952940941, "learning_rate": 2.727366727088669e-05, "loss": 0.0009, "step": 7245 }, { "epoch": 0.4001546277888226, "grad_norm": 1.9123961925506592, "learning_rate": 2.7270334810379008e-05, "loss": 0.1637, "step": 7246 }, { "epoch": 0.4002098519991164, "grad_norm": 3.0818114280700684, "learning_rate": 2.726700211727262e-05, "loss": 0.4553, "step": 7247 }, { "epoch": 0.4002650762094102, "grad_norm": 1.1731956005096436, "learning_rate": 2.7263669191674143e-05, "loss": 0.0783, "step": 7248 }, { "epoch": 0.400320300419704, "grad_norm": 0.9214805364608765, "learning_rate": 2.726033603369021e-05, "loss": 0.0259, "step": 7249 }, { "epoch": 0.4003755246299978, "grad_norm": 0.08718498796224594, "learning_rate": 2.725700264342746e-05, "loss": 0.0033, "step": 7250 }, { "epoch": 0.40043074884029156, "grad_norm": 1.2533706426620483, "learning_rate": 2.7253669020992534e-05, "loss": 0.0497, "step": 7251 }, { "epoch": 0.40048597305058536, "grad_norm": 0.5942964553833008, "learning_rate": 2.725033516649209e-05, "loss": 0.1146, "step": 7252 }, { "epoch": 0.40054119726087917, "grad_norm": 3.7287778854370117, "learning_rate": 2.7247001080032777e-05, "loss": 0.6094, "step": 7253 }, { "epoch": 0.40059642147117297, "grad_norm": 0.038309354335069656, "learning_rate": 2.724366676172127e-05, "loss": 0.0013, "step": 7254 }, { "epoch": 0.4006516456814668, "grad_norm": 0.7535353899002075, "learning_rate": 2.7240332211664245e-05, "loss": 0.0184, "step": 7255 }, { "epoch": 0.4007068698917606, "grad_norm": 2.03072452545166, "learning_rate": 2.7236997429968373e-05, "loss": 0.1697, "step": 7256 }, { "epoch": 0.4007620941020543, "grad_norm": 0.016250846907496452, "learning_rate": 2.7233662416740362e-05, "loss": 0.0004, "step": 7257 }, { "epoch": 0.4008173183123481, "grad_norm": 0.29238995909690857, "learning_rate": 2.723032717208689e-05, "loss": 0.0061, "step": 7258 }, { "epoch": 0.40087254252264193, "grad_norm": 3.2508952617645264, "learning_rate": 2.7226991696114665e-05, "loss": 0.3137, "step": 7259 }, { "epoch": 0.40092776673293573, "grad_norm": 0.8121210336685181, "learning_rate": 2.7223655988930405e-05, "loss": 0.0182, "step": 7260 }, { "epoch": 0.40098299094322953, "grad_norm": 1.2366905212402344, "learning_rate": 2.7220320050640823e-05, "loss": 0.0527, "step": 7261 }, { "epoch": 0.4010382151535233, "grad_norm": 2.688648223876953, "learning_rate": 2.721698388135265e-05, "loss": 0.0986, "step": 7262 }, { "epoch": 0.4010934393638171, "grad_norm": 3.4849953651428223, "learning_rate": 2.7213647481172616e-05, "loss": 0.1111, "step": 7263 }, { "epoch": 0.4011486635741109, "grad_norm": 2.830742835998535, "learning_rate": 2.7210310850207457e-05, "loss": 0.1463, "step": 7264 }, { "epoch": 0.4012038877844047, "grad_norm": 0.10369953513145447, "learning_rate": 2.7206973988563935e-05, "loss": 0.0027, "step": 7265 }, { "epoch": 0.4012591119946985, "grad_norm": 0.023160064592957497, "learning_rate": 2.7203636896348798e-05, "loss": 0.001, "step": 7266 }, { "epoch": 0.4013143362049923, "grad_norm": 1.243687391281128, "learning_rate": 2.72002995736688e-05, "loss": 0.0414, "step": 7267 }, { "epoch": 0.40136956041528604, "grad_norm": 5.729455947875977, "learning_rate": 2.719696202063073e-05, "loss": 1.1022, "step": 7268 }, { "epoch": 0.40142478462557984, "grad_norm": 3.9048666954040527, "learning_rate": 2.7193624237341348e-05, "loss": 0.6313, "step": 7269 }, { "epoch": 0.40148000883587365, "grad_norm": 0.01662723533809185, "learning_rate": 2.7190286223907452e-05, "loss": 0.0007, "step": 7270 }, { "epoch": 0.40153523304616745, "grad_norm": 0.08350665122270584, "learning_rate": 2.7186947980435833e-05, "loss": 0.0027, "step": 7271 }, { "epoch": 0.40159045725646125, "grad_norm": 0.07425647228956223, "learning_rate": 2.7183609507033278e-05, "loss": 0.0032, "step": 7272 }, { "epoch": 0.401645681466755, "grad_norm": 0.23653508722782135, "learning_rate": 2.7180270803806616e-05, "loss": 0.0057, "step": 7273 }, { "epoch": 0.4017009056770488, "grad_norm": 0.6234836578369141, "learning_rate": 2.7176931870862636e-05, "loss": 0.0237, "step": 7274 }, { "epoch": 0.4017561298873426, "grad_norm": 4.182833671569824, "learning_rate": 2.7173592708308187e-05, "loss": 0.7372, "step": 7275 }, { "epoch": 0.4018113540976364, "grad_norm": 4.29141092300415, "learning_rate": 2.7170253316250082e-05, "loss": 0.4152, "step": 7276 }, { "epoch": 0.4018665783079302, "grad_norm": 5.087009429931641, "learning_rate": 2.7166913694795155e-05, "loss": 0.892, "step": 7277 }, { "epoch": 0.401921802518224, "grad_norm": 0.3195335268974304, "learning_rate": 2.7163573844050258e-05, "loss": 0.0072, "step": 7278 }, { "epoch": 0.40197702672851776, "grad_norm": 0.03784290328621864, "learning_rate": 2.716023376412224e-05, "loss": 0.0016, "step": 7279 }, { "epoch": 0.40203225093881156, "grad_norm": 0.02959347702562809, "learning_rate": 2.715689345511796e-05, "loss": 0.0012, "step": 7280 }, { "epoch": 0.40208747514910537, "grad_norm": 0.06805504113435745, "learning_rate": 2.7153552917144286e-05, "loss": 0.0023, "step": 7281 }, { "epoch": 0.40214269935939917, "grad_norm": 0.09996679425239563, "learning_rate": 2.7150212150308083e-05, "loss": 0.0027, "step": 7282 }, { "epoch": 0.40219792356969297, "grad_norm": 4.420965671539307, "learning_rate": 2.714687115471624e-05, "loss": 0.6548, "step": 7283 }, { "epoch": 0.4022531477799867, "grad_norm": 0.17276893556118011, "learning_rate": 2.7143529930475648e-05, "loss": 0.0025, "step": 7284 }, { "epoch": 0.4023083719902805, "grad_norm": 0.147649884223938, "learning_rate": 2.714018847769319e-05, "loss": 0.0042, "step": 7285 }, { "epoch": 0.4023635962005743, "grad_norm": 0.3667799234390259, "learning_rate": 2.7136846796475777e-05, "loss": 0.0141, "step": 7286 }, { "epoch": 0.4024188204108681, "grad_norm": 0.1277395337820053, "learning_rate": 2.713350488693032e-05, "loss": 0.0042, "step": 7287 }, { "epoch": 0.40247404462116193, "grad_norm": 0.12819793820381165, "learning_rate": 2.713016274916373e-05, "loss": 0.0033, "step": 7288 }, { "epoch": 0.40252926883145573, "grad_norm": 5.2841339111328125, "learning_rate": 2.7126820383282938e-05, "loss": 1.0749, "step": 7289 }, { "epoch": 0.4025844930417495, "grad_norm": 1.7624930143356323, "learning_rate": 2.712347778939487e-05, "loss": 0.352, "step": 7290 }, { "epoch": 0.4026397172520433, "grad_norm": 6.523480415344238, "learning_rate": 2.712013496760647e-05, "loss": 0.6743, "step": 7291 }, { "epoch": 0.4026949414623371, "grad_norm": 6.7132463455200195, "learning_rate": 2.7116791918024686e-05, "loss": 1.3093, "step": 7292 }, { "epoch": 0.4027501656726309, "grad_norm": 2.9412732124328613, "learning_rate": 2.711344864075646e-05, "loss": 0.2507, "step": 7293 }, { "epoch": 0.4028053898829247, "grad_norm": 2.1976757049560547, "learning_rate": 2.7110105135908768e-05, "loss": 0.1093, "step": 7294 }, { "epoch": 0.4028606140932185, "grad_norm": 4.917292594909668, "learning_rate": 2.7106761403588566e-05, "loss": 0.794, "step": 7295 }, { "epoch": 0.40291583830351224, "grad_norm": 1.9581302404403687, "learning_rate": 2.7103417443902834e-05, "loss": 0.2029, "step": 7296 }, { "epoch": 0.40297106251380604, "grad_norm": 1.7056543827056885, "learning_rate": 2.710007325695856e-05, "loss": 0.2098, "step": 7297 }, { "epoch": 0.40302628672409985, "grad_norm": 0.10894280672073364, "learning_rate": 2.7096728842862724e-05, "loss": 0.003, "step": 7298 }, { "epoch": 0.40308151093439365, "grad_norm": 0.22180713713169098, "learning_rate": 2.709338420172233e-05, "loss": 0.0054, "step": 7299 }, { "epoch": 0.40313673514468745, "grad_norm": 2.597374677658081, "learning_rate": 2.7090039333644384e-05, "loss": 0.3294, "step": 7300 }, { "epoch": 0.4031919593549812, "grad_norm": 3.666073799133301, "learning_rate": 2.7086694238735894e-05, "loss": 0.5723, "step": 7301 }, { "epoch": 0.403247183565275, "grad_norm": 0.10533551126718521, "learning_rate": 2.7083348917103883e-05, "loss": 0.0023, "step": 7302 }, { "epoch": 0.4033024077755688, "grad_norm": 0.16567924618721008, "learning_rate": 2.7080003368855367e-05, "loss": 0.004, "step": 7303 }, { "epoch": 0.4033576319858626, "grad_norm": 1.4229785203933716, "learning_rate": 2.7076657594097397e-05, "loss": 0.0944, "step": 7304 }, { "epoch": 0.4034128561961564, "grad_norm": 2.297276735305786, "learning_rate": 2.7073311592937002e-05, "loss": 0.1435, "step": 7305 }, { "epoch": 0.4034680804064502, "grad_norm": 0.01787082850933075, "learning_rate": 2.7069965365481226e-05, "loss": 0.0009, "step": 7306 }, { "epoch": 0.40352330461674396, "grad_norm": 0.10294187813997269, "learning_rate": 2.7066618911837136e-05, "loss": 0.0025, "step": 7307 }, { "epoch": 0.40357852882703776, "grad_norm": 0.11184870451688766, "learning_rate": 2.7063272232111794e-05, "loss": 0.0029, "step": 7308 }, { "epoch": 0.40363375303733157, "grad_norm": 2.446537971496582, "learning_rate": 2.7059925326412257e-05, "loss": 0.9024, "step": 7309 }, { "epoch": 0.40368897724762537, "grad_norm": 4.391682147979736, "learning_rate": 2.7056578194845612e-05, "loss": 1.5961, "step": 7310 }, { "epoch": 0.40374420145791917, "grad_norm": 0.06075001135468483, "learning_rate": 2.7053230837518944e-05, "loss": 0.0025, "step": 7311 }, { "epoch": 0.4037994256682129, "grad_norm": 0.03678293153643608, "learning_rate": 2.7049883254539344e-05, "loss": 0.0015, "step": 7312 }, { "epoch": 0.4038546498785067, "grad_norm": 4.408691883087158, "learning_rate": 2.70465354460139e-05, "loss": 0.1503, "step": 7313 }, { "epoch": 0.4039098740888005, "grad_norm": 0.13353374600410461, "learning_rate": 2.704318741204973e-05, "loss": 0.0047, "step": 7314 }, { "epoch": 0.4039650982990943, "grad_norm": 1.656406044960022, "learning_rate": 2.7039839152753947e-05, "loss": 0.1151, "step": 7315 }, { "epoch": 0.40402032250938813, "grad_norm": 2.093691825866699, "learning_rate": 2.703649066823366e-05, "loss": 0.0488, "step": 7316 }, { "epoch": 0.40407554671968193, "grad_norm": 0.07420855015516281, "learning_rate": 2.7033141958596015e-05, "loss": 0.0033, "step": 7317 }, { "epoch": 0.4041307709299757, "grad_norm": 0.021468034014105797, "learning_rate": 2.7029793023948133e-05, "loss": 0.0007, "step": 7318 }, { "epoch": 0.4041859951402695, "grad_norm": 3.474942922592163, "learning_rate": 2.7026443864397153e-05, "loss": 0.4378, "step": 7319 }, { "epoch": 0.4042412193505633, "grad_norm": 2.3677196502685547, "learning_rate": 2.702309448005024e-05, "loss": 0.3212, "step": 7320 }, { "epoch": 0.4042964435608571, "grad_norm": 1.8891230821609497, "learning_rate": 2.701974487101453e-05, "loss": 0.0683, "step": 7321 }, { "epoch": 0.4043516677711509, "grad_norm": 0.4934145212173462, "learning_rate": 2.7016395037397207e-05, "loss": 0.0191, "step": 7322 }, { "epoch": 0.40440689198144464, "grad_norm": 0.21671561896800995, "learning_rate": 2.7013044979305427e-05, "loss": 0.0081, "step": 7323 }, { "epoch": 0.40446211619173844, "grad_norm": 0.03286362811923027, "learning_rate": 2.700969469684637e-05, "loss": 0.0012, "step": 7324 }, { "epoch": 0.40451734040203224, "grad_norm": 0.1435525268316269, "learning_rate": 2.700634419012723e-05, "loss": 0.0049, "step": 7325 }, { "epoch": 0.40457256461232605, "grad_norm": 1.5957759618759155, "learning_rate": 2.7002993459255192e-05, "loss": 0.3705, "step": 7326 }, { "epoch": 0.40462778882261985, "grad_norm": 0.058292318135499954, "learning_rate": 2.6999642504337457e-05, "loss": 0.0013, "step": 7327 }, { "epoch": 0.40468301303291365, "grad_norm": 4.040716648101807, "learning_rate": 2.699629132548123e-05, "loss": 0.8592, "step": 7328 }, { "epoch": 0.4047382372432074, "grad_norm": 0.05091124400496483, "learning_rate": 2.6992939922793723e-05, "loss": 0.0028, "step": 7329 }, { "epoch": 0.4047934614535012, "grad_norm": 1.5759459733963013, "learning_rate": 2.698958829638216e-05, "loss": 0.3351, "step": 7330 }, { "epoch": 0.404848685663795, "grad_norm": 3.0556421279907227, "learning_rate": 2.6986236446353774e-05, "loss": 1.2298, "step": 7331 }, { "epoch": 0.4049039098740888, "grad_norm": 1.1256877183914185, "learning_rate": 2.698288437281579e-05, "loss": 0.2754, "step": 7332 }, { "epoch": 0.4049591340843826, "grad_norm": 0.18826010823249817, "learning_rate": 2.6979532075875462e-05, "loss": 0.0055, "step": 7333 }, { "epoch": 0.4050143582946764, "grad_norm": 1.4893718957901, "learning_rate": 2.6976179555640024e-05, "loss": 0.0474, "step": 7334 }, { "epoch": 0.40506958250497016, "grad_norm": 0.23245544731616974, "learning_rate": 2.6972826812216747e-05, "loss": 0.006, "step": 7335 }, { "epoch": 0.40512480671526396, "grad_norm": 2.190458059310913, "learning_rate": 2.696947384571289e-05, "loss": 0.2458, "step": 7336 }, { "epoch": 0.40518003092555777, "grad_norm": 3.1552681922912598, "learning_rate": 2.696612065623572e-05, "loss": 0.1662, "step": 7337 }, { "epoch": 0.40523525513585157, "grad_norm": 1.7325737476348877, "learning_rate": 2.6962767243892524e-05, "loss": 0.0826, "step": 7338 }, { "epoch": 0.40529047934614537, "grad_norm": 0.7242985963821411, "learning_rate": 2.695941360879058e-05, "loss": 0.0164, "step": 7339 }, { "epoch": 0.4053457035564391, "grad_norm": 3.1132309436798096, "learning_rate": 2.695605975103718e-05, "loss": 0.2059, "step": 7340 }, { "epoch": 0.4054009277667329, "grad_norm": 1.5357747077941895, "learning_rate": 2.6952705670739628e-05, "loss": 0.1272, "step": 7341 }, { "epoch": 0.4054561519770267, "grad_norm": 2.1353142261505127, "learning_rate": 2.6949351368005223e-05, "loss": 0.1087, "step": 7342 }, { "epoch": 0.4055113761873205, "grad_norm": 0.15553872287273407, "learning_rate": 2.694599684294129e-05, "loss": 0.0031, "step": 7343 }, { "epoch": 0.40556660039761433, "grad_norm": 0.1395626962184906, "learning_rate": 2.694264209565514e-05, "loss": 0.0049, "step": 7344 }, { "epoch": 0.40562182460790813, "grad_norm": 0.12735074758529663, "learning_rate": 2.6939287126254105e-05, "loss": 0.0032, "step": 7345 }, { "epoch": 0.4056770488182019, "grad_norm": 1.9219053983688354, "learning_rate": 2.693593193484552e-05, "loss": 0.6943, "step": 7346 }, { "epoch": 0.4057322730284957, "grad_norm": 0.07030896097421646, "learning_rate": 2.693257652153673e-05, "loss": 0.0023, "step": 7347 }, { "epoch": 0.4057874972387895, "grad_norm": 1.2499319314956665, "learning_rate": 2.6929220886435078e-05, "loss": 0.0258, "step": 7348 }, { "epoch": 0.4058427214490833, "grad_norm": 1.8708021640777588, "learning_rate": 2.6925865029647922e-05, "loss": 0.7531, "step": 7349 }, { "epoch": 0.4058979456593771, "grad_norm": 0.12091541290283203, "learning_rate": 2.6922508951282625e-05, "loss": 0.0032, "step": 7350 }, { "epoch": 0.40595316986967084, "grad_norm": 0.22547614574432373, "learning_rate": 2.6919152651446565e-05, "loss": 0.0054, "step": 7351 }, { "epoch": 0.40600839407996464, "grad_norm": 5.870992660522461, "learning_rate": 2.691579613024711e-05, "loss": 0.4444, "step": 7352 }, { "epoch": 0.40606361829025844, "grad_norm": 3.6291699409484863, "learning_rate": 2.691243938779165e-05, "loss": 0.4395, "step": 7353 }, { "epoch": 0.40611884250055225, "grad_norm": 2.9716367721557617, "learning_rate": 2.690908242418757e-05, "loss": 0.2551, "step": 7354 }, { "epoch": 0.40617406671084605, "grad_norm": 0.8005124926567078, "learning_rate": 2.6905725239542284e-05, "loss": 0.0254, "step": 7355 }, { "epoch": 0.40622929092113985, "grad_norm": 2.2916958332061768, "learning_rate": 2.690236783396318e-05, "loss": 0.0966, "step": 7356 }, { "epoch": 0.4062845151314336, "grad_norm": 0.06233881413936615, "learning_rate": 2.689901020755768e-05, "loss": 0.0017, "step": 7357 }, { "epoch": 0.4063397393417274, "grad_norm": 0.856378972530365, "learning_rate": 2.6895652360433203e-05, "loss": 0.023, "step": 7358 }, { "epoch": 0.4063949635520212, "grad_norm": 5.495753288269043, "learning_rate": 2.689229429269718e-05, "loss": 1.0411, "step": 7359 }, { "epoch": 0.406450187762315, "grad_norm": 0.9686548113822937, "learning_rate": 2.6888936004457034e-05, "loss": 0.017, "step": 7360 }, { "epoch": 0.4065054119726088, "grad_norm": 3.782233953475952, "learning_rate": 2.6885577495820215e-05, "loss": 0.8658, "step": 7361 }, { "epoch": 0.40656063618290256, "grad_norm": 0.042557280510663986, "learning_rate": 2.688221876689417e-05, "loss": 0.0013, "step": 7362 }, { "epoch": 0.40661586039319636, "grad_norm": 3.4294235706329346, "learning_rate": 2.6878859817786355e-05, "loss": 1.208, "step": 7363 }, { "epoch": 0.40667108460349016, "grad_norm": 0.20614361763000488, "learning_rate": 2.6875500648604235e-05, "loss": 0.0081, "step": 7364 }, { "epoch": 0.40672630881378397, "grad_norm": 1.012294054031372, "learning_rate": 2.687214125945527e-05, "loss": 0.0437, "step": 7365 }, { "epoch": 0.40678153302407777, "grad_norm": 0.5582740902900696, "learning_rate": 2.686878165044694e-05, "loss": 0.0145, "step": 7366 }, { "epoch": 0.40683675723437157, "grad_norm": 2.239640235900879, "learning_rate": 2.686542182168674e-05, "loss": 0.2992, "step": 7367 }, { "epoch": 0.4068919814446653, "grad_norm": 0.11561812460422516, "learning_rate": 2.686206177328215e-05, "loss": 0.0033, "step": 7368 }, { "epoch": 0.4069472056549591, "grad_norm": 3.1157386302948, "learning_rate": 2.685870150534066e-05, "loss": 0.8497, "step": 7369 }, { "epoch": 0.4070024298652529, "grad_norm": 3.953781843185425, "learning_rate": 2.6855341017969786e-05, "loss": 0.3081, "step": 7370 }, { "epoch": 0.4070576540755467, "grad_norm": 0.2184518575668335, "learning_rate": 2.6851980311277034e-05, "loss": 0.0066, "step": 7371 }, { "epoch": 0.40711287828584053, "grad_norm": 2.711641311645508, "learning_rate": 2.6848619385369933e-05, "loss": 0.221, "step": 7372 }, { "epoch": 0.40716810249613433, "grad_norm": 0.1934933215379715, "learning_rate": 2.6845258240355997e-05, "loss": 0.0037, "step": 7373 }, { "epoch": 0.4072233267064281, "grad_norm": 2.623354434967041, "learning_rate": 2.6841896876342764e-05, "loss": 0.1368, "step": 7374 }, { "epoch": 0.4072785509167219, "grad_norm": 3.9497017860412598, "learning_rate": 2.683853529343777e-05, "loss": 0.1189, "step": 7375 }, { "epoch": 0.4073337751270157, "grad_norm": 0.38535916805267334, "learning_rate": 2.6835173491748562e-05, "loss": 0.0129, "step": 7376 }, { "epoch": 0.4073889993373095, "grad_norm": 2.4012980461120605, "learning_rate": 2.6831811471382695e-05, "loss": 0.353, "step": 7377 }, { "epoch": 0.4074442235476033, "grad_norm": 2.057119607925415, "learning_rate": 2.682844923244773e-05, "loss": 0.0649, "step": 7378 }, { "epoch": 0.40749944775789704, "grad_norm": 0.8481085896492004, "learning_rate": 2.6825086775051237e-05, "loss": 0.0666, "step": 7379 }, { "epoch": 0.40755467196819084, "grad_norm": 0.9185870885848999, "learning_rate": 2.6821724099300786e-05, "loss": 0.0198, "step": 7380 }, { "epoch": 0.40760989617848464, "grad_norm": 0.10861361771821976, "learning_rate": 2.6818361205303958e-05, "loss": 0.003, "step": 7381 }, { "epoch": 0.40766512038877845, "grad_norm": 0.30780303478240967, "learning_rate": 2.6814998093168347e-05, "loss": 0.0098, "step": 7382 }, { "epoch": 0.40772034459907225, "grad_norm": 1.8597533702850342, "learning_rate": 2.681163476300155e-05, "loss": 0.3516, "step": 7383 }, { "epoch": 0.40777556880936605, "grad_norm": 2.5776777267456055, "learning_rate": 2.6808271214911154e-05, "loss": 0.2991, "step": 7384 }, { "epoch": 0.4078307930196598, "grad_norm": 4.153050899505615, "learning_rate": 2.6804907449004787e-05, "loss": 1.7976, "step": 7385 }, { "epoch": 0.4078860172299536, "grad_norm": 9.196562767028809, "learning_rate": 2.6801543465390057e-05, "loss": 0.5707, "step": 7386 }, { "epoch": 0.4079412414402474, "grad_norm": 2.0256824493408203, "learning_rate": 2.679817926417459e-05, "loss": 0.2172, "step": 7387 }, { "epoch": 0.4079964656505412, "grad_norm": 1.8863612413406372, "learning_rate": 2.6794814845466012e-05, "loss": 0.0704, "step": 7388 }, { "epoch": 0.408051689860835, "grad_norm": 0.1317317634820938, "learning_rate": 2.6791450209371965e-05, "loss": 0.0055, "step": 7389 }, { "epoch": 0.40810691407112876, "grad_norm": 2.2090187072753906, "learning_rate": 2.6788085356000085e-05, "loss": 0.0799, "step": 7390 }, { "epoch": 0.40816213828142256, "grad_norm": 0.7614098191261292, "learning_rate": 2.6784720285458037e-05, "loss": 0.0317, "step": 7391 }, { "epoch": 0.40821736249171636, "grad_norm": 1.4930438995361328, "learning_rate": 2.6781354997853467e-05, "loss": 0.1147, "step": 7392 }, { "epoch": 0.40827258670201017, "grad_norm": 2.7171058654785156, "learning_rate": 2.6777989493294052e-05, "loss": 0.2541, "step": 7393 }, { "epoch": 0.40832781091230397, "grad_norm": 5.037413597106934, "learning_rate": 2.6774623771887453e-05, "loss": 0.0747, "step": 7394 }, { "epoch": 0.40838303512259777, "grad_norm": 0.2445681244134903, "learning_rate": 2.6771257833741348e-05, "loss": 0.0097, "step": 7395 }, { "epoch": 0.4084382593328915, "grad_norm": 1.862582802772522, "learning_rate": 2.6767891678963437e-05, "loss": 0.1033, "step": 7396 }, { "epoch": 0.4084934835431853, "grad_norm": 0.8650081157684326, "learning_rate": 2.67645253076614e-05, "loss": 0.0311, "step": 7397 }, { "epoch": 0.4085487077534791, "grad_norm": 3.6945266723632812, "learning_rate": 2.676115871994294e-05, "loss": 0.7677, "step": 7398 }, { "epoch": 0.4086039319637729, "grad_norm": 1.2689239978790283, "learning_rate": 2.6757791915915766e-05, "loss": 0.1574, "step": 7399 }, { "epoch": 0.40865915617406673, "grad_norm": 0.36573800444602966, "learning_rate": 2.6754424895687585e-05, "loss": 0.0139, "step": 7400 }, { "epoch": 0.4087143803843605, "grad_norm": 2.4880502223968506, "learning_rate": 2.6751057659366128e-05, "loss": 0.3254, "step": 7401 }, { "epoch": 0.4087696045946543, "grad_norm": 0.10896950960159302, "learning_rate": 2.6747690207059112e-05, "loss": 0.0027, "step": 7402 }, { "epoch": 0.4088248288049481, "grad_norm": 0.06204213947057724, "learning_rate": 2.674432253887428e-05, "loss": 0.0021, "step": 7403 }, { "epoch": 0.4088800530152419, "grad_norm": 0.039133328944444656, "learning_rate": 2.6740954654919374e-05, "loss": 0.0009, "step": 7404 }, { "epoch": 0.4089352772255357, "grad_norm": 0.2012830376625061, "learning_rate": 2.6737586555302133e-05, "loss": 0.0062, "step": 7405 }, { "epoch": 0.4089905014358295, "grad_norm": 0.13279515504837036, "learning_rate": 2.6734218240130315e-05, "loss": 0.0041, "step": 7406 }, { "epoch": 0.40904572564612324, "grad_norm": 1.8724839687347412, "learning_rate": 2.6730849709511692e-05, "loss": 0.2274, "step": 7407 }, { "epoch": 0.40910094985641704, "grad_norm": 0.068351611495018, "learning_rate": 2.6727480963554015e-05, "loss": 0.0023, "step": 7408 }, { "epoch": 0.40915617406671084, "grad_norm": 2.850666046142578, "learning_rate": 2.672411200236508e-05, "loss": 0.3084, "step": 7409 }, { "epoch": 0.40921139827700465, "grad_norm": 2.060081958770752, "learning_rate": 2.672074282605265e-05, "loss": 0.0461, "step": 7410 }, { "epoch": 0.40926662248729845, "grad_norm": 0.29649171233177185, "learning_rate": 2.6717373434724528e-05, "loss": 0.0084, "step": 7411 }, { "epoch": 0.40932184669759225, "grad_norm": 2.622405529022217, "learning_rate": 2.671400382848851e-05, "loss": 0.1923, "step": 7412 }, { "epoch": 0.409377070907886, "grad_norm": 0.09043841063976288, "learning_rate": 2.6710634007452383e-05, "loss": 0.0033, "step": 7413 }, { "epoch": 0.4094322951181798, "grad_norm": 4.6655120849609375, "learning_rate": 2.670726397172398e-05, "loss": 0.8668, "step": 7414 }, { "epoch": 0.4094875193284736, "grad_norm": 0.11982395499944687, "learning_rate": 2.670389372141111e-05, "loss": 0.0045, "step": 7415 }, { "epoch": 0.4095427435387674, "grad_norm": 0.8295523524284363, "learning_rate": 2.670052325662159e-05, "loss": 0.0184, "step": 7416 }, { "epoch": 0.4095979677490612, "grad_norm": 3.640590190887451, "learning_rate": 2.6697152577463256e-05, "loss": 0.7783, "step": 7417 }, { "epoch": 0.40965319195935496, "grad_norm": 0.3913673162460327, "learning_rate": 2.6693781684043943e-05, "loss": 0.0086, "step": 7418 }, { "epoch": 0.40970841616964876, "grad_norm": 0.04936012625694275, "learning_rate": 2.66904105764715e-05, "loss": 0.0018, "step": 7419 }, { "epoch": 0.40976364037994256, "grad_norm": 0.07293830811977386, "learning_rate": 2.6687039254853776e-05, "loss": 0.0029, "step": 7420 }, { "epoch": 0.40981886459023636, "grad_norm": 1.7617247104644775, "learning_rate": 2.6683667719298627e-05, "loss": 0.0867, "step": 7421 }, { "epoch": 0.40987408880053017, "grad_norm": 0.33419573307037354, "learning_rate": 2.6680295969913923e-05, "loss": 0.01, "step": 7422 }, { "epoch": 0.40992931301082397, "grad_norm": 2.206040859222412, "learning_rate": 2.667692400680753e-05, "loss": 0.2901, "step": 7423 }, { "epoch": 0.4099845372211177, "grad_norm": 2.145873546600342, "learning_rate": 2.6673551830087336e-05, "loss": 0.155, "step": 7424 }, { "epoch": 0.4100397614314115, "grad_norm": 1.5106854438781738, "learning_rate": 2.6670179439861215e-05, "loss": 0.1635, "step": 7425 }, { "epoch": 0.4100949856417053, "grad_norm": 3.497986316680908, "learning_rate": 2.666680683623706e-05, "loss": 0.3112, "step": 7426 }, { "epoch": 0.4101502098519991, "grad_norm": 0.1003652960062027, "learning_rate": 2.6663434019322782e-05, "loss": 0.0025, "step": 7427 }, { "epoch": 0.41020543406229293, "grad_norm": 2.9668564796447754, "learning_rate": 2.666006098922628e-05, "loss": 0.3023, "step": 7428 }, { "epoch": 0.4102606582725867, "grad_norm": 0.02185167744755745, "learning_rate": 2.6656687746055462e-05, "loss": 0.0005, "step": 7429 }, { "epoch": 0.4103158824828805, "grad_norm": 0.1214381530880928, "learning_rate": 2.6653314289918256e-05, "loss": 0.0055, "step": 7430 }, { "epoch": 0.4103711066931743, "grad_norm": 2.2990527153015137, "learning_rate": 2.6649940620922584e-05, "loss": 0.1922, "step": 7431 }, { "epoch": 0.4104263309034681, "grad_norm": 1.3853743076324463, "learning_rate": 2.6646566739176383e-05, "loss": 0.3934, "step": 7432 }, { "epoch": 0.4104815551137619, "grad_norm": 0.007591893430799246, "learning_rate": 2.6643192644787586e-05, "loss": 0.0003, "step": 7433 }, { "epoch": 0.4105367793240557, "grad_norm": 3.06567120552063, "learning_rate": 2.6639818337864144e-05, "loss": 0.6863, "step": 7434 }, { "epoch": 0.41059200353434944, "grad_norm": 0.22820128500461578, "learning_rate": 2.663644381851401e-05, "loss": 0.0056, "step": 7435 }, { "epoch": 0.41064722774464324, "grad_norm": 0.04451276361942291, "learning_rate": 2.663306908684515e-05, "loss": 0.0015, "step": 7436 }, { "epoch": 0.41070245195493704, "grad_norm": 3.44201922416687, "learning_rate": 2.6629694142965525e-05, "loss": 0.2121, "step": 7437 }, { "epoch": 0.41075767616523085, "grad_norm": 0.1294465810060501, "learning_rate": 2.6626318986983104e-05, "loss": 0.0064, "step": 7438 }, { "epoch": 0.41081290037552465, "grad_norm": 1.8288837671279907, "learning_rate": 2.6622943619005877e-05, "loss": 0.055, "step": 7439 }, { "epoch": 0.41086812458581845, "grad_norm": 0.6240993142127991, "learning_rate": 2.6619568039141834e-05, "loss": 0.0162, "step": 7440 }, { "epoch": 0.4109233487961122, "grad_norm": 0.026803625747561455, "learning_rate": 2.6616192247498957e-05, "loss": 0.0014, "step": 7441 }, { "epoch": 0.410978573006406, "grad_norm": 0.02331283688545227, "learning_rate": 2.6612816244185258e-05, "loss": 0.0009, "step": 7442 }, { "epoch": 0.4110337972166998, "grad_norm": 0.06115344911813736, "learning_rate": 2.6609440029308742e-05, "loss": 0.0022, "step": 7443 }, { "epoch": 0.4110890214269936, "grad_norm": 0.39445480704307556, "learning_rate": 2.660606360297742e-05, "loss": 0.0083, "step": 7444 }, { "epoch": 0.4111442456372874, "grad_norm": 4.011504650115967, "learning_rate": 2.6602686965299323e-05, "loss": 1.4442, "step": 7445 }, { "epoch": 0.41119946984758116, "grad_norm": 1.610694408416748, "learning_rate": 2.6599310116382475e-05, "loss": 0.0579, "step": 7446 }, { "epoch": 0.41125469405787496, "grad_norm": 0.032118409872055054, "learning_rate": 2.65959330563349e-05, "loss": 0.0013, "step": 7447 }, { "epoch": 0.41130991826816876, "grad_norm": 3.290619373321533, "learning_rate": 2.6592555785264652e-05, "loss": 0.2459, "step": 7448 }, { "epoch": 0.41136514247846256, "grad_norm": 0.1602567732334137, "learning_rate": 2.6589178303279773e-05, "loss": 0.0051, "step": 7449 }, { "epoch": 0.41142036668875637, "grad_norm": 1.9114640951156616, "learning_rate": 2.6585800610488326e-05, "loss": 0.1881, "step": 7450 }, { "epoch": 0.41147559089905017, "grad_norm": 0.027324896305799484, "learning_rate": 2.658242270699837e-05, "loss": 0.0009, "step": 7451 }, { "epoch": 0.4115308151093439, "grad_norm": 2.099907636642456, "learning_rate": 2.6579044592917965e-05, "loss": 0.1453, "step": 7452 }, { "epoch": 0.4115860393196377, "grad_norm": 3.5320887565612793, "learning_rate": 2.6575666268355204e-05, "loss": 0.2703, "step": 7453 }, { "epoch": 0.4116412635299315, "grad_norm": 0.2039995938539505, "learning_rate": 2.6572287733418152e-05, "loss": 0.0065, "step": 7454 }, { "epoch": 0.4116964877402253, "grad_norm": 0.07020389288663864, "learning_rate": 2.6568908988214906e-05, "loss": 0.0027, "step": 7455 }, { "epoch": 0.41175171195051913, "grad_norm": 4.657036781311035, "learning_rate": 2.6565530032853562e-05, "loss": 0.847, "step": 7456 }, { "epoch": 0.4118069361608129, "grad_norm": 0.8593257069587708, "learning_rate": 2.6562150867442217e-05, "loss": 0.0114, "step": 7457 }, { "epoch": 0.4118621603711067, "grad_norm": 0.026649028062820435, "learning_rate": 2.655877149208899e-05, "loss": 0.0012, "step": 7458 }, { "epoch": 0.4119173845814005, "grad_norm": 0.036608703434467316, "learning_rate": 2.655539190690199e-05, "loss": 0.0009, "step": 7459 }, { "epoch": 0.4119726087916943, "grad_norm": 0.0581938773393631, "learning_rate": 2.6552012111989335e-05, "loss": 0.0024, "step": 7460 }, { "epoch": 0.4120278330019881, "grad_norm": 1.9570560455322266, "learning_rate": 2.6548632107459166e-05, "loss": 0.1394, "step": 7461 }, { "epoch": 0.4120830572122819, "grad_norm": 2.6962051391601562, "learning_rate": 2.654525189341961e-05, "loss": 0.35, "step": 7462 }, { "epoch": 0.41213828142257564, "grad_norm": 0.35979852080345154, "learning_rate": 2.654187146997881e-05, "loss": 0.0083, "step": 7463 }, { "epoch": 0.41219350563286944, "grad_norm": 4.804599761962891, "learning_rate": 2.6538490837244925e-05, "loss": 0.7213, "step": 7464 }, { "epoch": 0.41224872984316324, "grad_norm": 0.3977881669998169, "learning_rate": 2.6535109995326096e-05, "loss": 0.0141, "step": 7465 }, { "epoch": 0.41230395405345704, "grad_norm": 3.391272783279419, "learning_rate": 2.6531728944330502e-05, "loss": 0.2778, "step": 7466 }, { "epoch": 0.41235917826375085, "grad_norm": 3.1757967472076416, "learning_rate": 2.6528347684366297e-05, "loss": 0.5996, "step": 7467 }, { "epoch": 0.4124144024740446, "grad_norm": 0.18895387649536133, "learning_rate": 2.6524966215541667e-05, "loss": 0.0053, "step": 7468 }, { "epoch": 0.4124696266843384, "grad_norm": 0.1139545887708664, "learning_rate": 2.6521584537964787e-05, "loss": 0.0031, "step": 7469 }, { "epoch": 0.4125248508946322, "grad_norm": 5.170706272125244, "learning_rate": 2.6518202651743855e-05, "loss": 0.6168, "step": 7470 }, { "epoch": 0.412580075104926, "grad_norm": 0.10814519971609116, "learning_rate": 2.6514820556987067e-05, "loss": 0.0035, "step": 7471 }, { "epoch": 0.4126352993152198, "grad_norm": 2.8856985569000244, "learning_rate": 2.6511438253802624e-05, "loss": 0.692, "step": 7472 }, { "epoch": 0.4126905235255136, "grad_norm": 0.06558965891599655, "learning_rate": 2.6508055742298727e-05, "loss": 0.0017, "step": 7473 }, { "epoch": 0.41274574773580736, "grad_norm": 0.028752001002430916, "learning_rate": 2.6504673022583603e-05, "loss": 0.0011, "step": 7474 }, { "epoch": 0.41280097194610116, "grad_norm": 0.18590331077575684, "learning_rate": 2.650129009476547e-05, "loss": 0.0046, "step": 7475 }, { "epoch": 0.41285619615639496, "grad_norm": 0.03336455672979355, "learning_rate": 2.6497906958952558e-05, "loss": 0.0012, "step": 7476 }, { "epoch": 0.41291142036668876, "grad_norm": 0.35198625922203064, "learning_rate": 2.6494523615253106e-05, "loss": 0.0097, "step": 7477 }, { "epoch": 0.41296664457698257, "grad_norm": 5.900866985321045, "learning_rate": 2.649114006377535e-05, "loss": 1.135, "step": 7478 }, { "epoch": 0.41302186878727637, "grad_norm": 4.5115790367126465, "learning_rate": 2.6487756304627546e-05, "loss": 0.6155, "step": 7479 }, { "epoch": 0.4130770929975701, "grad_norm": 0.0439273901283741, "learning_rate": 2.6484372337917953e-05, "loss": 0.0016, "step": 7480 }, { "epoch": 0.4131323172078639, "grad_norm": 0.25339147448539734, "learning_rate": 2.6480988163754823e-05, "loss": 0.0088, "step": 7481 }, { "epoch": 0.4131875414181577, "grad_norm": 1.7807223796844482, "learning_rate": 2.6477603782246433e-05, "loss": 0.111, "step": 7482 }, { "epoch": 0.4132427656284515, "grad_norm": 0.627081573009491, "learning_rate": 2.6474219193501055e-05, "loss": 0.0187, "step": 7483 }, { "epoch": 0.4132979898387453, "grad_norm": 0.23262763023376465, "learning_rate": 2.647083439762698e-05, "loss": 0.0079, "step": 7484 }, { "epoch": 0.4133532140490391, "grad_norm": 6.362146854400635, "learning_rate": 2.646744939473249e-05, "loss": 0.8663, "step": 7485 }, { "epoch": 0.4134084382593329, "grad_norm": 0.03542716056108475, "learning_rate": 2.6464064184925874e-05, "loss": 0.0013, "step": 7486 }, { "epoch": 0.4134636624696267, "grad_norm": 0.49928614497184753, "learning_rate": 2.6460678768315443e-05, "loss": 0.0162, "step": 7487 }, { "epoch": 0.4135188866799205, "grad_norm": 0.08296684920787811, "learning_rate": 2.6457293145009512e-05, "loss": 0.0023, "step": 7488 }, { "epoch": 0.4135741108902143, "grad_norm": 3.3790225982666016, "learning_rate": 2.6453907315116385e-05, "loss": 0.8692, "step": 7489 }, { "epoch": 0.4136293351005081, "grad_norm": 3.316445827484131, "learning_rate": 2.6450521278744395e-05, "loss": 0.1881, "step": 7490 }, { "epoch": 0.41368455931080184, "grad_norm": 6.144484043121338, "learning_rate": 2.6447135036001857e-05, "loss": 0.3259, "step": 7491 }, { "epoch": 0.41373978352109564, "grad_norm": 2.4070465564727783, "learning_rate": 2.6443748586997126e-05, "loss": 0.0567, "step": 7492 }, { "epoch": 0.41379500773138944, "grad_norm": 0.5944128036499023, "learning_rate": 2.6440361931838525e-05, "loss": 0.014, "step": 7493 }, { "epoch": 0.41385023194168324, "grad_norm": 1.9877548217773438, "learning_rate": 2.6436975070634416e-05, "loss": 0.1726, "step": 7494 }, { "epoch": 0.41390545615197705, "grad_norm": 0.0765358954668045, "learning_rate": 2.6433588003493148e-05, "loss": 0.0021, "step": 7495 }, { "epoch": 0.4139606803622708, "grad_norm": 5.2931671142578125, "learning_rate": 2.643020073052308e-05, "loss": 0.8897, "step": 7496 }, { "epoch": 0.4140159045725646, "grad_norm": 4.2014479637146, "learning_rate": 2.6426813251832587e-05, "loss": 1.2336, "step": 7497 }, { "epoch": 0.4140711287828584, "grad_norm": 0.013295850716531277, "learning_rate": 2.6423425567530046e-05, "loss": 0.0006, "step": 7498 }, { "epoch": 0.4141263529931522, "grad_norm": 0.08513691276311874, "learning_rate": 2.6420037677723827e-05, "loss": 0.0026, "step": 7499 }, { "epoch": 0.414181577203446, "grad_norm": 0.1858217865228653, "learning_rate": 2.641664958252233e-05, "loss": 0.0044, "step": 7500 }, { "epoch": 0.4142368014137398, "grad_norm": 1.6068333387374878, "learning_rate": 2.641326128203394e-05, "loss": 0.0423, "step": 7501 }, { "epoch": 0.41429202562403356, "grad_norm": 0.01724288985133171, "learning_rate": 2.640987277636707e-05, "loss": 0.0006, "step": 7502 }, { "epoch": 0.41434724983432736, "grad_norm": 2.546321392059326, "learning_rate": 2.6406484065630124e-05, "loss": 0.5441, "step": 7503 }, { "epoch": 0.41440247404462116, "grad_norm": 4.622097969055176, "learning_rate": 2.6403095149931507e-05, "loss": 1.3252, "step": 7504 }, { "epoch": 0.41445769825491496, "grad_norm": 0.0767182782292366, "learning_rate": 2.6399706029379653e-05, "loss": 0.0027, "step": 7505 }, { "epoch": 0.41451292246520877, "grad_norm": 4.315362453460693, "learning_rate": 2.6396316704082985e-05, "loss": 0.863, "step": 7506 }, { "epoch": 0.4145681466755025, "grad_norm": 0.04649021476507187, "learning_rate": 2.6392927174149933e-05, "loss": 0.0022, "step": 7507 }, { "epoch": 0.4146233708857963, "grad_norm": 0.017347251996397972, "learning_rate": 2.6389537439688938e-05, "loss": 0.0005, "step": 7508 }, { "epoch": 0.4146785950960901, "grad_norm": 0.18145900964736938, "learning_rate": 2.6386147500808454e-05, "loss": 0.0042, "step": 7509 }, { "epoch": 0.4147338193063839, "grad_norm": 3.887399435043335, "learning_rate": 2.6382757357616927e-05, "loss": 0.4152, "step": 7510 }, { "epoch": 0.4147890435166777, "grad_norm": 0.011595945805311203, "learning_rate": 2.637936701022283e-05, "loss": 0.0005, "step": 7511 }, { "epoch": 0.4148442677269715, "grad_norm": 0.1527019441127777, "learning_rate": 2.637597645873461e-05, "loss": 0.0049, "step": 7512 }, { "epoch": 0.4148994919372653, "grad_norm": 2.9757328033447266, "learning_rate": 2.637258570326076e-05, "loss": 0.0428, "step": 7513 }, { "epoch": 0.4149547161475591, "grad_norm": 0.14224453270435333, "learning_rate": 2.6369194743909744e-05, "loss": 0.0036, "step": 7514 }, { "epoch": 0.4150099403578529, "grad_norm": 0.012029418721795082, "learning_rate": 2.636580358079006e-05, "loss": 0.0005, "step": 7515 }, { "epoch": 0.4150651645681467, "grad_norm": 0.22544753551483154, "learning_rate": 2.63624122140102e-05, "loss": 0.0062, "step": 7516 }, { "epoch": 0.4151203887784405, "grad_norm": 0.21592438220977783, "learning_rate": 2.6359020643678657e-05, "loss": 0.0078, "step": 7517 }, { "epoch": 0.4151756129887343, "grad_norm": 0.1210395097732544, "learning_rate": 2.635562886990394e-05, "loss": 0.0037, "step": 7518 }, { "epoch": 0.41523083719902804, "grad_norm": 0.11162921041250229, "learning_rate": 2.6352236892794563e-05, "loss": 0.0025, "step": 7519 }, { "epoch": 0.41528606140932184, "grad_norm": 1.078543782234192, "learning_rate": 2.6348844712459044e-05, "loss": 0.0249, "step": 7520 }, { "epoch": 0.41534128561961564, "grad_norm": 0.33644992113113403, "learning_rate": 2.634545232900591e-05, "loss": 0.0089, "step": 7521 }, { "epoch": 0.41539650982990944, "grad_norm": 0.07836759835481644, "learning_rate": 2.6342059742543682e-05, "loss": 0.0025, "step": 7522 }, { "epoch": 0.41545173404020325, "grad_norm": 5.190088748931885, "learning_rate": 2.6338666953180917e-05, "loss": 0.4775, "step": 7523 }, { "epoch": 0.415506958250497, "grad_norm": 0.10875993221998215, "learning_rate": 2.6335273961026148e-05, "loss": 0.0041, "step": 7524 }, { "epoch": 0.4155621824607908, "grad_norm": 4.575653553009033, "learning_rate": 2.6331880766187925e-05, "loss": 0.5487, "step": 7525 }, { "epoch": 0.4156174066710846, "grad_norm": 0.5546875596046448, "learning_rate": 2.6328487368774816e-05, "loss": 0.0187, "step": 7526 }, { "epoch": 0.4156726308813784, "grad_norm": 0.23561885952949524, "learning_rate": 2.632509376889538e-05, "loss": 0.0093, "step": 7527 }, { "epoch": 0.4157278550916722, "grad_norm": 2.266123056411743, "learning_rate": 2.6321699966658184e-05, "loss": 0.5459, "step": 7528 }, { "epoch": 0.415783079301966, "grad_norm": 1.3882834911346436, "learning_rate": 2.6318305962171815e-05, "loss": 0.1625, "step": 7529 }, { "epoch": 0.41583830351225975, "grad_norm": 0.019406111910939217, "learning_rate": 2.6314911755544842e-05, "loss": 0.0006, "step": 7530 }, { "epoch": 0.41589352772255356, "grad_norm": 0.07136629521846771, "learning_rate": 2.631151734688587e-05, "loss": 0.002, "step": 7531 }, { "epoch": 0.41594875193284736, "grad_norm": 4.549195289611816, "learning_rate": 2.630812273630349e-05, "loss": 0.7233, "step": 7532 }, { "epoch": 0.41600397614314116, "grad_norm": 0.02038015052676201, "learning_rate": 2.63047279239063e-05, "loss": 0.0007, "step": 7533 }, { "epoch": 0.41605920035343497, "grad_norm": 1.9600709676742554, "learning_rate": 2.6301332909802923e-05, "loss": 0.1944, "step": 7534 }, { "epoch": 0.4161144245637287, "grad_norm": 3.2585623264312744, "learning_rate": 2.6297937694101964e-05, "loss": 0.2548, "step": 7535 }, { "epoch": 0.4161696487740225, "grad_norm": 0.025994326919317245, "learning_rate": 2.6294542276912047e-05, "loss": 0.001, "step": 7536 }, { "epoch": 0.4162248729843163, "grad_norm": 4.675134658813477, "learning_rate": 2.6291146658341805e-05, "loss": 0.5116, "step": 7537 }, { "epoch": 0.4162800971946101, "grad_norm": 1.4959826469421387, "learning_rate": 2.6287750838499862e-05, "loss": 0.1534, "step": 7538 }, { "epoch": 0.4163353214049039, "grad_norm": 3.374547243118286, "learning_rate": 2.6284354817494882e-05, "loss": 0.6742, "step": 7539 }, { "epoch": 0.4163905456151977, "grad_norm": 0.02574632689356804, "learning_rate": 2.6280958595435495e-05, "loss": 0.0012, "step": 7540 }, { "epoch": 0.4164457698254915, "grad_norm": 2.1659066677093506, "learning_rate": 2.6277562172430358e-05, "loss": 0.548, "step": 7541 }, { "epoch": 0.4165009940357853, "grad_norm": 0.42763978242874146, "learning_rate": 2.6274165548588143e-05, "loss": 0.0111, "step": 7542 }, { "epoch": 0.4165562182460791, "grad_norm": 0.8893898129463196, "learning_rate": 2.6270768724017507e-05, "loss": 0.0084, "step": 7543 }, { "epoch": 0.4166114424563729, "grad_norm": 0.2163151204586029, "learning_rate": 2.6267371698827128e-05, "loss": 0.0035, "step": 7544 }, { "epoch": 0.4166666666666667, "grad_norm": 0.3365241587162018, "learning_rate": 2.626397447312569e-05, "loss": 0.0114, "step": 7545 }, { "epoch": 0.41672189087696043, "grad_norm": 3.0876450538635254, "learning_rate": 2.626057704702187e-05, "loss": 0.3624, "step": 7546 }, { "epoch": 0.41677711508725424, "grad_norm": 5.035957336425781, "learning_rate": 2.6257179420624367e-05, "loss": 1.2942, "step": 7547 }, { "epoch": 0.41683233929754804, "grad_norm": 0.059781819581985474, "learning_rate": 2.6253781594041882e-05, "loss": 0.0021, "step": 7548 }, { "epoch": 0.41688756350784184, "grad_norm": 4.663821220397949, "learning_rate": 2.625038356738312e-05, "loss": 0.5242, "step": 7549 }, { "epoch": 0.41694278771813564, "grad_norm": 0.05582224950194359, "learning_rate": 2.6246985340756794e-05, "loss": 0.002, "step": 7550 }, { "epoch": 0.41699801192842945, "grad_norm": 1.262171983718872, "learning_rate": 2.6243586914271624e-05, "loss": 0.0841, "step": 7551 }, { "epoch": 0.4170532361387232, "grad_norm": 4.329230308532715, "learning_rate": 2.6240188288036336e-05, "loss": 1.1882, "step": 7552 }, { "epoch": 0.417108460349017, "grad_norm": 2.0881218910217285, "learning_rate": 2.6236789462159654e-05, "loss": 0.2313, "step": 7553 }, { "epoch": 0.4171636845593108, "grad_norm": 1.7252023220062256, "learning_rate": 2.6233390436750328e-05, "loss": 0.1059, "step": 7554 }, { "epoch": 0.4172189087696046, "grad_norm": 0.05103234946727753, "learning_rate": 2.6229991211917093e-05, "loss": 0.0019, "step": 7555 }, { "epoch": 0.4172741329798984, "grad_norm": 0.3660500943660736, "learning_rate": 2.62265917877687e-05, "loss": 0.0109, "step": 7556 }, { "epoch": 0.4173293571901922, "grad_norm": 2.300860643386841, "learning_rate": 2.6223192164413914e-05, "loss": 0.1511, "step": 7557 }, { "epoch": 0.41738458140048595, "grad_norm": 0.04635176435112953, "learning_rate": 2.6219792341961493e-05, "loss": 0.0017, "step": 7558 }, { "epoch": 0.41743980561077976, "grad_norm": 1.254957675933838, "learning_rate": 2.6216392320520205e-05, "loss": 0.1297, "step": 7559 }, { "epoch": 0.41749502982107356, "grad_norm": 0.7367035746574402, "learning_rate": 2.621299210019883e-05, "loss": 0.0197, "step": 7560 }, { "epoch": 0.41755025403136736, "grad_norm": 2.780315637588501, "learning_rate": 2.620959168110615e-05, "loss": 0.4986, "step": 7561 }, { "epoch": 0.41760547824166117, "grad_norm": 1.4811700582504272, "learning_rate": 2.6206191063350955e-05, "loss": 0.0363, "step": 7562 }, { "epoch": 0.4176607024519549, "grad_norm": 2.2343506813049316, "learning_rate": 2.6202790247042043e-05, "loss": 0.0593, "step": 7563 }, { "epoch": 0.4177159266622487, "grad_norm": 4.525289535522461, "learning_rate": 2.619938923228821e-05, "loss": 0.9392, "step": 7564 }, { "epoch": 0.4177711508725425, "grad_norm": 5.063432216644287, "learning_rate": 2.6195988019198268e-05, "loss": 0.4062, "step": 7565 }, { "epoch": 0.4178263750828363, "grad_norm": 0.029363175854086876, "learning_rate": 2.619258660788103e-05, "loss": 0.0011, "step": 7566 }, { "epoch": 0.4178815992931301, "grad_norm": 0.038219667971134186, "learning_rate": 2.618918499844531e-05, "loss": 0.0013, "step": 7567 }, { "epoch": 0.4179368235034239, "grad_norm": 3.0571138858795166, "learning_rate": 2.618578319099995e-05, "loss": 0.5214, "step": 7568 }, { "epoch": 0.4179920477137177, "grad_norm": 0.3274812400341034, "learning_rate": 2.6182381185653772e-05, "loss": 0.0117, "step": 7569 }, { "epoch": 0.4180472719240115, "grad_norm": 0.24385997653007507, "learning_rate": 2.617897898251562e-05, "loss": 0.0074, "step": 7570 }, { "epoch": 0.4181024961343053, "grad_norm": 0.1289362609386444, "learning_rate": 2.6175576581694345e-05, "loss": 0.004, "step": 7571 }, { "epoch": 0.4181577203445991, "grad_norm": 0.1518346071243286, "learning_rate": 2.6172173983298782e-05, "loss": 0.0053, "step": 7572 }, { "epoch": 0.4182129445548929, "grad_norm": 1.725625991821289, "learning_rate": 2.616877118743781e-05, "loss": 0.163, "step": 7573 }, { "epoch": 0.41826816876518663, "grad_norm": 0.26781055331230164, "learning_rate": 2.6165368194220282e-05, "loss": 0.0081, "step": 7574 }, { "epoch": 0.41832339297548043, "grad_norm": 3.2733185291290283, "learning_rate": 2.616196500375508e-05, "loss": 0.5336, "step": 7575 }, { "epoch": 0.41837861718577424, "grad_norm": 0.18712584674358368, "learning_rate": 2.6158561616151072e-05, "loss": 0.0054, "step": 7576 }, { "epoch": 0.41843384139606804, "grad_norm": 0.4144923686981201, "learning_rate": 2.6155158031517146e-05, "loss": 0.018, "step": 7577 }, { "epoch": 0.41848906560636184, "grad_norm": 0.8638169169425964, "learning_rate": 2.6151754249962188e-05, "loss": 0.0187, "step": 7578 }, { "epoch": 0.41854428981665565, "grad_norm": 4.068567752838135, "learning_rate": 2.6148350271595102e-05, "loss": 0.5749, "step": 7579 }, { "epoch": 0.4185995140269494, "grad_norm": 0.7906198501586914, "learning_rate": 2.6144946096524785e-05, "loss": 0.021, "step": 7580 }, { "epoch": 0.4186547382372432, "grad_norm": 2.420698642730713, "learning_rate": 2.614154172486015e-05, "loss": 0.0914, "step": 7581 }, { "epoch": 0.418709962447537, "grad_norm": 0.2805352509021759, "learning_rate": 2.6138137156710112e-05, "loss": 0.0042, "step": 7582 }, { "epoch": 0.4187651866578308, "grad_norm": 0.02936496026813984, "learning_rate": 2.613473239218359e-05, "loss": 0.0013, "step": 7583 }, { "epoch": 0.4188204108681246, "grad_norm": 0.22591528296470642, "learning_rate": 2.613132743138951e-05, "loss": 0.007, "step": 7584 }, { "epoch": 0.41887563507841835, "grad_norm": 1.8725205659866333, "learning_rate": 2.6127922274436816e-05, "loss": 0.3628, "step": 7585 }, { "epoch": 0.41893085928871215, "grad_norm": 1.2462141513824463, "learning_rate": 2.6124516921434442e-05, "loss": 0.0755, "step": 7586 }, { "epoch": 0.41898608349900596, "grad_norm": 2.588124990463257, "learning_rate": 2.6121111372491337e-05, "loss": 0.1798, "step": 7587 }, { "epoch": 0.41904130770929976, "grad_norm": 3.1146068572998047, "learning_rate": 2.611770562771645e-05, "loss": 0.688, "step": 7588 }, { "epoch": 0.41909653191959356, "grad_norm": 4.301279544830322, "learning_rate": 2.6114299687218747e-05, "loss": 0.7595, "step": 7589 }, { "epoch": 0.41915175612988737, "grad_norm": 2.2221567630767822, "learning_rate": 2.6110893551107186e-05, "loss": 0.5159, "step": 7590 }, { "epoch": 0.4192069803401811, "grad_norm": 0.05685275048017502, "learning_rate": 2.610748721949075e-05, "loss": 0.0022, "step": 7591 }, { "epoch": 0.4192622045504749, "grad_norm": 1.5280410051345825, "learning_rate": 2.6104080692478408e-05, "loss": 0.2658, "step": 7592 }, { "epoch": 0.4193174287607687, "grad_norm": 1.1533681154251099, "learning_rate": 2.6100673970179142e-05, "loss": 0.192, "step": 7593 }, { "epoch": 0.4193726529710625, "grad_norm": 2.0651891231536865, "learning_rate": 2.609726705270195e-05, "loss": 0.1749, "step": 7594 }, { "epoch": 0.4194278771813563, "grad_norm": 4.043938636779785, "learning_rate": 2.6093859940155833e-05, "loss": 0.8586, "step": 7595 }, { "epoch": 0.4194831013916501, "grad_norm": 0.9838019013404846, "learning_rate": 2.609045263264978e-05, "loss": 0.0352, "step": 7596 }, { "epoch": 0.4195383256019439, "grad_norm": 0.039346080273389816, "learning_rate": 2.6087045130292813e-05, "loss": 0.0011, "step": 7597 }, { "epoch": 0.4195935498122377, "grad_norm": 1.9147696495056152, "learning_rate": 2.608363743319394e-05, "loss": 0.4411, "step": 7598 }, { "epoch": 0.4196487740225315, "grad_norm": 8.548148155212402, "learning_rate": 2.608022954146219e-05, "loss": 1.4966, "step": 7599 }, { "epoch": 0.4197039982328253, "grad_norm": 4.556563377380371, "learning_rate": 2.607682145520659e-05, "loss": 0.818, "step": 7600 }, { "epoch": 0.4197592224431191, "grad_norm": 2.065023899078369, "learning_rate": 2.6073413174536162e-05, "loss": 0.0378, "step": 7601 }, { "epoch": 0.41981444665341283, "grad_norm": 0.009515517391264439, "learning_rate": 2.6070004699559965e-05, "loss": 0.0003, "step": 7602 }, { "epoch": 0.41986967086370663, "grad_norm": 0.018508344888687134, "learning_rate": 2.6066596030387034e-05, "loss": 0.0005, "step": 7603 }, { "epoch": 0.41992489507400044, "grad_norm": 4.5742669105529785, "learning_rate": 2.6063187167126423e-05, "loss": 0.2981, "step": 7604 }, { "epoch": 0.41998011928429424, "grad_norm": 5.162734031677246, "learning_rate": 2.6059778109887198e-05, "loss": 0.139, "step": 7605 }, { "epoch": 0.42003534349458804, "grad_norm": 0.05912071466445923, "learning_rate": 2.605636885877841e-05, "loss": 0.0016, "step": 7606 }, { "epoch": 0.42009056770488185, "grad_norm": 0.9272761344909668, "learning_rate": 2.6052959413909156e-05, "loss": 0.0258, "step": 7607 }, { "epoch": 0.4201457919151756, "grad_norm": 3.028512954711914, "learning_rate": 2.604954977538849e-05, "loss": 0.5657, "step": 7608 }, { "epoch": 0.4202010161254694, "grad_norm": 1.3878326416015625, "learning_rate": 2.6046139943325504e-05, "loss": 0.0293, "step": 7609 }, { "epoch": 0.4202562403357632, "grad_norm": 0.6125283241271973, "learning_rate": 2.604272991782929e-05, "loss": 0.0178, "step": 7610 }, { "epoch": 0.420311464546057, "grad_norm": 1.7679442167282104, "learning_rate": 2.6039319699008937e-05, "loss": 0.0561, "step": 7611 }, { "epoch": 0.4203666887563508, "grad_norm": 0.052867185324430466, "learning_rate": 2.603590928697356e-05, "loss": 0.0024, "step": 7612 }, { "epoch": 0.42042191296664455, "grad_norm": 2.1689302921295166, "learning_rate": 2.6032498681832262e-05, "loss": 0.1879, "step": 7613 }, { "epoch": 0.42047713717693835, "grad_norm": 4.580920219421387, "learning_rate": 2.6029087883694155e-05, "loss": 0.7914, "step": 7614 }, { "epoch": 0.42053236138723216, "grad_norm": 0.12578079104423523, "learning_rate": 2.6025676892668367e-05, "loss": 0.0035, "step": 7615 }, { "epoch": 0.42058758559752596, "grad_norm": 2.620173692703247, "learning_rate": 2.6022265708864016e-05, "loss": 0.2506, "step": 7616 }, { "epoch": 0.42064280980781976, "grad_norm": 0.14707548916339874, "learning_rate": 2.6018854332390243e-05, "loss": 0.0041, "step": 7617 }, { "epoch": 0.42069803401811356, "grad_norm": 2.2021403312683105, "learning_rate": 2.6015442763356182e-05, "loss": 0.2323, "step": 7618 }, { "epoch": 0.4207532582284073, "grad_norm": 3.4846575260162354, "learning_rate": 2.6012031001870983e-05, "loss": 0.3103, "step": 7619 }, { "epoch": 0.4208084824387011, "grad_norm": 5.031467437744141, "learning_rate": 2.6008619048043796e-05, "loss": 1.1726, "step": 7620 }, { "epoch": 0.4208637066489949, "grad_norm": 2.7555088996887207, "learning_rate": 2.6005206901983782e-05, "loss": 0.4124, "step": 7621 }, { "epoch": 0.4209189308592887, "grad_norm": 3.359145402908325, "learning_rate": 2.60017945638001e-05, "loss": 0.3457, "step": 7622 }, { "epoch": 0.4209741550695825, "grad_norm": 0.13262230157852173, "learning_rate": 2.599838203360193e-05, "loss": 0.0033, "step": 7623 }, { "epoch": 0.42102937927987627, "grad_norm": 0.08521253615617752, "learning_rate": 2.5994969311498436e-05, "loss": 0.0023, "step": 7624 }, { "epoch": 0.4210846034901701, "grad_norm": 1.7812715768814087, "learning_rate": 2.5991556397598804e-05, "loss": 0.2471, "step": 7625 }, { "epoch": 0.4211398277004639, "grad_norm": 3.0108447074890137, "learning_rate": 2.5988143292012237e-05, "loss": 0.8529, "step": 7626 }, { "epoch": 0.4211950519107577, "grad_norm": 0.14088451862335205, "learning_rate": 2.598472999484791e-05, "loss": 0.004, "step": 7627 }, { "epoch": 0.4212502761210515, "grad_norm": 4.5289788246154785, "learning_rate": 2.598131650621503e-05, "loss": 1.3539, "step": 7628 }, { "epoch": 0.4213055003313453, "grad_norm": 3.466517925262451, "learning_rate": 2.597790282622281e-05, "loss": 0.3255, "step": 7629 }, { "epoch": 0.42136072454163903, "grad_norm": 0.053062066435813904, "learning_rate": 2.5974488954980467e-05, "loss": 0.0016, "step": 7630 }, { "epoch": 0.42141594875193283, "grad_norm": 2.9082841873168945, "learning_rate": 2.597107489259721e-05, "loss": 0.77, "step": 7631 }, { "epoch": 0.42147117296222664, "grad_norm": 3.2159647941589355, "learning_rate": 2.5967660639182262e-05, "loss": 1.0699, "step": 7632 }, { "epoch": 0.42152639717252044, "grad_norm": 0.43367260694503784, "learning_rate": 2.596424619484487e-05, "loss": 0.0118, "step": 7633 }, { "epoch": 0.42158162138281424, "grad_norm": 2.487825632095337, "learning_rate": 2.5960831559694254e-05, "loss": 0.1965, "step": 7634 }, { "epoch": 0.42163684559310805, "grad_norm": 0.14405792951583862, "learning_rate": 2.595741673383967e-05, "loss": 0.0038, "step": 7635 }, { "epoch": 0.4216920698034018, "grad_norm": 4.337713718414307, "learning_rate": 2.5954001717390366e-05, "loss": 0.7598, "step": 7636 }, { "epoch": 0.4217472940136956, "grad_norm": 0.15163880586624146, "learning_rate": 2.5950586510455597e-05, "loss": 0.0072, "step": 7637 }, { "epoch": 0.4218025182239894, "grad_norm": 2.0876636505126953, "learning_rate": 2.5947171113144623e-05, "loss": 0.0968, "step": 7638 }, { "epoch": 0.4218577424342832, "grad_norm": 2.1773087978363037, "learning_rate": 2.594375552556672e-05, "loss": 0.3667, "step": 7639 }, { "epoch": 0.421912966644577, "grad_norm": 3.238272190093994, "learning_rate": 2.594033974783115e-05, "loss": 0.6903, "step": 7640 }, { "epoch": 0.42196819085487075, "grad_norm": 0.07884760946035385, "learning_rate": 2.5936923780047202e-05, "loss": 0.0029, "step": 7641 }, { "epoch": 0.42202341506516455, "grad_norm": 0.07962220907211304, "learning_rate": 2.593350762232416e-05, "loss": 0.0034, "step": 7642 }, { "epoch": 0.42207863927545836, "grad_norm": 2.0589442253112793, "learning_rate": 2.5930091274771315e-05, "loss": 0.1428, "step": 7643 }, { "epoch": 0.42213386348575216, "grad_norm": 3.3235158920288086, "learning_rate": 2.5926674737497973e-05, "loss": 0.7412, "step": 7644 }, { "epoch": 0.42218908769604596, "grad_norm": 2.9455902576446533, "learning_rate": 2.5923258010613436e-05, "loss": 0.3874, "step": 7645 }, { "epoch": 0.42224431190633976, "grad_norm": 3.730294704437256, "learning_rate": 2.5919841094227005e-05, "loss": 1.0479, "step": 7646 }, { "epoch": 0.4222995361166335, "grad_norm": 2.747138261795044, "learning_rate": 2.5916423988448013e-05, "loss": 0.2254, "step": 7647 }, { "epoch": 0.4223547603269273, "grad_norm": 4.29149055480957, "learning_rate": 2.5913006693385762e-05, "loss": 0.5159, "step": 7648 }, { "epoch": 0.4224099845372211, "grad_norm": 0.04239737614989281, "learning_rate": 2.5909589209149602e-05, "loss": 0.0018, "step": 7649 }, { "epoch": 0.4224652087475149, "grad_norm": 3.6212847232818604, "learning_rate": 2.5906171535848855e-05, "loss": 0.8207, "step": 7650 }, { "epoch": 0.4225204329578087, "grad_norm": 2.175260543823242, "learning_rate": 2.5902753673592872e-05, "loss": 0.2394, "step": 7651 }, { "epoch": 0.42257565716810247, "grad_norm": 0.35731440782546997, "learning_rate": 2.5899335622490995e-05, "loss": 0.0118, "step": 7652 }, { "epoch": 0.4226308813783963, "grad_norm": 0.1290845423936844, "learning_rate": 2.5895917382652565e-05, "loss": 0.0027, "step": 7653 }, { "epoch": 0.4226861055886901, "grad_norm": 4.900962829589844, "learning_rate": 2.5892498954186963e-05, "loss": 0.9263, "step": 7654 }, { "epoch": 0.4227413297989839, "grad_norm": 0.04621243104338646, "learning_rate": 2.5889080337203546e-05, "loss": 0.0017, "step": 7655 }, { "epoch": 0.4227965540092777, "grad_norm": 1.266975998878479, "learning_rate": 2.5885661531811677e-05, "loss": 0.0303, "step": 7656 }, { "epoch": 0.4228517782195715, "grad_norm": 0.033072322607040405, "learning_rate": 2.5882242538120745e-05, "loss": 0.0014, "step": 7657 }, { "epoch": 0.42290700242986523, "grad_norm": 0.11907314509153366, "learning_rate": 2.5878823356240123e-05, "loss": 0.0036, "step": 7658 }, { "epoch": 0.42296222664015903, "grad_norm": 0.0904221460223198, "learning_rate": 2.587540398627921e-05, "loss": 0.0036, "step": 7659 }, { "epoch": 0.42301745085045284, "grad_norm": 0.5637482404708862, "learning_rate": 2.5871984428347396e-05, "loss": 0.0194, "step": 7660 }, { "epoch": 0.42307267506074664, "grad_norm": 1.0663419961929321, "learning_rate": 2.586856468255408e-05, "loss": 0.0206, "step": 7661 }, { "epoch": 0.42312789927104044, "grad_norm": 4.226824760437012, "learning_rate": 2.5865144749008678e-05, "loss": 1.3793, "step": 7662 }, { "epoch": 0.42318312348133424, "grad_norm": 4.874966621398926, "learning_rate": 2.5861724627820596e-05, "loss": 1.233, "step": 7663 }, { "epoch": 0.423238347691628, "grad_norm": 4.9926371574401855, "learning_rate": 2.5858304319099253e-05, "loss": 0.5219, "step": 7664 }, { "epoch": 0.4232935719019218, "grad_norm": 1.213516116142273, "learning_rate": 2.5854883822954083e-05, "loss": 0.0393, "step": 7665 }, { "epoch": 0.4233487961122156, "grad_norm": 0.12115710228681564, "learning_rate": 2.5851463139494505e-05, "loss": 0.0042, "step": 7666 }, { "epoch": 0.4234040203225094, "grad_norm": 1.7604845762252808, "learning_rate": 2.5848042268829967e-05, "loss": 0.1163, "step": 7667 }, { "epoch": 0.4234592445328032, "grad_norm": 0.7689539790153503, "learning_rate": 2.5844621211069908e-05, "loss": 0.0224, "step": 7668 }, { "epoch": 0.42351446874309695, "grad_norm": 0.12712503969669342, "learning_rate": 2.5841199966323775e-05, "loss": 0.0042, "step": 7669 }, { "epoch": 0.42356969295339075, "grad_norm": 0.4959537386894226, "learning_rate": 2.583777853470103e-05, "loss": 0.0151, "step": 7670 }, { "epoch": 0.42362491716368456, "grad_norm": 2.6968941688537598, "learning_rate": 2.5834356916311122e-05, "loss": 0.1801, "step": 7671 }, { "epoch": 0.42368014137397836, "grad_norm": 0.08924409002065659, "learning_rate": 2.5830935111263537e-05, "loss": 0.0028, "step": 7672 }, { "epoch": 0.42373536558427216, "grad_norm": 1.4301339387893677, "learning_rate": 2.5827513119667736e-05, "loss": 0.0252, "step": 7673 }, { "epoch": 0.42379058979456596, "grad_norm": 0.3596220016479492, "learning_rate": 2.5824090941633193e-05, "loss": 0.0068, "step": 7674 }, { "epoch": 0.4238458140048597, "grad_norm": 1.588053584098816, "learning_rate": 2.5820668577269407e-05, "loss": 0.0557, "step": 7675 }, { "epoch": 0.4239010382151535, "grad_norm": 0.2754705250263214, "learning_rate": 2.5817246026685858e-05, "loss": 0.0075, "step": 7676 }, { "epoch": 0.4239562624254473, "grad_norm": 1.907910704612732, "learning_rate": 2.581382328999205e-05, "loss": 0.2384, "step": 7677 }, { "epoch": 0.4240114866357411, "grad_norm": 2.4956836700439453, "learning_rate": 2.5810400367297487e-05, "loss": 0.4456, "step": 7678 }, { "epoch": 0.4240667108460349, "grad_norm": 3.319004535675049, "learning_rate": 2.5806977258711668e-05, "loss": 0.4805, "step": 7679 }, { "epoch": 0.42412193505632867, "grad_norm": 0.6728551387786865, "learning_rate": 2.5803553964344116e-05, "loss": 0.0185, "step": 7680 }, { "epoch": 0.42417715926662247, "grad_norm": 2.905355453491211, "learning_rate": 2.580013048430435e-05, "loss": 1.0185, "step": 7681 }, { "epoch": 0.4242323834769163, "grad_norm": 0.076170414686203, "learning_rate": 2.5796706818701904e-05, "loss": 0.0025, "step": 7682 }, { "epoch": 0.4242876076872101, "grad_norm": 2.3272159099578857, "learning_rate": 2.5793282967646302e-05, "loss": 0.6053, "step": 7683 }, { "epoch": 0.4243428318975039, "grad_norm": 1.2973949909210205, "learning_rate": 2.578985893124708e-05, "loss": 0.0533, "step": 7684 }, { "epoch": 0.4243980561077977, "grad_norm": 1.950738787651062, "learning_rate": 2.5786434709613795e-05, "loss": 0.0602, "step": 7685 }, { "epoch": 0.42445328031809143, "grad_norm": 1.1397581100463867, "learning_rate": 2.5783010302855988e-05, "loss": 0.0279, "step": 7686 }, { "epoch": 0.42450850452838523, "grad_norm": 1.204804539680481, "learning_rate": 2.5779585711083216e-05, "loss": 0.0356, "step": 7687 }, { "epoch": 0.42456372873867904, "grad_norm": 4.768440246582031, "learning_rate": 2.5776160934405042e-05, "loss": 1.1002, "step": 7688 }, { "epoch": 0.42461895294897284, "grad_norm": 0.7748927474021912, "learning_rate": 2.5772735972931036e-05, "loss": 0.011, "step": 7689 }, { "epoch": 0.42467417715926664, "grad_norm": 3.330359935760498, "learning_rate": 2.5769310826770775e-05, "loss": 0.6344, "step": 7690 }, { "epoch": 0.4247294013695604, "grad_norm": 0.9687013030052185, "learning_rate": 2.5765885496033836e-05, "loss": 0.0294, "step": 7691 }, { "epoch": 0.4247846255798542, "grad_norm": 0.18060213327407837, "learning_rate": 2.57624599808298e-05, "loss": 0.0055, "step": 7692 }, { "epoch": 0.424839849790148, "grad_norm": 0.3307187557220459, "learning_rate": 2.575903428126827e-05, "loss": 0.0089, "step": 7693 }, { "epoch": 0.4248950740004418, "grad_norm": 0.01737969182431698, "learning_rate": 2.5755608397458836e-05, "loss": 0.0008, "step": 7694 }, { "epoch": 0.4249502982107356, "grad_norm": 2.5042998790740967, "learning_rate": 2.5752182329511105e-05, "loss": 0.5515, "step": 7695 }, { "epoch": 0.4250055224210294, "grad_norm": 1.6204683780670166, "learning_rate": 2.574875607753469e-05, "loss": 0.2384, "step": 7696 }, { "epoch": 0.42506074663132315, "grad_norm": 0.3073291480541229, "learning_rate": 2.5745329641639192e-05, "loss": 0.0079, "step": 7697 }, { "epoch": 0.42511597084161695, "grad_norm": 2.0334596633911133, "learning_rate": 2.574190302193425e-05, "loss": 0.1943, "step": 7698 }, { "epoch": 0.42517119505191076, "grad_norm": 1.2200733423233032, "learning_rate": 2.5738476218529478e-05, "loss": 0.0324, "step": 7699 }, { "epoch": 0.42522641926220456, "grad_norm": 1.0382903814315796, "learning_rate": 2.573504923153452e-05, "loss": 0.0246, "step": 7700 }, { "epoch": 0.42528164347249836, "grad_norm": 4.281463146209717, "learning_rate": 2.573162206105901e-05, "loss": 0.9059, "step": 7701 }, { "epoch": 0.42533686768279216, "grad_norm": 0.013253409415483475, "learning_rate": 2.5728194707212587e-05, "loss": 0.0003, "step": 7702 }, { "epoch": 0.4253920918930859, "grad_norm": 0.038997918367385864, "learning_rate": 2.572476717010491e-05, "loss": 0.0016, "step": 7703 }, { "epoch": 0.4254473161033797, "grad_norm": 4.276026725769043, "learning_rate": 2.5721339449845643e-05, "loss": 1.0582, "step": 7704 }, { "epoch": 0.4255025403136735, "grad_norm": 0.039325445890426636, "learning_rate": 2.5717911546544425e-05, "loss": 0.0019, "step": 7705 }, { "epoch": 0.4255577645239673, "grad_norm": 2.676701068878174, "learning_rate": 2.5714483460310947e-05, "loss": 0.374, "step": 7706 }, { "epoch": 0.4256129887342611, "grad_norm": 4.470614910125732, "learning_rate": 2.5711055191254878e-05, "loss": 0.393, "step": 7707 }, { "epoch": 0.42566821294455487, "grad_norm": 2.894737720489502, "learning_rate": 2.5707626739485888e-05, "loss": 0.1173, "step": 7708 }, { "epoch": 0.42572343715484867, "grad_norm": 0.8083159923553467, "learning_rate": 2.570419810511367e-05, "loss": 0.0194, "step": 7709 }, { "epoch": 0.4257786613651425, "grad_norm": 0.5402449369430542, "learning_rate": 2.570076928824792e-05, "loss": 0.018, "step": 7710 }, { "epoch": 0.4258338855754363, "grad_norm": 0.027040589600801468, "learning_rate": 2.5697340288998326e-05, "loss": 0.0007, "step": 7711 }, { "epoch": 0.4258891097857301, "grad_norm": 2.59340500831604, "learning_rate": 2.5693911107474598e-05, "loss": 0.0758, "step": 7712 }, { "epoch": 0.4259443339960239, "grad_norm": 3.524369239807129, "learning_rate": 2.5690481743786447e-05, "loss": 0.9476, "step": 7713 }, { "epoch": 0.42599955820631763, "grad_norm": 0.13647064566612244, "learning_rate": 2.568705219804358e-05, "loss": 0.0043, "step": 7714 }, { "epoch": 0.42605478241661143, "grad_norm": 0.994003176689148, "learning_rate": 2.5683622470355728e-05, "loss": 0.1475, "step": 7715 }, { "epoch": 0.42611000662690524, "grad_norm": 0.2965843975543976, "learning_rate": 2.5680192560832607e-05, "loss": 0.008, "step": 7716 }, { "epoch": 0.42616523083719904, "grad_norm": 2.626551389694214, "learning_rate": 2.5676762469583957e-05, "loss": 0.1835, "step": 7717 }, { "epoch": 0.42622045504749284, "grad_norm": 3.021759033203125, "learning_rate": 2.5673332196719517e-05, "loss": 0.4761, "step": 7718 }, { "epoch": 0.4262756792577866, "grad_norm": 0.5517913699150085, "learning_rate": 2.566990174234903e-05, "loss": 0.0153, "step": 7719 }, { "epoch": 0.4263309034680804, "grad_norm": 5.800675392150879, "learning_rate": 2.5666471106582243e-05, "loss": 0.7929, "step": 7720 }, { "epoch": 0.4263861276783742, "grad_norm": 3.47078800201416, "learning_rate": 2.566304028952891e-05, "loss": 0.2046, "step": 7721 }, { "epoch": 0.426441351888668, "grad_norm": 3.202697515487671, "learning_rate": 2.56596092912988e-05, "loss": 0.2895, "step": 7722 }, { "epoch": 0.4264965760989618, "grad_norm": 2.8073034286499023, "learning_rate": 2.5656178112001672e-05, "loss": 0.2414, "step": 7723 }, { "epoch": 0.4265518003092556, "grad_norm": 2.2008535861968994, "learning_rate": 2.565274675174731e-05, "loss": 0.0863, "step": 7724 }, { "epoch": 0.42660702451954935, "grad_norm": 0.07583397626876831, "learning_rate": 2.5649315210645486e-05, "loss": 0.003, "step": 7725 }, { "epoch": 0.42666224872984315, "grad_norm": 0.1468159556388855, "learning_rate": 2.564588348880598e-05, "loss": 0.0046, "step": 7726 }, { "epoch": 0.42671747294013695, "grad_norm": 0.034409668296575546, "learning_rate": 2.564245158633859e-05, "loss": 0.0015, "step": 7727 }, { "epoch": 0.42677269715043076, "grad_norm": 0.011709162965416908, "learning_rate": 2.5639019503353115e-05, "loss": 0.0004, "step": 7728 }, { "epoch": 0.42682792136072456, "grad_norm": 0.020466318354010582, "learning_rate": 2.563558723995935e-05, "loss": 0.0006, "step": 7729 }, { "epoch": 0.4268831455710183, "grad_norm": 1.3065075874328613, "learning_rate": 2.5632154796267104e-05, "loss": 0.0947, "step": 7730 }, { "epoch": 0.4269383697813121, "grad_norm": 0.28281012177467346, "learning_rate": 2.5628722172386195e-05, "loss": 0.0064, "step": 7731 }, { "epoch": 0.4269935939916059, "grad_norm": 1.522810935974121, "learning_rate": 2.5625289368426437e-05, "loss": 0.0963, "step": 7732 }, { "epoch": 0.4270488182018997, "grad_norm": 0.04982774332165718, "learning_rate": 2.562185638449766e-05, "loss": 0.0016, "step": 7733 }, { "epoch": 0.4271040424121935, "grad_norm": 0.7828007340431213, "learning_rate": 2.5618423220709693e-05, "loss": 0.0212, "step": 7734 }, { "epoch": 0.4271592666224873, "grad_norm": 2.2746241092681885, "learning_rate": 2.561498987717237e-05, "loss": 0.1505, "step": 7735 }, { "epoch": 0.42721449083278107, "grad_norm": 0.39954692125320435, "learning_rate": 2.5611556353995533e-05, "loss": 0.0106, "step": 7736 }, { "epoch": 0.42726971504307487, "grad_norm": 2.3985257148742676, "learning_rate": 2.5608122651289037e-05, "loss": 0.1184, "step": 7737 }, { "epoch": 0.4273249392533687, "grad_norm": 0.34953343868255615, "learning_rate": 2.5604688769162735e-05, "loss": 0.1137, "step": 7738 }, { "epoch": 0.4273801634636625, "grad_norm": 2.7603979110717773, "learning_rate": 2.560125470772647e-05, "loss": 0.1958, "step": 7739 }, { "epoch": 0.4274353876739563, "grad_norm": 4.152681827545166, "learning_rate": 2.5597820467090134e-05, "loss": 0.6408, "step": 7740 }, { "epoch": 0.4274906118842501, "grad_norm": 4.2485761642456055, "learning_rate": 2.5594386047363577e-05, "loss": 1.0314, "step": 7741 }, { "epoch": 0.42754583609454383, "grad_norm": 1.0252832174301147, "learning_rate": 2.559095144865669e-05, "loss": 0.0304, "step": 7742 }, { "epoch": 0.42760106030483763, "grad_norm": 3.8996901512145996, "learning_rate": 2.5587516671079348e-05, "loss": 0.7584, "step": 7743 }, { "epoch": 0.42765628451513144, "grad_norm": 2.0278639793395996, "learning_rate": 2.5584081714741437e-05, "loss": 0.1027, "step": 7744 }, { "epoch": 0.42771150872542524, "grad_norm": 2.9079229831695557, "learning_rate": 2.558064657975286e-05, "loss": 0.3942, "step": 7745 }, { "epoch": 0.42776673293571904, "grad_norm": 0.3194867968559265, "learning_rate": 2.557721126622351e-05, "loss": 0.0101, "step": 7746 }, { "epoch": 0.4278219571460128, "grad_norm": 1.175955891609192, "learning_rate": 2.557377577426329e-05, "loss": 0.034, "step": 7747 }, { "epoch": 0.4278771813563066, "grad_norm": 0.11089353263378143, "learning_rate": 2.5570340103982118e-05, "loss": 0.0019, "step": 7748 }, { "epoch": 0.4279324055666004, "grad_norm": 2.8828635215759277, "learning_rate": 2.5566904255489906e-05, "loss": 0.3298, "step": 7749 }, { "epoch": 0.4279876297768942, "grad_norm": 3.149289846420288, "learning_rate": 2.556346822889658e-05, "loss": 0.2755, "step": 7750 }, { "epoch": 0.428042853987188, "grad_norm": 2.113050937652588, "learning_rate": 2.5560032024312072e-05, "loss": 0.0937, "step": 7751 }, { "epoch": 0.4280980781974818, "grad_norm": 0.17172232270240784, "learning_rate": 2.5556595641846302e-05, "loss": 0.005, "step": 7752 }, { "epoch": 0.42815330240777555, "grad_norm": 4.5909833908081055, "learning_rate": 2.5553159081609225e-05, "loss": 0.6385, "step": 7753 }, { "epoch": 0.42820852661806935, "grad_norm": 2.5502660274505615, "learning_rate": 2.554972234371077e-05, "loss": 0.1816, "step": 7754 }, { "epoch": 0.42826375082836315, "grad_norm": 0.13544929027557373, "learning_rate": 2.554628542826091e-05, "loss": 0.004, "step": 7755 }, { "epoch": 0.42831897503865696, "grad_norm": 1.2392809391021729, "learning_rate": 2.5542848335369587e-05, "loss": 0.0641, "step": 7756 }, { "epoch": 0.42837419924895076, "grad_norm": 0.5187918543815613, "learning_rate": 2.553941106514676e-05, "loss": 0.0306, "step": 7757 }, { "epoch": 0.4284294234592445, "grad_norm": 1.6823004484176636, "learning_rate": 2.553597361770241e-05, "loss": 0.1147, "step": 7758 }, { "epoch": 0.4284846476695383, "grad_norm": 0.3435794413089752, "learning_rate": 2.5532535993146502e-05, "loss": 0.0075, "step": 7759 }, { "epoch": 0.4285398718798321, "grad_norm": 4.015007495880127, "learning_rate": 2.5529098191589014e-05, "loss": 0.6418, "step": 7760 }, { "epoch": 0.4285950960901259, "grad_norm": 0.6253699064254761, "learning_rate": 2.5525660213139936e-05, "loss": 0.0109, "step": 7761 }, { "epoch": 0.4286503203004197, "grad_norm": 1.7660471200942993, "learning_rate": 2.5522222057909255e-05, "loss": 0.1058, "step": 7762 }, { "epoch": 0.4287055445107135, "grad_norm": 0.698451042175293, "learning_rate": 2.5518783726006976e-05, "loss": 0.0124, "step": 7763 }, { "epoch": 0.42876076872100727, "grad_norm": 3.1586496829986572, "learning_rate": 2.5515345217543085e-05, "loss": 0.7978, "step": 7764 }, { "epoch": 0.42881599293130107, "grad_norm": 3.6970255374908447, "learning_rate": 2.5511906532627607e-05, "loss": 0.3864, "step": 7765 }, { "epoch": 0.4288712171415949, "grad_norm": 0.2570801377296448, "learning_rate": 2.550846767137054e-05, "loss": 0.0083, "step": 7766 }, { "epoch": 0.4289264413518887, "grad_norm": 2.087364673614502, "learning_rate": 2.5505028633881918e-05, "loss": 0.2868, "step": 7767 }, { "epoch": 0.4289816655621825, "grad_norm": 0.06138521060347557, "learning_rate": 2.5501589420271755e-05, "loss": 0.0015, "step": 7768 }, { "epoch": 0.4290368897724762, "grad_norm": 1.0297924280166626, "learning_rate": 2.5498150030650083e-05, "loss": 0.0261, "step": 7769 }, { "epoch": 0.42909211398277003, "grad_norm": 0.10307008028030396, "learning_rate": 2.5494710465126936e-05, "loss": 0.0029, "step": 7770 }, { "epoch": 0.42914733819306383, "grad_norm": 0.0721975564956665, "learning_rate": 2.5491270723812363e-05, "loss": 0.0024, "step": 7771 }, { "epoch": 0.42920256240335763, "grad_norm": 3.7174651622772217, "learning_rate": 2.5487830806816405e-05, "loss": 0.6327, "step": 7772 }, { "epoch": 0.42925778661365144, "grad_norm": 0.015472211875021458, "learning_rate": 2.5484390714249117e-05, "loss": 0.0005, "step": 7773 }, { "epoch": 0.42931301082394524, "grad_norm": 1.2078564167022705, "learning_rate": 2.5480950446220557e-05, "loss": 0.0454, "step": 7774 }, { "epoch": 0.429368235034239, "grad_norm": 1.3761028051376343, "learning_rate": 2.5477510002840788e-05, "loss": 0.0752, "step": 7775 }, { "epoch": 0.4294234592445328, "grad_norm": 1.3806941509246826, "learning_rate": 2.5474069384219873e-05, "loss": 0.0513, "step": 7776 }, { "epoch": 0.4294786834548266, "grad_norm": 0.0292676854878664, "learning_rate": 2.5470628590467907e-05, "loss": 0.0013, "step": 7777 }, { "epoch": 0.4295339076651204, "grad_norm": 0.020927364006638527, "learning_rate": 2.546718762169495e-05, "loss": 0.0009, "step": 7778 }, { "epoch": 0.4295891318754142, "grad_norm": 2.4221301078796387, "learning_rate": 2.54637464780111e-05, "loss": 0.1722, "step": 7779 }, { "epoch": 0.429644356085708, "grad_norm": 0.05573304370045662, "learning_rate": 2.546030515952645e-05, "loss": 0.0018, "step": 7780 }, { "epoch": 0.42969958029600175, "grad_norm": 1.014270305633545, "learning_rate": 2.545686366635108e-05, "loss": 0.0408, "step": 7781 }, { "epoch": 0.42975480450629555, "grad_norm": 1.053776741027832, "learning_rate": 2.545342199859512e-05, "loss": 0.043, "step": 7782 }, { "epoch": 0.42981002871658935, "grad_norm": 0.20168793201446533, "learning_rate": 2.5449980156368656e-05, "loss": 0.0069, "step": 7783 }, { "epoch": 0.42986525292688316, "grad_norm": 2.176164150238037, "learning_rate": 2.5446538139781814e-05, "loss": 0.1959, "step": 7784 }, { "epoch": 0.42992047713717696, "grad_norm": 3.9517924785614014, "learning_rate": 2.5443095948944712e-05, "loss": 0.6119, "step": 7785 }, { "epoch": 0.4299757013474707, "grad_norm": 1.237082839012146, "learning_rate": 2.5439653583967476e-05, "loss": 0.2237, "step": 7786 }, { "epoch": 0.4300309255577645, "grad_norm": 1.4344799518585205, "learning_rate": 2.5436211044960237e-05, "loss": 0.1273, "step": 7787 }, { "epoch": 0.4300861497680583, "grad_norm": 5.746659278869629, "learning_rate": 2.5432768332033128e-05, "loss": 1.7145, "step": 7788 }, { "epoch": 0.4301413739783521, "grad_norm": 0.4624357521533966, "learning_rate": 2.5429325445296292e-05, "loss": 0.0144, "step": 7789 }, { "epoch": 0.4301965981886459, "grad_norm": 0.11793597042560577, "learning_rate": 2.542588238485988e-05, "loss": 0.0028, "step": 7790 }, { "epoch": 0.4302518223989397, "grad_norm": 1.632826805114746, "learning_rate": 2.542243915083404e-05, "loss": 0.2967, "step": 7791 }, { "epoch": 0.43030704660923347, "grad_norm": 1.3266676664352417, "learning_rate": 2.5418995743328943e-05, "loss": 0.0279, "step": 7792 }, { "epoch": 0.43036227081952727, "grad_norm": 0.0681409016251564, "learning_rate": 2.541555216245474e-05, "loss": 0.0015, "step": 7793 }, { "epoch": 0.4304174950298211, "grad_norm": 0.07265687733888626, "learning_rate": 2.541210840832161e-05, "loss": 0.0024, "step": 7794 }, { "epoch": 0.4304727192401149, "grad_norm": 2.542619228363037, "learning_rate": 2.5408664481039722e-05, "loss": 0.1177, "step": 7795 }, { "epoch": 0.4305279434504087, "grad_norm": 4.434301853179932, "learning_rate": 2.5405220380719256e-05, "loss": 0.3167, "step": 7796 }, { "epoch": 0.4305831676607024, "grad_norm": 4.431769847869873, "learning_rate": 2.5401776107470408e-05, "loss": 0.0432, "step": 7797 }, { "epoch": 0.43063839187099623, "grad_norm": 0.3030114769935608, "learning_rate": 2.539833166140336e-05, "loss": 0.0099, "step": 7798 }, { "epoch": 0.43069361608129003, "grad_norm": 0.055141568183898926, "learning_rate": 2.539488704262831e-05, "loss": 0.0018, "step": 7799 }, { "epoch": 0.43074884029158383, "grad_norm": 0.05138646438717842, "learning_rate": 2.539144225125547e-05, "loss": 0.0015, "step": 7800 }, { "epoch": 0.43080406450187764, "grad_norm": 1.6040579080581665, "learning_rate": 2.538799728739504e-05, "loss": 0.2937, "step": 7801 }, { "epoch": 0.43085928871217144, "grad_norm": 2.0011160373687744, "learning_rate": 2.5384552151157244e-05, "loss": 0.0827, "step": 7802 }, { "epoch": 0.4309145129224652, "grad_norm": 1.4737377166748047, "learning_rate": 2.5381106842652292e-05, "loss": 0.1736, "step": 7803 }, { "epoch": 0.430969737132759, "grad_norm": 0.25701531767845154, "learning_rate": 2.5377661361990412e-05, "loss": 0.0112, "step": 7804 }, { "epoch": 0.4310249613430528, "grad_norm": 0.2880665957927704, "learning_rate": 2.537421570928184e-05, "loss": 0.0105, "step": 7805 }, { "epoch": 0.4310801855533466, "grad_norm": 0.35799893736839294, "learning_rate": 2.5370769884636802e-05, "loss": 0.0059, "step": 7806 }, { "epoch": 0.4311354097636404, "grad_norm": 2.7163572311401367, "learning_rate": 2.5367323888165548e-05, "loss": 0.1437, "step": 7807 }, { "epoch": 0.43119063397393415, "grad_norm": 1.1694163084030151, "learning_rate": 2.5363877719978324e-05, "loss": 0.031, "step": 7808 }, { "epoch": 0.43124585818422795, "grad_norm": 0.7284435629844666, "learning_rate": 2.5360431380185375e-05, "loss": 0.0163, "step": 7809 }, { "epoch": 0.43130108239452175, "grad_norm": 0.3257090151309967, "learning_rate": 2.5356984868896973e-05, "loss": 0.0121, "step": 7810 }, { "epoch": 0.43135630660481555, "grad_norm": 0.2378797084093094, "learning_rate": 2.5353538186223373e-05, "loss": 0.0096, "step": 7811 }, { "epoch": 0.43141153081510936, "grad_norm": 0.010905970819294453, "learning_rate": 2.5350091332274845e-05, "loss": 0.0005, "step": 7812 }, { "epoch": 0.43146675502540316, "grad_norm": 2.7917075157165527, "learning_rate": 2.5346644307161664e-05, "loss": 0.5214, "step": 7813 }, { "epoch": 0.4315219792356969, "grad_norm": 0.01391569059342146, "learning_rate": 2.5343197110994106e-05, "loss": 0.0005, "step": 7814 }, { "epoch": 0.4315772034459907, "grad_norm": 0.06137220934033394, "learning_rate": 2.533974974388247e-05, "loss": 0.0018, "step": 7815 }, { "epoch": 0.4316324276562845, "grad_norm": 4.379286289215088, "learning_rate": 2.5336302205937032e-05, "loss": 0.3945, "step": 7816 }, { "epoch": 0.4316876518665783, "grad_norm": 3.0721209049224854, "learning_rate": 2.533285449726809e-05, "loss": 0.2325, "step": 7817 }, { "epoch": 0.4317428760768721, "grad_norm": 0.028319980949163437, "learning_rate": 2.532940661798596e-05, "loss": 0.0011, "step": 7818 }, { "epoch": 0.4317981002871659, "grad_norm": 1.6917173862457275, "learning_rate": 2.532595856820094e-05, "loss": 0.0922, "step": 7819 }, { "epoch": 0.43185332449745967, "grad_norm": 2.820613145828247, "learning_rate": 2.532251034802334e-05, "loss": 0.1823, "step": 7820 }, { "epoch": 0.43190854870775347, "grad_norm": 2.4834537506103516, "learning_rate": 2.531906195756348e-05, "loss": 0.2434, "step": 7821 }, { "epoch": 0.4319637729180473, "grad_norm": 2.927701950073242, "learning_rate": 2.5315613396931685e-05, "loss": 0.4218, "step": 7822 }, { "epoch": 0.4320189971283411, "grad_norm": 0.18087947368621826, "learning_rate": 2.5312164666238287e-05, "loss": 0.0038, "step": 7823 }, { "epoch": 0.4320742213386349, "grad_norm": 0.5088608860969543, "learning_rate": 2.5308715765593618e-05, "loss": 0.0137, "step": 7824 }, { "epoch": 0.4321294455489286, "grad_norm": 3.100513458251953, "learning_rate": 2.5305266695108017e-05, "loss": 0.42, "step": 7825 }, { "epoch": 0.43218466975922243, "grad_norm": 2.6239125728607178, "learning_rate": 2.5301817454891833e-05, "loss": 0.1178, "step": 7826 }, { "epoch": 0.43223989396951623, "grad_norm": 0.020995022729039192, "learning_rate": 2.5298368045055415e-05, "loss": 0.0008, "step": 7827 }, { "epoch": 0.43229511817981003, "grad_norm": 0.05364334583282471, "learning_rate": 2.5294918465709116e-05, "loss": 0.002, "step": 7828 }, { "epoch": 0.43235034239010384, "grad_norm": 5.491672039031982, "learning_rate": 2.5291468716963302e-05, "loss": 1.0717, "step": 7829 }, { "epoch": 0.43240556660039764, "grad_norm": 1.6941660642623901, "learning_rate": 2.528801879892834e-05, "loss": 0.3983, "step": 7830 }, { "epoch": 0.4324607908106914, "grad_norm": 6.209287643432617, "learning_rate": 2.5284568711714607e-05, "loss": 1.2788, "step": 7831 }, { "epoch": 0.4325160150209852, "grad_norm": 5.434152603149414, "learning_rate": 2.5281118455432472e-05, "loss": 0.0859, "step": 7832 }, { "epoch": 0.432571239231279, "grad_norm": 0.3097369372844696, "learning_rate": 2.5277668030192323e-05, "loss": 0.0054, "step": 7833 }, { "epoch": 0.4326264634415728, "grad_norm": 0.05181356891989708, "learning_rate": 2.527421743610455e-05, "loss": 0.0019, "step": 7834 }, { "epoch": 0.4326816876518666, "grad_norm": 0.0825083777308464, "learning_rate": 2.527076667327955e-05, "loss": 0.0026, "step": 7835 }, { "epoch": 0.43273691186216034, "grad_norm": 0.014039813540875912, "learning_rate": 2.526731574182771e-05, "loss": 0.0004, "step": 7836 }, { "epoch": 0.43279213607245415, "grad_norm": 3.7216174602508545, "learning_rate": 2.5263864641859452e-05, "loss": 0.3871, "step": 7837 }, { "epoch": 0.43284736028274795, "grad_norm": 0.4869247376918793, "learning_rate": 2.526041337348517e-05, "loss": 0.0177, "step": 7838 }, { "epoch": 0.43290258449304175, "grad_norm": 20.017257690429688, "learning_rate": 2.5256961936815298e-05, "loss": 0.4636, "step": 7839 }, { "epoch": 0.43295780870333556, "grad_norm": 1.9456924200057983, "learning_rate": 2.5253510331960244e-05, "loss": 0.0893, "step": 7840 }, { "epoch": 0.43301303291362936, "grad_norm": 2.2656209468841553, "learning_rate": 2.5250058559030435e-05, "loss": 0.3341, "step": 7841 }, { "epoch": 0.4330682571239231, "grad_norm": 3.9809746742248535, "learning_rate": 2.524660661813631e-05, "loss": 0.1793, "step": 7842 }, { "epoch": 0.4331234813342169, "grad_norm": 0.27852582931518555, "learning_rate": 2.52431545093883e-05, "loss": 0.0084, "step": 7843 }, { "epoch": 0.4331787055445107, "grad_norm": 4.714850902557373, "learning_rate": 2.5239702232896856e-05, "loss": 0.5491, "step": 7844 }, { "epoch": 0.4332339297548045, "grad_norm": 0.6998686790466309, "learning_rate": 2.523624978877242e-05, "loss": 0.025, "step": 7845 }, { "epoch": 0.4332891539650983, "grad_norm": 0.032006848603487015, "learning_rate": 2.523279717712544e-05, "loss": 0.0013, "step": 7846 }, { "epoch": 0.43334437817539206, "grad_norm": 0.28458139300346375, "learning_rate": 2.5229344398066386e-05, "loss": 0.0063, "step": 7847 }, { "epoch": 0.43339960238568587, "grad_norm": 4.1768412590026855, "learning_rate": 2.5225891451705717e-05, "loss": 0.5314, "step": 7848 }, { "epoch": 0.43345482659597967, "grad_norm": 1.0251988172531128, "learning_rate": 2.5222438338153904e-05, "loss": 0.0109, "step": 7849 }, { "epoch": 0.4335100508062735, "grad_norm": 0.7200499176979065, "learning_rate": 2.521898505752142e-05, "loss": 0.0221, "step": 7850 }, { "epoch": 0.4335652750165673, "grad_norm": 2.482930898666382, "learning_rate": 2.5215531609918743e-05, "loss": 0.2815, "step": 7851 }, { "epoch": 0.4336204992268611, "grad_norm": 0.06457884609699249, "learning_rate": 2.5212077995456365e-05, "loss": 0.002, "step": 7852 }, { "epoch": 0.4336757234371548, "grad_norm": 2.996352434158325, "learning_rate": 2.5208624214244773e-05, "loss": 0.1727, "step": 7853 }, { "epoch": 0.43373094764744863, "grad_norm": 0.05845823511481285, "learning_rate": 2.520517026639447e-05, "loss": 0.0022, "step": 7854 }, { "epoch": 0.43378617185774243, "grad_norm": 2.6990480422973633, "learning_rate": 2.5201716152015946e-05, "loss": 0.1944, "step": 7855 }, { "epoch": 0.43384139606803623, "grad_norm": 1.5273183584213257, "learning_rate": 2.519826187121971e-05, "loss": 0.2503, "step": 7856 }, { "epoch": 0.43389662027833004, "grad_norm": 3.832155227661133, "learning_rate": 2.5194807424116285e-05, "loss": 0.6964, "step": 7857 }, { "epoch": 0.43395184448862384, "grad_norm": 2.651669979095459, "learning_rate": 2.519135281081618e-05, "loss": 0.1924, "step": 7858 }, { "epoch": 0.4340070686989176, "grad_norm": 1.6509051322937012, "learning_rate": 2.5187898031429914e-05, "loss": 0.0725, "step": 7859 }, { "epoch": 0.4340622929092114, "grad_norm": 1.1425901651382446, "learning_rate": 2.5184443086068027e-05, "loss": 0.0284, "step": 7860 }, { "epoch": 0.4341175171195052, "grad_norm": 0.6809940338134766, "learning_rate": 2.518098797484104e-05, "loss": 0.0198, "step": 7861 }, { "epoch": 0.434172741329799, "grad_norm": 0.09717720001935959, "learning_rate": 2.5177532697859507e-05, "loss": 0.0021, "step": 7862 }, { "epoch": 0.4342279655400928, "grad_norm": 5.650930881500244, "learning_rate": 2.517407725523396e-05, "loss": 0.9017, "step": 7863 }, { "epoch": 0.43428318975038654, "grad_norm": 0.10320932418107986, "learning_rate": 2.5170621647074943e-05, "loss": 0.0034, "step": 7864 }, { "epoch": 0.43433841396068035, "grad_norm": 0.26890724897384644, "learning_rate": 2.516716587349303e-05, "loss": 0.006, "step": 7865 }, { "epoch": 0.43439363817097415, "grad_norm": 0.2583670914173126, "learning_rate": 2.5163709934598765e-05, "loss": 0.0056, "step": 7866 }, { "epoch": 0.43444886238126795, "grad_norm": 0.4232237935066223, "learning_rate": 2.516025383050272e-05, "loss": 0.0131, "step": 7867 }, { "epoch": 0.43450408659156176, "grad_norm": 1.9114643335342407, "learning_rate": 2.5156797561315464e-05, "loss": 0.3073, "step": 7868 }, { "epoch": 0.43455931080185556, "grad_norm": 4.665897369384766, "learning_rate": 2.5153341127147574e-05, "loss": 0.499, "step": 7869 }, { "epoch": 0.4346145350121493, "grad_norm": 0.08919894695281982, "learning_rate": 2.514988452810963e-05, "loss": 0.0021, "step": 7870 }, { "epoch": 0.4346697592224431, "grad_norm": 6.547636032104492, "learning_rate": 2.514642776431222e-05, "loss": 0.9127, "step": 7871 }, { "epoch": 0.4347249834327369, "grad_norm": 4.880848407745361, "learning_rate": 2.5142970835865933e-05, "loss": 1.1992, "step": 7872 }, { "epoch": 0.4347802076430307, "grad_norm": 1.2674046754837036, "learning_rate": 2.513951374288137e-05, "loss": 0.3759, "step": 7873 }, { "epoch": 0.4348354318533245, "grad_norm": 0.6413964033126831, "learning_rate": 2.5136056485469125e-05, "loss": 0.1051, "step": 7874 }, { "epoch": 0.43489065606361826, "grad_norm": 2.5679521560668945, "learning_rate": 2.513259906373982e-05, "loss": 0.1375, "step": 7875 }, { "epoch": 0.43494588027391207, "grad_norm": 2.2799665927886963, "learning_rate": 2.5129141477804054e-05, "loss": 0.1369, "step": 7876 }, { "epoch": 0.43500110448420587, "grad_norm": 0.3126833736896515, "learning_rate": 2.512568372777245e-05, "loss": 0.0094, "step": 7877 }, { "epoch": 0.43505632869449967, "grad_norm": 0.5782492160797119, "learning_rate": 2.5122225813755635e-05, "loss": 0.0163, "step": 7878 }, { "epoch": 0.4351115529047935, "grad_norm": 2.399568557739258, "learning_rate": 2.511876773586423e-05, "loss": 0.3267, "step": 7879 }, { "epoch": 0.4351667771150873, "grad_norm": 0.4515897035598755, "learning_rate": 2.511530949420887e-05, "loss": 0.012, "step": 7880 }, { "epoch": 0.435222001325381, "grad_norm": 0.020700709894299507, "learning_rate": 2.5111851088900203e-05, "loss": 0.0009, "step": 7881 }, { "epoch": 0.4352772255356748, "grad_norm": 0.29867807030677795, "learning_rate": 2.5108392520048864e-05, "loss": 0.0101, "step": 7882 }, { "epoch": 0.43533244974596863, "grad_norm": 2.0163469314575195, "learning_rate": 2.51049337877655e-05, "loss": 0.604, "step": 7883 }, { "epoch": 0.43538767395626243, "grad_norm": 4.895586013793945, "learning_rate": 2.5101474892160785e-05, "loss": 1.0246, "step": 7884 }, { "epoch": 0.43544289816655624, "grad_norm": 0.19892235100269318, "learning_rate": 2.509801583334535e-05, "loss": 0.0038, "step": 7885 }, { "epoch": 0.43549812237685004, "grad_norm": 0.21941369771957397, "learning_rate": 2.5094556611429884e-05, "loss": 0.0056, "step": 7886 }, { "epoch": 0.4355533465871438, "grad_norm": 1.973567008972168, "learning_rate": 2.5091097226525046e-05, "loss": 0.1194, "step": 7887 }, { "epoch": 0.4356085707974376, "grad_norm": 0.167327418923378, "learning_rate": 2.5087637678741512e-05, "loss": 0.0081, "step": 7888 }, { "epoch": 0.4356637950077314, "grad_norm": 2.7072372436523438, "learning_rate": 2.508417796818997e-05, "loss": 0.3762, "step": 7889 }, { "epoch": 0.4357190192180252, "grad_norm": 0.05749472975730896, "learning_rate": 2.5080718094981092e-05, "loss": 0.0025, "step": 7890 }, { "epoch": 0.435774243428319, "grad_norm": 0.5250149369239807, "learning_rate": 2.507725805922559e-05, "loss": 0.0164, "step": 7891 }, { "epoch": 0.43582946763861274, "grad_norm": 0.05699047073721886, "learning_rate": 2.507379786103414e-05, "loss": 0.0017, "step": 7892 }, { "epoch": 0.43588469184890655, "grad_norm": 0.7823976278305054, "learning_rate": 2.507033750051745e-05, "loss": 0.0254, "step": 7893 }, { "epoch": 0.43593991605920035, "grad_norm": 2.921975612640381, "learning_rate": 2.506687697778624e-05, "loss": 0.1859, "step": 7894 }, { "epoch": 0.43599514026949415, "grad_norm": 3.158432960510254, "learning_rate": 2.5063416292951202e-05, "loss": 0.7631, "step": 7895 }, { "epoch": 0.43605036447978796, "grad_norm": 0.7684038877487183, "learning_rate": 2.5059955446123062e-05, "loss": 0.015, "step": 7896 }, { "epoch": 0.43610558869008176, "grad_norm": 1.0234277248382568, "learning_rate": 2.505649443741254e-05, "loss": 0.036, "step": 7897 }, { "epoch": 0.4361608129003755, "grad_norm": 0.8559738993644714, "learning_rate": 2.5053033266930367e-05, "loss": 0.0279, "step": 7898 }, { "epoch": 0.4362160371106693, "grad_norm": 4.511030197143555, "learning_rate": 2.504957193478728e-05, "loss": 0.2806, "step": 7899 }, { "epoch": 0.4362712613209631, "grad_norm": 0.9334914684295654, "learning_rate": 2.5046110441094008e-05, "loss": 0.0291, "step": 7900 }, { "epoch": 0.4363264855312569, "grad_norm": 0.1600681096315384, "learning_rate": 2.50426487859613e-05, "loss": 0.0056, "step": 7901 }, { "epoch": 0.4363817097415507, "grad_norm": 2.614384651184082, "learning_rate": 2.50391869694999e-05, "loss": 0.2464, "step": 7902 }, { "epoch": 0.43643693395184446, "grad_norm": 2.271775245666504, "learning_rate": 2.5035724991820555e-05, "loss": 0.0422, "step": 7903 }, { "epoch": 0.43649215816213827, "grad_norm": 2.9872095584869385, "learning_rate": 2.503226285303404e-05, "loss": 0.2515, "step": 7904 }, { "epoch": 0.43654738237243207, "grad_norm": 0.8925533890724182, "learning_rate": 2.5028800553251113e-05, "loss": 0.0561, "step": 7905 }, { "epoch": 0.43660260658272587, "grad_norm": 0.0722377747297287, "learning_rate": 2.502533809258253e-05, "loss": 0.0015, "step": 7906 }, { "epoch": 0.4366578307930197, "grad_norm": 0.06815104186534882, "learning_rate": 2.5021875471139082e-05, "loss": 0.0027, "step": 7907 }, { "epoch": 0.4367130550033135, "grad_norm": 0.0618768185377121, "learning_rate": 2.5018412689031538e-05, "loss": 0.0023, "step": 7908 }, { "epoch": 0.4367682792136072, "grad_norm": 1.5948430299758911, "learning_rate": 2.501494974637069e-05, "loss": 0.1409, "step": 7909 }, { "epoch": 0.436823503423901, "grad_norm": 3.829393148422241, "learning_rate": 2.5011486643267318e-05, "loss": 1.2259, "step": 7910 }, { "epoch": 0.43687872763419483, "grad_norm": 3.680163621902466, "learning_rate": 2.500802337983222e-05, "loss": 0.9916, "step": 7911 }, { "epoch": 0.43693395184448863, "grad_norm": 0.3931681215763092, "learning_rate": 2.50045599561762e-05, "loss": 0.0076, "step": 7912 }, { "epoch": 0.43698917605478244, "grad_norm": 5.425074577331543, "learning_rate": 2.5001096372410062e-05, "loss": 0.7765, "step": 7913 }, { "epoch": 0.4370444002650762, "grad_norm": 1.1690064668655396, "learning_rate": 2.499763262864461e-05, "loss": 0.0388, "step": 7914 }, { "epoch": 0.43709962447537, "grad_norm": 7.089419364929199, "learning_rate": 2.4994168724990666e-05, "loss": 0.7848, "step": 7915 }, { "epoch": 0.4371548486856638, "grad_norm": 2.4309487342834473, "learning_rate": 2.499070466155904e-05, "loss": 0.7122, "step": 7916 }, { "epoch": 0.4372100728959576, "grad_norm": 0.04735977202653885, "learning_rate": 2.498724043846057e-05, "loss": 0.0006, "step": 7917 }, { "epoch": 0.4372652971062514, "grad_norm": 0.7599666714668274, "learning_rate": 2.4983776055806082e-05, "loss": 0.0325, "step": 7918 }, { "epoch": 0.4373205213165452, "grad_norm": 0.13622550666332245, "learning_rate": 2.4980311513706403e-05, "loss": 0.0028, "step": 7919 }, { "epoch": 0.43737574552683894, "grad_norm": 2.46871280670166, "learning_rate": 2.4976846812272382e-05, "loss": 0.3444, "step": 7920 }, { "epoch": 0.43743096973713275, "grad_norm": 0.02110874466598034, "learning_rate": 2.4973381951614864e-05, "loss": 0.0007, "step": 7921 }, { "epoch": 0.43748619394742655, "grad_norm": 0.10598194599151611, "learning_rate": 2.49699169318447e-05, "loss": 0.0019, "step": 7922 }, { "epoch": 0.43754141815772035, "grad_norm": 4.095739364624023, "learning_rate": 2.4966451753072746e-05, "loss": 0.4037, "step": 7923 }, { "epoch": 0.43759664236801415, "grad_norm": 1.8295599222183228, "learning_rate": 2.4962986415409853e-05, "loss": 0.1539, "step": 7924 }, { "epoch": 0.43765186657830796, "grad_norm": 0.6505230665206909, "learning_rate": 2.4959520918966904e-05, "loss": 0.0193, "step": 7925 }, { "epoch": 0.4377070907886017, "grad_norm": 0.8883220553398132, "learning_rate": 2.495605526385476e-05, "loss": 0.0129, "step": 7926 }, { "epoch": 0.4377623149988955, "grad_norm": 4.336354732513428, "learning_rate": 2.49525894501843e-05, "loss": 0.6181, "step": 7927 }, { "epoch": 0.4378175392091893, "grad_norm": 5.45689582824707, "learning_rate": 2.4949123478066403e-05, "loss": 1.4624, "step": 7928 }, { "epoch": 0.4378727634194831, "grad_norm": 5.18123722076416, "learning_rate": 2.4945657347611954e-05, "loss": 0.4458, "step": 7929 }, { "epoch": 0.4379279876297769, "grad_norm": 2.834596872329712, "learning_rate": 2.4942191058931848e-05, "loss": 0.3406, "step": 7930 }, { "epoch": 0.43798321184007066, "grad_norm": 0.006434106267988682, "learning_rate": 2.4938724612136984e-05, "loss": 0.0002, "step": 7931 }, { "epoch": 0.43803843605036447, "grad_norm": 3.8129642009735107, "learning_rate": 2.4935258007338253e-05, "loss": 0.8179, "step": 7932 }, { "epoch": 0.43809366026065827, "grad_norm": 0.03403067588806152, "learning_rate": 2.4931791244646574e-05, "loss": 0.0011, "step": 7933 }, { "epoch": 0.43814888447095207, "grad_norm": 2.753347635269165, "learning_rate": 2.4928324324172854e-05, "loss": 0.8806, "step": 7934 }, { "epoch": 0.4382041086812459, "grad_norm": 0.12405695766210556, "learning_rate": 2.4924857246028e-05, "loss": 0.0048, "step": 7935 }, { "epoch": 0.4382593328915397, "grad_norm": 4.0150322914123535, "learning_rate": 2.492139001032295e-05, "loss": 0.8416, "step": 7936 }, { "epoch": 0.4383145571018334, "grad_norm": 1.4678868055343628, "learning_rate": 2.491792261716862e-05, "loss": 0.0651, "step": 7937 }, { "epoch": 0.4383697813121272, "grad_norm": 1.4310845136642456, "learning_rate": 2.4914455066675944e-05, "loss": 0.1511, "step": 7938 }, { "epoch": 0.43842500552242103, "grad_norm": 0.17948248982429504, "learning_rate": 2.4910987358955863e-05, "loss": 0.0055, "step": 7939 }, { "epoch": 0.43848022973271483, "grad_norm": 4.502809047698975, "learning_rate": 2.490751949411931e-05, "loss": 1.2441, "step": 7940 }, { "epoch": 0.43853545394300864, "grad_norm": 3.575218439102173, "learning_rate": 2.4904051472277243e-05, "loss": 0.8845, "step": 7941 }, { "epoch": 0.4385906781533024, "grad_norm": 0.046508822590112686, "learning_rate": 2.49005832935406e-05, "loss": 0.0008, "step": 7942 }, { "epoch": 0.4386459023635962, "grad_norm": 4.6008806228637695, "learning_rate": 2.489711495802036e-05, "loss": 0.2463, "step": 7943 }, { "epoch": 0.43870112657389, "grad_norm": 5.717164993286133, "learning_rate": 2.4893646465827457e-05, "loss": 0.7733, "step": 7944 }, { "epoch": 0.4387563507841838, "grad_norm": 4.501709938049316, "learning_rate": 2.4890177817072882e-05, "loss": 1.2317, "step": 7945 }, { "epoch": 0.4388115749944776, "grad_norm": 9.074830055236816, "learning_rate": 2.488670901186759e-05, "loss": 0.8404, "step": 7946 }, { "epoch": 0.4388667992047714, "grad_norm": 4.5373029708862305, "learning_rate": 2.488324005032257e-05, "loss": 0.813, "step": 7947 }, { "epoch": 0.43892202341506514, "grad_norm": 2.956700086593628, "learning_rate": 2.4879770932548794e-05, "loss": 0.27, "step": 7948 }, { "epoch": 0.43897724762535895, "grad_norm": 1.0256388187408447, "learning_rate": 2.487630165865726e-05, "loss": 0.0284, "step": 7949 }, { "epoch": 0.43903247183565275, "grad_norm": 2.9108853340148926, "learning_rate": 2.4872832228758945e-05, "loss": 0.7483, "step": 7950 }, { "epoch": 0.43908769604594655, "grad_norm": 7.3185930252075195, "learning_rate": 2.4869362642964864e-05, "loss": 0.9472, "step": 7951 }, { "epoch": 0.43914292025624035, "grad_norm": 1.8652046918869019, "learning_rate": 2.4865892901386005e-05, "loss": 0.0886, "step": 7952 }, { "epoch": 0.4391981444665341, "grad_norm": 0.025723475962877274, "learning_rate": 2.486242300413338e-05, "loss": 0.001, "step": 7953 }, { "epoch": 0.4392533686768279, "grad_norm": 6.489170551300049, "learning_rate": 2.4858952951318e-05, "loss": 0.4147, "step": 7954 }, { "epoch": 0.4393085928871217, "grad_norm": 0.05900466814637184, "learning_rate": 2.485548274305088e-05, "loss": 0.0021, "step": 7955 }, { "epoch": 0.4393638170974155, "grad_norm": 0.08240843564271927, "learning_rate": 2.4852012379443043e-05, "loss": 0.0034, "step": 7956 }, { "epoch": 0.4394190413077093, "grad_norm": 2.9399619102478027, "learning_rate": 2.4848541860605525e-05, "loss": 0.6759, "step": 7957 }, { "epoch": 0.4394742655180031, "grad_norm": 0.15499453246593475, "learning_rate": 2.4845071186649342e-05, "loss": 0.0033, "step": 7958 }, { "epoch": 0.43952948972829686, "grad_norm": 1.9570647478103638, "learning_rate": 2.4841600357685547e-05, "loss": 0.0698, "step": 7959 }, { "epoch": 0.43958471393859067, "grad_norm": 0.4415282607078552, "learning_rate": 2.4838129373825165e-05, "loss": 0.009, "step": 7960 }, { "epoch": 0.43963993814888447, "grad_norm": 1.7066912651062012, "learning_rate": 2.4834658235179253e-05, "loss": 0.3955, "step": 7961 }, { "epoch": 0.43969516235917827, "grad_norm": 0.561405599117279, "learning_rate": 2.483118694185886e-05, "loss": 0.0205, "step": 7962 }, { "epoch": 0.4397503865694721, "grad_norm": 3.6062493324279785, "learning_rate": 2.4827715493975043e-05, "loss": 1.2435, "step": 7963 }, { "epoch": 0.4398056107797659, "grad_norm": 2.414111852645874, "learning_rate": 2.4824243891638867e-05, "loss": 0.3971, "step": 7964 }, { "epoch": 0.4398608349900596, "grad_norm": 1.4268102645874023, "learning_rate": 2.4820772134961396e-05, "loss": 0.0591, "step": 7965 }, { "epoch": 0.4399160592003534, "grad_norm": 4.131947994232178, "learning_rate": 2.481730022405369e-05, "loss": 0.7379, "step": 7966 }, { "epoch": 0.43997128341064723, "grad_norm": 1.119071364402771, "learning_rate": 2.4813828159026844e-05, "loss": 0.0271, "step": 7967 }, { "epoch": 0.44002650762094103, "grad_norm": 0.12219301611185074, "learning_rate": 2.481035593999193e-05, "loss": 0.0035, "step": 7968 }, { "epoch": 0.44008173183123483, "grad_norm": 1.815801739692688, "learning_rate": 2.4806883567060035e-05, "loss": 0.2708, "step": 7969 }, { "epoch": 0.4401369560415286, "grad_norm": 2.795607805252075, "learning_rate": 2.4803411040342245e-05, "loss": 0.6218, "step": 7970 }, { "epoch": 0.4401921802518224, "grad_norm": 0.11135455220937729, "learning_rate": 2.4799938359949667e-05, "loss": 0.0047, "step": 7971 }, { "epoch": 0.4402474044621162, "grad_norm": 0.07487630099058151, "learning_rate": 2.4796465525993396e-05, "loss": 0.0028, "step": 7972 }, { "epoch": 0.44030262867241, "grad_norm": 3.050008535385132, "learning_rate": 2.4792992538584537e-05, "loss": 0.8732, "step": 7973 }, { "epoch": 0.4403578528827038, "grad_norm": 1.9698781967163086, "learning_rate": 2.47895193978342e-05, "loss": 0.0717, "step": 7974 }, { "epoch": 0.4404130770929976, "grad_norm": 1.4861339330673218, "learning_rate": 2.4786046103853506e-05, "loss": 0.0646, "step": 7975 }, { "epoch": 0.44046830130329134, "grad_norm": 0.30240026116371155, "learning_rate": 2.4782572656753568e-05, "loss": 0.0045, "step": 7976 }, { "epoch": 0.44052352551358515, "grad_norm": 2.8875904083251953, "learning_rate": 2.4779099056645513e-05, "loss": 0.1833, "step": 7977 }, { "epoch": 0.44057874972387895, "grad_norm": 0.07047171890735626, "learning_rate": 2.4775625303640484e-05, "loss": 0.0034, "step": 7978 }, { "epoch": 0.44063397393417275, "grad_norm": 1.1341252326965332, "learning_rate": 2.4772151397849592e-05, "loss": 0.0439, "step": 7979 }, { "epoch": 0.44068919814446655, "grad_norm": 0.5414832830429077, "learning_rate": 2.4768677339384e-05, "loss": 0.0176, "step": 7980 }, { "epoch": 0.4407444223547603, "grad_norm": 0.13754543662071228, "learning_rate": 2.476520312835484e-05, "loss": 0.0031, "step": 7981 }, { "epoch": 0.4407996465650541, "grad_norm": 0.18131496012210846, "learning_rate": 2.476172876487327e-05, "loss": 0.005, "step": 7982 }, { "epoch": 0.4408548707753479, "grad_norm": 0.03759997710585594, "learning_rate": 2.4758254249050442e-05, "loss": 0.0016, "step": 7983 }, { "epoch": 0.4409100949856417, "grad_norm": 6.039334774017334, "learning_rate": 2.4754779580997505e-05, "loss": 1.6054, "step": 7984 }, { "epoch": 0.4409653191959355, "grad_norm": 0.7815042734146118, "learning_rate": 2.4751304760825643e-05, "loss": 0.0223, "step": 7985 }, { "epoch": 0.4410205434062293, "grad_norm": 0.24299359321594238, "learning_rate": 2.4747829788646014e-05, "loss": 0.0067, "step": 7986 }, { "epoch": 0.44107576761652306, "grad_norm": 2.102773904800415, "learning_rate": 2.4744354664569786e-05, "loss": 0.4573, "step": 7987 }, { "epoch": 0.44113099182681687, "grad_norm": 0.10807959735393524, "learning_rate": 2.474087938870815e-05, "loss": 0.0039, "step": 7988 }, { "epoch": 0.44118621603711067, "grad_norm": 1.4345430135726929, "learning_rate": 2.4737403961172283e-05, "loss": 0.0299, "step": 7989 }, { "epoch": 0.44124144024740447, "grad_norm": 0.03041330724954605, "learning_rate": 2.4733928382073385e-05, "loss": 0.0013, "step": 7990 }, { "epoch": 0.4412966644576983, "grad_norm": 3.6574065685272217, "learning_rate": 2.4730452651522637e-05, "loss": 1.122, "step": 7991 }, { "epoch": 0.441351888667992, "grad_norm": 0.0573822557926178, "learning_rate": 2.4726976769631236e-05, "loss": 0.0018, "step": 7992 }, { "epoch": 0.4414071128782858, "grad_norm": 1.2700427770614624, "learning_rate": 2.47235007365104e-05, "loss": 0.0727, "step": 7993 }, { "epoch": 0.4414623370885796, "grad_norm": 4.230546951293945, "learning_rate": 2.4720024552271326e-05, "loss": 0.6196, "step": 7994 }, { "epoch": 0.44151756129887343, "grad_norm": 4.431208610534668, "learning_rate": 2.4716548217025224e-05, "loss": 1.1791, "step": 7995 }, { "epoch": 0.44157278550916723, "grad_norm": 0.8845793604850769, "learning_rate": 2.4713071730883324e-05, "loss": 0.0267, "step": 7996 }, { "epoch": 0.44162800971946103, "grad_norm": 0.06598487496376038, "learning_rate": 2.4709595093956833e-05, "loss": 0.0018, "step": 7997 }, { "epoch": 0.4416832339297548, "grad_norm": 3.2397572994232178, "learning_rate": 2.4706118306356994e-05, "loss": 0.9871, "step": 7998 }, { "epoch": 0.4417384581400486, "grad_norm": 1.9913021326065063, "learning_rate": 2.4702641368195032e-05, "loss": 0.3796, "step": 7999 }, { "epoch": 0.4417936823503424, "grad_norm": 2.271191120147705, "learning_rate": 2.4699164279582185e-05, "loss": 0.36, "step": 8000 }, { "epoch": 0.4418489065606362, "grad_norm": 4.5151047706604, "learning_rate": 2.4695687040629693e-05, "loss": 1.0112, "step": 8001 }, { "epoch": 0.44190413077093, "grad_norm": 3.1056370735168457, "learning_rate": 2.4692209651448803e-05, "loss": 0.2593, "step": 8002 }, { "epoch": 0.4419593549812238, "grad_norm": 5.954512596130371, "learning_rate": 2.468873211215077e-05, "loss": 1.5682, "step": 8003 }, { "epoch": 0.44201457919151754, "grad_norm": 0.9174391627311707, "learning_rate": 2.4685254422846853e-05, "loss": 0.151, "step": 8004 }, { "epoch": 0.44206980340181135, "grad_norm": 0.13866522908210754, "learning_rate": 2.4681776583648302e-05, "loss": 0.0054, "step": 8005 }, { "epoch": 0.44212502761210515, "grad_norm": 2.4018633365631104, "learning_rate": 2.4678298594666394e-05, "loss": 0.1131, "step": 8006 }, { "epoch": 0.44218025182239895, "grad_norm": 0.11888314038515091, "learning_rate": 2.4674820456012392e-05, "loss": 0.0028, "step": 8007 }, { "epoch": 0.44223547603269275, "grad_norm": 0.03169425576925278, "learning_rate": 2.4671342167797576e-05, "loss": 0.0011, "step": 8008 }, { "epoch": 0.4422907002429865, "grad_norm": 3.85335373878479, "learning_rate": 2.4667863730133226e-05, "loss": 0.4451, "step": 8009 }, { "epoch": 0.4423459244532803, "grad_norm": 6.7844438552856445, "learning_rate": 2.4664385143130627e-05, "loss": 1.4778, "step": 8010 }, { "epoch": 0.4424011486635741, "grad_norm": 0.634663462638855, "learning_rate": 2.4660906406901068e-05, "loss": 0.025, "step": 8011 }, { "epoch": 0.4424563728738679, "grad_norm": 3.0991268157958984, "learning_rate": 2.4657427521555844e-05, "loss": 0.4612, "step": 8012 }, { "epoch": 0.4425115970841617, "grad_norm": 1.3211137056350708, "learning_rate": 2.4653948487206256e-05, "loss": 0.0595, "step": 8013 }, { "epoch": 0.4425668212944555, "grad_norm": 1.4651145935058594, "learning_rate": 2.4650469303963603e-05, "loss": 0.085, "step": 8014 }, { "epoch": 0.44262204550474926, "grad_norm": 0.016812877729535103, "learning_rate": 2.46469899719392e-05, "loss": 0.0007, "step": 8015 }, { "epoch": 0.44267726971504306, "grad_norm": 0.11608952283859253, "learning_rate": 2.4643510491244357e-05, "loss": 0.0048, "step": 8016 }, { "epoch": 0.44273249392533687, "grad_norm": 0.07889848947525024, "learning_rate": 2.4640030861990397e-05, "loss": 0.0019, "step": 8017 }, { "epoch": 0.44278771813563067, "grad_norm": 0.06013962998986244, "learning_rate": 2.4636551084288635e-05, "loss": 0.0016, "step": 8018 }, { "epoch": 0.4428429423459245, "grad_norm": 1.272717833518982, "learning_rate": 2.4633071158250407e-05, "loss": 0.0145, "step": 8019 }, { "epoch": 0.4428981665562182, "grad_norm": 0.13406658172607422, "learning_rate": 2.4629591083987045e-05, "loss": 0.0043, "step": 8020 }, { "epoch": 0.442953390766512, "grad_norm": 0.06365277618169785, "learning_rate": 2.462611086160988e-05, "loss": 0.0018, "step": 8021 }, { "epoch": 0.4430086149768058, "grad_norm": 0.18579676747322083, "learning_rate": 2.4622630491230265e-05, "loss": 0.004, "step": 8022 }, { "epoch": 0.44306383918709963, "grad_norm": 1.8062140941619873, "learning_rate": 2.4619149972959533e-05, "loss": 0.0934, "step": 8023 }, { "epoch": 0.44311906339739343, "grad_norm": 0.2174723744392395, "learning_rate": 2.461566930690905e-05, "loss": 0.0074, "step": 8024 }, { "epoch": 0.44317428760768723, "grad_norm": 2.1572697162628174, "learning_rate": 2.4612188493190163e-05, "loss": 0.4938, "step": 8025 }, { "epoch": 0.443229511817981, "grad_norm": 0.42614510655403137, "learning_rate": 2.460870753191423e-05, "loss": 0.0079, "step": 8026 }, { "epoch": 0.4432847360282748, "grad_norm": 0.05102844163775444, "learning_rate": 2.460522642319263e-05, "loss": 0.0017, "step": 8027 }, { "epoch": 0.4433399602385686, "grad_norm": 2.6331963539123535, "learning_rate": 2.460174516713673e-05, "loss": 0.1217, "step": 8028 }, { "epoch": 0.4433951844488624, "grad_norm": 1.6834473609924316, "learning_rate": 2.459826376385789e-05, "loss": 0.1587, "step": 8029 }, { "epoch": 0.4434504086591562, "grad_norm": 1.8685060739517212, "learning_rate": 2.4594782213467506e-05, "loss": 0.3726, "step": 8030 }, { "epoch": 0.44350563286944994, "grad_norm": 3.9955787658691406, "learning_rate": 2.459130051607696e-05, "loss": 0.9102, "step": 8031 }, { "epoch": 0.44356085707974374, "grad_norm": 0.045411109924316406, "learning_rate": 2.4587818671797637e-05, "loss": 0.0009, "step": 8032 }, { "epoch": 0.44361608129003754, "grad_norm": 0.4258330464363098, "learning_rate": 2.4584336680740938e-05, "loss": 0.0084, "step": 8033 }, { "epoch": 0.44367130550033135, "grad_norm": 0.9726301431655884, "learning_rate": 2.4580854543018258e-05, "loss": 0.032, "step": 8034 }, { "epoch": 0.44372652971062515, "grad_norm": 0.14206892251968384, "learning_rate": 2.4577372258741e-05, "loss": 0.0043, "step": 8035 }, { "epoch": 0.44378175392091895, "grad_norm": 2.6988189220428467, "learning_rate": 2.4573889828020566e-05, "loss": 0.251, "step": 8036 }, { "epoch": 0.4438369781312127, "grad_norm": 0.013491670601069927, "learning_rate": 2.457040725096838e-05, "loss": 0.0006, "step": 8037 }, { "epoch": 0.4438922023415065, "grad_norm": 0.13145112991333008, "learning_rate": 2.4566924527695854e-05, "loss": 0.0049, "step": 8038 }, { "epoch": 0.4439474265518003, "grad_norm": 4.707676887512207, "learning_rate": 2.4563441658314408e-05, "loss": 0.9883, "step": 8039 }, { "epoch": 0.4440026507620941, "grad_norm": 0.14796847105026245, "learning_rate": 2.4559958642935477e-05, "loss": 0.0045, "step": 8040 }, { "epoch": 0.4440578749723879, "grad_norm": 0.04672800749540329, "learning_rate": 2.4556475481670482e-05, "loss": 0.0021, "step": 8041 }, { "epoch": 0.4441130991826817, "grad_norm": 0.25926631689071655, "learning_rate": 2.455299217463087e-05, "loss": 0.0058, "step": 8042 }, { "epoch": 0.44416832339297546, "grad_norm": 0.8230754733085632, "learning_rate": 2.4549508721928073e-05, "loss": 0.0263, "step": 8043 }, { "epoch": 0.44422354760326926, "grad_norm": 0.09790437668561935, "learning_rate": 2.454602512367354e-05, "loss": 0.0026, "step": 8044 }, { "epoch": 0.44427877181356307, "grad_norm": 0.35341954231262207, "learning_rate": 2.4542541379978726e-05, "loss": 0.0101, "step": 8045 }, { "epoch": 0.44433399602385687, "grad_norm": 0.0330444872379303, "learning_rate": 2.4539057490955078e-05, "loss": 0.0016, "step": 8046 }, { "epoch": 0.4443892202341507, "grad_norm": 1.4128473997116089, "learning_rate": 2.4535573456714055e-05, "loss": 0.0973, "step": 8047 }, { "epoch": 0.4444444444444444, "grad_norm": 0.040175069123506546, "learning_rate": 2.4532089277367127e-05, "loss": 0.0016, "step": 8048 }, { "epoch": 0.4444996686547382, "grad_norm": 0.12130811810493469, "learning_rate": 2.452860495302576e-05, "loss": 0.003, "step": 8049 }, { "epoch": 0.444554892865032, "grad_norm": 2.558281421661377, "learning_rate": 2.4525120483801433e-05, "loss": 0.6439, "step": 8050 }, { "epoch": 0.44461011707532583, "grad_norm": 0.5088147521018982, "learning_rate": 2.452163586980562e-05, "loss": 0.0216, "step": 8051 }, { "epoch": 0.44466534128561963, "grad_norm": 0.04405904561281204, "learning_rate": 2.4518151111149796e-05, "loss": 0.0015, "step": 8052 }, { "epoch": 0.44472056549591343, "grad_norm": 8.850339889526367, "learning_rate": 2.4514666207945458e-05, "loss": 0.322, "step": 8053 }, { "epoch": 0.4447757897062072, "grad_norm": 0.13269810378551483, "learning_rate": 2.4511181160304097e-05, "loss": 0.005, "step": 8054 }, { "epoch": 0.444831013916501, "grad_norm": 0.6540196537971497, "learning_rate": 2.4507695968337205e-05, "loss": 0.0224, "step": 8055 }, { "epoch": 0.4448862381267948, "grad_norm": 2.452655076980591, "learning_rate": 2.450421063215629e-05, "loss": 0.1939, "step": 8056 }, { "epoch": 0.4449414623370886, "grad_norm": 1.1088861227035522, "learning_rate": 2.4500725151872847e-05, "loss": 0.0186, "step": 8057 }, { "epoch": 0.4449966865473824, "grad_norm": 0.09379398077726364, "learning_rate": 2.44972395275984e-05, "loss": 0.0028, "step": 8058 }, { "epoch": 0.44505191075767614, "grad_norm": 2.8605613708496094, "learning_rate": 2.449375375944446e-05, "loss": 0.2103, "step": 8059 }, { "epoch": 0.44510713496796994, "grad_norm": 0.2366000860929489, "learning_rate": 2.4490267847522534e-05, "loss": 0.0046, "step": 8060 }, { "epoch": 0.44516235917826374, "grad_norm": 2.4093310832977295, "learning_rate": 2.4486781791944166e-05, "loss": 0.1393, "step": 8061 }, { "epoch": 0.44521758338855755, "grad_norm": 2.839226722717285, "learning_rate": 2.448329559282087e-05, "loss": 0.6197, "step": 8062 }, { "epoch": 0.44527280759885135, "grad_norm": 1.6253166198730469, "learning_rate": 2.4479809250264185e-05, "loss": 0.2659, "step": 8063 }, { "epoch": 0.44532803180914515, "grad_norm": 3.6042158603668213, "learning_rate": 2.447632276438565e-05, "loss": 0.4258, "step": 8064 }, { "epoch": 0.4453832560194389, "grad_norm": 5.212409973144531, "learning_rate": 2.4472836135296802e-05, "loss": 0.9325, "step": 8065 }, { "epoch": 0.4454384802297327, "grad_norm": 0.5921405553817749, "learning_rate": 2.4469349363109198e-05, "loss": 0.007, "step": 8066 }, { "epoch": 0.4454937044400265, "grad_norm": 0.12215206027030945, "learning_rate": 2.4465862447934385e-05, "loss": 0.0033, "step": 8067 }, { "epoch": 0.4455489286503203, "grad_norm": 0.12420659512281418, "learning_rate": 2.4462375389883915e-05, "loss": 0.003, "step": 8068 }, { "epoch": 0.4456041528606141, "grad_norm": 3.3205406665802, "learning_rate": 2.4458888189069352e-05, "loss": 0.3451, "step": 8069 }, { "epoch": 0.44565937707090786, "grad_norm": 0.043369095772504807, "learning_rate": 2.4455400845602264e-05, "loss": 0.0017, "step": 8070 }, { "epoch": 0.44571460128120166, "grad_norm": 3.034058094024658, "learning_rate": 2.445191335959422e-05, "loss": 0.3157, "step": 8071 }, { "epoch": 0.44576982549149546, "grad_norm": 1.6641901731491089, "learning_rate": 2.444842573115679e-05, "loss": 0.1647, "step": 8072 }, { "epoch": 0.44582504970178927, "grad_norm": 2.920299768447876, "learning_rate": 2.4444937960401556e-05, "loss": 0.4821, "step": 8073 }, { "epoch": 0.44588027391208307, "grad_norm": 1.7237880229949951, "learning_rate": 2.444145004744011e-05, "loss": 0.0342, "step": 8074 }, { "epoch": 0.44593549812237687, "grad_norm": 2.134065866470337, "learning_rate": 2.4437961992384027e-05, "loss": 0.1362, "step": 8075 }, { "epoch": 0.4459907223326706, "grad_norm": 3.329582929611206, "learning_rate": 2.4434473795344907e-05, "loss": 0.5868, "step": 8076 }, { "epoch": 0.4460459465429644, "grad_norm": 2.145712375640869, "learning_rate": 2.4430985456434345e-05, "loss": 0.1605, "step": 8077 }, { "epoch": 0.4461011707532582, "grad_norm": 3.690558910369873, "learning_rate": 2.4427496975763942e-05, "loss": 0.1396, "step": 8078 }, { "epoch": 0.446156394963552, "grad_norm": 1.6395307779312134, "learning_rate": 2.4424008353445308e-05, "loss": 0.0822, "step": 8079 }, { "epoch": 0.44621161917384583, "grad_norm": 0.8357690572738647, "learning_rate": 2.4420519589590056e-05, "loss": 0.0222, "step": 8080 }, { "epoch": 0.44626684338413963, "grad_norm": 3.2939841747283936, "learning_rate": 2.4417030684309792e-05, "loss": 0.2321, "step": 8081 }, { "epoch": 0.4463220675944334, "grad_norm": 2.4517483711242676, "learning_rate": 2.441354163771615e-05, "loss": 0.1934, "step": 8082 }, { "epoch": 0.4463772918047272, "grad_norm": 0.14676214754581451, "learning_rate": 2.441005244992073e-05, "loss": 0.005, "step": 8083 }, { "epoch": 0.446432516015021, "grad_norm": 3.3822531700134277, "learning_rate": 2.440656312103519e-05, "loss": 0.2279, "step": 8084 }, { "epoch": 0.4464877402253148, "grad_norm": 1.466157078742981, "learning_rate": 2.440307365117115e-05, "loss": 0.0847, "step": 8085 }, { "epoch": 0.4465429644356086, "grad_norm": 3.260817527770996, "learning_rate": 2.4399584040440245e-05, "loss": 0.5163, "step": 8086 }, { "epoch": 0.44659818864590234, "grad_norm": 0.32591691613197327, "learning_rate": 2.4396094288954125e-05, "loss": 0.0092, "step": 8087 }, { "epoch": 0.44665341285619614, "grad_norm": 1.4736138582229614, "learning_rate": 2.4392604396824434e-05, "loss": 0.0338, "step": 8088 }, { "epoch": 0.44670863706648994, "grad_norm": 0.2355952113866806, "learning_rate": 2.438911436416282e-05, "loss": 0.0075, "step": 8089 }, { "epoch": 0.44676386127678375, "grad_norm": 2.582700729370117, "learning_rate": 2.4385624191080944e-05, "loss": 0.0845, "step": 8090 }, { "epoch": 0.44681908548707755, "grad_norm": 2.724494457244873, "learning_rate": 2.4382133877690463e-05, "loss": 0.3481, "step": 8091 }, { "epoch": 0.44687430969737135, "grad_norm": 3.5123095512390137, "learning_rate": 2.4378643424103046e-05, "loss": 0.404, "step": 8092 }, { "epoch": 0.4469295339076651, "grad_norm": 1.5302670001983643, "learning_rate": 2.437515283043036e-05, "loss": 0.174, "step": 8093 }, { "epoch": 0.4469847581179589, "grad_norm": 2.3677706718444824, "learning_rate": 2.437166209678408e-05, "loss": 0.4261, "step": 8094 }, { "epoch": 0.4470399823282527, "grad_norm": 0.3313083052635193, "learning_rate": 2.4368171223275888e-05, "loss": 0.0074, "step": 8095 }, { "epoch": 0.4470952065385465, "grad_norm": 0.13914890587329865, "learning_rate": 2.4364680210017455e-05, "loss": 0.0048, "step": 8096 }, { "epoch": 0.4471504307488403, "grad_norm": 0.06874323636293411, "learning_rate": 2.4361189057120476e-05, "loss": 0.0031, "step": 8097 }, { "epoch": 0.44720565495913406, "grad_norm": 3.481372833251953, "learning_rate": 2.4357697764696653e-05, "loss": 0.7751, "step": 8098 }, { "epoch": 0.44726087916942786, "grad_norm": 0.09298454970121384, "learning_rate": 2.4354206332857664e-05, "loss": 0.0029, "step": 8099 }, { "epoch": 0.44731610337972166, "grad_norm": 0.11335590481758118, "learning_rate": 2.435071476171522e-05, "loss": 0.0035, "step": 8100 }, { "epoch": 0.44737132759001547, "grad_norm": 3.020045280456543, "learning_rate": 2.4347223051381025e-05, "loss": 0.5793, "step": 8101 }, { "epoch": 0.44742655180030927, "grad_norm": 5.0913496017456055, "learning_rate": 2.434373120196679e-05, "loss": 1.3001, "step": 8102 }, { "epoch": 0.44748177601060307, "grad_norm": 0.5115641355514526, "learning_rate": 2.4340239213584228e-05, "loss": 0.0126, "step": 8103 }, { "epoch": 0.4475370002208968, "grad_norm": 0.39511778950691223, "learning_rate": 2.4336747086345053e-05, "loss": 0.0149, "step": 8104 }, { "epoch": 0.4475922244311906, "grad_norm": 1.3521454334259033, "learning_rate": 2.4333254820361e-05, "loss": 0.0249, "step": 8105 }, { "epoch": 0.4476474486414844, "grad_norm": 0.1540420651435852, "learning_rate": 2.4329762415743786e-05, "loss": 0.0058, "step": 8106 }, { "epoch": 0.4477026728517782, "grad_norm": 0.34543731808662415, "learning_rate": 2.4326269872605143e-05, "loss": 0.0072, "step": 8107 }, { "epoch": 0.44775789706207203, "grad_norm": 3.286351442337036, "learning_rate": 2.4322777191056813e-05, "loss": 0.4411, "step": 8108 }, { "epoch": 0.44781312127236583, "grad_norm": 1.3825677633285522, "learning_rate": 2.4319284371210535e-05, "loss": 0.0408, "step": 8109 }, { "epoch": 0.4478683454826596, "grad_norm": 2.4689457416534424, "learning_rate": 2.431579141317805e-05, "loss": 0.7173, "step": 8110 }, { "epoch": 0.4479235696929534, "grad_norm": 3.9110283851623535, "learning_rate": 2.4312298317071116e-05, "loss": 1.1237, "step": 8111 }, { "epoch": 0.4479787939032472, "grad_norm": 0.008981128223240376, "learning_rate": 2.4308805083001477e-05, "loss": 0.0004, "step": 8112 }, { "epoch": 0.448034018113541, "grad_norm": 3.3442742824554443, "learning_rate": 2.43053117110809e-05, "loss": 0.4048, "step": 8113 }, { "epoch": 0.4480892423238348, "grad_norm": 3.175943374633789, "learning_rate": 2.4301818201421146e-05, "loss": 0.7849, "step": 8114 }, { "epoch": 0.44814446653412854, "grad_norm": 0.13254407048225403, "learning_rate": 2.4298324554133975e-05, "loss": 0.0043, "step": 8115 }, { "epoch": 0.44819969074442234, "grad_norm": 1.541557788848877, "learning_rate": 2.429483076933117e-05, "loss": 0.1479, "step": 8116 }, { "epoch": 0.44825491495471614, "grad_norm": 1.0768022537231445, "learning_rate": 2.4291336847124502e-05, "loss": 0.0415, "step": 8117 }, { "epoch": 0.44831013916500995, "grad_norm": 0.026491010561585426, "learning_rate": 2.4287842787625752e-05, "loss": 0.001, "step": 8118 }, { "epoch": 0.44836536337530375, "grad_norm": 0.056299589574337006, "learning_rate": 2.4284348590946703e-05, "loss": 0.0017, "step": 8119 }, { "epoch": 0.44842058758559755, "grad_norm": 2.3917763233184814, "learning_rate": 2.4280854257199146e-05, "loss": 1.1292, "step": 8120 }, { "epoch": 0.4484758117958913, "grad_norm": 5.270971298217773, "learning_rate": 2.4277359786494873e-05, "loss": 0.6741, "step": 8121 }, { "epoch": 0.4485310360061851, "grad_norm": 0.6603681445121765, "learning_rate": 2.427386517894568e-05, "loss": 0.035, "step": 8122 }, { "epoch": 0.4485862602164789, "grad_norm": 0.30664077401161194, "learning_rate": 2.4270370434663378e-05, "loss": 0.0108, "step": 8123 }, { "epoch": 0.4486414844267727, "grad_norm": 0.6846586465835571, "learning_rate": 2.4266875553759768e-05, "loss": 0.0217, "step": 8124 }, { "epoch": 0.4486967086370665, "grad_norm": 0.6416123509407043, "learning_rate": 2.426338053634666e-05, "loss": 0.021, "step": 8125 }, { "epoch": 0.44875193284736026, "grad_norm": 0.633963942527771, "learning_rate": 2.425988538253587e-05, "loss": 0.0242, "step": 8126 }, { "epoch": 0.44880715705765406, "grad_norm": 3.575269937515259, "learning_rate": 2.4256390092439226e-05, "loss": 1.0944, "step": 8127 }, { "epoch": 0.44886238126794786, "grad_norm": 0.9398651123046875, "learning_rate": 2.4252894666168536e-05, "loss": 0.0291, "step": 8128 }, { "epoch": 0.44891760547824167, "grad_norm": 0.783957839012146, "learning_rate": 2.4249399103835644e-05, "loss": 0.0552, "step": 8129 }, { "epoch": 0.44897282968853547, "grad_norm": 1.4544960260391235, "learning_rate": 2.4245903405552378e-05, "loss": 0.1918, "step": 8130 }, { "epoch": 0.44902805389882927, "grad_norm": 1.3321157693862915, "learning_rate": 2.424240757143057e-05, "loss": 0.2569, "step": 8131 }, { "epoch": 0.449083278109123, "grad_norm": 0.10876668989658356, "learning_rate": 2.423891160158207e-05, "loss": 0.0031, "step": 8132 }, { "epoch": 0.4491385023194168, "grad_norm": 0.4208223521709442, "learning_rate": 2.423541549611872e-05, "loss": 0.0158, "step": 8133 }, { "epoch": 0.4491937265297106, "grad_norm": 1.3310165405273438, "learning_rate": 2.423191925515237e-05, "loss": 0.0762, "step": 8134 }, { "epoch": 0.4492489507400044, "grad_norm": 0.018493501469492912, "learning_rate": 2.4228422878794877e-05, "loss": 0.0007, "step": 8135 }, { "epoch": 0.44930417495029823, "grad_norm": 0.1566839963197708, "learning_rate": 2.4224926367158093e-05, "loss": 0.0067, "step": 8136 }, { "epoch": 0.449359399160592, "grad_norm": 1.598893165588379, "learning_rate": 2.4221429720353892e-05, "loss": 0.3651, "step": 8137 }, { "epoch": 0.4494146233708858, "grad_norm": 0.11451560258865356, "learning_rate": 2.4217932938494137e-05, "loss": 0.0043, "step": 8138 }, { "epoch": 0.4494698475811796, "grad_norm": 1.4633934497833252, "learning_rate": 2.4214436021690696e-05, "loss": 0.0971, "step": 8139 }, { "epoch": 0.4495250717914734, "grad_norm": 2.4870574474334717, "learning_rate": 2.421093897005545e-05, "loss": 0.5408, "step": 8140 }, { "epoch": 0.4495802960017672, "grad_norm": 6.378811836242676, "learning_rate": 2.4207441783700274e-05, "loss": 0.9, "step": 8141 }, { "epoch": 0.449635520212061, "grad_norm": 0.050282932817935944, "learning_rate": 2.420394446273706e-05, "loss": 0.0012, "step": 8142 }, { "epoch": 0.44969074442235474, "grad_norm": 2.3132519721984863, "learning_rate": 2.4200447007277695e-05, "loss": 0.2476, "step": 8143 }, { "epoch": 0.44974596863264854, "grad_norm": 1.9177706241607666, "learning_rate": 2.419694941743408e-05, "loss": 0.161, "step": 8144 }, { "epoch": 0.44980119284294234, "grad_norm": 2.8519606590270996, "learning_rate": 2.4193451693318094e-05, "loss": 0.423, "step": 8145 }, { "epoch": 0.44985641705323615, "grad_norm": 2.1883647441864014, "learning_rate": 2.4189953835041653e-05, "loss": 0.3118, "step": 8146 }, { "epoch": 0.44991164126352995, "grad_norm": 0.042412541806697845, "learning_rate": 2.418645584271666e-05, "loss": 0.0019, "step": 8147 }, { "epoch": 0.44996686547382375, "grad_norm": 0.04293195903301239, "learning_rate": 2.4182957716455034e-05, "loss": 0.0016, "step": 8148 }, { "epoch": 0.4500220896841175, "grad_norm": 3.166835069656372, "learning_rate": 2.4179459456368673e-05, "loss": 0.0789, "step": 8149 }, { "epoch": 0.4500773138944113, "grad_norm": 4.003032207489014, "learning_rate": 2.4175961062569508e-05, "loss": 0.3865, "step": 8150 }, { "epoch": 0.4501325381047051, "grad_norm": 0.1977241337299347, "learning_rate": 2.417246253516946e-05, "loss": 0.0068, "step": 8151 }, { "epoch": 0.4501877623149989, "grad_norm": 0.0934525579214096, "learning_rate": 2.4168963874280456e-05, "loss": 0.0035, "step": 8152 }, { "epoch": 0.4502429865252927, "grad_norm": 2.17950701713562, "learning_rate": 2.416546508001443e-05, "loss": 0.2413, "step": 8153 }, { "epoch": 0.45029821073558646, "grad_norm": 0.021744953468441963, "learning_rate": 2.4161966152483322e-05, "loss": 0.0008, "step": 8154 }, { "epoch": 0.45035343494588026, "grad_norm": 0.1326465904712677, "learning_rate": 2.4158467091799068e-05, "loss": 0.0034, "step": 8155 }, { "epoch": 0.45040865915617406, "grad_norm": 3.7111384868621826, "learning_rate": 2.4154967898073606e-05, "loss": 1.178, "step": 8156 }, { "epoch": 0.45046388336646787, "grad_norm": 0.027416352182626724, "learning_rate": 2.4151468571418902e-05, "loss": 0.0012, "step": 8157 }, { "epoch": 0.45051910757676167, "grad_norm": 0.1020897850394249, "learning_rate": 2.414796911194689e-05, "loss": 0.0019, "step": 8158 }, { "epoch": 0.45057433178705547, "grad_norm": 3.576523780822754, "learning_rate": 2.414446951976954e-05, "loss": 0.3511, "step": 8159 }, { "epoch": 0.4506295559973492, "grad_norm": 5.6721343994140625, "learning_rate": 2.4140969794998815e-05, "loss": 1.0367, "step": 8160 }, { "epoch": 0.450684780207643, "grad_norm": 1.2476252317428589, "learning_rate": 2.4137469937746675e-05, "loss": 0.0214, "step": 8161 }, { "epoch": 0.4507400044179368, "grad_norm": 0.14046314358711243, "learning_rate": 2.413396994812509e-05, "loss": 0.0028, "step": 8162 }, { "epoch": 0.4507952286282306, "grad_norm": 0.14306645095348358, "learning_rate": 2.413046982624604e-05, "loss": 0.0041, "step": 8163 }, { "epoch": 0.45085045283852443, "grad_norm": 0.04316649213433266, "learning_rate": 2.41269695722215e-05, "loss": 0.002, "step": 8164 }, { "epoch": 0.4509056770488182, "grad_norm": 0.12849941849708557, "learning_rate": 2.4123469186163458e-05, "loss": 0.003, "step": 8165 }, { "epoch": 0.450960901259112, "grad_norm": 2.6491386890411377, "learning_rate": 2.41199686681839e-05, "loss": 0.4373, "step": 8166 }, { "epoch": 0.4510161254694058, "grad_norm": 0.14711642265319824, "learning_rate": 2.4116468018394806e-05, "loss": 0.0046, "step": 8167 }, { "epoch": 0.4510713496796996, "grad_norm": 2.1276767253875732, "learning_rate": 2.4112967236908187e-05, "loss": 0.1781, "step": 8168 }, { "epoch": 0.4511265738899934, "grad_norm": 0.07109279930591583, "learning_rate": 2.4109466323836034e-05, "loss": 0.003, "step": 8169 }, { "epoch": 0.4511817981002872, "grad_norm": 2.8077080249786377, "learning_rate": 2.4105965279290358e-05, "loss": 0.3217, "step": 8170 }, { "epoch": 0.45123702231058094, "grad_norm": 1.8343122005462646, "learning_rate": 2.4102464103383163e-05, "loss": 0.5361, "step": 8171 }, { "epoch": 0.45129224652087474, "grad_norm": 2.135580062866211, "learning_rate": 2.4098962796226458e-05, "loss": 0.1261, "step": 8172 }, { "epoch": 0.45134747073116854, "grad_norm": 0.8299713134765625, "learning_rate": 2.4095461357932268e-05, "loss": 0.0204, "step": 8173 }, { "epoch": 0.45140269494146235, "grad_norm": 2.0380280017852783, "learning_rate": 2.409195978861261e-05, "loss": 0.2327, "step": 8174 }, { "epoch": 0.45145791915175615, "grad_norm": 0.9654475450515747, "learning_rate": 2.4088458088379506e-05, "loss": 0.05, "step": 8175 }, { "epoch": 0.4515131433620499, "grad_norm": 1.31166672706604, "learning_rate": 2.4084956257344995e-05, "loss": 0.045, "step": 8176 }, { "epoch": 0.4515683675723437, "grad_norm": 3.811929941177368, "learning_rate": 2.4081454295621092e-05, "loss": 0.5919, "step": 8177 }, { "epoch": 0.4516235917826375, "grad_norm": 1.5519516468048096, "learning_rate": 2.4077952203319855e-05, "loss": 0.0876, "step": 8178 }, { "epoch": 0.4516788159929313, "grad_norm": 2.9326343536376953, "learning_rate": 2.4074449980553317e-05, "loss": 0.6919, "step": 8179 }, { "epoch": 0.4517340402032251, "grad_norm": 4.433566570281982, "learning_rate": 2.4070947627433522e-05, "loss": 0.152, "step": 8180 }, { "epoch": 0.4517892644135189, "grad_norm": 3.4945554733276367, "learning_rate": 2.4067445144072528e-05, "loss": 0.7369, "step": 8181 }, { "epoch": 0.45184448862381266, "grad_norm": 2.3444511890411377, "learning_rate": 2.4063942530582377e-05, "loss": 0.0609, "step": 8182 }, { "epoch": 0.45189971283410646, "grad_norm": 0.4463810622692108, "learning_rate": 2.406043978707514e-05, "loss": 0.0099, "step": 8183 }, { "epoch": 0.45195493704440026, "grad_norm": 4.962224960327148, "learning_rate": 2.4056936913662878e-05, "loss": 0.6741, "step": 8184 }, { "epoch": 0.45201016125469407, "grad_norm": 0.038188304752111435, "learning_rate": 2.4053433910457645e-05, "loss": 0.0012, "step": 8185 }, { "epoch": 0.45206538546498787, "grad_norm": 0.8267663717269897, "learning_rate": 2.404993077757153e-05, "loss": 0.0304, "step": 8186 }, { "epoch": 0.45212060967528167, "grad_norm": 0.1421785205602646, "learning_rate": 2.4046427515116603e-05, "loss": 0.0043, "step": 8187 }, { "epoch": 0.4521758338855754, "grad_norm": 2.7970335483551025, "learning_rate": 2.4042924123204925e-05, "loss": 0.5072, "step": 8188 }, { "epoch": 0.4522310580958692, "grad_norm": 3.311335325241089, "learning_rate": 2.4039420601948606e-05, "loss": 0.301, "step": 8189 }, { "epoch": 0.452286282306163, "grad_norm": 0.027482612058520317, "learning_rate": 2.4035916951459718e-05, "loss": 0.0009, "step": 8190 }, { "epoch": 0.4523415065164568, "grad_norm": 2.8045601844787598, "learning_rate": 2.403241317185036e-05, "loss": 0.9178, "step": 8191 }, { "epoch": 0.45239673072675063, "grad_norm": 0.839489221572876, "learning_rate": 2.4028909263232626e-05, "loss": 0.036, "step": 8192 }, { "epoch": 0.4524519549370444, "grad_norm": 0.22895312309265137, "learning_rate": 2.4025405225718606e-05, "loss": 0.0103, "step": 8193 }, { "epoch": 0.4525071791473382, "grad_norm": 0.5283854603767395, "learning_rate": 2.4021901059420426e-05, "loss": 0.0132, "step": 8194 }, { "epoch": 0.452562403357632, "grad_norm": 0.22476345300674438, "learning_rate": 2.4018396764450175e-05, "loss": 0.0087, "step": 8195 }, { "epoch": 0.4526176275679258, "grad_norm": 3.5042290687561035, "learning_rate": 2.4014892340919968e-05, "loss": 0.1464, "step": 8196 }, { "epoch": 0.4526728517782196, "grad_norm": 0.18831412494182587, "learning_rate": 2.401138778894193e-05, "loss": 0.0049, "step": 8197 }, { "epoch": 0.4527280759885134, "grad_norm": 3.4420387744903564, "learning_rate": 2.4007883108628175e-05, "loss": 0.1914, "step": 8198 }, { "epoch": 0.45278330019880714, "grad_norm": 5.115620136260986, "learning_rate": 2.400437830009083e-05, "loss": 0.9727, "step": 8199 }, { "epoch": 0.45283852440910094, "grad_norm": 0.9365800619125366, "learning_rate": 2.4000873363442026e-05, "loss": 0.1649, "step": 8200 }, { "epoch": 0.45289374861939474, "grad_norm": 0.599685549736023, "learning_rate": 2.3997368298793885e-05, "loss": 0.0167, "step": 8201 }, { "epoch": 0.45294897282968855, "grad_norm": 3.414699077606201, "learning_rate": 2.3993863106258558e-05, "loss": 0.5994, "step": 8202 }, { "epoch": 0.45300419703998235, "grad_norm": 2.99814772605896, "learning_rate": 2.3990357785948176e-05, "loss": 0.6807, "step": 8203 }, { "epoch": 0.4530594212502761, "grad_norm": 3.534006357192993, "learning_rate": 2.3986852337974895e-05, "loss": 1.0546, "step": 8204 }, { "epoch": 0.4531146454605699, "grad_norm": 2.941039562225342, "learning_rate": 2.3983346762450857e-05, "loss": 0.644, "step": 8205 }, { "epoch": 0.4531698696708637, "grad_norm": 2.8111095428466797, "learning_rate": 2.3979841059488207e-05, "loss": 0.5019, "step": 8206 }, { "epoch": 0.4532250938811575, "grad_norm": 0.23936760425567627, "learning_rate": 2.3976335229199118e-05, "loss": 0.005, "step": 8207 }, { "epoch": 0.4532803180914513, "grad_norm": 0.09245249629020691, "learning_rate": 2.3972829271695746e-05, "loss": 0.0028, "step": 8208 }, { "epoch": 0.4533355423017451, "grad_norm": 0.19438892602920532, "learning_rate": 2.3969323187090256e-05, "loss": 0.006, "step": 8209 }, { "epoch": 0.45339076651203886, "grad_norm": 0.09426171332597733, "learning_rate": 2.396581697549482e-05, "loss": 0.0035, "step": 8210 }, { "epoch": 0.45344599072233266, "grad_norm": 2.514683485031128, "learning_rate": 2.3962310637021594e-05, "loss": 0.348, "step": 8211 }, { "epoch": 0.45350121493262646, "grad_norm": 0.23761998116970062, "learning_rate": 2.3958804171782784e-05, "loss": 0.0118, "step": 8212 }, { "epoch": 0.45355643914292026, "grad_norm": 3.2201035022735596, "learning_rate": 2.3955297579890556e-05, "loss": 0.5866, "step": 8213 }, { "epoch": 0.45361166335321407, "grad_norm": 0.010391575284302235, "learning_rate": 2.39517908614571e-05, "loss": 0.0003, "step": 8214 }, { "epoch": 0.4536668875635078, "grad_norm": 5.967526435852051, "learning_rate": 2.39482840165946e-05, "loss": 1.4833, "step": 8215 }, { "epoch": 0.4537221117738016, "grad_norm": 0.6918323040008545, "learning_rate": 2.3944777045415256e-05, "loss": 0.0158, "step": 8216 }, { "epoch": 0.4537773359840954, "grad_norm": 5.195342063903809, "learning_rate": 2.394126994803126e-05, "loss": 0.5882, "step": 8217 }, { "epoch": 0.4538325601943892, "grad_norm": 2.252549409866333, "learning_rate": 2.3937762724554828e-05, "loss": 0.1732, "step": 8218 }, { "epoch": 0.453887784404683, "grad_norm": 0.05766373127698898, "learning_rate": 2.393425537509814e-05, "loss": 0.0023, "step": 8219 }, { "epoch": 0.45394300861497683, "grad_norm": 0.9441994428634644, "learning_rate": 2.3930747899773436e-05, "loss": 0.0484, "step": 8220 }, { "epoch": 0.4539982328252706, "grad_norm": 4.683650970458984, "learning_rate": 2.392724029869291e-05, "loss": 0.9737, "step": 8221 }, { "epoch": 0.4540534570355644, "grad_norm": 3.303053379058838, "learning_rate": 2.3923732571968793e-05, "loss": 0.3186, "step": 8222 }, { "epoch": 0.4541086812458582, "grad_norm": 0.3666721284389496, "learning_rate": 2.3920224719713298e-05, "loss": 0.006, "step": 8223 }, { "epoch": 0.454163905456152, "grad_norm": 0.31335726380348206, "learning_rate": 2.3916716742038648e-05, "loss": 0.0075, "step": 8224 }, { "epoch": 0.4542191296664458, "grad_norm": 2.068415403366089, "learning_rate": 2.3913208639057084e-05, "loss": 0.2056, "step": 8225 }, { "epoch": 0.4542743538767396, "grad_norm": 1.4690496921539307, "learning_rate": 2.3909700410880835e-05, "loss": 0.1507, "step": 8226 }, { "epoch": 0.45432957808703334, "grad_norm": 1.3392583131790161, "learning_rate": 2.3906192057622137e-05, "loss": 0.023, "step": 8227 }, { "epoch": 0.45438480229732714, "grad_norm": 0.45889580249786377, "learning_rate": 2.3902683579393234e-05, "loss": 0.018, "step": 8228 }, { "epoch": 0.45444002650762094, "grad_norm": 2.5683372020721436, "learning_rate": 2.3899174976306376e-05, "loss": 0.1267, "step": 8229 }, { "epoch": 0.45449525071791474, "grad_norm": 0.7725701332092285, "learning_rate": 2.389566624847381e-05, "loss": 0.0367, "step": 8230 }, { "epoch": 0.45455047492820855, "grad_norm": 3.7443675994873047, "learning_rate": 2.389215739600779e-05, "loss": 0.4181, "step": 8231 }, { "epoch": 0.4546056991385023, "grad_norm": 0.031187590211629868, "learning_rate": 2.388864841902057e-05, "loss": 0.0013, "step": 8232 }, { "epoch": 0.4546609233487961, "grad_norm": 0.057270120829343796, "learning_rate": 2.3885139317624422e-05, "loss": 0.0014, "step": 8233 }, { "epoch": 0.4547161475590899, "grad_norm": 0.02111409418284893, "learning_rate": 2.3881630091931607e-05, "loss": 0.0008, "step": 8234 }, { "epoch": 0.4547713717693837, "grad_norm": 4.2025909423828125, "learning_rate": 2.387812074205439e-05, "loss": 1.5291, "step": 8235 }, { "epoch": 0.4548265959796775, "grad_norm": 3.988245725631714, "learning_rate": 2.3874611268105054e-05, "loss": 0.6145, "step": 8236 }, { "epoch": 0.4548818201899713, "grad_norm": 0.49614274501800537, "learning_rate": 2.387110167019587e-05, "loss": 0.0174, "step": 8237 }, { "epoch": 0.45493704440026506, "grad_norm": 0.6556751132011414, "learning_rate": 2.386759194843913e-05, "loss": 0.0195, "step": 8238 }, { "epoch": 0.45499226861055886, "grad_norm": 4.102954387664795, "learning_rate": 2.3864082102947105e-05, "loss": 0.7607, "step": 8239 }, { "epoch": 0.45504749282085266, "grad_norm": 1.6508296728134155, "learning_rate": 2.3860572133832093e-05, "loss": 0.0709, "step": 8240 }, { "epoch": 0.45510271703114646, "grad_norm": 3.5767745971679688, "learning_rate": 2.3857062041206396e-05, "loss": 0.4395, "step": 8241 }, { "epoch": 0.45515794124144027, "grad_norm": 11.990403175354004, "learning_rate": 2.3853551825182293e-05, "loss": 0.6539, "step": 8242 }, { "epoch": 0.455213165451734, "grad_norm": 0.18843157589435577, "learning_rate": 2.38500414858721e-05, "loss": 0.005, "step": 8243 }, { "epoch": 0.4552683896620278, "grad_norm": 3.2700772285461426, "learning_rate": 2.3846531023388126e-05, "loss": 0.5426, "step": 8244 }, { "epoch": 0.4553236138723216, "grad_norm": 1.5186340808868408, "learning_rate": 2.3843020437842667e-05, "loss": 0.1174, "step": 8245 }, { "epoch": 0.4553788380826154, "grad_norm": 0.1803218126296997, "learning_rate": 2.383950972934805e-05, "loss": 0.0033, "step": 8246 }, { "epoch": 0.4554340622929092, "grad_norm": 0.3167954683303833, "learning_rate": 2.383599889801658e-05, "loss": 0.0105, "step": 8247 }, { "epoch": 0.45548928650320303, "grad_norm": 3.591374635696411, "learning_rate": 2.3832487943960585e-05, "loss": 0.6993, "step": 8248 }, { "epoch": 0.4555445107134968, "grad_norm": 0.55747389793396, "learning_rate": 2.3828976867292392e-05, "loss": 0.0107, "step": 8249 }, { "epoch": 0.4555997349237906, "grad_norm": 4.11976432800293, "learning_rate": 2.3825465668124327e-05, "loss": 0.7631, "step": 8250 }, { "epoch": 0.4556549591340844, "grad_norm": 0.07526037096977234, "learning_rate": 2.382195434656873e-05, "loss": 0.0023, "step": 8251 }, { "epoch": 0.4557101833443782, "grad_norm": 3.205918788909912, "learning_rate": 2.3818442902737927e-05, "loss": 0.4343, "step": 8252 }, { "epoch": 0.455765407554672, "grad_norm": 3.6112923622131348, "learning_rate": 2.3814931336744263e-05, "loss": 0.6115, "step": 8253 }, { "epoch": 0.45582063176496573, "grad_norm": 0.08699513971805573, "learning_rate": 2.3811419648700094e-05, "loss": 0.0032, "step": 8254 }, { "epoch": 0.45587585597525954, "grad_norm": 0.13255377113819122, "learning_rate": 2.3807907838717756e-05, "loss": 0.0061, "step": 8255 }, { "epoch": 0.45593108018555334, "grad_norm": 2.299954652786255, "learning_rate": 2.38043959069096e-05, "loss": 0.1441, "step": 8256 }, { "epoch": 0.45598630439584714, "grad_norm": 0.14044448733329773, "learning_rate": 2.380088385338799e-05, "loss": 0.004, "step": 8257 }, { "epoch": 0.45604152860614094, "grad_norm": 0.728500247001648, "learning_rate": 2.3797371678265286e-05, "loss": 0.0349, "step": 8258 }, { "epoch": 0.45609675281643475, "grad_norm": 3.8837978839874268, "learning_rate": 2.3793859381653856e-05, "loss": 0.35, "step": 8259 }, { "epoch": 0.4561519770267285, "grad_norm": 1.3931705951690674, "learning_rate": 2.379034696366606e-05, "loss": 0.1527, "step": 8260 }, { "epoch": 0.4562072012370223, "grad_norm": 0.325981080532074, "learning_rate": 2.3786834424414275e-05, "loss": 0.0092, "step": 8261 }, { "epoch": 0.4562624254473161, "grad_norm": 0.4590874910354614, "learning_rate": 2.378332176401087e-05, "loss": 0.0217, "step": 8262 }, { "epoch": 0.4563176496576099, "grad_norm": 0.10407768189907074, "learning_rate": 2.3779808982568242e-05, "loss": 0.0039, "step": 8263 }, { "epoch": 0.4563728738679037, "grad_norm": 0.19463634490966797, "learning_rate": 2.3776296080198754e-05, "loss": 0.0061, "step": 8264 }, { "epoch": 0.4564280980781975, "grad_norm": 1.383712887763977, "learning_rate": 2.377278305701481e-05, "loss": 0.0251, "step": 8265 }, { "epoch": 0.45648332228849126, "grad_norm": 11.20235538482666, "learning_rate": 2.3769269913128793e-05, "loss": 0.9834, "step": 8266 }, { "epoch": 0.45653854649878506, "grad_norm": 2.658799409866333, "learning_rate": 2.3765756648653103e-05, "loss": 0.5373, "step": 8267 }, { "epoch": 0.45659377070907886, "grad_norm": 2.5360264778137207, "learning_rate": 2.3762243263700135e-05, "loss": 0.1522, "step": 8268 }, { "epoch": 0.45664899491937266, "grad_norm": 3.6572611331939697, "learning_rate": 2.3758729758382292e-05, "loss": 0.9384, "step": 8269 }, { "epoch": 0.45670421912966647, "grad_norm": 4.775990962982178, "learning_rate": 2.3755216132811987e-05, "loss": 1.0468, "step": 8270 }, { "epoch": 0.4567594433399602, "grad_norm": 4.826624393463135, "learning_rate": 2.3751702387101626e-05, "loss": 0.3419, "step": 8271 }, { "epoch": 0.456814667550254, "grad_norm": 4.106576919555664, "learning_rate": 2.3748188521363627e-05, "loss": 1.0214, "step": 8272 }, { "epoch": 0.4568698917605478, "grad_norm": 3.996638774871826, "learning_rate": 2.3744674535710404e-05, "loss": 1.0462, "step": 8273 }, { "epoch": 0.4569251159708416, "grad_norm": 2.8543195724487305, "learning_rate": 2.374116043025439e-05, "loss": 0.1838, "step": 8274 }, { "epoch": 0.4569803401811354, "grad_norm": 1.305626630783081, "learning_rate": 2.3737646205108e-05, "loss": 0.0306, "step": 8275 }, { "epoch": 0.4570355643914292, "grad_norm": 5.75864839553833, "learning_rate": 2.3734131860383655e-05, "loss": 1.1671, "step": 8276 }, { "epoch": 0.457090788601723, "grad_norm": 3.847994804382324, "learning_rate": 2.3730617396193812e-05, "loss": 0.588, "step": 8277 }, { "epoch": 0.4571460128120168, "grad_norm": 1.2952755689620972, "learning_rate": 2.3727102812650898e-05, "loss": 0.1449, "step": 8278 }, { "epoch": 0.4572012370223106, "grad_norm": 0.32317498326301575, "learning_rate": 2.372358810986735e-05, "loss": 0.0132, "step": 8279 }, { "epoch": 0.4572564612326044, "grad_norm": 0.5840650796890259, "learning_rate": 2.372007328795562e-05, "loss": 0.0139, "step": 8280 }, { "epoch": 0.4573116854428982, "grad_norm": 2.7937357425689697, "learning_rate": 2.3716558347028156e-05, "loss": 0.562, "step": 8281 }, { "epoch": 0.45736690965319193, "grad_norm": 0.8834072351455688, "learning_rate": 2.371304328719741e-05, "loss": 0.0175, "step": 8282 }, { "epoch": 0.45742213386348574, "grad_norm": 0.220067098736763, "learning_rate": 2.3709528108575838e-05, "loss": 0.0046, "step": 8283 }, { "epoch": 0.45747735807377954, "grad_norm": 1.5426549911499023, "learning_rate": 2.3706012811275894e-05, "loss": 0.141, "step": 8284 }, { "epoch": 0.45753258228407334, "grad_norm": 2.8774306774139404, "learning_rate": 2.370249739541006e-05, "loss": 0.3205, "step": 8285 }, { "epoch": 0.45758780649436714, "grad_norm": 4.238494873046875, "learning_rate": 2.3698981861090797e-05, "loss": 0.8807, "step": 8286 }, { "epoch": 0.45764303070466095, "grad_norm": 4.624709129333496, "learning_rate": 2.369546620843056e-05, "loss": 0.0565, "step": 8287 }, { "epoch": 0.4576982549149547, "grad_norm": 0.049051716923713684, "learning_rate": 2.3691950437541848e-05, "loss": 0.0019, "step": 8288 }, { "epoch": 0.4577534791252485, "grad_norm": 2.621875524520874, "learning_rate": 2.368843454853713e-05, "loss": 0.1069, "step": 8289 }, { "epoch": 0.4578087033355423, "grad_norm": 2.0861241817474365, "learning_rate": 2.368491854152889e-05, "loss": 0.1309, "step": 8290 }, { "epoch": 0.4578639275458361, "grad_norm": 0.05855470895767212, "learning_rate": 2.3681402416629613e-05, "loss": 0.0017, "step": 8291 }, { "epoch": 0.4579191517561299, "grad_norm": 0.6426689624786377, "learning_rate": 2.3677886173951786e-05, "loss": 0.0113, "step": 8292 }, { "epoch": 0.45797437596642365, "grad_norm": 5.182770729064941, "learning_rate": 2.367436981360792e-05, "loss": 0.8187, "step": 8293 }, { "epoch": 0.45802960017671746, "grad_norm": 1.9288285970687866, "learning_rate": 2.3670853335710503e-05, "loss": 0.2525, "step": 8294 }, { "epoch": 0.45808482438701126, "grad_norm": 3.8058664798736572, "learning_rate": 2.3667336740372032e-05, "loss": 1.1139, "step": 8295 }, { "epoch": 0.45814004859730506, "grad_norm": 0.7832973003387451, "learning_rate": 2.3663820027705025e-05, "loss": 0.0185, "step": 8296 }, { "epoch": 0.45819527280759886, "grad_norm": 0.06297668069601059, "learning_rate": 2.3660303197821976e-05, "loss": 0.0015, "step": 8297 }, { "epoch": 0.45825049701789267, "grad_norm": 6.466672897338867, "learning_rate": 2.3656786250835416e-05, "loss": 0.6895, "step": 8298 }, { "epoch": 0.4583057212281864, "grad_norm": 0.46899473667144775, "learning_rate": 2.365326918685785e-05, "loss": 0.0095, "step": 8299 }, { "epoch": 0.4583609454384802, "grad_norm": 0.048950791358947754, "learning_rate": 2.3649752006001795e-05, "loss": 0.0009, "step": 8300 }, { "epoch": 0.458416169648774, "grad_norm": 1.8003286123275757, "learning_rate": 2.3646234708379793e-05, "loss": 0.0686, "step": 8301 }, { "epoch": 0.4584713938590678, "grad_norm": 0.17735907435417175, "learning_rate": 2.3642717294104357e-05, "loss": 0.0046, "step": 8302 }, { "epoch": 0.4585266180693616, "grad_norm": 1.6942460536956787, "learning_rate": 2.363919976328803e-05, "loss": 0.0349, "step": 8303 }, { "epoch": 0.4585818422796554, "grad_norm": 0.10540784895420074, "learning_rate": 2.3635682116043336e-05, "loss": 0.0025, "step": 8304 }, { "epoch": 0.4586370664899492, "grad_norm": 1.663737177848816, "learning_rate": 2.3632164352482826e-05, "loss": 0.1211, "step": 8305 }, { "epoch": 0.458692290700243, "grad_norm": 4.6286516189575195, "learning_rate": 2.3628646472719034e-05, "loss": 0.965, "step": 8306 }, { "epoch": 0.4587475149105368, "grad_norm": 2.3771474361419678, "learning_rate": 2.362512847686451e-05, "loss": 0.053, "step": 8307 }, { "epoch": 0.4588027391208306, "grad_norm": 2.435133695602417, "learning_rate": 2.362161036503181e-05, "loss": 0.2914, "step": 8308 }, { "epoch": 0.4588579633311244, "grad_norm": 1.0056480169296265, "learning_rate": 2.3618092137333482e-05, "loss": 0.0359, "step": 8309 }, { "epoch": 0.45891318754141813, "grad_norm": 0.801048219203949, "learning_rate": 2.3614573793882082e-05, "loss": 0.0261, "step": 8310 }, { "epoch": 0.45896841175171194, "grad_norm": 0.35231468081474304, "learning_rate": 2.3611055334790188e-05, "loss": 0.0113, "step": 8311 }, { "epoch": 0.45902363596200574, "grad_norm": 0.021229248493909836, "learning_rate": 2.3607536760170344e-05, "loss": 0.0009, "step": 8312 }, { "epoch": 0.45907886017229954, "grad_norm": 2.062739849090576, "learning_rate": 2.360401807013513e-05, "loss": 0.0994, "step": 8313 }, { "epoch": 0.45913408438259334, "grad_norm": 0.6681265830993652, "learning_rate": 2.360049926479712e-05, "loss": 0.0204, "step": 8314 }, { "epoch": 0.45918930859288715, "grad_norm": 4.2094573974609375, "learning_rate": 2.359698034426889e-05, "loss": 0.4537, "step": 8315 }, { "epoch": 0.4592445328031809, "grad_norm": 0.6822181940078735, "learning_rate": 2.359346130866301e-05, "loss": 0.0272, "step": 8316 }, { "epoch": 0.4592997570134747, "grad_norm": 3.7046570777893066, "learning_rate": 2.358994215809208e-05, "loss": 0.8668, "step": 8317 }, { "epoch": 0.4593549812237685, "grad_norm": 2.5335633754730225, "learning_rate": 2.3586422892668675e-05, "loss": 0.1978, "step": 8318 }, { "epoch": 0.4594102054340623, "grad_norm": 2.528347969055176, "learning_rate": 2.3582903512505402e-05, "loss": 0.5301, "step": 8319 }, { "epoch": 0.4594654296443561, "grad_norm": 0.5760464072227478, "learning_rate": 2.3579384017714836e-05, "loss": 0.0165, "step": 8320 }, { "epoch": 0.45952065385464985, "grad_norm": 2.3403706550598145, "learning_rate": 2.357586440840959e-05, "loss": 0.8008, "step": 8321 }, { "epoch": 0.45957587806494365, "grad_norm": 1.052949070930481, "learning_rate": 2.357234468470226e-05, "loss": 0.4476, "step": 8322 }, { "epoch": 0.45963110227523746, "grad_norm": 0.03574229031801224, "learning_rate": 2.3568824846705453e-05, "loss": 0.0011, "step": 8323 }, { "epoch": 0.45968632648553126, "grad_norm": 0.07396161556243896, "learning_rate": 2.356530489453178e-05, "loss": 0.0027, "step": 8324 }, { "epoch": 0.45974155069582506, "grad_norm": 4.500718593597412, "learning_rate": 2.3561784828293856e-05, "loss": 0.4045, "step": 8325 }, { "epoch": 0.45979677490611887, "grad_norm": 0.06293124705553055, "learning_rate": 2.3558264648104284e-05, "loss": 0.003, "step": 8326 }, { "epoch": 0.4598519991164126, "grad_norm": 0.44100141525268555, "learning_rate": 2.3554744354075707e-05, "loss": 0.0173, "step": 8327 }, { "epoch": 0.4599072233267064, "grad_norm": 3.895392417907715, "learning_rate": 2.3551223946320735e-05, "loss": 0.6478, "step": 8328 }, { "epoch": 0.4599624475370002, "grad_norm": 0.7856165170669556, "learning_rate": 2.3547703424951998e-05, "loss": 0.1446, "step": 8329 }, { "epoch": 0.460017671747294, "grad_norm": 1.9909173250198364, "learning_rate": 2.354418279008213e-05, "loss": 0.2258, "step": 8330 }, { "epoch": 0.4600728959575878, "grad_norm": 0.22039645910263062, "learning_rate": 2.3540662041823765e-05, "loss": 0.0046, "step": 8331 }, { "epoch": 0.4601281201678816, "grad_norm": 0.4246411919593811, "learning_rate": 2.3537141180289544e-05, "loss": 0.0088, "step": 8332 }, { "epoch": 0.4601833443781754, "grad_norm": 3.4661483764648438, "learning_rate": 2.3533620205592104e-05, "loss": 0.2516, "step": 8333 }, { "epoch": 0.4602385685884692, "grad_norm": 1.851471185684204, "learning_rate": 2.3530099117844097e-05, "loss": 0.1018, "step": 8334 }, { "epoch": 0.460293792798763, "grad_norm": 0.15666654706001282, "learning_rate": 2.3526577917158168e-05, "loss": 0.0036, "step": 8335 }, { "epoch": 0.4603490170090568, "grad_norm": 1.0412354469299316, "learning_rate": 2.352305660364697e-05, "loss": 0.0392, "step": 8336 }, { "epoch": 0.4604042412193506, "grad_norm": 0.011655216105282307, "learning_rate": 2.351953517742316e-05, "loss": 0.0003, "step": 8337 }, { "epoch": 0.46045946542964433, "grad_norm": 5.123457908630371, "learning_rate": 2.35160136385994e-05, "loss": 0.4669, "step": 8338 }, { "epoch": 0.46051468963993814, "grad_norm": 0.735368013381958, "learning_rate": 2.3512491987288353e-05, "loss": 0.0294, "step": 8339 }, { "epoch": 0.46056991385023194, "grad_norm": 0.16516320407390594, "learning_rate": 2.3508970223602698e-05, "loss": 0.0037, "step": 8340 }, { "epoch": 0.46062513806052574, "grad_norm": 1.9922256469726562, "learning_rate": 2.3505448347655083e-05, "loss": 0.0823, "step": 8341 }, { "epoch": 0.46068036227081954, "grad_norm": 0.1298225373029709, "learning_rate": 2.35019263595582e-05, "loss": 0.0027, "step": 8342 }, { "epoch": 0.46073558648111335, "grad_norm": 5.174160480499268, "learning_rate": 2.349840425942473e-05, "loss": 0.4792, "step": 8343 }, { "epoch": 0.4607908106914071, "grad_norm": 3.41324782371521, "learning_rate": 2.3494882047367334e-05, "loss": 0.2382, "step": 8344 }, { "epoch": 0.4608460349017009, "grad_norm": 2.022066831588745, "learning_rate": 2.349135972349873e-05, "loss": 0.7248, "step": 8345 }, { "epoch": 0.4609012591119947, "grad_norm": 1.5894538164138794, "learning_rate": 2.3487837287931578e-05, "loss": 0.3774, "step": 8346 }, { "epoch": 0.4609564833222885, "grad_norm": 2.945084810256958, "learning_rate": 2.3484314740778576e-05, "loss": 0.606, "step": 8347 }, { "epoch": 0.4610117075325823, "grad_norm": 3.3145532608032227, "learning_rate": 2.3480792082152437e-05, "loss": 0.0843, "step": 8348 }, { "epoch": 0.46106693174287605, "grad_norm": 0.15204298496246338, "learning_rate": 2.3477269312165846e-05, "loss": 0.0037, "step": 8349 }, { "epoch": 0.46112215595316985, "grad_norm": 0.09578128159046173, "learning_rate": 2.3473746430931513e-05, "loss": 0.0019, "step": 8350 }, { "epoch": 0.46117738016346366, "grad_norm": 1.429213285446167, "learning_rate": 2.3470223438562138e-05, "loss": 0.1087, "step": 8351 }, { "epoch": 0.46123260437375746, "grad_norm": 0.007296488154679537, "learning_rate": 2.3466700335170436e-05, "loss": 0.0002, "step": 8352 }, { "epoch": 0.46128782858405126, "grad_norm": 2.6566505432128906, "learning_rate": 2.346317712086912e-05, "loss": 0.3078, "step": 8353 }, { "epoch": 0.46134305279434507, "grad_norm": 0.8369790315628052, "learning_rate": 2.345965379577092e-05, "loss": 0.0355, "step": 8354 }, { "epoch": 0.4613982770046388, "grad_norm": 0.5410990118980408, "learning_rate": 2.345613035998853e-05, "loss": 0.0125, "step": 8355 }, { "epoch": 0.4614535012149326, "grad_norm": 0.13308241963386536, "learning_rate": 2.34526068136347e-05, "loss": 0.0045, "step": 8356 }, { "epoch": 0.4615087254252264, "grad_norm": 0.0910671129822731, "learning_rate": 2.3449083156822145e-05, "loss": 0.0023, "step": 8357 }, { "epoch": 0.4615639496355202, "grad_norm": 4.068859577178955, "learning_rate": 2.3445559389663605e-05, "loss": 0.1425, "step": 8358 }, { "epoch": 0.461619173845814, "grad_norm": 2.9938082695007324, "learning_rate": 2.3442035512271807e-05, "loss": 0.2454, "step": 8359 }, { "epoch": 0.46167439805610777, "grad_norm": 0.029741136357188225, "learning_rate": 2.3438511524759492e-05, "loss": 0.0009, "step": 8360 }, { "epoch": 0.4617296222664016, "grad_norm": 4.475722312927246, "learning_rate": 2.343498742723941e-05, "loss": 0.8837, "step": 8361 }, { "epoch": 0.4617848464766954, "grad_norm": 0.02878699079155922, "learning_rate": 2.3431463219824297e-05, "loss": 0.001, "step": 8362 }, { "epoch": 0.4618400706869892, "grad_norm": 0.09486523270606995, "learning_rate": 2.342793890262691e-05, "loss": 0.0026, "step": 8363 }, { "epoch": 0.461895294897283, "grad_norm": 4.25812292098999, "learning_rate": 2.342441447576e-05, "loss": 0.5855, "step": 8364 }, { "epoch": 0.4619505191075768, "grad_norm": 0.0189688540995121, "learning_rate": 2.342088993933632e-05, "loss": 0.0005, "step": 8365 }, { "epoch": 0.46200574331787053, "grad_norm": 3.1840202808380127, "learning_rate": 2.341736529346863e-05, "loss": 0.7964, "step": 8366 }, { "epoch": 0.46206096752816433, "grad_norm": 0.4243854880332947, "learning_rate": 2.3413840538269697e-05, "loss": 0.0126, "step": 8367 }, { "epoch": 0.46211619173845814, "grad_norm": 0.08180642873048782, "learning_rate": 2.3410315673852283e-05, "loss": 0.0025, "step": 8368 }, { "epoch": 0.46217141594875194, "grad_norm": 5.033848285675049, "learning_rate": 2.340679070032917e-05, "loss": 0.6898, "step": 8369 }, { "epoch": 0.46222664015904574, "grad_norm": 0.12621766328811646, "learning_rate": 2.3403265617813117e-05, "loss": 0.0043, "step": 8370 }, { "epoch": 0.46228186436933955, "grad_norm": 3.2590203285217285, "learning_rate": 2.339974042641691e-05, "loss": 0.7227, "step": 8371 }, { "epoch": 0.4623370885796333, "grad_norm": 0.26898935437202454, "learning_rate": 2.3396215126253326e-05, "loss": 0.0063, "step": 8372 }, { "epoch": 0.4623923127899271, "grad_norm": 0.13653837144374847, "learning_rate": 2.339268971743515e-05, "loss": 0.0032, "step": 8373 }, { "epoch": 0.4624475370002209, "grad_norm": 0.10054198652505875, "learning_rate": 2.338916420007518e-05, "loss": 0.0029, "step": 8374 }, { "epoch": 0.4625027612105147, "grad_norm": 6.878362655639648, "learning_rate": 2.3385638574286196e-05, "loss": 1.3693, "step": 8375 }, { "epoch": 0.4625579854208085, "grad_norm": 0.5550727248191833, "learning_rate": 2.3382112840180993e-05, "loss": 0.019, "step": 8376 }, { "epoch": 0.46261320963110225, "grad_norm": 0.0524841733276844, "learning_rate": 2.337858699787237e-05, "loss": 0.0019, "step": 8377 }, { "epoch": 0.46266843384139605, "grad_norm": 0.8825867772102356, "learning_rate": 2.337506104747313e-05, "loss": 0.009, "step": 8378 }, { "epoch": 0.46272365805168986, "grad_norm": 3.4588096141815186, "learning_rate": 2.3371534989096084e-05, "loss": 0.0395, "step": 8379 }, { "epoch": 0.46277888226198366, "grad_norm": 0.18159779906272888, "learning_rate": 2.3368008822854035e-05, "loss": 0.0062, "step": 8380 }, { "epoch": 0.46283410647227746, "grad_norm": 3.032510757446289, "learning_rate": 2.336448254885979e-05, "loss": 0.294, "step": 8381 }, { "epoch": 0.46288933068257127, "grad_norm": 0.04035045951604843, "learning_rate": 2.3360956167226173e-05, "loss": 0.0014, "step": 8382 }, { "epoch": 0.462944554892865, "grad_norm": 2.30546498298645, "learning_rate": 2.3357429678066002e-05, "loss": 0.1721, "step": 8383 }, { "epoch": 0.4629997791031588, "grad_norm": 2.4079947471618652, "learning_rate": 2.3353903081492093e-05, "loss": 0.1038, "step": 8384 }, { "epoch": 0.4630550033134526, "grad_norm": 0.06673926115036011, "learning_rate": 2.3350376377617283e-05, "loss": 0.0021, "step": 8385 }, { "epoch": 0.4631102275237464, "grad_norm": 3.262707471847534, "learning_rate": 2.3346849566554388e-05, "loss": 0.1866, "step": 8386 }, { "epoch": 0.4631654517340402, "grad_norm": 0.09510289877653122, "learning_rate": 2.334332264841625e-05, "loss": 0.0024, "step": 8387 }, { "epoch": 0.46322067594433397, "grad_norm": 1.655579686164856, "learning_rate": 2.3339795623315702e-05, "loss": 0.1796, "step": 8388 }, { "epoch": 0.4632759001546278, "grad_norm": 0.04607745632529259, "learning_rate": 2.3336268491365583e-05, "loss": 0.001, "step": 8389 }, { "epoch": 0.4633311243649216, "grad_norm": 3.844059705734253, "learning_rate": 2.333274125267874e-05, "loss": 0.4705, "step": 8390 }, { "epoch": 0.4633863485752154, "grad_norm": 0.22319276630878448, "learning_rate": 2.332921390736801e-05, "loss": 0.0078, "step": 8391 }, { "epoch": 0.4634415727855092, "grad_norm": 3.8785617351531982, "learning_rate": 2.3325686455546256e-05, "loss": 1.1406, "step": 8392 }, { "epoch": 0.463496796995803, "grad_norm": 1.4135282039642334, "learning_rate": 2.3322158897326325e-05, "loss": 0.283, "step": 8393 }, { "epoch": 0.46355202120609673, "grad_norm": 0.19748038053512573, "learning_rate": 2.3318631232821072e-05, "loss": 0.0052, "step": 8394 }, { "epoch": 0.46360724541639053, "grad_norm": 4.08188009262085, "learning_rate": 2.331510346214336e-05, "loss": 1.0315, "step": 8395 }, { "epoch": 0.46366246962668434, "grad_norm": 4.666872978210449, "learning_rate": 2.3311575585406043e-05, "loss": 0.6491, "step": 8396 }, { "epoch": 0.46371769383697814, "grad_norm": 1.087302327156067, "learning_rate": 2.3308047602722e-05, "loss": 0.0461, "step": 8397 }, { "epoch": 0.46377291804727194, "grad_norm": 0.07672753930091858, "learning_rate": 2.33045195142041e-05, "loss": 0.0012, "step": 8398 }, { "epoch": 0.4638281422575657, "grad_norm": 3.17350172996521, "learning_rate": 2.3300991319965206e-05, "loss": 0.0995, "step": 8399 }, { "epoch": 0.4638833664678595, "grad_norm": 0.958556592464447, "learning_rate": 2.329746302011821e-05, "loss": 0.008, "step": 8400 }, { "epoch": 0.4639385906781533, "grad_norm": 0.4275200068950653, "learning_rate": 2.329393461477597e-05, "loss": 0.0117, "step": 8401 }, { "epoch": 0.4639938148884471, "grad_norm": 1.290714979171753, "learning_rate": 2.32904061040514e-05, "loss": 0.0313, "step": 8402 }, { "epoch": 0.4640490390987409, "grad_norm": 0.23186790943145752, "learning_rate": 2.3286877488057368e-05, "loss": 0.0068, "step": 8403 }, { "epoch": 0.4641042633090347, "grad_norm": 3.0950467586517334, "learning_rate": 2.328334876690676e-05, "loss": 0.1714, "step": 8404 }, { "epoch": 0.46415948751932845, "grad_norm": 4.6582841873168945, "learning_rate": 2.327981994071249e-05, "loss": 0.1187, "step": 8405 }, { "epoch": 0.46421471172962225, "grad_norm": 0.014643852598965168, "learning_rate": 2.327629100958744e-05, "loss": 0.0004, "step": 8406 }, { "epoch": 0.46426993593991606, "grad_norm": 0.49942389130592346, "learning_rate": 2.3272761973644503e-05, "loss": 0.0148, "step": 8407 }, { "epoch": 0.46432516015020986, "grad_norm": 4.455037593841553, "learning_rate": 2.3269232832996603e-05, "loss": 0.6731, "step": 8408 }, { "epoch": 0.46438038436050366, "grad_norm": 3.9409451484680176, "learning_rate": 2.326570358775663e-05, "loss": 0.3913, "step": 8409 }, { "epoch": 0.46443560857079746, "grad_norm": 2.325387954711914, "learning_rate": 2.3262174238037506e-05, "loss": 0.1724, "step": 8410 }, { "epoch": 0.4644908327810912, "grad_norm": 0.5618546009063721, "learning_rate": 2.3258644783952145e-05, "loss": 0.0155, "step": 8411 }, { "epoch": 0.464546056991385, "grad_norm": 0.5971586108207703, "learning_rate": 2.325511522561345e-05, "loss": 0.0161, "step": 8412 }, { "epoch": 0.4646012812016788, "grad_norm": 1.9830137491226196, "learning_rate": 2.3251585563134366e-05, "loss": 0.2415, "step": 8413 }, { "epoch": 0.4646565054119726, "grad_norm": 4.62053108215332, "learning_rate": 2.3248055796627798e-05, "loss": 0.7467, "step": 8414 }, { "epoch": 0.4647117296222664, "grad_norm": 0.1284990757703781, "learning_rate": 2.3244525926206675e-05, "loss": 0.0034, "step": 8415 }, { "epoch": 0.46476695383256017, "grad_norm": 0.02327071875333786, "learning_rate": 2.3240995951983934e-05, "loss": 0.0009, "step": 8416 }, { "epoch": 0.464822178042854, "grad_norm": 0.06396812200546265, "learning_rate": 2.32374658740725e-05, "loss": 0.0019, "step": 8417 }, { "epoch": 0.4648774022531478, "grad_norm": 2.2492527961730957, "learning_rate": 2.323393569258532e-05, "loss": 0.2653, "step": 8418 }, { "epoch": 0.4649326264634416, "grad_norm": 0.10789614915847778, "learning_rate": 2.3230405407635335e-05, "loss": 0.0033, "step": 8419 }, { "epoch": 0.4649878506737354, "grad_norm": 1.3749300241470337, "learning_rate": 2.3226875019335476e-05, "loss": 0.2752, "step": 8420 }, { "epoch": 0.4650430748840292, "grad_norm": 7.080639362335205, "learning_rate": 2.3223344527798703e-05, "loss": 0.7828, "step": 8421 }, { "epoch": 0.46509829909432293, "grad_norm": 3.607330560684204, "learning_rate": 2.321981393313796e-05, "loss": 0.6097, "step": 8422 }, { "epoch": 0.46515352330461673, "grad_norm": 3.8277997970581055, "learning_rate": 2.3216283235466205e-05, "loss": 0.9748, "step": 8423 }, { "epoch": 0.46520874751491054, "grad_norm": 2.480663776397705, "learning_rate": 2.3212752434896393e-05, "loss": 0.4922, "step": 8424 }, { "epoch": 0.46526397172520434, "grad_norm": 4.12780237197876, "learning_rate": 2.320922153154148e-05, "loss": 0.483, "step": 8425 }, { "epoch": 0.46531919593549814, "grad_norm": 5.052811622619629, "learning_rate": 2.3205690525514443e-05, "loss": 0.7022, "step": 8426 }, { "epoch": 0.4653744201457919, "grad_norm": 5.132376670837402, "learning_rate": 2.3202159416928235e-05, "loss": 0.7978, "step": 8427 }, { "epoch": 0.4654296443560857, "grad_norm": 2.636251926422119, "learning_rate": 2.319862820589583e-05, "loss": 0.3314, "step": 8428 }, { "epoch": 0.4654848685663795, "grad_norm": 0.013377806171774864, "learning_rate": 2.3195096892530204e-05, "loss": 0.0003, "step": 8429 }, { "epoch": 0.4655400927766733, "grad_norm": 0.3122580945491791, "learning_rate": 2.319156547694433e-05, "loss": 0.0077, "step": 8430 }, { "epoch": 0.4655953169869671, "grad_norm": 0.3944639265537262, "learning_rate": 2.3188033959251195e-05, "loss": 0.012, "step": 8431 }, { "epoch": 0.4656505411972609, "grad_norm": 0.26834723353385925, "learning_rate": 2.3184502339563776e-05, "loss": 0.0094, "step": 8432 }, { "epoch": 0.46570576540755465, "grad_norm": 0.020806990563869476, "learning_rate": 2.3180970617995057e-05, "loss": 0.0006, "step": 8433 }, { "epoch": 0.46576098961784845, "grad_norm": 2.435764789581299, "learning_rate": 2.3177438794658037e-05, "loss": 0.2836, "step": 8434 }, { "epoch": 0.46581621382814226, "grad_norm": 0.8432942628860474, "learning_rate": 2.3173906869665706e-05, "loss": 0.0349, "step": 8435 }, { "epoch": 0.46587143803843606, "grad_norm": 1.6687278747558594, "learning_rate": 2.317037484313105e-05, "loss": 0.0747, "step": 8436 }, { "epoch": 0.46592666224872986, "grad_norm": 0.25962692499160767, "learning_rate": 2.3166842715167083e-05, "loss": 0.0098, "step": 8437 }, { "epoch": 0.4659818864590236, "grad_norm": 0.25615474581718445, "learning_rate": 2.31633104858868e-05, "loss": 0.0051, "step": 8438 }, { "epoch": 0.4660371106693174, "grad_norm": 2.667524576187134, "learning_rate": 2.3159778155403208e-05, "loss": 0.085, "step": 8439 }, { "epoch": 0.4660923348796112, "grad_norm": 1.6780650615692139, "learning_rate": 2.3156245723829325e-05, "loss": 0.0389, "step": 8440 }, { "epoch": 0.466147559089905, "grad_norm": 4.481848239898682, "learning_rate": 2.3152713191278147e-05, "loss": 0.2908, "step": 8441 }, { "epoch": 0.4662027833001988, "grad_norm": 3.5201311111450195, "learning_rate": 2.3149180557862706e-05, "loss": 0.6653, "step": 8442 }, { "epoch": 0.4662580075104926, "grad_norm": 0.07097987830638885, "learning_rate": 2.314564782369601e-05, "loss": 0.0029, "step": 8443 }, { "epoch": 0.46631323172078637, "grad_norm": 1.814170479774475, "learning_rate": 2.3142114988891083e-05, "loss": 0.169, "step": 8444 }, { "epoch": 0.4663684559310802, "grad_norm": 1.810719609260559, "learning_rate": 2.3138582053560953e-05, "loss": 0.0952, "step": 8445 }, { "epoch": 0.466423680141374, "grad_norm": 0.792834460735321, "learning_rate": 2.3135049017818644e-05, "loss": 0.0296, "step": 8446 }, { "epoch": 0.4664789043516678, "grad_norm": 1.7600154876708984, "learning_rate": 2.31315158817772e-05, "loss": 0.0944, "step": 8447 }, { "epoch": 0.4665341285619616, "grad_norm": 4.6755523681640625, "learning_rate": 2.3127982645549647e-05, "loss": 0.4877, "step": 8448 }, { "epoch": 0.4665893527722554, "grad_norm": 0.8149199485778809, "learning_rate": 2.312444930924902e-05, "loss": 0.0151, "step": 8449 }, { "epoch": 0.46664457698254913, "grad_norm": 1.5382537841796875, "learning_rate": 2.3120915872988366e-05, "loss": 0.3617, "step": 8450 }, { "epoch": 0.46669980119284293, "grad_norm": 5.101919174194336, "learning_rate": 2.3117382336880728e-05, "loss": 0.7785, "step": 8451 }, { "epoch": 0.46675502540313674, "grad_norm": 0.02143954485654831, "learning_rate": 2.3113848701039155e-05, "loss": 0.0008, "step": 8452 }, { "epoch": 0.46681024961343054, "grad_norm": 3.286651611328125, "learning_rate": 2.3110314965576702e-05, "loss": 0.5075, "step": 8453 }, { "epoch": 0.46686547382372434, "grad_norm": 0.9972192645072937, "learning_rate": 2.3106781130606414e-05, "loss": 0.0159, "step": 8454 }, { "epoch": 0.4669206980340181, "grad_norm": 7.4015984535217285, "learning_rate": 2.3103247196241353e-05, "loss": 1.2126, "step": 8455 }, { "epoch": 0.4669759222443119, "grad_norm": 0.22784823179244995, "learning_rate": 2.309971316259458e-05, "loss": 0.0075, "step": 8456 }, { "epoch": 0.4670311464546057, "grad_norm": 2.886382818222046, "learning_rate": 2.3096179029779154e-05, "loss": 0.6136, "step": 8457 }, { "epoch": 0.4670863706648995, "grad_norm": 0.1549353003501892, "learning_rate": 2.3092644797908154e-05, "loss": 0.0042, "step": 8458 }, { "epoch": 0.4671415948751933, "grad_norm": 1.9588067531585693, "learning_rate": 2.3089110467094638e-05, "loss": 0.4542, "step": 8459 }, { "epoch": 0.4671968190854871, "grad_norm": 3.381312370300293, "learning_rate": 2.3085576037451686e-05, "loss": 0.5932, "step": 8460 }, { "epoch": 0.46725204329578085, "grad_norm": 1.6510734558105469, "learning_rate": 2.3082041509092367e-05, "loss": 0.0743, "step": 8461 }, { "epoch": 0.46730726750607465, "grad_norm": 4.259249210357666, "learning_rate": 2.3078506882129773e-05, "loss": 1.3453, "step": 8462 }, { "epoch": 0.46736249171636846, "grad_norm": 0.19339825212955475, "learning_rate": 2.3074972156676977e-05, "loss": 0.0077, "step": 8463 }, { "epoch": 0.46741771592666226, "grad_norm": 0.12229643017053604, "learning_rate": 2.3071437332847064e-05, "loss": 0.0033, "step": 8464 }, { "epoch": 0.46747294013695606, "grad_norm": 3.6995067596435547, "learning_rate": 2.3067902410753132e-05, "loss": 0.6441, "step": 8465 }, { "epoch": 0.4675281643472498, "grad_norm": 3.4144577980041504, "learning_rate": 2.3064367390508273e-05, "loss": 0.4406, "step": 8466 }, { "epoch": 0.4675833885575436, "grad_norm": 1.3759472370147705, "learning_rate": 2.3060832272225566e-05, "loss": 0.1414, "step": 8467 }, { "epoch": 0.4676386127678374, "grad_norm": 5.15022611618042, "learning_rate": 2.3057297056018126e-05, "loss": 0.9771, "step": 8468 }, { "epoch": 0.4676938369781312, "grad_norm": 4.262362957000732, "learning_rate": 2.3053761741999042e-05, "loss": 1.0556, "step": 8469 }, { "epoch": 0.467749061188425, "grad_norm": 0.9271325469017029, "learning_rate": 2.3050226330281436e-05, "loss": 0.0422, "step": 8470 }, { "epoch": 0.4678042853987188, "grad_norm": 0.053888965398073196, "learning_rate": 2.3046690820978404e-05, "loss": 0.0016, "step": 8471 }, { "epoch": 0.46785950960901257, "grad_norm": 1.5338654518127441, "learning_rate": 2.3043155214203055e-05, "loss": 0.0736, "step": 8472 }, { "epoch": 0.46791473381930637, "grad_norm": 3.954880714416504, "learning_rate": 2.3039619510068513e-05, "loss": 0.3758, "step": 8473 }, { "epoch": 0.4679699580296002, "grad_norm": 4.053572654724121, "learning_rate": 2.3036083708687887e-05, "loss": 0.1896, "step": 8474 }, { "epoch": 0.468025182239894, "grad_norm": 5.095920562744141, "learning_rate": 2.30325478101743e-05, "loss": 0.9177, "step": 8475 }, { "epoch": 0.4680804064501878, "grad_norm": 1.285325288772583, "learning_rate": 2.3029011814640875e-05, "loss": 0.1136, "step": 8476 }, { "epoch": 0.4681356306604815, "grad_norm": 3.0262503623962402, "learning_rate": 2.3025475722200738e-05, "loss": 0.34, "step": 8477 }, { "epoch": 0.46819085487077533, "grad_norm": 0.5398020148277283, "learning_rate": 2.3021939532967022e-05, "loss": 0.0164, "step": 8478 }, { "epoch": 0.46824607908106913, "grad_norm": 4.083116054534912, "learning_rate": 2.3018403247052854e-05, "loss": 0.6685, "step": 8479 }, { "epoch": 0.46830130329136294, "grad_norm": 0.4122787415981293, "learning_rate": 2.3014866864571373e-05, "loss": 0.0125, "step": 8480 }, { "epoch": 0.46835652750165674, "grad_norm": 3.1280570030212402, "learning_rate": 2.301133038563572e-05, "loss": 0.033, "step": 8481 }, { "epoch": 0.46841175171195054, "grad_norm": 0.7517033219337463, "learning_rate": 2.3007793810359034e-05, "loss": 0.0239, "step": 8482 }, { "epoch": 0.4684669759222443, "grad_norm": 0.07728233188390732, "learning_rate": 2.3004257138854462e-05, "loss": 0.003, "step": 8483 }, { "epoch": 0.4685222001325381, "grad_norm": 0.700830340385437, "learning_rate": 2.3000720371235153e-05, "loss": 0.0193, "step": 8484 }, { "epoch": 0.4685774243428319, "grad_norm": 3.245266914367676, "learning_rate": 2.2997183507614252e-05, "loss": 0.2171, "step": 8485 }, { "epoch": 0.4686326485531257, "grad_norm": 0.046347081661224365, "learning_rate": 2.2993646548104926e-05, "loss": 0.0014, "step": 8486 }, { "epoch": 0.4686878727634195, "grad_norm": 4.597314834594727, "learning_rate": 2.299010949282032e-05, "loss": 1.0718, "step": 8487 }, { "epoch": 0.4687430969737133, "grad_norm": 1.5651040077209473, "learning_rate": 2.2986572341873595e-05, "loss": 0.1775, "step": 8488 }, { "epoch": 0.46879832118400705, "grad_norm": 2.182960033416748, "learning_rate": 2.2983035095377925e-05, "loss": 0.2544, "step": 8489 }, { "epoch": 0.46885354539430085, "grad_norm": 5.5170488357543945, "learning_rate": 2.297949775344646e-05, "loss": 1.4762, "step": 8490 }, { "epoch": 0.46890876960459466, "grad_norm": 1.5349342823028564, "learning_rate": 2.297596031619239e-05, "loss": 0.1517, "step": 8491 }, { "epoch": 0.46896399381488846, "grad_norm": 0.7572746276855469, "learning_rate": 2.2972422783728873e-05, "loss": 0.1091, "step": 8492 }, { "epoch": 0.46901921802518226, "grad_norm": 0.43204233050346375, "learning_rate": 2.2968885156169086e-05, "loss": 0.0111, "step": 8493 }, { "epoch": 0.469074442235476, "grad_norm": 0.18604214489459991, "learning_rate": 2.296534743362622e-05, "loss": 0.0069, "step": 8494 }, { "epoch": 0.4691296664457698, "grad_norm": 1.9140626192092896, "learning_rate": 2.2961809616213442e-05, "loss": 0.1261, "step": 8495 }, { "epoch": 0.4691848906560636, "grad_norm": 6.787134170532227, "learning_rate": 2.295827170404394e-05, "loss": 1.0044, "step": 8496 }, { "epoch": 0.4692401148663574, "grad_norm": 1.961069107055664, "learning_rate": 2.2954733697230904e-05, "loss": 0.0351, "step": 8497 }, { "epoch": 0.4692953390766512, "grad_norm": 3.187084913253784, "learning_rate": 2.295119559588753e-05, "loss": 0.604, "step": 8498 }, { "epoch": 0.469350563286945, "grad_norm": 0.015555378049612045, "learning_rate": 2.2947657400127007e-05, "loss": 0.0005, "step": 8499 }, { "epoch": 0.46940578749723877, "grad_norm": 2.40244460105896, "learning_rate": 2.294411911006253e-05, "loss": 0.4187, "step": 8500 }, { "epoch": 0.46946101170753257, "grad_norm": 0.06816300749778748, "learning_rate": 2.2940580725807297e-05, "loss": 0.0022, "step": 8501 }, { "epoch": 0.4695162359178264, "grad_norm": 0.0231257863342762, "learning_rate": 2.2937042247474525e-05, "loss": 0.0008, "step": 8502 }, { "epoch": 0.4695714601281202, "grad_norm": 0.04842245951294899, "learning_rate": 2.29335036751774e-05, "loss": 0.0019, "step": 8503 }, { "epoch": 0.469626684338414, "grad_norm": 4.116616249084473, "learning_rate": 2.2929965009029144e-05, "loss": 0.7249, "step": 8504 }, { "epoch": 0.4696819085487077, "grad_norm": 4.644250869750977, "learning_rate": 2.2926426249142973e-05, "loss": 1.4852, "step": 8505 }, { "epoch": 0.46973713275900153, "grad_norm": 1.5115324258804321, "learning_rate": 2.2922887395632086e-05, "loss": 0.0668, "step": 8506 }, { "epoch": 0.46979235696929533, "grad_norm": 0.2294551283121109, "learning_rate": 2.2919348448609713e-05, "loss": 0.0065, "step": 8507 }, { "epoch": 0.46984758117958914, "grad_norm": 0.6430019736289978, "learning_rate": 2.291580940818908e-05, "loss": 0.0243, "step": 8508 }, { "epoch": 0.46990280538988294, "grad_norm": 3.3037071228027344, "learning_rate": 2.291227027448339e-05, "loss": 0.3338, "step": 8509 }, { "epoch": 0.46995802960017674, "grad_norm": 0.28583768010139465, "learning_rate": 2.2908731047605892e-05, "loss": 0.0056, "step": 8510 }, { "epoch": 0.4700132538104705, "grad_norm": 6.876971244812012, "learning_rate": 2.29051917276698e-05, "loss": 1.581, "step": 8511 }, { "epoch": 0.4700684780207643, "grad_norm": 2.871135711669922, "learning_rate": 2.2901652314788363e-05, "loss": 0.7733, "step": 8512 }, { "epoch": 0.4701237022310581, "grad_norm": 2.951765775680542, "learning_rate": 2.2898112809074805e-05, "loss": 0.8875, "step": 8513 }, { "epoch": 0.4701789264413519, "grad_norm": 1.4536070823669434, "learning_rate": 2.2894573210642368e-05, "loss": 0.2283, "step": 8514 }, { "epoch": 0.4702341506516457, "grad_norm": 2.0063629150390625, "learning_rate": 2.2891033519604293e-05, "loss": 0.1084, "step": 8515 }, { "epoch": 0.4702893748619395, "grad_norm": 0.5336196422576904, "learning_rate": 2.2887493736073818e-05, "loss": 0.0174, "step": 8516 }, { "epoch": 0.47034459907223325, "grad_norm": 1.780857801437378, "learning_rate": 2.288395386016421e-05, "loss": 0.0663, "step": 8517 }, { "epoch": 0.47039982328252705, "grad_norm": 3.3540656566619873, "learning_rate": 2.28804138919887e-05, "loss": 0.1893, "step": 8518 }, { "epoch": 0.47045504749282085, "grad_norm": 4.743411064147949, "learning_rate": 2.287687383166055e-05, "loss": 0.6101, "step": 8519 }, { "epoch": 0.47051027170311466, "grad_norm": 0.1300073266029358, "learning_rate": 2.2873333679293017e-05, "loss": 0.0046, "step": 8520 }, { "epoch": 0.47056549591340846, "grad_norm": 0.23297344148159027, "learning_rate": 2.286979343499936e-05, "loss": 0.0068, "step": 8521 }, { "epoch": 0.4706207201237022, "grad_norm": 1.6716070175170898, "learning_rate": 2.286625309889284e-05, "loss": 0.0988, "step": 8522 }, { "epoch": 0.470675944333996, "grad_norm": 1.004004716873169, "learning_rate": 2.2862712671086725e-05, "loss": 0.0282, "step": 8523 }, { "epoch": 0.4707311685442898, "grad_norm": 1.8757836818695068, "learning_rate": 2.2859172151694276e-05, "loss": 0.1659, "step": 8524 }, { "epoch": 0.4707863927545836, "grad_norm": 0.09957161545753479, "learning_rate": 2.285563154082878e-05, "loss": 0.004, "step": 8525 }, { "epoch": 0.4708416169648774, "grad_norm": 1.9207395315170288, "learning_rate": 2.28520908386035e-05, "loss": 0.1221, "step": 8526 }, { "epoch": 0.4708968411751712, "grad_norm": 2.3386306762695312, "learning_rate": 2.2848550045131708e-05, "loss": 0.4773, "step": 8527 }, { "epoch": 0.47095206538546497, "grad_norm": 0.029780585318803787, "learning_rate": 2.2845009160526693e-05, "loss": 0.0009, "step": 8528 }, { "epoch": 0.47100728959575877, "grad_norm": 1.3207393884658813, "learning_rate": 2.2841468184901733e-05, "loss": 0.0335, "step": 8529 }, { "epoch": 0.4710625138060526, "grad_norm": 4.696089744567871, "learning_rate": 2.283792711837012e-05, "loss": 0.4946, "step": 8530 }, { "epoch": 0.4711177380163464, "grad_norm": 0.7101954221725464, "learning_rate": 2.2834385961045142e-05, "loss": 0.0305, "step": 8531 }, { "epoch": 0.4711729622266402, "grad_norm": 0.12397682666778564, "learning_rate": 2.2830844713040082e-05, "loss": 0.0036, "step": 8532 }, { "epoch": 0.4712281864369339, "grad_norm": 0.05615648627281189, "learning_rate": 2.2827303374468244e-05, "loss": 0.0019, "step": 8533 }, { "epoch": 0.47128341064722773, "grad_norm": 0.21332192420959473, "learning_rate": 2.2823761945442926e-05, "loss": 0.0075, "step": 8534 }, { "epoch": 0.47133863485752153, "grad_norm": 0.012959430925548077, "learning_rate": 2.2820220426077414e-05, "loss": 0.0003, "step": 8535 }, { "epoch": 0.47139385906781534, "grad_norm": 0.8350970149040222, "learning_rate": 2.2816678816485034e-05, "loss": 0.0349, "step": 8536 }, { "epoch": 0.47144908327810914, "grad_norm": 0.1064460501074791, "learning_rate": 2.281313711677907e-05, "loss": 0.0035, "step": 8537 }, { "epoch": 0.47150430748840294, "grad_norm": 2.831982135772705, "learning_rate": 2.2809595327072844e-05, "loss": 0.4111, "step": 8538 }, { "epoch": 0.4715595316986967, "grad_norm": 3.390068769454956, "learning_rate": 2.280605344747967e-05, "loss": 0.0444, "step": 8539 }, { "epoch": 0.4716147559089905, "grad_norm": 1.6793240308761597, "learning_rate": 2.280251147811285e-05, "loss": 0.3721, "step": 8540 }, { "epoch": 0.4716699801192843, "grad_norm": 5.2328715324401855, "learning_rate": 2.2798969419085714e-05, "loss": 0.6103, "step": 8541 }, { "epoch": 0.4717252043295781, "grad_norm": 6.389713287353516, "learning_rate": 2.2795427270511575e-05, "loss": 1.0614, "step": 8542 }, { "epoch": 0.4717804285398719, "grad_norm": 1.9679478406906128, "learning_rate": 2.279188503250376e-05, "loss": 0.0806, "step": 8543 }, { "epoch": 0.47183565275016565, "grad_norm": 0.04554694890975952, "learning_rate": 2.2788342705175598e-05, "loss": 0.0013, "step": 8544 }, { "epoch": 0.47189087696045945, "grad_norm": 1.5513137578964233, "learning_rate": 2.278480028864041e-05, "loss": 0.2674, "step": 8545 }, { "epoch": 0.47194610117075325, "grad_norm": 5.404987335205078, "learning_rate": 2.2781257783011538e-05, "loss": 1.1652, "step": 8546 }, { "epoch": 0.47200132538104705, "grad_norm": 2.4778473377227783, "learning_rate": 2.277771518840231e-05, "loss": 0.4673, "step": 8547 }, { "epoch": 0.47205654959134086, "grad_norm": 0.08314865082502365, "learning_rate": 2.2774172504926063e-05, "loss": 0.0032, "step": 8548 }, { "epoch": 0.47211177380163466, "grad_norm": 0.5862770080566406, "learning_rate": 2.2770629732696145e-05, "loss": 0.0152, "step": 8549 }, { "epoch": 0.4721669980119284, "grad_norm": 2.5385169982910156, "learning_rate": 2.2767086871825886e-05, "loss": 0.3176, "step": 8550 }, { "epoch": 0.4722222222222222, "grad_norm": 0.07401350885629654, "learning_rate": 2.2763543922428645e-05, "loss": 0.0022, "step": 8551 }, { "epoch": 0.472277446432516, "grad_norm": 3.2713801860809326, "learning_rate": 2.276000088461777e-05, "loss": 0.6006, "step": 8552 }, { "epoch": 0.4723326706428098, "grad_norm": 3.422762632369995, "learning_rate": 2.2756457758506604e-05, "loss": 0.6042, "step": 8553 }, { "epoch": 0.4723878948531036, "grad_norm": 2.895521640777588, "learning_rate": 2.2752914544208506e-05, "loss": 0.6223, "step": 8554 }, { "epoch": 0.4724431190633974, "grad_norm": 2.6564857959747314, "learning_rate": 2.274937124183684e-05, "loss": 0.3105, "step": 8555 }, { "epoch": 0.47249834327369117, "grad_norm": 3.0060369968414307, "learning_rate": 2.2745827851504955e-05, "loss": 0.2495, "step": 8556 }, { "epoch": 0.47255356748398497, "grad_norm": 0.2230546772480011, "learning_rate": 2.2742284373326228e-05, "loss": 0.0057, "step": 8557 }, { "epoch": 0.4726087916942788, "grad_norm": 2.68300461769104, "learning_rate": 2.2738740807414007e-05, "loss": 0.4774, "step": 8558 }, { "epoch": 0.4726640159045726, "grad_norm": 3.7160205841064453, "learning_rate": 2.273519715388168e-05, "loss": 0.851, "step": 8559 }, { "epoch": 0.4727192401148664, "grad_norm": 3.053812026977539, "learning_rate": 2.2731653412842604e-05, "loss": 0.1615, "step": 8560 }, { "epoch": 0.4727744643251601, "grad_norm": 2.2151806354522705, "learning_rate": 2.272810958441016e-05, "loss": 0.132, "step": 8561 }, { "epoch": 0.47282968853545393, "grad_norm": 4.651490211486816, "learning_rate": 2.2724565668697723e-05, "loss": 0.4378, "step": 8562 }, { "epoch": 0.47288491274574773, "grad_norm": 0.049180254340171814, "learning_rate": 2.2721021665818673e-05, "loss": 0.0014, "step": 8563 }, { "epoch": 0.47294013695604153, "grad_norm": 2.7496767044067383, "learning_rate": 2.2717477575886396e-05, "loss": 0.7621, "step": 8564 }, { "epoch": 0.47299536116633534, "grad_norm": 0.49369049072265625, "learning_rate": 2.2713933399014273e-05, "loss": 0.0144, "step": 8565 }, { "epoch": 0.47305058537662914, "grad_norm": 0.2071288675069809, "learning_rate": 2.271038913531569e-05, "loss": 0.0062, "step": 8566 }, { "epoch": 0.4731058095869229, "grad_norm": 1.8219170570373535, "learning_rate": 2.270684478490405e-05, "loss": 0.1955, "step": 8567 }, { "epoch": 0.4731610337972167, "grad_norm": 2.2165374755859375, "learning_rate": 2.270330034789274e-05, "loss": 0.3475, "step": 8568 }, { "epoch": 0.4732162580075105, "grad_norm": 0.16559366881847382, "learning_rate": 2.269975582439515e-05, "loss": 0.0069, "step": 8569 }, { "epoch": 0.4732714822178043, "grad_norm": 0.07997047156095505, "learning_rate": 2.2696211214524692e-05, "loss": 0.0022, "step": 8570 }, { "epoch": 0.4733267064280981, "grad_norm": 1.7778171300888062, "learning_rate": 2.269266651839475e-05, "loss": 0.2197, "step": 8571 }, { "epoch": 0.47338193063839185, "grad_norm": 0.387403279542923, "learning_rate": 2.268912173611875e-05, "loss": 0.012, "step": 8572 }, { "epoch": 0.47343715484868565, "grad_norm": 0.11775027960538864, "learning_rate": 2.2685576867810092e-05, "loss": 0.0038, "step": 8573 }, { "epoch": 0.47349237905897945, "grad_norm": 3.536358118057251, "learning_rate": 2.2682031913582177e-05, "loss": 1.0027, "step": 8574 }, { "epoch": 0.47354760326927325, "grad_norm": 7.1645026206970215, "learning_rate": 2.2678486873548438e-05, "loss": 1.152, "step": 8575 }, { "epoch": 0.47360282747956706, "grad_norm": 3.9445576667785645, "learning_rate": 2.2674941747822263e-05, "loss": 1.0919, "step": 8576 }, { "epoch": 0.47365805168986086, "grad_norm": 1.2523733377456665, "learning_rate": 2.2671396536517096e-05, "loss": 0.1109, "step": 8577 }, { "epoch": 0.4737132759001546, "grad_norm": 0.1874886304140091, "learning_rate": 2.266785123974635e-05, "loss": 0.0055, "step": 8578 }, { "epoch": 0.4737685001104484, "grad_norm": 0.4682249426841736, "learning_rate": 2.266430585762344e-05, "loss": 0.0157, "step": 8579 }, { "epoch": 0.4738237243207422, "grad_norm": 0.10381438583135605, "learning_rate": 2.2660760390261806e-05, "loss": 0.0028, "step": 8580 }, { "epoch": 0.473878948531036, "grad_norm": 1.049286127090454, "learning_rate": 2.265721483777487e-05, "loss": 0.0371, "step": 8581 }, { "epoch": 0.4739341727413298, "grad_norm": 0.1327543705701828, "learning_rate": 2.2653669200276066e-05, "loss": 0.0035, "step": 8582 }, { "epoch": 0.47398939695162357, "grad_norm": 0.10769354552030563, "learning_rate": 2.2650123477878833e-05, "loss": 0.0032, "step": 8583 }, { "epoch": 0.47404462116191737, "grad_norm": 0.5206279754638672, "learning_rate": 2.26465776706966e-05, "loss": 0.0164, "step": 8584 }, { "epoch": 0.47409984537221117, "grad_norm": 1.7132141590118408, "learning_rate": 2.2643031778842815e-05, "loss": 0.1539, "step": 8585 }, { "epoch": 0.474155069582505, "grad_norm": 0.2826087772846222, "learning_rate": 2.263948580243092e-05, "loss": 0.0116, "step": 8586 }, { "epoch": 0.4742102937927988, "grad_norm": 4.191715240478516, "learning_rate": 2.2635939741574358e-05, "loss": 0.7807, "step": 8587 }, { "epoch": 0.4742655180030926, "grad_norm": 0.15477848052978516, "learning_rate": 2.2632393596386585e-05, "loss": 0.0034, "step": 8588 }, { "epoch": 0.4743207422133863, "grad_norm": 0.2356322854757309, "learning_rate": 2.262884736698104e-05, "loss": 0.0049, "step": 8589 }, { "epoch": 0.47437596642368013, "grad_norm": 0.1752425581216812, "learning_rate": 2.2625301053471185e-05, "loss": 0.0052, "step": 8590 }, { "epoch": 0.47443119063397393, "grad_norm": 2.4993057250976562, "learning_rate": 2.262175465597048e-05, "loss": 0.3047, "step": 8591 }, { "epoch": 0.47448641484426773, "grad_norm": 3.0596561431884766, "learning_rate": 2.2618208174592374e-05, "loss": 0.6404, "step": 8592 }, { "epoch": 0.47454163905456154, "grad_norm": 0.24527521431446075, "learning_rate": 2.2614661609450345e-05, "loss": 0.0054, "step": 8593 }, { "epoch": 0.47459686326485534, "grad_norm": 2.808347463607788, "learning_rate": 2.261111496065784e-05, "loss": 0.3142, "step": 8594 }, { "epoch": 0.4746520874751491, "grad_norm": 0.11395355314016342, "learning_rate": 2.260756822832833e-05, "loss": 0.0052, "step": 8595 }, { "epoch": 0.4747073116854429, "grad_norm": 0.021637219935655594, "learning_rate": 2.2604021412575295e-05, "loss": 0.0008, "step": 8596 }, { "epoch": 0.4747625358957367, "grad_norm": 2.624561071395874, "learning_rate": 2.26004745135122e-05, "loss": 0.5049, "step": 8597 }, { "epoch": 0.4748177601060305, "grad_norm": 0.008107629604637623, "learning_rate": 2.259692753125252e-05, "loss": 0.0003, "step": 8598 }, { "epoch": 0.4748729843163243, "grad_norm": 0.02496729977428913, "learning_rate": 2.259338046590974e-05, "loss": 0.001, "step": 8599 }, { "epoch": 0.47492820852661805, "grad_norm": 0.015422398224473, "learning_rate": 2.258983331759733e-05, "loss": 0.0005, "step": 8600 }, { "epoch": 0.47498343273691185, "grad_norm": 2.9380710124969482, "learning_rate": 2.2586286086428785e-05, "loss": 0.1356, "step": 8601 }, { "epoch": 0.47503865694720565, "grad_norm": 0.06625043600797653, "learning_rate": 2.2582738772517576e-05, "loss": 0.0023, "step": 8602 }, { "epoch": 0.47509388115749945, "grad_norm": 3.0991761684417725, "learning_rate": 2.257919137597721e-05, "loss": 0.4329, "step": 8603 }, { "epoch": 0.47514910536779326, "grad_norm": 2.361534357070923, "learning_rate": 2.2575643896921167e-05, "loss": 0.2054, "step": 8604 }, { "epoch": 0.47520432957808706, "grad_norm": 0.38821515440940857, "learning_rate": 2.2572096335462943e-05, "loss": 0.0092, "step": 8605 }, { "epoch": 0.4752595537883808, "grad_norm": 0.1351403445005417, "learning_rate": 2.2568548691716033e-05, "loss": 0.0041, "step": 8606 }, { "epoch": 0.4753147779986746, "grad_norm": 2.2430081367492676, "learning_rate": 2.2565000965793944e-05, "loss": 0.0372, "step": 8607 }, { "epoch": 0.4753700022089684, "grad_norm": 1.178849220275879, "learning_rate": 2.2561453157810162e-05, "loss": 0.0384, "step": 8608 }, { "epoch": 0.4754252264192622, "grad_norm": 3.3214681148529053, "learning_rate": 2.2557905267878208e-05, "loss": 0.412, "step": 8609 }, { "epoch": 0.475480450629556, "grad_norm": 2.319782257080078, "learning_rate": 2.2554357296111583e-05, "loss": 0.4069, "step": 8610 }, { "epoch": 0.47553567483984976, "grad_norm": 0.03302396461367607, "learning_rate": 2.255080924262379e-05, "loss": 0.0013, "step": 8611 }, { "epoch": 0.47559089905014357, "grad_norm": 2.050508499145508, "learning_rate": 2.2547261107528356e-05, "loss": 0.1745, "step": 8612 }, { "epoch": 0.47564612326043737, "grad_norm": 5.243863582611084, "learning_rate": 2.2543712890938783e-05, "loss": 1.326, "step": 8613 }, { "epoch": 0.4757013474707312, "grad_norm": 0.3834501802921295, "learning_rate": 2.2540164592968596e-05, "loss": 0.0118, "step": 8614 }, { "epoch": 0.475756571681025, "grad_norm": 0.4100245535373688, "learning_rate": 2.253661621373131e-05, "loss": 0.0127, "step": 8615 }, { "epoch": 0.4758117958913188, "grad_norm": 2.9247570037841797, "learning_rate": 2.2533067753340447e-05, "loss": 0.0659, "step": 8616 }, { "epoch": 0.4758670201016125, "grad_norm": 2.2590551376342773, "learning_rate": 2.2529519211909538e-05, "loss": 0.0241, "step": 8617 }, { "epoch": 0.47592224431190633, "grad_norm": 2.4285707473754883, "learning_rate": 2.2525970589552104e-05, "loss": 0.169, "step": 8618 }, { "epoch": 0.47597746852220013, "grad_norm": 0.9386616349220276, "learning_rate": 2.2522421886381687e-05, "loss": 0.0246, "step": 8619 }, { "epoch": 0.47603269273249393, "grad_norm": 1.8204984664916992, "learning_rate": 2.251887310251181e-05, "loss": 0.0897, "step": 8620 }, { "epoch": 0.47608791694278774, "grad_norm": 0.03155268356204033, "learning_rate": 2.2515324238056008e-05, "loss": 0.0012, "step": 8621 }, { "epoch": 0.4761431411530815, "grad_norm": 6.135777950286865, "learning_rate": 2.251177529312783e-05, "loss": 0.9704, "step": 8622 }, { "epoch": 0.4761983653633753, "grad_norm": 0.522752583026886, "learning_rate": 2.2508226267840803e-05, "loss": 0.014, "step": 8623 }, { "epoch": 0.4762535895736691, "grad_norm": 0.26804766058921814, "learning_rate": 2.2504677162308476e-05, "loss": 0.0075, "step": 8624 }, { "epoch": 0.4763088137839629, "grad_norm": 0.06042558327317238, "learning_rate": 2.2501127976644405e-05, "loss": 0.0019, "step": 8625 }, { "epoch": 0.4763640379942567, "grad_norm": 1.367197871208191, "learning_rate": 2.249757871096212e-05, "loss": 0.0825, "step": 8626 }, { "epoch": 0.4764192622045505, "grad_norm": 2.671762466430664, "learning_rate": 2.2494029365375188e-05, "loss": 0.1194, "step": 8627 }, { "epoch": 0.47647448641484424, "grad_norm": 1.6918456554412842, "learning_rate": 2.2490479939997158e-05, "loss": 0.2058, "step": 8628 }, { "epoch": 0.47652971062513805, "grad_norm": 0.20581696927547455, "learning_rate": 2.2486930434941578e-05, "loss": 0.0058, "step": 8629 }, { "epoch": 0.47658493483543185, "grad_norm": 4.162893772125244, "learning_rate": 2.2483380850322014e-05, "loss": 1.0878, "step": 8630 }, { "epoch": 0.47664015904572565, "grad_norm": 0.38727089762687683, "learning_rate": 2.2479831186252028e-05, "loss": 0.006, "step": 8631 }, { "epoch": 0.47669538325601946, "grad_norm": 4.19456148147583, "learning_rate": 2.2476281442845184e-05, "loss": 0.6324, "step": 8632 }, { "epoch": 0.47675060746631326, "grad_norm": 2.011216402053833, "learning_rate": 2.247273162021505e-05, "loss": 0.0481, "step": 8633 }, { "epoch": 0.476805831676607, "grad_norm": 0.08313116431236267, "learning_rate": 2.2469181718475185e-05, "loss": 0.0024, "step": 8634 }, { "epoch": 0.4768610558869008, "grad_norm": 3.330205202102661, "learning_rate": 2.2465631737739177e-05, "loss": 0.7563, "step": 8635 }, { "epoch": 0.4769162800971946, "grad_norm": 3.3374452590942383, "learning_rate": 2.2462081678120586e-05, "loss": 0.328, "step": 8636 }, { "epoch": 0.4769715043074884, "grad_norm": 5.263863563537598, "learning_rate": 2.2458531539732992e-05, "loss": 0.1209, "step": 8637 }, { "epoch": 0.4770267285177822, "grad_norm": 0.10827223211526871, "learning_rate": 2.2454981322689974e-05, "loss": 0.0032, "step": 8638 }, { "epoch": 0.47708195272807596, "grad_norm": 1.4298508167266846, "learning_rate": 2.245143102710511e-05, "loss": 0.0281, "step": 8639 }, { "epoch": 0.47713717693836977, "grad_norm": 1.0203320980072021, "learning_rate": 2.2447880653092e-05, "loss": 0.024, "step": 8640 }, { "epoch": 0.47719240114866357, "grad_norm": 0.11420068144798279, "learning_rate": 2.2444330200764207e-05, "loss": 0.0043, "step": 8641 }, { "epoch": 0.4772476253589574, "grad_norm": 2.0153422355651855, "learning_rate": 2.2440779670235338e-05, "loss": 0.2188, "step": 8642 }, { "epoch": 0.4773028495692512, "grad_norm": 0.20701345801353455, "learning_rate": 2.2437229061618982e-05, "loss": 0.008, "step": 8643 }, { "epoch": 0.477358073779545, "grad_norm": 0.31571340560913086, "learning_rate": 2.243367837502872e-05, "loss": 0.0085, "step": 8644 }, { "epoch": 0.4774132979898387, "grad_norm": 0.017189456149935722, "learning_rate": 2.243012761057817e-05, "loss": 0.0007, "step": 8645 }, { "epoch": 0.47746852220013253, "grad_norm": 2.8615176677703857, "learning_rate": 2.2426576768380914e-05, "loss": 0.4177, "step": 8646 }, { "epoch": 0.47752374641042633, "grad_norm": 2.3406407833099365, "learning_rate": 2.2423025848550553e-05, "loss": 0.6532, "step": 8647 }, { "epoch": 0.47757897062072013, "grad_norm": 0.044085629284381866, "learning_rate": 2.2419474851200705e-05, "loss": 0.001, "step": 8648 }, { "epoch": 0.47763419483101394, "grad_norm": 0.07473278790712357, "learning_rate": 2.2415923776444965e-05, "loss": 0.002, "step": 8649 }, { "epoch": 0.4776894190413077, "grad_norm": 3.3540966510772705, "learning_rate": 2.241237262439695e-05, "loss": 0.2632, "step": 8650 }, { "epoch": 0.4777446432516015, "grad_norm": 0.10986899584531784, "learning_rate": 2.2408821395170267e-05, "loss": 0.0035, "step": 8651 }, { "epoch": 0.4777998674618953, "grad_norm": 2.1401724815368652, "learning_rate": 2.2405270088878522e-05, "loss": 0.029, "step": 8652 }, { "epoch": 0.4778550916721891, "grad_norm": 0.7596088647842407, "learning_rate": 2.2401718705635344e-05, "loss": 0.0259, "step": 8653 }, { "epoch": 0.4779103158824829, "grad_norm": 3.1203579902648926, "learning_rate": 2.239816724555435e-05, "loss": 0.1879, "step": 8654 }, { "epoch": 0.4779655400927767, "grad_norm": 1.2226626873016357, "learning_rate": 2.2394615708749155e-05, "loss": 0.0514, "step": 8655 }, { "epoch": 0.47802076430307044, "grad_norm": 0.07935573905706406, "learning_rate": 2.239106409533339e-05, "loss": 0.0026, "step": 8656 }, { "epoch": 0.47807598851336425, "grad_norm": 0.3086780607700348, "learning_rate": 2.238751240542067e-05, "loss": 0.0106, "step": 8657 }, { "epoch": 0.47813121272365805, "grad_norm": 2.2577364444732666, "learning_rate": 2.2383960639124636e-05, "loss": 0.2967, "step": 8658 }, { "epoch": 0.47818643693395185, "grad_norm": 1.6589182615280151, "learning_rate": 2.238040879655892e-05, "loss": 0.1372, "step": 8659 }, { "epoch": 0.47824166114424566, "grad_norm": 0.5408404469490051, "learning_rate": 2.2376856877837142e-05, "loss": 0.0173, "step": 8660 }, { "epoch": 0.4782968853545394, "grad_norm": 3.8178606033325195, "learning_rate": 2.2373304883072948e-05, "loss": 0.1522, "step": 8661 }, { "epoch": 0.4783521095648332, "grad_norm": 1.9958635568618774, "learning_rate": 2.236975281237997e-05, "loss": 0.0681, "step": 8662 }, { "epoch": 0.478407333775127, "grad_norm": 1.026406168937683, "learning_rate": 2.236620066587186e-05, "loss": 0.0314, "step": 8663 }, { "epoch": 0.4784625579854208, "grad_norm": 1.120342493057251, "learning_rate": 2.2362648443662254e-05, "loss": 0.0261, "step": 8664 }, { "epoch": 0.4785177821957146, "grad_norm": 2.9298877716064453, "learning_rate": 2.2359096145864796e-05, "loss": 0.9076, "step": 8665 }, { "epoch": 0.4785730064060084, "grad_norm": 0.18485328555107117, "learning_rate": 2.2355543772593138e-05, "loss": 0.0096, "step": 8666 }, { "epoch": 0.47862823061630216, "grad_norm": 1.7702556848526, "learning_rate": 2.2351991323960928e-05, "loss": 0.115, "step": 8667 }, { "epoch": 0.47868345482659597, "grad_norm": 0.46916624903678894, "learning_rate": 2.2348438800081818e-05, "loss": 0.0094, "step": 8668 }, { "epoch": 0.47873867903688977, "grad_norm": 0.03092360496520996, "learning_rate": 2.2344886201069466e-05, "loss": 0.0007, "step": 8669 }, { "epoch": 0.47879390324718357, "grad_norm": 0.08824785053730011, "learning_rate": 2.2341333527037526e-05, "loss": 0.0033, "step": 8670 }, { "epoch": 0.4788491274574774, "grad_norm": 1.9746572971343994, "learning_rate": 2.2337780778099668e-05, "loss": 0.4003, "step": 8671 }, { "epoch": 0.4789043516677712, "grad_norm": 0.12094812840223312, "learning_rate": 2.2334227954369543e-05, "loss": 0.005, "step": 8672 }, { "epoch": 0.4789595758780649, "grad_norm": 4.826447486877441, "learning_rate": 2.233067505596082e-05, "loss": 0.7476, "step": 8673 }, { "epoch": 0.4790148000883587, "grad_norm": 0.06179022416472435, "learning_rate": 2.232712208298717e-05, "loss": 0.0016, "step": 8674 }, { "epoch": 0.47907002429865253, "grad_norm": 2.992438316345215, "learning_rate": 2.2323569035562258e-05, "loss": 0.3876, "step": 8675 }, { "epoch": 0.47912524850894633, "grad_norm": 0.01267168577760458, "learning_rate": 2.2320015913799754e-05, "loss": 0.0005, "step": 8676 }, { "epoch": 0.47918047271924014, "grad_norm": 3.510117292404175, "learning_rate": 2.231646271781334e-05, "loss": 0.6473, "step": 8677 }, { "epoch": 0.4792356969295339, "grad_norm": 3.722630739212036, "learning_rate": 2.2312909447716685e-05, "loss": 0.6737, "step": 8678 }, { "epoch": 0.4792909211398277, "grad_norm": 0.19419147074222565, "learning_rate": 2.2309356103623476e-05, "loss": 0.0065, "step": 8679 }, { "epoch": 0.4793461453501215, "grad_norm": 3.535554885864258, "learning_rate": 2.2305802685647392e-05, "loss": 0.6787, "step": 8680 }, { "epoch": 0.4794013695604153, "grad_norm": 2.92795991897583, "learning_rate": 2.230224919390211e-05, "loss": 0.0631, "step": 8681 }, { "epoch": 0.4794565937707091, "grad_norm": 0.0179258044809103, "learning_rate": 2.2298695628501327e-05, "loss": 0.0007, "step": 8682 }, { "epoch": 0.4795118179810029, "grad_norm": 1.786958932876587, "learning_rate": 2.2295141989558727e-05, "loss": 0.0923, "step": 8683 }, { "epoch": 0.47956704219129664, "grad_norm": 0.762283205986023, "learning_rate": 2.2291588277187997e-05, "loss": 0.0139, "step": 8684 }, { "epoch": 0.47962226640159045, "grad_norm": 3.3150618076324463, "learning_rate": 2.228803449150284e-05, "loss": 0.2772, "step": 8685 }, { "epoch": 0.47967749061188425, "grad_norm": 0.3922604024410248, "learning_rate": 2.228448063261694e-05, "loss": 0.0047, "step": 8686 }, { "epoch": 0.47973271482217805, "grad_norm": 3.7328453063964844, "learning_rate": 2.2280926700644007e-05, "loss": 0.5341, "step": 8687 }, { "epoch": 0.47978793903247186, "grad_norm": 0.01865242049098015, "learning_rate": 2.2277372695697732e-05, "loss": 0.0005, "step": 8688 }, { "epoch": 0.4798431632427656, "grad_norm": 0.2103108912706375, "learning_rate": 2.2273818617891818e-05, "loss": 0.0073, "step": 8689 }, { "epoch": 0.4798983874530594, "grad_norm": 1.1931376457214355, "learning_rate": 2.227026446733998e-05, "loss": 0.0357, "step": 8690 }, { "epoch": 0.4799536116633532, "grad_norm": 3.933683395385742, "learning_rate": 2.226671024415591e-05, "loss": 0.2206, "step": 8691 }, { "epoch": 0.480008835873647, "grad_norm": 0.11928773671388626, "learning_rate": 2.2263155948453332e-05, "loss": 0.0039, "step": 8692 }, { "epoch": 0.4800640600839408, "grad_norm": 0.12761269509792328, "learning_rate": 2.225960158034595e-05, "loss": 0.0061, "step": 8693 }, { "epoch": 0.4801192842942346, "grad_norm": 1.4293622970581055, "learning_rate": 2.2256047139947482e-05, "loss": 0.1164, "step": 8694 }, { "epoch": 0.48017450850452836, "grad_norm": 1.8535054922103882, "learning_rate": 2.2252492627371648e-05, "loss": 0.0583, "step": 8695 }, { "epoch": 0.48022973271482217, "grad_norm": 1.2581285238265991, "learning_rate": 2.2248938042732155e-05, "loss": 0.1959, "step": 8696 }, { "epoch": 0.48028495692511597, "grad_norm": 0.87533038854599, "learning_rate": 2.2245383386142736e-05, "loss": 0.0232, "step": 8697 }, { "epoch": 0.48034018113540977, "grad_norm": 0.02413412183523178, "learning_rate": 2.2241828657717107e-05, "loss": 0.0009, "step": 8698 }, { "epoch": 0.4803954053457036, "grad_norm": 0.11974643915891647, "learning_rate": 2.2238273857569e-05, "loss": 0.0027, "step": 8699 }, { "epoch": 0.4804506295559973, "grad_norm": 2.3177080154418945, "learning_rate": 2.2234718985812135e-05, "loss": 0.2851, "step": 8700 }, { "epoch": 0.4805058537662911, "grad_norm": 0.01732851378619671, "learning_rate": 2.223116404256025e-05, "loss": 0.0006, "step": 8701 }, { "epoch": 0.4805610779765849, "grad_norm": 0.03527909144759178, "learning_rate": 2.222760902792708e-05, "loss": 0.001, "step": 8702 }, { "epoch": 0.48061630218687873, "grad_norm": 0.21581579744815826, "learning_rate": 2.2224053942026355e-05, "loss": 0.0096, "step": 8703 }, { "epoch": 0.48067152639717253, "grad_norm": 2.61055850982666, "learning_rate": 2.22204987849718e-05, "loss": 0.2594, "step": 8704 }, { "epoch": 0.48072675060746634, "grad_norm": 4.545163154602051, "learning_rate": 2.2216943556877185e-05, "loss": 1.4528, "step": 8705 }, { "epoch": 0.4807819748177601, "grad_norm": 5.006511211395264, "learning_rate": 2.2213388257856227e-05, "loss": 0.8675, "step": 8706 }, { "epoch": 0.4808371990280539, "grad_norm": 0.14389270544052124, "learning_rate": 2.220983288802267e-05, "loss": 0.0037, "step": 8707 }, { "epoch": 0.4808924232383477, "grad_norm": 3.3238608837127686, "learning_rate": 2.220627744749028e-05, "loss": 0.3202, "step": 8708 }, { "epoch": 0.4809476474486415, "grad_norm": 2.788809299468994, "learning_rate": 2.2202721936372783e-05, "loss": 0.3362, "step": 8709 }, { "epoch": 0.4810028716589353, "grad_norm": 0.2146395593881607, "learning_rate": 2.219916635478395e-05, "loss": 0.0083, "step": 8710 }, { "epoch": 0.4810580958692291, "grad_norm": 0.9466462731361389, "learning_rate": 2.219561070283752e-05, "loss": 0.348, "step": 8711 }, { "epoch": 0.48111332007952284, "grad_norm": 0.5349332690238953, "learning_rate": 2.219205498064725e-05, "loss": 0.028, "step": 8712 }, { "epoch": 0.48116854428981665, "grad_norm": 0.026298068463802338, "learning_rate": 2.2188499188326907e-05, "loss": 0.0009, "step": 8713 }, { "epoch": 0.48122376850011045, "grad_norm": 3.0905416011810303, "learning_rate": 2.2184943325990238e-05, "loss": 0.2146, "step": 8714 }, { "epoch": 0.48127899271040425, "grad_norm": 0.015444961376488209, "learning_rate": 2.2181387393751016e-05, "loss": 0.0006, "step": 8715 }, { "epoch": 0.48133421692069805, "grad_norm": 3.088791608810425, "learning_rate": 2.2177831391722998e-05, "loss": 0.4285, "step": 8716 }, { "epoch": 0.4813894411309918, "grad_norm": 0.033357471227645874, "learning_rate": 2.2174275320019954e-05, "loss": 0.0011, "step": 8717 }, { "epoch": 0.4814446653412856, "grad_norm": 3.8370015621185303, "learning_rate": 2.2170719178755658e-05, "loss": 0.6004, "step": 8718 }, { "epoch": 0.4814998895515794, "grad_norm": 0.7844743728637695, "learning_rate": 2.2167162968043875e-05, "loss": 0.0288, "step": 8719 }, { "epoch": 0.4815551137618732, "grad_norm": 0.2263554483652115, "learning_rate": 2.216360668799837e-05, "loss": 0.0104, "step": 8720 }, { "epoch": 0.481610337972167, "grad_norm": 3.0917272567749023, "learning_rate": 2.2160050338732936e-05, "loss": 0.5205, "step": 8721 }, { "epoch": 0.4816655621824608, "grad_norm": 0.8355414867401123, "learning_rate": 2.215649392036134e-05, "loss": 0.0321, "step": 8722 }, { "epoch": 0.48172078639275456, "grad_norm": 0.043481823056936264, "learning_rate": 2.215293743299736e-05, "loss": 0.0009, "step": 8723 }, { "epoch": 0.48177601060304837, "grad_norm": 0.35689815878868103, "learning_rate": 2.214938087675479e-05, "loss": 0.0105, "step": 8724 }, { "epoch": 0.48183123481334217, "grad_norm": 0.9337871670722961, "learning_rate": 2.21458242517474e-05, "loss": 0.0388, "step": 8725 }, { "epoch": 0.48188645902363597, "grad_norm": 0.9080949425697327, "learning_rate": 2.2142267558088992e-05, "loss": 0.029, "step": 8726 }, { "epoch": 0.4819416832339298, "grad_norm": 4.134309768676758, "learning_rate": 2.2138710795893343e-05, "loss": 0.7592, "step": 8727 }, { "epoch": 0.4819969074442235, "grad_norm": 3.7682714462280273, "learning_rate": 2.213515396527424e-05, "loss": 0.1937, "step": 8728 }, { "epoch": 0.4820521316545173, "grad_norm": 2.8322761058807373, "learning_rate": 2.213159706634549e-05, "loss": 0.1823, "step": 8729 }, { "epoch": 0.4821073558648111, "grad_norm": 2.2965216636657715, "learning_rate": 2.2128040099220875e-05, "loss": 0.4218, "step": 8730 }, { "epoch": 0.48216258007510493, "grad_norm": 0.07686197757720947, "learning_rate": 2.2124483064014205e-05, "loss": 0.0019, "step": 8731 }, { "epoch": 0.48221780428539873, "grad_norm": 4.3511271476745605, "learning_rate": 2.2120925960839276e-05, "loss": 1.1619, "step": 8732 }, { "epoch": 0.48227302849569254, "grad_norm": 1.5863909721374512, "learning_rate": 2.211736878980988e-05, "loss": 0.0656, "step": 8733 }, { "epoch": 0.4823282527059863, "grad_norm": 0.6728030443191528, "learning_rate": 2.211381155103983e-05, "loss": 0.0176, "step": 8734 }, { "epoch": 0.4823834769162801, "grad_norm": 4.502435684204102, "learning_rate": 2.2110254244642934e-05, "loss": 0.9292, "step": 8735 }, { "epoch": 0.4824387011265739, "grad_norm": 0.30975842475891113, "learning_rate": 2.2106696870732996e-05, "loss": 0.0084, "step": 8736 }, { "epoch": 0.4824939253368677, "grad_norm": 3.804206609725952, "learning_rate": 2.210313942942383e-05, "loss": 0.2191, "step": 8737 }, { "epoch": 0.4825491495471615, "grad_norm": 0.024685971438884735, "learning_rate": 2.2099581920829238e-05, "loss": 0.0006, "step": 8738 }, { "epoch": 0.4826043737574553, "grad_norm": 2.2641940116882324, "learning_rate": 2.209602434506305e-05, "loss": 0.3139, "step": 8739 }, { "epoch": 0.48265959796774904, "grad_norm": 1.1819119453430176, "learning_rate": 2.2092466702239075e-05, "loss": 0.1094, "step": 8740 }, { "epoch": 0.48271482217804285, "grad_norm": 3.2398734092712402, "learning_rate": 2.2088908992471133e-05, "loss": 0.1497, "step": 8741 }, { "epoch": 0.48277004638833665, "grad_norm": 0.41107916831970215, "learning_rate": 2.2085351215873048e-05, "loss": 0.012, "step": 8742 }, { "epoch": 0.48282527059863045, "grad_norm": 2.5077579021453857, "learning_rate": 2.2081793372558636e-05, "loss": 0.6637, "step": 8743 }, { "epoch": 0.48288049480892425, "grad_norm": 0.04174714908003807, "learning_rate": 2.207823546264173e-05, "loss": 0.0015, "step": 8744 }, { "epoch": 0.482935719019218, "grad_norm": 0.22836381196975708, "learning_rate": 2.2074677486236154e-05, "loss": 0.007, "step": 8745 }, { "epoch": 0.4829909432295118, "grad_norm": 1.9572516679763794, "learning_rate": 2.207111944345574e-05, "loss": 0.1623, "step": 8746 }, { "epoch": 0.4830461674398056, "grad_norm": 0.04917142912745476, "learning_rate": 2.206756133441432e-05, "loss": 0.0012, "step": 8747 }, { "epoch": 0.4831013916500994, "grad_norm": 1.8809791803359985, "learning_rate": 2.2064003159225727e-05, "loss": 0.2419, "step": 8748 }, { "epoch": 0.4831566158603932, "grad_norm": 0.03614427149295807, "learning_rate": 2.206044491800379e-05, "loss": 0.0015, "step": 8749 }, { "epoch": 0.483211840070687, "grad_norm": 0.1036403477191925, "learning_rate": 2.205688661086236e-05, "loss": 0.0025, "step": 8750 }, { "epoch": 0.48326706428098076, "grad_norm": 1.3225802183151245, "learning_rate": 2.205332823791527e-05, "loss": 0.0672, "step": 8751 }, { "epoch": 0.48332228849127457, "grad_norm": 0.13288654386997223, "learning_rate": 2.2049769799276368e-05, "loss": 0.0048, "step": 8752 }, { "epoch": 0.48337751270156837, "grad_norm": 2.3691205978393555, "learning_rate": 2.204621129505949e-05, "loss": 0.0911, "step": 8753 }, { "epoch": 0.48343273691186217, "grad_norm": 0.025305958464741707, "learning_rate": 2.2042652725378488e-05, "loss": 0.0009, "step": 8754 }, { "epoch": 0.483487961122156, "grad_norm": 3.5221498012542725, "learning_rate": 2.2039094090347218e-05, "loss": 0.2289, "step": 8755 }, { "epoch": 0.4835431853324497, "grad_norm": 1.3301331996917725, "learning_rate": 2.2035535390079518e-05, "loss": 0.0399, "step": 8756 }, { "epoch": 0.4835984095427435, "grad_norm": 3.1092963218688965, "learning_rate": 2.203197662468924e-05, "loss": 0.226, "step": 8757 }, { "epoch": 0.4836536337530373, "grad_norm": 0.06542469561100006, "learning_rate": 2.2028417794290253e-05, "loss": 0.0016, "step": 8758 }, { "epoch": 0.48370885796333113, "grad_norm": 0.03891023248434067, "learning_rate": 2.20248588989964e-05, "loss": 0.0015, "step": 8759 }, { "epoch": 0.48376408217362493, "grad_norm": 0.3816145956516266, "learning_rate": 2.202129993892155e-05, "loss": 0.0094, "step": 8760 }, { "epoch": 0.48381930638391873, "grad_norm": 0.11941699683666229, "learning_rate": 2.2017740914179557e-05, "loss": 0.0034, "step": 8761 }, { "epoch": 0.4838745305942125, "grad_norm": 4.7213134765625, "learning_rate": 2.2014181824884294e-05, "loss": 0.5817, "step": 8762 }, { "epoch": 0.4839297548045063, "grad_norm": 0.038641683757305145, "learning_rate": 2.2010622671149618e-05, "loss": 0.0014, "step": 8763 }, { "epoch": 0.4839849790148001, "grad_norm": 2.2940220832824707, "learning_rate": 2.2007063453089393e-05, "loss": 0.1904, "step": 8764 }, { "epoch": 0.4840402032250939, "grad_norm": 1.001678466796875, "learning_rate": 2.20035041708175e-05, "loss": 0.0295, "step": 8765 }, { "epoch": 0.4840954274353877, "grad_norm": 0.41774365305900574, "learning_rate": 2.1999944824447806e-05, "loss": 0.0046, "step": 8766 }, { "epoch": 0.48415065164568144, "grad_norm": 2.7599027156829834, "learning_rate": 2.1996385414094178e-05, "loss": 0.0565, "step": 8767 }, { "epoch": 0.48420587585597524, "grad_norm": 0.40635621547698975, "learning_rate": 2.19928259398705e-05, "loss": 0.0118, "step": 8768 }, { "epoch": 0.48426110006626905, "grad_norm": 4.044520854949951, "learning_rate": 2.198926640189064e-05, "loss": 0.5653, "step": 8769 }, { "epoch": 0.48431632427656285, "grad_norm": 2.830735206604004, "learning_rate": 2.1985706800268497e-05, "loss": 0.3129, "step": 8770 }, { "epoch": 0.48437154848685665, "grad_norm": 0.058662738651037216, "learning_rate": 2.198214713511794e-05, "loss": 0.0022, "step": 8771 }, { "epoch": 0.48442677269715045, "grad_norm": 6.204972267150879, "learning_rate": 2.1978587406552844e-05, "loss": 0.2998, "step": 8772 }, { "epoch": 0.4844819969074442, "grad_norm": 0.6578923463821411, "learning_rate": 2.197502761468711e-05, "loss": 0.013, "step": 8773 }, { "epoch": 0.484537221117738, "grad_norm": 1.4301725625991821, "learning_rate": 2.197146775963462e-05, "loss": 0.0516, "step": 8774 }, { "epoch": 0.4845924453280318, "grad_norm": 0.13798542320728302, "learning_rate": 2.196790784150926e-05, "loss": 0.0054, "step": 8775 }, { "epoch": 0.4846476695383256, "grad_norm": 3.5181028842926025, "learning_rate": 2.1964347860424925e-05, "loss": 0.9751, "step": 8776 }, { "epoch": 0.4847028937486194, "grad_norm": 2.9937589168548584, "learning_rate": 2.1960787816495515e-05, "loss": 0.2893, "step": 8777 }, { "epoch": 0.4847581179589132, "grad_norm": 2.068751573562622, "learning_rate": 2.195722770983492e-05, "loss": 0.4633, "step": 8778 }, { "epoch": 0.48481334216920696, "grad_norm": 3.1341710090637207, "learning_rate": 2.195366754055704e-05, "loss": 0.9236, "step": 8779 }, { "epoch": 0.48486856637950076, "grad_norm": 2.124068260192871, "learning_rate": 2.1950107308775762e-05, "loss": 0.6468, "step": 8780 }, { "epoch": 0.48492379058979457, "grad_norm": 2.6899895668029785, "learning_rate": 2.194654701460501e-05, "loss": 0.4701, "step": 8781 }, { "epoch": 0.48497901480008837, "grad_norm": 0.02446467988193035, "learning_rate": 2.1942986658158672e-05, "loss": 0.0009, "step": 8782 }, { "epoch": 0.4850342390103822, "grad_norm": 2.4424619674682617, "learning_rate": 2.193942623955066e-05, "loss": 0.3579, "step": 8783 }, { "epoch": 0.4850894632206759, "grad_norm": 1.680717945098877, "learning_rate": 2.193586575889489e-05, "loss": 0.5205, "step": 8784 }, { "epoch": 0.4851446874309697, "grad_norm": 0.2771156132221222, "learning_rate": 2.1932305216305256e-05, "loss": 0.0076, "step": 8785 }, { "epoch": 0.4851999116412635, "grad_norm": 0.022818557918071747, "learning_rate": 2.192874461189568e-05, "loss": 0.0006, "step": 8786 }, { "epoch": 0.48525513585155733, "grad_norm": 0.486862450838089, "learning_rate": 2.192518394578007e-05, "loss": 0.0173, "step": 8787 }, { "epoch": 0.48531036006185113, "grad_norm": 5.001492023468018, "learning_rate": 2.1921623218072346e-05, "loss": 0.6322, "step": 8788 }, { "epoch": 0.48536558427214493, "grad_norm": 4.904816627502441, "learning_rate": 2.1918062428886424e-05, "loss": 0.2116, "step": 8789 }, { "epoch": 0.4854208084824387, "grad_norm": 0.1884671300649643, "learning_rate": 2.1914501578336225e-05, "loss": 0.0069, "step": 8790 }, { "epoch": 0.4854760326927325, "grad_norm": 1.9707854986190796, "learning_rate": 2.191094066653567e-05, "loss": 0.7899, "step": 8791 }, { "epoch": 0.4855312569030263, "grad_norm": 0.590287983417511, "learning_rate": 2.1907379693598684e-05, "loss": 0.0162, "step": 8792 }, { "epoch": 0.4855864811133201, "grad_norm": 1.505282998085022, "learning_rate": 2.1903818659639187e-05, "loss": 0.0548, "step": 8793 }, { "epoch": 0.4856417053236139, "grad_norm": 4.3258867263793945, "learning_rate": 2.1900257564771117e-05, "loss": 1.0355, "step": 8794 }, { "epoch": 0.48569692953390764, "grad_norm": 0.06857473403215408, "learning_rate": 2.1896696409108395e-05, "loss": 0.0019, "step": 8795 }, { "epoch": 0.48575215374420144, "grad_norm": 1.2154186964035034, "learning_rate": 2.1893135192764957e-05, "loss": 0.0234, "step": 8796 }, { "epoch": 0.48580737795449525, "grad_norm": 4.350090503692627, "learning_rate": 2.1889573915854734e-05, "loss": 0.3015, "step": 8797 }, { "epoch": 0.48586260216478905, "grad_norm": 3.4105043411254883, "learning_rate": 2.188601257849166e-05, "loss": 0.2413, "step": 8798 }, { "epoch": 0.48591782637508285, "grad_norm": 2.0015218257904053, "learning_rate": 2.1882451180789674e-05, "loss": 0.7278, "step": 8799 }, { "epoch": 0.48597305058537665, "grad_norm": 2.9269189834594727, "learning_rate": 2.1878889722862723e-05, "loss": 0.0525, "step": 8800 }, { "epoch": 0.4860282747956704, "grad_norm": 4.201211452484131, "learning_rate": 2.1875328204824727e-05, "loss": 0.4413, "step": 8801 }, { "epoch": 0.4860834990059642, "grad_norm": 0.11096446216106415, "learning_rate": 2.1871766626789656e-05, "loss": 0.0032, "step": 8802 }, { "epoch": 0.486138723216258, "grad_norm": 0.09483562409877777, "learning_rate": 2.1868204988871436e-05, "loss": 0.0019, "step": 8803 }, { "epoch": 0.4861939474265518, "grad_norm": 1.0700201988220215, "learning_rate": 2.186464329118402e-05, "loss": 0.0196, "step": 8804 }, { "epoch": 0.4862491716368456, "grad_norm": 0.053266435861587524, "learning_rate": 2.1861081533841357e-05, "loss": 0.0014, "step": 8805 }, { "epoch": 0.48630439584713936, "grad_norm": 3.251530170440674, "learning_rate": 2.1857519716957398e-05, "loss": 0.931, "step": 8806 }, { "epoch": 0.48635962005743316, "grad_norm": 0.07573655992746353, "learning_rate": 2.1853957840646095e-05, "loss": 0.0025, "step": 8807 }, { "epoch": 0.48641484426772696, "grad_norm": 0.18063482642173767, "learning_rate": 2.1850395905021405e-05, "loss": 0.0059, "step": 8808 }, { "epoch": 0.48647006847802077, "grad_norm": 2.0274884700775146, "learning_rate": 2.1846833910197278e-05, "loss": 0.1377, "step": 8809 }, { "epoch": 0.48652529268831457, "grad_norm": 4.957770824432373, "learning_rate": 2.1843271856287682e-05, "loss": 0.4703, "step": 8810 }, { "epoch": 0.4865805168986084, "grad_norm": 1.4293227195739746, "learning_rate": 2.1839709743406562e-05, "loss": 0.035, "step": 8811 }, { "epoch": 0.4866357411089021, "grad_norm": 2.7623629570007324, "learning_rate": 2.1836147571667897e-05, "loss": 0.9692, "step": 8812 }, { "epoch": 0.4866909653191959, "grad_norm": 0.03121958114206791, "learning_rate": 2.1832585341185644e-05, "loss": 0.001, "step": 8813 }, { "epoch": 0.4867461895294897, "grad_norm": 1.2653664350509644, "learning_rate": 2.1829023052073766e-05, "loss": 0.1089, "step": 8814 }, { "epoch": 0.48680141373978353, "grad_norm": 0.04005102068185806, "learning_rate": 2.1825460704446243e-05, "loss": 0.0015, "step": 8815 }, { "epoch": 0.48685663795007733, "grad_norm": 2.835115909576416, "learning_rate": 2.1821898298417022e-05, "loss": 0.2516, "step": 8816 }, { "epoch": 0.48691186216037113, "grad_norm": 0.21946999430656433, "learning_rate": 2.18183358341001e-05, "loss": 0.0053, "step": 8817 }, { "epoch": 0.4869670863706649, "grad_norm": 3.696903705596924, "learning_rate": 2.1814773311609434e-05, "loss": 1.1683, "step": 8818 }, { "epoch": 0.4870223105809587, "grad_norm": 2.0032386779785156, "learning_rate": 2.1811210731058995e-05, "loss": 0.1288, "step": 8819 }, { "epoch": 0.4870775347912525, "grad_norm": 0.06454914063215256, "learning_rate": 2.1807648092562777e-05, "loss": 0.0021, "step": 8820 }, { "epoch": 0.4871327590015463, "grad_norm": 0.058761775493621826, "learning_rate": 2.1804085396234744e-05, "loss": 0.0019, "step": 8821 }, { "epoch": 0.4871879832118401, "grad_norm": 3.6944549083709717, "learning_rate": 2.180052264218889e-05, "loss": 0.0754, "step": 8822 }, { "epoch": 0.48724320742213384, "grad_norm": 2.2617390155792236, "learning_rate": 2.1796959830539186e-05, "loss": 0.4004, "step": 8823 }, { "epoch": 0.48729843163242764, "grad_norm": 2.979081392288208, "learning_rate": 2.1793396961399623e-05, "loss": 0.7894, "step": 8824 }, { "epoch": 0.48735365584272144, "grad_norm": 0.07207179069519043, "learning_rate": 2.1789834034884187e-05, "loss": 0.0031, "step": 8825 }, { "epoch": 0.48740888005301525, "grad_norm": 0.3742154836654663, "learning_rate": 2.1786271051106864e-05, "loss": 0.0118, "step": 8826 }, { "epoch": 0.48746410426330905, "grad_norm": 0.8813511729240417, "learning_rate": 2.1782708010181644e-05, "loss": 0.0376, "step": 8827 }, { "epoch": 0.48751932847360285, "grad_norm": 0.2148481160402298, "learning_rate": 2.1779144912222517e-05, "loss": 0.0051, "step": 8828 }, { "epoch": 0.4875745526838966, "grad_norm": 1.3681519031524658, "learning_rate": 2.177558175734348e-05, "loss": 0.0321, "step": 8829 }, { "epoch": 0.4876297768941904, "grad_norm": 1.4285314083099365, "learning_rate": 2.177201854565853e-05, "loss": 0.0405, "step": 8830 }, { "epoch": 0.4876850011044842, "grad_norm": 0.0813826248049736, "learning_rate": 2.1768455277281663e-05, "loss": 0.0029, "step": 8831 }, { "epoch": 0.487740225314778, "grad_norm": 1.4890010356903076, "learning_rate": 2.1764891952326875e-05, "loss": 0.5505, "step": 8832 }, { "epoch": 0.4877954495250718, "grad_norm": 4.092508316040039, "learning_rate": 2.176132857090817e-05, "loss": 0.8269, "step": 8833 }, { "epoch": 0.48785067373536556, "grad_norm": 4.01376485824585, "learning_rate": 2.1757765133139554e-05, "loss": 1.1026, "step": 8834 }, { "epoch": 0.48790589794565936, "grad_norm": 0.13667218387126923, "learning_rate": 2.175420163913502e-05, "loss": 0.004, "step": 8835 }, { "epoch": 0.48796112215595316, "grad_norm": 4.071953773498535, "learning_rate": 2.1750638089008586e-05, "loss": 0.8421, "step": 8836 }, { "epoch": 0.48801634636624697, "grad_norm": 0.30877405405044556, "learning_rate": 2.1747074482874248e-05, "loss": 0.0134, "step": 8837 }, { "epoch": 0.48807157057654077, "grad_norm": 0.3861634135246277, "learning_rate": 2.1743510820846033e-05, "loss": 0.0064, "step": 8838 }, { "epoch": 0.4881267947868346, "grad_norm": 0.14290915429592133, "learning_rate": 2.1739947103037943e-05, "loss": 0.0044, "step": 8839 }, { "epoch": 0.4881820189971283, "grad_norm": 1.4348492622375488, "learning_rate": 2.1736383329563987e-05, "loss": 0.0373, "step": 8840 }, { "epoch": 0.4882372432074221, "grad_norm": 0.5455902814865112, "learning_rate": 2.1732819500538187e-05, "loss": 0.0145, "step": 8841 }, { "epoch": 0.4882924674177159, "grad_norm": 0.011148863472044468, "learning_rate": 2.1729255616074556e-05, "loss": 0.0005, "step": 8842 }, { "epoch": 0.48834769162800973, "grad_norm": 3.0409369468688965, "learning_rate": 2.1725691676287117e-05, "loss": 0.3048, "step": 8843 }, { "epoch": 0.48840291583830353, "grad_norm": 0.01811663992702961, "learning_rate": 2.172212768128989e-05, "loss": 0.0006, "step": 8844 }, { "epoch": 0.4884581400485973, "grad_norm": 0.11776676028966904, "learning_rate": 2.1718563631196892e-05, "loss": 0.0029, "step": 8845 }, { "epoch": 0.4885133642588911, "grad_norm": 1.3697978258132935, "learning_rate": 2.1714999526122154e-05, "loss": 0.0402, "step": 8846 }, { "epoch": 0.4885685884691849, "grad_norm": 3.6564884185791016, "learning_rate": 2.17114353661797e-05, "loss": 0.3139, "step": 8847 }, { "epoch": 0.4886238126794787, "grad_norm": 0.07786563038825989, "learning_rate": 2.170787115148355e-05, "loss": 0.0032, "step": 8848 }, { "epoch": 0.4886790368897725, "grad_norm": 2.7099220752716064, "learning_rate": 2.1704306882147746e-05, "loss": 0.4764, "step": 8849 }, { "epoch": 0.4887342611000663, "grad_norm": 1.6444294452667236, "learning_rate": 2.1700742558286306e-05, "loss": 0.3318, "step": 8850 }, { "epoch": 0.48878948531036004, "grad_norm": 0.04050811380147934, "learning_rate": 2.1697178180013278e-05, "loss": 0.001, "step": 8851 }, { "epoch": 0.48884470952065384, "grad_norm": 0.33391040563583374, "learning_rate": 2.1693613747442687e-05, "loss": 0.0126, "step": 8852 }, { "epoch": 0.48889993373094764, "grad_norm": 2.810098648071289, "learning_rate": 2.1690049260688567e-05, "loss": 0.2299, "step": 8853 }, { "epoch": 0.48895515794124145, "grad_norm": 0.030673861503601074, "learning_rate": 2.168648471986496e-05, "loss": 0.0008, "step": 8854 }, { "epoch": 0.48901038215153525, "grad_norm": 2.2118136882781982, "learning_rate": 2.168292012508591e-05, "loss": 0.1808, "step": 8855 }, { "epoch": 0.48906560636182905, "grad_norm": 5.0980024337768555, "learning_rate": 2.1679355476465446e-05, "loss": 0.9268, "step": 8856 }, { "epoch": 0.4891208305721228, "grad_norm": 0.23281224071979523, "learning_rate": 2.167579077411763e-05, "loss": 0.0042, "step": 8857 }, { "epoch": 0.4891760547824166, "grad_norm": 2.784245014190674, "learning_rate": 2.1672226018156483e-05, "loss": 0.6364, "step": 8858 }, { "epoch": 0.4892312789927104, "grad_norm": 4.6205620765686035, "learning_rate": 2.1668661208696075e-05, "loss": 1.1406, "step": 8859 }, { "epoch": 0.4892865032030042, "grad_norm": 0.0372726246714592, "learning_rate": 2.1665096345850447e-05, "loss": 0.0014, "step": 8860 }, { "epoch": 0.489341727413298, "grad_norm": 0.2615370452404022, "learning_rate": 2.1661531429733635e-05, "loss": 0.0045, "step": 8861 }, { "epoch": 0.48939695162359176, "grad_norm": 4.228905200958252, "learning_rate": 2.1657966460459713e-05, "loss": 0.4254, "step": 8862 }, { "epoch": 0.48945217583388556, "grad_norm": 1.6650545597076416, "learning_rate": 2.165440143814272e-05, "loss": 0.0602, "step": 8863 }, { "epoch": 0.48950740004417936, "grad_norm": 2.6605279445648193, "learning_rate": 2.1650836362896716e-05, "loss": 0.0887, "step": 8864 }, { "epoch": 0.48956262425447317, "grad_norm": 4.146833896636963, "learning_rate": 2.1647271234835757e-05, "loss": 0.4608, "step": 8865 }, { "epoch": 0.48961784846476697, "grad_norm": 0.5471181869506836, "learning_rate": 2.1643706054073896e-05, "loss": 0.0165, "step": 8866 }, { "epoch": 0.48967307267506077, "grad_norm": 1.7634714841842651, "learning_rate": 2.1640140820725208e-05, "loss": 0.4012, "step": 8867 }, { "epoch": 0.4897282968853545, "grad_norm": 0.0333084799349308, "learning_rate": 2.1636575534903743e-05, "loss": 0.0012, "step": 8868 }, { "epoch": 0.4897835210956483, "grad_norm": 2.0291430950164795, "learning_rate": 2.1633010196723566e-05, "loss": 0.7015, "step": 8869 }, { "epoch": 0.4898387453059421, "grad_norm": 0.1330646574497223, "learning_rate": 2.1629444806298744e-05, "loss": 0.0046, "step": 8870 }, { "epoch": 0.4898939695162359, "grad_norm": 0.059943787753582, "learning_rate": 2.1625879363743342e-05, "loss": 0.0021, "step": 8871 }, { "epoch": 0.48994919372652973, "grad_norm": 1.5336195230484009, "learning_rate": 2.162231386917143e-05, "loss": 0.0991, "step": 8872 }, { "epoch": 0.4900044179368235, "grad_norm": 3.7005279064178467, "learning_rate": 2.1618748322697084e-05, "loss": 0.7727, "step": 8873 }, { "epoch": 0.4900596421471173, "grad_norm": 2.9878599643707275, "learning_rate": 2.1615182724434364e-05, "loss": 0.4265, "step": 8874 }, { "epoch": 0.4901148663574111, "grad_norm": 0.13131928443908691, "learning_rate": 2.1611617074497362e-05, "loss": 0.0043, "step": 8875 }, { "epoch": 0.4901700905677049, "grad_norm": 0.16273187100887299, "learning_rate": 2.1608051373000133e-05, "loss": 0.0045, "step": 8876 }, { "epoch": 0.4902253147779987, "grad_norm": 3.8007185459136963, "learning_rate": 2.1604485620056766e-05, "loss": 0.1072, "step": 8877 }, { "epoch": 0.4902805389882925, "grad_norm": 4.487771034240723, "learning_rate": 2.1600919815781335e-05, "loss": 0.3724, "step": 8878 }, { "epoch": 0.49033576319858624, "grad_norm": 0.018176663666963577, "learning_rate": 2.1597353960287916e-05, "loss": 0.0006, "step": 8879 }, { "epoch": 0.49039098740888004, "grad_norm": 4.958280563354492, "learning_rate": 2.1593788053690603e-05, "loss": 0.6229, "step": 8880 }, { "epoch": 0.49044621161917384, "grad_norm": 5.176272392272949, "learning_rate": 2.159022209610347e-05, "loss": 0.7025, "step": 8881 }, { "epoch": 0.49050143582946765, "grad_norm": 0.04511057212948799, "learning_rate": 2.1586656087640606e-05, "loss": 0.0013, "step": 8882 }, { "epoch": 0.49055666003976145, "grad_norm": 0.6304219365119934, "learning_rate": 2.1583090028416098e-05, "loss": 0.0141, "step": 8883 }, { "epoch": 0.4906118842500552, "grad_norm": 2.2093610763549805, "learning_rate": 2.1579523918544028e-05, "loss": 0.0816, "step": 8884 }, { "epoch": 0.490667108460349, "grad_norm": 0.7415561676025391, "learning_rate": 2.1575957758138493e-05, "loss": 0.0259, "step": 8885 }, { "epoch": 0.4907223326706428, "grad_norm": 2.400096893310547, "learning_rate": 2.157239154731359e-05, "loss": 0.1714, "step": 8886 }, { "epoch": 0.4907775568809366, "grad_norm": 0.01748225837945938, "learning_rate": 2.1568825286183398e-05, "loss": 0.0005, "step": 8887 }, { "epoch": 0.4908327810912304, "grad_norm": 0.1998511403799057, "learning_rate": 2.1565258974862023e-05, "loss": 0.0044, "step": 8888 }, { "epoch": 0.4908880053015242, "grad_norm": 0.6285380721092224, "learning_rate": 2.1561692613463553e-05, "loss": 0.0131, "step": 8889 }, { "epoch": 0.49094322951181796, "grad_norm": 1.792032241821289, "learning_rate": 2.1558126202102092e-05, "loss": 0.1837, "step": 8890 }, { "epoch": 0.49099845372211176, "grad_norm": 0.1487421840429306, "learning_rate": 2.155455974089174e-05, "loss": 0.0037, "step": 8891 }, { "epoch": 0.49105367793240556, "grad_norm": 0.24137721955776215, "learning_rate": 2.155099322994659e-05, "loss": 0.0083, "step": 8892 }, { "epoch": 0.49110890214269937, "grad_norm": 4.344865322113037, "learning_rate": 2.1547426669380757e-05, "loss": 0.6663, "step": 8893 }, { "epoch": 0.49116412635299317, "grad_norm": 0.2596634328365326, "learning_rate": 2.154386005930834e-05, "loss": 0.0053, "step": 8894 }, { "epoch": 0.49121935056328697, "grad_norm": 3.5704331398010254, "learning_rate": 2.154029339984344e-05, "loss": 0.6434, "step": 8895 }, { "epoch": 0.4912745747735807, "grad_norm": 4.977902412414551, "learning_rate": 2.1536726691100173e-05, "loss": 0.4955, "step": 8896 }, { "epoch": 0.4913297989838745, "grad_norm": 0.020539410412311554, "learning_rate": 2.153315993319264e-05, "loss": 0.0007, "step": 8897 }, { "epoch": 0.4913850231941683, "grad_norm": 0.04511014372110367, "learning_rate": 2.152959312623496e-05, "loss": 0.0009, "step": 8898 }, { "epoch": 0.4914402474044621, "grad_norm": 0.842211902141571, "learning_rate": 2.1526026270341242e-05, "loss": 0.0236, "step": 8899 }, { "epoch": 0.49149547161475593, "grad_norm": 1.6268270015716553, "learning_rate": 2.1522459365625594e-05, "loss": 0.0416, "step": 8900 }, { "epoch": 0.4915506958250497, "grad_norm": 2.61149263381958, "learning_rate": 2.151889241220214e-05, "loss": 0.4279, "step": 8901 }, { "epoch": 0.4916059200353435, "grad_norm": 2.920825719833374, "learning_rate": 2.1515325410184994e-05, "loss": 0.2232, "step": 8902 }, { "epoch": 0.4916611442456373, "grad_norm": 2.5877890586853027, "learning_rate": 2.1511758359688273e-05, "loss": 0.0711, "step": 8903 }, { "epoch": 0.4917163684559311, "grad_norm": 0.12492685765028, "learning_rate": 2.15081912608261e-05, "loss": 0.0031, "step": 8904 }, { "epoch": 0.4917715926662249, "grad_norm": 0.15107573568820953, "learning_rate": 2.150462411371259e-05, "loss": 0.0038, "step": 8905 }, { "epoch": 0.4918268168765187, "grad_norm": 1.6258528232574463, "learning_rate": 2.150105691846188e-05, "loss": 0.2342, "step": 8906 }, { "epoch": 0.49188204108681244, "grad_norm": 4.157129764556885, "learning_rate": 2.149748967518808e-05, "loss": 0.1665, "step": 8907 }, { "epoch": 0.49193726529710624, "grad_norm": 3.5331406593322754, "learning_rate": 2.1493922384005322e-05, "loss": 0.2278, "step": 8908 }, { "epoch": 0.49199248950740004, "grad_norm": 3.733609914779663, "learning_rate": 2.1490355045027736e-05, "loss": 0.7368, "step": 8909 }, { "epoch": 0.49204771371769385, "grad_norm": 1.9220409393310547, "learning_rate": 2.1486787658369447e-05, "loss": 0.043, "step": 8910 }, { "epoch": 0.49210293792798765, "grad_norm": 0.6991243958473206, "learning_rate": 2.1483220224144592e-05, "loss": 0.0237, "step": 8911 }, { "epoch": 0.4921581621382814, "grad_norm": 0.3780742585659027, "learning_rate": 2.1479652742467295e-05, "loss": 0.0125, "step": 8912 }, { "epoch": 0.4922133863485752, "grad_norm": 0.34854769706726074, "learning_rate": 2.1476085213451694e-05, "loss": 0.0107, "step": 8913 }, { "epoch": 0.492268610558869, "grad_norm": 0.11738118529319763, "learning_rate": 2.147251763721193e-05, "loss": 0.0032, "step": 8914 }, { "epoch": 0.4923238347691628, "grad_norm": 0.15066871047019958, "learning_rate": 2.1468950013862132e-05, "loss": 0.0043, "step": 8915 }, { "epoch": 0.4923790589794566, "grad_norm": 3.4704153537750244, "learning_rate": 2.146538234351644e-05, "loss": 0.8964, "step": 8916 }, { "epoch": 0.4924342831897504, "grad_norm": 0.6428706645965576, "learning_rate": 2.1461814626289e-05, "loss": 0.1183, "step": 8917 }, { "epoch": 0.49248950740004416, "grad_norm": 2.2961418628692627, "learning_rate": 2.145824686229394e-05, "loss": 0.5393, "step": 8918 }, { "epoch": 0.49254473161033796, "grad_norm": 0.0867881029844284, "learning_rate": 2.1454679051645417e-05, "loss": 0.0017, "step": 8919 }, { "epoch": 0.49259995582063176, "grad_norm": 0.855021059513092, "learning_rate": 2.145111119445757e-05, "loss": 0.025, "step": 8920 }, { "epoch": 0.49265518003092557, "grad_norm": 0.04893822595477104, "learning_rate": 2.144754329084454e-05, "loss": 0.0016, "step": 8921 }, { "epoch": 0.49271040424121937, "grad_norm": 3.3742125034332275, "learning_rate": 2.1443975340920487e-05, "loss": 0.4117, "step": 8922 }, { "epoch": 0.4927656284515131, "grad_norm": 1.804254174232483, "learning_rate": 2.144040734479955e-05, "loss": 0.1388, "step": 8923 }, { "epoch": 0.4928208526618069, "grad_norm": 2.2992148399353027, "learning_rate": 2.1436839302595874e-05, "loss": 0.0585, "step": 8924 }, { "epoch": 0.4928760768721007, "grad_norm": 1.0867425203323364, "learning_rate": 2.1433271214423623e-05, "loss": 0.036, "step": 8925 }, { "epoch": 0.4929313010823945, "grad_norm": 0.09464060515165329, "learning_rate": 2.1429703080396943e-05, "loss": 0.0025, "step": 8926 }, { "epoch": 0.4929865252926883, "grad_norm": 3.815690517425537, "learning_rate": 2.142613490063e-05, "loss": 0.9107, "step": 8927 }, { "epoch": 0.49304174950298213, "grad_norm": 3.2344930171966553, "learning_rate": 2.1422566675236936e-05, "loss": 0.2378, "step": 8928 }, { "epoch": 0.4930969737132759, "grad_norm": 1.6452535390853882, "learning_rate": 2.1418998404331913e-05, "loss": 0.0407, "step": 8929 }, { "epoch": 0.4931521979235697, "grad_norm": 3.8507330417633057, "learning_rate": 2.1415430088029092e-05, "loss": 0.5099, "step": 8930 }, { "epoch": 0.4932074221338635, "grad_norm": 2.873434543609619, "learning_rate": 2.141186172644263e-05, "loss": 0.3521, "step": 8931 }, { "epoch": 0.4932626463441573, "grad_norm": 0.8300555348396301, "learning_rate": 2.1408293319686698e-05, "loss": 0.025, "step": 8932 }, { "epoch": 0.4933178705544511, "grad_norm": 3.2099294662475586, "learning_rate": 2.140472486787545e-05, "loss": 0.2407, "step": 8933 }, { "epoch": 0.4933730947647449, "grad_norm": 5.106487274169922, "learning_rate": 2.140115637112305e-05, "loss": 1.0155, "step": 8934 }, { "epoch": 0.49342831897503864, "grad_norm": 0.06532122939825058, "learning_rate": 2.1397587829543676e-05, "loss": 0.0024, "step": 8935 }, { "epoch": 0.49348354318533244, "grad_norm": 0.24601216614246368, "learning_rate": 2.139401924325149e-05, "loss": 0.0073, "step": 8936 }, { "epoch": 0.49353876739562624, "grad_norm": 0.021899718791246414, "learning_rate": 2.1390450612360654e-05, "loss": 0.0007, "step": 8937 }, { "epoch": 0.49359399160592005, "grad_norm": 6.116998195648193, "learning_rate": 2.1386881936985354e-05, "loss": 0.8391, "step": 8938 }, { "epoch": 0.49364921581621385, "grad_norm": 1.9357272386550903, "learning_rate": 2.1383313217239737e-05, "loss": 0.051, "step": 8939 }, { "epoch": 0.4937044400265076, "grad_norm": 0.1348363310098648, "learning_rate": 2.1379744453238004e-05, "loss": 0.003, "step": 8940 }, { "epoch": 0.4937596642368014, "grad_norm": 0.14321087300777435, "learning_rate": 2.1376175645094315e-05, "loss": 0.0028, "step": 8941 }, { "epoch": 0.4938148884470952, "grad_norm": 0.3232196569442749, "learning_rate": 2.137260679292285e-05, "loss": 0.0077, "step": 8942 }, { "epoch": 0.493870112657389, "grad_norm": 0.33879444003105164, "learning_rate": 2.1369037896837783e-05, "loss": 0.0097, "step": 8943 }, { "epoch": 0.4939253368676828, "grad_norm": 4.187911033630371, "learning_rate": 2.1365468956953297e-05, "loss": 0.8575, "step": 8944 }, { "epoch": 0.4939805610779766, "grad_norm": 1.837199091911316, "learning_rate": 2.136189997338357e-05, "loss": 0.1526, "step": 8945 }, { "epoch": 0.49403578528827036, "grad_norm": 0.9787800908088684, "learning_rate": 2.135833094624279e-05, "loss": 0.0543, "step": 8946 }, { "epoch": 0.49409100949856416, "grad_norm": 2.0469021797180176, "learning_rate": 2.1354761875645135e-05, "loss": 0.2303, "step": 8947 }, { "epoch": 0.49414623370885796, "grad_norm": 0.16606688499450684, "learning_rate": 2.135119276170479e-05, "loss": 0.0043, "step": 8948 }, { "epoch": 0.49420145791915177, "grad_norm": 0.06007937714457512, "learning_rate": 2.134762360453594e-05, "loss": 0.002, "step": 8949 }, { "epoch": 0.49425668212944557, "grad_norm": 0.0584903359413147, "learning_rate": 2.1344054404252778e-05, "loss": 0.0014, "step": 8950 }, { "epoch": 0.4943119063397393, "grad_norm": 1.7030962705612183, "learning_rate": 2.134048516096949e-05, "loss": 0.047, "step": 8951 }, { "epoch": 0.4943671305500331, "grad_norm": 0.23020720481872559, "learning_rate": 2.133691587480026e-05, "loss": 0.0071, "step": 8952 }, { "epoch": 0.4944223547603269, "grad_norm": 3.2510597705841064, "learning_rate": 2.1333346545859287e-05, "loss": 0.1473, "step": 8953 }, { "epoch": 0.4944775789706207, "grad_norm": 3.12048602104187, "learning_rate": 2.132977717426077e-05, "loss": 0.3346, "step": 8954 }, { "epoch": 0.4945328031809145, "grad_norm": 0.05287813022732735, "learning_rate": 2.1326207760118885e-05, "loss": 0.0012, "step": 8955 }, { "epoch": 0.49458802739120833, "grad_norm": 3.2030835151672363, "learning_rate": 2.1322638303547842e-05, "loss": 0.7926, "step": 8956 }, { "epoch": 0.4946432516015021, "grad_norm": 2.1187198162078857, "learning_rate": 2.131906880466183e-05, "loss": 0.265, "step": 8957 }, { "epoch": 0.4946984758117959, "grad_norm": 0.04959363862872124, "learning_rate": 2.131549926357506e-05, "loss": 0.0016, "step": 8958 }, { "epoch": 0.4947537000220897, "grad_norm": 0.008861541748046875, "learning_rate": 2.1311929680401723e-05, "loss": 0.0002, "step": 8959 }, { "epoch": 0.4948089242323835, "grad_norm": 4.075121879577637, "learning_rate": 2.130836005525601e-05, "loss": 0.2812, "step": 8960 }, { "epoch": 0.4948641484426773, "grad_norm": 0.341680645942688, "learning_rate": 2.1304790388252146e-05, "loss": 0.0112, "step": 8961 }, { "epoch": 0.4949193726529711, "grad_norm": 2.2388830184936523, "learning_rate": 2.1301220679504318e-05, "loss": 0.2088, "step": 8962 }, { "epoch": 0.49497459686326484, "grad_norm": 0.6711943745613098, "learning_rate": 2.129765092912673e-05, "loss": 0.0162, "step": 8963 }, { "epoch": 0.49502982107355864, "grad_norm": 4.717570781707764, "learning_rate": 2.1294081137233603e-05, "loss": 0.9864, "step": 8964 }, { "epoch": 0.49508504528385244, "grad_norm": 3.5908422470092773, "learning_rate": 2.129051130393913e-05, "loss": 0.2258, "step": 8965 }, { "epoch": 0.49514026949414625, "grad_norm": 5.334197998046875, "learning_rate": 2.1286941429357535e-05, "loss": 1.4651, "step": 8966 }, { "epoch": 0.49519549370444005, "grad_norm": 1.6002302169799805, "learning_rate": 2.128337151360302e-05, "loss": 0.0404, "step": 8967 }, { "epoch": 0.4952507179147338, "grad_norm": 0.15537390112876892, "learning_rate": 2.1279801556789788e-05, "loss": 0.0033, "step": 8968 }, { "epoch": 0.4953059421250276, "grad_norm": 2.0483717918395996, "learning_rate": 2.1276231559032068e-05, "loss": 0.1009, "step": 8969 }, { "epoch": 0.4953611663353214, "grad_norm": 3.252872943878174, "learning_rate": 2.1272661520444057e-05, "loss": 0.1616, "step": 8970 }, { "epoch": 0.4954163905456152, "grad_norm": 2.6506283283233643, "learning_rate": 2.126909144113999e-05, "loss": 0.1762, "step": 8971 }, { "epoch": 0.495471614755909, "grad_norm": 1.4375944137573242, "learning_rate": 2.1265521321234076e-05, "loss": 0.0467, "step": 8972 }, { "epoch": 0.4955268389662028, "grad_norm": 0.5978363156318665, "learning_rate": 2.126195116084053e-05, "loss": 0.0219, "step": 8973 }, { "epoch": 0.49558206317649656, "grad_norm": 0.6073651909828186, "learning_rate": 2.125838096007357e-05, "loss": 0.0374, "step": 8974 }, { "epoch": 0.49563728738679036, "grad_norm": 1.7742047309875488, "learning_rate": 2.1254810719047423e-05, "loss": 0.1192, "step": 8975 }, { "epoch": 0.49569251159708416, "grad_norm": 3.9164223670959473, "learning_rate": 2.125124043787631e-05, "loss": 0.8583, "step": 8976 }, { "epoch": 0.49574773580737796, "grad_norm": 0.2679080665111542, "learning_rate": 2.1247670116674453e-05, "loss": 0.0066, "step": 8977 }, { "epoch": 0.49580296001767177, "grad_norm": 0.09028154611587524, "learning_rate": 2.1244099755556072e-05, "loss": 0.0028, "step": 8978 }, { "epoch": 0.4958581842279655, "grad_norm": 0.742657482624054, "learning_rate": 2.1240529354635406e-05, "loss": 0.0166, "step": 8979 }, { "epoch": 0.4959134084382593, "grad_norm": 0.13979575037956238, "learning_rate": 2.1236958914026672e-05, "loss": 0.0046, "step": 8980 }, { "epoch": 0.4959686326485531, "grad_norm": 0.8940388560295105, "learning_rate": 2.1233388433844095e-05, "loss": 0.0358, "step": 8981 }, { "epoch": 0.4960238568588469, "grad_norm": 0.35238683223724365, "learning_rate": 2.122981791420192e-05, "loss": 0.1024, "step": 8982 }, { "epoch": 0.4960790810691407, "grad_norm": 0.8387529253959656, "learning_rate": 2.1226247355214365e-05, "loss": 0.0133, "step": 8983 }, { "epoch": 0.49613430527943453, "grad_norm": 0.08047730475664139, "learning_rate": 2.1222676756995663e-05, "loss": 0.0019, "step": 8984 }, { "epoch": 0.4961895294897283, "grad_norm": 0.43904909491539, "learning_rate": 2.1219106119660054e-05, "loss": 0.0122, "step": 8985 }, { "epoch": 0.4962447537000221, "grad_norm": 3.9798173904418945, "learning_rate": 2.1215535443321764e-05, "loss": 0.0538, "step": 8986 }, { "epoch": 0.4962999779103159, "grad_norm": 0.25565245747566223, "learning_rate": 2.121196472809504e-05, "loss": 0.007, "step": 8987 }, { "epoch": 0.4963552021206097, "grad_norm": 2.444319486618042, "learning_rate": 2.1208393974094116e-05, "loss": 0.2499, "step": 8988 }, { "epoch": 0.4964104263309035, "grad_norm": 0.23224791884422302, "learning_rate": 2.1204823181433224e-05, "loss": 0.0059, "step": 8989 }, { "epoch": 0.49646565054119723, "grad_norm": 4.554417133331299, "learning_rate": 2.1201252350226614e-05, "loss": 0.4062, "step": 8990 }, { "epoch": 0.49652087475149104, "grad_norm": 2.943905830383301, "learning_rate": 2.1197681480588513e-05, "loss": 0.119, "step": 8991 }, { "epoch": 0.49657609896178484, "grad_norm": 4.0594072341918945, "learning_rate": 2.1194110572633176e-05, "loss": 1.1824, "step": 8992 }, { "epoch": 0.49663132317207864, "grad_norm": 0.07810713350772858, "learning_rate": 2.1190539626474848e-05, "loss": 0.0017, "step": 8993 }, { "epoch": 0.49668654738237245, "grad_norm": 1.8202027082443237, "learning_rate": 2.1186968642227758e-05, "loss": 0.1101, "step": 8994 }, { "epoch": 0.49674177159266625, "grad_norm": 1.4814518690109253, "learning_rate": 2.118339762000617e-05, "loss": 0.0597, "step": 8995 }, { "epoch": 0.49679699580296, "grad_norm": 5.141696453094482, "learning_rate": 2.117982655992432e-05, "loss": 0.6313, "step": 8996 }, { "epoch": 0.4968522200132538, "grad_norm": 0.051234837621450424, "learning_rate": 2.117625546209646e-05, "loss": 0.0015, "step": 8997 }, { "epoch": 0.4969074442235476, "grad_norm": 1.7464966773986816, "learning_rate": 2.1172684326636844e-05, "loss": 0.0567, "step": 8998 }, { "epoch": 0.4969626684338414, "grad_norm": 0.42016997933387756, "learning_rate": 2.1169113153659707e-05, "loss": 0.0103, "step": 8999 }, { "epoch": 0.4970178926441352, "grad_norm": 2.968527317047119, "learning_rate": 2.116554194327932e-05, "loss": 0.2545, "step": 9000 }, { "epoch": 0.497073116854429, "grad_norm": 0.07880569994449615, "learning_rate": 2.1161970695609924e-05, "loss": 0.0026, "step": 9001 }, { "epoch": 0.49712834106472276, "grad_norm": 0.8476845622062683, "learning_rate": 2.115839941076578e-05, "loss": 0.0278, "step": 9002 }, { "epoch": 0.49718356527501656, "grad_norm": 2.719329595565796, "learning_rate": 2.1154828088861145e-05, "loss": 0.5491, "step": 9003 }, { "epoch": 0.49723878948531036, "grad_norm": 1.0014311075210571, "learning_rate": 2.115125673001026e-05, "loss": 0.0242, "step": 9004 }, { "epoch": 0.49729401369560416, "grad_norm": 3.751577615737915, "learning_rate": 2.1147685334327407e-05, "loss": 0.3771, "step": 9005 }, { "epoch": 0.49734923790589797, "grad_norm": 1.576348066329956, "learning_rate": 2.1144113901926827e-05, "loss": 0.4006, "step": 9006 }, { "epoch": 0.4974044621161917, "grad_norm": 3.5075159072875977, "learning_rate": 2.1140542432922785e-05, "loss": 0.5459, "step": 9007 }, { "epoch": 0.4974596863264855, "grad_norm": 0.6084157824516296, "learning_rate": 2.1136970927429546e-05, "loss": 0.0092, "step": 9008 }, { "epoch": 0.4975149105367793, "grad_norm": 1.654927134513855, "learning_rate": 2.1133399385561365e-05, "loss": 0.144, "step": 9009 }, { "epoch": 0.4975701347470731, "grad_norm": 6.454556465148926, "learning_rate": 2.1129827807432516e-05, "loss": 0.6876, "step": 9010 }, { "epoch": 0.4976253589573669, "grad_norm": 0.015352561138570309, "learning_rate": 2.112625619315726e-05, "loss": 0.0004, "step": 9011 }, { "epoch": 0.49768058316766073, "grad_norm": 0.9335182309150696, "learning_rate": 2.112268454284986e-05, "loss": 0.0243, "step": 9012 }, { "epoch": 0.4977358073779545, "grad_norm": 0.7891470193862915, "learning_rate": 2.1119112856624588e-05, "loss": 0.0198, "step": 9013 }, { "epoch": 0.4977910315882483, "grad_norm": 0.8895705342292786, "learning_rate": 2.1115541134595707e-05, "loss": 0.018, "step": 9014 }, { "epoch": 0.4978462557985421, "grad_norm": 0.1084570437669754, "learning_rate": 2.1111969376877487e-05, "loss": 0.0028, "step": 9015 }, { "epoch": 0.4979014800088359, "grad_norm": 4.750255584716797, "learning_rate": 2.1108397583584208e-05, "loss": 1.2524, "step": 9016 }, { "epoch": 0.4979567042191297, "grad_norm": 2.06302809715271, "learning_rate": 2.1104825754830128e-05, "loss": 0.3053, "step": 9017 }, { "epoch": 0.49801192842942343, "grad_norm": 0.013384114019572735, "learning_rate": 2.1101253890729526e-05, "loss": 0.0005, "step": 9018 }, { "epoch": 0.49806715263971724, "grad_norm": 2.469388484954834, "learning_rate": 2.1097681991396683e-05, "loss": 0.0627, "step": 9019 }, { "epoch": 0.49812237685001104, "grad_norm": 0.019150983542203903, "learning_rate": 2.1094110056945865e-05, "loss": 0.0006, "step": 9020 }, { "epoch": 0.49817760106030484, "grad_norm": 3.1742160320281982, "learning_rate": 2.1090538087491352e-05, "loss": 0.3074, "step": 9021 }, { "epoch": 0.49823282527059864, "grad_norm": 0.10160204768180847, "learning_rate": 2.1086966083147424e-05, "loss": 0.0033, "step": 9022 }, { "epoch": 0.49828804948089245, "grad_norm": 2.589210033416748, "learning_rate": 2.1083394044028348e-05, "loss": 0.8628, "step": 9023 }, { "epoch": 0.4983432736911862, "grad_norm": 0.24509820342063904, "learning_rate": 2.1079821970248423e-05, "loss": 0.0107, "step": 9024 }, { "epoch": 0.49839849790148, "grad_norm": 2.7409119606018066, "learning_rate": 2.107624986192191e-05, "loss": 0.2475, "step": 9025 }, { "epoch": 0.4984537221117738, "grad_norm": 0.1949155181646347, "learning_rate": 2.1072677719163105e-05, "loss": 0.0034, "step": 9026 }, { "epoch": 0.4985089463220676, "grad_norm": 2.4819891452789307, "learning_rate": 2.1069105542086285e-05, "loss": 0.0955, "step": 9027 }, { "epoch": 0.4985641705323614, "grad_norm": 0.019646689295768738, "learning_rate": 2.1065533330805733e-05, "loss": 0.0007, "step": 9028 }, { "epoch": 0.49861939474265515, "grad_norm": 1.411360502243042, "learning_rate": 2.106196108543574e-05, "loss": 0.0342, "step": 9029 }, { "epoch": 0.49867461895294896, "grad_norm": 0.3407711088657379, "learning_rate": 2.1058388806090585e-05, "loss": 0.011, "step": 9030 }, { "epoch": 0.49872984316324276, "grad_norm": 1.0954920053482056, "learning_rate": 2.1054816492884563e-05, "loss": 0.1096, "step": 9031 }, { "epoch": 0.49878506737353656, "grad_norm": 3.547983407974243, "learning_rate": 2.1051244145931955e-05, "loss": 0.6369, "step": 9032 }, { "epoch": 0.49884029158383036, "grad_norm": 3.9217379093170166, "learning_rate": 2.1047671765347054e-05, "loss": 0.3869, "step": 9033 }, { "epoch": 0.49889551579412417, "grad_norm": 0.06611146777868271, "learning_rate": 2.1044099351244154e-05, "loss": 0.0017, "step": 9034 }, { "epoch": 0.4989507400044179, "grad_norm": 0.010209068655967712, "learning_rate": 2.104052690373754e-05, "loss": 0.0003, "step": 9035 }, { "epoch": 0.4990059642147117, "grad_norm": 1.943267583847046, "learning_rate": 2.103695442294151e-05, "loss": 0.0959, "step": 9036 }, { "epoch": 0.4990611884250055, "grad_norm": 0.011462518945336342, "learning_rate": 2.1033381908970357e-05, "loss": 0.0003, "step": 9037 }, { "epoch": 0.4991164126352993, "grad_norm": 1.0700461864471436, "learning_rate": 2.102980936193837e-05, "loss": 0.1121, "step": 9038 }, { "epoch": 0.4991716368455931, "grad_norm": 2.0562405586242676, "learning_rate": 2.102623678195985e-05, "loss": 0.2121, "step": 9039 }, { "epoch": 0.49922686105588693, "grad_norm": 0.4345874786376953, "learning_rate": 2.10226641691491e-05, "loss": 0.008, "step": 9040 }, { "epoch": 0.4992820852661807, "grad_norm": 3.3023500442504883, "learning_rate": 2.101909152362041e-05, "loss": 0.4622, "step": 9041 }, { "epoch": 0.4993373094764745, "grad_norm": 4.035273551940918, "learning_rate": 2.101551884548808e-05, "loss": 0.6311, "step": 9042 }, { "epoch": 0.4993925336867683, "grad_norm": 0.04120674356818199, "learning_rate": 2.1011946134866412e-05, "loss": 0.0013, "step": 9043 }, { "epoch": 0.4994477578970621, "grad_norm": 1.2030197381973267, "learning_rate": 2.10083733918697e-05, "loss": 0.0092, "step": 9044 }, { "epoch": 0.4995029821073559, "grad_norm": 0.6273332238197327, "learning_rate": 2.1004800616612256e-05, "loss": 0.0946, "step": 9045 }, { "epoch": 0.49955820631764963, "grad_norm": 0.1762818545103073, "learning_rate": 2.100122780920838e-05, "loss": 0.0065, "step": 9046 }, { "epoch": 0.49961343052794344, "grad_norm": 2.158801555633545, "learning_rate": 2.099765496977238e-05, "loss": 0.1654, "step": 9047 }, { "epoch": 0.49966865473823724, "grad_norm": 0.18711791932582855, "learning_rate": 2.0994082098418554e-05, "loss": 0.005, "step": 9048 }, { "epoch": 0.49972387894853104, "grad_norm": 0.03741571679711342, "learning_rate": 2.0990509195261213e-05, "loss": 0.0014, "step": 9049 }, { "epoch": 0.49977910315882484, "grad_norm": 4.151329517364502, "learning_rate": 2.0986936260414665e-05, "loss": 0.987, "step": 9050 }, { "epoch": 0.49983432736911865, "grad_norm": 0.5778416395187378, "learning_rate": 2.0983363293993205e-05, "loss": 0.0254, "step": 9051 }, { "epoch": 0.4998895515794124, "grad_norm": 0.7443971037864685, "learning_rate": 2.0979790296111163e-05, "loss": 0.0215, "step": 9052 }, { "epoch": 0.4999447757897062, "grad_norm": 0.9200392961502075, "learning_rate": 2.097621726688284e-05, "loss": 0.036, "step": 9053 }, { "epoch": 0.5, "grad_norm": 0.7596307992935181, "learning_rate": 2.0972644206422546e-05, "loss": 0.019, "step": 9054 }, { "epoch": 0.5000552242102938, "grad_norm": 0.9167304039001465, "learning_rate": 2.09690711148446e-05, "loss": 0.0744, "step": 9055 }, { "epoch": 0.5001104484205876, "grad_norm": 0.5098588466644287, "learning_rate": 2.0965497992263305e-05, "loss": 0.0105, "step": 9056 }, { "epoch": 0.5001656726308814, "grad_norm": 0.15073516964912415, "learning_rate": 2.0961924838792983e-05, "loss": 0.0037, "step": 9057 }, { "epoch": 0.5002208968411752, "grad_norm": 0.08018222451210022, "learning_rate": 2.0958351654547947e-05, "loss": 0.0023, "step": 9058 }, { "epoch": 0.500276121051469, "grad_norm": 0.652965247631073, "learning_rate": 2.0954778439642508e-05, "loss": 0.0178, "step": 9059 }, { "epoch": 0.5003313452617627, "grad_norm": 1.6411654949188232, "learning_rate": 2.0951205194190994e-05, "loss": 0.0605, "step": 9060 }, { "epoch": 0.5003865694720565, "grad_norm": 0.231351837515831, "learning_rate": 2.0947631918307714e-05, "loss": 0.0054, "step": 9061 }, { "epoch": 0.5004417936823503, "grad_norm": 0.292298823595047, "learning_rate": 2.0944058612106994e-05, "loss": 0.0074, "step": 9062 }, { "epoch": 0.5004970178926441, "grad_norm": 0.06967280805110931, "learning_rate": 2.0940485275703152e-05, "loss": 0.0019, "step": 9063 }, { "epoch": 0.5005522421029379, "grad_norm": 1.78874671459198, "learning_rate": 2.0936911909210505e-05, "loss": 0.08, "step": 9064 }, { "epoch": 0.5006074663132317, "grad_norm": 0.5880500078201294, "learning_rate": 2.093333851274338e-05, "loss": 0.0142, "step": 9065 }, { "epoch": 0.5006626905235255, "grad_norm": 2.516719102859497, "learning_rate": 2.0929765086416102e-05, "loss": 0.0775, "step": 9066 }, { "epoch": 0.5007179147338193, "grad_norm": 2.8565778732299805, "learning_rate": 2.0926191630342988e-05, "loss": 0.401, "step": 9067 }, { "epoch": 0.5007731389441131, "grad_norm": 2.250166654586792, "learning_rate": 2.0922618144638368e-05, "loss": 0.2115, "step": 9068 }, { "epoch": 0.5008283631544069, "grad_norm": 3.7246909141540527, "learning_rate": 2.0919044629416567e-05, "loss": 0.5179, "step": 9069 }, { "epoch": 0.5008835873647007, "grad_norm": 0.11673823744058609, "learning_rate": 2.0915471084791915e-05, "loss": 0.0038, "step": 9070 }, { "epoch": 0.5009388115749944, "grad_norm": 0.0623275563120842, "learning_rate": 2.0911897510878734e-05, "loss": 0.002, "step": 9071 }, { "epoch": 0.5009940357852882, "grad_norm": 2.7929117679595947, "learning_rate": 2.0908323907791353e-05, "loss": 0.206, "step": 9072 }, { "epoch": 0.501049259995582, "grad_norm": 3.9357051849365234, "learning_rate": 2.090475027564411e-05, "loss": 0.5407, "step": 9073 }, { "epoch": 0.5011044842058758, "grad_norm": 1.9525809288024902, "learning_rate": 2.0901176614551328e-05, "loss": 0.0944, "step": 9074 }, { "epoch": 0.5011597084161696, "grad_norm": 3.5941953659057617, "learning_rate": 2.0897602924627335e-05, "loss": 0.7843, "step": 9075 }, { "epoch": 0.5012149326264634, "grad_norm": 0.19134725630283356, "learning_rate": 2.0894029205986476e-05, "loss": 0.0072, "step": 9076 }, { "epoch": 0.5012701568367572, "grad_norm": 0.13726875185966492, "learning_rate": 2.0890455458743072e-05, "loss": 0.0053, "step": 9077 }, { "epoch": 0.501325381047051, "grad_norm": 1.4495667219161987, "learning_rate": 2.0886881683011468e-05, "loss": 0.0501, "step": 9078 }, { "epoch": 0.5013806052573448, "grad_norm": 4.774809837341309, "learning_rate": 2.088330787890599e-05, "loss": 0.9369, "step": 9079 }, { "epoch": 0.5014358294676386, "grad_norm": 1.8382703065872192, "learning_rate": 2.0879734046540983e-05, "loss": 0.0204, "step": 9080 }, { "epoch": 0.5014910536779325, "grad_norm": 0.3084361255168915, "learning_rate": 2.0876160186030776e-05, "loss": 0.0114, "step": 9081 }, { "epoch": 0.5015462778882261, "grad_norm": 0.20252160727977753, "learning_rate": 2.0872586297489713e-05, "loss": 0.0065, "step": 9082 }, { "epoch": 0.50160150209852, "grad_norm": 0.0931854322552681, "learning_rate": 2.0869012381032126e-05, "loss": 0.0021, "step": 9083 }, { "epoch": 0.5016567263088137, "grad_norm": 5.636804580688477, "learning_rate": 2.0865438436772362e-05, "loss": 0.4463, "step": 9084 }, { "epoch": 0.5017119505191076, "grad_norm": 0.04406875744462013, "learning_rate": 2.086186446482476e-05, "loss": 0.0015, "step": 9085 }, { "epoch": 0.5017671747294014, "grad_norm": 0.8235501050949097, "learning_rate": 2.0858290465303654e-05, "loss": 0.0629, "step": 9086 }, { "epoch": 0.5018223989396952, "grad_norm": 1.3599202632904053, "learning_rate": 2.08547164383234e-05, "loss": 0.043, "step": 9087 }, { "epoch": 0.501877623149989, "grad_norm": 3.3901848793029785, "learning_rate": 2.0851142383998327e-05, "loss": 0.3865, "step": 9088 }, { "epoch": 0.5019328473602828, "grad_norm": 1.8761874437332153, "learning_rate": 2.0847568302442793e-05, "loss": 0.1984, "step": 9089 }, { "epoch": 0.5019880715705766, "grad_norm": 0.04026021435856819, "learning_rate": 2.0843994193771125e-05, "loss": 0.001, "step": 9090 }, { "epoch": 0.5020432957808704, "grad_norm": 0.027074314653873444, "learning_rate": 2.0840420058097694e-05, "loss": 0.0009, "step": 9091 }, { "epoch": 0.5020985199911642, "grad_norm": 7.063852310180664, "learning_rate": 2.083684589553683e-05, "loss": 0.6259, "step": 9092 }, { "epoch": 0.502153744201458, "grad_norm": 0.0898795798420906, "learning_rate": 2.0833271706202874e-05, "loss": 0.0029, "step": 9093 }, { "epoch": 0.5022089684117517, "grad_norm": 0.10108155012130737, "learning_rate": 2.082969749021019e-05, "loss": 0.0023, "step": 9094 }, { "epoch": 0.5022641926220455, "grad_norm": 0.18563421070575714, "learning_rate": 2.0826123247673125e-05, "loss": 0.0063, "step": 9095 }, { "epoch": 0.5023194168323393, "grad_norm": 0.01424804050475359, "learning_rate": 2.082254897870602e-05, "loss": 0.0005, "step": 9096 }, { "epoch": 0.5023746410426331, "grad_norm": 3.3812692165374756, "learning_rate": 2.0818974683423228e-05, "loss": 0.4914, "step": 9097 }, { "epoch": 0.5024298652529269, "grad_norm": 1.7729787826538086, "learning_rate": 2.081540036193911e-05, "loss": 0.1868, "step": 9098 }, { "epoch": 0.5024850894632207, "grad_norm": 3.6616599559783936, "learning_rate": 2.0811826014368014e-05, "loss": 0.4846, "step": 9099 }, { "epoch": 0.5025403136735145, "grad_norm": 1.936521053314209, "learning_rate": 2.0808251640824292e-05, "loss": 0.2214, "step": 9100 }, { "epoch": 0.5025955378838083, "grad_norm": 3.2212255001068115, "learning_rate": 2.0804677241422294e-05, "loss": 0.5135, "step": 9101 }, { "epoch": 0.5026507620941021, "grad_norm": 3.9110219478607178, "learning_rate": 2.0801102816276387e-05, "loss": 0.2149, "step": 9102 }, { "epoch": 0.5027059863043959, "grad_norm": 0.012867903336882591, "learning_rate": 2.0797528365500922e-05, "loss": 0.0004, "step": 9103 }, { "epoch": 0.5027612105146897, "grad_norm": 2.9465718269348145, "learning_rate": 2.0793953889210244e-05, "loss": 0.3873, "step": 9104 }, { "epoch": 0.5028164347249834, "grad_norm": 0.03917544707655907, "learning_rate": 2.0790379387518728e-05, "loss": 0.001, "step": 9105 }, { "epoch": 0.5028716589352772, "grad_norm": 0.15473560988903046, "learning_rate": 2.078680486054072e-05, "loss": 0.0048, "step": 9106 }, { "epoch": 0.502926883145571, "grad_norm": 0.07125075906515121, "learning_rate": 2.078323030839059e-05, "loss": 0.0021, "step": 9107 }, { "epoch": 0.5029821073558648, "grad_norm": 1.0526635646820068, "learning_rate": 2.0779655731182693e-05, "loss": 0.0364, "step": 9108 }, { "epoch": 0.5030373315661586, "grad_norm": 0.09798844158649445, "learning_rate": 2.0776081129031386e-05, "loss": 0.0019, "step": 9109 }, { "epoch": 0.5030925557764524, "grad_norm": 2.6341402530670166, "learning_rate": 2.0772506502051035e-05, "loss": 0.27, "step": 9110 }, { "epoch": 0.5031477799867462, "grad_norm": 2.9622297286987305, "learning_rate": 2.0768931850356e-05, "loss": 0.425, "step": 9111 }, { "epoch": 0.50320300419704, "grad_norm": 2.4405975341796875, "learning_rate": 2.076535717406065e-05, "loss": 0.0846, "step": 9112 }, { "epoch": 0.5032582284073338, "grad_norm": 3.45251727104187, "learning_rate": 2.0761782473279347e-05, "loss": 0.3887, "step": 9113 }, { "epoch": 0.5033134526176276, "grad_norm": 4.931960105895996, "learning_rate": 2.0758207748126448e-05, "loss": 0.3911, "step": 9114 }, { "epoch": 0.5033686768279214, "grad_norm": 2.119295120239258, "learning_rate": 2.0754632998716328e-05, "loss": 0.0542, "step": 9115 }, { "epoch": 0.5034239010382151, "grad_norm": 0.25540876388549805, "learning_rate": 2.075105822516335e-05, "loss": 0.0091, "step": 9116 }, { "epoch": 0.5034791252485089, "grad_norm": 0.04891772195696831, "learning_rate": 2.0747483427581884e-05, "loss": 0.0018, "step": 9117 }, { "epoch": 0.5035343494588027, "grad_norm": 0.20000658929347992, "learning_rate": 2.0743908606086292e-05, "loss": 0.0058, "step": 9118 }, { "epoch": 0.5035895736690965, "grad_norm": 0.23146887123584747, "learning_rate": 2.074033376079094e-05, "loss": 0.0063, "step": 9119 }, { "epoch": 0.5036447978793903, "grad_norm": 4.197676181793213, "learning_rate": 2.0736758891810215e-05, "loss": 1.387, "step": 9120 }, { "epoch": 0.5037000220896841, "grad_norm": 7.001603126525879, "learning_rate": 2.0733183999258463e-05, "loss": 1.6335, "step": 9121 }, { "epoch": 0.5037552462999779, "grad_norm": 0.13593973219394684, "learning_rate": 2.072960908325008e-05, "loss": 0.0045, "step": 9122 }, { "epoch": 0.5038104705102717, "grad_norm": 1.905806541442871, "learning_rate": 2.072603414389942e-05, "loss": 0.044, "step": 9123 }, { "epoch": 0.5038656947205655, "grad_norm": 0.4669792950153351, "learning_rate": 2.0722459181320858e-05, "loss": 0.0072, "step": 9124 }, { "epoch": 0.5039209189308593, "grad_norm": 0.12835784256458282, "learning_rate": 2.0718884195628773e-05, "loss": 0.0033, "step": 9125 }, { "epoch": 0.5039761431411531, "grad_norm": 0.2695366442203522, "learning_rate": 2.0715309186937538e-05, "loss": 0.0062, "step": 9126 }, { "epoch": 0.5040313673514468, "grad_norm": 2.124032735824585, "learning_rate": 2.071173415536152e-05, "loss": 0.0621, "step": 9127 }, { "epoch": 0.5040865915617406, "grad_norm": 0.033241670578718185, "learning_rate": 2.0708159101015103e-05, "loss": 0.0009, "step": 9128 }, { "epoch": 0.5041418157720344, "grad_norm": 2.0496034622192383, "learning_rate": 2.0704584024012657e-05, "loss": 0.0769, "step": 9129 }, { "epoch": 0.5041970399823282, "grad_norm": 2.5460121631622314, "learning_rate": 2.070100892446857e-05, "loss": 0.1713, "step": 9130 }, { "epoch": 0.504252264192622, "grad_norm": 0.04098281264305115, "learning_rate": 2.0697433802497208e-05, "loss": 0.0012, "step": 9131 }, { "epoch": 0.5043074884029158, "grad_norm": 2.9964122772216797, "learning_rate": 2.069385865821295e-05, "loss": 0.3193, "step": 9132 }, { "epoch": 0.5043627126132096, "grad_norm": 0.06893374025821686, "learning_rate": 2.0690283491730182e-05, "loss": 0.0022, "step": 9133 }, { "epoch": 0.5044179368235034, "grad_norm": 0.7454213500022888, "learning_rate": 2.0686708303163278e-05, "loss": 0.0245, "step": 9134 }, { "epoch": 0.5044731610337972, "grad_norm": 0.11689326167106628, "learning_rate": 2.0683133092626623e-05, "loss": 0.0032, "step": 9135 }, { "epoch": 0.504528385244091, "grad_norm": 0.3754124641418457, "learning_rate": 2.0679557860234593e-05, "loss": 0.0084, "step": 9136 }, { "epoch": 0.5045836094543849, "grad_norm": 4.675313949584961, "learning_rate": 2.067598260610157e-05, "loss": 0.1052, "step": 9137 }, { "epoch": 0.5046388336646785, "grad_norm": 0.02117653749883175, "learning_rate": 2.0672407330341943e-05, "loss": 0.0007, "step": 9138 }, { "epoch": 0.5046940578749723, "grad_norm": 2.1736197471618652, "learning_rate": 2.0668832033070093e-05, "loss": 0.1325, "step": 9139 }, { "epoch": 0.5047492820852661, "grad_norm": 0.4954807162284851, "learning_rate": 2.0665256714400398e-05, "loss": 0.0146, "step": 9140 }, { "epoch": 0.50480450629556, "grad_norm": 1.415174126625061, "learning_rate": 2.066168137444725e-05, "loss": 0.0281, "step": 9141 }, { "epoch": 0.5048597305058538, "grad_norm": 5.53858757019043, "learning_rate": 2.065810601332503e-05, "loss": 0.693, "step": 9142 }, { "epoch": 0.5049149547161476, "grad_norm": 0.6761834025382996, "learning_rate": 2.0654530631148124e-05, "loss": 0.0183, "step": 9143 }, { "epoch": 0.5049701789264414, "grad_norm": 0.05949088931083679, "learning_rate": 2.065095522803092e-05, "loss": 0.0023, "step": 9144 }, { "epoch": 0.5050254031367352, "grad_norm": 0.01953493244946003, "learning_rate": 2.06473798040878e-05, "loss": 0.0006, "step": 9145 }, { "epoch": 0.505080627347029, "grad_norm": 0.03387872874736786, "learning_rate": 2.0643804359433167e-05, "loss": 0.001, "step": 9146 }, { "epoch": 0.5051358515573228, "grad_norm": 4.623629570007324, "learning_rate": 2.06402288941814e-05, "loss": 0.7017, "step": 9147 }, { "epoch": 0.5051910757676166, "grad_norm": 0.12794750928878784, "learning_rate": 2.0636653408446876e-05, "loss": 0.0056, "step": 9148 }, { "epoch": 0.5052462999779103, "grad_norm": 1.5295921564102173, "learning_rate": 2.0633077902344007e-05, "loss": 0.0975, "step": 9149 }, { "epoch": 0.5053015241882041, "grad_norm": 4.449501037597656, "learning_rate": 2.0629502375987166e-05, "loss": 0.7873, "step": 9150 }, { "epoch": 0.5053567483984979, "grad_norm": 4.897256851196289, "learning_rate": 2.0625926829490762e-05, "loss": 2.2409, "step": 9151 }, { "epoch": 0.5054119726087917, "grad_norm": 0.19596008956432343, "learning_rate": 2.0622351262969175e-05, "loss": 0.0025, "step": 9152 }, { "epoch": 0.5054671968190855, "grad_norm": 4.732868671417236, "learning_rate": 2.0618775676536787e-05, "loss": 1.1645, "step": 9153 }, { "epoch": 0.5055224210293793, "grad_norm": 0.052342820912599564, "learning_rate": 2.0615200070308016e-05, "loss": 0.0011, "step": 9154 }, { "epoch": 0.5055776452396731, "grad_norm": 1.2946988344192505, "learning_rate": 2.0611624444397242e-05, "loss": 0.1261, "step": 9155 }, { "epoch": 0.5056328694499669, "grad_norm": 4.739322185516357, "learning_rate": 2.0608048798918858e-05, "loss": 0.7803, "step": 9156 }, { "epoch": 0.5056880936602607, "grad_norm": 2.2768590450286865, "learning_rate": 2.060447313398726e-05, "loss": 0.3521, "step": 9157 }, { "epoch": 0.5057433178705545, "grad_norm": 2.841308116912842, "learning_rate": 2.060089744971685e-05, "loss": 0.1028, "step": 9158 }, { "epoch": 0.5057985420808483, "grad_norm": 0.13813120126724243, "learning_rate": 2.0597321746222018e-05, "loss": 0.004, "step": 9159 }, { "epoch": 0.505853766291142, "grad_norm": 0.7434695959091187, "learning_rate": 2.0593746023617164e-05, "loss": 0.026, "step": 9160 }, { "epoch": 0.5059089905014358, "grad_norm": 0.2257043421268463, "learning_rate": 2.059017028201668e-05, "loss": 0.0059, "step": 9161 }, { "epoch": 0.5059642147117296, "grad_norm": 0.22943562269210815, "learning_rate": 2.0586594521534974e-05, "loss": 0.005, "step": 9162 }, { "epoch": 0.5060194389220234, "grad_norm": 2.2405972480773926, "learning_rate": 2.058301874228644e-05, "loss": 0.1302, "step": 9163 }, { "epoch": 0.5060746631323172, "grad_norm": 1.2484792470932007, "learning_rate": 2.057944294438547e-05, "loss": 0.0313, "step": 9164 }, { "epoch": 0.506129887342611, "grad_norm": 0.9040282964706421, "learning_rate": 2.0575867127946475e-05, "loss": 0.0272, "step": 9165 }, { "epoch": 0.5061851115529048, "grad_norm": 5.635469436645508, "learning_rate": 2.0572291293083847e-05, "loss": 0.6234, "step": 9166 }, { "epoch": 0.5062403357631986, "grad_norm": 4.942932605743408, "learning_rate": 2.0568715439911995e-05, "loss": 1.2029, "step": 9167 }, { "epoch": 0.5062955599734924, "grad_norm": 3.8684372901916504, "learning_rate": 2.056513956854532e-05, "loss": 0.5581, "step": 9168 }, { "epoch": 0.5063507841837862, "grad_norm": 2.697748899459839, "learning_rate": 2.0561563679098215e-05, "loss": 0.6768, "step": 9169 }, { "epoch": 0.50640600839408, "grad_norm": 1.432975172996521, "learning_rate": 2.0557987771685094e-05, "loss": 0.0592, "step": 9170 }, { "epoch": 0.5064612326043738, "grad_norm": 3.275834798812866, "learning_rate": 2.0554411846420354e-05, "loss": 0.2786, "step": 9171 }, { "epoch": 0.5065164568146675, "grad_norm": 3.7425544261932373, "learning_rate": 2.0550835903418398e-05, "loss": 0.9524, "step": 9172 }, { "epoch": 0.5065716810249613, "grad_norm": 2.596126079559326, "learning_rate": 2.0547259942793637e-05, "loss": 0.1195, "step": 9173 }, { "epoch": 0.5066269052352551, "grad_norm": 1.5857168436050415, "learning_rate": 2.054368396466047e-05, "loss": 0.0282, "step": 9174 }, { "epoch": 0.5066821294455489, "grad_norm": 0.08900824189186096, "learning_rate": 2.0540107969133308e-05, "loss": 0.0026, "step": 9175 }, { "epoch": 0.5067373536558427, "grad_norm": 2.721142053604126, "learning_rate": 2.0536531956326558e-05, "loss": 0.2127, "step": 9176 }, { "epoch": 0.5067925778661365, "grad_norm": 6.697082996368408, "learning_rate": 2.0532955926354616e-05, "loss": 1.9307, "step": 9177 }, { "epoch": 0.5068478020764303, "grad_norm": 1.9812846183776855, "learning_rate": 2.0529379879331902e-05, "loss": 0.1083, "step": 9178 }, { "epoch": 0.5069030262867241, "grad_norm": 0.009617788717150688, "learning_rate": 2.0525803815372815e-05, "loss": 0.0003, "step": 9179 }, { "epoch": 0.5069582504970179, "grad_norm": 0.8197235465049744, "learning_rate": 2.052222773459177e-05, "loss": 0.0314, "step": 9180 }, { "epoch": 0.5070134747073117, "grad_norm": 0.7067477703094482, "learning_rate": 2.0518651637103163e-05, "loss": 0.0222, "step": 9181 }, { "epoch": 0.5070686989176055, "grad_norm": 1.715024709701538, "learning_rate": 2.0515075523021423e-05, "loss": 0.2085, "step": 9182 }, { "epoch": 0.5071239231278992, "grad_norm": 0.17483367025852203, "learning_rate": 2.0511499392460948e-05, "loss": 0.0038, "step": 9183 }, { "epoch": 0.507179147338193, "grad_norm": 2.8375301361083984, "learning_rate": 2.0507923245536153e-05, "loss": 0.2367, "step": 9184 }, { "epoch": 0.5072343715484868, "grad_norm": 0.02154131978750229, "learning_rate": 2.0504347082361447e-05, "loss": 0.0005, "step": 9185 }, { "epoch": 0.5072895957587806, "grad_norm": 1.827654242515564, "learning_rate": 2.0500770903051244e-05, "loss": 0.1224, "step": 9186 }, { "epoch": 0.5073448199690744, "grad_norm": 6.652122497558594, "learning_rate": 2.049719470771995e-05, "loss": 1.1507, "step": 9187 }, { "epoch": 0.5074000441793682, "grad_norm": 0.7508941888809204, "learning_rate": 2.0493618496481985e-05, "loss": 0.0319, "step": 9188 }, { "epoch": 0.507455268389662, "grad_norm": 1.8707329034805298, "learning_rate": 2.0490042269451752e-05, "loss": 0.2936, "step": 9189 }, { "epoch": 0.5075104925999558, "grad_norm": 0.04238812252879143, "learning_rate": 2.048646602674368e-05, "loss": 0.0009, "step": 9190 }, { "epoch": 0.5075657168102496, "grad_norm": 3.7308833599090576, "learning_rate": 2.0482889768472173e-05, "loss": 0.902, "step": 9191 }, { "epoch": 0.5076209410205434, "grad_norm": 1.7737501859664917, "learning_rate": 2.0479313494751647e-05, "loss": 0.0171, "step": 9192 }, { "epoch": 0.5076761652308373, "grad_norm": 0.29550039768218994, "learning_rate": 2.047573720569652e-05, "loss": 0.0064, "step": 9193 }, { "epoch": 0.5077313894411309, "grad_norm": 3.7912635803222656, "learning_rate": 2.0472160901421205e-05, "loss": 0.652, "step": 9194 }, { "epoch": 0.5077866136514247, "grad_norm": 3.2421717643737793, "learning_rate": 2.046858458204011e-05, "loss": 0.2798, "step": 9195 }, { "epoch": 0.5078418378617185, "grad_norm": 0.008572143502533436, "learning_rate": 2.046500824766767e-05, "loss": 0.0003, "step": 9196 }, { "epoch": 0.5078970620720124, "grad_norm": 3.8102312088012695, "learning_rate": 2.0461431898418284e-05, "loss": 0.2715, "step": 9197 }, { "epoch": 0.5079522862823062, "grad_norm": 2.7498488426208496, "learning_rate": 2.0457855534406388e-05, "loss": 0.2422, "step": 9198 }, { "epoch": 0.5080075104926, "grad_norm": 4.376546859741211, "learning_rate": 2.0454279155746385e-05, "loss": 1.1397, "step": 9199 }, { "epoch": 0.5080627347028938, "grad_norm": 0.9645074009895325, "learning_rate": 2.0450702762552696e-05, "loss": 0.1586, "step": 9200 }, { "epoch": 0.5081179589131876, "grad_norm": 1.9545905590057373, "learning_rate": 2.0447126354939745e-05, "loss": 0.0816, "step": 9201 }, { "epoch": 0.5081731831234814, "grad_norm": 0.6461217999458313, "learning_rate": 2.0443549933021952e-05, "loss": 0.0119, "step": 9202 }, { "epoch": 0.5082284073337752, "grad_norm": 1.2834727764129639, "learning_rate": 2.043997349691373e-05, "loss": 0.0623, "step": 9203 }, { "epoch": 0.508283631544069, "grad_norm": 2.691890239715576, "learning_rate": 2.0436397046729505e-05, "loss": 0.2466, "step": 9204 }, { "epoch": 0.5083388557543627, "grad_norm": 0.21895438432693481, "learning_rate": 2.043282058258369e-05, "loss": 0.0068, "step": 9205 }, { "epoch": 0.5083940799646565, "grad_norm": 5.043296813964844, "learning_rate": 2.0429244104590718e-05, "loss": 0.6699, "step": 9206 }, { "epoch": 0.5084493041749503, "grad_norm": 4.576726913452148, "learning_rate": 2.042566761286501e-05, "loss": 0.3044, "step": 9207 }, { "epoch": 0.5085045283852441, "grad_norm": 0.00870799832046032, "learning_rate": 2.0422091107520977e-05, "loss": 0.0003, "step": 9208 }, { "epoch": 0.5085597525955379, "grad_norm": 0.06353044509887695, "learning_rate": 2.0418514588673048e-05, "loss": 0.0014, "step": 9209 }, { "epoch": 0.5086149768058317, "grad_norm": 3.4612302780151367, "learning_rate": 2.0414938056435644e-05, "loss": 0.6, "step": 9210 }, { "epoch": 0.5086702010161255, "grad_norm": 0.39503684639930725, "learning_rate": 2.0411361510923195e-05, "loss": 0.0097, "step": 9211 }, { "epoch": 0.5087254252264193, "grad_norm": 1.8452188968658447, "learning_rate": 2.0407784952250117e-05, "loss": 0.085, "step": 9212 }, { "epoch": 0.5087806494367131, "grad_norm": 2.952329158782959, "learning_rate": 2.0404208380530838e-05, "loss": 0.3389, "step": 9213 }, { "epoch": 0.5088358736470069, "grad_norm": 3.4343390464782715, "learning_rate": 2.0400631795879785e-05, "loss": 0.4916, "step": 9214 }, { "epoch": 0.5088910978573007, "grad_norm": 2.025256395339966, "learning_rate": 2.039705519841138e-05, "loss": 0.1334, "step": 9215 }, { "epoch": 0.5089463220675944, "grad_norm": 4.675699710845947, "learning_rate": 2.0393478588240042e-05, "loss": 0.5237, "step": 9216 }, { "epoch": 0.5090015462778882, "grad_norm": 3.754930257797241, "learning_rate": 2.038990196548021e-05, "loss": 0.4249, "step": 9217 }, { "epoch": 0.509056770488182, "grad_norm": 0.17808499932289124, "learning_rate": 2.03863253302463e-05, "loss": 0.0042, "step": 9218 }, { "epoch": 0.5091119946984758, "grad_norm": 0.27649420499801636, "learning_rate": 2.0382748682652748e-05, "loss": 0.005, "step": 9219 }, { "epoch": 0.5091672189087696, "grad_norm": 0.7868707776069641, "learning_rate": 2.037917202281398e-05, "loss": 0.0187, "step": 9220 }, { "epoch": 0.5092224431190634, "grad_norm": 0.10177735984325409, "learning_rate": 2.037559535084441e-05, "loss": 0.0031, "step": 9221 }, { "epoch": 0.5092776673293572, "grad_norm": 0.1952006220817566, "learning_rate": 2.037201866685848e-05, "loss": 0.0062, "step": 9222 }, { "epoch": 0.509332891539651, "grad_norm": 4.272674560546875, "learning_rate": 2.0368441970970613e-05, "loss": 0.3702, "step": 9223 }, { "epoch": 0.5093881157499448, "grad_norm": 2.1043860912323, "learning_rate": 2.036486526329523e-05, "loss": 0.5303, "step": 9224 }, { "epoch": 0.5094433399602386, "grad_norm": 3.1972594261169434, "learning_rate": 2.0361288543946783e-05, "loss": 0.2914, "step": 9225 }, { "epoch": 0.5094985641705324, "grad_norm": 2.026855945587158, "learning_rate": 2.0357711813039675e-05, "loss": 0.3578, "step": 9226 }, { "epoch": 0.5095537883808261, "grad_norm": 2.567199468612671, "learning_rate": 2.0354135070688357e-05, "loss": 0.1587, "step": 9227 }, { "epoch": 0.5096090125911199, "grad_norm": 3.920717477798462, "learning_rate": 2.0350558317007247e-05, "loss": 0.4141, "step": 9228 }, { "epoch": 0.5096642368014137, "grad_norm": 2.600858449935913, "learning_rate": 2.0346981552110778e-05, "loss": 0.2431, "step": 9229 }, { "epoch": 0.5097194610117075, "grad_norm": 0.309525728225708, "learning_rate": 2.034340477611338e-05, "loss": 0.007, "step": 9230 }, { "epoch": 0.5097746852220013, "grad_norm": 0.34213361144065857, "learning_rate": 2.033982798912949e-05, "loss": 0.0058, "step": 9231 }, { "epoch": 0.5098299094322951, "grad_norm": 0.84356290102005, "learning_rate": 2.0336251191273527e-05, "loss": 0.0162, "step": 9232 }, { "epoch": 0.5098851336425889, "grad_norm": 2.0359153747558594, "learning_rate": 2.033267438265994e-05, "loss": 0.3137, "step": 9233 }, { "epoch": 0.5099403578528827, "grad_norm": 0.17031322419643402, "learning_rate": 2.032909756340314e-05, "loss": 0.0047, "step": 9234 }, { "epoch": 0.5099955820631765, "grad_norm": 0.12367536872625351, "learning_rate": 2.0325520733617585e-05, "loss": 0.0032, "step": 9235 }, { "epoch": 0.5100508062734703, "grad_norm": 0.4682874083518982, "learning_rate": 2.032194389341769e-05, "loss": 0.017, "step": 9236 }, { "epoch": 0.5101060304837641, "grad_norm": 0.027274152263998985, "learning_rate": 2.0318367042917897e-05, "loss": 0.0011, "step": 9237 }, { "epoch": 0.5101612546940578, "grad_norm": 0.08401540666818619, "learning_rate": 2.031479018223263e-05, "loss": 0.002, "step": 9238 }, { "epoch": 0.5102164789043516, "grad_norm": 3.9085259437561035, "learning_rate": 2.031121331147633e-05, "loss": 1.0687, "step": 9239 }, { "epoch": 0.5102717031146454, "grad_norm": 0.09337925910949707, "learning_rate": 2.0307636430763434e-05, "loss": 0.002, "step": 9240 }, { "epoch": 0.5103269273249392, "grad_norm": 2.6605141162872314, "learning_rate": 2.0304059540208366e-05, "loss": 0.4929, "step": 9241 }, { "epoch": 0.510382151535233, "grad_norm": 0.42761892080307007, "learning_rate": 2.0300482639925576e-05, "loss": 0.0121, "step": 9242 }, { "epoch": 0.5104373757455268, "grad_norm": 3.2031872272491455, "learning_rate": 2.0296905730029487e-05, "loss": 0.9626, "step": 9243 }, { "epoch": 0.5104925999558206, "grad_norm": 2.207054615020752, "learning_rate": 2.0293328810634536e-05, "loss": 0.1885, "step": 9244 }, { "epoch": 0.5105478241661144, "grad_norm": 1.4620450735092163, "learning_rate": 2.0289751881855166e-05, "loss": 0.1785, "step": 9245 }, { "epoch": 0.5106030483764082, "grad_norm": 3.545341968536377, "learning_rate": 2.028617494380581e-05, "loss": 0.9365, "step": 9246 }, { "epoch": 0.510658272586702, "grad_norm": 2.232513189315796, "learning_rate": 2.0282597996600893e-05, "loss": 0.1721, "step": 9247 }, { "epoch": 0.5107134967969958, "grad_norm": 2.2735424041748047, "learning_rate": 2.0279021040354873e-05, "loss": 0.2922, "step": 9248 }, { "epoch": 0.5107687210072896, "grad_norm": 2.515204906463623, "learning_rate": 2.0275444075182166e-05, "loss": 0.1075, "step": 9249 }, { "epoch": 0.5108239452175833, "grad_norm": 1.5548499822616577, "learning_rate": 2.0271867101197223e-05, "loss": 0.1809, "step": 9250 }, { "epoch": 0.5108791694278771, "grad_norm": 3.0305159091949463, "learning_rate": 2.0268290118514478e-05, "loss": 0.2962, "step": 9251 }, { "epoch": 0.510934393638171, "grad_norm": 1.1420633792877197, "learning_rate": 2.026471312724837e-05, "loss": 0.025, "step": 9252 }, { "epoch": 0.5109896178484647, "grad_norm": 6.022318363189697, "learning_rate": 2.026113612751333e-05, "loss": 2.0265, "step": 9253 }, { "epoch": 0.5110448420587586, "grad_norm": 3.4597043991088867, "learning_rate": 2.0257559119423807e-05, "loss": 0.1962, "step": 9254 }, { "epoch": 0.5111000662690524, "grad_norm": 2.9651527404785156, "learning_rate": 2.025398210309423e-05, "loss": 0.4894, "step": 9255 }, { "epoch": 0.5111552904793462, "grad_norm": 4.271976947784424, "learning_rate": 2.0250405078639046e-05, "loss": 0.6568, "step": 9256 }, { "epoch": 0.51121051468964, "grad_norm": 0.260593056678772, "learning_rate": 2.0246828046172688e-05, "loss": 0.0052, "step": 9257 }, { "epoch": 0.5112657388999338, "grad_norm": 4.349380970001221, "learning_rate": 2.0243251005809598e-05, "loss": 0.734, "step": 9258 }, { "epoch": 0.5113209631102276, "grad_norm": 4.304101943969727, "learning_rate": 2.0239673957664224e-05, "loss": 0.6024, "step": 9259 }, { "epoch": 0.5113761873205214, "grad_norm": 0.47793301939964294, "learning_rate": 2.0236096901850985e-05, "loss": 0.0121, "step": 9260 }, { "epoch": 0.5114314115308151, "grad_norm": 5.88646125793457, "learning_rate": 2.0232519838484347e-05, "loss": 1.5504, "step": 9261 }, { "epoch": 0.5114866357411089, "grad_norm": 0.08902934193611145, "learning_rate": 2.0228942767678727e-05, "loss": 0.0016, "step": 9262 }, { "epoch": 0.5115418599514027, "grad_norm": 3.922708034515381, "learning_rate": 2.0225365689548576e-05, "loss": 0.594, "step": 9263 }, { "epoch": 0.5115970841616965, "grad_norm": 0.08189284801483154, "learning_rate": 2.0221788604208345e-05, "loss": 0.0021, "step": 9264 }, { "epoch": 0.5116523083719903, "grad_norm": 1.1552131175994873, "learning_rate": 2.0218211511772457e-05, "loss": 0.0409, "step": 9265 }, { "epoch": 0.5117075325822841, "grad_norm": 0.3941735029220581, "learning_rate": 2.0214634412355365e-05, "loss": 0.0117, "step": 9266 }, { "epoch": 0.5117627567925779, "grad_norm": 0.02776963636279106, "learning_rate": 2.0211057306071506e-05, "loss": 0.0009, "step": 9267 }, { "epoch": 0.5118179810028717, "grad_norm": 0.0055311559699475765, "learning_rate": 2.020748019303532e-05, "loss": 0.0002, "step": 9268 }, { "epoch": 0.5118732052131655, "grad_norm": 4.463985443115234, "learning_rate": 2.0203903073361256e-05, "loss": 0.6581, "step": 9269 }, { "epoch": 0.5119284294234593, "grad_norm": 6.010798454284668, "learning_rate": 2.0200325947163746e-05, "loss": 1.2183, "step": 9270 }, { "epoch": 0.5119836536337531, "grad_norm": 0.02054665796458721, "learning_rate": 2.0196748814557247e-05, "loss": 0.0006, "step": 9271 }, { "epoch": 0.5120388778440468, "grad_norm": 0.05199979990720749, "learning_rate": 2.019317167565619e-05, "loss": 0.0018, "step": 9272 }, { "epoch": 0.5120941020543406, "grad_norm": 1.1406322717666626, "learning_rate": 2.0189594530575015e-05, "loss": 0.0223, "step": 9273 }, { "epoch": 0.5121493262646344, "grad_norm": 3.802541494369507, "learning_rate": 2.018601737942818e-05, "loss": 0.4495, "step": 9274 }, { "epoch": 0.5122045504749282, "grad_norm": 0.41523128747940063, "learning_rate": 2.018244022233012e-05, "loss": 0.0093, "step": 9275 }, { "epoch": 0.512259774685222, "grad_norm": 6.007911205291748, "learning_rate": 2.017886305939527e-05, "loss": 1.0947, "step": 9276 }, { "epoch": 0.5123149988955158, "grad_norm": 0.10658812522888184, "learning_rate": 2.017528589073809e-05, "loss": 0.0026, "step": 9277 }, { "epoch": 0.5123702231058096, "grad_norm": 2.3838281631469727, "learning_rate": 2.0171708716473007e-05, "loss": 0.2788, "step": 9278 }, { "epoch": 0.5124254473161034, "grad_norm": 0.35133394598960876, "learning_rate": 2.016813153671448e-05, "loss": 0.0059, "step": 9279 }, { "epoch": 0.5124806715263972, "grad_norm": 1.3238269090652466, "learning_rate": 2.0164554351576946e-05, "loss": 0.0624, "step": 9280 }, { "epoch": 0.512535895736691, "grad_norm": 1.2939472198486328, "learning_rate": 2.0160977161174845e-05, "loss": 0.0582, "step": 9281 }, { "epoch": 0.5125911199469848, "grad_norm": 0.21940919756889343, "learning_rate": 2.015739996562263e-05, "loss": 0.0067, "step": 9282 }, { "epoch": 0.5126463441572785, "grad_norm": 1.0627467632293701, "learning_rate": 2.0153822765034744e-05, "loss": 0.0258, "step": 9283 }, { "epoch": 0.5127015683675723, "grad_norm": 2.3686513900756836, "learning_rate": 2.0150245559525623e-05, "loss": 0.1262, "step": 9284 }, { "epoch": 0.5127567925778661, "grad_norm": 0.04513033851981163, "learning_rate": 2.0146668349209726e-05, "loss": 0.0012, "step": 9285 }, { "epoch": 0.5128120167881599, "grad_norm": 0.16626062989234924, "learning_rate": 2.0143091134201483e-05, "loss": 0.0048, "step": 9286 }, { "epoch": 0.5128672409984537, "grad_norm": 1.6775950193405151, "learning_rate": 2.0139513914615353e-05, "loss": 0.0564, "step": 9287 }, { "epoch": 0.5129224652087475, "grad_norm": 3.266890525817871, "learning_rate": 2.0135936690565782e-05, "loss": 1.2287, "step": 9288 }, { "epoch": 0.5129776894190413, "grad_norm": 0.009548199363052845, "learning_rate": 2.0132359462167195e-05, "loss": 0.0003, "step": 9289 }, { "epoch": 0.5130329136293351, "grad_norm": 2.6513638496398926, "learning_rate": 2.0128782229534064e-05, "loss": 0.0225, "step": 9290 }, { "epoch": 0.5130881378396289, "grad_norm": 3.123109817504883, "learning_rate": 2.0125204992780815e-05, "loss": 0.2114, "step": 9291 }, { "epoch": 0.5131433620499227, "grad_norm": 0.4861851930618286, "learning_rate": 2.0121627752021906e-05, "loss": 0.0151, "step": 9292 }, { "epoch": 0.5131985862602165, "grad_norm": 0.11846350133419037, "learning_rate": 2.0118050507371776e-05, "loss": 0.0026, "step": 9293 }, { "epoch": 0.5132538104705102, "grad_norm": 0.29884085059165955, "learning_rate": 2.0114473258944875e-05, "loss": 0.0099, "step": 9294 }, { "epoch": 0.513309034680804, "grad_norm": 0.7674614191055298, "learning_rate": 2.011089600685565e-05, "loss": 0.0113, "step": 9295 }, { "epoch": 0.5133642588910978, "grad_norm": 2.8832411766052246, "learning_rate": 2.010731875121855e-05, "loss": 0.0753, "step": 9296 }, { "epoch": 0.5134194831013916, "grad_norm": 0.05292479321360588, "learning_rate": 2.0103741492148014e-05, "loss": 0.0016, "step": 9297 }, { "epoch": 0.5134747073116854, "grad_norm": 2.7072598934173584, "learning_rate": 2.0100164229758493e-05, "loss": 0.1108, "step": 9298 }, { "epoch": 0.5135299315219792, "grad_norm": 4.953305721282959, "learning_rate": 2.009658696416443e-05, "loss": 0.7387, "step": 9299 }, { "epoch": 0.513585155732273, "grad_norm": 7.472039699554443, "learning_rate": 2.0093009695480274e-05, "loss": 1.9178, "step": 9300 }, { "epoch": 0.5136403799425668, "grad_norm": 4.994480609893799, "learning_rate": 2.0089432423820476e-05, "loss": 0.9766, "step": 9301 }, { "epoch": 0.5136956041528606, "grad_norm": 1.618304967880249, "learning_rate": 2.008585514929948e-05, "loss": 0.0305, "step": 9302 }, { "epoch": 0.5137508283631544, "grad_norm": 1.5219852924346924, "learning_rate": 2.008227787203174e-05, "loss": 0.0524, "step": 9303 }, { "epoch": 0.5138060525734482, "grad_norm": 0.015148499980568886, "learning_rate": 2.0078700592131685e-05, "loss": 0.0005, "step": 9304 }, { "epoch": 0.5138612767837419, "grad_norm": 0.35641998052597046, "learning_rate": 2.007512330971378e-05, "loss": 0.0086, "step": 9305 }, { "epoch": 0.5139165009940357, "grad_norm": 2.361492156982422, "learning_rate": 2.0071546024892467e-05, "loss": 0.1484, "step": 9306 }, { "epoch": 0.5139717252043295, "grad_norm": 1.8154261112213135, "learning_rate": 2.0067968737782188e-05, "loss": 0.3453, "step": 9307 }, { "epoch": 0.5140269494146233, "grad_norm": 3.4278721809387207, "learning_rate": 2.00643914484974e-05, "loss": 0.9411, "step": 9308 }, { "epoch": 0.5140821736249171, "grad_norm": 4.689221382141113, "learning_rate": 2.0060814157152538e-05, "loss": 0.9669, "step": 9309 }, { "epoch": 0.514137397835211, "grad_norm": 3.668909788131714, "learning_rate": 2.005723686386207e-05, "loss": 0.1544, "step": 9310 }, { "epoch": 0.5141926220455048, "grad_norm": 0.44571661949157715, "learning_rate": 2.0053659568740427e-05, "loss": 0.0118, "step": 9311 }, { "epoch": 0.5142478462557986, "grad_norm": 0.2592793405056, "learning_rate": 2.005008227190206e-05, "loss": 0.0068, "step": 9312 }, { "epoch": 0.5143030704660924, "grad_norm": 0.231342151761055, "learning_rate": 2.004650497346142e-05, "loss": 0.0054, "step": 9313 }, { "epoch": 0.5143582946763862, "grad_norm": 3.6735239028930664, "learning_rate": 2.0042927673532957e-05, "loss": 0.2825, "step": 9314 }, { "epoch": 0.51441351888668, "grad_norm": 1.046523928642273, "learning_rate": 2.003935037223111e-05, "loss": 0.1592, "step": 9315 }, { "epoch": 0.5144687430969738, "grad_norm": 0.07259810715913773, "learning_rate": 2.0035773069670335e-05, "loss": 0.0013, "step": 9316 }, { "epoch": 0.5145239673072675, "grad_norm": 0.4756336510181427, "learning_rate": 2.0032195765965078e-05, "loss": 0.0157, "step": 9317 }, { "epoch": 0.5145791915175613, "grad_norm": 0.554744303226471, "learning_rate": 2.002861846122978e-05, "loss": 0.014, "step": 9318 }, { "epoch": 0.5146344157278551, "grad_norm": 3.603243589401245, "learning_rate": 2.002504115557891e-05, "loss": 0.747, "step": 9319 }, { "epoch": 0.5146896399381489, "grad_norm": 5.036639213562012, "learning_rate": 2.002146384912689e-05, "loss": 0.5686, "step": 9320 }, { "epoch": 0.5147448641484427, "grad_norm": 2.0799789428710938, "learning_rate": 2.001788654198819e-05, "loss": 0.0718, "step": 9321 }, { "epoch": 0.5148000883587365, "grad_norm": 0.509046733379364, "learning_rate": 2.0014309234277242e-05, "loss": 0.0097, "step": 9322 }, { "epoch": 0.5148553125690303, "grad_norm": 5.795633316040039, "learning_rate": 2.00107319261085e-05, "loss": 0.7131, "step": 9323 }, { "epoch": 0.5149105367793241, "grad_norm": 4.130279541015625, "learning_rate": 2.0007154617596412e-05, "loss": 0.1694, "step": 9324 }, { "epoch": 0.5149657609896179, "grad_norm": 0.06706362962722778, "learning_rate": 2.000357730885543e-05, "loss": 0.0016, "step": 9325 }, { "epoch": 0.5150209851999117, "grad_norm": 0.22108194231987, "learning_rate": 2e-05, "loss": 0.0061, "step": 9326 }, { "epoch": 0.5150762094102055, "grad_norm": 0.08196214586496353, "learning_rate": 1.9996422691144574e-05, "loss": 0.0022, "step": 9327 }, { "epoch": 0.5151314336204992, "grad_norm": 2.0926661491394043, "learning_rate": 1.999284538240359e-05, "loss": 0.0553, "step": 9328 }, { "epoch": 0.515186657830793, "grad_norm": 1.0088319778442383, "learning_rate": 1.9989268073891513e-05, "loss": 0.0203, "step": 9329 }, { "epoch": 0.5152418820410868, "grad_norm": 4.935739517211914, "learning_rate": 1.9985690765722765e-05, "loss": 0.3286, "step": 9330 }, { "epoch": 0.5152971062513806, "grad_norm": 2.1105353832244873, "learning_rate": 1.9982113458011825e-05, "loss": 0.1297, "step": 9331 }, { "epoch": 0.5153523304616744, "grad_norm": 2.7019925117492676, "learning_rate": 1.9978536150873116e-05, "loss": 0.1807, "step": 9332 }, { "epoch": 0.5154075546719682, "grad_norm": 3.322901487350464, "learning_rate": 1.99749588444211e-05, "loss": 0.1765, "step": 9333 }, { "epoch": 0.515462778882262, "grad_norm": 0.029845573008060455, "learning_rate": 1.9971381538770222e-05, "loss": 0.0007, "step": 9334 }, { "epoch": 0.5155180030925558, "grad_norm": 0.04193104803562164, "learning_rate": 1.9967804234034932e-05, "loss": 0.0008, "step": 9335 }, { "epoch": 0.5155732273028496, "grad_norm": 0.025677813217043877, "learning_rate": 1.996422693032967e-05, "loss": 0.0008, "step": 9336 }, { "epoch": 0.5156284515131434, "grad_norm": 1.587132453918457, "learning_rate": 1.99606496277689e-05, "loss": 0.0534, "step": 9337 }, { "epoch": 0.5156836757234372, "grad_norm": 2.078230381011963, "learning_rate": 1.995707232646705e-05, "loss": 0.1051, "step": 9338 }, { "epoch": 0.5157388999337309, "grad_norm": 0.36874598264694214, "learning_rate": 1.9953495026538587e-05, "loss": 0.006, "step": 9339 }, { "epoch": 0.5157941241440247, "grad_norm": 0.21543091535568237, "learning_rate": 1.9949917728097944e-05, "loss": 0.0061, "step": 9340 }, { "epoch": 0.5158493483543185, "grad_norm": 0.1171666607260704, "learning_rate": 1.994634043125958e-05, "loss": 0.0037, "step": 9341 }, { "epoch": 0.5159045725646123, "grad_norm": 1.5893760919570923, "learning_rate": 1.9942763136137934e-05, "loss": 0.0364, "step": 9342 }, { "epoch": 0.5159597967749061, "grad_norm": 0.034326519817113876, "learning_rate": 1.9939185842847465e-05, "loss": 0.0006, "step": 9343 }, { "epoch": 0.5160150209851999, "grad_norm": 3.9711837768554688, "learning_rate": 1.9935608551502608e-05, "loss": 1.2772, "step": 9344 }, { "epoch": 0.5160702451954937, "grad_norm": 1.2808305025100708, "learning_rate": 1.9932031262217822e-05, "loss": 0.0359, "step": 9345 }, { "epoch": 0.5161254694057875, "grad_norm": 0.18960528075695038, "learning_rate": 1.992845397510754e-05, "loss": 0.0061, "step": 9346 }, { "epoch": 0.5161806936160813, "grad_norm": 0.22193697094917297, "learning_rate": 1.992487669028623e-05, "loss": 0.0086, "step": 9347 }, { "epoch": 0.5162359178263751, "grad_norm": 5.207141876220703, "learning_rate": 1.9921299407868325e-05, "loss": 0.3956, "step": 9348 }, { "epoch": 0.5162911420366689, "grad_norm": 0.5105049014091492, "learning_rate": 1.9917722127968275e-05, "loss": 0.0074, "step": 9349 }, { "epoch": 0.5163463662469626, "grad_norm": 0.2373834103345871, "learning_rate": 1.9914144850700525e-05, "loss": 0.0057, "step": 9350 }, { "epoch": 0.5164015904572564, "grad_norm": 0.1774715781211853, "learning_rate": 1.991056757617953e-05, "loss": 0.0031, "step": 9351 }, { "epoch": 0.5164568146675502, "grad_norm": 0.061511073261499405, "learning_rate": 1.990699030451973e-05, "loss": 0.002, "step": 9352 }, { "epoch": 0.516512038877844, "grad_norm": 0.46241557598114014, "learning_rate": 1.990341303583558e-05, "loss": 0.0085, "step": 9353 }, { "epoch": 0.5165672630881378, "grad_norm": 2.8388633728027344, "learning_rate": 1.9899835770241514e-05, "loss": 0.915, "step": 9354 }, { "epoch": 0.5166224872984316, "grad_norm": 0.675972044467926, "learning_rate": 1.9896258507851996e-05, "loss": 0.0202, "step": 9355 }, { "epoch": 0.5166777115087254, "grad_norm": 2.0670416355133057, "learning_rate": 1.989268124878146e-05, "loss": 0.0522, "step": 9356 }, { "epoch": 0.5167329357190192, "grad_norm": 0.4592411518096924, "learning_rate": 1.9889103993144352e-05, "loss": 0.0079, "step": 9357 }, { "epoch": 0.516788159929313, "grad_norm": 0.2020440250635147, "learning_rate": 1.9885526741055125e-05, "loss": 0.0024, "step": 9358 }, { "epoch": 0.5168433841396068, "grad_norm": 1.2418662309646606, "learning_rate": 1.9881949492628227e-05, "loss": 0.0547, "step": 9359 }, { "epoch": 0.5168986083499006, "grad_norm": 0.24262967705726624, "learning_rate": 1.9878372247978097e-05, "loss": 0.0045, "step": 9360 }, { "epoch": 0.5169538325601943, "grad_norm": 0.6403864026069641, "learning_rate": 1.987479500721919e-05, "loss": 0.0969, "step": 9361 }, { "epoch": 0.5170090567704881, "grad_norm": 2.769230365753174, "learning_rate": 1.987121777046594e-05, "loss": 0.1399, "step": 9362 }, { "epoch": 0.5170642809807819, "grad_norm": 0.4415878355503082, "learning_rate": 1.9867640537832808e-05, "loss": 0.0094, "step": 9363 }, { "epoch": 0.5171195051910757, "grad_norm": 0.10056834667921066, "learning_rate": 1.9864063309434228e-05, "loss": 0.0029, "step": 9364 }, { "epoch": 0.5171747294013695, "grad_norm": 0.5281997323036194, "learning_rate": 1.986048608538465e-05, "loss": 0.0164, "step": 9365 }, { "epoch": 0.5172299536116634, "grad_norm": 1.6404870748519897, "learning_rate": 1.9856908865798516e-05, "loss": 0.0886, "step": 9366 }, { "epoch": 0.5172851778219572, "grad_norm": 5.637039661407471, "learning_rate": 1.985333165079028e-05, "loss": 0.3942, "step": 9367 }, { "epoch": 0.517340402032251, "grad_norm": 0.5212289690971375, "learning_rate": 1.9849754440474377e-05, "loss": 0.0057, "step": 9368 }, { "epoch": 0.5173956262425448, "grad_norm": 0.5851573348045349, "learning_rate": 1.9846177234965263e-05, "loss": 0.0181, "step": 9369 }, { "epoch": 0.5174508504528386, "grad_norm": 0.13786344230175018, "learning_rate": 1.984260003437737e-05, "loss": 0.004, "step": 9370 }, { "epoch": 0.5175060746631324, "grad_norm": 3.3285679817199707, "learning_rate": 1.9839022838825162e-05, "loss": 0.7569, "step": 9371 }, { "epoch": 0.5175612988734261, "grad_norm": 0.12907984852790833, "learning_rate": 1.983544564842306e-05, "loss": 0.0035, "step": 9372 }, { "epoch": 0.5176165230837199, "grad_norm": 3.228496789932251, "learning_rate": 1.9831868463285526e-05, "loss": 0.1157, "step": 9373 }, { "epoch": 0.5176717472940137, "grad_norm": 0.43771055340766907, "learning_rate": 1.9828291283526993e-05, "loss": 0.0063, "step": 9374 }, { "epoch": 0.5177269715043075, "grad_norm": 4.961625576019287, "learning_rate": 1.9824714109261916e-05, "loss": 0.1267, "step": 9375 }, { "epoch": 0.5177821957146013, "grad_norm": 0.09837168455123901, "learning_rate": 1.9821136940604732e-05, "loss": 0.0012, "step": 9376 }, { "epoch": 0.5178374199248951, "grad_norm": 0.31856775283813477, "learning_rate": 1.9817559777669886e-05, "loss": 0.0058, "step": 9377 }, { "epoch": 0.5178926441351889, "grad_norm": 1.4714409112930298, "learning_rate": 1.981398262057182e-05, "loss": 0.0769, "step": 9378 }, { "epoch": 0.5179478683454827, "grad_norm": 2.6059317588806152, "learning_rate": 1.9810405469424988e-05, "loss": 0.2903, "step": 9379 }, { "epoch": 0.5180030925557765, "grad_norm": 0.07629778981208801, "learning_rate": 1.980682832434381e-05, "loss": 0.0025, "step": 9380 }, { "epoch": 0.5180583167660703, "grad_norm": 0.13503830134868622, "learning_rate": 1.980325118544276e-05, "loss": 0.0018, "step": 9381 }, { "epoch": 0.5181135409763641, "grad_norm": 0.23987634479999542, "learning_rate": 1.9799674052836257e-05, "loss": 0.0073, "step": 9382 }, { "epoch": 0.5181687651866578, "grad_norm": 1.051935076713562, "learning_rate": 1.979609692663875e-05, "loss": 0.0095, "step": 9383 }, { "epoch": 0.5182239893969516, "grad_norm": 2.8390796184539795, "learning_rate": 1.9792519806964683e-05, "loss": 0.6389, "step": 9384 }, { "epoch": 0.5182792136072454, "grad_norm": 0.142062708735466, "learning_rate": 1.97889426939285e-05, "loss": 0.0039, "step": 9385 }, { "epoch": 0.5183344378175392, "grad_norm": 0.3517448902130127, "learning_rate": 1.9785365587644638e-05, "loss": 0.0111, "step": 9386 }, { "epoch": 0.518389662027833, "grad_norm": 1.283372163772583, "learning_rate": 1.9781788488227553e-05, "loss": 0.022, "step": 9387 }, { "epoch": 0.5184448862381268, "grad_norm": 4.668755054473877, "learning_rate": 1.9778211395791666e-05, "loss": 0.2481, "step": 9388 }, { "epoch": 0.5185001104484206, "grad_norm": 2.1839869022369385, "learning_rate": 1.9774634310451428e-05, "loss": 0.153, "step": 9389 }, { "epoch": 0.5185553346587144, "grad_norm": 5.615080833435059, "learning_rate": 1.977105723232128e-05, "loss": 0.7266, "step": 9390 }, { "epoch": 0.5186105588690082, "grad_norm": 0.9732394218444824, "learning_rate": 1.9767480161515663e-05, "loss": 0.0258, "step": 9391 }, { "epoch": 0.518665783079302, "grad_norm": 3.1814026832580566, "learning_rate": 1.9763903098149025e-05, "loss": 0.2685, "step": 9392 }, { "epoch": 0.5187210072895958, "grad_norm": 0.16853351891040802, "learning_rate": 1.9760326042335783e-05, "loss": 0.0047, "step": 9393 }, { "epoch": 0.5187762314998896, "grad_norm": 1.5522069931030273, "learning_rate": 1.975674899419041e-05, "loss": 0.1545, "step": 9394 }, { "epoch": 0.5188314557101833, "grad_norm": 0.6793712377548218, "learning_rate": 1.975317195382732e-05, "loss": 0.02, "step": 9395 }, { "epoch": 0.5188866799204771, "grad_norm": 0.17502130568027496, "learning_rate": 1.9749594921360964e-05, "loss": 0.0035, "step": 9396 }, { "epoch": 0.5189419041307709, "grad_norm": 2.093740940093994, "learning_rate": 1.9746017896905776e-05, "loss": 0.3328, "step": 9397 }, { "epoch": 0.5189971283410647, "grad_norm": 0.9424132108688354, "learning_rate": 1.9742440880576203e-05, "loss": 0.0187, "step": 9398 }, { "epoch": 0.5190523525513585, "grad_norm": 4.386669635772705, "learning_rate": 1.9738863872486674e-05, "loss": 0.9555, "step": 9399 }, { "epoch": 0.5191075767616523, "grad_norm": 0.26386624574661255, "learning_rate": 1.973528687275164e-05, "loss": 0.0049, "step": 9400 }, { "epoch": 0.5191628009719461, "grad_norm": 1.6352301836013794, "learning_rate": 1.973170988148553e-05, "loss": 0.2912, "step": 9401 }, { "epoch": 0.5192180251822399, "grad_norm": 0.09440479427576065, "learning_rate": 1.9728132898802787e-05, "loss": 0.0031, "step": 9402 }, { "epoch": 0.5192732493925337, "grad_norm": 1.3035914897918701, "learning_rate": 1.972455592481784e-05, "loss": 0.0129, "step": 9403 }, { "epoch": 0.5193284736028275, "grad_norm": 0.4510498642921448, "learning_rate": 1.972097895964514e-05, "loss": 0.007, "step": 9404 }, { "epoch": 0.5193836978131213, "grad_norm": 0.9394583106040955, "learning_rate": 1.971740200339911e-05, "loss": 0.0155, "step": 9405 }, { "epoch": 0.519438922023415, "grad_norm": 0.05868745595216751, "learning_rate": 1.97138250561942e-05, "loss": 0.001, "step": 9406 }, { "epoch": 0.5194941462337088, "grad_norm": 3.7492835521698, "learning_rate": 1.9710248118144838e-05, "loss": 0.5972, "step": 9407 }, { "epoch": 0.5195493704440026, "grad_norm": 0.008265385404229164, "learning_rate": 1.970667118936547e-05, "loss": 0.0002, "step": 9408 }, { "epoch": 0.5196045946542964, "grad_norm": 0.05783826485276222, "learning_rate": 1.9703094269970517e-05, "loss": 0.001, "step": 9409 }, { "epoch": 0.5196598188645902, "grad_norm": 3.383479118347168, "learning_rate": 1.9699517360074434e-05, "loss": 0.2159, "step": 9410 }, { "epoch": 0.519715043074884, "grad_norm": 0.2384611964225769, "learning_rate": 1.9695940459791637e-05, "loss": 0.0068, "step": 9411 }, { "epoch": 0.5197702672851778, "grad_norm": 0.012864852324128151, "learning_rate": 1.9692363569236573e-05, "loss": 0.0004, "step": 9412 }, { "epoch": 0.5198254914954716, "grad_norm": 0.050460606813430786, "learning_rate": 1.9688786688523672e-05, "loss": 0.0019, "step": 9413 }, { "epoch": 0.5198807157057654, "grad_norm": 5.210738182067871, "learning_rate": 1.9685209817767377e-05, "loss": 0.9411, "step": 9414 }, { "epoch": 0.5199359399160592, "grad_norm": 2.4826467037200928, "learning_rate": 1.968163295708211e-05, "loss": 0.2302, "step": 9415 }, { "epoch": 0.519991164126353, "grad_norm": 4.6043877601623535, "learning_rate": 1.9678056106582315e-05, "loss": 0.4201, "step": 9416 }, { "epoch": 0.5200463883366467, "grad_norm": 0.24360932409763336, "learning_rate": 1.9674479266382418e-05, "loss": 0.0047, "step": 9417 }, { "epoch": 0.5201016125469405, "grad_norm": 0.010915680788457394, "learning_rate": 1.9670902436596865e-05, "loss": 0.0004, "step": 9418 }, { "epoch": 0.5201568367572343, "grad_norm": 0.034534551203250885, "learning_rate": 1.9667325617340064e-05, "loss": 0.0007, "step": 9419 }, { "epoch": 0.5202120609675281, "grad_norm": 0.06980913877487183, "learning_rate": 1.966374880872648e-05, "loss": 0.0024, "step": 9420 }, { "epoch": 0.520267285177822, "grad_norm": 0.12925726175308228, "learning_rate": 1.9660172010870518e-05, "loss": 0.001, "step": 9421 }, { "epoch": 0.5203225093881158, "grad_norm": 2.295100450515747, "learning_rate": 1.9656595223886624e-05, "loss": 0.0316, "step": 9422 }, { "epoch": 0.5203777335984096, "grad_norm": 3.155465602874756, "learning_rate": 1.9653018447889226e-05, "loss": 0.2497, "step": 9423 }, { "epoch": 0.5204329578087034, "grad_norm": 0.04532265290617943, "learning_rate": 1.964944168299276e-05, "loss": 0.0015, "step": 9424 }, { "epoch": 0.5204881820189972, "grad_norm": 0.08391597867012024, "learning_rate": 1.9645864929311643e-05, "loss": 0.0017, "step": 9425 }, { "epoch": 0.520543406229291, "grad_norm": 3.904033899307251, "learning_rate": 1.9642288186960328e-05, "loss": 0.9009, "step": 9426 }, { "epoch": 0.5205986304395848, "grad_norm": 2.602529287338257, "learning_rate": 1.963871145605322e-05, "loss": 0.4869, "step": 9427 }, { "epoch": 0.5206538546498785, "grad_norm": 0.07799325883388519, "learning_rate": 1.9635134736704772e-05, "loss": 0.0033, "step": 9428 }, { "epoch": 0.5207090788601723, "grad_norm": 0.04485080763697624, "learning_rate": 1.9631558029029393e-05, "loss": 0.0014, "step": 9429 }, { "epoch": 0.5207643030704661, "grad_norm": 0.19641432166099548, "learning_rate": 1.9627981333141528e-05, "loss": 0.0053, "step": 9430 }, { "epoch": 0.5208195272807599, "grad_norm": 0.8734714388847351, "learning_rate": 1.9624404649155594e-05, "loss": 0.0191, "step": 9431 }, { "epoch": 0.5208747514910537, "grad_norm": 6.015531539916992, "learning_rate": 1.962082797718603e-05, "loss": 0.6756, "step": 9432 }, { "epoch": 0.5209299757013475, "grad_norm": 0.8997337222099304, "learning_rate": 1.9617251317347252e-05, "loss": 0.0218, "step": 9433 }, { "epoch": 0.5209851999116413, "grad_norm": 6.436057090759277, "learning_rate": 1.9613674669753705e-05, "loss": 1.6344, "step": 9434 }, { "epoch": 0.5210404241219351, "grad_norm": 0.0738457515835762, "learning_rate": 1.961009803451979e-05, "loss": 0.0016, "step": 9435 }, { "epoch": 0.5210956483322289, "grad_norm": 3.4998772144317627, "learning_rate": 1.960652141175996e-05, "loss": 0.8865, "step": 9436 }, { "epoch": 0.5211508725425227, "grad_norm": 2.431433916091919, "learning_rate": 1.9602944801588625e-05, "loss": 0.3104, "step": 9437 }, { "epoch": 0.5212060967528165, "grad_norm": 0.19325454533100128, "learning_rate": 1.9599368204120222e-05, "loss": 0.0056, "step": 9438 }, { "epoch": 0.5212613209631102, "grad_norm": 0.04025841876864433, "learning_rate": 1.9595791619469162e-05, "loss": 0.0014, "step": 9439 }, { "epoch": 0.521316545173404, "grad_norm": 0.019178763031959534, "learning_rate": 1.9592215047749886e-05, "loss": 0.0005, "step": 9440 }, { "epoch": 0.5213717693836978, "grad_norm": 3.5012197494506836, "learning_rate": 1.9588638489076808e-05, "loss": 0.6154, "step": 9441 }, { "epoch": 0.5214269935939916, "grad_norm": 5.422947406768799, "learning_rate": 1.9585061943564362e-05, "loss": 0.2909, "step": 9442 }, { "epoch": 0.5214822178042854, "grad_norm": 2.129889726638794, "learning_rate": 1.9581485411326952e-05, "loss": 0.2631, "step": 9443 }, { "epoch": 0.5215374420145792, "grad_norm": 2.959010362625122, "learning_rate": 1.9577908892479033e-05, "loss": 0.4433, "step": 9444 }, { "epoch": 0.521592666224873, "grad_norm": 0.11856075376272202, "learning_rate": 1.9574332387134997e-05, "loss": 0.0032, "step": 9445 }, { "epoch": 0.5216478904351668, "grad_norm": 0.02592579647898674, "learning_rate": 1.9570755895409285e-05, "loss": 0.0007, "step": 9446 }, { "epoch": 0.5217031146454606, "grad_norm": 0.017975689843297005, "learning_rate": 1.9567179417416312e-05, "loss": 0.0005, "step": 9447 }, { "epoch": 0.5217583388557544, "grad_norm": 2.7362592220306396, "learning_rate": 1.9563602953270502e-05, "loss": 0.7036, "step": 9448 }, { "epoch": 0.5218135630660482, "grad_norm": 1.5253108739852905, "learning_rate": 1.956002650308628e-05, "loss": 0.0556, "step": 9449 }, { "epoch": 0.5218687872763419, "grad_norm": 0.00818774662911892, "learning_rate": 1.9556450066978054e-05, "loss": 0.0003, "step": 9450 }, { "epoch": 0.5219240114866357, "grad_norm": 0.051240481436252594, "learning_rate": 1.9552873645060265e-05, "loss": 0.0016, "step": 9451 }, { "epoch": 0.5219792356969295, "grad_norm": 2.1755244731903076, "learning_rate": 1.954929723744731e-05, "loss": 0.2272, "step": 9452 }, { "epoch": 0.5220344599072233, "grad_norm": 2.2195894718170166, "learning_rate": 1.9545720844253625e-05, "loss": 0.0356, "step": 9453 }, { "epoch": 0.5220896841175171, "grad_norm": 1.5348628759384155, "learning_rate": 1.954214446559362e-05, "loss": 0.0559, "step": 9454 }, { "epoch": 0.5221449083278109, "grad_norm": 3.9120090007781982, "learning_rate": 1.953856810158172e-05, "loss": 0.7802, "step": 9455 }, { "epoch": 0.5222001325381047, "grad_norm": 0.6675938963890076, "learning_rate": 1.9534991752332337e-05, "loss": 0.0196, "step": 9456 }, { "epoch": 0.5222553567483985, "grad_norm": 0.05084867775440216, "learning_rate": 1.95314154179599e-05, "loss": 0.0014, "step": 9457 }, { "epoch": 0.5223105809586923, "grad_norm": 0.0649484172463417, "learning_rate": 1.9527839098578805e-05, "loss": 0.0019, "step": 9458 }, { "epoch": 0.5223658051689861, "grad_norm": 4.465451717376709, "learning_rate": 1.952426279430349e-05, "loss": 1.0323, "step": 9459 }, { "epoch": 0.5224210293792799, "grad_norm": 2.7633814811706543, "learning_rate": 1.952068650524836e-05, "loss": 0.5754, "step": 9460 }, { "epoch": 0.5224762535895736, "grad_norm": 0.050445977598428726, "learning_rate": 1.9517110231527837e-05, "loss": 0.0012, "step": 9461 }, { "epoch": 0.5225314777998674, "grad_norm": 0.6395161747932434, "learning_rate": 1.9513533973256326e-05, "loss": 0.0089, "step": 9462 }, { "epoch": 0.5225867020101612, "grad_norm": 0.1395113170146942, "learning_rate": 1.950995773054825e-05, "loss": 0.0039, "step": 9463 }, { "epoch": 0.522641926220455, "grad_norm": 0.11767300218343735, "learning_rate": 1.9506381503518022e-05, "loss": 0.0035, "step": 9464 }, { "epoch": 0.5226971504307488, "grad_norm": 0.031219610944390297, "learning_rate": 1.950280529228006e-05, "loss": 0.0011, "step": 9465 }, { "epoch": 0.5227523746410426, "grad_norm": 0.04993255436420441, "learning_rate": 1.9499229096948763e-05, "loss": 0.0015, "step": 9466 }, { "epoch": 0.5228075988513364, "grad_norm": 0.039194103330373764, "learning_rate": 1.949565291763856e-05, "loss": 0.0015, "step": 9467 }, { "epoch": 0.5228628230616302, "grad_norm": 3.567135810852051, "learning_rate": 1.9492076754463854e-05, "loss": 0.3257, "step": 9468 }, { "epoch": 0.522918047271924, "grad_norm": 0.30722442269325256, "learning_rate": 1.948850060753906e-05, "loss": 0.0102, "step": 9469 }, { "epoch": 0.5229732714822178, "grad_norm": 0.8797686100006104, "learning_rate": 1.948492447697858e-05, "loss": 0.0344, "step": 9470 }, { "epoch": 0.5230284956925116, "grad_norm": 4.154189586639404, "learning_rate": 1.948134836289684e-05, "loss": 0.1773, "step": 9471 }, { "epoch": 0.5230837199028054, "grad_norm": 2.468147039413452, "learning_rate": 1.9477772265408238e-05, "loss": 0.2017, "step": 9472 }, { "epoch": 0.5231389441130991, "grad_norm": 2.6661109924316406, "learning_rate": 1.94741961846272e-05, "loss": 0.352, "step": 9473 }, { "epoch": 0.5231941683233929, "grad_norm": 1.5744073390960693, "learning_rate": 1.9470620120668105e-05, "loss": 0.0591, "step": 9474 }, { "epoch": 0.5232493925336867, "grad_norm": 3.28347110748291, "learning_rate": 1.9467044073645394e-05, "loss": 0.2872, "step": 9475 }, { "epoch": 0.5233046167439805, "grad_norm": 3.631485939025879, "learning_rate": 1.946346804367345e-05, "loss": 0.582, "step": 9476 }, { "epoch": 0.5233598409542743, "grad_norm": 1.096158504486084, "learning_rate": 1.9459892030866695e-05, "loss": 0.0902, "step": 9477 }, { "epoch": 0.5234150651645681, "grad_norm": 0.03886822238564491, "learning_rate": 1.945631603533953e-05, "loss": 0.0011, "step": 9478 }, { "epoch": 0.523470289374862, "grad_norm": 1.809968113899231, "learning_rate": 1.9452740057206366e-05, "loss": 0.1127, "step": 9479 }, { "epoch": 0.5235255135851558, "grad_norm": 0.04991349205374718, "learning_rate": 1.9449164096581602e-05, "loss": 0.0017, "step": 9480 }, { "epoch": 0.5235807377954496, "grad_norm": 3.351942300796509, "learning_rate": 1.9445588153579656e-05, "loss": 0.5301, "step": 9481 }, { "epoch": 0.5236359620057434, "grad_norm": 0.06499853730201721, "learning_rate": 1.944201222831491e-05, "loss": 0.0016, "step": 9482 }, { "epoch": 0.5236911862160372, "grad_norm": 0.32080891728401184, "learning_rate": 1.943843632090179e-05, "loss": 0.0104, "step": 9483 }, { "epoch": 0.5237464104263309, "grad_norm": 1.224544882774353, "learning_rate": 1.9434860431454687e-05, "loss": 0.0349, "step": 9484 }, { "epoch": 0.5238016346366247, "grad_norm": 3.6968472003936768, "learning_rate": 1.9431284560088008e-05, "loss": 1.0699, "step": 9485 }, { "epoch": 0.5238568588469185, "grad_norm": 3.0402028560638428, "learning_rate": 1.9427708706916153e-05, "loss": 0.7344, "step": 9486 }, { "epoch": 0.5239120830572123, "grad_norm": 2.0524470806121826, "learning_rate": 1.942413287205353e-05, "loss": 0.0857, "step": 9487 }, { "epoch": 0.5239673072675061, "grad_norm": 0.3573915958404541, "learning_rate": 1.9420557055614534e-05, "loss": 0.0094, "step": 9488 }, { "epoch": 0.5240225314777999, "grad_norm": 0.13642239570617676, "learning_rate": 1.9416981257713568e-05, "loss": 0.0042, "step": 9489 }, { "epoch": 0.5240777556880937, "grad_norm": 0.09413567185401917, "learning_rate": 1.941340547846503e-05, "loss": 0.0024, "step": 9490 }, { "epoch": 0.5241329798983875, "grad_norm": 1.4578458070755005, "learning_rate": 1.9409829717983325e-05, "loss": 0.1219, "step": 9491 }, { "epoch": 0.5241882041086813, "grad_norm": 1.1269817352294922, "learning_rate": 1.9406253976382843e-05, "loss": 0.0266, "step": 9492 }, { "epoch": 0.5242434283189751, "grad_norm": 4.533129692077637, "learning_rate": 1.940267825377799e-05, "loss": 0.6588, "step": 9493 }, { "epoch": 0.5242986525292689, "grad_norm": 4.741065502166748, "learning_rate": 1.9399102550283154e-05, "loss": 0.3544, "step": 9494 }, { "epoch": 0.5243538767395626, "grad_norm": 0.03974287584424019, "learning_rate": 1.9395526866012745e-05, "loss": 0.0009, "step": 9495 }, { "epoch": 0.5244091009498564, "grad_norm": 3.570486068725586, "learning_rate": 1.9391951201081145e-05, "loss": 0.4176, "step": 9496 }, { "epoch": 0.5244643251601502, "grad_norm": 5.228432655334473, "learning_rate": 1.938837555560276e-05, "loss": 0.4721, "step": 9497 }, { "epoch": 0.524519549370444, "grad_norm": 0.036904703825712204, "learning_rate": 1.9384799929691984e-05, "loss": 0.0012, "step": 9498 }, { "epoch": 0.5245747735807378, "grad_norm": 1.2970234155654907, "learning_rate": 1.9381224323463216e-05, "loss": 0.0358, "step": 9499 }, { "epoch": 0.5246299977910316, "grad_norm": 1.9507122039794922, "learning_rate": 1.9377648737030835e-05, "loss": 0.1237, "step": 9500 }, { "epoch": 0.5246852220013254, "grad_norm": 0.01718355342745781, "learning_rate": 1.9374073170509244e-05, "loss": 0.0006, "step": 9501 }, { "epoch": 0.5247404462116192, "grad_norm": 5.691056251525879, "learning_rate": 1.937049762401283e-05, "loss": 1.4189, "step": 9502 }, { "epoch": 0.524795670421913, "grad_norm": 0.5091886520385742, "learning_rate": 1.9366922097655997e-05, "loss": 0.0124, "step": 9503 }, { "epoch": 0.5248508946322068, "grad_norm": 0.7247151732444763, "learning_rate": 1.9363346591553123e-05, "loss": 0.0252, "step": 9504 }, { "epoch": 0.5249061188425006, "grad_norm": 5.1366777420043945, "learning_rate": 1.9359771105818608e-05, "loss": 0.4951, "step": 9505 }, { "epoch": 0.5249613430527943, "grad_norm": 2.186199903488159, "learning_rate": 1.9356195640566832e-05, "loss": 0.2976, "step": 9506 }, { "epoch": 0.5250165672630881, "grad_norm": 0.052240144461393356, "learning_rate": 1.93526201959122e-05, "loss": 0.0014, "step": 9507 }, { "epoch": 0.5250717914733819, "grad_norm": 0.10610272735357285, "learning_rate": 1.934904477196909e-05, "loss": 0.0028, "step": 9508 }, { "epoch": 0.5251270156836757, "grad_norm": 0.05764824524521828, "learning_rate": 1.9345469368851883e-05, "loss": 0.0015, "step": 9509 }, { "epoch": 0.5251822398939695, "grad_norm": 0.07055412977933884, "learning_rate": 1.934189398667498e-05, "loss": 0.0025, "step": 9510 }, { "epoch": 0.5252374641042633, "grad_norm": 3.9652211666107178, "learning_rate": 1.9338318625552758e-05, "loss": 0.4317, "step": 9511 }, { "epoch": 0.5252926883145571, "grad_norm": 0.02344120293855667, "learning_rate": 1.9334743285599612e-05, "loss": 0.0008, "step": 9512 }, { "epoch": 0.5253479125248509, "grad_norm": 1.4276576042175293, "learning_rate": 1.933116796692991e-05, "loss": 0.045, "step": 9513 }, { "epoch": 0.5254031367351447, "grad_norm": 0.02696295455098152, "learning_rate": 1.9327592669658067e-05, "loss": 0.001, "step": 9514 }, { "epoch": 0.5254583609454385, "grad_norm": 0.037451472133398056, "learning_rate": 1.9324017393898435e-05, "loss": 0.0015, "step": 9515 }, { "epoch": 0.5255135851557323, "grad_norm": 0.1588674932718277, "learning_rate": 1.9320442139765417e-05, "loss": 0.005, "step": 9516 }, { "epoch": 0.525568809366026, "grad_norm": 5.886358261108398, "learning_rate": 1.9316866907373384e-05, "loss": 0.2135, "step": 9517 }, { "epoch": 0.5256240335763198, "grad_norm": 1.045941710472107, "learning_rate": 1.931329169683673e-05, "loss": 0.0204, "step": 9518 }, { "epoch": 0.5256792577866136, "grad_norm": 0.8305107355117798, "learning_rate": 1.930971650826982e-05, "loss": 0.1856, "step": 9519 }, { "epoch": 0.5257344819969074, "grad_norm": 1.9456250667572021, "learning_rate": 1.9306141341787058e-05, "loss": 0.3796, "step": 9520 }, { "epoch": 0.5257897062072012, "grad_norm": 0.05053199455142021, "learning_rate": 1.9302566197502795e-05, "loss": 0.0013, "step": 9521 }, { "epoch": 0.525844930417495, "grad_norm": 2.940988540649414, "learning_rate": 1.929899107553144e-05, "loss": 0.3935, "step": 9522 }, { "epoch": 0.5259001546277888, "grad_norm": 0.08717216551303864, "learning_rate": 1.9295415975987346e-05, "loss": 0.0022, "step": 9523 }, { "epoch": 0.5259553788380826, "grad_norm": 0.020345443859696388, "learning_rate": 1.9291840898984907e-05, "loss": 0.0006, "step": 9524 }, { "epoch": 0.5260106030483764, "grad_norm": 2.874338388442993, "learning_rate": 1.9288265844638487e-05, "loss": 0.5356, "step": 9525 }, { "epoch": 0.5260658272586702, "grad_norm": 0.08781498670578003, "learning_rate": 1.9284690813062475e-05, "loss": 0.003, "step": 9526 }, { "epoch": 0.526121051468964, "grad_norm": 0.0354071706533432, "learning_rate": 1.9281115804371233e-05, "loss": 0.0013, "step": 9527 }, { "epoch": 0.5261762756792577, "grad_norm": 4.015531063079834, "learning_rate": 1.927754081867915e-05, "loss": 0.0702, "step": 9528 }, { "epoch": 0.5262314998895515, "grad_norm": 0.10142335295677185, "learning_rate": 1.9273965856100587e-05, "loss": 0.0012, "step": 9529 }, { "epoch": 0.5262867240998453, "grad_norm": 2.1584720611572266, "learning_rate": 1.9270390916749932e-05, "loss": 0.154, "step": 9530 }, { "epoch": 0.5263419483101391, "grad_norm": 0.1483435183763504, "learning_rate": 1.926681600074154e-05, "loss": 0.0046, "step": 9531 }, { "epoch": 0.5263971725204329, "grad_norm": 0.02009216696023941, "learning_rate": 1.9263241108189795e-05, "loss": 0.0004, "step": 9532 }, { "epoch": 0.5264523967307267, "grad_norm": 1.328065276145935, "learning_rate": 1.9259666239209062e-05, "loss": 0.0232, "step": 9533 }, { "epoch": 0.5265076209410205, "grad_norm": 4.503627300262451, "learning_rate": 1.9256091393913718e-05, "loss": 0.7519, "step": 9534 }, { "epoch": 0.5265628451513144, "grad_norm": 0.4393756091594696, "learning_rate": 1.9252516572418123e-05, "loss": 0.0075, "step": 9535 }, { "epoch": 0.5266180693616082, "grad_norm": 1.634156346321106, "learning_rate": 1.9248941774836653e-05, "loss": 0.1883, "step": 9536 }, { "epoch": 0.526673293571902, "grad_norm": 2.9373373985290527, "learning_rate": 1.9245367001283672e-05, "loss": 0.1713, "step": 9537 }, { "epoch": 0.5267285177821958, "grad_norm": 0.34489014744758606, "learning_rate": 1.924179225187356e-05, "loss": 0.0096, "step": 9538 }, { "epoch": 0.5267837419924896, "grad_norm": 1.8420284986495972, "learning_rate": 1.9238217526720657e-05, "loss": 0.0893, "step": 9539 }, { "epoch": 0.5268389662027833, "grad_norm": 0.7178332805633545, "learning_rate": 1.9234642825939352e-05, "loss": 0.0254, "step": 9540 }, { "epoch": 0.5268941904130771, "grad_norm": 0.5535820722579956, "learning_rate": 1.9231068149644e-05, "loss": 0.0157, "step": 9541 }, { "epoch": 0.5269494146233709, "grad_norm": 3.2043001651763916, "learning_rate": 1.922749349794897e-05, "loss": 0.0412, "step": 9542 }, { "epoch": 0.5270046388336647, "grad_norm": 1.6188865900039673, "learning_rate": 1.9223918870968618e-05, "loss": 0.182, "step": 9543 }, { "epoch": 0.5270598630439585, "grad_norm": 5.4634108543396, "learning_rate": 1.9220344268817314e-05, "loss": 0.1029, "step": 9544 }, { "epoch": 0.5271150872542523, "grad_norm": 0.03314577788114548, "learning_rate": 1.9216769691609412e-05, "loss": 0.0013, "step": 9545 }, { "epoch": 0.5271703114645461, "grad_norm": 2.569214344024658, "learning_rate": 1.9213195139459283e-05, "loss": 0.2143, "step": 9546 }, { "epoch": 0.5272255356748399, "grad_norm": 3.3940725326538086, "learning_rate": 1.9209620612481272e-05, "loss": 0.2745, "step": 9547 }, { "epoch": 0.5272807598851337, "grad_norm": 4.484429836273193, "learning_rate": 1.9206046110789763e-05, "loss": 0.7097, "step": 9548 }, { "epoch": 0.5273359840954275, "grad_norm": 4.153498649597168, "learning_rate": 1.9202471634499088e-05, "loss": 0.9535, "step": 9549 }, { "epoch": 0.5273912083057213, "grad_norm": 0.0389418751001358, "learning_rate": 1.919889718372362e-05, "loss": 0.0011, "step": 9550 }, { "epoch": 0.527446432516015, "grad_norm": 0.6304996013641357, "learning_rate": 1.9195322758577706e-05, "loss": 0.024, "step": 9551 }, { "epoch": 0.5275016567263088, "grad_norm": 1.0611324310302734, "learning_rate": 1.919174835917571e-05, "loss": 0.0601, "step": 9552 }, { "epoch": 0.5275568809366026, "grad_norm": 0.05738888308405876, "learning_rate": 1.918817398563199e-05, "loss": 0.0016, "step": 9553 }, { "epoch": 0.5276121051468964, "grad_norm": 3.302727460861206, "learning_rate": 1.9184599638060896e-05, "loss": 0.7473, "step": 9554 }, { "epoch": 0.5276673293571902, "grad_norm": 0.950564444065094, "learning_rate": 1.9181025316576768e-05, "loss": 0.0224, "step": 9555 }, { "epoch": 0.527722553567484, "grad_norm": 2.6537139415740967, "learning_rate": 1.9177451021293988e-05, "loss": 0.0701, "step": 9556 }, { "epoch": 0.5277777777777778, "grad_norm": 3.052060842514038, "learning_rate": 1.9173876752326882e-05, "loss": 0.7298, "step": 9557 }, { "epoch": 0.5278330019880716, "grad_norm": 4.852339744567871, "learning_rate": 1.9170302509789816e-05, "loss": 0.4105, "step": 9558 }, { "epoch": 0.5278882261983654, "grad_norm": 0.26972395181655884, "learning_rate": 1.916672829379713e-05, "loss": 0.0081, "step": 9559 }, { "epoch": 0.5279434504086592, "grad_norm": 0.17284949123859406, "learning_rate": 1.9163154104463178e-05, "loss": 0.005, "step": 9560 }, { "epoch": 0.527998674618953, "grad_norm": 0.11595446616411209, "learning_rate": 1.915957994190231e-05, "loss": 0.0047, "step": 9561 }, { "epoch": 0.5280538988292467, "grad_norm": 2.546121120452881, "learning_rate": 1.9156005806228878e-05, "loss": 0.4222, "step": 9562 }, { "epoch": 0.5281091230395405, "grad_norm": 0.895435094833374, "learning_rate": 1.915243169755721e-05, "loss": 0.0293, "step": 9563 }, { "epoch": 0.5281643472498343, "grad_norm": 3.992952823638916, "learning_rate": 1.914885761600168e-05, "loss": 0.7488, "step": 9564 }, { "epoch": 0.5282195714601281, "grad_norm": 0.0883263498544693, "learning_rate": 1.9145283561676605e-05, "loss": 0.0025, "step": 9565 }, { "epoch": 0.5282747956704219, "grad_norm": 0.15258483588695526, "learning_rate": 1.9141709534696353e-05, "loss": 0.004, "step": 9566 }, { "epoch": 0.5283300198807157, "grad_norm": 3.6435775756835938, "learning_rate": 1.913813553517525e-05, "loss": 0.5306, "step": 9567 }, { "epoch": 0.5283852440910095, "grad_norm": 3.0183444023132324, "learning_rate": 1.913456156322764e-05, "loss": 0.1718, "step": 9568 }, { "epoch": 0.5284404683013033, "grad_norm": 0.023198630660772324, "learning_rate": 1.9130987618967884e-05, "loss": 0.0005, "step": 9569 }, { "epoch": 0.5284956925115971, "grad_norm": 0.49189984798431396, "learning_rate": 1.9127413702510293e-05, "loss": 0.0134, "step": 9570 }, { "epoch": 0.5285509167218909, "grad_norm": 0.09713819622993469, "learning_rate": 1.9123839813969234e-05, "loss": 0.0026, "step": 9571 }, { "epoch": 0.5286061409321847, "grad_norm": 3.849290132522583, "learning_rate": 1.9120265953459027e-05, "loss": 0.4223, "step": 9572 }, { "epoch": 0.5286613651424784, "grad_norm": 4.589353084564209, "learning_rate": 1.9116692121094016e-05, "loss": 0.4249, "step": 9573 }, { "epoch": 0.5287165893527722, "grad_norm": 0.7180034518241882, "learning_rate": 1.911311831698854e-05, "loss": 0.0199, "step": 9574 }, { "epoch": 0.528771813563066, "grad_norm": 0.10265886783599854, "learning_rate": 1.9109544541256934e-05, "loss": 0.0032, "step": 9575 }, { "epoch": 0.5288270377733598, "grad_norm": 5.436096668243408, "learning_rate": 1.910597079401353e-05, "loss": 1.3126, "step": 9576 }, { "epoch": 0.5288822619836536, "grad_norm": 0.44179749488830566, "learning_rate": 1.9102397075372675e-05, "loss": 0.0092, "step": 9577 }, { "epoch": 0.5289374861939474, "grad_norm": 0.25892841815948486, "learning_rate": 1.909882338544868e-05, "loss": 0.0062, "step": 9578 }, { "epoch": 0.5289927104042412, "grad_norm": 0.029455427080392838, "learning_rate": 1.9095249724355902e-05, "loss": 0.0006, "step": 9579 }, { "epoch": 0.529047934614535, "grad_norm": 0.018940886482596397, "learning_rate": 1.9091676092208654e-05, "loss": 0.0008, "step": 9580 }, { "epoch": 0.5291031588248288, "grad_norm": 1.6059980392456055, "learning_rate": 1.9088102489121276e-05, "loss": 0.056, "step": 9581 }, { "epoch": 0.5291583830351226, "grad_norm": 3.7873332500457764, "learning_rate": 1.9084528915208095e-05, "loss": 0.0789, "step": 9582 }, { "epoch": 0.5292136072454164, "grad_norm": 0.3749435544013977, "learning_rate": 1.908095537058344e-05, "loss": 0.0101, "step": 9583 }, { "epoch": 0.5292688314557101, "grad_norm": 1.9837367534637451, "learning_rate": 1.9077381855361635e-05, "loss": 0.6342, "step": 9584 }, { "epoch": 0.5293240556660039, "grad_norm": 2.189863681793213, "learning_rate": 1.9073808369657022e-05, "loss": 0.1964, "step": 9585 }, { "epoch": 0.5293792798762977, "grad_norm": 6.245926856994629, "learning_rate": 1.90702349135839e-05, "loss": 1.3435, "step": 9586 }, { "epoch": 0.5294345040865915, "grad_norm": 5.965689659118652, "learning_rate": 1.906666148725663e-05, "loss": 0.4151, "step": 9587 }, { "epoch": 0.5294897282968853, "grad_norm": 0.04455454275012016, "learning_rate": 1.9063088090789502e-05, "loss": 0.0012, "step": 9588 }, { "epoch": 0.5295449525071791, "grad_norm": 0.10327349603176117, "learning_rate": 1.9059514724296858e-05, "loss": 0.0024, "step": 9589 }, { "epoch": 0.529600176717473, "grad_norm": 0.8212754726409912, "learning_rate": 1.9055941387893013e-05, "loss": 0.0192, "step": 9590 }, { "epoch": 0.5296554009277668, "grad_norm": 3.49399995803833, "learning_rate": 1.9052368081692292e-05, "loss": 0.3221, "step": 9591 }, { "epoch": 0.5297106251380606, "grad_norm": 2.3849806785583496, "learning_rate": 1.9048794805809012e-05, "loss": 0.2184, "step": 9592 }, { "epoch": 0.5297658493483544, "grad_norm": 0.5079809427261353, "learning_rate": 1.9045221560357502e-05, "loss": 0.0187, "step": 9593 }, { "epoch": 0.5298210735586482, "grad_norm": 0.5993674993515015, "learning_rate": 1.904164834545206e-05, "loss": 0.012, "step": 9594 }, { "epoch": 0.5298762977689419, "grad_norm": 3.490544557571411, "learning_rate": 1.9038075161207027e-05, "loss": 0.8822, "step": 9595 }, { "epoch": 0.5299315219792357, "grad_norm": 2.8291845321655273, "learning_rate": 1.90345020077367e-05, "loss": 0.1696, "step": 9596 }, { "epoch": 0.5299867461895295, "grad_norm": 3.254138946533203, "learning_rate": 1.9030928885155408e-05, "loss": 0.7193, "step": 9597 }, { "epoch": 0.5300419703998233, "grad_norm": 0.20731942355632782, "learning_rate": 1.9027355793577454e-05, "loss": 0.0056, "step": 9598 }, { "epoch": 0.5300971946101171, "grad_norm": 0.020372867584228516, "learning_rate": 1.9023782733117163e-05, "loss": 0.0007, "step": 9599 }, { "epoch": 0.5301524188204109, "grad_norm": 4.08535099029541, "learning_rate": 1.9020209703888834e-05, "loss": 0.888, "step": 9600 }, { "epoch": 0.5302076430307047, "grad_norm": 3.6428778171539307, "learning_rate": 1.90166367060068e-05, "loss": 0.5937, "step": 9601 }, { "epoch": 0.5302628672409985, "grad_norm": 0.019048651680350304, "learning_rate": 1.901306373958534e-05, "loss": 0.0006, "step": 9602 }, { "epoch": 0.5303180914512923, "grad_norm": 4.289059162139893, "learning_rate": 1.9009490804738794e-05, "loss": 0.817, "step": 9603 }, { "epoch": 0.5303733156615861, "grad_norm": 0.3222043812274933, "learning_rate": 1.900591790158145e-05, "loss": 0.0103, "step": 9604 }, { "epoch": 0.5304285398718799, "grad_norm": 3.922977924346924, "learning_rate": 1.9002345030227623e-05, "loss": 0.1172, "step": 9605 }, { "epoch": 0.5304837640821736, "grad_norm": 1.295331597328186, "learning_rate": 1.899877219079162e-05, "loss": 0.3852, "step": 9606 }, { "epoch": 0.5305389882924674, "grad_norm": 0.10003604739904404, "learning_rate": 1.8995199383387747e-05, "loss": 0.0037, "step": 9607 }, { "epoch": 0.5305942125027612, "grad_norm": 0.47721168398857117, "learning_rate": 1.89916266081303e-05, "loss": 0.0074, "step": 9608 }, { "epoch": 0.530649436713055, "grad_norm": 2.944749355316162, "learning_rate": 1.8988053865133594e-05, "loss": 0.3111, "step": 9609 }, { "epoch": 0.5307046609233488, "grad_norm": 0.01570471189916134, "learning_rate": 1.8984481154511924e-05, "loss": 0.0005, "step": 9610 }, { "epoch": 0.5307598851336426, "grad_norm": 0.011592292226850986, "learning_rate": 1.89809084763796e-05, "loss": 0.0004, "step": 9611 }, { "epoch": 0.5308151093439364, "grad_norm": 0.0999467521905899, "learning_rate": 1.8977335830850906e-05, "loss": 0.0017, "step": 9612 }, { "epoch": 0.5308703335542302, "grad_norm": 3.0921058654785156, "learning_rate": 1.897376321804015e-05, "loss": 0.2387, "step": 9613 }, { "epoch": 0.530925557764524, "grad_norm": 0.24833187460899353, "learning_rate": 1.897019063806163e-05, "loss": 0.0054, "step": 9614 }, { "epoch": 0.5309807819748178, "grad_norm": 0.9676300883293152, "learning_rate": 1.896661809102965e-05, "loss": 0.0062, "step": 9615 }, { "epoch": 0.5310360061851116, "grad_norm": 0.010945410467684269, "learning_rate": 1.8963045577058493e-05, "loss": 0.0003, "step": 9616 }, { "epoch": 0.5310912303954054, "grad_norm": 3.448094129562378, "learning_rate": 1.8959473096262465e-05, "loss": 0.3092, "step": 9617 }, { "epoch": 0.5311464546056991, "grad_norm": 2.0471479892730713, "learning_rate": 1.895590064875585e-05, "loss": 0.2181, "step": 9618 }, { "epoch": 0.5312016788159929, "grad_norm": 1.609943151473999, "learning_rate": 1.8952328234652953e-05, "loss": 0.1314, "step": 9619 }, { "epoch": 0.5312569030262867, "grad_norm": 2.9832406044006348, "learning_rate": 1.8948755854068048e-05, "loss": 0.3829, "step": 9620 }, { "epoch": 0.5313121272365805, "grad_norm": 0.9560662508010864, "learning_rate": 1.8945183507115444e-05, "loss": 0.0313, "step": 9621 }, { "epoch": 0.5313673514468743, "grad_norm": 3.257068395614624, "learning_rate": 1.8941611193909418e-05, "loss": 0.4716, "step": 9622 }, { "epoch": 0.5314225756571681, "grad_norm": 4.649433135986328, "learning_rate": 1.8938038914564266e-05, "loss": 1.1756, "step": 9623 }, { "epoch": 0.5314777998674619, "grad_norm": 1.834391474723816, "learning_rate": 1.8934466669194267e-05, "loss": 0.0437, "step": 9624 }, { "epoch": 0.5315330240777557, "grad_norm": 0.3568115234375, "learning_rate": 1.893089445791372e-05, "loss": 0.0077, "step": 9625 }, { "epoch": 0.5315882482880495, "grad_norm": 0.7392519116401672, "learning_rate": 1.8927322280836895e-05, "loss": 0.0238, "step": 9626 }, { "epoch": 0.5316434724983433, "grad_norm": 3.5530285835266113, "learning_rate": 1.8923750138078097e-05, "loss": 1.0031, "step": 9627 }, { "epoch": 0.5316986967086371, "grad_norm": 0.43847498297691345, "learning_rate": 1.8920178029751587e-05, "loss": 0.0037, "step": 9628 }, { "epoch": 0.5317539209189308, "grad_norm": 1.448517918586731, "learning_rate": 1.8916605955971655e-05, "loss": 0.0542, "step": 9629 }, { "epoch": 0.5318091451292246, "grad_norm": 3.5273473262786865, "learning_rate": 1.8913033916852586e-05, "loss": 0.1695, "step": 9630 }, { "epoch": 0.5318643693395184, "grad_norm": 1.5525797605514526, "learning_rate": 1.8909461912508654e-05, "loss": 0.1228, "step": 9631 }, { "epoch": 0.5319195935498122, "grad_norm": 0.2806997001171112, "learning_rate": 1.8905889943054145e-05, "loss": 0.0104, "step": 9632 }, { "epoch": 0.531974817760106, "grad_norm": 0.5505928993225098, "learning_rate": 1.890231800860332e-05, "loss": 0.0186, "step": 9633 }, { "epoch": 0.5320300419703998, "grad_norm": 5.004481792449951, "learning_rate": 1.889874610927048e-05, "loss": 1.1814, "step": 9634 }, { "epoch": 0.5320852661806936, "grad_norm": 0.2972829341888428, "learning_rate": 1.8895174245169882e-05, "loss": 0.0069, "step": 9635 }, { "epoch": 0.5321404903909874, "grad_norm": 2.455937385559082, "learning_rate": 1.8891602416415803e-05, "loss": 0.385, "step": 9636 }, { "epoch": 0.5321957146012812, "grad_norm": 4.136443614959717, "learning_rate": 1.8888030623122517e-05, "loss": 0.5024, "step": 9637 }, { "epoch": 0.532250938811575, "grad_norm": 0.23806898295879364, "learning_rate": 1.8884458865404303e-05, "loss": 0.0066, "step": 9638 }, { "epoch": 0.5323061630218688, "grad_norm": 0.23170635104179382, "learning_rate": 1.888088714337542e-05, "loss": 0.0036, "step": 9639 }, { "epoch": 0.5323613872321625, "grad_norm": 0.03160973638296127, "learning_rate": 1.8877315457150147e-05, "loss": 0.001, "step": 9640 }, { "epoch": 0.5324166114424563, "grad_norm": 3.6553585529327393, "learning_rate": 1.8873743806842745e-05, "loss": 0.3544, "step": 9641 }, { "epoch": 0.5324718356527501, "grad_norm": 0.5303176045417786, "learning_rate": 1.8870172192567494e-05, "loss": 0.0143, "step": 9642 }, { "epoch": 0.5325270598630439, "grad_norm": 3.913243293762207, "learning_rate": 1.886660061443864e-05, "loss": 0.2828, "step": 9643 }, { "epoch": 0.5325822840733377, "grad_norm": 0.05729333683848381, "learning_rate": 1.8863029072570464e-05, "loss": 0.0017, "step": 9644 }, { "epoch": 0.5326375082836315, "grad_norm": 7.165492534637451, "learning_rate": 1.8859457567077225e-05, "loss": 0.4493, "step": 9645 }, { "epoch": 0.5326927324939253, "grad_norm": 0.026339396834373474, "learning_rate": 1.8855886098073183e-05, "loss": 0.0008, "step": 9646 }, { "epoch": 0.5327479567042191, "grad_norm": 0.8304805755615234, "learning_rate": 1.8852314665672603e-05, "loss": 0.0299, "step": 9647 }, { "epoch": 0.532803180914513, "grad_norm": 0.11326520144939423, "learning_rate": 1.8848743269989745e-05, "loss": 0.0035, "step": 9648 }, { "epoch": 0.5328584051248068, "grad_norm": 1.5462745428085327, "learning_rate": 1.8845171911138865e-05, "loss": 0.0864, "step": 9649 }, { "epoch": 0.5329136293351006, "grad_norm": 0.9849872589111328, "learning_rate": 1.884160058923423e-05, "loss": 0.0202, "step": 9650 }, { "epoch": 0.5329688535453942, "grad_norm": 0.1101180836558342, "learning_rate": 1.8838029304390083e-05, "loss": 0.0028, "step": 9651 }, { "epoch": 0.533024077755688, "grad_norm": 0.1987900584936142, "learning_rate": 1.883445805672069e-05, "loss": 0.0061, "step": 9652 }, { "epoch": 0.5330793019659819, "grad_norm": 2.1115481853485107, "learning_rate": 1.8830886846340296e-05, "loss": 0.5393, "step": 9653 }, { "epoch": 0.5331345261762757, "grad_norm": 1.70383882522583, "learning_rate": 1.8827315673363166e-05, "loss": 0.1683, "step": 9654 }, { "epoch": 0.5331897503865695, "grad_norm": 4.0062055587768555, "learning_rate": 1.8823744537903544e-05, "loss": 0.4516, "step": 9655 }, { "epoch": 0.5332449745968633, "grad_norm": 1.9365631341934204, "learning_rate": 1.8820173440075686e-05, "loss": 0.5948, "step": 9656 }, { "epoch": 0.5333001988071571, "grad_norm": 0.05497296527028084, "learning_rate": 1.881660237999383e-05, "loss": 0.0017, "step": 9657 }, { "epoch": 0.5333554230174509, "grad_norm": 2.13710880279541, "learning_rate": 1.8813031357772245e-05, "loss": 0.3267, "step": 9658 }, { "epoch": 0.5334106472277447, "grad_norm": 5.740593910217285, "learning_rate": 1.8809460373525156e-05, "loss": 0.3644, "step": 9659 }, { "epoch": 0.5334658714380385, "grad_norm": 3.6925182342529297, "learning_rate": 1.8805889427366827e-05, "loss": 0.285, "step": 9660 }, { "epoch": 0.5335210956483323, "grad_norm": 0.3172450065612793, "learning_rate": 1.880231851941149e-05, "loss": 0.008, "step": 9661 }, { "epoch": 0.533576319858626, "grad_norm": 0.17115476727485657, "learning_rate": 1.8798747649773396e-05, "loss": 0.0048, "step": 9662 }, { "epoch": 0.5336315440689198, "grad_norm": 0.06260540336370468, "learning_rate": 1.879517681856678e-05, "loss": 0.0021, "step": 9663 }, { "epoch": 0.5336867682792136, "grad_norm": 2.1770551204681396, "learning_rate": 1.8791606025905887e-05, "loss": 0.3801, "step": 9664 }, { "epoch": 0.5337419924895074, "grad_norm": 2.7047064304351807, "learning_rate": 1.8788035271904958e-05, "loss": 0.2251, "step": 9665 }, { "epoch": 0.5337972166998012, "grad_norm": 2.490187406539917, "learning_rate": 1.878446455667824e-05, "loss": 0.0504, "step": 9666 }, { "epoch": 0.533852440910095, "grad_norm": 0.06383632868528366, "learning_rate": 1.878089388033995e-05, "loss": 0.002, "step": 9667 }, { "epoch": 0.5339076651203888, "grad_norm": 0.04853050038218498, "learning_rate": 1.8777323243004344e-05, "loss": 0.0014, "step": 9668 }, { "epoch": 0.5339628893306826, "grad_norm": 1.7141931056976318, "learning_rate": 1.8773752644785642e-05, "loss": 0.0476, "step": 9669 }, { "epoch": 0.5340181135409764, "grad_norm": 0.012545207515358925, "learning_rate": 1.8770182085798088e-05, "loss": 0.0004, "step": 9670 }, { "epoch": 0.5340733377512702, "grad_norm": 0.13102255761623383, "learning_rate": 1.8766611566155905e-05, "loss": 0.0037, "step": 9671 }, { "epoch": 0.534128561961564, "grad_norm": 1.1359407901763916, "learning_rate": 1.8763041085973334e-05, "loss": 0.029, "step": 9672 }, { "epoch": 0.5341837861718577, "grad_norm": 2.452378749847412, "learning_rate": 1.8759470645364598e-05, "loss": 0.3139, "step": 9673 }, { "epoch": 0.5342390103821515, "grad_norm": 0.32112041115760803, "learning_rate": 1.875590024444393e-05, "loss": 0.0097, "step": 9674 }, { "epoch": 0.5342942345924453, "grad_norm": 0.47513535618782043, "learning_rate": 1.8752329883325547e-05, "loss": 0.014, "step": 9675 }, { "epoch": 0.5343494588027391, "grad_norm": 1.436781883239746, "learning_rate": 1.87487595621237e-05, "loss": 0.1065, "step": 9676 }, { "epoch": 0.5344046830130329, "grad_norm": 1.3997151851654053, "learning_rate": 1.874518928095258e-05, "loss": 0.0373, "step": 9677 }, { "epoch": 0.5344599072233267, "grad_norm": 0.1119563952088356, "learning_rate": 1.8741619039926435e-05, "loss": 0.0032, "step": 9678 }, { "epoch": 0.5345151314336205, "grad_norm": 4.011725425720215, "learning_rate": 1.8738048839159475e-05, "loss": 1.1843, "step": 9679 }, { "epoch": 0.5345703556439143, "grad_norm": 0.014131344854831696, "learning_rate": 1.873447867876593e-05, "loss": 0.0005, "step": 9680 }, { "epoch": 0.5346255798542081, "grad_norm": 0.03611394762992859, "learning_rate": 1.873090855886001e-05, "loss": 0.0011, "step": 9681 }, { "epoch": 0.5346808040645019, "grad_norm": 3.390591859817505, "learning_rate": 1.8727338479555946e-05, "loss": 0.5525, "step": 9682 }, { "epoch": 0.5347360282747957, "grad_norm": 0.128509983420372, "learning_rate": 1.8723768440967935e-05, "loss": 0.0043, "step": 9683 }, { "epoch": 0.5347912524850894, "grad_norm": 0.9340135455131531, "learning_rate": 1.872019844321022e-05, "loss": 0.0155, "step": 9684 }, { "epoch": 0.5348464766953832, "grad_norm": 4.634525299072266, "learning_rate": 1.8716628486396987e-05, "loss": 0.2566, "step": 9685 }, { "epoch": 0.534901700905677, "grad_norm": 2.363297462463379, "learning_rate": 1.871305857064247e-05, "loss": 0.3385, "step": 9686 }, { "epoch": 0.5349569251159708, "grad_norm": 0.13983012735843658, "learning_rate": 1.8709488696060873e-05, "loss": 0.0053, "step": 9687 }, { "epoch": 0.5350121493262646, "grad_norm": 1.6501877307891846, "learning_rate": 1.87059188627664e-05, "loss": 0.0584, "step": 9688 }, { "epoch": 0.5350673735365584, "grad_norm": 1.3600605726242065, "learning_rate": 1.8702349070873276e-05, "loss": 0.0548, "step": 9689 }, { "epoch": 0.5351225977468522, "grad_norm": 2.254091739654541, "learning_rate": 1.869877932049569e-05, "loss": 0.0628, "step": 9690 }, { "epoch": 0.535177821957146, "grad_norm": 3.22481107711792, "learning_rate": 1.8695209611747867e-05, "loss": 0.3092, "step": 9691 }, { "epoch": 0.5352330461674398, "grad_norm": 1.3301408290863037, "learning_rate": 1.8691639944743994e-05, "loss": 0.031, "step": 9692 }, { "epoch": 0.5352882703777336, "grad_norm": 0.1636846363544464, "learning_rate": 1.868807031959829e-05, "loss": 0.0046, "step": 9693 }, { "epoch": 0.5353434945880274, "grad_norm": 2.810368776321411, "learning_rate": 1.8684500736424946e-05, "loss": 0.5116, "step": 9694 }, { "epoch": 0.5353987187983212, "grad_norm": 1.0505167245864868, "learning_rate": 1.8680931195338175e-05, "loss": 0.0497, "step": 9695 }, { "epoch": 0.5354539430086149, "grad_norm": 1.8766098022460938, "learning_rate": 1.867736169645216e-05, "loss": 0.1304, "step": 9696 }, { "epoch": 0.5355091672189087, "grad_norm": 0.10032183676958084, "learning_rate": 1.867379223988113e-05, "loss": 0.0028, "step": 9697 }, { "epoch": 0.5355643914292025, "grad_norm": 0.13798941671848297, "learning_rate": 1.867022282573924e-05, "loss": 0.0026, "step": 9698 }, { "epoch": 0.5356196156394963, "grad_norm": 0.1071614995598793, "learning_rate": 1.866665345414072e-05, "loss": 0.0025, "step": 9699 }, { "epoch": 0.5356748398497901, "grad_norm": 0.021680142730474472, "learning_rate": 1.8663084125199747e-05, "loss": 0.0006, "step": 9700 }, { "epoch": 0.5357300640600839, "grad_norm": 2.296534299850464, "learning_rate": 1.865951483903052e-05, "loss": 0.0581, "step": 9701 }, { "epoch": 0.5357852882703777, "grad_norm": 0.05250668525695801, "learning_rate": 1.8655945595747225e-05, "loss": 0.0011, "step": 9702 }, { "epoch": 0.5358405124806715, "grad_norm": 0.051227957010269165, "learning_rate": 1.8652376395464066e-05, "loss": 0.0014, "step": 9703 }, { "epoch": 0.5358957366909654, "grad_norm": 0.10991834849119186, "learning_rate": 1.8648807238295216e-05, "loss": 0.0032, "step": 9704 }, { "epoch": 0.5359509609012592, "grad_norm": 1.4612538814544678, "learning_rate": 1.8645238124354875e-05, "loss": 0.0518, "step": 9705 }, { "epoch": 0.536006185111553, "grad_norm": 4.68102502822876, "learning_rate": 1.8641669053757214e-05, "loss": 1.2269, "step": 9706 }, { "epoch": 0.5360614093218466, "grad_norm": 0.010308080352842808, "learning_rate": 1.863810002661644e-05, "loss": 0.0004, "step": 9707 }, { "epoch": 0.5361166335321405, "grad_norm": 0.8994638323783875, "learning_rate": 1.863453104304671e-05, "loss": 0.0058, "step": 9708 }, { "epoch": 0.5361718577424343, "grad_norm": 2.1424732208251953, "learning_rate": 1.8630962103162227e-05, "loss": 0.1226, "step": 9709 }, { "epoch": 0.5362270819527281, "grad_norm": 6.379857063293457, "learning_rate": 1.8627393207077158e-05, "loss": 0.52, "step": 9710 }, { "epoch": 0.5362823061630219, "grad_norm": 1.1761959791183472, "learning_rate": 1.8623824354905692e-05, "loss": 0.0514, "step": 9711 }, { "epoch": 0.5363375303733157, "grad_norm": 2.739823579788208, "learning_rate": 1.8620255546762e-05, "loss": 0.2974, "step": 9712 }, { "epoch": 0.5363927545836095, "grad_norm": 5.6124749183654785, "learning_rate": 1.861668678276027e-05, "loss": 0.769, "step": 9713 }, { "epoch": 0.5364479787939033, "grad_norm": 0.12510958313941956, "learning_rate": 1.8613118063014656e-05, "loss": 0.0037, "step": 9714 }, { "epoch": 0.5365032030041971, "grad_norm": 4.03131628036499, "learning_rate": 1.8609549387639352e-05, "loss": 1.3887, "step": 9715 }, { "epoch": 0.5365584272144909, "grad_norm": 4.929471969604492, "learning_rate": 1.8605980756748515e-05, "loss": 0.9321, "step": 9716 }, { "epoch": 0.5366136514247847, "grad_norm": 3.9066343307495117, "learning_rate": 1.8602412170456327e-05, "loss": 0.9988, "step": 9717 }, { "epoch": 0.5366688756350784, "grad_norm": 2.1802451610565186, "learning_rate": 1.859884362887695e-05, "loss": 0.0948, "step": 9718 }, { "epoch": 0.5367240998453722, "grad_norm": 0.04179471731185913, "learning_rate": 1.8595275132124556e-05, "loss": 0.0012, "step": 9719 }, { "epoch": 0.536779324055666, "grad_norm": 2.3909575939178467, "learning_rate": 1.8591706680313306e-05, "loss": 0.12, "step": 9720 }, { "epoch": 0.5368345482659598, "grad_norm": 2.333425283432007, "learning_rate": 1.8588138273557378e-05, "loss": 0.4342, "step": 9721 }, { "epoch": 0.5368897724762536, "grad_norm": 0.7353608012199402, "learning_rate": 1.8584569911970908e-05, "loss": 0.0186, "step": 9722 }, { "epoch": 0.5369449966865474, "grad_norm": 1.7733267545700073, "learning_rate": 1.8581001595668097e-05, "loss": 0.1044, "step": 9723 }, { "epoch": 0.5370002208968412, "grad_norm": 2.680161952972412, "learning_rate": 1.857743332476307e-05, "loss": 0.685, "step": 9724 }, { "epoch": 0.537055445107135, "grad_norm": 5.127110004425049, "learning_rate": 1.857386509937001e-05, "loss": 0.1539, "step": 9725 }, { "epoch": 0.5371106693174288, "grad_norm": 0.03670184314250946, "learning_rate": 1.8570296919603054e-05, "loss": 0.0015, "step": 9726 }, { "epoch": 0.5371658935277226, "grad_norm": 4.297914981842041, "learning_rate": 1.856672878557638e-05, "loss": 0.0776, "step": 9727 }, { "epoch": 0.5372211177380164, "grad_norm": 0.0453745536506176, "learning_rate": 1.856316069740413e-05, "loss": 0.0012, "step": 9728 }, { "epoch": 0.5372763419483101, "grad_norm": 6.816233158111572, "learning_rate": 1.8559592655200458e-05, "loss": 1.3451, "step": 9729 }, { "epoch": 0.5373315661586039, "grad_norm": 2.0599212646484375, "learning_rate": 1.8556024659079517e-05, "loss": 0.0576, "step": 9730 }, { "epoch": 0.5373867903688977, "grad_norm": 0.21090638637542725, "learning_rate": 1.8552456709155464e-05, "loss": 0.0052, "step": 9731 }, { "epoch": 0.5374420145791915, "grad_norm": 0.08661498129367828, "learning_rate": 1.8548888805542436e-05, "loss": 0.0021, "step": 9732 }, { "epoch": 0.5374972387894853, "grad_norm": 0.72967928647995, "learning_rate": 1.854532094835459e-05, "loss": 0.0129, "step": 9733 }, { "epoch": 0.5375524629997791, "grad_norm": 0.012576769106090069, "learning_rate": 1.8541753137706064e-05, "loss": 0.0003, "step": 9734 }, { "epoch": 0.5376076872100729, "grad_norm": 0.014393080025911331, "learning_rate": 1.8538185373711008e-05, "loss": 0.0005, "step": 9735 }, { "epoch": 0.5376629114203667, "grad_norm": 0.03532876446843147, "learning_rate": 1.8534617656483562e-05, "loss": 0.001, "step": 9736 }, { "epoch": 0.5377181356306605, "grad_norm": 0.022993527352809906, "learning_rate": 1.853104998613787e-05, "loss": 0.001, "step": 9737 }, { "epoch": 0.5377733598409543, "grad_norm": 1.485435962677002, "learning_rate": 1.8527482362788073e-05, "loss": 0.0421, "step": 9738 }, { "epoch": 0.5378285840512481, "grad_norm": 0.22780728340148926, "learning_rate": 1.852391478654831e-05, "loss": 0.0054, "step": 9739 }, { "epoch": 0.5378838082615418, "grad_norm": 0.9752526879310608, "learning_rate": 1.852034725753271e-05, "loss": 0.1235, "step": 9740 }, { "epoch": 0.5379390324718356, "grad_norm": 2.7558035850524902, "learning_rate": 1.8516779775855415e-05, "loss": 0.1508, "step": 9741 }, { "epoch": 0.5379942566821294, "grad_norm": 0.6419126987457275, "learning_rate": 1.8513212341630557e-05, "loss": 0.0178, "step": 9742 }, { "epoch": 0.5380494808924232, "grad_norm": 4.1195268630981445, "learning_rate": 1.8509644954972267e-05, "loss": 0.5414, "step": 9743 }, { "epoch": 0.538104705102717, "grad_norm": 0.2286168932914734, "learning_rate": 1.850607761599468e-05, "loss": 0.0055, "step": 9744 }, { "epoch": 0.5381599293130108, "grad_norm": 0.5674654841423035, "learning_rate": 1.8502510324811923e-05, "loss": 0.0139, "step": 9745 }, { "epoch": 0.5382151535233046, "grad_norm": 3.9597339630126953, "learning_rate": 1.8498943081538123e-05, "loss": 0.2584, "step": 9746 }, { "epoch": 0.5382703777335984, "grad_norm": 0.8552152514457703, "learning_rate": 1.8495375886287413e-05, "loss": 0.0205, "step": 9747 }, { "epoch": 0.5383256019438922, "grad_norm": 3.6840107440948486, "learning_rate": 1.849180873917391e-05, "loss": 0.3146, "step": 9748 }, { "epoch": 0.538380826154186, "grad_norm": 0.8338351249694824, "learning_rate": 1.8488241640311733e-05, "loss": 0.0199, "step": 9749 }, { "epoch": 0.5384360503644798, "grad_norm": 3.5919036865234375, "learning_rate": 1.8484674589815013e-05, "loss": 0.2931, "step": 9750 }, { "epoch": 0.5384912745747735, "grad_norm": 2.677433729171753, "learning_rate": 1.8481107587797864e-05, "loss": 0.1217, "step": 9751 }, { "epoch": 0.5385464987850673, "grad_norm": 0.24871550500392914, "learning_rate": 1.847754063437442e-05, "loss": 0.0097, "step": 9752 }, { "epoch": 0.5386017229953611, "grad_norm": 0.15388888120651245, "learning_rate": 1.8473973729658764e-05, "loss": 0.0045, "step": 9753 }, { "epoch": 0.5386569472056549, "grad_norm": 0.11561587452888489, "learning_rate": 1.847040687376505e-05, "loss": 0.0031, "step": 9754 }, { "epoch": 0.5387121714159487, "grad_norm": 2.545820951461792, "learning_rate": 1.846684006680737e-05, "loss": 0.1388, "step": 9755 }, { "epoch": 0.5387673956262425, "grad_norm": 0.15265913307666779, "learning_rate": 1.8463273308899837e-05, "loss": 0.0028, "step": 9756 }, { "epoch": 0.5388226198365363, "grad_norm": 0.043963722884655, "learning_rate": 1.8459706600156567e-05, "loss": 0.0016, "step": 9757 }, { "epoch": 0.5388778440468301, "grad_norm": 2.9725308418273926, "learning_rate": 1.845613994069167e-05, "loss": 0.2427, "step": 9758 }, { "epoch": 0.538933068257124, "grad_norm": 0.3812604248523712, "learning_rate": 1.845257333061925e-05, "loss": 0.013, "step": 9759 }, { "epoch": 0.5389882924674178, "grad_norm": 1.9801043272018433, "learning_rate": 1.8449006770053416e-05, "loss": 0.201, "step": 9760 }, { "epoch": 0.5390435166777116, "grad_norm": 0.3543494939804077, "learning_rate": 1.8445440259108267e-05, "loss": 0.0092, "step": 9761 }, { "epoch": 0.5390987408880054, "grad_norm": 1.761508822441101, "learning_rate": 1.844187379789792e-05, "loss": 0.0801, "step": 9762 }, { "epoch": 0.539153965098299, "grad_norm": 0.213108628988266, "learning_rate": 1.8438307386536457e-05, "loss": 0.005, "step": 9763 }, { "epoch": 0.5392091893085929, "grad_norm": 5.5511956214904785, "learning_rate": 1.843474102513799e-05, "loss": 0.7593, "step": 9764 }, { "epoch": 0.5392644135188867, "grad_norm": 3.1071879863739014, "learning_rate": 1.843117471381661e-05, "loss": 0.3307, "step": 9765 }, { "epoch": 0.5393196377291805, "grad_norm": 2.1965904235839844, "learning_rate": 1.842760845268642e-05, "loss": 0.4411, "step": 9766 }, { "epoch": 0.5393748619394743, "grad_norm": 0.09960447251796722, "learning_rate": 1.842404224186151e-05, "loss": 0.0026, "step": 9767 }, { "epoch": 0.5394300861497681, "grad_norm": 3.307298421859741, "learning_rate": 1.8420476081455976e-05, "loss": 0.9299, "step": 9768 }, { "epoch": 0.5394853103600619, "grad_norm": 4.1333417892456055, "learning_rate": 1.841690997158391e-05, "loss": 1.1944, "step": 9769 }, { "epoch": 0.5395405345703557, "grad_norm": 0.2585618495941162, "learning_rate": 1.8413343912359404e-05, "loss": 0.0055, "step": 9770 }, { "epoch": 0.5395957587806495, "grad_norm": 1.3253265619277954, "learning_rate": 1.8409777903896537e-05, "loss": 0.0869, "step": 9771 }, { "epoch": 0.5396509829909433, "grad_norm": 1.9052460193634033, "learning_rate": 1.8406211946309407e-05, "loss": 0.1106, "step": 9772 }, { "epoch": 0.5397062072012371, "grad_norm": 0.13929232954978943, "learning_rate": 1.8402646039712088e-05, "loss": 0.0035, "step": 9773 }, { "epoch": 0.5397614314115308, "grad_norm": 0.030896680429577827, "learning_rate": 1.8399080184218675e-05, "loss": 0.0009, "step": 9774 }, { "epoch": 0.5398166556218246, "grad_norm": 4.237918853759766, "learning_rate": 1.839551437994324e-05, "loss": 0.4754, "step": 9775 }, { "epoch": 0.5398718798321184, "grad_norm": 0.24258975684642792, "learning_rate": 1.8391948626999873e-05, "loss": 0.006, "step": 9776 }, { "epoch": 0.5399271040424122, "grad_norm": 0.10718325525522232, "learning_rate": 1.8388382925502644e-05, "loss": 0.0027, "step": 9777 }, { "epoch": 0.539982328252706, "grad_norm": 3.094531536102295, "learning_rate": 1.838481727556564e-05, "loss": 0.0428, "step": 9778 }, { "epoch": 0.5400375524629998, "grad_norm": 3.377610445022583, "learning_rate": 1.8381251677302916e-05, "loss": 0.2009, "step": 9779 }, { "epoch": 0.5400927766732936, "grad_norm": 0.05296732485294342, "learning_rate": 1.8377686130828572e-05, "loss": 0.0018, "step": 9780 }, { "epoch": 0.5401480008835874, "grad_norm": 0.045954879373311996, "learning_rate": 1.837412063625666e-05, "loss": 0.0013, "step": 9781 }, { "epoch": 0.5402032250938812, "grad_norm": 0.027334267273545265, "learning_rate": 1.8370555193701263e-05, "loss": 0.0006, "step": 9782 }, { "epoch": 0.540258449304175, "grad_norm": 0.01662173494696617, "learning_rate": 1.8366989803276437e-05, "loss": 0.0005, "step": 9783 }, { "epoch": 0.5403136735144688, "grad_norm": 0.019296668469905853, "learning_rate": 1.8363424465096264e-05, "loss": 0.0006, "step": 9784 }, { "epoch": 0.5403688977247625, "grad_norm": 0.6076871752738953, "learning_rate": 1.8359859179274792e-05, "loss": 0.1192, "step": 9785 }, { "epoch": 0.5404241219350563, "grad_norm": 0.06906982511281967, "learning_rate": 1.8356293945926107e-05, "loss": 0.0021, "step": 9786 }, { "epoch": 0.5404793461453501, "grad_norm": 0.22857198119163513, "learning_rate": 1.8352728765164246e-05, "loss": 0.0053, "step": 9787 }, { "epoch": 0.5405345703556439, "grad_norm": 2.48991322517395, "learning_rate": 1.834916363710329e-05, "loss": 0.3581, "step": 9788 }, { "epoch": 0.5405897945659377, "grad_norm": 1.5572586059570312, "learning_rate": 1.8345598561857283e-05, "loss": 0.164, "step": 9789 }, { "epoch": 0.5406450187762315, "grad_norm": 1.2058364152908325, "learning_rate": 1.834203353954029e-05, "loss": 0.04, "step": 9790 }, { "epoch": 0.5407002429865253, "grad_norm": 1.4944998025894165, "learning_rate": 1.8338468570266365e-05, "loss": 0.1501, "step": 9791 }, { "epoch": 0.5407554671968191, "grad_norm": 2.6905057430267334, "learning_rate": 1.833490365414956e-05, "loss": 0.2981, "step": 9792 }, { "epoch": 0.5408106914071129, "grad_norm": 0.007952399551868439, "learning_rate": 1.8331338791303925e-05, "loss": 0.0003, "step": 9793 }, { "epoch": 0.5408659156174067, "grad_norm": 0.8182218074798584, "learning_rate": 1.832777398184352e-05, "loss": 0.0176, "step": 9794 }, { "epoch": 0.5409211398277005, "grad_norm": 4.529772758483887, "learning_rate": 1.8324209225882373e-05, "loss": 1.555, "step": 9795 }, { "epoch": 0.5409763640379942, "grad_norm": 2.7824926376342773, "learning_rate": 1.832064452353456e-05, "loss": 0.4001, "step": 9796 }, { "epoch": 0.541031588248288, "grad_norm": 3.185579776763916, "learning_rate": 1.8317079874914098e-05, "loss": 0.6441, "step": 9797 }, { "epoch": 0.5410868124585818, "grad_norm": 0.02770497091114521, "learning_rate": 1.8313515280135047e-05, "loss": 0.001, "step": 9798 }, { "epoch": 0.5411420366688756, "grad_norm": 0.37391558289527893, "learning_rate": 1.8309950739311436e-05, "loss": 0.0147, "step": 9799 }, { "epoch": 0.5411972608791694, "grad_norm": 2.170741319656372, "learning_rate": 1.830638625255732e-05, "loss": 0.0902, "step": 9800 }, { "epoch": 0.5412524850894632, "grad_norm": 1.2979241609573364, "learning_rate": 1.8302821819986726e-05, "loss": 0.0575, "step": 9801 }, { "epoch": 0.541307709299757, "grad_norm": 3.3682360649108887, "learning_rate": 1.8299257441713698e-05, "loss": 0.9747, "step": 9802 }, { "epoch": 0.5413629335100508, "grad_norm": 3.993182420730591, "learning_rate": 1.8295693117852257e-05, "loss": 0.6168, "step": 9803 }, { "epoch": 0.5414181577203446, "grad_norm": 5.262040615081787, "learning_rate": 1.8292128848516455e-05, "loss": 1.0009, "step": 9804 }, { "epoch": 0.5414733819306384, "grad_norm": 0.21589277684688568, "learning_rate": 1.828856463382031e-05, "loss": 0.0061, "step": 9805 }, { "epoch": 0.5415286061409322, "grad_norm": 0.41690266132354736, "learning_rate": 1.8285000473877853e-05, "loss": 0.0164, "step": 9806 }, { "epoch": 0.5415838303512259, "grad_norm": 6.276009559631348, "learning_rate": 1.8281436368803108e-05, "loss": 1.2442, "step": 9807 }, { "epoch": 0.5416390545615197, "grad_norm": 1.9986495971679688, "learning_rate": 1.8277872318710116e-05, "loss": 0.1784, "step": 9808 }, { "epoch": 0.5416942787718135, "grad_norm": 3.9482908248901367, "learning_rate": 1.8274308323712893e-05, "loss": 0.5363, "step": 9809 }, { "epoch": 0.5417495029821073, "grad_norm": 0.1848013699054718, "learning_rate": 1.827074438392545e-05, "loss": 0.0067, "step": 9810 }, { "epoch": 0.5418047271924011, "grad_norm": 0.060391616076231, "learning_rate": 1.8267180499461823e-05, "loss": 0.0015, "step": 9811 }, { "epoch": 0.5418599514026949, "grad_norm": 1.2793573141098022, "learning_rate": 1.826361667043602e-05, "loss": 0.0367, "step": 9812 }, { "epoch": 0.5419151756129887, "grad_norm": 0.009480898268520832, "learning_rate": 1.8260052896962067e-05, "loss": 0.0002, "step": 9813 }, { "epoch": 0.5419703998232825, "grad_norm": 1.79004967212677, "learning_rate": 1.825648917915397e-05, "loss": 0.0777, "step": 9814 }, { "epoch": 0.5420256240335763, "grad_norm": 3.311448812484741, "learning_rate": 1.8252925517125755e-05, "loss": 0.0951, "step": 9815 }, { "epoch": 0.5420808482438702, "grad_norm": 0.010600791312754154, "learning_rate": 1.824936191099142e-05, "loss": 0.0004, "step": 9816 }, { "epoch": 0.542136072454164, "grad_norm": 4.372776985168457, "learning_rate": 1.824579836086499e-05, "loss": 0.5834, "step": 9817 }, { "epoch": 0.5421912966644576, "grad_norm": 3.2649102210998535, "learning_rate": 1.8242234866860453e-05, "loss": 0.3321, "step": 9818 }, { "epoch": 0.5422465208747514, "grad_norm": 0.05103257670998573, "learning_rate": 1.823867142909184e-05, "loss": 0.0022, "step": 9819 }, { "epoch": 0.5423017450850453, "grad_norm": 0.500510573387146, "learning_rate": 1.823510804767313e-05, "loss": 0.014, "step": 9820 }, { "epoch": 0.542356969295339, "grad_norm": 0.5741702914237976, "learning_rate": 1.8231544722718343e-05, "loss": 0.0166, "step": 9821 }, { "epoch": 0.5424121935056329, "grad_norm": 0.34085163474082947, "learning_rate": 1.8227981454341473e-05, "loss": 0.0106, "step": 9822 }, { "epoch": 0.5424674177159267, "grad_norm": 0.5019432306289673, "learning_rate": 1.8224418242656525e-05, "loss": 0.0138, "step": 9823 }, { "epoch": 0.5425226419262205, "grad_norm": 5.894011497497559, "learning_rate": 1.8220855087777486e-05, "loss": 0.4687, "step": 9824 }, { "epoch": 0.5425778661365143, "grad_norm": 2.5275704860687256, "learning_rate": 1.821729198981837e-05, "loss": 0.3547, "step": 9825 }, { "epoch": 0.5426330903468081, "grad_norm": 2.7527196407318115, "learning_rate": 1.821372894889314e-05, "loss": 0.7559, "step": 9826 }, { "epoch": 0.5426883145571019, "grad_norm": 0.037565816193819046, "learning_rate": 1.8210165965115823e-05, "loss": 0.0011, "step": 9827 }, { "epoch": 0.5427435387673957, "grad_norm": 3.834327220916748, "learning_rate": 1.8206603038600383e-05, "loss": 1.1058, "step": 9828 }, { "epoch": 0.5427987629776894, "grad_norm": 7.2571821212768555, "learning_rate": 1.820304016946082e-05, "loss": 0.7393, "step": 9829 }, { "epoch": 0.5428539871879832, "grad_norm": 2.3922579288482666, "learning_rate": 1.8199477357811116e-05, "loss": 0.1756, "step": 9830 }, { "epoch": 0.542909211398277, "grad_norm": 3.643099308013916, "learning_rate": 1.8195914603765262e-05, "loss": 1.0464, "step": 9831 }, { "epoch": 0.5429644356085708, "grad_norm": 4.076047897338867, "learning_rate": 1.819235190743723e-05, "loss": 0.684, "step": 9832 }, { "epoch": 0.5430196598188646, "grad_norm": 2.7490153312683105, "learning_rate": 1.8188789268941015e-05, "loss": 0.7321, "step": 9833 }, { "epoch": 0.5430748840291584, "grad_norm": 0.13306055963039398, "learning_rate": 1.8185226688390572e-05, "loss": 0.0052, "step": 9834 }, { "epoch": 0.5431301082394522, "grad_norm": 2.992835760116577, "learning_rate": 1.8181664165899914e-05, "loss": 0.3196, "step": 9835 }, { "epoch": 0.543185332449746, "grad_norm": 0.25296518206596375, "learning_rate": 1.817810170158298e-05, "loss": 0.0062, "step": 9836 }, { "epoch": 0.5432405566600398, "grad_norm": 1.904103398323059, "learning_rate": 1.8174539295553767e-05, "loss": 0.1469, "step": 9837 }, { "epoch": 0.5432957808703336, "grad_norm": 2.412055015563965, "learning_rate": 1.8170976947926234e-05, "loss": 0.2904, "step": 9838 }, { "epoch": 0.5433510050806274, "grad_norm": 5.513004779815674, "learning_rate": 1.816741465881436e-05, "loss": 0.7812, "step": 9839 }, { "epoch": 0.5434062292909212, "grad_norm": 0.010777892544865608, "learning_rate": 1.81638524283321e-05, "loss": 0.0002, "step": 9840 }, { "epoch": 0.5434614535012149, "grad_norm": 4.307239532470703, "learning_rate": 1.816029025659344e-05, "loss": 0.3503, "step": 9841 }, { "epoch": 0.5435166777115087, "grad_norm": 5.505363941192627, "learning_rate": 1.815672814371232e-05, "loss": 0.2777, "step": 9842 }, { "epoch": 0.5435719019218025, "grad_norm": 1.7061433792114258, "learning_rate": 1.8153166089802726e-05, "loss": 0.032, "step": 9843 }, { "epoch": 0.5436271261320963, "grad_norm": 2.919022560119629, "learning_rate": 1.8149604094978598e-05, "loss": 0.7975, "step": 9844 }, { "epoch": 0.5436823503423901, "grad_norm": 0.21051132678985596, "learning_rate": 1.8146042159353908e-05, "loss": 0.0073, "step": 9845 }, { "epoch": 0.5437375745526839, "grad_norm": 3.1692214012145996, "learning_rate": 1.81424802830426e-05, "loss": 0.0869, "step": 9846 }, { "epoch": 0.5437927987629777, "grad_norm": 2.382568120956421, "learning_rate": 1.8138918466158646e-05, "loss": 0.3317, "step": 9847 }, { "epoch": 0.5438480229732715, "grad_norm": 0.0536544993519783, "learning_rate": 1.813535670881598e-05, "loss": 0.0013, "step": 9848 }, { "epoch": 0.5439032471835653, "grad_norm": 2.107844352722168, "learning_rate": 1.8131795011128567e-05, "loss": 0.1012, "step": 9849 }, { "epoch": 0.5439584713938591, "grad_norm": 0.28671374917030334, "learning_rate": 1.8128233373210347e-05, "loss": 0.0042, "step": 9850 }, { "epoch": 0.5440136956041529, "grad_norm": 2.962185859680176, "learning_rate": 1.8124671795175276e-05, "loss": 0.2096, "step": 9851 }, { "epoch": 0.5440689198144466, "grad_norm": 0.2982623875141144, "learning_rate": 1.8121110277137287e-05, "loss": 0.0084, "step": 9852 }, { "epoch": 0.5441241440247404, "grad_norm": 0.8657447695732117, "learning_rate": 1.8117548819210333e-05, "loss": 0.0209, "step": 9853 }, { "epoch": 0.5441793682350342, "grad_norm": 3.95224928855896, "learning_rate": 1.8113987421508342e-05, "loss": 0.2348, "step": 9854 }, { "epoch": 0.544234592445328, "grad_norm": 2.467733860015869, "learning_rate": 1.8110426084145273e-05, "loss": 0.1073, "step": 9855 }, { "epoch": 0.5442898166556218, "grad_norm": 0.09604332596063614, "learning_rate": 1.8106864807235046e-05, "loss": 0.0035, "step": 9856 }, { "epoch": 0.5443450408659156, "grad_norm": 6.255794525146484, "learning_rate": 1.810330359089161e-05, "loss": 0.3472, "step": 9857 }, { "epoch": 0.5444002650762094, "grad_norm": 1.9951953887939453, "learning_rate": 1.8099742435228883e-05, "loss": 0.2025, "step": 9858 }, { "epoch": 0.5444554892865032, "grad_norm": 4.648390769958496, "learning_rate": 1.8096181340360816e-05, "loss": 0.5186, "step": 9859 }, { "epoch": 0.544510713496797, "grad_norm": 3.204573154449463, "learning_rate": 1.809262030640132e-05, "loss": 0.2161, "step": 9860 }, { "epoch": 0.5445659377070908, "grad_norm": 2.986849546432495, "learning_rate": 1.8089059333464336e-05, "loss": 0.5017, "step": 9861 }, { "epoch": 0.5446211619173846, "grad_norm": 1.2101365327835083, "learning_rate": 1.8085498421663778e-05, "loss": 0.0584, "step": 9862 }, { "epoch": 0.5446763861276783, "grad_norm": 0.13170328736305237, "learning_rate": 1.8081937571113583e-05, "loss": 0.005, "step": 9863 }, { "epoch": 0.5447316103379721, "grad_norm": 0.03952762112021446, "learning_rate": 1.8078376781927658e-05, "loss": 0.0012, "step": 9864 }, { "epoch": 0.5447868345482659, "grad_norm": 1.7396999597549438, "learning_rate": 1.8074816054219933e-05, "loss": 0.1162, "step": 9865 }, { "epoch": 0.5448420587585597, "grad_norm": 4.242096900939941, "learning_rate": 1.8071255388104324e-05, "loss": 0.5778, "step": 9866 }, { "epoch": 0.5448972829688535, "grad_norm": 1.5010377168655396, "learning_rate": 1.806769478369475e-05, "loss": 0.1382, "step": 9867 }, { "epoch": 0.5449525071791473, "grad_norm": 0.1385187804698944, "learning_rate": 1.806413424110512e-05, "loss": 0.0046, "step": 9868 }, { "epoch": 0.5450077313894411, "grad_norm": 0.9264638423919678, "learning_rate": 1.806057376044934e-05, "loss": 0.0284, "step": 9869 }, { "epoch": 0.5450629555997349, "grad_norm": 2.658236265182495, "learning_rate": 1.8057013341841334e-05, "loss": 0.2384, "step": 9870 }, { "epoch": 0.5451181798100287, "grad_norm": 3.02600359916687, "learning_rate": 1.8053452985394994e-05, "loss": 0.5116, "step": 9871 }, { "epoch": 0.5451734040203225, "grad_norm": 0.02301790751516819, "learning_rate": 1.8049892691224248e-05, "loss": 0.0008, "step": 9872 }, { "epoch": 0.5452286282306164, "grad_norm": 4.656130790710449, "learning_rate": 1.804633245944297e-05, "loss": 0.3868, "step": 9873 }, { "epoch": 0.54528385244091, "grad_norm": 3.5916194915771484, "learning_rate": 1.8042772290165095e-05, "loss": 0.2219, "step": 9874 }, { "epoch": 0.5453390766512038, "grad_norm": 0.20108041167259216, "learning_rate": 1.8039212183504492e-05, "loss": 0.0049, "step": 9875 }, { "epoch": 0.5453943008614976, "grad_norm": 2.669241428375244, "learning_rate": 1.803565213957508e-05, "loss": 0.2864, "step": 9876 }, { "epoch": 0.5454495250717915, "grad_norm": 4.5818634033203125, "learning_rate": 1.8032092158490748e-05, "loss": 0.817, "step": 9877 }, { "epoch": 0.5455047492820853, "grad_norm": 3.633089780807495, "learning_rate": 1.8028532240365392e-05, "loss": 0.7461, "step": 9878 }, { "epoch": 0.5455599734923791, "grad_norm": 0.03326698765158653, "learning_rate": 1.8024972385312897e-05, "loss": 0.0012, "step": 9879 }, { "epoch": 0.5456151977026729, "grad_norm": 0.5816736817359924, "learning_rate": 1.8021412593447162e-05, "loss": 0.0111, "step": 9880 }, { "epoch": 0.5456704219129667, "grad_norm": 4.296621799468994, "learning_rate": 1.8017852864882067e-05, "loss": 0.4235, "step": 9881 }, { "epoch": 0.5457256461232605, "grad_norm": 0.20660877227783203, "learning_rate": 1.8014293199731513e-05, "loss": 0.0056, "step": 9882 }, { "epoch": 0.5457808703335543, "grad_norm": 0.1554439663887024, "learning_rate": 1.801073359810936e-05, "loss": 0.0034, "step": 9883 }, { "epoch": 0.5458360945438481, "grad_norm": 0.5665920972824097, "learning_rate": 1.800717406012951e-05, "loss": 0.0147, "step": 9884 }, { "epoch": 0.5458913187541418, "grad_norm": 0.056792136281728745, "learning_rate": 1.800361458590583e-05, "loss": 0.0016, "step": 9885 }, { "epoch": 0.5459465429644356, "grad_norm": 0.09111405909061432, "learning_rate": 1.8000055175552204e-05, "loss": 0.0023, "step": 9886 }, { "epoch": 0.5460017671747294, "grad_norm": 3.0651988983154297, "learning_rate": 1.7996495829182506e-05, "loss": 0.221, "step": 9887 }, { "epoch": 0.5460569913850232, "grad_norm": 2.604274034500122, "learning_rate": 1.7992936546910614e-05, "loss": 0.1303, "step": 9888 }, { "epoch": 0.546112215595317, "grad_norm": 4.058056831359863, "learning_rate": 1.798937732885039e-05, "loss": 0.9998, "step": 9889 }, { "epoch": 0.5461674398056108, "grad_norm": 1.2724772691726685, "learning_rate": 1.798581817511572e-05, "loss": 0.2378, "step": 9890 }, { "epoch": 0.5462226640159046, "grad_norm": 0.19296583533287048, "learning_rate": 1.7982259085820447e-05, "loss": 0.003, "step": 9891 }, { "epoch": 0.5462778882261984, "grad_norm": 1.1282140016555786, "learning_rate": 1.797870006107846e-05, "loss": 0.0379, "step": 9892 }, { "epoch": 0.5463331124364922, "grad_norm": 8.1030912399292, "learning_rate": 1.7975141101003606e-05, "loss": 0.1083, "step": 9893 }, { "epoch": 0.546388336646786, "grad_norm": 3.204883337020874, "learning_rate": 1.7971582205709757e-05, "loss": 0.7432, "step": 9894 }, { "epoch": 0.5464435608570798, "grad_norm": 0.1014976054430008, "learning_rate": 1.7968023375310762e-05, "loss": 0.0016, "step": 9895 }, { "epoch": 0.5464987850673735, "grad_norm": 0.008987764827907085, "learning_rate": 1.7964464609920492e-05, "loss": 0.0003, "step": 9896 }, { "epoch": 0.5465540092776673, "grad_norm": 0.10171764343976974, "learning_rate": 1.7960905909652785e-05, "loss": 0.0026, "step": 9897 }, { "epoch": 0.5466092334879611, "grad_norm": 3.849716901779175, "learning_rate": 1.7957347274621516e-05, "loss": 0.2837, "step": 9898 }, { "epoch": 0.5466644576982549, "grad_norm": 0.8975062966346741, "learning_rate": 1.795378870494051e-05, "loss": 0.032, "step": 9899 }, { "epoch": 0.5467196819085487, "grad_norm": 4.634673118591309, "learning_rate": 1.795023020072364e-05, "loss": 0.7038, "step": 9900 }, { "epoch": 0.5467749061188425, "grad_norm": 0.008729069493710995, "learning_rate": 1.794667176208473e-05, "loss": 0.0003, "step": 9901 }, { "epoch": 0.5468301303291363, "grad_norm": 2.8383805751800537, "learning_rate": 1.7943113389137642e-05, "loss": 0.0835, "step": 9902 }, { "epoch": 0.5468853545394301, "grad_norm": 2.358278274536133, "learning_rate": 1.7939555081996212e-05, "loss": 0.3005, "step": 9903 }, { "epoch": 0.5469405787497239, "grad_norm": 1.1946781873703003, "learning_rate": 1.793599684077428e-05, "loss": 0.0305, "step": 9904 }, { "epoch": 0.5469958029600177, "grad_norm": 4.84097957611084, "learning_rate": 1.793243866558568e-05, "loss": 0.7853, "step": 9905 }, { "epoch": 0.5470510271703115, "grad_norm": 1.1075611114501953, "learning_rate": 1.7928880556544268e-05, "loss": 0.052, "step": 9906 }, { "epoch": 0.5471062513806052, "grad_norm": 0.030421914532780647, "learning_rate": 1.7925322513763846e-05, "loss": 0.0013, "step": 9907 }, { "epoch": 0.547161475590899, "grad_norm": 0.2451116442680359, "learning_rate": 1.7921764537358278e-05, "loss": 0.0077, "step": 9908 }, { "epoch": 0.5472166998011928, "grad_norm": 1.0596939325332642, "learning_rate": 1.7918206627441367e-05, "loss": 0.0342, "step": 9909 }, { "epoch": 0.5472719240114866, "grad_norm": 3.9074089527130127, "learning_rate": 1.791464878412696e-05, "loss": 1.185, "step": 9910 }, { "epoch": 0.5473271482217804, "grad_norm": 1.4551258087158203, "learning_rate": 1.791109100752887e-05, "loss": 0.056, "step": 9911 }, { "epoch": 0.5473823724320742, "grad_norm": 0.3502557575702667, "learning_rate": 1.790753329776093e-05, "loss": 0.012, "step": 9912 }, { "epoch": 0.547437596642368, "grad_norm": 0.10551463067531586, "learning_rate": 1.7903975654936952e-05, "loss": 0.0021, "step": 9913 }, { "epoch": 0.5474928208526618, "grad_norm": 3.374443769454956, "learning_rate": 1.790041807917077e-05, "loss": 0.1033, "step": 9914 }, { "epoch": 0.5475480450629556, "grad_norm": 2.0061402320861816, "learning_rate": 1.7896860570576174e-05, "loss": 0.6702, "step": 9915 }, { "epoch": 0.5476032692732494, "grad_norm": 4.173752784729004, "learning_rate": 1.789330312926701e-05, "loss": 0.1329, "step": 9916 }, { "epoch": 0.5476584934835432, "grad_norm": 0.20304805040359497, "learning_rate": 1.788974575535707e-05, "loss": 0.0054, "step": 9917 }, { "epoch": 0.547713717693837, "grad_norm": 0.45759114623069763, "learning_rate": 1.7886188448960173e-05, "loss": 0.0144, "step": 9918 }, { "epoch": 0.5477689419041307, "grad_norm": 4.540560245513916, "learning_rate": 1.7882631210190123e-05, "loss": 0.1224, "step": 9919 }, { "epoch": 0.5478241661144245, "grad_norm": 0.911145031452179, "learning_rate": 1.7879074039160734e-05, "loss": 0.0492, "step": 9920 }, { "epoch": 0.5478793903247183, "grad_norm": 0.04507656767964363, "learning_rate": 1.78755169359858e-05, "loss": 0.0013, "step": 9921 }, { "epoch": 0.5479346145350121, "grad_norm": 2.976071357727051, "learning_rate": 1.787195990077913e-05, "loss": 0.2339, "step": 9922 }, { "epoch": 0.5479898387453059, "grad_norm": 0.025492805987596512, "learning_rate": 1.7868402933654513e-05, "loss": 0.0009, "step": 9923 }, { "epoch": 0.5480450629555997, "grad_norm": 1.2085176706314087, "learning_rate": 1.7864846034725767e-05, "loss": 0.0573, "step": 9924 }, { "epoch": 0.5481002871658935, "grad_norm": 0.05847304314374924, "learning_rate": 1.7861289204106667e-05, "loss": 0.0017, "step": 9925 }, { "epoch": 0.5481555113761873, "grad_norm": 0.623699963092804, "learning_rate": 1.7857732441911015e-05, "loss": 0.0164, "step": 9926 }, { "epoch": 0.5482107355864811, "grad_norm": 5.253626346588135, "learning_rate": 1.78541757482526e-05, "loss": 0.3281, "step": 9927 }, { "epoch": 0.548265959796775, "grad_norm": 4.090383529663086, "learning_rate": 1.7850619123245215e-05, "loss": 1.2758, "step": 9928 }, { "epoch": 0.5483211840070688, "grad_norm": 0.02148641273379326, "learning_rate": 1.7847062567002645e-05, "loss": 0.0007, "step": 9929 }, { "epoch": 0.5483764082173624, "grad_norm": 3.5026116371154785, "learning_rate": 1.7843506079638667e-05, "loss": 0.7636, "step": 9930 }, { "epoch": 0.5484316324276562, "grad_norm": 3.366882801055908, "learning_rate": 1.7839949661267074e-05, "loss": 0.1809, "step": 9931 }, { "epoch": 0.54848685663795, "grad_norm": 1.968648076057434, "learning_rate": 1.7836393312001633e-05, "loss": 0.2288, "step": 9932 }, { "epoch": 0.5485420808482439, "grad_norm": 3.5398600101470947, "learning_rate": 1.783283703195614e-05, "loss": 0.6966, "step": 9933 }, { "epoch": 0.5485973050585377, "grad_norm": 1.4774364233016968, "learning_rate": 1.782928082124435e-05, "loss": 0.0483, "step": 9934 }, { "epoch": 0.5486525292688315, "grad_norm": 0.013348684646189213, "learning_rate": 1.782572467998005e-05, "loss": 0.0005, "step": 9935 }, { "epoch": 0.5487077534791253, "grad_norm": 0.36907708644866943, "learning_rate": 1.7822168608277005e-05, "loss": 0.006, "step": 9936 }, { "epoch": 0.5487629776894191, "grad_norm": 0.06461780518293381, "learning_rate": 1.7818612606248994e-05, "loss": 0.0023, "step": 9937 }, { "epoch": 0.5488182018997129, "grad_norm": 5.846613883972168, "learning_rate": 1.7815056674009766e-05, "loss": 0.4136, "step": 9938 }, { "epoch": 0.5488734261100067, "grad_norm": 3.1001949310302734, "learning_rate": 1.7811500811673107e-05, "loss": 0.4967, "step": 9939 }, { "epoch": 0.5489286503203005, "grad_norm": 3.5059850215911865, "learning_rate": 1.7807945019352757e-05, "loss": 1.0674, "step": 9940 }, { "epoch": 0.5489838745305942, "grad_norm": 4.34925651550293, "learning_rate": 1.7804389297162494e-05, "loss": 0.3867, "step": 9941 }, { "epoch": 0.549039098740888, "grad_norm": 0.2103310525417328, "learning_rate": 1.780083364521606e-05, "loss": 0.0049, "step": 9942 }, { "epoch": 0.5490943229511818, "grad_norm": 2.3684890270233154, "learning_rate": 1.779727806362722e-05, "loss": 0.2889, "step": 9943 }, { "epoch": 0.5491495471614756, "grad_norm": 2.1647424697875977, "learning_rate": 1.7793722552509728e-05, "loss": 0.3479, "step": 9944 }, { "epoch": 0.5492047713717694, "grad_norm": 3.99565052986145, "learning_rate": 1.7790167111977336e-05, "loss": 0.3807, "step": 9945 }, { "epoch": 0.5492599955820632, "grad_norm": 1.2358698844909668, "learning_rate": 1.778661174214378e-05, "loss": 0.1673, "step": 9946 }, { "epoch": 0.549315219792357, "grad_norm": 0.38608527183532715, "learning_rate": 1.778305644312283e-05, "loss": 0.0111, "step": 9947 }, { "epoch": 0.5493704440026508, "grad_norm": 0.18803010880947113, "learning_rate": 1.77795012150282e-05, "loss": 0.0061, "step": 9948 }, { "epoch": 0.5494256682129446, "grad_norm": 0.058230381458997726, "learning_rate": 1.777594605797366e-05, "loss": 0.0016, "step": 9949 }, { "epoch": 0.5494808924232384, "grad_norm": 0.021184636279940605, "learning_rate": 1.777239097207293e-05, "loss": 0.001, "step": 9950 }, { "epoch": 0.5495361166335322, "grad_norm": 4.348365783691406, "learning_rate": 1.7768835957439752e-05, "loss": 0.5107, "step": 9951 }, { "epoch": 0.5495913408438259, "grad_norm": 3.5095670223236084, "learning_rate": 1.776528101418787e-05, "loss": 0.8518, "step": 9952 }, { "epoch": 0.5496465650541197, "grad_norm": 0.4347646236419678, "learning_rate": 1.7761726142431013e-05, "loss": 0.0079, "step": 9953 }, { "epoch": 0.5497017892644135, "grad_norm": 3.291555404663086, "learning_rate": 1.7758171342282896e-05, "loss": 0.3817, "step": 9954 }, { "epoch": 0.5497570134747073, "grad_norm": 4.866657257080078, "learning_rate": 1.7754616613857274e-05, "loss": 0.848, "step": 9955 }, { "epoch": 0.5498122376850011, "grad_norm": 0.024287119507789612, "learning_rate": 1.775106195726785e-05, "loss": 0.0008, "step": 9956 }, { "epoch": 0.5498674618952949, "grad_norm": 0.03981196880340576, "learning_rate": 1.7747507372628362e-05, "loss": 0.0017, "step": 9957 }, { "epoch": 0.5499226861055887, "grad_norm": 5.191476345062256, "learning_rate": 1.774395286005252e-05, "loss": 0.6842, "step": 9958 }, { "epoch": 0.5499779103158825, "grad_norm": 2.953873872756958, "learning_rate": 1.7740398419654052e-05, "loss": 0.6896, "step": 9959 }, { "epoch": 0.5500331345261763, "grad_norm": 0.3618065118789673, "learning_rate": 1.7736844051546667e-05, "loss": 0.009, "step": 9960 }, { "epoch": 0.5500883587364701, "grad_norm": 2.0665700435638428, "learning_rate": 1.7733289755844096e-05, "loss": 0.2281, "step": 9961 }, { "epoch": 0.5501435829467639, "grad_norm": 4.183004856109619, "learning_rate": 1.7729735532660023e-05, "loss": 0.4575, "step": 9962 }, { "epoch": 0.5501988071570576, "grad_norm": 4.892446517944336, "learning_rate": 1.772618138210819e-05, "loss": 1.0729, "step": 9963 }, { "epoch": 0.5502540313673514, "grad_norm": 0.7009468078613281, "learning_rate": 1.7722627304302274e-05, "loss": 0.0225, "step": 9964 }, { "epoch": 0.5503092555776452, "grad_norm": 3.7306628227233887, "learning_rate": 1.7719073299356e-05, "loss": 0.622, "step": 9965 }, { "epoch": 0.550364479787939, "grad_norm": 2.19708251953125, "learning_rate": 1.771551936738306e-05, "loss": 0.2705, "step": 9966 }, { "epoch": 0.5504197039982328, "grad_norm": 1.5921289920806885, "learning_rate": 1.7711965508497165e-05, "loss": 0.1042, "step": 9967 }, { "epoch": 0.5504749282085266, "grad_norm": 0.07516694068908691, "learning_rate": 1.7708411722812003e-05, "loss": 0.0026, "step": 9968 }, { "epoch": 0.5505301524188204, "grad_norm": 4.540255069732666, "learning_rate": 1.7704858010441276e-05, "loss": 1.3128, "step": 9969 }, { "epoch": 0.5505853766291142, "grad_norm": 0.24057817459106445, "learning_rate": 1.770130437149867e-05, "loss": 0.0066, "step": 9970 }, { "epoch": 0.550640600839408, "grad_norm": 0.6388888955116272, "learning_rate": 1.7697750806097893e-05, "loss": 0.019, "step": 9971 }, { "epoch": 0.5506958250497018, "grad_norm": 3.2181334495544434, "learning_rate": 1.769419731435261e-05, "loss": 0.3882, "step": 9972 }, { "epoch": 0.5507510492599956, "grad_norm": 3.8366377353668213, "learning_rate": 1.769064389637653e-05, "loss": 0.3658, "step": 9973 }, { "epoch": 0.5508062734702893, "grad_norm": 4.331545352935791, "learning_rate": 1.7687090552283318e-05, "loss": 0.4783, "step": 9974 }, { "epoch": 0.5508614976805831, "grad_norm": 1.1588830947875977, "learning_rate": 1.7683537282186664e-05, "loss": 0.0338, "step": 9975 }, { "epoch": 0.5509167218908769, "grad_norm": 0.5736005306243896, "learning_rate": 1.767998408620025e-05, "loss": 0.0164, "step": 9976 }, { "epoch": 0.5509719461011707, "grad_norm": 4.248070240020752, "learning_rate": 1.767643096443775e-05, "loss": 0.8697, "step": 9977 }, { "epoch": 0.5510271703114645, "grad_norm": 0.32375189661979675, "learning_rate": 1.7672877917012833e-05, "loss": 0.0136, "step": 9978 }, { "epoch": 0.5510823945217583, "grad_norm": 0.20249180495738983, "learning_rate": 1.7669324944039188e-05, "loss": 0.0049, "step": 9979 }, { "epoch": 0.5511376187320521, "grad_norm": 0.05206309258937836, "learning_rate": 1.7665772045630464e-05, "loss": 0.0013, "step": 9980 }, { "epoch": 0.5511928429423459, "grad_norm": 3.8615167140960693, "learning_rate": 1.766221922190034e-05, "loss": 0.0579, "step": 9981 }, { "epoch": 0.5512480671526397, "grad_norm": 0.3737964928150177, "learning_rate": 1.7658666472962474e-05, "loss": 0.0096, "step": 9982 }, { "epoch": 0.5513032913629335, "grad_norm": 0.17804640531539917, "learning_rate": 1.7655113798930538e-05, "loss": 0.0038, "step": 9983 }, { "epoch": 0.5513585155732273, "grad_norm": 0.30662447214126587, "learning_rate": 1.7651561199918182e-05, "loss": 0.0082, "step": 9984 }, { "epoch": 0.5514137397835212, "grad_norm": 0.024047985672950745, "learning_rate": 1.7648008676039075e-05, "loss": 0.0008, "step": 9985 }, { "epoch": 0.5514689639938148, "grad_norm": 5.6971635818481445, "learning_rate": 1.7644456227406862e-05, "loss": 0.6247, "step": 9986 }, { "epoch": 0.5515241882041086, "grad_norm": 0.05766918882727623, "learning_rate": 1.764090385413521e-05, "loss": 0.0018, "step": 9987 }, { "epoch": 0.5515794124144024, "grad_norm": 0.6364727020263672, "learning_rate": 1.7637351556337753e-05, "loss": 0.014, "step": 9988 }, { "epoch": 0.5516346366246963, "grad_norm": 1.9293442964553833, "learning_rate": 1.7633799334128142e-05, "loss": 0.0821, "step": 9989 }, { "epoch": 0.55168986083499, "grad_norm": 2.6654703617095947, "learning_rate": 1.7630247187620032e-05, "loss": 0.1373, "step": 9990 }, { "epoch": 0.5517450850452839, "grad_norm": 6.204476833343506, "learning_rate": 1.762669511692706e-05, "loss": 0.984, "step": 9991 }, { "epoch": 0.5518003092555777, "grad_norm": 4.577073574066162, "learning_rate": 1.7623143122162868e-05, "loss": 0.7884, "step": 9992 }, { "epoch": 0.5518555334658715, "grad_norm": 1.8401100635528564, "learning_rate": 1.7619591203441087e-05, "loss": 0.282, "step": 9993 }, { "epoch": 0.5519107576761653, "grad_norm": 3.698300361633301, "learning_rate": 1.761603936087537e-05, "loss": 0.4835, "step": 9994 }, { "epoch": 0.5519659818864591, "grad_norm": 0.43205440044403076, "learning_rate": 1.7612487594579333e-05, "loss": 0.0103, "step": 9995 }, { "epoch": 0.5520212060967529, "grad_norm": 0.3513486683368683, "learning_rate": 1.7608935904666623e-05, "loss": 0.0109, "step": 9996 }, { "epoch": 0.5520764303070466, "grad_norm": 1.3643566370010376, "learning_rate": 1.760538429125085e-05, "loss": 0.0279, "step": 9997 }, { "epoch": 0.5521316545173404, "grad_norm": 5.384316444396973, "learning_rate": 1.760183275444566e-05, "loss": 1.112, "step": 9998 }, { "epoch": 0.5521868787276342, "grad_norm": 2.8704679012298584, "learning_rate": 1.759828129436466e-05, "loss": 0.6396, "step": 9999 }, { "epoch": 0.552242102937928, "grad_norm": 3.533186674118042, "learning_rate": 1.7594729911121485e-05, "loss": 0.0374, "step": 10000 }, { "epoch": 0.5522973271482218, "grad_norm": 2.199254274368286, "learning_rate": 1.7591178604829743e-05, "loss": 0.1955, "step": 10001 }, { "epoch": 0.5523525513585156, "grad_norm": 2.1939969062805176, "learning_rate": 1.7587627375603064e-05, "loss": 0.2651, "step": 10002 }, { "epoch": 0.5524077755688094, "grad_norm": 3.846461772918701, "learning_rate": 1.758407622355504e-05, "loss": 0.4455, "step": 10003 }, { "epoch": 0.5524629997791032, "grad_norm": 2.816159725189209, "learning_rate": 1.7580525148799305e-05, "loss": 0.409, "step": 10004 }, { "epoch": 0.552518223989397, "grad_norm": 0.010318320244550705, "learning_rate": 1.757697415144945e-05, "loss": 0.0004, "step": 10005 }, { "epoch": 0.5525734481996908, "grad_norm": 2.8370368480682373, "learning_rate": 1.75734232316191e-05, "loss": 0.484, "step": 10006 }, { "epoch": 0.5526286724099846, "grad_norm": 0.028355641290545464, "learning_rate": 1.7569872389421838e-05, "loss": 0.0008, "step": 10007 }, { "epoch": 0.5526838966202783, "grad_norm": 0.028510015457868576, "learning_rate": 1.7566321624971285e-05, "loss": 0.0008, "step": 10008 }, { "epoch": 0.5527391208305721, "grad_norm": 0.04613500088453293, "learning_rate": 1.7562770938381028e-05, "loss": 0.002, "step": 10009 }, { "epoch": 0.5527943450408659, "grad_norm": 0.3293452262878418, "learning_rate": 1.7559220329764672e-05, "loss": 0.0123, "step": 10010 }, { "epoch": 0.5528495692511597, "grad_norm": 0.06804081797599792, "learning_rate": 1.75556697992358e-05, "loss": 0.0015, "step": 10011 }, { "epoch": 0.5529047934614535, "grad_norm": 0.012977725826203823, "learning_rate": 1.7552119346908015e-05, "loss": 0.0004, "step": 10012 }, { "epoch": 0.5529600176717473, "grad_norm": 0.4263617992401123, "learning_rate": 1.7548568972894893e-05, "loss": 0.0153, "step": 10013 }, { "epoch": 0.5530152418820411, "grad_norm": 0.031183913350105286, "learning_rate": 1.7545018677310037e-05, "loss": 0.0008, "step": 10014 }, { "epoch": 0.5530704660923349, "grad_norm": 1.8098912239074707, "learning_rate": 1.7541468460267018e-05, "loss": 0.2774, "step": 10015 }, { "epoch": 0.5531256903026287, "grad_norm": 1.0664533376693726, "learning_rate": 1.7537918321879424e-05, "loss": 0.1637, "step": 10016 }, { "epoch": 0.5531809145129225, "grad_norm": 0.2059767097234726, "learning_rate": 1.7534368262260826e-05, "loss": 0.0043, "step": 10017 }, { "epoch": 0.5532361387232163, "grad_norm": 0.8903157711029053, "learning_rate": 1.753081828152482e-05, "loss": 0.0217, "step": 10018 }, { "epoch": 0.55329136293351, "grad_norm": 3.582918882369995, "learning_rate": 1.7527268379784952e-05, "loss": 0.445, "step": 10019 }, { "epoch": 0.5533465871438038, "grad_norm": 0.03443192318081856, "learning_rate": 1.752371855715482e-05, "loss": 0.0009, "step": 10020 }, { "epoch": 0.5534018113540976, "grad_norm": 0.07986769825220108, "learning_rate": 1.7520168813747972e-05, "loss": 0.0025, "step": 10021 }, { "epoch": 0.5534570355643914, "grad_norm": 0.2425786405801773, "learning_rate": 1.751661914967799e-05, "loss": 0.0083, "step": 10022 }, { "epoch": 0.5535122597746852, "grad_norm": 5.203094959259033, "learning_rate": 1.7513069565058425e-05, "loss": 0.168, "step": 10023 }, { "epoch": 0.553567483984979, "grad_norm": 0.07003367692232132, "learning_rate": 1.750952006000285e-05, "loss": 0.0011, "step": 10024 }, { "epoch": 0.5536227081952728, "grad_norm": 0.8378488421440125, "learning_rate": 1.7505970634624815e-05, "loss": 0.0162, "step": 10025 }, { "epoch": 0.5536779324055666, "grad_norm": 0.08037514984607697, "learning_rate": 1.7502421289037885e-05, "loss": 0.0018, "step": 10026 }, { "epoch": 0.5537331566158604, "grad_norm": 0.017135731875896454, "learning_rate": 1.7498872023355598e-05, "loss": 0.0005, "step": 10027 }, { "epoch": 0.5537883808261542, "grad_norm": 2.542847156524658, "learning_rate": 1.7495322837691528e-05, "loss": 0.311, "step": 10028 }, { "epoch": 0.553843605036448, "grad_norm": 1.4033262729644775, "learning_rate": 1.74917737321592e-05, "loss": 0.0536, "step": 10029 }, { "epoch": 0.5538988292467417, "grad_norm": 2.527967691421509, "learning_rate": 1.7488224706872178e-05, "loss": 0.3368, "step": 10030 }, { "epoch": 0.5539540534570355, "grad_norm": 0.034343793988227844, "learning_rate": 1.7484675761943992e-05, "loss": 0.001, "step": 10031 }, { "epoch": 0.5540092776673293, "grad_norm": 2.5935521125793457, "learning_rate": 1.7481126897488195e-05, "loss": 0.4518, "step": 10032 }, { "epoch": 0.5540645018776231, "grad_norm": 0.06847450137138367, "learning_rate": 1.7477578113618313e-05, "loss": 0.0025, "step": 10033 }, { "epoch": 0.5541197260879169, "grad_norm": 3.5180957317352295, "learning_rate": 1.74740294104479e-05, "loss": 0.3703, "step": 10034 }, { "epoch": 0.5541749502982107, "grad_norm": 2.0989391803741455, "learning_rate": 1.7470480788090462e-05, "loss": 0.0717, "step": 10035 }, { "epoch": 0.5542301745085045, "grad_norm": 1.4583901166915894, "learning_rate": 1.746693224665956e-05, "loss": 0.064, "step": 10036 }, { "epoch": 0.5542853987187983, "grad_norm": 1.3843199014663696, "learning_rate": 1.7463383786268697e-05, "loss": 0.1787, "step": 10037 }, { "epoch": 0.5543406229290921, "grad_norm": 1.5115052461624146, "learning_rate": 1.745983540703141e-05, "loss": 0.093, "step": 10038 }, { "epoch": 0.5543958471393859, "grad_norm": 3.8708479404449463, "learning_rate": 1.745628710906122e-05, "loss": 1.2796, "step": 10039 }, { "epoch": 0.5544510713496797, "grad_norm": 0.04530120640993118, "learning_rate": 1.7452738892471647e-05, "loss": 0.0014, "step": 10040 }, { "epoch": 0.5545062955599734, "grad_norm": 2.898000478744507, "learning_rate": 1.7449190757376205e-05, "loss": 0.1514, "step": 10041 }, { "epoch": 0.5545615197702672, "grad_norm": 6.562012195587158, "learning_rate": 1.7445642703888427e-05, "loss": 1.3245, "step": 10042 }, { "epoch": 0.554616743980561, "grad_norm": 1.58723783493042, "learning_rate": 1.744209473212179e-05, "loss": 0.0777, "step": 10043 }, { "epoch": 0.5546719681908548, "grad_norm": 3.2377147674560547, "learning_rate": 1.743854684218984e-05, "loss": 0.4503, "step": 10044 }, { "epoch": 0.5547271924011486, "grad_norm": 2.951582908630371, "learning_rate": 1.7434999034206062e-05, "loss": 0.6319, "step": 10045 }, { "epoch": 0.5547824166114425, "grad_norm": 4.519124507904053, "learning_rate": 1.743145130828397e-05, "loss": 0.3477, "step": 10046 }, { "epoch": 0.5548376408217363, "grad_norm": 0.14702528715133667, "learning_rate": 1.742790366453706e-05, "loss": 0.0068, "step": 10047 }, { "epoch": 0.5548928650320301, "grad_norm": 0.6450609564781189, "learning_rate": 1.7424356103078836e-05, "loss": 0.0202, "step": 10048 }, { "epoch": 0.5549480892423239, "grad_norm": 0.2897460460662842, "learning_rate": 1.74208086240228e-05, "loss": 0.009, "step": 10049 }, { "epoch": 0.5550033134526177, "grad_norm": 0.45335254073143005, "learning_rate": 1.7417261227482428e-05, "loss": 0.0162, "step": 10050 }, { "epoch": 0.5550585376629115, "grad_norm": 0.18184992671012878, "learning_rate": 1.7413713913571225e-05, "loss": 0.0049, "step": 10051 }, { "epoch": 0.5551137618732052, "grad_norm": 3.4751336574554443, "learning_rate": 1.7410166682402677e-05, "loss": 0.995, "step": 10052 }, { "epoch": 0.555168986083499, "grad_norm": 1.8121732473373413, "learning_rate": 1.740661953409027e-05, "loss": 0.281, "step": 10053 }, { "epoch": 0.5552242102937928, "grad_norm": 0.16151782870292664, "learning_rate": 1.7403072468747484e-05, "loss": 0.0054, "step": 10054 }, { "epoch": 0.5552794345040866, "grad_norm": 0.1643560379743576, "learning_rate": 1.739952548648781e-05, "loss": 0.0051, "step": 10055 }, { "epoch": 0.5553346587143804, "grad_norm": 0.05613965913653374, "learning_rate": 1.7395978587424712e-05, "loss": 0.002, "step": 10056 }, { "epoch": 0.5553898829246742, "grad_norm": 1.0211844444274902, "learning_rate": 1.7392431771671682e-05, "loss": 0.1332, "step": 10057 }, { "epoch": 0.555445107134968, "grad_norm": 0.06548875570297241, "learning_rate": 1.7388885039342168e-05, "loss": 0.0026, "step": 10058 }, { "epoch": 0.5555003313452618, "grad_norm": 0.171592578291893, "learning_rate": 1.738533839054967e-05, "loss": 0.0051, "step": 10059 }, { "epoch": 0.5555555555555556, "grad_norm": 1.7087070941925049, "learning_rate": 1.738179182540763e-05, "loss": 0.0394, "step": 10060 }, { "epoch": 0.5556107797658494, "grad_norm": 0.24546539783477783, "learning_rate": 1.737824534402953e-05, "loss": 0.0079, "step": 10061 }, { "epoch": 0.5556660039761432, "grad_norm": 0.05697838217020035, "learning_rate": 1.7374698946528818e-05, "loss": 0.0024, "step": 10062 }, { "epoch": 0.555721228186437, "grad_norm": 0.2675473690032959, "learning_rate": 1.7371152633018966e-05, "loss": 0.0108, "step": 10063 }, { "epoch": 0.5557764523967307, "grad_norm": 8.078240394592285, "learning_rate": 1.736760640361342e-05, "loss": 0.6947, "step": 10064 }, { "epoch": 0.5558316766070245, "grad_norm": 0.5929592251777649, "learning_rate": 1.7364060258425652e-05, "loss": 0.0196, "step": 10065 }, { "epoch": 0.5558869008173183, "grad_norm": 0.03289414569735527, "learning_rate": 1.7360514197569082e-05, "loss": 0.0011, "step": 10066 }, { "epoch": 0.5559421250276121, "grad_norm": 2.71266508102417, "learning_rate": 1.7356968221157195e-05, "loss": 0.7335, "step": 10067 }, { "epoch": 0.5559973492379059, "grad_norm": 0.022553909569978714, "learning_rate": 1.7353422329303407e-05, "loss": 0.0008, "step": 10068 }, { "epoch": 0.5560525734481997, "grad_norm": 0.03891611844301224, "learning_rate": 1.7349876522121177e-05, "loss": 0.0011, "step": 10069 }, { "epoch": 0.5561077976584935, "grad_norm": 2.311063766479492, "learning_rate": 1.734633079972394e-05, "loss": 0.2026, "step": 10070 }, { "epoch": 0.5561630218687873, "grad_norm": 4.021125793457031, "learning_rate": 1.734278516222514e-05, "loss": 0.5957, "step": 10071 }, { "epoch": 0.5562182460790811, "grad_norm": 3.185973644256592, "learning_rate": 1.73392396097382e-05, "loss": 0.212, "step": 10072 }, { "epoch": 0.5562734702893749, "grad_norm": 2.936204671859741, "learning_rate": 1.733569414237657e-05, "loss": 0.5687, "step": 10073 }, { "epoch": 0.5563286944996687, "grad_norm": 3.2472259998321533, "learning_rate": 1.7332148760253657e-05, "loss": 0.2339, "step": 10074 }, { "epoch": 0.5563839187099624, "grad_norm": 0.08205370604991913, "learning_rate": 1.7328603463482914e-05, "loss": 0.0025, "step": 10075 }, { "epoch": 0.5564391429202562, "grad_norm": 3.261868715286255, "learning_rate": 1.732505825217774e-05, "loss": 0.2294, "step": 10076 }, { "epoch": 0.55649436713055, "grad_norm": 0.021348485723137856, "learning_rate": 1.7321513126451576e-05, "loss": 0.0007, "step": 10077 }, { "epoch": 0.5565495913408438, "grad_norm": 0.02579265460371971, "learning_rate": 1.7317968086417823e-05, "loss": 0.0009, "step": 10078 }, { "epoch": 0.5566048155511376, "grad_norm": 0.39974483847618103, "learning_rate": 1.731442313218991e-05, "loss": 0.0194, "step": 10079 }, { "epoch": 0.5566600397614314, "grad_norm": 3.354294538497925, "learning_rate": 1.7310878263881246e-05, "loss": 0.8139, "step": 10080 }, { "epoch": 0.5567152639717252, "grad_norm": 2.2988510131835938, "learning_rate": 1.7307333481605254e-05, "loss": 0.3674, "step": 10081 }, { "epoch": 0.556770488182019, "grad_norm": 0.4081294536590576, "learning_rate": 1.730378878547531e-05, "loss": 0.0138, "step": 10082 }, { "epoch": 0.5568257123923128, "grad_norm": 3.6759755611419678, "learning_rate": 1.7300244175604856e-05, "loss": 0.5275, "step": 10083 }, { "epoch": 0.5568809366026066, "grad_norm": 1.6321734189987183, "learning_rate": 1.7296699652107265e-05, "loss": 0.0673, "step": 10084 }, { "epoch": 0.5569361608129004, "grad_norm": 4.146628379821777, "learning_rate": 1.7293155215095952e-05, "loss": 0.6691, "step": 10085 }, { "epoch": 0.5569913850231941, "grad_norm": 0.0755852535367012, "learning_rate": 1.7289610864684306e-05, "loss": 0.0028, "step": 10086 }, { "epoch": 0.5570466092334879, "grad_norm": 0.5915536284446716, "learning_rate": 1.7286066600985733e-05, "loss": 0.0176, "step": 10087 }, { "epoch": 0.5571018334437817, "grad_norm": 2.398719072341919, "learning_rate": 1.7282522424113608e-05, "loss": 0.2431, "step": 10088 }, { "epoch": 0.5571570576540755, "grad_norm": 2.406334161758423, "learning_rate": 1.727897833418133e-05, "loss": 0.6024, "step": 10089 }, { "epoch": 0.5572122818643693, "grad_norm": 0.09452148526906967, "learning_rate": 1.7275434331302277e-05, "loss": 0.0026, "step": 10090 }, { "epoch": 0.5572675060746631, "grad_norm": 3.5970191955566406, "learning_rate": 1.727189041558985e-05, "loss": 0.5651, "step": 10091 }, { "epoch": 0.5573227302849569, "grad_norm": 2.221959352493286, "learning_rate": 1.72683465871574e-05, "loss": 0.3106, "step": 10092 }, { "epoch": 0.5573779544952507, "grad_norm": 0.09676234424114227, "learning_rate": 1.7264802846118328e-05, "loss": 0.0035, "step": 10093 }, { "epoch": 0.5574331787055445, "grad_norm": 3.820430040359497, "learning_rate": 1.7261259192585996e-05, "loss": 0.2844, "step": 10094 }, { "epoch": 0.5574884029158383, "grad_norm": 0.3747858703136444, "learning_rate": 1.7257715626673782e-05, "loss": 0.0122, "step": 10095 }, { "epoch": 0.5575436271261321, "grad_norm": 3.106440782546997, "learning_rate": 1.7254172148495045e-05, "loss": 0.5959, "step": 10096 }, { "epoch": 0.5575988513364258, "grad_norm": 1.0365188121795654, "learning_rate": 1.7250628758163166e-05, "loss": 0.026, "step": 10097 }, { "epoch": 0.5576540755467196, "grad_norm": 0.2072252631187439, "learning_rate": 1.7247085455791494e-05, "loss": 0.0086, "step": 10098 }, { "epoch": 0.5577092997570134, "grad_norm": 4.8892059326171875, "learning_rate": 1.7243542241493406e-05, "loss": 0.5884, "step": 10099 }, { "epoch": 0.5577645239673072, "grad_norm": 3.149210214614868, "learning_rate": 1.7239999115382237e-05, "loss": 0.7651, "step": 10100 }, { "epoch": 0.557819748177601, "grad_norm": 5.940989971160889, "learning_rate": 1.723645607757136e-05, "loss": 1.6872, "step": 10101 }, { "epoch": 0.5578749723878949, "grad_norm": 5.677232265472412, "learning_rate": 1.7232913128174114e-05, "loss": 1.5996, "step": 10102 }, { "epoch": 0.5579301965981887, "grad_norm": 0.02743007242679596, "learning_rate": 1.7229370267303865e-05, "loss": 0.001, "step": 10103 }, { "epoch": 0.5579854208084825, "grad_norm": 3.27669095993042, "learning_rate": 1.722582749507394e-05, "loss": 0.2524, "step": 10104 }, { "epoch": 0.5580406450187763, "grad_norm": 4.420713424682617, "learning_rate": 1.7222284811597692e-05, "loss": 0.7653, "step": 10105 }, { "epoch": 0.5580958692290701, "grad_norm": 0.3625088036060333, "learning_rate": 1.7218742216988462e-05, "loss": 0.0097, "step": 10106 }, { "epoch": 0.5581510934393639, "grad_norm": 0.03342995420098305, "learning_rate": 1.7215199711359595e-05, "loss": 0.0014, "step": 10107 }, { "epoch": 0.5582063176496576, "grad_norm": 0.5342500805854797, "learning_rate": 1.7211657294824412e-05, "loss": 0.0125, "step": 10108 }, { "epoch": 0.5582615418599514, "grad_norm": 1.1247291564941406, "learning_rate": 1.7208114967496242e-05, "loss": 0.041, "step": 10109 }, { "epoch": 0.5583167660702452, "grad_norm": 2.783381700515747, "learning_rate": 1.720457272948843e-05, "loss": 0.6129, "step": 10110 }, { "epoch": 0.558371990280539, "grad_norm": 3.3337457180023193, "learning_rate": 1.720103058091429e-05, "loss": 0.0803, "step": 10111 }, { "epoch": 0.5584272144908328, "grad_norm": 1.427092432975769, "learning_rate": 1.719748852188716e-05, "loss": 0.0608, "step": 10112 }, { "epoch": 0.5584824387011266, "grad_norm": 0.12539063394069672, "learning_rate": 1.7193946552520338e-05, "loss": 0.0029, "step": 10113 }, { "epoch": 0.5585376629114204, "grad_norm": 3.529123306274414, "learning_rate": 1.7190404672927163e-05, "loss": 0.4672, "step": 10114 }, { "epoch": 0.5585928871217142, "grad_norm": 0.08541102707386017, "learning_rate": 1.7186862883220935e-05, "loss": 0.0028, "step": 10115 }, { "epoch": 0.558648111332008, "grad_norm": 2.3643441200256348, "learning_rate": 1.718332118351498e-05, "loss": 0.0843, "step": 10116 }, { "epoch": 0.5587033355423018, "grad_norm": 3.4909846782684326, "learning_rate": 1.717977957392259e-05, "loss": 0.2472, "step": 10117 }, { "epoch": 0.5587585597525956, "grad_norm": 0.02642105706036091, "learning_rate": 1.7176238054557088e-05, "loss": 0.0009, "step": 10118 }, { "epoch": 0.5588137839628893, "grad_norm": 0.030162561684846878, "learning_rate": 1.717269662553176e-05, "loss": 0.0011, "step": 10119 }, { "epoch": 0.5588690081731831, "grad_norm": 6.287935256958008, "learning_rate": 1.7169155286959928e-05, "loss": 0.9712, "step": 10120 }, { "epoch": 0.5589242323834769, "grad_norm": 3.1628904342651367, "learning_rate": 1.7165614038954864e-05, "loss": 0.812, "step": 10121 }, { "epoch": 0.5589794565937707, "grad_norm": 1.8479002714157104, "learning_rate": 1.716207288162989e-05, "loss": 0.1327, "step": 10122 }, { "epoch": 0.5590346808040645, "grad_norm": 0.06512749940156937, "learning_rate": 1.715853181509827e-05, "loss": 0.0022, "step": 10123 }, { "epoch": 0.5590899050143583, "grad_norm": 1.4635978937149048, "learning_rate": 1.7154990839473317e-05, "loss": 0.1717, "step": 10124 }, { "epoch": 0.5591451292246521, "grad_norm": 1.3741252422332764, "learning_rate": 1.71514499548683e-05, "loss": 0.0602, "step": 10125 }, { "epoch": 0.5592003534349459, "grad_norm": 0.8197019696235657, "learning_rate": 1.714790916139651e-05, "loss": 0.0257, "step": 10126 }, { "epoch": 0.5592555776452397, "grad_norm": 1.5210670232772827, "learning_rate": 1.7144368459171225e-05, "loss": 0.0814, "step": 10127 }, { "epoch": 0.5593108018555335, "grad_norm": 2.351921558380127, "learning_rate": 1.7140827848305727e-05, "loss": 0.204, "step": 10128 }, { "epoch": 0.5593660260658273, "grad_norm": 0.16035228967666626, "learning_rate": 1.713728732891328e-05, "loss": 0.0064, "step": 10129 }, { "epoch": 0.559421250276121, "grad_norm": 4.373507976531982, "learning_rate": 1.7133746901107172e-05, "loss": 1.2689, "step": 10130 }, { "epoch": 0.5594764744864148, "grad_norm": 3.5500752925872803, "learning_rate": 1.713020656500065e-05, "loss": 0.5467, "step": 10131 }, { "epoch": 0.5595316986967086, "grad_norm": 1.831571102142334, "learning_rate": 1.7126666320706993e-05, "loss": 0.103, "step": 10132 }, { "epoch": 0.5595869229070024, "grad_norm": 0.13537681102752686, "learning_rate": 1.7123126168339457e-05, "loss": 0.0042, "step": 10133 }, { "epoch": 0.5596421471172962, "grad_norm": 0.16146233677864075, "learning_rate": 1.7119586108011307e-05, "loss": 0.0044, "step": 10134 }, { "epoch": 0.55969737132759, "grad_norm": 3.8614349365234375, "learning_rate": 1.7116046139835798e-05, "loss": 0.3, "step": 10135 }, { "epoch": 0.5597525955378838, "grad_norm": 0.04671107232570648, "learning_rate": 1.7112506263926185e-05, "loss": 0.0021, "step": 10136 }, { "epoch": 0.5598078197481776, "grad_norm": 1.9868284463882446, "learning_rate": 1.7108966480395714e-05, "loss": 0.2121, "step": 10137 }, { "epoch": 0.5598630439584714, "grad_norm": 0.0986487865447998, "learning_rate": 1.7105426789357642e-05, "loss": 0.0034, "step": 10138 }, { "epoch": 0.5599182681687652, "grad_norm": 3.4883949756622314, "learning_rate": 1.71018871909252e-05, "loss": 0.9661, "step": 10139 }, { "epoch": 0.559973492379059, "grad_norm": 0.09622526913881302, "learning_rate": 1.7098347685211643e-05, "loss": 0.0031, "step": 10140 }, { "epoch": 0.5600287165893528, "grad_norm": 2.5821585655212402, "learning_rate": 1.70948082723302e-05, "loss": 0.3486, "step": 10141 }, { "epoch": 0.5600839407996465, "grad_norm": 4.9788408279418945, "learning_rate": 1.709126895239411e-05, "loss": 0.5528, "step": 10142 }, { "epoch": 0.5601391650099403, "grad_norm": 2.6805572509765625, "learning_rate": 1.708772972551661e-05, "loss": 0.0783, "step": 10143 }, { "epoch": 0.5601943892202341, "grad_norm": 0.089103102684021, "learning_rate": 1.7084190591810927e-05, "loss": 0.0031, "step": 10144 }, { "epoch": 0.5602496134305279, "grad_norm": 0.038763366639614105, "learning_rate": 1.7080651551390283e-05, "loss": 0.0014, "step": 10145 }, { "epoch": 0.5603048376408217, "grad_norm": 1.252328872680664, "learning_rate": 1.707711260436792e-05, "loss": 0.0257, "step": 10146 }, { "epoch": 0.5603600618511155, "grad_norm": 0.41017600893974304, "learning_rate": 1.707357375085703e-05, "loss": 0.0051, "step": 10147 }, { "epoch": 0.5604152860614093, "grad_norm": 1.7320916652679443, "learning_rate": 1.707003499097086e-05, "loss": 0.4012, "step": 10148 }, { "epoch": 0.5604705102717031, "grad_norm": 3.7801668643951416, "learning_rate": 1.7066496324822603e-05, "loss": 0.3024, "step": 10149 }, { "epoch": 0.5605257344819969, "grad_norm": 0.2399684637784958, "learning_rate": 1.7062957752525485e-05, "loss": 0.0072, "step": 10150 }, { "epoch": 0.5605809586922907, "grad_norm": 1.421226978302002, "learning_rate": 1.7059419274192703e-05, "loss": 0.0549, "step": 10151 }, { "epoch": 0.5606361829025845, "grad_norm": 0.07308153063058853, "learning_rate": 1.7055880889937476e-05, "loss": 0.0025, "step": 10152 }, { "epoch": 0.5606914071128782, "grad_norm": 2.407832145690918, "learning_rate": 1.7052342599872996e-05, "loss": 0.1411, "step": 10153 }, { "epoch": 0.560746631323172, "grad_norm": 1.7700647115707397, "learning_rate": 1.7048804404112476e-05, "loss": 0.0372, "step": 10154 }, { "epoch": 0.5608018555334658, "grad_norm": 1.077250361442566, "learning_rate": 1.7045266302769096e-05, "loss": 0.0958, "step": 10155 }, { "epoch": 0.5608570797437596, "grad_norm": 0.4046502411365509, "learning_rate": 1.704172829595607e-05, "loss": 0.0092, "step": 10156 }, { "epoch": 0.5609123039540534, "grad_norm": 1.0772740840911865, "learning_rate": 1.7038190383786564e-05, "loss": 0.0474, "step": 10157 }, { "epoch": 0.5609675281643473, "grad_norm": 0.047144778072834015, "learning_rate": 1.7034652566373788e-05, "loss": 0.0014, "step": 10158 }, { "epoch": 0.561022752374641, "grad_norm": 0.02358110249042511, "learning_rate": 1.7031114843830914e-05, "loss": 0.0006, "step": 10159 }, { "epoch": 0.5610779765849349, "grad_norm": 3.099165916442871, "learning_rate": 1.7027577216271133e-05, "loss": 0.5833, "step": 10160 }, { "epoch": 0.5611332007952287, "grad_norm": 0.05794905871152878, "learning_rate": 1.7024039683807613e-05, "loss": 0.0024, "step": 10161 }, { "epoch": 0.5611884250055225, "grad_norm": 0.06451694667339325, "learning_rate": 1.7020502246553547e-05, "loss": 0.0022, "step": 10162 }, { "epoch": 0.5612436492158163, "grad_norm": 2.873748779296875, "learning_rate": 1.701696490462208e-05, "loss": 0.4282, "step": 10163 }, { "epoch": 0.56129887342611, "grad_norm": 0.4077037572860718, "learning_rate": 1.7013427658126412e-05, "loss": 0.0125, "step": 10164 }, { "epoch": 0.5613540976364038, "grad_norm": 0.1935032457113266, "learning_rate": 1.7009890507179687e-05, "loss": 0.0053, "step": 10165 }, { "epoch": 0.5614093218466976, "grad_norm": 2.2204079627990723, "learning_rate": 1.7006353451895084e-05, "loss": 0.1233, "step": 10166 }, { "epoch": 0.5614645460569914, "grad_norm": 0.7581601738929749, "learning_rate": 1.700281649238575e-05, "loss": 0.1351, "step": 10167 }, { "epoch": 0.5615197702672852, "grad_norm": 0.8537783622741699, "learning_rate": 1.699927962876485e-05, "loss": 0.0275, "step": 10168 }, { "epoch": 0.561574994477579, "grad_norm": 1.3682129383087158, "learning_rate": 1.699574286114555e-05, "loss": 0.185, "step": 10169 }, { "epoch": 0.5616302186878728, "grad_norm": 0.06400945782661438, "learning_rate": 1.6992206189640973e-05, "loss": 0.0022, "step": 10170 }, { "epoch": 0.5616854428981666, "grad_norm": 0.05999613553285599, "learning_rate": 1.6988669614364287e-05, "loss": 0.0029, "step": 10171 }, { "epoch": 0.5617406671084604, "grad_norm": 2.531364917755127, "learning_rate": 1.6985133135428633e-05, "loss": 0.1618, "step": 10172 }, { "epoch": 0.5617958913187542, "grad_norm": 0.01325349509716034, "learning_rate": 1.6981596752947152e-05, "loss": 0.0004, "step": 10173 }, { "epoch": 0.561851115529048, "grad_norm": 0.00777107197791338, "learning_rate": 1.6978060467032988e-05, "loss": 0.0002, "step": 10174 }, { "epoch": 0.5619063397393417, "grad_norm": 1.4218980073928833, "learning_rate": 1.697452427779927e-05, "loss": 0.0997, "step": 10175 }, { "epoch": 0.5619615639496355, "grad_norm": 0.018930627033114433, "learning_rate": 1.6970988185359128e-05, "loss": 0.0005, "step": 10176 }, { "epoch": 0.5620167881599293, "grad_norm": 4.7467942237854, "learning_rate": 1.696745218982571e-05, "loss": 0.5715, "step": 10177 }, { "epoch": 0.5620720123702231, "grad_norm": 0.13961546123027802, "learning_rate": 1.6963916291312116e-05, "loss": 0.0043, "step": 10178 }, { "epoch": 0.5621272365805169, "grad_norm": 3.6471314430236816, "learning_rate": 1.6960380489931497e-05, "loss": 0.3304, "step": 10179 }, { "epoch": 0.5621824607908107, "grad_norm": 0.034539684653282166, "learning_rate": 1.6956844785796948e-05, "loss": 0.0011, "step": 10180 }, { "epoch": 0.5622376850011045, "grad_norm": 0.0389210544526577, "learning_rate": 1.6953309179021603e-05, "loss": 0.0016, "step": 10181 }, { "epoch": 0.5622929092113983, "grad_norm": 0.07435621321201324, "learning_rate": 1.6949773669718568e-05, "loss": 0.0019, "step": 10182 }, { "epoch": 0.5623481334216921, "grad_norm": 2.7184715270996094, "learning_rate": 1.694623825800096e-05, "loss": 0.284, "step": 10183 }, { "epoch": 0.5624033576319859, "grad_norm": 2.8823864459991455, "learning_rate": 1.694270294398188e-05, "loss": 0.5815, "step": 10184 }, { "epoch": 0.5624585818422797, "grad_norm": 0.5695838928222656, "learning_rate": 1.6939167727774447e-05, "loss": 0.0186, "step": 10185 }, { "epoch": 0.5625138060525734, "grad_norm": 0.035438183695077896, "learning_rate": 1.6935632609491737e-05, "loss": 0.0011, "step": 10186 }, { "epoch": 0.5625690302628672, "grad_norm": 1.9652289152145386, "learning_rate": 1.6932097589246878e-05, "loss": 0.5131, "step": 10187 }, { "epoch": 0.562624254473161, "grad_norm": 0.27291929721832275, "learning_rate": 1.692856266715294e-05, "loss": 0.0076, "step": 10188 }, { "epoch": 0.5626794786834548, "grad_norm": 1.9608392715454102, "learning_rate": 1.6925027843323033e-05, "loss": 0.1464, "step": 10189 }, { "epoch": 0.5627347028937486, "grad_norm": 4.679953575134277, "learning_rate": 1.6921493117870233e-05, "loss": 1.0884, "step": 10190 }, { "epoch": 0.5627899271040424, "grad_norm": 1.3567426204681396, "learning_rate": 1.6917958490907636e-05, "loss": 0.0665, "step": 10191 }, { "epoch": 0.5628451513143362, "grad_norm": 3.7985339164733887, "learning_rate": 1.691442396254832e-05, "loss": 0.54, "step": 10192 }, { "epoch": 0.56290037552463, "grad_norm": 0.06928804516792297, "learning_rate": 1.6910889532905372e-05, "loss": 0.0027, "step": 10193 }, { "epoch": 0.5629555997349238, "grad_norm": 0.0784977450966835, "learning_rate": 1.690735520209185e-05, "loss": 0.0019, "step": 10194 }, { "epoch": 0.5630108239452176, "grad_norm": 2.4284682273864746, "learning_rate": 1.6903820970220852e-05, "loss": 0.3172, "step": 10195 }, { "epoch": 0.5630660481555114, "grad_norm": 0.6802414655685425, "learning_rate": 1.6900286837405428e-05, "loss": 0.018, "step": 10196 }, { "epoch": 0.5631212723658051, "grad_norm": 0.773063600063324, "learning_rate": 1.6896752803758657e-05, "loss": 0.0421, "step": 10197 }, { "epoch": 0.5631764965760989, "grad_norm": 0.36800849437713623, "learning_rate": 1.6893218869393593e-05, "loss": 0.0116, "step": 10198 }, { "epoch": 0.5632317207863927, "grad_norm": 0.3751536011695862, "learning_rate": 1.6889685034423308e-05, "loss": 0.0083, "step": 10199 }, { "epoch": 0.5632869449966865, "grad_norm": 2.7419302463531494, "learning_rate": 1.6886151298960848e-05, "loss": 0.5038, "step": 10200 }, { "epoch": 0.5633421692069803, "grad_norm": 0.9309281706809998, "learning_rate": 1.688261766311928e-05, "loss": 0.019, "step": 10201 }, { "epoch": 0.5633973934172741, "grad_norm": 3.3881330490112305, "learning_rate": 1.6879084127011634e-05, "loss": 0.1024, "step": 10202 }, { "epoch": 0.5634526176275679, "grad_norm": 0.16834749281406403, "learning_rate": 1.687555069075099e-05, "loss": 0.0041, "step": 10203 }, { "epoch": 0.5635078418378617, "grad_norm": 0.023693716153502464, "learning_rate": 1.687201735445036e-05, "loss": 0.0006, "step": 10204 }, { "epoch": 0.5635630660481555, "grad_norm": 2.2082009315490723, "learning_rate": 1.6868484118222807e-05, "loss": 0.1911, "step": 10205 }, { "epoch": 0.5636182902584493, "grad_norm": 0.1537110060453415, "learning_rate": 1.6864950982181355e-05, "loss": 0.0059, "step": 10206 }, { "epoch": 0.5636735144687431, "grad_norm": 0.004412418697029352, "learning_rate": 1.686141794643905e-05, "loss": 0.0001, "step": 10207 }, { "epoch": 0.563728738679037, "grad_norm": 3.643601655960083, "learning_rate": 1.685788501110892e-05, "loss": 0.8126, "step": 10208 }, { "epoch": 0.5637839628893306, "grad_norm": 4.2823615074157715, "learning_rate": 1.6854352176303997e-05, "loss": 0.6233, "step": 10209 }, { "epoch": 0.5638391870996244, "grad_norm": 0.6387202143669128, "learning_rate": 1.6850819442137297e-05, "loss": 0.021, "step": 10210 }, { "epoch": 0.5638944113099182, "grad_norm": 0.12048549950122833, "learning_rate": 1.684728680872186e-05, "loss": 0.0036, "step": 10211 }, { "epoch": 0.563949635520212, "grad_norm": 0.1016584262251854, "learning_rate": 1.684375427617068e-05, "loss": 0.0038, "step": 10212 }, { "epoch": 0.5640048597305058, "grad_norm": 3.6322855949401855, "learning_rate": 1.6840221844596795e-05, "loss": 0.1976, "step": 10213 }, { "epoch": 0.5640600839407997, "grad_norm": 2.8058536052703857, "learning_rate": 1.68366895141132e-05, "loss": 0.6514, "step": 10214 }, { "epoch": 0.5641153081510935, "grad_norm": 0.03697742521762848, "learning_rate": 1.683315728483292e-05, "loss": 0.001, "step": 10215 }, { "epoch": 0.5641705323613873, "grad_norm": 0.039541203528642654, "learning_rate": 1.682962515686895e-05, "loss": 0.0013, "step": 10216 }, { "epoch": 0.5642257565716811, "grad_norm": 1.7249140739440918, "learning_rate": 1.6826093130334304e-05, "loss": 0.0844, "step": 10217 }, { "epoch": 0.5642809807819749, "grad_norm": 0.01452258974313736, "learning_rate": 1.6822561205341966e-05, "loss": 0.0005, "step": 10218 }, { "epoch": 0.5643362049922687, "grad_norm": 1.0254008769989014, "learning_rate": 1.6819029382004946e-05, "loss": 0.0241, "step": 10219 }, { "epoch": 0.5643914292025624, "grad_norm": 0.627726674079895, "learning_rate": 1.681549766043623e-05, "loss": 0.0249, "step": 10220 }, { "epoch": 0.5644466534128562, "grad_norm": 0.04597245901823044, "learning_rate": 1.681196604074881e-05, "loss": 0.0009, "step": 10221 }, { "epoch": 0.56450187762315, "grad_norm": 4.1004557609558105, "learning_rate": 1.6808434523055672e-05, "loss": 0.5527, "step": 10222 }, { "epoch": 0.5645571018334438, "grad_norm": 0.23626063764095306, "learning_rate": 1.68049031074698e-05, "loss": 0.0049, "step": 10223 }, { "epoch": 0.5646123260437376, "grad_norm": 2.7953784465789795, "learning_rate": 1.680137179410417e-05, "loss": 0.2146, "step": 10224 }, { "epoch": 0.5646675502540314, "grad_norm": 2.0827817916870117, "learning_rate": 1.6797840583071768e-05, "loss": 0.1458, "step": 10225 }, { "epoch": 0.5647227744643252, "grad_norm": 2.959210157394409, "learning_rate": 1.679430947448556e-05, "loss": 0.5802, "step": 10226 }, { "epoch": 0.564777998674619, "grad_norm": 0.6304976344108582, "learning_rate": 1.6790778468458522e-05, "loss": 0.0123, "step": 10227 }, { "epoch": 0.5648332228849128, "grad_norm": 0.3206407129764557, "learning_rate": 1.6787247565103607e-05, "loss": 0.0082, "step": 10228 }, { "epoch": 0.5648884470952066, "grad_norm": 2.220123291015625, "learning_rate": 1.67837167645338e-05, "loss": 0.2009, "step": 10229 }, { "epoch": 0.5649436713055004, "grad_norm": 0.06717511266469955, "learning_rate": 1.6780186066862047e-05, "loss": 0.0024, "step": 10230 }, { "epoch": 0.5649988955157941, "grad_norm": 3.205613136291504, "learning_rate": 1.6776655472201303e-05, "loss": 0.5527, "step": 10231 }, { "epoch": 0.5650541197260879, "grad_norm": 4.665905475616455, "learning_rate": 1.6773124980664534e-05, "loss": 0.1776, "step": 10232 }, { "epoch": 0.5651093439363817, "grad_norm": 0.7171289324760437, "learning_rate": 1.676959459236467e-05, "loss": 0.0131, "step": 10233 }, { "epoch": 0.5651645681466755, "grad_norm": 0.4991919994354248, "learning_rate": 1.6766064307414688e-05, "loss": 0.0161, "step": 10234 }, { "epoch": 0.5652197923569693, "grad_norm": 3.9984943866729736, "learning_rate": 1.6762534125927508e-05, "loss": 0.5772, "step": 10235 }, { "epoch": 0.5652750165672631, "grad_norm": 1.5600184202194214, "learning_rate": 1.675900404801608e-05, "loss": 0.0485, "step": 10236 }, { "epoch": 0.5653302407775569, "grad_norm": 1.5302536487579346, "learning_rate": 1.6755474073793336e-05, "loss": 0.0394, "step": 10237 }, { "epoch": 0.5653854649878507, "grad_norm": 0.1919224113225937, "learning_rate": 1.6751944203372216e-05, "loss": 0.0053, "step": 10238 }, { "epoch": 0.5654406891981445, "grad_norm": 2.2236483097076416, "learning_rate": 1.674841443686564e-05, "loss": 0.4499, "step": 10239 }, { "epoch": 0.5654959134084383, "grad_norm": 2.056809186935425, "learning_rate": 1.6744884774386556e-05, "loss": 0.1082, "step": 10240 }, { "epoch": 0.5655511376187321, "grad_norm": 4.532970905303955, "learning_rate": 1.674135521604786e-05, "loss": 0.2977, "step": 10241 }, { "epoch": 0.5656063618290258, "grad_norm": 0.09251300990581512, "learning_rate": 1.6737825761962504e-05, "loss": 0.0025, "step": 10242 }, { "epoch": 0.5656615860393196, "grad_norm": 3.763401508331299, "learning_rate": 1.6734296412243376e-05, "loss": 0.3267, "step": 10243 }, { "epoch": 0.5657168102496134, "grad_norm": 0.06700494140386581, "learning_rate": 1.673076716700341e-05, "loss": 0.0017, "step": 10244 }, { "epoch": 0.5657720344599072, "grad_norm": 1.0189459323883057, "learning_rate": 1.6727238026355503e-05, "loss": 0.0446, "step": 10245 }, { "epoch": 0.565827258670201, "grad_norm": 0.20279201865196228, "learning_rate": 1.6723708990412575e-05, "loss": 0.0052, "step": 10246 }, { "epoch": 0.5658824828804948, "grad_norm": 0.9906629323959351, "learning_rate": 1.6720180059287517e-05, "loss": 0.0299, "step": 10247 }, { "epoch": 0.5659377070907886, "grad_norm": 1.014643669128418, "learning_rate": 1.6716651233093243e-05, "loss": 0.0218, "step": 10248 }, { "epoch": 0.5659929313010824, "grad_norm": 4.73309850692749, "learning_rate": 1.6713122511942635e-05, "loss": 0.9362, "step": 10249 }, { "epoch": 0.5660481555113762, "grad_norm": 1.5142360925674438, "learning_rate": 1.670959389594861e-05, "loss": 0.0573, "step": 10250 }, { "epoch": 0.56610337972167, "grad_norm": 2.0256431102752686, "learning_rate": 1.6706065385224032e-05, "loss": 0.1214, "step": 10251 }, { "epoch": 0.5661586039319638, "grad_norm": 2.304577589035034, "learning_rate": 1.67025369798818e-05, "loss": 0.241, "step": 10252 }, { "epoch": 0.5662138281422575, "grad_norm": 2.900397300720215, "learning_rate": 1.66990086800348e-05, "loss": 0.2432, "step": 10253 }, { "epoch": 0.5662690523525513, "grad_norm": 1.8367403745651245, "learning_rate": 1.669548048579591e-05, "loss": 0.0817, "step": 10254 }, { "epoch": 0.5663242765628451, "grad_norm": 1.1292625665664673, "learning_rate": 1.6691952397278003e-05, "loss": 0.0399, "step": 10255 }, { "epoch": 0.5663795007731389, "grad_norm": 0.010211903601884842, "learning_rate": 1.668842441459396e-05, "loss": 0.0003, "step": 10256 }, { "epoch": 0.5664347249834327, "grad_norm": 0.2736603319644928, "learning_rate": 1.6684896537856647e-05, "loss": 0.0086, "step": 10257 }, { "epoch": 0.5664899491937265, "grad_norm": 2.057260274887085, "learning_rate": 1.6681368767178938e-05, "loss": 0.2209, "step": 10258 }, { "epoch": 0.5665451734040203, "grad_norm": 0.022692540660500526, "learning_rate": 1.667784110267368e-05, "loss": 0.0008, "step": 10259 }, { "epoch": 0.5666003976143141, "grad_norm": 3.0712149143218994, "learning_rate": 1.6674313544453747e-05, "loss": 0.8331, "step": 10260 }, { "epoch": 0.5666556218246079, "grad_norm": 1.836323618888855, "learning_rate": 1.667078609263199e-05, "loss": 0.043, "step": 10261 }, { "epoch": 0.5667108460349017, "grad_norm": 0.4205750524997711, "learning_rate": 1.6667258747321266e-05, "loss": 0.0129, "step": 10262 }, { "epoch": 0.5667660702451955, "grad_norm": 0.0701715424656868, "learning_rate": 1.6663731508634417e-05, "loss": 0.0016, "step": 10263 }, { "epoch": 0.5668212944554892, "grad_norm": 2.333702325820923, "learning_rate": 1.66602043766843e-05, "loss": 0.2627, "step": 10264 }, { "epoch": 0.566876518665783, "grad_norm": 0.21527926623821259, "learning_rate": 1.6656677351583752e-05, "loss": 0.0053, "step": 10265 }, { "epoch": 0.5669317428760768, "grad_norm": 9.507407188415527, "learning_rate": 1.665315043344562e-05, "loss": 1.4736, "step": 10266 }, { "epoch": 0.5669869670863706, "grad_norm": 1.4792420864105225, "learning_rate": 1.664962362238272e-05, "loss": 0.1677, "step": 10267 }, { "epoch": 0.5670421912966644, "grad_norm": 2.1197240352630615, "learning_rate": 1.664609691850791e-05, "loss": 0.272, "step": 10268 }, { "epoch": 0.5670974155069582, "grad_norm": 4.327943325042725, "learning_rate": 1.6642570321934e-05, "loss": 0.4824, "step": 10269 }, { "epoch": 0.567152639717252, "grad_norm": 3.0261294841766357, "learning_rate": 1.663904383277383e-05, "loss": 0.5737, "step": 10270 }, { "epoch": 0.5672078639275459, "grad_norm": 0.34972381591796875, "learning_rate": 1.6635517451140214e-05, "loss": 0.0104, "step": 10271 }, { "epoch": 0.5672630881378397, "grad_norm": 0.024011408910155296, "learning_rate": 1.663199117714597e-05, "loss": 0.0007, "step": 10272 }, { "epoch": 0.5673183123481335, "grad_norm": 7.264928817749023, "learning_rate": 1.6628465010903915e-05, "loss": 0.2241, "step": 10273 }, { "epoch": 0.5673735365584273, "grad_norm": 0.39203059673309326, "learning_rate": 1.6624938952526874e-05, "loss": 0.0103, "step": 10274 }, { "epoch": 0.567428760768721, "grad_norm": 0.014403747394680977, "learning_rate": 1.662141300212763e-05, "loss": 0.0004, "step": 10275 }, { "epoch": 0.5674839849790148, "grad_norm": 0.22301840782165527, "learning_rate": 1.6617887159819013e-05, "loss": 0.0046, "step": 10276 }, { "epoch": 0.5675392091893086, "grad_norm": 0.3272877633571625, "learning_rate": 1.661436142571381e-05, "loss": 0.0042, "step": 10277 }, { "epoch": 0.5675944333996024, "grad_norm": 0.37862342596054077, "learning_rate": 1.6610835799924826e-05, "loss": 0.0135, "step": 10278 }, { "epoch": 0.5676496576098962, "grad_norm": 1.6649019718170166, "learning_rate": 1.6607310282564848e-05, "loss": 0.0775, "step": 10279 }, { "epoch": 0.56770488182019, "grad_norm": 0.08327657729387283, "learning_rate": 1.6603784873746677e-05, "loss": 0.0036, "step": 10280 }, { "epoch": 0.5677601060304838, "grad_norm": 3.659433603286743, "learning_rate": 1.6600259573583094e-05, "loss": 0.3357, "step": 10281 }, { "epoch": 0.5678153302407776, "grad_norm": 3.660644769668579, "learning_rate": 1.6596734382186893e-05, "loss": 1.0483, "step": 10282 }, { "epoch": 0.5678705544510714, "grad_norm": 2.0575573444366455, "learning_rate": 1.659320929967083e-05, "loss": 0.448, "step": 10283 }, { "epoch": 0.5679257786613652, "grad_norm": 0.5258764028549194, "learning_rate": 1.658968432614772e-05, "loss": 0.004, "step": 10284 }, { "epoch": 0.567981002871659, "grad_norm": 1.2448738813400269, "learning_rate": 1.6586159461730306e-05, "loss": 0.0683, "step": 10285 }, { "epoch": 0.5680362270819528, "grad_norm": 4.438192844390869, "learning_rate": 1.6582634706531377e-05, "loss": 0.8508, "step": 10286 }, { "epoch": 0.5680914512922465, "grad_norm": 3.0906245708465576, "learning_rate": 1.6579110060663682e-05, "loss": 0.161, "step": 10287 }, { "epoch": 0.5681466755025403, "grad_norm": 0.31092363595962524, "learning_rate": 1.6575585524240004e-05, "loss": 0.0076, "step": 10288 }, { "epoch": 0.5682018997128341, "grad_norm": 3.4524900913238525, "learning_rate": 1.65720610973731e-05, "loss": 1.2389, "step": 10289 }, { "epoch": 0.5682571239231279, "grad_norm": 4.571169853210449, "learning_rate": 1.6568536780175706e-05, "loss": 1.3132, "step": 10290 }, { "epoch": 0.5683123481334217, "grad_norm": 0.691753089427948, "learning_rate": 1.6565012572760597e-05, "loss": 0.0188, "step": 10291 }, { "epoch": 0.5683675723437155, "grad_norm": 2.107717990875244, "learning_rate": 1.656148847524051e-05, "loss": 0.1534, "step": 10292 }, { "epoch": 0.5684227965540093, "grad_norm": 0.5240866541862488, "learning_rate": 1.65579644877282e-05, "loss": 0.0141, "step": 10293 }, { "epoch": 0.5684780207643031, "grad_norm": 2.5926833152770996, "learning_rate": 1.65544406103364e-05, "loss": 0.2043, "step": 10294 }, { "epoch": 0.5685332449745969, "grad_norm": 1.322239637374878, "learning_rate": 1.655091684317786e-05, "loss": 0.0379, "step": 10295 }, { "epoch": 0.5685884691848907, "grad_norm": 3.894390344619751, "learning_rate": 1.6547393186365305e-05, "loss": 0.4792, "step": 10296 }, { "epoch": 0.5686436933951845, "grad_norm": 4.6990509033203125, "learning_rate": 1.654386964001148e-05, "loss": 0.5455, "step": 10297 }, { "epoch": 0.5686989176054782, "grad_norm": 1.908499002456665, "learning_rate": 1.654034620422909e-05, "loss": 0.1512, "step": 10298 }, { "epoch": 0.568754141815772, "grad_norm": 3.1071228981018066, "learning_rate": 1.6536822879130886e-05, "loss": 0.1349, "step": 10299 }, { "epoch": 0.5688093660260658, "grad_norm": 0.06360669434070587, "learning_rate": 1.653329966482957e-05, "loss": 0.0019, "step": 10300 }, { "epoch": 0.5688645902363596, "grad_norm": 0.44433829188346863, "learning_rate": 1.6529776561437873e-05, "loss": 0.0143, "step": 10301 }, { "epoch": 0.5689198144466534, "grad_norm": 6.39220666885376, "learning_rate": 1.6526253569068497e-05, "loss": 0.7032, "step": 10302 }, { "epoch": 0.5689750386569472, "grad_norm": 4.684204578399658, "learning_rate": 1.652273068783416e-05, "loss": 0.4807, "step": 10303 }, { "epoch": 0.569030262867241, "grad_norm": 0.10078143328428268, "learning_rate": 1.651920791784757e-05, "loss": 0.0029, "step": 10304 }, { "epoch": 0.5690854870775348, "grad_norm": 5.018352508544922, "learning_rate": 1.651568525922143e-05, "loss": 0.4835, "step": 10305 }, { "epoch": 0.5691407112878286, "grad_norm": 2.6988189220428467, "learning_rate": 1.651216271206843e-05, "loss": 0.2862, "step": 10306 }, { "epoch": 0.5691959354981224, "grad_norm": 2.8768057823181152, "learning_rate": 1.6508640276501284e-05, "loss": 0.3172, "step": 10307 }, { "epoch": 0.5692511597084162, "grad_norm": 1.6897367238998413, "learning_rate": 1.650511795263267e-05, "loss": 0.0788, "step": 10308 }, { "epoch": 0.5693063839187099, "grad_norm": 1.4179058074951172, "learning_rate": 1.6501595740575283e-05, "loss": 0.0695, "step": 10309 }, { "epoch": 0.5693616081290037, "grad_norm": 1.559897541999817, "learning_rate": 1.6498073640441804e-05, "loss": 0.1505, "step": 10310 }, { "epoch": 0.5694168323392975, "grad_norm": 0.042722493410110474, "learning_rate": 1.6494551652344924e-05, "loss": 0.0015, "step": 10311 }, { "epoch": 0.5694720565495913, "grad_norm": 0.4471091032028198, "learning_rate": 1.6491029776397312e-05, "loss": 0.0132, "step": 10312 }, { "epoch": 0.5695272807598851, "grad_norm": 1.6005816459655762, "learning_rate": 1.6487508012711653e-05, "loss": 0.1485, "step": 10313 }, { "epoch": 0.5695825049701789, "grad_norm": 0.08747933059930801, "learning_rate": 1.6483986361400605e-05, "loss": 0.0027, "step": 10314 }, { "epoch": 0.5696377291804727, "grad_norm": 2.165147304534912, "learning_rate": 1.648046482257685e-05, "loss": 0.1561, "step": 10315 }, { "epoch": 0.5696929533907665, "grad_norm": 7.254192352294922, "learning_rate": 1.647694339635304e-05, "loss": 1.5338, "step": 10316 }, { "epoch": 0.5697481776010603, "grad_norm": 0.0334492027759552, "learning_rate": 1.6473422082841842e-05, "loss": 0.0008, "step": 10317 }, { "epoch": 0.5698034018113541, "grad_norm": 0.1036713644862175, "learning_rate": 1.646990088215591e-05, "loss": 0.0031, "step": 10318 }, { "epoch": 0.5698586260216479, "grad_norm": 3.8146543502807617, "learning_rate": 1.64663797944079e-05, "loss": 0.4556, "step": 10319 }, { "epoch": 0.5699138502319416, "grad_norm": 4.95025110244751, "learning_rate": 1.646285881971046e-05, "loss": 1.3728, "step": 10320 }, { "epoch": 0.5699690744422354, "grad_norm": 0.42923685908317566, "learning_rate": 1.645933795817624e-05, "loss": 0.0098, "step": 10321 }, { "epoch": 0.5700242986525292, "grad_norm": 2.80033016204834, "learning_rate": 1.6455817209917867e-05, "loss": 0.0862, "step": 10322 }, { "epoch": 0.570079522862823, "grad_norm": 5.626710891723633, "learning_rate": 1.6452296575048006e-05, "loss": 1.1214, "step": 10323 }, { "epoch": 0.5701347470731168, "grad_norm": 0.4847305119037628, "learning_rate": 1.6448776053679268e-05, "loss": 0.0146, "step": 10324 }, { "epoch": 0.5701899712834106, "grad_norm": 2.61327862739563, "learning_rate": 1.64452556459243e-05, "loss": 0.2037, "step": 10325 }, { "epoch": 0.5702451954937044, "grad_norm": 4.625295639038086, "learning_rate": 1.6441735351895716e-05, "loss": 0.3494, "step": 10326 }, { "epoch": 0.5703004197039983, "grad_norm": 0.0867643654346466, "learning_rate": 1.6438215171706154e-05, "loss": 0.0037, "step": 10327 }, { "epoch": 0.570355643914292, "grad_norm": 2.358314275741577, "learning_rate": 1.6434695105468223e-05, "loss": 0.5359, "step": 10328 }, { "epoch": 0.5704108681245859, "grad_norm": 1.3984808921813965, "learning_rate": 1.6431175153294553e-05, "loss": 0.0596, "step": 10329 }, { "epoch": 0.5704660923348797, "grad_norm": 2.2048990726470947, "learning_rate": 1.642765531529774e-05, "loss": 0.4307, "step": 10330 }, { "epoch": 0.5705213165451734, "grad_norm": 1.7097023725509644, "learning_rate": 1.642413559159042e-05, "loss": 0.0867, "step": 10331 }, { "epoch": 0.5705765407554672, "grad_norm": 1.1963574886322021, "learning_rate": 1.6420615982285167e-05, "loss": 0.0323, "step": 10332 }, { "epoch": 0.570631764965761, "grad_norm": 6.498368740081787, "learning_rate": 1.6417096487494605e-05, "loss": 0.0474, "step": 10333 }, { "epoch": 0.5706869891760548, "grad_norm": 2.3673083782196045, "learning_rate": 1.641357710733132e-05, "loss": 0.2693, "step": 10334 }, { "epoch": 0.5707422133863486, "grad_norm": 1.9348028898239136, "learning_rate": 1.6410057841907923e-05, "loss": 0.2958, "step": 10335 }, { "epoch": 0.5707974375966424, "grad_norm": 5.3207197189331055, "learning_rate": 1.640653869133699e-05, "loss": 1.1254, "step": 10336 }, { "epoch": 0.5708526618069362, "grad_norm": 0.01765645481646061, "learning_rate": 1.6403019655731116e-05, "loss": 0.0006, "step": 10337 }, { "epoch": 0.57090788601723, "grad_norm": 0.5986521244049072, "learning_rate": 1.639950073520288e-05, "loss": 0.0194, "step": 10338 }, { "epoch": 0.5709631102275238, "grad_norm": 5.570796012878418, "learning_rate": 1.6395981929864877e-05, "loss": 0.8376, "step": 10339 }, { "epoch": 0.5710183344378176, "grad_norm": 0.1497197300195694, "learning_rate": 1.6392463239829662e-05, "loss": 0.0036, "step": 10340 }, { "epoch": 0.5710735586481114, "grad_norm": 2.558072328567505, "learning_rate": 1.638894466520982e-05, "loss": 0.0841, "step": 10341 }, { "epoch": 0.5711287828584051, "grad_norm": 0.42722806334495544, "learning_rate": 1.6385426206117917e-05, "loss": 0.0131, "step": 10342 }, { "epoch": 0.5711840070686989, "grad_norm": 5.082093715667725, "learning_rate": 1.638190786266652e-05, "loss": 0.574, "step": 10343 }, { "epoch": 0.5712392312789927, "grad_norm": 0.06592009216547012, "learning_rate": 1.6378389634968192e-05, "loss": 0.0029, "step": 10344 }, { "epoch": 0.5712944554892865, "grad_norm": 0.4388622045516968, "learning_rate": 1.6374871523135492e-05, "loss": 0.0141, "step": 10345 }, { "epoch": 0.5713496796995803, "grad_norm": 0.1480429619550705, "learning_rate": 1.637135352728097e-05, "loss": 0.0057, "step": 10346 }, { "epoch": 0.5714049039098741, "grad_norm": 0.08395354449748993, "learning_rate": 1.6367835647517184e-05, "loss": 0.0027, "step": 10347 }, { "epoch": 0.5714601281201679, "grad_norm": 5.429727554321289, "learning_rate": 1.6364317883956664e-05, "loss": 0.5577, "step": 10348 }, { "epoch": 0.5715153523304617, "grad_norm": 0.07623258978128433, "learning_rate": 1.6360800236711977e-05, "loss": 0.004, "step": 10349 }, { "epoch": 0.5715705765407555, "grad_norm": 5.252138137817383, "learning_rate": 1.635728270589565e-05, "loss": 0.3137, "step": 10350 }, { "epoch": 0.5716258007510493, "grad_norm": 2.5752322673797607, "learning_rate": 1.6353765291620213e-05, "loss": 0.14, "step": 10351 }, { "epoch": 0.5716810249613431, "grad_norm": 0.0334525927901268, "learning_rate": 1.6350247993998212e-05, "loss": 0.0011, "step": 10352 }, { "epoch": 0.5717362491716369, "grad_norm": 5.693081378936768, "learning_rate": 1.634673081314216e-05, "loss": 0.4645, "step": 10353 }, { "epoch": 0.5717914733819306, "grad_norm": 1.9099228382110596, "learning_rate": 1.6343213749164597e-05, "loss": 0.1367, "step": 10354 }, { "epoch": 0.5718466975922244, "grad_norm": 0.04944462329149246, "learning_rate": 1.633969680217803e-05, "loss": 0.0015, "step": 10355 }, { "epoch": 0.5719019218025182, "grad_norm": 2.465731620788574, "learning_rate": 1.633617997229499e-05, "loss": 0.2445, "step": 10356 }, { "epoch": 0.571957146012812, "grad_norm": 3.620993137359619, "learning_rate": 1.633266325962797e-05, "loss": 0.8021, "step": 10357 }, { "epoch": 0.5720123702231058, "grad_norm": 0.6522741317749023, "learning_rate": 1.6329146664289507e-05, "loss": 0.1412, "step": 10358 }, { "epoch": 0.5720675944333996, "grad_norm": 1.8998347520828247, "learning_rate": 1.6325630186392084e-05, "loss": 0.1853, "step": 10359 }, { "epoch": 0.5721228186436934, "grad_norm": 5.500931262969971, "learning_rate": 1.632211382604822e-05, "loss": 0.3462, "step": 10360 }, { "epoch": 0.5721780428539872, "grad_norm": 3.6318793296813965, "learning_rate": 1.6318597583370393e-05, "loss": 1.047, "step": 10361 }, { "epoch": 0.572233267064281, "grad_norm": 4.797713279724121, "learning_rate": 1.6315081458471125e-05, "loss": 1.2166, "step": 10362 }, { "epoch": 0.5722884912745748, "grad_norm": 0.23774148523807526, "learning_rate": 1.631156545146288e-05, "loss": 0.007, "step": 10363 }, { "epoch": 0.5723437154848686, "grad_norm": 2.6437125205993652, "learning_rate": 1.6308049562458162e-05, "loss": 0.2225, "step": 10364 }, { "epoch": 0.5723989396951623, "grad_norm": 0.04038208723068237, "learning_rate": 1.6304533791569443e-05, "loss": 0.0011, "step": 10365 }, { "epoch": 0.5724541639054561, "grad_norm": 3.8674330711364746, "learning_rate": 1.6301018138909217e-05, "loss": 0.7974, "step": 10366 }, { "epoch": 0.5725093881157499, "grad_norm": 0.22433717548847198, "learning_rate": 1.6297502604589942e-05, "loss": 0.0101, "step": 10367 }, { "epoch": 0.5725646123260437, "grad_norm": 0.01311010867357254, "learning_rate": 1.629398718872411e-05, "loss": 0.0004, "step": 10368 }, { "epoch": 0.5726198365363375, "grad_norm": 2.138838768005371, "learning_rate": 1.629047189142417e-05, "loss": 0.0678, "step": 10369 }, { "epoch": 0.5726750607466313, "grad_norm": 0.06326846033334732, "learning_rate": 1.62869567128026e-05, "loss": 0.002, "step": 10370 }, { "epoch": 0.5727302849569251, "grad_norm": 2.0535385608673096, "learning_rate": 1.628344165297185e-05, "loss": 0.2573, "step": 10371 }, { "epoch": 0.5727855091672189, "grad_norm": 1.2722926139831543, "learning_rate": 1.6279926712044387e-05, "loss": 0.0199, "step": 10372 }, { "epoch": 0.5728407333775127, "grad_norm": 5.040965557098389, "learning_rate": 1.6276411890132656e-05, "loss": 0.7284, "step": 10373 }, { "epoch": 0.5728959575878065, "grad_norm": 6.181323051452637, "learning_rate": 1.6272897187349112e-05, "loss": 1.2155, "step": 10374 }, { "epoch": 0.5729511817981003, "grad_norm": 1.380791425704956, "learning_rate": 1.626938260380619e-05, "loss": 0.046, "step": 10375 }, { "epoch": 0.573006406008394, "grad_norm": 1.8883490562438965, "learning_rate": 1.6265868139616348e-05, "loss": 0.1884, "step": 10376 }, { "epoch": 0.5730616302186878, "grad_norm": 3.0584099292755127, "learning_rate": 1.6262353794892008e-05, "loss": 0.3341, "step": 10377 }, { "epoch": 0.5731168544289816, "grad_norm": 2.607330083847046, "learning_rate": 1.625883956974562e-05, "loss": 0.3669, "step": 10378 }, { "epoch": 0.5731720786392754, "grad_norm": 2.722965717315674, "learning_rate": 1.62553254642896e-05, "loss": 0.435, "step": 10379 }, { "epoch": 0.5732273028495692, "grad_norm": 3.777376174926758, "learning_rate": 1.625181147863638e-05, "loss": 0.7838, "step": 10380 }, { "epoch": 0.573282527059863, "grad_norm": 0.6816563010215759, "learning_rate": 1.6248297612898377e-05, "loss": 0.0217, "step": 10381 }, { "epoch": 0.5733377512701568, "grad_norm": 0.7726106643676758, "learning_rate": 1.6244783867188016e-05, "loss": 0.0087, "step": 10382 }, { "epoch": 0.5733929754804507, "grad_norm": 3.2614099979400635, "learning_rate": 1.6241270241617708e-05, "loss": 0.2462, "step": 10383 }, { "epoch": 0.5734481996907445, "grad_norm": 0.03608636185526848, "learning_rate": 1.623775673629987e-05, "loss": 0.0012, "step": 10384 }, { "epoch": 0.5735034239010383, "grad_norm": 2.335038185119629, "learning_rate": 1.62342433513469e-05, "loss": 0.7105, "step": 10385 }, { "epoch": 0.5735586481113321, "grad_norm": 0.1676216572523117, "learning_rate": 1.6230730086871214e-05, "loss": 0.0059, "step": 10386 }, { "epoch": 0.5736138723216258, "grad_norm": 0.14613598585128784, "learning_rate": 1.6227216942985192e-05, "loss": 0.0019, "step": 10387 }, { "epoch": 0.5736690965319196, "grad_norm": 0.2532428801059723, "learning_rate": 1.622370391980125e-05, "loss": 0.0069, "step": 10388 }, { "epoch": 0.5737243207422134, "grad_norm": 1.7254985570907593, "learning_rate": 1.6220191017431765e-05, "loss": 0.0749, "step": 10389 }, { "epoch": 0.5737795449525072, "grad_norm": 1.902671456336975, "learning_rate": 1.6216678235989132e-05, "loss": 0.3722, "step": 10390 }, { "epoch": 0.573834769162801, "grad_norm": 5.030662536621094, "learning_rate": 1.621316557558573e-05, "loss": 0.7087, "step": 10391 }, { "epoch": 0.5738899933730948, "grad_norm": 5.7004008293151855, "learning_rate": 1.6209653036333946e-05, "loss": 0.3007, "step": 10392 }, { "epoch": 0.5739452175833886, "grad_norm": 3.993353843688965, "learning_rate": 1.6206140618346147e-05, "loss": 0.5351, "step": 10393 }, { "epoch": 0.5740004417936824, "grad_norm": 3.754390001296997, "learning_rate": 1.6202628321734717e-05, "loss": 0.3327, "step": 10394 }, { "epoch": 0.5740556660039762, "grad_norm": 2.1943275928497314, "learning_rate": 1.6199116146612007e-05, "loss": 0.0818, "step": 10395 }, { "epoch": 0.57411089021427, "grad_norm": 2.254924774169922, "learning_rate": 1.6195604093090407e-05, "loss": 0.3742, "step": 10396 }, { "epoch": 0.5741661144245638, "grad_norm": 1.12671959400177, "learning_rate": 1.6192092161282254e-05, "loss": 0.0363, "step": 10397 }, { "epoch": 0.5742213386348575, "grad_norm": 0.6342028379440308, "learning_rate": 1.6188580351299913e-05, "loss": 0.0182, "step": 10398 }, { "epoch": 0.5742765628451513, "grad_norm": 1.2859328985214233, "learning_rate": 1.6185068663255737e-05, "loss": 0.0457, "step": 10399 }, { "epoch": 0.5743317870554451, "grad_norm": 2.521791458129883, "learning_rate": 1.618155709726208e-05, "loss": 0.5813, "step": 10400 }, { "epoch": 0.5743870112657389, "grad_norm": 2.046365737915039, "learning_rate": 1.6178045653431275e-05, "loss": 0.2212, "step": 10401 }, { "epoch": 0.5744422354760327, "grad_norm": 3.110670804977417, "learning_rate": 1.617453433187568e-05, "loss": 0.6648, "step": 10402 }, { "epoch": 0.5744974596863265, "grad_norm": 0.4216448664665222, "learning_rate": 1.6171023132707607e-05, "loss": 0.0109, "step": 10403 }, { "epoch": 0.5745526838966203, "grad_norm": 1.6123822927474976, "learning_rate": 1.6167512056039422e-05, "loss": 0.1434, "step": 10404 }, { "epoch": 0.5746079081069141, "grad_norm": 3.0696918964385986, "learning_rate": 1.6164001101983423e-05, "loss": 0.6134, "step": 10405 }, { "epoch": 0.5746631323172079, "grad_norm": 3.0850412845611572, "learning_rate": 1.6160490270651958e-05, "loss": 0.2852, "step": 10406 }, { "epoch": 0.5747183565275017, "grad_norm": 0.08170635253190994, "learning_rate": 1.6156979562157333e-05, "loss": 0.0033, "step": 10407 }, { "epoch": 0.5747735807377955, "grad_norm": 2.4027445316314697, "learning_rate": 1.6153468976611878e-05, "loss": 0.0935, "step": 10408 }, { "epoch": 0.5748288049480892, "grad_norm": 0.12630422413349152, "learning_rate": 1.6149958514127906e-05, "loss": 0.0047, "step": 10409 }, { "epoch": 0.574884029158383, "grad_norm": 0.6570201516151428, "learning_rate": 1.6146448174817713e-05, "loss": 0.0181, "step": 10410 }, { "epoch": 0.5749392533686768, "grad_norm": 0.0933106541633606, "learning_rate": 1.6142937958793617e-05, "loss": 0.0027, "step": 10411 }, { "epoch": 0.5749944775789706, "grad_norm": 2.860475540161133, "learning_rate": 1.613942786616791e-05, "loss": 0.3154, "step": 10412 }, { "epoch": 0.5750497017892644, "grad_norm": 1.9586434364318848, "learning_rate": 1.6135917897052905e-05, "loss": 0.0671, "step": 10413 }, { "epoch": 0.5751049259995582, "grad_norm": 3.3472180366516113, "learning_rate": 1.613240805156088e-05, "loss": 0.9798, "step": 10414 }, { "epoch": 0.575160150209852, "grad_norm": 3.352902889251709, "learning_rate": 1.612889832980414e-05, "loss": 0.0479, "step": 10415 }, { "epoch": 0.5752153744201458, "grad_norm": 1.0164942741394043, "learning_rate": 1.612538873189495e-05, "loss": 0.0443, "step": 10416 }, { "epoch": 0.5752705986304396, "grad_norm": 5.6050801277160645, "learning_rate": 1.612187925794562e-05, "loss": 1.2032, "step": 10417 }, { "epoch": 0.5753258228407334, "grad_norm": 1.543228030204773, "learning_rate": 1.61183699080684e-05, "loss": 0.0885, "step": 10418 }, { "epoch": 0.5753810470510272, "grad_norm": 2.6585118770599365, "learning_rate": 1.6114860682375585e-05, "loss": 0.1177, "step": 10419 }, { "epoch": 0.5754362712613209, "grad_norm": 0.6987392902374268, "learning_rate": 1.6111351580979437e-05, "loss": 0.0222, "step": 10420 }, { "epoch": 0.5754914954716147, "grad_norm": 1.1588380336761475, "learning_rate": 1.6107842603992222e-05, "loss": 0.0451, "step": 10421 }, { "epoch": 0.5755467196819085, "grad_norm": 0.3475903868675232, "learning_rate": 1.61043337515262e-05, "loss": 0.014, "step": 10422 }, { "epoch": 0.5756019438922023, "grad_norm": 3.529162883758545, "learning_rate": 1.610082502369363e-05, "loss": 0.609, "step": 10423 }, { "epoch": 0.5756571681024961, "grad_norm": 0.6795170903205872, "learning_rate": 1.609731642060677e-05, "loss": 0.0101, "step": 10424 }, { "epoch": 0.5757123923127899, "grad_norm": 0.41822221875190735, "learning_rate": 1.6093807942377873e-05, "loss": 0.1123, "step": 10425 }, { "epoch": 0.5757676165230837, "grad_norm": 4.17834997177124, "learning_rate": 1.609029958911917e-05, "loss": 0.3115, "step": 10426 }, { "epoch": 0.5758228407333775, "grad_norm": 0.06348927319049835, "learning_rate": 1.608679136094293e-05, "loss": 0.0025, "step": 10427 }, { "epoch": 0.5758780649436713, "grad_norm": 0.2743200361728668, "learning_rate": 1.608328325796136e-05, "loss": 0.0123, "step": 10428 }, { "epoch": 0.5759332891539651, "grad_norm": 3.781792402267456, "learning_rate": 1.6079775280286715e-05, "loss": 0.9951, "step": 10429 }, { "epoch": 0.5759885133642589, "grad_norm": 0.10405806452035904, "learning_rate": 1.6076267428031217e-05, "loss": 0.0042, "step": 10430 }, { "epoch": 0.5760437375745527, "grad_norm": 0.4054344594478607, "learning_rate": 1.6072759701307096e-05, "loss": 0.0094, "step": 10431 }, { "epoch": 0.5760989617848464, "grad_norm": 2.900642156600952, "learning_rate": 1.606925210022657e-05, "loss": 0.2828, "step": 10432 }, { "epoch": 0.5761541859951402, "grad_norm": 3.6260411739349365, "learning_rate": 1.6065744624901865e-05, "loss": 0.2668, "step": 10433 }, { "epoch": 0.576209410205434, "grad_norm": 0.07498391717672348, "learning_rate": 1.6062237275445182e-05, "loss": 0.0028, "step": 10434 }, { "epoch": 0.5762646344157278, "grad_norm": 4.575332164764404, "learning_rate": 1.6058730051968746e-05, "loss": 0.7926, "step": 10435 }, { "epoch": 0.5763198586260216, "grad_norm": 0.8308996558189392, "learning_rate": 1.605522295458475e-05, "loss": 0.0255, "step": 10436 }, { "epoch": 0.5763750828363154, "grad_norm": 0.030575022101402283, "learning_rate": 1.6051715983405406e-05, "loss": 0.0009, "step": 10437 }, { "epoch": 0.5764303070466092, "grad_norm": 0.6010207533836365, "learning_rate": 1.6048209138542906e-05, "loss": 0.011, "step": 10438 }, { "epoch": 0.576485531256903, "grad_norm": 0.11844910681247711, "learning_rate": 1.6044702420109447e-05, "loss": 0.0053, "step": 10439 }, { "epoch": 0.5765407554671969, "grad_norm": 0.17257702350616455, "learning_rate": 1.6041195828217216e-05, "loss": 0.0033, "step": 10440 }, { "epoch": 0.5765959796774907, "grad_norm": 4.172450542449951, "learning_rate": 1.603768936297841e-05, "loss": 0.2157, "step": 10441 }, { "epoch": 0.5766512038877845, "grad_norm": 2.662255048751831, "learning_rate": 1.6034183024505185e-05, "loss": 0.0983, "step": 10442 }, { "epoch": 0.5767064280980781, "grad_norm": 0.24389930069446564, "learning_rate": 1.603067681290975e-05, "loss": 0.0046, "step": 10443 }, { "epoch": 0.576761652308372, "grad_norm": 0.9450145363807678, "learning_rate": 1.6027170728304257e-05, "loss": 0.015, "step": 10444 }, { "epoch": 0.5768168765186658, "grad_norm": 0.9373859167098999, "learning_rate": 1.6023664770800885e-05, "loss": 0.0355, "step": 10445 }, { "epoch": 0.5768721007289596, "grad_norm": 0.012018151581287384, "learning_rate": 1.6020158940511793e-05, "loss": 0.0003, "step": 10446 }, { "epoch": 0.5769273249392534, "grad_norm": 0.02413240075111389, "learning_rate": 1.601665323754915e-05, "loss": 0.001, "step": 10447 }, { "epoch": 0.5769825491495472, "grad_norm": 6.525979042053223, "learning_rate": 1.6013147662025108e-05, "loss": 2.0242, "step": 10448 }, { "epoch": 0.577037773359841, "grad_norm": 3.291778326034546, "learning_rate": 1.6009642214051827e-05, "loss": 0.6451, "step": 10449 }, { "epoch": 0.5770929975701348, "grad_norm": 0.17258435487747192, "learning_rate": 1.600613689374144e-05, "loss": 0.0045, "step": 10450 }, { "epoch": 0.5771482217804286, "grad_norm": 0.07204511761665344, "learning_rate": 1.6002631701206118e-05, "loss": 0.0023, "step": 10451 }, { "epoch": 0.5772034459907224, "grad_norm": 1.215582251548767, "learning_rate": 1.599912663655798e-05, "loss": 0.0364, "step": 10452 }, { "epoch": 0.5772586702010162, "grad_norm": 0.9647443890571594, "learning_rate": 1.5995621699909176e-05, "loss": 0.0276, "step": 10453 }, { "epoch": 0.5773138944113099, "grad_norm": 2.922851085662842, "learning_rate": 1.5992116891371828e-05, "loss": 0.8412, "step": 10454 }, { "epoch": 0.5773691186216037, "grad_norm": 4.283971786499023, "learning_rate": 1.5988612211058073e-05, "loss": 0.543, "step": 10455 }, { "epoch": 0.5774243428318975, "grad_norm": 0.1666955202817917, "learning_rate": 1.5985107659080032e-05, "loss": 0.0061, "step": 10456 }, { "epoch": 0.5774795670421913, "grad_norm": 0.3406893312931061, "learning_rate": 1.5981603235549828e-05, "loss": 0.0126, "step": 10457 }, { "epoch": 0.5775347912524851, "grad_norm": 4.038902759552002, "learning_rate": 1.5978098940579578e-05, "loss": 0.8438, "step": 10458 }, { "epoch": 0.5775900154627789, "grad_norm": 0.13291335105895996, "learning_rate": 1.5974594774281397e-05, "loss": 0.0028, "step": 10459 }, { "epoch": 0.5776452396730727, "grad_norm": 0.10266526788473129, "learning_rate": 1.597109073676738e-05, "loss": 0.0036, "step": 10460 }, { "epoch": 0.5777004638833665, "grad_norm": 3.955270290374756, "learning_rate": 1.5967586828149646e-05, "loss": 0.1387, "step": 10461 }, { "epoch": 0.5777556880936603, "grad_norm": 4.837582111358643, "learning_rate": 1.5964083048540282e-05, "loss": 1.161, "step": 10462 }, { "epoch": 0.5778109123039541, "grad_norm": 2.4628965854644775, "learning_rate": 1.59605793980514e-05, "loss": 0.2261, "step": 10463 }, { "epoch": 0.5778661365142479, "grad_norm": 1.904679775238037, "learning_rate": 1.5957075876795074e-05, "loss": 0.1947, "step": 10464 }, { "epoch": 0.5779213607245416, "grad_norm": 0.249914288520813, "learning_rate": 1.5953572484883407e-05, "loss": 0.0053, "step": 10465 }, { "epoch": 0.5779765849348354, "grad_norm": 0.09845589101314545, "learning_rate": 1.595006922242847e-05, "loss": 0.0025, "step": 10466 }, { "epoch": 0.5780318091451292, "grad_norm": 0.5374242663383484, "learning_rate": 1.5946566089542358e-05, "loss": 0.0116, "step": 10467 }, { "epoch": 0.578087033355423, "grad_norm": 0.08897122740745544, "learning_rate": 1.594306308633713e-05, "loss": 0.0021, "step": 10468 }, { "epoch": 0.5781422575657168, "grad_norm": 2.512190580368042, "learning_rate": 1.5939560212924865e-05, "loss": 0.2388, "step": 10469 }, { "epoch": 0.5781974817760106, "grad_norm": 0.060939282178878784, "learning_rate": 1.5936057469417627e-05, "loss": 0.002, "step": 10470 }, { "epoch": 0.5782527059863044, "grad_norm": 0.06700378656387329, "learning_rate": 1.593255485592748e-05, "loss": 0.0021, "step": 10471 }, { "epoch": 0.5783079301965982, "grad_norm": 0.2983991503715515, "learning_rate": 1.5929052372566488e-05, "loss": 0.0102, "step": 10472 }, { "epoch": 0.578363154406892, "grad_norm": 1.9817073345184326, "learning_rate": 1.5925550019446686e-05, "loss": 0.1189, "step": 10473 }, { "epoch": 0.5784183786171858, "grad_norm": 2.1054556369781494, "learning_rate": 1.5922047796680155e-05, "loss": 0.2322, "step": 10474 }, { "epoch": 0.5784736028274796, "grad_norm": 2.466956853866577, "learning_rate": 1.5918545704378914e-05, "loss": 0.1238, "step": 10475 }, { "epoch": 0.5785288270377733, "grad_norm": 0.11899840831756592, "learning_rate": 1.591504374265502e-05, "loss": 0.0038, "step": 10476 }, { "epoch": 0.5785840512480671, "grad_norm": 0.02947082370519638, "learning_rate": 1.59115419116205e-05, "loss": 0.0006, "step": 10477 }, { "epoch": 0.5786392754583609, "grad_norm": 2.266634702682495, "learning_rate": 1.59080402113874e-05, "loss": 0.1104, "step": 10478 }, { "epoch": 0.5786944996686547, "grad_norm": 3.1924524307250977, "learning_rate": 1.5904538642067736e-05, "loss": 0.4344, "step": 10479 }, { "epoch": 0.5787497238789485, "grad_norm": 3.528273105621338, "learning_rate": 1.5901037203773552e-05, "loss": 0.8487, "step": 10480 }, { "epoch": 0.5788049480892423, "grad_norm": 0.01705818437039852, "learning_rate": 1.5897535896616844e-05, "loss": 0.0005, "step": 10481 }, { "epoch": 0.5788601722995361, "grad_norm": 0.49455738067626953, "learning_rate": 1.5894034720709652e-05, "loss": 0.0131, "step": 10482 }, { "epoch": 0.5789153965098299, "grad_norm": 4.014406681060791, "learning_rate": 1.5890533676163972e-05, "loss": 0.2784, "step": 10483 }, { "epoch": 0.5789706207201237, "grad_norm": 0.134115070104599, "learning_rate": 1.588703276309182e-05, "loss": 0.0029, "step": 10484 }, { "epoch": 0.5790258449304175, "grad_norm": 1.720513105392456, "learning_rate": 1.5883531981605198e-05, "loss": 0.0555, "step": 10485 }, { "epoch": 0.5790810691407113, "grad_norm": 5.354410648345947, "learning_rate": 1.5880031331816113e-05, "loss": 0.5132, "step": 10486 }, { "epoch": 0.579136293351005, "grad_norm": 2.7637009620666504, "learning_rate": 1.5876530813836545e-05, "loss": 0.3234, "step": 10487 }, { "epoch": 0.5791915175612988, "grad_norm": 2.6578726768493652, "learning_rate": 1.5873030427778504e-05, "loss": 0.0799, "step": 10488 }, { "epoch": 0.5792467417715926, "grad_norm": 1.771888256072998, "learning_rate": 1.5869530173753962e-05, "loss": 0.1031, "step": 10489 }, { "epoch": 0.5793019659818864, "grad_norm": 2.4192802906036377, "learning_rate": 1.586603005187492e-05, "loss": 0.2205, "step": 10490 }, { "epoch": 0.5793571901921802, "grad_norm": 0.07836758345365524, "learning_rate": 1.5862530062253335e-05, "loss": 0.0025, "step": 10491 }, { "epoch": 0.579412414402474, "grad_norm": 0.08977252244949341, "learning_rate": 1.5859030205001195e-05, "loss": 0.002, "step": 10492 }, { "epoch": 0.5794676386127678, "grad_norm": 1.4708231687545776, "learning_rate": 1.5855530480230465e-05, "loss": 0.0185, "step": 10493 }, { "epoch": 0.5795228628230616, "grad_norm": 0.09177573025226593, "learning_rate": 1.585203088805312e-05, "loss": 0.0017, "step": 10494 }, { "epoch": 0.5795780870333554, "grad_norm": 1.1463321447372437, "learning_rate": 1.5848531428581108e-05, "loss": 0.0399, "step": 10495 }, { "epoch": 0.5796333112436493, "grad_norm": 0.8953704237937927, "learning_rate": 1.5845032101926398e-05, "loss": 0.0311, "step": 10496 }, { "epoch": 0.579688535453943, "grad_norm": 4.374939441680908, "learning_rate": 1.5841532908200935e-05, "loss": 0.2766, "step": 10497 }, { "epoch": 0.5797437596642367, "grad_norm": 4.964682102203369, "learning_rate": 1.5838033847516684e-05, "loss": 0.9925, "step": 10498 }, { "epoch": 0.5797989838745305, "grad_norm": 0.021114956587553024, "learning_rate": 1.5834534919985573e-05, "loss": 0.0007, "step": 10499 }, { "epoch": 0.5798542080848244, "grad_norm": 0.43440744280815125, "learning_rate": 1.5831036125719547e-05, "loss": 0.0152, "step": 10500 }, { "epoch": 0.5799094322951182, "grad_norm": 1.7174162864685059, "learning_rate": 1.582753746483054e-05, "loss": 0.1359, "step": 10501 }, { "epoch": 0.579964656505412, "grad_norm": 4.157703399658203, "learning_rate": 1.5824038937430496e-05, "loss": 1.0657, "step": 10502 }, { "epoch": 0.5800198807157058, "grad_norm": 0.02474006824195385, "learning_rate": 1.582054054363133e-05, "loss": 0.0007, "step": 10503 }, { "epoch": 0.5800751049259996, "grad_norm": 0.2258232831954956, "learning_rate": 1.5817042283544973e-05, "loss": 0.0099, "step": 10504 }, { "epoch": 0.5801303291362934, "grad_norm": 0.07486537843942642, "learning_rate": 1.581354415728334e-05, "loss": 0.0024, "step": 10505 }, { "epoch": 0.5801855533465872, "grad_norm": 3.0240750312805176, "learning_rate": 1.5810046164958354e-05, "loss": 0.1028, "step": 10506 }, { "epoch": 0.580240777556881, "grad_norm": 1.7567152976989746, "learning_rate": 1.5806548306681905e-05, "loss": 0.0432, "step": 10507 }, { "epoch": 0.5802960017671748, "grad_norm": 2.1524124145507812, "learning_rate": 1.580305058256593e-05, "loss": 0.0793, "step": 10508 }, { "epoch": 0.5803512259774686, "grad_norm": 1.5293760299682617, "learning_rate": 1.5799552992722305e-05, "loss": 0.0548, "step": 10509 }, { "epoch": 0.5804064501877623, "grad_norm": 3.805722236633301, "learning_rate": 1.5796055537262942e-05, "loss": 0.0937, "step": 10510 }, { "epoch": 0.5804616743980561, "grad_norm": 0.08664432168006897, "learning_rate": 1.5792558216299726e-05, "loss": 0.0027, "step": 10511 }, { "epoch": 0.5805168986083499, "grad_norm": 0.3568090796470642, "learning_rate": 1.5789061029944557e-05, "loss": 0.0078, "step": 10512 }, { "epoch": 0.5805721228186437, "grad_norm": 3.3133697509765625, "learning_rate": 1.5785563978309307e-05, "loss": 0.5624, "step": 10513 }, { "epoch": 0.5806273470289375, "grad_norm": 0.41340839862823486, "learning_rate": 1.5782067061505873e-05, "loss": 0.0133, "step": 10514 }, { "epoch": 0.5806825712392313, "grad_norm": 3.2041640281677246, "learning_rate": 1.5778570279646108e-05, "loss": 0.6204, "step": 10515 }, { "epoch": 0.5807377954495251, "grad_norm": 2.865557909011841, "learning_rate": 1.577507363284191e-05, "loss": 0.5367, "step": 10516 }, { "epoch": 0.5807930196598189, "grad_norm": 4.352612495422363, "learning_rate": 1.577157712120513e-05, "loss": 1.1706, "step": 10517 }, { "epoch": 0.5808482438701127, "grad_norm": 0.14798453450202942, "learning_rate": 1.5768080744847635e-05, "loss": 0.006, "step": 10518 }, { "epoch": 0.5809034680804065, "grad_norm": 0.24006770551204681, "learning_rate": 1.576458450388128e-05, "loss": 0.0062, "step": 10519 }, { "epoch": 0.5809586922907003, "grad_norm": 0.21549703180789948, "learning_rate": 1.5761088398417933e-05, "loss": 0.0062, "step": 10520 }, { "epoch": 0.581013916500994, "grad_norm": 3.1431148052215576, "learning_rate": 1.575759242856943e-05, "loss": 0.128, "step": 10521 }, { "epoch": 0.5810691407112878, "grad_norm": 2.8075575828552246, "learning_rate": 1.575409659444763e-05, "loss": 0.5482, "step": 10522 }, { "epoch": 0.5811243649215816, "grad_norm": 4.209105968475342, "learning_rate": 1.5750600896164353e-05, "loss": 0.4272, "step": 10523 }, { "epoch": 0.5811795891318754, "grad_norm": 2.5879855155944824, "learning_rate": 1.5747105333831467e-05, "loss": 0.1253, "step": 10524 }, { "epoch": 0.5812348133421692, "grad_norm": 0.015911083668470383, "learning_rate": 1.574360990756078e-05, "loss": 0.0005, "step": 10525 }, { "epoch": 0.581290037552463, "grad_norm": 1.969928503036499, "learning_rate": 1.5740114617464132e-05, "loss": 0.0761, "step": 10526 }, { "epoch": 0.5813452617627568, "grad_norm": 4.57798957824707, "learning_rate": 1.5736619463653343e-05, "loss": 0.7869, "step": 10527 }, { "epoch": 0.5814004859730506, "grad_norm": 0.024694522842764854, "learning_rate": 1.573312444624024e-05, "loss": 0.0007, "step": 10528 }, { "epoch": 0.5814557101833444, "grad_norm": 0.19510871171951294, "learning_rate": 1.5729629565336625e-05, "loss": 0.0051, "step": 10529 }, { "epoch": 0.5815109343936382, "grad_norm": 2.870792865753174, "learning_rate": 1.5726134821054326e-05, "loss": 0.3307, "step": 10530 }, { "epoch": 0.581566158603932, "grad_norm": 0.1859303116798401, "learning_rate": 1.5722640213505138e-05, "loss": 0.0026, "step": 10531 }, { "epoch": 0.5816213828142257, "grad_norm": 0.06912023574113846, "learning_rate": 1.5719145742800864e-05, "loss": 0.0016, "step": 10532 }, { "epoch": 0.5816766070245195, "grad_norm": 0.1486528515815735, "learning_rate": 1.5715651409053307e-05, "loss": 0.0039, "step": 10533 }, { "epoch": 0.5817318312348133, "grad_norm": 3.265303373336792, "learning_rate": 1.5712157212374254e-05, "loss": 0.2559, "step": 10534 }, { "epoch": 0.5817870554451071, "grad_norm": 0.1372213214635849, "learning_rate": 1.5708663152875504e-05, "loss": 0.0049, "step": 10535 }, { "epoch": 0.5818422796554009, "grad_norm": 0.3473510444164276, "learning_rate": 1.5705169230668832e-05, "loss": 0.0064, "step": 10536 }, { "epoch": 0.5818975038656947, "grad_norm": 3.036437749862671, "learning_rate": 1.570167544586603e-05, "loss": 0.2447, "step": 10537 }, { "epoch": 0.5819527280759885, "grad_norm": 0.02917955070734024, "learning_rate": 1.5698181798578857e-05, "loss": 0.0009, "step": 10538 }, { "epoch": 0.5820079522862823, "grad_norm": 0.015106014907360077, "learning_rate": 1.5694688288919108e-05, "loss": 0.0004, "step": 10539 }, { "epoch": 0.5820631764965761, "grad_norm": 0.1643768846988678, "learning_rate": 1.569119491699853e-05, "loss": 0.0063, "step": 10540 }, { "epoch": 0.5821184007068699, "grad_norm": 0.11286512017250061, "learning_rate": 1.5687701682928894e-05, "loss": 0.0033, "step": 10541 }, { "epoch": 0.5821736249171637, "grad_norm": 0.341026246547699, "learning_rate": 1.5684208586821952e-05, "loss": 0.0105, "step": 10542 }, { "epoch": 0.5822288491274574, "grad_norm": 0.25859612226486206, "learning_rate": 1.5680715628789472e-05, "loss": 0.0051, "step": 10543 }, { "epoch": 0.5822840733377512, "grad_norm": 0.13351909816265106, "learning_rate": 1.5677222808943193e-05, "loss": 0.0029, "step": 10544 }, { "epoch": 0.582339297548045, "grad_norm": 1.7443510293960571, "learning_rate": 1.5673730127394867e-05, "loss": 0.088, "step": 10545 }, { "epoch": 0.5823945217583388, "grad_norm": 0.07519818097352982, "learning_rate": 1.567023758425622e-05, "loss": 0.0015, "step": 10546 }, { "epoch": 0.5824497459686326, "grad_norm": 0.11416693776845932, "learning_rate": 1.5666745179639012e-05, "loss": 0.0034, "step": 10547 }, { "epoch": 0.5825049701789264, "grad_norm": 0.0926273912191391, "learning_rate": 1.5663252913654953e-05, "loss": 0.0032, "step": 10548 }, { "epoch": 0.5825601943892202, "grad_norm": 0.22308394312858582, "learning_rate": 1.5659760786415782e-05, "loss": 0.0076, "step": 10549 }, { "epoch": 0.582615418599514, "grad_norm": 3.5973803997039795, "learning_rate": 1.5656268798033216e-05, "loss": 0.4362, "step": 10550 }, { "epoch": 0.5826706428098078, "grad_norm": 1.9922547340393066, "learning_rate": 1.5652776948618982e-05, "loss": 0.5552, "step": 10551 }, { "epoch": 0.5827258670201017, "grad_norm": 0.12476544082164764, "learning_rate": 1.5649285238284786e-05, "loss": 0.0033, "step": 10552 }, { "epoch": 0.5827810912303955, "grad_norm": 2.220954656600952, "learning_rate": 1.564579366714235e-05, "loss": 0.043, "step": 10553 }, { "epoch": 0.5828363154406891, "grad_norm": 2.8474042415618896, "learning_rate": 1.5642302235303354e-05, "loss": 0.2989, "step": 10554 }, { "epoch": 0.582891539650983, "grad_norm": 0.011118943803012371, "learning_rate": 1.563881094287953e-05, "loss": 0.0004, "step": 10555 }, { "epoch": 0.5829467638612768, "grad_norm": 1.1114197969436646, "learning_rate": 1.5635319789982552e-05, "loss": 0.0222, "step": 10556 }, { "epoch": 0.5830019880715706, "grad_norm": 0.01925744116306305, "learning_rate": 1.5631828776724125e-05, "loss": 0.0003, "step": 10557 }, { "epoch": 0.5830572122818644, "grad_norm": 1.0128508806228638, "learning_rate": 1.5628337903215923e-05, "loss": 0.031, "step": 10558 }, { "epoch": 0.5831124364921582, "grad_norm": 2.2830801010131836, "learning_rate": 1.5624847169569645e-05, "loss": 0.3444, "step": 10559 }, { "epoch": 0.583167660702452, "grad_norm": 0.05891421437263489, "learning_rate": 1.5621356575896954e-05, "loss": 0.0016, "step": 10560 }, { "epoch": 0.5832228849127458, "grad_norm": 3.9331960678100586, "learning_rate": 1.5617866122309544e-05, "loss": 0.627, "step": 10561 }, { "epoch": 0.5832781091230396, "grad_norm": 2.978095769882202, "learning_rate": 1.561437580891906e-05, "loss": 0.156, "step": 10562 }, { "epoch": 0.5833333333333334, "grad_norm": 0.3085517883300781, "learning_rate": 1.5610885635837187e-05, "loss": 0.0094, "step": 10563 }, { "epoch": 0.5833885575436272, "grad_norm": 1.105780005455017, "learning_rate": 1.5607395603175572e-05, "loss": 0.0254, "step": 10564 }, { "epoch": 0.5834437817539209, "grad_norm": 4.414437770843506, "learning_rate": 1.5603905711045882e-05, "loss": 0.0364, "step": 10565 }, { "epoch": 0.5834990059642147, "grad_norm": 0.04348866641521454, "learning_rate": 1.5600415959559755e-05, "loss": 0.002, "step": 10566 }, { "epoch": 0.5835542301745085, "grad_norm": 2.6640312671661377, "learning_rate": 1.5596926348828856e-05, "loss": 0.0897, "step": 10567 }, { "epoch": 0.5836094543848023, "grad_norm": 0.7110207676887512, "learning_rate": 1.559343687896481e-05, "loss": 0.0201, "step": 10568 }, { "epoch": 0.5836646785950961, "grad_norm": 1.4850165843963623, "learning_rate": 1.5589947550079272e-05, "loss": 0.0705, "step": 10569 }, { "epoch": 0.5837199028053899, "grad_norm": 0.26695072650909424, "learning_rate": 1.5586458362283854e-05, "loss": 0.0049, "step": 10570 }, { "epoch": 0.5837751270156837, "grad_norm": 0.4140503704547882, "learning_rate": 1.5582969315690214e-05, "loss": 0.0151, "step": 10571 }, { "epoch": 0.5838303512259775, "grad_norm": 0.36534586548805237, "learning_rate": 1.557948041040995e-05, "loss": 0.0157, "step": 10572 }, { "epoch": 0.5838855754362713, "grad_norm": 0.07446620613336563, "learning_rate": 1.5575991646554696e-05, "loss": 0.0023, "step": 10573 }, { "epoch": 0.5839407996465651, "grad_norm": 6.764693260192871, "learning_rate": 1.557250302423606e-05, "loss": 1.4562, "step": 10574 }, { "epoch": 0.5839960238568589, "grad_norm": 0.15611502528190613, "learning_rate": 1.556901454356566e-05, "loss": 0.0061, "step": 10575 }, { "epoch": 0.5840512480671527, "grad_norm": 1.622649908065796, "learning_rate": 1.5565526204655096e-05, "loss": 0.3364, "step": 10576 }, { "epoch": 0.5841064722774464, "grad_norm": 3.330962896347046, "learning_rate": 1.5562038007615976e-05, "loss": 0.6613, "step": 10577 }, { "epoch": 0.5841616964877402, "grad_norm": 0.24702796339988708, "learning_rate": 1.555854995255989e-05, "loss": 0.0087, "step": 10578 }, { "epoch": 0.584216920698034, "grad_norm": 1.5173887014389038, "learning_rate": 1.5555062039598447e-05, "loss": 0.226, "step": 10579 }, { "epoch": 0.5842721449083278, "grad_norm": 0.004104800056666136, "learning_rate": 1.5551574268843213e-05, "loss": 0.0001, "step": 10580 }, { "epoch": 0.5843273691186216, "grad_norm": 2.1906094551086426, "learning_rate": 1.5548086640405785e-05, "loss": 0.076, "step": 10581 }, { "epoch": 0.5843825933289154, "grad_norm": 0.6754757165908813, "learning_rate": 1.554459915439774e-05, "loss": 0.0205, "step": 10582 }, { "epoch": 0.5844378175392092, "grad_norm": 1.5087080001831055, "learning_rate": 1.554111181093065e-05, "loss": 0.0551, "step": 10583 }, { "epoch": 0.584493041749503, "grad_norm": 0.03866561874747276, "learning_rate": 1.5537624610116088e-05, "loss": 0.0011, "step": 10584 }, { "epoch": 0.5845482659597968, "grad_norm": 3.2439255714416504, "learning_rate": 1.553413755206562e-05, "loss": 0.2202, "step": 10585 }, { "epoch": 0.5846034901700906, "grad_norm": 0.11727756261825562, "learning_rate": 1.5530650636890802e-05, "loss": 0.0033, "step": 10586 }, { "epoch": 0.5846587143803844, "grad_norm": 0.22076401114463806, "learning_rate": 1.55271638647032e-05, "loss": 0.0047, "step": 10587 }, { "epoch": 0.5847139385906781, "grad_norm": 1.622336983680725, "learning_rate": 1.5523677235614353e-05, "loss": 0.092, "step": 10588 }, { "epoch": 0.5847691628009719, "grad_norm": 0.08658262342214584, "learning_rate": 1.552019074973582e-05, "loss": 0.0018, "step": 10589 }, { "epoch": 0.5848243870112657, "grad_norm": 4.881964206695557, "learning_rate": 1.551670440717914e-05, "loss": 0.5382, "step": 10590 }, { "epoch": 0.5848796112215595, "grad_norm": 0.020066741853952408, "learning_rate": 1.551321820805584e-05, "loss": 0.0006, "step": 10591 }, { "epoch": 0.5849348354318533, "grad_norm": 2.595529794692993, "learning_rate": 1.5509732152477473e-05, "loss": 0.3278, "step": 10592 }, { "epoch": 0.5849900596421471, "grad_norm": 0.6605741381645203, "learning_rate": 1.5506246240555548e-05, "loss": 0.0186, "step": 10593 }, { "epoch": 0.5850452838524409, "grad_norm": 0.12676869332790375, "learning_rate": 1.550276047240161e-05, "loss": 0.003, "step": 10594 }, { "epoch": 0.5851005080627347, "grad_norm": 0.08987416326999664, "learning_rate": 1.5499274848127156e-05, "loss": 0.0028, "step": 10595 }, { "epoch": 0.5851557322730285, "grad_norm": 3.028705358505249, "learning_rate": 1.549578936784372e-05, "loss": 0.2858, "step": 10596 }, { "epoch": 0.5852109564833223, "grad_norm": 0.4082188308238983, "learning_rate": 1.54923040316628e-05, "loss": 0.0114, "step": 10597 }, { "epoch": 0.5852661806936161, "grad_norm": 2.698310136795044, "learning_rate": 1.5488818839695913e-05, "loss": 0.1824, "step": 10598 }, { "epoch": 0.5853214049039098, "grad_norm": 3.0719048976898193, "learning_rate": 1.548533379205455e-05, "loss": 0.2024, "step": 10599 }, { "epoch": 0.5853766291142036, "grad_norm": 0.367120623588562, "learning_rate": 1.5481848888850218e-05, "loss": 0.0089, "step": 10600 }, { "epoch": 0.5854318533244974, "grad_norm": 0.21585601568222046, "learning_rate": 1.547836413019439e-05, "loss": 0.0031, "step": 10601 }, { "epoch": 0.5854870775347912, "grad_norm": 4.580939769744873, "learning_rate": 1.5474879516198577e-05, "loss": 0.4079, "step": 10602 }, { "epoch": 0.585542301745085, "grad_norm": 4.683459281921387, "learning_rate": 1.5471395046974244e-05, "loss": 0.4315, "step": 10603 }, { "epoch": 0.5855975259553788, "grad_norm": 0.20132212340831757, "learning_rate": 1.5467910722632883e-05, "loss": 0.0055, "step": 10604 }, { "epoch": 0.5856527501656726, "grad_norm": 0.679207444190979, "learning_rate": 1.546442654328595e-05, "loss": 0.0147, "step": 10605 }, { "epoch": 0.5857079743759664, "grad_norm": 0.08825241029262543, "learning_rate": 1.5460942509044936e-05, "loss": 0.0017, "step": 10606 }, { "epoch": 0.5857631985862602, "grad_norm": 1.4300587177276611, "learning_rate": 1.545745862002128e-05, "loss": 0.022, "step": 10607 }, { "epoch": 0.585818422796554, "grad_norm": 0.31890735030174255, "learning_rate": 1.5453974876326464e-05, "loss": 0.0064, "step": 10608 }, { "epoch": 0.5858736470068479, "grad_norm": 2.560002565383911, "learning_rate": 1.545049127807193e-05, "loss": 0.2724, "step": 10609 }, { "epoch": 0.5859288712171415, "grad_norm": 0.48893430829048157, "learning_rate": 1.544700782536914e-05, "loss": 0.0106, "step": 10610 }, { "epoch": 0.5859840954274353, "grad_norm": 0.14317891001701355, "learning_rate": 1.544352451832952e-05, "loss": 0.0052, "step": 10611 }, { "epoch": 0.5860393196377292, "grad_norm": 3.3919906616210938, "learning_rate": 1.5440041357064533e-05, "loss": 0.6464, "step": 10612 }, { "epoch": 0.586094543848023, "grad_norm": 0.5608571171760559, "learning_rate": 1.5436558341685595e-05, "loss": 0.0139, "step": 10613 }, { "epoch": 0.5861497680583168, "grad_norm": 4.372920513153076, "learning_rate": 1.5433075472304153e-05, "loss": 0.9077, "step": 10614 }, { "epoch": 0.5862049922686106, "grad_norm": 0.010317834094166756, "learning_rate": 1.5429592749031622e-05, "loss": 0.0005, "step": 10615 }, { "epoch": 0.5862602164789044, "grad_norm": 0.2717418968677521, "learning_rate": 1.5426110171979437e-05, "loss": 0.0068, "step": 10616 }, { "epoch": 0.5863154406891982, "grad_norm": 0.016626613214612007, "learning_rate": 1.5422627741259004e-05, "loss": 0.0004, "step": 10617 }, { "epoch": 0.586370664899492, "grad_norm": 0.5068783164024353, "learning_rate": 1.541914545698175e-05, "loss": 0.0089, "step": 10618 }, { "epoch": 0.5864258891097858, "grad_norm": 0.13154976069927216, "learning_rate": 1.5415663319259065e-05, "loss": 0.0027, "step": 10619 }, { "epoch": 0.5864811133200796, "grad_norm": 1.5837831497192383, "learning_rate": 1.5412181328202366e-05, "loss": 0.1832, "step": 10620 }, { "epoch": 0.5865363375303733, "grad_norm": 2.0018553733825684, "learning_rate": 1.5408699483923043e-05, "loss": 0.2307, "step": 10621 }, { "epoch": 0.5865915617406671, "grad_norm": 0.580795407295227, "learning_rate": 1.5405217786532497e-05, "loss": 0.021, "step": 10622 }, { "epoch": 0.5866467859509609, "grad_norm": 1.948785424232483, "learning_rate": 1.5401736236142114e-05, "loss": 0.1789, "step": 10623 }, { "epoch": 0.5867020101612547, "grad_norm": 0.028729340061545372, "learning_rate": 1.539825483286328e-05, "loss": 0.0008, "step": 10624 }, { "epoch": 0.5867572343715485, "grad_norm": 0.061869312077760696, "learning_rate": 1.539477357680737e-05, "loss": 0.0019, "step": 10625 }, { "epoch": 0.5868124585818423, "grad_norm": 0.4375472664833069, "learning_rate": 1.5391292468085773e-05, "loss": 0.0116, "step": 10626 }, { "epoch": 0.5868676827921361, "grad_norm": 0.7707841992378235, "learning_rate": 1.538781150680984e-05, "loss": 0.0207, "step": 10627 }, { "epoch": 0.5869229070024299, "grad_norm": 0.09930086880922318, "learning_rate": 1.538433069309096e-05, "loss": 0.0027, "step": 10628 }, { "epoch": 0.5869781312127237, "grad_norm": 4.189327716827393, "learning_rate": 1.538085002704047e-05, "loss": 0.6074, "step": 10629 }, { "epoch": 0.5870333554230175, "grad_norm": 0.9657450318336487, "learning_rate": 1.537736950876974e-05, "loss": 0.031, "step": 10630 }, { "epoch": 0.5870885796333113, "grad_norm": 2.6655232906341553, "learning_rate": 1.5373889138390122e-05, "loss": 0.1466, "step": 10631 }, { "epoch": 0.587143803843605, "grad_norm": 0.1236194297671318, "learning_rate": 1.537040891601296e-05, "loss": 0.0044, "step": 10632 }, { "epoch": 0.5871990280538988, "grad_norm": 4.027867794036865, "learning_rate": 1.5366928841749593e-05, "loss": 0.2921, "step": 10633 }, { "epoch": 0.5872542522641926, "grad_norm": 0.2904379665851593, "learning_rate": 1.5363448915711372e-05, "loss": 0.006, "step": 10634 }, { "epoch": 0.5873094764744864, "grad_norm": 0.07903596758842468, "learning_rate": 1.5359969138009606e-05, "loss": 0.0025, "step": 10635 }, { "epoch": 0.5873647006847802, "grad_norm": 0.3448208272457123, "learning_rate": 1.535648950875565e-05, "loss": 0.01, "step": 10636 }, { "epoch": 0.587419924895074, "grad_norm": 1.4680005311965942, "learning_rate": 1.5353010028060803e-05, "loss": 0.0877, "step": 10637 }, { "epoch": 0.5874751491053678, "grad_norm": 0.065777488052845, "learning_rate": 1.5349530696036403e-05, "loss": 0.0022, "step": 10638 }, { "epoch": 0.5875303733156616, "grad_norm": 3.6701290607452393, "learning_rate": 1.5346051512793748e-05, "loss": 0.0534, "step": 10639 }, { "epoch": 0.5875855975259554, "grad_norm": 5.307991027832031, "learning_rate": 1.534257247844416e-05, "loss": 0.7933, "step": 10640 }, { "epoch": 0.5876408217362492, "grad_norm": 4.392944812774658, "learning_rate": 1.5339093593098935e-05, "loss": 0.2257, "step": 10641 }, { "epoch": 0.587696045946543, "grad_norm": 0.022953202947974205, "learning_rate": 1.533561485686938e-05, "loss": 0.001, "step": 10642 }, { "epoch": 0.5877512701568367, "grad_norm": 0.06971725076436996, "learning_rate": 1.5332136269866774e-05, "loss": 0.0028, "step": 10643 }, { "epoch": 0.5878064943671305, "grad_norm": 0.12448018044233322, "learning_rate": 1.532865783220243e-05, "loss": 0.0033, "step": 10644 }, { "epoch": 0.5878617185774243, "grad_norm": 0.011497316882014275, "learning_rate": 1.532517954398761e-05, "loss": 0.0004, "step": 10645 }, { "epoch": 0.5879169427877181, "grad_norm": 1.145828127861023, "learning_rate": 1.5321701405333613e-05, "loss": 0.0431, "step": 10646 }, { "epoch": 0.5879721669980119, "grad_norm": 0.32217633724212646, "learning_rate": 1.53182234163517e-05, "loss": 0.007, "step": 10647 }, { "epoch": 0.5880273912083057, "grad_norm": 4.336891174316406, "learning_rate": 1.5314745577153153e-05, "loss": 0.0299, "step": 10648 }, { "epoch": 0.5880826154185995, "grad_norm": 0.01700884848833084, "learning_rate": 1.531126788784923e-05, "loss": 0.0006, "step": 10649 }, { "epoch": 0.5881378396288933, "grad_norm": 0.3796338737010956, "learning_rate": 1.5307790348551204e-05, "loss": 0.0119, "step": 10650 }, { "epoch": 0.5881930638391871, "grad_norm": 0.1877320557832718, "learning_rate": 1.5304312959370317e-05, "loss": 0.0051, "step": 10651 }, { "epoch": 0.5882482880494809, "grad_norm": 2.732002019882202, "learning_rate": 1.5300835720417825e-05, "loss": 0.0462, "step": 10652 }, { "epoch": 0.5883035122597747, "grad_norm": 0.3076063096523285, "learning_rate": 1.5297358631804978e-05, "loss": 0.0067, "step": 10653 }, { "epoch": 0.5883587364700685, "grad_norm": 0.0027645810041576624, "learning_rate": 1.529388169364301e-05, "loss": 0.0001, "step": 10654 }, { "epoch": 0.5884139606803622, "grad_norm": 0.014632855542004108, "learning_rate": 1.5290404906043174e-05, "loss": 0.0005, "step": 10655 }, { "epoch": 0.588469184890656, "grad_norm": 0.4035555124282837, "learning_rate": 1.5286928269116686e-05, "loss": 0.0086, "step": 10656 }, { "epoch": 0.5885244091009498, "grad_norm": 0.0157344751060009, "learning_rate": 1.5283451782974786e-05, "loss": 0.0004, "step": 10657 }, { "epoch": 0.5885796333112436, "grad_norm": 4.0604567527771, "learning_rate": 1.527997544772868e-05, "loss": 0.9089, "step": 10658 }, { "epoch": 0.5886348575215374, "grad_norm": 0.5171937942504883, "learning_rate": 1.527649926348961e-05, "loss": 0.0137, "step": 10659 }, { "epoch": 0.5886900817318312, "grad_norm": 5.498988628387451, "learning_rate": 1.5273023230368768e-05, "loss": 0.5127, "step": 10660 }, { "epoch": 0.588745305942125, "grad_norm": 0.04248851165175438, "learning_rate": 1.5269547348477373e-05, "loss": 0.0017, "step": 10661 }, { "epoch": 0.5888005301524188, "grad_norm": 1.663989543914795, "learning_rate": 1.5266071617926622e-05, "loss": 0.0849, "step": 10662 }, { "epoch": 0.5888557543627126, "grad_norm": 0.08277446031570435, "learning_rate": 1.526259603882772e-05, "loss": 0.002, "step": 10663 }, { "epoch": 0.5889109785730064, "grad_norm": 0.5026265382766724, "learning_rate": 1.5259120611291852e-05, "loss": 0.0174, "step": 10664 }, { "epoch": 0.5889662027833003, "grad_norm": 2.2798333168029785, "learning_rate": 1.5255645335430224e-05, "loss": 0.6085, "step": 10665 }, { "epoch": 0.5890214269935939, "grad_norm": 2.9996776580810547, "learning_rate": 1.5252170211353994e-05, "loss": 0.514, "step": 10666 }, { "epoch": 0.5890766512038877, "grad_norm": 0.6893577575683594, "learning_rate": 1.5248695239174369e-05, "loss": 0.0342, "step": 10667 }, { "epoch": 0.5891318754141815, "grad_norm": 2.112952470779419, "learning_rate": 1.52452204190025e-05, "loss": 0.0334, "step": 10668 }, { "epoch": 0.5891870996244754, "grad_norm": 0.0014744065701961517, "learning_rate": 1.524174575094957e-05, "loss": 0.0, "step": 10669 }, { "epoch": 0.5892423238347692, "grad_norm": 0.07241209596395493, "learning_rate": 1.5238271235126736e-05, "loss": 0.0017, "step": 10670 }, { "epoch": 0.589297548045063, "grad_norm": 0.817794919013977, "learning_rate": 1.5234796871645166e-05, "loss": 0.0206, "step": 10671 }, { "epoch": 0.5893527722553568, "grad_norm": 0.7470222115516663, "learning_rate": 1.5231322660616006e-05, "loss": 0.0168, "step": 10672 }, { "epoch": 0.5894079964656506, "grad_norm": 0.197539821267128, "learning_rate": 1.5227848602150416e-05, "loss": 0.0058, "step": 10673 }, { "epoch": 0.5894632206759444, "grad_norm": 1.7645376920700073, "learning_rate": 1.5224374696359525e-05, "loss": 0.1216, "step": 10674 }, { "epoch": 0.5895184448862382, "grad_norm": 0.010354582220315933, "learning_rate": 1.5220900943354495e-05, "loss": 0.0004, "step": 10675 }, { "epoch": 0.589573669096532, "grad_norm": 4.036314010620117, "learning_rate": 1.521742734324644e-05, "loss": 0.1405, "step": 10676 }, { "epoch": 0.5896288933068257, "grad_norm": 3.1752493381500244, "learning_rate": 1.5213953896146505e-05, "loss": 0.2611, "step": 10677 }, { "epoch": 0.5896841175171195, "grad_norm": 0.09059646725654602, "learning_rate": 1.5210480602165805e-05, "loss": 0.0027, "step": 10678 }, { "epoch": 0.5897393417274133, "grad_norm": 0.43783068656921387, "learning_rate": 1.520700746141547e-05, "loss": 0.0129, "step": 10679 }, { "epoch": 0.5897945659377071, "grad_norm": 0.025543134659528732, "learning_rate": 1.5203534474006607e-05, "loss": 0.0008, "step": 10680 }, { "epoch": 0.5898497901480009, "grad_norm": 1.2194172143936157, "learning_rate": 1.520006164005034e-05, "loss": 0.0344, "step": 10681 }, { "epoch": 0.5899050143582947, "grad_norm": 2.45475172996521, "learning_rate": 1.5196588959657755e-05, "loss": 0.3965, "step": 10682 }, { "epoch": 0.5899602385685885, "grad_norm": 0.06311221420764923, "learning_rate": 1.5193116432939973e-05, "loss": 0.0007, "step": 10683 }, { "epoch": 0.5900154627788823, "grad_norm": 0.010630184784531593, "learning_rate": 1.5189644060008076e-05, "loss": 0.0004, "step": 10684 }, { "epoch": 0.5900706869891761, "grad_norm": 0.01793273165822029, "learning_rate": 1.5186171840973161e-05, "loss": 0.0005, "step": 10685 }, { "epoch": 0.5901259111994699, "grad_norm": 0.02612990513443947, "learning_rate": 1.518269977594631e-05, "loss": 0.0009, "step": 10686 }, { "epoch": 0.5901811354097637, "grad_norm": 7.582857608795166, "learning_rate": 1.5179227865038612e-05, "loss": 1.0764, "step": 10687 }, { "epoch": 0.5902363596200574, "grad_norm": 0.34712377190589905, "learning_rate": 1.5175756108361134e-05, "loss": 0.0081, "step": 10688 }, { "epoch": 0.5902915838303512, "grad_norm": 0.5728552937507629, "learning_rate": 1.5172284506024962e-05, "loss": 0.0113, "step": 10689 }, { "epoch": 0.590346808040645, "grad_norm": 5.406423568725586, "learning_rate": 1.5168813058141138e-05, "loss": 2.2028, "step": 10690 }, { "epoch": 0.5904020322509388, "grad_norm": 2.507669448852539, "learning_rate": 1.5165341764820754e-05, "loss": 0.1492, "step": 10691 }, { "epoch": 0.5904572564612326, "grad_norm": 0.07663868367671967, "learning_rate": 1.516187062617484e-05, "loss": 0.0015, "step": 10692 }, { "epoch": 0.5905124806715264, "grad_norm": 6.173920154571533, "learning_rate": 1.5158399642314462e-05, "loss": 0.5867, "step": 10693 }, { "epoch": 0.5905677048818202, "grad_norm": 2.5141875743865967, "learning_rate": 1.5154928813350658e-05, "loss": 0.0898, "step": 10694 }, { "epoch": 0.590622929092114, "grad_norm": 1.336037278175354, "learning_rate": 1.515145813939448e-05, "loss": 0.0566, "step": 10695 }, { "epoch": 0.5906781533024078, "grad_norm": 0.00759529322385788, "learning_rate": 1.5147987620556955e-05, "loss": 0.0002, "step": 10696 }, { "epoch": 0.5907333775127016, "grad_norm": 5.9652557373046875, "learning_rate": 1.5144517256949122e-05, "loss": 1.2127, "step": 10697 }, { "epoch": 0.5907886017229954, "grad_norm": 1.7926702499389648, "learning_rate": 1.5141047048682002e-05, "loss": 0.0831, "step": 10698 }, { "epoch": 0.5908438259332891, "grad_norm": 4.465991020202637, "learning_rate": 1.5137576995866628e-05, "loss": 1.1059, "step": 10699 }, { "epoch": 0.5908990501435829, "grad_norm": 2.6323041915893555, "learning_rate": 1.5134107098613999e-05, "loss": 0.1901, "step": 10700 }, { "epoch": 0.5909542743538767, "grad_norm": 5.109724998474121, "learning_rate": 1.5130637357035143e-05, "loss": 1.3486, "step": 10701 }, { "epoch": 0.5910094985641705, "grad_norm": 0.03887313976883888, "learning_rate": 1.5127167771241055e-05, "loss": 0.0011, "step": 10702 }, { "epoch": 0.5910647227744643, "grad_norm": 0.058394283056259155, "learning_rate": 1.5123698341342748e-05, "loss": 0.0016, "step": 10703 }, { "epoch": 0.5911199469847581, "grad_norm": 5.124629020690918, "learning_rate": 1.5120229067451206e-05, "loss": 1.1759, "step": 10704 }, { "epoch": 0.5911751711950519, "grad_norm": 2.4583961963653564, "learning_rate": 1.5116759949677433e-05, "loss": 0.1465, "step": 10705 }, { "epoch": 0.5912303954053457, "grad_norm": 0.028272222727537155, "learning_rate": 1.511329098813241e-05, "loss": 0.001, "step": 10706 }, { "epoch": 0.5912856196156395, "grad_norm": 0.009833795949816704, "learning_rate": 1.5109822182927127e-05, "loss": 0.0003, "step": 10707 }, { "epoch": 0.5913408438259333, "grad_norm": 0.6317005753517151, "learning_rate": 1.5106353534172544e-05, "loss": 0.0195, "step": 10708 }, { "epoch": 0.5913960680362271, "grad_norm": 4.416604042053223, "learning_rate": 1.5102885041979649e-05, "loss": 1.3285, "step": 10709 }, { "epoch": 0.5914512922465208, "grad_norm": 0.01778559572994709, "learning_rate": 1.5099416706459402e-05, "loss": 0.0007, "step": 10710 }, { "epoch": 0.5915065164568146, "grad_norm": 0.09843578934669495, "learning_rate": 1.5095948527722763e-05, "loss": 0.0036, "step": 10711 }, { "epoch": 0.5915617406671084, "grad_norm": 4.445732593536377, "learning_rate": 1.5092480505880697e-05, "loss": 1.0284, "step": 10712 }, { "epoch": 0.5916169648774022, "grad_norm": 0.3585340678691864, "learning_rate": 1.5089012641044143e-05, "loss": 0.0111, "step": 10713 }, { "epoch": 0.591672189087696, "grad_norm": 0.34629273414611816, "learning_rate": 1.5085544933324065e-05, "loss": 0.0101, "step": 10714 }, { "epoch": 0.5917274132979898, "grad_norm": 3.0823073387145996, "learning_rate": 1.5082077382831389e-05, "loss": 0.9768, "step": 10715 }, { "epoch": 0.5917826375082836, "grad_norm": 3.313514471054077, "learning_rate": 1.507860998967706e-05, "loss": 0.8255, "step": 10716 }, { "epoch": 0.5918378617185774, "grad_norm": 0.8237661123275757, "learning_rate": 1.5075142753972004e-05, "loss": 0.0268, "step": 10717 }, { "epoch": 0.5918930859288712, "grad_norm": 3.5366806983947754, "learning_rate": 1.5071675675827158e-05, "loss": 0.5907, "step": 10718 }, { "epoch": 0.591948310139165, "grad_norm": 7.766000747680664, "learning_rate": 1.5068208755353433e-05, "loss": 1.1719, "step": 10719 }, { "epoch": 0.5920035343494588, "grad_norm": 0.02001596800982952, "learning_rate": 1.5064741992661755e-05, "loss": 0.0006, "step": 10720 }, { "epoch": 0.5920587585597525, "grad_norm": 1.8914625644683838, "learning_rate": 1.5061275387863021e-05, "loss": 0.4438, "step": 10721 }, { "epoch": 0.5921139827700463, "grad_norm": 0.5048168301582336, "learning_rate": 1.5057808941068162e-05, "loss": 0.0191, "step": 10722 }, { "epoch": 0.5921692069803401, "grad_norm": 1.6078579425811768, "learning_rate": 1.5054342652388051e-05, "loss": 0.045, "step": 10723 }, { "epoch": 0.592224431190634, "grad_norm": 0.893701434135437, "learning_rate": 1.5050876521933609e-05, "loss": 0.0192, "step": 10724 }, { "epoch": 0.5922796554009278, "grad_norm": 4.71257209777832, "learning_rate": 1.5047410549815706e-05, "loss": 1.4894, "step": 10725 }, { "epoch": 0.5923348796112216, "grad_norm": 1.4167996644973755, "learning_rate": 1.5043944736145246e-05, "loss": 0.1355, "step": 10726 }, { "epoch": 0.5923901038215154, "grad_norm": 0.18616721034049988, "learning_rate": 1.50404790810331e-05, "loss": 0.0056, "step": 10727 }, { "epoch": 0.5924453280318092, "grad_norm": 6.116595268249512, "learning_rate": 1.503701358459015e-05, "loss": 1.6939, "step": 10728 }, { "epoch": 0.592500552242103, "grad_norm": 3.5008022785186768, "learning_rate": 1.503354824692726e-05, "loss": 0.3664, "step": 10729 }, { "epoch": 0.5925557764523968, "grad_norm": 2.5281081199645996, "learning_rate": 1.503008306815531e-05, "loss": 0.2585, "step": 10730 }, { "epoch": 0.5926110006626906, "grad_norm": 1.9741413593292236, "learning_rate": 1.5026618048385141e-05, "loss": 0.118, "step": 10731 }, { "epoch": 0.5926662248729844, "grad_norm": 2.3777711391448975, "learning_rate": 1.5023153187727626e-05, "loss": 0.1909, "step": 10732 }, { "epoch": 0.5927214490832781, "grad_norm": 2.598018169403076, "learning_rate": 1.5019688486293604e-05, "loss": 0.7123, "step": 10733 }, { "epoch": 0.5927766732935719, "grad_norm": 0.12054271250963211, "learning_rate": 1.501622394419393e-05, "loss": 0.0023, "step": 10734 }, { "epoch": 0.5928318975038657, "grad_norm": 0.9563707113265991, "learning_rate": 1.5012759561539434e-05, "loss": 0.0241, "step": 10735 }, { "epoch": 0.5928871217141595, "grad_norm": 4.077694892883301, "learning_rate": 1.5009295338440964e-05, "loss": 0.2576, "step": 10736 }, { "epoch": 0.5929423459244533, "grad_norm": 3.805466413497925, "learning_rate": 1.5005831275009339e-05, "loss": 0.1173, "step": 10737 }, { "epoch": 0.5929975701347471, "grad_norm": 3.3008503913879395, "learning_rate": 1.5002367371355399e-05, "loss": 0.1814, "step": 10738 }, { "epoch": 0.5930527943450409, "grad_norm": 2.962373971939087, "learning_rate": 1.4998903627589943e-05, "loss": 0.1723, "step": 10739 }, { "epoch": 0.5931080185553347, "grad_norm": 0.08548460900783539, "learning_rate": 1.4995440043823806e-05, "loss": 0.0021, "step": 10740 }, { "epoch": 0.5931632427656285, "grad_norm": 0.011941908858716488, "learning_rate": 1.499197662016778e-05, "loss": 0.0002, "step": 10741 }, { "epoch": 0.5932184669759223, "grad_norm": 3.483896017074585, "learning_rate": 1.4988513356732686e-05, "loss": 0.5849, "step": 10742 }, { "epoch": 0.5932736911862161, "grad_norm": 2.1939711570739746, "learning_rate": 1.4985050253629315e-05, "loss": 0.0996, "step": 10743 }, { "epoch": 0.5933289153965098, "grad_norm": 1.797414779663086, "learning_rate": 1.4981587310968463e-05, "loss": 0.1475, "step": 10744 }, { "epoch": 0.5933841396068036, "grad_norm": 3.391948699951172, "learning_rate": 1.4978124528860918e-05, "loss": 0.4668, "step": 10745 }, { "epoch": 0.5934393638170974, "grad_norm": 3.1458888053894043, "learning_rate": 1.4974661907417476e-05, "loss": 1.3483, "step": 10746 }, { "epoch": 0.5934945880273912, "grad_norm": 6.5761566162109375, "learning_rate": 1.497119944674889e-05, "loss": 1.7939, "step": 10747 }, { "epoch": 0.593549812237685, "grad_norm": 0.01952989213168621, "learning_rate": 1.4967737146965965e-05, "loss": 0.0006, "step": 10748 }, { "epoch": 0.5936050364479788, "grad_norm": 0.9516245722770691, "learning_rate": 1.4964275008179443e-05, "loss": 0.007, "step": 10749 }, { "epoch": 0.5936602606582726, "grad_norm": 4.7100830078125, "learning_rate": 1.4960813030500108e-05, "loss": 0.1127, "step": 10750 }, { "epoch": 0.5937154848685664, "grad_norm": 3.776731014251709, "learning_rate": 1.4957351214038705e-05, "loss": 0.3659, "step": 10751 }, { "epoch": 0.5937707090788602, "grad_norm": 1.6175427436828613, "learning_rate": 1.4953889558905994e-05, "loss": 0.0383, "step": 10752 }, { "epoch": 0.593825933289154, "grad_norm": 3.5492639541625977, "learning_rate": 1.495042806521272e-05, "loss": 0.3478, "step": 10753 }, { "epoch": 0.5938811574994478, "grad_norm": 0.017938699573278427, "learning_rate": 1.4946966733069634e-05, "loss": 0.0005, "step": 10754 }, { "epoch": 0.5939363817097415, "grad_norm": 1.3707339763641357, "learning_rate": 1.4943505562587458e-05, "loss": 0.0711, "step": 10755 }, { "epoch": 0.5939916059200353, "grad_norm": 0.7162588238716125, "learning_rate": 1.4940044553876946e-05, "loss": 0.0219, "step": 10756 }, { "epoch": 0.5940468301303291, "grad_norm": 0.5927386283874512, "learning_rate": 1.4936583707048803e-05, "loss": 0.0102, "step": 10757 }, { "epoch": 0.5941020543406229, "grad_norm": 1.953547477722168, "learning_rate": 1.4933123022213768e-05, "loss": 0.0553, "step": 10758 }, { "epoch": 0.5941572785509167, "grad_norm": 0.008386272005736828, "learning_rate": 1.4929662499482549e-05, "loss": 0.0002, "step": 10759 }, { "epoch": 0.5942125027612105, "grad_norm": 1.9272774457931519, "learning_rate": 1.4926202138965863e-05, "loss": 0.2969, "step": 10760 }, { "epoch": 0.5942677269715043, "grad_norm": 0.8642370104789734, "learning_rate": 1.4922741940774415e-05, "loss": 0.0134, "step": 10761 }, { "epoch": 0.5943229511817981, "grad_norm": 0.15165361762046814, "learning_rate": 1.491928190501891e-05, "loss": 0.0033, "step": 10762 }, { "epoch": 0.5943781753920919, "grad_norm": 0.8345507383346558, "learning_rate": 1.491582203181003e-05, "loss": 0.0127, "step": 10763 }, { "epoch": 0.5944333996023857, "grad_norm": 0.038094695657491684, "learning_rate": 1.4912362321258491e-05, "loss": 0.0012, "step": 10764 }, { "epoch": 0.5944886238126795, "grad_norm": 0.017728818580508232, "learning_rate": 1.4908902773474959e-05, "loss": 0.0006, "step": 10765 }, { "epoch": 0.5945438480229732, "grad_norm": 0.9078773856163025, "learning_rate": 1.4905443388570123e-05, "loss": 0.0178, "step": 10766 }, { "epoch": 0.594599072233267, "grad_norm": 0.5083409547805786, "learning_rate": 1.490198416665465e-05, "loss": 0.0226, "step": 10767 }, { "epoch": 0.5946542964435608, "grad_norm": 1.7440606355667114, "learning_rate": 1.4898525107839224e-05, "loss": 0.4659, "step": 10768 }, { "epoch": 0.5947095206538546, "grad_norm": 3.5239012241363525, "learning_rate": 1.4895066212234497e-05, "loss": 0.6924, "step": 10769 }, { "epoch": 0.5947647448641484, "grad_norm": 0.13973724842071533, "learning_rate": 1.4891607479951144e-05, "loss": 0.0026, "step": 10770 }, { "epoch": 0.5948199690744422, "grad_norm": 0.2998962700366974, "learning_rate": 1.4888148911099807e-05, "loss": 0.0113, "step": 10771 }, { "epoch": 0.594875193284736, "grad_norm": 3.210200786590576, "learning_rate": 1.4884690505791134e-05, "loss": 0.7524, "step": 10772 }, { "epoch": 0.5949304174950298, "grad_norm": 3.1043665409088135, "learning_rate": 1.4881232264135781e-05, "loss": 0.2445, "step": 10773 }, { "epoch": 0.5949856417053236, "grad_norm": 0.10011446475982666, "learning_rate": 1.4877774186244374e-05, "loss": 0.0019, "step": 10774 }, { "epoch": 0.5950408659156174, "grad_norm": 3.512887477874756, "learning_rate": 1.4874316272227556e-05, "loss": 0.5095, "step": 10775 }, { "epoch": 0.5950960901259112, "grad_norm": 5.046546936035156, "learning_rate": 1.487085852219595e-05, "loss": 0.3588, "step": 10776 }, { "epoch": 0.5951513143362049, "grad_norm": 0.8604860901832581, "learning_rate": 1.4867400936260192e-05, "loss": 0.0265, "step": 10777 }, { "epoch": 0.5952065385464987, "grad_norm": 1.6732146739959717, "learning_rate": 1.4863943514530878e-05, "loss": 0.0483, "step": 10778 }, { "epoch": 0.5952617627567925, "grad_norm": 1.0711086988449097, "learning_rate": 1.486048625711864e-05, "loss": 0.033, "step": 10779 }, { "epoch": 0.5953169869670863, "grad_norm": 2.4823098182678223, "learning_rate": 1.4857029164134073e-05, "loss": 0.2912, "step": 10780 }, { "epoch": 0.5953722111773802, "grad_norm": 2.4354865550994873, "learning_rate": 1.4853572235687788e-05, "loss": 0.1597, "step": 10781 }, { "epoch": 0.595427435387674, "grad_norm": 0.0739903673529625, "learning_rate": 1.4850115471890374e-05, "loss": 0.0019, "step": 10782 }, { "epoch": 0.5954826595979678, "grad_norm": 2.389949321746826, "learning_rate": 1.4846658872852432e-05, "loss": 0.099, "step": 10783 }, { "epoch": 0.5955378838082616, "grad_norm": 2.187211036682129, "learning_rate": 1.484320243868454e-05, "loss": 0.025, "step": 10784 }, { "epoch": 0.5955931080185554, "grad_norm": 0.2896524667739868, "learning_rate": 1.4839746169497292e-05, "loss": 0.0086, "step": 10785 }, { "epoch": 0.5956483322288492, "grad_norm": 2.0948386192321777, "learning_rate": 1.4836290065401238e-05, "loss": 0.4496, "step": 10786 }, { "epoch": 0.595703556439143, "grad_norm": 6.243473529815674, "learning_rate": 1.483283412650698e-05, "loss": 1.3358, "step": 10787 }, { "epoch": 0.5957587806494367, "grad_norm": 3.101259708404541, "learning_rate": 1.4829378352925062e-05, "loss": 0.3948, "step": 10788 }, { "epoch": 0.5958140048597305, "grad_norm": 2.3306474685668945, "learning_rate": 1.4825922744766053e-05, "loss": 0.1685, "step": 10789 }, { "epoch": 0.5958692290700243, "grad_norm": 0.05151943117380142, "learning_rate": 1.4822467302140502e-05, "loss": 0.0016, "step": 10790 }, { "epoch": 0.5959244532803181, "grad_norm": 2.734313726425171, "learning_rate": 1.4819012025158963e-05, "loss": 0.5777, "step": 10791 }, { "epoch": 0.5959796774906119, "grad_norm": 0.47200241684913635, "learning_rate": 1.481555691393198e-05, "loss": 0.0077, "step": 10792 }, { "epoch": 0.5960349017009057, "grad_norm": 0.03440424054861069, "learning_rate": 1.4812101968570094e-05, "loss": 0.0008, "step": 10793 }, { "epoch": 0.5960901259111995, "grad_norm": 3.1293389797210693, "learning_rate": 1.4808647189183827e-05, "loss": 0.4428, "step": 10794 }, { "epoch": 0.5961453501214933, "grad_norm": 0.3816303312778473, "learning_rate": 1.4805192575883726e-05, "loss": 0.0089, "step": 10795 }, { "epoch": 0.5962005743317871, "grad_norm": 2.5736751556396484, "learning_rate": 1.4801738128780294e-05, "loss": 0.0644, "step": 10796 }, { "epoch": 0.5962557985420809, "grad_norm": 8.29384708404541, "learning_rate": 1.4798283847984066e-05, "loss": 1.0613, "step": 10797 }, { "epoch": 0.5963110227523747, "grad_norm": 2.8182215690612793, "learning_rate": 1.4794829733605536e-05, "loss": 0.2038, "step": 10798 }, { "epoch": 0.5963662469626685, "grad_norm": 0.21362316608428955, "learning_rate": 1.4791375785755232e-05, "loss": 0.0051, "step": 10799 }, { "epoch": 0.5964214711729622, "grad_norm": 3.2464544773101807, "learning_rate": 1.4787922004543635e-05, "loss": 0.1395, "step": 10800 }, { "epoch": 0.596476695383256, "grad_norm": 0.03969071805477142, "learning_rate": 1.4784468390081264e-05, "loss": 0.0005, "step": 10801 }, { "epoch": 0.5965319195935498, "grad_norm": 1.7371360063552856, "learning_rate": 1.4781014942478583e-05, "loss": 0.0932, "step": 10802 }, { "epoch": 0.5965871438038436, "grad_norm": 3.363546848297119, "learning_rate": 1.4777561661846104e-05, "loss": 0.5364, "step": 10803 }, { "epoch": 0.5966423680141374, "grad_norm": 2.237478256225586, "learning_rate": 1.4774108548294286e-05, "loss": 0.3188, "step": 10804 }, { "epoch": 0.5966975922244312, "grad_norm": 0.15848910808563232, "learning_rate": 1.477065560193362e-05, "loss": 0.0055, "step": 10805 }, { "epoch": 0.596752816434725, "grad_norm": 0.5899908542633057, "learning_rate": 1.476720282287456e-05, "loss": 0.0227, "step": 10806 }, { "epoch": 0.5968080406450188, "grad_norm": 0.9406006336212158, "learning_rate": 1.4763750211227588e-05, "loss": 0.1156, "step": 10807 }, { "epoch": 0.5968632648553126, "grad_norm": 0.17397746443748474, "learning_rate": 1.4760297767103147e-05, "loss": 0.0049, "step": 10808 }, { "epoch": 0.5969184890656064, "grad_norm": 2.538443088531494, "learning_rate": 1.4756845490611707e-05, "loss": 0.0367, "step": 10809 }, { "epoch": 0.5969737132759002, "grad_norm": 5.067767143249512, "learning_rate": 1.475339338186369e-05, "loss": 0.6279, "step": 10810 }, { "epoch": 0.5970289374861939, "grad_norm": 0.47722572088241577, "learning_rate": 1.474994144096957e-05, "loss": 0.0047, "step": 10811 }, { "epoch": 0.5970841616964877, "grad_norm": 0.24451647698879242, "learning_rate": 1.4746489668039763e-05, "loss": 0.0063, "step": 10812 }, { "epoch": 0.5971393859067815, "grad_norm": 6.206401824951172, "learning_rate": 1.4743038063184709e-05, "loss": 1.5234, "step": 10813 }, { "epoch": 0.5971946101170753, "grad_norm": 0.4335428774356842, "learning_rate": 1.473958662651483e-05, "loss": 0.0157, "step": 10814 }, { "epoch": 0.5972498343273691, "grad_norm": 3.509990692138672, "learning_rate": 1.4736135358140555e-05, "loss": 0.6946, "step": 10815 }, { "epoch": 0.5973050585376629, "grad_norm": 1.860365390777588, "learning_rate": 1.4732684258172291e-05, "loss": 0.1756, "step": 10816 }, { "epoch": 0.5973602827479567, "grad_norm": 0.17051458358764648, "learning_rate": 1.4729233326720459e-05, "loss": 0.0052, "step": 10817 }, { "epoch": 0.5974155069582505, "grad_norm": 4.486471176147461, "learning_rate": 1.4725782563895452e-05, "loss": 0.3468, "step": 10818 }, { "epoch": 0.5974707311685443, "grad_norm": 0.061580024659633636, "learning_rate": 1.4722331969807684e-05, "loss": 0.0016, "step": 10819 }, { "epoch": 0.5975259553788381, "grad_norm": 0.23508121073246002, "learning_rate": 1.4718881544567531e-05, "loss": 0.0051, "step": 10820 }, { "epoch": 0.5975811795891319, "grad_norm": 2.2896268367767334, "learning_rate": 1.47154312882854e-05, "loss": 0.0754, "step": 10821 }, { "epoch": 0.5976364037994256, "grad_norm": 3.5548436641693115, "learning_rate": 1.471198120107166e-05, "loss": 0.4271, "step": 10822 }, { "epoch": 0.5976916280097194, "grad_norm": 2.4221460819244385, "learning_rate": 1.47085312830367e-05, "loss": 0.1554, "step": 10823 }, { "epoch": 0.5977468522200132, "grad_norm": 0.12618042528629303, "learning_rate": 1.4705081534290886e-05, "loss": 0.0055, "step": 10824 }, { "epoch": 0.597802076430307, "grad_norm": 3.2225606441497803, "learning_rate": 1.470163195494459e-05, "loss": 0.1019, "step": 10825 }, { "epoch": 0.5978573006406008, "grad_norm": 0.7458510994911194, "learning_rate": 1.469818254510817e-05, "loss": 0.162, "step": 10826 }, { "epoch": 0.5979125248508946, "grad_norm": 0.387319415807724, "learning_rate": 1.469473330489199e-05, "loss": 0.0137, "step": 10827 }, { "epoch": 0.5979677490611884, "grad_norm": 4.975418567657471, "learning_rate": 1.4691284234406387e-05, "loss": 0.4049, "step": 10828 }, { "epoch": 0.5980229732714822, "grad_norm": 1.2903249263763428, "learning_rate": 1.468783533376172e-05, "loss": 0.0389, "step": 10829 }, { "epoch": 0.598078197481776, "grad_norm": 0.7201699614524841, "learning_rate": 1.4684386603068322e-05, "loss": 0.0099, "step": 10830 }, { "epoch": 0.5981334216920698, "grad_norm": 4.229341983795166, "learning_rate": 1.4680938042436526e-05, "loss": 0.3729, "step": 10831 }, { "epoch": 0.5981886459023636, "grad_norm": 1.3104363679885864, "learning_rate": 1.4677489651976673e-05, "loss": 0.0653, "step": 10832 }, { "epoch": 0.5982438701126573, "grad_norm": 1.2619624137878418, "learning_rate": 1.4674041431799064e-05, "loss": 0.0246, "step": 10833 }, { "epoch": 0.5982990943229511, "grad_norm": 3.8296875953674316, "learning_rate": 1.4670593382014047e-05, "loss": 0.4551, "step": 10834 }, { "epoch": 0.5983543185332449, "grad_norm": 1.518781065940857, "learning_rate": 1.4667145502731912e-05, "loss": 0.0561, "step": 10835 }, { "epoch": 0.5984095427435387, "grad_norm": 1.5301347970962524, "learning_rate": 1.4663697794062976e-05, "loss": 0.0784, "step": 10836 }, { "epoch": 0.5984647669538325, "grad_norm": 0.6404343247413635, "learning_rate": 1.466025025611754e-05, "loss": 0.0153, "step": 10837 }, { "epoch": 0.5985199911641264, "grad_norm": 2.7919604778289795, "learning_rate": 1.4656802889005899e-05, "loss": 0.5279, "step": 10838 }, { "epoch": 0.5985752153744202, "grad_norm": 2.2498273849487305, "learning_rate": 1.4653355692838342e-05, "loss": 0.3541, "step": 10839 }, { "epoch": 0.598630439584714, "grad_norm": 2.836644172668457, "learning_rate": 1.4649908667725168e-05, "loss": 0.1302, "step": 10840 }, { "epoch": 0.5986856637950078, "grad_norm": 0.3775970935821533, "learning_rate": 1.464646181377663e-05, "loss": 0.0113, "step": 10841 }, { "epoch": 0.5987408880053016, "grad_norm": 0.631468653678894, "learning_rate": 1.4643015131103036e-05, "loss": 0.0091, "step": 10842 }, { "epoch": 0.5987961122155954, "grad_norm": 0.4507482349872589, "learning_rate": 1.4639568619814628e-05, "loss": 0.0135, "step": 10843 }, { "epoch": 0.5988513364258891, "grad_norm": 0.141206756234169, "learning_rate": 1.4636122280021688e-05, "loss": 0.0036, "step": 10844 }, { "epoch": 0.5989065606361829, "grad_norm": 1.2851436138153076, "learning_rate": 1.4632676111834459e-05, "loss": 0.0589, "step": 10845 }, { "epoch": 0.5989617848464767, "grad_norm": 2.5493054389953613, "learning_rate": 1.4629230115363205e-05, "loss": 0.2916, "step": 10846 }, { "epoch": 0.5990170090567705, "grad_norm": 1.602874994277954, "learning_rate": 1.4625784290718166e-05, "loss": 0.1671, "step": 10847 }, { "epoch": 0.5990722332670643, "grad_norm": 0.11950615048408508, "learning_rate": 1.4622338638009593e-05, "loss": 0.0029, "step": 10848 }, { "epoch": 0.5991274574773581, "grad_norm": 1.4911688566207886, "learning_rate": 1.461889315734771e-05, "loss": 0.0525, "step": 10849 }, { "epoch": 0.5991826816876519, "grad_norm": 6.519047260284424, "learning_rate": 1.4615447848842765e-05, "loss": 1.4921, "step": 10850 }, { "epoch": 0.5992379058979457, "grad_norm": 0.08043430000543594, "learning_rate": 1.4612002712604962e-05, "loss": 0.0024, "step": 10851 }, { "epoch": 0.5992931301082395, "grad_norm": 0.03860031068325043, "learning_rate": 1.4608557748744538e-05, "loss": 0.0009, "step": 10852 }, { "epoch": 0.5993483543185333, "grad_norm": 0.6043640971183777, "learning_rate": 1.4605112957371694e-05, "loss": 0.0131, "step": 10853 }, { "epoch": 0.5994035785288271, "grad_norm": 0.12536513805389404, "learning_rate": 1.460166833859665e-05, "loss": 0.0029, "step": 10854 }, { "epoch": 0.5994588027391208, "grad_norm": 0.7969284653663635, "learning_rate": 1.4598223892529602e-05, "loss": 0.0262, "step": 10855 }, { "epoch": 0.5995140269494146, "grad_norm": 0.08253195136785507, "learning_rate": 1.459477961928075e-05, "loss": 0.0021, "step": 10856 }, { "epoch": 0.5995692511597084, "grad_norm": 5.3079657554626465, "learning_rate": 1.4591335518960283e-05, "loss": 0.4625, "step": 10857 }, { "epoch": 0.5996244753700022, "grad_norm": 1.402961254119873, "learning_rate": 1.45878915916784e-05, "loss": 0.1116, "step": 10858 }, { "epoch": 0.599679699580296, "grad_norm": 0.06781163811683655, "learning_rate": 1.4584447837545264e-05, "loss": 0.0013, "step": 10859 }, { "epoch": 0.5997349237905898, "grad_norm": 2.3169596195220947, "learning_rate": 1.4581004256671064e-05, "loss": 0.2154, "step": 10860 }, { "epoch": 0.5997901480008836, "grad_norm": 0.5616297125816345, "learning_rate": 1.4577560849165959e-05, "loss": 0.0117, "step": 10861 }, { "epoch": 0.5998453722111774, "grad_norm": 4.299022674560547, "learning_rate": 1.4574117615140124e-05, "loss": 0.6203, "step": 10862 }, { "epoch": 0.5999005964214712, "grad_norm": 3.420149803161621, "learning_rate": 1.457067455470371e-05, "loss": 0.7647, "step": 10863 }, { "epoch": 0.599955820631765, "grad_norm": 0.1734306961297989, "learning_rate": 1.4567231667966879e-05, "loss": 0.0033, "step": 10864 }, { "epoch": 0.6000110448420588, "grad_norm": 1.972044587135315, "learning_rate": 1.4563788955039767e-05, "loss": 0.1593, "step": 10865 }, { "epoch": 0.6000662690523525, "grad_norm": 0.177792489528656, "learning_rate": 1.4560346416032532e-05, "loss": 0.0041, "step": 10866 }, { "epoch": 0.6001214932626463, "grad_norm": 0.05055738240480423, "learning_rate": 1.4556904051055286e-05, "loss": 0.0013, "step": 10867 }, { "epoch": 0.6001767174729401, "grad_norm": 3.064180612564087, "learning_rate": 1.455346186021819e-05, "loss": 0.1396, "step": 10868 }, { "epoch": 0.6002319416832339, "grad_norm": 0.4394683539867401, "learning_rate": 1.4550019843631346e-05, "loss": 0.014, "step": 10869 }, { "epoch": 0.6002871658935277, "grad_norm": 0.14573970437049866, "learning_rate": 1.4546578001404888e-05, "loss": 0.003, "step": 10870 }, { "epoch": 0.6003423901038215, "grad_norm": 0.033543866127729416, "learning_rate": 1.4543136333648919e-05, "loss": 0.0009, "step": 10871 }, { "epoch": 0.6003976143141153, "grad_norm": 1.7611525058746338, "learning_rate": 1.4539694840473559e-05, "loss": 0.2681, "step": 10872 }, { "epoch": 0.6004528385244091, "grad_norm": 3.146876573562622, "learning_rate": 1.4536253521988902e-05, "loss": 0.1524, "step": 10873 }, { "epoch": 0.6005080627347029, "grad_norm": 0.00977455172687769, "learning_rate": 1.4532812378305057e-05, "loss": 0.0004, "step": 10874 }, { "epoch": 0.6005632869449967, "grad_norm": 0.8596721291542053, "learning_rate": 1.4529371409532096e-05, "loss": 0.0347, "step": 10875 }, { "epoch": 0.6006185111552905, "grad_norm": 2.72989559173584, "learning_rate": 1.4525930615780128e-05, "loss": 0.8164, "step": 10876 }, { "epoch": 0.6006737353655843, "grad_norm": 0.006742993835359812, "learning_rate": 1.4522489997159217e-05, "loss": 0.0002, "step": 10877 }, { "epoch": 0.600728959575878, "grad_norm": 0.4034847915172577, "learning_rate": 1.4519049553779451e-05, "loss": 0.0093, "step": 10878 }, { "epoch": 0.6007841837861718, "grad_norm": 2.2732021808624268, "learning_rate": 1.4515609285750886e-05, "loss": 0.2119, "step": 10879 }, { "epoch": 0.6008394079964656, "grad_norm": 5.286451816558838, "learning_rate": 1.45121691931836e-05, "loss": 0.3221, "step": 10880 }, { "epoch": 0.6008946322067594, "grad_norm": 1.0747727155685425, "learning_rate": 1.450872927618764e-05, "loss": 0.1298, "step": 10881 }, { "epoch": 0.6009498564170532, "grad_norm": 0.01358721498399973, "learning_rate": 1.4505289534873073e-05, "loss": 0.0004, "step": 10882 }, { "epoch": 0.601005080627347, "grad_norm": 0.30443838238716125, "learning_rate": 1.4501849969349922e-05, "loss": 0.011, "step": 10883 }, { "epoch": 0.6010603048376408, "grad_norm": 0.011084658093750477, "learning_rate": 1.4498410579728256e-05, "loss": 0.0004, "step": 10884 }, { "epoch": 0.6011155290479346, "grad_norm": 0.0778503492474556, "learning_rate": 1.4494971366118087e-05, "loss": 0.002, "step": 10885 }, { "epoch": 0.6011707532582284, "grad_norm": 0.11275336891412735, "learning_rate": 1.4491532328629464e-05, "loss": 0.0027, "step": 10886 }, { "epoch": 0.6012259774685222, "grad_norm": 0.8312968015670776, "learning_rate": 1.4488093467372398e-05, "loss": 0.0191, "step": 10887 }, { "epoch": 0.601281201678816, "grad_norm": 2.39263916015625, "learning_rate": 1.4484654782456917e-05, "loss": 0.239, "step": 10888 }, { "epoch": 0.6013364258891097, "grad_norm": 4.171697616577148, "learning_rate": 1.4481216273993029e-05, "loss": 0.2961, "step": 10889 }, { "epoch": 0.6013916500994035, "grad_norm": 2.373899221420288, "learning_rate": 1.447777794209075e-05, "loss": 0.2935, "step": 10890 }, { "epoch": 0.6014468743096973, "grad_norm": 3.867443323135376, "learning_rate": 1.4474339786860072e-05, "loss": 0.8336, "step": 10891 }, { "epoch": 0.6015020985199911, "grad_norm": 0.01215627882629633, "learning_rate": 1.4470901808410993e-05, "loss": 0.0004, "step": 10892 }, { "epoch": 0.601557322730285, "grad_norm": 0.01602897420525551, "learning_rate": 1.446746400685351e-05, "loss": 0.0004, "step": 10893 }, { "epoch": 0.6016125469405788, "grad_norm": 3.0492210388183594, "learning_rate": 1.4464026382297596e-05, "loss": 0.2198, "step": 10894 }, { "epoch": 0.6016677711508726, "grad_norm": 1.8699606657028198, "learning_rate": 1.4460588934853244e-05, "loss": 0.3576, "step": 10895 }, { "epoch": 0.6017229953611664, "grad_norm": 4.902611255645752, "learning_rate": 1.445715166463042e-05, "loss": 0.435, "step": 10896 }, { "epoch": 0.6017782195714602, "grad_norm": 3.100193500518799, "learning_rate": 1.44537145717391e-05, "loss": 0.8013, "step": 10897 }, { "epoch": 0.601833443781754, "grad_norm": 3.668548107147217, "learning_rate": 1.4450277656289232e-05, "loss": 0.8, "step": 10898 }, { "epoch": 0.6018886679920478, "grad_norm": 0.0479322224855423, "learning_rate": 1.4446840918390787e-05, "loss": 0.0014, "step": 10899 }, { "epoch": 0.6019438922023415, "grad_norm": 2.8143651485443115, "learning_rate": 1.4443404358153705e-05, "loss": 0.0895, "step": 10900 }, { "epoch": 0.6019991164126353, "grad_norm": 0.02112540230154991, "learning_rate": 1.443996797568794e-05, "loss": 0.0007, "step": 10901 }, { "epoch": 0.6020543406229291, "grad_norm": 2.3451058864593506, "learning_rate": 1.4436531771103424e-05, "loss": 0.2897, "step": 10902 }, { "epoch": 0.6021095648332229, "grad_norm": 0.20676805078983307, "learning_rate": 1.4433095744510102e-05, "loss": 0.0061, "step": 10903 }, { "epoch": 0.6021647890435167, "grad_norm": 2.050072193145752, "learning_rate": 1.4429659896017887e-05, "loss": 0.0755, "step": 10904 }, { "epoch": 0.6022200132538105, "grad_norm": 4.116295337677002, "learning_rate": 1.4426224225736723e-05, "loss": 1.1902, "step": 10905 }, { "epoch": 0.6022752374641043, "grad_norm": 3.3503499031066895, "learning_rate": 1.4422788733776498e-05, "loss": 1.0248, "step": 10906 }, { "epoch": 0.6023304616743981, "grad_norm": 0.11856049299240112, "learning_rate": 1.4419353420247153e-05, "loss": 0.0029, "step": 10907 }, { "epoch": 0.6023856858846919, "grad_norm": 1.433108925819397, "learning_rate": 1.4415918285258568e-05, "loss": 0.0277, "step": 10908 }, { "epoch": 0.6024409100949857, "grad_norm": 0.407789409160614, "learning_rate": 1.4412483328920664e-05, "loss": 0.0167, "step": 10909 }, { "epoch": 0.6024961343052795, "grad_norm": 0.04821512848138809, "learning_rate": 1.4409048551343317e-05, "loss": 0.0017, "step": 10910 }, { "epoch": 0.6025513585155732, "grad_norm": 3.2473201751708984, "learning_rate": 1.4405613952636428e-05, "loss": 0.757, "step": 10911 }, { "epoch": 0.602606582725867, "grad_norm": 3.475358247756958, "learning_rate": 1.4402179532909872e-05, "loss": 0.4333, "step": 10912 }, { "epoch": 0.6026618069361608, "grad_norm": 0.06312504410743713, "learning_rate": 1.4398745292273538e-05, "loss": 0.0028, "step": 10913 }, { "epoch": 0.6027170311464546, "grad_norm": 0.02252248115837574, "learning_rate": 1.4395311230837274e-05, "loss": 0.0005, "step": 10914 }, { "epoch": 0.6027722553567484, "grad_norm": 3.3645057678222656, "learning_rate": 1.4391877348710975e-05, "loss": 0.8501, "step": 10915 }, { "epoch": 0.6028274795670422, "grad_norm": 3.607231855392456, "learning_rate": 1.4388443646004473e-05, "loss": 0.9852, "step": 10916 }, { "epoch": 0.602882703777336, "grad_norm": 4.033812046051025, "learning_rate": 1.4385010122827639e-05, "loss": 0.8015, "step": 10917 }, { "epoch": 0.6029379279876298, "grad_norm": 1.4056270122528076, "learning_rate": 1.4381576779290314e-05, "loss": 0.0544, "step": 10918 }, { "epoch": 0.6029931521979236, "grad_norm": 1.0669763088226318, "learning_rate": 1.4378143615502347e-05, "loss": 0.0269, "step": 10919 }, { "epoch": 0.6030483764082174, "grad_norm": 3.8432931900024414, "learning_rate": 1.4374710631573563e-05, "loss": 0.1335, "step": 10920 }, { "epoch": 0.6031036006185112, "grad_norm": 4.566112995147705, "learning_rate": 1.4371277827613814e-05, "loss": 1.2691, "step": 10921 }, { "epoch": 0.6031588248288049, "grad_norm": 0.27284714579582214, "learning_rate": 1.4367845203732896e-05, "loss": 0.0096, "step": 10922 }, { "epoch": 0.6032140490390987, "grad_norm": 6.608461380004883, "learning_rate": 1.4364412760040656e-05, "loss": 1.24, "step": 10923 }, { "epoch": 0.6032692732493925, "grad_norm": 6.795037269592285, "learning_rate": 1.4360980496646888e-05, "loss": 0.258, "step": 10924 }, { "epoch": 0.6033244974596863, "grad_norm": 0.22788986563682556, "learning_rate": 1.435754841366141e-05, "loss": 0.0082, "step": 10925 }, { "epoch": 0.6033797216699801, "grad_norm": 4.2106122970581055, "learning_rate": 1.435411651119402e-05, "loss": 0.3441, "step": 10926 }, { "epoch": 0.6034349458802739, "grad_norm": 0.048400022089481354, "learning_rate": 1.435068478935452e-05, "loss": 0.0014, "step": 10927 }, { "epoch": 0.6034901700905677, "grad_norm": 0.053596965968608856, "learning_rate": 1.4347253248252692e-05, "loss": 0.0015, "step": 10928 }, { "epoch": 0.6035453943008615, "grad_norm": 1.9261544942855835, "learning_rate": 1.4343821887998333e-05, "loss": 0.3054, "step": 10929 }, { "epoch": 0.6036006185111553, "grad_norm": 0.054770663380622864, "learning_rate": 1.4340390708701202e-05, "loss": 0.0018, "step": 10930 }, { "epoch": 0.6036558427214491, "grad_norm": 5.261458873748779, "learning_rate": 1.4336959710471097e-05, "loss": 0.5829, "step": 10931 }, { "epoch": 0.6037110669317429, "grad_norm": 3.6014561653137207, "learning_rate": 1.4333528893417763e-05, "loss": 0.3534, "step": 10932 }, { "epoch": 0.6037662911420366, "grad_norm": 0.3085460066795349, "learning_rate": 1.4330098257650978e-05, "loss": 0.0066, "step": 10933 }, { "epoch": 0.6038215153523304, "grad_norm": 0.18328003585338593, "learning_rate": 1.4326667803280485e-05, "loss": 0.0053, "step": 10934 }, { "epoch": 0.6038767395626242, "grad_norm": 0.09947387129068375, "learning_rate": 1.4323237530416045e-05, "loss": 0.0034, "step": 10935 }, { "epoch": 0.603931963772918, "grad_norm": 1.4135468006134033, "learning_rate": 1.4319807439167393e-05, "loss": 0.052, "step": 10936 }, { "epoch": 0.6039871879832118, "grad_norm": 0.03589201346039772, "learning_rate": 1.4316377529644277e-05, "loss": 0.0011, "step": 10937 }, { "epoch": 0.6040424121935056, "grad_norm": 0.1280403733253479, "learning_rate": 1.431294780195642e-05, "loss": 0.0031, "step": 10938 }, { "epoch": 0.6040976364037994, "grad_norm": 0.2367953062057495, "learning_rate": 1.4309518256213562e-05, "loss": 0.0074, "step": 10939 }, { "epoch": 0.6041528606140932, "grad_norm": 0.0473710335791111, "learning_rate": 1.4306088892525405e-05, "loss": 0.001, "step": 10940 }, { "epoch": 0.604208084824387, "grad_norm": 0.08414459973573685, "learning_rate": 1.430265971100168e-05, "loss": 0.0012, "step": 10941 }, { "epoch": 0.6042633090346808, "grad_norm": 3.5014803409576416, "learning_rate": 1.4299230711752086e-05, "loss": 0.3664, "step": 10942 }, { "epoch": 0.6043185332449746, "grad_norm": 0.672467827796936, "learning_rate": 1.4295801894886333e-05, "loss": 0.0173, "step": 10943 }, { "epoch": 0.6043737574552683, "grad_norm": 0.010542691685259342, "learning_rate": 1.4292373260514114e-05, "loss": 0.0003, "step": 10944 }, { "epoch": 0.6044289816655621, "grad_norm": 0.0298539400100708, "learning_rate": 1.4288944808745129e-05, "loss": 0.0007, "step": 10945 }, { "epoch": 0.6044842058758559, "grad_norm": 3.5405402183532715, "learning_rate": 1.4285516539689051e-05, "loss": 0.4081, "step": 10946 }, { "epoch": 0.6045394300861497, "grad_norm": 0.05622771382331848, "learning_rate": 1.4282088453455579e-05, "loss": 0.0016, "step": 10947 }, { "epoch": 0.6045946542964435, "grad_norm": 1.884178638458252, "learning_rate": 1.4278660550154364e-05, "loss": 0.1391, "step": 10948 }, { "epoch": 0.6046498785067373, "grad_norm": 3.799398899078369, "learning_rate": 1.4275232829895092e-05, "loss": 0.8962, "step": 10949 }, { "epoch": 0.6047051027170312, "grad_norm": 3.000199317932129, "learning_rate": 1.4271805292787412e-05, "loss": 0.9449, "step": 10950 }, { "epoch": 0.604760326927325, "grad_norm": 0.788110077381134, "learning_rate": 1.4268377938940998e-05, "loss": 0.1438, "step": 10951 }, { "epoch": 0.6048155511376188, "grad_norm": 0.6314170956611633, "learning_rate": 1.4264950768465493e-05, "loss": 0.0196, "step": 10952 }, { "epoch": 0.6048707753479126, "grad_norm": 3.115877866744995, "learning_rate": 1.4261523781470525e-05, "loss": 0.0898, "step": 10953 }, { "epoch": 0.6049259995582064, "grad_norm": 4.895016670227051, "learning_rate": 1.4258096978065763e-05, "loss": 0.4775, "step": 10954 }, { "epoch": 0.6049812237685002, "grad_norm": 4.284177780151367, "learning_rate": 1.4254670358360816e-05, "loss": 0.4109, "step": 10955 }, { "epoch": 0.6050364479787939, "grad_norm": 0.09027653932571411, "learning_rate": 1.4251243922465323e-05, "loss": 0.0028, "step": 10956 }, { "epoch": 0.6050916721890877, "grad_norm": 1.7916691303253174, "learning_rate": 1.4247817670488902e-05, "loss": 0.3826, "step": 10957 }, { "epoch": 0.6051468963993815, "grad_norm": 0.459743469953537, "learning_rate": 1.424439160254117e-05, "loss": 0.0099, "step": 10958 }, { "epoch": 0.6052021206096753, "grad_norm": 2.805866241455078, "learning_rate": 1.4240965718731734e-05, "loss": 0.2812, "step": 10959 }, { "epoch": 0.6052573448199691, "grad_norm": 1.9178128242492676, "learning_rate": 1.4237540019170209e-05, "loss": 0.4769, "step": 10960 }, { "epoch": 0.6053125690302629, "grad_norm": 6.149500370025635, "learning_rate": 1.4234114503966167e-05, "loss": 0.8192, "step": 10961 }, { "epoch": 0.6053677932405567, "grad_norm": 0.1637067049741745, "learning_rate": 1.4230689173229235e-05, "loss": 0.0057, "step": 10962 }, { "epoch": 0.6054230174508505, "grad_norm": 5.2611589431762695, "learning_rate": 1.422726402706897e-05, "loss": 0.6529, "step": 10963 }, { "epoch": 0.6054782416611443, "grad_norm": 0.32378119230270386, "learning_rate": 1.4223839065594966e-05, "loss": 0.0103, "step": 10964 }, { "epoch": 0.6055334658714381, "grad_norm": 2.8825793266296387, "learning_rate": 1.4220414288916792e-05, "loss": 0.1101, "step": 10965 }, { "epoch": 0.6055886900817319, "grad_norm": 5.215950965881348, "learning_rate": 1.4216989697144024e-05, "loss": 0.6752, "step": 10966 }, { "epoch": 0.6056439142920256, "grad_norm": 0.07732293754816055, "learning_rate": 1.4213565290386213e-05, "loss": 0.0022, "step": 10967 }, { "epoch": 0.6056991385023194, "grad_norm": 0.44686099886894226, "learning_rate": 1.4210141068752923e-05, "loss": 0.0077, "step": 10968 }, { "epoch": 0.6057543627126132, "grad_norm": 2.2429592609405518, "learning_rate": 1.4206717032353703e-05, "loss": 0.2439, "step": 10969 }, { "epoch": 0.605809586922907, "grad_norm": 0.11816918104887009, "learning_rate": 1.4203293181298106e-05, "loss": 0.0033, "step": 10970 }, { "epoch": 0.6058648111332008, "grad_norm": 0.6532800793647766, "learning_rate": 1.4199869515695652e-05, "loss": 0.0147, "step": 10971 }, { "epoch": 0.6059200353434946, "grad_norm": 1.2337969541549683, "learning_rate": 1.419644603565589e-05, "loss": 0.0215, "step": 10972 }, { "epoch": 0.6059752595537884, "grad_norm": 0.02160533517599106, "learning_rate": 1.4193022741288337e-05, "loss": 0.0008, "step": 10973 }, { "epoch": 0.6060304837640822, "grad_norm": 1.402085542678833, "learning_rate": 1.4189599632702521e-05, "loss": 0.0372, "step": 10974 }, { "epoch": 0.606085707974376, "grad_norm": 0.8701085448265076, "learning_rate": 1.4186176710007952e-05, "loss": 0.0315, "step": 10975 }, { "epoch": 0.6061409321846698, "grad_norm": 2.5439672470092773, "learning_rate": 1.4182753973314147e-05, "loss": 0.468, "step": 10976 }, { "epoch": 0.6061961563949636, "grad_norm": 2.1923747062683105, "learning_rate": 1.4179331422730598e-05, "loss": 0.3494, "step": 10977 }, { "epoch": 0.6062513806052573, "grad_norm": 0.06016184762120247, "learning_rate": 1.4175909058366815e-05, "loss": 0.0017, "step": 10978 }, { "epoch": 0.6063066048155511, "grad_norm": 1.0107667446136475, "learning_rate": 1.4172486880332272e-05, "loss": 0.0403, "step": 10979 }, { "epoch": 0.6063618290258449, "grad_norm": 3.1325650215148926, "learning_rate": 1.416906488873647e-05, "loss": 0.2776, "step": 10980 }, { "epoch": 0.6064170532361387, "grad_norm": 3.136631488800049, "learning_rate": 1.4165643083688878e-05, "loss": 0.0926, "step": 10981 }, { "epoch": 0.6064722774464325, "grad_norm": 2.34364652633667, "learning_rate": 1.4162221465298975e-05, "loss": 0.1412, "step": 10982 }, { "epoch": 0.6065275016567263, "grad_norm": 0.20720776915550232, "learning_rate": 1.4158800033676228e-05, "loss": 0.0054, "step": 10983 }, { "epoch": 0.6065827258670201, "grad_norm": 0.154205784201622, "learning_rate": 1.4155378788930097e-05, "loss": 0.0054, "step": 10984 }, { "epoch": 0.6066379500773139, "grad_norm": 0.03514294698834419, "learning_rate": 1.4151957731170031e-05, "loss": 0.0008, "step": 10985 }, { "epoch": 0.6066931742876077, "grad_norm": 4.157078266143799, "learning_rate": 1.41485368605055e-05, "loss": 1.2608, "step": 10986 }, { "epoch": 0.6067483984979015, "grad_norm": 0.4193863868713379, "learning_rate": 1.4145116177045917e-05, "loss": 0.0053, "step": 10987 }, { "epoch": 0.6068036227081953, "grad_norm": 0.5083219408988953, "learning_rate": 1.4141695680900748e-05, "loss": 0.015, "step": 10988 }, { "epoch": 0.606858846918489, "grad_norm": 0.24413378536701202, "learning_rate": 1.4138275372179406e-05, "loss": 0.0095, "step": 10989 }, { "epoch": 0.6069140711287828, "grad_norm": 3.687973737716675, "learning_rate": 1.4134855250991327e-05, "loss": 0.5603, "step": 10990 }, { "epoch": 0.6069692953390766, "grad_norm": 0.25843310356140137, "learning_rate": 1.4131435317445918e-05, "loss": 0.0058, "step": 10991 }, { "epoch": 0.6070245195493704, "grad_norm": 3.3123416900634766, "learning_rate": 1.4128015571652607e-05, "loss": 0.2745, "step": 10992 }, { "epoch": 0.6070797437596642, "grad_norm": 0.7230230569839478, "learning_rate": 1.4124596013720791e-05, "loss": 0.0185, "step": 10993 }, { "epoch": 0.607134967969958, "grad_norm": 3.9105467796325684, "learning_rate": 1.4121176643759882e-05, "loss": 0.3396, "step": 10994 }, { "epoch": 0.6071901921802518, "grad_norm": 2.5004043579101562, "learning_rate": 1.4117757461879258e-05, "loss": 0.6055, "step": 10995 }, { "epoch": 0.6072454163905456, "grad_norm": 0.24714885652065277, "learning_rate": 1.4114338468188326e-05, "loss": 0.0076, "step": 10996 }, { "epoch": 0.6073006406008394, "grad_norm": 0.02100597321987152, "learning_rate": 1.411091966279646e-05, "loss": 0.0007, "step": 10997 }, { "epoch": 0.6073558648111332, "grad_norm": 0.11527670919895172, "learning_rate": 1.4107501045813038e-05, "loss": 0.0039, "step": 10998 }, { "epoch": 0.607411089021427, "grad_norm": 2.8425376415252686, "learning_rate": 1.4104082617347434e-05, "loss": 0.1461, "step": 10999 }, { "epoch": 0.6074663132317207, "grad_norm": 2.3953843116760254, "learning_rate": 1.4100664377509015e-05, "loss": 0.2487, "step": 11000 }, { "epoch": 0.6075215374420145, "grad_norm": 1.178679347038269, "learning_rate": 1.409724632640713e-05, "loss": 0.0981, "step": 11001 }, { "epoch": 0.6075767616523083, "grad_norm": 0.15400955080986023, "learning_rate": 1.4093828464151148e-05, "loss": 0.0048, "step": 11002 }, { "epoch": 0.6076319858626021, "grad_norm": 3.208778142929077, "learning_rate": 1.4090410790850398e-05, "loss": 0.4593, "step": 11003 }, { "epoch": 0.607687210072896, "grad_norm": 0.4747414290904999, "learning_rate": 1.4086993306614243e-05, "loss": 0.0123, "step": 11004 }, { "epoch": 0.6077424342831897, "grad_norm": 1.9596920013427734, "learning_rate": 1.4083576011551996e-05, "loss": 0.7623, "step": 11005 }, { "epoch": 0.6077976584934836, "grad_norm": 4.580569267272949, "learning_rate": 1.4080158905773001e-05, "loss": 0.484, "step": 11006 }, { "epoch": 0.6078528827037774, "grad_norm": 3.257972002029419, "learning_rate": 1.4076741989386569e-05, "loss": 0.8051, "step": 11007 }, { "epoch": 0.6079081069140712, "grad_norm": 0.03274684026837349, "learning_rate": 1.4073325262502029e-05, "loss": 0.0008, "step": 11008 }, { "epoch": 0.607963331124365, "grad_norm": 3.790567636489868, "learning_rate": 1.4069908725228682e-05, "loss": 1.2003, "step": 11009 }, { "epoch": 0.6080185553346588, "grad_norm": 4.5810723304748535, "learning_rate": 1.4066492377675846e-05, "loss": 0.9594, "step": 11010 }, { "epoch": 0.6080737795449525, "grad_norm": 0.8589540719985962, "learning_rate": 1.4063076219952807e-05, "loss": 0.0259, "step": 11011 }, { "epoch": 0.6081290037552463, "grad_norm": 2.446359395980835, "learning_rate": 1.4059660252168858e-05, "loss": 0.6269, "step": 11012 }, { "epoch": 0.6081842279655401, "grad_norm": 0.6646078824996948, "learning_rate": 1.405624447443329e-05, "loss": 0.0072, "step": 11013 }, { "epoch": 0.6082394521758339, "grad_norm": 2.7676637172698975, "learning_rate": 1.4052828886855382e-05, "loss": 0.3009, "step": 11014 }, { "epoch": 0.6082946763861277, "grad_norm": 0.5809999108314514, "learning_rate": 1.404941348954441e-05, "loss": 0.0157, "step": 11015 }, { "epoch": 0.6083499005964215, "grad_norm": 0.01839541271328926, "learning_rate": 1.4045998282609636e-05, "loss": 0.0006, "step": 11016 }, { "epoch": 0.6084051248067153, "grad_norm": 2.0155227184295654, "learning_rate": 1.404258326616034e-05, "loss": 0.0438, "step": 11017 }, { "epoch": 0.6084603490170091, "grad_norm": 0.12974031269550323, "learning_rate": 1.4039168440305753e-05, "loss": 0.0043, "step": 11018 }, { "epoch": 0.6085155732273029, "grad_norm": 1.4818661212921143, "learning_rate": 1.4035753805155144e-05, "loss": 0.0723, "step": 11019 }, { "epoch": 0.6085707974375967, "grad_norm": 2.363192081451416, "learning_rate": 1.4032339360817744e-05, "loss": 0.5099, "step": 11020 }, { "epoch": 0.6086260216478905, "grad_norm": 3.500951051712036, "learning_rate": 1.4028925107402802e-05, "loss": 0.8339, "step": 11021 }, { "epoch": 0.6086812458581843, "grad_norm": 2.9929981231689453, "learning_rate": 1.4025511045019542e-05, "loss": 0.6869, "step": 11022 }, { "epoch": 0.608736470068478, "grad_norm": 5.0777506828308105, "learning_rate": 1.4022097173777194e-05, "loss": 1.0886, "step": 11023 }, { "epoch": 0.6087916942787718, "grad_norm": 0.14147302508354187, "learning_rate": 1.4018683493784972e-05, "loss": 0.0041, "step": 11024 }, { "epoch": 0.6088469184890656, "grad_norm": 5.28024959564209, "learning_rate": 1.4015270005152104e-05, "loss": 0.7376, "step": 11025 }, { "epoch": 0.6089021426993594, "grad_norm": 0.0971531942486763, "learning_rate": 1.401185670798777e-05, "loss": 0.0015, "step": 11026 }, { "epoch": 0.6089573669096532, "grad_norm": 6.194334983825684, "learning_rate": 1.4008443602401203e-05, "loss": 1.1687, "step": 11027 }, { "epoch": 0.609012591119947, "grad_norm": 0.05044980347156525, "learning_rate": 1.4005030688501572e-05, "loss": 0.0018, "step": 11028 }, { "epoch": 0.6090678153302408, "grad_norm": 4.048343181610107, "learning_rate": 1.4001617966398082e-05, "loss": 0.3096, "step": 11029 }, { "epoch": 0.6091230395405346, "grad_norm": 1.5468703508377075, "learning_rate": 1.3998205436199906e-05, "loss": 0.0286, "step": 11030 }, { "epoch": 0.6091782637508284, "grad_norm": 3.3358047008514404, "learning_rate": 1.3994793098016226e-05, "loss": 0.7329, "step": 11031 }, { "epoch": 0.6092334879611222, "grad_norm": 2.9145619869232178, "learning_rate": 1.3991380951956207e-05, "loss": 0.5767, "step": 11032 }, { "epoch": 0.609288712171416, "grad_norm": 0.24849174916744232, "learning_rate": 1.3987968998129029e-05, "loss": 0.004, "step": 11033 }, { "epoch": 0.6093439363817097, "grad_norm": 2.3517308235168457, "learning_rate": 1.3984557236643821e-05, "loss": 0.4834, "step": 11034 }, { "epoch": 0.6093991605920035, "grad_norm": 3.6509363651275635, "learning_rate": 1.3981145667609768e-05, "loss": 0.7849, "step": 11035 }, { "epoch": 0.6094543848022973, "grad_norm": 5.208071708679199, "learning_rate": 1.397773429113599e-05, "loss": 0.9351, "step": 11036 }, { "epoch": 0.6095096090125911, "grad_norm": 0.35685884952545166, "learning_rate": 1.3974323107331642e-05, "loss": 0.0082, "step": 11037 }, { "epoch": 0.6095648332228849, "grad_norm": 2.4240705966949463, "learning_rate": 1.3970912116305848e-05, "loss": 0.1699, "step": 11038 }, { "epoch": 0.6096200574331787, "grad_norm": 4.118597507476807, "learning_rate": 1.3967501318167744e-05, "loss": 0.4824, "step": 11039 }, { "epoch": 0.6096752816434725, "grad_norm": 0.965299665927887, "learning_rate": 1.3964090713026441e-05, "loss": 0.0297, "step": 11040 }, { "epoch": 0.6097305058537663, "grad_norm": 0.007810470648109913, "learning_rate": 1.396068030099107e-05, "loss": 0.0002, "step": 11041 }, { "epoch": 0.6097857300640601, "grad_norm": 0.5360682606697083, "learning_rate": 1.3957270082170716e-05, "loss": 0.0218, "step": 11042 }, { "epoch": 0.6098409542743539, "grad_norm": 3.2638769149780273, "learning_rate": 1.3953860056674504e-05, "loss": 0.5256, "step": 11043 }, { "epoch": 0.6098961784846477, "grad_norm": 1.9697206020355225, "learning_rate": 1.3950450224611518e-05, "loss": 0.2035, "step": 11044 }, { "epoch": 0.6099514026949414, "grad_norm": 0.07765481621026993, "learning_rate": 1.3947040586090851e-05, "loss": 0.0019, "step": 11045 }, { "epoch": 0.6100066269052352, "grad_norm": 4.526113033294678, "learning_rate": 1.3943631141221588e-05, "loss": 0.5382, "step": 11046 }, { "epoch": 0.610061851115529, "grad_norm": 2.152947425842285, "learning_rate": 1.3940221890112809e-05, "loss": 0.2444, "step": 11047 }, { "epoch": 0.6101170753258228, "grad_norm": 1.7964768409729004, "learning_rate": 1.3936812832873578e-05, "loss": 0.1909, "step": 11048 }, { "epoch": 0.6101722995361166, "grad_norm": 1.0070834159851074, "learning_rate": 1.3933403969612975e-05, "loss": 0.0318, "step": 11049 }, { "epoch": 0.6102275237464104, "grad_norm": 1.5413228273391724, "learning_rate": 1.3929995300440035e-05, "loss": 0.2859, "step": 11050 }, { "epoch": 0.6102827479567042, "grad_norm": 3.1176648139953613, "learning_rate": 1.3926586825463844e-05, "loss": 0.1886, "step": 11051 }, { "epoch": 0.610337972166998, "grad_norm": 1.1284894943237305, "learning_rate": 1.3923178544793418e-05, "loss": 0.0242, "step": 11052 }, { "epoch": 0.6103931963772918, "grad_norm": 0.3628512918949127, "learning_rate": 1.3919770458537816e-05, "loss": 0.0103, "step": 11053 }, { "epoch": 0.6104484205875856, "grad_norm": 0.4538382291793823, "learning_rate": 1.3916362566806061e-05, "loss": 0.0121, "step": 11054 }, { "epoch": 0.6105036447978794, "grad_norm": 0.4005085229873657, "learning_rate": 1.3912954869707192e-05, "loss": 0.0121, "step": 11055 }, { "epoch": 0.6105588690081731, "grad_norm": 2.114495277404785, "learning_rate": 1.3909547367350222e-05, "loss": 0.1051, "step": 11056 }, { "epoch": 0.6106140932184669, "grad_norm": 4.6157450675964355, "learning_rate": 1.3906140059844174e-05, "loss": 0.6167, "step": 11057 }, { "epoch": 0.6106693174287607, "grad_norm": 0.29157763719558716, "learning_rate": 1.3902732947298047e-05, "loss": 0.0061, "step": 11058 }, { "epoch": 0.6107245416390545, "grad_norm": 2.7666988372802734, "learning_rate": 1.3899326029820866e-05, "loss": 0.1848, "step": 11059 }, { "epoch": 0.6107797658493483, "grad_norm": 2.2903847694396973, "learning_rate": 1.3895919307521599e-05, "loss": 0.4662, "step": 11060 }, { "epoch": 0.6108349900596421, "grad_norm": 0.43767717480659485, "learning_rate": 1.3892512780509257e-05, "loss": 0.0142, "step": 11061 }, { "epoch": 0.610890214269936, "grad_norm": 0.029321841895580292, "learning_rate": 1.3889106448892815e-05, "loss": 0.0009, "step": 11062 }, { "epoch": 0.6109454384802298, "grad_norm": 3.0500409603118896, "learning_rate": 1.3885700312781258e-05, "loss": 0.3001, "step": 11063 }, { "epoch": 0.6110006626905236, "grad_norm": 3.0275380611419678, "learning_rate": 1.3882294372283551e-05, "loss": 0.3217, "step": 11064 }, { "epoch": 0.6110558869008174, "grad_norm": 1.7804783582687378, "learning_rate": 1.3878888627508666e-05, "loss": 0.1107, "step": 11065 }, { "epoch": 0.6111111111111112, "grad_norm": 0.12187688797712326, "learning_rate": 1.3875483078565556e-05, "loss": 0.0026, "step": 11066 }, { "epoch": 0.6111663353214049, "grad_norm": 0.7489770650863647, "learning_rate": 1.387207772556319e-05, "loss": 0.0186, "step": 11067 }, { "epoch": 0.6112215595316987, "grad_norm": 0.11728501319885254, "learning_rate": 1.386867256861049e-05, "loss": 0.0032, "step": 11068 }, { "epoch": 0.6112767837419925, "grad_norm": 2.994861364364624, "learning_rate": 1.3865267607816417e-05, "loss": 0.3621, "step": 11069 }, { "epoch": 0.6113320079522863, "grad_norm": 2.867774724960327, "learning_rate": 1.3861862843289893e-05, "loss": 0.2082, "step": 11070 }, { "epoch": 0.6113872321625801, "grad_norm": 2.1810436248779297, "learning_rate": 1.3858458275139857e-05, "loss": 0.0528, "step": 11071 }, { "epoch": 0.6114424563728739, "grad_norm": 1.1858797073364258, "learning_rate": 1.3855053903475227e-05, "loss": 0.022, "step": 11072 }, { "epoch": 0.6114976805831677, "grad_norm": 1.858478307723999, "learning_rate": 1.3851649728404901e-05, "loss": 0.2488, "step": 11073 }, { "epoch": 0.6115529047934615, "grad_norm": 0.17039638757705688, "learning_rate": 1.384824575003782e-05, "loss": 0.0042, "step": 11074 }, { "epoch": 0.6116081290037553, "grad_norm": 0.2523013651371002, "learning_rate": 1.3844841968482863e-05, "loss": 0.0047, "step": 11075 }, { "epoch": 0.6116633532140491, "grad_norm": 3.1914381980895996, "learning_rate": 1.3841438383848935e-05, "loss": 0.4355, "step": 11076 }, { "epoch": 0.6117185774243429, "grad_norm": 0.0719207152724266, "learning_rate": 1.3838034996244924e-05, "loss": 0.002, "step": 11077 }, { "epoch": 0.6117738016346366, "grad_norm": 0.157398983836174, "learning_rate": 1.3834631805779721e-05, "loss": 0.0061, "step": 11078 }, { "epoch": 0.6118290258449304, "grad_norm": 0.016115397214889526, "learning_rate": 1.3831228812562193e-05, "loss": 0.0006, "step": 11079 }, { "epoch": 0.6118842500552242, "grad_norm": 0.2929503619670868, "learning_rate": 1.3827826016701228e-05, "loss": 0.0098, "step": 11080 }, { "epoch": 0.611939474265518, "grad_norm": 0.17269833385944366, "learning_rate": 1.3824423418305663e-05, "loss": 0.0042, "step": 11081 }, { "epoch": 0.6119946984758118, "grad_norm": 0.6205500364303589, "learning_rate": 1.3821021017484389e-05, "loss": 0.0179, "step": 11082 }, { "epoch": 0.6120499226861056, "grad_norm": 2.3440797328948975, "learning_rate": 1.3817618814346236e-05, "loss": 0.0429, "step": 11083 }, { "epoch": 0.6121051468963994, "grad_norm": 0.02241857722401619, "learning_rate": 1.3814216809000058e-05, "loss": 0.0008, "step": 11084 }, { "epoch": 0.6121603711066932, "grad_norm": 1.1926270723342896, "learning_rate": 1.3810815001554694e-05, "loss": 0.0557, "step": 11085 }, { "epoch": 0.612215595316987, "grad_norm": 0.17541727423667908, "learning_rate": 1.3807413392118983e-05, "loss": 0.0045, "step": 11086 }, { "epoch": 0.6122708195272808, "grad_norm": 2.293644666671753, "learning_rate": 1.3804011980801739e-05, "loss": 0.193, "step": 11087 }, { "epoch": 0.6123260437375746, "grad_norm": 2.763204574584961, "learning_rate": 1.3800610767711802e-05, "loss": 0.6156, "step": 11088 }, { "epoch": 0.6123812679478683, "grad_norm": 0.3904046416282654, "learning_rate": 1.379720975295796e-05, "loss": 0.0097, "step": 11089 }, { "epoch": 0.6124364921581621, "grad_norm": 2.3430094718933105, "learning_rate": 1.3793808936649052e-05, "loss": 0.207, "step": 11090 }, { "epoch": 0.6124917163684559, "grad_norm": 3.2068605422973633, "learning_rate": 1.3790408318893855e-05, "loss": 1.0237, "step": 11091 }, { "epoch": 0.6125469405787497, "grad_norm": 0.4726293087005615, "learning_rate": 1.3787007899801177e-05, "loss": 0.0071, "step": 11092 }, { "epoch": 0.6126021647890435, "grad_norm": 2.9838521480560303, "learning_rate": 1.3783607679479802e-05, "loss": 0.1338, "step": 11093 }, { "epoch": 0.6126573889993373, "grad_norm": 5.237642288208008, "learning_rate": 1.3780207658038517e-05, "loss": 1.5045, "step": 11094 }, { "epoch": 0.6127126132096311, "grad_norm": 1.95430588722229, "learning_rate": 1.3776807835586092e-05, "loss": 0.1397, "step": 11095 }, { "epoch": 0.6127678374199249, "grad_norm": 0.058657217770814896, "learning_rate": 1.3773408212231308e-05, "loss": 0.002, "step": 11096 }, { "epoch": 0.6128230616302187, "grad_norm": 0.054095666855573654, "learning_rate": 1.3770008788082914e-05, "loss": 0.0019, "step": 11097 }, { "epoch": 0.6128782858405125, "grad_norm": 4.642754077911377, "learning_rate": 1.3766609563249684e-05, "loss": 0.5327, "step": 11098 }, { "epoch": 0.6129335100508063, "grad_norm": 3.4930646419525146, "learning_rate": 1.3763210537840351e-05, "loss": 0.5632, "step": 11099 }, { "epoch": 0.6129887342611001, "grad_norm": 4.0969014167785645, "learning_rate": 1.3759811711963673e-05, "loss": 0.4303, "step": 11100 }, { "epoch": 0.6130439584713938, "grad_norm": 2.793273687362671, "learning_rate": 1.3756413085728379e-05, "loss": 0.1758, "step": 11101 }, { "epoch": 0.6130991826816876, "grad_norm": 2.3448116779327393, "learning_rate": 1.3753014659243209e-05, "loss": 0.0666, "step": 11102 }, { "epoch": 0.6131544068919814, "grad_norm": 0.03667164966464043, "learning_rate": 1.374961643261688e-05, "loss": 0.0012, "step": 11103 }, { "epoch": 0.6132096311022752, "grad_norm": 2.096925973892212, "learning_rate": 1.374621840595812e-05, "loss": 0.1995, "step": 11104 }, { "epoch": 0.613264855312569, "grad_norm": 0.2801986038684845, "learning_rate": 1.3742820579375633e-05, "loss": 0.0075, "step": 11105 }, { "epoch": 0.6133200795228628, "grad_norm": 2.359632730484009, "learning_rate": 1.3739422952978139e-05, "loss": 0.1971, "step": 11106 }, { "epoch": 0.6133753037331566, "grad_norm": 0.33924269676208496, "learning_rate": 1.3736025526874317e-05, "loss": 0.0057, "step": 11107 }, { "epoch": 0.6134305279434504, "grad_norm": 0.02620658464729786, "learning_rate": 1.3732628301172877e-05, "loss": 0.0009, "step": 11108 }, { "epoch": 0.6134857521537442, "grad_norm": 0.8136304616928101, "learning_rate": 1.3729231275982495e-05, "loss": 0.0165, "step": 11109 }, { "epoch": 0.613540976364038, "grad_norm": 5.23870849609375, "learning_rate": 1.3725834451411858e-05, "loss": 1.2285, "step": 11110 }, { "epoch": 0.6135962005743318, "grad_norm": 0.04821568354964256, "learning_rate": 1.3722437827569638e-05, "loss": 0.0013, "step": 11111 }, { "epoch": 0.6136514247846255, "grad_norm": 0.2455073893070221, "learning_rate": 1.3719041404564509e-05, "loss": 0.0069, "step": 11112 }, { "epoch": 0.6137066489949193, "grad_norm": 0.3399173617362976, "learning_rate": 1.371564518250512e-05, "loss": 0.0117, "step": 11113 }, { "epoch": 0.6137618732052131, "grad_norm": 2.7838504314422607, "learning_rate": 1.371224916150014e-05, "loss": 0.1179, "step": 11114 }, { "epoch": 0.6138170974155069, "grad_norm": 2.24123477935791, "learning_rate": 1.37088533416582e-05, "loss": 0.2156, "step": 11115 }, { "epoch": 0.6138723216258007, "grad_norm": 2.7501561641693115, "learning_rate": 1.370545772308796e-05, "loss": 0.5311, "step": 11116 }, { "epoch": 0.6139275458360945, "grad_norm": 2.617319107055664, "learning_rate": 1.3702062305898043e-05, "loss": 0.2818, "step": 11117 }, { "epoch": 0.6139827700463883, "grad_norm": 0.7275051474571228, "learning_rate": 1.3698667090197084e-05, "loss": 0.0171, "step": 11118 }, { "epoch": 0.6140379942566822, "grad_norm": 0.07839882373809814, "learning_rate": 1.36952720760937e-05, "loss": 0.003, "step": 11119 }, { "epoch": 0.614093218466976, "grad_norm": 4.020297050476074, "learning_rate": 1.3691877263696516e-05, "loss": 0.0757, "step": 11120 }, { "epoch": 0.6141484426772698, "grad_norm": 0.04398458078503609, "learning_rate": 1.3688482653114133e-05, "loss": 0.001, "step": 11121 }, { "epoch": 0.6142036668875636, "grad_norm": 0.13510030508041382, "learning_rate": 1.3685088244455165e-05, "loss": 0.0038, "step": 11122 }, { "epoch": 0.6142588910978573, "grad_norm": 2.1283950805664062, "learning_rate": 1.3681694037828188e-05, "loss": 0.1833, "step": 11123 }, { "epoch": 0.614314115308151, "grad_norm": 0.11238173395395279, "learning_rate": 1.367830003334182e-05, "loss": 0.0034, "step": 11124 }, { "epoch": 0.6143693395184449, "grad_norm": 0.12287446111440659, "learning_rate": 1.3674906231104625e-05, "loss": 0.0051, "step": 11125 }, { "epoch": 0.6144245637287387, "grad_norm": 0.8273420333862305, "learning_rate": 1.3671512631225187e-05, "loss": 0.009, "step": 11126 }, { "epoch": 0.6144797879390325, "grad_norm": 0.13251811265945435, "learning_rate": 1.3668119233812074e-05, "loss": 0.0039, "step": 11127 }, { "epoch": 0.6145350121493263, "grad_norm": 1.1156651973724365, "learning_rate": 1.3664726038973859e-05, "loss": 0.0339, "step": 11128 }, { "epoch": 0.6145902363596201, "grad_norm": 2.501417875289917, "learning_rate": 1.3661333046819088e-05, "loss": 0.1921, "step": 11129 }, { "epoch": 0.6146454605699139, "grad_norm": 0.04696759954094887, "learning_rate": 1.3657940257456326e-05, "loss": 0.0012, "step": 11130 }, { "epoch": 0.6147006847802077, "grad_norm": 0.07181272655725479, "learning_rate": 1.3654547670994105e-05, "loss": 0.0016, "step": 11131 }, { "epoch": 0.6147559089905015, "grad_norm": 0.28884825110435486, "learning_rate": 1.3651155287540964e-05, "loss": 0.0115, "step": 11132 }, { "epoch": 0.6148111332007953, "grad_norm": 0.053949419409036636, "learning_rate": 1.3647763107205445e-05, "loss": 0.0014, "step": 11133 }, { "epoch": 0.614866357411089, "grad_norm": 2.952274799346924, "learning_rate": 1.3644371130096067e-05, "loss": 0.3445, "step": 11134 }, { "epoch": 0.6149215816213828, "grad_norm": 0.10438220202922821, "learning_rate": 1.3640979356321351e-05, "loss": 0.0037, "step": 11135 }, { "epoch": 0.6149768058316766, "grad_norm": 0.87205570936203, "learning_rate": 1.3637587785989806e-05, "loss": 0.0332, "step": 11136 }, { "epoch": 0.6150320300419704, "grad_norm": 0.052241113036870956, "learning_rate": 1.3634196419209946e-05, "loss": 0.0014, "step": 11137 }, { "epoch": 0.6150872542522642, "grad_norm": 0.10684047639369965, "learning_rate": 1.3630805256090263e-05, "loss": 0.0037, "step": 11138 }, { "epoch": 0.615142478462558, "grad_norm": 0.13420948386192322, "learning_rate": 1.3627414296739253e-05, "loss": 0.006, "step": 11139 }, { "epoch": 0.6151977026728518, "grad_norm": 0.03891972452402115, "learning_rate": 1.3624023541265397e-05, "loss": 0.001, "step": 11140 }, { "epoch": 0.6152529268831456, "grad_norm": 5.567626953125, "learning_rate": 1.3620632989777183e-05, "loss": 0.4678, "step": 11141 }, { "epoch": 0.6153081510934394, "grad_norm": 0.1878592073917389, "learning_rate": 1.3617242642383076e-05, "loss": 0.005, "step": 11142 }, { "epoch": 0.6153633753037332, "grad_norm": 1.0204880237579346, "learning_rate": 1.3613852499191553e-05, "loss": 0.0189, "step": 11143 }, { "epoch": 0.615418599514027, "grad_norm": 0.4492814540863037, "learning_rate": 1.3610462560311067e-05, "loss": 0.0118, "step": 11144 }, { "epoch": 0.6154738237243207, "grad_norm": 0.2079690545797348, "learning_rate": 1.360707282585008e-05, "loss": 0.0054, "step": 11145 }, { "epoch": 0.6155290479346145, "grad_norm": 4.365381240844727, "learning_rate": 1.360368329591702e-05, "loss": 1.163, "step": 11146 }, { "epoch": 0.6155842721449083, "grad_norm": 0.2452029138803482, "learning_rate": 1.3600293970620355e-05, "loss": 0.0073, "step": 11147 }, { "epoch": 0.6156394963552021, "grad_norm": 5.623844146728516, "learning_rate": 1.3596904850068496e-05, "loss": 0.4509, "step": 11148 }, { "epoch": 0.6156947205654959, "grad_norm": 0.4859681725502014, "learning_rate": 1.3593515934369885e-05, "loss": 0.0119, "step": 11149 }, { "epoch": 0.6157499447757897, "grad_norm": 0.46676647663116455, "learning_rate": 1.3590127223632932e-05, "loss": 0.0115, "step": 11150 }, { "epoch": 0.6158051689860835, "grad_norm": 1.8159364461898804, "learning_rate": 1.3586738717966062e-05, "loss": 0.4318, "step": 11151 }, { "epoch": 0.6158603931963773, "grad_norm": 0.33209890127182007, "learning_rate": 1.3583350417477674e-05, "loss": 0.012, "step": 11152 }, { "epoch": 0.6159156174066711, "grad_norm": 0.08950931578874588, "learning_rate": 1.3579962322276182e-05, "loss": 0.0027, "step": 11153 }, { "epoch": 0.6159708416169649, "grad_norm": 0.09806685894727707, "learning_rate": 1.357657443246996e-05, "loss": 0.0039, "step": 11154 }, { "epoch": 0.6160260658272587, "grad_norm": 0.05911165103316307, "learning_rate": 1.3573186748167422e-05, "loss": 0.0019, "step": 11155 }, { "epoch": 0.6160812900375524, "grad_norm": 3.978332996368408, "learning_rate": 1.3569799269476926e-05, "loss": 0.7734, "step": 11156 }, { "epoch": 0.6161365142478462, "grad_norm": 3.2008328437805176, "learning_rate": 1.356641199650686e-05, "loss": 0.2758, "step": 11157 }, { "epoch": 0.61619173845814, "grad_norm": 0.026839926838874817, "learning_rate": 1.3563024929365591e-05, "loss": 0.0008, "step": 11158 }, { "epoch": 0.6162469626684338, "grad_norm": 4.312629222869873, "learning_rate": 1.355963806816148e-05, "loss": 0.3061, "step": 11159 }, { "epoch": 0.6163021868787276, "grad_norm": 5.42092227935791, "learning_rate": 1.3556251413002879e-05, "loss": 0.1034, "step": 11160 }, { "epoch": 0.6163574110890214, "grad_norm": 0.4937990605831146, "learning_rate": 1.3552864963998147e-05, "loss": 0.0147, "step": 11161 }, { "epoch": 0.6164126352993152, "grad_norm": 4.8729095458984375, "learning_rate": 1.3549478721255608e-05, "loss": 0.5586, "step": 11162 }, { "epoch": 0.616467859509609, "grad_norm": 0.13834203779697418, "learning_rate": 1.3546092684883621e-05, "loss": 0.0067, "step": 11163 }, { "epoch": 0.6165230837199028, "grad_norm": 0.011281839571893215, "learning_rate": 1.3542706854990493e-05, "loss": 0.0003, "step": 11164 }, { "epoch": 0.6165783079301966, "grad_norm": 0.4441945254802704, "learning_rate": 1.3539321231684562e-05, "loss": 0.0121, "step": 11165 }, { "epoch": 0.6166335321404904, "grad_norm": 2.73066782951355, "learning_rate": 1.3535935815074131e-05, "loss": 0.1345, "step": 11166 }, { "epoch": 0.6166887563507841, "grad_norm": 0.014092265628278255, "learning_rate": 1.3532550605267521e-05, "loss": 0.0006, "step": 11167 }, { "epoch": 0.6167439805610779, "grad_norm": 0.7397370934486389, "learning_rate": 1.3529165602373025e-05, "loss": 0.0244, "step": 11168 }, { "epoch": 0.6167992047713717, "grad_norm": 1.7126961946487427, "learning_rate": 1.3525780806498952e-05, "loss": 0.1424, "step": 11169 }, { "epoch": 0.6168544289816655, "grad_norm": 4.428406715393066, "learning_rate": 1.3522396217753568e-05, "loss": 0.8581, "step": 11170 }, { "epoch": 0.6169096531919593, "grad_norm": 1.5496816635131836, "learning_rate": 1.3519011836245182e-05, "loss": 0.1636, "step": 11171 }, { "epoch": 0.6169648774022531, "grad_norm": 18.219139099121094, "learning_rate": 1.3515627662082053e-05, "loss": 0.4611, "step": 11172 }, { "epoch": 0.617020101612547, "grad_norm": 2.0077803134918213, "learning_rate": 1.3512243695372455e-05, "loss": 0.1348, "step": 11173 }, { "epoch": 0.6170753258228407, "grad_norm": 2.7958972454071045, "learning_rate": 1.3508859936224653e-05, "loss": 0.2337, "step": 11174 }, { "epoch": 0.6171305500331346, "grad_norm": 0.0805373340845108, "learning_rate": 1.3505476384746899e-05, "loss": 0.0031, "step": 11175 }, { "epoch": 0.6171857742434284, "grad_norm": 6.22196102142334, "learning_rate": 1.3502093041047442e-05, "loss": 1.2755, "step": 11176 }, { "epoch": 0.6172409984537222, "grad_norm": 0.20717214047908783, "learning_rate": 1.3498709905234532e-05, "loss": 0.0065, "step": 11177 }, { "epoch": 0.617296222664016, "grad_norm": 3.510984420776367, "learning_rate": 1.3495326977416396e-05, "loss": 0.218, "step": 11178 }, { "epoch": 0.6173514468743097, "grad_norm": 0.9706912040710449, "learning_rate": 1.349194425770128e-05, "loss": 0.0246, "step": 11179 }, { "epoch": 0.6174066710846035, "grad_norm": 0.4710954427719116, "learning_rate": 1.3488561746197383e-05, "loss": 0.0227, "step": 11180 }, { "epoch": 0.6174618952948973, "grad_norm": 4.931197166442871, "learning_rate": 1.3485179443012936e-05, "loss": 0.9088, "step": 11181 }, { "epoch": 0.6175171195051911, "grad_norm": 0.08222774416208267, "learning_rate": 1.3481797348256143e-05, "loss": 0.0024, "step": 11182 }, { "epoch": 0.6175723437154849, "grad_norm": 3.6434860229492188, "learning_rate": 1.3478415462035215e-05, "loss": 0.2733, "step": 11183 }, { "epoch": 0.6176275679257787, "grad_norm": 0.04371466860175133, "learning_rate": 1.3475033784458335e-05, "loss": 0.0012, "step": 11184 }, { "epoch": 0.6176827921360725, "grad_norm": 0.7286311388015747, "learning_rate": 1.3471652315633708e-05, "loss": 0.0119, "step": 11185 }, { "epoch": 0.6177380163463663, "grad_norm": 1.9047750234603882, "learning_rate": 1.3468271055669502e-05, "loss": 0.0695, "step": 11186 }, { "epoch": 0.6177932405566601, "grad_norm": 3.612614154815674, "learning_rate": 1.3464890004673907e-05, "loss": 0.768, "step": 11187 }, { "epoch": 0.6178484647669539, "grad_norm": 0.01302473247051239, "learning_rate": 1.346150916275508e-05, "loss": 0.0005, "step": 11188 }, { "epoch": 0.6179036889772477, "grad_norm": 0.05493941903114319, "learning_rate": 1.3458128530021193e-05, "loss": 0.0021, "step": 11189 }, { "epoch": 0.6179589131875414, "grad_norm": 2.925879955291748, "learning_rate": 1.3454748106580394e-05, "loss": 0.5047, "step": 11190 }, { "epoch": 0.6180141373978352, "grad_norm": 0.03365299105644226, "learning_rate": 1.3451367892540839e-05, "loss": 0.0009, "step": 11191 }, { "epoch": 0.618069361608129, "grad_norm": 1.6667745113372803, "learning_rate": 1.3447987888010672e-05, "loss": 0.3626, "step": 11192 }, { "epoch": 0.6181245858184228, "grad_norm": 0.037685103714466095, "learning_rate": 1.3444608093098015e-05, "loss": 0.0012, "step": 11193 }, { "epoch": 0.6181798100287166, "grad_norm": 2.997885227203369, "learning_rate": 1.3441228507911019e-05, "loss": 0.3001, "step": 11194 }, { "epoch": 0.6182350342390104, "grad_norm": 3.933741807937622, "learning_rate": 1.3437849132557786e-05, "loss": 0.1399, "step": 11195 }, { "epoch": 0.6182902584493042, "grad_norm": 0.16738441586494446, "learning_rate": 1.3434469967146446e-05, "loss": 0.0039, "step": 11196 }, { "epoch": 0.618345482659598, "grad_norm": 2.306274890899658, "learning_rate": 1.3431091011785098e-05, "loss": 0.4465, "step": 11197 }, { "epoch": 0.6184007068698918, "grad_norm": 0.01720353774726391, "learning_rate": 1.3427712266581856e-05, "loss": 0.0004, "step": 11198 }, { "epoch": 0.6184559310801856, "grad_norm": 0.21099379658699036, "learning_rate": 1.3424333731644803e-05, "loss": 0.0035, "step": 11199 }, { "epoch": 0.6185111552904794, "grad_norm": 0.04626499488949776, "learning_rate": 1.3420955407082042e-05, "loss": 0.0014, "step": 11200 }, { "epoch": 0.6185663795007731, "grad_norm": 2.497249126434326, "learning_rate": 1.3417577293001633e-05, "loss": 0.1174, "step": 11201 }, { "epoch": 0.6186216037110669, "grad_norm": 2.587946653366089, "learning_rate": 1.3414199389511682e-05, "loss": 0.1609, "step": 11202 }, { "epoch": 0.6186768279213607, "grad_norm": 2.947572708129883, "learning_rate": 1.3410821696720233e-05, "loss": 0.2959, "step": 11203 }, { "epoch": 0.6187320521316545, "grad_norm": 0.06594915688037872, "learning_rate": 1.3407444214735356e-05, "loss": 0.0017, "step": 11204 }, { "epoch": 0.6187872763419483, "grad_norm": 2.267221689224243, "learning_rate": 1.3404066943665108e-05, "loss": 0.2542, "step": 11205 }, { "epoch": 0.6188425005522421, "grad_norm": 0.02139396406710148, "learning_rate": 1.3400689883617539e-05, "loss": 0.0007, "step": 11206 }, { "epoch": 0.6188977247625359, "grad_norm": 4.66049861907959, "learning_rate": 1.3397313034700684e-05, "loss": 0.3282, "step": 11207 }, { "epoch": 0.6189529489728297, "grad_norm": 0.33220532536506653, "learning_rate": 1.3393936397022587e-05, "loss": 0.007, "step": 11208 }, { "epoch": 0.6190081731831235, "grad_norm": 2.813832998275757, "learning_rate": 1.3390559970691261e-05, "loss": 0.2007, "step": 11209 }, { "epoch": 0.6190633973934173, "grad_norm": 3.669401168823242, "learning_rate": 1.3387183755814749e-05, "loss": 1.0785, "step": 11210 }, { "epoch": 0.6191186216037111, "grad_norm": 0.9974340796470642, "learning_rate": 1.338380775250105e-05, "loss": 0.0197, "step": 11211 }, { "epoch": 0.6191738458140048, "grad_norm": 4.18177604675293, "learning_rate": 1.3380431960858178e-05, "loss": 0.4783, "step": 11212 }, { "epoch": 0.6192290700242986, "grad_norm": 4.513016700744629, "learning_rate": 1.337705638099413e-05, "loss": 0.8131, "step": 11213 }, { "epoch": 0.6192842942345924, "grad_norm": 4.312724590301514, "learning_rate": 1.3373681013016904e-05, "loss": 0.4953, "step": 11214 }, { "epoch": 0.6193395184448862, "grad_norm": 0.020116616040468216, "learning_rate": 1.3370305857034485e-05, "loss": 0.0005, "step": 11215 }, { "epoch": 0.61939474265518, "grad_norm": 0.02804061397910118, "learning_rate": 1.336693091315486e-05, "loss": 0.0008, "step": 11216 }, { "epoch": 0.6194499668654738, "grad_norm": 0.08521868288516998, "learning_rate": 1.3363556181485992e-05, "loss": 0.0034, "step": 11217 }, { "epoch": 0.6195051910757676, "grad_norm": 0.09894918650388718, "learning_rate": 1.3360181662135868e-05, "loss": 0.0034, "step": 11218 }, { "epoch": 0.6195604152860614, "grad_norm": 3.586183547973633, "learning_rate": 1.3356807355212423e-05, "loss": 0.5365, "step": 11219 }, { "epoch": 0.6196156394963552, "grad_norm": 0.05375286564230919, "learning_rate": 1.3353433260823625e-05, "loss": 0.0014, "step": 11220 }, { "epoch": 0.619670863706649, "grad_norm": 0.06905780732631683, "learning_rate": 1.3350059379077421e-05, "loss": 0.0019, "step": 11221 }, { "epoch": 0.6197260879169428, "grad_norm": 1.7274366617202759, "learning_rate": 1.3346685710081748e-05, "loss": 0.138, "step": 11222 }, { "epoch": 0.6197813121272365, "grad_norm": 0.04030619189143181, "learning_rate": 1.3343312253944538e-05, "loss": 0.0017, "step": 11223 }, { "epoch": 0.6198365363375303, "grad_norm": 3.4363670349121094, "learning_rate": 1.3339939010773723e-05, "loss": 0.5983, "step": 11224 }, { "epoch": 0.6198917605478241, "grad_norm": 0.33808600902557373, "learning_rate": 1.3336565980677216e-05, "loss": 0.0096, "step": 11225 }, { "epoch": 0.6199469847581179, "grad_norm": 3.365842819213867, "learning_rate": 1.3333193163762943e-05, "loss": 0.1109, "step": 11226 }, { "epoch": 0.6200022089684117, "grad_norm": 1.059943675994873, "learning_rate": 1.332982056013879e-05, "loss": 0.0701, "step": 11227 }, { "epoch": 0.6200574331787055, "grad_norm": 0.647296130657196, "learning_rate": 1.3326448169912674e-05, "loss": 0.0204, "step": 11228 }, { "epoch": 0.6201126573889993, "grad_norm": 4.949034690856934, "learning_rate": 1.3323075993192471e-05, "loss": 0.4067, "step": 11229 }, { "epoch": 0.6201678815992931, "grad_norm": 0.08599457144737244, "learning_rate": 1.331970403008608e-05, "loss": 0.0024, "step": 11230 }, { "epoch": 0.620223105809587, "grad_norm": 4.083098411560059, "learning_rate": 1.3316332280701375e-05, "loss": 0.2863, "step": 11231 }, { "epoch": 0.6202783300198808, "grad_norm": 0.03938823193311691, "learning_rate": 1.3312960745146229e-05, "loss": 0.0012, "step": 11232 }, { "epoch": 0.6203335542301746, "grad_norm": 0.0954759493470192, "learning_rate": 1.3309589423528502e-05, "loss": 0.0034, "step": 11233 }, { "epoch": 0.6203887784404682, "grad_norm": 1.965240716934204, "learning_rate": 1.3306218315956065e-05, "loss": 0.0772, "step": 11234 }, { "epoch": 0.620444002650762, "grad_norm": 0.07221609354019165, "learning_rate": 1.3302847422536747e-05, "loss": 0.002, "step": 11235 }, { "epoch": 0.6204992268610559, "grad_norm": 0.10494513064622879, "learning_rate": 1.3299476743378418e-05, "loss": 0.0027, "step": 11236 }, { "epoch": 0.6205544510713497, "grad_norm": 0.7783161997795105, "learning_rate": 1.3296106278588897e-05, "loss": 0.0302, "step": 11237 }, { "epoch": 0.6206096752816435, "grad_norm": 0.21095198392868042, "learning_rate": 1.3292736028276024e-05, "loss": 0.0052, "step": 11238 }, { "epoch": 0.6206648994919373, "grad_norm": 4.020984172821045, "learning_rate": 1.3289365992547617e-05, "loss": 0.6465, "step": 11239 }, { "epoch": 0.6207201237022311, "grad_norm": 0.022961130365729332, "learning_rate": 1.3285996171511499e-05, "loss": 0.0009, "step": 11240 }, { "epoch": 0.6207753479125249, "grad_norm": 3.1287569999694824, "learning_rate": 1.3282626565275476e-05, "loss": 0.4887, "step": 11241 }, { "epoch": 0.6208305721228187, "grad_norm": 0.05621255561709404, "learning_rate": 1.3279257173947358e-05, "loss": 0.0013, "step": 11242 }, { "epoch": 0.6208857963331125, "grad_norm": 0.20566344261169434, "learning_rate": 1.3275887997634925e-05, "loss": 0.0053, "step": 11243 }, { "epoch": 0.6209410205434063, "grad_norm": 1.9143344163894653, "learning_rate": 1.327251903644599e-05, "loss": 0.5657, "step": 11244 }, { "epoch": 0.6209962447537001, "grad_norm": 0.01084255799651146, "learning_rate": 1.3269150290488314e-05, "loss": 0.0004, "step": 11245 }, { "epoch": 0.6210514689639938, "grad_norm": 5.222980499267578, "learning_rate": 1.3265781759869687e-05, "loss": 0.3105, "step": 11246 }, { "epoch": 0.6211066931742876, "grad_norm": 3.8440160751342773, "learning_rate": 1.326241344469787e-05, "loss": 0.241, "step": 11247 }, { "epoch": 0.6211619173845814, "grad_norm": 0.30289357900619507, "learning_rate": 1.3259045345080633e-05, "loss": 0.0044, "step": 11248 }, { "epoch": 0.6212171415948752, "grad_norm": 2.1549060344696045, "learning_rate": 1.3255677461125717e-05, "loss": 0.0813, "step": 11249 }, { "epoch": 0.621272365805169, "grad_norm": 0.2554756700992584, "learning_rate": 1.3252309792940891e-05, "loss": 0.0071, "step": 11250 }, { "epoch": 0.6213275900154628, "grad_norm": 0.8782750964164734, "learning_rate": 1.3248942340633879e-05, "loss": 0.0267, "step": 11251 }, { "epoch": 0.6213828142257566, "grad_norm": 3.047201156616211, "learning_rate": 1.3245575104312418e-05, "loss": 0.7515, "step": 11252 }, { "epoch": 0.6214380384360504, "grad_norm": 2.6793534755706787, "learning_rate": 1.3242208084084243e-05, "loss": 0.3195, "step": 11253 }, { "epoch": 0.6214932626463442, "grad_norm": 1.5512176752090454, "learning_rate": 1.3238841280057066e-05, "loss": 0.0809, "step": 11254 }, { "epoch": 0.621548486856638, "grad_norm": 0.33684495091438293, "learning_rate": 1.3235474692338608e-05, "loss": 0.0076, "step": 11255 }, { "epoch": 0.6216037110669318, "grad_norm": 0.45186519622802734, "learning_rate": 1.3232108321036568e-05, "loss": 0.011, "step": 11256 }, { "epoch": 0.6216589352772255, "grad_norm": 1.7255395650863647, "learning_rate": 1.3228742166258658e-05, "loss": 0.1422, "step": 11257 }, { "epoch": 0.6217141594875193, "grad_norm": 0.3802388906478882, "learning_rate": 1.3225376228112556e-05, "loss": 0.0073, "step": 11258 }, { "epoch": 0.6217693836978131, "grad_norm": 0.029369119554758072, "learning_rate": 1.3222010506705958e-05, "loss": 0.0008, "step": 11259 }, { "epoch": 0.6218246079081069, "grad_norm": 3.5191023349761963, "learning_rate": 1.3218645002146535e-05, "loss": 0.2682, "step": 11260 }, { "epoch": 0.6218798321184007, "grad_norm": 0.038089171051979065, "learning_rate": 1.3215279714541971e-05, "loss": 0.0014, "step": 11261 }, { "epoch": 0.6219350563286945, "grad_norm": 0.027501415461301804, "learning_rate": 1.3211914643999917e-05, "loss": 0.0012, "step": 11262 }, { "epoch": 0.6219902805389883, "grad_norm": 3.7317333221435547, "learning_rate": 1.3208549790628044e-05, "loss": 0.6927, "step": 11263 }, { "epoch": 0.6220455047492821, "grad_norm": 2.3212058544158936, "learning_rate": 1.3205185154533994e-05, "loss": 0.2169, "step": 11264 }, { "epoch": 0.6221007289595759, "grad_norm": 2.3907463550567627, "learning_rate": 1.3201820735825423e-05, "loss": 0.2977, "step": 11265 }, { "epoch": 0.6221559531698697, "grad_norm": 0.053332746028900146, "learning_rate": 1.3198456534609948e-05, "loss": 0.0024, "step": 11266 }, { "epoch": 0.6222111773801635, "grad_norm": 2.4925427436828613, "learning_rate": 1.3195092550995222e-05, "loss": 0.3326, "step": 11267 }, { "epoch": 0.6222664015904572, "grad_norm": 2.711122989654541, "learning_rate": 1.3191728785088853e-05, "loss": 0.3753, "step": 11268 }, { "epoch": 0.622321625800751, "grad_norm": 0.156607523560524, "learning_rate": 1.3188365236998463e-05, "loss": 0.0036, "step": 11269 }, { "epoch": 0.6223768500110448, "grad_norm": 0.18039090931415558, "learning_rate": 1.3185001906831658e-05, "loss": 0.0037, "step": 11270 }, { "epoch": 0.6224320742213386, "grad_norm": 0.2978840172290802, "learning_rate": 1.318163879469605e-05, "loss": 0.0065, "step": 11271 }, { "epoch": 0.6224872984316324, "grad_norm": 2.27000093460083, "learning_rate": 1.317827590069922e-05, "loss": 0.2051, "step": 11272 }, { "epoch": 0.6225425226419262, "grad_norm": 3.9391415119171143, "learning_rate": 1.3174913224948775e-05, "loss": 0.9455, "step": 11273 }, { "epoch": 0.62259774685222, "grad_norm": 0.8831945061683655, "learning_rate": 1.3171550767552272e-05, "loss": 0.0197, "step": 11274 }, { "epoch": 0.6226529710625138, "grad_norm": 0.49279874563217163, "learning_rate": 1.3168188528617315e-05, "loss": 0.0165, "step": 11275 }, { "epoch": 0.6227081952728076, "grad_norm": 0.16740991175174713, "learning_rate": 1.3164826508251447e-05, "loss": 0.0045, "step": 11276 }, { "epoch": 0.6227634194831014, "grad_norm": 0.2714060842990875, "learning_rate": 1.316146470656224e-05, "loss": 0.0099, "step": 11277 }, { "epoch": 0.6228186436933952, "grad_norm": 2.8727917671203613, "learning_rate": 1.3158103123657244e-05, "loss": 0.475, "step": 11278 }, { "epoch": 0.6228738679036889, "grad_norm": 3.3123795986175537, "learning_rate": 1.315474175964401e-05, "loss": 0.1325, "step": 11279 }, { "epoch": 0.6229290921139827, "grad_norm": 0.2624818980693817, "learning_rate": 1.3151380614630069e-05, "loss": 0.0076, "step": 11280 }, { "epoch": 0.6229843163242765, "grad_norm": 2.0340614318847656, "learning_rate": 1.3148019688722971e-05, "loss": 0.1414, "step": 11281 }, { "epoch": 0.6230395405345703, "grad_norm": 1.555530309677124, "learning_rate": 1.3144658982030216e-05, "loss": 0.2439, "step": 11282 }, { "epoch": 0.6230947647448641, "grad_norm": 1.0995525121688843, "learning_rate": 1.3141298494659349e-05, "loss": 0.1195, "step": 11283 }, { "epoch": 0.6231499889551579, "grad_norm": 4.952154636383057, "learning_rate": 1.3137938226717859e-05, "loss": 1.3524, "step": 11284 }, { "epoch": 0.6232052131654517, "grad_norm": 3.236966133117676, "learning_rate": 1.3134578178313264e-05, "loss": 0.5317, "step": 11285 }, { "epoch": 0.6232604373757455, "grad_norm": 0.637973427772522, "learning_rate": 1.3131218349553057e-05, "loss": 0.1217, "step": 11286 }, { "epoch": 0.6233156615860393, "grad_norm": 2.3027145862579346, "learning_rate": 1.3127858740544733e-05, "loss": 0.41, "step": 11287 }, { "epoch": 0.6233708857963332, "grad_norm": 2.678495168685913, "learning_rate": 1.3124499351395767e-05, "loss": 0.2359, "step": 11288 }, { "epoch": 0.623426110006627, "grad_norm": 5.17054557800293, "learning_rate": 1.312114018221365e-05, "loss": 1.3048, "step": 11289 }, { "epoch": 0.6234813342169206, "grad_norm": 0.053927768021821976, "learning_rate": 1.3117781233105828e-05, "loss": 0.0016, "step": 11290 }, { "epoch": 0.6235365584272144, "grad_norm": 3.9815797805786133, "learning_rate": 1.3114422504179788e-05, "loss": 0.4819, "step": 11291 }, { "epoch": 0.6235917826375083, "grad_norm": 0.6384831666946411, "learning_rate": 1.3111063995542969e-05, "loss": 0.0126, "step": 11292 }, { "epoch": 0.623647006847802, "grad_norm": 1.289949893951416, "learning_rate": 1.310770570730283e-05, "loss": 0.0709, "step": 11293 }, { "epoch": 0.6237022310580959, "grad_norm": 3.0779337882995605, "learning_rate": 1.3104347639566802e-05, "loss": 0.5699, "step": 11294 }, { "epoch": 0.6237574552683897, "grad_norm": 2.3761746883392334, "learning_rate": 1.3100989792442325e-05, "loss": 0.1551, "step": 11295 }, { "epoch": 0.6238126794786835, "grad_norm": 0.07588812708854675, "learning_rate": 1.3097632166036824e-05, "loss": 0.0018, "step": 11296 }, { "epoch": 0.6238679036889773, "grad_norm": 2.4985721111297607, "learning_rate": 1.3094274760457723e-05, "loss": 0.3569, "step": 11297 }, { "epoch": 0.6239231278992711, "grad_norm": 1.051189661026001, "learning_rate": 1.3090917575812427e-05, "loss": 0.0252, "step": 11298 }, { "epoch": 0.6239783521095649, "grad_norm": 3.0827090740203857, "learning_rate": 1.3087560612208359e-05, "loss": 0.5539, "step": 11299 }, { "epoch": 0.6240335763198587, "grad_norm": 2.857846975326538, "learning_rate": 1.3084203869752896e-05, "loss": 0.8549, "step": 11300 }, { "epoch": 0.6240888005301524, "grad_norm": 0.19013933837413788, "learning_rate": 1.3080847348553443e-05, "loss": 0.0069, "step": 11301 }, { "epoch": 0.6241440247404462, "grad_norm": 0.11399226635694504, "learning_rate": 1.3077491048717375e-05, "loss": 0.0034, "step": 11302 }, { "epoch": 0.62419924895074, "grad_norm": 3.45184326171875, "learning_rate": 1.3074134970352083e-05, "loss": 0.6179, "step": 11303 }, { "epoch": 0.6242544731610338, "grad_norm": 0.38450679183006287, "learning_rate": 1.3070779113564927e-05, "loss": 0.0119, "step": 11304 }, { "epoch": 0.6243096973713276, "grad_norm": 1.5094759464263916, "learning_rate": 1.3067423478463275e-05, "loss": 0.2117, "step": 11305 }, { "epoch": 0.6243649215816214, "grad_norm": 0.8953709602355957, "learning_rate": 1.3064068065154479e-05, "loss": 0.0343, "step": 11306 }, { "epoch": 0.6244201457919152, "grad_norm": 0.07232414186000824, "learning_rate": 1.30607128737459e-05, "loss": 0.0018, "step": 11307 }, { "epoch": 0.624475370002209, "grad_norm": 2.5027129650115967, "learning_rate": 1.3057357904344862e-05, "loss": 0.1831, "step": 11308 }, { "epoch": 0.6245305942125028, "grad_norm": 0.064738929271698, "learning_rate": 1.3054003157058715e-05, "loss": 0.002, "step": 11309 }, { "epoch": 0.6245858184227966, "grad_norm": 4.029858112335205, "learning_rate": 1.3050648631994778e-05, "loss": 0.5527, "step": 11310 }, { "epoch": 0.6246410426330904, "grad_norm": 3.1982452869415283, "learning_rate": 1.3047294329260378e-05, "loss": 0.2474, "step": 11311 }, { "epoch": 0.6246962668433841, "grad_norm": 0.08147423714399338, "learning_rate": 1.3043940248962833e-05, "loss": 0.0017, "step": 11312 }, { "epoch": 0.6247514910536779, "grad_norm": 0.5108804106712341, "learning_rate": 1.3040586391209424e-05, "loss": 0.013, "step": 11313 }, { "epoch": 0.6248067152639717, "grad_norm": 4.416062355041504, "learning_rate": 1.3037232756107484e-05, "loss": 0.8394, "step": 11314 }, { "epoch": 0.6248619394742655, "grad_norm": 0.047160178422927856, "learning_rate": 1.3033879343764285e-05, "loss": 0.0013, "step": 11315 }, { "epoch": 0.6249171636845593, "grad_norm": 0.02438390627503395, "learning_rate": 1.3030526154287117e-05, "loss": 0.0006, "step": 11316 }, { "epoch": 0.6249723878948531, "grad_norm": 3.29752779006958, "learning_rate": 1.3027173187783258e-05, "loss": 0.697, "step": 11317 }, { "epoch": 0.6250276121051469, "grad_norm": 2.1098432540893555, "learning_rate": 1.3023820444359983e-05, "loss": 0.3131, "step": 11318 }, { "epoch": 0.6250828363154407, "grad_norm": 0.502354085445404, "learning_rate": 1.3020467924124546e-05, "loss": 0.0146, "step": 11319 }, { "epoch": 0.6251380605257345, "grad_norm": 0.09405961632728577, "learning_rate": 1.301711562718422e-05, "loss": 0.0031, "step": 11320 }, { "epoch": 0.6251932847360283, "grad_norm": 0.6861661672592163, "learning_rate": 1.3013763553646231e-05, "loss": 0.0143, "step": 11321 }, { "epoch": 0.6252485089463221, "grad_norm": 0.8389642834663391, "learning_rate": 1.3010411703617848e-05, "loss": 0.0275, "step": 11322 }, { "epoch": 0.6253037331566159, "grad_norm": 2.079584836959839, "learning_rate": 1.3007060077206286e-05, "loss": 0.1785, "step": 11323 }, { "epoch": 0.6253589573669096, "grad_norm": 3.6881895065307617, "learning_rate": 1.3003708674518783e-05, "loss": 0.2176, "step": 11324 }, { "epoch": 0.6254141815772034, "grad_norm": 0.073003388941288, "learning_rate": 1.3000357495662551e-05, "loss": 0.0025, "step": 11325 }, { "epoch": 0.6254694057874972, "grad_norm": 4.2291259765625, "learning_rate": 1.2997006540744816e-05, "loss": 0.4901, "step": 11326 }, { "epoch": 0.625524629997791, "grad_norm": 0.09717079252004623, "learning_rate": 1.2993655809872774e-05, "loss": 0.0014, "step": 11327 }, { "epoch": 0.6255798542080848, "grad_norm": 0.12417245656251907, "learning_rate": 1.299030530315364e-05, "loss": 0.0029, "step": 11328 }, { "epoch": 0.6256350784183786, "grad_norm": 0.34583714604377747, "learning_rate": 1.2986955020694578e-05, "loss": 0.0031, "step": 11329 }, { "epoch": 0.6256903026286724, "grad_norm": 2.639948844909668, "learning_rate": 1.2983604962602805e-05, "loss": 0.2189, "step": 11330 }, { "epoch": 0.6257455268389662, "grad_norm": 1.0167204141616821, "learning_rate": 1.2980255128985474e-05, "loss": 0.0331, "step": 11331 }, { "epoch": 0.62580075104926, "grad_norm": 2.6069576740264893, "learning_rate": 1.2976905519949772e-05, "loss": 0.129, "step": 11332 }, { "epoch": 0.6258559752595538, "grad_norm": 0.5762543082237244, "learning_rate": 1.2973556135602852e-05, "loss": 0.0126, "step": 11333 }, { "epoch": 0.6259111994698476, "grad_norm": 0.08777934312820435, "learning_rate": 1.2970206976051877e-05, "loss": 0.0027, "step": 11334 }, { "epoch": 0.6259664236801413, "grad_norm": 0.07800373435020447, "learning_rate": 1.2966858041403992e-05, "loss": 0.0025, "step": 11335 }, { "epoch": 0.6260216478904351, "grad_norm": 2.48854660987854, "learning_rate": 1.2963509331766343e-05, "loss": 0.1047, "step": 11336 }, { "epoch": 0.6260768721007289, "grad_norm": 4.15458869934082, "learning_rate": 1.296016084724606e-05, "loss": 0.3944, "step": 11337 }, { "epoch": 0.6261320963110227, "grad_norm": 2.0654852390289307, "learning_rate": 1.2956812587950279e-05, "loss": 0.4051, "step": 11338 }, { "epoch": 0.6261873205213165, "grad_norm": 1.2893322706222534, "learning_rate": 1.2953464553986106e-05, "loss": 0.0559, "step": 11339 }, { "epoch": 0.6262425447316103, "grad_norm": 0.10109555721282959, "learning_rate": 1.2950116745460668e-05, "loss": 0.0034, "step": 11340 }, { "epoch": 0.6262977689419041, "grad_norm": 4.626823902130127, "learning_rate": 1.2946769162481061e-05, "loss": 0.8245, "step": 11341 }, { "epoch": 0.626352993152198, "grad_norm": 1.6158567667007446, "learning_rate": 1.2943421805154393e-05, "loss": 0.1099, "step": 11342 }, { "epoch": 0.6264082173624917, "grad_norm": 4.823261737823486, "learning_rate": 1.2940074673587746e-05, "loss": 0.7704, "step": 11343 }, { "epoch": 0.6264634415727856, "grad_norm": 0.025631297379732132, "learning_rate": 1.2936727767888213e-05, "loss": 0.0007, "step": 11344 }, { "epoch": 0.6265186657830794, "grad_norm": 0.10533657670021057, "learning_rate": 1.2933381088162862e-05, "loss": 0.0029, "step": 11345 }, { "epoch": 0.626573889993373, "grad_norm": 0.2647189795970917, "learning_rate": 1.2930034634518777e-05, "loss": 0.0079, "step": 11346 }, { "epoch": 0.6266291142036668, "grad_norm": 4.125478744506836, "learning_rate": 1.2926688407063004e-05, "loss": 0.7622, "step": 11347 }, { "epoch": 0.6266843384139607, "grad_norm": 2.09096360206604, "learning_rate": 1.2923342405902608e-05, "loss": 0.1162, "step": 11348 }, { "epoch": 0.6267395626242545, "grad_norm": 6.6967949867248535, "learning_rate": 1.2919996631144631e-05, "loss": 0.965, "step": 11349 }, { "epoch": 0.6267947868345483, "grad_norm": 0.00800409447401762, "learning_rate": 1.2916651082896123e-05, "loss": 0.0003, "step": 11350 }, { "epoch": 0.6268500110448421, "grad_norm": 1.8616938591003418, "learning_rate": 1.2913305761264108e-05, "loss": 0.5455, "step": 11351 }, { "epoch": 0.6269052352551359, "grad_norm": 0.019148148596286774, "learning_rate": 1.290996066635562e-05, "loss": 0.0005, "step": 11352 }, { "epoch": 0.6269604594654297, "grad_norm": 0.0877024233341217, "learning_rate": 1.2906615798277669e-05, "loss": 0.0019, "step": 11353 }, { "epoch": 0.6270156836757235, "grad_norm": 3.062384843826294, "learning_rate": 1.2903271157137285e-05, "loss": 0.3109, "step": 11354 }, { "epoch": 0.6270709078860173, "grad_norm": 0.2698866128921509, "learning_rate": 1.2899926743041445e-05, "loss": 0.0063, "step": 11355 }, { "epoch": 0.6271261320963111, "grad_norm": 7.966177940368652, "learning_rate": 1.2896582556097173e-05, "loss": 0.3892, "step": 11356 }, { "epoch": 0.6271813563066048, "grad_norm": 0.2118382453918457, "learning_rate": 1.289323859641144e-05, "loss": 0.0053, "step": 11357 }, { "epoch": 0.6272365805168986, "grad_norm": 4.8939409255981445, "learning_rate": 1.288989486409124e-05, "loss": 1.8925, "step": 11358 }, { "epoch": 0.6272918047271924, "grad_norm": 2.478755474090576, "learning_rate": 1.2886551359243545e-05, "loss": 0.0805, "step": 11359 }, { "epoch": 0.6273470289374862, "grad_norm": 0.2672017216682434, "learning_rate": 1.2883208081975323e-05, "loss": 0.0067, "step": 11360 }, { "epoch": 0.62740225314778, "grad_norm": 2.943233013153076, "learning_rate": 1.2879865032393531e-05, "loss": 0.1461, "step": 11361 }, { "epoch": 0.6274574773580738, "grad_norm": 1.8046308755874634, "learning_rate": 1.2876522210605135e-05, "loss": 0.1213, "step": 11362 }, { "epoch": 0.6275127015683676, "grad_norm": 2.7422354221343994, "learning_rate": 1.2873179616717062e-05, "loss": 0.295, "step": 11363 }, { "epoch": 0.6275679257786614, "grad_norm": 2.155866861343384, "learning_rate": 1.2869837250836274e-05, "loss": 0.0996, "step": 11364 }, { "epoch": 0.6276231499889552, "grad_norm": 1.6232242584228516, "learning_rate": 1.2866495113069684e-05, "loss": 0.162, "step": 11365 }, { "epoch": 0.627678374199249, "grad_norm": 1.5169451236724854, "learning_rate": 1.2863153203524225e-05, "loss": 0.025, "step": 11366 }, { "epoch": 0.6277335984095428, "grad_norm": 0.08587318658828735, "learning_rate": 1.285981152230681e-05, "loss": 0.0015, "step": 11367 }, { "epoch": 0.6277888226198365, "grad_norm": 0.04059014096856117, "learning_rate": 1.2856470069524357e-05, "loss": 0.0011, "step": 11368 }, { "epoch": 0.6278440468301303, "grad_norm": 2.2002363204956055, "learning_rate": 1.2853128845283757e-05, "loss": 0.1054, "step": 11369 }, { "epoch": 0.6278992710404241, "grad_norm": 1.8236178159713745, "learning_rate": 1.2849787849691922e-05, "loss": 0.0987, "step": 11370 }, { "epoch": 0.6279544952507179, "grad_norm": 0.06816890835762024, "learning_rate": 1.2846447082855717e-05, "loss": 0.0011, "step": 11371 }, { "epoch": 0.6280097194610117, "grad_norm": 0.35992947220802307, "learning_rate": 1.2843106544882047e-05, "loss": 0.0093, "step": 11372 }, { "epoch": 0.6280649436713055, "grad_norm": 2.972230911254883, "learning_rate": 1.2839766235877767e-05, "loss": 0.1407, "step": 11373 }, { "epoch": 0.6281201678815993, "grad_norm": 2.104179859161377, "learning_rate": 1.2836426155949746e-05, "loss": 0.2646, "step": 11374 }, { "epoch": 0.6281753920918931, "grad_norm": 1.693707823753357, "learning_rate": 1.2833086305204852e-05, "loss": 0.0964, "step": 11375 }, { "epoch": 0.6282306163021869, "grad_norm": 1.5972133874893188, "learning_rate": 1.2829746683749926e-05, "loss": 0.1188, "step": 11376 }, { "epoch": 0.6282858405124807, "grad_norm": 2.477553129196167, "learning_rate": 1.2826407291691822e-05, "loss": 0.3111, "step": 11377 }, { "epoch": 0.6283410647227745, "grad_norm": 0.04931191727519035, "learning_rate": 1.2823068129137366e-05, "loss": 0.0017, "step": 11378 }, { "epoch": 0.6283962889330682, "grad_norm": 4.872196197509766, "learning_rate": 1.2819729196193396e-05, "loss": 1.1136, "step": 11379 }, { "epoch": 0.628451513143362, "grad_norm": 0.03879587724804878, "learning_rate": 1.2816390492966723e-05, "loss": 0.0012, "step": 11380 }, { "epoch": 0.6285067373536558, "grad_norm": 0.10817398875951767, "learning_rate": 1.2813052019564176e-05, "loss": 0.0043, "step": 11381 }, { "epoch": 0.6285619615639496, "grad_norm": 1.6425342559814453, "learning_rate": 1.2809713776092551e-05, "loss": 0.2079, "step": 11382 }, { "epoch": 0.6286171857742434, "grad_norm": 2.427025318145752, "learning_rate": 1.2806375762658659e-05, "loss": 0.2319, "step": 11383 }, { "epoch": 0.6286724099845372, "grad_norm": 0.33781948685646057, "learning_rate": 1.2803037979369277e-05, "loss": 0.0081, "step": 11384 }, { "epoch": 0.628727634194831, "grad_norm": 0.05014780908823013, "learning_rate": 1.2799700426331207e-05, "loss": 0.0018, "step": 11385 }, { "epoch": 0.6287828584051248, "grad_norm": 3.349331855773926, "learning_rate": 1.2796363103651209e-05, "loss": 0.2297, "step": 11386 }, { "epoch": 0.6288380826154186, "grad_norm": 0.15296603739261627, "learning_rate": 1.2793026011436073e-05, "loss": 0.0053, "step": 11387 }, { "epoch": 0.6288933068257124, "grad_norm": 0.24447613954544067, "learning_rate": 1.2789689149792546e-05, "loss": 0.0049, "step": 11388 }, { "epoch": 0.6289485310360062, "grad_norm": 0.3903360366821289, "learning_rate": 1.2786352518827395e-05, "loss": 0.0095, "step": 11389 }, { "epoch": 0.6290037552462999, "grad_norm": 1.9371685981750488, "learning_rate": 1.2783016118647357e-05, "loss": 0.2446, "step": 11390 }, { "epoch": 0.6290589794565937, "grad_norm": 0.20367228984832764, "learning_rate": 1.2779679949359186e-05, "loss": 0.0061, "step": 11391 }, { "epoch": 0.6291142036668875, "grad_norm": 4.0325188636779785, "learning_rate": 1.2776344011069601e-05, "loss": 1.0706, "step": 11392 }, { "epoch": 0.6291694278771813, "grad_norm": 0.9568875432014465, "learning_rate": 1.2773008303885343e-05, "loss": 0.0332, "step": 11393 }, { "epoch": 0.6292246520874751, "grad_norm": 0.4873095154762268, "learning_rate": 1.2769672827913117e-05, "loss": 0.0161, "step": 11394 }, { "epoch": 0.6292798762977689, "grad_norm": 3.2009620666503906, "learning_rate": 1.2766337583259652e-05, "loss": 0.1417, "step": 11395 }, { "epoch": 0.6293351005080627, "grad_norm": 3.017764091491699, "learning_rate": 1.2763002570031628e-05, "loss": 0.1135, "step": 11396 }, { "epoch": 0.6293903247183565, "grad_norm": 0.7163463830947876, "learning_rate": 1.2759667788335763e-05, "loss": 0.0214, "step": 11397 }, { "epoch": 0.6294455489286503, "grad_norm": 1.3063201904296875, "learning_rate": 1.2756333238278734e-05, "loss": 0.4543, "step": 11398 }, { "epoch": 0.6295007731389441, "grad_norm": 0.3565223813056946, "learning_rate": 1.2752998919967228e-05, "loss": 0.0134, "step": 11399 }, { "epoch": 0.629555997349238, "grad_norm": 4.634606838226318, "learning_rate": 1.2749664833507916e-05, "loss": 0.8109, "step": 11400 }, { "epoch": 0.6296112215595318, "grad_norm": 2.6291086673736572, "learning_rate": 1.2746330979007473e-05, "loss": 0.5352, "step": 11401 }, { "epoch": 0.6296664457698254, "grad_norm": 0.33017244935035706, "learning_rate": 1.2742997356572543e-05, "loss": 0.0047, "step": 11402 }, { "epoch": 0.6297216699801192, "grad_norm": 0.01860656403005123, "learning_rate": 1.2739663966309797e-05, "loss": 0.0007, "step": 11403 }, { "epoch": 0.629776894190413, "grad_norm": 0.0602027103304863, "learning_rate": 1.2736330808325863e-05, "loss": 0.0018, "step": 11404 }, { "epoch": 0.6298321184007069, "grad_norm": 0.24557943642139435, "learning_rate": 1.2732997882727387e-05, "loss": 0.0076, "step": 11405 }, { "epoch": 0.6298873426110007, "grad_norm": 0.04031534865498543, "learning_rate": 1.2729665189620994e-05, "loss": 0.0012, "step": 11406 }, { "epoch": 0.6299425668212945, "grad_norm": 0.05366504564881325, "learning_rate": 1.2726332729113313e-05, "loss": 0.002, "step": 11407 }, { "epoch": 0.6299977910315883, "grad_norm": 0.33666765689849854, "learning_rate": 1.2723000501310954e-05, "loss": 0.0095, "step": 11408 }, { "epoch": 0.6300530152418821, "grad_norm": 2.862942695617676, "learning_rate": 1.2719668506320533e-05, "loss": 0.2928, "step": 11409 }, { "epoch": 0.6301082394521759, "grad_norm": 2.4479010105133057, "learning_rate": 1.2716336744248627e-05, "loss": 0.1791, "step": 11410 }, { "epoch": 0.6301634636624697, "grad_norm": 0.04473888874053955, "learning_rate": 1.271300521520186e-05, "loss": 0.0016, "step": 11411 }, { "epoch": 0.6302186878727635, "grad_norm": 0.3983972668647766, "learning_rate": 1.2709673919286791e-05, "loss": 0.0098, "step": 11412 }, { "epoch": 0.6302739120830572, "grad_norm": 1.3997660875320435, "learning_rate": 1.2706342856610014e-05, "loss": 0.0537, "step": 11413 }, { "epoch": 0.630329136293351, "grad_norm": 0.2825388014316559, "learning_rate": 1.2703012027278088e-05, "loss": 0.0053, "step": 11414 }, { "epoch": 0.6303843605036448, "grad_norm": 2.23521089553833, "learning_rate": 1.2699681431397584e-05, "loss": 0.1453, "step": 11415 }, { "epoch": 0.6304395847139386, "grad_norm": 2.028364896774292, "learning_rate": 1.2696351069075053e-05, "loss": 0.1142, "step": 11416 }, { "epoch": 0.6304948089242324, "grad_norm": 5.391220569610596, "learning_rate": 1.2693020940417049e-05, "loss": 0.9727, "step": 11417 }, { "epoch": 0.6305500331345262, "grad_norm": 0.007246341556310654, "learning_rate": 1.2689691045530096e-05, "loss": 0.0002, "step": 11418 }, { "epoch": 0.63060525734482, "grad_norm": 2.2118632793426514, "learning_rate": 1.2686361384520752e-05, "loss": 0.1815, "step": 11419 }, { "epoch": 0.6306604815551138, "grad_norm": 0.3774033486843109, "learning_rate": 1.2683031957495517e-05, "loss": 0.0101, "step": 11420 }, { "epoch": 0.6307157057654076, "grad_norm": 0.1922275274991989, "learning_rate": 1.2679702764560924e-05, "loss": 0.0054, "step": 11421 }, { "epoch": 0.6307709299757014, "grad_norm": 3.554936408996582, "learning_rate": 1.2676373805823479e-05, "loss": 0.4564, "step": 11422 }, { "epoch": 0.6308261541859952, "grad_norm": 6.3696184158325195, "learning_rate": 1.2673045081389685e-05, "loss": 0.097, "step": 11423 }, { "epoch": 0.6308813783962889, "grad_norm": 2.0275423526763916, "learning_rate": 1.2669716591366039e-05, "loss": 0.2097, "step": 11424 }, { "epoch": 0.6309366026065827, "grad_norm": 0.1007356196641922, "learning_rate": 1.2666388335859028e-05, "loss": 0.0026, "step": 11425 }, { "epoch": 0.6309918268168765, "grad_norm": 0.04519946500658989, "learning_rate": 1.2663060314975129e-05, "loss": 0.0023, "step": 11426 }, { "epoch": 0.6310470510271703, "grad_norm": 1.0539844036102295, "learning_rate": 1.2659732528820825e-05, "loss": 0.04, "step": 11427 }, { "epoch": 0.6311022752374641, "grad_norm": 3.752406358718872, "learning_rate": 1.2656404977502568e-05, "loss": 0.3711, "step": 11428 }, { "epoch": 0.6311574994477579, "grad_norm": 0.13549907505512238, "learning_rate": 1.2653077661126825e-05, "loss": 0.005, "step": 11429 }, { "epoch": 0.6312127236580517, "grad_norm": 2.0493929386138916, "learning_rate": 1.2649750579800038e-05, "loss": 0.2338, "step": 11430 }, { "epoch": 0.6312679478683455, "grad_norm": 2.7311513423919678, "learning_rate": 1.264642373362866e-05, "loss": 0.1537, "step": 11431 }, { "epoch": 0.6313231720786393, "grad_norm": 2.4748027324676514, "learning_rate": 1.2643097122719127e-05, "loss": 0.1433, "step": 11432 }, { "epoch": 0.6313783962889331, "grad_norm": 2.617377996444702, "learning_rate": 1.263977074717785e-05, "loss": 0.3291, "step": 11433 }, { "epoch": 0.6314336204992269, "grad_norm": 0.27809950709342957, "learning_rate": 1.2636444607111268e-05, "loss": 0.0036, "step": 11434 }, { "epoch": 0.6314888447095206, "grad_norm": 4.991445541381836, "learning_rate": 1.2633118702625783e-05, "loss": 0.7673, "step": 11435 }, { "epoch": 0.6315440689198144, "grad_norm": 0.27777454257011414, "learning_rate": 1.2629793033827804e-05, "loss": 0.0061, "step": 11436 }, { "epoch": 0.6315992931301082, "grad_norm": 0.5337687134742737, "learning_rate": 1.2626467600823724e-05, "loss": 0.0108, "step": 11437 }, { "epoch": 0.631654517340402, "grad_norm": 2.9921419620513916, "learning_rate": 1.2623142403719944e-05, "loss": 0.7131, "step": 11438 }, { "epoch": 0.6317097415506958, "grad_norm": 0.9318603873252869, "learning_rate": 1.2619817442622832e-05, "loss": 0.0069, "step": 11439 }, { "epoch": 0.6317649657609896, "grad_norm": 8.153459548950195, "learning_rate": 1.261649271763878e-05, "loss": 1.5428, "step": 11440 }, { "epoch": 0.6318201899712834, "grad_norm": 2.91329026222229, "learning_rate": 1.2613168228874132e-05, "loss": 0.3918, "step": 11441 }, { "epoch": 0.6318754141815772, "grad_norm": 0.308376282453537, "learning_rate": 1.2609843976435279e-05, "loss": 0.0078, "step": 11442 }, { "epoch": 0.631930638391871, "grad_norm": 0.8916289806365967, "learning_rate": 1.2606519960428542e-05, "loss": 0.0126, "step": 11443 }, { "epoch": 0.6319858626021648, "grad_norm": 2.60593318939209, "learning_rate": 1.2603196180960287e-05, "loss": 0.7718, "step": 11444 }, { "epoch": 0.6320410868124586, "grad_norm": 3.9003348350524902, "learning_rate": 1.2599872638136841e-05, "loss": 1.0047, "step": 11445 }, { "epoch": 0.6320963110227523, "grad_norm": 3.927825927734375, "learning_rate": 1.2596549332064538e-05, "loss": 1.3855, "step": 11446 }, { "epoch": 0.6321515352330461, "grad_norm": 0.29150962829589844, "learning_rate": 1.2593226262849697e-05, "loss": 0.0067, "step": 11447 }, { "epoch": 0.6322067594433399, "grad_norm": 0.12005108594894409, "learning_rate": 1.2589903430598641e-05, "loss": 0.0034, "step": 11448 }, { "epoch": 0.6322619836536337, "grad_norm": 5.268399238586426, "learning_rate": 1.2586580835417657e-05, "loss": 1.0809, "step": 11449 }, { "epoch": 0.6323172078639275, "grad_norm": 0.13337674736976624, "learning_rate": 1.2583258477413067e-05, "loss": 0.0039, "step": 11450 }, { "epoch": 0.6323724320742213, "grad_norm": 1.5575289726257324, "learning_rate": 1.2579936356691147e-05, "loss": 0.0434, "step": 11451 }, { "epoch": 0.6324276562845151, "grad_norm": 6.366377353668213, "learning_rate": 1.2576614473358194e-05, "loss": 1.6599, "step": 11452 }, { "epoch": 0.6324828804948089, "grad_norm": 1.4177446365356445, "learning_rate": 1.2573292827520466e-05, "loss": 0.0206, "step": 11453 }, { "epoch": 0.6325381047051027, "grad_norm": 0.2191987782716751, "learning_rate": 1.2569971419284255e-05, "loss": 0.0073, "step": 11454 }, { "epoch": 0.6325933289153965, "grad_norm": 0.3837941884994507, "learning_rate": 1.2566650248755804e-05, "loss": 0.009, "step": 11455 }, { "epoch": 0.6326485531256903, "grad_norm": 4.10557746887207, "learning_rate": 1.2563329316041376e-05, "loss": 0.8354, "step": 11456 }, { "epoch": 0.632703777335984, "grad_norm": 0.34356844425201416, "learning_rate": 1.256000862124721e-05, "loss": 0.0088, "step": 11457 }, { "epoch": 0.6327590015462778, "grad_norm": 4.856956481933594, "learning_rate": 1.255668816447956e-05, "loss": 1.36, "step": 11458 }, { "epoch": 0.6328142257565716, "grad_norm": 0.27796071767807007, "learning_rate": 1.2553367945844635e-05, "loss": 0.0067, "step": 11459 }, { "epoch": 0.6328694499668654, "grad_norm": 0.05568169057369232, "learning_rate": 1.2550047965448675e-05, "loss": 0.0016, "step": 11460 }, { "epoch": 0.6329246741771593, "grad_norm": 0.8914682269096375, "learning_rate": 1.2546728223397885e-05, "loss": 0.0279, "step": 11461 }, { "epoch": 0.632979898387453, "grad_norm": 1.615936279296875, "learning_rate": 1.254340871979848e-05, "loss": 0.038, "step": 11462 }, { "epoch": 0.6330351225977469, "grad_norm": 0.2667084038257599, "learning_rate": 1.2540089454756657e-05, "loss": 0.0119, "step": 11463 }, { "epoch": 0.6330903468080407, "grad_norm": 0.11015629023313522, "learning_rate": 1.253677042837861e-05, "loss": 0.0028, "step": 11464 }, { "epoch": 0.6331455710183345, "grad_norm": 1.6314115524291992, "learning_rate": 1.2533451640770525e-05, "loss": 0.0192, "step": 11465 }, { "epoch": 0.6332007952286283, "grad_norm": 3.2636303901672363, "learning_rate": 1.2530133092038584e-05, "loss": 0.6142, "step": 11466 }, { "epoch": 0.6332560194389221, "grad_norm": 2.3714213371276855, "learning_rate": 1.252681478228894e-05, "loss": 0.2179, "step": 11467 }, { "epoch": 0.6333112436492159, "grad_norm": 6.365471363067627, "learning_rate": 1.2523496711627773e-05, "loss": 0.5118, "step": 11468 }, { "epoch": 0.6333664678595096, "grad_norm": 2.9925103187561035, "learning_rate": 1.2520178880161226e-05, "loss": 0.2444, "step": 11469 }, { "epoch": 0.6334216920698034, "grad_norm": 0.035369113087654114, "learning_rate": 1.2516861287995456e-05, "loss": 0.0011, "step": 11470 }, { "epoch": 0.6334769162800972, "grad_norm": 4.241449356079102, "learning_rate": 1.2513543935236591e-05, "loss": 0.3673, "step": 11471 }, { "epoch": 0.633532140490391, "grad_norm": 0.5672035813331604, "learning_rate": 1.2510226821990776e-05, "loss": 0.0131, "step": 11472 }, { "epoch": 0.6335873647006848, "grad_norm": 2.9766433238983154, "learning_rate": 1.250690994836412e-05, "loss": 0.035, "step": 11473 }, { "epoch": 0.6336425889109786, "grad_norm": 0.0714431032538414, "learning_rate": 1.2503593314462758e-05, "loss": 0.0019, "step": 11474 }, { "epoch": 0.6336978131212724, "grad_norm": 1.7209941148757935, "learning_rate": 1.2500276920392774e-05, "loss": 0.1067, "step": 11475 }, { "epoch": 0.6337530373315662, "grad_norm": 0.03546321019530296, "learning_rate": 1.2496960766260293e-05, "loss": 0.0014, "step": 11476 }, { "epoch": 0.63380826154186, "grad_norm": 0.012504861690104008, "learning_rate": 1.249364485217139e-05, "loss": 0.0003, "step": 11477 }, { "epoch": 0.6338634857521538, "grad_norm": 2.743853807449341, "learning_rate": 1.2490329178232158e-05, "loss": 0.5424, "step": 11478 }, { "epoch": 0.6339187099624476, "grad_norm": 0.057529814541339874, "learning_rate": 1.2487013744548677e-05, "loss": 0.0016, "step": 11479 }, { "epoch": 0.6339739341727413, "grad_norm": 0.1359449177980423, "learning_rate": 1.2483698551227014e-05, "loss": 0.0041, "step": 11480 }, { "epoch": 0.6340291583830351, "grad_norm": 1.3298170566558838, "learning_rate": 1.2480383598373229e-05, "loss": 0.0639, "step": 11481 }, { "epoch": 0.6340843825933289, "grad_norm": 0.02299034781754017, "learning_rate": 1.247706888609339e-05, "loss": 0.0007, "step": 11482 }, { "epoch": 0.6341396068036227, "grad_norm": 4.652082443237305, "learning_rate": 1.2473754414493521e-05, "loss": 0.3338, "step": 11483 }, { "epoch": 0.6341948310139165, "grad_norm": 4.221462249755859, "learning_rate": 1.2470440183679689e-05, "loss": 0.3555, "step": 11484 }, { "epoch": 0.6342500552242103, "grad_norm": 4.149962425231934, "learning_rate": 1.24671261937579e-05, "loss": 0.461, "step": 11485 }, { "epoch": 0.6343052794345041, "grad_norm": 2.7408416271209717, "learning_rate": 1.2463812444834196e-05, "loss": 0.4149, "step": 11486 }, { "epoch": 0.6343605036447979, "grad_norm": 1.0359236001968384, "learning_rate": 1.246049893701458e-05, "loss": 0.0186, "step": 11487 }, { "epoch": 0.6344157278550917, "grad_norm": 2.2005250453948975, "learning_rate": 1.2457185670405072e-05, "loss": 0.3211, "step": 11488 }, { "epoch": 0.6344709520653855, "grad_norm": 3.906172275543213, "learning_rate": 1.2453872645111664e-05, "loss": 0.8804, "step": 11489 }, { "epoch": 0.6345261762756793, "grad_norm": 1.741938829421997, "learning_rate": 1.2450559861240362e-05, "loss": 0.0926, "step": 11490 }, { "epoch": 0.634581400485973, "grad_norm": 0.5543974041938782, "learning_rate": 1.2447247318897127e-05, "loss": 0.0142, "step": 11491 }, { "epoch": 0.6346366246962668, "grad_norm": 3.8134021759033203, "learning_rate": 1.2443935018187968e-05, "loss": 0.2562, "step": 11492 }, { "epoch": 0.6346918489065606, "grad_norm": 1.0781896114349365, "learning_rate": 1.2440622959218832e-05, "loss": 0.1581, "step": 11493 }, { "epoch": 0.6347470731168544, "grad_norm": 1.748790979385376, "learning_rate": 1.2437311142095685e-05, "loss": 0.1013, "step": 11494 }, { "epoch": 0.6348022973271482, "grad_norm": 0.110601045191288, "learning_rate": 1.2433999566924488e-05, "loss": 0.0025, "step": 11495 }, { "epoch": 0.634857521537442, "grad_norm": 0.009776006452739239, "learning_rate": 1.2430688233811182e-05, "loss": 0.0003, "step": 11496 }, { "epoch": 0.6349127457477358, "grad_norm": 1.9596178531646729, "learning_rate": 1.2427377142861716e-05, "loss": 0.1483, "step": 11497 }, { "epoch": 0.6349679699580296, "grad_norm": 0.41293588280677795, "learning_rate": 1.2424066294182002e-05, "loss": 0.0108, "step": 11498 }, { "epoch": 0.6350231941683234, "grad_norm": 3.172142505645752, "learning_rate": 1.2420755687877984e-05, "loss": 0.3237, "step": 11499 }, { "epoch": 0.6350784183786172, "grad_norm": 1.0523890256881714, "learning_rate": 1.2417445324055562e-05, "loss": 0.0268, "step": 11500 }, { "epoch": 0.635133642588911, "grad_norm": 4.024652004241943, "learning_rate": 1.2414135202820655e-05, "loss": 0.6838, "step": 11501 }, { "epoch": 0.6351888667992047, "grad_norm": 1.2049423456192017, "learning_rate": 1.2410825324279154e-05, "loss": 0.0433, "step": 11502 }, { "epoch": 0.6352440910094985, "grad_norm": 0.04528549313545227, "learning_rate": 1.2407515688536963e-05, "loss": 0.0015, "step": 11503 }, { "epoch": 0.6352993152197923, "grad_norm": 3.2278285026550293, "learning_rate": 1.2404206295699953e-05, "loss": 0.1228, "step": 11504 }, { "epoch": 0.6353545394300861, "grad_norm": 1.8742326498031616, "learning_rate": 1.2400897145874015e-05, "loss": 0.0654, "step": 11505 }, { "epoch": 0.6354097636403799, "grad_norm": 0.0057181548327207565, "learning_rate": 1.2397588239165001e-05, "loss": 0.0002, "step": 11506 }, { "epoch": 0.6354649878506737, "grad_norm": 3.6796200275421143, "learning_rate": 1.2394279575678799e-05, "loss": 0.6943, "step": 11507 }, { "epoch": 0.6355202120609675, "grad_norm": 3.925337553024292, "learning_rate": 1.2390971155521232e-05, "loss": 0.3661, "step": 11508 }, { "epoch": 0.6355754362712613, "grad_norm": 0.10263647884130478, "learning_rate": 1.2387662978798164e-05, "loss": 0.0028, "step": 11509 }, { "epoch": 0.6356306604815551, "grad_norm": 0.011020129546523094, "learning_rate": 1.2384355045615426e-05, "loss": 0.0004, "step": 11510 }, { "epoch": 0.635685884691849, "grad_norm": 0.3467257022857666, "learning_rate": 1.2381047356078852e-05, "loss": 0.0101, "step": 11511 }, { "epoch": 0.6357411089021427, "grad_norm": 2.519224166870117, "learning_rate": 1.2377739910294264e-05, "loss": 0.1978, "step": 11512 }, { "epoch": 0.6357963331124364, "grad_norm": 3.410041570663452, "learning_rate": 1.2374432708367481e-05, "loss": 0.2977, "step": 11513 }, { "epoch": 0.6358515573227302, "grad_norm": 2.88262939453125, "learning_rate": 1.2371125750404294e-05, "loss": 0.6716, "step": 11514 }, { "epoch": 0.635906781533024, "grad_norm": 0.2950841188430786, "learning_rate": 1.2367819036510524e-05, "loss": 0.0048, "step": 11515 }, { "epoch": 0.6359620057433178, "grad_norm": 2.4533777236938477, "learning_rate": 1.2364512566791942e-05, "loss": 0.5893, "step": 11516 }, { "epoch": 0.6360172299536117, "grad_norm": 0.3072291910648346, "learning_rate": 1.2361206341354346e-05, "loss": 0.0075, "step": 11517 }, { "epoch": 0.6360724541639055, "grad_norm": 0.4898867905139923, "learning_rate": 1.2357900360303502e-05, "loss": 0.0068, "step": 11518 }, { "epoch": 0.6361276783741993, "grad_norm": 0.3657163083553314, "learning_rate": 1.2354594623745185e-05, "loss": 0.0096, "step": 11519 }, { "epoch": 0.6361829025844931, "grad_norm": 4.063526153564453, "learning_rate": 1.2351289131785146e-05, "loss": 0.5514, "step": 11520 }, { "epoch": 0.6362381267947869, "grad_norm": 0.201260507106781, "learning_rate": 1.234798388452915e-05, "loss": 0.0053, "step": 11521 }, { "epoch": 0.6362933510050807, "grad_norm": 0.0101192407310009, "learning_rate": 1.2344678882082924e-05, "loss": 0.0004, "step": 11522 }, { "epoch": 0.6363485752153745, "grad_norm": 2.2152304649353027, "learning_rate": 1.2341374124552226e-05, "loss": 0.0949, "step": 11523 }, { "epoch": 0.6364037994256682, "grad_norm": 4.934824466705322, "learning_rate": 1.2338069612042767e-05, "loss": 0.1947, "step": 11524 }, { "epoch": 0.636459023635962, "grad_norm": 0.022892901673913002, "learning_rate": 1.2334765344660273e-05, "loss": 0.0007, "step": 11525 }, { "epoch": 0.6365142478462558, "grad_norm": 0.1506810486316681, "learning_rate": 1.2331461322510456e-05, "loss": 0.0041, "step": 11526 }, { "epoch": 0.6365694720565496, "grad_norm": 0.0823504850268364, "learning_rate": 1.2328157545699027e-05, "loss": 0.0031, "step": 11527 }, { "epoch": 0.6366246962668434, "grad_norm": 2.1200685501098633, "learning_rate": 1.2324854014331676e-05, "loss": 0.3165, "step": 11528 }, { "epoch": 0.6366799204771372, "grad_norm": 3.8901960849761963, "learning_rate": 1.23215507285141e-05, "loss": 0.3027, "step": 11529 }, { "epoch": 0.636735144687431, "grad_norm": 0.9804010987281799, "learning_rate": 1.2318247688351965e-05, "loss": 0.0197, "step": 11530 }, { "epoch": 0.6367903688977248, "grad_norm": 2.9013895988464355, "learning_rate": 1.2314944893950968e-05, "loss": 0.3649, "step": 11531 }, { "epoch": 0.6368455931080186, "grad_norm": 0.033036164939403534, "learning_rate": 1.2311642345416757e-05, "loss": 0.0009, "step": 11532 }, { "epoch": 0.6369008173183124, "grad_norm": 0.4298363924026489, "learning_rate": 1.2308340042854993e-05, "loss": 0.0094, "step": 11533 }, { "epoch": 0.6369560415286062, "grad_norm": 0.04948810115456581, "learning_rate": 1.2305037986371329e-05, "loss": 0.0012, "step": 11534 }, { "epoch": 0.6370112657388999, "grad_norm": 3.0800557136535645, "learning_rate": 1.2301736176071409e-05, "loss": 0.1903, "step": 11535 }, { "epoch": 0.6370664899491937, "grad_norm": 4.342803478240967, "learning_rate": 1.2298434612060861e-05, "loss": 1.0268, "step": 11536 }, { "epoch": 0.6371217141594875, "grad_norm": 4.032612323760986, "learning_rate": 1.2295133294445323e-05, "loss": 0.4241, "step": 11537 }, { "epoch": 0.6371769383697813, "grad_norm": 0.22538135945796967, "learning_rate": 1.2291832223330393e-05, "loss": 0.0056, "step": 11538 }, { "epoch": 0.6372321625800751, "grad_norm": 2.183920383453369, "learning_rate": 1.2288531398821708e-05, "loss": 0.1469, "step": 11539 }, { "epoch": 0.6372873867903689, "grad_norm": 2.0282933712005615, "learning_rate": 1.2285230821024846e-05, "loss": 0.1789, "step": 11540 }, { "epoch": 0.6373426110006627, "grad_norm": 5.004090309143066, "learning_rate": 1.228193049004542e-05, "loss": 0.9392, "step": 11541 }, { "epoch": 0.6373978352109565, "grad_norm": 1.4321151971817017, "learning_rate": 1.2278630405989006e-05, "loss": 0.0476, "step": 11542 }, { "epoch": 0.6374530594212503, "grad_norm": 2.3116261959075928, "learning_rate": 1.2275330568961188e-05, "loss": 0.1797, "step": 11543 }, { "epoch": 0.6375082836315441, "grad_norm": 0.027262046933174133, "learning_rate": 1.2272030979067536e-05, "loss": 0.0007, "step": 11544 }, { "epoch": 0.6375635078418379, "grad_norm": 4.160881042480469, "learning_rate": 1.2268731636413614e-05, "loss": 0.8631, "step": 11545 }, { "epoch": 0.6376187320521317, "grad_norm": 4.773026943206787, "learning_rate": 1.2265432541104976e-05, "loss": 1.2236, "step": 11546 }, { "epoch": 0.6376739562624254, "grad_norm": 3.6229734420776367, "learning_rate": 1.2262133693247176e-05, "loss": 0.2909, "step": 11547 }, { "epoch": 0.6377291804727192, "grad_norm": 2.8495306968688965, "learning_rate": 1.2258835092945743e-05, "loss": 0.267, "step": 11548 }, { "epoch": 0.637784404683013, "grad_norm": 0.7374749779701233, "learning_rate": 1.2255536740306213e-05, "loss": 0.1322, "step": 11549 }, { "epoch": 0.6378396288933068, "grad_norm": 0.05512685328722, "learning_rate": 1.2252238635434108e-05, "loss": 0.0021, "step": 11550 }, { "epoch": 0.6378948531036006, "grad_norm": 0.08291313797235489, "learning_rate": 1.2248940778434952e-05, "loss": 0.0025, "step": 11551 }, { "epoch": 0.6379500773138944, "grad_norm": 1.7995960712432861, "learning_rate": 1.224564316941425e-05, "loss": 0.0404, "step": 11552 }, { "epoch": 0.6380053015241882, "grad_norm": 2.0281589031219482, "learning_rate": 1.2242345808477488e-05, "loss": 0.173, "step": 11553 }, { "epoch": 0.638060525734482, "grad_norm": 4.757926940917969, "learning_rate": 1.2239048695730178e-05, "loss": 0.6889, "step": 11554 }, { "epoch": 0.6381157499447758, "grad_norm": 2.171203136444092, "learning_rate": 1.2235751831277787e-05, "loss": 0.2437, "step": 11555 }, { "epoch": 0.6381709741550696, "grad_norm": 0.3536668121814728, "learning_rate": 1.2232455215225802e-05, "loss": 0.011, "step": 11556 }, { "epoch": 0.6382261983653634, "grad_norm": 0.1335449516773224, "learning_rate": 1.2229158847679686e-05, "loss": 0.004, "step": 11557 }, { "epoch": 0.6382814225756571, "grad_norm": 2.4214706420898438, "learning_rate": 1.2225862728744903e-05, "loss": 0.1029, "step": 11558 }, { "epoch": 0.6383366467859509, "grad_norm": 0.40194040536880493, "learning_rate": 1.22225668585269e-05, "loss": 0.0075, "step": 11559 }, { "epoch": 0.6383918709962447, "grad_norm": 3.8557498455047607, "learning_rate": 1.2219271237131132e-05, "loss": 0.1313, "step": 11560 }, { "epoch": 0.6384470952065385, "grad_norm": 0.09449508786201477, "learning_rate": 1.221597586466302e-05, "loss": 0.0041, "step": 11561 }, { "epoch": 0.6385023194168323, "grad_norm": 0.031164415180683136, "learning_rate": 1.2212680741228006e-05, "loss": 0.0011, "step": 11562 }, { "epoch": 0.6385575436271261, "grad_norm": 1.3383867740631104, "learning_rate": 1.22093858669315e-05, "loss": 0.0768, "step": 11563 }, { "epoch": 0.6386127678374199, "grad_norm": 4.876748561859131, "learning_rate": 1.2206091241878924e-05, "loss": 1.3731, "step": 11564 }, { "epoch": 0.6386679920477137, "grad_norm": 1.9665135145187378, "learning_rate": 1.220279686617567e-05, "loss": 0.1212, "step": 11565 }, { "epoch": 0.6387232162580075, "grad_norm": 0.014371074736118317, "learning_rate": 1.219950273992715e-05, "loss": 0.0004, "step": 11566 }, { "epoch": 0.6387784404683013, "grad_norm": 0.1106955036520958, "learning_rate": 1.219620886323874e-05, "loss": 0.0026, "step": 11567 }, { "epoch": 0.6388336646785951, "grad_norm": 2.738332509994507, "learning_rate": 1.2192915236215828e-05, "loss": 0.4302, "step": 11568 }, { "epoch": 0.6388888888888888, "grad_norm": 0.08651997894048691, "learning_rate": 1.2189621858963776e-05, "loss": 0.0026, "step": 11569 }, { "epoch": 0.6389441130991826, "grad_norm": 0.04461382329463959, "learning_rate": 1.2186328731587966e-05, "loss": 0.0014, "step": 11570 }, { "epoch": 0.6389993373094764, "grad_norm": 0.01815689355134964, "learning_rate": 1.2183035854193736e-05, "loss": 0.0004, "step": 11571 }, { "epoch": 0.6390545615197702, "grad_norm": 1.9371613264083862, "learning_rate": 1.2179743226886449e-05, "loss": 0.1383, "step": 11572 }, { "epoch": 0.639109785730064, "grad_norm": 4.842488765716553, "learning_rate": 1.2176450849771433e-05, "loss": 0.8481, "step": 11573 }, { "epoch": 0.6391650099403579, "grad_norm": 2.893458604812622, "learning_rate": 1.2173158722954032e-05, "loss": 0.3487, "step": 11574 }, { "epoch": 0.6392202341506517, "grad_norm": 3.1264610290527344, "learning_rate": 1.2169866846539561e-05, "loss": 0.1564, "step": 11575 }, { "epoch": 0.6392754583609455, "grad_norm": 0.4961983263492584, "learning_rate": 1.216657522063335e-05, "loss": 0.0153, "step": 11576 }, { "epoch": 0.6393306825712393, "grad_norm": 1.4220316410064697, "learning_rate": 1.216328384534069e-05, "loss": 0.1414, "step": 11577 }, { "epoch": 0.6393859067815331, "grad_norm": 2.6976099014282227, "learning_rate": 1.2159992720766898e-05, "loss": 0.3529, "step": 11578 }, { "epoch": 0.6394411309918269, "grad_norm": 1.6455354690551758, "learning_rate": 1.215670184701725e-05, "loss": 0.1042, "step": 11579 }, { "epoch": 0.6394963552021206, "grad_norm": 0.6119991540908813, "learning_rate": 1.2153411224197042e-05, "loss": 0.0231, "step": 11580 }, { "epoch": 0.6395515794124144, "grad_norm": 0.08057621121406555, "learning_rate": 1.2150120852411544e-05, "loss": 0.0016, "step": 11581 }, { "epoch": 0.6396068036227082, "grad_norm": 0.4289458692073822, "learning_rate": 1.2146830731766033e-05, "loss": 0.0119, "step": 11582 }, { "epoch": 0.639662027833002, "grad_norm": 0.23054148256778717, "learning_rate": 1.2143540862365759e-05, "loss": 0.0053, "step": 11583 }, { "epoch": 0.6397172520432958, "grad_norm": 1.5490971803665161, "learning_rate": 1.2140251244315983e-05, "loss": 0.3071, "step": 11584 }, { "epoch": 0.6397724762535896, "grad_norm": 1.7397857904434204, "learning_rate": 1.213696187772194e-05, "loss": 0.2384, "step": 11585 }, { "epoch": 0.6398277004638834, "grad_norm": 0.09166278690099716, "learning_rate": 1.2133672762688881e-05, "loss": 0.0023, "step": 11586 }, { "epoch": 0.6398829246741772, "grad_norm": 2.017564535140991, "learning_rate": 1.2130383899322017e-05, "loss": 0.1794, "step": 11587 }, { "epoch": 0.639938148884471, "grad_norm": 0.0694706067442894, "learning_rate": 1.212709528772658e-05, "loss": 0.0018, "step": 11588 }, { "epoch": 0.6399933730947648, "grad_norm": 1.2624913454055786, "learning_rate": 1.2123806928007774e-05, "loss": 0.0626, "step": 11589 }, { "epoch": 0.6400485973050586, "grad_norm": 2.488816022872925, "learning_rate": 1.212051882027081e-05, "loss": 0.0911, "step": 11590 }, { "epoch": 0.6401038215153523, "grad_norm": 0.1062060222029686, "learning_rate": 1.2117230964620878e-05, "loss": 0.0025, "step": 11591 }, { "epoch": 0.6401590457256461, "grad_norm": 3.5404090881347656, "learning_rate": 1.2113943361163174e-05, "loss": 0.5021, "step": 11592 }, { "epoch": 0.6402142699359399, "grad_norm": 5.299429416656494, "learning_rate": 1.2110656010002867e-05, "loss": 1.451, "step": 11593 }, { "epoch": 0.6402694941462337, "grad_norm": 2.856794834136963, "learning_rate": 1.210736891124514e-05, "loss": 0.169, "step": 11594 }, { "epoch": 0.6403247183565275, "grad_norm": 0.33790117502212524, "learning_rate": 1.2104082064995143e-05, "loss": 0.0031, "step": 11595 }, { "epoch": 0.6403799425668213, "grad_norm": 2.8426384925842285, "learning_rate": 1.2100795471358047e-05, "loss": 0.1422, "step": 11596 }, { "epoch": 0.6404351667771151, "grad_norm": 4.558505535125732, "learning_rate": 1.2097509130438985e-05, "loss": 1.375, "step": 11597 }, { "epoch": 0.6404903909874089, "grad_norm": 0.38338997960090637, "learning_rate": 1.2094223042343107e-05, "loss": 0.0093, "step": 11598 }, { "epoch": 0.6405456151977027, "grad_norm": 0.292376309633255, "learning_rate": 1.2090937207175539e-05, "loss": 0.009, "step": 11599 }, { "epoch": 0.6406008394079965, "grad_norm": 1.7922919988632202, "learning_rate": 1.208765162504141e-05, "loss": 0.1419, "step": 11600 }, { "epoch": 0.6406560636182903, "grad_norm": 2.1390748023986816, "learning_rate": 1.2084366296045826e-05, "loss": 0.2594, "step": 11601 }, { "epoch": 0.640711287828584, "grad_norm": 2.493238687515259, "learning_rate": 1.2081081220293905e-05, "loss": 0.1999, "step": 11602 }, { "epoch": 0.6407665120388778, "grad_norm": 5.645130157470703, "learning_rate": 1.2077796397890729e-05, "loss": 0.4475, "step": 11603 }, { "epoch": 0.6408217362491716, "grad_norm": 3.4439175128936768, "learning_rate": 1.2074511828941414e-05, "loss": 0.358, "step": 11604 }, { "epoch": 0.6408769604594654, "grad_norm": 2.4996650218963623, "learning_rate": 1.2071227513551019e-05, "loss": 0.2313, "step": 11605 }, { "epoch": 0.6409321846697592, "grad_norm": 3.046785831451416, "learning_rate": 1.2067943451824631e-05, "loss": 0.4161, "step": 11606 }, { "epoch": 0.640987408880053, "grad_norm": 0.46321845054626465, "learning_rate": 1.2064659643867312e-05, "loss": 0.0141, "step": 11607 }, { "epoch": 0.6410426330903468, "grad_norm": 0.10183870047330856, "learning_rate": 1.2061376089784122e-05, "loss": 0.0028, "step": 11608 }, { "epoch": 0.6410978573006406, "grad_norm": 6.029293537139893, "learning_rate": 1.205809278968011e-05, "loss": 0.3124, "step": 11609 }, { "epoch": 0.6411530815109344, "grad_norm": 2.5331411361694336, "learning_rate": 1.2054809743660328e-05, "loss": 0.3002, "step": 11610 }, { "epoch": 0.6412083057212282, "grad_norm": 2.6662633419036865, "learning_rate": 1.2051526951829789e-05, "loss": 0.3301, "step": 11611 }, { "epoch": 0.641263529931522, "grad_norm": 2.935136556625366, "learning_rate": 1.204824441429354e-05, "loss": 0.2632, "step": 11612 }, { "epoch": 0.6413187541418157, "grad_norm": 0.04136224836111069, "learning_rate": 1.2044962131156587e-05, "loss": 0.0014, "step": 11613 }, { "epoch": 0.6413739783521095, "grad_norm": 4.193265914916992, "learning_rate": 1.204168010252394e-05, "loss": 0.6929, "step": 11614 }, { "epoch": 0.6414292025624033, "grad_norm": 3.7818939685821533, "learning_rate": 1.2038398328500606e-05, "loss": 0.6548, "step": 11615 }, { "epoch": 0.6414844267726971, "grad_norm": 0.17453812062740326, "learning_rate": 1.2035116809191572e-05, "loss": 0.0061, "step": 11616 }, { "epoch": 0.6415396509829909, "grad_norm": 0.2723860442638397, "learning_rate": 1.2031835544701833e-05, "loss": 0.0069, "step": 11617 }, { "epoch": 0.6415948751932847, "grad_norm": 0.012353900820016861, "learning_rate": 1.2028554535136352e-05, "loss": 0.0004, "step": 11618 }, { "epoch": 0.6416500994035785, "grad_norm": 0.564406156539917, "learning_rate": 1.2025273780600108e-05, "loss": 0.0146, "step": 11619 }, { "epoch": 0.6417053236138723, "grad_norm": 3.551056385040283, "learning_rate": 1.2021993281198059e-05, "loss": 0.4458, "step": 11620 }, { "epoch": 0.6417605478241661, "grad_norm": 2.717733860015869, "learning_rate": 1.2018713037035157e-05, "loss": 0.0839, "step": 11621 }, { "epoch": 0.6418157720344599, "grad_norm": 3.936126232147217, "learning_rate": 1.2015433048216343e-05, "loss": 0.4225, "step": 11622 }, { "epoch": 0.6418709962447537, "grad_norm": 1.961610198020935, "learning_rate": 1.2012153314846563e-05, "loss": 0.0922, "step": 11623 }, { "epoch": 0.6419262204550475, "grad_norm": 2.6035354137420654, "learning_rate": 1.2008873837030732e-05, "loss": 0.5994, "step": 11624 }, { "epoch": 0.6419814446653412, "grad_norm": 0.11608517915010452, "learning_rate": 1.2005594614873787e-05, "loss": 0.004, "step": 11625 }, { "epoch": 0.642036668875635, "grad_norm": 0.4870382249355316, "learning_rate": 1.2002315648480616e-05, "loss": 0.0145, "step": 11626 }, { "epoch": 0.6420918930859288, "grad_norm": 0.4846152067184448, "learning_rate": 1.1999036937956147e-05, "loss": 0.0137, "step": 11627 }, { "epoch": 0.6421471172962226, "grad_norm": 0.3094594478607178, "learning_rate": 1.1995758483405257e-05, "loss": 0.0074, "step": 11628 }, { "epoch": 0.6422023415065164, "grad_norm": 0.009232401847839355, "learning_rate": 1.1992480284932847e-05, "loss": 0.0003, "step": 11629 }, { "epoch": 0.6422575657168103, "grad_norm": 4.10017204284668, "learning_rate": 1.1989202342643781e-05, "loss": 0.7921, "step": 11630 }, { "epoch": 0.642312789927104, "grad_norm": 0.40588781237602234, "learning_rate": 1.1985924656642945e-05, "loss": 0.0099, "step": 11631 }, { "epoch": 0.6423680141373979, "grad_norm": 0.294370174407959, "learning_rate": 1.1982647227035189e-05, "loss": 0.006, "step": 11632 }, { "epoch": 0.6424232383476917, "grad_norm": 0.5226501226425171, "learning_rate": 1.197937005392538e-05, "loss": 0.0172, "step": 11633 }, { "epoch": 0.6424784625579855, "grad_norm": 0.014605896547436714, "learning_rate": 1.1976093137418342e-05, "loss": 0.0004, "step": 11634 }, { "epoch": 0.6425336867682793, "grad_norm": 4.042918682098389, "learning_rate": 1.1972816477618945e-05, "loss": 0.7554, "step": 11635 }, { "epoch": 0.642588910978573, "grad_norm": 0.0033546737395226955, "learning_rate": 1.196954007463199e-05, "loss": 0.0001, "step": 11636 }, { "epoch": 0.6426441351888668, "grad_norm": 1.4354201555252075, "learning_rate": 1.1966263928562314e-05, "loss": 0.0341, "step": 11637 }, { "epoch": 0.6426993593991606, "grad_norm": 0.13426105678081512, "learning_rate": 1.1962988039514723e-05, "loss": 0.0045, "step": 11638 }, { "epoch": 0.6427545836094544, "grad_norm": 5.565062522888184, "learning_rate": 1.1959712407594029e-05, "loss": 0.6027, "step": 11639 }, { "epoch": 0.6428098078197482, "grad_norm": 0.25246983766555786, "learning_rate": 1.195643703290502e-05, "loss": 0.0051, "step": 11640 }, { "epoch": 0.642865032030042, "grad_norm": 0.8841681480407715, "learning_rate": 1.1953161915552498e-05, "loss": 0.0235, "step": 11641 }, { "epoch": 0.6429202562403358, "grad_norm": 0.06885375827550888, "learning_rate": 1.1949887055641223e-05, "loss": 0.0021, "step": 11642 }, { "epoch": 0.6429754804506296, "grad_norm": 0.10075045377016068, "learning_rate": 1.194661245327599e-05, "loss": 0.0026, "step": 11643 }, { "epoch": 0.6430307046609234, "grad_norm": 0.0062771812081336975, "learning_rate": 1.1943338108561542e-05, "loss": 0.0002, "step": 11644 }, { "epoch": 0.6430859288712172, "grad_norm": 0.13752761483192444, "learning_rate": 1.1940064021602651e-05, "loss": 0.0047, "step": 11645 }, { "epoch": 0.643141153081511, "grad_norm": 0.31272998452186584, "learning_rate": 1.1936790192504053e-05, "loss": 0.0091, "step": 11646 }, { "epoch": 0.6431963772918047, "grad_norm": 0.14294101297855377, "learning_rate": 1.1933516621370496e-05, "loss": 0.003, "step": 11647 }, { "epoch": 0.6432516015020985, "grad_norm": 3.0157582759857178, "learning_rate": 1.1930243308306698e-05, "loss": 0.3481, "step": 11648 }, { "epoch": 0.6433068257123923, "grad_norm": 1.2189452648162842, "learning_rate": 1.1926970253417403e-05, "loss": 0.0422, "step": 11649 }, { "epoch": 0.6433620499226861, "grad_norm": 7.022066593170166, "learning_rate": 1.1923697456807299e-05, "loss": 1.4709, "step": 11650 }, { "epoch": 0.6434172741329799, "grad_norm": 3.382732629776001, "learning_rate": 1.192042491858112e-05, "loss": 0.2385, "step": 11651 }, { "epoch": 0.6434724983432737, "grad_norm": 0.038525961339473724, "learning_rate": 1.1917152638843538e-05, "loss": 0.0012, "step": 11652 }, { "epoch": 0.6435277225535675, "grad_norm": 0.015393720008432865, "learning_rate": 1.1913880617699261e-05, "loss": 0.0004, "step": 11653 }, { "epoch": 0.6435829467638613, "grad_norm": 1.409085988998413, "learning_rate": 1.1910608855252956e-05, "loss": 0.03, "step": 11654 }, { "epoch": 0.6436381709741551, "grad_norm": 2.458183526992798, "learning_rate": 1.1907337351609307e-05, "loss": 0.5983, "step": 11655 }, { "epoch": 0.6436933951844489, "grad_norm": 0.6816363334655762, "learning_rate": 1.1904066106872973e-05, "loss": 0.0102, "step": 11656 }, { "epoch": 0.6437486193947427, "grad_norm": 0.06406143307685852, "learning_rate": 1.1900795121148621e-05, "loss": 0.0027, "step": 11657 }, { "epoch": 0.6438038436050364, "grad_norm": 8.200377464294434, "learning_rate": 1.1897524394540876e-05, "loss": 0.2579, "step": 11658 }, { "epoch": 0.6438590678153302, "grad_norm": 3.0592737197875977, "learning_rate": 1.1894253927154407e-05, "loss": 0.4139, "step": 11659 }, { "epoch": 0.643914292025624, "grad_norm": 3.427617073059082, "learning_rate": 1.189098371909382e-05, "loss": 0.0454, "step": 11660 }, { "epoch": 0.6439695162359178, "grad_norm": 0.2818082571029663, "learning_rate": 1.1887713770463756e-05, "loss": 0.0052, "step": 11661 }, { "epoch": 0.6440247404462116, "grad_norm": 0.39868175983428955, "learning_rate": 1.1884444081368817e-05, "loss": 0.0104, "step": 11662 }, { "epoch": 0.6440799646565054, "grad_norm": 1.7286049127578735, "learning_rate": 1.188117465191362e-05, "loss": 0.0946, "step": 11663 }, { "epoch": 0.6441351888667992, "grad_norm": 5.107885837554932, "learning_rate": 1.1877905482202756e-05, "loss": 0.7182, "step": 11664 }, { "epoch": 0.644190413077093, "grad_norm": 3.7098968029022217, "learning_rate": 1.1874636572340821e-05, "loss": 0.2365, "step": 11665 }, { "epoch": 0.6442456372873868, "grad_norm": 5.5236687660217285, "learning_rate": 1.1871367922432392e-05, "loss": 0.0595, "step": 11666 }, { "epoch": 0.6443008614976806, "grad_norm": 2.2723820209503174, "learning_rate": 1.1868099532582052e-05, "loss": 0.1308, "step": 11667 }, { "epoch": 0.6443560857079744, "grad_norm": 0.2155742198228836, "learning_rate": 1.1864831402894349e-05, "loss": 0.0042, "step": 11668 }, { "epoch": 0.6444113099182681, "grad_norm": 2.6572227478027344, "learning_rate": 1.1861563533473855e-05, "loss": 0.3593, "step": 11669 }, { "epoch": 0.6444665341285619, "grad_norm": 2.397581100463867, "learning_rate": 1.1858295924425107e-05, "loss": 0.1387, "step": 11670 }, { "epoch": 0.6445217583388557, "grad_norm": 3.1070475578308105, "learning_rate": 1.1855028575852656e-05, "loss": 0.1808, "step": 11671 }, { "epoch": 0.6445769825491495, "grad_norm": 0.022992966696619987, "learning_rate": 1.185176148786103e-05, "loss": 0.0006, "step": 11672 }, { "epoch": 0.6446322067594433, "grad_norm": 2.951179265975952, "learning_rate": 1.1848494660554741e-05, "loss": 0.2223, "step": 11673 }, { "epoch": 0.6446874309697371, "grad_norm": 2.8624541759490967, "learning_rate": 1.1845228094038328e-05, "loss": 0.4326, "step": 11674 }, { "epoch": 0.6447426551800309, "grad_norm": 2.772265911102295, "learning_rate": 1.1841961788416275e-05, "loss": 0.4792, "step": 11675 }, { "epoch": 0.6447978793903247, "grad_norm": 1.2766311168670654, "learning_rate": 1.1838695743793092e-05, "loss": 0.0643, "step": 11676 }, { "epoch": 0.6448531036006185, "grad_norm": 1.4493082761764526, "learning_rate": 1.1835429960273261e-05, "loss": 0.0967, "step": 11677 }, { "epoch": 0.6449083278109123, "grad_norm": 2.361546277999878, "learning_rate": 1.1832164437961274e-05, "loss": 0.4708, "step": 11678 }, { "epoch": 0.6449635520212061, "grad_norm": 0.05778467282652855, "learning_rate": 1.1828899176961595e-05, "loss": 0.0014, "step": 11679 }, { "epoch": 0.6450187762314998, "grad_norm": 0.2987406849861145, "learning_rate": 1.1825634177378705e-05, "loss": 0.0099, "step": 11680 }, { "epoch": 0.6450740004417936, "grad_norm": 4.092106342315674, "learning_rate": 1.1822369439317032e-05, "loss": 0.4731, "step": 11681 }, { "epoch": 0.6451292246520874, "grad_norm": 0.15097860991954803, "learning_rate": 1.1819104962881057e-05, "loss": 0.0043, "step": 11682 }, { "epoch": 0.6451844488623812, "grad_norm": 0.14320515096187592, "learning_rate": 1.1815840748175196e-05, "loss": 0.0047, "step": 11683 }, { "epoch": 0.645239673072675, "grad_norm": 0.1283172219991684, "learning_rate": 1.181257679530389e-05, "loss": 0.0022, "step": 11684 }, { "epoch": 0.6452948972829688, "grad_norm": 2.936272621154785, "learning_rate": 1.1809313104371558e-05, "loss": 0.8443, "step": 11685 }, { "epoch": 0.6453501214932627, "grad_norm": 0.7872640490531921, "learning_rate": 1.1806049675482623e-05, "loss": 0.0193, "step": 11686 }, { "epoch": 0.6454053457035565, "grad_norm": 0.18509939312934875, "learning_rate": 1.1802786508741485e-05, "loss": 0.0051, "step": 11687 }, { "epoch": 0.6454605699138503, "grad_norm": 6.354471206665039, "learning_rate": 1.1799523604252544e-05, "loss": 1.2628, "step": 11688 }, { "epoch": 0.6455157941241441, "grad_norm": 2.9136807918548584, "learning_rate": 1.1796260962120181e-05, "loss": 0.229, "step": 11689 }, { "epoch": 0.6455710183344379, "grad_norm": 0.014469930902123451, "learning_rate": 1.1792998582448796e-05, "loss": 0.0006, "step": 11690 }, { "epoch": 0.6456262425447317, "grad_norm": 0.05493189021945, "learning_rate": 1.1789736465342742e-05, "loss": 0.0014, "step": 11691 }, { "epoch": 0.6456814667550254, "grad_norm": 3.105846643447876, "learning_rate": 1.1786474610906398e-05, "loss": 0.2024, "step": 11692 }, { "epoch": 0.6457366909653192, "grad_norm": 2.0001208782196045, "learning_rate": 1.1783213019244109e-05, "loss": 0.2635, "step": 11693 }, { "epoch": 0.645791915175613, "grad_norm": 0.0741935446858406, "learning_rate": 1.177995169046023e-05, "loss": 0.0026, "step": 11694 }, { "epoch": 0.6458471393859068, "grad_norm": 0.05805452540516853, "learning_rate": 1.1776690624659095e-05, "loss": 0.0011, "step": 11695 }, { "epoch": 0.6459023635962006, "grad_norm": 4.424041271209717, "learning_rate": 1.1773429821945042e-05, "loss": 1.2513, "step": 11696 }, { "epoch": 0.6459575878064944, "grad_norm": 0.02575591206550598, "learning_rate": 1.1770169282422384e-05, "loss": 0.0008, "step": 11697 }, { "epoch": 0.6460128120167882, "grad_norm": 5.3576788902282715, "learning_rate": 1.176690900619545e-05, "loss": 1.3586, "step": 11698 }, { "epoch": 0.646068036227082, "grad_norm": 3.888831377029419, "learning_rate": 1.1763648993368526e-05, "loss": 0.6363, "step": 11699 }, { "epoch": 0.6461232604373758, "grad_norm": 1.8428493738174438, "learning_rate": 1.1760389244045922e-05, "loss": 0.1724, "step": 11700 }, { "epoch": 0.6461784846476696, "grad_norm": 1.0177446603775024, "learning_rate": 1.175712975833192e-05, "loss": 0.0143, "step": 11701 }, { "epoch": 0.6462337088579634, "grad_norm": 3.37367582321167, "learning_rate": 1.1753870536330807e-05, "loss": 0.4331, "step": 11702 }, { "epoch": 0.6462889330682571, "grad_norm": 0.12760917842388153, "learning_rate": 1.1750611578146848e-05, "loss": 0.0045, "step": 11703 }, { "epoch": 0.6463441572785509, "grad_norm": 1.9105113744735718, "learning_rate": 1.1747352883884312e-05, "loss": 0.2416, "step": 11704 }, { "epoch": 0.6463993814888447, "grad_norm": 0.02111155539751053, "learning_rate": 1.174409445364745e-05, "loss": 0.0005, "step": 11705 }, { "epoch": 0.6464546056991385, "grad_norm": 4.777829170227051, "learning_rate": 1.1740836287540516e-05, "loss": 0.9442, "step": 11706 }, { "epoch": 0.6465098299094323, "grad_norm": 0.03486456349492073, "learning_rate": 1.1737578385667735e-05, "loss": 0.0014, "step": 11707 }, { "epoch": 0.6465650541197261, "grad_norm": 0.2734781801700592, "learning_rate": 1.1734320748133348e-05, "loss": 0.0071, "step": 11708 }, { "epoch": 0.6466202783300199, "grad_norm": 1.2296091318130493, "learning_rate": 1.1731063375041565e-05, "loss": 0.1895, "step": 11709 }, { "epoch": 0.6466755025403137, "grad_norm": 0.8167469501495361, "learning_rate": 1.172780626649661e-05, "loss": 0.0316, "step": 11710 }, { "epoch": 0.6467307267506075, "grad_norm": 0.4579322040081024, "learning_rate": 1.1724549422602683e-05, "loss": 0.0109, "step": 11711 }, { "epoch": 0.6467859509609013, "grad_norm": 2.9493184089660645, "learning_rate": 1.1721292843463976e-05, "loss": 0.4793, "step": 11712 }, { "epoch": 0.6468411751711951, "grad_norm": 6.7553606033325195, "learning_rate": 1.171803652918468e-05, "loss": 0.7012, "step": 11713 }, { "epoch": 0.6468963993814888, "grad_norm": 4.164996147155762, "learning_rate": 1.1714780479868981e-05, "loss": 0.527, "step": 11714 }, { "epoch": 0.6469516235917826, "grad_norm": 0.4217788875102997, "learning_rate": 1.1711524695621028e-05, "loss": 0.0138, "step": 11715 }, { "epoch": 0.6470068478020764, "grad_norm": 0.04576105251908302, "learning_rate": 1.1708269176545008e-05, "loss": 0.0018, "step": 11716 }, { "epoch": 0.6470620720123702, "grad_norm": 0.07068184018135071, "learning_rate": 1.1705013922745056e-05, "loss": 0.002, "step": 11717 }, { "epoch": 0.647117296222664, "grad_norm": 5.183931350708008, "learning_rate": 1.1701758934325327e-05, "loss": 0.2671, "step": 11718 }, { "epoch": 0.6471725204329578, "grad_norm": 0.007249376270920038, "learning_rate": 1.169850421138995e-05, "loss": 0.0002, "step": 11719 }, { "epoch": 0.6472277446432516, "grad_norm": 1.8125542402267456, "learning_rate": 1.1695249754043058e-05, "loss": 0.0529, "step": 11720 }, { "epoch": 0.6472829688535454, "grad_norm": 4.608390808105469, "learning_rate": 1.1691995562388768e-05, "loss": 0.9792, "step": 11721 }, { "epoch": 0.6473381930638392, "grad_norm": 0.5876147150993347, "learning_rate": 1.1688741636531198e-05, "loss": 0.0139, "step": 11722 }, { "epoch": 0.647393417274133, "grad_norm": 0.5163386464118958, "learning_rate": 1.1685487976574432e-05, "loss": 0.0137, "step": 11723 }, { "epoch": 0.6474486414844268, "grad_norm": 2.0818769931793213, "learning_rate": 1.1682234582622591e-05, "loss": 0.6092, "step": 11724 }, { "epoch": 0.6475038656947205, "grad_norm": 0.1050741970539093, "learning_rate": 1.1678981454779734e-05, "loss": 0.0026, "step": 11725 }, { "epoch": 0.6475590899050143, "grad_norm": 3.5920701026916504, "learning_rate": 1.1675728593149955e-05, "loss": 0.3669, "step": 11726 }, { "epoch": 0.6476143141153081, "grad_norm": 1.3318915367126465, "learning_rate": 1.1672475997837306e-05, "loss": 0.0137, "step": 11727 }, { "epoch": 0.6476695383256019, "grad_norm": 0.0982450544834137, "learning_rate": 1.1669223668945877e-05, "loss": 0.0039, "step": 11728 }, { "epoch": 0.6477247625358957, "grad_norm": 0.07072571665048599, "learning_rate": 1.1665971606579683e-05, "loss": 0.0021, "step": 11729 }, { "epoch": 0.6477799867461895, "grad_norm": 0.07773710042238235, "learning_rate": 1.1662719810842788e-05, "loss": 0.0015, "step": 11730 }, { "epoch": 0.6478352109564833, "grad_norm": 0.16079384088516235, "learning_rate": 1.1659468281839224e-05, "loss": 0.0052, "step": 11731 }, { "epoch": 0.6478904351667771, "grad_norm": 0.042729996144771576, "learning_rate": 1.1656217019673011e-05, "loss": 0.0013, "step": 11732 }, { "epoch": 0.6479456593770709, "grad_norm": 3.092780590057373, "learning_rate": 1.1652966024448173e-05, "loss": 0.5618, "step": 11733 }, { "epoch": 0.6480008835873647, "grad_norm": 1.2824132442474365, "learning_rate": 1.1649715296268714e-05, "loss": 0.0262, "step": 11734 }, { "epoch": 0.6480561077976585, "grad_norm": 0.5056334733963013, "learning_rate": 1.1646464835238633e-05, "loss": 0.0122, "step": 11735 }, { "epoch": 0.6481113320079522, "grad_norm": 0.024430541321635246, "learning_rate": 1.1643214641461917e-05, "loss": 0.0009, "step": 11736 }, { "epoch": 0.648166556218246, "grad_norm": 0.3237575888633728, "learning_rate": 1.1639964715042563e-05, "loss": 0.0042, "step": 11737 }, { "epoch": 0.6482217804285398, "grad_norm": 0.03861458599567413, "learning_rate": 1.1636715056084538e-05, "loss": 0.0008, "step": 11738 }, { "epoch": 0.6482770046388336, "grad_norm": 0.2179400622844696, "learning_rate": 1.1633465664691808e-05, "loss": 0.0084, "step": 11739 }, { "epoch": 0.6483322288491274, "grad_norm": 2.192566156387329, "learning_rate": 1.163021654096832e-05, "loss": 0.3046, "step": 11740 }, { "epoch": 0.6483874530594212, "grad_norm": 0.060441382229328156, "learning_rate": 1.1626967685018049e-05, "loss": 0.0019, "step": 11741 }, { "epoch": 0.648442677269715, "grad_norm": 0.33835864067077637, "learning_rate": 1.1623719096944903e-05, "loss": 0.0124, "step": 11742 }, { "epoch": 0.6484979014800089, "grad_norm": 0.9708632230758667, "learning_rate": 1.1620470776852838e-05, "loss": 0.0192, "step": 11743 }, { "epoch": 0.6485531256903027, "grad_norm": 4.176026344299316, "learning_rate": 1.161722272484577e-05, "loss": 0.4216, "step": 11744 }, { "epoch": 0.6486083499005965, "grad_norm": 0.8392964005470276, "learning_rate": 1.1613974941027609e-05, "loss": 0.0217, "step": 11745 }, { "epoch": 0.6486635741108903, "grad_norm": 0.17376059293746948, "learning_rate": 1.1610727425502257e-05, "loss": 0.0045, "step": 11746 }, { "epoch": 0.648718798321184, "grad_norm": 4.109475612640381, "learning_rate": 1.1607480178373623e-05, "loss": 0.7782, "step": 11747 }, { "epoch": 0.6487740225314778, "grad_norm": 1.6732826232910156, "learning_rate": 1.1604233199745594e-05, "loss": 0.0611, "step": 11748 }, { "epoch": 0.6488292467417716, "grad_norm": 0.05420106649398804, "learning_rate": 1.1600986489722046e-05, "loss": 0.002, "step": 11749 }, { "epoch": 0.6488844709520654, "grad_norm": 0.12228363752365112, "learning_rate": 1.159774004840684e-05, "loss": 0.0054, "step": 11750 }, { "epoch": 0.6489396951623592, "grad_norm": 3.5049922466278076, "learning_rate": 1.159449387590387e-05, "loss": 0.3816, "step": 11751 }, { "epoch": 0.648994919372653, "grad_norm": 0.1379328817129135, "learning_rate": 1.1591247972316952e-05, "loss": 0.0026, "step": 11752 }, { "epoch": 0.6490501435829468, "grad_norm": 1.542266607284546, "learning_rate": 1.158800233774996e-05, "loss": 0.1235, "step": 11753 }, { "epoch": 0.6491053677932406, "grad_norm": 4.212788105010986, "learning_rate": 1.158475697230672e-05, "loss": 0.441, "step": 11754 }, { "epoch": 0.6491605920035344, "grad_norm": 1.5282191038131714, "learning_rate": 1.1581511876091062e-05, "loss": 0.0376, "step": 11755 }, { "epoch": 0.6492158162138282, "grad_norm": 0.0841377004981041, "learning_rate": 1.1578267049206797e-05, "loss": 0.0028, "step": 11756 }, { "epoch": 0.649271040424122, "grad_norm": 5.040698051452637, "learning_rate": 1.1575022491757761e-05, "loss": 1.1776, "step": 11757 }, { "epoch": 0.6493262646344157, "grad_norm": 0.16271352767944336, "learning_rate": 1.1571778203847723e-05, "loss": 0.0062, "step": 11758 }, { "epoch": 0.6493814888447095, "grad_norm": 0.0836445763707161, "learning_rate": 1.1568534185580505e-05, "loss": 0.0017, "step": 11759 }, { "epoch": 0.6494367130550033, "grad_norm": 0.02763262949883938, "learning_rate": 1.1565290437059877e-05, "loss": 0.001, "step": 11760 }, { "epoch": 0.6494919372652971, "grad_norm": 2.5140221118927, "learning_rate": 1.1562046958389626e-05, "loss": 0.1267, "step": 11761 }, { "epoch": 0.6495471614755909, "grad_norm": 1.3536756038665771, "learning_rate": 1.1558803749673503e-05, "loss": 0.0603, "step": 11762 }, { "epoch": 0.6496023856858847, "grad_norm": 0.13783612847328186, "learning_rate": 1.1555560811015289e-05, "loss": 0.0031, "step": 11763 }, { "epoch": 0.6496576098961785, "grad_norm": 2.6960690021514893, "learning_rate": 1.1552318142518723e-05, "loss": 0.1316, "step": 11764 }, { "epoch": 0.6497128341064723, "grad_norm": 0.1364961713552475, "learning_rate": 1.154907574428755e-05, "loss": 0.0048, "step": 11765 }, { "epoch": 0.6497680583167661, "grad_norm": 0.1735081821680069, "learning_rate": 1.1545833616425494e-05, "loss": 0.0056, "step": 11766 }, { "epoch": 0.6498232825270599, "grad_norm": 0.8966436386108398, "learning_rate": 1.1542591759036308e-05, "loss": 0.0146, "step": 11767 }, { "epoch": 0.6498785067373537, "grad_norm": 0.04248370602726936, "learning_rate": 1.1539350172223668e-05, "loss": 0.001, "step": 11768 }, { "epoch": 0.6499337309476475, "grad_norm": 0.014292782172560692, "learning_rate": 1.1536108856091316e-05, "loss": 0.0006, "step": 11769 }, { "epoch": 0.6499889551579412, "grad_norm": 0.07854785025119781, "learning_rate": 1.1532867810742934e-05, "loss": 0.002, "step": 11770 }, { "epoch": 0.650044179368235, "grad_norm": 0.04209800809621811, "learning_rate": 1.1529627036282214e-05, "loss": 0.0011, "step": 11771 }, { "epoch": 0.6500994035785288, "grad_norm": 6.444925785064697, "learning_rate": 1.1526386532812832e-05, "loss": 1.3875, "step": 11772 }, { "epoch": 0.6501546277888226, "grad_norm": 0.05090376362204552, "learning_rate": 1.1523146300438486e-05, "loss": 0.0016, "step": 11773 }, { "epoch": 0.6502098519991164, "grad_norm": 5.810526371002197, "learning_rate": 1.1519906339262805e-05, "loss": 0.2653, "step": 11774 }, { "epoch": 0.6502650762094102, "grad_norm": 0.004718957468867302, "learning_rate": 1.1516666649389469e-05, "loss": 0.0002, "step": 11775 }, { "epoch": 0.650320300419704, "grad_norm": 0.2604500949382782, "learning_rate": 1.1513427230922121e-05, "loss": 0.008, "step": 11776 }, { "epoch": 0.6503755246299978, "grad_norm": 0.0070140669122338295, "learning_rate": 1.1510188083964393e-05, "loss": 0.0002, "step": 11777 }, { "epoch": 0.6504307488402916, "grad_norm": 1.4056212902069092, "learning_rate": 1.1506949208619911e-05, "loss": 0.0238, "step": 11778 }, { "epoch": 0.6504859730505854, "grad_norm": 0.23747918009757996, "learning_rate": 1.150371060499231e-05, "loss": 0.0055, "step": 11779 }, { "epoch": 0.6505411972608792, "grad_norm": 0.130307137966156, "learning_rate": 1.1500472273185194e-05, "loss": 0.0033, "step": 11780 }, { "epoch": 0.6505964214711729, "grad_norm": 0.29381081461906433, "learning_rate": 1.1497234213302168e-05, "loss": 0.0061, "step": 11781 }, { "epoch": 0.6506516456814667, "grad_norm": 0.09192899614572525, "learning_rate": 1.1493996425446819e-05, "loss": 0.0024, "step": 11782 }, { "epoch": 0.6507068698917605, "grad_norm": 4.977092742919922, "learning_rate": 1.1490758909722754e-05, "loss": 1.1347, "step": 11783 }, { "epoch": 0.6507620941020543, "grad_norm": 3.9518415927886963, "learning_rate": 1.1487521666233521e-05, "loss": 0.8525, "step": 11784 }, { "epoch": 0.6508173183123481, "grad_norm": 0.03185980021953583, "learning_rate": 1.1484284695082713e-05, "loss": 0.0008, "step": 11785 }, { "epoch": 0.6508725425226419, "grad_norm": 0.03845272213220596, "learning_rate": 1.148104799637388e-05, "loss": 0.001, "step": 11786 }, { "epoch": 0.6509277667329357, "grad_norm": 2.5257036685943604, "learning_rate": 1.1477811570210573e-05, "loss": 0.3721, "step": 11787 }, { "epoch": 0.6509829909432295, "grad_norm": 0.14061449468135834, "learning_rate": 1.1474575416696325e-05, "loss": 0.004, "step": 11788 }, { "epoch": 0.6510382151535233, "grad_norm": 1.5486007928848267, "learning_rate": 1.1471339535934693e-05, "loss": 0.2075, "step": 11789 }, { "epoch": 0.6510934393638171, "grad_norm": 2.925379753112793, "learning_rate": 1.1468103928029186e-05, "loss": 0.3673, "step": 11790 }, { "epoch": 0.6511486635741109, "grad_norm": 0.09585317224264145, "learning_rate": 1.1464868593083325e-05, "loss": 0.0027, "step": 11791 }, { "epoch": 0.6512038877844046, "grad_norm": 1.8538297414779663, "learning_rate": 1.1461633531200618e-05, "loss": 0.2348, "step": 11792 }, { "epoch": 0.6512591119946984, "grad_norm": 0.0641796663403511, "learning_rate": 1.145839874248456e-05, "loss": 0.0011, "step": 11793 }, { "epoch": 0.6513143362049922, "grad_norm": 0.017584150657057762, "learning_rate": 1.1455164227038642e-05, "loss": 0.0004, "step": 11794 }, { "epoch": 0.651369560415286, "grad_norm": 1.3936742544174194, "learning_rate": 1.145192998496634e-05, "loss": 0.0497, "step": 11795 }, { "epoch": 0.6514247846255798, "grad_norm": 0.19231659173965454, "learning_rate": 1.1448696016371148e-05, "loss": 0.0059, "step": 11796 }, { "epoch": 0.6514800088358736, "grad_norm": 7.59191370010376, "learning_rate": 1.14454623213565e-05, "loss": 0.1284, "step": 11797 }, { "epoch": 0.6515352330461675, "grad_norm": 0.09273253381252289, "learning_rate": 1.1442228900025873e-05, "loss": 0.0017, "step": 11798 }, { "epoch": 0.6515904572564613, "grad_norm": 6.391822814941406, "learning_rate": 1.1438995752482706e-05, "loss": 0.5861, "step": 11799 }, { "epoch": 0.6516456814667551, "grad_norm": 0.21796713769435883, "learning_rate": 1.1435762878830441e-05, "loss": 0.0059, "step": 11800 }, { "epoch": 0.6517009056770489, "grad_norm": 0.07146003842353821, "learning_rate": 1.1432530279172491e-05, "loss": 0.0015, "step": 11801 }, { "epoch": 0.6517561298873427, "grad_norm": 5.437784671783447, "learning_rate": 1.1429297953612295e-05, "loss": 1.048, "step": 11802 }, { "epoch": 0.6518113540976364, "grad_norm": 0.44700169563293457, "learning_rate": 1.1426065902253261e-05, "loss": 0.0137, "step": 11803 }, { "epoch": 0.6518665783079302, "grad_norm": 0.07493095844984055, "learning_rate": 1.1422834125198784e-05, "loss": 0.0026, "step": 11804 }, { "epoch": 0.651921802518224, "grad_norm": 0.13296620547771454, "learning_rate": 1.1419602622552257e-05, "loss": 0.0037, "step": 11805 }, { "epoch": 0.6519770267285178, "grad_norm": 2.438608407974243, "learning_rate": 1.1416371394417082e-05, "loss": 0.2562, "step": 11806 }, { "epoch": 0.6520322509388116, "grad_norm": 3.575806140899658, "learning_rate": 1.1413140440896609e-05, "loss": 0.2816, "step": 11807 }, { "epoch": 0.6520874751491054, "grad_norm": 5.293093681335449, "learning_rate": 1.1409909762094227e-05, "loss": 0.7146, "step": 11808 }, { "epoch": 0.6521426993593992, "grad_norm": 0.21624737977981567, "learning_rate": 1.1406679358113283e-05, "loss": 0.0059, "step": 11809 }, { "epoch": 0.652197923569693, "grad_norm": 0.010268907994031906, "learning_rate": 1.1403449229057135e-05, "loss": 0.0004, "step": 11810 }, { "epoch": 0.6522531477799868, "grad_norm": 2.1301755905151367, "learning_rate": 1.140021937502911e-05, "loss": 0.5261, "step": 11811 }, { "epoch": 0.6523083719902806, "grad_norm": 1.9730862379074097, "learning_rate": 1.1396989796132565e-05, "loss": 0.0705, "step": 11812 }, { "epoch": 0.6523635962005744, "grad_norm": 1.5257519483566284, "learning_rate": 1.1393760492470791e-05, "loss": 0.0816, "step": 11813 }, { "epoch": 0.6524188204108681, "grad_norm": 1.6937185525894165, "learning_rate": 1.139053146414713e-05, "loss": 0.1933, "step": 11814 }, { "epoch": 0.6524740446211619, "grad_norm": 0.004068166948854923, "learning_rate": 1.1387302711264876e-05, "loss": 0.0001, "step": 11815 }, { "epoch": 0.6525292688314557, "grad_norm": 6.106431007385254, "learning_rate": 1.1384074233927329e-05, "loss": 0.3078, "step": 11816 }, { "epoch": 0.6525844930417495, "grad_norm": 5.310836315155029, "learning_rate": 1.1380846032237764e-05, "loss": 0.5808, "step": 11817 }, { "epoch": 0.6526397172520433, "grad_norm": 0.364580899477005, "learning_rate": 1.1377618106299484e-05, "loss": 0.0069, "step": 11818 }, { "epoch": 0.6526949414623371, "grad_norm": 0.22566422820091248, "learning_rate": 1.1374390456215747e-05, "loss": 0.0077, "step": 11819 }, { "epoch": 0.6527501656726309, "grad_norm": 0.43272554874420166, "learning_rate": 1.1371163082089813e-05, "loss": 0.0135, "step": 11820 }, { "epoch": 0.6528053898829247, "grad_norm": 0.03016061894595623, "learning_rate": 1.1367935984024933e-05, "loss": 0.0008, "step": 11821 }, { "epoch": 0.6528606140932185, "grad_norm": 5.819457054138184, "learning_rate": 1.1364709162124367e-05, "loss": 1.4756, "step": 11822 }, { "epoch": 0.6529158383035123, "grad_norm": 0.06834505498409271, "learning_rate": 1.1361482616491327e-05, "loss": 0.0017, "step": 11823 }, { "epoch": 0.6529710625138061, "grad_norm": 4.645638942718506, "learning_rate": 1.1358256347229055e-05, "loss": 1.0553, "step": 11824 }, { "epoch": 0.6530262867240998, "grad_norm": 1.1873877048492432, "learning_rate": 1.1355030354440767e-05, "loss": 0.0408, "step": 11825 }, { "epoch": 0.6530815109343936, "grad_norm": 2.0550873279571533, "learning_rate": 1.135180463822967e-05, "loss": 0.0816, "step": 11826 }, { "epoch": 0.6531367351446874, "grad_norm": 1.4349485635757446, "learning_rate": 1.1348579198698953e-05, "loss": 0.0264, "step": 11827 }, { "epoch": 0.6531919593549812, "grad_norm": 3.801976442337036, "learning_rate": 1.1345354035951823e-05, "loss": 0.8319, "step": 11828 }, { "epoch": 0.653247183565275, "grad_norm": 0.14111961424350739, "learning_rate": 1.1342129150091459e-05, "loss": 0.0048, "step": 11829 }, { "epoch": 0.6533024077755688, "grad_norm": 3.7181296348571777, "learning_rate": 1.133890454122103e-05, "loss": 0.5718, "step": 11830 }, { "epoch": 0.6533576319858626, "grad_norm": 3.77795147895813, "learning_rate": 1.1335680209443703e-05, "loss": 0.7109, "step": 11831 }, { "epoch": 0.6534128561961564, "grad_norm": 2.595928430557251, "learning_rate": 1.133245615486263e-05, "loss": 0.0772, "step": 11832 }, { "epoch": 0.6534680804064502, "grad_norm": 3.2225496768951416, "learning_rate": 1.1329232377580954e-05, "loss": 0.5627, "step": 11833 }, { "epoch": 0.653523304616744, "grad_norm": 3.0572497844696045, "learning_rate": 1.1326008877701826e-05, "loss": 0.5349, "step": 11834 }, { "epoch": 0.6535785288270378, "grad_norm": 2.2157318592071533, "learning_rate": 1.132278565532837e-05, "loss": 0.4154, "step": 11835 }, { "epoch": 0.6536337530373315, "grad_norm": 1.7943862676620483, "learning_rate": 1.13195627105637e-05, "loss": 0.0327, "step": 11836 }, { "epoch": 0.6536889772476253, "grad_norm": 3.4640634059906006, "learning_rate": 1.1316340043510925e-05, "loss": 1.0313, "step": 11837 }, { "epoch": 0.6537442014579191, "grad_norm": 0.134063720703125, "learning_rate": 1.131311765427317e-05, "loss": 0.0034, "step": 11838 }, { "epoch": 0.6537994256682129, "grad_norm": 3.318207263946533, "learning_rate": 1.1309895542953492e-05, "loss": 0.3308, "step": 11839 }, { "epoch": 0.6538546498785067, "grad_norm": 0.17225776612758636, "learning_rate": 1.1306673709655009e-05, "loss": 0.004, "step": 11840 }, { "epoch": 0.6539098740888005, "grad_norm": 0.29124146699905396, "learning_rate": 1.1303452154480778e-05, "loss": 0.006, "step": 11841 }, { "epoch": 0.6539650982990943, "grad_norm": 2.812647581100464, "learning_rate": 1.1300230877533873e-05, "loss": 0.1436, "step": 11842 }, { "epoch": 0.6540203225093881, "grad_norm": 0.043620798736810684, "learning_rate": 1.1297009878917343e-05, "loss": 0.001, "step": 11843 }, { "epoch": 0.6540755467196819, "grad_norm": 0.4289470911026001, "learning_rate": 1.1293789158734247e-05, "loss": 0.011, "step": 11844 }, { "epoch": 0.6541307709299757, "grad_norm": 0.054897110909223557, "learning_rate": 1.1290568717087625e-05, "loss": 0.001, "step": 11845 }, { "epoch": 0.6541859951402695, "grad_norm": 1.785080909729004, "learning_rate": 1.1287348554080505e-05, "loss": 0.1581, "step": 11846 }, { "epoch": 0.6542412193505633, "grad_norm": 2.8335986137390137, "learning_rate": 1.1284128669815897e-05, "loss": 0.213, "step": 11847 }, { "epoch": 0.654296443560857, "grad_norm": 0.051741164177656174, "learning_rate": 1.128090906439684e-05, "loss": 0.0011, "step": 11848 }, { "epoch": 0.6543516677711508, "grad_norm": 0.4244869351387024, "learning_rate": 1.1277689737926314e-05, "loss": 0.0083, "step": 11849 }, { "epoch": 0.6544068919814446, "grad_norm": 5.5308966636657715, "learning_rate": 1.1274470690507328e-05, "loss": 0.5558, "step": 11850 }, { "epoch": 0.6544621161917384, "grad_norm": 1.8851466178894043, "learning_rate": 1.1271251922242867e-05, "loss": 0.0871, "step": 11851 }, { "epoch": 0.6545173404020322, "grad_norm": 0.0264858677983284, "learning_rate": 1.1268033433235907e-05, "loss": 0.0009, "step": 11852 }, { "epoch": 0.654572564612326, "grad_norm": 1.0289467573165894, "learning_rate": 1.1264815223589415e-05, "loss": 0.0315, "step": 11853 }, { "epoch": 0.6546277888226198, "grad_norm": 1.8623188734054565, "learning_rate": 1.1261597293406354e-05, "loss": 0.1006, "step": 11854 }, { "epoch": 0.6546830130329137, "grad_norm": 0.011447658762335777, "learning_rate": 1.1258379642789671e-05, "loss": 0.0004, "step": 11855 }, { "epoch": 0.6547382372432075, "grad_norm": 2.2011899948120117, "learning_rate": 1.1255162271842303e-05, "loss": 0.1451, "step": 11856 }, { "epoch": 0.6547934614535013, "grad_norm": 5.168397426605225, "learning_rate": 1.12519451806672e-05, "loss": 1.3468, "step": 11857 }, { "epoch": 0.6548486856637951, "grad_norm": 6.687968730926514, "learning_rate": 1.124872836936727e-05, "loss": 0.2755, "step": 11858 }, { "epoch": 0.6549039098740888, "grad_norm": 0.40460747480392456, "learning_rate": 1.1245511838045436e-05, "loss": 0.0124, "step": 11859 }, { "epoch": 0.6549591340843826, "grad_norm": 0.03715440258383751, "learning_rate": 1.124229558680459e-05, "loss": 0.0011, "step": 11860 }, { "epoch": 0.6550143582946764, "grad_norm": 0.33362799882888794, "learning_rate": 1.1239079615747662e-05, "loss": 0.009, "step": 11861 }, { "epoch": 0.6550695825049702, "grad_norm": 1.2035722732543945, "learning_rate": 1.1235863924977497e-05, "loss": 0.0163, "step": 11862 }, { "epoch": 0.655124806715264, "grad_norm": 2.5083489418029785, "learning_rate": 1.1232648514597004e-05, "loss": 0.9746, "step": 11863 }, { "epoch": 0.6551800309255578, "grad_norm": 0.07136145979166031, "learning_rate": 1.1229433384709047e-05, "loss": 0.0022, "step": 11864 }, { "epoch": 0.6552352551358516, "grad_norm": 4.307434558868408, "learning_rate": 1.1226218535416484e-05, "loss": 0.4523, "step": 11865 }, { "epoch": 0.6552904793461454, "grad_norm": 4.594808578491211, "learning_rate": 1.1223003966822158e-05, "loss": 0.3045, "step": 11866 }, { "epoch": 0.6553457035564392, "grad_norm": 0.020978672429919243, "learning_rate": 1.1219789679028935e-05, "loss": 0.0005, "step": 11867 }, { "epoch": 0.655400927766733, "grad_norm": 0.5018909573554993, "learning_rate": 1.1216575672139631e-05, "loss": 0.0144, "step": 11868 }, { "epoch": 0.6554561519770268, "grad_norm": 0.03774068132042885, "learning_rate": 1.121336194625708e-05, "loss": 0.0013, "step": 11869 }, { "epoch": 0.6555113761873205, "grad_norm": 5.538861274719238, "learning_rate": 1.1210148501484084e-05, "loss": 0.2672, "step": 11870 }, { "epoch": 0.6555666003976143, "grad_norm": 3.286015748977661, "learning_rate": 1.120693533792348e-05, "loss": 0.6627, "step": 11871 }, { "epoch": 0.6556218246079081, "grad_norm": 0.022621866315603256, "learning_rate": 1.1203722455678028e-05, "loss": 0.0007, "step": 11872 }, { "epoch": 0.6556770488182019, "grad_norm": 0.20202460885047913, "learning_rate": 1.1200509854850545e-05, "loss": 0.0038, "step": 11873 }, { "epoch": 0.6557322730284957, "grad_norm": 0.20338478684425354, "learning_rate": 1.1197297535543805e-05, "loss": 0.005, "step": 11874 }, { "epoch": 0.6557874972387895, "grad_norm": 0.4080005884170532, "learning_rate": 1.1194085497860576e-05, "loss": 0.0099, "step": 11875 }, { "epoch": 0.6558427214490833, "grad_norm": 1.4922282695770264, "learning_rate": 1.1190873741903613e-05, "loss": 0.0387, "step": 11876 }, { "epoch": 0.6558979456593771, "grad_norm": 3.1024065017700195, "learning_rate": 1.1187662267775694e-05, "loss": 0.3098, "step": 11877 }, { "epoch": 0.6559531698696709, "grad_norm": 1.7445447444915771, "learning_rate": 1.118445107557953e-05, "loss": 0.0674, "step": 11878 }, { "epoch": 0.6560083940799647, "grad_norm": 2.418436288833618, "learning_rate": 1.118124016541788e-05, "loss": 0.4805, "step": 11879 }, { "epoch": 0.6560636182902585, "grad_norm": 0.014642305672168732, "learning_rate": 1.1178029537393465e-05, "loss": 0.0006, "step": 11880 }, { "epoch": 0.6561188425005522, "grad_norm": 0.2886659502983093, "learning_rate": 1.1174819191609e-05, "loss": 0.0076, "step": 11881 }, { "epoch": 0.656174066710846, "grad_norm": 1.7140499353408813, "learning_rate": 1.1171609128167184e-05, "loss": 0.0645, "step": 11882 }, { "epoch": 0.6562292909211398, "grad_norm": 5.605841636657715, "learning_rate": 1.1168399347170733e-05, "loss": 0.6352, "step": 11883 }, { "epoch": 0.6562845151314336, "grad_norm": 2.4343502521514893, "learning_rate": 1.1165189848722333e-05, "loss": 0.2215, "step": 11884 }, { "epoch": 0.6563397393417274, "grad_norm": 0.017935916781425476, "learning_rate": 1.1161980632924658e-05, "loss": 0.0005, "step": 11885 }, { "epoch": 0.6563949635520212, "grad_norm": 0.1579824835062027, "learning_rate": 1.1158771699880374e-05, "loss": 0.0046, "step": 11886 }, { "epoch": 0.656450187762315, "grad_norm": 2.02361798286438, "learning_rate": 1.1155563049692173e-05, "loss": 0.106, "step": 11887 }, { "epoch": 0.6565054119726088, "grad_norm": 0.04168692231178284, "learning_rate": 1.115235468246267e-05, "loss": 0.0011, "step": 11888 }, { "epoch": 0.6565606361829026, "grad_norm": 0.07381252944469452, "learning_rate": 1.1149146598294538e-05, "loss": 0.003, "step": 11889 }, { "epoch": 0.6566158603931964, "grad_norm": 1.2704564332962036, "learning_rate": 1.1145938797290404e-05, "loss": 0.0729, "step": 11890 }, { "epoch": 0.6566710846034902, "grad_norm": 0.0350709930062294, "learning_rate": 1.1142731279552895e-05, "loss": 0.0011, "step": 11891 }, { "epoch": 0.6567263088137839, "grad_norm": 2.8955154418945312, "learning_rate": 1.1139524045184618e-05, "loss": 0.5482, "step": 11892 }, { "epoch": 0.6567815330240777, "grad_norm": 3.002765417098999, "learning_rate": 1.1136317094288206e-05, "loss": 0.6509, "step": 11893 }, { "epoch": 0.6568367572343715, "grad_norm": 0.024156643077731133, "learning_rate": 1.1133110426966231e-05, "loss": 0.0005, "step": 11894 }, { "epoch": 0.6568919814446653, "grad_norm": 0.02907211147248745, "learning_rate": 1.1129904043321304e-05, "loss": 0.0009, "step": 11895 }, { "epoch": 0.6569472056549591, "grad_norm": 0.1926238238811493, "learning_rate": 1.1126697943455998e-05, "loss": 0.0053, "step": 11896 }, { "epoch": 0.6570024298652529, "grad_norm": 0.1370103657245636, "learning_rate": 1.1123492127472886e-05, "loss": 0.0039, "step": 11897 }, { "epoch": 0.6570576540755467, "grad_norm": 0.0372636616230011, "learning_rate": 1.1120286595474524e-05, "loss": 0.0015, "step": 11898 }, { "epoch": 0.6571128782858405, "grad_norm": 0.35508543252944946, "learning_rate": 1.1117081347563479e-05, "loss": 0.007, "step": 11899 }, { "epoch": 0.6571681024961343, "grad_norm": 0.26944324374198914, "learning_rate": 1.1113876383842292e-05, "loss": 0.0058, "step": 11900 }, { "epoch": 0.6572233267064281, "grad_norm": 0.005749276373535395, "learning_rate": 1.1110671704413496e-05, "loss": 0.0002, "step": 11901 }, { "epoch": 0.6572785509167219, "grad_norm": 0.03846757858991623, "learning_rate": 1.1107467309379612e-05, "loss": 0.001, "step": 11902 }, { "epoch": 0.6573337751270156, "grad_norm": 0.17650839686393738, "learning_rate": 1.1104263198843182e-05, "loss": 0.0031, "step": 11903 }, { "epoch": 0.6573889993373094, "grad_norm": 2.6075665950775146, "learning_rate": 1.1101059372906678e-05, "loss": 0.1541, "step": 11904 }, { "epoch": 0.6574442235476032, "grad_norm": 3.233560562133789, "learning_rate": 1.1097855831672628e-05, "loss": 0.5684, "step": 11905 }, { "epoch": 0.657499447757897, "grad_norm": 2.729703903198242, "learning_rate": 1.1094652575243515e-05, "loss": 0.2973, "step": 11906 }, { "epoch": 0.6575546719681908, "grad_norm": 5.613759994506836, "learning_rate": 1.1091449603721816e-05, "loss": 0.3896, "step": 11907 }, { "epoch": 0.6576098961784846, "grad_norm": 4.67647647857666, "learning_rate": 1.1088246917209999e-05, "loss": 0.6685, "step": 11908 }, { "epoch": 0.6576651203887784, "grad_norm": 1.49759042263031, "learning_rate": 1.1085044515810544e-05, "loss": 0.0578, "step": 11909 }, { "epoch": 0.6577203445990722, "grad_norm": 0.27464282512664795, "learning_rate": 1.108184239962589e-05, "loss": 0.007, "step": 11910 }, { "epoch": 0.657775568809366, "grad_norm": 0.1327458918094635, "learning_rate": 1.1078640568758489e-05, "loss": 0.0019, "step": 11911 }, { "epoch": 0.6578307930196599, "grad_norm": 3.07895827293396, "learning_rate": 1.1075439023310776e-05, "loss": 0.4908, "step": 11912 }, { "epoch": 0.6578860172299537, "grad_norm": 3.4376986026763916, "learning_rate": 1.1072237763385174e-05, "loss": 0.1349, "step": 11913 }, { "epoch": 0.6579412414402475, "grad_norm": 0.12669216096401215, "learning_rate": 1.10690367890841e-05, "loss": 0.0032, "step": 11914 }, { "epoch": 0.6579964656505412, "grad_norm": 6.066680908203125, "learning_rate": 1.106583610050996e-05, "loss": 0.7002, "step": 11915 }, { "epoch": 0.658051689860835, "grad_norm": 0.0194405410438776, "learning_rate": 1.1062635697765171e-05, "loss": 0.0004, "step": 11916 }, { "epoch": 0.6581069140711288, "grad_norm": 0.06915245205163956, "learning_rate": 1.1059435580952096e-05, "loss": 0.0025, "step": 11917 }, { "epoch": 0.6581621382814226, "grad_norm": 0.09225146472454071, "learning_rate": 1.1056235750173134e-05, "loss": 0.0019, "step": 11918 }, { "epoch": 0.6582173624917164, "grad_norm": 2.4375977516174316, "learning_rate": 1.1053036205530657e-05, "loss": 0.4604, "step": 11919 }, { "epoch": 0.6582725867020102, "grad_norm": 7.837510108947754, "learning_rate": 1.104983694712702e-05, "loss": 0.2947, "step": 11920 }, { "epoch": 0.658327810912304, "grad_norm": 1.6985349655151367, "learning_rate": 1.1046637975064569e-05, "loss": 0.3005, "step": 11921 }, { "epoch": 0.6583830351225978, "grad_norm": 0.052127089351415634, "learning_rate": 1.1043439289445668e-05, "loss": 0.0017, "step": 11922 }, { "epoch": 0.6584382593328916, "grad_norm": 2.857858419418335, "learning_rate": 1.1040240890372642e-05, "loss": 0.4979, "step": 11923 }, { "epoch": 0.6584934835431854, "grad_norm": 3.418182849884033, "learning_rate": 1.103704277794782e-05, "loss": 0.5305, "step": 11924 }, { "epoch": 0.6585487077534792, "grad_norm": 5.1187615394592285, "learning_rate": 1.1033844952273504e-05, "loss": 1.1916, "step": 11925 }, { "epoch": 0.6586039319637729, "grad_norm": 0.017608752474188805, "learning_rate": 1.103064741345203e-05, "loss": 0.0004, "step": 11926 }, { "epoch": 0.6586591561740667, "grad_norm": 0.020444227382540703, "learning_rate": 1.1027450161585667e-05, "loss": 0.0006, "step": 11927 }, { "epoch": 0.6587143803843605, "grad_norm": 0.029749415814876556, "learning_rate": 1.1024253196776721e-05, "loss": 0.001, "step": 11928 }, { "epoch": 0.6587696045946543, "grad_norm": 2.412243127822876, "learning_rate": 1.1021056519127474e-05, "loss": 0.2886, "step": 11929 }, { "epoch": 0.6588248288049481, "grad_norm": 1.838836431503296, "learning_rate": 1.1017860128740186e-05, "loss": 0.0761, "step": 11930 }, { "epoch": 0.6588800530152419, "grad_norm": 1.6933964490890503, "learning_rate": 1.1014664025717114e-05, "loss": 0.0503, "step": 11931 }, { "epoch": 0.6589352772255357, "grad_norm": 0.02670644409954548, "learning_rate": 1.1011468210160538e-05, "loss": 0.0008, "step": 11932 }, { "epoch": 0.6589905014358295, "grad_norm": 3.157639980316162, "learning_rate": 1.100827268217267e-05, "loss": 0.1992, "step": 11933 }, { "epoch": 0.6590457256461233, "grad_norm": 2.415523052215576, "learning_rate": 1.1005077441855763e-05, "loss": 0.6431, "step": 11934 }, { "epoch": 0.6591009498564171, "grad_norm": 1.6172281503677368, "learning_rate": 1.1001882489312034e-05, "loss": 0.0991, "step": 11935 }, { "epoch": 0.6591561740667109, "grad_norm": 0.42482030391693115, "learning_rate": 1.0998687824643703e-05, "loss": 0.0061, "step": 11936 }, { "epoch": 0.6592113982770046, "grad_norm": 1.0388494729995728, "learning_rate": 1.0995493447952965e-05, "loss": 0.0405, "step": 11937 }, { "epoch": 0.6592666224872984, "grad_norm": 5.461990833282471, "learning_rate": 1.0992299359342036e-05, "loss": 0.4125, "step": 11938 }, { "epoch": 0.6593218466975922, "grad_norm": 2.0878756046295166, "learning_rate": 1.0989105558913091e-05, "loss": 0.054, "step": 11939 }, { "epoch": 0.659377070907886, "grad_norm": 0.5525025725364685, "learning_rate": 1.0985912046768315e-05, "loss": 0.0152, "step": 11940 }, { "epoch": 0.6594322951181798, "grad_norm": 0.023801634088158607, "learning_rate": 1.0982718823009866e-05, "loss": 0.0009, "step": 11941 }, { "epoch": 0.6594875193284736, "grad_norm": 5.348731517791748, "learning_rate": 1.097952588773993e-05, "loss": 1.4387, "step": 11942 }, { "epoch": 0.6595427435387674, "grad_norm": 0.07163698971271515, "learning_rate": 1.0976333241060624e-05, "loss": 0.002, "step": 11943 }, { "epoch": 0.6595979677490612, "grad_norm": 3.355931282043457, "learning_rate": 1.0973140883074114e-05, "loss": 0.1203, "step": 11944 }, { "epoch": 0.659653191959355, "grad_norm": 2.2934324741363525, "learning_rate": 1.0969948813882527e-05, "loss": 0.2179, "step": 11945 }, { "epoch": 0.6597084161696488, "grad_norm": 5.468616962432861, "learning_rate": 1.0966757033587982e-05, "loss": 1.1981, "step": 11946 }, { "epoch": 0.6597636403799426, "grad_norm": 1.0498567819595337, "learning_rate": 1.096356554229259e-05, "loss": 0.0186, "step": 11947 }, { "epoch": 0.6598188645902363, "grad_norm": 0.1716044396162033, "learning_rate": 1.0960374340098472e-05, "loss": 0.0034, "step": 11948 }, { "epoch": 0.6598740888005301, "grad_norm": 0.8747572898864746, "learning_rate": 1.0957183427107711e-05, "loss": 0.0199, "step": 11949 }, { "epoch": 0.6599293130108239, "grad_norm": 3.365938901901245, "learning_rate": 1.0953992803422396e-05, "loss": 0.8506, "step": 11950 }, { "epoch": 0.6599845372211177, "grad_norm": 3.504751205444336, "learning_rate": 1.0950802469144603e-05, "loss": 0.8657, "step": 11951 }, { "epoch": 0.6600397614314115, "grad_norm": 0.1519482284784317, "learning_rate": 1.0947612424376403e-05, "loss": 0.003, "step": 11952 }, { "epoch": 0.6600949856417053, "grad_norm": 1.5215280055999756, "learning_rate": 1.0944422669219845e-05, "loss": 0.0574, "step": 11953 }, { "epoch": 0.6601502098519991, "grad_norm": 0.8918730616569519, "learning_rate": 1.094123320377699e-05, "loss": 0.0276, "step": 11954 }, { "epoch": 0.6602054340622929, "grad_norm": 1.8026247024536133, "learning_rate": 1.0938044028149878e-05, "loss": 0.0664, "step": 11955 }, { "epoch": 0.6602606582725867, "grad_norm": 0.011957311071455479, "learning_rate": 1.0934855142440534e-05, "loss": 0.0006, "step": 11956 }, { "epoch": 0.6603158824828805, "grad_norm": 2.138221502304077, "learning_rate": 1.0931666546750975e-05, "loss": 0.0936, "step": 11957 }, { "epoch": 0.6603711066931743, "grad_norm": 2.5405020713806152, "learning_rate": 1.0928478241183233e-05, "loss": 0.2385, "step": 11958 }, { "epoch": 0.660426330903468, "grad_norm": 3.087177276611328, "learning_rate": 1.0925290225839285e-05, "loss": 0.0657, "step": 11959 }, { "epoch": 0.6604815551137618, "grad_norm": 2.2996232509613037, "learning_rate": 1.0922102500821141e-05, "loss": 0.5271, "step": 11960 }, { "epoch": 0.6605367793240556, "grad_norm": 0.01552844513207674, "learning_rate": 1.0918915066230784e-05, "loss": 0.0005, "step": 11961 }, { "epoch": 0.6605920035343494, "grad_norm": 0.16966019570827484, "learning_rate": 1.0915727922170187e-05, "loss": 0.0047, "step": 11962 }, { "epoch": 0.6606472277446432, "grad_norm": 0.6828019022941589, "learning_rate": 1.0912541068741308e-05, "loss": 0.0097, "step": 11963 }, { "epoch": 0.660702451954937, "grad_norm": 0.017049524933099747, "learning_rate": 1.0909354506046118e-05, "loss": 0.0005, "step": 11964 }, { "epoch": 0.6607576761652308, "grad_norm": 0.015006919391453266, "learning_rate": 1.0906168234186556e-05, "loss": 0.0005, "step": 11965 }, { "epoch": 0.6608129003755246, "grad_norm": 0.019523655995726585, "learning_rate": 1.0902982253264562e-05, "loss": 0.0009, "step": 11966 }, { "epoch": 0.6608681245858185, "grad_norm": 0.09341973811388016, "learning_rate": 1.0899796563382056e-05, "loss": 0.0015, "step": 11967 }, { "epoch": 0.6609233487961123, "grad_norm": 0.13237276673316956, "learning_rate": 1.0896611164640982e-05, "loss": 0.0052, "step": 11968 }, { "epoch": 0.6609785730064061, "grad_norm": 0.41299909353256226, "learning_rate": 1.0893426057143217e-05, "loss": 0.0062, "step": 11969 }, { "epoch": 0.6610337972166997, "grad_norm": 0.04013243690133095, "learning_rate": 1.0890241240990687e-05, "loss": 0.0016, "step": 11970 }, { "epoch": 0.6610890214269936, "grad_norm": 0.3000614643096924, "learning_rate": 1.0887056716285271e-05, "loss": 0.0057, "step": 11971 }, { "epoch": 0.6611442456372874, "grad_norm": 0.15801461040973663, "learning_rate": 1.0883872483128854e-05, "loss": 0.0019, "step": 11972 }, { "epoch": 0.6611994698475812, "grad_norm": 0.7166174650192261, "learning_rate": 1.088068854162331e-05, "loss": 0.0174, "step": 11973 }, { "epoch": 0.661254694057875, "grad_norm": 2.7536325454711914, "learning_rate": 1.0877504891870502e-05, "loss": 0.2852, "step": 11974 }, { "epoch": 0.6613099182681688, "grad_norm": 0.016592271625995636, "learning_rate": 1.0874321533972281e-05, "loss": 0.0007, "step": 11975 }, { "epoch": 0.6613651424784626, "grad_norm": 0.5285589694976807, "learning_rate": 1.0871138468030487e-05, "loss": 0.1139, "step": 11976 }, { "epoch": 0.6614203666887564, "grad_norm": 3.167379856109619, "learning_rate": 1.086795569414697e-05, "loss": 0.6493, "step": 11977 }, { "epoch": 0.6614755908990502, "grad_norm": 0.1340491622686386, "learning_rate": 1.086477321242355e-05, "loss": 0.0038, "step": 11978 }, { "epoch": 0.661530815109344, "grad_norm": 0.012900693342089653, "learning_rate": 1.086159102296204e-05, "loss": 0.0004, "step": 11979 }, { "epoch": 0.6615860393196378, "grad_norm": 0.02527806907892227, "learning_rate": 1.085840912586424e-05, "loss": 0.0008, "step": 11980 }, { "epoch": 0.6616412635299315, "grad_norm": 2.7553904056549072, "learning_rate": 1.0855227521231973e-05, "loss": 0.4968, "step": 11981 }, { "epoch": 0.6616964877402253, "grad_norm": 1.9262205362319946, "learning_rate": 1.0852046209166995e-05, "loss": 0.3618, "step": 11982 }, { "epoch": 0.6617517119505191, "grad_norm": 0.27748191356658936, "learning_rate": 1.0848865189771114e-05, "loss": 0.0062, "step": 11983 }, { "epoch": 0.6618069361608129, "grad_norm": 0.30389800667762756, "learning_rate": 1.0845684463146084e-05, "loss": 0.0037, "step": 11984 }, { "epoch": 0.6618621603711067, "grad_norm": 2.8592793941497803, "learning_rate": 1.0842504029393672e-05, "loss": 0.6654, "step": 11985 }, { "epoch": 0.6619173845814005, "grad_norm": 1.595763921737671, "learning_rate": 1.0839323888615617e-05, "loss": 0.0336, "step": 11986 }, { "epoch": 0.6619726087916943, "grad_norm": 0.010761699639260769, "learning_rate": 1.0836144040913677e-05, "loss": 0.0003, "step": 11987 }, { "epoch": 0.6620278330019881, "grad_norm": 2.1653456687927246, "learning_rate": 1.0832964486389579e-05, "loss": 0.1425, "step": 11988 }, { "epoch": 0.6620830572122819, "grad_norm": 0.05370283126831055, "learning_rate": 1.0829785225145042e-05, "loss": 0.0013, "step": 11989 }, { "epoch": 0.6621382814225757, "grad_norm": 0.4123702943325043, "learning_rate": 1.0826606257281776e-05, "loss": 0.0101, "step": 11990 }, { "epoch": 0.6621935056328695, "grad_norm": 1.8753650188446045, "learning_rate": 1.0823427582901507e-05, "loss": 0.157, "step": 11991 }, { "epoch": 0.6622487298431633, "grad_norm": 0.40386781096458435, "learning_rate": 1.08202492021059e-05, "loss": 0.0088, "step": 11992 }, { "epoch": 0.662303954053457, "grad_norm": 0.9535421133041382, "learning_rate": 1.081707111499666e-05, "loss": 0.136, "step": 11993 }, { "epoch": 0.6623591782637508, "grad_norm": 2.8965935707092285, "learning_rate": 1.0813893321675457e-05, "loss": 0.6458, "step": 11994 }, { "epoch": 0.6624144024740446, "grad_norm": 0.09811588376760483, "learning_rate": 1.081071582224396e-05, "loss": 0.0023, "step": 11995 }, { "epoch": 0.6624696266843384, "grad_norm": 2.8160088062286377, "learning_rate": 1.0807538616803819e-05, "loss": 0.4086, "step": 11996 }, { "epoch": 0.6625248508946322, "grad_norm": 0.11950446665287018, "learning_rate": 1.0804361705456699e-05, "loss": 0.0035, "step": 11997 }, { "epoch": 0.662580075104926, "grad_norm": 2.207885265350342, "learning_rate": 1.0801185088304213e-05, "loss": 0.0995, "step": 11998 }, { "epoch": 0.6626352993152198, "grad_norm": 0.20391814410686493, "learning_rate": 1.0798008765448012e-05, "loss": 0.0027, "step": 11999 }, { "epoch": 0.6626905235255136, "grad_norm": 0.8606491088867188, "learning_rate": 1.0794832736989706e-05, "loss": 0.0172, "step": 12000 }, { "epoch": 0.6627457477358074, "grad_norm": 4.56015682220459, "learning_rate": 1.0791657003030909e-05, "loss": 0.3209, "step": 12001 }, { "epoch": 0.6628009719461012, "grad_norm": 4.820712566375732, "learning_rate": 1.078848156367321e-05, "loss": 1.4405, "step": 12002 }, { "epoch": 0.662856196156395, "grad_norm": 0.5088120698928833, "learning_rate": 1.0785306419018218e-05, "loss": 0.015, "step": 12003 }, { "epoch": 0.6629114203666887, "grad_norm": 5.516849994659424, "learning_rate": 1.0782131569167507e-05, "loss": 1.1715, "step": 12004 }, { "epoch": 0.6629666445769825, "grad_norm": 1.7878241539001465, "learning_rate": 1.077895701422265e-05, "loss": 0.3133, "step": 12005 }, { "epoch": 0.6630218687872763, "grad_norm": 0.01750045083463192, "learning_rate": 1.07757827542852e-05, "loss": 0.0004, "step": 12006 }, { "epoch": 0.6630770929975701, "grad_norm": 4.154969215393066, "learning_rate": 1.0772608789456736e-05, "loss": 0.101, "step": 12007 }, { "epoch": 0.6631323172078639, "grad_norm": 0.05931894853711128, "learning_rate": 1.0769435119838772e-05, "loss": 0.0019, "step": 12008 }, { "epoch": 0.6631875414181577, "grad_norm": 2.8837385177612305, "learning_rate": 1.0766261745532863e-05, "loss": 0.3467, "step": 12009 }, { "epoch": 0.6632427656284515, "grad_norm": 5.009943008422852, "learning_rate": 1.0763088666640526e-05, "loss": 0.0537, "step": 12010 }, { "epoch": 0.6632979898387453, "grad_norm": 3.6243817806243896, "learning_rate": 1.0759915883263282e-05, "loss": 0.3654, "step": 12011 }, { "epoch": 0.6633532140490391, "grad_norm": 0.1770186424255371, "learning_rate": 1.0756743395502625e-05, "loss": 0.0042, "step": 12012 }, { "epoch": 0.6634084382593329, "grad_norm": 0.18153557181358337, "learning_rate": 1.0753571203460077e-05, "loss": 0.0063, "step": 12013 }, { "epoch": 0.6634636624696267, "grad_norm": 2.092639446258545, "learning_rate": 1.0750399307237094e-05, "loss": 0.0782, "step": 12014 }, { "epoch": 0.6635188866799204, "grad_norm": 0.033619243651628494, "learning_rate": 1.0747227706935177e-05, "loss": 0.0007, "step": 12015 }, { "epoch": 0.6635741108902142, "grad_norm": 1.3630752563476562, "learning_rate": 1.074405640265579e-05, "loss": 0.0419, "step": 12016 }, { "epoch": 0.663629335100508, "grad_norm": 4.094429016113281, "learning_rate": 1.0740885394500384e-05, "loss": 0.4024, "step": 12017 }, { "epoch": 0.6636845593108018, "grad_norm": 0.16327759623527527, "learning_rate": 1.073771468257041e-05, "loss": 0.0037, "step": 12018 }, { "epoch": 0.6637397835210956, "grad_norm": 0.826404869556427, "learning_rate": 1.0734544266967316e-05, "loss": 0.0319, "step": 12019 }, { "epoch": 0.6637950077313894, "grad_norm": 0.10247734934091568, "learning_rate": 1.0731374147792532e-05, "loss": 0.0034, "step": 12020 }, { "epoch": 0.6638502319416832, "grad_norm": 4.112728595733643, "learning_rate": 1.0728204325147476e-05, "loss": 1.2292, "step": 12021 }, { "epoch": 0.663905456151977, "grad_norm": 0.027859358116984367, "learning_rate": 1.0725034799133549e-05, "loss": 0.0007, "step": 12022 }, { "epoch": 0.6639606803622708, "grad_norm": 6.954827308654785, "learning_rate": 1.0721865569852182e-05, "loss": 1.0647, "step": 12023 }, { "epoch": 0.6640159045725647, "grad_norm": 3.3260416984558105, "learning_rate": 1.071869663740473e-05, "loss": 0.3731, "step": 12024 }, { "epoch": 0.6640711287828585, "grad_norm": 2.312433958053589, "learning_rate": 1.0715528001892603e-05, "loss": 0.046, "step": 12025 }, { "epoch": 0.6641263529931521, "grad_norm": 2.1640427112579346, "learning_rate": 1.071235966341717e-05, "loss": 0.2078, "step": 12026 }, { "epoch": 0.664181577203446, "grad_norm": 0.034142713993787766, "learning_rate": 1.0709191622079792e-05, "loss": 0.0009, "step": 12027 }, { "epoch": 0.6642368014137398, "grad_norm": 0.04880203306674957, "learning_rate": 1.0706023877981813e-05, "loss": 0.0018, "step": 12028 }, { "epoch": 0.6642920256240336, "grad_norm": 0.36401572823524475, "learning_rate": 1.0702856431224599e-05, "loss": 0.0123, "step": 12029 }, { "epoch": 0.6643472498343274, "grad_norm": 1.784488320350647, "learning_rate": 1.0699689281909475e-05, "loss": 0.0335, "step": 12030 }, { "epoch": 0.6644024740446212, "grad_norm": 3.700821876525879, "learning_rate": 1.0696522430137768e-05, "loss": 0.1535, "step": 12031 }, { "epoch": 0.664457698254915, "grad_norm": 0.17480993270874023, "learning_rate": 1.0693355876010793e-05, "loss": 0.0047, "step": 12032 }, { "epoch": 0.6645129224652088, "grad_norm": 3.1855874061584473, "learning_rate": 1.069018961962986e-05, "loss": 0.6913, "step": 12033 }, { "epoch": 0.6645681466755026, "grad_norm": 0.022882163524627686, "learning_rate": 1.0687023661096263e-05, "loss": 0.0006, "step": 12034 }, { "epoch": 0.6646233708857964, "grad_norm": 2.8660919666290283, "learning_rate": 1.0683858000511287e-05, "loss": 0.1387, "step": 12035 }, { "epoch": 0.6646785950960902, "grad_norm": 0.10642674565315247, "learning_rate": 1.068069263797623e-05, "loss": 0.0028, "step": 12036 }, { "epoch": 0.6647338193063839, "grad_norm": 0.11191540211439133, "learning_rate": 1.0677527573592327e-05, "loss": 0.0022, "step": 12037 }, { "epoch": 0.6647890435166777, "grad_norm": 4.963648796081543, "learning_rate": 1.0674362807460869e-05, "loss": 1.4239, "step": 12038 }, { "epoch": 0.6648442677269715, "grad_norm": 1.5437854528427124, "learning_rate": 1.0671198339683094e-05, "loss": 0.0823, "step": 12039 }, { "epoch": 0.6648994919372653, "grad_norm": 0.12869875133037567, "learning_rate": 1.066803417036024e-05, "loss": 0.0027, "step": 12040 }, { "epoch": 0.6649547161475591, "grad_norm": 0.014335612766444683, "learning_rate": 1.0664870299593532e-05, "loss": 0.0004, "step": 12041 }, { "epoch": 0.6650099403578529, "grad_norm": 0.2628370225429535, "learning_rate": 1.0661706727484208e-05, "loss": 0.0089, "step": 12042 }, { "epoch": 0.6650651645681467, "grad_norm": 3.887319326400757, "learning_rate": 1.065854345413347e-05, "loss": 0.633, "step": 12043 }, { "epoch": 0.6651203887784405, "grad_norm": 0.39079493284225464, "learning_rate": 1.0655380479642522e-05, "loss": 0.0155, "step": 12044 }, { "epoch": 0.6651756129887343, "grad_norm": 0.18294987082481384, "learning_rate": 1.0652217804112545e-05, "loss": 0.0041, "step": 12045 }, { "epoch": 0.6652308371990281, "grad_norm": 1.8966447114944458, "learning_rate": 1.064905542764475e-05, "loss": 0.6105, "step": 12046 }, { "epoch": 0.6652860614093219, "grad_norm": 0.05741141363978386, "learning_rate": 1.0645893350340278e-05, "loss": 0.0009, "step": 12047 }, { "epoch": 0.6653412856196156, "grad_norm": 0.09950414299964905, "learning_rate": 1.0642731572300313e-05, "loss": 0.0025, "step": 12048 }, { "epoch": 0.6653965098299094, "grad_norm": 0.007901805453002453, "learning_rate": 1.0639570093626004e-05, "loss": 0.0002, "step": 12049 }, { "epoch": 0.6654517340402032, "grad_norm": 4.0339579582214355, "learning_rate": 1.0636408914418496e-05, "loss": 0.9355, "step": 12050 }, { "epoch": 0.665506958250497, "grad_norm": 1.4215749502182007, "learning_rate": 1.063324803477892e-05, "loss": 0.0946, "step": 12051 }, { "epoch": 0.6655621824607908, "grad_norm": 1.1515910625457764, "learning_rate": 1.0630087454808418e-05, "loss": 0.0278, "step": 12052 }, { "epoch": 0.6656174066710846, "grad_norm": 3.4833905696868896, "learning_rate": 1.0626927174608077e-05, "loss": 0.3854, "step": 12053 }, { "epoch": 0.6656726308813784, "grad_norm": 3.385801315307617, "learning_rate": 1.0623767194279027e-05, "loss": 0.1782, "step": 12054 }, { "epoch": 0.6657278550916722, "grad_norm": 5.431140422821045, "learning_rate": 1.0620607513922359e-05, "loss": 1.0993, "step": 12055 }, { "epoch": 0.665783079301966, "grad_norm": 2.5833001136779785, "learning_rate": 1.0617448133639159e-05, "loss": 0.1099, "step": 12056 }, { "epoch": 0.6658383035122598, "grad_norm": 0.014860161580145359, "learning_rate": 1.0614289053530493e-05, "loss": 0.0004, "step": 12057 }, { "epoch": 0.6658935277225536, "grad_norm": 0.40511301159858704, "learning_rate": 1.061113027369745e-05, "loss": 0.0115, "step": 12058 }, { "epoch": 0.6659487519328473, "grad_norm": 0.11753489822149277, "learning_rate": 1.0607971794241082e-05, "loss": 0.0034, "step": 12059 }, { "epoch": 0.6660039761431411, "grad_norm": 0.1474970579147339, "learning_rate": 1.060481361526243e-05, "loss": 0.0029, "step": 12060 }, { "epoch": 0.6660592003534349, "grad_norm": 0.5673863887786865, "learning_rate": 1.0601655736862529e-05, "loss": 0.0155, "step": 12061 }, { "epoch": 0.6661144245637287, "grad_norm": 4.135953426361084, "learning_rate": 1.0598498159142434e-05, "loss": 0.0999, "step": 12062 }, { "epoch": 0.6661696487740225, "grad_norm": 0.024685760959982872, "learning_rate": 1.0595340882203132e-05, "loss": 0.0009, "step": 12063 }, { "epoch": 0.6662248729843163, "grad_norm": 3.339677333831787, "learning_rate": 1.0592183906145657e-05, "loss": 0.5149, "step": 12064 }, { "epoch": 0.6662800971946101, "grad_norm": 2.915576457977295, "learning_rate": 1.0589027231071003e-05, "loss": 0.1543, "step": 12065 }, { "epoch": 0.6663353214049039, "grad_norm": 6.486481189727783, "learning_rate": 1.0585870857080157e-05, "loss": 0.8843, "step": 12066 }, { "epoch": 0.6663905456151977, "grad_norm": 0.9345744848251343, "learning_rate": 1.0582714784274097e-05, "loss": 0.0282, "step": 12067 }, { "epoch": 0.6664457698254915, "grad_norm": 4.840213775634766, "learning_rate": 1.0579559012753808e-05, "loss": 0.2633, "step": 12068 }, { "epoch": 0.6665009940357853, "grad_norm": 1.7913655042648315, "learning_rate": 1.0576403542620245e-05, "loss": 0.0403, "step": 12069 }, { "epoch": 0.6665562182460791, "grad_norm": 0.10213195532560349, "learning_rate": 1.0573248373974362e-05, "loss": 0.0015, "step": 12070 }, { "epoch": 0.6666114424563728, "grad_norm": 0.00915028341114521, "learning_rate": 1.05700935069171e-05, "loss": 0.0003, "step": 12071 }, { "epoch": 0.6666666666666666, "grad_norm": 0.9822558164596558, "learning_rate": 1.0566938941549392e-05, "loss": 0.0268, "step": 12072 }, { "epoch": 0.6667218908769604, "grad_norm": 0.17796637117862701, "learning_rate": 1.0563784677972154e-05, "loss": 0.0056, "step": 12073 }, { "epoch": 0.6667771150872542, "grad_norm": 3.4094371795654297, "learning_rate": 1.0560630716286316e-05, "loss": 0.192, "step": 12074 }, { "epoch": 0.666832339297548, "grad_norm": 0.1964837610721588, "learning_rate": 1.055747705659277e-05, "loss": 0.0041, "step": 12075 }, { "epoch": 0.6668875635078418, "grad_norm": 2.2115588188171387, "learning_rate": 1.055432369899242e-05, "loss": 0.1595, "step": 12076 }, { "epoch": 0.6669427877181356, "grad_norm": 1.8715238571166992, "learning_rate": 1.0551170643586134e-05, "loss": 0.0399, "step": 12077 }, { "epoch": 0.6669980119284294, "grad_norm": 1.9493577480316162, "learning_rate": 1.0548017890474817e-05, "loss": 0.0502, "step": 12078 }, { "epoch": 0.6670532361387232, "grad_norm": 0.05371534079313278, "learning_rate": 1.05448654397593e-05, "loss": 0.0015, "step": 12079 }, { "epoch": 0.667108460349017, "grad_norm": 0.022024981677532196, "learning_rate": 1.0541713291540463e-05, "loss": 0.001, "step": 12080 }, { "epoch": 0.6671636845593109, "grad_norm": 0.04645899683237076, "learning_rate": 1.0538561445919144e-05, "loss": 0.0015, "step": 12081 }, { "epoch": 0.6672189087696045, "grad_norm": 0.05165311321616173, "learning_rate": 1.053540990299618e-05, "loss": 0.0017, "step": 12082 }, { "epoch": 0.6672741329798983, "grad_norm": 0.05211219564080238, "learning_rate": 1.0532258662872392e-05, "loss": 0.001, "step": 12083 }, { "epoch": 0.6673293571901922, "grad_norm": 3.504163980484009, "learning_rate": 1.052910772564861e-05, "loss": 0.1753, "step": 12084 }, { "epoch": 0.667384581400486, "grad_norm": 2.3345985412597656, "learning_rate": 1.052595709142563e-05, "loss": 0.1966, "step": 12085 }, { "epoch": 0.6674398056107798, "grad_norm": 0.113224558532238, "learning_rate": 1.0522806760304256e-05, "loss": 0.0019, "step": 12086 }, { "epoch": 0.6674950298210736, "grad_norm": 2.2746846675872803, "learning_rate": 1.0519656732385269e-05, "loss": 0.0661, "step": 12087 }, { "epoch": 0.6675502540313674, "grad_norm": 0.03884601220488548, "learning_rate": 1.0516507007769465e-05, "loss": 0.0009, "step": 12088 }, { "epoch": 0.6676054782416612, "grad_norm": 4.273723602294922, "learning_rate": 1.0513357586557586e-05, "loss": 1.015, "step": 12089 }, { "epoch": 0.667660702451955, "grad_norm": 1.3199728727340698, "learning_rate": 1.0510208468850414e-05, "loss": 0.0691, "step": 12090 }, { "epoch": 0.6677159266622488, "grad_norm": 0.2318989336490631, "learning_rate": 1.0507059654748688e-05, "loss": 0.0054, "step": 12091 }, { "epoch": 0.6677711508725426, "grad_norm": 0.17750681936740875, "learning_rate": 1.050391114435315e-05, "loss": 0.0048, "step": 12092 }, { "epoch": 0.6678263750828363, "grad_norm": 0.5686811804771423, "learning_rate": 1.0500762937764525e-05, "loss": 0.0136, "step": 12093 }, { "epoch": 0.6678815992931301, "grad_norm": 0.41149383783340454, "learning_rate": 1.0497615035083539e-05, "loss": 0.0079, "step": 12094 }, { "epoch": 0.6679368235034239, "grad_norm": 0.020456276834011078, "learning_rate": 1.0494467436410903e-05, "loss": 0.0005, "step": 12095 }, { "epoch": 0.6679920477137177, "grad_norm": 0.8957390189170837, "learning_rate": 1.0491320141847304e-05, "loss": 0.0271, "step": 12096 }, { "epoch": 0.6680472719240115, "grad_norm": 4.736240386962891, "learning_rate": 1.048817315149345e-05, "loss": 0.5087, "step": 12097 }, { "epoch": 0.6681024961343053, "grad_norm": 0.2412520796060562, "learning_rate": 1.0485026465450019e-05, "loss": 0.0085, "step": 12098 }, { "epoch": 0.6681577203445991, "grad_norm": 0.24230821430683136, "learning_rate": 1.0481880083817677e-05, "loss": 0.0078, "step": 12099 }, { "epoch": 0.6682129445548929, "grad_norm": 3.694066047668457, "learning_rate": 1.0478734006697083e-05, "loss": 0.262, "step": 12100 }, { "epoch": 0.6682681687651867, "grad_norm": 0.019336678087711334, "learning_rate": 1.0475588234188907e-05, "loss": 0.0006, "step": 12101 }, { "epoch": 0.6683233929754805, "grad_norm": 0.08606871217489243, "learning_rate": 1.0472442766393764e-05, "loss": 0.0017, "step": 12102 }, { "epoch": 0.6683786171857743, "grad_norm": 1.5180017948150635, "learning_rate": 1.0469297603412307e-05, "loss": 0.0727, "step": 12103 }, { "epoch": 0.668433841396068, "grad_norm": 0.3308686316013336, "learning_rate": 1.0466152745345153e-05, "loss": 0.0081, "step": 12104 }, { "epoch": 0.6684890656063618, "grad_norm": 0.2323986440896988, "learning_rate": 1.0463008192292916e-05, "loss": 0.0063, "step": 12105 }, { "epoch": 0.6685442898166556, "grad_norm": 1.5348066091537476, "learning_rate": 1.0459863944356186e-05, "loss": 0.0938, "step": 12106 }, { "epoch": 0.6685995140269494, "grad_norm": 0.013961829245090485, "learning_rate": 1.0456720001635579e-05, "loss": 0.0002, "step": 12107 }, { "epoch": 0.6686547382372432, "grad_norm": 0.06595288217067719, "learning_rate": 1.0453576364231667e-05, "loss": 0.0021, "step": 12108 }, { "epoch": 0.668709962447537, "grad_norm": 0.017625611275434494, "learning_rate": 1.0450433032245024e-05, "loss": 0.0004, "step": 12109 }, { "epoch": 0.6687651866578308, "grad_norm": 1.8334499597549438, "learning_rate": 1.0447290005776207e-05, "loss": 0.1537, "step": 12110 }, { "epoch": 0.6688204108681246, "grad_norm": 0.8095431327819824, "learning_rate": 1.0444147284925794e-05, "loss": 0.0217, "step": 12111 }, { "epoch": 0.6688756350784184, "grad_norm": 0.07458386570215225, "learning_rate": 1.0441004869794298e-05, "loss": 0.0034, "step": 12112 }, { "epoch": 0.6689308592887122, "grad_norm": 0.48444607853889465, "learning_rate": 1.0437862760482279e-05, "loss": 0.0136, "step": 12113 }, { "epoch": 0.668986083499006, "grad_norm": 0.04262435436248779, "learning_rate": 1.0434720957090247e-05, "loss": 0.0013, "step": 12114 }, { "epoch": 0.6690413077092997, "grad_norm": 0.4561047852039337, "learning_rate": 1.0431579459718727e-05, "loss": 0.0129, "step": 12115 }, { "epoch": 0.6690965319195935, "grad_norm": 0.01748676784336567, "learning_rate": 1.0428438268468213e-05, "loss": 0.0006, "step": 12116 }, { "epoch": 0.6691517561298873, "grad_norm": 0.7753629088401794, "learning_rate": 1.0425297383439222e-05, "loss": 0.0232, "step": 12117 }, { "epoch": 0.6692069803401811, "grad_norm": 0.07876412570476532, "learning_rate": 1.0422156804732211e-05, "loss": 0.0021, "step": 12118 }, { "epoch": 0.6692622045504749, "grad_norm": 4.362391471862793, "learning_rate": 1.0419016532447679e-05, "loss": 1.0017, "step": 12119 }, { "epoch": 0.6693174287607687, "grad_norm": 0.24435925483703613, "learning_rate": 1.0415876566686081e-05, "loss": 0.0058, "step": 12120 }, { "epoch": 0.6693726529710625, "grad_norm": 0.051747824996709824, "learning_rate": 1.0412736907547877e-05, "loss": 0.0017, "step": 12121 }, { "epoch": 0.6694278771813563, "grad_norm": 3.2122576236724854, "learning_rate": 1.0409597555133506e-05, "loss": 0.3552, "step": 12122 }, { "epoch": 0.6694831013916501, "grad_norm": 0.01607154868543148, "learning_rate": 1.0406458509543423e-05, "loss": 0.0004, "step": 12123 }, { "epoch": 0.6695383256019439, "grad_norm": 4.250358581542969, "learning_rate": 1.040331977087804e-05, "loss": 1.0761, "step": 12124 }, { "epoch": 0.6695935498122377, "grad_norm": 0.1339583545923233, "learning_rate": 1.0400181339237778e-05, "loss": 0.0039, "step": 12125 }, { "epoch": 0.6696487740225314, "grad_norm": 1.724841833114624, "learning_rate": 1.039704321472304e-05, "loss": 0.1459, "step": 12126 }, { "epoch": 0.6697039982328252, "grad_norm": 0.06226823478937149, "learning_rate": 1.0393905397434238e-05, "loss": 0.0017, "step": 12127 }, { "epoch": 0.669759222443119, "grad_norm": 0.8507531881332397, "learning_rate": 1.039076788747174e-05, "loss": 0.0296, "step": 12128 }, { "epoch": 0.6698144466534128, "grad_norm": 0.02164548449218273, "learning_rate": 1.038763068493594e-05, "loss": 0.0007, "step": 12129 }, { "epoch": 0.6698696708637066, "grad_norm": 0.026408100500702858, "learning_rate": 1.0384493789927195e-05, "loss": 0.0012, "step": 12130 }, { "epoch": 0.6699248950740004, "grad_norm": 0.40017780661582947, "learning_rate": 1.0381357202545872e-05, "loss": 0.0078, "step": 12131 }, { "epoch": 0.6699801192842942, "grad_norm": 0.027850408107042313, "learning_rate": 1.0378220922892308e-05, "loss": 0.0009, "step": 12132 }, { "epoch": 0.670035343494588, "grad_norm": 0.5904706716537476, "learning_rate": 1.0375084951066863e-05, "loss": 0.0177, "step": 12133 }, { "epoch": 0.6700905677048818, "grad_norm": 0.3337748050689697, "learning_rate": 1.0371949287169833e-05, "loss": 0.0059, "step": 12134 }, { "epoch": 0.6701457919151756, "grad_norm": 0.02678140252828598, "learning_rate": 1.0368813931301567e-05, "loss": 0.0009, "step": 12135 }, { "epoch": 0.6702010161254695, "grad_norm": 3.3183577060699463, "learning_rate": 1.036567888356236e-05, "loss": 0.6779, "step": 12136 }, { "epoch": 0.6702562403357633, "grad_norm": 0.02069178596138954, "learning_rate": 1.0362544144052513e-05, "loss": 0.0008, "step": 12137 }, { "epoch": 0.670311464546057, "grad_norm": 0.03320338577032089, "learning_rate": 1.0359409712872308e-05, "loss": 0.0015, "step": 12138 }, { "epoch": 0.6703666887563507, "grad_norm": 0.10023240000009537, "learning_rate": 1.035627559012204e-05, "loss": 0.0031, "step": 12139 }, { "epoch": 0.6704219129666446, "grad_norm": 0.009697877801954746, "learning_rate": 1.0353141775901971e-05, "loss": 0.0003, "step": 12140 }, { "epoch": 0.6704771371769384, "grad_norm": 0.43259361386299133, "learning_rate": 1.035000827031236e-05, "loss": 0.0064, "step": 12141 }, { "epoch": 0.6705323613872322, "grad_norm": 5.784059047698975, "learning_rate": 1.0346875073453448e-05, "loss": 1.2945, "step": 12142 }, { "epoch": 0.670587585597526, "grad_norm": 2.0632660388946533, "learning_rate": 1.0343742185425501e-05, "loss": 0.0264, "step": 12143 }, { "epoch": 0.6706428098078198, "grad_norm": 2.736771821975708, "learning_rate": 1.0340609606328713e-05, "loss": 0.4252, "step": 12144 }, { "epoch": 0.6706980340181136, "grad_norm": 0.015211016871035099, "learning_rate": 1.0337477336263331e-05, "loss": 0.0003, "step": 12145 }, { "epoch": 0.6707532582284074, "grad_norm": 2.2974843978881836, "learning_rate": 1.0334345375329557e-05, "loss": 0.118, "step": 12146 }, { "epoch": 0.6708084824387012, "grad_norm": 0.20370763540267944, "learning_rate": 1.0331213723627593e-05, "loss": 0.0062, "step": 12147 }, { "epoch": 0.670863706648995, "grad_norm": 2.5275564193725586, "learning_rate": 1.032808238125762e-05, "loss": 0.6908, "step": 12148 }, { "epoch": 0.6709189308592887, "grad_norm": 3.080901861190796, "learning_rate": 1.0324951348319834e-05, "loss": 0.2322, "step": 12149 }, { "epoch": 0.6709741550695825, "grad_norm": 4.976996898651123, "learning_rate": 1.0321820624914398e-05, "loss": 0.5147, "step": 12150 }, { "epoch": 0.6710293792798763, "grad_norm": 2.645282745361328, "learning_rate": 1.0318690211141472e-05, "loss": 0.0997, "step": 12151 }, { "epoch": 0.6710846034901701, "grad_norm": 3.0265793800354004, "learning_rate": 1.0315560107101208e-05, "loss": 0.6566, "step": 12152 }, { "epoch": 0.6711398277004639, "grad_norm": 3.072094202041626, "learning_rate": 1.0312430312893747e-05, "loss": 0.209, "step": 12153 }, { "epoch": 0.6711950519107577, "grad_norm": 5.002901554107666, "learning_rate": 1.030930082861922e-05, "loss": 0.8214, "step": 12154 }, { "epoch": 0.6712502761210515, "grad_norm": 0.3097535967826843, "learning_rate": 1.0306171654377736e-05, "loss": 0.0083, "step": 12155 }, { "epoch": 0.6713055003313453, "grad_norm": 3.4857177734375, "learning_rate": 1.0303042790269437e-05, "loss": 0.2525, "step": 12156 }, { "epoch": 0.6713607245416391, "grad_norm": 4.799767017364502, "learning_rate": 1.0299914236394391e-05, "loss": 0.6886, "step": 12157 }, { "epoch": 0.6714159487519329, "grad_norm": 0.46299469470977783, "learning_rate": 1.029678599285271e-05, "loss": 0.0127, "step": 12158 }, { "epoch": 0.6714711729622267, "grad_norm": 6.137687683105469, "learning_rate": 1.0293658059744467e-05, "loss": 1.1154, "step": 12159 }, { "epoch": 0.6715263971725204, "grad_norm": 0.06158315762877464, "learning_rate": 1.0290530437169735e-05, "loss": 0.0019, "step": 12160 }, { "epoch": 0.6715816213828142, "grad_norm": 3.765401601791382, "learning_rate": 1.028740312522857e-05, "loss": 0.1005, "step": 12161 }, { "epoch": 0.671636845593108, "grad_norm": 0.21806883811950684, "learning_rate": 1.0284276124021038e-05, "loss": 0.0067, "step": 12162 }, { "epoch": 0.6716920698034018, "grad_norm": 0.12604744732379913, "learning_rate": 1.028114943364717e-05, "loss": 0.0034, "step": 12163 }, { "epoch": 0.6717472940136956, "grad_norm": 0.1615469753742218, "learning_rate": 1.0278023054207002e-05, "loss": 0.0029, "step": 12164 }, { "epoch": 0.6718025182239894, "grad_norm": 1.1258498430252075, "learning_rate": 1.0274896985800544e-05, "loss": 0.0398, "step": 12165 }, { "epoch": 0.6718577424342832, "grad_norm": 0.3432477116584778, "learning_rate": 1.0271771228527835e-05, "loss": 0.0146, "step": 12166 }, { "epoch": 0.671912966644577, "grad_norm": 0.45175108313560486, "learning_rate": 1.0268645782488844e-05, "loss": 0.0073, "step": 12167 }, { "epoch": 0.6719681908548708, "grad_norm": 1.0617430210113525, "learning_rate": 1.0265520647783585e-05, "loss": 0.0329, "step": 12168 }, { "epoch": 0.6720234150651646, "grad_norm": 2.4521899223327637, "learning_rate": 1.0262395824512032e-05, "loss": 0.1314, "step": 12169 }, { "epoch": 0.6720786392754584, "grad_norm": 0.06820964068174362, "learning_rate": 1.0259271312774162e-05, "loss": 0.0017, "step": 12170 }, { "epoch": 0.6721338634857521, "grad_norm": 0.07390514761209488, "learning_rate": 1.0256147112669926e-05, "loss": 0.0028, "step": 12171 }, { "epoch": 0.6721890876960459, "grad_norm": 0.2499886304140091, "learning_rate": 1.0253023224299294e-05, "loss": 0.0057, "step": 12172 }, { "epoch": 0.6722443119063397, "grad_norm": 0.027625368908047676, "learning_rate": 1.0249899647762186e-05, "loss": 0.0008, "step": 12173 }, { "epoch": 0.6722995361166335, "grad_norm": 0.2624979317188263, "learning_rate": 1.024677638315855e-05, "loss": 0.0076, "step": 12174 }, { "epoch": 0.6723547603269273, "grad_norm": 4.977989196777344, "learning_rate": 1.0243653430588307e-05, "loss": 1.2121, "step": 12175 }, { "epoch": 0.6724099845372211, "grad_norm": 0.1759461611509323, "learning_rate": 1.0240530790151361e-05, "loss": 0.0036, "step": 12176 }, { "epoch": 0.6724652087475149, "grad_norm": 0.5901713371276855, "learning_rate": 1.0237408461947615e-05, "loss": 0.0123, "step": 12177 }, { "epoch": 0.6725204329578087, "grad_norm": 0.027194121852517128, "learning_rate": 1.0234286446076976e-05, "loss": 0.0012, "step": 12178 }, { "epoch": 0.6725756571681025, "grad_norm": 3.35180401802063, "learning_rate": 1.023116474263931e-05, "loss": 0.5477, "step": 12179 }, { "epoch": 0.6726308813783963, "grad_norm": 0.32187071442604065, "learning_rate": 1.0228043351734496e-05, "loss": 0.0099, "step": 12180 }, { "epoch": 0.6726861055886901, "grad_norm": 2.24385404586792, "learning_rate": 1.0224922273462388e-05, "loss": 0.4024, "step": 12181 }, { "epoch": 0.6727413297989838, "grad_norm": 2.197140693664551, "learning_rate": 1.022180150792286e-05, "loss": 0.1908, "step": 12182 }, { "epoch": 0.6727965540092776, "grad_norm": 0.12461443990468979, "learning_rate": 1.0218681055215722e-05, "loss": 0.0035, "step": 12183 }, { "epoch": 0.6728517782195714, "grad_norm": 0.02456100843846798, "learning_rate": 1.0215560915440832e-05, "loss": 0.0005, "step": 12184 }, { "epoch": 0.6729070024298652, "grad_norm": 0.5098260641098022, "learning_rate": 1.0212441088698005e-05, "loss": 0.0099, "step": 12185 }, { "epoch": 0.672962226640159, "grad_norm": 2.187032699584961, "learning_rate": 1.020932157508705e-05, "loss": 0.2237, "step": 12186 }, { "epoch": 0.6730174508504528, "grad_norm": 0.5095050930976868, "learning_rate": 1.0206202374707761e-05, "loss": 0.0075, "step": 12187 }, { "epoch": 0.6730726750607466, "grad_norm": 0.0914490818977356, "learning_rate": 1.020308348765995e-05, "loss": 0.0014, "step": 12188 }, { "epoch": 0.6731278992710404, "grad_norm": 1.144227147102356, "learning_rate": 1.019996491404339e-05, "loss": 0.0889, "step": 12189 }, { "epoch": 0.6731831234813342, "grad_norm": 3.8220362663269043, "learning_rate": 1.019684665395785e-05, "loss": 0.7491, "step": 12190 }, { "epoch": 0.673238347691628, "grad_norm": 2.8123772144317627, "learning_rate": 1.0193728707503094e-05, "loss": 0.2698, "step": 12191 }, { "epoch": 0.6732935719019219, "grad_norm": 2.0167758464813232, "learning_rate": 1.0190611074778873e-05, "loss": 0.1164, "step": 12192 }, { "epoch": 0.6733487961122155, "grad_norm": 1.877197265625, "learning_rate": 1.0187493755884922e-05, "loss": 0.1294, "step": 12193 }, { "epoch": 0.6734040203225093, "grad_norm": 3.247130870819092, "learning_rate": 1.018437675092099e-05, "loss": 0.3833, "step": 12194 }, { "epoch": 0.6734592445328031, "grad_norm": 0.015145057812333107, "learning_rate": 1.0181260059986791e-05, "loss": 0.0003, "step": 12195 }, { "epoch": 0.673514468743097, "grad_norm": 0.016613947227597237, "learning_rate": 1.0178143683182031e-05, "loss": 0.0006, "step": 12196 }, { "epoch": 0.6735696929533908, "grad_norm": 0.719235360622406, "learning_rate": 1.0175027620606413e-05, "loss": 0.0189, "step": 12197 }, { "epoch": 0.6736249171636846, "grad_norm": 0.30402225255966187, "learning_rate": 1.0171911872359644e-05, "loss": 0.0071, "step": 12198 }, { "epoch": 0.6736801413739784, "grad_norm": 1.8320449590682983, "learning_rate": 1.016879643854138e-05, "loss": 0.0574, "step": 12199 }, { "epoch": 0.6737353655842722, "grad_norm": 3.593696355819702, "learning_rate": 1.0165681319251313e-05, "loss": 0.8153, "step": 12200 }, { "epoch": 0.673790589794566, "grad_norm": 1.3274855613708496, "learning_rate": 1.0162566514589096e-05, "loss": 0.0419, "step": 12201 }, { "epoch": 0.6738458140048598, "grad_norm": 1.7894779443740845, "learning_rate": 1.0159452024654383e-05, "loss": 0.0391, "step": 12202 }, { "epoch": 0.6739010382151536, "grad_norm": 1.000940203666687, "learning_rate": 1.015633784954681e-05, "loss": 0.0354, "step": 12203 }, { "epoch": 0.6739562624254473, "grad_norm": 0.8972639441490173, "learning_rate": 1.0153223989366017e-05, "loss": 0.0519, "step": 12204 }, { "epoch": 0.6740114866357411, "grad_norm": 2.603959798812866, "learning_rate": 1.0150110444211623e-05, "loss": 0.2447, "step": 12205 }, { "epoch": 0.6740667108460349, "grad_norm": 2.1070146560668945, "learning_rate": 1.0146997214183236e-05, "loss": 0.3387, "step": 12206 }, { "epoch": 0.6741219350563287, "grad_norm": 0.1392861008644104, "learning_rate": 1.014388429938045e-05, "loss": 0.0028, "step": 12207 }, { "epoch": 0.6741771592666225, "grad_norm": 2.0670692920684814, "learning_rate": 1.0140771699902882e-05, "loss": 0.2973, "step": 12208 }, { "epoch": 0.6742323834769163, "grad_norm": 4.639678001403809, "learning_rate": 1.013765941585008e-05, "loss": 0.4657, "step": 12209 }, { "epoch": 0.6742876076872101, "grad_norm": 2.9064667224884033, "learning_rate": 1.0134547447321636e-05, "loss": 0.2506, "step": 12210 }, { "epoch": 0.6743428318975039, "grad_norm": 2.626784324645996, "learning_rate": 1.0131435794417105e-05, "loss": 0.1793, "step": 12211 }, { "epoch": 0.6743980561077977, "grad_norm": 5.840662002563477, "learning_rate": 1.0128324457236039e-05, "loss": 1.0363, "step": 12212 }, { "epoch": 0.6744532803180915, "grad_norm": 0.048614419996738434, "learning_rate": 1.0125213435877969e-05, "loss": 0.0011, "step": 12213 }, { "epoch": 0.6745085045283853, "grad_norm": 0.19769452512264252, "learning_rate": 1.0122102730442446e-05, "loss": 0.0058, "step": 12214 }, { "epoch": 0.6745637287386791, "grad_norm": 6.118162631988525, "learning_rate": 1.0118992341028972e-05, "loss": 1.3366, "step": 12215 }, { "epoch": 0.6746189529489728, "grad_norm": 2.8621060848236084, "learning_rate": 1.0115882267737059e-05, "loss": 0.2223, "step": 12216 }, { "epoch": 0.6746741771592666, "grad_norm": 0.05073226988315582, "learning_rate": 1.0112772510666216e-05, "loss": 0.002, "step": 12217 }, { "epoch": 0.6747294013695604, "grad_norm": 2.750725746154785, "learning_rate": 1.0109663069915925e-05, "loss": 0.3388, "step": 12218 }, { "epoch": 0.6747846255798542, "grad_norm": 2.4127955436706543, "learning_rate": 1.0106553945585672e-05, "loss": 0.1069, "step": 12219 }, { "epoch": 0.674839849790148, "grad_norm": 3.851231098175049, "learning_rate": 1.0103445137774917e-05, "loss": 0.4791, "step": 12220 }, { "epoch": 0.6748950740004418, "grad_norm": 2.076977252960205, "learning_rate": 1.0100336646583138e-05, "loss": 0.2857, "step": 12221 }, { "epoch": 0.6749502982107356, "grad_norm": 0.2439599633216858, "learning_rate": 1.0097228472109762e-05, "loss": 0.0071, "step": 12222 }, { "epoch": 0.6750055224210294, "grad_norm": 0.027327686548233032, "learning_rate": 1.0094120614454241e-05, "loss": 0.001, "step": 12223 }, { "epoch": 0.6750607466313232, "grad_norm": 0.3512767553329468, "learning_rate": 1.0091013073716008e-05, "loss": 0.0091, "step": 12224 }, { "epoch": 0.675115970841617, "grad_norm": 0.09649593383073807, "learning_rate": 1.0087905849994475e-05, "loss": 0.0015, "step": 12225 }, { "epoch": 0.6751711950519108, "grad_norm": 0.9162760972976685, "learning_rate": 1.0084798943389042e-05, "loss": 0.0334, "step": 12226 }, { "epoch": 0.6752264192622045, "grad_norm": 4.99034309387207, "learning_rate": 1.0081692353999126e-05, "loss": 1.446, "step": 12227 }, { "epoch": 0.6752816434724983, "grad_norm": 1.8347856998443604, "learning_rate": 1.007858608192411e-05, "loss": 0.1872, "step": 12228 }, { "epoch": 0.6753368676827921, "grad_norm": 0.1657409965991974, "learning_rate": 1.007548012726337e-05, "loss": 0.0036, "step": 12229 }, { "epoch": 0.6753920918930859, "grad_norm": 0.42328721284866333, "learning_rate": 1.0072374490116275e-05, "loss": 0.0105, "step": 12230 }, { "epoch": 0.6754473161033797, "grad_norm": 0.05777328833937645, "learning_rate": 1.006926917058218e-05, "loss": 0.0019, "step": 12231 }, { "epoch": 0.6755025403136735, "grad_norm": 4.645854949951172, "learning_rate": 1.0066164168760432e-05, "loss": 1.4971, "step": 12232 }, { "epoch": 0.6755577645239673, "grad_norm": 2.4481449127197266, "learning_rate": 1.0063059484750379e-05, "loss": 0.261, "step": 12233 }, { "epoch": 0.6756129887342611, "grad_norm": 2.4558050632476807, "learning_rate": 1.0059955118651339e-05, "loss": 0.2194, "step": 12234 }, { "epoch": 0.6756682129445549, "grad_norm": 1.0087372064590454, "learning_rate": 1.0056851070562637e-05, "loss": 0.0282, "step": 12235 }, { "epoch": 0.6757234371548487, "grad_norm": 2.5963871479034424, "learning_rate": 1.0053747340583566e-05, "loss": 0.1209, "step": 12236 }, { "epoch": 0.6757786613651425, "grad_norm": 0.15370811522006989, "learning_rate": 1.005064392881345e-05, "loss": 0.0041, "step": 12237 }, { "epoch": 0.6758338855754362, "grad_norm": 1.662118673324585, "learning_rate": 1.0047540835351544e-05, "loss": 0.0748, "step": 12238 }, { "epoch": 0.67588910978573, "grad_norm": 2.4760584831237793, "learning_rate": 1.0044438060297149e-05, "loss": 0.6209, "step": 12239 }, { "epoch": 0.6759443339960238, "grad_norm": 0.019732289016246796, "learning_rate": 1.0041335603749519e-05, "loss": 0.0009, "step": 12240 }, { "epoch": 0.6759995582063176, "grad_norm": 2.488859176635742, "learning_rate": 1.0038233465807914e-05, "loss": 0.4035, "step": 12241 }, { "epoch": 0.6760547824166114, "grad_norm": 0.11382589489221573, "learning_rate": 1.0035131646571577e-05, "loss": 0.0051, "step": 12242 }, { "epoch": 0.6761100066269052, "grad_norm": 3.861713409423828, "learning_rate": 1.003203014613975e-05, "loss": 0.5483, "step": 12243 }, { "epoch": 0.676165230837199, "grad_norm": 0.8789424300193787, "learning_rate": 1.0028928964611659e-05, "loss": 0.0235, "step": 12244 }, { "epoch": 0.6762204550474928, "grad_norm": 4.299908638000488, "learning_rate": 1.0025828102086516e-05, "loss": 0.2691, "step": 12245 }, { "epoch": 0.6762756792577866, "grad_norm": 1.7687715291976929, "learning_rate": 1.0022727558663523e-05, "loss": 0.0094, "step": 12246 }, { "epoch": 0.6763309034680804, "grad_norm": 1.0143123865127563, "learning_rate": 1.0019627334441893e-05, "loss": 0.0364, "step": 12247 }, { "epoch": 0.6763861276783742, "grad_norm": 3.4451513290405273, "learning_rate": 1.0016527429520779e-05, "loss": 0.1383, "step": 12248 }, { "epoch": 0.6764413518886679, "grad_norm": 2.411553144454956, "learning_rate": 1.0013427843999384e-05, "loss": 0.0613, "step": 12249 }, { "epoch": 0.6764965760989617, "grad_norm": 0.678342878818512, "learning_rate": 1.0010328577976861e-05, "loss": 0.0224, "step": 12250 }, { "epoch": 0.6765518003092555, "grad_norm": 0.1151624396443367, "learning_rate": 1.000722963155237e-05, "loss": 0.0032, "step": 12251 }, { "epoch": 0.6766070245195493, "grad_norm": 2.866535186767578, "learning_rate": 1.0004131004825041e-05, "loss": 0.2473, "step": 12252 }, { "epoch": 0.6766622487298432, "grad_norm": 5.647118091583252, "learning_rate": 1.0001032697894036e-05, "loss": 0.3273, "step": 12253 }, { "epoch": 0.676717472940137, "grad_norm": 1.909064531326294, "learning_rate": 9.997934710858441e-06, "loss": 0.0946, "step": 12254 }, { "epoch": 0.6767726971504308, "grad_norm": 0.04879672825336456, "learning_rate": 9.9948370438174e-06, "loss": 0.001, "step": 12255 }, { "epoch": 0.6768279213607246, "grad_norm": 0.6093412041664124, "learning_rate": 9.991739696870004e-06, "loss": 0.0192, "step": 12256 }, { "epoch": 0.6768831455710184, "grad_norm": 0.04309656843543053, "learning_rate": 9.988642670115347e-06, "loss": 0.0014, "step": 12257 }, { "epoch": 0.6769383697813122, "grad_norm": 0.2827664911746979, "learning_rate": 9.985545963652505e-06, "loss": 0.0028, "step": 12258 }, { "epoch": 0.676993593991606, "grad_norm": 8.898030281066895, "learning_rate": 9.982449577580566e-06, "loss": 0.0732, "step": 12259 }, { "epoch": 0.6770488182018997, "grad_norm": 5.369270324707031, "learning_rate": 9.979353511998583e-06, "loss": 0.071, "step": 12260 }, { "epoch": 0.6771040424121935, "grad_norm": 0.08722716569900513, "learning_rate": 9.97625776700561e-06, "loss": 0.0022, "step": 12261 }, { "epoch": 0.6771592666224873, "grad_norm": 0.46461620926856995, "learning_rate": 9.973162342700678e-06, "loss": 0.0153, "step": 12262 }, { "epoch": 0.6772144908327811, "grad_norm": 0.011694321408867836, "learning_rate": 9.970067239182844e-06, "loss": 0.0004, "step": 12263 }, { "epoch": 0.6772697150430749, "grad_norm": 0.864787220954895, "learning_rate": 9.966972456551095e-06, "loss": 0.0062, "step": 12264 }, { "epoch": 0.6773249392533687, "grad_norm": 1.642596960067749, "learning_rate": 9.963877994904471e-06, "loss": 0.0705, "step": 12265 }, { "epoch": 0.6773801634636625, "grad_norm": 0.04148301109671593, "learning_rate": 9.960783854341962e-06, "loss": 0.001, "step": 12266 }, { "epoch": 0.6774353876739563, "grad_norm": 3.528963088989258, "learning_rate": 9.957690034962554e-06, "loss": 0.274, "step": 12267 }, { "epoch": 0.6774906118842501, "grad_norm": 0.15000967681407928, "learning_rate": 9.954596536865227e-06, "loss": 0.0024, "step": 12268 }, { "epoch": 0.6775458360945439, "grad_norm": 0.16408087313175201, "learning_rate": 9.951503360148962e-06, "loss": 0.0064, "step": 12269 }, { "epoch": 0.6776010603048377, "grad_norm": 4.488316059112549, "learning_rate": 9.94841050491271e-06, "loss": 0.4646, "step": 12270 }, { "epoch": 0.6776562845151314, "grad_norm": 0.24861222505569458, "learning_rate": 9.945317971255422e-06, "loss": 0.0061, "step": 12271 }, { "epoch": 0.6777115087254252, "grad_norm": 0.7189986705780029, "learning_rate": 9.942225759276036e-06, "loss": 0.0335, "step": 12272 }, { "epoch": 0.677766732935719, "grad_norm": 3.3204445838928223, "learning_rate": 9.939133869073481e-06, "loss": 0.8202, "step": 12273 }, { "epoch": 0.6778219571460128, "grad_norm": 3.4232540130615234, "learning_rate": 9.936042300746677e-06, "loss": 0.6499, "step": 12274 }, { "epoch": 0.6778771813563066, "grad_norm": 2.794259786605835, "learning_rate": 9.932951054394522e-06, "loss": 0.2786, "step": 12275 }, { "epoch": 0.6779324055666004, "grad_norm": 0.0675356388092041, "learning_rate": 9.929860130115938e-06, "loss": 0.0017, "step": 12276 }, { "epoch": 0.6779876297768942, "grad_norm": 0.02026459574699402, "learning_rate": 9.926769528009782e-06, "loss": 0.0007, "step": 12277 }, { "epoch": 0.678042853987188, "grad_norm": 0.6261695623397827, "learning_rate": 9.923679248174952e-06, "loss": 0.1241, "step": 12278 }, { "epoch": 0.6780980781974818, "grad_norm": 3.7276508808135986, "learning_rate": 9.92058929071031e-06, "loss": 0.6731, "step": 12279 }, { "epoch": 0.6781533024077756, "grad_norm": 0.016879821196198463, "learning_rate": 9.91749965571471e-06, "loss": 0.0004, "step": 12280 }, { "epoch": 0.6782085266180694, "grad_norm": 1.093214511871338, "learning_rate": 9.914410343286994e-06, "loss": 0.0455, "step": 12281 }, { "epoch": 0.6782637508283631, "grad_norm": 0.019726719707250595, "learning_rate": 9.911321353526011e-06, "loss": 0.0006, "step": 12282 }, { "epoch": 0.6783189750386569, "grad_norm": 2.8085947036743164, "learning_rate": 9.908232686530579e-06, "loss": 0.4927, "step": 12283 }, { "epoch": 0.6783741992489507, "grad_norm": 0.11719752103090286, "learning_rate": 9.905144342399511e-06, "loss": 0.0047, "step": 12284 }, { "epoch": 0.6784294234592445, "grad_norm": 1.9480385780334473, "learning_rate": 9.90205632123161e-06, "loss": 0.6797, "step": 12285 }, { "epoch": 0.6784846476695383, "grad_norm": 0.1837317794561386, "learning_rate": 9.898968623125688e-06, "loss": 0.0037, "step": 12286 }, { "epoch": 0.6785398718798321, "grad_norm": 2.2610559463500977, "learning_rate": 9.8958812481805e-06, "loss": 0.0842, "step": 12287 }, { "epoch": 0.6785950960901259, "grad_norm": 0.10015816241502762, "learning_rate": 9.892794196494845e-06, "loss": 0.0027, "step": 12288 }, { "epoch": 0.6786503203004197, "grad_norm": 3.1815123558044434, "learning_rate": 9.88970746816748e-06, "loss": 0.0352, "step": 12289 }, { "epoch": 0.6787055445107135, "grad_norm": 0.10846305638551712, "learning_rate": 9.886621063297153e-06, "loss": 0.0021, "step": 12290 }, { "epoch": 0.6787607687210073, "grad_norm": 3.114987850189209, "learning_rate": 9.883534981982603e-06, "loss": 0.295, "step": 12291 }, { "epoch": 0.6788159929313011, "grad_norm": 4.424894332885742, "learning_rate": 9.880449224322583e-06, "loss": 0.4935, "step": 12292 }, { "epoch": 0.6788712171415949, "grad_norm": 0.9642422795295715, "learning_rate": 9.877363790415788e-06, "loss": 0.0242, "step": 12293 }, { "epoch": 0.6789264413518886, "grad_norm": 1.978442668914795, "learning_rate": 9.874278680360949e-06, "loss": 0.1573, "step": 12294 }, { "epoch": 0.6789816655621824, "grad_norm": 2.8713395595550537, "learning_rate": 9.871193894256762e-06, "loss": 0.1508, "step": 12295 }, { "epoch": 0.6790368897724762, "grad_norm": 6.738611221313477, "learning_rate": 9.86810943220192e-06, "loss": 1.573, "step": 12296 }, { "epoch": 0.67909211398277, "grad_norm": 2.149961471557617, "learning_rate": 9.865025294295092e-06, "loss": 0.1434, "step": 12297 }, { "epoch": 0.6791473381930638, "grad_norm": 3.3726987838745117, "learning_rate": 9.861941480634965e-06, "loss": 0.4516, "step": 12298 }, { "epoch": 0.6792025624033576, "grad_norm": 0.017785171046853065, "learning_rate": 9.858857991320192e-06, "loss": 0.0004, "step": 12299 }, { "epoch": 0.6792577866136514, "grad_norm": 4.120243072509766, "learning_rate": 9.855774826449425e-06, "loss": 0.068, "step": 12300 }, { "epoch": 0.6793130108239452, "grad_norm": 0.9051544070243835, "learning_rate": 9.85269198612129e-06, "loss": 0.0397, "step": 12301 }, { "epoch": 0.679368235034239, "grad_norm": 2.2878828048706055, "learning_rate": 9.849609470434443e-06, "loss": 0.1895, "step": 12302 }, { "epoch": 0.6794234592445328, "grad_norm": 4.096171855926514, "learning_rate": 9.84652727948747e-06, "loss": 0.7484, "step": 12303 }, { "epoch": 0.6794786834548266, "grad_norm": 0.259719580411911, "learning_rate": 9.843445413379003e-06, "loss": 0.0093, "step": 12304 }, { "epoch": 0.6795339076651203, "grad_norm": 0.06603312492370605, "learning_rate": 9.840363872207632e-06, "loss": 0.0026, "step": 12305 }, { "epoch": 0.6795891318754141, "grad_norm": 0.1597733050584793, "learning_rate": 9.837282656071943e-06, "loss": 0.0038, "step": 12306 }, { "epoch": 0.679644356085708, "grad_norm": 0.02683323621749878, "learning_rate": 9.834201765070508e-06, "loss": 0.0011, "step": 12307 }, { "epoch": 0.6796995802960017, "grad_norm": 0.265426903963089, "learning_rate": 9.831121199301905e-06, "loss": 0.0065, "step": 12308 }, { "epoch": 0.6797548045062956, "grad_norm": 0.3774028718471527, "learning_rate": 9.828040958864684e-06, "loss": 0.0121, "step": 12309 }, { "epoch": 0.6798100287165894, "grad_norm": 0.010586557909846306, "learning_rate": 9.824961043857392e-06, "loss": 0.0003, "step": 12310 }, { "epoch": 0.6798652529268832, "grad_norm": 8.374825477600098, "learning_rate": 9.821881454378564e-06, "loss": 1.7507, "step": 12311 }, { "epoch": 0.679920477137177, "grad_norm": 0.02359141781926155, "learning_rate": 9.818802190526724e-06, "loss": 0.0008, "step": 12312 }, { "epoch": 0.6799757013474708, "grad_norm": 0.04801509529352188, "learning_rate": 9.815723252400378e-06, "loss": 0.0012, "step": 12313 }, { "epoch": 0.6800309255577646, "grad_norm": 0.029860753566026688, "learning_rate": 9.812644640098045e-06, "loss": 0.0007, "step": 12314 }, { "epoch": 0.6800861497680584, "grad_norm": 1.1100419759750366, "learning_rate": 9.809566353718215e-06, "loss": 0.013, "step": 12315 }, { "epoch": 0.6801413739783521, "grad_norm": 3.5980465412139893, "learning_rate": 9.806488393359365e-06, "loss": 0.7228, "step": 12316 }, { "epoch": 0.6801965981886459, "grad_norm": 0.06427138298749924, "learning_rate": 9.803410759119968e-06, "loss": 0.0019, "step": 12317 }, { "epoch": 0.6802518223989397, "grad_norm": 0.7250404357910156, "learning_rate": 9.800333451098498e-06, "loss": 0.0181, "step": 12318 }, { "epoch": 0.6803070466092335, "grad_norm": 0.2360319346189499, "learning_rate": 9.797256469393387e-06, "loss": 0.0055, "step": 12319 }, { "epoch": 0.6803622708195273, "grad_norm": 4.0022430419921875, "learning_rate": 9.794179814103096e-06, "loss": 0.3267, "step": 12320 }, { "epoch": 0.6804174950298211, "grad_norm": 2.5160248279571533, "learning_rate": 9.791103485326045e-06, "loss": 0.3373, "step": 12321 }, { "epoch": 0.6804727192401149, "grad_norm": 4.637862205505371, "learning_rate": 9.788027483160658e-06, "loss": 0.383, "step": 12322 }, { "epoch": 0.6805279434504087, "grad_norm": 0.03373917192220688, "learning_rate": 9.784951807705336e-06, "loss": 0.0011, "step": 12323 }, { "epoch": 0.6805831676607025, "grad_norm": 0.06987594068050385, "learning_rate": 9.781876459058494e-06, "loss": 0.0021, "step": 12324 }, { "epoch": 0.6806383918709963, "grad_norm": 3.172652244567871, "learning_rate": 9.778801437318514e-06, "loss": 0.2558, "step": 12325 }, { "epoch": 0.6806936160812901, "grad_norm": 4.528167724609375, "learning_rate": 9.775726742583776e-06, "loss": 0.4512, "step": 12326 }, { "epoch": 0.6807488402915838, "grad_norm": 0.04100315272808075, "learning_rate": 9.772652374952637e-06, "loss": 0.0011, "step": 12327 }, { "epoch": 0.6808040645018776, "grad_norm": 0.025793731212615967, "learning_rate": 9.769578334523479e-06, "loss": 0.001, "step": 12328 }, { "epoch": 0.6808592887121714, "grad_norm": 2.4915597438812256, "learning_rate": 9.766504621394622e-06, "loss": 0.4363, "step": 12329 }, { "epoch": 0.6809145129224652, "grad_norm": 0.03553595021367073, "learning_rate": 9.763431235664422e-06, "loss": 0.0008, "step": 12330 }, { "epoch": 0.680969737132759, "grad_norm": 0.09691394120454788, "learning_rate": 9.760358177431199e-06, "loss": 0.0016, "step": 12331 }, { "epoch": 0.6810249613430528, "grad_norm": 2.6755106449127197, "learning_rate": 9.75728544679327e-06, "loss": 0.1025, "step": 12332 }, { "epoch": 0.6810801855533466, "grad_norm": 2.441235303878784, "learning_rate": 9.75421304384893e-06, "loss": 0.1434, "step": 12333 }, { "epoch": 0.6811354097636404, "grad_norm": 0.4546464681625366, "learning_rate": 9.7511409686965e-06, "loss": 0.0154, "step": 12334 }, { "epoch": 0.6811906339739342, "grad_norm": 0.12733159959316254, "learning_rate": 9.748069221434237e-06, "loss": 0.0046, "step": 12335 }, { "epoch": 0.681245858184228, "grad_norm": 3.8757917881011963, "learning_rate": 9.74499780216042e-06, "loss": 0.6608, "step": 12336 }, { "epoch": 0.6813010823945218, "grad_norm": 2.0813395977020264, "learning_rate": 9.741926710973327e-06, "loss": 0.3208, "step": 12337 }, { "epoch": 0.6813563066048155, "grad_norm": 0.4549214243888855, "learning_rate": 9.7388559479712e-06, "loss": 0.0067, "step": 12338 }, { "epoch": 0.6814115308151093, "grad_norm": 1.0521875619888306, "learning_rate": 9.735785513252286e-06, "loss": 0.0379, "step": 12339 }, { "epoch": 0.6814667550254031, "grad_norm": 1.6029653549194336, "learning_rate": 9.732715406914803e-06, "loss": 0.1059, "step": 12340 }, { "epoch": 0.6815219792356969, "grad_norm": 0.5534335970878601, "learning_rate": 9.729645629057001e-06, "loss": 0.0161, "step": 12341 }, { "epoch": 0.6815772034459907, "grad_norm": 0.34317368268966675, "learning_rate": 9.726576179777058e-06, "loss": 0.0119, "step": 12342 }, { "epoch": 0.6816324276562845, "grad_norm": 2.0243330001831055, "learning_rate": 9.723507059173198e-06, "loss": 0.4337, "step": 12343 }, { "epoch": 0.6816876518665783, "grad_norm": 0.21044482290744781, "learning_rate": 9.720438267343603e-06, "loss": 0.0072, "step": 12344 }, { "epoch": 0.6817428760768721, "grad_norm": 1.6661360263824463, "learning_rate": 9.717369804386454e-06, "loss": 0.0612, "step": 12345 }, { "epoch": 0.6817981002871659, "grad_norm": 0.34227898716926575, "learning_rate": 9.714301670399909e-06, "loss": 0.0078, "step": 12346 }, { "epoch": 0.6818533244974597, "grad_norm": 0.009219841100275517, "learning_rate": 9.711233865482143e-06, "loss": 0.0003, "step": 12347 }, { "epoch": 0.6819085487077535, "grad_norm": 0.08221836388111115, "learning_rate": 9.708166389731297e-06, "loss": 0.0017, "step": 12348 }, { "epoch": 0.6819637729180472, "grad_norm": 3.981410026550293, "learning_rate": 9.705099243245508e-06, "loss": 1.056, "step": 12349 }, { "epoch": 0.682018997128341, "grad_norm": 2.275692939758301, "learning_rate": 9.702032426122903e-06, "loss": 0.1246, "step": 12350 }, { "epoch": 0.6820742213386348, "grad_norm": 2.708468198776245, "learning_rate": 9.698965938461598e-06, "loss": 0.3269, "step": 12351 }, { "epoch": 0.6821294455489286, "grad_norm": 0.05417612940073013, "learning_rate": 9.695899780359688e-06, "loss": 0.0011, "step": 12352 }, { "epoch": 0.6821846697592224, "grad_norm": 2.8342533111572266, "learning_rate": 9.692833951915287e-06, "loss": 0.1342, "step": 12353 }, { "epoch": 0.6822398939695162, "grad_norm": 0.15564726293087006, "learning_rate": 9.689768453226474e-06, "loss": 0.0047, "step": 12354 }, { "epoch": 0.68229511817981, "grad_norm": 0.336931049823761, "learning_rate": 9.686703284391317e-06, "loss": 0.0067, "step": 12355 }, { "epoch": 0.6823503423901038, "grad_norm": 2.5571632385253906, "learning_rate": 9.683638445507877e-06, "loss": 0.5329, "step": 12356 }, { "epoch": 0.6824055666003976, "grad_norm": 0.3392767906188965, "learning_rate": 9.680573936674227e-06, "loss": 0.0085, "step": 12357 }, { "epoch": 0.6824607908106914, "grad_norm": 0.014948769472539425, "learning_rate": 9.67750975798838e-06, "loss": 0.0004, "step": 12358 }, { "epoch": 0.6825160150209852, "grad_norm": 0.2825511693954468, "learning_rate": 9.674445909548388e-06, "loss": 0.0086, "step": 12359 }, { "epoch": 0.682571239231279, "grad_norm": 1.5125491619110107, "learning_rate": 9.67138239145227e-06, "loss": 0.0298, "step": 12360 }, { "epoch": 0.6826264634415727, "grad_norm": 1.8087118864059448, "learning_rate": 9.668319203798032e-06, "loss": 0.0861, "step": 12361 }, { "epoch": 0.6826816876518665, "grad_norm": 0.8776392936706543, "learning_rate": 9.665256346683667e-06, "loss": 0.016, "step": 12362 }, { "epoch": 0.6827369118621603, "grad_norm": 0.3933515250682831, "learning_rate": 9.662193820207181e-06, "loss": 0.009, "step": 12363 }, { "epoch": 0.6827921360724541, "grad_norm": 2.268489360809326, "learning_rate": 9.659131624466547e-06, "loss": 0.1078, "step": 12364 }, { "epoch": 0.682847360282748, "grad_norm": 0.05204252526164055, "learning_rate": 9.656069759559732e-06, "loss": 0.0018, "step": 12365 }, { "epoch": 0.6829025844930418, "grad_norm": 2.5714831352233887, "learning_rate": 9.653008225584683e-06, "loss": 0.2456, "step": 12366 }, { "epoch": 0.6829578087033356, "grad_norm": 4.752844333648682, "learning_rate": 9.649947022639374e-06, "loss": 0.9988, "step": 12367 }, { "epoch": 0.6830130329136294, "grad_norm": 3.304415702819824, "learning_rate": 9.64688615082171e-06, "loss": 0.3839, "step": 12368 }, { "epoch": 0.6830682571239232, "grad_norm": 0.7559004426002502, "learning_rate": 9.64382561022964e-06, "loss": 0.0173, "step": 12369 }, { "epoch": 0.683123481334217, "grad_norm": 0.36001038551330566, "learning_rate": 9.640765400961069e-06, "loss": 0.0106, "step": 12370 }, { "epoch": 0.6831787055445108, "grad_norm": 0.04814950004220009, "learning_rate": 9.637705523113907e-06, "loss": 0.0009, "step": 12371 }, { "epoch": 0.6832339297548045, "grad_norm": 3.726107358932495, "learning_rate": 9.634645976786037e-06, "loss": 0.1307, "step": 12372 }, { "epoch": 0.6832891539650983, "grad_norm": 1.984919786453247, "learning_rate": 9.631586762075366e-06, "loss": 0.0512, "step": 12373 }, { "epoch": 0.6833443781753921, "grad_norm": 3.788530111312866, "learning_rate": 9.628527879079736e-06, "loss": 0.2894, "step": 12374 }, { "epoch": 0.6833996023856859, "grad_norm": 0.04656386002898216, "learning_rate": 9.625469327897035e-06, "loss": 0.0013, "step": 12375 }, { "epoch": 0.6834548265959797, "grad_norm": 0.5904961824417114, "learning_rate": 9.622411108625106e-06, "loss": 0.0139, "step": 12376 }, { "epoch": 0.6835100508062735, "grad_norm": 3.0342180728912354, "learning_rate": 9.619353221361787e-06, "loss": 0.4778, "step": 12377 }, { "epoch": 0.6835652750165673, "grad_norm": 3.8443262577056885, "learning_rate": 9.616295666204902e-06, "loss": 0.0788, "step": 12378 }, { "epoch": 0.6836204992268611, "grad_norm": 3.367281436920166, "learning_rate": 9.61323844325229e-06, "loss": 0.6658, "step": 12379 }, { "epoch": 0.6836757234371549, "grad_norm": 2.5226173400878906, "learning_rate": 9.61018155260175e-06, "loss": 0.3452, "step": 12380 }, { "epoch": 0.6837309476474487, "grad_norm": 7.402852535247803, "learning_rate": 9.607124994351078e-06, "loss": 0.5579, "step": 12381 }, { "epoch": 0.6837861718577425, "grad_norm": 0.20613853633403778, "learning_rate": 9.60406876859806e-06, "loss": 0.0033, "step": 12382 }, { "epoch": 0.6838413960680362, "grad_norm": 0.22193847596645355, "learning_rate": 9.601012875440492e-06, "loss": 0.0058, "step": 12383 }, { "epoch": 0.68389662027833, "grad_norm": 0.01967058703303337, "learning_rate": 9.597957314976113e-06, "loss": 0.0005, "step": 12384 }, { "epoch": 0.6839518444886238, "grad_norm": 10.395941734313965, "learning_rate": 9.594902087302697e-06, "loss": 1.1906, "step": 12385 }, { "epoch": 0.6840070686989176, "grad_norm": 5.645023345947266, "learning_rate": 9.591847192517987e-06, "loss": 1.6402, "step": 12386 }, { "epoch": 0.6840622929092114, "grad_norm": 0.09086808562278748, "learning_rate": 9.588792630719716e-06, "loss": 0.0018, "step": 12387 }, { "epoch": 0.6841175171195052, "grad_norm": 0.01673199236392975, "learning_rate": 9.5857384020056e-06, "loss": 0.0006, "step": 12388 }, { "epoch": 0.684172741329799, "grad_norm": 0.0677114799618721, "learning_rate": 9.58268450647337e-06, "loss": 0.0022, "step": 12389 }, { "epoch": 0.6842279655400928, "grad_norm": 0.3430543541908264, "learning_rate": 9.579630944220717e-06, "loss": 0.0107, "step": 12390 }, { "epoch": 0.6842831897503866, "grad_norm": 2.0610830783843994, "learning_rate": 9.57657771534534e-06, "loss": 0.0216, "step": 12391 }, { "epoch": 0.6843384139606804, "grad_norm": 1.674391746520996, "learning_rate": 9.573524819944911e-06, "loss": 0.0796, "step": 12392 }, { "epoch": 0.6843936381709742, "grad_norm": 0.03054673783481121, "learning_rate": 9.570472258117107e-06, "loss": 0.0009, "step": 12393 }, { "epoch": 0.6844488623812679, "grad_norm": 0.11765111237764359, "learning_rate": 9.567420029959588e-06, "loss": 0.0019, "step": 12394 }, { "epoch": 0.6845040865915617, "grad_norm": 2.2030022144317627, "learning_rate": 9.564368135569995e-06, "loss": 0.1029, "step": 12395 }, { "epoch": 0.6845593108018555, "grad_norm": 0.05831803008913994, "learning_rate": 9.561316575045989e-06, "loss": 0.0018, "step": 12396 }, { "epoch": 0.6846145350121493, "grad_norm": 0.21905118227005005, "learning_rate": 9.55826534848517e-06, "loss": 0.0049, "step": 12397 }, { "epoch": 0.6846697592224431, "grad_norm": 1.9514840841293335, "learning_rate": 9.555214455985174e-06, "loss": 0.5409, "step": 12398 }, { "epoch": 0.6847249834327369, "grad_norm": 2.5283257961273193, "learning_rate": 9.552163897643603e-06, "loss": 0.5098, "step": 12399 }, { "epoch": 0.6847802076430307, "grad_norm": 2.2410671710968018, "learning_rate": 9.549113673558052e-06, "loss": 0.1507, "step": 12400 }, { "epoch": 0.6848354318533245, "grad_norm": 0.02076706290245056, "learning_rate": 9.5460637838261e-06, "loss": 0.0008, "step": 12401 }, { "epoch": 0.6848906560636183, "grad_norm": 2.596661329269409, "learning_rate": 9.543014228545337e-06, "loss": 0.2974, "step": 12402 }, { "epoch": 0.6849458802739121, "grad_norm": 0.2054491639137268, "learning_rate": 9.53996500781332e-06, "loss": 0.0035, "step": 12403 }, { "epoch": 0.6850011044842059, "grad_norm": 4.009050369262695, "learning_rate": 9.536916121727597e-06, "loss": 0.4965, "step": 12404 }, { "epoch": 0.6850563286944996, "grad_norm": 0.21906837821006775, "learning_rate": 9.533867570385709e-06, "loss": 0.0052, "step": 12405 }, { "epoch": 0.6851115529047934, "grad_norm": 0.020595967769622803, "learning_rate": 9.530819353885208e-06, "loss": 0.0006, "step": 12406 }, { "epoch": 0.6851667771150872, "grad_norm": 0.014329813420772552, "learning_rate": 9.527771472323584e-06, "loss": 0.0004, "step": 12407 }, { "epoch": 0.685222001325381, "grad_norm": 0.6868683099746704, "learning_rate": 9.524723925798372e-06, "loss": 0.0134, "step": 12408 }, { "epoch": 0.6852772255356748, "grad_norm": 2.262310028076172, "learning_rate": 9.521676714407064e-06, "loss": 0.2404, "step": 12409 }, { "epoch": 0.6853324497459686, "grad_norm": 2.077702760696411, "learning_rate": 9.518629838247149e-06, "loss": 0.1602, "step": 12410 }, { "epoch": 0.6853876739562624, "grad_norm": 6.15312385559082, "learning_rate": 9.515583297416096e-06, "loss": 0.2525, "step": 12411 }, { "epoch": 0.6854428981665562, "grad_norm": 2.0221588611602783, "learning_rate": 9.512537092011395e-06, "loss": 0.1452, "step": 12412 }, { "epoch": 0.68549812237685, "grad_norm": 2.8416433334350586, "learning_rate": 9.509491222130475e-06, "loss": 0.3032, "step": 12413 }, { "epoch": 0.6855533465871438, "grad_norm": 5.691502571105957, "learning_rate": 9.506445687870804e-06, "loss": 1.3926, "step": 12414 }, { "epoch": 0.6856085707974376, "grad_norm": 0.1484578251838684, "learning_rate": 9.503400489329808e-06, "loss": 0.0047, "step": 12415 }, { "epoch": 0.6856637950077313, "grad_norm": 0.6089072823524475, "learning_rate": 9.500355626604913e-06, "loss": 0.018, "step": 12416 }, { "epoch": 0.6857190192180251, "grad_norm": 1.4002656936645508, "learning_rate": 9.497311099793527e-06, "loss": 0.0128, "step": 12417 }, { "epoch": 0.6857742434283189, "grad_norm": 0.08455557376146317, "learning_rate": 9.494266908993065e-06, "loss": 0.0023, "step": 12418 }, { "epoch": 0.6858294676386127, "grad_norm": 0.12315494567155838, "learning_rate": 9.491223054300913e-06, "loss": 0.0038, "step": 12419 }, { "epoch": 0.6858846918489065, "grad_norm": 0.17341600358486176, "learning_rate": 9.488179535814454e-06, "loss": 0.0048, "step": 12420 }, { "epoch": 0.6859399160592003, "grad_norm": 4.27401065826416, "learning_rate": 9.485136353631048e-06, "loss": 0.641, "step": 12421 }, { "epoch": 0.6859951402694942, "grad_norm": 0.04230108484625816, "learning_rate": 9.48209350784808e-06, "loss": 0.001, "step": 12422 }, { "epoch": 0.686050364479788, "grad_norm": 3.8436028957366943, "learning_rate": 9.479050998562871e-06, "loss": 0.1217, "step": 12423 }, { "epoch": 0.6861055886900818, "grad_norm": 2.514893054962158, "learning_rate": 9.476008825872777e-06, "loss": 0.1542, "step": 12424 }, { "epoch": 0.6861608129003756, "grad_norm": 3.1529805660247803, "learning_rate": 9.472966989875122e-06, "loss": 0.3782, "step": 12425 }, { "epoch": 0.6862160371106694, "grad_norm": 3.4966824054718018, "learning_rate": 9.469925490667222e-06, "loss": 0.7519, "step": 12426 }, { "epoch": 0.686271261320963, "grad_norm": 0.11619994789361954, "learning_rate": 9.466884328346378e-06, "loss": 0.003, "step": 12427 }, { "epoch": 0.6863264855312569, "grad_norm": 3.4475655555725098, "learning_rate": 9.463843503009896e-06, "loss": 0.1855, "step": 12428 }, { "epoch": 0.6863817097415507, "grad_norm": 3.308201313018799, "learning_rate": 9.460803014755056e-06, "loss": 0.2619, "step": 12429 }, { "epoch": 0.6864369339518445, "grad_norm": 3.0091774463653564, "learning_rate": 9.457762863679129e-06, "loss": 0.4478, "step": 12430 }, { "epoch": 0.6864921581621383, "grad_norm": 0.0768527016043663, "learning_rate": 9.454723049879384e-06, "loss": 0.0017, "step": 12431 }, { "epoch": 0.6865473823724321, "grad_norm": 1.1409400701522827, "learning_rate": 9.451683573453067e-06, "loss": 0.032, "step": 12432 }, { "epoch": 0.6866026065827259, "grad_norm": 0.06369776278734207, "learning_rate": 9.448644434497419e-06, "loss": 0.0014, "step": 12433 }, { "epoch": 0.6866578307930197, "grad_norm": 5.4129638671875, "learning_rate": 9.445605633109677e-06, "loss": 1.6563, "step": 12434 }, { "epoch": 0.6867130550033135, "grad_norm": 0.10691346228122711, "learning_rate": 9.44256716938706e-06, "loss": 0.0027, "step": 12435 }, { "epoch": 0.6867682792136073, "grad_norm": 4.206390857696533, "learning_rate": 9.439529043426774e-06, "loss": 0.3211, "step": 12436 }, { "epoch": 0.6868235034239011, "grad_norm": 0.08367905020713806, "learning_rate": 9.43649125532601e-06, "loss": 0.003, "step": 12437 }, { "epoch": 0.6868787276341949, "grad_norm": 0.16541457176208496, "learning_rate": 9.43345380518198e-06, "loss": 0.0046, "step": 12438 }, { "epoch": 0.6869339518444886, "grad_norm": 1.8275426626205444, "learning_rate": 9.43041669309183e-06, "loss": 0.0353, "step": 12439 }, { "epoch": 0.6869891760547824, "grad_norm": 0.10082574933767319, "learning_rate": 9.427379919152746e-06, "loss": 0.0025, "step": 12440 }, { "epoch": 0.6870444002650762, "grad_norm": 1.331131935119629, "learning_rate": 9.424343483461878e-06, "loss": 0.0607, "step": 12441 }, { "epoch": 0.68709962447537, "grad_norm": 0.25290045142173767, "learning_rate": 9.421307386116369e-06, "loss": 0.006, "step": 12442 }, { "epoch": 0.6871548486856638, "grad_norm": 0.009032513946294785, "learning_rate": 9.418271627213347e-06, "loss": 0.0003, "step": 12443 }, { "epoch": 0.6872100728959576, "grad_norm": 0.08078978210687637, "learning_rate": 9.415236206849946e-06, "loss": 0.0023, "step": 12444 }, { "epoch": 0.6872652971062514, "grad_norm": 0.6035776734352112, "learning_rate": 9.412201125123276e-06, "loss": 0.0142, "step": 12445 }, { "epoch": 0.6873205213165452, "grad_norm": 0.05389823019504547, "learning_rate": 9.40916638213043e-06, "loss": 0.0013, "step": 12446 }, { "epoch": 0.687375745526839, "grad_norm": 4.546655178070068, "learning_rate": 9.406131977968496e-06, "loss": 1.1314, "step": 12447 }, { "epoch": 0.6874309697371328, "grad_norm": 0.0911700576543808, "learning_rate": 9.403097912734576e-06, "loss": 0.0036, "step": 12448 }, { "epoch": 0.6874861939474266, "grad_norm": 0.06808854639530182, "learning_rate": 9.400064186525703e-06, "loss": 0.0013, "step": 12449 }, { "epoch": 0.6875414181577203, "grad_norm": 2.344965696334839, "learning_rate": 9.397030799438964e-06, "loss": 0.5359, "step": 12450 }, { "epoch": 0.6875966423680141, "grad_norm": 2.95424222946167, "learning_rate": 9.393997751571396e-06, "loss": 0.5837, "step": 12451 }, { "epoch": 0.6876518665783079, "grad_norm": 0.12858639657497406, "learning_rate": 9.39096504302003e-06, "loss": 0.0019, "step": 12452 }, { "epoch": 0.6877070907886017, "grad_norm": 0.023352930322289467, "learning_rate": 9.38793267388189e-06, "loss": 0.0006, "step": 12453 }, { "epoch": 0.6877623149988955, "grad_norm": 2.701162099838257, "learning_rate": 9.384900644254009e-06, "loss": 0.1631, "step": 12454 }, { "epoch": 0.6878175392091893, "grad_norm": 0.07586535066366196, "learning_rate": 9.381868954233371e-06, "loss": 0.0016, "step": 12455 }, { "epoch": 0.6878727634194831, "grad_norm": 2.4352002143859863, "learning_rate": 9.378837603916963e-06, "loss": 0.2891, "step": 12456 }, { "epoch": 0.6879279876297769, "grad_norm": 2.5683412551879883, "learning_rate": 9.375806593401786e-06, "loss": 0.5487, "step": 12457 }, { "epoch": 0.6879832118400707, "grad_norm": 3.274477005004883, "learning_rate": 9.372775922784802e-06, "loss": 0.3204, "step": 12458 }, { "epoch": 0.6880384360503645, "grad_norm": 0.07331240177154541, "learning_rate": 9.36974559216297e-06, "loss": 0.0022, "step": 12459 }, { "epoch": 0.6880936602606583, "grad_norm": 0.15285441279411316, "learning_rate": 9.366715601633234e-06, "loss": 0.0023, "step": 12460 }, { "epoch": 0.688148884470952, "grad_norm": 0.28159263730049133, "learning_rate": 9.36368595129255e-06, "loss": 0.0088, "step": 12461 }, { "epoch": 0.6882041086812458, "grad_norm": 2.343299150466919, "learning_rate": 9.36065664123782e-06, "loss": 0.1086, "step": 12462 }, { "epoch": 0.6882593328915396, "grad_norm": 2.5900957584381104, "learning_rate": 9.357627671565978e-06, "loss": 0.1087, "step": 12463 }, { "epoch": 0.6883145571018334, "grad_norm": 0.06579271703958511, "learning_rate": 9.354599042373923e-06, "loss": 0.002, "step": 12464 }, { "epoch": 0.6883697813121272, "grad_norm": 3.7326700687408447, "learning_rate": 9.351570753758555e-06, "loss": 1.0188, "step": 12465 }, { "epoch": 0.688425005522421, "grad_norm": 0.7681881785392761, "learning_rate": 9.348542805816744e-06, "loss": 0.0201, "step": 12466 }, { "epoch": 0.6884802297327148, "grad_norm": 0.005115744192153215, "learning_rate": 9.345515198645379e-06, "loss": 0.0002, "step": 12467 }, { "epoch": 0.6885354539430086, "grad_norm": 4.806521415710449, "learning_rate": 9.342487932341315e-06, "loss": 0.7923, "step": 12468 }, { "epoch": 0.6885906781533024, "grad_norm": 0.02568455971777439, "learning_rate": 9.339461007001402e-06, "loss": 0.0008, "step": 12469 }, { "epoch": 0.6886459023635962, "grad_norm": 1.8867393732070923, "learning_rate": 9.336434422722482e-06, "loss": 0.0461, "step": 12470 }, { "epoch": 0.68870112657389, "grad_norm": 1.9464246034622192, "learning_rate": 9.333408179601383e-06, "loss": 0.1871, "step": 12471 }, { "epoch": 0.6887563507841837, "grad_norm": 2.5084567070007324, "learning_rate": 9.330382277734913e-06, "loss": 0.2625, "step": 12472 }, { "epoch": 0.6888115749944775, "grad_norm": 0.2251199185848236, "learning_rate": 9.327356717219898e-06, "loss": 0.0041, "step": 12473 }, { "epoch": 0.6888667992047713, "grad_norm": 0.014326872304081917, "learning_rate": 9.324331498153125e-06, "loss": 0.0003, "step": 12474 }, { "epoch": 0.6889220234150651, "grad_norm": 3.2194268703460693, "learning_rate": 9.32130662063138e-06, "loss": 0.6115, "step": 12475 }, { "epoch": 0.688977247625359, "grad_norm": 2.997671604156494, "learning_rate": 9.31828208475143e-06, "loss": 0.5629, "step": 12476 }, { "epoch": 0.6890324718356527, "grad_norm": 2.1537160873413086, "learning_rate": 9.31525789061006e-06, "loss": 0.1472, "step": 12477 }, { "epoch": 0.6890876960459466, "grad_norm": 2.217311382293701, "learning_rate": 9.312234038303994e-06, "loss": 0.1011, "step": 12478 }, { "epoch": 0.6891429202562404, "grad_norm": 4.177574157714844, "learning_rate": 9.309210527929993e-06, "loss": 1.2045, "step": 12479 }, { "epoch": 0.6891981444665342, "grad_norm": 0.13082255423069, "learning_rate": 9.306187359584783e-06, "loss": 0.0027, "step": 12480 }, { "epoch": 0.689253368676828, "grad_norm": 0.11553449928760529, "learning_rate": 9.303164533365086e-06, "loss": 0.0037, "step": 12481 }, { "epoch": 0.6893085928871218, "grad_norm": 5.499388217926025, "learning_rate": 9.300142049367598e-06, "loss": 0.1622, "step": 12482 }, { "epoch": 0.6893638170974155, "grad_norm": 1.1104434728622437, "learning_rate": 9.297119907689036e-06, "loss": 0.022, "step": 12483 }, { "epoch": 0.6894190413077093, "grad_norm": 2.7457265853881836, "learning_rate": 9.294098108426078e-06, "loss": 0.1873, "step": 12484 }, { "epoch": 0.6894742655180031, "grad_norm": 0.04949608072638512, "learning_rate": 9.291076651675399e-06, "loss": 0.0011, "step": 12485 }, { "epoch": 0.6895294897282969, "grad_norm": 0.06490074098110199, "learning_rate": 9.288055537533656e-06, "loss": 0.0018, "step": 12486 }, { "epoch": 0.6895847139385907, "grad_norm": 5.594409942626953, "learning_rate": 9.28503476609753e-06, "loss": 0.5886, "step": 12487 }, { "epoch": 0.6896399381488845, "grad_norm": 0.013028478249907494, "learning_rate": 9.282014337463627e-06, "loss": 0.0003, "step": 12488 }, { "epoch": 0.6896951623591783, "grad_norm": 0.36647698283195496, "learning_rate": 9.278994251728611e-06, "loss": 0.0059, "step": 12489 }, { "epoch": 0.6897503865694721, "grad_norm": 0.14939571917057037, "learning_rate": 9.275974508989086e-06, "loss": 0.0049, "step": 12490 }, { "epoch": 0.6898056107797659, "grad_norm": 0.7936017513275146, "learning_rate": 9.272955109341668e-06, "loss": 0.011, "step": 12491 }, { "epoch": 0.6898608349900597, "grad_norm": 0.0624367780983448, "learning_rate": 9.269936052882946e-06, "loss": 0.0019, "step": 12492 }, { "epoch": 0.6899160592003535, "grad_norm": 0.014230328612029552, "learning_rate": 9.266917339709534e-06, "loss": 0.0004, "step": 12493 }, { "epoch": 0.6899712834106472, "grad_norm": 0.07255573570728302, "learning_rate": 9.263898969917976e-06, "loss": 0.0017, "step": 12494 }, { "epoch": 0.690026507620941, "grad_norm": 3.3285059928894043, "learning_rate": 9.26088094360486e-06, "loss": 0.772, "step": 12495 }, { "epoch": 0.6900817318312348, "grad_norm": 0.17365239560604095, "learning_rate": 9.257863260866738e-06, "loss": 0.0036, "step": 12496 }, { "epoch": 0.6901369560415286, "grad_norm": 4.655468463897705, "learning_rate": 9.254845921800149e-06, "loss": 1.0061, "step": 12497 }, { "epoch": 0.6901921802518224, "grad_norm": 0.060096777975559235, "learning_rate": 9.251828926501622e-06, "loss": 0.0018, "step": 12498 }, { "epoch": 0.6902474044621162, "grad_norm": 0.07873573154211044, "learning_rate": 9.248812275067695e-06, "loss": 0.0022, "step": 12499 }, { "epoch": 0.69030262867241, "grad_norm": 1.2469234466552734, "learning_rate": 9.245795967594872e-06, "loss": 0.0394, "step": 12500 }, { "epoch": 0.6903578528827038, "grad_norm": 2.357668161392212, "learning_rate": 9.24278000417965e-06, "loss": 0.3713, "step": 12501 }, { "epoch": 0.6904130770929976, "grad_norm": 4.043280601501465, "learning_rate": 9.239764384918513e-06, "loss": 0.1293, "step": 12502 }, { "epoch": 0.6904683013032914, "grad_norm": 0.5168341398239136, "learning_rate": 9.236749109907963e-06, "loss": 0.0072, "step": 12503 }, { "epoch": 0.6905235255135852, "grad_norm": 2.3709487915039062, "learning_rate": 9.233734179244434e-06, "loss": 0.8737, "step": 12504 }, { "epoch": 0.690578749723879, "grad_norm": 0.008336404338479042, "learning_rate": 9.230719593024407e-06, "loss": 0.0003, "step": 12505 }, { "epoch": 0.6906339739341727, "grad_norm": 5.3740153312683105, "learning_rate": 9.227705351344317e-06, "loss": 1.0367, "step": 12506 }, { "epoch": 0.6906891981444665, "grad_norm": 2.0886168479919434, "learning_rate": 9.2246914543006e-06, "loss": 0.4328, "step": 12507 }, { "epoch": 0.6907444223547603, "grad_norm": 0.18969734013080597, "learning_rate": 9.221677901989674e-06, "loss": 0.0032, "step": 12508 }, { "epoch": 0.6907996465650541, "grad_norm": 0.04258859157562256, "learning_rate": 9.218664694507964e-06, "loss": 0.0007, "step": 12509 }, { "epoch": 0.6908548707753479, "grad_norm": 5.393700122833252, "learning_rate": 9.215651831951864e-06, "loss": 0.3662, "step": 12510 }, { "epoch": 0.6909100949856417, "grad_norm": 0.30547988414764404, "learning_rate": 9.212639314417762e-06, "loss": 0.0086, "step": 12511 }, { "epoch": 0.6909653191959355, "grad_norm": 6.147181034088135, "learning_rate": 9.209627142002037e-06, "loss": 1.2611, "step": 12512 }, { "epoch": 0.6910205434062293, "grad_norm": 0.5413229465484619, "learning_rate": 9.206615314801062e-06, "loss": 0.0107, "step": 12513 }, { "epoch": 0.6910757676165231, "grad_norm": 1.6606041193008423, "learning_rate": 9.20360383291119e-06, "loss": 0.0796, "step": 12514 }, { "epoch": 0.6911309918268169, "grad_norm": 2.969724416732788, "learning_rate": 9.200592696428759e-06, "loss": 0.2772, "step": 12515 }, { "epoch": 0.6911862160371107, "grad_norm": 2.6263320446014404, "learning_rate": 9.197581905450126e-06, "loss": 0.2233, "step": 12516 }, { "epoch": 0.6912414402474044, "grad_norm": 0.337167888879776, "learning_rate": 9.194571460071586e-06, "loss": 0.0092, "step": 12517 }, { "epoch": 0.6912966644576982, "grad_norm": 0.08235403895378113, "learning_rate": 9.191561360389477e-06, "loss": 0.0027, "step": 12518 }, { "epoch": 0.691351888667992, "grad_norm": 1.8132209777832031, "learning_rate": 9.188551606500086e-06, "loss": 0.0839, "step": 12519 }, { "epoch": 0.6914071128782858, "grad_norm": 4.096273422241211, "learning_rate": 9.185542198499713e-06, "loss": 0.1344, "step": 12520 }, { "epoch": 0.6914623370885796, "grad_norm": 2.768599510192871, "learning_rate": 9.182533136484622e-06, "loss": 0.2444, "step": 12521 }, { "epoch": 0.6915175612988734, "grad_norm": 0.6670980453491211, "learning_rate": 9.1795244205511e-06, "loss": 0.0123, "step": 12522 }, { "epoch": 0.6915727855091672, "grad_norm": 0.2847827672958374, "learning_rate": 9.176516050795397e-06, "loss": 0.0093, "step": 12523 }, { "epoch": 0.691628009719461, "grad_norm": 2.843893527984619, "learning_rate": 9.173508027313756e-06, "loss": 0.1657, "step": 12524 }, { "epoch": 0.6916832339297548, "grad_norm": 2.3120265007019043, "learning_rate": 9.170500350202409e-06, "loss": 0.1016, "step": 12525 }, { "epoch": 0.6917384581400486, "grad_norm": 5.502047061920166, "learning_rate": 9.167493019557604e-06, "loss": 1.112, "step": 12526 }, { "epoch": 0.6917936823503424, "grad_norm": 0.10040213167667389, "learning_rate": 9.164486035475517e-06, "loss": 0.0026, "step": 12527 }, { "epoch": 0.6918489065606361, "grad_norm": 1.7587379217147827, "learning_rate": 9.161479398052377e-06, "loss": 0.1482, "step": 12528 }, { "epoch": 0.6919041307709299, "grad_norm": 0.12477178871631622, "learning_rate": 9.158473107384369e-06, "loss": 0.0036, "step": 12529 }, { "epoch": 0.6919593549812237, "grad_norm": 0.1957903951406479, "learning_rate": 9.155467163567668e-06, "loss": 0.005, "step": 12530 }, { "epoch": 0.6920145791915175, "grad_norm": 2.293095827102661, "learning_rate": 9.152461566698441e-06, "loss": 0.1024, "step": 12531 }, { "epoch": 0.6920698034018113, "grad_norm": 0.1612757444381714, "learning_rate": 9.149456316872863e-06, "loss": 0.0059, "step": 12532 }, { "epoch": 0.6921250276121051, "grad_norm": 2.4503509998321533, "learning_rate": 9.146451414187052e-06, "loss": 0.5706, "step": 12533 }, { "epoch": 0.692180251822399, "grad_norm": 0.09337133169174194, "learning_rate": 9.143446858737168e-06, "loss": 0.0032, "step": 12534 }, { "epoch": 0.6922354760326928, "grad_norm": 0.16228187084197998, "learning_rate": 9.140442650619325e-06, "loss": 0.0047, "step": 12535 }, { "epoch": 0.6922907002429866, "grad_norm": 1.2806742191314697, "learning_rate": 9.13743878992964e-06, "loss": 0.0687, "step": 12536 }, { "epoch": 0.6923459244532804, "grad_norm": 0.11998676508665085, "learning_rate": 9.134435276764201e-06, "loss": 0.0037, "step": 12537 }, { "epoch": 0.6924011486635742, "grad_norm": 0.039344605058431625, "learning_rate": 9.13143211121912e-06, "loss": 0.0007, "step": 12538 }, { "epoch": 0.6924563728738679, "grad_norm": 0.12558016180992126, "learning_rate": 9.128429293390468e-06, "loss": 0.0017, "step": 12539 }, { "epoch": 0.6925115970841617, "grad_norm": 0.24097944796085358, "learning_rate": 9.125426823374313e-06, "loss": 0.0062, "step": 12540 }, { "epoch": 0.6925668212944555, "grad_norm": 0.3008238971233368, "learning_rate": 9.122424701266703e-06, "loss": 0.0051, "step": 12541 }, { "epoch": 0.6926220455047493, "grad_norm": 3.531696319580078, "learning_rate": 9.11942292716371e-06, "loss": 0.0707, "step": 12542 }, { "epoch": 0.6926772697150431, "grad_norm": 0.060781098902225494, "learning_rate": 9.116421501161338e-06, "loss": 0.0013, "step": 12543 }, { "epoch": 0.6927324939253369, "grad_norm": 2.16017746925354, "learning_rate": 9.113420423355635e-06, "loss": 0.2898, "step": 12544 }, { "epoch": 0.6927877181356307, "grad_norm": 0.29057034850120544, "learning_rate": 9.110419693842604e-06, "loss": 0.0051, "step": 12545 }, { "epoch": 0.6928429423459245, "grad_norm": 2.314629316329956, "learning_rate": 9.10741931271825e-06, "loss": 0.2383, "step": 12546 }, { "epoch": 0.6928981665562183, "grad_norm": 0.2805179953575134, "learning_rate": 9.104419280078551e-06, "loss": 0.0069, "step": 12547 }, { "epoch": 0.6929533907665121, "grad_norm": 0.8736543655395508, "learning_rate": 9.10141959601951e-06, "loss": 0.0142, "step": 12548 }, { "epoch": 0.6930086149768059, "grad_norm": 0.022283969447016716, "learning_rate": 9.09842026063708e-06, "loss": 0.0005, "step": 12549 }, { "epoch": 0.6930638391870996, "grad_norm": 0.094784215092659, "learning_rate": 9.09542127402722e-06, "loss": 0.0027, "step": 12550 }, { "epoch": 0.6931190633973934, "grad_norm": 1.5004812479019165, "learning_rate": 9.092422636285878e-06, "loss": 0.0903, "step": 12551 }, { "epoch": 0.6931742876076872, "grad_norm": 0.19815298914909363, "learning_rate": 9.08942434750899e-06, "loss": 0.0062, "step": 12552 }, { "epoch": 0.693229511817981, "grad_norm": 2.8004250526428223, "learning_rate": 9.08642640779247e-06, "loss": 0.1795, "step": 12553 }, { "epoch": 0.6932847360282748, "grad_norm": 0.035753823816776276, "learning_rate": 9.083428817232248e-06, "loss": 0.001, "step": 12554 }, { "epoch": 0.6933399602385686, "grad_norm": 3.6081459522247314, "learning_rate": 9.080431575924213e-06, "loss": 0.2752, "step": 12555 }, { "epoch": 0.6933951844488624, "grad_norm": 4.881059646606445, "learning_rate": 9.077434683964258e-06, "loss": 0.629, "step": 12556 }, { "epoch": 0.6934504086591562, "grad_norm": 0.26663047075271606, "learning_rate": 9.07443814144826e-06, "loss": 0.0041, "step": 12557 }, { "epoch": 0.69350563286945, "grad_norm": 1.3499597311019897, "learning_rate": 9.0714419484721e-06, "loss": 0.0446, "step": 12558 }, { "epoch": 0.6935608570797438, "grad_norm": 0.4733518660068512, "learning_rate": 9.068446105131612e-06, "loss": 0.0052, "step": 12559 }, { "epoch": 0.6936160812900376, "grad_norm": 0.011669929139316082, "learning_rate": 9.06545061152266e-06, "loss": 0.0004, "step": 12560 }, { "epoch": 0.6936713055003313, "grad_norm": 0.019554298371076584, "learning_rate": 9.062455467741072e-06, "loss": 0.0006, "step": 12561 }, { "epoch": 0.6937265297106251, "grad_norm": 0.3000253736972809, "learning_rate": 9.059460673882671e-06, "loss": 0.0097, "step": 12562 }, { "epoch": 0.6937817539209189, "grad_norm": 1.6445974111557007, "learning_rate": 9.056466230043263e-06, "loss": 0.0854, "step": 12563 }, { "epoch": 0.6938369781312127, "grad_norm": 2.751208543777466, "learning_rate": 9.053472136318664e-06, "loss": 0.1049, "step": 12564 }, { "epoch": 0.6938922023415065, "grad_norm": 0.06230303645133972, "learning_rate": 9.050478392804652e-06, "loss": 0.001, "step": 12565 }, { "epoch": 0.6939474265518003, "grad_norm": 4.245516777038574, "learning_rate": 9.047484999597009e-06, "loss": 0.3869, "step": 12566 }, { "epoch": 0.6940026507620941, "grad_norm": 0.06427912414073944, "learning_rate": 9.044491956791495e-06, "loss": 0.0018, "step": 12567 }, { "epoch": 0.6940578749723879, "grad_norm": 0.1613897979259491, "learning_rate": 9.041499264483887e-06, "loss": 0.0039, "step": 12568 }, { "epoch": 0.6941130991826817, "grad_norm": 4.93207311630249, "learning_rate": 9.038506922769898e-06, "loss": 1.3255, "step": 12569 }, { "epoch": 0.6941683233929755, "grad_norm": 0.5217113494873047, "learning_rate": 9.035514931745288e-06, "loss": 0.0136, "step": 12570 }, { "epoch": 0.6942235476032693, "grad_norm": 1.5151640176773071, "learning_rate": 9.032523291505769e-06, "loss": 0.1079, "step": 12571 }, { "epoch": 0.694278771813563, "grad_norm": 0.3077049255371094, "learning_rate": 9.029532002147052e-06, "loss": 0.0064, "step": 12572 }, { "epoch": 0.6943339960238568, "grad_norm": 3.870145320892334, "learning_rate": 9.026541063764833e-06, "loss": 0.0719, "step": 12573 }, { "epoch": 0.6943892202341506, "grad_norm": 2.368842124938965, "learning_rate": 9.02355047645482e-06, "loss": 0.2238, "step": 12574 }, { "epoch": 0.6944444444444444, "grad_norm": 5.375169277191162, "learning_rate": 9.020560240312666e-06, "loss": 0.3284, "step": 12575 }, { "epoch": 0.6944996686547382, "grad_norm": 0.12931866943836212, "learning_rate": 9.01757035543404e-06, "loss": 0.0028, "step": 12576 }, { "epoch": 0.694554892865032, "grad_norm": 0.4994088113307953, "learning_rate": 9.01458082191461e-06, "loss": 0.0088, "step": 12577 }, { "epoch": 0.6946101170753258, "grad_norm": 0.03226001188158989, "learning_rate": 9.011591639850017e-06, "loss": 0.0007, "step": 12578 }, { "epoch": 0.6946653412856196, "grad_norm": 0.3046817183494568, "learning_rate": 9.00860280933589e-06, "loss": 0.0083, "step": 12579 }, { "epoch": 0.6947205654959134, "grad_norm": 0.7537820339202881, "learning_rate": 9.00561433046784e-06, "loss": 0.012, "step": 12580 }, { "epoch": 0.6947757897062072, "grad_norm": 0.049745697528123856, "learning_rate": 9.002626203341504e-06, "loss": 0.0012, "step": 12581 }, { "epoch": 0.694831013916501, "grad_norm": 5.401520729064941, "learning_rate": 8.999638428052449e-06, "loss": 0.6646, "step": 12582 }, { "epoch": 0.6948862381267948, "grad_norm": 2.3559792041778564, "learning_rate": 8.996651004696283e-06, "loss": 0.092, "step": 12583 }, { "epoch": 0.6949414623370885, "grad_norm": 3.216353416442871, "learning_rate": 8.99366393336858e-06, "loss": 0.779, "step": 12584 }, { "epoch": 0.6949966865473823, "grad_norm": 2.5952072143554688, "learning_rate": 8.990677214164899e-06, "loss": 0.1912, "step": 12585 }, { "epoch": 0.6950519107576761, "grad_norm": 3.339052438735962, "learning_rate": 8.987690847180788e-06, "loss": 0.2814, "step": 12586 }, { "epoch": 0.6951071349679699, "grad_norm": 0.4019547700881958, "learning_rate": 8.984704832511806e-06, "loss": 0.005, "step": 12587 }, { "epoch": 0.6951623591782637, "grad_norm": 1.7483205795288086, "learning_rate": 8.981719170253476e-06, "loss": 0.0319, "step": 12588 }, { "epoch": 0.6952175833885575, "grad_norm": 2.0620999336242676, "learning_rate": 8.978733860501316e-06, "loss": 0.0552, "step": 12589 }, { "epoch": 0.6952728075988514, "grad_norm": 1.1303776502609253, "learning_rate": 8.975748903350835e-06, "loss": 0.1471, "step": 12590 }, { "epoch": 0.6953280318091452, "grad_norm": 0.5673744082450867, "learning_rate": 8.972764298897535e-06, "loss": 0.007, "step": 12591 }, { "epoch": 0.695383256019439, "grad_norm": 0.7108454704284668, "learning_rate": 8.969780047236888e-06, "loss": 0.0187, "step": 12592 }, { "epoch": 0.6954384802297328, "grad_norm": 3.0318050384521484, "learning_rate": 8.966796148464387e-06, "loss": 0.0433, "step": 12593 }, { "epoch": 0.6954937044400266, "grad_norm": 0.7460300922393799, "learning_rate": 8.963812602675489e-06, "loss": 0.0252, "step": 12594 }, { "epoch": 0.6955489286503203, "grad_norm": 1.1449977159500122, "learning_rate": 8.96082940996564e-06, "loss": 0.0386, "step": 12595 }, { "epoch": 0.6956041528606141, "grad_norm": 0.04151518642902374, "learning_rate": 8.957846570430284e-06, "loss": 0.0015, "step": 12596 }, { "epoch": 0.6956593770709079, "grad_norm": 1.4097769260406494, "learning_rate": 8.954864084164862e-06, "loss": 0.0554, "step": 12597 }, { "epoch": 0.6957146012812017, "grad_norm": 0.055028293281793594, "learning_rate": 8.951881951264769e-06, "loss": 0.0021, "step": 12598 }, { "epoch": 0.6957698254914955, "grad_norm": 3.9435768127441406, "learning_rate": 8.948900171825433e-06, "loss": 0.2932, "step": 12599 }, { "epoch": 0.6958250497017893, "grad_norm": 0.0747046172618866, "learning_rate": 8.94591874594224e-06, "loss": 0.002, "step": 12600 }, { "epoch": 0.6958802739120831, "grad_norm": 5.778460502624512, "learning_rate": 8.942937673710577e-06, "loss": 0.8219, "step": 12601 }, { "epoch": 0.6959354981223769, "grad_norm": 3.205664873123169, "learning_rate": 8.939956955225808e-06, "loss": 0.1577, "step": 12602 }, { "epoch": 0.6959907223326707, "grad_norm": 0.1200786679983139, "learning_rate": 8.936976590583311e-06, "loss": 0.0028, "step": 12603 }, { "epoch": 0.6960459465429645, "grad_norm": 0.47543632984161377, "learning_rate": 8.933996579878426e-06, "loss": 0.0089, "step": 12604 }, { "epoch": 0.6961011707532583, "grad_norm": 0.44563212990760803, "learning_rate": 8.931016923206495e-06, "loss": 0.0112, "step": 12605 }, { "epoch": 0.696156394963552, "grad_norm": 3.238372802734375, "learning_rate": 8.928037620662838e-06, "loss": 0.2066, "step": 12606 }, { "epoch": 0.6962116191738458, "grad_norm": 1.2877966165542603, "learning_rate": 8.92505867234279e-06, "loss": 0.0393, "step": 12607 }, { "epoch": 0.6962668433841396, "grad_norm": 3.269646406173706, "learning_rate": 8.922080078341631e-06, "loss": 0.2162, "step": 12608 }, { "epoch": 0.6963220675944334, "grad_norm": 4.944519996643066, "learning_rate": 8.919101838754676e-06, "loss": 0.6782, "step": 12609 }, { "epoch": 0.6963772918047272, "grad_norm": 3.0702733993530273, "learning_rate": 8.916123953677198e-06, "loss": 0.5067, "step": 12610 }, { "epoch": 0.696432516015021, "grad_norm": 2.0726096630096436, "learning_rate": 8.913146423204468e-06, "loss": 0.0678, "step": 12611 }, { "epoch": 0.6964877402253148, "grad_norm": 0.22960324585437775, "learning_rate": 8.910169247431741e-06, "loss": 0.0061, "step": 12612 }, { "epoch": 0.6965429644356086, "grad_norm": 5.017828941345215, "learning_rate": 8.907192426454287e-06, "loss": 0.8875, "step": 12613 }, { "epoch": 0.6965981886459024, "grad_norm": 0.6744678020477295, "learning_rate": 8.90421596036731e-06, "loss": 0.0161, "step": 12614 }, { "epoch": 0.6966534128561962, "grad_norm": 3.2031359672546387, "learning_rate": 8.901239849266062e-06, "loss": 0.0947, "step": 12615 }, { "epoch": 0.69670863706649, "grad_norm": 0.2049500048160553, "learning_rate": 8.898264093245748e-06, "loss": 0.0057, "step": 12616 }, { "epoch": 0.6967638612767837, "grad_norm": 0.18930645287036896, "learning_rate": 8.895288692401568e-06, "loss": 0.0047, "step": 12617 }, { "epoch": 0.6968190854870775, "grad_norm": 6.116673469543457, "learning_rate": 8.892313646828713e-06, "loss": 1.6007, "step": 12618 }, { "epoch": 0.6968743096973713, "grad_norm": 1.0182825326919556, "learning_rate": 8.88933895662237e-06, "loss": 0.1582, "step": 12619 }, { "epoch": 0.6969295339076651, "grad_norm": 2.6230971813201904, "learning_rate": 8.886364621877707e-06, "loss": 0.1454, "step": 12620 }, { "epoch": 0.6969847581179589, "grad_norm": 0.1466984897851944, "learning_rate": 8.88339064268988e-06, "loss": 0.0034, "step": 12621 }, { "epoch": 0.6970399823282527, "grad_norm": 4.235260009765625, "learning_rate": 8.880417019154024e-06, "loss": 1.1053, "step": 12622 }, { "epoch": 0.6970952065385465, "grad_norm": 0.02274053916335106, "learning_rate": 8.8774437513653e-06, "loss": 0.0008, "step": 12623 }, { "epoch": 0.6971504307488403, "grad_norm": 0.3190279006958008, "learning_rate": 8.874470839418798e-06, "loss": 0.0088, "step": 12624 }, { "epoch": 0.6972056549591341, "grad_norm": 2.715144395828247, "learning_rate": 8.871498283409656e-06, "loss": 0.1465, "step": 12625 }, { "epoch": 0.6972608791694279, "grad_norm": 4.185348987579346, "learning_rate": 8.868526083432965e-06, "loss": 0.3195, "step": 12626 }, { "epoch": 0.6973161033797217, "grad_norm": 5.3590497970581055, "learning_rate": 8.865554239583816e-06, "loss": 0.5166, "step": 12627 }, { "epoch": 0.6973713275900154, "grad_norm": 1.11978280544281, "learning_rate": 8.862582751957276e-06, "loss": 0.0202, "step": 12628 }, { "epoch": 0.6974265518003092, "grad_norm": 3.1132404804229736, "learning_rate": 8.859611620648428e-06, "loss": 0.2983, "step": 12629 }, { "epoch": 0.697481776010603, "grad_norm": 0.2409069538116455, "learning_rate": 8.85664084575232e-06, "loss": 0.0085, "step": 12630 }, { "epoch": 0.6975370002208968, "grad_norm": 0.11861816793680191, "learning_rate": 8.853670427363995e-06, "loss": 0.0023, "step": 12631 }, { "epoch": 0.6975922244311906, "grad_norm": 4.253532409667969, "learning_rate": 8.850700365578485e-06, "loss": 0.625, "step": 12632 }, { "epoch": 0.6976474486414844, "grad_norm": 0.016867056488990784, "learning_rate": 8.84773066049081e-06, "loss": 0.0003, "step": 12633 }, { "epoch": 0.6977026728517782, "grad_norm": 0.22267268598079681, "learning_rate": 8.844761312195975e-06, "loss": 0.0097, "step": 12634 }, { "epoch": 0.697757897062072, "grad_norm": 0.0875888541340828, "learning_rate": 8.841792320788989e-06, "loss": 0.0022, "step": 12635 }, { "epoch": 0.6978131212723658, "grad_norm": 1.2290527820587158, "learning_rate": 8.838823686364841e-06, "loss": 0.0278, "step": 12636 }, { "epoch": 0.6978683454826596, "grad_norm": 0.16026367247104645, "learning_rate": 8.835855409018481e-06, "loss": 0.0051, "step": 12637 }, { "epoch": 0.6979235696929534, "grad_norm": 1.0949130058288574, "learning_rate": 8.832887488844899e-06, "loss": 0.0405, "step": 12638 }, { "epoch": 0.6979787939032471, "grad_norm": 0.10905162990093231, "learning_rate": 8.829919925939037e-06, "loss": 0.002, "step": 12639 }, { "epoch": 0.6980340181135409, "grad_norm": 2.990475654602051, "learning_rate": 8.826952720395835e-06, "loss": 0.2291, "step": 12640 }, { "epoch": 0.6980892423238347, "grad_norm": 1.2338652610778809, "learning_rate": 8.82398587231022e-06, "loss": 0.0392, "step": 12641 }, { "epoch": 0.6981444665341285, "grad_norm": 1.4683104753494263, "learning_rate": 8.821019381777119e-06, "loss": 0.2604, "step": 12642 }, { "epoch": 0.6981996907444223, "grad_norm": 0.010684531182050705, "learning_rate": 8.818053248891432e-06, "loss": 0.0003, "step": 12643 }, { "epoch": 0.6982549149547161, "grad_norm": 1.9551359415054321, "learning_rate": 8.815087473748056e-06, "loss": 0.4024, "step": 12644 }, { "epoch": 0.69831013916501, "grad_norm": 1.6203594207763672, "learning_rate": 8.812122056441866e-06, "loss": 0.1551, "step": 12645 }, { "epoch": 0.6983653633753037, "grad_norm": 3.691291093826294, "learning_rate": 8.809156997067758e-06, "loss": 0.1321, "step": 12646 }, { "epoch": 0.6984205875855976, "grad_norm": 0.37360191345214844, "learning_rate": 8.80619229572056e-06, "loss": 0.0083, "step": 12647 }, { "epoch": 0.6984758117958914, "grad_norm": 3.3480608463287354, "learning_rate": 8.803227952495145e-06, "loss": 0.1277, "step": 12648 }, { "epoch": 0.6985310360061852, "grad_norm": 2.1074836254119873, "learning_rate": 8.800263967486345e-06, "loss": 0.0809, "step": 12649 }, { "epoch": 0.6985862602164788, "grad_norm": 0.04518771916627884, "learning_rate": 8.797300340788986e-06, "loss": 0.001, "step": 12650 }, { "epoch": 0.6986414844267727, "grad_norm": 0.04897652566432953, "learning_rate": 8.794337072497871e-06, "loss": 0.001, "step": 12651 }, { "epoch": 0.6986967086370665, "grad_norm": 2.7441704273223877, "learning_rate": 8.79137416270783e-06, "loss": 0.2364, "step": 12652 }, { "epoch": 0.6987519328473603, "grad_norm": 1.7954862117767334, "learning_rate": 8.788411611513628e-06, "loss": 0.44, "step": 12653 }, { "epoch": 0.6988071570576541, "grad_norm": 0.011202458292245865, "learning_rate": 8.78544941901006e-06, "loss": 0.0004, "step": 12654 }, { "epoch": 0.6988623812679479, "grad_norm": 3.606468677520752, "learning_rate": 8.782487585291893e-06, "loss": 0.2041, "step": 12655 }, { "epoch": 0.6989176054782417, "grad_norm": 4.090313911437988, "learning_rate": 8.779526110453881e-06, "loss": 0.1272, "step": 12656 }, { "epoch": 0.6989728296885355, "grad_norm": 0.0257561132311821, "learning_rate": 8.776564994590765e-06, "loss": 0.0009, "step": 12657 }, { "epoch": 0.6990280538988293, "grad_norm": 2.4335601329803467, "learning_rate": 8.773604237797298e-06, "loss": 0.0852, "step": 12658 }, { "epoch": 0.6990832781091231, "grad_norm": 0.0850202813744545, "learning_rate": 8.770643840168187e-06, "loss": 0.0026, "step": 12659 }, { "epoch": 0.6991385023194169, "grad_norm": 1.4456589221954346, "learning_rate": 8.76768380179815e-06, "loss": 0.139, "step": 12660 }, { "epoch": 0.6991937265297107, "grad_norm": 0.7429369688034058, "learning_rate": 8.764724122781878e-06, "loss": 0.014, "step": 12661 }, { "epoch": 0.6992489507400044, "grad_norm": 0.029906172305345535, "learning_rate": 8.76176480321408e-06, "loss": 0.0011, "step": 12662 }, { "epoch": 0.6993041749502982, "grad_norm": 0.11371865123510361, "learning_rate": 8.758805843189407e-06, "loss": 0.0026, "step": 12663 }, { "epoch": 0.699359399160592, "grad_norm": 0.1455177366733551, "learning_rate": 8.755847242802544e-06, "loss": 0.0037, "step": 12664 }, { "epoch": 0.6994146233708858, "grad_norm": 4.121389865875244, "learning_rate": 8.752889002148137e-06, "loss": 1.2028, "step": 12665 }, { "epoch": 0.6994698475811796, "grad_norm": 2.811478853225708, "learning_rate": 8.749931121320831e-06, "loss": 0.1333, "step": 12666 }, { "epoch": 0.6995250717914734, "grad_norm": 0.018451431766152382, "learning_rate": 8.74697360041525e-06, "loss": 0.0004, "step": 12667 }, { "epoch": 0.6995802960017672, "grad_norm": 0.09884386509656906, "learning_rate": 8.744016439526025e-06, "loss": 0.0035, "step": 12668 }, { "epoch": 0.699635520212061, "grad_norm": 4.062110424041748, "learning_rate": 8.741059638747757e-06, "loss": 0.504, "step": 12669 }, { "epoch": 0.6996907444223548, "grad_norm": 3.7689034938812256, "learning_rate": 8.738103198175047e-06, "loss": 0.3034, "step": 12670 }, { "epoch": 0.6997459686326486, "grad_norm": 4.040482044219971, "learning_rate": 8.735147117902476e-06, "loss": 0.5513, "step": 12671 }, { "epoch": 0.6998011928429424, "grad_norm": 0.0039506880566477776, "learning_rate": 8.732191398024619e-06, "loss": 0.0002, "step": 12672 }, { "epoch": 0.6998564170532361, "grad_norm": 1.0678741931915283, "learning_rate": 8.729236038636028e-06, "loss": 0.0233, "step": 12673 }, { "epoch": 0.6999116412635299, "grad_norm": 1.3901612758636475, "learning_rate": 8.72628103983127e-06, "loss": 0.076, "step": 12674 }, { "epoch": 0.6999668654738237, "grad_norm": 0.20640990138053894, "learning_rate": 8.723326401704878e-06, "loss": 0.007, "step": 12675 }, { "epoch": 0.7000220896841175, "grad_norm": 2.6610989570617676, "learning_rate": 8.720372124351378e-06, "loss": 0.2494, "step": 12676 }, { "epoch": 0.7000773138944113, "grad_norm": 3.274528741836548, "learning_rate": 8.717418207865277e-06, "loss": 0.3804, "step": 12677 }, { "epoch": 0.7001325381047051, "grad_norm": 0.2409248948097229, "learning_rate": 8.714464652341102e-06, "loss": 0.0034, "step": 12678 }, { "epoch": 0.7001877623149989, "grad_norm": 3.5771114826202393, "learning_rate": 8.711511457873315e-06, "loss": 0.3743, "step": 12679 }, { "epoch": 0.7002429865252927, "grad_norm": 0.027729744091629982, "learning_rate": 8.708558624556425e-06, "loss": 0.0008, "step": 12680 }, { "epoch": 0.7002982107355865, "grad_norm": 0.023703843355178833, "learning_rate": 8.705606152484887e-06, "loss": 0.001, "step": 12681 }, { "epoch": 0.7003534349458803, "grad_norm": 1.8143168687820435, "learning_rate": 8.702654041753162e-06, "loss": 0.2212, "step": 12682 }, { "epoch": 0.7004086591561741, "grad_norm": 0.049682315438985825, "learning_rate": 8.69970229245569e-06, "loss": 0.0011, "step": 12683 }, { "epoch": 0.7004638833664678, "grad_norm": 3.8263001441955566, "learning_rate": 8.696750904686917e-06, "loss": 0.936, "step": 12684 }, { "epoch": 0.7005191075767616, "grad_norm": 4.275937080383301, "learning_rate": 8.693799878541265e-06, "loss": 0.9997, "step": 12685 }, { "epoch": 0.7005743317870554, "grad_norm": 0.021209003403782845, "learning_rate": 8.69084921411314e-06, "loss": 0.0008, "step": 12686 }, { "epoch": 0.7006295559973492, "grad_norm": 0.1978262960910797, "learning_rate": 8.687898911496937e-06, "loss": 0.0046, "step": 12687 }, { "epoch": 0.700684780207643, "grad_norm": 1.9461824893951416, "learning_rate": 8.684948970787068e-06, "loss": 0.0827, "step": 12688 }, { "epoch": 0.7007400044179368, "grad_norm": 1.164191722869873, "learning_rate": 8.681999392077878e-06, "loss": 0.0385, "step": 12689 }, { "epoch": 0.7007952286282306, "grad_norm": 0.5307052135467529, "learning_rate": 8.679050175463757e-06, "loss": 0.0157, "step": 12690 }, { "epoch": 0.7008504528385244, "grad_norm": 2.771118640899658, "learning_rate": 8.676101321039047e-06, "loss": 0.2845, "step": 12691 }, { "epoch": 0.7009056770488182, "grad_norm": 1.8151975870132446, "learning_rate": 8.673152828898098e-06, "loss": 0.0484, "step": 12692 }, { "epoch": 0.700960901259112, "grad_norm": 0.12571415305137634, "learning_rate": 8.670204699135224e-06, "loss": 0.0026, "step": 12693 }, { "epoch": 0.7010161254694058, "grad_norm": 0.04896803945302963, "learning_rate": 8.667256931844774e-06, "loss": 0.0011, "step": 12694 }, { "epoch": 0.7010713496796995, "grad_norm": 4.777647972106934, "learning_rate": 8.664309527121031e-06, "loss": 1.1783, "step": 12695 }, { "epoch": 0.7011265738899933, "grad_norm": 0.058896493166685104, "learning_rate": 8.661362485058289e-06, "loss": 0.0019, "step": 12696 }, { "epoch": 0.7011817981002871, "grad_norm": 0.19465214014053345, "learning_rate": 8.658415805750848e-06, "loss": 0.0037, "step": 12697 }, { "epoch": 0.7012370223105809, "grad_norm": 0.07377218455076218, "learning_rate": 8.655469489292974e-06, "loss": 0.0007, "step": 12698 }, { "epoch": 0.7012922465208747, "grad_norm": 1.7355891466140747, "learning_rate": 8.652523535778927e-06, "loss": 0.1373, "step": 12699 }, { "epoch": 0.7013474707311685, "grad_norm": 1.61007821559906, "learning_rate": 8.64957794530295e-06, "loss": 0.077, "step": 12700 }, { "epoch": 0.7014026949414623, "grad_norm": 0.21355406939983368, "learning_rate": 8.6466327179593e-06, "loss": 0.0057, "step": 12701 }, { "epoch": 0.7014579191517561, "grad_norm": 2.6114273071289062, "learning_rate": 8.64368785384218e-06, "loss": 0.1619, "step": 12702 }, { "epoch": 0.70151314336205, "grad_norm": 4.378568172454834, "learning_rate": 8.64074335304582e-06, "loss": 0.277, "step": 12703 }, { "epoch": 0.7015683675723438, "grad_norm": 0.6892814636230469, "learning_rate": 8.63779921566442e-06, "loss": 0.0206, "step": 12704 }, { "epoch": 0.7016235917826376, "grad_norm": 5.830115795135498, "learning_rate": 8.63485544179217e-06, "loss": 0.6907, "step": 12705 }, { "epoch": 0.7016788159929312, "grad_norm": 0.09728633612394333, "learning_rate": 8.63191203152324e-06, "loss": 0.003, "step": 12706 }, { "epoch": 0.701734040203225, "grad_norm": 0.63498455286026, "learning_rate": 8.628968984951818e-06, "loss": 0.0181, "step": 12707 }, { "epoch": 0.7017892644135189, "grad_norm": 3.5468907356262207, "learning_rate": 8.626026302172048e-06, "loss": 1.0019, "step": 12708 }, { "epoch": 0.7018444886238127, "grad_norm": 4.618762493133545, "learning_rate": 8.623083983278077e-06, "loss": 0.0993, "step": 12709 }, { "epoch": 0.7018997128341065, "grad_norm": 0.02382032200694084, "learning_rate": 8.620142028364037e-06, "loss": 0.001, "step": 12710 }, { "epoch": 0.7019549370444003, "grad_norm": 0.05390273779630661, "learning_rate": 8.617200437524053e-06, "loss": 0.0018, "step": 12711 }, { "epoch": 0.7020101612546941, "grad_norm": 0.19017566740512848, "learning_rate": 8.614259210852224e-06, "loss": 0.0053, "step": 12712 }, { "epoch": 0.7020653854649879, "grad_norm": 0.012317744083702564, "learning_rate": 8.611318348442665e-06, "loss": 0.0004, "step": 12713 }, { "epoch": 0.7021206096752817, "grad_norm": 1.1462551355361938, "learning_rate": 8.608377850389453e-06, "loss": 0.1607, "step": 12714 }, { "epoch": 0.7021758338855755, "grad_norm": 4.749123573303223, "learning_rate": 8.605437716786665e-06, "loss": 0.5784, "step": 12715 }, { "epoch": 0.7022310580958693, "grad_norm": 2.3122398853302, "learning_rate": 8.602497947728354e-06, "loss": 0.111, "step": 12716 }, { "epoch": 0.702286282306163, "grad_norm": 0.07395637035369873, "learning_rate": 8.5995585433086e-06, "loss": 0.0022, "step": 12717 }, { "epoch": 0.7023415065164568, "grad_norm": 0.31320515275001526, "learning_rate": 8.596619503621405e-06, "loss": 0.0111, "step": 12718 }, { "epoch": 0.7023967307267506, "grad_norm": 0.7571514248847961, "learning_rate": 8.593680828760824e-06, "loss": 0.0139, "step": 12719 }, { "epoch": 0.7024519549370444, "grad_norm": 2.662567138671875, "learning_rate": 8.590742518820866e-06, "loss": 0.1581, "step": 12720 }, { "epoch": 0.7025071791473382, "grad_norm": 3.1260340213775635, "learning_rate": 8.587804573895535e-06, "loss": 0.2386, "step": 12721 }, { "epoch": 0.702562403357632, "grad_norm": 0.6830379366874695, "learning_rate": 8.584866994078817e-06, "loss": 0.1541, "step": 12722 }, { "epoch": 0.7026176275679258, "grad_norm": 3.192370653152466, "learning_rate": 8.58192977946471e-06, "loss": 0.1938, "step": 12723 }, { "epoch": 0.7026728517782196, "grad_norm": 1.489147663116455, "learning_rate": 8.578992930147176e-06, "loss": 0.014, "step": 12724 }, { "epoch": 0.7027280759885134, "grad_norm": 2.8183393478393555, "learning_rate": 8.57605644622017e-06, "loss": 0.4006, "step": 12725 }, { "epoch": 0.7027833001988072, "grad_norm": 4.389022350311279, "learning_rate": 8.573120327777635e-06, "loss": 0.6675, "step": 12726 }, { "epoch": 0.702838524409101, "grad_norm": 0.016721295192837715, "learning_rate": 8.570184574913527e-06, "loss": 0.0006, "step": 12727 }, { "epoch": 0.7028937486193948, "grad_norm": 2.0091092586517334, "learning_rate": 8.567249187721738e-06, "loss": 0.3622, "step": 12728 }, { "epoch": 0.7029489728296885, "grad_norm": 0.13550354540348053, "learning_rate": 8.564314166296202e-06, "loss": 0.0036, "step": 12729 }, { "epoch": 0.7030041970399823, "grad_norm": 1.3719656467437744, "learning_rate": 8.561379510730811e-06, "loss": 0.0456, "step": 12730 }, { "epoch": 0.7030594212502761, "grad_norm": 0.40836116671562195, "learning_rate": 8.558445221119456e-06, "loss": 0.0097, "step": 12731 }, { "epoch": 0.7031146454605699, "grad_norm": 0.11528562754392624, "learning_rate": 8.555511297556003e-06, "loss": 0.0044, "step": 12732 }, { "epoch": 0.7031698696708637, "grad_norm": 2.5363609790802, "learning_rate": 8.552577740134337e-06, "loss": 0.3962, "step": 12733 }, { "epoch": 0.7032250938811575, "grad_norm": 0.24039685726165771, "learning_rate": 8.549644548948288e-06, "loss": 0.0055, "step": 12734 }, { "epoch": 0.7032803180914513, "grad_norm": 0.9345121383666992, "learning_rate": 8.546711724091711e-06, "loss": 0.0204, "step": 12735 }, { "epoch": 0.7033355423017451, "grad_norm": 3.17515230178833, "learning_rate": 8.543779265658433e-06, "loss": 0.6178, "step": 12736 }, { "epoch": 0.7033907665120389, "grad_norm": 2.8562381267547607, "learning_rate": 8.540847173742273e-06, "loss": 0.2116, "step": 12737 }, { "epoch": 0.7034459907223327, "grad_norm": 2.4511184692382812, "learning_rate": 8.537915448437026e-06, "loss": 0.7245, "step": 12738 }, { "epoch": 0.7035012149326265, "grad_norm": 3.8325347900390625, "learning_rate": 8.534984089836502e-06, "loss": 0.392, "step": 12739 }, { "epoch": 0.7035564391429202, "grad_norm": 2.7551815509796143, "learning_rate": 8.532053098034476e-06, "loss": 0.3063, "step": 12740 }, { "epoch": 0.703611663353214, "grad_norm": 0.048036739230155945, "learning_rate": 8.529122473124718e-06, "loss": 0.0015, "step": 12741 }, { "epoch": 0.7036668875635078, "grad_norm": 2.4635236263275146, "learning_rate": 8.526192215200983e-06, "loss": 0.0896, "step": 12742 }, { "epoch": 0.7037221117738016, "grad_norm": 7.545773983001709, "learning_rate": 8.523262324357038e-06, "loss": 0.7461, "step": 12743 }, { "epoch": 0.7037773359840954, "grad_norm": 3.8687281608581543, "learning_rate": 8.520332800686589e-06, "loss": 0.2811, "step": 12744 }, { "epoch": 0.7038325601943892, "grad_norm": 0.2071865350008011, "learning_rate": 8.517403644283383e-06, "loss": 0.0061, "step": 12745 }, { "epoch": 0.703887784404683, "grad_norm": 0.4674506187438965, "learning_rate": 8.514474855241122e-06, "loss": 0.0096, "step": 12746 }, { "epoch": 0.7039430086149768, "grad_norm": 3.857259511947632, "learning_rate": 8.51154643365351e-06, "loss": 0.8037, "step": 12747 }, { "epoch": 0.7039982328252706, "grad_norm": 1.9932677745819092, "learning_rate": 8.508618379614227e-06, "loss": 0.0396, "step": 12748 }, { "epoch": 0.7040534570355644, "grad_norm": 0.019927874207496643, "learning_rate": 8.505690693216961e-06, "loss": 0.0005, "step": 12749 }, { "epoch": 0.7041086812458582, "grad_norm": 0.2157190591096878, "learning_rate": 8.502763374555374e-06, "loss": 0.004, "step": 12750 }, { "epoch": 0.7041639054561519, "grad_norm": 3.004650354385376, "learning_rate": 8.499836423723117e-06, "loss": 0.2346, "step": 12751 }, { "epoch": 0.7042191296664457, "grad_norm": 0.02768765762448311, "learning_rate": 8.496909840813834e-06, "loss": 0.0004, "step": 12752 }, { "epoch": 0.7042743538767395, "grad_norm": 0.04518570005893707, "learning_rate": 8.493983625921151e-06, "loss": 0.0014, "step": 12753 }, { "epoch": 0.7043295780870333, "grad_norm": 2.41131591796875, "learning_rate": 8.491057779138682e-06, "loss": 0.0818, "step": 12754 }, { "epoch": 0.7043848022973271, "grad_norm": 0.9314897060394287, "learning_rate": 8.488132300560048e-06, "loss": 0.0281, "step": 12755 }, { "epoch": 0.7044400265076209, "grad_norm": 0.27881595492362976, "learning_rate": 8.485207190278842e-06, "loss": 0.0085, "step": 12756 }, { "epoch": 0.7044952507179147, "grad_norm": 0.27892476320266724, "learning_rate": 8.482282448388621e-06, "loss": 0.0074, "step": 12757 }, { "epoch": 0.7045504749282085, "grad_norm": 3.0649006366729736, "learning_rate": 8.479358074982984e-06, "loss": 0.7142, "step": 12758 }, { "epoch": 0.7046056991385024, "grad_norm": 0.037088509649038315, "learning_rate": 8.476434070155479e-06, "loss": 0.0013, "step": 12759 }, { "epoch": 0.7046609233487962, "grad_norm": 0.17425180971622467, "learning_rate": 8.473510433999655e-06, "loss": 0.0031, "step": 12760 }, { "epoch": 0.70471614755909, "grad_norm": 4.293916702270508, "learning_rate": 8.470587166609039e-06, "loss": 0.8494, "step": 12761 }, { "epoch": 0.7047713717693836, "grad_norm": 0.37531623244285583, "learning_rate": 8.46766426807717e-06, "loss": 0.0153, "step": 12762 }, { "epoch": 0.7048265959796775, "grad_norm": 1.2006924152374268, "learning_rate": 8.46474173849755e-06, "loss": 0.0575, "step": 12763 }, { "epoch": 0.7048818201899713, "grad_norm": 3.8896913528442383, "learning_rate": 8.461819577963683e-06, "loss": 0.3555, "step": 12764 }, { "epoch": 0.7049370444002651, "grad_norm": 1.89321768283844, "learning_rate": 8.458897786569047e-06, "loss": 0.2504, "step": 12765 }, { "epoch": 0.7049922686105589, "grad_norm": 0.07695069909095764, "learning_rate": 8.455976364407143e-06, "loss": 0.0017, "step": 12766 }, { "epoch": 0.7050474928208527, "grad_norm": 0.9514254331588745, "learning_rate": 8.453055311571406e-06, "loss": 0.0076, "step": 12767 }, { "epoch": 0.7051027170311465, "grad_norm": 2.5388550758361816, "learning_rate": 8.450134628155307e-06, "loss": 0.1253, "step": 12768 }, { "epoch": 0.7051579412414403, "grad_norm": 0.16342386603355408, "learning_rate": 8.44721431425228e-06, "loss": 0.0058, "step": 12769 }, { "epoch": 0.7052131654517341, "grad_norm": 1.2645128965377808, "learning_rate": 8.444294369955761e-06, "loss": 0.0179, "step": 12770 }, { "epoch": 0.7052683896620279, "grad_norm": 4.07503604888916, "learning_rate": 8.441374795359154e-06, "loss": 1.1095, "step": 12771 }, { "epoch": 0.7053236138723217, "grad_norm": 2.1238365173339844, "learning_rate": 8.438455590555888e-06, "loss": 0.0496, "step": 12772 }, { "epoch": 0.7053788380826154, "grad_norm": 0.19891391694545746, "learning_rate": 8.435536755639326e-06, "loss": 0.0031, "step": 12773 }, { "epoch": 0.7054340622929092, "grad_norm": 5.782723426818848, "learning_rate": 8.432618290702877e-06, "loss": 1.0627, "step": 12774 }, { "epoch": 0.705489286503203, "grad_norm": 0.04213927686214447, "learning_rate": 8.429700195839896e-06, "loss": 0.0014, "step": 12775 }, { "epoch": 0.7055445107134968, "grad_norm": 0.2468230426311493, "learning_rate": 8.426782471143747e-06, "loss": 0.0042, "step": 12776 }, { "epoch": 0.7055997349237906, "grad_norm": 2.1402087211608887, "learning_rate": 8.423865116707764e-06, "loss": 0.4102, "step": 12777 }, { "epoch": 0.7056549591340844, "grad_norm": 0.12631343305110931, "learning_rate": 8.420948132625302e-06, "loss": 0.0033, "step": 12778 }, { "epoch": 0.7057101833443782, "grad_norm": 0.5217241048812866, "learning_rate": 8.418031518989671e-06, "loss": 0.0103, "step": 12779 }, { "epoch": 0.705765407554672, "grad_norm": 0.07826749235391617, "learning_rate": 8.415115275894185e-06, "loss": 0.002, "step": 12780 }, { "epoch": 0.7058206317649658, "grad_norm": 0.0613168329000473, "learning_rate": 8.412199403432136e-06, "loss": 0.0012, "step": 12781 }, { "epoch": 0.7058758559752596, "grad_norm": 3.0072007179260254, "learning_rate": 8.40928390169683e-06, "loss": 0.1198, "step": 12782 }, { "epoch": 0.7059310801855534, "grad_norm": 0.26077815890312195, "learning_rate": 8.406368770781514e-06, "loss": 0.0054, "step": 12783 }, { "epoch": 0.7059863043958471, "grad_norm": 2.2820956707000732, "learning_rate": 8.403454010779478e-06, "loss": 0.1271, "step": 12784 }, { "epoch": 0.7060415286061409, "grad_norm": 0.0681491494178772, "learning_rate": 8.400539621783958e-06, "loss": 0.0018, "step": 12785 }, { "epoch": 0.7060967528164347, "grad_norm": 3.146728038787842, "learning_rate": 8.397625603888198e-06, "loss": 0.7625, "step": 12786 }, { "epoch": 0.7061519770267285, "grad_norm": 0.15334491431713104, "learning_rate": 8.39471195718542e-06, "loss": 0.0048, "step": 12787 }, { "epoch": 0.7062072012370223, "grad_norm": 2.2070860862731934, "learning_rate": 8.391798681768853e-06, "loss": 0.0578, "step": 12788 }, { "epoch": 0.7062624254473161, "grad_norm": 0.741607129573822, "learning_rate": 8.38888577773169e-06, "loss": 0.0133, "step": 12789 }, { "epoch": 0.7063176496576099, "grad_norm": 0.07500816881656647, "learning_rate": 8.385973245167129e-06, "loss": 0.0018, "step": 12790 }, { "epoch": 0.7063728738679037, "grad_norm": 3.5492212772369385, "learning_rate": 8.383061084168347e-06, "loss": 0.0674, "step": 12791 }, { "epoch": 0.7064280980781975, "grad_norm": 1.1746656894683838, "learning_rate": 8.380149294828512e-06, "loss": 0.0341, "step": 12792 }, { "epoch": 0.7064833222884913, "grad_norm": 1.2117905616760254, "learning_rate": 8.377237877240776e-06, "loss": 0.0351, "step": 12793 }, { "epoch": 0.7065385464987851, "grad_norm": 2.045767307281494, "learning_rate": 8.374326831498293e-06, "loss": 0.2568, "step": 12794 }, { "epoch": 0.7065937707090788, "grad_norm": 3.041674852371216, "learning_rate": 8.371416157694194e-06, "loss": 0.3928, "step": 12795 }, { "epoch": 0.7066489949193726, "grad_norm": 0.05161425098776817, "learning_rate": 8.368505855921597e-06, "loss": 0.0016, "step": 12796 }, { "epoch": 0.7067042191296664, "grad_norm": 4.416234016418457, "learning_rate": 8.365595926273604e-06, "loss": 0.7139, "step": 12797 }, { "epoch": 0.7067594433399602, "grad_norm": 0.8697138428688049, "learning_rate": 8.362686368843333e-06, "loss": 0.0128, "step": 12798 }, { "epoch": 0.706814667550254, "grad_norm": 2.905919075012207, "learning_rate": 8.359777183723841e-06, "loss": 0.3736, "step": 12799 }, { "epoch": 0.7068698917605478, "grad_norm": 3.0227105617523193, "learning_rate": 8.35686837100822e-06, "loss": 0.5212, "step": 12800 }, { "epoch": 0.7069251159708416, "grad_norm": 1.0107694864273071, "learning_rate": 8.353959930789528e-06, "loss": 0.0277, "step": 12801 }, { "epoch": 0.7069803401811354, "grad_norm": 1.032873272895813, "learning_rate": 8.351051863160813e-06, "loss": 0.0346, "step": 12802 }, { "epoch": 0.7070355643914292, "grad_norm": 0.07987646758556366, "learning_rate": 8.348144168215106e-06, "loss": 0.0019, "step": 12803 }, { "epoch": 0.707090788601723, "grad_norm": 0.2433144599199295, "learning_rate": 8.345236846045444e-06, "loss": 0.007, "step": 12804 }, { "epoch": 0.7071460128120168, "grad_norm": 2.5846590995788574, "learning_rate": 8.342329896744834e-06, "loss": 0.2023, "step": 12805 }, { "epoch": 0.7072012370223106, "grad_norm": 3.815558910369873, "learning_rate": 8.339423320406282e-06, "loss": 0.4489, "step": 12806 }, { "epoch": 0.7072564612326043, "grad_norm": 1.0414882898330688, "learning_rate": 8.336517117122763e-06, "loss": 0.0458, "step": 12807 }, { "epoch": 0.7073116854428981, "grad_norm": 0.36295485496520996, "learning_rate": 8.333611286987283e-06, "loss": 0.0077, "step": 12808 }, { "epoch": 0.7073669096531919, "grad_norm": 0.14798952639102936, "learning_rate": 8.330705830092773e-06, "loss": 0.0026, "step": 12809 }, { "epoch": 0.7074221338634857, "grad_norm": 1.8271020650863647, "learning_rate": 8.327800746532215e-06, "loss": 0.4485, "step": 12810 }, { "epoch": 0.7074773580737795, "grad_norm": 1.798241376876831, "learning_rate": 8.32489603639854e-06, "loss": 0.1635, "step": 12811 }, { "epoch": 0.7075325822840733, "grad_norm": 0.7088028192520142, "learning_rate": 8.321991699784677e-06, "loss": 0.1172, "step": 12812 }, { "epoch": 0.7075878064943671, "grad_norm": 2.275465965270996, "learning_rate": 8.319087736783538e-06, "loss": 0.0739, "step": 12813 }, { "epoch": 0.707643030704661, "grad_norm": 0.27892830967903137, "learning_rate": 8.316184147488051e-06, "loss": 0.0058, "step": 12814 }, { "epoch": 0.7076982549149547, "grad_norm": 0.02267404831945896, "learning_rate": 8.31328093199109e-06, "loss": 0.0006, "step": 12815 }, { "epoch": 0.7077534791252486, "grad_norm": 0.09635820984840393, "learning_rate": 8.310378090385533e-06, "loss": 0.003, "step": 12816 }, { "epoch": 0.7078087033355424, "grad_norm": 0.038057584315538406, "learning_rate": 8.307475622764269e-06, "loss": 0.0013, "step": 12817 }, { "epoch": 0.707863927545836, "grad_norm": 4.25453519821167, "learning_rate": 8.304573529220146e-06, "loss": 1.2002, "step": 12818 }, { "epoch": 0.7079191517561298, "grad_norm": 0.17721152305603027, "learning_rate": 8.301671809846013e-06, "loss": 0.0047, "step": 12819 }, { "epoch": 0.7079743759664237, "grad_norm": 0.04216613247990608, "learning_rate": 8.298770464734693e-06, "loss": 0.0005, "step": 12820 }, { "epoch": 0.7080296001767175, "grad_norm": 0.6865506768226624, "learning_rate": 8.295869493979032e-06, "loss": 0.0138, "step": 12821 }, { "epoch": 0.7080848243870113, "grad_norm": 0.11267326772212982, "learning_rate": 8.292968897671813e-06, "loss": 0.0036, "step": 12822 }, { "epoch": 0.7081400485973051, "grad_norm": 0.5128762722015381, "learning_rate": 8.290068675905854e-06, "loss": 0.0132, "step": 12823 }, { "epoch": 0.7081952728075989, "grad_norm": 0.016920266672968864, "learning_rate": 8.287168828773936e-06, "loss": 0.0004, "step": 12824 }, { "epoch": 0.7082504970178927, "grad_norm": 0.08391088247299194, "learning_rate": 8.284269356368831e-06, "loss": 0.0022, "step": 12825 }, { "epoch": 0.7083057212281865, "grad_norm": 0.0763186514377594, "learning_rate": 8.281370258783295e-06, "loss": 0.0014, "step": 12826 }, { "epoch": 0.7083609454384803, "grad_norm": 0.0038553422782570124, "learning_rate": 8.278471536110091e-06, "loss": 0.0001, "step": 12827 }, { "epoch": 0.7084161696487741, "grad_norm": 2.177694082260132, "learning_rate": 8.275573188441954e-06, "loss": 0.4098, "step": 12828 }, { "epoch": 0.7084713938590678, "grad_norm": 0.25391098856925964, "learning_rate": 8.272675215871611e-06, "loss": 0.0055, "step": 12829 }, { "epoch": 0.7085266180693616, "grad_norm": 4.721210956573486, "learning_rate": 8.269777618491773e-06, "loss": 0.3943, "step": 12830 }, { "epoch": 0.7085818422796554, "grad_norm": 4.89355993270874, "learning_rate": 8.26688039639514e-06, "loss": 0.4911, "step": 12831 }, { "epoch": 0.7086370664899492, "grad_norm": 0.35590454936027527, "learning_rate": 8.263983549674404e-06, "loss": 0.0075, "step": 12832 }, { "epoch": 0.708692290700243, "grad_norm": 5.310136318206787, "learning_rate": 8.26108707842225e-06, "loss": 0.4399, "step": 12833 }, { "epoch": 0.7087475149105368, "grad_norm": 1.0277268886566162, "learning_rate": 8.258190982731338e-06, "loss": 0.0343, "step": 12834 }, { "epoch": 0.7088027391208306, "grad_norm": 0.029252924025058746, "learning_rate": 8.255295262694324e-06, "loss": 0.0011, "step": 12835 }, { "epoch": 0.7088579633311244, "grad_norm": 0.02823932096362114, "learning_rate": 8.252399918403847e-06, "loss": 0.0009, "step": 12836 }, { "epoch": 0.7089131875414182, "grad_norm": 2.9761807918548584, "learning_rate": 8.249504949952552e-06, "loss": 0.1437, "step": 12837 }, { "epoch": 0.708968411751712, "grad_norm": 1.4377082586288452, "learning_rate": 8.246610357433029e-06, "loss": 0.0293, "step": 12838 }, { "epoch": 0.7090236359620058, "grad_norm": 4.11282205581665, "learning_rate": 8.243716140937911e-06, "loss": 0.2113, "step": 12839 }, { "epoch": 0.7090788601722995, "grad_norm": 4.031936168670654, "learning_rate": 8.240822300559783e-06, "loss": 0.9161, "step": 12840 }, { "epoch": 0.7091340843825933, "grad_norm": 0.0320364311337471, "learning_rate": 8.237928836391226e-06, "loss": 0.0009, "step": 12841 }, { "epoch": 0.7091893085928871, "grad_norm": 2.1555495262145996, "learning_rate": 8.235035748524802e-06, "loss": 0.1373, "step": 12842 }, { "epoch": 0.7092445328031809, "grad_norm": 0.012566122226417065, "learning_rate": 8.232143037053087e-06, "loss": 0.0003, "step": 12843 }, { "epoch": 0.7092997570134747, "grad_norm": 0.1445625126361847, "learning_rate": 8.229250702068616e-06, "loss": 0.0052, "step": 12844 }, { "epoch": 0.7093549812237685, "grad_norm": 2.3096847534179688, "learning_rate": 8.226358743663928e-06, "loss": 0.0849, "step": 12845 }, { "epoch": 0.7094102054340623, "grad_norm": 0.15872865915298462, "learning_rate": 8.22346716193153e-06, "loss": 0.0037, "step": 12846 }, { "epoch": 0.7094654296443561, "grad_norm": 0.07139655947685242, "learning_rate": 8.220575956963963e-06, "loss": 0.0021, "step": 12847 }, { "epoch": 0.7095206538546499, "grad_norm": 0.01641209051012993, "learning_rate": 8.21768512885369e-06, "loss": 0.0005, "step": 12848 }, { "epoch": 0.7095758780649437, "grad_norm": 0.09512211382389069, "learning_rate": 8.214794677693216e-06, "loss": 0.0025, "step": 12849 }, { "epoch": 0.7096311022752375, "grad_norm": 2.333369255065918, "learning_rate": 8.211904603575017e-06, "loss": 0.1662, "step": 12850 }, { "epoch": 0.7096863264855312, "grad_norm": 0.018684202805161476, "learning_rate": 8.209014906591544e-06, "loss": 0.0005, "step": 12851 }, { "epoch": 0.709741550695825, "grad_norm": 0.13777582347393036, "learning_rate": 8.206125586835247e-06, "loss": 0.0022, "step": 12852 }, { "epoch": 0.7097967749061188, "grad_norm": 0.03294289857149124, "learning_rate": 8.20323664439858e-06, "loss": 0.0007, "step": 12853 }, { "epoch": 0.7098519991164126, "grad_norm": 5.2810587882995605, "learning_rate": 8.200348079373946e-06, "loss": 0.2618, "step": 12854 }, { "epoch": 0.7099072233267064, "grad_norm": 0.4694942831993103, "learning_rate": 8.197459891853774e-06, "loss": 0.0212, "step": 12855 }, { "epoch": 0.7099624475370002, "grad_norm": 4.3998703956604, "learning_rate": 8.19457208193046e-06, "loss": 0.337, "step": 12856 }, { "epoch": 0.710017671747294, "grad_norm": 1.8695605993270874, "learning_rate": 8.191684649696394e-06, "loss": 0.1037, "step": 12857 }, { "epoch": 0.7100728959575878, "grad_norm": 0.54795902967453, "learning_rate": 8.188797595243947e-06, "loss": 0.0191, "step": 12858 }, { "epoch": 0.7101281201678816, "grad_norm": 0.012352418154478073, "learning_rate": 8.185910918665497e-06, "loss": 0.0003, "step": 12859 }, { "epoch": 0.7101833443781754, "grad_norm": 3.834104299545288, "learning_rate": 8.183024620053388e-06, "loss": 0.1236, "step": 12860 }, { "epoch": 0.7102385685884692, "grad_norm": 3.6049630641937256, "learning_rate": 8.180138699499964e-06, "loss": 0.19, "step": 12861 }, { "epoch": 0.7102937927987629, "grad_norm": 0.12263620644807816, "learning_rate": 8.177253157097544e-06, "loss": 0.0034, "step": 12862 }, { "epoch": 0.7103490170090567, "grad_norm": 5.407588005065918, "learning_rate": 8.17436799293847e-06, "loss": 1.9065, "step": 12863 }, { "epoch": 0.7104042412193505, "grad_norm": 0.01761460304260254, "learning_rate": 8.171483207115014e-06, "loss": 0.0005, "step": 12864 }, { "epoch": 0.7104594654296443, "grad_norm": 1.6680108308792114, "learning_rate": 8.168598799719494e-06, "loss": 0.163, "step": 12865 }, { "epoch": 0.7105146896399381, "grad_norm": 0.06168634817004204, "learning_rate": 8.16571477084418e-06, "loss": 0.0016, "step": 12866 }, { "epoch": 0.7105699138502319, "grad_norm": 0.09270026534795761, "learning_rate": 8.162831120581341e-06, "loss": 0.0017, "step": 12867 }, { "epoch": 0.7106251380605257, "grad_norm": 1.2151849269866943, "learning_rate": 8.159947849023224e-06, "loss": 0.0349, "step": 12868 }, { "epoch": 0.7106803622708195, "grad_norm": 2.309126615524292, "learning_rate": 8.1570649562621e-06, "loss": 0.0608, "step": 12869 }, { "epoch": 0.7107355864811133, "grad_norm": 1.9240052700042725, "learning_rate": 8.154182442390167e-06, "loss": 0.1039, "step": 12870 }, { "epoch": 0.7107908106914071, "grad_norm": 2.4837591648101807, "learning_rate": 8.151300307499668e-06, "loss": 0.1784, "step": 12871 }, { "epoch": 0.710846034901701, "grad_norm": 0.44552555680274963, "learning_rate": 8.148418551682803e-06, "loss": 0.0104, "step": 12872 }, { "epoch": 0.7109012591119946, "grad_norm": 3.1866166591644287, "learning_rate": 8.145537175031772e-06, "loss": 0.7128, "step": 12873 }, { "epoch": 0.7109564833222884, "grad_norm": 0.10818499326705933, "learning_rate": 8.142656177638746e-06, "loss": 0.0034, "step": 12874 }, { "epoch": 0.7110117075325822, "grad_norm": 4.662201404571533, "learning_rate": 8.139775559595913e-06, "loss": 0.2147, "step": 12875 }, { "epoch": 0.711066931742876, "grad_norm": 1.5002020597457886, "learning_rate": 8.13689532099543e-06, "loss": 0.0522, "step": 12876 }, { "epoch": 0.7111221559531699, "grad_norm": 1.865068793296814, "learning_rate": 8.134015461929426e-06, "loss": 0.1054, "step": 12877 }, { "epoch": 0.7111773801634637, "grad_norm": 2.3985676765441895, "learning_rate": 8.131135982490055e-06, "loss": 0.2265, "step": 12878 }, { "epoch": 0.7112326043737575, "grad_norm": 1.2853097915649414, "learning_rate": 8.128256882769433e-06, "loss": 0.0241, "step": 12879 }, { "epoch": 0.7112878285840513, "grad_norm": 4.149235248565674, "learning_rate": 8.12537816285967e-06, "loss": 0.8826, "step": 12880 }, { "epoch": 0.7113430527943451, "grad_norm": 1.301166296005249, "learning_rate": 8.122499822852858e-06, "loss": 0.0829, "step": 12881 }, { "epoch": 0.7113982770046389, "grad_norm": 0.10089338570833206, "learning_rate": 8.119621862841098e-06, "loss": 0.003, "step": 12882 }, { "epoch": 0.7114535012149327, "grad_norm": 0.4168250262737274, "learning_rate": 8.116744282916458e-06, "loss": 0.0085, "step": 12883 }, { "epoch": 0.7115087254252265, "grad_norm": 4.248510837554932, "learning_rate": 8.113867083170997e-06, "loss": 0.7435, "step": 12884 }, { "epoch": 0.7115639496355202, "grad_norm": 2.556199312210083, "learning_rate": 8.110990263696759e-06, "loss": 0.2359, "step": 12885 }, { "epoch": 0.711619173845814, "grad_norm": 0.25956693291664124, "learning_rate": 8.108113824585803e-06, "loss": 0.003, "step": 12886 }, { "epoch": 0.7116743980561078, "grad_norm": 0.03699851036071777, "learning_rate": 8.105237765930128e-06, "loss": 0.0009, "step": 12887 }, { "epoch": 0.7117296222664016, "grad_norm": 0.9968989491462708, "learning_rate": 8.102362087821765e-06, "loss": 0.0371, "step": 12888 }, { "epoch": 0.7117848464766954, "grad_norm": 0.05742665007710457, "learning_rate": 8.099486790352709e-06, "loss": 0.0016, "step": 12889 }, { "epoch": 0.7118400706869892, "grad_norm": 0.07611995190382004, "learning_rate": 8.096611873614952e-06, "loss": 0.0017, "step": 12890 }, { "epoch": 0.711895294897283, "grad_norm": 3.684323310852051, "learning_rate": 8.09373733770046e-06, "loss": 0.1382, "step": 12891 }, { "epoch": 0.7119505191075768, "grad_norm": 0.05501297861337662, "learning_rate": 8.090863182701223e-06, "loss": 0.0015, "step": 12892 }, { "epoch": 0.7120057433178706, "grad_norm": 0.39673399925231934, "learning_rate": 8.08798940870916e-06, "loss": 0.0053, "step": 12893 }, { "epoch": 0.7120609675281644, "grad_norm": 4.758833885192871, "learning_rate": 8.085116015816235e-06, "loss": 0.215, "step": 12894 }, { "epoch": 0.7121161917384582, "grad_norm": 2.8430607318878174, "learning_rate": 8.082243004114369e-06, "loss": 0.0828, "step": 12895 }, { "epoch": 0.7121714159487519, "grad_norm": 2.083245277404785, "learning_rate": 8.079370373695479e-06, "loss": 0.0667, "step": 12896 }, { "epoch": 0.7122266401590457, "grad_norm": 0.10081413388252258, "learning_rate": 8.076498124651456e-06, "loss": 0.0037, "step": 12897 }, { "epoch": 0.7122818643693395, "grad_norm": 2.8233420848846436, "learning_rate": 8.073626257074214e-06, "loss": 0.077, "step": 12898 }, { "epoch": 0.7123370885796333, "grad_norm": 3.2330050468444824, "learning_rate": 8.07075477105562e-06, "loss": 0.2851, "step": 12899 }, { "epoch": 0.7123923127899271, "grad_norm": 3.6051387786865234, "learning_rate": 8.067883666687544e-06, "loss": 0.5197, "step": 12900 }, { "epoch": 0.7124475370002209, "grad_norm": 4.177722930908203, "learning_rate": 8.065012944061828e-06, "loss": 1.1261, "step": 12901 }, { "epoch": 0.7125027612105147, "grad_norm": 2.5210037231445312, "learning_rate": 8.062142603270341e-06, "loss": 0.4435, "step": 12902 }, { "epoch": 0.7125579854208085, "grad_norm": 2.949920654296875, "learning_rate": 8.059272644404883e-06, "loss": 0.0679, "step": 12903 }, { "epoch": 0.7126132096311023, "grad_norm": 0.27942466735839844, "learning_rate": 8.056403067557294e-06, "loss": 0.012, "step": 12904 }, { "epoch": 0.7126684338413961, "grad_norm": 0.06386025995016098, "learning_rate": 8.053533872819375e-06, "loss": 0.0008, "step": 12905 }, { "epoch": 0.7127236580516899, "grad_norm": 2.9180126190185547, "learning_rate": 8.050665060282915e-06, "loss": 0.0948, "step": 12906 }, { "epoch": 0.7127788822619836, "grad_norm": 3.9274933338165283, "learning_rate": 8.04779663003969e-06, "loss": 0.9818, "step": 12907 }, { "epoch": 0.7128341064722774, "grad_norm": 0.06707353889942169, "learning_rate": 8.044928582181486e-06, "loss": 0.0009, "step": 12908 }, { "epoch": 0.7128893306825712, "grad_norm": 0.0493227057158947, "learning_rate": 8.042060916800052e-06, "loss": 0.0011, "step": 12909 }, { "epoch": 0.712944554892865, "grad_norm": 5.702679634094238, "learning_rate": 8.03919363398713e-06, "loss": 0.7502, "step": 12910 }, { "epoch": 0.7129997791031588, "grad_norm": 0.025270625948905945, "learning_rate": 8.036326733834457e-06, "loss": 0.0008, "step": 12911 }, { "epoch": 0.7130550033134526, "grad_norm": 0.032993465662002563, "learning_rate": 8.033460216433748e-06, "loss": 0.001, "step": 12912 }, { "epoch": 0.7131102275237464, "grad_norm": 2.698479175567627, "learning_rate": 8.030594081876708e-06, "loss": 0.057, "step": 12913 }, { "epoch": 0.7131654517340402, "grad_norm": 2.491380214691162, "learning_rate": 8.027728330255047e-06, "loss": 0.4182, "step": 12914 }, { "epoch": 0.713220675944334, "grad_norm": 5.418583869934082, "learning_rate": 8.02486296166044e-06, "loss": 1.0754, "step": 12915 }, { "epoch": 0.7132759001546278, "grad_norm": 0.12054511159658432, "learning_rate": 8.021997976184557e-06, "loss": 0.0031, "step": 12916 }, { "epoch": 0.7133311243649216, "grad_norm": 3.1076815128326416, "learning_rate": 8.019133373919052e-06, "loss": 0.3278, "step": 12917 }, { "epoch": 0.7133863485752153, "grad_norm": 0.10683396458625793, "learning_rate": 8.016269154955594e-06, "loss": 0.0029, "step": 12918 }, { "epoch": 0.7134415727855091, "grad_norm": 0.04207118600606918, "learning_rate": 8.013405319385788e-06, "loss": 0.0011, "step": 12919 }, { "epoch": 0.7134967969958029, "grad_norm": 4.201173782348633, "learning_rate": 8.010541867301273e-06, "loss": 0.7655, "step": 12920 }, { "epoch": 0.7135520212060967, "grad_norm": 0.7029271721839905, "learning_rate": 8.007678798793661e-06, "loss": 0.014, "step": 12921 }, { "epoch": 0.7136072454163905, "grad_norm": 0.167894646525383, "learning_rate": 8.004816113954543e-06, "loss": 0.004, "step": 12922 }, { "epoch": 0.7136624696266843, "grad_norm": 5.176792621612549, "learning_rate": 8.001953812875499e-06, "loss": 0.7587, "step": 12923 }, { "epoch": 0.7137176938369781, "grad_norm": 0.5155906081199646, "learning_rate": 7.999091895648117e-06, "loss": 0.1256, "step": 12924 }, { "epoch": 0.7137729180472719, "grad_norm": 0.03750065714120865, "learning_rate": 7.996230362363948e-06, "loss": 0.0008, "step": 12925 }, { "epoch": 0.7138281422575657, "grad_norm": 2.164994478225708, "learning_rate": 7.993369213114546e-06, "loss": 0.051, "step": 12926 }, { "epoch": 0.7138833664678595, "grad_norm": 1.2801765203475952, "learning_rate": 7.990508447991436e-06, "loss": 0.1498, "step": 12927 }, { "epoch": 0.7139385906781534, "grad_norm": 0.012845098972320557, "learning_rate": 7.987648067086164e-06, "loss": 0.0004, "step": 12928 }, { "epoch": 0.713993814888447, "grad_norm": 0.49036166071891785, "learning_rate": 7.984788070490215e-06, "loss": 0.0109, "step": 12929 }, { "epoch": 0.7140490390987408, "grad_norm": 0.4852670133113861, "learning_rate": 7.981928458295107e-06, "loss": 0.0119, "step": 12930 }, { "epoch": 0.7141042633090346, "grad_norm": 1.3954896926879883, "learning_rate": 7.979069230592322e-06, "loss": 0.034, "step": 12931 }, { "epoch": 0.7141594875193285, "grad_norm": 0.03751644492149353, "learning_rate": 7.976210387473335e-06, "loss": 0.0006, "step": 12932 }, { "epoch": 0.7142147117296223, "grad_norm": 0.7632366418838501, "learning_rate": 7.9733519290296e-06, "loss": 0.0224, "step": 12933 }, { "epoch": 0.7142699359399161, "grad_norm": 1.7905840873718262, "learning_rate": 7.97049385535259e-06, "loss": 0.3059, "step": 12934 }, { "epoch": 0.7143251601502099, "grad_norm": 0.6460147500038147, "learning_rate": 7.967636166533714e-06, "loss": 0.1085, "step": 12935 }, { "epoch": 0.7143803843605037, "grad_norm": 0.13695821166038513, "learning_rate": 7.96477886266442e-06, "loss": 0.0038, "step": 12936 }, { "epoch": 0.7144356085707975, "grad_norm": 2.447859287261963, "learning_rate": 7.961921943836111e-06, "loss": 0.0898, "step": 12937 }, { "epoch": 0.7144908327810913, "grad_norm": 0.11464673280715942, "learning_rate": 7.95906541014019e-06, "loss": 0.0026, "step": 12938 }, { "epoch": 0.7145460569913851, "grad_norm": 0.04414840787649155, "learning_rate": 7.956209261668047e-06, "loss": 0.001, "step": 12939 }, { "epoch": 0.7146012812016788, "grad_norm": 0.008243661373853683, "learning_rate": 7.953353498511047e-06, "loss": 0.0003, "step": 12940 }, { "epoch": 0.7146565054119726, "grad_norm": 2.1596884727478027, "learning_rate": 7.950498120760582e-06, "loss": 0.0974, "step": 12941 }, { "epoch": 0.7147117296222664, "grad_norm": 0.42343902587890625, "learning_rate": 7.947643128507967e-06, "loss": 0.0147, "step": 12942 }, { "epoch": 0.7147669538325602, "grad_norm": 0.009979926981031895, "learning_rate": 7.944788521844569e-06, "loss": 0.0003, "step": 12943 }, { "epoch": 0.714822178042854, "grad_norm": 0.04093277454376221, "learning_rate": 7.941934300861707e-06, "loss": 0.0011, "step": 12944 }, { "epoch": 0.7148774022531478, "grad_norm": 0.10344463586807251, "learning_rate": 7.939080465650693e-06, "loss": 0.002, "step": 12945 }, { "epoch": 0.7149326264634416, "grad_norm": 5.800797462463379, "learning_rate": 7.936227016302824e-06, "loss": 0.344, "step": 12946 }, { "epoch": 0.7149878506737354, "grad_norm": 4.050399303436279, "learning_rate": 7.933373952909405e-06, "loss": 0.203, "step": 12947 }, { "epoch": 0.7150430748840292, "grad_norm": 8.54288387298584, "learning_rate": 7.930521275561702e-06, "loss": 1.2328, "step": 12948 }, { "epoch": 0.715098299094323, "grad_norm": 0.16951517760753632, "learning_rate": 7.927668984350987e-06, "loss": 0.0054, "step": 12949 }, { "epoch": 0.7151535233046168, "grad_norm": 2.86053466796875, "learning_rate": 7.924817079368509e-06, "loss": 0.1675, "step": 12950 }, { "epoch": 0.7152087475149106, "grad_norm": 0.04264107346534729, "learning_rate": 7.921965560705508e-06, "loss": 0.0012, "step": 12951 }, { "epoch": 0.7152639717252043, "grad_norm": 1.546923041343689, "learning_rate": 7.919114428453207e-06, "loss": 0.0367, "step": 12952 }, { "epoch": 0.7153191959354981, "grad_norm": 0.6226464509963989, "learning_rate": 7.916263682702836e-06, "loss": 0.0179, "step": 12953 }, { "epoch": 0.7153744201457919, "grad_norm": 4.4173126220703125, "learning_rate": 7.91341332354559e-06, "loss": 0.1835, "step": 12954 }, { "epoch": 0.7154296443560857, "grad_norm": 2.109832763671875, "learning_rate": 7.91056335107266e-06, "loss": 0.1273, "step": 12955 }, { "epoch": 0.7154848685663795, "grad_norm": 2.2572505474090576, "learning_rate": 7.90771376537522e-06, "loss": 0.0468, "step": 12956 }, { "epoch": 0.7155400927766733, "grad_norm": 3.004127264022827, "learning_rate": 7.904864566544454e-06, "loss": 0.495, "step": 12957 }, { "epoch": 0.7155953169869671, "grad_norm": 0.40420475602149963, "learning_rate": 7.902015754671493e-06, "loss": 0.0124, "step": 12958 }, { "epoch": 0.7156505411972609, "grad_norm": 0.050080306828022, "learning_rate": 7.899167329847493e-06, "loss": 0.0012, "step": 12959 }, { "epoch": 0.7157057654075547, "grad_norm": 2.7756330966949463, "learning_rate": 7.896319292163581e-06, "loss": 0.62, "step": 12960 }, { "epoch": 0.7157609896178485, "grad_norm": 2.933966636657715, "learning_rate": 7.893471641710872e-06, "loss": 0.4833, "step": 12961 }, { "epoch": 0.7158162138281423, "grad_norm": 3.0227785110473633, "learning_rate": 7.890624378580465e-06, "loss": 0.6065, "step": 12962 }, { "epoch": 0.715871438038436, "grad_norm": 0.021666988730430603, "learning_rate": 7.887777502863465e-06, "loss": 0.0005, "step": 12963 }, { "epoch": 0.7159266622487298, "grad_norm": 0.02198977954685688, "learning_rate": 7.884931014650945e-06, "loss": 0.0006, "step": 12964 }, { "epoch": 0.7159818864590236, "grad_norm": 0.25406765937805176, "learning_rate": 7.88208491403397e-06, "loss": 0.0074, "step": 12965 }, { "epoch": 0.7160371106693174, "grad_norm": 2.941646099090576, "learning_rate": 7.87923920110359e-06, "loss": 0.4395, "step": 12966 }, { "epoch": 0.7160923348796112, "grad_norm": 0.07050544768571854, "learning_rate": 7.87639387595087e-06, "loss": 0.0021, "step": 12967 }, { "epoch": 0.716147559089905, "grad_norm": 0.4905407726764679, "learning_rate": 7.87354893866681e-06, "loss": 0.0138, "step": 12968 }, { "epoch": 0.7162027833001988, "grad_norm": 0.08933071047067642, "learning_rate": 7.870704389342447e-06, "loss": 0.0027, "step": 12969 }, { "epoch": 0.7162580075104926, "grad_norm": 0.8938410878181458, "learning_rate": 7.867860228068781e-06, "loss": 0.0299, "step": 12970 }, { "epoch": 0.7163132317207864, "grad_norm": 0.059011638164520264, "learning_rate": 7.865016454936809e-06, "loss": 0.0015, "step": 12971 }, { "epoch": 0.7163684559310802, "grad_norm": 1.3997095823287964, "learning_rate": 7.862173070037497e-06, "loss": 0.0562, "step": 12972 }, { "epoch": 0.716423680141374, "grad_norm": 5.396946430206299, "learning_rate": 7.859330073461838e-06, "loss": 1.3002, "step": 12973 }, { "epoch": 0.7164789043516677, "grad_norm": 2.7868175506591797, "learning_rate": 7.85648746530076e-06, "loss": 0.5805, "step": 12974 }, { "epoch": 0.7165341285619615, "grad_norm": 2.630481719970703, "learning_rate": 7.853645245645225e-06, "loss": 0.05, "step": 12975 }, { "epoch": 0.7165893527722553, "grad_norm": 0.1735193282365799, "learning_rate": 7.850803414586157e-06, "loss": 0.0047, "step": 12976 }, { "epoch": 0.7166445769825491, "grad_norm": 6.189390659332275, "learning_rate": 7.847961972214474e-06, "loss": 0.7944, "step": 12977 }, { "epoch": 0.7166998011928429, "grad_norm": 0.029383856803178787, "learning_rate": 7.845120918621079e-06, "loss": 0.0007, "step": 12978 }, { "epoch": 0.7167550254031367, "grad_norm": 0.05584938824176788, "learning_rate": 7.842280253896874e-06, "loss": 0.0012, "step": 12979 }, { "epoch": 0.7168102496134305, "grad_norm": 3.6296095848083496, "learning_rate": 7.839439978132738e-06, "loss": 0.5697, "step": 12980 }, { "epoch": 0.7168654738237243, "grad_norm": 4.337772369384766, "learning_rate": 7.836600091419533e-06, "loss": 0.5345, "step": 12981 }, { "epoch": 0.7169206980340181, "grad_norm": 0.0008329076808877289, "learning_rate": 7.833760593848115e-06, "loss": 0.0, "step": 12982 }, { "epoch": 0.716975922244312, "grad_norm": 4.719167709350586, "learning_rate": 7.830921485509342e-06, "loss": 0.8577, "step": 12983 }, { "epoch": 0.7170311464546058, "grad_norm": 0.5374695658683777, "learning_rate": 7.828082766494024e-06, "loss": 0.016, "step": 12984 }, { "epoch": 0.7170863706648994, "grad_norm": 0.43329259753227234, "learning_rate": 7.825244436892994e-06, "loss": 0.0068, "step": 12985 }, { "epoch": 0.7171415948751932, "grad_norm": 6.9168171882629395, "learning_rate": 7.822406496797058e-06, "loss": 1.5199, "step": 12986 }, { "epoch": 0.717196819085487, "grad_norm": 5.615001201629639, "learning_rate": 7.819568946297002e-06, "loss": 0.812, "step": 12987 }, { "epoch": 0.7172520432957809, "grad_norm": 0.35323095321655273, "learning_rate": 7.816731785483607e-06, "loss": 0.0064, "step": 12988 }, { "epoch": 0.7173072675060747, "grad_norm": 0.542797327041626, "learning_rate": 7.813895014447661e-06, "loss": 0.013, "step": 12989 }, { "epoch": 0.7173624917163685, "grad_norm": 0.6285386085510254, "learning_rate": 7.81105863327989e-06, "loss": 0.0137, "step": 12990 }, { "epoch": 0.7174177159266623, "grad_norm": 0.20002934336662292, "learning_rate": 7.808222642071062e-06, "loss": 0.0061, "step": 12991 }, { "epoch": 0.7174729401369561, "grad_norm": 0.06567545980215073, "learning_rate": 7.8053870409119e-06, "loss": 0.0019, "step": 12992 }, { "epoch": 0.7175281643472499, "grad_norm": 4.046887397766113, "learning_rate": 7.802551829893124e-06, "loss": 0.2381, "step": 12993 }, { "epoch": 0.7175833885575437, "grad_norm": 2.243342638015747, "learning_rate": 7.79971700910543e-06, "loss": 0.5823, "step": 12994 }, { "epoch": 0.7176386127678375, "grad_norm": 1.5084547996520996, "learning_rate": 7.79688257863953e-06, "loss": 0.1913, "step": 12995 }, { "epoch": 0.7176938369781312, "grad_norm": 3.0769102573394775, "learning_rate": 7.794048538586103e-06, "loss": 0.151, "step": 12996 }, { "epoch": 0.717749061188425, "grad_norm": 0.09567583352327347, "learning_rate": 7.791214889035801e-06, "loss": 0.0021, "step": 12997 }, { "epoch": 0.7178042853987188, "grad_norm": 0.10454824566841125, "learning_rate": 7.788381630079296e-06, "loss": 0.0028, "step": 12998 }, { "epoch": 0.7178595096090126, "grad_norm": 0.8479748964309692, "learning_rate": 7.785548761807226e-06, "loss": 0.0195, "step": 12999 }, { "epoch": 0.7179147338193064, "grad_norm": 1.1430872678756714, "learning_rate": 7.782716284310227e-06, "loss": 0.186, "step": 13000 }, { "epoch": 0.7179699580296002, "grad_norm": 3.204422950744629, "learning_rate": 7.779884197678909e-06, "loss": 0.4003, "step": 13001 }, { "epoch": 0.718025182239894, "grad_norm": 0.7093278169631958, "learning_rate": 7.77705250200389e-06, "loss": 0.0174, "step": 13002 }, { "epoch": 0.7180804064501878, "grad_norm": 0.249172180891037, "learning_rate": 7.774221197375758e-06, "loss": 0.005, "step": 13003 }, { "epoch": 0.7181356306604816, "grad_norm": 0.4580094516277313, "learning_rate": 7.771390283885095e-06, "loss": 0.0124, "step": 13004 }, { "epoch": 0.7181908548707754, "grad_norm": 0.9183892607688904, "learning_rate": 7.768559761622465e-06, "loss": 0.0388, "step": 13005 }, { "epoch": 0.7182460790810692, "grad_norm": 1.4945130348205566, "learning_rate": 7.765729630678442e-06, "loss": 0.0403, "step": 13006 }, { "epoch": 0.7183013032913629, "grad_norm": 0.5848990082740784, "learning_rate": 7.762899891143545e-06, "loss": 0.0101, "step": 13007 }, { "epoch": 0.7183565275016567, "grad_norm": 5.807216167449951, "learning_rate": 7.760070543108325e-06, "loss": 0.6547, "step": 13008 }, { "epoch": 0.7184117517119505, "grad_norm": 0.32384195923805237, "learning_rate": 7.757241586663291e-06, "loss": 0.0052, "step": 13009 }, { "epoch": 0.7184669759222443, "grad_norm": 0.1288653463125229, "learning_rate": 7.754413021898955e-06, "loss": 0.0036, "step": 13010 }, { "epoch": 0.7185222001325381, "grad_norm": 0.11857486516237259, "learning_rate": 7.7515848489058e-06, "loss": 0.0026, "step": 13011 }, { "epoch": 0.7185774243428319, "grad_norm": 3.7205824851989746, "learning_rate": 7.74875706777433e-06, "loss": 0.6304, "step": 13012 }, { "epoch": 0.7186326485531257, "grad_norm": 0.6939077973365784, "learning_rate": 7.745929678594985e-06, "loss": 0.0159, "step": 13013 }, { "epoch": 0.7186878727634195, "grad_norm": 0.22045329213142395, "learning_rate": 7.743102681458241e-06, "loss": 0.0072, "step": 13014 }, { "epoch": 0.7187430969737133, "grad_norm": 1.7930232286453247, "learning_rate": 7.740276076454538e-06, "loss": 0.0904, "step": 13015 }, { "epoch": 0.7187983211840071, "grad_norm": 0.24076126515865326, "learning_rate": 7.737449863674304e-06, "loss": 0.0034, "step": 13016 }, { "epoch": 0.7188535453943009, "grad_norm": 0.12854954600334167, "learning_rate": 7.734624043207953e-06, "loss": 0.0027, "step": 13017 }, { "epoch": 0.7189087696045946, "grad_norm": 5.476766109466553, "learning_rate": 7.731798615145903e-06, "loss": 0.4048, "step": 13018 }, { "epoch": 0.7189639938148884, "grad_norm": 4.923778533935547, "learning_rate": 7.72897357957854e-06, "loss": 0.554, "step": 13019 }, { "epoch": 0.7190192180251822, "grad_norm": 3.6418747901916504, "learning_rate": 7.72614893659625e-06, "loss": 0.629, "step": 13020 }, { "epoch": 0.719074442235476, "grad_norm": 3.5906896591186523, "learning_rate": 7.723324686289386e-06, "loss": 0.1231, "step": 13021 }, { "epoch": 0.7191296664457698, "grad_norm": 0.8486276268959045, "learning_rate": 7.720500828748332e-06, "loss": 0.0147, "step": 13022 }, { "epoch": 0.7191848906560636, "grad_norm": 3.8307738304138184, "learning_rate": 7.7176773640634e-06, "loss": 0.1806, "step": 13023 }, { "epoch": 0.7192401148663574, "grad_norm": 2.9639341831207275, "learning_rate": 7.714854292324943e-06, "loss": 0.2642, "step": 13024 }, { "epoch": 0.7192953390766512, "grad_norm": 0.05629073083400726, "learning_rate": 7.712031613623272e-06, "loss": 0.0022, "step": 13025 }, { "epoch": 0.719350563286945, "grad_norm": 1.8365139961242676, "learning_rate": 7.70920932804869e-06, "loss": 0.0556, "step": 13026 }, { "epoch": 0.7194057874972388, "grad_norm": 3.329381227493286, "learning_rate": 7.706387435691487e-06, "loss": 0.1665, "step": 13027 }, { "epoch": 0.7194610117075326, "grad_norm": 0.1704554557800293, "learning_rate": 7.703565936641955e-06, "loss": 0.0041, "step": 13028 }, { "epoch": 0.7195162359178264, "grad_norm": 2.9462428092956543, "learning_rate": 7.700744830990353e-06, "loss": 0.5046, "step": 13029 }, { "epoch": 0.7195714601281201, "grad_norm": 0.10416682064533234, "learning_rate": 7.69792411882694e-06, "loss": 0.0028, "step": 13030 }, { "epoch": 0.7196266843384139, "grad_norm": 1.6717054843902588, "learning_rate": 7.695103800241956e-06, "loss": 0.0949, "step": 13031 }, { "epoch": 0.7196819085487077, "grad_norm": 1.3649626970291138, "learning_rate": 7.692283875325633e-06, "loss": 0.0184, "step": 13032 }, { "epoch": 0.7197371327590015, "grad_norm": 3.501786470413208, "learning_rate": 7.68946434416818e-06, "loss": 0.4833, "step": 13033 }, { "epoch": 0.7197923569692953, "grad_norm": 0.32743486762046814, "learning_rate": 7.686645206859815e-06, "loss": 0.0104, "step": 13034 }, { "epoch": 0.7198475811795891, "grad_norm": 2.7489945888519287, "learning_rate": 7.683826463490727e-06, "loss": 0.3127, "step": 13035 }, { "epoch": 0.7199028053898829, "grad_norm": 1.4502099752426147, "learning_rate": 7.68100811415109e-06, "loss": 0.0588, "step": 13036 }, { "epoch": 0.7199580296001767, "grad_norm": 0.058363206684589386, "learning_rate": 7.678190158931068e-06, "loss": 0.0013, "step": 13037 }, { "epoch": 0.7200132538104705, "grad_norm": 0.010118003934621811, "learning_rate": 7.675372597920836e-06, "loss": 0.0004, "step": 13038 }, { "epoch": 0.7200684780207643, "grad_norm": 3.1420862674713135, "learning_rate": 7.67255543121051e-06, "loss": 0.1618, "step": 13039 }, { "epoch": 0.7201237022310581, "grad_norm": 0.0038752080872654915, "learning_rate": 7.669738658890234e-06, "loss": 0.0001, "step": 13040 }, { "epoch": 0.7201789264413518, "grad_norm": 1.01910400390625, "learning_rate": 7.666922281050119e-06, "loss": 0.1463, "step": 13041 }, { "epoch": 0.7202341506516456, "grad_norm": 1.7684831619262695, "learning_rate": 7.664106297780274e-06, "loss": 0.0673, "step": 13042 }, { "epoch": 0.7202893748619394, "grad_norm": 0.07150772213935852, "learning_rate": 7.661290709170781e-06, "loss": 0.0021, "step": 13043 }, { "epoch": 0.7203445990722332, "grad_norm": 2.9690568447113037, "learning_rate": 7.658475515311729e-06, "loss": 0.2239, "step": 13044 }, { "epoch": 0.720399823282527, "grad_norm": 0.049439508467912674, "learning_rate": 7.655660716293182e-06, "loss": 0.0017, "step": 13045 }, { "epoch": 0.7204550474928209, "grad_norm": 0.02708381600677967, "learning_rate": 7.652846312205194e-06, "loss": 0.0007, "step": 13046 }, { "epoch": 0.7205102717031147, "grad_norm": 1.3744560480117798, "learning_rate": 7.650032303137792e-06, "loss": 0.0228, "step": 13047 }, { "epoch": 0.7205654959134085, "grad_norm": 3.226489543914795, "learning_rate": 7.64721868918103e-06, "loss": 0.3876, "step": 13048 }, { "epoch": 0.7206207201237023, "grad_norm": 3.46012282371521, "learning_rate": 7.644405470424895e-06, "loss": 0.6982, "step": 13049 }, { "epoch": 0.7206759443339961, "grad_norm": 0.08940986543893814, "learning_rate": 7.641592646959413e-06, "loss": 0.0015, "step": 13050 }, { "epoch": 0.7207311685442899, "grad_norm": 2.236004590988159, "learning_rate": 7.638780218874565e-06, "loss": 0.2936, "step": 13051 }, { "epoch": 0.7207863927545836, "grad_norm": 4.026935577392578, "learning_rate": 7.635968186260324e-06, "loss": 1.0678, "step": 13052 }, { "epoch": 0.7208416169648774, "grad_norm": 0.07661423087120056, "learning_rate": 7.633156549206657e-06, "loss": 0.0018, "step": 13053 }, { "epoch": 0.7208968411751712, "grad_norm": 0.08636220544576645, "learning_rate": 7.630345307803533e-06, "loss": 0.0034, "step": 13054 }, { "epoch": 0.720952065385465, "grad_norm": 0.022095154970884323, "learning_rate": 7.627534462140862e-06, "loss": 0.0005, "step": 13055 }, { "epoch": 0.7210072895957588, "grad_norm": 2.7016806602478027, "learning_rate": 7.624724012308593e-06, "loss": 0.4684, "step": 13056 }, { "epoch": 0.7210625138060526, "grad_norm": 1.99494206905365, "learning_rate": 7.6219139583966366e-06, "loss": 0.0482, "step": 13057 }, { "epoch": 0.7211177380163464, "grad_norm": 0.1262548714876175, "learning_rate": 7.619104300494889e-06, "loss": 0.0039, "step": 13058 }, { "epoch": 0.7211729622266402, "grad_norm": 0.14877760410308838, "learning_rate": 7.61629503869324e-06, "loss": 0.0045, "step": 13059 }, { "epoch": 0.721228186436934, "grad_norm": 2.852961540222168, "learning_rate": 7.613486173081563e-06, "loss": 0.5808, "step": 13060 }, { "epoch": 0.7212834106472278, "grad_norm": 0.0376080684363842, "learning_rate": 7.61067770374974e-06, "loss": 0.0008, "step": 13061 }, { "epoch": 0.7213386348575216, "grad_norm": 2.225196599960327, "learning_rate": 7.607869630787595e-06, "loss": 0.1101, "step": 13062 }, { "epoch": 0.7213938590678153, "grad_norm": 4.046980857849121, "learning_rate": 7.605061954284983e-06, "loss": 0.5224, "step": 13063 }, { "epoch": 0.7214490832781091, "grad_norm": 3.975714683532715, "learning_rate": 7.602254674331728e-06, "loss": 0.0635, "step": 13064 }, { "epoch": 0.7215043074884029, "grad_norm": 0.14808496832847595, "learning_rate": 7.59944779101764e-06, "loss": 0.0039, "step": 13065 }, { "epoch": 0.7215595316986967, "grad_norm": 1.6812827587127686, "learning_rate": 7.596641304432515e-06, "loss": 0.2279, "step": 13066 }, { "epoch": 0.7216147559089905, "grad_norm": 0.20601579546928406, "learning_rate": 7.593835214666152e-06, "loss": 0.0049, "step": 13067 }, { "epoch": 0.7216699801192843, "grad_norm": 1.919692039489746, "learning_rate": 7.591029521808317e-06, "loss": 0.0243, "step": 13068 }, { "epoch": 0.7217252043295781, "grad_norm": 0.006144477054476738, "learning_rate": 7.588224225948777e-06, "loss": 0.0002, "step": 13069 }, { "epoch": 0.7217804285398719, "grad_norm": 0.006949261762201786, "learning_rate": 7.585419327177277e-06, "loss": 0.0002, "step": 13070 }, { "epoch": 0.7218356527501657, "grad_norm": 3.642347574234009, "learning_rate": 7.5826148255835565e-06, "loss": 0.5124, "step": 13071 }, { "epoch": 0.7218908769604595, "grad_norm": 0.08754219114780426, "learning_rate": 7.57981072125733e-06, "loss": 0.0025, "step": 13072 }, { "epoch": 0.7219461011707533, "grad_norm": 0.5798311829566956, "learning_rate": 7.5770070142883265e-06, "loss": 0.0139, "step": 13073 }, { "epoch": 0.722001325381047, "grad_norm": 2.654876470565796, "learning_rate": 7.574203704766235e-06, "loss": 0.0413, "step": 13074 }, { "epoch": 0.7220565495913408, "grad_norm": 3.547168016433716, "learning_rate": 7.571400792780739e-06, "loss": 0.6031, "step": 13075 }, { "epoch": 0.7221117738016346, "grad_norm": 6.728883266448975, "learning_rate": 7.568598278421509e-06, "loss": 0.4415, "step": 13076 }, { "epoch": 0.7221669980119284, "grad_norm": 0.10974255949258804, "learning_rate": 7.565796161778225e-06, "loss": 0.0024, "step": 13077 }, { "epoch": 0.7222222222222222, "grad_norm": 3.3135035037994385, "learning_rate": 7.562994442940506e-06, "loss": 0.8698, "step": 13078 }, { "epoch": 0.722277446432516, "grad_norm": 0.04280015826225281, "learning_rate": 7.560193121998007e-06, "loss": 0.0012, "step": 13079 }, { "epoch": 0.7223326706428098, "grad_norm": 0.08234874904155731, "learning_rate": 7.557392199040348e-06, "loss": 0.0017, "step": 13080 }, { "epoch": 0.7223878948531036, "grad_norm": 4.176209449768066, "learning_rate": 7.554591674157132e-06, "loss": 0.7257, "step": 13081 }, { "epoch": 0.7224431190633974, "grad_norm": 0.10676360875368118, "learning_rate": 7.551791547437954e-06, "loss": 0.0037, "step": 13082 }, { "epoch": 0.7224983432736912, "grad_norm": 1.4939666986465454, "learning_rate": 7.548991818972409e-06, "loss": 0.0796, "step": 13083 }, { "epoch": 0.722553567483985, "grad_norm": 2.6178245544433594, "learning_rate": 7.546192488850062e-06, "loss": 0.1545, "step": 13084 }, { "epoch": 0.7226087916942787, "grad_norm": 1.6615471839904785, "learning_rate": 7.54339355716047e-06, "loss": 0.0579, "step": 13085 }, { "epoch": 0.7226640159045725, "grad_norm": 0.022853517904877663, "learning_rate": 7.5405950239931755e-06, "loss": 0.0005, "step": 13086 }, { "epoch": 0.7227192401148663, "grad_norm": 0.0752810388803482, "learning_rate": 7.5377968894377315e-06, "loss": 0.0023, "step": 13087 }, { "epoch": 0.7227744643251601, "grad_norm": 0.018659617751836777, "learning_rate": 7.5349991535836265e-06, "loss": 0.0006, "step": 13088 }, { "epoch": 0.7228296885354539, "grad_norm": 0.022837644442915916, "learning_rate": 7.5322018165203945e-06, "loss": 0.0004, "step": 13089 }, { "epoch": 0.7228849127457477, "grad_norm": 4.917269229888916, "learning_rate": 7.5294048783375185e-06, "loss": 0.9053, "step": 13090 }, { "epoch": 0.7229401369560415, "grad_norm": 0.009451784193515778, "learning_rate": 7.526608339124484e-06, "loss": 0.0003, "step": 13091 }, { "epoch": 0.7229953611663353, "grad_norm": 1.2920260429382324, "learning_rate": 7.5238121989707525e-06, "loss": 0.0618, "step": 13092 }, { "epoch": 0.7230505853766291, "grad_norm": 0.0052405172027647495, "learning_rate": 7.521016457965799e-06, "loss": 0.0001, "step": 13093 }, { "epoch": 0.7231058095869229, "grad_norm": 0.9987270832061768, "learning_rate": 7.518221116199043e-06, "loss": 0.0259, "step": 13094 }, { "epoch": 0.7231610337972167, "grad_norm": 3.3052265644073486, "learning_rate": 7.515426173759934e-06, "loss": 0.891, "step": 13095 }, { "epoch": 0.7232162580075104, "grad_norm": 0.904097855091095, "learning_rate": 7.512631630737883e-06, "loss": 0.026, "step": 13096 }, { "epoch": 0.7232714822178042, "grad_norm": 0.7298281788825989, "learning_rate": 7.509837487222296e-06, "loss": 0.0134, "step": 13097 }, { "epoch": 0.723326706428098, "grad_norm": 5.527271747589111, "learning_rate": 7.5070437433025604e-06, "loss": 0.7677, "step": 13098 }, { "epoch": 0.7233819306383918, "grad_norm": 0.34771549701690674, "learning_rate": 7.504250399068067e-06, "loss": 0.0081, "step": 13099 }, { "epoch": 0.7234371548486856, "grad_norm": 0.01228648517280817, "learning_rate": 7.5014574546081766e-06, "loss": 0.0003, "step": 13100 }, { "epoch": 0.7234923790589795, "grad_norm": 0.08062968403100967, "learning_rate": 7.498664910012243e-06, "loss": 0.0023, "step": 13101 }, { "epoch": 0.7235476032692733, "grad_norm": 3.8464467525482178, "learning_rate": 7.495872765369605e-06, "loss": 1.1568, "step": 13102 }, { "epoch": 0.7236028274795671, "grad_norm": 2.9286367893218994, "learning_rate": 7.493081020769606e-06, "loss": 0.1404, "step": 13103 }, { "epoch": 0.7236580516898609, "grad_norm": 0.18262694776058197, "learning_rate": 7.490289676301539e-06, "loss": 0.0022, "step": 13104 }, { "epoch": 0.7237132759001547, "grad_norm": 4.132158279418945, "learning_rate": 7.487498732054725e-06, "loss": 0.8513, "step": 13105 }, { "epoch": 0.7237685001104485, "grad_norm": 0.02210249938070774, "learning_rate": 7.484708188118448e-06, "loss": 0.0005, "step": 13106 }, { "epoch": 0.7238237243207423, "grad_norm": 2.9934470653533936, "learning_rate": 7.481918044581984e-06, "loss": 0.0977, "step": 13107 }, { "epoch": 0.723878948531036, "grad_norm": 3.632636070251465, "learning_rate": 7.479128301534595e-06, "loss": 0.39, "step": 13108 }, { "epoch": 0.7239341727413298, "grad_norm": 3.6275038719177246, "learning_rate": 7.476338959065548e-06, "loss": 0.0425, "step": 13109 }, { "epoch": 0.7239893969516236, "grad_norm": 4.47600793838501, "learning_rate": 7.473550017264059e-06, "loss": 1.3974, "step": 13110 }, { "epoch": 0.7240446211619174, "grad_norm": 0.21574652194976807, "learning_rate": 7.470761476219372e-06, "loss": 0.0041, "step": 13111 }, { "epoch": 0.7240998453722112, "grad_norm": 4.1403303146362305, "learning_rate": 7.467973336020695e-06, "loss": 0.3332, "step": 13112 }, { "epoch": 0.724155069582505, "grad_norm": 4.00830078125, "learning_rate": 7.46518559675723e-06, "loss": 0.2125, "step": 13113 }, { "epoch": 0.7242102937927988, "grad_norm": 0.019588319584727287, "learning_rate": 7.462398258518153e-06, "loss": 0.0004, "step": 13114 }, { "epoch": 0.7242655180030926, "grad_norm": 1.9094946384429932, "learning_rate": 7.459611321392657e-06, "loss": 0.3554, "step": 13115 }, { "epoch": 0.7243207422133864, "grad_norm": 0.3372149169445038, "learning_rate": 7.4568247854699025e-06, "loss": 0.0109, "step": 13116 }, { "epoch": 0.7243759664236802, "grad_norm": 1.1988396644592285, "learning_rate": 7.454038650839017e-06, "loss": 0.0421, "step": 13117 }, { "epoch": 0.724431190633974, "grad_norm": 0.029201865196228027, "learning_rate": 7.45125291758916e-06, "loss": 0.0009, "step": 13118 }, { "epoch": 0.7244864148442677, "grad_norm": 0.07958155125379562, "learning_rate": 7.448467585809447e-06, "loss": 0.0021, "step": 13119 }, { "epoch": 0.7245416390545615, "grad_norm": 6.1797590255737305, "learning_rate": 7.445682655588989e-06, "loss": 0.6101, "step": 13120 }, { "epoch": 0.7245968632648553, "grad_norm": 5.108695030212402, "learning_rate": 7.4428981270168754e-06, "loss": 0.7296, "step": 13121 }, { "epoch": 0.7246520874751491, "grad_norm": 0.304566353559494, "learning_rate": 7.440114000182206e-06, "loss": 0.0061, "step": 13122 }, { "epoch": 0.7247073116854429, "grad_norm": 3.064849853515625, "learning_rate": 7.437330275174046e-06, "loss": 0.0967, "step": 13123 }, { "epoch": 0.7247625358957367, "grad_norm": 0.01669745333492756, "learning_rate": 7.434546952081456e-06, "loss": 0.0005, "step": 13124 }, { "epoch": 0.7248177601060305, "grad_norm": 4.78464937210083, "learning_rate": 7.431764030993474e-06, "loss": 0.3422, "step": 13125 }, { "epoch": 0.7248729843163243, "grad_norm": 0.6705039739608765, "learning_rate": 7.428981511999154e-06, "loss": 0.0179, "step": 13126 }, { "epoch": 0.7249282085266181, "grad_norm": 0.053031329065561295, "learning_rate": 7.42619939518749e-06, "loss": 0.0012, "step": 13127 }, { "epoch": 0.7249834327369119, "grad_norm": 2.4449970722198486, "learning_rate": 7.423417680647509e-06, "loss": 0.0943, "step": 13128 }, { "epoch": 0.7250386569472057, "grad_norm": 0.0270705483853817, "learning_rate": 7.420636368468201e-06, "loss": 0.0007, "step": 13129 }, { "epoch": 0.7250938811574994, "grad_norm": 0.2854921817779541, "learning_rate": 7.41785545873855e-06, "loss": 0.0029, "step": 13130 }, { "epoch": 0.7251491053677932, "grad_norm": 2.987116813659668, "learning_rate": 7.415074951547514e-06, "loss": 0.742, "step": 13131 }, { "epoch": 0.725204329578087, "grad_norm": 0.01603713631629944, "learning_rate": 7.412294846984071e-06, "loss": 0.0006, "step": 13132 }, { "epoch": 0.7252595537883808, "grad_norm": 0.9237675666809082, "learning_rate": 7.409515145137138e-06, "loss": 0.0203, "step": 13133 }, { "epoch": 0.7253147779986746, "grad_norm": 0.19566944241523743, "learning_rate": 7.406735846095668e-06, "loss": 0.0055, "step": 13134 }, { "epoch": 0.7253700022089684, "grad_norm": 4.01544189453125, "learning_rate": 7.403956949948565e-06, "loss": 0.5884, "step": 13135 }, { "epoch": 0.7254252264192622, "grad_norm": 1.7369396686553955, "learning_rate": 7.401178456784743e-06, "loss": 0.1505, "step": 13136 }, { "epoch": 0.725480450629556, "grad_norm": 0.02571786381304264, "learning_rate": 7.398400366693081e-06, "loss": 0.0007, "step": 13137 }, { "epoch": 0.7255356748398498, "grad_norm": 1.6806304454803467, "learning_rate": 7.395622679762473e-06, "loss": 0.3679, "step": 13138 }, { "epoch": 0.7255908990501436, "grad_norm": 3.411060094833374, "learning_rate": 7.392845396081778e-06, "loss": 0.1431, "step": 13139 }, { "epoch": 0.7256461232604374, "grad_norm": 0.14020425081253052, "learning_rate": 7.390068515739852e-06, "loss": 0.0034, "step": 13140 }, { "epoch": 0.7257013474707311, "grad_norm": 1.8262273073196411, "learning_rate": 7.387292038825524e-06, "loss": 0.1667, "step": 13141 }, { "epoch": 0.7257565716810249, "grad_norm": 0.04769299551844597, "learning_rate": 7.384515965427645e-06, "loss": 0.0016, "step": 13142 }, { "epoch": 0.7258117958913187, "grad_norm": 0.08560535311698914, "learning_rate": 7.381740295635e-06, "loss": 0.0023, "step": 13143 }, { "epoch": 0.7258670201016125, "grad_norm": 1.6141486167907715, "learning_rate": 7.378965029536416e-06, "loss": 0.051, "step": 13144 }, { "epoch": 0.7259222443119063, "grad_norm": 0.09189123660326004, "learning_rate": 7.376190167220667e-06, "loss": 0.0027, "step": 13145 }, { "epoch": 0.7259774685222001, "grad_norm": 0.2462126910686493, "learning_rate": 7.373415708776535e-06, "loss": 0.0079, "step": 13146 }, { "epoch": 0.7260326927324939, "grad_norm": 0.02571476809680462, "learning_rate": 7.370641654292774e-06, "loss": 0.0009, "step": 13147 }, { "epoch": 0.7260879169427877, "grad_norm": 11.035247802734375, "learning_rate": 7.367868003858147e-06, "loss": 0.5295, "step": 13148 }, { "epoch": 0.7261431411530815, "grad_norm": 3.766847848892212, "learning_rate": 7.365094757561384e-06, "loss": 0.1842, "step": 13149 }, { "epoch": 0.7261983653633753, "grad_norm": 0.11978433281183243, "learning_rate": 7.36232191549121e-06, "loss": 0.0029, "step": 13150 }, { "epoch": 0.7262535895736691, "grad_norm": 0.6591487526893616, "learning_rate": 7.359549477736339e-06, "loss": 0.1054, "step": 13151 }, { "epoch": 0.7263088137839628, "grad_norm": 0.0774260088801384, "learning_rate": 7.356777444385461e-06, "loss": 0.001, "step": 13152 }, { "epoch": 0.7263640379942566, "grad_norm": 2.883112907409668, "learning_rate": 7.3540058155272634e-06, "loss": 0.6856, "step": 13153 }, { "epoch": 0.7264192622045504, "grad_norm": 0.20941835641860962, "learning_rate": 7.351234591250424e-06, "loss": 0.0046, "step": 13154 }, { "epoch": 0.7264744864148442, "grad_norm": 4.499423980712891, "learning_rate": 7.348463771643604e-06, "loss": 0.9982, "step": 13155 }, { "epoch": 0.726529710625138, "grad_norm": 0.7456168532371521, "learning_rate": 7.3456933567954426e-06, "loss": 0.02, "step": 13156 }, { "epoch": 0.7265849348354319, "grad_norm": 0.009416512213647366, "learning_rate": 7.3429233467945705e-06, "loss": 0.0003, "step": 13157 }, { "epoch": 0.7266401590457257, "grad_norm": 0.01723504066467285, "learning_rate": 7.340153741729625e-06, "loss": 0.0004, "step": 13158 }, { "epoch": 0.7266953832560195, "grad_norm": 0.11678583920001984, "learning_rate": 7.33738454168919e-06, "loss": 0.0024, "step": 13159 }, { "epoch": 0.7267506074663133, "grad_norm": 3.4093892574310303, "learning_rate": 7.334615746761879e-06, "loss": 0.2396, "step": 13160 }, { "epoch": 0.7268058316766071, "grad_norm": 0.16608645021915436, "learning_rate": 7.331847357036268e-06, "loss": 0.0058, "step": 13161 }, { "epoch": 0.7268610558869009, "grad_norm": 0.017920345067977905, "learning_rate": 7.329079372600925e-06, "loss": 0.0005, "step": 13162 }, { "epoch": 0.7269162800971946, "grad_norm": 0.026403727009892464, "learning_rate": 7.326311793544396e-06, "loss": 0.0005, "step": 13163 }, { "epoch": 0.7269715043074884, "grad_norm": 2.8038642406463623, "learning_rate": 7.323544619955243e-06, "loss": 0.2236, "step": 13164 }, { "epoch": 0.7270267285177822, "grad_norm": 3.656754732131958, "learning_rate": 7.320777851921983e-06, "loss": 0.7524, "step": 13165 }, { "epoch": 0.727081952728076, "grad_norm": 1.904571294784546, "learning_rate": 7.318011489533137e-06, "loss": 0.031, "step": 13166 }, { "epoch": 0.7271371769383698, "grad_norm": 1.9022310972213745, "learning_rate": 7.3152455328771995e-06, "loss": 0.1796, "step": 13167 }, { "epoch": 0.7271924011486636, "grad_norm": 0.7095900177955627, "learning_rate": 7.3124799820426865e-06, "loss": 0.0097, "step": 13168 }, { "epoch": 0.7272476253589574, "grad_norm": 1.37738037109375, "learning_rate": 7.309714837118041e-06, "loss": 0.0692, "step": 13169 }, { "epoch": 0.7273028495692512, "grad_norm": 5.235723495483398, "learning_rate": 7.306950098191754e-06, "loss": 0.5231, "step": 13170 }, { "epoch": 0.727358073779545, "grad_norm": 4.892983913421631, "learning_rate": 7.304185765352269e-06, "loss": 1.1838, "step": 13171 }, { "epoch": 0.7274132979898388, "grad_norm": 2.538154125213623, "learning_rate": 7.301421838688025e-06, "loss": 0.232, "step": 13172 }, { "epoch": 0.7274685222001326, "grad_norm": 3.2249505519866943, "learning_rate": 7.29865831828744e-06, "loss": 0.671, "step": 13173 }, { "epoch": 0.7275237464104264, "grad_norm": 2.683084487915039, "learning_rate": 7.295895204238948e-06, "loss": 0.1323, "step": 13174 }, { "epoch": 0.7275789706207201, "grad_norm": 0.0022061157505959272, "learning_rate": 7.293132496630923e-06, "loss": 0.0001, "step": 13175 }, { "epoch": 0.7276341948310139, "grad_norm": 0.04200707748532295, "learning_rate": 7.29037019555177e-06, "loss": 0.0011, "step": 13176 }, { "epoch": 0.7276894190413077, "grad_norm": 1.484743595123291, "learning_rate": 7.2876083010898565e-06, "loss": 0.0408, "step": 13177 }, { "epoch": 0.7277446432516015, "grad_norm": 4.865283966064453, "learning_rate": 7.284846813333546e-06, "loss": 0.7396, "step": 13178 }, { "epoch": 0.7277998674618953, "grad_norm": 0.03671855852007866, "learning_rate": 7.282085732371182e-06, "loss": 0.001, "step": 13179 }, { "epoch": 0.7278550916721891, "grad_norm": 0.48707225918769836, "learning_rate": 7.279325058291098e-06, "loss": 0.0135, "step": 13180 }, { "epoch": 0.7279103158824829, "grad_norm": 1.0252833366394043, "learning_rate": 7.276564791181631e-06, "loss": 0.1488, "step": 13181 }, { "epoch": 0.7279655400927767, "grad_norm": 0.23613613843917847, "learning_rate": 7.2738049311310656e-06, "loss": 0.0063, "step": 13182 }, { "epoch": 0.7280207643030705, "grad_norm": 0.037992216646671295, "learning_rate": 7.271045478227716e-06, "loss": 0.001, "step": 13183 }, { "epoch": 0.7280759885133643, "grad_norm": 1.7431024312973022, "learning_rate": 7.268286432559859e-06, "loss": 0.1879, "step": 13184 }, { "epoch": 0.7281312127236581, "grad_norm": 3.1898605823516846, "learning_rate": 7.265527794215767e-06, "loss": 0.7052, "step": 13185 }, { "epoch": 0.7281864369339518, "grad_norm": 1.7812424898147583, "learning_rate": 7.262769563283685e-06, "loss": 0.1586, "step": 13186 }, { "epoch": 0.7282416611442456, "grad_norm": 0.09914499521255493, "learning_rate": 7.260011739851876e-06, "loss": 0.0017, "step": 13187 }, { "epoch": 0.7282968853545394, "grad_norm": 4.628076076507568, "learning_rate": 7.257254324008558e-06, "loss": 0.9974, "step": 13188 }, { "epoch": 0.7283521095648332, "grad_norm": 3.592576503753662, "learning_rate": 7.254497315841951e-06, "loss": 0.5244, "step": 13189 }, { "epoch": 0.728407333775127, "grad_norm": 0.02088320627808571, "learning_rate": 7.2517407154402606e-06, "loss": 0.0006, "step": 13190 }, { "epoch": 0.7284625579854208, "grad_norm": 0.014008601196110249, "learning_rate": 7.248984522891676e-06, "loss": 0.0004, "step": 13191 }, { "epoch": 0.7285177821957146, "grad_norm": 0.022879289463162422, "learning_rate": 7.246228738284371e-06, "loss": 0.0006, "step": 13192 }, { "epoch": 0.7285730064060084, "grad_norm": 2.8285694122314453, "learning_rate": 7.243473361706526e-06, "loss": 0.4349, "step": 13193 }, { "epoch": 0.7286282306163022, "grad_norm": 1.721948504447937, "learning_rate": 7.240718393246282e-06, "loss": 0.0849, "step": 13194 }, { "epoch": 0.728683454826596, "grad_norm": 1.3878995180130005, "learning_rate": 7.237963832991781e-06, "loss": 0.0515, "step": 13195 }, { "epoch": 0.7287386790368898, "grad_norm": 0.05071205273270607, "learning_rate": 7.235209681031141e-06, "loss": 0.0018, "step": 13196 }, { "epoch": 0.7287939032471835, "grad_norm": 0.5069336891174316, "learning_rate": 7.232455937452498e-06, "loss": 0.0094, "step": 13197 }, { "epoch": 0.7288491274574773, "grad_norm": 0.03590533882379532, "learning_rate": 7.2297026023439245e-06, "loss": 0.0012, "step": 13198 }, { "epoch": 0.7289043516677711, "grad_norm": 0.1530943363904953, "learning_rate": 7.226949675793527e-06, "loss": 0.0037, "step": 13199 }, { "epoch": 0.7289595758780649, "grad_norm": 0.04602455347776413, "learning_rate": 7.22419715788937e-06, "loss": 0.0012, "step": 13200 }, { "epoch": 0.7290148000883587, "grad_norm": 0.46765485405921936, "learning_rate": 7.22144504871952e-06, "loss": 0.0033, "step": 13201 }, { "epoch": 0.7290700242986525, "grad_norm": 0.560819685459137, "learning_rate": 7.218693348372013e-06, "loss": 0.1324, "step": 13202 }, { "epoch": 0.7291252485089463, "grad_norm": 2.6433730125427246, "learning_rate": 7.215942056934899e-06, "loss": 0.1485, "step": 13203 }, { "epoch": 0.7291804727192401, "grad_norm": 0.025415800511837006, "learning_rate": 7.213191174496195e-06, "loss": 0.0006, "step": 13204 }, { "epoch": 0.7292356969295339, "grad_norm": 0.022708946838974953, "learning_rate": 7.210440701143906e-06, "loss": 0.0006, "step": 13205 }, { "epoch": 0.7292909211398277, "grad_norm": 2.7013018131256104, "learning_rate": 7.207690636966025e-06, "loss": 0.1723, "step": 13206 }, { "epoch": 0.7293461453501215, "grad_norm": 0.6514377593994141, "learning_rate": 7.20494098205055e-06, "loss": 0.0186, "step": 13207 }, { "epoch": 0.7294013695604152, "grad_norm": 2.3831827640533447, "learning_rate": 7.202191736485424e-06, "loss": 0.1204, "step": 13208 }, { "epoch": 0.729456593770709, "grad_norm": 0.05491485074162483, "learning_rate": 7.199442900358629e-06, "loss": 0.0013, "step": 13209 }, { "epoch": 0.7295118179810028, "grad_norm": 0.20667098462581635, "learning_rate": 7.196694473758094e-06, "loss": 0.007, "step": 13210 }, { "epoch": 0.7295670421912966, "grad_norm": 8.662239074707031, "learning_rate": 7.193946456771752e-06, "loss": 0.3969, "step": 13211 }, { "epoch": 0.7296222664015904, "grad_norm": 0.1414075791835785, "learning_rate": 7.191198849487515e-06, "loss": 0.0045, "step": 13212 }, { "epoch": 0.7296774906118842, "grad_norm": 0.8889639973640442, "learning_rate": 7.1884516519933045e-06, "loss": 0.0258, "step": 13213 }, { "epoch": 0.729732714822178, "grad_norm": 0.4653243124485016, "learning_rate": 7.185704864376986e-06, "loss": 0.0162, "step": 13214 }, { "epoch": 0.7297879390324719, "grad_norm": 0.3938950002193451, "learning_rate": 7.182958486726457e-06, "loss": 0.0144, "step": 13215 }, { "epoch": 0.7298431632427657, "grad_norm": 4.37877082824707, "learning_rate": 7.180212519129572e-06, "loss": 0.897, "step": 13216 }, { "epoch": 0.7298983874530595, "grad_norm": 3.6902008056640625, "learning_rate": 7.177466961674187e-06, "loss": 0.4049, "step": 13217 }, { "epoch": 0.7299536116633533, "grad_norm": 2.9227778911590576, "learning_rate": 7.174721814448129e-06, "loss": 0.6639, "step": 13218 }, { "epoch": 0.730008835873647, "grad_norm": 1.1622859239578247, "learning_rate": 7.1719770775392405e-06, "loss": 0.0292, "step": 13219 }, { "epoch": 0.7300640600839408, "grad_norm": 5.410101413726807, "learning_rate": 7.1692327510353245e-06, "loss": 0.4277, "step": 13220 }, { "epoch": 0.7301192842942346, "grad_norm": 0.007442296948283911, "learning_rate": 7.166488835024181e-06, "loss": 0.0002, "step": 13221 }, { "epoch": 0.7301745085045284, "grad_norm": 0.536767303943634, "learning_rate": 7.163745329593588e-06, "loss": 0.0083, "step": 13222 }, { "epoch": 0.7302297327148222, "grad_norm": 0.7022016644477844, "learning_rate": 7.161002234831338e-06, "loss": 0.0169, "step": 13223 }, { "epoch": 0.730284956925116, "grad_norm": 6.003079414367676, "learning_rate": 7.158259550825164e-06, "loss": 1.1876, "step": 13224 }, { "epoch": 0.7303401811354098, "grad_norm": 0.16567888855934143, "learning_rate": 7.155517277662833e-06, "loss": 0.0038, "step": 13225 }, { "epoch": 0.7303954053457036, "grad_norm": 0.1254855990409851, "learning_rate": 7.152775415432071e-06, "loss": 0.0034, "step": 13226 }, { "epoch": 0.7304506295559974, "grad_norm": 0.423111230134964, "learning_rate": 7.150033964220597e-06, "loss": 0.0102, "step": 13227 }, { "epoch": 0.7305058537662912, "grad_norm": 0.11510691046714783, "learning_rate": 7.147292924116114e-06, "loss": 0.0038, "step": 13228 }, { "epoch": 0.730561077976585, "grad_norm": 3.2013890743255615, "learning_rate": 7.144552295206333e-06, "loss": 0.287, "step": 13229 }, { "epoch": 0.7306163021868787, "grad_norm": 4.104191303253174, "learning_rate": 7.141812077578907e-06, "loss": 0.4723, "step": 13230 }, { "epoch": 0.7306715263971725, "grad_norm": 2.859830617904663, "learning_rate": 7.139072271321525e-06, "loss": 0.2212, "step": 13231 }, { "epoch": 0.7307267506074663, "grad_norm": 0.22310122847557068, "learning_rate": 7.136332876521837e-06, "loss": 0.0056, "step": 13232 }, { "epoch": 0.7307819748177601, "grad_norm": 0.11695192754268646, "learning_rate": 7.133593893267479e-06, "loss": 0.0032, "step": 13233 }, { "epoch": 0.7308371990280539, "grad_norm": 0.13494248688220978, "learning_rate": 7.130855321646075e-06, "loss": 0.0037, "step": 13234 }, { "epoch": 0.7308924232383477, "grad_norm": 0.008964220993220806, "learning_rate": 7.128117161745254e-06, "loss": 0.0002, "step": 13235 }, { "epoch": 0.7309476474486415, "grad_norm": 3.4670376777648926, "learning_rate": 7.125379413652615e-06, "loss": 0.0857, "step": 13236 }, { "epoch": 0.7310028716589353, "grad_norm": 2.054269313812256, "learning_rate": 7.12264207745573e-06, "loss": 0.04, "step": 13237 }, { "epoch": 0.7310580958692291, "grad_norm": 1.075007677078247, "learning_rate": 7.11990515324219e-06, "loss": 0.0258, "step": 13238 }, { "epoch": 0.7311133200795229, "grad_norm": 0.35959821939468384, "learning_rate": 7.117168641099552e-06, "loss": 0.0047, "step": 13239 }, { "epoch": 0.7311685442898167, "grad_norm": 1.6545249223709106, "learning_rate": 7.114432541115366e-06, "loss": 0.0468, "step": 13240 }, { "epoch": 0.7312237685001104, "grad_norm": 3.1562063694000244, "learning_rate": 7.111696853377159e-06, "loss": 0.2951, "step": 13241 }, { "epoch": 0.7312789927104042, "grad_norm": 0.06588689982891083, "learning_rate": 7.108961577972468e-06, "loss": 0.0009, "step": 13242 }, { "epoch": 0.731334216920698, "grad_norm": 0.08579917997121811, "learning_rate": 7.106226714988796e-06, "loss": 0.002, "step": 13243 }, { "epoch": 0.7313894411309918, "grad_norm": 0.09313049167394638, "learning_rate": 7.103492264513636e-06, "loss": 0.0026, "step": 13244 }, { "epoch": 0.7314446653412856, "grad_norm": 3.8132190704345703, "learning_rate": 7.10075822663447e-06, "loss": 0.4372, "step": 13245 }, { "epoch": 0.7314998895515794, "grad_norm": 0.0123796621337533, "learning_rate": 7.098024601438782e-06, "loss": 0.0004, "step": 13246 }, { "epoch": 0.7315551137618732, "grad_norm": 2.2679712772369385, "learning_rate": 7.095291389014003e-06, "loss": 0.1123, "step": 13247 }, { "epoch": 0.731610337972167, "grad_norm": 4.9280266761779785, "learning_rate": 7.0925585894476e-06, "loss": 0.7697, "step": 13248 }, { "epoch": 0.7316655621824608, "grad_norm": 0.07440478354692459, "learning_rate": 7.089826202826991e-06, "loss": 0.0018, "step": 13249 }, { "epoch": 0.7317207863927546, "grad_norm": 3.2855589389801025, "learning_rate": 7.087094229239597e-06, "loss": 0.1827, "step": 13250 }, { "epoch": 0.7317760106030484, "grad_norm": 2.6401026248931885, "learning_rate": 7.0843626687728125e-06, "loss": 0.1461, "step": 13251 }, { "epoch": 0.7318312348133422, "grad_norm": 0.050305355340242386, "learning_rate": 7.0816315215140495e-06, "loss": 0.0011, "step": 13252 }, { "epoch": 0.7318864590236359, "grad_norm": 0.017175747081637383, "learning_rate": 7.0789007875506575e-06, "loss": 0.0005, "step": 13253 }, { "epoch": 0.7319416832339297, "grad_norm": 0.07274132966995239, "learning_rate": 7.076170466970021e-06, "loss": 0.0021, "step": 13254 }, { "epoch": 0.7319969074442235, "grad_norm": 4.303864002227783, "learning_rate": 7.073440559859484e-06, "loss": 0.6945, "step": 13255 }, { "epoch": 0.7320521316545173, "grad_norm": 0.992965817451477, "learning_rate": 7.070711066306382e-06, "loss": 0.0199, "step": 13256 }, { "epoch": 0.7321073558648111, "grad_norm": 6.542145729064941, "learning_rate": 7.067981986398036e-06, "loss": 1.1324, "step": 13257 }, { "epoch": 0.7321625800751049, "grad_norm": 0.06291928887367249, "learning_rate": 7.065253320221768e-06, "loss": 0.0019, "step": 13258 }, { "epoch": 0.7322178042853987, "grad_norm": 4.423456192016602, "learning_rate": 7.062525067864869e-06, "loss": 0.9761, "step": 13259 }, { "epoch": 0.7322730284956925, "grad_norm": 0.12131060659885406, "learning_rate": 7.059797229414627e-06, "loss": 0.0028, "step": 13260 }, { "epoch": 0.7323282527059863, "grad_norm": 0.781967043876648, "learning_rate": 7.057069804958301e-06, "loss": 0.115, "step": 13261 }, { "epoch": 0.7323834769162801, "grad_norm": 2.4839231967926025, "learning_rate": 7.054342794583173e-06, "loss": 0.3974, "step": 13262 }, { "epoch": 0.7324387011265739, "grad_norm": 0.016131309792399406, "learning_rate": 7.051616198376463e-06, "loss": 0.0004, "step": 13263 }, { "epoch": 0.7324939253368676, "grad_norm": 4.548856258392334, "learning_rate": 7.048890016425418e-06, "loss": 0.5054, "step": 13264 }, { "epoch": 0.7325491495471614, "grad_norm": 4.100402355194092, "learning_rate": 7.046164248817251e-06, "loss": 0.2906, "step": 13265 }, { "epoch": 0.7326043737574552, "grad_norm": 1.5466516017913818, "learning_rate": 7.043438895639167e-06, "loss": 0.0801, "step": 13266 }, { "epoch": 0.732659597967749, "grad_norm": 6.129128932952881, "learning_rate": 7.040713956978353e-06, "loss": 1.0508, "step": 13267 }, { "epoch": 0.7327148221780428, "grad_norm": 0.049740664660930634, "learning_rate": 7.037989432922001e-06, "loss": 0.0016, "step": 13268 }, { "epoch": 0.7327700463883366, "grad_norm": 10.426374435424805, "learning_rate": 7.035265323557265e-06, "loss": 0.6477, "step": 13269 }, { "epoch": 0.7328252705986305, "grad_norm": 0.7309433817863464, "learning_rate": 7.0325416289713035e-06, "loss": 0.0214, "step": 13270 }, { "epoch": 0.7328804948089243, "grad_norm": 0.6453999280929565, "learning_rate": 7.02981834925125e-06, "loss": 0.018, "step": 13271 }, { "epoch": 0.7329357190192181, "grad_norm": 0.01617377996444702, "learning_rate": 7.027095484484232e-06, "loss": 0.0007, "step": 13272 }, { "epoch": 0.7329909432295119, "grad_norm": 0.9583132266998291, "learning_rate": 7.024373034757357e-06, "loss": 0.0251, "step": 13273 }, { "epoch": 0.7330461674398057, "grad_norm": 0.5400466322898865, "learning_rate": 7.021651000157732e-06, "loss": 0.0086, "step": 13274 }, { "epoch": 0.7331013916500994, "grad_norm": 2.9817259311676025, "learning_rate": 7.018929380772442e-06, "loss": 0.2351, "step": 13275 }, { "epoch": 0.7331566158603932, "grad_norm": 4.872275352478027, "learning_rate": 7.016208176688555e-06, "loss": 0.876, "step": 13276 }, { "epoch": 0.733211840070687, "grad_norm": 3.671710968017578, "learning_rate": 7.013487387993126e-06, "loss": 0.4166, "step": 13277 }, { "epoch": 0.7332670642809808, "grad_norm": 2.5110416412353516, "learning_rate": 7.010767014773219e-06, "loss": 0.6423, "step": 13278 }, { "epoch": 0.7333222884912746, "grad_norm": 3.677520513534546, "learning_rate": 7.008047057115841e-06, "loss": 0.3567, "step": 13279 }, { "epoch": 0.7333775127015684, "grad_norm": 1.8281044960021973, "learning_rate": 7.005327515108031e-06, "loss": 0.0159, "step": 13280 }, { "epoch": 0.7334327369118622, "grad_norm": 0.015812719240784645, "learning_rate": 7.002608388836787e-06, "loss": 0.0005, "step": 13281 }, { "epoch": 0.733487961122156, "grad_norm": 0.025619912892580032, "learning_rate": 6.999889678389105e-06, "loss": 0.0006, "step": 13282 }, { "epoch": 0.7335431853324498, "grad_norm": 3.194692611694336, "learning_rate": 6.997171383851953e-06, "loss": 0.2092, "step": 13283 }, { "epoch": 0.7335984095427436, "grad_norm": 0.08345849812030792, "learning_rate": 6.994453505312311e-06, "loss": 0.0022, "step": 13284 }, { "epoch": 0.7336536337530374, "grad_norm": 0.5975714325904846, "learning_rate": 6.991736042857129e-06, "loss": 0.0113, "step": 13285 }, { "epoch": 0.7337088579633311, "grad_norm": 2.0647435188293457, "learning_rate": 6.989018996573345e-06, "loss": 0.4122, "step": 13286 }, { "epoch": 0.7337640821736249, "grad_norm": 0.04664301127195358, "learning_rate": 6.986302366547874e-06, "loss": 0.001, "step": 13287 }, { "epoch": 0.7338193063839187, "grad_norm": 1.5462849140167236, "learning_rate": 6.983586152867654e-06, "loss": 0.1027, "step": 13288 }, { "epoch": 0.7338745305942125, "grad_norm": 0.4093739986419678, "learning_rate": 6.980870355619556e-06, "loss": 0.0089, "step": 13289 }, { "epoch": 0.7339297548045063, "grad_norm": 1.821885347366333, "learning_rate": 6.978154974890483e-06, "loss": 0.0976, "step": 13290 }, { "epoch": 0.7339849790148001, "grad_norm": 2.5479955673217773, "learning_rate": 6.975440010767307e-06, "loss": 0.5494, "step": 13291 }, { "epoch": 0.7340402032250939, "grad_norm": 2.5674591064453125, "learning_rate": 6.972725463336883e-06, "loss": 0.4526, "step": 13292 }, { "epoch": 0.7340954274353877, "grad_norm": 0.10246367752552032, "learning_rate": 6.970011332686053e-06, "loss": 0.0036, "step": 13293 }, { "epoch": 0.7341506516456815, "grad_norm": 2.718437910079956, "learning_rate": 6.967297618901667e-06, "loss": 0.1924, "step": 13294 }, { "epoch": 0.7342058758559753, "grad_norm": 2.141991138458252, "learning_rate": 6.9645843220705204e-06, "loss": 0.1788, "step": 13295 }, { "epoch": 0.7342611000662691, "grad_norm": 0.21848620474338531, "learning_rate": 6.961871442279438e-06, "loss": 0.005, "step": 13296 }, { "epoch": 0.7343163242765628, "grad_norm": 0.016013024374842644, "learning_rate": 6.959158979615204e-06, "loss": 0.0005, "step": 13297 }, { "epoch": 0.7343715484868566, "grad_norm": 0.014179800637066364, "learning_rate": 6.9564469341646024e-06, "loss": 0.0003, "step": 13298 }, { "epoch": 0.7344267726971504, "grad_norm": 0.12367167323827744, "learning_rate": 6.953735306014395e-06, "loss": 0.0029, "step": 13299 }, { "epoch": 0.7344819969074442, "grad_norm": 0.20012162625789642, "learning_rate": 6.951024095251331e-06, "loss": 0.0043, "step": 13300 }, { "epoch": 0.734537221117738, "grad_norm": 0.6696488261222839, "learning_rate": 6.948313301962168e-06, "loss": 0.0176, "step": 13301 }, { "epoch": 0.7345924453280318, "grad_norm": 0.02393135242164135, "learning_rate": 6.945602926233606e-06, "loss": 0.0007, "step": 13302 }, { "epoch": 0.7346476695383256, "grad_norm": 1.853489875793457, "learning_rate": 6.942892968152377e-06, "loss": 0.1271, "step": 13303 }, { "epoch": 0.7347028937486194, "grad_norm": 0.5208232998847961, "learning_rate": 6.940183427805174e-06, "loss": 0.1347, "step": 13304 }, { "epoch": 0.7347581179589132, "grad_norm": 1.280529499053955, "learning_rate": 6.937474305278682e-06, "loss": 0.0267, "step": 13305 }, { "epoch": 0.734813342169207, "grad_norm": 0.050134867429733276, "learning_rate": 6.934765600659567e-06, "loss": 0.0014, "step": 13306 }, { "epoch": 0.7348685663795008, "grad_norm": 3.243635416030884, "learning_rate": 6.932057314034504e-06, "loss": 0.3957, "step": 13307 }, { "epoch": 0.7349237905897945, "grad_norm": 0.21061457693576813, "learning_rate": 6.92934944549013e-06, "loss": 0.0059, "step": 13308 }, { "epoch": 0.7349790148000883, "grad_norm": 0.028590241447091103, "learning_rate": 6.926641995113077e-06, "loss": 0.001, "step": 13309 }, { "epoch": 0.7350342390103821, "grad_norm": 1.604743242263794, "learning_rate": 6.923934962989964e-06, "loss": 0.1914, "step": 13310 }, { "epoch": 0.7350894632206759, "grad_norm": 5.051899433135986, "learning_rate": 6.921228349207399e-06, "loss": 0.6729, "step": 13311 }, { "epoch": 0.7351446874309697, "grad_norm": 2.8415307998657227, "learning_rate": 6.918522153851965e-06, "loss": 0.5, "step": 13312 }, { "epoch": 0.7351999116412635, "grad_norm": 2.2843525409698486, "learning_rate": 6.915816377010256e-06, "loss": 0.5532, "step": 13313 }, { "epoch": 0.7352551358515573, "grad_norm": 0.06800636649131775, "learning_rate": 6.91311101876883e-06, "loss": 0.0021, "step": 13314 }, { "epoch": 0.7353103600618511, "grad_norm": 5.467953205108643, "learning_rate": 6.9104060792142405e-06, "loss": 0.5027, "step": 13315 }, { "epoch": 0.7353655842721449, "grad_norm": 0.010385687462985516, "learning_rate": 6.907701558433015e-06, "loss": 0.0003, "step": 13316 }, { "epoch": 0.7354208084824387, "grad_norm": 6.783547401428223, "learning_rate": 6.904997456511704e-06, "loss": 0.5503, "step": 13317 }, { "epoch": 0.7354760326927325, "grad_norm": 0.1476464420557022, "learning_rate": 6.902293773536792e-06, "loss": 0.0041, "step": 13318 }, { "epoch": 0.7355312569030262, "grad_norm": 3.2535905838012695, "learning_rate": 6.899590509594796e-06, "loss": 1.0542, "step": 13319 }, { "epoch": 0.73558648111332, "grad_norm": 5.244416236877441, "learning_rate": 6.8968876647721935e-06, "loss": 0.4023, "step": 13320 }, { "epoch": 0.7356417053236138, "grad_norm": 0.17381292581558228, "learning_rate": 6.894185239155457e-06, "loss": 0.003, "step": 13321 }, { "epoch": 0.7356969295339076, "grad_norm": 0.0923457220196724, "learning_rate": 6.89148323283104e-06, "loss": 0.0019, "step": 13322 }, { "epoch": 0.7357521537442014, "grad_norm": 0.20651309192180634, "learning_rate": 6.8887816458854e-06, "loss": 0.0046, "step": 13323 }, { "epoch": 0.7358073779544952, "grad_norm": 2.1421525478363037, "learning_rate": 6.886080478404959e-06, "loss": 0.189, "step": 13324 }, { "epoch": 0.735862602164789, "grad_norm": 0.10902616381645203, "learning_rate": 6.883379730476138e-06, "loss": 0.0032, "step": 13325 }, { "epoch": 0.7359178263750829, "grad_norm": 0.7302594780921936, "learning_rate": 6.8806794021853355e-06, "loss": 0.0248, "step": 13326 }, { "epoch": 0.7359730505853767, "grad_norm": 0.311603307723999, "learning_rate": 6.87797949361896e-06, "loss": 0.0048, "step": 13327 }, { "epoch": 0.7360282747956705, "grad_norm": 0.11267225444316864, "learning_rate": 6.875280004863365e-06, "loss": 0.0033, "step": 13328 }, { "epoch": 0.7360834990059643, "grad_norm": 2.4089012145996094, "learning_rate": 6.8725809360049335e-06, "loss": 0.4526, "step": 13329 }, { "epoch": 0.7361387232162581, "grad_norm": 0.9693521857261658, "learning_rate": 6.8698822871300076e-06, "loss": 0.0103, "step": 13330 }, { "epoch": 0.7361939474265518, "grad_norm": 0.8148421049118042, "learning_rate": 6.867184058324929e-06, "loss": 0.0199, "step": 13331 }, { "epoch": 0.7362491716368456, "grad_norm": 1.5276652574539185, "learning_rate": 6.864486249676014e-06, "loss": 0.1396, "step": 13332 }, { "epoch": 0.7363043958471394, "grad_norm": 4.839404106140137, "learning_rate": 6.861788861269591e-06, "loss": 0.257, "step": 13333 }, { "epoch": 0.7363596200574332, "grad_norm": 2.615607261657715, "learning_rate": 6.859091893191931e-06, "loss": 0.1041, "step": 13334 }, { "epoch": 0.736414844267727, "grad_norm": 0.025043250992894173, "learning_rate": 6.856395345529341e-06, "loss": 0.0009, "step": 13335 }, { "epoch": 0.7364700684780208, "grad_norm": 4.456101894378662, "learning_rate": 6.853699218368082e-06, "loss": 0.1684, "step": 13336 }, { "epoch": 0.7365252926883146, "grad_norm": 1.8930103778839111, "learning_rate": 6.851003511794409e-06, "loss": 0.1099, "step": 13337 }, { "epoch": 0.7365805168986084, "grad_norm": 0.8605015873908997, "learning_rate": 6.848308225894562e-06, "loss": 0.027, "step": 13338 }, { "epoch": 0.7366357411089022, "grad_norm": 0.0430079810321331, "learning_rate": 6.845613360754781e-06, "loss": 0.0011, "step": 13339 }, { "epoch": 0.736690965319196, "grad_norm": 3.2481024265289307, "learning_rate": 6.842918916461279e-06, "loss": 0.2255, "step": 13340 }, { "epoch": 0.7367461895294898, "grad_norm": 1.0054481029510498, "learning_rate": 6.840224893100255e-06, "loss": 0.1129, "step": 13341 }, { "epoch": 0.7368014137397835, "grad_norm": 1.7785311937332153, "learning_rate": 6.837531290757897e-06, "loss": 0.143, "step": 13342 }, { "epoch": 0.7368566379500773, "grad_norm": 0.052843429148197174, "learning_rate": 6.834838109520399e-06, "loss": 0.0016, "step": 13343 }, { "epoch": 0.7369118621603711, "grad_norm": 0.31343352794647217, "learning_rate": 6.832145349473893e-06, "loss": 0.0119, "step": 13344 }, { "epoch": 0.7369670863706649, "grad_norm": 2.7376842498779297, "learning_rate": 6.829453010704552e-06, "loss": 0.2189, "step": 13345 }, { "epoch": 0.7370223105809587, "grad_norm": 6.520823001861572, "learning_rate": 6.826761093298506e-06, "loss": 1.9696, "step": 13346 }, { "epoch": 0.7370775347912525, "grad_norm": 3.753338575363159, "learning_rate": 6.824069597341874e-06, "loss": 0.9582, "step": 13347 }, { "epoch": 0.7371327590015463, "grad_norm": 4.969063758850098, "learning_rate": 6.821378522920758e-06, "loss": 0.5025, "step": 13348 }, { "epoch": 0.7371879832118401, "grad_norm": 0.005075132008641958, "learning_rate": 6.818687870121275e-06, "loss": 0.0001, "step": 13349 }, { "epoch": 0.7372432074221339, "grad_norm": 5.585345268249512, "learning_rate": 6.815997639029479e-06, "loss": 0.6721, "step": 13350 }, { "epoch": 0.7372984316324277, "grad_norm": 5.07741641998291, "learning_rate": 6.8133078297314595e-06, "loss": 0.7477, "step": 13351 }, { "epoch": 0.7373536558427215, "grad_norm": 0.09388769418001175, "learning_rate": 6.810618442313262e-06, "loss": 0.0035, "step": 13352 }, { "epoch": 0.7374088800530152, "grad_norm": 0.32791614532470703, "learning_rate": 6.8079294768609305e-06, "loss": 0.0074, "step": 13353 }, { "epoch": 0.737464104263309, "grad_norm": 0.3465583622455597, "learning_rate": 6.805240933460484e-06, "loss": 0.0067, "step": 13354 }, { "epoch": 0.7375193284736028, "grad_norm": 0.2729319632053375, "learning_rate": 6.802552812197949e-06, "loss": 0.0052, "step": 13355 }, { "epoch": 0.7375745526838966, "grad_norm": 0.08790666610002518, "learning_rate": 6.799865113159323e-06, "loss": 0.0023, "step": 13356 }, { "epoch": 0.7376297768941904, "grad_norm": 4.330316543579102, "learning_rate": 6.7971778364305904e-06, "loss": 0.4047, "step": 13357 }, { "epoch": 0.7376850011044842, "grad_norm": 0.008903250098228455, "learning_rate": 6.794490982097726e-06, "loss": 0.0002, "step": 13358 }, { "epoch": 0.737740225314778, "grad_norm": 0.1265294849872589, "learning_rate": 6.791804550246688e-06, "loss": 0.0032, "step": 13359 }, { "epoch": 0.7377954495250718, "grad_norm": 1.473404884338379, "learning_rate": 6.789118540963426e-06, "loss": 0.0701, "step": 13360 }, { "epoch": 0.7378506737353656, "grad_norm": 3.459676504135132, "learning_rate": 6.786432954333864e-06, "loss": 0.3461, "step": 13361 }, { "epoch": 0.7379058979456594, "grad_norm": 0.009798786602914333, "learning_rate": 6.7837477904439375e-06, "loss": 0.0003, "step": 13362 }, { "epoch": 0.7379611221559532, "grad_norm": 1.8962661027908325, "learning_rate": 6.781063049379541e-06, "loss": 0.0409, "step": 13363 }, { "epoch": 0.7380163463662469, "grad_norm": 0.15911969542503357, "learning_rate": 6.778378731226574e-06, "loss": 0.0049, "step": 13364 }, { "epoch": 0.7380715705765407, "grad_norm": 0.035032231360673904, "learning_rate": 6.775694836070903e-06, "loss": 0.0007, "step": 13365 }, { "epoch": 0.7381267947868345, "grad_norm": 1.9153742790222168, "learning_rate": 6.773011363998416e-06, "loss": 0.4682, "step": 13366 }, { "epoch": 0.7381820189971283, "grad_norm": 0.5491878390312195, "learning_rate": 6.770328315094936e-06, "loss": 0.01, "step": 13367 }, { "epoch": 0.7382372432074221, "grad_norm": 2.966339349746704, "learning_rate": 6.767645689446325e-06, "loss": 0.0299, "step": 13368 }, { "epoch": 0.7382924674177159, "grad_norm": 3.7238454818725586, "learning_rate": 6.764963487138398e-06, "loss": 0.4752, "step": 13369 }, { "epoch": 0.7383476916280097, "grad_norm": 4.00361967086792, "learning_rate": 6.762281708256968e-06, "loss": 0.3371, "step": 13370 }, { "epoch": 0.7384029158383035, "grad_norm": 2.778465509414673, "learning_rate": 6.759600352887827e-06, "loss": 0.4272, "step": 13371 }, { "epoch": 0.7384581400485973, "grad_norm": 0.22159311175346375, "learning_rate": 6.756919421116777e-06, "loss": 0.0042, "step": 13372 }, { "epoch": 0.7385133642588911, "grad_norm": 0.01037320215255022, "learning_rate": 6.754238913029563e-06, "loss": 0.0003, "step": 13373 }, { "epoch": 0.7385685884691849, "grad_norm": 1.4705246686935425, "learning_rate": 6.751558828711959e-06, "loss": 0.013, "step": 13374 }, { "epoch": 0.7386238126794786, "grad_norm": 2.553849220275879, "learning_rate": 6.748879168249707e-06, "loss": 0.1912, "step": 13375 }, { "epoch": 0.7386790368897724, "grad_norm": 8.791029930114746, "learning_rate": 6.7461999317285345e-06, "loss": 0.9442, "step": 13376 }, { "epoch": 0.7387342611000662, "grad_norm": 0.01125011034309864, "learning_rate": 6.743521119234153e-06, "loss": 0.0003, "step": 13377 }, { "epoch": 0.73878948531036, "grad_norm": 3.9967241287231445, "learning_rate": 6.740842730852275e-06, "loss": 0.2673, "step": 13378 }, { "epoch": 0.7388447095206538, "grad_norm": 0.005274080205708742, "learning_rate": 6.738164766668585e-06, "loss": 0.0001, "step": 13379 }, { "epoch": 0.7388999337309476, "grad_norm": 0.41197553277015686, "learning_rate": 6.73548722676876e-06, "loss": 0.0073, "step": 13380 }, { "epoch": 0.7389551579412414, "grad_norm": 0.15243323147296906, "learning_rate": 6.732810111238455e-06, "loss": 0.004, "step": 13381 }, { "epoch": 0.7390103821515353, "grad_norm": 0.46839162707328796, "learning_rate": 6.730133420163336e-06, "loss": 0.0112, "step": 13382 }, { "epoch": 0.739065606361829, "grad_norm": 5.693646430969238, "learning_rate": 6.727457153629014e-06, "loss": 0.0689, "step": 13383 }, { "epoch": 0.7391208305721229, "grad_norm": 1.6224277019500732, "learning_rate": 6.724781311721129e-06, "loss": 0.0323, "step": 13384 }, { "epoch": 0.7391760547824167, "grad_norm": 0.1720849573612213, "learning_rate": 6.722105894525284e-06, "loss": 0.0046, "step": 13385 }, { "epoch": 0.7392312789927104, "grad_norm": 0.10175913572311401, "learning_rate": 6.719430902127071e-06, "loss": 0.0025, "step": 13386 }, { "epoch": 0.7392865032030042, "grad_norm": 0.07810863852500916, "learning_rate": 6.716756334612064e-06, "loss": 0.002, "step": 13387 }, { "epoch": 0.739341727413298, "grad_norm": 0.12714865803718567, "learning_rate": 6.714082192065847e-06, "loss": 0.0027, "step": 13388 }, { "epoch": 0.7393969516235918, "grad_norm": 0.2518683075904846, "learning_rate": 6.711408474573961e-06, "loss": 0.0082, "step": 13389 }, { "epoch": 0.7394521758338856, "grad_norm": 0.09580933302640915, "learning_rate": 6.70873518222195e-06, "loss": 0.0034, "step": 13390 }, { "epoch": 0.7395074000441794, "grad_norm": 0.008262407034635544, "learning_rate": 6.706062315095341e-06, "loss": 0.0002, "step": 13391 }, { "epoch": 0.7395626242544732, "grad_norm": 2.2502171993255615, "learning_rate": 6.703389873279642e-06, "loss": 0.0963, "step": 13392 }, { "epoch": 0.739617848464767, "grad_norm": 1.2376751899719238, "learning_rate": 6.7007178568603505e-06, "loss": 0.0347, "step": 13393 }, { "epoch": 0.7396730726750608, "grad_norm": 2.0537476539611816, "learning_rate": 6.6980462659229615e-06, "loss": 0.1221, "step": 13394 }, { "epoch": 0.7397282968853546, "grad_norm": 2.7867214679718018, "learning_rate": 6.695375100552941e-06, "loss": 0.0203, "step": 13395 }, { "epoch": 0.7397835210956484, "grad_norm": 0.053737763315439224, "learning_rate": 6.692704360835747e-06, "loss": 0.0012, "step": 13396 }, { "epoch": 0.7398387453059422, "grad_norm": 1.2204365730285645, "learning_rate": 6.690034046856819e-06, "loss": 0.0184, "step": 13397 }, { "epoch": 0.7398939695162359, "grad_norm": 0.39525771141052246, "learning_rate": 6.687364158701608e-06, "loss": 0.0074, "step": 13398 }, { "epoch": 0.7399491937265297, "grad_norm": 4.642842769622803, "learning_rate": 6.684694696455503e-06, "loss": 0.0797, "step": 13399 }, { "epoch": 0.7400044179368235, "grad_norm": 5.469331741333008, "learning_rate": 6.682025660203926e-06, "loss": 0.2909, "step": 13400 }, { "epoch": 0.7400596421471173, "grad_norm": 0.051504041999578476, "learning_rate": 6.679357050032265e-06, "loss": 0.001, "step": 13401 }, { "epoch": 0.7401148663574111, "grad_norm": 4.356762409210205, "learning_rate": 6.676688866025893e-06, "loss": 0.3905, "step": 13402 }, { "epoch": 0.7401700905677049, "grad_norm": 5.6978302001953125, "learning_rate": 6.674021108270168e-06, "loss": 1.0357, "step": 13403 }, { "epoch": 0.7402253147779987, "grad_norm": 4.434247970581055, "learning_rate": 6.6713537768504535e-06, "loss": 0.301, "step": 13404 }, { "epoch": 0.7402805389882925, "grad_norm": 0.20048877596855164, "learning_rate": 6.668686871852075e-06, "loss": 0.0055, "step": 13405 }, { "epoch": 0.7403357631985863, "grad_norm": 0.07929883152246475, "learning_rate": 6.666020393360355e-06, "loss": 0.0016, "step": 13406 }, { "epoch": 0.7403909874088801, "grad_norm": 6.126005172729492, "learning_rate": 6.663354341460597e-06, "loss": 0.4087, "step": 13407 }, { "epoch": 0.7404462116191739, "grad_norm": 2.8513147830963135, "learning_rate": 6.660688716238115e-06, "loss": 0.4093, "step": 13408 }, { "epoch": 0.7405014358294676, "grad_norm": 1.1552703380584717, "learning_rate": 6.6580235177781625e-06, "loss": 0.0484, "step": 13409 }, { "epoch": 0.7405566600397614, "grad_norm": 2.709921360015869, "learning_rate": 6.655358746166028e-06, "loss": 0.4355, "step": 13410 }, { "epoch": 0.7406118842500552, "grad_norm": 0.03404409438371658, "learning_rate": 6.652694401486957e-06, "loss": 0.0007, "step": 13411 }, { "epoch": 0.740667108460349, "grad_norm": 3.2457807064056396, "learning_rate": 6.650030483826191e-06, "loss": 0.3179, "step": 13412 }, { "epoch": 0.7407223326706428, "grad_norm": 2.785327911376953, "learning_rate": 6.647366993268947e-06, "loss": 0.0896, "step": 13413 }, { "epoch": 0.7407775568809366, "grad_norm": 0.1455342173576355, "learning_rate": 6.644703929900462e-06, "loss": 0.0029, "step": 13414 }, { "epoch": 0.7408327810912304, "grad_norm": 0.02243829146027565, "learning_rate": 6.6420412938059034e-06, "loss": 0.0005, "step": 13415 }, { "epoch": 0.7408880053015242, "grad_norm": 0.8680335879325867, "learning_rate": 6.6393790850704805e-06, "loss": 0.0265, "step": 13416 }, { "epoch": 0.740943229511818, "grad_norm": 1.3647403717041016, "learning_rate": 6.636717303779357e-06, "loss": 0.0412, "step": 13417 }, { "epoch": 0.7409984537221118, "grad_norm": 0.9439486861228943, "learning_rate": 6.634055950017688e-06, "loss": 0.024, "step": 13418 }, { "epoch": 0.7410536779324056, "grad_norm": 0.014050837606191635, "learning_rate": 6.631395023870624e-06, "loss": 0.0005, "step": 13419 }, { "epoch": 0.7411089021426993, "grad_norm": 3.2053797245025635, "learning_rate": 6.628734525423281e-06, "loss": 0.3334, "step": 13420 }, { "epoch": 0.7411641263529931, "grad_norm": 4.726440906524658, "learning_rate": 6.626074454760805e-06, "loss": 0.5059, "step": 13421 }, { "epoch": 0.7412193505632869, "grad_norm": 1.8428236246109009, "learning_rate": 6.623414811968265e-06, "loss": 0.0562, "step": 13422 }, { "epoch": 0.7412745747735807, "grad_norm": 0.06758664548397064, "learning_rate": 6.6207555971307725e-06, "loss": 0.0019, "step": 13423 }, { "epoch": 0.7413297989838745, "grad_norm": 0.050904933363199234, "learning_rate": 6.618096810333398e-06, "loss": 0.0019, "step": 13424 }, { "epoch": 0.7413850231941683, "grad_norm": 1.0015530586242676, "learning_rate": 6.615438451661205e-06, "loss": 0.0211, "step": 13425 }, { "epoch": 0.7414402474044621, "grad_norm": 1.7984226942062378, "learning_rate": 6.612780521199231e-06, "loss": 0.0863, "step": 13426 }, { "epoch": 0.7414954716147559, "grad_norm": 3.3444974422454834, "learning_rate": 6.610123019032528e-06, "loss": 0.3231, "step": 13427 }, { "epoch": 0.7415506958250497, "grad_norm": 6.537845611572266, "learning_rate": 6.607465945246107e-06, "loss": 0.9094, "step": 13428 }, { "epoch": 0.7416059200353435, "grad_norm": 0.043845709413290024, "learning_rate": 6.604809299924979e-06, "loss": 0.0011, "step": 13429 }, { "epoch": 0.7416611442456373, "grad_norm": 0.010412808507680893, "learning_rate": 6.6021530831541365e-06, "loss": 0.0002, "step": 13430 }, { "epoch": 0.741716368455931, "grad_norm": 0.1230190247297287, "learning_rate": 6.599497295018558e-06, "loss": 0.0036, "step": 13431 }, { "epoch": 0.7417715926662248, "grad_norm": 0.09569300711154938, "learning_rate": 6.596841935603205e-06, "loss": 0.0023, "step": 13432 }, { "epoch": 0.7418268168765186, "grad_norm": 0.09551655501127243, "learning_rate": 6.5941870049930404e-06, "loss": 0.0025, "step": 13433 }, { "epoch": 0.7418820410868124, "grad_norm": 0.029840568080544472, "learning_rate": 6.591532503272997e-06, "loss": 0.0008, "step": 13434 }, { "epoch": 0.7419372652971062, "grad_norm": 0.11281055957078934, "learning_rate": 6.588878430528003e-06, "loss": 0.0025, "step": 13435 }, { "epoch": 0.7419924895074, "grad_norm": 5.674570560455322, "learning_rate": 6.586224786842963e-06, "loss": 0.913, "step": 13436 }, { "epoch": 0.7420477137176938, "grad_norm": 4.216251850128174, "learning_rate": 6.5835715723027895e-06, "loss": 1.3331, "step": 13437 }, { "epoch": 0.7421029379279876, "grad_norm": 5.518595218658447, "learning_rate": 6.580918786992345e-06, "loss": 1.3515, "step": 13438 }, { "epoch": 0.7421581621382815, "grad_norm": 0.07396572828292847, "learning_rate": 6.578266430996516e-06, "loss": 0.0022, "step": 13439 }, { "epoch": 0.7422133863485753, "grad_norm": 0.066026471555233, "learning_rate": 6.575614504400154e-06, "loss": 0.0025, "step": 13440 }, { "epoch": 0.7422686105588691, "grad_norm": 0.1355755776166916, "learning_rate": 6.572963007288102e-06, "loss": 0.0031, "step": 13441 }, { "epoch": 0.7423238347691627, "grad_norm": 2.18662428855896, "learning_rate": 6.570311939745182e-06, "loss": 0.1749, "step": 13442 }, { "epoch": 0.7423790589794566, "grad_norm": 0.08926237374544144, "learning_rate": 6.567661301856223e-06, "loss": 0.0026, "step": 13443 }, { "epoch": 0.7424342831897504, "grad_norm": 4.5629143714904785, "learning_rate": 6.56501109370602e-06, "loss": 1.0649, "step": 13444 }, { "epoch": 0.7424895074000442, "grad_norm": 2.846107006072998, "learning_rate": 6.562361315379358e-06, "loss": 0.147, "step": 13445 }, { "epoch": 0.742544731610338, "grad_norm": 0.2808057963848114, "learning_rate": 6.559711966961004e-06, "loss": 0.007, "step": 13446 }, { "epoch": 0.7425999558206318, "grad_norm": 0.018673542886972427, "learning_rate": 6.557063048535743e-06, "loss": 0.0003, "step": 13447 }, { "epoch": 0.7426551800309256, "grad_norm": 5.964505195617676, "learning_rate": 6.5544145601882935e-06, "loss": 0.6764, "step": 13448 }, { "epoch": 0.7427104042412194, "grad_norm": 3.1491334438323975, "learning_rate": 6.5517665020034046e-06, "loss": 0.2106, "step": 13449 }, { "epoch": 0.7427656284515132, "grad_norm": 5.877392292022705, "learning_rate": 6.549118874065792e-06, "loss": 1.7926, "step": 13450 }, { "epoch": 0.742820852661807, "grad_norm": 4.000627517700195, "learning_rate": 6.5464716764601575e-06, "loss": 0.8616, "step": 13451 }, { "epoch": 0.7428760768721008, "grad_norm": 2.4228103160858154, "learning_rate": 6.543824909271191e-06, "loss": 0.2462, "step": 13452 }, { "epoch": 0.7429313010823945, "grad_norm": 1.3733608722686768, "learning_rate": 6.5411785725835845e-06, "loss": 0.0401, "step": 13453 }, { "epoch": 0.7429865252926883, "grad_norm": 2.075788736343384, "learning_rate": 6.5385326664819786e-06, "loss": 0.1579, "step": 13454 }, { "epoch": 0.7430417495029821, "grad_norm": 0.1853637844324112, "learning_rate": 6.53588719105104e-06, "loss": 0.0043, "step": 13455 }, { "epoch": 0.7430969737132759, "grad_norm": 0.08889137208461761, "learning_rate": 6.533242146375405e-06, "loss": 0.0033, "step": 13456 }, { "epoch": 0.7431521979235697, "grad_norm": 0.12515203654766083, "learning_rate": 6.5305975325396885e-06, "loss": 0.004, "step": 13457 }, { "epoch": 0.7432074221338635, "grad_norm": 0.1307254284620285, "learning_rate": 6.527953349628498e-06, "loss": 0.003, "step": 13458 }, { "epoch": 0.7432626463441573, "grad_norm": 0.03607213497161865, "learning_rate": 6.525309597726439e-06, "loss": 0.0011, "step": 13459 }, { "epoch": 0.7433178705544511, "grad_norm": 4.27969217300415, "learning_rate": 6.522666276918086e-06, "loss": 0.3961, "step": 13460 }, { "epoch": 0.7433730947647449, "grad_norm": 4.901159286499023, "learning_rate": 6.520023387288008e-06, "loss": 1.0787, "step": 13461 }, { "epoch": 0.7434283189750387, "grad_norm": 0.0567425861954689, "learning_rate": 6.517380928920751e-06, "loss": 0.0014, "step": 13462 }, { "epoch": 0.7434835431853325, "grad_norm": 3.378472089767456, "learning_rate": 6.514738901900875e-06, "loss": 0.4403, "step": 13463 }, { "epoch": 0.7435387673956262, "grad_norm": 3.791105270385742, "learning_rate": 6.512097306312879e-06, "loss": 0.9455, "step": 13464 }, { "epoch": 0.74359399160592, "grad_norm": 0.07685471326112747, "learning_rate": 6.509456142241295e-06, "loss": 0.0017, "step": 13465 }, { "epoch": 0.7436492158162138, "grad_norm": 0.16625696420669556, "learning_rate": 6.506815409770615e-06, "loss": 0.0035, "step": 13466 }, { "epoch": 0.7437044400265076, "grad_norm": 1.6427721977233887, "learning_rate": 6.504175108985322e-06, "loss": 0.0391, "step": 13467 }, { "epoch": 0.7437596642368014, "grad_norm": 3.9543583393096924, "learning_rate": 6.501535239969883e-06, "loss": 0.6796, "step": 13468 }, { "epoch": 0.7438148884470952, "grad_norm": 1.5331124067306519, "learning_rate": 6.498895802808774e-06, "loss": 0.0703, "step": 13469 }, { "epoch": 0.743870112657389, "grad_norm": 0.04743940010666847, "learning_rate": 6.496256797586409e-06, "loss": 0.0014, "step": 13470 }, { "epoch": 0.7439253368676828, "grad_norm": 0.044427983462810516, "learning_rate": 6.493618224387239e-06, "loss": 0.0013, "step": 13471 }, { "epoch": 0.7439805610779766, "grad_norm": 2.6804752349853516, "learning_rate": 6.490980083295675e-06, "loss": 0.1886, "step": 13472 }, { "epoch": 0.7440357852882704, "grad_norm": 0.14972364902496338, "learning_rate": 6.488342374396115e-06, "loss": 0.002, "step": 13473 }, { "epoch": 0.7440910094985642, "grad_norm": 2.2639524936676025, "learning_rate": 6.485705097772943e-06, "loss": 0.5676, "step": 13474 }, { "epoch": 0.744146233708858, "grad_norm": 0.022467192262411118, "learning_rate": 6.483068253510545e-06, "loss": 0.0005, "step": 13475 }, { "epoch": 0.7442014579191517, "grad_norm": 1.3433083295822144, "learning_rate": 6.480431841693273e-06, "loss": 0.0743, "step": 13476 }, { "epoch": 0.7442566821294455, "grad_norm": 4.6595964431762695, "learning_rate": 6.477795862405476e-06, "loss": 0.8526, "step": 13477 }, { "epoch": 0.7443119063397393, "grad_norm": 0.11363358795642853, "learning_rate": 6.475160315731485e-06, "loss": 0.0021, "step": 13478 }, { "epoch": 0.7443671305500331, "grad_norm": 2.5425100326538086, "learning_rate": 6.472525201755619e-06, "loss": 0.0854, "step": 13479 }, { "epoch": 0.7444223547603269, "grad_norm": 2.2313783168792725, "learning_rate": 6.469890520562185e-06, "loss": 0.1981, "step": 13480 }, { "epoch": 0.7444775789706207, "grad_norm": 0.10329602658748627, "learning_rate": 6.467256272235463e-06, "loss": 0.0023, "step": 13481 }, { "epoch": 0.7445328031809145, "grad_norm": 1.5383151769638062, "learning_rate": 6.464622456859746e-06, "loss": 0.1097, "step": 13482 }, { "epoch": 0.7445880273912083, "grad_norm": 0.016402272507548332, "learning_rate": 6.461989074519291e-06, "loss": 0.0004, "step": 13483 }, { "epoch": 0.7446432516015021, "grad_norm": 3.2357256412506104, "learning_rate": 6.459356125298344e-06, "loss": 0.4678, "step": 13484 }, { "epoch": 0.7446984758117959, "grad_norm": 0.27739912271499634, "learning_rate": 6.456723609281137e-06, "loss": 0.0059, "step": 13485 }, { "epoch": 0.7447537000220897, "grad_norm": 0.08936962485313416, "learning_rate": 6.454091526551914e-06, "loss": 0.0022, "step": 13486 }, { "epoch": 0.7448089242323834, "grad_norm": 5.766408443450928, "learning_rate": 6.45145987719485e-06, "loss": 0.8484, "step": 13487 }, { "epoch": 0.7448641484426772, "grad_norm": 3.779829740524292, "learning_rate": 6.448828661294162e-06, "loss": 0.2809, "step": 13488 }, { "epoch": 0.744919372652971, "grad_norm": 2.8806841373443604, "learning_rate": 6.446197878934026e-06, "loss": 0.6495, "step": 13489 }, { "epoch": 0.7449745968632648, "grad_norm": 3.88564395904541, "learning_rate": 6.443567530198605e-06, "loss": 0.2608, "step": 13490 }, { "epoch": 0.7450298210735586, "grad_norm": 1.2305561304092407, "learning_rate": 6.4409376151720445e-06, "loss": 0.0426, "step": 13491 }, { "epoch": 0.7450850452838524, "grad_norm": 4.604785442352295, "learning_rate": 6.4383081339385045e-06, "loss": 0.7473, "step": 13492 }, { "epoch": 0.7451402694941462, "grad_norm": 5.8755669593811035, "learning_rate": 6.4356790865820825e-06, "loss": 1.4019, "step": 13493 }, { "epoch": 0.74519549370444, "grad_norm": 0.009164871647953987, "learning_rate": 6.43305047318691e-06, "loss": 0.0002, "step": 13494 }, { "epoch": 0.7452507179147339, "grad_norm": 0.09424310177564621, "learning_rate": 6.430422293837075e-06, "loss": 0.002, "step": 13495 }, { "epoch": 0.7453059421250277, "grad_norm": 0.10236623883247375, "learning_rate": 6.427794548616662e-06, "loss": 0.0028, "step": 13496 }, { "epoch": 0.7453611663353215, "grad_norm": 0.06392272561788559, "learning_rate": 6.425167237609733e-06, "loss": 0.0018, "step": 13497 }, { "epoch": 0.7454163905456151, "grad_norm": 0.10744214802980423, "learning_rate": 6.422540360900358e-06, "loss": 0.0025, "step": 13498 }, { "epoch": 0.745471614755909, "grad_norm": 2.6263229846954346, "learning_rate": 6.419913918572566e-06, "loss": 0.2435, "step": 13499 }, { "epoch": 0.7455268389662028, "grad_norm": 0.13005904853343964, "learning_rate": 6.417287910710392e-06, "loss": 0.0021, "step": 13500 }, { "epoch": 0.7455820631764966, "grad_norm": 1.6421159505844116, "learning_rate": 6.414662337397839e-06, "loss": 0.0477, "step": 13501 }, { "epoch": 0.7456372873867904, "grad_norm": 3.4949398040771484, "learning_rate": 6.412037198718928e-06, "loss": 0.2938, "step": 13502 }, { "epoch": 0.7456925115970842, "grad_norm": 0.09060482680797577, "learning_rate": 6.409412494757614e-06, "loss": 0.0025, "step": 13503 }, { "epoch": 0.745747735807378, "grad_norm": 5.622811317443848, "learning_rate": 6.406788225597895e-06, "loss": 0.5792, "step": 13504 }, { "epoch": 0.7458029600176718, "grad_norm": 0.14858323335647583, "learning_rate": 6.404164391323717e-06, "loss": 0.0047, "step": 13505 }, { "epoch": 0.7458581842279656, "grad_norm": 3.8874752521514893, "learning_rate": 6.4015409920190244e-06, "loss": 0.4361, "step": 13506 }, { "epoch": 0.7459134084382594, "grad_norm": 0.03650122135877609, "learning_rate": 6.398918027767744e-06, "loss": 0.0011, "step": 13507 }, { "epoch": 0.7459686326485532, "grad_norm": 1.607040286064148, "learning_rate": 6.396295498653808e-06, "loss": 0.0797, "step": 13508 }, { "epoch": 0.7460238568588469, "grad_norm": 0.043757133185863495, "learning_rate": 6.393673404761096e-06, "loss": 0.0009, "step": 13509 }, { "epoch": 0.7460790810691407, "grad_norm": 7.57210111618042, "learning_rate": 6.391051746173514e-06, "loss": 1.4618, "step": 13510 }, { "epoch": 0.7461343052794345, "grad_norm": 2.2409446239471436, "learning_rate": 6.3884305229749265e-06, "loss": 0.3507, "step": 13511 }, { "epoch": 0.7461895294897283, "grad_norm": 0.08809211105108261, "learning_rate": 6.3858097352492e-06, "loss": 0.0024, "step": 13512 }, { "epoch": 0.7462447537000221, "grad_norm": 3.1636784076690674, "learning_rate": 6.3831893830801686e-06, "loss": 0.6364, "step": 13513 }, { "epoch": 0.7462999779103159, "grad_norm": 0.07093480974435806, "learning_rate": 6.380569466551682e-06, "loss": 0.0019, "step": 13514 }, { "epoch": 0.7463552021206097, "grad_norm": 0.8889316320419312, "learning_rate": 6.377949985747551e-06, "loss": 0.0092, "step": 13515 }, { "epoch": 0.7464104263309035, "grad_norm": 1.9086625576019287, "learning_rate": 6.3753309407515806e-06, "loss": 0.1896, "step": 13516 }, { "epoch": 0.7464656505411973, "grad_norm": 0.15264001488685608, "learning_rate": 6.372712331647555e-06, "loss": 0.0032, "step": 13517 }, { "epoch": 0.7465208747514911, "grad_norm": 2.853362560272217, "learning_rate": 6.370094158519269e-06, "loss": 0.5579, "step": 13518 }, { "epoch": 0.7465760989617849, "grad_norm": 2.49251651763916, "learning_rate": 6.367476421450463e-06, "loss": 0.1863, "step": 13519 }, { "epoch": 0.7466313231720786, "grad_norm": 4.588718891143799, "learning_rate": 6.3648591205249e-06, "loss": 0.4228, "step": 13520 }, { "epoch": 0.7466865473823724, "grad_norm": 2.827573776245117, "learning_rate": 6.362242255826312e-06, "loss": 0.4647, "step": 13521 }, { "epoch": 0.7467417715926662, "grad_norm": 4.608460903167725, "learning_rate": 6.359625827438418e-06, "loss": 0.3825, "step": 13522 }, { "epoch": 0.74679699580296, "grad_norm": 0.8861463665962219, "learning_rate": 6.357009835444923e-06, "loss": 0.0106, "step": 13523 }, { "epoch": 0.7468522200132538, "grad_norm": 3.463315010070801, "learning_rate": 6.354394279929528e-06, "loss": 0.8218, "step": 13524 }, { "epoch": 0.7469074442235476, "grad_norm": 1.2290161848068237, "learning_rate": 6.351779160975906e-06, "loss": 0.0384, "step": 13525 }, { "epoch": 0.7469626684338414, "grad_norm": 2.706536293029785, "learning_rate": 6.349164478667724e-06, "loss": 0.1344, "step": 13526 }, { "epoch": 0.7470178926441352, "grad_norm": 1.3784410953521729, "learning_rate": 6.346550233088633e-06, "loss": 0.0519, "step": 13527 }, { "epoch": 0.747073116854429, "grad_norm": 2.02813982963562, "learning_rate": 6.34393642432227e-06, "loss": 0.1438, "step": 13528 }, { "epoch": 0.7471283410647228, "grad_norm": 0.014086654409766197, "learning_rate": 6.34132305245225e-06, "loss": 0.0004, "step": 13529 }, { "epoch": 0.7471835652750166, "grad_norm": 1.0359774827957153, "learning_rate": 6.338710117562199e-06, "loss": 0.0351, "step": 13530 }, { "epoch": 0.7472387894853103, "grad_norm": 8.54386043548584, "learning_rate": 6.336097619735702e-06, "loss": 1.4387, "step": 13531 }, { "epoch": 0.7472940136956041, "grad_norm": 0.06880929321050644, "learning_rate": 6.333485559056341e-06, "loss": 0.0022, "step": 13532 }, { "epoch": 0.7473492379058979, "grad_norm": 3.6839025020599365, "learning_rate": 6.330873935607677e-06, "loss": 0.5735, "step": 13533 }, { "epoch": 0.7474044621161917, "grad_norm": 4.310235023498535, "learning_rate": 6.328262749473286e-06, "loss": 1.29, "step": 13534 }, { "epoch": 0.7474596863264855, "grad_norm": 0.045870985835790634, "learning_rate": 6.325652000736675e-06, "loss": 0.0012, "step": 13535 }, { "epoch": 0.7475149105367793, "grad_norm": 0.10865498334169388, "learning_rate": 6.323041689481393e-06, "loss": 0.0017, "step": 13536 }, { "epoch": 0.7475701347470731, "grad_norm": 0.02797526679933071, "learning_rate": 6.320431815790946e-06, "loss": 0.0007, "step": 13537 }, { "epoch": 0.7476253589573669, "grad_norm": 0.6077877283096313, "learning_rate": 6.317822379748826e-06, "loss": 0.0064, "step": 13538 }, { "epoch": 0.7476805831676607, "grad_norm": 2.0535101890563965, "learning_rate": 6.315213381438521e-06, "loss": 0.2141, "step": 13539 }, { "epoch": 0.7477358073779545, "grad_norm": 3.074401378631592, "learning_rate": 6.3126048209434935e-06, "loss": 0.6543, "step": 13540 }, { "epoch": 0.7477910315882483, "grad_norm": 2.983081817626953, "learning_rate": 6.309996698347216e-06, "loss": 0.3903, "step": 13541 }, { "epoch": 0.747846255798542, "grad_norm": 0.15640008449554443, "learning_rate": 6.307389013733105e-06, "loss": 0.0042, "step": 13542 }, { "epoch": 0.7479014800088358, "grad_norm": 0.09102467447519302, "learning_rate": 6.304781767184606e-06, "loss": 0.0019, "step": 13543 }, { "epoch": 0.7479567042191296, "grad_norm": 0.03942495211958885, "learning_rate": 6.302174958785128e-06, "loss": 0.0011, "step": 13544 }, { "epoch": 0.7480119284294234, "grad_norm": 5.723106384277344, "learning_rate": 6.299568588618068e-06, "loss": 0.9571, "step": 13545 }, { "epoch": 0.7480671526397172, "grad_norm": 5.296392440795898, "learning_rate": 6.296962656766807e-06, "loss": 0.0952, "step": 13546 }, { "epoch": 0.748122376850011, "grad_norm": 0.015744226053357124, "learning_rate": 6.294357163314729e-06, "loss": 0.0006, "step": 13547 }, { "epoch": 0.7481776010603048, "grad_norm": 0.06480742990970612, "learning_rate": 6.2917521083451794e-06, "loss": 0.0016, "step": 13548 }, { "epoch": 0.7482328252705986, "grad_norm": 0.07533121854066849, "learning_rate": 6.289147491941509e-06, "loss": 0.002, "step": 13549 }, { "epoch": 0.7482880494808924, "grad_norm": 5.285122871398926, "learning_rate": 6.286543314187041e-06, "loss": 0.9326, "step": 13550 }, { "epoch": 0.7483432736911863, "grad_norm": 2.1784186363220215, "learning_rate": 6.2839395751650945e-06, "loss": 0.0745, "step": 13551 }, { "epoch": 0.74839849790148, "grad_norm": 0.3664793372154236, "learning_rate": 6.281336274958962e-06, "loss": 0.0087, "step": 13552 }, { "epoch": 0.7484537221117739, "grad_norm": 0.1892644464969635, "learning_rate": 6.278733413651945e-06, "loss": 0.0036, "step": 13553 }, { "epoch": 0.7485089463220675, "grad_norm": 0.16833971440792084, "learning_rate": 6.276130991327307e-06, "loss": 0.0049, "step": 13554 }, { "epoch": 0.7485641705323614, "grad_norm": 1.935982584953308, "learning_rate": 6.273529008068311e-06, "loss": 0.0833, "step": 13555 }, { "epoch": 0.7486193947426552, "grad_norm": 1.1754990816116333, "learning_rate": 6.270927463958192e-06, "loss": 0.0454, "step": 13556 }, { "epoch": 0.748674618952949, "grad_norm": 0.2959372401237488, "learning_rate": 6.2683263590802015e-06, "loss": 0.0053, "step": 13557 }, { "epoch": 0.7487298431632428, "grad_norm": 0.08345538377761841, "learning_rate": 6.265725693517528e-06, "loss": 0.0031, "step": 13558 }, { "epoch": 0.7487850673735366, "grad_norm": 0.05640462040901184, "learning_rate": 6.263125467353397e-06, "loss": 0.0016, "step": 13559 }, { "epoch": 0.7488402915838304, "grad_norm": 0.15609650313854218, "learning_rate": 6.26052568067099e-06, "loss": 0.0042, "step": 13560 }, { "epoch": 0.7488955157941242, "grad_norm": 0.5893005728721619, "learning_rate": 6.257926333553481e-06, "loss": 0.0147, "step": 13561 }, { "epoch": 0.748950740004418, "grad_norm": 0.12750354409217834, "learning_rate": 6.255327426084023e-06, "loss": 0.003, "step": 13562 }, { "epoch": 0.7490059642147118, "grad_norm": 0.019022822380065918, "learning_rate": 6.25272895834578e-06, "loss": 0.0008, "step": 13563 }, { "epoch": 0.7490611884250056, "grad_norm": 0.06018911302089691, "learning_rate": 6.250130930421871e-06, "loss": 0.0017, "step": 13564 }, { "epoch": 0.7491164126352993, "grad_norm": 3.654656171798706, "learning_rate": 6.247533342395418e-06, "loss": 0.2111, "step": 13565 }, { "epoch": 0.7491716368455931, "grad_norm": 0.4061243534088135, "learning_rate": 6.2449361943495204e-06, "loss": 0.0119, "step": 13566 }, { "epoch": 0.7492268610558869, "grad_norm": 0.010882933624088764, "learning_rate": 6.2423394863672835e-06, "loss": 0.0003, "step": 13567 }, { "epoch": 0.7492820852661807, "grad_norm": 0.1369413137435913, "learning_rate": 6.23974321853176e-06, "loss": 0.003, "step": 13568 }, { "epoch": 0.7493373094764745, "grad_norm": 3.389686346054077, "learning_rate": 6.2371473909260325e-06, "loss": 0.6383, "step": 13569 }, { "epoch": 0.7493925336867683, "grad_norm": 2.920848846435547, "learning_rate": 6.2345520036331385e-06, "loss": 0.1664, "step": 13570 }, { "epoch": 0.7494477578970621, "grad_norm": 0.15377546846866608, "learning_rate": 6.231957056736117e-06, "loss": 0.004, "step": 13571 }, { "epoch": 0.7495029821073559, "grad_norm": 0.04903355613350868, "learning_rate": 6.229362550317979e-06, "loss": 0.0013, "step": 13572 }, { "epoch": 0.7495582063176497, "grad_norm": 0.04957597330212593, "learning_rate": 6.226768484461747e-06, "loss": 0.0016, "step": 13573 }, { "epoch": 0.7496134305279435, "grad_norm": 0.3595212996006012, "learning_rate": 6.224174859250389e-06, "loss": 0.0131, "step": 13574 }, { "epoch": 0.7496686547382373, "grad_norm": 2.6222829818725586, "learning_rate": 6.221581674766904e-06, "loss": 0.1061, "step": 13575 }, { "epoch": 0.749723878948531, "grad_norm": 0.03146576136350632, "learning_rate": 6.218988931094245e-06, "loss": 0.0008, "step": 13576 }, { "epoch": 0.7497791031588248, "grad_norm": 0.022105595096945763, "learning_rate": 6.216396628315364e-06, "loss": 0.0005, "step": 13577 }, { "epoch": 0.7498343273691186, "grad_norm": 0.20500117540359497, "learning_rate": 6.213804766513187e-06, "loss": 0.0072, "step": 13578 }, { "epoch": 0.7498895515794124, "grad_norm": 0.3972945511341095, "learning_rate": 6.2112133457706504e-06, "loss": 0.0111, "step": 13579 }, { "epoch": 0.7499447757897062, "grad_norm": 1.6059954166412354, "learning_rate": 6.208622366170654e-06, "loss": 0.0803, "step": 13580 }, { "epoch": 0.75, "grad_norm": 0.019894875586032867, "learning_rate": 6.206031827796091e-06, "loss": 0.0006, "step": 13581 }, { "epoch": 0.7500552242102938, "grad_norm": 1.8595283031463623, "learning_rate": 6.203441730729831e-06, "loss": 0.0717, "step": 13582 }, { "epoch": 0.7501104484205876, "grad_norm": 10.281147956848145, "learning_rate": 6.200852075054762e-06, "loss": 0.6463, "step": 13583 }, { "epoch": 0.7501656726308814, "grad_norm": 2.689530849456787, "learning_rate": 6.198262860853706e-06, "loss": 0.4494, "step": 13584 }, { "epoch": 0.7502208968411752, "grad_norm": 1.7600361108779907, "learning_rate": 6.19567408820952e-06, "loss": 0.1607, "step": 13585 }, { "epoch": 0.750276121051469, "grad_norm": 1.7434296607971191, "learning_rate": 6.1930857572050175e-06, "loss": 0.0647, "step": 13586 }, { "epoch": 0.7503313452617627, "grad_norm": 0.018862133845686913, "learning_rate": 6.190497867923009e-06, "loss": 0.0004, "step": 13587 }, { "epoch": 0.7503865694720565, "grad_norm": 0.6784267425537109, "learning_rate": 6.187910420446281e-06, "loss": 0.0211, "step": 13588 }, { "epoch": 0.7504417936823503, "grad_norm": 0.5555224418640137, "learning_rate": 6.185323414857634e-06, "loss": 0.0184, "step": 13589 }, { "epoch": 0.7504970178926441, "grad_norm": 0.19396845996379852, "learning_rate": 6.182736851239805e-06, "loss": 0.0046, "step": 13590 }, { "epoch": 0.7505522421029379, "grad_norm": 2.160975456237793, "learning_rate": 6.180150729675567e-06, "loss": 0.0406, "step": 13591 }, { "epoch": 0.7506074663132317, "grad_norm": 0.10327864438295364, "learning_rate": 6.177565050247651e-06, "loss": 0.0014, "step": 13592 }, { "epoch": 0.7506626905235255, "grad_norm": 1.3941644430160522, "learning_rate": 6.174979813038779e-06, "loss": 0.0598, "step": 13593 }, { "epoch": 0.7507179147338193, "grad_norm": 2.9180359840393066, "learning_rate": 6.172395018131656e-06, "loss": 0.2979, "step": 13594 }, { "epoch": 0.7507731389441131, "grad_norm": 0.028862323611974716, "learning_rate": 6.169810665608986e-06, "loss": 0.0006, "step": 13595 }, { "epoch": 0.7508283631544069, "grad_norm": 0.2030947357416153, "learning_rate": 6.1672267555534485e-06, "loss": 0.0042, "step": 13596 }, { "epoch": 0.7508835873647007, "grad_norm": 1.2941652536392212, "learning_rate": 6.164643288047705e-06, "loss": 0.0261, "step": 13597 }, { "epoch": 0.7509388115749944, "grad_norm": 0.08252599090337753, "learning_rate": 6.162060263174409e-06, "loss": 0.0017, "step": 13598 }, { "epoch": 0.7509940357852882, "grad_norm": 3.799365282058716, "learning_rate": 6.159477681016204e-06, "loss": 0.5909, "step": 13599 }, { "epoch": 0.751049259995582, "grad_norm": 1.9133132696151733, "learning_rate": 6.156895541655708e-06, "loss": 0.0891, "step": 13600 }, { "epoch": 0.7511044842058758, "grad_norm": 4.6587653160095215, "learning_rate": 6.154313845175525e-06, "loss": 0.2026, "step": 13601 }, { "epoch": 0.7511597084161696, "grad_norm": 0.018129916861653328, "learning_rate": 6.151732591658268e-06, "loss": 0.0006, "step": 13602 }, { "epoch": 0.7512149326264634, "grad_norm": 5.084447860717773, "learning_rate": 6.149151781186509e-06, "loss": 0.9094, "step": 13603 }, { "epoch": 0.7512701568367572, "grad_norm": 0.4399184286594391, "learning_rate": 6.1465714138428165e-06, "loss": 0.0081, "step": 13604 }, { "epoch": 0.751325381047051, "grad_norm": 0.0034618366044014692, "learning_rate": 6.143991489709737e-06, "loss": 0.0001, "step": 13605 }, { "epoch": 0.7513806052573448, "grad_norm": 2.1985011100769043, "learning_rate": 6.141412008869829e-06, "loss": 0.1194, "step": 13606 }, { "epoch": 0.7514358294676386, "grad_norm": 0.029770376160740852, "learning_rate": 6.1388329714055906e-06, "loss": 0.001, "step": 13607 }, { "epoch": 0.7514910536779325, "grad_norm": 4.578957557678223, "learning_rate": 6.136254377399553e-06, "loss": 0.2826, "step": 13608 }, { "epoch": 0.7515462778882261, "grad_norm": 0.39731648564338684, "learning_rate": 6.133676226934206e-06, "loss": 0.0102, "step": 13609 }, { "epoch": 0.75160150209852, "grad_norm": 0.949613094329834, "learning_rate": 6.131098520092034e-06, "loss": 0.1591, "step": 13610 }, { "epoch": 0.7516567263088137, "grad_norm": 2.8480074405670166, "learning_rate": 6.128521256955495e-06, "loss": 0.6453, "step": 13611 }, { "epoch": 0.7517119505191076, "grad_norm": 1.289340615272522, "learning_rate": 6.125944437607065e-06, "loss": 0.1509, "step": 13612 }, { "epoch": 0.7517671747294014, "grad_norm": 3.8664681911468506, "learning_rate": 6.123368062129158e-06, "loss": 0.5085, "step": 13613 }, { "epoch": 0.7518223989396952, "grad_norm": 3.8566360473632812, "learning_rate": 6.1207921306042165e-06, "loss": 0.1024, "step": 13614 }, { "epoch": 0.751877623149989, "grad_norm": 1.9164586067199707, "learning_rate": 6.118216643114647e-06, "loss": 0.1365, "step": 13615 }, { "epoch": 0.7519328473602828, "grad_norm": 0.1196804940700531, "learning_rate": 6.11564159974285e-06, "loss": 0.003, "step": 13616 }, { "epoch": 0.7519880715705766, "grad_norm": 1.0414186716079712, "learning_rate": 6.1130670005711955e-06, "loss": 0.0272, "step": 13617 }, { "epoch": 0.7520432957808704, "grad_norm": 0.056972526013851166, "learning_rate": 6.11049284568207e-06, "loss": 0.0023, "step": 13618 }, { "epoch": 0.7520985199911642, "grad_norm": 0.00958298146724701, "learning_rate": 6.107919135157818e-06, "loss": 0.0002, "step": 13619 }, { "epoch": 0.752153744201458, "grad_norm": 0.029220085591077805, "learning_rate": 6.105345869080783e-06, "loss": 0.0007, "step": 13620 }, { "epoch": 0.7522089684117517, "grad_norm": 0.10418030619621277, "learning_rate": 6.102773047533286e-06, "loss": 0.0029, "step": 13621 }, { "epoch": 0.7522641926220455, "grad_norm": 0.07746287435293198, "learning_rate": 6.100200670597651e-06, "loss": 0.0021, "step": 13622 }, { "epoch": 0.7523194168323393, "grad_norm": 0.01612161658704281, "learning_rate": 6.0976287383561584e-06, "loss": 0.0005, "step": 13623 }, { "epoch": 0.7523746410426331, "grad_norm": 0.02689445950090885, "learning_rate": 6.095057250891106e-06, "loss": 0.0008, "step": 13624 }, { "epoch": 0.7524298652529269, "grad_norm": 2.2790298461914062, "learning_rate": 6.092486208284758e-06, "loss": 0.1393, "step": 13625 }, { "epoch": 0.7524850894632207, "grad_norm": 0.07554537057876587, "learning_rate": 6.089915610619368e-06, "loss": 0.002, "step": 13626 }, { "epoch": 0.7525403136735145, "grad_norm": 3.710792303085327, "learning_rate": 6.087345457977174e-06, "loss": 0.3699, "step": 13627 }, { "epoch": 0.7525955378838083, "grad_norm": 4.224424839019775, "learning_rate": 6.084775750440417e-06, "loss": 1.328, "step": 13628 }, { "epoch": 0.7526507620941021, "grad_norm": 1.1934046745300293, "learning_rate": 6.082206488091287e-06, "loss": 0.0441, "step": 13629 }, { "epoch": 0.7527059863043959, "grad_norm": 5.378978252410889, "learning_rate": 6.0796376710119975e-06, "loss": 0.9005, "step": 13630 }, { "epoch": 0.7527612105146897, "grad_norm": 0.09456861019134521, "learning_rate": 6.077069299284732e-06, "loss": 0.0024, "step": 13631 }, { "epoch": 0.7528164347249834, "grad_norm": 0.0358085036277771, "learning_rate": 6.074501372991655e-06, "loss": 0.0011, "step": 13632 }, { "epoch": 0.7528716589352772, "grad_norm": 2.961954116821289, "learning_rate": 6.071933892214916e-06, "loss": 0.4609, "step": 13633 }, { "epoch": 0.752926883145571, "grad_norm": 0.23851457238197327, "learning_rate": 6.069366857036669e-06, "loss": 0.0034, "step": 13634 }, { "epoch": 0.7529821073558648, "grad_norm": 0.16310477256774902, "learning_rate": 6.066800267539037e-06, "loss": 0.0039, "step": 13635 }, { "epoch": 0.7530373315661586, "grad_norm": 6.280858039855957, "learning_rate": 6.064234123804129e-06, "loss": 0.9954, "step": 13636 }, { "epoch": 0.7530925557764524, "grad_norm": 0.039048485457897186, "learning_rate": 6.06166842591404e-06, "loss": 0.0012, "step": 13637 }, { "epoch": 0.7531477799867462, "grad_norm": 0.0885409265756607, "learning_rate": 6.059103173950871e-06, "loss": 0.0029, "step": 13638 }, { "epoch": 0.75320300419704, "grad_norm": 0.13714499771595, "learning_rate": 6.056538367996665e-06, "loss": 0.0043, "step": 13639 }, { "epoch": 0.7532582284073338, "grad_norm": 4.04478645324707, "learning_rate": 6.0539740081335006e-06, "loss": 0.5263, "step": 13640 }, { "epoch": 0.7533134526176276, "grad_norm": 0.6126439571380615, "learning_rate": 6.051410094443409e-06, "loss": 0.0187, "step": 13641 }, { "epoch": 0.7533686768279214, "grad_norm": 0.13520972430706024, "learning_rate": 6.048846627008418e-06, "loss": 0.0029, "step": 13642 }, { "epoch": 0.7534239010382151, "grad_norm": 0.01832764223217964, "learning_rate": 6.046283605910535e-06, "loss": 0.0004, "step": 13643 }, { "epoch": 0.7534791252485089, "grad_norm": 0.01506013609468937, "learning_rate": 6.043721031231771e-06, "loss": 0.0005, "step": 13644 }, { "epoch": 0.7535343494588027, "grad_norm": 2.057360887527466, "learning_rate": 6.0411589030541e-06, "loss": 0.1853, "step": 13645 }, { "epoch": 0.7535895736690965, "grad_norm": 0.004538760986179113, "learning_rate": 6.038597221459499e-06, "loss": 0.0001, "step": 13646 }, { "epoch": 0.7536447978793903, "grad_norm": 3.573986530303955, "learning_rate": 6.036035986529916e-06, "loss": 0.3349, "step": 13647 }, { "epoch": 0.7537000220896841, "grad_norm": 0.10848800837993622, "learning_rate": 6.033475198347296e-06, "loss": 0.0035, "step": 13648 }, { "epoch": 0.7537552462999779, "grad_norm": 5.923640251159668, "learning_rate": 6.030914856993559e-06, "loss": 0.4695, "step": 13649 }, { "epoch": 0.7538104705102717, "grad_norm": 0.2688663899898529, "learning_rate": 6.028354962550631e-06, "loss": 0.0092, "step": 13650 }, { "epoch": 0.7538656947205655, "grad_norm": 2.6060452461242676, "learning_rate": 6.025795515100403e-06, "loss": 0.6602, "step": 13651 }, { "epoch": 0.7539209189308593, "grad_norm": 0.01585233211517334, "learning_rate": 6.02323651472476e-06, "loss": 0.0005, "step": 13652 }, { "epoch": 0.7539761431411531, "grad_norm": 1.7887682914733887, "learning_rate": 6.020677961505563e-06, "loss": 0.1427, "step": 13653 }, { "epoch": 0.7540313673514468, "grad_norm": 0.34027037024497986, "learning_rate": 6.018119855524689e-06, "loss": 0.0103, "step": 13654 }, { "epoch": 0.7540865915617406, "grad_norm": 0.033814024180173874, "learning_rate": 6.015562196863953e-06, "loss": 0.0013, "step": 13655 }, { "epoch": 0.7541418157720344, "grad_norm": 0.09028872102499008, "learning_rate": 6.0130049856052e-06, "loss": 0.0019, "step": 13656 }, { "epoch": 0.7541970399823282, "grad_norm": 0.2370721995830536, "learning_rate": 6.010448221830236e-06, "loss": 0.0058, "step": 13657 }, { "epoch": 0.754252264192622, "grad_norm": 0.0898846983909607, "learning_rate": 6.007891905620862e-06, "loss": 0.0035, "step": 13658 }, { "epoch": 0.7543074884029158, "grad_norm": 5.395998954772949, "learning_rate": 6.005336037058858e-06, "loss": 1.0052, "step": 13659 }, { "epoch": 0.7543627126132096, "grad_norm": 0.032693713903427124, "learning_rate": 6.00278061622599e-06, "loss": 0.0008, "step": 13660 }, { "epoch": 0.7544179368235034, "grad_norm": 0.010852032341063023, "learning_rate": 6.00022564320403e-06, "loss": 0.0004, "step": 13661 }, { "epoch": 0.7544731610337972, "grad_norm": 0.06869973987340927, "learning_rate": 5.9976711180746946e-06, "loss": 0.002, "step": 13662 }, { "epoch": 0.754528385244091, "grad_norm": 0.1980658769607544, "learning_rate": 5.995117040919732e-06, "loss": 0.006, "step": 13663 }, { "epoch": 0.7545836094543849, "grad_norm": 0.13831712305545807, "learning_rate": 5.992563411820842e-06, "loss": 0.0026, "step": 13664 }, { "epoch": 0.7546388336646785, "grad_norm": 0.09769591689109802, "learning_rate": 5.990010230859726e-06, "loss": 0.003, "step": 13665 }, { "epoch": 0.7546940578749723, "grad_norm": 0.012984484434127808, "learning_rate": 5.987457498118063e-06, "loss": 0.0004, "step": 13666 }, { "epoch": 0.7547492820852661, "grad_norm": 0.15631897747516632, "learning_rate": 5.984905213677532e-06, "loss": 0.0045, "step": 13667 }, { "epoch": 0.75480450629556, "grad_norm": 2.3657994270324707, "learning_rate": 5.982353377619783e-06, "loss": 0.1534, "step": 13668 }, { "epoch": 0.7548597305058538, "grad_norm": 0.05299805849790573, "learning_rate": 5.979801990026455e-06, "loss": 0.0021, "step": 13669 }, { "epoch": 0.7549149547161476, "grad_norm": 3.5016119480133057, "learning_rate": 5.977251050979176e-06, "loss": 0.5023, "step": 13670 }, { "epoch": 0.7549701789264414, "grad_norm": 3.024026393890381, "learning_rate": 5.974700560559557e-06, "loss": 0.5677, "step": 13671 }, { "epoch": 0.7550254031367352, "grad_norm": 2.8472156524658203, "learning_rate": 5.9721505188491866e-06, "loss": 0.5753, "step": 13672 }, { "epoch": 0.755080627347029, "grad_norm": 0.040505703538656235, "learning_rate": 5.969600925929666e-06, "loss": 0.0017, "step": 13673 }, { "epoch": 0.7551358515573228, "grad_norm": 0.3885082006454468, "learning_rate": 5.967051781882554e-06, "loss": 0.0081, "step": 13674 }, { "epoch": 0.7551910757676166, "grad_norm": 2.980482816696167, "learning_rate": 5.964503086789404e-06, "loss": 0.6113, "step": 13675 }, { "epoch": 0.7552462999779103, "grad_norm": 9.199884414672852, "learning_rate": 5.961954840731752e-06, "loss": 1.4931, "step": 13676 }, { "epoch": 0.7553015241882041, "grad_norm": 0.20204800367355347, "learning_rate": 5.959407043791141e-06, "loss": 0.0036, "step": 13677 }, { "epoch": 0.7553567483984979, "grad_norm": 3.9815924167633057, "learning_rate": 5.95685969604906e-06, "loss": 1.4485, "step": 13678 }, { "epoch": 0.7554119726087917, "grad_norm": 0.24660034477710724, "learning_rate": 5.9543127975870206e-06, "loss": 0.0043, "step": 13679 }, { "epoch": 0.7554671968190855, "grad_norm": 1.6223150491714478, "learning_rate": 5.951766348486501e-06, "loss": 0.3404, "step": 13680 }, { "epoch": 0.7555224210293793, "grad_norm": 1.82943594455719, "learning_rate": 5.94922034882897e-06, "loss": 0.1109, "step": 13681 }, { "epoch": 0.7555776452396731, "grad_norm": 0.19754794239997864, "learning_rate": 5.946674798695875e-06, "loss": 0.0072, "step": 13682 }, { "epoch": 0.7556328694499669, "grad_norm": 4.1203932762146, "learning_rate": 5.944129698168668e-06, "loss": 0.4513, "step": 13683 }, { "epoch": 0.7556880936602607, "grad_norm": 1.4411050081253052, "learning_rate": 5.941585047328766e-06, "loss": 0.0199, "step": 13684 }, { "epoch": 0.7557433178705545, "grad_norm": 3.702561378479004, "learning_rate": 5.939040846257582e-06, "loss": 0.9535, "step": 13685 }, { "epoch": 0.7557985420808483, "grad_norm": 3.957550048828125, "learning_rate": 5.9364970950365046e-06, "loss": 0.2698, "step": 13686 }, { "epoch": 0.755853766291142, "grad_norm": 0.08149635046720505, "learning_rate": 5.933953793746934e-06, "loss": 0.0026, "step": 13687 }, { "epoch": 0.7559089905014358, "grad_norm": 2.2369794845581055, "learning_rate": 5.931410942470215e-06, "loss": 0.2181, "step": 13688 }, { "epoch": 0.7559642147117296, "grad_norm": 2.9713830947875977, "learning_rate": 5.928868541287715e-06, "loss": 0.5578, "step": 13689 }, { "epoch": 0.7560194389220234, "grad_norm": 1.7648402452468872, "learning_rate": 5.926326590280771e-06, "loss": 0.06, "step": 13690 }, { "epoch": 0.7560746631323172, "grad_norm": 4.127222061157227, "learning_rate": 5.923785089530705e-06, "loss": 0.8464, "step": 13691 }, { "epoch": 0.756129887342611, "grad_norm": 2.430804491043091, "learning_rate": 5.9212440391188204e-06, "loss": 0.4281, "step": 13692 }, { "epoch": 0.7561851115529048, "grad_norm": 0.4028548300266266, "learning_rate": 5.918703439126432e-06, "loss": 0.007, "step": 13693 }, { "epoch": 0.7562403357631986, "grad_norm": 3.2197554111480713, "learning_rate": 5.916163289634796e-06, "loss": 0.4509, "step": 13694 }, { "epoch": 0.7562955599734924, "grad_norm": 2.6725013256073, "learning_rate": 5.913623590725197e-06, "loss": 0.0508, "step": 13695 }, { "epoch": 0.7563507841837862, "grad_norm": 0.13621625304222107, "learning_rate": 5.911084342478883e-06, "loss": 0.0026, "step": 13696 }, { "epoch": 0.75640600839408, "grad_norm": 2.9772562980651855, "learning_rate": 5.908545544977089e-06, "loss": 0.2229, "step": 13697 }, { "epoch": 0.7564612326043738, "grad_norm": 2.284680128097534, "learning_rate": 5.906007198301034e-06, "loss": 0.3117, "step": 13698 }, { "epoch": 0.7565164568146675, "grad_norm": 0.003878387389704585, "learning_rate": 5.903469302531939e-06, "loss": 0.0001, "step": 13699 }, { "epoch": 0.7565716810249613, "grad_norm": 0.17858141660690308, "learning_rate": 5.900931857750991e-06, "loss": 0.0045, "step": 13700 }, { "epoch": 0.7566269052352551, "grad_norm": 0.27587106823921204, "learning_rate": 5.898394864039372e-06, "loss": 0.0068, "step": 13701 }, { "epoch": 0.7566821294455489, "grad_norm": 5.629361152648926, "learning_rate": 5.895858321478239e-06, "loss": 0.4152, "step": 13702 }, { "epoch": 0.7567373536558427, "grad_norm": 0.23725152015686035, "learning_rate": 5.893322230148766e-06, "loss": 0.0071, "step": 13703 }, { "epoch": 0.7567925778661365, "grad_norm": 2.8040242195129395, "learning_rate": 5.89078659013206e-06, "loss": 0.2872, "step": 13704 }, { "epoch": 0.7568478020764303, "grad_norm": 0.01040484569966793, "learning_rate": 5.888251401509266e-06, "loss": 0.0002, "step": 13705 }, { "epoch": 0.7569030262867241, "grad_norm": 2.573025941848755, "learning_rate": 5.885716664361483e-06, "loss": 0.5417, "step": 13706 }, { "epoch": 0.7569582504970179, "grad_norm": 4.549288272857666, "learning_rate": 5.883182378769805e-06, "loss": 1.423, "step": 13707 }, { "epoch": 0.7570134747073117, "grad_norm": 0.5220312476158142, "learning_rate": 5.8806485448153065e-06, "loss": 0.0089, "step": 13708 }, { "epoch": 0.7570686989176055, "grad_norm": 1.1645268201828003, "learning_rate": 5.87811516257907e-06, "loss": 0.056, "step": 13709 }, { "epoch": 0.7571239231278992, "grad_norm": 1.3480168581008911, "learning_rate": 5.875582232142119e-06, "loss": 0.0239, "step": 13710 }, { "epoch": 0.757179147338193, "grad_norm": 6.364842891693115, "learning_rate": 5.873049753585509e-06, "loss": 0.7294, "step": 13711 }, { "epoch": 0.7572343715484868, "grad_norm": 1.8669718503952026, "learning_rate": 5.8705177269902545e-06, "loss": 0.0871, "step": 13712 }, { "epoch": 0.7572895957587806, "grad_norm": 0.053493645042181015, "learning_rate": 5.867986152437364e-06, "loss": 0.0015, "step": 13713 }, { "epoch": 0.7573448199690744, "grad_norm": 4.000186443328857, "learning_rate": 5.865455030007823e-06, "loss": 0.5537, "step": 13714 }, { "epoch": 0.7574000441793682, "grad_norm": 0.39047423005104065, "learning_rate": 5.8629243597826205e-06, "loss": 0.0119, "step": 13715 }, { "epoch": 0.757455268389662, "grad_norm": 3.36134934425354, "learning_rate": 5.8603941418427136e-06, "loss": 0.7006, "step": 13716 }, { "epoch": 0.7575104925999558, "grad_norm": 0.8712213635444641, "learning_rate": 5.857864376269051e-06, "loss": 0.0171, "step": 13717 }, { "epoch": 0.7575657168102496, "grad_norm": 2.588935136795044, "learning_rate": 5.855335063142569e-06, "loss": 0.1613, "step": 13718 }, { "epoch": 0.7576209410205434, "grad_norm": 0.039092615246772766, "learning_rate": 5.852806202544186e-06, "loss": 0.0008, "step": 13719 }, { "epoch": 0.7576761652308373, "grad_norm": 0.0433773547410965, "learning_rate": 5.8502777945548085e-06, "loss": 0.0008, "step": 13720 }, { "epoch": 0.7577313894411309, "grad_norm": 0.055049750953912735, "learning_rate": 5.847749839255321e-06, "loss": 0.0019, "step": 13721 }, { "epoch": 0.7577866136514247, "grad_norm": 2.800867795944214, "learning_rate": 5.84522233672661e-06, "loss": 0.3991, "step": 13722 }, { "epoch": 0.7578418378617185, "grad_norm": 1.8443493843078613, "learning_rate": 5.842695287049536e-06, "loss": 0.0148, "step": 13723 }, { "epoch": 0.7578970620720124, "grad_norm": 0.015686683356761932, "learning_rate": 5.840168690304941e-06, "loss": 0.0005, "step": 13724 }, { "epoch": 0.7579522862823062, "grad_norm": 2.47188138961792, "learning_rate": 5.837642546573656e-06, "loss": 0.1884, "step": 13725 }, { "epoch": 0.7580075104926, "grad_norm": 0.01393298152834177, "learning_rate": 5.835116855936518e-06, "loss": 0.0003, "step": 13726 }, { "epoch": 0.7580627347028938, "grad_norm": 0.01319954078644514, "learning_rate": 5.8325916184743035e-06, "loss": 0.0004, "step": 13727 }, { "epoch": 0.7581179589131876, "grad_norm": 0.19781547784805298, "learning_rate": 5.8300668342678226e-06, "loss": 0.0048, "step": 13728 }, { "epoch": 0.7581731831234814, "grad_norm": 2.8751282691955566, "learning_rate": 5.827542503397843e-06, "loss": 0.3079, "step": 13729 }, { "epoch": 0.7582284073337752, "grad_norm": 1.5619010925292969, "learning_rate": 5.825018625945127e-06, "loss": 0.0301, "step": 13730 }, { "epoch": 0.758283631544069, "grad_norm": 2.715519428253174, "learning_rate": 5.822495201990412e-06, "loss": 0.1217, "step": 13731 }, { "epoch": 0.7583388557543627, "grad_norm": 0.061985988169908524, "learning_rate": 5.81997223161445e-06, "loss": 0.0012, "step": 13732 }, { "epoch": 0.7583940799646565, "grad_norm": 0.09427101165056229, "learning_rate": 5.817449714897934e-06, "loss": 0.0022, "step": 13733 }, { "epoch": 0.7584493041749503, "grad_norm": 0.9780398011207581, "learning_rate": 5.8149276519215825e-06, "loss": 0.025, "step": 13734 }, { "epoch": 0.7585045283852441, "grad_norm": 1.6092760562896729, "learning_rate": 5.812406042766079e-06, "loss": 0.1859, "step": 13735 }, { "epoch": 0.7585597525955379, "grad_norm": 0.22818179428577423, "learning_rate": 5.809884887512096e-06, "loss": 0.0039, "step": 13736 }, { "epoch": 0.7586149768058317, "grad_norm": 2.6739072799682617, "learning_rate": 5.8073641862402854e-06, "loss": 0.1059, "step": 13737 }, { "epoch": 0.7586702010161255, "grad_norm": 3.1895387172698975, "learning_rate": 5.804843939031308e-06, "loss": 0.3702, "step": 13738 }, { "epoch": 0.7587254252264193, "grad_norm": 0.2719350755214691, "learning_rate": 5.802324145965783e-06, "loss": 0.0076, "step": 13739 }, { "epoch": 0.7587806494367131, "grad_norm": 1.1887636184692383, "learning_rate": 5.799804807124328e-06, "loss": 0.0254, "step": 13740 }, { "epoch": 0.7588358736470069, "grad_norm": 0.08399812132120132, "learning_rate": 5.797285922587537e-06, "loss": 0.0017, "step": 13741 }, { "epoch": 0.7588910978573007, "grad_norm": 0.03886108472943306, "learning_rate": 5.7947674924360155e-06, "loss": 0.0012, "step": 13742 }, { "epoch": 0.7589463220675944, "grad_norm": 2.428860902786255, "learning_rate": 5.79224951675031e-06, "loss": 0.3462, "step": 13743 }, { "epoch": 0.7590015462778882, "grad_norm": 2.118110179901123, "learning_rate": 5.789731995610996e-06, "loss": 0.2238, "step": 13744 }, { "epoch": 0.759056770488182, "grad_norm": 1.0545328855514526, "learning_rate": 5.787214929098612e-06, "loss": 0.0336, "step": 13745 }, { "epoch": 0.7591119946984758, "grad_norm": 0.12712280452251434, "learning_rate": 5.784698317293682e-06, "loss": 0.0029, "step": 13746 }, { "epoch": 0.7591672189087696, "grad_norm": 0.053468577563762665, "learning_rate": 5.782182160276717e-06, "loss": 0.0013, "step": 13747 }, { "epoch": 0.7592224431190634, "grad_norm": 0.011126686818897724, "learning_rate": 5.779666458128232e-06, "loss": 0.0004, "step": 13748 }, { "epoch": 0.7592776673293572, "grad_norm": 0.008670303039252758, "learning_rate": 5.7771512109286905e-06, "loss": 0.0003, "step": 13749 }, { "epoch": 0.759332891539651, "grad_norm": 2.4719197750091553, "learning_rate": 5.774636418758577e-06, "loss": 0.3873, "step": 13750 }, { "epoch": 0.7593881157499448, "grad_norm": 0.009345822967588902, "learning_rate": 5.772122081698344e-06, "loss": 0.0003, "step": 13751 }, { "epoch": 0.7594433399602386, "grad_norm": 3.1200528144836426, "learning_rate": 5.769608199828429e-06, "loss": 0.3823, "step": 13752 }, { "epoch": 0.7594985641705324, "grad_norm": 2.105393409729004, "learning_rate": 5.7670947732292535e-06, "loss": 0.0694, "step": 13753 }, { "epoch": 0.7595537883808261, "grad_norm": 1.7671012878417969, "learning_rate": 5.764581801981241e-06, "loss": 0.0331, "step": 13754 }, { "epoch": 0.7596090125911199, "grad_norm": 0.039594486355781555, "learning_rate": 5.762069286164784e-06, "loss": 0.0013, "step": 13755 }, { "epoch": 0.7596642368014137, "grad_norm": 1.6710370779037476, "learning_rate": 5.759557225860266e-06, "loss": 0.2911, "step": 13756 }, { "epoch": 0.7597194610117075, "grad_norm": 0.0347989983856678, "learning_rate": 5.757045621148046e-06, "loss": 0.001, "step": 13757 }, { "epoch": 0.7597746852220013, "grad_norm": 0.017450423911213875, "learning_rate": 5.754534472108495e-06, "loss": 0.0003, "step": 13758 }, { "epoch": 0.7598299094322951, "grad_norm": 0.04474784433841705, "learning_rate": 5.752023778821929e-06, "loss": 0.0013, "step": 13759 }, { "epoch": 0.7598851336425889, "grad_norm": 2.810797691345215, "learning_rate": 5.749513541368692e-06, "loss": 0.1258, "step": 13760 }, { "epoch": 0.7599403578528827, "grad_norm": 2.4661881923675537, "learning_rate": 5.747003759829086e-06, "loss": 0.4288, "step": 13761 }, { "epoch": 0.7599955820631765, "grad_norm": 2.1833136081695557, "learning_rate": 5.744494434283405e-06, "loss": 0.2124, "step": 13762 }, { "epoch": 0.7600508062734703, "grad_norm": 0.05807226523756981, "learning_rate": 5.741985564811927e-06, "loss": 0.0013, "step": 13763 }, { "epoch": 0.7601060304837641, "grad_norm": 2.780452251434326, "learning_rate": 5.739477151494925e-06, "loss": 0.3337, "step": 13764 }, { "epoch": 0.7601612546940578, "grad_norm": 0.35467904806137085, "learning_rate": 5.736969194412649e-06, "loss": 0.0085, "step": 13765 }, { "epoch": 0.7602164789043516, "grad_norm": 3.0039923191070557, "learning_rate": 5.734461693645332e-06, "loss": 0.0557, "step": 13766 }, { "epoch": 0.7602717031146454, "grad_norm": 2.7013823986053467, "learning_rate": 5.731954649273199e-06, "loss": 0.4725, "step": 13767 }, { "epoch": 0.7603269273249392, "grad_norm": 2.568828582763672, "learning_rate": 5.729448061376455e-06, "loss": 0.0929, "step": 13768 }, { "epoch": 0.760382151535233, "grad_norm": 1.619368314743042, "learning_rate": 5.726941930035288e-06, "loss": 0.2421, "step": 13769 }, { "epoch": 0.7604373757455268, "grad_norm": 0.016889944672584534, "learning_rate": 5.7244362553298885e-06, "loss": 0.0006, "step": 13770 }, { "epoch": 0.7604925999558206, "grad_norm": 0.10050316154956818, "learning_rate": 5.721931037340413e-06, "loss": 0.0025, "step": 13771 }, { "epoch": 0.7605478241661144, "grad_norm": 3.6479859352111816, "learning_rate": 5.7194262761470134e-06, "loss": 0.2804, "step": 13772 }, { "epoch": 0.7606030483764082, "grad_norm": 3.3661069869995117, "learning_rate": 5.716921971829814e-06, "loss": 0.1862, "step": 13773 }, { "epoch": 0.760658272586702, "grad_norm": 2.80124831199646, "learning_rate": 5.714418124468956e-06, "loss": 0.0762, "step": 13774 }, { "epoch": 0.7607134967969958, "grad_norm": 0.11854500323534012, "learning_rate": 5.711914734144521e-06, "loss": 0.0024, "step": 13775 }, { "epoch": 0.7607687210072896, "grad_norm": 0.41390591859817505, "learning_rate": 5.709411800936615e-06, "loss": 0.011, "step": 13776 }, { "epoch": 0.7608239452175833, "grad_norm": 0.029782187193632126, "learning_rate": 5.706909324925307e-06, "loss": 0.0013, "step": 13777 }, { "epoch": 0.7608791694278771, "grad_norm": 3.698366403579712, "learning_rate": 5.704407306190662e-06, "loss": 0.2078, "step": 13778 }, { "epoch": 0.760934393638171, "grad_norm": 0.8081920742988586, "learning_rate": 5.701905744812726e-06, "loss": 0.0117, "step": 13779 }, { "epoch": 0.7609896178484647, "grad_norm": 5.781530380249023, "learning_rate": 5.699404640871522e-06, "loss": 0.4038, "step": 13780 }, { "epoch": 0.7610448420587586, "grad_norm": 0.23294073343276978, "learning_rate": 5.69690399444709e-06, "loss": 0.0068, "step": 13781 }, { "epoch": 0.7611000662690524, "grad_norm": 3.4091310501098633, "learning_rate": 5.694403805619404e-06, "loss": 0.3245, "step": 13782 }, { "epoch": 0.7611552904793462, "grad_norm": 0.8951425552368164, "learning_rate": 5.691904074468473e-06, "loss": 0.0318, "step": 13783 }, { "epoch": 0.76121051468964, "grad_norm": 0.004502413794398308, "learning_rate": 5.689404801074263e-06, "loss": 0.0002, "step": 13784 }, { "epoch": 0.7612657388999338, "grad_norm": 0.043302323669195175, "learning_rate": 5.6869059855167356e-06, "loss": 0.0015, "step": 13785 }, { "epoch": 0.7613209631102276, "grad_norm": 0.07796037942171097, "learning_rate": 5.684407627875828e-06, "loss": 0.0029, "step": 13786 }, { "epoch": 0.7613761873205214, "grad_norm": 3.9158506393432617, "learning_rate": 5.681909728231478e-06, "loss": 0.8419, "step": 13787 }, { "epoch": 0.7614314115308151, "grad_norm": 0.4283190071582794, "learning_rate": 5.679412286663601e-06, "loss": 0.004, "step": 13788 }, { "epoch": 0.7614866357411089, "grad_norm": 2.645339012145996, "learning_rate": 5.6769153032520905e-06, "loss": 0.4688, "step": 13789 }, { "epoch": 0.7615418599514027, "grad_norm": 2.401585340499878, "learning_rate": 5.674418778076838e-06, "loss": 0.1854, "step": 13790 }, { "epoch": 0.7615970841616965, "grad_norm": 0.07966674119234085, "learning_rate": 5.671922711217712e-06, "loss": 0.0022, "step": 13791 }, { "epoch": 0.7616523083719903, "grad_norm": 0.12103694677352905, "learning_rate": 5.669427102754561e-06, "loss": 0.0039, "step": 13792 }, { "epoch": 0.7617075325822841, "grad_norm": 2.0251457691192627, "learning_rate": 5.666931952767243e-06, "loss": 0.0561, "step": 13793 }, { "epoch": 0.7617627567925779, "grad_norm": 0.10266745835542679, "learning_rate": 5.664437261335574e-06, "loss": 0.0031, "step": 13794 }, { "epoch": 0.7618179810028717, "grad_norm": 2.415644407272339, "learning_rate": 5.661943028539369e-06, "loss": 0.4575, "step": 13795 }, { "epoch": 0.7618732052131655, "grad_norm": 4.794097423553467, "learning_rate": 5.659449254458418e-06, "loss": 0.0394, "step": 13796 }, { "epoch": 0.7619284294234593, "grad_norm": 1.1100276708602905, "learning_rate": 5.656955939172526e-06, "loss": 0.089, "step": 13797 }, { "epoch": 0.7619836536337531, "grad_norm": 5.033387660980225, "learning_rate": 5.654463082761432e-06, "loss": 0.592, "step": 13798 }, { "epoch": 0.7620388778440468, "grad_norm": 0.0549345538020134, "learning_rate": 5.65197068530491e-06, "loss": 0.0009, "step": 13799 }, { "epoch": 0.7620941020543406, "grad_norm": 0.19655384123325348, "learning_rate": 5.649478746882693e-06, "loss": 0.0056, "step": 13800 }, { "epoch": 0.7621493262646344, "grad_norm": 4.430357933044434, "learning_rate": 5.646987267574506e-06, "loss": 0.1526, "step": 13801 }, { "epoch": 0.7622045504749282, "grad_norm": 0.005096335429698229, "learning_rate": 5.644496247460049e-06, "loss": 0.0002, "step": 13802 }, { "epoch": 0.762259774685222, "grad_norm": 0.1338779628276825, "learning_rate": 5.6420056866190346e-06, "loss": 0.0019, "step": 13803 }, { "epoch": 0.7623149988955158, "grad_norm": 4.246066570281982, "learning_rate": 5.639515585131133e-06, "loss": 0.6687, "step": 13804 }, { "epoch": 0.7623702231058096, "grad_norm": 1.6292333602905273, "learning_rate": 5.637025943076009e-06, "loss": 0.3158, "step": 13805 }, { "epoch": 0.7624254473161034, "grad_norm": 9.172598838806152, "learning_rate": 5.634536760533309e-06, "loss": 0.6102, "step": 13806 }, { "epoch": 0.7624806715263972, "grad_norm": 0.2313813418149948, "learning_rate": 5.632048037582687e-06, "loss": 0.004, "step": 13807 }, { "epoch": 0.762535895736691, "grad_norm": 2.7407569885253906, "learning_rate": 5.629559774303741e-06, "loss": 0.0838, "step": 13808 }, { "epoch": 0.7625911199469848, "grad_norm": 0.17853985726833344, "learning_rate": 5.627071970776093e-06, "loss": 0.0057, "step": 13809 }, { "epoch": 0.7626463441572785, "grad_norm": 3.634784698486328, "learning_rate": 5.62458462707933e-06, "loss": 0.3183, "step": 13810 }, { "epoch": 0.7627015683675723, "grad_norm": 1.1402077674865723, "learning_rate": 5.622097743293031e-06, "loss": 0.0197, "step": 13811 }, { "epoch": 0.7627567925778661, "grad_norm": 0.009044448845088482, "learning_rate": 5.619611319496751e-06, "loss": 0.0003, "step": 13812 }, { "epoch": 0.7628120167881599, "grad_norm": 0.12443476915359497, "learning_rate": 5.617125355770057e-06, "loss": 0.0017, "step": 13813 }, { "epoch": 0.7628672409984537, "grad_norm": 3.58913516998291, "learning_rate": 5.614639852192456e-06, "loss": 0.6003, "step": 13814 }, { "epoch": 0.7629224652087475, "grad_norm": 3.256148099899292, "learning_rate": 5.612154808843486e-06, "loss": 0.1626, "step": 13815 }, { "epoch": 0.7629776894190413, "grad_norm": 0.05675778165459633, "learning_rate": 5.609670225802644e-06, "loss": 0.0016, "step": 13816 }, { "epoch": 0.7630329136293351, "grad_norm": 0.04120305925607681, "learning_rate": 5.60718610314942e-06, "loss": 0.0013, "step": 13817 }, { "epoch": 0.7630881378396289, "grad_norm": 1.8473608493804932, "learning_rate": 5.604702440963279e-06, "loss": 0.2123, "step": 13818 }, { "epoch": 0.7631433620499227, "grad_norm": 5.9257402420043945, "learning_rate": 5.6022192393236965e-06, "loss": 0.0723, "step": 13819 }, { "epoch": 0.7631985862602165, "grad_norm": 0.4784037172794342, "learning_rate": 5.599736498310106e-06, "loss": 0.104, "step": 13820 }, { "epoch": 0.7632538104705102, "grad_norm": 3.4691903591156006, "learning_rate": 5.597254218001944e-06, "loss": 0.7494, "step": 13821 }, { "epoch": 0.763309034680804, "grad_norm": 0.10557635128498077, "learning_rate": 5.594772398478614e-06, "loss": 0.0019, "step": 13822 }, { "epoch": 0.7633642588910978, "grad_norm": 0.36696869134902954, "learning_rate": 5.59229103981954e-06, "loss": 0.0074, "step": 13823 }, { "epoch": 0.7634194831013916, "grad_norm": 0.06010357663035393, "learning_rate": 5.5898101421040775e-06, "loss": 0.0013, "step": 13824 }, { "epoch": 0.7634747073116854, "grad_norm": 7.895251750946045, "learning_rate": 5.587329705411619e-06, "loss": 0.0755, "step": 13825 }, { "epoch": 0.7635299315219792, "grad_norm": 2.319924831390381, "learning_rate": 5.584849729821516e-06, "loss": 0.1504, "step": 13826 }, { "epoch": 0.763585155732273, "grad_norm": 2.895714044570923, "learning_rate": 5.582370215413107e-06, "loss": 0.2989, "step": 13827 }, { "epoch": 0.7636403799425668, "grad_norm": 0.06196967512369156, "learning_rate": 5.579891162265714e-06, "loss": 0.002, "step": 13828 }, { "epoch": 0.7636956041528606, "grad_norm": 6.1412672996521, "learning_rate": 5.5774125704586665e-06, "loss": 0.9002, "step": 13829 }, { "epoch": 0.7637508283631544, "grad_norm": 4.0400309562683105, "learning_rate": 5.574934440071238e-06, "loss": 0.2971, "step": 13830 }, { "epoch": 0.7638060525734482, "grad_norm": 3.2820682525634766, "learning_rate": 5.572456771182731e-06, "loss": 0.1503, "step": 13831 }, { "epoch": 0.7638612767837419, "grad_norm": 2.6921803951263428, "learning_rate": 5.569979563872403e-06, "loss": 0.2637, "step": 13832 }, { "epoch": 0.7639165009940357, "grad_norm": 2.7526357173919678, "learning_rate": 5.56750281821951e-06, "loss": 0.2768, "step": 13833 }, { "epoch": 0.7639717252043295, "grad_norm": 0.5097469091415405, "learning_rate": 5.5650265343032835e-06, "loss": 0.0085, "step": 13834 }, { "epoch": 0.7640269494146233, "grad_norm": 0.8259165287017822, "learning_rate": 5.562550712202959e-06, "loss": 0.0233, "step": 13835 }, { "epoch": 0.7640821736249171, "grad_norm": 0.04832955077290535, "learning_rate": 5.560075351997738e-06, "loss": 0.0016, "step": 13836 }, { "epoch": 0.764137397835211, "grad_norm": 0.1291591227054596, "learning_rate": 5.557600453766816e-06, "loss": 0.0028, "step": 13837 }, { "epoch": 0.7641926220455048, "grad_norm": 2.487868547439575, "learning_rate": 5.555126017589372e-06, "loss": 0.1557, "step": 13838 }, { "epoch": 0.7642478462557986, "grad_norm": 1.2723979949951172, "learning_rate": 5.5526520435445685e-06, "loss": 0.0542, "step": 13839 }, { "epoch": 0.7643030704660924, "grad_norm": 0.06098506599664688, "learning_rate": 5.550178531711554e-06, "loss": 0.0019, "step": 13840 }, { "epoch": 0.7643582946763862, "grad_norm": 0.009213654324412346, "learning_rate": 5.547705482169461e-06, "loss": 0.0003, "step": 13841 }, { "epoch": 0.76441351888668, "grad_norm": 2.1854913234710693, "learning_rate": 5.5452328949974185e-06, "loss": 0.1248, "step": 13842 }, { "epoch": 0.7644687430969738, "grad_norm": 2.3616862297058105, "learning_rate": 5.542760770274529e-06, "loss": 0.5113, "step": 13843 }, { "epoch": 0.7645239673072675, "grad_norm": 3.1720895767211914, "learning_rate": 5.5402891080798795e-06, "loss": 0.2935, "step": 13844 }, { "epoch": 0.7645791915175613, "grad_norm": 1.499024510383606, "learning_rate": 5.537817908492538e-06, "loss": 0.3801, "step": 13845 }, { "epoch": 0.7646344157278551, "grad_norm": 0.18678832054138184, "learning_rate": 5.535347171591588e-06, "loss": 0.0062, "step": 13846 }, { "epoch": 0.7646896399381489, "grad_norm": 0.03511182218790054, "learning_rate": 5.532876897456048e-06, "loss": 0.0007, "step": 13847 }, { "epoch": 0.7647448641484427, "grad_norm": 0.31936511397361755, "learning_rate": 5.530407086164968e-06, "loss": 0.0072, "step": 13848 }, { "epoch": 0.7648000883587365, "grad_norm": 0.22002512216567993, "learning_rate": 5.52793773779736e-06, "loss": 0.0034, "step": 13849 }, { "epoch": 0.7648553125690303, "grad_norm": 0.053773779422044754, "learning_rate": 5.525468852432223e-06, "loss": 0.0021, "step": 13850 }, { "epoch": 0.7649105367793241, "grad_norm": 0.022121883928775787, "learning_rate": 5.523000430148538e-06, "loss": 0.0004, "step": 13851 }, { "epoch": 0.7649657609896179, "grad_norm": 0.12854470312595367, "learning_rate": 5.520532471025295e-06, "loss": 0.0032, "step": 13852 }, { "epoch": 0.7650209851999117, "grad_norm": 0.12440811842679977, "learning_rate": 5.5180649751414285e-06, "loss": 0.0024, "step": 13853 }, { "epoch": 0.7650762094102055, "grad_norm": 0.5020081400871277, "learning_rate": 5.5155979425758966e-06, "loss": 0.0117, "step": 13854 }, { "epoch": 0.7651314336204992, "grad_norm": 5.382112979888916, "learning_rate": 5.513131373407623e-06, "loss": 0.3487, "step": 13855 }, { "epoch": 0.765186657830793, "grad_norm": 0.04576024040579796, "learning_rate": 5.510665267715518e-06, "loss": 0.0013, "step": 13856 }, { "epoch": 0.7652418820410868, "grad_norm": 3.230698347091675, "learning_rate": 5.508199625578477e-06, "loss": 0.2568, "step": 13857 }, { "epoch": 0.7652971062513806, "grad_norm": 6.136823654174805, "learning_rate": 5.505734447075391e-06, "loss": 0.6701, "step": 13858 }, { "epoch": 0.7653523304616744, "grad_norm": 0.1386137753725052, "learning_rate": 5.503269732285122e-06, "loss": 0.004, "step": 13859 }, { "epoch": 0.7654075546719682, "grad_norm": 5.660206317901611, "learning_rate": 5.500805481286524e-06, "loss": 0.4312, "step": 13860 }, { "epoch": 0.765462778882262, "grad_norm": 1.7429331541061401, "learning_rate": 5.498341694158431e-06, "loss": 0.0587, "step": 13861 }, { "epoch": 0.7655180030925558, "grad_norm": 0.8688969016075134, "learning_rate": 5.495878370979686e-06, "loss": 0.0334, "step": 13862 }, { "epoch": 0.7655732273028496, "grad_norm": 0.41678759455680847, "learning_rate": 5.493415511829068e-06, "loss": 0.0106, "step": 13863 }, { "epoch": 0.7656284515131434, "grad_norm": 0.036933742463588715, "learning_rate": 5.490953116785394e-06, "loss": 0.0008, "step": 13864 }, { "epoch": 0.7656836757234372, "grad_norm": 2.0599405765533447, "learning_rate": 5.488491185927434e-06, "loss": 0.0397, "step": 13865 }, { "epoch": 0.7657388999337309, "grad_norm": 0.11670172959566116, "learning_rate": 5.486029719333954e-06, "loss": 0.0021, "step": 13866 }, { "epoch": 0.7657941241440247, "grad_norm": 0.1533413827419281, "learning_rate": 5.4835687170836956e-06, "loss": 0.0037, "step": 13867 }, { "epoch": 0.7658493483543185, "grad_norm": 0.03694134205579758, "learning_rate": 5.481108179255414e-06, "loss": 0.0008, "step": 13868 }, { "epoch": 0.7659045725646123, "grad_norm": 0.1649317890405655, "learning_rate": 5.478648105927804e-06, "loss": 0.0036, "step": 13869 }, { "epoch": 0.7659597967749061, "grad_norm": 4.599065780639648, "learning_rate": 5.4761884971795865e-06, "loss": 0.5864, "step": 13870 }, { "epoch": 0.7660150209851999, "grad_norm": 3.361205816268921, "learning_rate": 5.473729353089446e-06, "loss": 0.2589, "step": 13871 }, { "epoch": 0.7660702451954937, "grad_norm": 4.767358303070068, "learning_rate": 5.4712706737360575e-06, "loss": 1.1827, "step": 13872 }, { "epoch": 0.7661254694057875, "grad_norm": 0.07948349416255951, "learning_rate": 5.4688124591980766e-06, "loss": 0.0021, "step": 13873 }, { "epoch": 0.7661806936160813, "grad_norm": 3.137843370437622, "learning_rate": 5.46635470955416e-06, "loss": 0.2057, "step": 13874 }, { "epoch": 0.7662359178263751, "grad_norm": 0.1802097111940384, "learning_rate": 5.463897424882931e-06, "loss": 0.0035, "step": 13875 }, { "epoch": 0.7662911420366689, "grad_norm": 4.037589073181152, "learning_rate": 5.461440605263007e-06, "loss": 0.4421, "step": 13876 }, { "epoch": 0.7663463662469626, "grad_norm": 0.49411845207214355, "learning_rate": 5.4589842507729785e-06, "loss": 0.0116, "step": 13877 }, { "epoch": 0.7664015904572564, "grad_norm": 1.572731852531433, "learning_rate": 5.456528361491455e-06, "loss": 0.0814, "step": 13878 }, { "epoch": 0.7664568146675502, "grad_norm": 2.561905860900879, "learning_rate": 5.454072937496979e-06, "loss": 0.2556, "step": 13879 }, { "epoch": 0.766512038877844, "grad_norm": 2.799030303955078, "learning_rate": 5.451617978868127e-06, "loss": 0.0829, "step": 13880 }, { "epoch": 0.7665672630881378, "grad_norm": 0.30794596672058105, "learning_rate": 5.449163485683433e-06, "loss": 0.0104, "step": 13881 }, { "epoch": 0.7666224872984316, "grad_norm": 2.7305195331573486, "learning_rate": 5.446709458021424e-06, "loss": 0.2941, "step": 13882 }, { "epoch": 0.7666777115087254, "grad_norm": 1.0359652042388916, "learning_rate": 5.444255895960604e-06, "loss": 0.0191, "step": 13883 }, { "epoch": 0.7667329357190192, "grad_norm": 5.886668682098389, "learning_rate": 5.441802799579483e-06, "loss": 0.5662, "step": 13884 }, { "epoch": 0.766788159929313, "grad_norm": 3.829876661300659, "learning_rate": 5.4393501689565344e-06, "loss": 0.2755, "step": 13885 }, { "epoch": 0.7668433841396068, "grad_norm": 0.3234696388244629, "learning_rate": 5.436898004170228e-06, "loss": 0.0075, "step": 13886 }, { "epoch": 0.7668986083499006, "grad_norm": 3.6987295150756836, "learning_rate": 5.4344463052990125e-06, "loss": 0.4618, "step": 13887 }, { "epoch": 0.7669538325601943, "grad_norm": 0.1573067307472229, "learning_rate": 5.4319950724213275e-06, "loss": 0.0039, "step": 13888 }, { "epoch": 0.7670090567704881, "grad_norm": 0.009824269451200962, "learning_rate": 5.429544305615586e-06, "loss": 0.0003, "step": 13889 }, { "epoch": 0.7670642809807819, "grad_norm": 3.1025872230529785, "learning_rate": 5.427094004960209e-06, "loss": 0.2262, "step": 13890 }, { "epoch": 0.7671195051910757, "grad_norm": 2.2308831214904785, "learning_rate": 5.424644170533582e-06, "loss": 0.1388, "step": 13891 }, { "epoch": 0.7671747294013695, "grad_norm": 0.035679277032613754, "learning_rate": 5.422194802414082e-06, "loss": 0.0011, "step": 13892 }, { "epoch": 0.7672299536116634, "grad_norm": 1.504915714263916, "learning_rate": 5.419745900680064e-06, "loss": 0.0241, "step": 13893 }, { "epoch": 0.7672851778219572, "grad_norm": 0.16258639097213745, "learning_rate": 5.417297465409899e-06, "loss": 0.004, "step": 13894 }, { "epoch": 0.767340402032251, "grad_norm": 1.3953932523727417, "learning_rate": 5.414849496681886e-06, "loss": 0.0084, "step": 13895 }, { "epoch": 0.7673956262425448, "grad_norm": 0.011676494032144547, "learning_rate": 5.41240199457437e-06, "loss": 0.0003, "step": 13896 }, { "epoch": 0.7674508504528386, "grad_norm": 7.541710376739502, "learning_rate": 5.4099549591656395e-06, "loss": 0.5631, "step": 13897 }, { "epoch": 0.7675060746631324, "grad_norm": 0.05618304759263992, "learning_rate": 5.407508390533989e-06, "loss": 0.0019, "step": 13898 }, { "epoch": 0.7675612988734261, "grad_norm": 0.05834906920790672, "learning_rate": 5.405062288757688e-06, "loss": 0.0011, "step": 13899 }, { "epoch": 0.7676165230837199, "grad_norm": 0.35227352380752563, "learning_rate": 5.402616653914985e-06, "loss": 0.0081, "step": 13900 }, { "epoch": 0.7676717472940137, "grad_norm": 6.495976448059082, "learning_rate": 5.400171486084147e-06, "loss": 1.4837, "step": 13901 }, { "epoch": 0.7677269715043075, "grad_norm": 6.827165603637695, "learning_rate": 5.397726785343374e-06, "loss": 0.8388, "step": 13902 }, { "epoch": 0.7677821957146013, "grad_norm": 0.373975545167923, "learning_rate": 5.3952825517709e-06, "loss": 0.0091, "step": 13903 }, { "epoch": 0.7678374199248951, "grad_norm": 3.875023365020752, "learning_rate": 5.3928387854449115e-06, "loss": 0.6174, "step": 13904 }, { "epoch": 0.7678926441351889, "grad_norm": 2.9259111881256104, "learning_rate": 5.390395486443598e-06, "loss": 0.3519, "step": 13905 }, { "epoch": 0.7679478683454827, "grad_norm": 6.607215881347656, "learning_rate": 5.3879526548451164e-06, "loss": 0.2062, "step": 13906 }, { "epoch": 0.7680030925557765, "grad_norm": 5.127948760986328, "learning_rate": 5.385510290727635e-06, "loss": 0.1978, "step": 13907 }, { "epoch": 0.7680583167660703, "grad_norm": 0.2747500240802765, "learning_rate": 5.383068394169284e-06, "loss": 0.0072, "step": 13908 }, { "epoch": 0.7681135409763641, "grad_norm": 0.023792369291186333, "learning_rate": 5.38062696524819e-06, "loss": 0.0007, "step": 13909 }, { "epoch": 0.7681687651866578, "grad_norm": 4.797098636627197, "learning_rate": 5.378186004042456e-06, "loss": 0.5759, "step": 13910 }, { "epoch": 0.7682239893969516, "grad_norm": 0.055463265627622604, "learning_rate": 5.375745510630182e-06, "loss": 0.0013, "step": 13911 }, { "epoch": 0.7682792136072454, "grad_norm": 0.008590365760028362, "learning_rate": 5.3733054850894325e-06, "loss": 0.0003, "step": 13912 }, { "epoch": 0.7683344378175392, "grad_norm": 0.9864419102668762, "learning_rate": 5.37086592749829e-06, "loss": 0.1646, "step": 13913 }, { "epoch": 0.768389662027833, "grad_norm": 0.10736080259084702, "learning_rate": 5.368426837934791e-06, "loss": 0.0023, "step": 13914 }, { "epoch": 0.7684448862381268, "grad_norm": 0.021675238385796547, "learning_rate": 5.365988216476974e-06, "loss": 0.0007, "step": 13915 }, { "epoch": 0.7685001104484206, "grad_norm": 0.026628660038113594, "learning_rate": 5.363550063202847e-06, "loss": 0.0008, "step": 13916 }, { "epoch": 0.7685553346587144, "grad_norm": 0.21786153316497803, "learning_rate": 5.361112378190436e-06, "loss": 0.0022, "step": 13917 }, { "epoch": 0.7686105588690082, "grad_norm": 0.41855794191360474, "learning_rate": 5.3586751615177015e-06, "loss": 0.0106, "step": 13918 }, { "epoch": 0.768665783079302, "grad_norm": 1.9937456846237183, "learning_rate": 5.356238413262638e-06, "loss": 0.1874, "step": 13919 }, { "epoch": 0.7687210072895958, "grad_norm": 0.011627896688878536, "learning_rate": 5.353802133503195e-06, "loss": 0.0004, "step": 13920 }, { "epoch": 0.7687762314998896, "grad_norm": 6.204183101654053, "learning_rate": 5.351366322317318e-06, "loss": 0.7404, "step": 13921 }, { "epoch": 0.7688314557101833, "grad_norm": 0.05813748389482498, "learning_rate": 5.348930979782929e-06, "loss": 0.0014, "step": 13922 }, { "epoch": 0.7688866799204771, "grad_norm": 8.207913398742676, "learning_rate": 5.346496105977954e-06, "loss": 0.0927, "step": 13923 }, { "epoch": 0.7689419041307709, "grad_norm": 0.14962531626224518, "learning_rate": 5.344061700980285e-06, "loss": 0.0028, "step": 13924 }, { "epoch": 0.7689971283410647, "grad_norm": 0.15229541063308716, "learning_rate": 5.3416277648678074e-06, "loss": 0.0042, "step": 13925 }, { "epoch": 0.7690523525513585, "grad_norm": 2.598418951034546, "learning_rate": 5.33919429771838e-06, "loss": 0.0454, "step": 13926 }, { "epoch": 0.7691075767616523, "grad_norm": 6.395741939544678, "learning_rate": 5.336761299609876e-06, "loss": 0.4068, "step": 13927 }, { "epoch": 0.7691628009719461, "grad_norm": 0.14683745801448822, "learning_rate": 5.334328770620112e-06, "loss": 0.0034, "step": 13928 }, { "epoch": 0.7692180251822399, "grad_norm": 3.9844248294830322, "learning_rate": 5.331896710826929e-06, "loss": 0.7653, "step": 13929 }, { "epoch": 0.7692732493925337, "grad_norm": 5.131086349487305, "learning_rate": 5.329465120308126e-06, "loss": 0.0295, "step": 13930 }, { "epoch": 0.7693284736028275, "grad_norm": 2.87680983543396, "learning_rate": 5.3270339991415e-06, "loss": 0.6106, "step": 13931 }, { "epoch": 0.7693836978131213, "grad_norm": 4.043137073516846, "learning_rate": 5.324603347404822e-06, "loss": 0.6465, "step": 13932 }, { "epoch": 0.769438922023415, "grad_norm": 0.20376169681549072, "learning_rate": 5.322173165175875e-06, "loss": 0.0041, "step": 13933 }, { "epoch": 0.7694941462337088, "grad_norm": 0.6178833246231079, "learning_rate": 5.319743452532382e-06, "loss": 0.0126, "step": 13934 }, { "epoch": 0.7695493704440026, "grad_norm": 0.23271989822387695, "learning_rate": 5.317314209552096e-06, "loss": 0.0053, "step": 13935 }, { "epoch": 0.7696045946542964, "grad_norm": 0.01402420736849308, "learning_rate": 5.314885436312727e-06, "loss": 0.0004, "step": 13936 }, { "epoch": 0.7696598188645902, "grad_norm": 0.353008508682251, "learning_rate": 5.312457132891977e-06, "loss": 0.0056, "step": 13937 }, { "epoch": 0.769715043074884, "grad_norm": 0.2768769860267639, "learning_rate": 5.310029299367534e-06, "loss": 0.0061, "step": 13938 }, { "epoch": 0.7697702672851778, "grad_norm": 0.054553113877773285, "learning_rate": 5.307601935817079e-06, "loss": 0.001, "step": 13939 }, { "epoch": 0.7698254914954716, "grad_norm": 0.10517354309558868, "learning_rate": 5.305175042318267e-06, "loss": 0.0041, "step": 13940 }, { "epoch": 0.7698807157057654, "grad_norm": 1.8901091814041138, "learning_rate": 5.302748618948739e-06, "loss": 0.3211, "step": 13941 }, { "epoch": 0.7699359399160592, "grad_norm": 4.0091986656188965, "learning_rate": 5.300322665786117e-06, "loss": 0.3654, "step": 13942 }, { "epoch": 0.769991164126353, "grad_norm": 4.304612159729004, "learning_rate": 5.297897182908034e-06, "loss": 0.7644, "step": 13943 }, { "epoch": 0.7700463883366467, "grad_norm": 0.02813665382564068, "learning_rate": 5.295472170392062e-06, "loss": 0.0009, "step": 13944 }, { "epoch": 0.7701016125469405, "grad_norm": 0.8696414232254028, "learning_rate": 5.293047628315804e-06, "loss": 0.0226, "step": 13945 }, { "epoch": 0.7701568367572343, "grad_norm": 3.735942840576172, "learning_rate": 5.290623556756822e-06, "loss": 0.3938, "step": 13946 }, { "epoch": 0.7702120609675281, "grad_norm": 3.0113673210144043, "learning_rate": 5.288199955792666e-06, "loss": 0.3778, "step": 13947 }, { "epoch": 0.770267285177822, "grad_norm": 0.03312673792243004, "learning_rate": 5.285776825500872e-06, "loss": 0.0006, "step": 13948 }, { "epoch": 0.7703225093881158, "grad_norm": 0.4014955759048462, "learning_rate": 5.283354165958978e-06, "loss": 0.0076, "step": 13949 }, { "epoch": 0.7703777335984096, "grad_norm": 4.82888126373291, "learning_rate": 5.280931977244468e-06, "loss": 0.9873, "step": 13950 }, { "epoch": 0.7704329578087034, "grad_norm": 4.017398357391357, "learning_rate": 5.2785102594348544e-06, "loss": 0.4821, "step": 13951 }, { "epoch": 0.7704881820189972, "grad_norm": 0.01661989651620388, "learning_rate": 5.276089012607608e-06, "loss": 0.0004, "step": 13952 }, { "epoch": 0.770543406229291, "grad_norm": 4.30396842956543, "learning_rate": 5.27366823684019e-06, "loss": 0.7123, "step": 13953 }, { "epoch": 0.7705986304395848, "grad_norm": 0.6042986512184143, "learning_rate": 5.271247932210047e-06, "loss": 0.0134, "step": 13954 }, { "epoch": 0.7706538546498785, "grad_norm": 2.0204544067382812, "learning_rate": 5.268828098794614e-06, "loss": 0.0727, "step": 13955 }, { "epoch": 0.7707090788601723, "grad_norm": 3.345473051071167, "learning_rate": 5.266408736671311e-06, "loss": 0.0933, "step": 13956 }, { "epoch": 0.7707643030704661, "grad_norm": 0.5354083776473999, "learning_rate": 5.263989845917537e-06, "loss": 0.0115, "step": 13957 }, { "epoch": 0.7708195272807599, "grad_norm": 3.3253390789031982, "learning_rate": 5.261571426610679e-06, "loss": 0.1828, "step": 13958 }, { "epoch": 0.7708747514910537, "grad_norm": 2.5909085273742676, "learning_rate": 5.25915347882811e-06, "loss": 0.1627, "step": 13959 }, { "epoch": 0.7709299757013475, "grad_norm": 0.18501316010951996, "learning_rate": 5.256736002647185e-06, "loss": 0.0048, "step": 13960 }, { "epoch": 0.7709851999116413, "grad_norm": 0.019431402906775475, "learning_rate": 5.254318998145243e-06, "loss": 0.0005, "step": 13961 }, { "epoch": 0.7710404241219351, "grad_norm": 0.14483067393302917, "learning_rate": 5.251902465399621e-06, "loss": 0.0046, "step": 13962 }, { "epoch": 0.7710956483322289, "grad_norm": 0.11747999489307404, "learning_rate": 5.249486404487625e-06, "loss": 0.0026, "step": 13963 }, { "epoch": 0.7711508725425227, "grad_norm": 2.8339006900787354, "learning_rate": 5.2470708154865525e-06, "loss": 0.4062, "step": 13964 }, { "epoch": 0.7712060967528165, "grad_norm": 0.18235521018505096, "learning_rate": 5.244655698473678e-06, "loss": 0.004, "step": 13965 }, { "epoch": 0.7712613209631102, "grad_norm": 0.018601182848215103, "learning_rate": 5.2422410535262846e-06, "loss": 0.0006, "step": 13966 }, { "epoch": 0.771316545173404, "grad_norm": 0.12957045435905457, "learning_rate": 5.239826880721604e-06, "loss": 0.0026, "step": 13967 }, { "epoch": 0.7713717693836978, "grad_norm": 3.587873697280884, "learning_rate": 5.237413180136886e-06, "loss": 0.6979, "step": 13968 }, { "epoch": 0.7714269935939916, "grad_norm": 0.029568377882242203, "learning_rate": 5.234999951849346e-06, "loss": 0.001, "step": 13969 }, { "epoch": 0.7714822178042854, "grad_norm": 5.391842842102051, "learning_rate": 5.232587195936197e-06, "loss": 0.3695, "step": 13970 }, { "epoch": 0.7715374420145792, "grad_norm": 1.8498085737228394, "learning_rate": 5.2301749124746145e-06, "loss": 0.4562, "step": 13971 }, { "epoch": 0.771592666224873, "grad_norm": 1.0426217317581177, "learning_rate": 5.227763101541796e-06, "loss": 0.0198, "step": 13972 }, { "epoch": 0.7716478904351668, "grad_norm": 0.16318918764591217, "learning_rate": 5.225351763214881e-06, "loss": 0.0048, "step": 13973 }, { "epoch": 0.7717031146454606, "grad_norm": 0.4798949956893921, "learning_rate": 5.22294089757103e-06, "loss": 0.0164, "step": 13974 }, { "epoch": 0.7717583388557544, "grad_norm": 0.02399994060397148, "learning_rate": 5.220530504687366e-06, "loss": 0.0008, "step": 13975 }, { "epoch": 0.7718135630660482, "grad_norm": 3.9383151531219482, "learning_rate": 5.2181205846410085e-06, "loss": 0.0953, "step": 13976 }, { "epoch": 0.7718687872763419, "grad_norm": 0.1426471322774887, "learning_rate": 5.21571113750905e-06, "loss": 0.0039, "step": 13977 }, { "epoch": 0.7719240114866357, "grad_norm": 1.4720901250839233, "learning_rate": 5.2133021633685856e-06, "loss": 0.025, "step": 13978 }, { "epoch": 0.7719792356969295, "grad_norm": 6.546457767486572, "learning_rate": 5.210893662296681e-06, "loss": 0.8429, "step": 13979 }, { "epoch": 0.7720344599072233, "grad_norm": 0.0840061828494072, "learning_rate": 5.20848563437039e-06, "loss": 0.0022, "step": 13980 }, { "epoch": 0.7720896841175171, "grad_norm": 0.14097246527671814, "learning_rate": 5.20607807966675e-06, "loss": 0.0033, "step": 13981 }, { "epoch": 0.7721449083278109, "grad_norm": 2.5120737552642822, "learning_rate": 5.2036709982627995e-06, "loss": 0.1594, "step": 13982 }, { "epoch": 0.7722001325381047, "grad_norm": 1.1492654085159302, "learning_rate": 5.201264390235525e-06, "loss": 0.0272, "step": 13983 }, { "epoch": 0.7722553567483985, "grad_norm": 4.117672920227051, "learning_rate": 5.198858255661939e-06, "loss": 0.0687, "step": 13984 }, { "epoch": 0.7723105809586923, "grad_norm": 0.05428839102387428, "learning_rate": 5.1964525946190124e-06, "loss": 0.0015, "step": 13985 }, { "epoch": 0.7723658051689861, "grad_norm": 1.9110348224639893, "learning_rate": 5.194047407183713e-06, "loss": 0.103, "step": 13986 }, { "epoch": 0.7724210293792799, "grad_norm": 0.05597997084259987, "learning_rate": 5.191642693432981e-06, "loss": 0.0016, "step": 13987 }, { "epoch": 0.7724762535895736, "grad_norm": 3.221179246902466, "learning_rate": 5.18923845344377e-06, "loss": 0.7153, "step": 13988 }, { "epoch": 0.7725314777998674, "grad_norm": 0.08470547199249268, "learning_rate": 5.186834687292972e-06, "loss": 0.0023, "step": 13989 }, { "epoch": 0.7725867020101612, "grad_norm": 1.379421353340149, "learning_rate": 5.18443139505751e-06, "loss": 0.0561, "step": 13990 }, { "epoch": 0.772641926220455, "grad_norm": 0.009819122031331062, "learning_rate": 5.182028576814266e-06, "loss": 0.0003, "step": 13991 }, { "epoch": 0.7726971504307488, "grad_norm": 2.7610504627227783, "learning_rate": 5.179626232640111e-06, "loss": 0.244, "step": 13992 }, { "epoch": 0.7727523746410426, "grad_norm": 0.14369772374629974, "learning_rate": 5.177224362611901e-06, "loss": 0.0033, "step": 13993 }, { "epoch": 0.7728075988513364, "grad_norm": 0.2556096911430359, "learning_rate": 5.174822966806488e-06, "loss": 0.0067, "step": 13994 }, { "epoch": 0.7728628230616302, "grad_norm": 0.04481365159153938, "learning_rate": 5.172422045300693e-06, "loss": 0.0013, "step": 13995 }, { "epoch": 0.772918047271924, "grad_norm": 2.3561978340148926, "learning_rate": 5.170021598171329e-06, "loss": 0.3263, "step": 13996 }, { "epoch": 0.7729732714822178, "grad_norm": 0.13118554651737213, "learning_rate": 5.167621625495188e-06, "loss": 0.0032, "step": 13997 }, { "epoch": 0.7730284956925116, "grad_norm": 0.03393881395459175, "learning_rate": 5.165222127349065e-06, "loss": 0.0008, "step": 13998 }, { "epoch": 0.7730837199028054, "grad_norm": 1.2784711122512817, "learning_rate": 5.1628231038097105e-06, "loss": 0.0303, "step": 13999 }, { "epoch": 0.7731389441130991, "grad_norm": 0.07937870919704437, "learning_rate": 5.160424554953891e-06, "loss": 0.0026, "step": 14000 }, { "epoch": 0.7731941683233929, "grad_norm": 6.305591583251953, "learning_rate": 5.158026480858336e-06, "loss": 0.5294, "step": 14001 }, { "epoch": 0.7732493925336867, "grad_norm": 0.2649669349193573, "learning_rate": 5.155628881599766e-06, "loss": 0.0057, "step": 14002 }, { "epoch": 0.7733046167439805, "grad_norm": 0.11215628683567047, "learning_rate": 5.1532317572548815e-06, "loss": 0.0025, "step": 14003 }, { "epoch": 0.7733598409542743, "grad_norm": 0.15751425921916962, "learning_rate": 5.150835107900387e-06, "loss": 0.0041, "step": 14004 }, { "epoch": 0.7734150651645681, "grad_norm": 3.6303441524505615, "learning_rate": 5.148438933612951e-06, "loss": 0.3289, "step": 14005 }, { "epoch": 0.773470289374862, "grad_norm": 5.442107200622559, "learning_rate": 5.146043234469235e-06, "loss": 1.0215, "step": 14006 }, { "epoch": 0.7735255135851558, "grad_norm": 0.3739975094795227, "learning_rate": 5.143648010545883e-06, "loss": 0.0062, "step": 14007 }, { "epoch": 0.7735807377954496, "grad_norm": 3.9330568313598633, "learning_rate": 5.141253261919525e-06, "loss": 0.5135, "step": 14008 }, { "epoch": 0.7736359620057434, "grad_norm": 2.4754481315612793, "learning_rate": 5.138858988666771e-06, "loss": 0.5368, "step": 14009 }, { "epoch": 0.7736911862160372, "grad_norm": 2.619248151779175, "learning_rate": 5.1364651908642286e-06, "loss": 0.5417, "step": 14010 }, { "epoch": 0.7737464104263309, "grad_norm": 3.543931722640991, "learning_rate": 5.134071868588482e-06, "loss": 0.4557, "step": 14011 }, { "epoch": 0.7738016346366247, "grad_norm": 0.23279821872711182, "learning_rate": 5.131679021916096e-06, "loss": 0.0043, "step": 14012 }, { "epoch": 0.7738568588469185, "grad_norm": 0.017314355820417404, "learning_rate": 5.1292866509236215e-06, "loss": 0.0006, "step": 14013 }, { "epoch": 0.7739120830572123, "grad_norm": 2.9335930347442627, "learning_rate": 5.126894755687615e-06, "loss": 0.221, "step": 14014 }, { "epoch": 0.7739673072675061, "grad_norm": 0.06717178970575333, "learning_rate": 5.124503336284574e-06, "loss": 0.0015, "step": 14015 }, { "epoch": 0.7740225314777999, "grad_norm": 3.60481333732605, "learning_rate": 5.122112392791025e-06, "loss": 0.5311, "step": 14016 }, { "epoch": 0.7740777556880937, "grad_norm": 1.202843427658081, "learning_rate": 5.119721925283459e-06, "loss": 0.0311, "step": 14017 }, { "epoch": 0.7741329798983875, "grad_norm": 3.6058006286621094, "learning_rate": 5.117331933838347e-06, "loss": 0.6634, "step": 14018 }, { "epoch": 0.7741882041086813, "grad_norm": 0.2533183991909027, "learning_rate": 5.114942418532158e-06, "loss": 0.0078, "step": 14019 }, { "epoch": 0.7742434283189751, "grad_norm": 2.9049630165100098, "learning_rate": 5.112553379441332e-06, "loss": 0.2809, "step": 14020 }, { "epoch": 0.7742986525292689, "grad_norm": 0.5186722278594971, "learning_rate": 5.110164816642315e-06, "loss": 0.0166, "step": 14021 }, { "epoch": 0.7743538767395626, "grad_norm": 3.4068875312805176, "learning_rate": 5.107776730211505e-06, "loss": 0.1797, "step": 14022 }, { "epoch": 0.7744091009498564, "grad_norm": 0.044426046311855316, "learning_rate": 5.105389120225319e-06, "loss": 0.0011, "step": 14023 }, { "epoch": 0.7744643251601502, "grad_norm": 4.995096683502197, "learning_rate": 5.103001986760139e-06, "loss": 0.5506, "step": 14024 }, { "epoch": 0.774519549370444, "grad_norm": 2.3202853202819824, "learning_rate": 5.100615329892336e-06, "loss": 0.1614, "step": 14025 }, { "epoch": 0.7745747735807378, "grad_norm": 4.04636287689209, "learning_rate": 5.098229149698257e-06, "loss": 0.8024, "step": 14026 }, { "epoch": 0.7746299977910316, "grad_norm": 0.06947916001081467, "learning_rate": 5.095843446254263e-06, "loss": 0.0021, "step": 14027 }, { "epoch": 0.7746852220013254, "grad_norm": 0.06332292407751083, "learning_rate": 5.093458219636655e-06, "loss": 0.0016, "step": 14028 }, { "epoch": 0.7747404462116192, "grad_norm": 0.9943709373474121, "learning_rate": 5.091073469921764e-06, "loss": 0.0359, "step": 14029 }, { "epoch": 0.774795670421913, "grad_norm": 1.8782613277435303, "learning_rate": 5.088689197185877e-06, "loss": 0.1431, "step": 14030 }, { "epoch": 0.7748508946322068, "grad_norm": 1.4947655200958252, "learning_rate": 5.086305401505269e-06, "loss": 0.0659, "step": 14031 }, { "epoch": 0.7749061188425006, "grad_norm": 0.20606985688209534, "learning_rate": 5.083922082956208e-06, "loss": 0.0043, "step": 14032 }, { "epoch": 0.7749613430527943, "grad_norm": 2.173557758331299, "learning_rate": 5.081539241614946e-06, "loss": 0.3264, "step": 14033 }, { "epoch": 0.7750165672630881, "grad_norm": 0.0544578842818737, "learning_rate": 5.079156877557714e-06, "loss": 0.0016, "step": 14034 }, { "epoch": 0.7750717914733819, "grad_norm": 2.6059906482696533, "learning_rate": 5.076774990860733e-06, "loss": 0.3037, "step": 14035 }, { "epoch": 0.7751270156836757, "grad_norm": 0.7457542419433594, "learning_rate": 5.074393581600199e-06, "loss": 0.1122, "step": 14036 }, { "epoch": 0.7751822398939695, "grad_norm": 0.2185688018798828, "learning_rate": 5.072012649852318e-06, "loss": 0.0046, "step": 14037 }, { "epoch": 0.7752374641042633, "grad_norm": 0.02882034331560135, "learning_rate": 5.069632195693237e-06, "loss": 0.0011, "step": 14038 }, { "epoch": 0.7752926883145571, "grad_norm": 0.3856576681137085, "learning_rate": 5.0672522191991325e-06, "loss": 0.0051, "step": 14039 }, { "epoch": 0.7753479125248509, "grad_norm": 0.04571153596043587, "learning_rate": 5.064872720446144e-06, "loss": 0.0009, "step": 14040 }, { "epoch": 0.7754031367351447, "grad_norm": 0.03138194978237152, "learning_rate": 5.062493699510391e-06, "loss": 0.0008, "step": 14041 }, { "epoch": 0.7754583609454385, "grad_norm": 0.07833263278007507, "learning_rate": 5.060115156467989e-06, "loss": 0.0022, "step": 14042 }, { "epoch": 0.7755135851557323, "grad_norm": 3.6397898197174072, "learning_rate": 5.0577370913950365e-06, "loss": 0.4089, "step": 14043 }, { "epoch": 0.775568809366026, "grad_norm": 3.4799365997314453, "learning_rate": 5.055359504367616e-06, "loss": 0.3188, "step": 14044 }, { "epoch": 0.7756240335763198, "grad_norm": 4.5680694580078125, "learning_rate": 5.05298239546179e-06, "loss": 0.4357, "step": 14045 }, { "epoch": 0.7756792577866136, "grad_norm": 0.0572066456079483, "learning_rate": 5.050605764753609e-06, "loss": 0.0013, "step": 14046 }, { "epoch": 0.7757344819969074, "grad_norm": 0.35771310329437256, "learning_rate": 5.048229612319109e-06, "loss": 0.0101, "step": 14047 }, { "epoch": 0.7757897062072012, "grad_norm": 1.1203337907791138, "learning_rate": 5.045853938234302e-06, "loss": 0.0241, "step": 14048 }, { "epoch": 0.775844930417495, "grad_norm": 0.24921506643295288, "learning_rate": 5.043478742575208e-06, "loss": 0.0068, "step": 14049 }, { "epoch": 0.7759001546277888, "grad_norm": 1.6565115451812744, "learning_rate": 5.041104025417807e-06, "loss": 0.0394, "step": 14050 }, { "epoch": 0.7759553788380826, "grad_norm": 0.1091558113694191, "learning_rate": 5.038729786838075e-06, "loss": 0.0034, "step": 14051 }, { "epoch": 0.7760106030483764, "grad_norm": 0.8036861419677734, "learning_rate": 5.036356026911964e-06, "loss": 0.0258, "step": 14052 }, { "epoch": 0.7760658272586702, "grad_norm": 0.01763233356177807, "learning_rate": 5.033982745715435e-06, "loss": 0.0006, "step": 14053 }, { "epoch": 0.776121051468964, "grad_norm": 0.12216638028621674, "learning_rate": 5.031609943324394e-06, "loss": 0.0022, "step": 14054 }, { "epoch": 0.7761762756792577, "grad_norm": 0.2874247133731842, "learning_rate": 5.029237619814769e-06, "loss": 0.0073, "step": 14055 }, { "epoch": 0.7762314998895515, "grad_norm": 9.001016616821289, "learning_rate": 5.026865775262451e-06, "loss": 1.8628, "step": 14056 }, { "epoch": 0.7762867240998453, "grad_norm": 4.419386386871338, "learning_rate": 5.024494409743323e-06, "loss": 0.051, "step": 14057 }, { "epoch": 0.7763419483101391, "grad_norm": 1.1714447736740112, "learning_rate": 5.022123523333249e-06, "loss": 0.0257, "step": 14058 }, { "epoch": 0.7763971725204329, "grad_norm": 2.3968307971954346, "learning_rate": 5.019753116108088e-06, "loss": 0.3837, "step": 14059 }, { "epoch": 0.7764523967307267, "grad_norm": 0.012007472105324268, "learning_rate": 5.017383188143672e-06, "loss": 0.0003, "step": 14060 }, { "epoch": 0.7765076209410205, "grad_norm": 0.01940101943910122, "learning_rate": 5.015013739515821e-06, "loss": 0.0004, "step": 14061 }, { "epoch": 0.7765628451513144, "grad_norm": 0.1314772218465805, "learning_rate": 5.012644770300335e-06, "loss": 0.0034, "step": 14062 }, { "epoch": 0.7766180693616082, "grad_norm": 0.1760765165090561, "learning_rate": 5.010276280573023e-06, "loss": 0.0067, "step": 14063 }, { "epoch": 0.776673293571902, "grad_norm": 0.4115133285522461, "learning_rate": 5.007908270409634e-06, "loss": 0.0065, "step": 14064 }, { "epoch": 0.7767285177821958, "grad_norm": 0.8549004793167114, "learning_rate": 5.005540739885946e-06, "loss": 0.0377, "step": 14065 }, { "epoch": 0.7767837419924896, "grad_norm": 0.27070242166519165, "learning_rate": 5.003173689077696e-06, "loss": 0.0088, "step": 14066 }, { "epoch": 0.7768389662027833, "grad_norm": 0.21705372631549835, "learning_rate": 5.000807118060616e-06, "loss": 0.0073, "step": 14067 }, { "epoch": 0.7768941904130771, "grad_norm": 0.01782028190791607, "learning_rate": 4.998441026910408e-06, "loss": 0.0005, "step": 14068 }, { "epoch": 0.7769494146233709, "grad_norm": 5.456303119659424, "learning_rate": 4.996075415702792e-06, "loss": 1.3016, "step": 14069 }, { "epoch": 0.7770046388336647, "grad_norm": 0.6928568482398987, "learning_rate": 4.993710284513426e-06, "loss": 0.0172, "step": 14070 }, { "epoch": 0.7770598630439585, "grad_norm": 0.13495367765426636, "learning_rate": 4.991345633417997e-06, "loss": 0.0027, "step": 14071 }, { "epoch": 0.7771150872542523, "grad_norm": 1.5184804201126099, "learning_rate": 4.988981462492148e-06, "loss": 0.0527, "step": 14072 }, { "epoch": 0.7771703114645461, "grad_norm": 1.5619044303894043, "learning_rate": 4.986617771811515e-06, "loss": 0.0604, "step": 14073 }, { "epoch": 0.7772255356748399, "grad_norm": 0.04538829252123833, "learning_rate": 4.9842545614517156e-06, "loss": 0.0014, "step": 14074 }, { "epoch": 0.7772807598851337, "grad_norm": 0.06880617886781693, "learning_rate": 4.981891831488368e-06, "loss": 0.0027, "step": 14075 }, { "epoch": 0.7773359840954275, "grad_norm": 2.648314952850342, "learning_rate": 4.9795295819970535e-06, "loss": 0.0725, "step": 14076 }, { "epoch": 0.7773912083057213, "grad_norm": 3.2686939239501953, "learning_rate": 4.97716781305335e-06, "loss": 0.5731, "step": 14077 }, { "epoch": 0.777446432516015, "grad_norm": 3.9588942527770996, "learning_rate": 4.974806524732816e-06, "loss": 0.6056, "step": 14078 }, { "epoch": 0.7775016567263088, "grad_norm": 2.9967098236083984, "learning_rate": 4.972445717110997e-06, "loss": 0.193, "step": 14079 }, { "epoch": 0.7775568809366026, "grad_norm": 2.4372775554656982, "learning_rate": 4.970085390263419e-06, "loss": 0.2563, "step": 14080 }, { "epoch": 0.7776121051468964, "grad_norm": 1.3545441627502441, "learning_rate": 4.967725544265593e-06, "loss": 0.0471, "step": 14081 }, { "epoch": 0.7776673293571902, "grad_norm": 6.954972743988037, "learning_rate": 4.965366179193027e-06, "loss": 1.3362, "step": 14082 }, { "epoch": 0.777722553567484, "grad_norm": 0.01820106990635395, "learning_rate": 4.963007295121201e-06, "loss": 0.0005, "step": 14083 }, { "epoch": 0.7777777777777778, "grad_norm": 4.6031413078308105, "learning_rate": 4.960648892125577e-06, "loss": 0.7561, "step": 14084 }, { "epoch": 0.7778330019880716, "grad_norm": 0.36559411883354187, "learning_rate": 4.958290970281605e-06, "loss": 0.0128, "step": 14085 }, { "epoch": 0.7778882261983654, "grad_norm": 5.283080577850342, "learning_rate": 4.955933529664738e-06, "loss": 0.113, "step": 14086 }, { "epoch": 0.7779434504086592, "grad_norm": 1.7773114442825317, "learning_rate": 4.953576570350376e-06, "loss": 0.028, "step": 14087 }, { "epoch": 0.777998674618953, "grad_norm": 5.5784406661987305, "learning_rate": 4.95122009241394e-06, "loss": 1.6741, "step": 14088 }, { "epoch": 0.7780538988292467, "grad_norm": 2.557349920272827, "learning_rate": 4.948864095930814e-06, "loss": 0.1456, "step": 14089 }, { "epoch": 0.7781091230395405, "grad_norm": 0.1110539510846138, "learning_rate": 4.946508580976377e-06, "loss": 0.0034, "step": 14090 }, { "epoch": 0.7781643472498343, "grad_norm": 3.3330838680267334, "learning_rate": 4.944153547625979e-06, "loss": 0.5141, "step": 14091 }, { "epoch": 0.7782195714601281, "grad_norm": 3.845974922180176, "learning_rate": 4.94179899595498e-06, "loss": 0.3602, "step": 14092 }, { "epoch": 0.7782747956704219, "grad_norm": 1.1843397617340088, "learning_rate": 4.93944492603869e-06, "loss": 0.0593, "step": 14093 }, { "epoch": 0.7783300198807157, "grad_norm": 3.7327253818511963, "learning_rate": 4.93709133795244e-06, "loss": 0.1978, "step": 14094 }, { "epoch": 0.7783852440910095, "grad_norm": 3.949106216430664, "learning_rate": 4.934738231771519e-06, "loss": 0.6407, "step": 14095 }, { "epoch": 0.7784404683013033, "grad_norm": 1.4803158044815063, "learning_rate": 4.932385607571208e-06, "loss": 0.0292, "step": 14096 }, { "epoch": 0.7784956925115971, "grad_norm": 0.010268357582390308, "learning_rate": 4.930033465426776e-06, "loss": 0.0003, "step": 14097 }, { "epoch": 0.7785509167218909, "grad_norm": 2.7834067344665527, "learning_rate": 4.927681805413478e-06, "loss": 0.6583, "step": 14098 }, { "epoch": 0.7786061409321847, "grad_norm": 3.7480175495147705, "learning_rate": 4.9253306276065505e-06, "loss": 0.1289, "step": 14099 }, { "epoch": 0.7786613651424784, "grad_norm": 1.3942705392837524, "learning_rate": 4.922979932081211e-06, "loss": 0.0493, "step": 14100 }, { "epoch": 0.7787165893527722, "grad_norm": 1.2052608728408813, "learning_rate": 4.92062971891266e-06, "loss": 0.0268, "step": 14101 }, { "epoch": 0.778771813563066, "grad_norm": 0.027571948245167732, "learning_rate": 4.918279988176105e-06, "loss": 0.0007, "step": 14102 }, { "epoch": 0.7788270377733598, "grad_norm": 0.15173792839050293, "learning_rate": 4.915930739946695e-06, "loss": 0.0035, "step": 14103 }, { "epoch": 0.7788822619836536, "grad_norm": 1.7471598386764526, "learning_rate": 4.913581974299612e-06, "loss": 0.0197, "step": 14104 }, { "epoch": 0.7789374861939474, "grad_norm": 0.03394694626331329, "learning_rate": 4.911233691309989e-06, "loss": 0.0007, "step": 14105 }, { "epoch": 0.7789927104042412, "grad_norm": 1.6682764291763306, "learning_rate": 4.908885891052957e-06, "loss": 0.0865, "step": 14106 }, { "epoch": 0.779047934614535, "grad_norm": 1.8663792610168457, "learning_rate": 4.906538573603621e-06, "loss": 0.0525, "step": 14107 }, { "epoch": 0.7791031588248288, "grad_norm": 3.579091787338257, "learning_rate": 4.9041917390370985e-06, "loss": 0.5025, "step": 14108 }, { "epoch": 0.7791583830351226, "grad_norm": 1.412693738937378, "learning_rate": 4.901845387428445e-06, "loss": 0.0545, "step": 14109 }, { "epoch": 0.7792136072454164, "grad_norm": 3.0066068172454834, "learning_rate": 4.899499518852746e-06, "loss": 0.0753, "step": 14110 }, { "epoch": 0.7792688314557101, "grad_norm": 1.536535382270813, "learning_rate": 4.897154133385049e-06, "loss": 0.1627, "step": 14111 }, { "epoch": 0.7793240556660039, "grad_norm": 3.8547585010528564, "learning_rate": 4.894809231100384e-06, "loss": 0.4118, "step": 14112 }, { "epoch": 0.7793792798762977, "grad_norm": 3.6796724796295166, "learning_rate": 4.89246481207377e-06, "loss": 0.4833, "step": 14113 }, { "epoch": 0.7794345040865915, "grad_norm": 0.550138533115387, "learning_rate": 4.890120876380222e-06, "loss": 0.0207, "step": 14114 }, { "epoch": 0.7794897282968853, "grad_norm": 3.8099279403686523, "learning_rate": 4.8877774240947214e-06, "loss": 0.6864, "step": 14115 }, { "epoch": 0.7795449525071791, "grad_norm": 1.8500345945358276, "learning_rate": 4.885434455292246e-06, "loss": 0.1052, "step": 14116 }, { "epoch": 0.779600176717473, "grad_norm": 0.05865345150232315, "learning_rate": 4.883091970047744e-06, "loss": 0.0018, "step": 14117 }, { "epoch": 0.7796554009277668, "grad_norm": 0.577785313129425, "learning_rate": 4.8807499684361785e-06, "loss": 0.0164, "step": 14118 }, { "epoch": 0.7797106251380606, "grad_norm": 0.1253131628036499, "learning_rate": 4.878408450532452e-06, "loss": 0.0029, "step": 14119 }, { "epoch": 0.7797658493483544, "grad_norm": 1.033726453781128, "learning_rate": 4.876067416411494e-06, "loss": 0.0315, "step": 14120 }, { "epoch": 0.7798210735586482, "grad_norm": 0.2209935039281845, "learning_rate": 4.873726866148196e-06, "loss": 0.0086, "step": 14121 }, { "epoch": 0.7798762977689419, "grad_norm": 3.979649543762207, "learning_rate": 4.8713867998174365e-06, "loss": 0.7338, "step": 14122 }, { "epoch": 0.7799315219792357, "grad_norm": 2.692117929458618, "learning_rate": 4.8690472174940785e-06, "loss": 0.5588, "step": 14123 }, { "epoch": 0.7799867461895295, "grad_norm": 1.555490493774414, "learning_rate": 4.866708119252981e-06, "loss": 0.1412, "step": 14124 }, { "epoch": 0.7800419703998233, "grad_norm": 0.4919185936450958, "learning_rate": 4.864369505168973e-06, "loss": 0.015, "step": 14125 }, { "epoch": 0.7800971946101171, "grad_norm": 1.3960281610488892, "learning_rate": 4.862031375316876e-06, "loss": 0.0975, "step": 14126 }, { "epoch": 0.7801524188204109, "grad_norm": 0.7635430097579956, "learning_rate": 4.8596937297714885e-06, "loss": 0.0194, "step": 14127 }, { "epoch": 0.7802076430307047, "grad_norm": 0.0665493756532669, "learning_rate": 4.857356568607601e-06, "loss": 0.002, "step": 14128 }, { "epoch": 0.7802628672409985, "grad_norm": 0.8052455186843872, "learning_rate": 4.855019891899981e-06, "loss": 0.0295, "step": 14129 }, { "epoch": 0.7803180914512923, "grad_norm": 0.05845096334815025, "learning_rate": 4.852683699723397e-06, "loss": 0.0012, "step": 14130 }, { "epoch": 0.7803733156615861, "grad_norm": 0.09511196613311768, "learning_rate": 4.850347992152584e-06, "loss": 0.0033, "step": 14131 }, { "epoch": 0.7804285398718799, "grad_norm": 0.03341620787978172, "learning_rate": 4.848012769262267e-06, "loss": 0.0012, "step": 14132 }, { "epoch": 0.7804837640821736, "grad_norm": 0.05851595103740692, "learning_rate": 4.845678031127152e-06, "loss": 0.0017, "step": 14133 }, { "epoch": 0.7805389882924674, "grad_norm": 0.031243253499269485, "learning_rate": 4.843343777821952e-06, "loss": 0.001, "step": 14134 }, { "epoch": 0.7805942125027612, "grad_norm": 1.252238154411316, "learning_rate": 4.841010009421321e-06, "loss": 0.0418, "step": 14135 }, { "epoch": 0.780649436713055, "grad_norm": 0.019673049449920654, "learning_rate": 4.83867672599994e-06, "loss": 0.0005, "step": 14136 }, { "epoch": 0.7807046609233488, "grad_norm": 2.2820332050323486, "learning_rate": 4.8363439276324545e-06, "loss": 0.437, "step": 14137 }, { "epoch": 0.7807598851336426, "grad_norm": 0.0225947555154562, "learning_rate": 4.834011614393495e-06, "loss": 0.0005, "step": 14138 }, { "epoch": 0.7808151093439364, "grad_norm": 0.810620903968811, "learning_rate": 4.831679786357679e-06, "loss": 0.0188, "step": 14139 }, { "epoch": 0.7808703335542302, "grad_norm": 0.011225448921322823, "learning_rate": 4.829348443599604e-06, "loss": 0.0005, "step": 14140 }, { "epoch": 0.780925557764524, "grad_norm": 2.0601391792297363, "learning_rate": 4.827017586193874e-06, "loss": 0.1901, "step": 14141 }, { "epoch": 0.7809807819748178, "grad_norm": 4.214131832122803, "learning_rate": 4.824687214215034e-06, "loss": 0.4053, "step": 14142 }, { "epoch": 0.7810360061851116, "grad_norm": 0.08716384321451187, "learning_rate": 4.822357327737659e-06, "loss": 0.0023, "step": 14143 }, { "epoch": 0.7810912303954054, "grad_norm": 3.155083417892456, "learning_rate": 4.820027926836279e-06, "loss": 0.3648, "step": 14144 }, { "epoch": 0.7811464546056991, "grad_norm": 3.170579671859741, "learning_rate": 4.817699011585424e-06, "loss": 0.1977, "step": 14145 }, { "epoch": 0.7812016788159929, "grad_norm": 0.6651533246040344, "learning_rate": 4.815370582059593e-06, "loss": 0.0084, "step": 14146 }, { "epoch": 0.7812569030262867, "grad_norm": 0.4760003387928009, "learning_rate": 4.813042638333298e-06, "loss": 0.0115, "step": 14147 }, { "epoch": 0.7813121272365805, "grad_norm": 0.026014387607574463, "learning_rate": 4.810715180480992e-06, "loss": 0.0008, "step": 14148 }, { "epoch": 0.7813673514468743, "grad_norm": 0.04148105904459953, "learning_rate": 4.808388208577155e-06, "loss": 0.0014, "step": 14149 }, { "epoch": 0.7814225756571681, "grad_norm": 2.1337883472442627, "learning_rate": 4.806061722696229e-06, "loss": 0.4893, "step": 14150 }, { "epoch": 0.7814777998674619, "grad_norm": 0.018848227337002754, "learning_rate": 4.803735722912643e-06, "loss": 0.0008, "step": 14151 }, { "epoch": 0.7815330240777557, "grad_norm": 0.2466302216053009, "learning_rate": 4.801410209300807e-06, "loss": 0.0071, "step": 14152 }, { "epoch": 0.7815882482880495, "grad_norm": 0.5399686694145203, "learning_rate": 4.799085181935133e-06, "loss": 0.0127, "step": 14153 }, { "epoch": 0.7816434724983433, "grad_norm": 0.09587325155735016, "learning_rate": 4.7967606408899995e-06, "loss": 0.0018, "step": 14154 }, { "epoch": 0.7816986967086371, "grad_norm": 3.879560708999634, "learning_rate": 4.7944365862397744e-06, "loss": 1.0912, "step": 14155 }, { "epoch": 0.7817539209189308, "grad_norm": 2.3930320739746094, "learning_rate": 4.792113018058803e-06, "loss": 0.0427, "step": 14156 }, { "epoch": 0.7818091451292246, "grad_norm": 4.591771602630615, "learning_rate": 4.789789936421447e-06, "loss": 1.4205, "step": 14157 }, { "epoch": 0.7818643693395184, "grad_norm": 0.2590796947479248, "learning_rate": 4.787467341401999e-06, "loss": 0.0077, "step": 14158 }, { "epoch": 0.7819195935498122, "grad_norm": 1.6030353307724, "learning_rate": 4.785145233074784e-06, "loss": 0.0823, "step": 14159 }, { "epoch": 0.781974817760106, "grad_norm": 0.5349602699279785, "learning_rate": 4.782823611514089e-06, "loss": 0.011, "step": 14160 }, { "epoch": 0.7820300419703998, "grad_norm": 1.6591945886611938, "learning_rate": 4.780502476794187e-06, "loss": 0.0664, "step": 14161 }, { "epoch": 0.7820852661806936, "grad_norm": 1.7846626043319702, "learning_rate": 4.7781818289893345e-06, "loss": 0.2269, "step": 14162 }, { "epoch": 0.7821404903909874, "grad_norm": 0.5112592577934265, "learning_rate": 4.775861668173785e-06, "loss": 0.0135, "step": 14163 }, { "epoch": 0.7821957146012812, "grad_norm": 2.419271945953369, "learning_rate": 4.7735419944217595e-06, "loss": 0.1017, "step": 14164 }, { "epoch": 0.782250938811575, "grad_norm": 1.343300700187683, "learning_rate": 4.771222807807476e-06, "loss": 0.0397, "step": 14165 }, { "epoch": 0.7823061630218688, "grad_norm": 0.7963530421257019, "learning_rate": 4.768904108405128e-06, "loss": 0.0223, "step": 14166 }, { "epoch": 0.7823613872321625, "grad_norm": 0.017597246915102005, "learning_rate": 4.7665858962889e-06, "loss": 0.0006, "step": 14167 }, { "epoch": 0.7824166114424563, "grad_norm": 0.5139945149421692, "learning_rate": 4.764268171532951e-06, "loss": 0.0126, "step": 14168 }, { "epoch": 0.7824718356527501, "grad_norm": 6.462514400482178, "learning_rate": 4.761950934211441e-06, "loss": 0.4127, "step": 14169 }, { "epoch": 0.7825270598630439, "grad_norm": 0.0481153279542923, "learning_rate": 4.759634184398502e-06, "loss": 0.0015, "step": 14170 }, { "epoch": 0.7825822840733377, "grad_norm": 4.944828987121582, "learning_rate": 4.757317922168254e-06, "loss": 0.1746, "step": 14171 }, { "epoch": 0.7826375082836315, "grad_norm": 0.035565085709095, "learning_rate": 4.755002147594794e-06, "loss": 0.0006, "step": 14172 }, { "epoch": 0.7826927324939253, "grad_norm": 1.6585413217544556, "learning_rate": 4.752686860752227e-06, "loss": 0.0591, "step": 14173 }, { "epoch": 0.7827479567042191, "grad_norm": 1.3463143110275269, "learning_rate": 4.750372061714603e-06, "loss": 0.0472, "step": 14174 }, { "epoch": 0.782803180914513, "grad_norm": 0.04649431258440018, "learning_rate": 4.748057750555996e-06, "loss": 0.0013, "step": 14175 }, { "epoch": 0.7828584051248068, "grad_norm": 0.042353637516498566, "learning_rate": 4.745743927350444e-06, "loss": 0.0009, "step": 14176 }, { "epoch": 0.7829136293351006, "grad_norm": 0.07725276052951813, "learning_rate": 4.743430592171967e-06, "loss": 0.0028, "step": 14177 }, { "epoch": 0.7829688535453942, "grad_norm": 3.3621203899383545, "learning_rate": 4.741117745094577e-06, "loss": 0.4017, "step": 14178 }, { "epoch": 0.783024077755688, "grad_norm": 0.1875307559967041, "learning_rate": 4.738805386192273e-06, "loss": 0.0055, "step": 14179 }, { "epoch": 0.7830793019659819, "grad_norm": 4.243446350097656, "learning_rate": 4.736493515539034e-06, "loss": 0.8029, "step": 14180 }, { "epoch": 0.7831345261762757, "grad_norm": 0.15280909836292267, "learning_rate": 4.734182133208818e-06, "loss": 0.0046, "step": 14181 }, { "epoch": 0.7831897503865695, "grad_norm": 2.4148831367492676, "learning_rate": 4.731871239275572e-06, "loss": 0.0683, "step": 14182 }, { "epoch": 0.7832449745968633, "grad_norm": 2.4991328716278076, "learning_rate": 4.729560833813241e-06, "loss": 0.4386, "step": 14183 }, { "epoch": 0.7833001988071571, "grad_norm": 0.043207455426454544, "learning_rate": 4.72725091689572e-06, "loss": 0.0014, "step": 14184 }, { "epoch": 0.7833554230174509, "grad_norm": 0.5587369203567505, "learning_rate": 4.72494148859693e-06, "loss": 0.0184, "step": 14185 }, { "epoch": 0.7834106472277447, "grad_norm": 0.29786375164985657, "learning_rate": 4.722632548990747e-06, "loss": 0.0113, "step": 14186 }, { "epoch": 0.7834658714380385, "grad_norm": 6.029703140258789, "learning_rate": 4.7203240981510415e-06, "loss": 1.4533, "step": 14187 }, { "epoch": 0.7835210956483323, "grad_norm": 1.7225323915481567, "learning_rate": 4.718016136151662e-06, "loss": 0.0486, "step": 14188 }, { "epoch": 0.783576319858626, "grad_norm": 5.8926100730896, "learning_rate": 4.715708663066463e-06, "loss": 0.8482, "step": 14189 }, { "epoch": 0.7836315440689198, "grad_norm": 0.016719890758395195, "learning_rate": 4.7134016789692446e-06, "loss": 0.0005, "step": 14190 }, { "epoch": 0.7836867682792136, "grad_norm": 3.4005563259124756, "learning_rate": 4.7110951839338315e-06, "loss": 0.384, "step": 14191 }, { "epoch": 0.7837419924895074, "grad_norm": 0.4066217243671417, "learning_rate": 4.70878917803401e-06, "loss": 0.0121, "step": 14192 }, { "epoch": 0.7837972166998012, "grad_norm": 5.5790252685546875, "learning_rate": 4.706483661343553e-06, "loss": 0.1501, "step": 14193 }, { "epoch": 0.783852440910095, "grad_norm": 0.1061207503080368, "learning_rate": 4.704178633936218e-06, "loss": 0.0034, "step": 14194 }, { "epoch": 0.7839076651203888, "grad_norm": 0.010000280104577541, "learning_rate": 4.701874095885759e-06, "loss": 0.0003, "step": 14195 }, { "epoch": 0.7839628893306826, "grad_norm": 4.410121440887451, "learning_rate": 4.6995700472659e-06, "loss": 0.855, "step": 14196 }, { "epoch": 0.7840181135409764, "grad_norm": 0.2217494547367096, "learning_rate": 4.697266488150354e-06, "loss": 0.0082, "step": 14197 }, { "epoch": 0.7840733377512702, "grad_norm": 4.7608795166015625, "learning_rate": 4.69496341861281e-06, "loss": 0.7071, "step": 14198 }, { "epoch": 0.784128561961564, "grad_norm": 4.114375114440918, "learning_rate": 4.692660838726972e-06, "loss": 0.7774, "step": 14199 }, { "epoch": 0.7841837861718577, "grad_norm": 0.7418397665023804, "learning_rate": 4.690358748566484e-06, "loss": 0.0302, "step": 14200 }, { "epoch": 0.7842390103821515, "grad_norm": 4.160282611846924, "learning_rate": 4.688057148205001e-06, "loss": 0.8853, "step": 14201 }, { "epoch": 0.7842942345924453, "grad_norm": 0.008079444989562035, "learning_rate": 4.685756037716164e-06, "loss": 0.0003, "step": 14202 }, { "epoch": 0.7843494588027391, "grad_norm": 5.605352401733398, "learning_rate": 4.683455417173591e-06, "loss": 1.3163, "step": 14203 }, { "epoch": 0.7844046830130329, "grad_norm": 5.766538143157959, "learning_rate": 4.681155286650882e-06, "loss": 0.2321, "step": 14204 }, { "epoch": 0.7844599072233267, "grad_norm": 0.11385542899370193, "learning_rate": 4.678855646221621e-06, "loss": 0.0044, "step": 14205 }, { "epoch": 0.7845151314336205, "grad_norm": 0.07181288301944733, "learning_rate": 4.676556495959397e-06, "loss": 0.0019, "step": 14206 }, { "epoch": 0.7845703556439143, "grad_norm": 0.15231885015964508, "learning_rate": 4.674257835937743e-06, "loss": 0.0043, "step": 14207 }, { "epoch": 0.7846255798542081, "grad_norm": 2.3007185459136963, "learning_rate": 4.671959666230217e-06, "loss": 0.1398, "step": 14208 }, { "epoch": 0.7846808040645019, "grad_norm": 0.19551724195480347, "learning_rate": 4.669661986910336e-06, "loss": 0.0031, "step": 14209 }, { "epoch": 0.7847360282747957, "grad_norm": 0.10391520708799362, "learning_rate": 4.667364798051615e-06, "loss": 0.0017, "step": 14210 }, { "epoch": 0.7847912524850894, "grad_norm": 3.5984182357788086, "learning_rate": 4.665068099727537e-06, "loss": 0.3168, "step": 14211 }, { "epoch": 0.7848464766953832, "grad_norm": 0.4085160791873932, "learning_rate": 4.662771892011599e-06, "loss": 0.0167, "step": 14212 }, { "epoch": 0.784901700905677, "grad_norm": 0.3097391128540039, "learning_rate": 4.6604761749772396e-06, "loss": 0.0101, "step": 14213 }, { "epoch": 0.7849569251159708, "grad_norm": 4.107147693634033, "learning_rate": 4.6581809486979234e-06, "loss": 0.3329, "step": 14214 }, { "epoch": 0.7850121493262646, "grad_norm": 2.0066590309143066, "learning_rate": 4.655886213247074e-06, "loss": 0.1635, "step": 14215 }, { "epoch": 0.7850673735365584, "grad_norm": 4.363328456878662, "learning_rate": 4.653591968698108e-06, "loss": 0.4749, "step": 14216 }, { "epoch": 0.7851225977468522, "grad_norm": 0.3707493841648102, "learning_rate": 4.651298215124418e-06, "loss": 0.0069, "step": 14217 }, { "epoch": 0.785177821957146, "grad_norm": 1.9981207847595215, "learning_rate": 4.6490049525994e-06, "loss": 0.1672, "step": 14218 }, { "epoch": 0.7852330461674398, "grad_norm": 2.353684902191162, "learning_rate": 4.646712181196416e-06, "loss": 0.1251, "step": 14219 }, { "epoch": 0.7852882703777336, "grad_norm": 0.03194432705640793, "learning_rate": 4.644419900988817e-06, "loss": 0.0006, "step": 14220 }, { "epoch": 0.7853434945880274, "grad_norm": 1.2251930236816406, "learning_rate": 4.642128112049937e-06, "loss": 0.0268, "step": 14221 }, { "epoch": 0.7853987187983212, "grad_norm": 0.01019600685685873, "learning_rate": 4.639836814453112e-06, "loss": 0.0004, "step": 14222 }, { "epoch": 0.7854539430086149, "grad_norm": 1.6708351373672485, "learning_rate": 4.637546008271623e-06, "loss": 0.1114, "step": 14223 }, { "epoch": 0.7855091672189087, "grad_norm": 0.03139730542898178, "learning_rate": 4.635255693578777e-06, "loss": 0.0011, "step": 14224 }, { "epoch": 0.7855643914292025, "grad_norm": 0.6953055262565613, "learning_rate": 4.632965870447845e-06, "loss": 0.0084, "step": 14225 }, { "epoch": 0.7856196156394963, "grad_norm": 0.9513493776321411, "learning_rate": 4.630676538952082e-06, "loss": 0.0938, "step": 14226 }, { "epoch": 0.7856748398497901, "grad_norm": 0.045375678688287735, "learning_rate": 4.628387699164725e-06, "loss": 0.0013, "step": 14227 }, { "epoch": 0.7857300640600839, "grad_norm": 0.09942258149385452, "learning_rate": 4.626099351159019e-06, "loss": 0.0025, "step": 14228 }, { "epoch": 0.7857852882703777, "grad_norm": 0.039649587124586105, "learning_rate": 4.623811495008148e-06, "loss": 0.0013, "step": 14229 }, { "epoch": 0.7858405124806715, "grad_norm": 1.8084124326705933, "learning_rate": 4.621524130785331e-06, "loss": 0.1993, "step": 14230 }, { "epoch": 0.7858957366909654, "grad_norm": 3.750612497329712, "learning_rate": 4.619237258563736e-06, "loss": 0.9608, "step": 14231 }, { "epoch": 0.7859509609012592, "grad_norm": 4.181371688842773, "learning_rate": 4.616950878416526e-06, "loss": 1.1792, "step": 14232 }, { "epoch": 0.786006185111553, "grad_norm": 4.329962253570557, "learning_rate": 4.614664990416848e-06, "loss": 1.0475, "step": 14233 }, { "epoch": 0.7860614093218466, "grad_norm": 0.315722793340683, "learning_rate": 4.612379594637842e-06, "loss": 0.0083, "step": 14234 }, { "epoch": 0.7861166335321405, "grad_norm": 2.9754340648651123, "learning_rate": 4.61009469115262e-06, "loss": 0.8191, "step": 14235 }, { "epoch": 0.7861718577424343, "grad_norm": 3.4335265159606934, "learning_rate": 4.607810280034281e-06, "loss": 0.7858, "step": 14236 }, { "epoch": 0.7862270819527281, "grad_norm": 2.432992458343506, "learning_rate": 4.605526361355905e-06, "loss": 0.1026, "step": 14237 }, { "epoch": 0.7862823061630219, "grad_norm": 6.598905086517334, "learning_rate": 4.60324293519058e-06, "loss": 0.829, "step": 14238 }, { "epoch": 0.7863375303733157, "grad_norm": 3.607353448867798, "learning_rate": 4.600960001611332e-06, "loss": 0.2243, "step": 14239 }, { "epoch": 0.7863927545836095, "grad_norm": 0.0066121830604970455, "learning_rate": 4.59867756069122e-06, "loss": 0.0002, "step": 14240 }, { "epoch": 0.7864479787939033, "grad_norm": 3.6776254177093506, "learning_rate": 4.596395612503259e-06, "loss": 0.6168, "step": 14241 }, { "epoch": 0.7865032030041971, "grad_norm": 4.918013095855713, "learning_rate": 4.5941141571204525e-06, "loss": 1.0705, "step": 14242 }, { "epoch": 0.7865584272144909, "grad_norm": 2.072909116744995, "learning_rate": 4.591833194615789e-06, "loss": 0.1751, "step": 14243 }, { "epoch": 0.7866136514247847, "grad_norm": 2.872267007827759, "learning_rate": 4.589552725062251e-06, "loss": 0.3584, "step": 14244 }, { "epoch": 0.7866688756350784, "grad_norm": 1.0486059188842773, "learning_rate": 4.587272748532794e-06, "loss": 0.0207, "step": 14245 }, { "epoch": 0.7867240998453722, "grad_norm": 4.146628379821777, "learning_rate": 4.58499326510036e-06, "loss": 0.691, "step": 14246 }, { "epoch": 0.786779324055666, "grad_norm": 0.2792953550815582, "learning_rate": 4.582714274837874e-06, "loss": 0.0067, "step": 14247 }, { "epoch": 0.7868345482659598, "grad_norm": 2.1632020473480225, "learning_rate": 4.580435777818251e-06, "loss": 0.3129, "step": 14248 }, { "epoch": 0.7868897724762536, "grad_norm": 2.8696515560150146, "learning_rate": 4.57815777411438e-06, "loss": 0.1264, "step": 14249 }, { "epoch": 0.7869449966865474, "grad_norm": 1.4747645854949951, "learning_rate": 4.575880263799151e-06, "loss": 0.4274, "step": 14250 }, { "epoch": 0.7870002208968412, "grad_norm": 3.688814640045166, "learning_rate": 4.573603246945422e-06, "loss": 0.5606, "step": 14251 }, { "epoch": 0.787055445107135, "grad_norm": 0.36323967576026917, "learning_rate": 4.5713267236260414e-06, "loss": 0.0076, "step": 14252 }, { "epoch": 0.7871106693174288, "grad_norm": 2.2238752841949463, "learning_rate": 4.569050693913839e-06, "loss": 0.0554, "step": 14253 }, { "epoch": 0.7871658935277226, "grad_norm": 0.02992880716919899, "learning_rate": 4.566775157881644e-06, "loss": 0.0008, "step": 14254 }, { "epoch": 0.7872211177380164, "grad_norm": 2.768690347671509, "learning_rate": 4.564500115602239e-06, "loss": 0.0626, "step": 14255 }, { "epoch": 0.7872763419483101, "grad_norm": 0.12168866395950317, "learning_rate": 4.562225567148424e-06, "loss": 0.0029, "step": 14256 }, { "epoch": 0.7873315661586039, "grad_norm": 0.7561863660812378, "learning_rate": 4.559951512592962e-06, "loss": 0.0111, "step": 14257 }, { "epoch": 0.7873867903688977, "grad_norm": 2.381739377975464, "learning_rate": 4.557677952008606e-06, "loss": 0.2112, "step": 14258 }, { "epoch": 0.7874420145791915, "grad_norm": 0.7585809826850891, "learning_rate": 4.5554048854680936e-06, "loss": 0.0196, "step": 14259 }, { "epoch": 0.7874972387894853, "grad_norm": 2.346796989440918, "learning_rate": 4.553132313044144e-06, "loss": 0.1858, "step": 14260 }, { "epoch": 0.7875524629997791, "grad_norm": 0.21105708181858063, "learning_rate": 4.5508602348094775e-06, "loss": 0.0049, "step": 14261 }, { "epoch": 0.7876076872100729, "grad_norm": 1.9703125953674316, "learning_rate": 4.548588650836763e-06, "loss": 0.0787, "step": 14262 }, { "epoch": 0.7876629114203667, "grad_norm": 0.2053116261959076, "learning_rate": 4.546317561198692e-06, "loss": 0.0033, "step": 14263 }, { "epoch": 0.7877181356306605, "grad_norm": 1.3784795999526978, "learning_rate": 4.5440469659679164e-06, "loss": 0.0489, "step": 14264 }, { "epoch": 0.7877733598409543, "grad_norm": 3.4705450534820557, "learning_rate": 4.541776865217078e-06, "loss": 0.6048, "step": 14265 }, { "epoch": 0.7878285840512481, "grad_norm": 3.2768702507019043, "learning_rate": 4.539507259018803e-06, "loss": 0.881, "step": 14266 }, { "epoch": 0.7878838082615418, "grad_norm": 0.14748406410217285, "learning_rate": 4.537238147445713e-06, "loss": 0.003, "step": 14267 }, { "epoch": 0.7879390324718356, "grad_norm": 2.4004898071289062, "learning_rate": 4.534969530570385e-06, "loss": 0.4156, "step": 14268 }, { "epoch": 0.7879942566821294, "grad_norm": 1.9958834648132324, "learning_rate": 4.532701408465414e-06, "loss": 0.1644, "step": 14269 }, { "epoch": 0.7880494808924232, "grad_norm": 2.337580442428589, "learning_rate": 4.5304337812033585e-06, "loss": 0.0587, "step": 14270 }, { "epoch": 0.788104705102717, "grad_norm": 0.016686521470546722, "learning_rate": 4.5281666488567665e-06, "loss": 0.0005, "step": 14271 }, { "epoch": 0.7881599293130108, "grad_norm": 0.6546507477760315, "learning_rate": 4.525900011498166e-06, "loss": 0.0152, "step": 14272 }, { "epoch": 0.7882151535233046, "grad_norm": 0.035922206938266754, "learning_rate": 4.5236338692000795e-06, "loss": 0.0017, "step": 14273 }, { "epoch": 0.7882703777335984, "grad_norm": 0.15268678963184357, "learning_rate": 4.521368222035005e-06, "loss": 0.0051, "step": 14274 }, { "epoch": 0.7883256019438922, "grad_norm": 1.1391502618789673, "learning_rate": 4.519103070075428e-06, "loss": 0.0697, "step": 14275 }, { "epoch": 0.788380826154186, "grad_norm": 3.5744335651397705, "learning_rate": 4.516838413393809e-06, "loss": 0.524, "step": 14276 }, { "epoch": 0.7884360503644798, "grad_norm": 0.012400200590491295, "learning_rate": 4.514574252062622e-06, "loss": 0.0003, "step": 14277 }, { "epoch": 0.7884912745747735, "grad_norm": 7.626445770263672, "learning_rate": 4.512310586154276e-06, "loss": 1.1372, "step": 14278 }, { "epoch": 0.7885464987850673, "grad_norm": 0.043082885444164276, "learning_rate": 4.510047415741212e-06, "loss": 0.0019, "step": 14279 }, { "epoch": 0.7886017229953611, "grad_norm": 0.3289912939071655, "learning_rate": 4.507784740895828e-06, "loss": 0.006, "step": 14280 }, { "epoch": 0.7886569472056549, "grad_norm": 0.010326280258595943, "learning_rate": 4.505522561690516e-06, "loss": 0.0004, "step": 14281 }, { "epoch": 0.7887121714159487, "grad_norm": 0.5439008474349976, "learning_rate": 4.503260878197644e-06, "loss": 0.0112, "step": 14282 }, { "epoch": 0.7887673956262425, "grad_norm": 0.7955573797225952, "learning_rate": 4.500999690489576e-06, "loss": 0.0293, "step": 14283 }, { "epoch": 0.7888226198365363, "grad_norm": 3.698784112930298, "learning_rate": 4.498738998638654e-06, "loss": 0.343, "step": 14284 }, { "epoch": 0.7888778440468301, "grad_norm": 0.05970451980829239, "learning_rate": 4.496478802717199e-06, "loss": 0.0016, "step": 14285 }, { "epoch": 0.788933068257124, "grad_norm": 0.440570592880249, "learning_rate": 4.494219102797526e-06, "loss": 0.1062, "step": 14286 }, { "epoch": 0.7889882924674178, "grad_norm": 3.6416633129119873, "learning_rate": 4.491959898951927e-06, "loss": 0.2767, "step": 14287 }, { "epoch": 0.7890435166777116, "grad_norm": 1.0519828796386719, "learning_rate": 4.4897011912526735e-06, "loss": 0.0123, "step": 14288 }, { "epoch": 0.7890987408880054, "grad_norm": 1.0590728521347046, "learning_rate": 4.487442979772041e-06, "loss": 0.0304, "step": 14289 }, { "epoch": 0.789153965098299, "grad_norm": 3.64988112449646, "learning_rate": 4.4851852645822705e-06, "loss": 0.4999, "step": 14290 }, { "epoch": 0.7892091893085929, "grad_norm": 0.01773208938539028, "learning_rate": 4.4829280457555905e-06, "loss": 0.0005, "step": 14291 }, { "epoch": 0.7892644135188867, "grad_norm": 0.03712823987007141, "learning_rate": 4.480671323364212e-06, "loss": 0.0008, "step": 14292 }, { "epoch": 0.7893196377291805, "grad_norm": 0.09226104617118835, "learning_rate": 4.478415097480351e-06, "loss": 0.0031, "step": 14293 }, { "epoch": 0.7893748619394743, "grad_norm": 3.6172025203704834, "learning_rate": 4.476159368176167e-06, "loss": 0.1548, "step": 14294 }, { "epoch": 0.7894300861497681, "grad_norm": 0.41555339097976685, "learning_rate": 4.4739041355238474e-06, "loss": 0.0118, "step": 14295 }, { "epoch": 0.7894853103600619, "grad_norm": 3.61269211769104, "learning_rate": 4.471649399595533e-06, "loss": 0.751, "step": 14296 }, { "epoch": 0.7895405345703557, "grad_norm": 5.20737886428833, "learning_rate": 4.469395160463364e-06, "loss": 0.4927, "step": 14297 }, { "epoch": 0.7895957587806495, "grad_norm": 1.7564510107040405, "learning_rate": 4.46714141819945e-06, "loss": 0.1473, "step": 14298 }, { "epoch": 0.7896509829909433, "grad_norm": 0.04093588888645172, "learning_rate": 4.4648881728759076e-06, "loss": 0.0012, "step": 14299 }, { "epoch": 0.7897062072012371, "grad_norm": 8.90456771850586, "learning_rate": 4.4626354245648185e-06, "loss": 1.1172, "step": 14300 }, { "epoch": 0.7897614314115308, "grad_norm": 2.7368814945220947, "learning_rate": 4.460383173338256e-06, "loss": 0.4109, "step": 14301 }, { "epoch": 0.7898166556218246, "grad_norm": 0.24655666947364807, "learning_rate": 4.45813141926827e-06, "loss": 0.0067, "step": 14302 }, { "epoch": 0.7898718798321184, "grad_norm": 0.39901086688041687, "learning_rate": 4.455880162426915e-06, "loss": 0.0097, "step": 14303 }, { "epoch": 0.7899271040424122, "grad_norm": 3.227139472961426, "learning_rate": 4.453629402886197e-06, "loss": 0.6336, "step": 14304 }, { "epoch": 0.789982328252706, "grad_norm": 3.5443966388702393, "learning_rate": 4.451379140718137e-06, "loss": 0.2613, "step": 14305 }, { "epoch": 0.7900375524629998, "grad_norm": 5.9176201820373535, "learning_rate": 4.449129375994725e-06, "loss": 1.1513, "step": 14306 }, { "epoch": 0.7900927766732936, "grad_norm": 0.13824959099292755, "learning_rate": 4.446880108787935e-06, "loss": 0.0038, "step": 14307 }, { "epoch": 0.7901480008835874, "grad_norm": 5.892267227172852, "learning_rate": 4.44463133916972e-06, "loss": 0.7699, "step": 14308 }, { "epoch": 0.7902032250938812, "grad_norm": 3.8139865398406982, "learning_rate": 4.442383067212046e-06, "loss": 0.5266, "step": 14309 }, { "epoch": 0.790258449304175, "grad_norm": 0.667468786239624, "learning_rate": 4.440135292986816e-06, "loss": 0.021, "step": 14310 }, { "epoch": 0.7903136735144688, "grad_norm": 3.5626220703125, "learning_rate": 4.437888016565961e-06, "loss": 0.1213, "step": 14311 }, { "epoch": 0.7903688977247625, "grad_norm": 2.2864720821380615, "learning_rate": 4.435641238021373e-06, "loss": 0.4052, "step": 14312 }, { "epoch": 0.7904241219350563, "grad_norm": 3.6390292644500732, "learning_rate": 4.43339495742493e-06, "loss": 0.5448, "step": 14313 }, { "epoch": 0.7904793461453501, "grad_norm": 4.602133750915527, "learning_rate": 4.431149174848495e-06, "loss": 1.265, "step": 14314 }, { "epoch": 0.7905345703556439, "grad_norm": 0.009392842650413513, "learning_rate": 4.428903890363922e-06, "loss": 0.0003, "step": 14315 }, { "epoch": 0.7905897945659377, "grad_norm": 1.278363585472107, "learning_rate": 4.426659104043045e-06, "loss": 0.0501, "step": 14316 }, { "epoch": 0.7906450187762315, "grad_norm": 0.6460327506065369, "learning_rate": 4.4244148159576804e-06, "loss": 0.0126, "step": 14317 }, { "epoch": 0.7907002429865253, "grad_norm": 3.2133758068084717, "learning_rate": 4.4221710261796205e-06, "loss": 0.1429, "step": 14318 }, { "epoch": 0.7907554671968191, "grad_norm": 0.13472558557987213, "learning_rate": 4.419927734780667e-06, "loss": 0.0049, "step": 14319 }, { "epoch": 0.7908106914071129, "grad_norm": 0.060128893703222275, "learning_rate": 4.417684941832576e-06, "loss": 0.0018, "step": 14320 }, { "epoch": 0.7908659156174067, "grad_norm": 1.6742048263549805, "learning_rate": 4.415442647407098e-06, "loss": 0.1952, "step": 14321 }, { "epoch": 0.7909211398277005, "grad_norm": 0.03882439434528351, "learning_rate": 4.413200851575983e-06, "loss": 0.0012, "step": 14322 }, { "epoch": 0.7909763640379942, "grad_norm": 0.03307347372174263, "learning_rate": 4.410959554410948e-06, "loss": 0.001, "step": 14323 }, { "epoch": 0.791031588248288, "grad_norm": 2.1492724418640137, "learning_rate": 4.408718755983694e-06, "loss": 0.0444, "step": 14324 }, { "epoch": 0.7910868124585818, "grad_norm": 4.326048851013184, "learning_rate": 4.4064784563659105e-06, "loss": 0.4653, "step": 14325 }, { "epoch": 0.7911420366688756, "grad_norm": 2.461160659790039, "learning_rate": 4.404238655629283e-06, "loss": 0.1416, "step": 14326 }, { "epoch": 0.7911972608791694, "grad_norm": 3.237435817718506, "learning_rate": 4.40199935384545e-06, "loss": 0.251, "step": 14327 }, { "epoch": 0.7912524850894632, "grad_norm": 0.6304818987846375, "learning_rate": 4.399760551086067e-06, "loss": 0.0167, "step": 14328 }, { "epoch": 0.791307709299757, "grad_norm": 0.16802562773227692, "learning_rate": 4.397522247422759e-06, "loss": 0.0047, "step": 14329 }, { "epoch": 0.7913629335100508, "grad_norm": 2.780583143234253, "learning_rate": 4.39528444292713e-06, "loss": 0.2601, "step": 14330 }, { "epoch": 0.7914181577203446, "grad_norm": 4.143349647521973, "learning_rate": 4.393047137670772e-06, "loss": 0.1818, "step": 14331 }, { "epoch": 0.7914733819306384, "grad_norm": 0.08192020654678345, "learning_rate": 4.390810331725277e-06, "loss": 0.0024, "step": 14332 }, { "epoch": 0.7915286061409322, "grad_norm": 0.047724414616823196, "learning_rate": 4.388574025162189e-06, "loss": 0.0019, "step": 14333 }, { "epoch": 0.7915838303512259, "grad_norm": 2.481333017349243, "learning_rate": 4.386338218053063e-06, "loss": 0.4018, "step": 14334 }, { "epoch": 0.7916390545615197, "grad_norm": 4.060023307800293, "learning_rate": 4.38410291046943e-06, "loss": 0.4882, "step": 14335 }, { "epoch": 0.7916942787718135, "grad_norm": 0.8621591925621033, "learning_rate": 4.3818681024828e-06, "loss": 0.1245, "step": 14336 }, { "epoch": 0.7917495029821073, "grad_norm": 2.1943700313568115, "learning_rate": 4.379633794164668e-06, "loss": 0.1514, "step": 14337 }, { "epoch": 0.7918047271924011, "grad_norm": 0.013367199338972569, "learning_rate": 4.3773999855865255e-06, "loss": 0.0004, "step": 14338 }, { "epoch": 0.7918599514026949, "grad_norm": 0.477356880903244, "learning_rate": 4.375166676819833e-06, "loss": 0.0085, "step": 14339 }, { "epoch": 0.7919151756129887, "grad_norm": 0.0648542195558548, "learning_rate": 4.37293386793604e-06, "loss": 0.001, "step": 14340 }, { "epoch": 0.7919703998232825, "grad_norm": 0.09144550561904907, "learning_rate": 4.370701559006576e-06, "loss": 0.0015, "step": 14341 }, { "epoch": 0.7920256240335763, "grad_norm": 0.15732142329216003, "learning_rate": 4.368469750102875e-06, "loss": 0.0028, "step": 14342 }, { "epoch": 0.7920808482438702, "grad_norm": 0.04180637374520302, "learning_rate": 4.366238441296316e-06, "loss": 0.0015, "step": 14343 }, { "epoch": 0.792136072454164, "grad_norm": 0.04306713491678238, "learning_rate": 4.364007632658303e-06, "loss": 0.0013, "step": 14344 }, { "epoch": 0.7921912966644576, "grad_norm": 0.12086101621389389, "learning_rate": 4.3617773242601965e-06, "loss": 0.006, "step": 14345 }, { "epoch": 0.7922465208747514, "grad_norm": 0.008664911612868309, "learning_rate": 4.359547516173357e-06, "loss": 0.0003, "step": 14346 }, { "epoch": 0.7923017450850453, "grad_norm": 0.019035661593079567, "learning_rate": 4.357318208469112e-06, "loss": 0.0005, "step": 14347 }, { "epoch": 0.792356969295339, "grad_norm": 4.889545917510986, "learning_rate": 4.355089401218801e-06, "loss": 0.5173, "step": 14348 }, { "epoch": 0.7924121935056329, "grad_norm": 2.0466108322143555, "learning_rate": 4.3528610944937075e-06, "loss": 0.1144, "step": 14349 }, { "epoch": 0.7924674177159267, "grad_norm": 4.363304138183594, "learning_rate": 4.350633288365141e-06, "loss": 0.6068, "step": 14350 }, { "epoch": 0.7925226419262205, "grad_norm": 3.2472991943359375, "learning_rate": 4.348405982904365e-06, "loss": 0.4566, "step": 14351 }, { "epoch": 0.7925778661365143, "grad_norm": 1.1273771524429321, "learning_rate": 4.346179178182641e-06, "loss": 0.1369, "step": 14352 }, { "epoch": 0.7926330903468081, "grad_norm": 0.103690005838871, "learning_rate": 4.343952874271202e-06, "loss": 0.0025, "step": 14353 }, { "epoch": 0.7926883145571019, "grad_norm": 2.1927878856658936, "learning_rate": 4.341727071241288e-06, "loss": 0.1292, "step": 14354 }, { "epoch": 0.7927435387673957, "grad_norm": 0.013012795709073544, "learning_rate": 4.339501769164103e-06, "loss": 0.0003, "step": 14355 }, { "epoch": 0.7927987629776894, "grad_norm": 3.033499002456665, "learning_rate": 4.33727696811084e-06, "loss": 0.4142, "step": 14356 }, { "epoch": 0.7928539871879832, "grad_norm": 3.58560848236084, "learning_rate": 4.335052668152671e-06, "loss": 0.5379, "step": 14357 }, { "epoch": 0.792909211398277, "grad_norm": 0.2150818258523941, "learning_rate": 4.332828869360772e-06, "loss": 0.0047, "step": 14358 }, { "epoch": 0.7929644356085708, "grad_norm": 1.5948104858398438, "learning_rate": 4.3306055718062725e-06, "loss": 0.0329, "step": 14359 }, { "epoch": 0.7930196598188646, "grad_norm": 4.289669990539551, "learning_rate": 4.328382775560311e-06, "loss": 1.0064, "step": 14360 }, { "epoch": 0.7930748840291584, "grad_norm": 0.09197324514389038, "learning_rate": 4.326160480694004e-06, "loss": 0.0027, "step": 14361 }, { "epoch": 0.7931301082394522, "grad_norm": 0.28226372599601746, "learning_rate": 4.323938687278441e-06, "loss": 0.0059, "step": 14362 }, { "epoch": 0.793185332449746, "grad_norm": 0.13066065311431885, "learning_rate": 4.321717395384704e-06, "loss": 0.0028, "step": 14363 }, { "epoch": 0.7932405566600398, "grad_norm": 1.5528616905212402, "learning_rate": 4.319496605083866e-06, "loss": 0.0696, "step": 14364 }, { "epoch": 0.7932957808703336, "grad_norm": 0.04460896551609039, "learning_rate": 4.317276316446972e-06, "loss": 0.001, "step": 14365 }, { "epoch": 0.7933510050806274, "grad_norm": 0.047760702669620514, "learning_rate": 4.315056529545056e-06, "loss": 0.0012, "step": 14366 }, { "epoch": 0.7934062292909212, "grad_norm": 0.1680355966091156, "learning_rate": 4.3128372444491354e-06, "loss": 0.0031, "step": 14367 }, { "epoch": 0.7934614535012149, "grad_norm": 2.459002733230591, "learning_rate": 4.310618461230209e-06, "loss": 0.0658, "step": 14368 }, { "epoch": 0.7935166777115087, "grad_norm": 5.274020195007324, "learning_rate": 4.308400179959258e-06, "loss": 0.2592, "step": 14369 }, { "epoch": 0.7935719019218025, "grad_norm": 3.781172037124634, "learning_rate": 4.306182400707264e-06, "loss": 0.1145, "step": 14370 }, { "epoch": 0.7936271261320963, "grad_norm": 3.331387996673584, "learning_rate": 4.303965123545173e-06, "loss": 0.534, "step": 14371 }, { "epoch": 0.7936823503423901, "grad_norm": 5.857084274291992, "learning_rate": 4.301748348543922e-06, "loss": 0.6075, "step": 14372 }, { "epoch": 0.7937375745526839, "grad_norm": 0.05956033244729042, "learning_rate": 4.299532075774427e-06, "loss": 0.002, "step": 14373 }, { "epoch": 0.7937927987629777, "grad_norm": 0.12597759068012238, "learning_rate": 4.297316305307608e-06, "loss": 0.0039, "step": 14374 }, { "epoch": 0.7938480229732715, "grad_norm": 1.6572767496109009, "learning_rate": 4.295101037214335e-06, "loss": 0.2607, "step": 14375 }, { "epoch": 0.7939032471835653, "grad_norm": 2.139875888824463, "learning_rate": 4.292886271565495e-06, "loss": 0.2215, "step": 14376 }, { "epoch": 0.7939584713938591, "grad_norm": 2.4058403968811035, "learning_rate": 4.290672008431937e-06, "loss": 0.0217, "step": 14377 }, { "epoch": 0.7940136956041529, "grad_norm": 0.13844631612300873, "learning_rate": 4.288458247884506e-06, "loss": 0.0038, "step": 14378 }, { "epoch": 0.7940689198144466, "grad_norm": 0.5474146008491516, "learning_rate": 4.286244989994024e-06, "loss": 0.0187, "step": 14379 }, { "epoch": 0.7941241440247404, "grad_norm": 0.12483774125576019, "learning_rate": 4.284032234831295e-06, "loss": 0.0033, "step": 14380 }, { "epoch": 0.7941793682350342, "grad_norm": 0.24917027354240417, "learning_rate": 4.281819982467126e-06, "loss": 0.0066, "step": 14381 }, { "epoch": 0.794234592445328, "grad_norm": 0.6272369623184204, "learning_rate": 4.279608232972272e-06, "loss": 0.0198, "step": 14382 }, { "epoch": 0.7942898166556218, "grad_norm": 0.189655601978302, "learning_rate": 4.2773969864175125e-06, "loss": 0.0051, "step": 14383 }, { "epoch": 0.7943450408659156, "grad_norm": 2.886629104614258, "learning_rate": 4.2751862428735815e-06, "loss": 0.3212, "step": 14384 }, { "epoch": 0.7944002650762094, "grad_norm": 1.2104129791259766, "learning_rate": 4.272976002411211e-06, "loss": 0.0574, "step": 14385 }, { "epoch": 0.7944554892865032, "grad_norm": 0.07706965506076813, "learning_rate": 4.2707662651011025e-06, "loss": 0.002, "step": 14386 }, { "epoch": 0.794510713496797, "grad_norm": 2.4683759212493896, "learning_rate": 4.268557031013973e-06, "loss": 0.0775, "step": 14387 }, { "epoch": 0.7945659377070908, "grad_norm": 1.669034481048584, "learning_rate": 4.26634830022048e-06, "loss": 0.0121, "step": 14388 }, { "epoch": 0.7946211619173846, "grad_norm": 0.06634670495986938, "learning_rate": 4.264140072791301e-06, "loss": 0.0019, "step": 14389 }, { "epoch": 0.7946763861276783, "grad_norm": 1.6323035955429077, "learning_rate": 4.261932348797077e-06, "loss": 0.0824, "step": 14390 }, { "epoch": 0.7947316103379721, "grad_norm": 5.312585830688477, "learning_rate": 4.259725128308445e-06, "loss": 1.0089, "step": 14391 }, { "epoch": 0.7947868345482659, "grad_norm": 0.8902631998062134, "learning_rate": 4.2575184113960085e-06, "loss": 0.0243, "step": 14392 }, { "epoch": 0.7948420587585597, "grad_norm": 1.5476082563400269, "learning_rate": 4.255312198130384e-06, "loss": 0.0547, "step": 14393 }, { "epoch": 0.7948972829688535, "grad_norm": 5.106414794921875, "learning_rate": 4.253106488582142e-06, "loss": 1.0135, "step": 14394 }, { "epoch": 0.7949525071791473, "grad_norm": 4.909669399261475, "learning_rate": 4.250901282821853e-06, "loss": 0.8798, "step": 14395 }, { "epoch": 0.7950077313894411, "grad_norm": 0.4162062406539917, "learning_rate": 4.248696580920062e-06, "loss": 0.0087, "step": 14396 }, { "epoch": 0.7950629555997349, "grad_norm": 0.020849617198109627, "learning_rate": 4.246492382947323e-06, "loss": 0.0004, "step": 14397 }, { "epoch": 0.7951181798100287, "grad_norm": 3.9467380046844482, "learning_rate": 4.2442886889741275e-06, "loss": 0.3809, "step": 14398 }, { "epoch": 0.7951734040203225, "grad_norm": 0.32550230622291565, "learning_rate": 4.242085499070998e-06, "loss": 0.0083, "step": 14399 }, { "epoch": 0.7952286282306164, "grad_norm": 0.03404361009597778, "learning_rate": 4.239882813308413e-06, "loss": 0.0009, "step": 14400 }, { "epoch": 0.79528385244091, "grad_norm": 4.368680953979492, "learning_rate": 4.237680631756844e-06, "loss": 0.4793, "step": 14401 }, { "epoch": 0.7953390766512038, "grad_norm": 1.1345235109329224, "learning_rate": 4.23547895448674e-06, "loss": 0.0513, "step": 14402 }, { "epoch": 0.7953943008614976, "grad_norm": 5.086257457733154, "learning_rate": 4.23327778156855e-06, "loss": 0.308, "step": 14403 }, { "epoch": 0.7954495250717915, "grad_norm": 3.153592586517334, "learning_rate": 4.231077113072688e-06, "loss": 0.5393, "step": 14404 }, { "epoch": 0.7955047492820853, "grad_norm": 0.015206233598291874, "learning_rate": 4.228876949069562e-06, "loss": 0.0004, "step": 14405 }, { "epoch": 0.7955599734923791, "grad_norm": 1.6225553750991821, "learning_rate": 4.226677289629561e-06, "loss": 0.3081, "step": 14406 }, { "epoch": 0.7956151977026729, "grad_norm": 2.4416730403900146, "learning_rate": 4.224478134823058e-06, "loss": 0.1492, "step": 14407 }, { "epoch": 0.7956704219129667, "grad_norm": 2.8132131099700928, "learning_rate": 4.2222794847204065e-06, "loss": 0.0942, "step": 14408 }, { "epoch": 0.7957256461232605, "grad_norm": 1.0204808712005615, "learning_rate": 4.220081339391955e-06, "loss": 0.0309, "step": 14409 }, { "epoch": 0.7957808703335543, "grad_norm": 2.5982019901275635, "learning_rate": 4.217883698908025e-06, "loss": 0.153, "step": 14410 }, { "epoch": 0.7958360945438481, "grad_norm": 1.2790387868881226, "learning_rate": 4.215686563338926e-06, "loss": 0.0512, "step": 14411 }, { "epoch": 0.7958913187541418, "grad_norm": 0.1498667448759079, "learning_rate": 4.213489932754944e-06, "loss": 0.0031, "step": 14412 }, { "epoch": 0.7959465429644356, "grad_norm": 0.025083132088184357, "learning_rate": 4.211293807226371e-06, "loss": 0.0008, "step": 14413 }, { "epoch": 0.7960017671747294, "grad_norm": 0.14446409046649933, "learning_rate": 4.209098186823448e-06, "loss": 0.0035, "step": 14414 }, { "epoch": 0.7960569913850232, "grad_norm": 0.021969983354210854, "learning_rate": 4.206903071616435e-06, "loss": 0.0009, "step": 14415 }, { "epoch": 0.796112215595317, "grad_norm": 3.296576499938965, "learning_rate": 4.204708461675553e-06, "loss": 0.5784, "step": 14416 }, { "epoch": 0.7961674398056108, "grad_norm": 2.8427600860595703, "learning_rate": 4.202514357071012e-06, "loss": 0.3131, "step": 14417 }, { "epoch": 0.7962226640159046, "grad_norm": 0.06743229180574417, "learning_rate": 4.200320757873009e-06, "loss": 0.0022, "step": 14418 }, { "epoch": 0.7962778882261984, "grad_norm": 8.61213207244873, "learning_rate": 4.198127664151727e-06, "loss": 0.1334, "step": 14419 }, { "epoch": 0.7963331124364922, "grad_norm": 3.81455659866333, "learning_rate": 4.195935075977329e-06, "loss": 0.4724, "step": 14420 }, { "epoch": 0.796388336646786, "grad_norm": 2.3556101322174072, "learning_rate": 4.193742993419958e-06, "loss": 0.3284, "step": 14421 }, { "epoch": 0.7964435608570798, "grad_norm": 2.944628953933716, "learning_rate": 4.191551416549742e-06, "loss": 0.2599, "step": 14422 }, { "epoch": 0.7964987850673735, "grad_norm": 3.3289361000061035, "learning_rate": 4.189360345436813e-06, "loss": 0.5967, "step": 14423 }, { "epoch": 0.7965540092776673, "grad_norm": 2.9884421825408936, "learning_rate": 4.187169780151246e-06, "loss": 0.1431, "step": 14424 }, { "epoch": 0.7966092334879611, "grad_norm": 0.4116506278514862, "learning_rate": 4.18497972076314e-06, "loss": 0.0099, "step": 14425 }, { "epoch": 0.7966644576982549, "grad_norm": 2.5467827320098877, "learning_rate": 4.182790167342557e-06, "loss": 0.12, "step": 14426 }, { "epoch": 0.7967196819085487, "grad_norm": 4.647087574005127, "learning_rate": 4.180601119959544e-06, "loss": 0.3003, "step": 14427 }, { "epoch": 0.7967749061188425, "grad_norm": 0.12553547322750092, "learning_rate": 4.178412578684133e-06, "loss": 0.0028, "step": 14428 }, { "epoch": 0.7968301303291363, "grad_norm": 0.014803946018218994, "learning_rate": 4.176224543586356e-06, "loss": 0.0007, "step": 14429 }, { "epoch": 0.7968853545394301, "grad_norm": 0.16894523799419403, "learning_rate": 4.1740370147361944e-06, "loss": 0.004, "step": 14430 }, { "epoch": 0.7969405787497239, "grad_norm": 5.970142364501953, "learning_rate": 4.171849992203647e-06, "loss": 0.8322, "step": 14431 }, { "epoch": 0.7969958029600177, "grad_norm": 0.36474698781967163, "learning_rate": 4.169663476058681e-06, "loss": 0.0095, "step": 14432 }, { "epoch": 0.7970510271703115, "grad_norm": 0.04802504926919937, "learning_rate": 4.167477466371246e-06, "loss": 0.0018, "step": 14433 }, { "epoch": 0.7971062513806052, "grad_norm": 0.435037225484848, "learning_rate": 4.165291963211276e-06, "loss": 0.0183, "step": 14434 }, { "epoch": 0.797161475590899, "grad_norm": 0.020343109965324402, "learning_rate": 4.1631069666487e-06, "loss": 0.0007, "step": 14435 }, { "epoch": 0.7972166998011928, "grad_norm": 0.08672411739826202, "learning_rate": 4.160922476753417e-06, "loss": 0.0022, "step": 14436 }, { "epoch": 0.7972719240114866, "grad_norm": 2.983194351196289, "learning_rate": 4.158738493595318e-06, "loss": 0.6818, "step": 14437 }, { "epoch": 0.7973271482217804, "grad_norm": 1.3218003511428833, "learning_rate": 4.156555017244266e-06, "loss": 0.0331, "step": 14438 }, { "epoch": 0.7973823724320742, "grad_norm": 0.021431293338537216, "learning_rate": 4.154372047770132e-06, "loss": 0.0004, "step": 14439 }, { "epoch": 0.797437596642368, "grad_norm": 0.031318310648202896, "learning_rate": 4.152189585242745e-06, "loss": 0.0009, "step": 14440 }, { "epoch": 0.7974928208526618, "grad_norm": 0.1027163565158844, "learning_rate": 4.1500076297319226e-06, "loss": 0.0019, "step": 14441 }, { "epoch": 0.7975480450629556, "grad_norm": 2.141878843307495, "learning_rate": 4.1478261813074835e-06, "loss": 0.2705, "step": 14442 }, { "epoch": 0.7976032692732494, "grad_norm": 0.04149993136525154, "learning_rate": 4.1456452400392155e-06, "loss": 0.0012, "step": 14443 }, { "epoch": 0.7976584934835432, "grad_norm": 5.635501384735107, "learning_rate": 4.14346480599689e-06, "loss": 1.1671, "step": 14444 }, { "epoch": 0.797713717693837, "grad_norm": 0.032543886452913284, "learning_rate": 4.141284879250265e-06, "loss": 0.0011, "step": 14445 }, { "epoch": 0.7977689419041307, "grad_norm": 3.633519172668457, "learning_rate": 4.1391054598690925e-06, "loss": 0.4881, "step": 14446 }, { "epoch": 0.7978241661144245, "grad_norm": 0.04020686820149422, "learning_rate": 4.136926547923079e-06, "loss": 0.0015, "step": 14447 }, { "epoch": 0.7978793903247183, "grad_norm": 2.717655897140503, "learning_rate": 4.134748143481953e-06, "loss": 0.5581, "step": 14448 }, { "epoch": 0.7979346145350121, "grad_norm": 1.417191982269287, "learning_rate": 4.132570246615397e-06, "loss": 0.2064, "step": 14449 }, { "epoch": 0.7979898387453059, "grad_norm": 2.804001808166504, "learning_rate": 4.130392857393095e-06, "loss": 0.2197, "step": 14450 }, { "epoch": 0.7980450629555997, "grad_norm": 0.011933359317481518, "learning_rate": 4.128215975884698e-06, "loss": 0.0004, "step": 14451 }, { "epoch": 0.7981002871658935, "grad_norm": 3.3123929500579834, "learning_rate": 4.126039602159866e-06, "loss": 0.0709, "step": 14452 }, { "epoch": 0.7981555113761873, "grad_norm": 0.16255483031272888, "learning_rate": 4.123863736288209e-06, "loss": 0.0037, "step": 14453 }, { "epoch": 0.7982107355864811, "grad_norm": 2.1258621215820312, "learning_rate": 4.121688378339353e-06, "loss": 0.0292, "step": 14454 }, { "epoch": 0.798265959796775, "grad_norm": 4.061599254608154, "learning_rate": 4.11951352838289e-06, "loss": 0.8938, "step": 14455 }, { "epoch": 0.7983211840070688, "grad_norm": 3.51851224899292, "learning_rate": 4.117339186488398e-06, "loss": 0.6859, "step": 14456 }, { "epoch": 0.7983764082173624, "grad_norm": 0.35237666964530945, "learning_rate": 4.115165352725437e-06, "loss": 0.0074, "step": 14457 }, { "epoch": 0.7984316324276562, "grad_norm": 2.319641590118408, "learning_rate": 4.112992027163562e-06, "loss": 0.2933, "step": 14458 }, { "epoch": 0.79848685663795, "grad_norm": 0.024137454107403755, "learning_rate": 4.1108192098723035e-06, "loss": 0.0006, "step": 14459 }, { "epoch": 0.7985420808482439, "grad_norm": 2.9734585285186768, "learning_rate": 4.1086469009211714e-06, "loss": 0.1499, "step": 14460 }, { "epoch": 0.7985973050585377, "grad_norm": 2.979443311691284, "learning_rate": 4.106475100379659e-06, "loss": 0.5107, "step": 14461 }, { "epoch": 0.7986525292688315, "grad_norm": 0.8610965013504028, "learning_rate": 4.104303808317267e-06, "loss": 0.0232, "step": 14462 }, { "epoch": 0.7987077534791253, "grad_norm": 0.49173271656036377, "learning_rate": 4.102133024803438e-06, "loss": 0.0101, "step": 14463 }, { "epoch": 0.7987629776894191, "grad_norm": 3.15673828125, "learning_rate": 4.099962749907638e-06, "loss": 0.1287, "step": 14464 }, { "epoch": 0.7988182018997129, "grad_norm": 3.780045986175537, "learning_rate": 4.097792983699296e-06, "loss": 0.7579, "step": 14465 }, { "epoch": 0.7988734261100067, "grad_norm": 3.53855562210083, "learning_rate": 4.095623726247828e-06, "loss": 0.189, "step": 14466 }, { "epoch": 0.7989286503203005, "grad_norm": 4.616189002990723, "learning_rate": 4.093454977622629e-06, "loss": 0.5734, "step": 14467 }, { "epoch": 0.7989838745305942, "grad_norm": 0.3567844331264496, "learning_rate": 4.091286737893099e-06, "loss": 0.009, "step": 14468 }, { "epoch": 0.799039098740888, "grad_norm": 0.3196491599082947, "learning_rate": 4.089119007128586e-06, "loss": 0.0074, "step": 14469 }, { "epoch": 0.7990943229511818, "grad_norm": 0.29850518703460693, "learning_rate": 4.086951785398459e-06, "loss": 0.0112, "step": 14470 }, { "epoch": 0.7991495471614756, "grad_norm": 0.29894334077835083, "learning_rate": 4.084785072772046e-06, "loss": 0.0085, "step": 14471 }, { "epoch": 0.7992047713717694, "grad_norm": 0.39264893531799316, "learning_rate": 4.082618869318667e-06, "loss": 0.0073, "step": 14472 }, { "epoch": 0.7992599955820632, "grad_norm": 0.9644775986671448, "learning_rate": 4.080453175107619e-06, "loss": 0.1364, "step": 14473 }, { "epoch": 0.799315219792357, "grad_norm": 0.0705895721912384, "learning_rate": 4.078287990208201e-06, "loss": 0.0022, "step": 14474 }, { "epoch": 0.7993704440026508, "grad_norm": 2.2954773902893066, "learning_rate": 4.076123314689677e-06, "loss": 0.1989, "step": 14475 }, { "epoch": 0.7994256682129446, "grad_norm": 0.11204208433628082, "learning_rate": 4.073959148621303e-06, "loss": 0.0028, "step": 14476 }, { "epoch": 0.7994808924232384, "grad_norm": 0.026569334790110588, "learning_rate": 4.071795492072308e-06, "loss": 0.001, "step": 14477 }, { "epoch": 0.7995361166335322, "grad_norm": 0.2920379340648651, "learning_rate": 4.069632345111931e-06, "loss": 0.0038, "step": 14478 }, { "epoch": 0.7995913408438259, "grad_norm": 0.009944587014615536, "learning_rate": 4.067469707809359e-06, "loss": 0.0003, "step": 14479 }, { "epoch": 0.7996465650541197, "grad_norm": 0.858242392539978, "learning_rate": 4.065307580233793e-06, "loss": 0.0321, "step": 14480 }, { "epoch": 0.7997017892644135, "grad_norm": 0.021112186834216118, "learning_rate": 4.0631459624544e-06, "loss": 0.0006, "step": 14481 }, { "epoch": 0.7997570134747073, "grad_norm": 1.194928765296936, "learning_rate": 4.060984854540339e-06, "loss": 0.0169, "step": 14482 }, { "epoch": 0.7998122376850011, "grad_norm": 0.04952167719602585, "learning_rate": 4.058824256560745e-06, "loss": 0.0017, "step": 14483 }, { "epoch": 0.7998674618952949, "grad_norm": 2.7522358894348145, "learning_rate": 4.056664168584749e-06, "loss": 0.0316, "step": 14484 }, { "epoch": 0.7999226861055887, "grad_norm": 2.4186651706695557, "learning_rate": 4.0545045906814565e-06, "loss": 0.2236, "step": 14485 }, { "epoch": 0.7999779103158825, "grad_norm": 0.11507759243249893, "learning_rate": 4.052345522919956e-06, "loss": 0.0033, "step": 14486 }, { "epoch": 0.8000331345261763, "grad_norm": 2.5440049171447754, "learning_rate": 4.050186965369322e-06, "loss": 0.1255, "step": 14487 }, { "epoch": 0.8000883587364701, "grad_norm": 0.3380200266838074, "learning_rate": 4.048028918098614e-06, "loss": 0.0103, "step": 14488 }, { "epoch": 0.8001435829467639, "grad_norm": 0.22238421440124512, "learning_rate": 4.045871381176871e-06, "loss": 0.0051, "step": 14489 }, { "epoch": 0.8001988071570576, "grad_norm": 3.346099376678467, "learning_rate": 4.043714354673127e-06, "loss": 0.1308, "step": 14490 }, { "epoch": 0.8002540313673514, "grad_norm": 3.941056489944458, "learning_rate": 4.041557838656385e-06, "loss": 0.8913, "step": 14491 }, { "epoch": 0.8003092555776452, "grad_norm": 2.6180553436279297, "learning_rate": 4.03940183319564e-06, "loss": 0.0272, "step": 14492 }, { "epoch": 0.800364479787939, "grad_norm": 0.09394398331642151, "learning_rate": 4.037246338359864e-06, "loss": 0.0024, "step": 14493 }, { "epoch": 0.8004197039982328, "grad_norm": 3.2269833087921143, "learning_rate": 4.03509135421803e-06, "loss": 0.4349, "step": 14494 }, { "epoch": 0.8004749282085266, "grad_norm": 2.4409685134887695, "learning_rate": 4.032936880839065e-06, "loss": 0.1203, "step": 14495 }, { "epoch": 0.8005301524188204, "grad_norm": 2.2473864555358887, "learning_rate": 4.030782918291909e-06, "loss": 0.1098, "step": 14496 }, { "epoch": 0.8005853766291142, "grad_norm": 0.01195264421403408, "learning_rate": 4.02862946664547e-06, "loss": 0.0005, "step": 14497 }, { "epoch": 0.800640600839408, "grad_norm": 4.841939449310303, "learning_rate": 4.026476525968644e-06, "loss": 0.9271, "step": 14498 }, { "epoch": 0.8006958250497018, "grad_norm": 4.990894794464111, "learning_rate": 4.024324096330308e-06, "loss": 1.3429, "step": 14499 }, { "epoch": 0.8007510492599956, "grad_norm": 1.0862847566604614, "learning_rate": 4.022172177799319e-06, "loss": 0.0578, "step": 14500 }, { "epoch": 0.8008062734702893, "grad_norm": 0.023400625213980675, "learning_rate": 4.020020770444542e-06, "loss": 0.0004, "step": 14501 }, { "epoch": 0.8008614976805831, "grad_norm": 0.020797662436962128, "learning_rate": 4.017869874334779e-06, "loss": 0.0006, "step": 14502 }, { "epoch": 0.8009167218908769, "grad_norm": 4.384981155395508, "learning_rate": 4.015719489538865e-06, "loss": 0.1387, "step": 14503 }, { "epoch": 0.8009719461011707, "grad_norm": 0.11104366183280945, "learning_rate": 4.01356961612559e-06, "loss": 0.0042, "step": 14504 }, { "epoch": 0.8010271703114645, "grad_norm": 4.745349407196045, "learning_rate": 4.011420254163736e-06, "loss": 0.3408, "step": 14505 }, { "epoch": 0.8010823945217583, "grad_norm": 2.427438735961914, "learning_rate": 4.009271403722057e-06, "loss": 0.2011, "step": 14506 }, { "epoch": 0.8011376187320521, "grad_norm": 2.7133102416992188, "learning_rate": 4.0071230648693226e-06, "loss": 0.6764, "step": 14507 }, { "epoch": 0.8011928429423459, "grad_norm": 1.3296961784362793, "learning_rate": 4.004975237674238e-06, "loss": 0.0335, "step": 14508 }, { "epoch": 0.8012480671526397, "grad_norm": 0.06175008416175842, "learning_rate": 4.002827922205539e-06, "loss": 0.0016, "step": 14509 }, { "epoch": 0.8013032913629335, "grad_norm": 7.337651252746582, "learning_rate": 4.000681118531915e-06, "loss": 0.3848, "step": 14510 }, { "epoch": 0.8013585155732273, "grad_norm": 0.1198902279138565, "learning_rate": 3.998534826722051e-06, "loss": 0.0019, "step": 14511 }, { "epoch": 0.8014137397835212, "grad_norm": 0.045598577708005905, "learning_rate": 3.996389046844607e-06, "loss": 0.0016, "step": 14512 }, { "epoch": 0.8014689639938148, "grad_norm": 0.2642808258533478, "learning_rate": 3.994243778968241e-06, "loss": 0.0086, "step": 14513 }, { "epoch": 0.8015241882041086, "grad_norm": 0.008671421557664871, "learning_rate": 3.992099023161584e-06, "loss": 0.0002, "step": 14514 }, { "epoch": 0.8015794124144024, "grad_norm": 2.0952162742614746, "learning_rate": 3.989954779493252e-06, "loss": 0.06, "step": 14515 }, { "epoch": 0.8016346366246963, "grad_norm": 0.019999846816062927, "learning_rate": 3.9878110480318396e-06, "loss": 0.0006, "step": 14516 }, { "epoch": 0.80168986083499, "grad_norm": 4.002491474151611, "learning_rate": 3.985667828845949e-06, "loss": 0.9634, "step": 14517 }, { "epoch": 0.8017450850452839, "grad_norm": 4.12819766998291, "learning_rate": 3.983525122004121e-06, "loss": 0.8199, "step": 14518 }, { "epoch": 0.8018003092555777, "grad_norm": 1.926400899887085, "learning_rate": 3.9813829275749305e-06, "loss": 0.0288, "step": 14519 }, { "epoch": 0.8018555334658715, "grad_norm": 0.02921445108950138, "learning_rate": 3.979241245626901e-06, "loss": 0.0009, "step": 14520 }, { "epoch": 0.8019107576761653, "grad_norm": 0.23707547783851624, "learning_rate": 3.977100076228553e-06, "loss": 0.0041, "step": 14521 }, { "epoch": 0.8019659818864591, "grad_norm": 0.2529238760471344, "learning_rate": 3.974959419448383e-06, "loss": 0.0054, "step": 14522 }, { "epoch": 0.8020212060967529, "grad_norm": 0.2444240301847458, "learning_rate": 3.972819275354889e-06, "loss": 0.0062, "step": 14523 }, { "epoch": 0.8020764303070466, "grad_norm": 0.4391058385372162, "learning_rate": 3.970679644016533e-06, "loss": 0.0101, "step": 14524 }, { "epoch": 0.8021316545173404, "grad_norm": 2.4975085258483887, "learning_rate": 3.968540525501769e-06, "loss": 0.1018, "step": 14525 }, { "epoch": 0.8021868787276342, "grad_norm": 0.010533145628869534, "learning_rate": 3.966401919879033e-06, "loss": 0.0003, "step": 14526 }, { "epoch": 0.802242102937928, "grad_norm": 0.041411884129047394, "learning_rate": 3.964263827216745e-06, "loss": 0.0014, "step": 14527 }, { "epoch": 0.8022973271482218, "grad_norm": 2.567995071411133, "learning_rate": 3.962126247583305e-06, "loss": 0.3994, "step": 14528 }, { "epoch": 0.8023525513585156, "grad_norm": 2.6001479625701904, "learning_rate": 3.959989181047108e-06, "loss": 0.0935, "step": 14529 }, { "epoch": 0.8024077755688094, "grad_norm": 4.575782775878906, "learning_rate": 3.957852627676522e-06, "loss": 0.2185, "step": 14530 }, { "epoch": 0.8024629997791032, "grad_norm": 1.6964294910430908, "learning_rate": 3.9557165875399e-06, "loss": 0.1019, "step": 14531 }, { "epoch": 0.802518223989397, "grad_norm": 3.0091404914855957, "learning_rate": 3.953581060705573e-06, "loss": 0.6673, "step": 14532 }, { "epoch": 0.8025734481996908, "grad_norm": 3.550384044647217, "learning_rate": 3.951446047241883e-06, "loss": 0.4555, "step": 14533 }, { "epoch": 0.8026286724099846, "grad_norm": 0.6225656867027283, "learning_rate": 3.949311547217112e-06, "loss": 0.0118, "step": 14534 }, { "epoch": 0.8026838966202783, "grad_norm": 7.924152851104736, "learning_rate": 3.947177560699562e-06, "loss": 0.7421, "step": 14535 }, { "epoch": 0.8027391208305721, "grad_norm": 0.5715089440345764, "learning_rate": 3.945044087757504e-06, "loss": 0.0096, "step": 14536 }, { "epoch": 0.8027943450408659, "grad_norm": 0.13262325525283813, "learning_rate": 3.942911128459191e-06, "loss": 0.0025, "step": 14537 }, { "epoch": 0.8028495692511597, "grad_norm": 2.730998992919922, "learning_rate": 3.940778682872859e-06, "loss": 0.2286, "step": 14538 }, { "epoch": 0.8029047934614535, "grad_norm": 5.509427547454834, "learning_rate": 3.938646751066739e-06, "loss": 0.805, "step": 14539 }, { "epoch": 0.8029600176717473, "grad_norm": 0.9474294185638428, "learning_rate": 3.936515333109037e-06, "loss": 0.1274, "step": 14540 }, { "epoch": 0.8030152418820411, "grad_norm": 0.624090850353241, "learning_rate": 3.934384429067936e-06, "loss": 0.011, "step": 14541 }, { "epoch": 0.8030704660923349, "grad_norm": 5.106894016265869, "learning_rate": 3.932254039011614e-06, "loss": 1.0906, "step": 14542 }, { "epoch": 0.8031256903026287, "grad_norm": 3.175320625305176, "learning_rate": 3.930124163008235e-06, "loss": 0.2729, "step": 14543 }, { "epoch": 0.8031809145129225, "grad_norm": 0.7552119493484497, "learning_rate": 3.927994801125923e-06, "loss": 0.0163, "step": 14544 }, { "epoch": 0.8032361387232163, "grad_norm": 0.2956867516040802, "learning_rate": 3.925865953432817e-06, "loss": 0.0042, "step": 14545 }, { "epoch": 0.80329136293351, "grad_norm": 0.0513467937707901, "learning_rate": 3.923737619997021e-06, "loss": 0.0009, "step": 14546 }, { "epoch": 0.8033465871438038, "grad_norm": 0.3903990089893341, "learning_rate": 3.921609800886627e-06, "loss": 0.0134, "step": 14547 }, { "epoch": 0.8034018113540976, "grad_norm": 0.06441299617290497, "learning_rate": 3.919482496169702e-06, "loss": 0.0013, "step": 14548 }, { "epoch": 0.8034570355643914, "grad_norm": 2.965986967086792, "learning_rate": 3.917355705914321e-06, "loss": 0.1231, "step": 14549 }, { "epoch": 0.8035122597746852, "grad_norm": 0.00861238781362772, "learning_rate": 3.915229430188508e-06, "loss": 0.0003, "step": 14550 }, { "epoch": 0.803567483984979, "grad_norm": 3.95764422416687, "learning_rate": 3.913103669060299e-06, "loss": 0.2798, "step": 14551 }, { "epoch": 0.8036227081952728, "grad_norm": 0.2670537531375885, "learning_rate": 3.910978422597702e-06, "loss": 0.0071, "step": 14552 }, { "epoch": 0.8036779324055666, "grad_norm": 0.041475068777799606, "learning_rate": 3.9088536908687105e-06, "loss": 0.0012, "step": 14553 }, { "epoch": 0.8037331566158604, "grad_norm": 0.022560784593224525, "learning_rate": 3.906729473941291e-06, "loss": 0.0008, "step": 14554 }, { "epoch": 0.8037883808261542, "grad_norm": 5.019450664520264, "learning_rate": 3.904605771883419e-06, "loss": 1.3169, "step": 14555 }, { "epoch": 0.803843605036448, "grad_norm": 4.362029552459717, "learning_rate": 3.9024825847630274e-06, "loss": 0.7354, "step": 14556 }, { "epoch": 0.8038988292467417, "grad_norm": 2.161949634552002, "learning_rate": 3.900359912648048e-06, "loss": 0.214, "step": 14557 }, { "epoch": 0.8039540534570355, "grad_norm": 0.5754639506340027, "learning_rate": 3.8982377556063825e-06, "loss": 0.0079, "step": 14558 }, { "epoch": 0.8040092776673293, "grad_norm": 1.6091636419296265, "learning_rate": 3.896116113705941e-06, "loss": 0.3811, "step": 14559 }, { "epoch": 0.8040645018776231, "grad_norm": 1.3396930694580078, "learning_rate": 3.893994987014584e-06, "loss": 0.0347, "step": 14560 }, { "epoch": 0.8041197260879169, "grad_norm": 3.2122650146484375, "learning_rate": 3.891874375600175e-06, "loss": 0.1165, "step": 14561 }, { "epoch": 0.8041749502982107, "grad_norm": 4.238293170928955, "learning_rate": 3.889754279530569e-06, "loss": 0.425, "step": 14562 }, { "epoch": 0.8042301745085045, "grad_norm": 0.0033474068623036146, "learning_rate": 3.887634698873588e-06, "loss": 0.0001, "step": 14563 }, { "epoch": 0.8042853987187983, "grad_norm": 3.2442524433135986, "learning_rate": 3.885515633697041e-06, "loss": 0.5103, "step": 14564 }, { "epoch": 0.8043406229290921, "grad_norm": 0.04207436367869377, "learning_rate": 3.883397084068719e-06, "loss": 0.0012, "step": 14565 }, { "epoch": 0.8043958471393859, "grad_norm": 0.046376850455999374, "learning_rate": 3.881279050056419e-06, "loss": 0.001, "step": 14566 }, { "epoch": 0.8044510713496797, "grad_norm": 0.051742345094680786, "learning_rate": 3.879161531727878e-06, "loss": 0.0012, "step": 14567 }, { "epoch": 0.8045062955599734, "grad_norm": 1.8260260820388794, "learning_rate": 3.8770445291508595e-06, "loss": 0.1447, "step": 14568 }, { "epoch": 0.8045615197702672, "grad_norm": 0.0264693945646286, "learning_rate": 3.874928042393085e-06, "loss": 0.0009, "step": 14569 }, { "epoch": 0.804616743980561, "grad_norm": 0.4179547131061554, "learning_rate": 3.872812071522269e-06, "loss": 0.0074, "step": 14570 }, { "epoch": 0.8046719681908548, "grad_norm": 2.406731605529785, "learning_rate": 3.870696616606104e-06, "loss": 0.2745, "step": 14571 }, { "epoch": 0.8047271924011486, "grad_norm": 6.378372669219971, "learning_rate": 3.868581677712279e-06, "loss": 1.4835, "step": 14572 }, { "epoch": 0.8047824166114425, "grad_norm": 2.0526905059814453, "learning_rate": 3.866467254908444e-06, "loss": 0.0797, "step": 14573 }, { "epoch": 0.8048376408217363, "grad_norm": 4.328588962554932, "learning_rate": 3.864353348262255e-06, "loss": 0.7158, "step": 14574 }, { "epoch": 0.8048928650320301, "grad_norm": 0.010394642129540443, "learning_rate": 3.862239957841338e-06, "loss": 0.0003, "step": 14575 }, { "epoch": 0.8049480892423239, "grad_norm": 5.464025974273682, "learning_rate": 3.860127083713307e-06, "loss": 0.9327, "step": 14576 }, { "epoch": 0.8050033134526177, "grad_norm": 0.0466577410697937, "learning_rate": 3.858014725945753e-06, "loss": 0.0011, "step": 14577 }, { "epoch": 0.8050585376629115, "grad_norm": 3.38870906829834, "learning_rate": 3.855902884606269e-06, "loss": 0.6791, "step": 14578 }, { "epoch": 0.8051137618732052, "grad_norm": 5.399721145629883, "learning_rate": 3.85379155976241e-06, "loss": 0.6851, "step": 14579 }, { "epoch": 0.805168986083499, "grad_norm": 0.8015196323394775, "learning_rate": 3.851680751481728e-06, "loss": 0.0149, "step": 14580 }, { "epoch": 0.8052242102937928, "grad_norm": 0.07399151474237442, "learning_rate": 3.849570459831744e-06, "loss": 0.0012, "step": 14581 }, { "epoch": 0.8052794345040866, "grad_norm": 3.074728012084961, "learning_rate": 3.8474606848799886e-06, "loss": 0.5557, "step": 14582 }, { "epoch": 0.8053346587143804, "grad_norm": 1.129414677619934, "learning_rate": 3.845351426693942e-06, "loss": 0.0524, "step": 14583 }, { "epoch": 0.8053898829246742, "grad_norm": 2.77581787109375, "learning_rate": 3.843242685341097e-06, "loss": 0.0926, "step": 14584 }, { "epoch": 0.805445107134968, "grad_norm": 7.54946756362915, "learning_rate": 3.841134460888916e-06, "loss": 2.2819, "step": 14585 }, { "epoch": 0.8055003313452618, "grad_norm": 0.15242908895015717, "learning_rate": 3.8390267534048444e-06, "loss": 0.0031, "step": 14586 }, { "epoch": 0.8055555555555556, "grad_norm": 0.058984432369470596, "learning_rate": 3.83691956295631e-06, "loss": 0.0016, "step": 14587 }, { "epoch": 0.8056107797658494, "grad_norm": 2.447350263595581, "learning_rate": 3.8348128896107435e-06, "loss": 0.022, "step": 14588 }, { "epoch": 0.8056660039761432, "grad_norm": 2.428433895111084, "learning_rate": 3.832706733435525e-06, "loss": 0.1982, "step": 14589 }, { "epoch": 0.805721228186437, "grad_norm": 0.18919934332370758, "learning_rate": 3.830601094498048e-06, "loss": 0.0064, "step": 14590 }, { "epoch": 0.8057764523967307, "grad_norm": 1.6475985050201416, "learning_rate": 3.828495972865674e-06, "loss": 0.0839, "step": 14591 }, { "epoch": 0.8058316766070245, "grad_norm": 0.15820984542369843, "learning_rate": 3.826391368605751e-06, "loss": 0.004, "step": 14592 }, { "epoch": 0.8058869008173183, "grad_norm": 0.01657896302640438, "learning_rate": 3.824287281785608e-06, "loss": 0.0004, "step": 14593 }, { "epoch": 0.8059421250276121, "grad_norm": 2.043199300765991, "learning_rate": 3.822183712472569e-06, "loss": 0.0826, "step": 14594 }, { "epoch": 0.8059973492379059, "grad_norm": 3.9997706413269043, "learning_rate": 3.820080660733931e-06, "loss": 0.5321, "step": 14595 }, { "epoch": 0.8060525734481997, "grad_norm": 0.2878750264644623, "learning_rate": 3.817978126636974e-06, "loss": 0.0054, "step": 14596 }, { "epoch": 0.8061077976584935, "grad_norm": 1.2340668439865112, "learning_rate": 3.815876110248962e-06, "loss": 0.0305, "step": 14597 }, { "epoch": 0.8061630218687873, "grad_norm": 0.14608579874038696, "learning_rate": 3.8137746116371553e-06, "loss": 0.0039, "step": 14598 }, { "epoch": 0.8062182460790811, "grad_norm": 0.7342995405197144, "learning_rate": 3.8116736308687684e-06, "loss": 0.0098, "step": 14599 }, { "epoch": 0.8062734702893749, "grad_norm": 2.777395486831665, "learning_rate": 3.809573168011034e-06, "loss": 0.3014, "step": 14600 }, { "epoch": 0.8063286944996687, "grad_norm": 2.721933603286743, "learning_rate": 3.807473223131146e-06, "loss": 0.436, "step": 14601 }, { "epoch": 0.8063839187099624, "grad_norm": 0.008979862555861473, "learning_rate": 3.8053737962962877e-06, "loss": 0.0003, "step": 14602 }, { "epoch": 0.8064391429202562, "grad_norm": 2.606995105743408, "learning_rate": 3.8032748875736227e-06, "loss": 0.358, "step": 14603 }, { "epoch": 0.80649436713055, "grad_norm": 1.0352123975753784, "learning_rate": 3.8011764970303055e-06, "loss": 0.0308, "step": 14604 }, { "epoch": 0.8065495913408438, "grad_norm": 0.03124452754855156, "learning_rate": 3.7990786247334697e-06, "loss": 0.0009, "step": 14605 }, { "epoch": 0.8066048155511376, "grad_norm": 2.652085065841675, "learning_rate": 3.796981270750233e-06, "loss": 0.393, "step": 14606 }, { "epoch": 0.8066600397614314, "grad_norm": 0.09683337062597275, "learning_rate": 3.7948844351476898e-06, "loss": 0.003, "step": 14607 }, { "epoch": 0.8067152639717252, "grad_norm": 3.074477195739746, "learning_rate": 3.792788117992929e-06, "loss": 0.1187, "step": 14608 }, { "epoch": 0.806770488182019, "grad_norm": 0.1242995336651802, "learning_rate": 3.790692319353011e-06, "loss": 0.0033, "step": 14609 }, { "epoch": 0.8068257123923128, "grad_norm": 1.631455421447754, "learning_rate": 3.7885970392949966e-06, "loss": 0.0336, "step": 14610 }, { "epoch": 0.8068809366026066, "grad_norm": 0.03181403502821922, "learning_rate": 3.786502277885915e-06, "loss": 0.0009, "step": 14611 }, { "epoch": 0.8069361608129004, "grad_norm": 5.0833659172058105, "learning_rate": 3.7844080351927836e-06, "loss": 1.0987, "step": 14612 }, { "epoch": 0.8069913850231941, "grad_norm": 0.029809197410941124, "learning_rate": 3.782314311282598e-06, "loss": 0.0009, "step": 14613 }, { "epoch": 0.8070466092334879, "grad_norm": 1.1634708642959595, "learning_rate": 3.780221106222355e-06, "loss": 0.0584, "step": 14614 }, { "epoch": 0.8071018334437817, "grad_norm": 0.3923090398311615, "learning_rate": 3.7781284200790058e-06, "loss": 0.0118, "step": 14615 }, { "epoch": 0.8071570576540755, "grad_norm": 0.02520095184445381, "learning_rate": 3.776036252919517e-06, "loss": 0.0005, "step": 14616 }, { "epoch": 0.8072122818643693, "grad_norm": 5.4018025398254395, "learning_rate": 3.773944604810813e-06, "loss": 0.9312, "step": 14617 }, { "epoch": 0.8072675060746631, "grad_norm": 1.0774897336959839, "learning_rate": 3.771853475819818e-06, "loss": 0.0335, "step": 14618 }, { "epoch": 0.8073227302849569, "grad_norm": 4.361435413360596, "learning_rate": 3.769762866013422e-06, "loss": 0.8781, "step": 14619 }, { "epoch": 0.8073779544952507, "grad_norm": 1.2108073234558105, "learning_rate": 3.767672775458524e-06, "loss": 0.0686, "step": 14620 }, { "epoch": 0.8074331787055445, "grad_norm": 1.5427247285842896, "learning_rate": 3.7655832042219896e-06, "loss": 0.0203, "step": 14621 }, { "epoch": 0.8074884029158383, "grad_norm": 5.035977840423584, "learning_rate": 3.763494152370655e-06, "loss": 0.5377, "step": 14622 }, { "epoch": 0.8075436271261321, "grad_norm": 1.3883153200149536, "learning_rate": 3.761405619971372e-06, "loss": 0.0733, "step": 14623 }, { "epoch": 0.8075988513364258, "grad_norm": 3.345337390899658, "learning_rate": 3.7593176070909508e-06, "loss": 0.605, "step": 14624 }, { "epoch": 0.8076540755467196, "grad_norm": 0.042948052287101746, "learning_rate": 3.7572301137961954e-06, "loss": 0.0009, "step": 14625 }, { "epoch": 0.8077092997570134, "grad_norm": 0.027187179774045944, "learning_rate": 3.755143140153885e-06, "loss": 0.001, "step": 14626 }, { "epoch": 0.8077645239673072, "grad_norm": 3.697077989578247, "learning_rate": 3.753056686230803e-06, "loss": 0.2946, "step": 14627 }, { "epoch": 0.807819748177601, "grad_norm": 4.429695129394531, "learning_rate": 3.750970752093681e-06, "loss": 0.8226, "step": 14628 }, { "epoch": 0.8078749723878949, "grad_norm": 5.7055487632751465, "learning_rate": 3.748885337809267e-06, "loss": 0.5062, "step": 14629 }, { "epoch": 0.8079301965981887, "grad_norm": 3.312983274459839, "learning_rate": 3.7468004434442763e-06, "loss": 0.1907, "step": 14630 }, { "epoch": 0.8079854208084825, "grad_norm": 0.056110039353370667, "learning_rate": 3.7447160690654105e-06, "loss": 0.0016, "step": 14631 }, { "epoch": 0.8080406450187763, "grad_norm": 2.547067403793335, "learning_rate": 3.7426322147393502e-06, "loss": 0.2385, "step": 14632 }, { "epoch": 0.8080958692290701, "grad_norm": 0.282499223947525, "learning_rate": 3.7405488805327726e-06, "loss": 0.0083, "step": 14633 }, { "epoch": 0.8081510934393639, "grad_norm": 0.06903952360153198, "learning_rate": 3.738466066512325e-06, "loss": 0.0021, "step": 14634 }, { "epoch": 0.8082063176496576, "grad_norm": 1.1213433742523193, "learning_rate": 3.7363837727446427e-06, "loss": 0.0349, "step": 14635 }, { "epoch": 0.8082615418599514, "grad_norm": 2.300922393798828, "learning_rate": 3.734301999296337e-06, "loss": 0.0549, "step": 14636 }, { "epoch": 0.8083167660702452, "grad_norm": 0.49251803755760193, "learning_rate": 3.73222074623403e-06, "loss": 0.1304, "step": 14637 }, { "epoch": 0.808371990280539, "grad_norm": 1.660831093788147, "learning_rate": 3.7301400136242792e-06, "loss": 0.3414, "step": 14638 }, { "epoch": 0.8084272144908328, "grad_norm": 0.3497259020805359, "learning_rate": 3.7280598015336766e-06, "loss": 0.0077, "step": 14639 }, { "epoch": 0.8084824387011266, "grad_norm": 4.0337910652160645, "learning_rate": 3.725980110028764e-06, "loss": 0.0974, "step": 14640 }, { "epoch": 0.8085376629114204, "grad_norm": 3.666332721710205, "learning_rate": 3.723900939176077e-06, "loss": 0.1398, "step": 14641 }, { "epoch": 0.8085928871217142, "grad_norm": 2.507390022277832, "learning_rate": 3.7218222890421297e-06, "loss": 0.3714, "step": 14642 }, { "epoch": 0.808648111332008, "grad_norm": 0.8181101083755493, "learning_rate": 3.719744159693435e-06, "loss": 0.2112, "step": 14643 }, { "epoch": 0.8087033355423018, "grad_norm": 4.252519607543945, "learning_rate": 3.7176665511964726e-06, "loss": 0.2125, "step": 14644 }, { "epoch": 0.8087585597525956, "grad_norm": 2.072488784790039, "learning_rate": 3.7155894636177103e-06, "loss": 0.1568, "step": 14645 }, { "epoch": 0.8088137839628893, "grad_norm": 0.29874879121780396, "learning_rate": 3.713512897023603e-06, "loss": 0.0057, "step": 14646 }, { "epoch": 0.8088690081731831, "grad_norm": 3.0487258434295654, "learning_rate": 3.7114368514805808e-06, "loss": 0.341, "step": 14647 }, { "epoch": 0.8089242323834769, "grad_norm": 0.9273697733879089, "learning_rate": 3.709361327055061e-06, "loss": 0.1371, "step": 14648 }, { "epoch": 0.8089794565937707, "grad_norm": 5.7100911140441895, "learning_rate": 3.707286323813455e-06, "loss": 0.5281, "step": 14649 }, { "epoch": 0.8090346808040645, "grad_norm": 4.391587734222412, "learning_rate": 3.7052118418221427e-06, "loss": 0.5039, "step": 14650 }, { "epoch": 0.8090899050143583, "grad_norm": 0.01826673187315464, "learning_rate": 3.7031378811474937e-06, "loss": 0.0005, "step": 14651 }, { "epoch": 0.8091451292246521, "grad_norm": 0.02189492993056774, "learning_rate": 3.7010644418558528e-06, "loss": 0.0005, "step": 14652 }, { "epoch": 0.8092003534349459, "grad_norm": 0.038979727774858475, "learning_rate": 3.698991524013573e-06, "loss": 0.0008, "step": 14653 }, { "epoch": 0.8092555776452397, "grad_norm": 1.3586488962173462, "learning_rate": 3.696919127686951e-06, "loss": 0.0218, "step": 14654 }, { "epoch": 0.8093108018555335, "grad_norm": 2.6950294971466064, "learning_rate": 3.6948472529423018e-06, "loss": 0.4047, "step": 14655 }, { "epoch": 0.8093660260658273, "grad_norm": 3.0445752143859863, "learning_rate": 3.6927758998459085e-06, "loss": 0.2961, "step": 14656 }, { "epoch": 0.809421250276121, "grad_norm": 2.2546207904815674, "learning_rate": 3.69070506846404e-06, "loss": 0.1385, "step": 14657 }, { "epoch": 0.8094764744864148, "grad_norm": 0.19906757771968842, "learning_rate": 3.6886347588629413e-06, "loss": 0.0083, "step": 14658 }, { "epoch": 0.8095316986967086, "grad_norm": 6.042508602142334, "learning_rate": 3.686564971108857e-06, "loss": 0.8519, "step": 14659 }, { "epoch": 0.8095869229070024, "grad_norm": 0.3728931248188019, "learning_rate": 3.684495705268003e-06, "loss": 0.0097, "step": 14660 }, { "epoch": 0.8096421471172962, "grad_norm": 0.17501527070999146, "learning_rate": 3.68242696140658e-06, "loss": 0.0055, "step": 14661 }, { "epoch": 0.80969737132759, "grad_norm": 1.7141417264938354, "learning_rate": 3.680358739590766e-06, "loss": 0.115, "step": 14662 }, { "epoch": 0.8097525955378838, "grad_norm": 0.005186539143323898, "learning_rate": 3.6782910398867455e-06, "loss": 0.0002, "step": 14663 }, { "epoch": 0.8098078197481776, "grad_norm": 0.016570137813687325, "learning_rate": 3.6762238623606527e-06, "loss": 0.0004, "step": 14664 }, { "epoch": 0.8098630439584714, "grad_norm": 9.389836311340332, "learning_rate": 3.6741572070786324e-06, "loss": 1.6691, "step": 14665 }, { "epoch": 0.8099182681687652, "grad_norm": 5.693726062774658, "learning_rate": 3.6720910741068028e-06, "loss": 0.292, "step": 14666 }, { "epoch": 0.809973492379059, "grad_norm": 0.35423508286476135, "learning_rate": 3.670025463511262e-06, "loss": 0.0071, "step": 14667 }, { "epoch": 0.8100287165893528, "grad_norm": 0.1937672197818756, "learning_rate": 3.6679603753580927e-06, "loss": 0.0046, "step": 14668 }, { "epoch": 0.8100839407996465, "grad_norm": 3.032200574874878, "learning_rate": 3.6658958097133757e-06, "loss": 0.4627, "step": 14669 }, { "epoch": 0.8101391650099403, "grad_norm": 0.22014491260051727, "learning_rate": 3.663831766643142e-06, "loss": 0.0047, "step": 14670 }, { "epoch": 0.8101943892202341, "grad_norm": 0.005795817822217941, "learning_rate": 3.6617682462134418e-06, "loss": 0.0001, "step": 14671 }, { "epoch": 0.8102496134305279, "grad_norm": 0.016219403594732285, "learning_rate": 3.6597052484902884e-06, "loss": 0.0004, "step": 14672 }, { "epoch": 0.8103048376408217, "grad_norm": 0.0045607853680849075, "learning_rate": 3.6576427735396845e-06, "loss": 0.0001, "step": 14673 }, { "epoch": 0.8103600618511155, "grad_norm": 0.10251075774431229, "learning_rate": 3.6555808214276068e-06, "loss": 0.0026, "step": 14674 }, { "epoch": 0.8104152860614093, "grad_norm": 0.014247640036046505, "learning_rate": 3.6535193922200353e-06, "loss": 0.0003, "step": 14675 }, { "epoch": 0.8104705102717031, "grad_norm": 2.75331711769104, "learning_rate": 3.651458485982913e-06, "loss": 0.339, "step": 14676 }, { "epoch": 0.8105257344819969, "grad_norm": 0.12939077615737915, "learning_rate": 3.6493981027821755e-06, "loss": 0.0034, "step": 14677 }, { "epoch": 0.8105809586922907, "grad_norm": 0.031295374035835266, "learning_rate": 3.647338242683738e-06, "loss": 0.0006, "step": 14678 }, { "epoch": 0.8106361829025845, "grad_norm": 4.0933427810668945, "learning_rate": 3.645278905753513e-06, "loss": 0.3843, "step": 14679 }, { "epoch": 0.8106914071128782, "grad_norm": 2.111173391342163, "learning_rate": 3.6432200920573714e-06, "loss": 0.2159, "step": 14680 }, { "epoch": 0.810746631323172, "grad_norm": 10.261847496032715, "learning_rate": 3.641161801661177e-06, "loss": 0.3701, "step": 14681 }, { "epoch": 0.8108018555334658, "grad_norm": 1.4471535682678223, "learning_rate": 3.639104034630796e-06, "loss": 0.069, "step": 14682 }, { "epoch": 0.8108570797437596, "grad_norm": 0.11296675354242325, "learning_rate": 3.6370467910320527e-06, "loss": 0.004, "step": 14683 }, { "epoch": 0.8109123039540534, "grad_norm": 6.7828688621521, "learning_rate": 3.634990070930766e-06, "loss": 0.7446, "step": 14684 }, { "epoch": 0.8109675281643473, "grad_norm": 3.8410351276397705, "learning_rate": 3.632933874392739e-06, "loss": 0.175, "step": 14685 }, { "epoch": 0.811022752374641, "grad_norm": 2.4568631649017334, "learning_rate": 3.6308782014837497e-06, "loss": 0.1976, "step": 14686 }, { "epoch": 0.8110779765849349, "grad_norm": 0.17476651072502136, "learning_rate": 3.628823052269561e-06, "loss": 0.0058, "step": 14687 }, { "epoch": 0.8111332007952287, "grad_norm": 0.08403486013412476, "learning_rate": 3.6267684268159364e-06, "loss": 0.0021, "step": 14688 }, { "epoch": 0.8111884250055225, "grad_norm": 1.4114923477172852, "learning_rate": 3.624714325188603e-06, "loss": 0.0493, "step": 14689 }, { "epoch": 0.8112436492158163, "grad_norm": 5.265194416046143, "learning_rate": 3.622660747453275e-06, "loss": 0.9262, "step": 14690 }, { "epoch": 0.81129887342611, "grad_norm": 0.6345071196556091, "learning_rate": 3.6206076936756506e-06, "loss": 0.011, "step": 14691 }, { "epoch": 0.8113540976364038, "grad_norm": 2.250073194503784, "learning_rate": 3.6185551639214266e-06, "loss": 0.0608, "step": 14692 }, { "epoch": 0.8114093218466976, "grad_norm": 1.0617440938949585, "learning_rate": 3.616503158256246e-06, "loss": 0.0807, "step": 14693 }, { "epoch": 0.8114645460569914, "grad_norm": 1.8547099828720093, "learning_rate": 3.614451676745778e-06, "loss": 0.0823, "step": 14694 }, { "epoch": 0.8115197702672852, "grad_norm": 4.192280292510986, "learning_rate": 3.6124007194556488e-06, "loss": 0.6838, "step": 14695 }, { "epoch": 0.811574994477579, "grad_norm": 5.273353576660156, "learning_rate": 3.6103502864514737e-06, "loss": 1.1943, "step": 14696 }, { "epoch": 0.8116302186878728, "grad_norm": 0.05201476439833641, "learning_rate": 3.6083003777988455e-06, "loss": 0.0015, "step": 14697 }, { "epoch": 0.8116854428981666, "grad_norm": 5.3737664222717285, "learning_rate": 3.6062509935633604e-06, "loss": 1.0763, "step": 14698 }, { "epoch": 0.8117406671084604, "grad_norm": 3.5096359252929688, "learning_rate": 3.6042021338105772e-06, "loss": 0.2357, "step": 14699 }, { "epoch": 0.8117958913187542, "grad_norm": 2.7395200729370117, "learning_rate": 3.6021537986060427e-06, "loss": 0.6099, "step": 14700 }, { "epoch": 0.811851115529048, "grad_norm": 0.030707761645317078, "learning_rate": 3.600105988015288e-06, "loss": 0.0007, "step": 14701 }, { "epoch": 0.8119063397393417, "grad_norm": 3.2091212272644043, "learning_rate": 3.5980587021038393e-06, "loss": 0.1102, "step": 14702 }, { "epoch": 0.8119615639496355, "grad_norm": 4.687887668609619, "learning_rate": 3.5960119409371764e-06, "loss": 0.3368, "step": 14703 }, { "epoch": 0.8120167881599293, "grad_norm": 0.09195303171873093, "learning_rate": 3.5939657045807973e-06, "loss": 0.0024, "step": 14704 }, { "epoch": 0.8120720123702231, "grad_norm": 4.190958023071289, "learning_rate": 3.5919199931001615e-06, "loss": 0.8335, "step": 14705 }, { "epoch": 0.8121272365805169, "grad_norm": 3.538830041885376, "learning_rate": 3.589874806560718e-06, "loss": 0.1794, "step": 14706 }, { "epoch": 0.8121824607908107, "grad_norm": 0.022082572802901268, "learning_rate": 3.587830145027891e-06, "loss": 0.0005, "step": 14707 }, { "epoch": 0.8122376850011045, "grad_norm": 0.05225057154893875, "learning_rate": 3.5857860085671115e-06, "loss": 0.0018, "step": 14708 }, { "epoch": 0.8122929092113983, "grad_norm": 0.3463764488697052, "learning_rate": 3.5837423972437545e-06, "loss": 0.0117, "step": 14709 }, { "epoch": 0.8123481334216921, "grad_norm": 2.2994329929351807, "learning_rate": 3.5816993111232214e-06, "loss": 0.1897, "step": 14710 }, { "epoch": 0.8124033576319859, "grad_norm": 0.027358481660485268, "learning_rate": 3.5796567502708657e-06, "loss": 0.0006, "step": 14711 }, { "epoch": 0.8124585818422797, "grad_norm": 0.5492101311683655, "learning_rate": 3.577614714752038e-06, "loss": 0.0187, "step": 14712 }, { "epoch": 0.8125138060525734, "grad_norm": 0.013810536824166775, "learning_rate": 3.5755732046320635e-06, "loss": 0.0004, "step": 14713 }, { "epoch": 0.8125690302628672, "grad_norm": 0.10529455542564392, "learning_rate": 3.5735322199762655e-06, "loss": 0.0039, "step": 14714 }, { "epoch": 0.812624254473161, "grad_norm": 2.442241668701172, "learning_rate": 3.5714917608499368e-06, "loss": 0.0751, "step": 14715 }, { "epoch": 0.8126794786834548, "grad_norm": 0.9039211273193359, "learning_rate": 3.5694518273183554e-06, "loss": 0.0245, "step": 14716 }, { "epoch": 0.8127347028937486, "grad_norm": 0.0049937209114432335, "learning_rate": 3.567412419446781e-06, "loss": 0.0001, "step": 14717 }, { "epoch": 0.8127899271040424, "grad_norm": 3.2118513584136963, "learning_rate": 3.5653735373004737e-06, "loss": 0.2208, "step": 14718 }, { "epoch": 0.8128451513143362, "grad_norm": 2.5039336681365967, "learning_rate": 3.563335180944645e-06, "loss": 0.0856, "step": 14719 }, { "epoch": 0.81290037552463, "grad_norm": 4.084842205047607, "learning_rate": 3.5612973504445212e-06, "loss": 0.4551, "step": 14720 }, { "epoch": 0.8129555997349238, "grad_norm": 0.0517570786178112, "learning_rate": 3.559260045865296e-06, "loss": 0.0012, "step": 14721 }, { "epoch": 0.8130108239452176, "grad_norm": 0.0763738602399826, "learning_rate": 3.557223267272145e-06, "loss": 0.0013, "step": 14722 }, { "epoch": 0.8130660481555114, "grad_norm": 4.737919807434082, "learning_rate": 3.555187014730228e-06, "loss": 0.5192, "step": 14723 }, { "epoch": 0.8131212723658051, "grad_norm": 4.593163013458252, "learning_rate": 3.5531512883046994e-06, "loss": 0.948, "step": 14724 }, { "epoch": 0.8131764965760989, "grad_norm": 2.368380546569824, "learning_rate": 3.551116088060682e-06, "loss": 0.0711, "step": 14725 }, { "epoch": 0.8132317207863927, "grad_norm": 7.28556489944458, "learning_rate": 3.5490814140632913e-06, "loss": 0.7776, "step": 14726 }, { "epoch": 0.8132869449966865, "grad_norm": 2.634566068649292, "learning_rate": 3.547047266377619e-06, "loss": 0.1863, "step": 14727 }, { "epoch": 0.8133421692069803, "grad_norm": 4.748292922973633, "learning_rate": 3.5450136450687424e-06, "loss": 0.167, "step": 14728 }, { "epoch": 0.8133973934172741, "grad_norm": 0.03098795935511589, "learning_rate": 3.5429805502017223e-06, "loss": 0.0006, "step": 14729 }, { "epoch": 0.8134526176275679, "grad_norm": 0.7547889351844788, "learning_rate": 3.540947981841609e-06, "loss": 0.0193, "step": 14730 }, { "epoch": 0.8135078418378617, "grad_norm": 4.727231502532959, "learning_rate": 3.538915940053427e-06, "loss": 0.0936, "step": 14731 }, { "epoch": 0.8135630660481555, "grad_norm": 1.4316051006317139, "learning_rate": 3.536884424902185e-06, "loss": 0.1104, "step": 14732 }, { "epoch": 0.8136182902584493, "grad_norm": 0.7464407086372375, "learning_rate": 3.5348534364528762e-06, "loss": 0.0128, "step": 14733 }, { "epoch": 0.8136735144687431, "grad_norm": 0.5438031554222107, "learning_rate": 3.532822974770489e-06, "loss": 0.0178, "step": 14734 }, { "epoch": 0.813728738679037, "grad_norm": 3.2441961765289307, "learning_rate": 3.530793039919964e-06, "loss": 0.2949, "step": 14735 }, { "epoch": 0.8137839628893306, "grad_norm": 2.791692018508911, "learning_rate": 3.528763631966261e-06, "loss": 0.1734, "step": 14736 }, { "epoch": 0.8138391870996244, "grad_norm": 0.20420505106449127, "learning_rate": 3.526734750974301e-06, "loss": 0.0053, "step": 14737 }, { "epoch": 0.8138944113099182, "grad_norm": 2.9827640056610107, "learning_rate": 3.5247063970089943e-06, "loss": 0.7742, "step": 14738 }, { "epoch": 0.813949635520212, "grad_norm": 6.706496715545654, "learning_rate": 3.5226785701352273e-06, "loss": 0.7789, "step": 14739 }, { "epoch": 0.8140048597305058, "grad_norm": 0.21312861144542694, "learning_rate": 3.5206512704178876e-06, "loss": 0.0062, "step": 14740 }, { "epoch": 0.8140600839407997, "grad_norm": 1.1896311044692993, "learning_rate": 3.518624497921832e-06, "loss": 0.0502, "step": 14741 }, { "epoch": 0.8141153081510935, "grad_norm": 0.0062297675758600235, "learning_rate": 3.516598252711889e-06, "loss": 0.0002, "step": 14742 }, { "epoch": 0.8141705323613873, "grad_norm": 0.03384105861186981, "learning_rate": 3.5145725348529002e-06, "loss": 0.0006, "step": 14743 }, { "epoch": 0.8142257565716811, "grad_norm": 0.1225525289773941, "learning_rate": 3.512547344409667e-06, "loss": 0.0052, "step": 14744 }, { "epoch": 0.8142809807819749, "grad_norm": 0.5157813429832458, "learning_rate": 3.510522681446984e-06, "loss": 0.0135, "step": 14745 }, { "epoch": 0.8143362049922687, "grad_norm": 4.692737579345703, "learning_rate": 3.5084985460296173e-06, "loss": 1.0031, "step": 14746 }, { "epoch": 0.8143914292025624, "grad_norm": 4.727815628051758, "learning_rate": 3.5064749382223416e-06, "loss": 1.0333, "step": 14747 }, { "epoch": 0.8144466534128562, "grad_norm": 0.08548793941736221, "learning_rate": 3.5044518580898767e-06, "loss": 0.0017, "step": 14748 }, { "epoch": 0.81450187762315, "grad_norm": 4.447452545166016, "learning_rate": 3.5024293056969637e-06, "loss": 0.7711, "step": 14749 }, { "epoch": 0.8145571018334438, "grad_norm": 1.2871668338775635, "learning_rate": 3.5004072811083025e-06, "loss": 0.0327, "step": 14750 }, { "epoch": 0.8146123260437376, "grad_norm": 2.185903787612915, "learning_rate": 3.4983857843885873e-06, "loss": 0.1593, "step": 14751 }, { "epoch": 0.8146675502540314, "grad_norm": 0.0899772197008133, "learning_rate": 3.496364815602482e-06, "loss": 0.0033, "step": 14752 }, { "epoch": 0.8147227744643252, "grad_norm": 1.2724491357803345, "learning_rate": 3.4943443748146534e-06, "loss": 0.0757, "step": 14753 }, { "epoch": 0.814777998674619, "grad_norm": 1.5390385389328003, "learning_rate": 3.49232446208974e-06, "loss": 0.1581, "step": 14754 }, { "epoch": 0.8148332228849128, "grad_norm": 8.14063549041748, "learning_rate": 3.490305077492362e-06, "loss": 1.3101, "step": 14755 }, { "epoch": 0.8148884470952066, "grad_norm": 3.471616744995117, "learning_rate": 3.4882862210871203e-06, "loss": 0.673, "step": 14756 }, { "epoch": 0.8149436713055004, "grad_norm": 0.08410143852233887, "learning_rate": 3.4862678929386196e-06, "loss": 0.002, "step": 14757 }, { "epoch": 0.8149988955157941, "grad_norm": 3.536641836166382, "learning_rate": 3.4842500931114098e-06, "loss": 0.5827, "step": 14758 }, { "epoch": 0.8150541197260879, "grad_norm": 0.06335225701332092, "learning_rate": 3.4822328216700664e-06, "loss": 0.0018, "step": 14759 }, { "epoch": 0.8151093439363817, "grad_norm": 0.06673275679349899, "learning_rate": 3.480216078679115e-06, "loss": 0.0014, "step": 14760 }, { "epoch": 0.8151645681466755, "grad_norm": 2.4361512660980225, "learning_rate": 3.4781998642030824e-06, "loss": 0.117, "step": 14761 }, { "epoch": 0.8152197923569693, "grad_norm": 3.3142080307006836, "learning_rate": 3.476184178306468e-06, "loss": 0.338, "step": 14762 }, { "epoch": 0.8152750165672631, "grad_norm": 2.468475341796875, "learning_rate": 3.474169021053766e-06, "loss": 0.1218, "step": 14763 }, { "epoch": 0.8153302407775569, "grad_norm": 1.1156502962112427, "learning_rate": 3.472154392509446e-06, "loss": 0.0438, "step": 14764 }, { "epoch": 0.8153854649878507, "grad_norm": 0.024481195956468582, "learning_rate": 3.470140292737958e-06, "loss": 0.0006, "step": 14765 }, { "epoch": 0.8154406891981445, "grad_norm": 5.647340774536133, "learning_rate": 3.4681267218037417e-06, "loss": 0.8263, "step": 14766 }, { "epoch": 0.8154959134084383, "grad_norm": 2.522768020629883, "learning_rate": 3.4661136797712145e-06, "loss": 0.5918, "step": 14767 }, { "epoch": 0.8155511376187321, "grad_norm": 2.3455464839935303, "learning_rate": 3.4641011667047765e-06, "loss": 0.2917, "step": 14768 }, { "epoch": 0.8156063618290258, "grad_norm": 0.017337219789624214, "learning_rate": 3.462089182668822e-06, "loss": 0.0004, "step": 14769 }, { "epoch": 0.8156615860393196, "grad_norm": 0.08314443379640579, "learning_rate": 3.460077727727715e-06, "loss": 0.0028, "step": 14770 }, { "epoch": 0.8157168102496134, "grad_norm": 0.0393492616713047, "learning_rate": 3.458066801945812e-06, "loss": 0.0011, "step": 14771 }, { "epoch": 0.8157720344599072, "grad_norm": 0.03732924908399582, "learning_rate": 3.456056405387438e-06, "loss": 0.0012, "step": 14772 }, { "epoch": 0.815827258670201, "grad_norm": 0.9602112174034119, "learning_rate": 3.4540465381169265e-06, "loss": 0.0194, "step": 14773 }, { "epoch": 0.8158824828804948, "grad_norm": 0.06035618111491203, "learning_rate": 3.4520372001985615e-06, "loss": 0.0015, "step": 14774 }, { "epoch": 0.8159377070907886, "grad_norm": 0.031078649684786797, "learning_rate": 3.4500283916966424e-06, "loss": 0.0009, "step": 14775 }, { "epoch": 0.8159929313010824, "grad_norm": 4.531204700469971, "learning_rate": 3.44802011267543e-06, "loss": 0.4774, "step": 14776 }, { "epoch": 0.8160481555113762, "grad_norm": 0.059280138462781906, "learning_rate": 3.446012363199176e-06, "loss": 0.002, "step": 14777 }, { "epoch": 0.81610337972167, "grad_norm": 0.30748450756073, "learning_rate": 3.4440051433321077e-06, "loss": 0.0072, "step": 14778 }, { "epoch": 0.8161586039319638, "grad_norm": 0.5055208802223206, "learning_rate": 3.441998453138453e-06, "loss": 0.0148, "step": 14779 }, { "epoch": 0.8162138281422575, "grad_norm": 5.131640911102295, "learning_rate": 3.439992292682406e-06, "loss": 1.1845, "step": 14780 }, { "epoch": 0.8162690523525513, "grad_norm": 0.226046621799469, "learning_rate": 3.43798666202815e-06, "loss": 0.0071, "step": 14781 }, { "epoch": 0.8163242765628451, "grad_norm": 0.21303477883338928, "learning_rate": 3.4359815612398473e-06, "loss": 0.005, "step": 14782 }, { "epoch": 0.8163795007731389, "grad_norm": 1.9474380016326904, "learning_rate": 3.4339769903816576e-06, "loss": 0.0893, "step": 14783 }, { "epoch": 0.8164347249834327, "grad_norm": 0.07709842920303345, "learning_rate": 3.4319729495176967e-06, "loss": 0.0019, "step": 14784 }, { "epoch": 0.8164899491937265, "grad_norm": 0.7968148589134216, "learning_rate": 3.429969438712093e-06, "loss": 0.031, "step": 14785 }, { "epoch": 0.8165451734040203, "grad_norm": 8.59721565246582, "learning_rate": 3.4279664580289394e-06, "loss": 1.46, "step": 14786 }, { "epoch": 0.8166003976143141, "grad_norm": 3.315476894378662, "learning_rate": 3.4259640075323186e-06, "loss": 0.6238, "step": 14787 }, { "epoch": 0.8166556218246079, "grad_norm": 1.5320128202438354, "learning_rate": 3.4239620872862878e-06, "loss": 0.066, "step": 14788 }, { "epoch": 0.8167108460349017, "grad_norm": 3.3529727458953857, "learning_rate": 3.421960697354909e-06, "loss": 0.6396, "step": 14789 }, { "epoch": 0.8167660702451955, "grad_norm": 2.7536208629608154, "learning_rate": 3.4199598378021937e-06, "loss": 0.2273, "step": 14790 }, { "epoch": 0.8168212944554892, "grad_norm": 0.7387523651123047, "learning_rate": 3.41795950869217e-06, "loss": 0.0235, "step": 14791 }, { "epoch": 0.816876518665783, "grad_norm": 0.9383196830749512, "learning_rate": 3.4159597100888277e-06, "loss": 0.0102, "step": 14792 }, { "epoch": 0.8169317428760768, "grad_norm": 0.4713555574417114, "learning_rate": 3.4139604420561457e-06, "loss": 0.1212, "step": 14793 }, { "epoch": 0.8169869670863706, "grad_norm": 1.1347918510437012, "learning_rate": 3.4119617046580846e-06, "loss": 0.0384, "step": 14794 }, { "epoch": 0.8170421912966644, "grad_norm": 2.062617540359497, "learning_rate": 3.4099634979585974e-06, "loss": 0.0753, "step": 14795 }, { "epoch": 0.8170974155069582, "grad_norm": 3.0058629512786865, "learning_rate": 3.4079658220216062e-06, "loss": 0.1312, "step": 14796 }, { "epoch": 0.817152639717252, "grad_norm": 1.1405311822891235, "learning_rate": 3.4059686769110246e-06, "loss": 0.0398, "step": 14797 }, { "epoch": 0.8172078639275459, "grad_norm": 0.15955445170402527, "learning_rate": 3.4039720626907414e-06, "loss": 0.006, "step": 14798 }, { "epoch": 0.8172630881378397, "grad_norm": 0.2740849554538727, "learning_rate": 3.40197597942465e-06, "loss": 0.003, "step": 14799 }, { "epoch": 0.8173183123481335, "grad_norm": 0.02957678958773613, "learning_rate": 3.3999804271765923e-06, "loss": 0.0005, "step": 14800 }, { "epoch": 0.8173735365584273, "grad_norm": 0.43243861198425293, "learning_rate": 3.3979854060104157e-06, "loss": 0.008, "step": 14801 }, { "epoch": 0.817428760768721, "grad_norm": 0.015114369802176952, "learning_rate": 3.3959909159899528e-06, "loss": 0.0003, "step": 14802 }, { "epoch": 0.8174839849790148, "grad_norm": 3.174384355545044, "learning_rate": 3.393996957179011e-06, "loss": 0.5954, "step": 14803 }, { "epoch": 0.8175392091893086, "grad_norm": 5.6988677978515625, "learning_rate": 3.3920035296413813e-06, "loss": 1.2569, "step": 14804 }, { "epoch": 0.8175944333996024, "grad_norm": 0.28775554895401, "learning_rate": 3.3900106334408413e-06, "loss": 0.0087, "step": 14805 }, { "epoch": 0.8176496576098962, "grad_norm": 0.05607283487915993, "learning_rate": 3.3880182686411444e-06, "loss": 0.0016, "step": 14806 }, { "epoch": 0.81770488182019, "grad_norm": 1.406535267829895, "learning_rate": 3.3860264353060336e-06, "loss": 0.0583, "step": 14807 }, { "epoch": 0.8177601060304838, "grad_norm": 3.07129168510437, "learning_rate": 3.3840351334992395e-06, "loss": 0.7239, "step": 14808 }, { "epoch": 0.8178153302407776, "grad_norm": 0.179007425904274, "learning_rate": 3.3820443632844625e-06, "loss": 0.0035, "step": 14809 }, { "epoch": 0.8178705544510714, "grad_norm": 0.7880167365074158, "learning_rate": 3.3800541247253982e-06, "loss": 0.0207, "step": 14810 }, { "epoch": 0.8179257786613652, "grad_norm": 0.35584312677383423, "learning_rate": 3.3780644178857113e-06, "loss": 0.0098, "step": 14811 }, { "epoch": 0.817981002871659, "grad_norm": 2.8241963386535645, "learning_rate": 3.3760752428290732e-06, "loss": 0.2122, "step": 14812 }, { "epoch": 0.8180362270819528, "grad_norm": 0.017990315333008766, "learning_rate": 3.3740865996191063e-06, "loss": 0.0004, "step": 14813 }, { "epoch": 0.8180914512922465, "grad_norm": 0.6486129760742188, "learning_rate": 3.372098488319444e-06, "loss": 0.1027, "step": 14814 }, { "epoch": 0.8181466755025403, "grad_norm": 1.4650373458862305, "learning_rate": 3.370110908993691e-06, "loss": 0.0558, "step": 14815 }, { "epoch": 0.8182018997128341, "grad_norm": 0.04721829667687416, "learning_rate": 3.3681238617054324e-06, "loss": 0.0014, "step": 14816 }, { "epoch": 0.8182571239231279, "grad_norm": 0.008824499323964119, "learning_rate": 3.3661373465182347e-06, "loss": 0.0002, "step": 14817 }, { "epoch": 0.8183123481334217, "grad_norm": 5.561806678771973, "learning_rate": 3.3641513634956623e-06, "loss": 0.6651, "step": 14818 }, { "epoch": 0.8183675723437155, "grad_norm": 0.12077775597572327, "learning_rate": 3.3621659127012495e-06, "loss": 0.0033, "step": 14819 }, { "epoch": 0.8184227965540093, "grad_norm": 1.6507132053375244, "learning_rate": 3.360180994198512e-06, "loss": 0.11, "step": 14820 }, { "epoch": 0.8184780207643031, "grad_norm": 3.6144344806671143, "learning_rate": 3.3581966080509544e-06, "loss": 0.4382, "step": 14821 }, { "epoch": 0.8185332449745969, "grad_norm": 3.161229133605957, "learning_rate": 3.3562127543220725e-06, "loss": 0.1863, "step": 14822 }, { "epoch": 0.8185884691848907, "grad_norm": 5.086432933807373, "learning_rate": 3.3542294330753177e-06, "loss": 0.4417, "step": 14823 }, { "epoch": 0.8186436933951845, "grad_norm": 2.740863561630249, "learning_rate": 3.3522466443741574e-06, "loss": 0.1987, "step": 14824 }, { "epoch": 0.8186989176054782, "grad_norm": 0.09733244776725769, "learning_rate": 3.350264388282021e-06, "loss": 0.0028, "step": 14825 }, { "epoch": 0.818754141815772, "grad_norm": 0.043878573924303055, "learning_rate": 3.3482826648623257e-06, "loss": 0.0007, "step": 14826 }, { "epoch": 0.8188093660260658, "grad_norm": 0.20117032527923584, "learning_rate": 3.3463014741784682e-06, "loss": 0.0062, "step": 14827 }, { "epoch": 0.8188645902363596, "grad_norm": 5.2609710693359375, "learning_rate": 3.3443208162938468e-06, "loss": 0.9634, "step": 14828 }, { "epoch": 0.8189198144466534, "grad_norm": 0.9353684186935425, "learning_rate": 3.3423406912718104e-06, "loss": 0.0208, "step": 14829 }, { "epoch": 0.8189750386569472, "grad_norm": 2.7775208950042725, "learning_rate": 3.340361099175724e-06, "loss": 0.1578, "step": 14830 }, { "epoch": 0.819030262867241, "grad_norm": 3.4185643196105957, "learning_rate": 3.3383820400689105e-06, "loss": 0.3396, "step": 14831 }, { "epoch": 0.8190854870775348, "grad_norm": 2.657245397567749, "learning_rate": 3.3364035140146924e-06, "loss": 0.4578, "step": 14832 }, { "epoch": 0.8191407112878286, "grad_norm": 1.2456773519515991, "learning_rate": 3.3344255210763587e-06, "loss": 0.0411, "step": 14833 }, { "epoch": 0.8191959354981224, "grad_norm": 0.4138842225074768, "learning_rate": 3.3324480613172018e-06, "loss": 0.0066, "step": 14834 }, { "epoch": 0.8192511597084162, "grad_norm": 0.056359387934207916, "learning_rate": 3.3304711348004815e-06, "loss": 0.0018, "step": 14835 }, { "epoch": 0.8193063839187099, "grad_norm": 0.6642009019851685, "learning_rate": 3.3284947415894454e-06, "loss": 0.019, "step": 14836 }, { "epoch": 0.8193616081290037, "grad_norm": 1.6138551235198975, "learning_rate": 3.3265188817473203e-06, "loss": 0.1915, "step": 14837 }, { "epoch": 0.8194168323392975, "grad_norm": 3.668543577194214, "learning_rate": 3.324543555337334e-06, "loss": 0.3639, "step": 14838 }, { "epoch": 0.8194720565495913, "grad_norm": 2.8883438110351562, "learning_rate": 3.322568762422662e-06, "loss": 0.4909, "step": 14839 }, { "epoch": 0.8195272807598851, "grad_norm": 2.6292107105255127, "learning_rate": 3.320594503066499e-06, "loss": 0.4021, "step": 14840 }, { "epoch": 0.8195825049701789, "grad_norm": 1.9415165185928345, "learning_rate": 3.3186207773320002e-06, "loss": 0.0704, "step": 14841 }, { "epoch": 0.8196377291804727, "grad_norm": 1.5170259475708008, "learning_rate": 3.3166475852823134e-06, "loss": 0.0374, "step": 14842 }, { "epoch": 0.8196929533907665, "grad_norm": 0.19720052182674408, "learning_rate": 3.314674926980561e-06, "loss": 0.0034, "step": 14843 }, { "epoch": 0.8197481776010603, "grad_norm": 0.6024632453918457, "learning_rate": 3.3127028024898644e-06, "loss": 0.1032, "step": 14844 }, { "epoch": 0.8198034018113541, "grad_norm": 0.24734026193618774, "learning_rate": 3.31073121187331e-06, "loss": 0.0052, "step": 14845 }, { "epoch": 0.8198586260216479, "grad_norm": 4.201658248901367, "learning_rate": 3.3087601551939773e-06, "loss": 0.9985, "step": 14846 }, { "epoch": 0.8199138502319416, "grad_norm": 5.407805919647217, "learning_rate": 3.306789632514926e-06, "loss": 0.2194, "step": 14847 }, { "epoch": 0.8199690744422354, "grad_norm": 1.8110283613204956, "learning_rate": 3.3048196438991974e-06, "loss": 0.1203, "step": 14848 }, { "epoch": 0.8200242986525292, "grad_norm": 2.9149839878082275, "learning_rate": 3.302850189409812e-06, "loss": 0.4566, "step": 14849 }, { "epoch": 0.820079522862823, "grad_norm": 0.029154350981116295, "learning_rate": 3.300881269109788e-06, "loss": 0.0009, "step": 14850 }, { "epoch": 0.8201347470731168, "grad_norm": 0.20047248899936676, "learning_rate": 3.298912883062115e-06, "loss": 0.005, "step": 14851 }, { "epoch": 0.8201899712834106, "grad_norm": 4.007165908813477, "learning_rate": 3.2969450313297615e-06, "loss": 0.966, "step": 14852 }, { "epoch": 0.8202451954937044, "grad_norm": 0.03001256287097931, "learning_rate": 3.2949777139756843e-06, "loss": 0.0007, "step": 14853 }, { "epoch": 0.8203004197039983, "grad_norm": 0.5180357694625854, "learning_rate": 3.293010931062839e-06, "loss": 0.0115, "step": 14854 }, { "epoch": 0.820355643914292, "grad_norm": 0.3705446422100067, "learning_rate": 3.2910446826541254e-06, "loss": 0.01, "step": 14855 }, { "epoch": 0.8204108681245859, "grad_norm": 0.3689381182193756, "learning_rate": 3.2890789688124646e-06, "loss": 0.1292, "step": 14856 }, { "epoch": 0.8204660923348797, "grad_norm": 2.4863102436065674, "learning_rate": 3.2871137896007422e-06, "loss": 0.1236, "step": 14857 }, { "epoch": 0.8205213165451734, "grad_norm": 0.013568298891186714, "learning_rate": 3.2851491450818297e-06, "loss": 0.0004, "step": 14858 }, { "epoch": 0.8205765407554672, "grad_norm": 0.3388943076133728, "learning_rate": 3.2831850353185744e-06, "loss": 0.0051, "step": 14859 }, { "epoch": 0.820631764965761, "grad_norm": 0.6556620597839355, "learning_rate": 3.281221460373827e-06, "loss": 0.0269, "step": 14860 }, { "epoch": 0.8206869891760548, "grad_norm": 3.0283069610595703, "learning_rate": 3.279258420310407e-06, "loss": 0.3863, "step": 14861 }, { "epoch": 0.8207422133863486, "grad_norm": 5.297527313232422, "learning_rate": 3.277295915191101e-06, "loss": 0.6565, "step": 14862 }, { "epoch": 0.8207974375966424, "grad_norm": 0.5070071816444397, "learning_rate": 3.2753339450787114e-06, "loss": 0.0118, "step": 14863 }, { "epoch": 0.8208526618069362, "grad_norm": 2.0484845638275146, "learning_rate": 3.2733725100360013e-06, "loss": 0.0461, "step": 14864 }, { "epoch": 0.82090788601723, "grad_norm": 3.2431089878082275, "learning_rate": 3.271411610125723e-06, "loss": 0.0551, "step": 14865 }, { "epoch": 0.8209631102275238, "grad_norm": 0.04968477413058281, "learning_rate": 3.2694512454106063e-06, "loss": 0.0009, "step": 14866 }, { "epoch": 0.8210183344378176, "grad_norm": 0.04301737993955612, "learning_rate": 3.2674914159533855e-06, "loss": 0.001, "step": 14867 }, { "epoch": 0.8210735586481114, "grad_norm": 0.44774556159973145, "learning_rate": 3.265532121816739e-06, "loss": 0.0106, "step": 14868 }, { "epoch": 0.8211287828584051, "grad_norm": 4.065955638885498, "learning_rate": 3.263573363063366e-06, "loss": 0.2161, "step": 14869 }, { "epoch": 0.8211840070686989, "grad_norm": 3.4452877044677734, "learning_rate": 3.261615139755927e-06, "loss": 0.1979, "step": 14870 }, { "epoch": 0.8212392312789927, "grad_norm": 0.3258785605430603, "learning_rate": 3.259657451957072e-06, "loss": 0.0081, "step": 14871 }, { "epoch": 0.8212944554892865, "grad_norm": 0.037289079278707504, "learning_rate": 3.257700299729427e-06, "loss": 0.001, "step": 14872 }, { "epoch": 0.8213496796995803, "grad_norm": 0.2512015104293823, "learning_rate": 3.2557436831356195e-06, "loss": 0.0051, "step": 14873 }, { "epoch": 0.8214049039098741, "grad_norm": 0.04862520843744278, "learning_rate": 3.253787602238239e-06, "loss": 0.0014, "step": 14874 }, { "epoch": 0.8214601281201679, "grad_norm": 0.26341092586517334, "learning_rate": 3.251832057099866e-06, "loss": 0.005, "step": 14875 }, { "epoch": 0.8215153523304617, "grad_norm": 1.5506479740142822, "learning_rate": 3.249877047783063e-06, "loss": 0.4019, "step": 14876 }, { "epoch": 0.8215705765407555, "grad_norm": 0.0794345885515213, "learning_rate": 3.2479225743503885e-06, "loss": 0.0026, "step": 14877 }, { "epoch": 0.8216258007510493, "grad_norm": 0.14092187583446503, "learning_rate": 3.245968636864352e-06, "loss": 0.0033, "step": 14878 }, { "epoch": 0.8216810249613431, "grad_norm": 0.06288906931877136, "learning_rate": 3.2440152353874787e-06, "loss": 0.0021, "step": 14879 }, { "epoch": 0.8217362491716369, "grad_norm": 0.16673152148723602, "learning_rate": 3.2420623699822618e-06, "loss": 0.0058, "step": 14880 }, { "epoch": 0.8217914733819306, "grad_norm": 7.474091529846191, "learning_rate": 3.2401100407111753e-06, "loss": 1.611, "step": 14881 }, { "epoch": 0.8218466975922244, "grad_norm": 1.9566478729248047, "learning_rate": 3.238158247636678e-06, "loss": 0.1787, "step": 14882 }, { "epoch": 0.8219019218025182, "grad_norm": 4.9558000564575195, "learning_rate": 3.2362069908212245e-06, "loss": 0.1911, "step": 14883 }, { "epoch": 0.821957146012812, "grad_norm": 0.06171407923102379, "learning_rate": 3.2342562703272318e-06, "loss": 0.0016, "step": 14884 }, { "epoch": 0.8220123702231058, "grad_norm": 0.03902998939156532, "learning_rate": 3.2323060862171096e-06, "loss": 0.0009, "step": 14885 }, { "epoch": 0.8220675944333996, "grad_norm": 1.7373801469802856, "learning_rate": 3.2303564385532525e-06, "loss": 0.0177, "step": 14886 }, { "epoch": 0.8221228186436934, "grad_norm": 3.4382989406585693, "learning_rate": 3.2284073273980355e-06, "loss": 0.6457, "step": 14887 }, { "epoch": 0.8221780428539872, "grad_norm": 2.30804705619812, "learning_rate": 3.226458752813808e-06, "loss": 0.0503, "step": 14888 }, { "epoch": 0.822233267064281, "grad_norm": 0.01257314346730709, "learning_rate": 3.2245107148629228e-06, "loss": 0.0004, "step": 14889 }, { "epoch": 0.8222884912745748, "grad_norm": 1.8178911209106445, "learning_rate": 3.2225632136076967e-06, "loss": 0.4504, "step": 14890 }, { "epoch": 0.8223437154848686, "grad_norm": 0.006608095485717058, "learning_rate": 3.2206162491104375e-06, "loss": 0.0002, "step": 14891 }, { "epoch": 0.8223989396951623, "grad_norm": 3.114197015762329, "learning_rate": 3.2186698214334266e-06, "loss": 0.3808, "step": 14892 }, { "epoch": 0.8224541639054561, "grad_norm": 2.0539941787719727, "learning_rate": 3.216723930638954e-06, "loss": 0.5684, "step": 14893 }, { "epoch": 0.8225093881157499, "grad_norm": 3.4671754837036133, "learning_rate": 3.2147785767892525e-06, "loss": 0.7885, "step": 14894 }, { "epoch": 0.8225646123260437, "grad_norm": 1.6810579299926758, "learning_rate": 3.2128337599465743e-06, "loss": 0.0974, "step": 14895 }, { "epoch": 0.8226198365363375, "grad_norm": 0.484068900346756, "learning_rate": 3.210889480173136e-06, "loss": 0.0117, "step": 14896 }, { "epoch": 0.8226750607466313, "grad_norm": 0.1342030167579651, "learning_rate": 3.2089457375311393e-06, "loss": 0.0051, "step": 14897 }, { "epoch": 0.8227302849569251, "grad_norm": 0.11121866106987, "learning_rate": 3.207002532082766e-06, "loss": 0.0039, "step": 14898 }, { "epoch": 0.8227855091672189, "grad_norm": 4.145593166351318, "learning_rate": 3.205059863890192e-06, "loss": 0.0967, "step": 14899 }, { "epoch": 0.8228407333775127, "grad_norm": 0.011400270275771618, "learning_rate": 3.203117733015568e-06, "loss": 0.0003, "step": 14900 }, { "epoch": 0.8228959575878065, "grad_norm": 1.1449230909347534, "learning_rate": 3.2011761395210272e-06, "loss": 0.021, "step": 14901 }, { "epoch": 0.8229511817981003, "grad_norm": 5.025078773498535, "learning_rate": 3.199235083468679e-06, "loss": 0.1997, "step": 14902 }, { "epoch": 0.823006406008394, "grad_norm": 3.6885757446289062, "learning_rate": 3.197294564920641e-06, "loss": 0.3043, "step": 14903 }, { "epoch": 0.8230616302186878, "grad_norm": 5.592804908752441, "learning_rate": 3.195354583938974e-06, "loss": 1.549, "step": 14904 }, { "epoch": 0.8231168544289816, "grad_norm": 2.4435696601867676, "learning_rate": 3.1934151405857606e-06, "loss": 0.164, "step": 14905 }, { "epoch": 0.8231720786392754, "grad_norm": 3.979149580001831, "learning_rate": 3.1914762349230434e-06, "loss": 0.7653, "step": 14906 }, { "epoch": 0.8232273028495692, "grad_norm": 0.07646940648555756, "learning_rate": 3.189537867012853e-06, "loss": 0.0025, "step": 14907 }, { "epoch": 0.823282527059863, "grad_norm": 0.41724663972854614, "learning_rate": 3.1876000369171977e-06, "loss": 0.0107, "step": 14908 }, { "epoch": 0.8233377512701568, "grad_norm": 0.9462496042251587, "learning_rate": 3.1856627446980905e-06, "loss": 0.0414, "step": 14909 }, { "epoch": 0.8233929754804507, "grad_norm": 0.02516932226717472, "learning_rate": 3.18372599041749e-06, "loss": 0.0009, "step": 14910 }, { "epoch": 0.8234481996907445, "grad_norm": 0.01524883508682251, "learning_rate": 3.1817897741373736e-06, "loss": 0.0004, "step": 14911 }, { "epoch": 0.8235034239010383, "grad_norm": 2.9573049545288086, "learning_rate": 3.1798540959196832e-06, "loss": 0.6659, "step": 14912 }, { "epoch": 0.8235586481113321, "grad_norm": 0.02264668606221676, "learning_rate": 3.1779189558263424e-06, "loss": 0.0007, "step": 14913 }, { "epoch": 0.8236138723216258, "grad_norm": 0.09607622027397156, "learning_rate": 3.1759843539192616e-06, "loss": 0.0029, "step": 14914 }, { "epoch": 0.8236690965319196, "grad_norm": 0.05722123757004738, "learning_rate": 3.174050290260342e-06, "loss": 0.0013, "step": 14915 }, { "epoch": 0.8237243207422134, "grad_norm": 4.944343090057373, "learning_rate": 3.172116764911455e-06, "loss": 1.3396, "step": 14916 }, { "epoch": 0.8237795449525072, "grad_norm": 5.811701774597168, "learning_rate": 3.170183777934459e-06, "loss": 0.5029, "step": 14917 }, { "epoch": 0.823834769162801, "grad_norm": 0.004797250498086214, "learning_rate": 3.168251329391192e-06, "loss": 0.0001, "step": 14918 }, { "epoch": 0.8238899933730948, "grad_norm": 0.3725142478942871, "learning_rate": 3.1663194193434934e-06, "loss": 0.0109, "step": 14919 }, { "epoch": 0.8239452175833886, "grad_norm": 0.06736744195222855, "learning_rate": 3.1643880478531486e-06, "loss": 0.0024, "step": 14920 }, { "epoch": 0.8240004417936824, "grad_norm": 0.6321780681610107, "learning_rate": 3.1624572149819643e-06, "loss": 0.0155, "step": 14921 }, { "epoch": 0.8240556660039762, "grad_norm": 0.28121206164360046, "learning_rate": 3.1605269207917068e-06, "loss": 0.0082, "step": 14922 }, { "epoch": 0.82411089021427, "grad_norm": 4.2606024742126465, "learning_rate": 3.158597165344135e-06, "loss": 0.0414, "step": 14923 }, { "epoch": 0.8241661144245638, "grad_norm": 0.42291179299354553, "learning_rate": 3.1566679487009845e-06, "loss": 0.0151, "step": 14924 }, { "epoch": 0.8242213386348575, "grad_norm": 6.7363104820251465, "learning_rate": 3.1547392709239766e-06, "loss": 0.8091, "step": 14925 }, { "epoch": 0.8242765628451513, "grad_norm": 0.576743483543396, "learning_rate": 3.152811132074818e-06, "loss": 0.017, "step": 14926 }, { "epoch": 0.8243317870554451, "grad_norm": 3.3622875213623047, "learning_rate": 3.1508835322151855e-06, "loss": 0.0765, "step": 14927 }, { "epoch": 0.8243870112657389, "grad_norm": 2.356773614883423, "learning_rate": 3.148956471406761e-06, "loss": 0.2783, "step": 14928 }, { "epoch": 0.8244422354760327, "grad_norm": 2.434849739074707, "learning_rate": 3.1470299497111932e-06, "loss": 0.1494, "step": 14929 }, { "epoch": 0.8244974596863265, "grad_norm": 0.0411502905189991, "learning_rate": 3.145103967190115e-06, "loss": 0.001, "step": 14930 }, { "epoch": 0.8245526838966203, "grad_norm": 0.11824551969766617, "learning_rate": 3.1431785239051415e-06, "loss": 0.0026, "step": 14931 }, { "epoch": 0.8246079081069141, "grad_norm": 2.6460888385772705, "learning_rate": 3.1412536199178833e-06, "loss": 0.1106, "step": 14932 }, { "epoch": 0.8246631323172079, "grad_norm": 0.8453181982040405, "learning_rate": 3.139329255289909e-06, "loss": 0.0169, "step": 14933 }, { "epoch": 0.8247183565275017, "grad_norm": 0.6682043075561523, "learning_rate": 3.137405430082796e-06, "loss": 0.0176, "step": 14934 }, { "epoch": 0.8247735807377955, "grad_norm": 3.4935221672058105, "learning_rate": 3.1354821443580886e-06, "loss": 0.3877, "step": 14935 }, { "epoch": 0.8248288049480892, "grad_norm": 0.503044068813324, "learning_rate": 3.1335593981773194e-06, "loss": 0.0121, "step": 14936 }, { "epoch": 0.824884029158383, "grad_norm": 0.21648353338241577, "learning_rate": 3.131637191601995e-06, "loss": 0.0067, "step": 14937 }, { "epoch": 0.8249392533686768, "grad_norm": 5.892816066741943, "learning_rate": 3.1297155246936262e-06, "loss": 0.7646, "step": 14938 }, { "epoch": 0.8249944775789706, "grad_norm": 0.033424947410821915, "learning_rate": 3.127794397513684e-06, "loss": 0.0009, "step": 14939 }, { "epoch": 0.8250497017892644, "grad_norm": 0.013970151543617249, "learning_rate": 3.1258738101236317e-06, "loss": 0.0004, "step": 14940 }, { "epoch": 0.8251049259995582, "grad_norm": 0.0870562493801117, "learning_rate": 3.1239537625849104e-06, "loss": 0.0023, "step": 14941 }, { "epoch": 0.825160150209852, "grad_norm": 2.010223627090454, "learning_rate": 3.122034254958961e-06, "loss": 0.1537, "step": 14942 }, { "epoch": 0.8252153744201458, "grad_norm": 0.17628982663154602, "learning_rate": 3.120115287307177e-06, "loss": 0.0039, "step": 14943 }, { "epoch": 0.8252705986304396, "grad_norm": 2.561744213104248, "learning_rate": 3.1181968596909652e-06, "loss": 0.1518, "step": 14944 }, { "epoch": 0.8253258228407334, "grad_norm": 0.10793957114219666, "learning_rate": 3.1162789721716937e-06, "loss": 0.0019, "step": 14945 }, { "epoch": 0.8253810470510272, "grad_norm": 0.8647563457489014, "learning_rate": 3.1143616248107244e-06, "loss": 0.0179, "step": 14946 }, { "epoch": 0.8254362712613209, "grad_norm": 0.02743317186832428, "learning_rate": 3.1124448176693956e-06, "loss": 0.0008, "step": 14947 }, { "epoch": 0.8254914954716147, "grad_norm": 0.13315021991729736, "learning_rate": 3.110528550809042e-06, "loss": 0.0035, "step": 14948 }, { "epoch": 0.8255467196819085, "grad_norm": 5.5605082511901855, "learning_rate": 3.108612824290951e-06, "loss": 0.2135, "step": 14949 }, { "epoch": 0.8256019438922023, "grad_norm": 0.1600242555141449, "learning_rate": 3.10669763817643e-06, "loss": 0.0038, "step": 14950 }, { "epoch": 0.8256571681024961, "grad_norm": 0.17497646808624268, "learning_rate": 3.104782992526745e-06, "loss": 0.0037, "step": 14951 }, { "epoch": 0.8257123923127899, "grad_norm": 0.023579243570566177, "learning_rate": 3.10286888740315e-06, "loss": 0.0009, "step": 14952 }, { "epoch": 0.8257676165230837, "grad_norm": 0.049236271530389786, "learning_rate": 3.1009553228668764e-06, "loss": 0.0019, "step": 14953 }, { "epoch": 0.8258228407333775, "grad_norm": 2.8272082805633545, "learning_rate": 3.09904229897916e-06, "loss": 0.1585, "step": 14954 }, { "epoch": 0.8258780649436713, "grad_norm": 1.8399890661239624, "learning_rate": 3.097129815801192e-06, "loss": 0.3811, "step": 14955 }, { "epoch": 0.8259332891539651, "grad_norm": 0.73138427734375, "learning_rate": 3.095217873394165e-06, "loss": 0.1169, "step": 14956 }, { "epoch": 0.8259885133642589, "grad_norm": 6.97601842880249, "learning_rate": 3.0933064718192375e-06, "loss": 1.7625, "step": 14957 }, { "epoch": 0.8260437375745527, "grad_norm": 1.8659160137176514, "learning_rate": 3.0913956111375755e-06, "loss": 0.121, "step": 14958 }, { "epoch": 0.8260989617848464, "grad_norm": 2.219324827194214, "learning_rate": 3.0894852914102968e-06, "loss": 0.3491, "step": 14959 }, { "epoch": 0.8261541859951402, "grad_norm": 0.6475417613983154, "learning_rate": 3.0875755126985286e-06, "loss": 0.0166, "step": 14960 }, { "epoch": 0.826209410205434, "grad_norm": 0.01077846996486187, "learning_rate": 3.0856662750633683e-06, "loss": 0.0003, "step": 14961 }, { "epoch": 0.8262646344157278, "grad_norm": 1.984673023223877, "learning_rate": 3.083757578565898e-06, "loss": 0.1067, "step": 14962 }, { "epoch": 0.8263198586260216, "grad_norm": 1.468037724494934, "learning_rate": 3.081849423267176e-06, "loss": 0.0745, "step": 14963 }, { "epoch": 0.8263750828363154, "grad_norm": 0.003818964120000601, "learning_rate": 3.0799418092282575e-06, "loss": 0.0001, "step": 14964 }, { "epoch": 0.8264303070466092, "grad_norm": 0.42857277393341064, "learning_rate": 3.0780347365101716e-06, "loss": 0.0096, "step": 14965 }, { "epoch": 0.826485531256903, "grad_norm": 3.2834253311157227, "learning_rate": 3.0761282051739295e-06, "loss": 0.0655, "step": 14966 }, { "epoch": 0.8265407554671969, "grad_norm": 2.5419061183929443, "learning_rate": 3.0742222152805246e-06, "loss": 0.2464, "step": 14967 }, { "epoch": 0.8265959796774907, "grad_norm": 1.8336269855499268, "learning_rate": 3.072316766890937e-06, "loss": 0.0992, "step": 14968 }, { "epoch": 0.8266512038877845, "grad_norm": 0.4621991217136383, "learning_rate": 3.070411860066125e-06, "loss": 0.0113, "step": 14969 }, { "epoch": 0.8267064280980781, "grad_norm": 0.050178829580545425, "learning_rate": 3.0685074948670346e-06, "loss": 0.0013, "step": 14970 }, { "epoch": 0.826761652308372, "grad_norm": 0.681926965713501, "learning_rate": 3.0666036713545933e-06, "loss": 0.1657, "step": 14971 }, { "epoch": 0.8268168765186658, "grad_norm": 0.5365489721298218, "learning_rate": 3.0647003895897074e-06, "loss": 0.0169, "step": 14972 }, { "epoch": 0.8268721007289596, "grad_norm": 0.003360267961397767, "learning_rate": 3.0627976496332647e-06, "loss": 0.0001, "step": 14973 }, { "epoch": 0.8269273249392534, "grad_norm": 0.8975973725318909, "learning_rate": 3.060895451546153e-06, "loss": 0.1314, "step": 14974 }, { "epoch": 0.8269825491495472, "grad_norm": 0.08352448791265488, "learning_rate": 3.058993795389209e-06, "loss": 0.0027, "step": 14975 }, { "epoch": 0.827037773359841, "grad_norm": 5.492309093475342, "learning_rate": 3.057092681223288e-06, "loss": 0.1864, "step": 14976 }, { "epoch": 0.8270929975701348, "grad_norm": 0.11459499597549438, "learning_rate": 3.055192109109204e-06, "loss": 0.0018, "step": 14977 }, { "epoch": 0.8271482217804286, "grad_norm": 2.28391695022583, "learning_rate": 3.0532920791077657e-06, "loss": 0.5082, "step": 14978 }, { "epoch": 0.8272034459907224, "grad_norm": 0.16134148836135864, "learning_rate": 3.051392591279756e-06, "loss": 0.0046, "step": 14979 }, { "epoch": 0.8272586702010162, "grad_norm": 4.6222243309021, "learning_rate": 3.0494936456859505e-06, "loss": 0.343, "step": 14980 }, { "epoch": 0.8273138944113099, "grad_norm": 0.26768919825553894, "learning_rate": 3.047595242387105e-06, "loss": 0.0044, "step": 14981 }, { "epoch": 0.8273691186216037, "grad_norm": 0.8504558205604553, "learning_rate": 3.045697381443937e-06, "loss": 0.0248, "step": 14982 }, { "epoch": 0.8274243428318975, "grad_norm": 5.501133441925049, "learning_rate": 3.0438000629171838e-06, "loss": 1.0642, "step": 14983 }, { "epoch": 0.8274795670421913, "grad_norm": 0.020359043031930923, "learning_rate": 3.041903286867538e-06, "loss": 0.0005, "step": 14984 }, { "epoch": 0.8275347912524851, "grad_norm": 1.9850211143493652, "learning_rate": 3.0400070533556846e-06, "loss": 0.0909, "step": 14985 }, { "epoch": 0.8275900154627789, "grad_norm": 3.4390361309051514, "learning_rate": 3.038111362442282e-06, "loss": 0.6188, "step": 14986 }, { "epoch": 0.8276452396730727, "grad_norm": 0.08226937055587769, "learning_rate": 3.036216214187997e-06, "loss": 0.002, "step": 14987 }, { "epoch": 0.8277004638833665, "grad_norm": 0.051957760006189346, "learning_rate": 3.034321608653439e-06, "loss": 0.0005, "step": 14988 }, { "epoch": 0.8277556880936603, "grad_norm": 1.7714183330535889, "learning_rate": 3.0324275458992346e-06, "loss": 0.0832, "step": 14989 }, { "epoch": 0.8278109123039541, "grad_norm": 1.0095312595367432, "learning_rate": 3.0305340259859782e-06, "loss": 0.0317, "step": 14990 }, { "epoch": 0.8278661365142479, "grad_norm": 3.204277515411377, "learning_rate": 3.02864104897425e-06, "loss": 0.7187, "step": 14991 }, { "epoch": 0.8279213607245416, "grad_norm": 3.527454376220703, "learning_rate": 3.026748614924604e-06, "loss": 0.6946, "step": 14992 }, { "epoch": 0.8279765849348354, "grad_norm": 0.15293416380882263, "learning_rate": 3.0248567238975956e-06, "loss": 0.003, "step": 14993 }, { "epoch": 0.8280318091451292, "grad_norm": 0.8980989456176758, "learning_rate": 3.022965375953746e-06, "loss": 0.0238, "step": 14994 }, { "epoch": 0.828087033355423, "grad_norm": 0.015141657553613186, "learning_rate": 3.021074571153566e-06, "loss": 0.0005, "step": 14995 }, { "epoch": 0.8281422575657168, "grad_norm": 1.5573482513427734, "learning_rate": 3.0191843095575433e-06, "loss": 0.047, "step": 14996 }, { "epoch": 0.8281974817760106, "grad_norm": 2.4615440368652344, "learning_rate": 3.0172945912261653e-06, "loss": 0.2155, "step": 14997 }, { "epoch": 0.8282527059863044, "grad_norm": 2.251312494277954, "learning_rate": 3.015405416219872e-06, "loss": 0.3696, "step": 14998 }, { "epoch": 0.8283079301965982, "grad_norm": 1.3255780935287476, "learning_rate": 3.0135167845991152e-06, "loss": 0.0636, "step": 14999 }, { "epoch": 0.828363154406892, "grad_norm": 2.984790802001953, "learning_rate": 3.0116286964243178e-06, "loss": 0.234, "step": 15000 }, { "epoch": 0.8284183786171858, "grad_norm": 2.5603723526000977, "learning_rate": 3.0097411517558804e-06, "loss": 0.5699, "step": 15001 }, { "epoch": 0.8284736028274796, "grad_norm": 2.566171884536743, "learning_rate": 3.007854150654188e-06, "loss": 0.1613, "step": 15002 }, { "epoch": 0.8285288270377733, "grad_norm": 3.074695110321045, "learning_rate": 3.005967693179621e-06, "loss": 0.2171, "step": 15003 }, { "epoch": 0.8285840512480671, "grad_norm": 5.646749019622803, "learning_rate": 3.004081779392527e-06, "loss": 0.4254, "step": 15004 }, { "epoch": 0.8286392754583609, "grad_norm": 2.671542167663574, "learning_rate": 3.002196409353244e-06, "loss": 0.6392, "step": 15005 }, { "epoch": 0.8286944996686547, "grad_norm": 3.7940304279327393, "learning_rate": 3.0003115831220863e-06, "loss": 0.6327, "step": 15006 }, { "epoch": 0.8287497238789485, "grad_norm": 0.2538658082485199, "learning_rate": 2.998427300759357e-06, "loss": 0.0092, "step": 15007 }, { "epoch": 0.8288049480892423, "grad_norm": 0.008085550740361214, "learning_rate": 2.996543562325336e-06, "loss": 0.0002, "step": 15008 }, { "epoch": 0.8288601722995361, "grad_norm": 3.4139997959136963, "learning_rate": 2.994660367880298e-06, "loss": 0.1888, "step": 15009 }, { "epoch": 0.8289153965098299, "grad_norm": 1.2571731805801392, "learning_rate": 2.9927777174844854e-06, "loss": 0.0289, "step": 15010 }, { "epoch": 0.8289706207201237, "grad_norm": 0.683258056640625, "learning_rate": 2.9908956111981323e-06, "loss": 0.015, "step": 15011 }, { "epoch": 0.8290258449304175, "grad_norm": 0.10760267078876495, "learning_rate": 2.9890140490814466e-06, "loss": 0.0031, "step": 15012 }, { "epoch": 0.8290810691407113, "grad_norm": 0.11815925687551498, "learning_rate": 2.987133031194638e-06, "loss": 0.0039, "step": 15013 }, { "epoch": 0.829136293351005, "grad_norm": 3.8938310146331787, "learning_rate": 2.9852525575978687e-06, "loss": 0.4523, "step": 15014 }, { "epoch": 0.8291915175612988, "grad_norm": 3.243614435195923, "learning_rate": 2.983372628351313e-06, "loss": 0.5787, "step": 15015 }, { "epoch": 0.8292467417715926, "grad_norm": 5.804521083831787, "learning_rate": 2.9814932435151124e-06, "loss": 0.4093, "step": 15016 }, { "epoch": 0.8293019659818864, "grad_norm": 0.3593992292881012, "learning_rate": 2.9796144031493913e-06, "loss": 0.013, "step": 15017 }, { "epoch": 0.8293571901921802, "grad_norm": 1.6841983795166016, "learning_rate": 2.9777361073142553e-06, "loss": 0.1029, "step": 15018 }, { "epoch": 0.829412414402474, "grad_norm": 0.060836680233478546, "learning_rate": 2.9758583560698073e-06, "loss": 0.0013, "step": 15019 }, { "epoch": 0.8294676386127678, "grad_norm": 0.08530674874782562, "learning_rate": 2.973981149476115e-06, "loss": 0.0015, "step": 15020 }, { "epoch": 0.8295228628230616, "grad_norm": 2.2871906757354736, "learning_rate": 2.972104487593237e-06, "loss": 0.1227, "step": 15021 }, { "epoch": 0.8295780870333554, "grad_norm": 0.35824137926101685, "learning_rate": 2.9702283704812097e-06, "loss": 0.0097, "step": 15022 }, { "epoch": 0.8296333112436493, "grad_norm": 2.4427897930145264, "learning_rate": 2.968352798200065e-06, "loss": 0.066, "step": 15023 }, { "epoch": 0.829688535453943, "grad_norm": 0.09974255412817001, "learning_rate": 2.9664777708097948e-06, "loss": 0.0024, "step": 15024 }, { "epoch": 0.8297437596642367, "grad_norm": 3.8954310417175293, "learning_rate": 2.9646032883703957e-06, "loss": 0.306, "step": 15025 }, { "epoch": 0.8297989838745305, "grad_norm": 0.23551204800605774, "learning_rate": 2.9627293509418354e-06, "loss": 0.0051, "step": 15026 }, { "epoch": 0.8298542080848244, "grad_norm": 5.661612510681152, "learning_rate": 2.9608559585840656e-06, "loss": 0.6108, "step": 15027 }, { "epoch": 0.8299094322951182, "grad_norm": 7.769200325012207, "learning_rate": 2.9589831113570166e-06, "loss": 1.2239, "step": 15028 }, { "epoch": 0.829964656505412, "grad_norm": 0.7221991419792175, "learning_rate": 2.9571108093206225e-06, "loss": 0.0194, "step": 15029 }, { "epoch": 0.8300198807157058, "grad_norm": 0.29393497109413147, "learning_rate": 2.955239052534764e-06, "loss": 0.0056, "step": 15030 }, { "epoch": 0.8300751049259996, "grad_norm": 0.8708253502845764, "learning_rate": 2.953367841059336e-06, "loss": 0.0177, "step": 15031 }, { "epoch": 0.8301303291362934, "grad_norm": 3.2708580493927, "learning_rate": 2.951497174954199e-06, "loss": 0.1382, "step": 15032 }, { "epoch": 0.8301855533465872, "grad_norm": 1.0169216394424438, "learning_rate": 2.949627054279205e-06, "loss": 0.0297, "step": 15033 }, { "epoch": 0.830240777556881, "grad_norm": 1.6271140575408936, "learning_rate": 2.9477574790941752e-06, "loss": 0.1296, "step": 15034 }, { "epoch": 0.8302960017671748, "grad_norm": 0.07019698619842529, "learning_rate": 2.9458884494589334e-06, "loss": 0.0017, "step": 15035 }, { "epoch": 0.8303512259774686, "grad_norm": 4.3235087394714355, "learning_rate": 2.9440199654332734e-06, "loss": 0.4165, "step": 15036 }, { "epoch": 0.8304064501877623, "grad_norm": 1.8709121942520142, "learning_rate": 2.94215202707697e-06, "loss": 0.4283, "step": 15037 }, { "epoch": 0.8304616743980561, "grad_norm": 2.6289427280426025, "learning_rate": 2.940284634449779e-06, "loss": 0.1112, "step": 15038 }, { "epoch": 0.8305168986083499, "grad_norm": 4.9044880867004395, "learning_rate": 2.938417787611458e-06, "loss": 0.3658, "step": 15039 }, { "epoch": 0.8305721228186437, "grad_norm": 1.9773448705673218, "learning_rate": 2.936551486621717e-06, "loss": 0.064, "step": 15040 }, { "epoch": 0.8306273470289375, "grad_norm": 0.2791915237903595, "learning_rate": 2.9346857315402766e-06, "loss": 0.004, "step": 15041 }, { "epoch": 0.8306825712392313, "grad_norm": 3.518249750137329, "learning_rate": 2.93282052242682e-06, "loss": 0.0484, "step": 15042 }, { "epoch": 0.8307377954495251, "grad_norm": 5.574002742767334, "learning_rate": 2.930955859341025e-06, "loss": 0.13, "step": 15043 }, { "epoch": 0.8307930196598189, "grad_norm": 0.16336308419704437, "learning_rate": 2.9290917423425447e-06, "loss": 0.0016, "step": 15044 }, { "epoch": 0.8308482438701127, "grad_norm": 2.071601152420044, "learning_rate": 2.927228171491019e-06, "loss": 0.3455, "step": 15045 }, { "epoch": 0.8309034680804065, "grad_norm": 0.06640596687793732, "learning_rate": 2.9253651468460664e-06, "loss": 0.0013, "step": 15046 }, { "epoch": 0.8309586922907003, "grad_norm": 5.408066272735596, "learning_rate": 2.9235026684672886e-06, "loss": 1.2943, "step": 15047 }, { "epoch": 0.831013916500994, "grad_norm": 0.02134474739432335, "learning_rate": 2.9216407364142797e-06, "loss": 0.0006, "step": 15048 }, { "epoch": 0.8310691407112878, "grad_norm": 0.030777348205447197, "learning_rate": 2.919779350746603e-06, "loss": 0.0008, "step": 15049 }, { "epoch": 0.8311243649215816, "grad_norm": 0.013577034696936607, "learning_rate": 2.9179185115238094e-06, "loss": 0.0003, "step": 15050 }, { "epoch": 0.8311795891318754, "grad_norm": 0.38128572702407837, "learning_rate": 2.916058218805431e-06, "loss": 0.0088, "step": 15051 }, { "epoch": 0.8312348133421692, "grad_norm": 5.615695476531982, "learning_rate": 2.914198472650993e-06, "loss": 0.8726, "step": 15052 }, { "epoch": 0.831290037552463, "grad_norm": 0.9876444935798645, "learning_rate": 2.9123392731199794e-06, "loss": 0.0267, "step": 15053 }, { "epoch": 0.8313452617627568, "grad_norm": 0.031925614923238754, "learning_rate": 2.9104806202718827e-06, "loss": 0.001, "step": 15054 }, { "epoch": 0.8314004859730506, "grad_norm": 0.03791488707065582, "learning_rate": 2.9086225141661617e-06, "loss": 0.0009, "step": 15055 }, { "epoch": 0.8314557101833444, "grad_norm": 0.09136392921209335, "learning_rate": 2.9067649548622647e-06, "loss": 0.0022, "step": 15056 }, { "epoch": 0.8315109343936382, "grad_norm": 0.9515436291694641, "learning_rate": 2.9049079424196148e-06, "loss": 0.0242, "step": 15057 }, { "epoch": 0.831566158603932, "grad_norm": 2.230293035507202, "learning_rate": 2.9030514768976313e-06, "loss": 0.5002, "step": 15058 }, { "epoch": 0.8316213828142257, "grad_norm": 0.003610112238675356, "learning_rate": 2.9011955583557026e-06, "loss": 0.0001, "step": 15059 }, { "epoch": 0.8316766070245195, "grad_norm": 0.13404801487922668, "learning_rate": 2.899340186853208e-06, "loss": 0.0032, "step": 15060 }, { "epoch": 0.8317318312348133, "grad_norm": 3.8932340145111084, "learning_rate": 2.897485362449499e-06, "loss": 0.3553, "step": 15061 }, { "epoch": 0.8317870554451071, "grad_norm": 3.8180129528045654, "learning_rate": 2.8956310852039315e-06, "loss": 0.8984, "step": 15062 }, { "epoch": 0.8318422796554009, "grad_norm": 2.998586654663086, "learning_rate": 2.893777355175811e-06, "loss": 0.2571, "step": 15063 }, { "epoch": 0.8318975038656947, "grad_norm": 0.13785693049430847, "learning_rate": 2.891924172424456e-06, "loss": 0.0028, "step": 15064 }, { "epoch": 0.8319527280759885, "grad_norm": 2.7292962074279785, "learning_rate": 2.8900715370091514e-06, "loss": 0.091, "step": 15065 }, { "epoch": 0.8320079522862823, "grad_norm": 1.3783725500106812, "learning_rate": 2.8882194489891667e-06, "loss": 0.045, "step": 15066 }, { "epoch": 0.8320631764965761, "grad_norm": 1.4651604890823364, "learning_rate": 2.886367908423755e-06, "loss": 0.0683, "step": 15067 }, { "epoch": 0.8321184007068699, "grad_norm": 4.71749210357666, "learning_rate": 2.884516915372162e-06, "loss": 0.9615, "step": 15068 }, { "epoch": 0.8321736249171637, "grad_norm": 0.08320141583681107, "learning_rate": 2.882666469893589e-06, "loss": 0.0025, "step": 15069 }, { "epoch": 0.8322288491274574, "grad_norm": 0.2144988626241684, "learning_rate": 2.8808165720472513e-06, "loss": 0.0036, "step": 15070 }, { "epoch": 0.8322840733377512, "grad_norm": 0.021857334300875664, "learning_rate": 2.8789672218923283e-06, "loss": 0.0006, "step": 15071 }, { "epoch": 0.832339297548045, "grad_norm": 5.825393199920654, "learning_rate": 2.8771184194879833e-06, "loss": 1.0104, "step": 15072 }, { "epoch": 0.8323945217583388, "grad_norm": 0.03216696158051491, "learning_rate": 2.8752701648933644e-06, "loss": 0.0009, "step": 15073 }, { "epoch": 0.8324497459686326, "grad_norm": 6.415592193603516, "learning_rate": 2.8734224581676073e-06, "loss": 0.9545, "step": 15074 }, { "epoch": 0.8325049701789264, "grad_norm": 8.369889259338379, "learning_rate": 2.8715752993698244e-06, "loss": 0.0848, "step": 15075 }, { "epoch": 0.8325601943892202, "grad_norm": 0.9540456533432007, "learning_rate": 2.86972868855911e-06, "loss": 0.0292, "step": 15076 }, { "epoch": 0.832615418599514, "grad_norm": 2.9068849086761475, "learning_rate": 2.867882625794538e-06, "loss": 0.2688, "step": 15077 }, { "epoch": 0.8326706428098078, "grad_norm": 5.213193416595459, "learning_rate": 2.8660371111351824e-06, "loss": 0.4847, "step": 15078 }, { "epoch": 0.8327258670201017, "grad_norm": 0.05766842141747475, "learning_rate": 2.86419214464007e-06, "loss": 0.0022, "step": 15079 }, { "epoch": 0.8327810912303955, "grad_norm": 0.5958218574523926, "learning_rate": 2.8623477263682376e-06, "loss": 0.0111, "step": 15080 }, { "epoch": 0.8328363154406891, "grad_norm": 7.040406227111816, "learning_rate": 2.8605038563786915e-06, "loss": 0.7836, "step": 15081 }, { "epoch": 0.832891539650983, "grad_norm": 3.61108136177063, "learning_rate": 2.85866053473042e-06, "loss": 0.5686, "step": 15082 }, { "epoch": 0.8329467638612768, "grad_norm": 2.9024932384490967, "learning_rate": 2.856817761482393e-06, "loss": 0.0905, "step": 15083 }, { "epoch": 0.8330019880715706, "grad_norm": 1.7847063541412354, "learning_rate": 2.854975536693574e-06, "loss": 0.1019, "step": 15084 }, { "epoch": 0.8330572122818644, "grad_norm": 0.03150194138288498, "learning_rate": 2.853133860422899e-06, "loss": 0.001, "step": 15085 }, { "epoch": 0.8331124364921582, "grad_norm": 0.02402719296514988, "learning_rate": 2.851292732729285e-06, "loss": 0.0008, "step": 15086 }, { "epoch": 0.833167660702452, "grad_norm": 0.055906280875205994, "learning_rate": 2.849452153671639e-06, "loss": 0.0014, "step": 15087 }, { "epoch": 0.8332228849127458, "grad_norm": 2.39853835105896, "learning_rate": 2.8476121233088427e-06, "loss": 0.1044, "step": 15088 }, { "epoch": 0.8332781091230396, "grad_norm": 3.1915740966796875, "learning_rate": 2.84577264169976e-06, "loss": 0.3289, "step": 15089 }, { "epoch": 0.8333333333333334, "grad_norm": 3.609795570373535, "learning_rate": 2.8439337089032504e-06, "loss": 0.6743, "step": 15090 }, { "epoch": 0.8333885575436272, "grad_norm": 1.6369118690490723, "learning_rate": 2.8420953249781446e-06, "loss": 0.0409, "step": 15091 }, { "epoch": 0.8334437817539209, "grad_norm": 1.0871694087982178, "learning_rate": 2.8402574899832557e-06, "loss": 0.1368, "step": 15092 }, { "epoch": 0.8334990059642147, "grad_norm": 0.02213384211063385, "learning_rate": 2.8384202039773743e-06, "loss": 0.0007, "step": 15093 }, { "epoch": 0.8335542301745085, "grad_norm": 1.6084853410720825, "learning_rate": 2.8365834670192983e-06, "loss": 0.1741, "step": 15094 }, { "epoch": 0.8336094543848023, "grad_norm": 3.0713961124420166, "learning_rate": 2.834747279167771e-06, "loss": 0.4639, "step": 15095 }, { "epoch": 0.8336646785950961, "grad_norm": 0.04162095487117767, "learning_rate": 2.8329116404815483e-06, "loss": 0.001, "step": 15096 }, { "epoch": 0.8337199028053899, "grad_norm": 5.969539642333984, "learning_rate": 2.831076551019356e-06, "loss": 1.1908, "step": 15097 }, { "epoch": 0.8337751270156837, "grad_norm": 2.829124927520752, "learning_rate": 2.829242010839903e-06, "loss": 0.2946, "step": 15098 }, { "epoch": 0.8338303512259775, "grad_norm": 0.6064326763153076, "learning_rate": 2.8274080200018737e-06, "loss": 0.023, "step": 15099 }, { "epoch": 0.8338855754362713, "grad_norm": 2.782979965209961, "learning_rate": 2.8255745785639588e-06, "loss": 0.2245, "step": 15100 }, { "epoch": 0.8339407996465651, "grad_norm": 0.01765085756778717, "learning_rate": 2.823741686584809e-06, "loss": 0.0006, "step": 15101 }, { "epoch": 0.8339960238568589, "grad_norm": 3.490992307662964, "learning_rate": 2.8219093441230506e-06, "loss": 0.1963, "step": 15102 }, { "epoch": 0.8340512480671527, "grad_norm": 0.03400016948580742, "learning_rate": 2.8200775512373237e-06, "loss": 0.0009, "step": 15103 }, { "epoch": 0.8341064722774464, "grad_norm": 3.609809637069702, "learning_rate": 2.8182463079862232e-06, "loss": 0.5915, "step": 15104 }, { "epoch": 0.8341616964877402, "grad_norm": 1.7153218984603882, "learning_rate": 2.816415614428336e-06, "loss": 0.1672, "step": 15105 }, { "epoch": 0.834216920698034, "grad_norm": 0.006601160392165184, "learning_rate": 2.814585470622231e-06, "loss": 0.0002, "step": 15106 }, { "epoch": 0.8342721449083278, "grad_norm": 0.6457998156547546, "learning_rate": 2.8127558766264694e-06, "loss": 0.014, "step": 15107 }, { "epoch": 0.8343273691186216, "grad_norm": 0.06295951455831528, "learning_rate": 2.8109268324995677e-06, "loss": 0.0009, "step": 15108 }, { "epoch": 0.8343825933289154, "grad_norm": 0.11251884698867798, "learning_rate": 2.809098338300058e-06, "loss": 0.0026, "step": 15109 }, { "epoch": 0.8344378175392092, "grad_norm": 0.09685906022787094, "learning_rate": 2.8072703940864323e-06, "loss": 0.0012, "step": 15110 }, { "epoch": 0.834493041749503, "grad_norm": 2.406492233276367, "learning_rate": 2.8054429999171716e-06, "loss": 0.2591, "step": 15111 }, { "epoch": 0.8345482659597968, "grad_norm": 0.11978310346603394, "learning_rate": 2.8036161558507345e-06, "loss": 0.0041, "step": 15112 }, { "epoch": 0.8346034901700906, "grad_norm": 4.642092704772949, "learning_rate": 2.8017898619455784e-06, "loss": 0.8319, "step": 15113 }, { "epoch": 0.8346587143803844, "grad_norm": 4.888377666473389, "learning_rate": 2.7999641182601255e-06, "loss": 0.7128, "step": 15114 }, { "epoch": 0.8347139385906781, "grad_norm": 0.1537647545337677, "learning_rate": 2.798138924852787e-06, "loss": 0.003, "step": 15115 }, { "epoch": 0.8347691628009719, "grad_norm": 4.662309646606445, "learning_rate": 2.796314281781951e-06, "loss": 0.4388, "step": 15116 }, { "epoch": 0.8348243870112657, "grad_norm": 2.5884718894958496, "learning_rate": 2.7944901891060074e-06, "loss": 0.3435, "step": 15117 }, { "epoch": 0.8348796112215595, "grad_norm": 0.04521742835640907, "learning_rate": 2.792666646883295e-06, "loss": 0.0014, "step": 15118 }, { "epoch": 0.8349348354318533, "grad_norm": 1.7403453588485718, "learning_rate": 2.7908436551721684e-06, "loss": 0.0635, "step": 15119 }, { "epoch": 0.8349900596421471, "grad_norm": 5.97658634185791, "learning_rate": 2.7890212140309446e-06, "loss": 0.4137, "step": 15120 }, { "epoch": 0.8350452838524409, "grad_norm": 0.31724461913108826, "learning_rate": 2.7871993235179305e-06, "loss": 0.0028, "step": 15121 }, { "epoch": 0.8351005080627347, "grad_norm": 2.4680750370025635, "learning_rate": 2.7853779836914083e-06, "loss": 0.382, "step": 15122 }, { "epoch": 0.8351557322730285, "grad_norm": 0.09824935346841812, "learning_rate": 2.7835571946096586e-06, "loss": 0.0022, "step": 15123 }, { "epoch": 0.8352109564833223, "grad_norm": 0.7913472652435303, "learning_rate": 2.781736956330925e-06, "loss": 0.0197, "step": 15124 }, { "epoch": 0.8352661806936161, "grad_norm": 0.009261462837457657, "learning_rate": 2.7799172689134435e-06, "loss": 0.0003, "step": 15125 }, { "epoch": 0.8353214049039098, "grad_norm": 0.22312618792057037, "learning_rate": 2.7780981324154342e-06, "loss": 0.0048, "step": 15126 }, { "epoch": 0.8353766291142036, "grad_norm": 3.834242343902588, "learning_rate": 2.7762795468950933e-06, "loss": 0.21, "step": 15127 }, { "epoch": 0.8354318533244974, "grad_norm": 0.00923221930861473, "learning_rate": 2.774461512410598e-06, "loss": 0.0003, "step": 15128 }, { "epoch": 0.8354870775347912, "grad_norm": 2.153733491897583, "learning_rate": 2.772644029020124e-06, "loss": 0.203, "step": 15129 }, { "epoch": 0.835542301745085, "grad_norm": 1.98423171043396, "learning_rate": 2.7708270967818095e-06, "loss": 0.0962, "step": 15130 }, { "epoch": 0.8355975259553788, "grad_norm": 0.08788545429706573, "learning_rate": 2.7690107157537883e-06, "loss": 0.0026, "step": 15131 }, { "epoch": 0.8356527501656726, "grad_norm": 4.010363578796387, "learning_rate": 2.767194885994162e-06, "loss": 0.5146, "step": 15132 }, { "epoch": 0.8357079743759664, "grad_norm": 5.71727180480957, "learning_rate": 2.765379607561041e-06, "loss": 0.9986, "step": 15133 }, { "epoch": 0.8357631985862602, "grad_norm": 0.9654393196105957, "learning_rate": 2.7635648805124814e-06, "loss": 0.015, "step": 15134 }, { "epoch": 0.835818422796554, "grad_norm": 0.8804228901863098, "learning_rate": 2.7617507049065564e-06, "loss": 0.0202, "step": 15135 }, { "epoch": 0.8358736470068479, "grad_norm": 3.526477575302124, "learning_rate": 2.7599370808013002e-06, "loss": 0.0335, "step": 15136 }, { "epoch": 0.8359288712171415, "grad_norm": 0.0781743973493576, "learning_rate": 2.758124008254739e-06, "loss": 0.002, "step": 15137 }, { "epoch": 0.8359840954274353, "grad_norm": 0.01949988678097725, "learning_rate": 2.756311487324872e-06, "loss": 0.0007, "step": 15138 }, { "epoch": 0.8360393196377292, "grad_norm": 4.021472454071045, "learning_rate": 2.7544995180696932e-06, "loss": 0.7127, "step": 15139 }, { "epoch": 0.836094543848023, "grad_norm": 2.86295223236084, "learning_rate": 2.752688100547172e-06, "loss": 0.3976, "step": 15140 }, { "epoch": 0.8361497680583168, "grad_norm": 4.323757171630859, "learning_rate": 2.750877234815259e-06, "loss": 0.7184, "step": 15141 }, { "epoch": 0.8362049922686106, "grad_norm": 0.22044678032398224, "learning_rate": 2.7490669209318844e-06, "loss": 0.0053, "step": 15142 }, { "epoch": 0.8362602164789044, "grad_norm": 0.2486928403377533, "learning_rate": 2.747257158954981e-06, "loss": 0.0054, "step": 15143 }, { "epoch": 0.8363154406891982, "grad_norm": 0.05171770602464676, "learning_rate": 2.7454479489424278e-06, "loss": 0.0011, "step": 15144 }, { "epoch": 0.836370664899492, "grad_norm": 0.09336633235216141, "learning_rate": 2.7436392909521204e-06, "loss": 0.0025, "step": 15145 }, { "epoch": 0.8364258891097858, "grad_norm": 0.014321519061923027, "learning_rate": 2.741831185041919e-06, "loss": 0.0004, "step": 15146 }, { "epoch": 0.8364811133200796, "grad_norm": 3.216170310974121, "learning_rate": 2.740023631269668e-06, "loss": 0.1391, "step": 15147 }, { "epoch": 0.8365363375303733, "grad_norm": 0.04938814789056778, "learning_rate": 2.7382166296931956e-06, "loss": 0.0016, "step": 15148 }, { "epoch": 0.8365915617406671, "grad_norm": 3.628610372543335, "learning_rate": 2.7364101803703235e-06, "loss": 0.2383, "step": 15149 }, { "epoch": 0.8366467859509609, "grad_norm": 7.685842037200928, "learning_rate": 2.734604283358828e-06, "loss": 2.0797, "step": 15150 }, { "epoch": 0.8367020101612547, "grad_norm": 2.605226755142212, "learning_rate": 2.732798938716499e-06, "loss": 0.1381, "step": 15151 }, { "epoch": 0.8367572343715485, "grad_norm": 0.9228571653366089, "learning_rate": 2.7309941465010894e-06, "loss": 0.0142, "step": 15152 }, { "epoch": 0.8368124585818423, "grad_norm": 3.1725313663482666, "learning_rate": 2.7291899067703376e-06, "loss": 0.8391, "step": 15153 }, { "epoch": 0.8368676827921361, "grad_norm": 0.6725207567214966, "learning_rate": 2.7273862195819667e-06, "loss": 0.015, "step": 15154 }, { "epoch": 0.8369229070024299, "grad_norm": 0.23279331624507904, "learning_rate": 2.725583084993688e-06, "loss": 0.0028, "step": 15155 }, { "epoch": 0.8369781312127237, "grad_norm": 1.2576534748077393, "learning_rate": 2.7237805030631825e-06, "loss": 0.0464, "step": 15156 }, { "epoch": 0.8370333554230175, "grad_norm": 1.1761127710342407, "learning_rate": 2.7219784738481236e-06, "loss": 0.1778, "step": 15157 }, { "epoch": 0.8370885796333113, "grad_norm": 0.8099488019943237, "learning_rate": 2.7201769974061566e-06, "loss": 0.0253, "step": 15158 }, { "epoch": 0.837143803843605, "grad_norm": 3.5954439640045166, "learning_rate": 2.7183760737949307e-06, "loss": 0.4332, "step": 15159 }, { "epoch": 0.8371990280538988, "grad_norm": 0.025583360344171524, "learning_rate": 2.716575703072042e-06, "loss": 0.0005, "step": 15160 }, { "epoch": 0.8372542522641926, "grad_norm": 0.04275321587920189, "learning_rate": 2.7147758852951066e-06, "loss": 0.0013, "step": 15161 }, { "epoch": 0.8373094764744864, "grad_norm": 3.629197120666504, "learning_rate": 2.712976620521699e-06, "loss": 0.2061, "step": 15162 }, { "epoch": 0.8373647006847802, "grad_norm": 0.015146281570196152, "learning_rate": 2.7111779088093814e-06, "loss": 0.0005, "step": 15163 }, { "epoch": 0.837419924895074, "grad_norm": 3.827496290206909, "learning_rate": 2.7093797502157036e-06, "loss": 0.1838, "step": 15164 }, { "epoch": 0.8374751491053678, "grad_norm": 3.4069485664367676, "learning_rate": 2.707582144798191e-06, "loss": 0.2457, "step": 15165 }, { "epoch": 0.8375303733156616, "grad_norm": 0.04826023429632187, "learning_rate": 2.705785092614357e-06, "loss": 0.0013, "step": 15166 }, { "epoch": 0.8375855975259554, "grad_norm": 2.877279043197632, "learning_rate": 2.7039885937216847e-06, "loss": 0.4001, "step": 15167 }, { "epoch": 0.8376408217362492, "grad_norm": 0.03257262334227562, "learning_rate": 2.702192648177664e-06, "loss": 0.0007, "step": 15168 }, { "epoch": 0.837696045946543, "grad_norm": 0.87796550989151, "learning_rate": 2.700397256039744e-06, "loss": 0.0352, "step": 15169 }, { "epoch": 0.8377512701568367, "grad_norm": 4.507759094238281, "learning_rate": 2.6986024173653656e-06, "loss": 0.429, "step": 15170 }, { "epoch": 0.8378064943671305, "grad_norm": 2.54202938079834, "learning_rate": 2.6968081322119455e-06, "loss": 0.2588, "step": 15171 }, { "epoch": 0.8378617185774243, "grad_norm": 3.8099372386932373, "learning_rate": 2.6950144006369037e-06, "loss": 0.6405, "step": 15172 }, { "epoch": 0.8379169427877181, "grad_norm": 0.06485331803560257, "learning_rate": 2.693221222697606e-06, "loss": 0.0019, "step": 15173 }, { "epoch": 0.8379721669980119, "grad_norm": 0.24416182935237885, "learning_rate": 2.6914285984514376e-06, "loss": 0.0068, "step": 15174 }, { "epoch": 0.8380273912083057, "grad_norm": 0.6012107729911804, "learning_rate": 2.6896365279557413e-06, "loss": 0.0242, "step": 15175 }, { "epoch": 0.8380826154185995, "grad_norm": 0.20962141454219818, "learning_rate": 2.6878450112678558e-06, "loss": 0.0061, "step": 15176 }, { "epoch": 0.8381378396288933, "grad_norm": 0.29924148321151733, "learning_rate": 2.686054048445088e-06, "loss": 0.0043, "step": 15177 }, { "epoch": 0.8381930638391871, "grad_norm": 2.5690741539001465, "learning_rate": 2.684263639544746e-06, "loss": 0.3379, "step": 15178 }, { "epoch": 0.8382482880494809, "grad_norm": 3.171574592590332, "learning_rate": 2.6824737846241044e-06, "loss": 0.5976, "step": 15179 }, { "epoch": 0.8383035122597747, "grad_norm": 4.390889644622803, "learning_rate": 2.68068448374043e-06, "loss": 0.2433, "step": 15180 }, { "epoch": 0.8383587364700685, "grad_norm": 0.08389807492494583, "learning_rate": 2.6788957369509593e-06, "loss": 0.0018, "step": 15181 }, { "epoch": 0.8384139606803622, "grad_norm": 0.1399639993906021, "learning_rate": 2.6771075443129334e-06, "loss": 0.005, "step": 15182 }, { "epoch": 0.838469184890656, "grad_norm": 0.07867922633886337, "learning_rate": 2.6753199058835466e-06, "loss": 0.0024, "step": 15183 }, { "epoch": 0.8385244091009498, "grad_norm": 3.8746540546417236, "learning_rate": 2.6735328217199994e-06, "loss": 0.2525, "step": 15184 }, { "epoch": 0.8385796333112436, "grad_norm": 0.008816919289529324, "learning_rate": 2.6717462918794646e-06, "loss": 0.0003, "step": 15185 }, { "epoch": 0.8386348575215374, "grad_norm": 0.057324085384607315, "learning_rate": 2.6699603164190957e-06, "loss": 0.0014, "step": 15186 }, { "epoch": 0.8386900817318312, "grad_norm": 0.04180894419550896, "learning_rate": 2.6681748953960296e-06, "loss": 0.0014, "step": 15187 }, { "epoch": 0.838745305942125, "grad_norm": 2.8047056198120117, "learning_rate": 2.6663900288673984e-06, "loss": 0.2573, "step": 15188 }, { "epoch": 0.8388005301524188, "grad_norm": 2.576181650161743, "learning_rate": 2.6646057168902874e-06, "loss": 0.1008, "step": 15189 }, { "epoch": 0.8388557543627126, "grad_norm": 2.2954306602478027, "learning_rate": 2.6628219595217976e-06, "loss": 0.1865, "step": 15190 }, { "epoch": 0.8389109785730064, "grad_norm": 5.7023773193359375, "learning_rate": 2.6610387568189877e-06, "loss": 0.5104, "step": 15191 }, { "epoch": 0.8389662027833003, "grad_norm": 3.1678457260131836, "learning_rate": 2.6592561088389126e-06, "loss": 0.8324, "step": 15192 }, { "epoch": 0.8390214269935939, "grad_norm": 0.9592583775520325, "learning_rate": 2.657474015638595e-06, "loss": 0.0279, "step": 15193 }, { "epoch": 0.8390766512038877, "grad_norm": 0.4537869989871979, "learning_rate": 2.6556924772750604e-06, "loss": 0.0041, "step": 15194 }, { "epoch": 0.8391318754141815, "grad_norm": 1.0967059135437012, "learning_rate": 2.653911493805301e-06, "loss": 0.0233, "step": 15195 }, { "epoch": 0.8391870996244754, "grad_norm": 0.1044243723154068, "learning_rate": 2.652131065286294e-06, "loss": 0.0034, "step": 15196 }, { "epoch": 0.8392423238347692, "grad_norm": 0.012181892991065979, "learning_rate": 2.650351191774998e-06, "loss": 0.0003, "step": 15197 }, { "epoch": 0.839297548045063, "grad_norm": 2.9793765544891357, "learning_rate": 2.648571873328367e-06, "loss": 0.4011, "step": 15198 }, { "epoch": 0.8393527722553568, "grad_norm": 0.1185990571975708, "learning_rate": 2.646793110003312e-06, "loss": 0.0034, "step": 15199 }, { "epoch": 0.8394079964656506, "grad_norm": 0.9823076725006104, "learning_rate": 2.6450149018567508e-06, "loss": 0.0563, "step": 15200 }, { "epoch": 0.8394632206759444, "grad_norm": 0.14408178627490997, "learning_rate": 2.6432372489455716e-06, "loss": 0.0044, "step": 15201 }, { "epoch": 0.8395184448862382, "grad_norm": 0.05099600553512573, "learning_rate": 2.6414601513266447e-06, "loss": 0.0018, "step": 15202 }, { "epoch": 0.839573669096532, "grad_norm": 3.1069564819335938, "learning_rate": 2.6396836090568203e-06, "loss": 0.5231, "step": 15203 }, { "epoch": 0.8396288933068257, "grad_norm": 5.376589298248291, "learning_rate": 2.6379076221929457e-06, "loss": 0.6605, "step": 15204 }, { "epoch": 0.8396841175171195, "grad_norm": 2.359463691711426, "learning_rate": 2.6361321907918336e-06, "loss": 0.7434, "step": 15205 }, { "epoch": 0.8397393417274133, "grad_norm": 0.03237786144018173, "learning_rate": 2.6343573149102852e-06, "loss": 0.0009, "step": 15206 }, { "epoch": 0.8397945659377071, "grad_norm": 0.4119848310947418, "learning_rate": 2.632582994605084e-06, "loss": 0.0149, "step": 15207 }, { "epoch": 0.8398497901480009, "grad_norm": 5.296230316162109, "learning_rate": 2.6308092299329934e-06, "loss": 1.0203, "step": 15208 }, { "epoch": 0.8399050143582947, "grad_norm": 0.4235735833644867, "learning_rate": 2.6290360209507614e-06, "loss": 0.0054, "step": 15209 }, { "epoch": 0.8399602385685885, "grad_norm": 1.163124918937683, "learning_rate": 2.627263367715125e-06, "loss": 0.0631, "step": 15210 }, { "epoch": 0.8400154627788823, "grad_norm": 2.889695167541504, "learning_rate": 2.6254912702827896e-06, "loss": 0.2908, "step": 15211 }, { "epoch": 0.8400706869891761, "grad_norm": 1.8415862321853638, "learning_rate": 2.6237197287104543e-06, "loss": 0.0805, "step": 15212 }, { "epoch": 0.8401259111994699, "grad_norm": 3.5725014209747314, "learning_rate": 2.6219487430547854e-06, "loss": 0.3747, "step": 15213 }, { "epoch": 0.8401811354097637, "grad_norm": 0.558476984500885, "learning_rate": 2.620178313372459e-06, "loss": 0.0132, "step": 15214 }, { "epoch": 0.8402363596200574, "grad_norm": 0.25809556245803833, "learning_rate": 2.618408439720099e-06, "loss": 0.0056, "step": 15215 }, { "epoch": 0.8402915838303512, "grad_norm": 0.11974900215864182, "learning_rate": 2.6166391221543407e-06, "loss": 0.0042, "step": 15216 }, { "epoch": 0.840346808040645, "grad_norm": 0.26168304681777954, "learning_rate": 2.614870360731783e-06, "loss": 0.0052, "step": 15217 }, { "epoch": 0.8404020322509388, "grad_norm": 17.55343246459961, "learning_rate": 2.6131021555090176e-06, "loss": 0.2451, "step": 15218 }, { "epoch": 0.8404572564612326, "grad_norm": 0.044890034943819046, "learning_rate": 2.6113345065426067e-06, "loss": 0.0012, "step": 15219 }, { "epoch": 0.8405124806715264, "grad_norm": 6.294854164123535, "learning_rate": 2.6095674138891138e-06, "loss": 1.3401, "step": 15220 }, { "epoch": 0.8405677048818202, "grad_norm": 0.01706084981560707, "learning_rate": 2.607800877605071e-06, "loss": 0.0005, "step": 15221 }, { "epoch": 0.840622929092114, "grad_norm": 0.07387901842594147, "learning_rate": 2.606034897746985e-06, "loss": 0.0018, "step": 15222 }, { "epoch": 0.8406781533024078, "grad_norm": 0.011553910560905933, "learning_rate": 2.6042694743713636e-06, "loss": 0.0002, "step": 15223 }, { "epoch": 0.8407333775127016, "grad_norm": 0.05443340167403221, "learning_rate": 2.602504607534686e-06, "loss": 0.0015, "step": 15224 }, { "epoch": 0.8407886017229954, "grad_norm": 0.24072147905826569, "learning_rate": 2.600740297293414e-06, "loss": 0.0067, "step": 15225 }, { "epoch": 0.8408438259332891, "grad_norm": 4.909544944763184, "learning_rate": 2.5989765437039883e-06, "loss": 0.7017, "step": 15226 }, { "epoch": 0.8408990501435829, "grad_norm": 2.486759901046753, "learning_rate": 2.5972133468228512e-06, "loss": 0.443, "step": 15227 }, { "epoch": 0.8409542743538767, "grad_norm": 0.44833657145500183, "learning_rate": 2.595450706706393e-06, "loss": 0.0084, "step": 15228 }, { "epoch": 0.8410094985641705, "grad_norm": 3.924090623855591, "learning_rate": 2.593688623411019e-06, "loss": 0.2188, "step": 15229 }, { "epoch": 0.8410647227744643, "grad_norm": 0.0266876183450222, "learning_rate": 2.591927096993101e-06, "loss": 0.001, "step": 15230 }, { "epoch": 0.8411199469847581, "grad_norm": 0.014265387319028378, "learning_rate": 2.590166127508995e-06, "loss": 0.0003, "step": 15231 }, { "epoch": 0.8411751711950519, "grad_norm": 1.4491304159164429, "learning_rate": 2.588405715015032e-06, "loss": 0.0632, "step": 15232 }, { "epoch": 0.8412303954053457, "grad_norm": 2.375776767730713, "learning_rate": 2.5866458595675425e-06, "loss": 0.1245, "step": 15233 }, { "epoch": 0.8412856196156395, "grad_norm": 0.436750203371048, "learning_rate": 2.584886561222828e-06, "loss": 0.0152, "step": 15234 }, { "epoch": 0.8413408438259333, "grad_norm": 0.05375204607844353, "learning_rate": 2.583127820037168e-06, "loss": 0.0015, "step": 15235 }, { "epoch": 0.8413960680362271, "grad_norm": 5.567663669586182, "learning_rate": 2.5813696360668304e-06, "loss": 0.4604, "step": 15236 }, { "epoch": 0.8414512922465208, "grad_norm": 0.16782669723033905, "learning_rate": 2.5796120093680753e-06, "loss": 0.0038, "step": 15237 }, { "epoch": 0.8415065164568146, "grad_norm": 1.35135018825531, "learning_rate": 2.5778549399971154e-06, "loss": 0.0196, "step": 15238 }, { "epoch": 0.8415617406671084, "grad_norm": 0.308264821767807, "learning_rate": 2.576098428010181e-06, "loss": 0.0066, "step": 15239 }, { "epoch": 0.8416169648774022, "grad_norm": 7.210552215576172, "learning_rate": 2.5743424734634603e-06, "loss": 0.4066, "step": 15240 }, { "epoch": 0.841672189087696, "grad_norm": 0.05147138237953186, "learning_rate": 2.5725870764131334e-06, "loss": 0.0018, "step": 15241 }, { "epoch": 0.8417274132979898, "grad_norm": 3.8842766284942627, "learning_rate": 2.5708322369153547e-06, "loss": 0.774, "step": 15242 }, { "epoch": 0.8417826375082836, "grad_norm": 0.2607383131980896, "learning_rate": 2.5690779550262757e-06, "loss": 0.0074, "step": 15243 }, { "epoch": 0.8418378617185774, "grad_norm": 4.772622585296631, "learning_rate": 2.5673242308020174e-06, "loss": 0.8647, "step": 15244 }, { "epoch": 0.8418930859288712, "grad_norm": 3.549543619155884, "learning_rate": 2.5655710642986843e-06, "loss": 0.3707, "step": 15245 }, { "epoch": 0.841948310139165, "grad_norm": 0.7372486591339111, "learning_rate": 2.5638184555723665e-06, "loss": 0.0155, "step": 15246 }, { "epoch": 0.8420035343494588, "grad_norm": 2.959329605102539, "learning_rate": 2.5620664046791355e-06, "loss": 0.1312, "step": 15247 }, { "epoch": 0.8420587585597525, "grad_norm": 2.5595977306365967, "learning_rate": 2.5603149116750394e-06, "loss": 0.1978, "step": 15248 }, { "epoch": 0.8421139827700463, "grad_norm": 0.020445622503757477, "learning_rate": 2.5585639766161217e-06, "loss": 0.0007, "step": 15249 }, { "epoch": 0.8421692069803401, "grad_norm": 6.542922496795654, "learning_rate": 2.5568135995583964e-06, "loss": 0.5773, "step": 15250 }, { "epoch": 0.842224431190634, "grad_norm": 3.822120428085327, "learning_rate": 2.5550637805578625e-06, "loss": 0.6843, "step": 15251 }, { "epoch": 0.8422796554009278, "grad_norm": 4.070441246032715, "learning_rate": 2.5533145196704977e-06, "loss": 0.2702, "step": 15252 }, { "epoch": 0.8423348796112216, "grad_norm": 0.05344438552856445, "learning_rate": 2.5515658169522793e-06, "loss": 0.0013, "step": 15253 }, { "epoch": 0.8423901038215154, "grad_norm": 0.27314236760139465, "learning_rate": 2.549817672459134e-06, "loss": 0.0078, "step": 15254 }, { "epoch": 0.8424453280318092, "grad_norm": 0.17608945071697235, "learning_rate": 2.5480700862470053e-06, "loss": 0.0051, "step": 15255 }, { "epoch": 0.842500552242103, "grad_norm": 2.991602659225464, "learning_rate": 2.546323058371798e-06, "loss": 0.1324, "step": 15256 }, { "epoch": 0.8425557764523968, "grad_norm": 3.1207027435302734, "learning_rate": 2.5445765888894023e-06, "loss": 0.5266, "step": 15257 }, { "epoch": 0.8426110006626906, "grad_norm": 0.20722447335720062, "learning_rate": 2.542830677855692e-06, "loss": 0.0047, "step": 15258 }, { "epoch": 0.8426662248729844, "grad_norm": 0.9460940361022949, "learning_rate": 2.541085325326531e-06, "loss": 0.0211, "step": 15259 }, { "epoch": 0.8427214490832781, "grad_norm": 2.7727909088134766, "learning_rate": 2.5393405313577547e-06, "loss": 0.2329, "step": 15260 }, { "epoch": 0.8427766732935719, "grad_norm": 0.10047860443592072, "learning_rate": 2.5375962960051823e-06, "loss": 0.0023, "step": 15261 }, { "epoch": 0.8428318975038657, "grad_norm": 0.08167234063148499, "learning_rate": 2.5358526193246126e-06, "loss": 0.0023, "step": 15262 }, { "epoch": 0.8428871217141595, "grad_norm": 1.2730332612991333, "learning_rate": 2.5341095013718463e-06, "loss": 0.021, "step": 15263 }, { "epoch": 0.8429423459244533, "grad_norm": 0.013504049740731716, "learning_rate": 2.5323669422026287e-06, "loss": 0.0005, "step": 15264 }, { "epoch": 0.8429975701347471, "grad_norm": 0.5916882157325745, "learning_rate": 2.530624941872728e-06, "loss": 0.0078, "step": 15265 }, { "epoch": 0.8430527943450409, "grad_norm": 0.13059860467910767, "learning_rate": 2.5288835004378664e-06, "loss": 0.0043, "step": 15266 }, { "epoch": 0.8431080185553347, "grad_norm": 2.512648820877075, "learning_rate": 2.527142617953762e-06, "loss": 0.1137, "step": 15267 }, { "epoch": 0.8431632427656285, "grad_norm": 2.532593250274658, "learning_rate": 2.5254022944761025e-06, "loss": 0.6197, "step": 15268 }, { "epoch": 0.8432184669759223, "grad_norm": 0.5334587097167969, "learning_rate": 2.52366253006058e-06, "loss": 0.103, "step": 15269 }, { "epoch": 0.8432736911862161, "grad_norm": 5.903414726257324, "learning_rate": 2.521923324762836e-06, "loss": 1.0056, "step": 15270 }, { "epoch": 0.8433289153965098, "grad_norm": 0.01535788457840681, "learning_rate": 2.5201846786385287e-06, "loss": 0.0004, "step": 15271 }, { "epoch": 0.8433841396068036, "grad_norm": 0.45091527700424194, "learning_rate": 2.5184465917432778e-06, "loss": 0.0086, "step": 15272 }, { "epoch": 0.8434393638170974, "grad_norm": 0.06681004166603088, "learning_rate": 2.5167090641326854e-06, "loss": 0.0019, "step": 15273 }, { "epoch": 0.8434945880273912, "grad_norm": 5.328179359436035, "learning_rate": 2.5149720958623403e-06, "loss": 0.4717, "step": 15274 }, { "epoch": 0.843549812237685, "grad_norm": 0.31292828917503357, "learning_rate": 2.5132356869878204e-06, "loss": 0.0107, "step": 15275 }, { "epoch": 0.8436050364479788, "grad_norm": 0.4075729250907898, "learning_rate": 2.5114998375646726e-06, "loss": 0.0088, "step": 15276 }, { "epoch": 0.8436602606582726, "grad_norm": 2.846827983856201, "learning_rate": 2.5097645476484324e-06, "loss": 0.5952, "step": 15277 }, { "epoch": 0.8437154848685664, "grad_norm": 0.31963837146759033, "learning_rate": 2.5080298172946104e-06, "loss": 0.0109, "step": 15278 }, { "epoch": 0.8437707090788602, "grad_norm": 4.210583686828613, "learning_rate": 2.506295646558723e-06, "loss": 0.2331, "step": 15279 }, { "epoch": 0.843825933289154, "grad_norm": 0.1254901885986328, "learning_rate": 2.504562035496232e-06, "loss": 0.0028, "step": 15280 }, { "epoch": 0.8438811574994478, "grad_norm": 2.1256749629974365, "learning_rate": 2.502828984162613e-06, "loss": 0.3562, "step": 15281 }, { "epoch": 0.8439363817097415, "grad_norm": 3.3868536949157715, "learning_rate": 2.5010964926133065e-06, "loss": 0.2125, "step": 15282 }, { "epoch": 0.8439916059200353, "grad_norm": 0.01856561191380024, "learning_rate": 2.4993645609037388e-06, "loss": 0.0006, "step": 15283 }, { "epoch": 0.8440468301303291, "grad_norm": 2.6699061393737793, "learning_rate": 2.4976331890893235e-06, "loss": 0.1748, "step": 15284 }, { "epoch": 0.8441020543406229, "grad_norm": 0.015218362212181091, "learning_rate": 2.4959023772254477e-06, "loss": 0.0005, "step": 15285 }, { "epoch": 0.8441572785509167, "grad_norm": 3.1014997959136963, "learning_rate": 2.494172125367489e-06, "loss": 0.3279, "step": 15286 }, { "epoch": 0.8442125027612105, "grad_norm": 0.0392797626554966, "learning_rate": 2.492442433570794e-06, "loss": 0.0009, "step": 15287 }, { "epoch": 0.8442677269715043, "grad_norm": 2.4271750450134277, "learning_rate": 2.4907133018907127e-06, "loss": 0.4509, "step": 15288 }, { "epoch": 0.8443229511817981, "grad_norm": 0.08474338799715042, "learning_rate": 2.48898473038256e-06, "loss": 0.0029, "step": 15289 }, { "epoch": 0.8443781753920919, "grad_norm": 5.62951135635376, "learning_rate": 2.487256719101636e-06, "loss": 0.6533, "step": 15290 }, { "epoch": 0.8444333996023857, "grad_norm": 4.369344711303711, "learning_rate": 2.485529268103224e-06, "loss": 0.5518, "step": 15291 }, { "epoch": 0.8444886238126795, "grad_norm": 0.03624642640352249, "learning_rate": 2.483802377442599e-06, "loss": 0.0011, "step": 15292 }, { "epoch": 0.8445438480229732, "grad_norm": 0.060176242142915726, "learning_rate": 2.482076047174995e-06, "loss": 0.0015, "step": 15293 }, { "epoch": 0.844599072233267, "grad_norm": 0.6946867108345032, "learning_rate": 2.4803502773556543e-06, "loss": 0.1185, "step": 15294 }, { "epoch": 0.8446542964435608, "grad_norm": 3.3310158252716064, "learning_rate": 2.4786250680397815e-06, "loss": 0.5077, "step": 15295 }, { "epoch": 0.8447095206538546, "grad_norm": 0.06043177843093872, "learning_rate": 2.4769004192825773e-06, "loss": 0.0024, "step": 15296 }, { "epoch": 0.8447647448641484, "grad_norm": 0.038572218269109726, "learning_rate": 2.4751763311392084e-06, "loss": 0.0011, "step": 15297 }, { "epoch": 0.8448199690744422, "grad_norm": 2.3042635917663574, "learning_rate": 2.4734528036648443e-06, "loss": 0.0878, "step": 15298 }, { "epoch": 0.844875193284736, "grad_norm": 0.03924145549535751, "learning_rate": 2.4717298369146226e-06, "loss": 0.0011, "step": 15299 }, { "epoch": 0.8449304174950298, "grad_norm": 2.7859456539154053, "learning_rate": 2.4700074309436617e-06, "loss": 0.2074, "step": 15300 }, { "epoch": 0.8449856417053236, "grad_norm": 4.749453544616699, "learning_rate": 2.4682855858070664e-06, "loss": 0.2005, "step": 15301 }, { "epoch": 0.8450408659156174, "grad_norm": 0.04563315957784653, "learning_rate": 2.4665643015599326e-06, "loss": 0.001, "step": 15302 }, { "epoch": 0.8450960901259112, "grad_norm": 0.1338929533958435, "learning_rate": 2.464843578257314e-06, "loss": 0.0035, "step": 15303 }, { "epoch": 0.8451513143362049, "grad_norm": 1.4708818197250366, "learning_rate": 2.4631234159542738e-06, "loss": 0.0805, "step": 15304 }, { "epoch": 0.8452065385464987, "grad_norm": 0.0455874465405941, "learning_rate": 2.4614038147058426e-06, "loss": 0.0011, "step": 15305 }, { "epoch": 0.8452617627567925, "grad_norm": 0.1198478415608406, "learning_rate": 2.4596847745670326e-06, "loss": 0.004, "step": 15306 }, { "epoch": 0.8453169869670863, "grad_norm": 0.21762515604496002, "learning_rate": 2.4579662955928373e-06, "loss": 0.005, "step": 15307 }, { "epoch": 0.8453722111773802, "grad_norm": 0.13282042741775513, "learning_rate": 2.4562483778382483e-06, "loss": 0.004, "step": 15308 }, { "epoch": 0.845427435387674, "grad_norm": 1.6706726551055908, "learning_rate": 2.454531021358211e-06, "loss": 0.0292, "step": 15309 }, { "epoch": 0.8454826595979678, "grad_norm": 5.236725807189941, "learning_rate": 2.4528142262076804e-06, "loss": 0.3737, "step": 15310 }, { "epoch": 0.8455378838082616, "grad_norm": 2.520857334136963, "learning_rate": 2.4510979924415757e-06, "loss": 0.1288, "step": 15311 }, { "epoch": 0.8455931080185554, "grad_norm": 1.855440378189087, "learning_rate": 2.449382320114806e-06, "loss": 0.0341, "step": 15312 }, { "epoch": 0.8456483322288492, "grad_norm": 2.1961801052093506, "learning_rate": 2.4476672092822583e-06, "loss": 0.4882, "step": 15313 }, { "epoch": 0.845703556439143, "grad_norm": 3.1026620864868164, "learning_rate": 2.445952659998807e-06, "loss": 0.1395, "step": 15314 }, { "epoch": 0.8457587806494367, "grad_norm": 4.1309733390808105, "learning_rate": 2.4442386723193055e-06, "loss": 1.0055, "step": 15315 }, { "epoch": 0.8458140048597305, "grad_norm": 0.03849879652261734, "learning_rate": 2.4425252462985882e-06, "loss": 0.0012, "step": 15316 }, { "epoch": 0.8458692290700243, "grad_norm": 0.18498940765857697, "learning_rate": 2.4408123819914685e-06, "loss": 0.0046, "step": 15317 }, { "epoch": 0.8459244532803181, "grad_norm": 0.5136169195175171, "learning_rate": 2.4391000794527586e-06, "loss": 0.0079, "step": 15318 }, { "epoch": 0.8459796774906119, "grad_norm": 3.2887704372406006, "learning_rate": 2.437388338737221e-06, "loss": 0.2859, "step": 15319 }, { "epoch": 0.8460349017009057, "grad_norm": 0.0076322052627801895, "learning_rate": 2.435677159899632e-06, "loss": 0.0002, "step": 15320 }, { "epoch": 0.8460901259111995, "grad_norm": 4.80965518951416, "learning_rate": 2.4339665429947367e-06, "loss": 1.0727, "step": 15321 }, { "epoch": 0.8461453501214933, "grad_norm": 5.043717384338379, "learning_rate": 2.432256488077258e-06, "loss": 1.2038, "step": 15322 }, { "epoch": 0.8462005743317871, "grad_norm": 0.05636300891637802, "learning_rate": 2.4305469952019036e-06, "loss": 0.0015, "step": 15323 }, { "epoch": 0.8462557985420809, "grad_norm": 3.7582569122314453, "learning_rate": 2.428838064423378e-06, "loss": 0.0417, "step": 15324 }, { "epoch": 0.8463110227523747, "grad_norm": 2.1835901737213135, "learning_rate": 2.4271296957963375e-06, "loss": 0.0273, "step": 15325 }, { "epoch": 0.8463662469626685, "grad_norm": 4.0262322425842285, "learning_rate": 2.4254218893754476e-06, "loss": 0.7527, "step": 15326 }, { "epoch": 0.8464214711729622, "grad_norm": 3.604362726211548, "learning_rate": 2.423714645215347e-06, "loss": 0.2262, "step": 15327 }, { "epoch": 0.846476695383256, "grad_norm": 0.09131971001625061, "learning_rate": 2.4220079633706515e-06, "loss": 0.0022, "step": 15328 }, { "epoch": 0.8465319195935498, "grad_norm": 0.0420503169298172, "learning_rate": 2.420301843895958e-06, "loss": 0.0011, "step": 15329 }, { "epoch": 0.8465871438038436, "grad_norm": 3.3761229515075684, "learning_rate": 2.41859628684586e-06, "loss": 0.3401, "step": 15330 }, { "epoch": 0.8466423680141374, "grad_norm": 0.06885058432817459, "learning_rate": 2.416891292274921e-06, "loss": 0.0019, "step": 15331 }, { "epoch": 0.8466975922244312, "grad_norm": 0.1548576056957245, "learning_rate": 2.4151868602376838e-06, "loss": 0.0041, "step": 15332 }, { "epoch": 0.846752816434725, "grad_norm": 0.023059701547026634, "learning_rate": 2.413482990788678e-06, "loss": 0.0008, "step": 15333 }, { "epoch": 0.8468080406450188, "grad_norm": 0.19373813271522522, "learning_rate": 2.411779683982427e-06, "loss": 0.0042, "step": 15334 }, { "epoch": 0.8468632648553126, "grad_norm": 0.22003690898418427, "learning_rate": 2.410076939873405e-06, "loss": 0.0049, "step": 15335 }, { "epoch": 0.8469184890656064, "grad_norm": 1.6419200897216797, "learning_rate": 2.4083747585161033e-06, "loss": 0.0385, "step": 15336 }, { "epoch": 0.8469737132759002, "grad_norm": 3.2825584411621094, "learning_rate": 2.4066731399649745e-06, "loss": 0.5801, "step": 15337 }, { "epoch": 0.8470289374861939, "grad_norm": 0.270096093416214, "learning_rate": 2.404972084274457e-06, "loss": 0.0054, "step": 15338 }, { "epoch": 0.8470841616964877, "grad_norm": 0.1273137480020523, "learning_rate": 2.40327159149897e-06, "loss": 0.0035, "step": 15339 }, { "epoch": 0.8471393859067815, "grad_norm": 0.04352060332894325, "learning_rate": 2.401571661692925e-06, "loss": 0.0008, "step": 15340 }, { "epoch": 0.8471946101170753, "grad_norm": 0.9783251881599426, "learning_rate": 2.399872294910701e-06, "loss": 0.0112, "step": 15341 }, { "epoch": 0.8472498343273691, "grad_norm": 0.5329504609107971, "learning_rate": 2.39817349120667e-06, "loss": 0.011, "step": 15342 }, { "epoch": 0.8473050585376629, "grad_norm": 4.439807415008545, "learning_rate": 2.3964752506351774e-06, "loss": 0.1924, "step": 15343 }, { "epoch": 0.8473602827479567, "grad_norm": 5.635930061340332, "learning_rate": 2.394777573250557e-06, "loss": 1.2355, "step": 15344 }, { "epoch": 0.8474155069582505, "grad_norm": 4.430942535400391, "learning_rate": 2.3930804591071242e-06, "loss": 0.8616, "step": 15345 }, { "epoch": 0.8474707311685443, "grad_norm": 0.0998360812664032, "learning_rate": 2.391383908259166e-06, "loss": 0.0021, "step": 15346 }, { "epoch": 0.8475259553788381, "grad_norm": 0.23287375271320343, "learning_rate": 2.389687920760975e-06, "loss": 0.0062, "step": 15347 }, { "epoch": 0.8475811795891319, "grad_norm": 0.008724878542125225, "learning_rate": 2.3879924966667913e-06, "loss": 0.0003, "step": 15348 }, { "epoch": 0.8476364037994256, "grad_norm": 4.002545356750488, "learning_rate": 2.386297636030872e-06, "loss": 0.9236, "step": 15349 }, { "epoch": 0.8476916280097194, "grad_norm": 0.5286908149719238, "learning_rate": 2.384603338907436e-06, "loss": 0.0139, "step": 15350 }, { "epoch": 0.8477468522200132, "grad_norm": 2.2938973903656006, "learning_rate": 2.3829096053506895e-06, "loss": 0.5592, "step": 15351 }, { "epoch": 0.847802076430307, "grad_norm": 0.15362878143787384, "learning_rate": 2.3812164354148125e-06, "loss": 0.0039, "step": 15352 }, { "epoch": 0.8478573006406008, "grad_norm": 0.10140011459589005, "learning_rate": 2.3795238291539844e-06, "loss": 0.0027, "step": 15353 }, { "epoch": 0.8479125248508946, "grad_norm": 3.147491693496704, "learning_rate": 2.377831786622351e-06, "loss": 0.6289, "step": 15354 }, { "epoch": 0.8479677490611884, "grad_norm": 1.8089144229888916, "learning_rate": 2.3761403078740484e-06, "loss": 0.0557, "step": 15355 }, { "epoch": 0.8480229732714822, "grad_norm": 7.9523749351501465, "learning_rate": 2.374449392963185e-06, "loss": 0.1405, "step": 15356 }, { "epoch": 0.848078197481776, "grad_norm": 4.864156246185303, "learning_rate": 2.372759041943873e-06, "loss": 1.2193, "step": 15357 }, { "epoch": 0.8481334216920698, "grad_norm": 0.1570120006799698, "learning_rate": 2.371069254870173e-06, "loss": 0.0029, "step": 15358 }, { "epoch": 0.8481886459023636, "grad_norm": 6.577442646026611, "learning_rate": 2.3693800317961604e-06, "loss": 1.5174, "step": 15359 }, { "epoch": 0.8482438701126573, "grad_norm": 3.7589163780212402, "learning_rate": 2.367691372775871e-06, "loss": 0.2626, "step": 15360 }, { "epoch": 0.8482990943229511, "grad_norm": 0.03316046670079231, "learning_rate": 2.3660032778633314e-06, "loss": 0.0009, "step": 15361 }, { "epoch": 0.8483543185332449, "grad_norm": 0.024806804955005646, "learning_rate": 2.3643157471125444e-06, "loss": 0.0007, "step": 15362 }, { "epoch": 0.8484095427435387, "grad_norm": 3.7729897499084473, "learning_rate": 2.3626287805775073e-06, "loss": 0.6885, "step": 15363 }, { "epoch": 0.8484647669538325, "grad_norm": 0.4126235544681549, "learning_rate": 2.3609423783121875e-06, "loss": 0.0117, "step": 15364 }, { "epoch": 0.8485199911641264, "grad_norm": 1.5733791589736938, "learning_rate": 2.3592565403705383e-06, "loss": 0.0681, "step": 15365 }, { "epoch": 0.8485752153744202, "grad_norm": 0.08340201526880264, "learning_rate": 2.357571266806491e-06, "loss": 0.0032, "step": 15366 }, { "epoch": 0.848630439584714, "grad_norm": 1.8621501922607422, "learning_rate": 2.3558865576739655e-06, "loss": 0.0672, "step": 15367 }, { "epoch": 0.8486856637950078, "grad_norm": 5.109185218811035, "learning_rate": 2.354202413026856e-06, "loss": 0.5204, "step": 15368 }, { "epoch": 0.8487408880053016, "grad_norm": 0.7408642172813416, "learning_rate": 2.3525188329190507e-06, "loss": 0.0154, "step": 15369 }, { "epoch": 0.8487961122155954, "grad_norm": 6.845506191253662, "learning_rate": 2.350835817404409e-06, "loss": 1.7592, "step": 15370 }, { "epoch": 0.8488513364258891, "grad_norm": 4.58931303024292, "learning_rate": 2.3491533665367715e-06, "loss": 0.3103, "step": 15371 }, { "epoch": 0.8489065606361829, "grad_norm": 4.647490501403809, "learning_rate": 2.3474714803699648e-06, "loss": 1.1292, "step": 15372 }, { "epoch": 0.8489617848464767, "grad_norm": 0.64771568775177, "learning_rate": 2.34579015895781e-06, "loss": 0.0146, "step": 15373 }, { "epoch": 0.8490170090567705, "grad_norm": 0.727354884147644, "learning_rate": 2.3441094023540777e-06, "loss": 0.0123, "step": 15374 }, { "epoch": 0.8490722332670643, "grad_norm": 3.525967836380005, "learning_rate": 2.3424292106125536e-06, "loss": 0.4437, "step": 15375 }, { "epoch": 0.8491274574773581, "grad_norm": 1.9653656482696533, "learning_rate": 2.3407495837869875e-06, "loss": 0.0922, "step": 15376 }, { "epoch": 0.8491826816876519, "grad_norm": 0.10818116366863251, "learning_rate": 2.3390705219311174e-06, "loss": 0.0034, "step": 15377 }, { "epoch": 0.8492379058979457, "grad_norm": 2.5761725902557373, "learning_rate": 2.337392025098655e-06, "loss": 0.124, "step": 15378 }, { "epoch": 0.8492931301082395, "grad_norm": 0.40477824211120605, "learning_rate": 2.3357140933433085e-06, "loss": 0.006, "step": 15379 }, { "epoch": 0.8493483543185333, "grad_norm": 0.0997927263379097, "learning_rate": 2.3340367267187558e-06, "loss": 0.0028, "step": 15380 }, { "epoch": 0.8494035785288271, "grad_norm": 5.319115161895752, "learning_rate": 2.332359925278662e-06, "loss": 1.6405, "step": 15381 }, { "epoch": 0.8494588027391208, "grad_norm": 0.46017369627952576, "learning_rate": 2.330683689076667e-06, "loss": 0.012, "step": 15382 }, { "epoch": 0.8495140269494146, "grad_norm": 2.968029260635376, "learning_rate": 2.329008018166412e-06, "loss": 0.2352, "step": 15383 }, { "epoch": 0.8495692511597084, "grad_norm": 0.037448957562446594, "learning_rate": 2.32733291260149e-06, "loss": 0.001, "step": 15384 }, { "epoch": 0.8496244753700022, "grad_norm": 2.9335501194000244, "learning_rate": 2.3256583724355018e-06, "loss": 0.435, "step": 15385 }, { "epoch": 0.849679699580296, "grad_norm": 0.21709753572940826, "learning_rate": 2.323984397722021e-06, "loss": 0.0041, "step": 15386 }, { "epoch": 0.8497349237905898, "grad_norm": 2.597229242324829, "learning_rate": 2.3223109885146e-06, "loss": 0.2534, "step": 15387 }, { "epoch": 0.8497901480008836, "grad_norm": 1.0478376150131226, "learning_rate": 2.3206381448667715e-06, "loss": 0.008, "step": 15388 }, { "epoch": 0.8498453722111774, "grad_norm": 4.406644821166992, "learning_rate": 2.3189658668320703e-06, "loss": 0.5818, "step": 15389 }, { "epoch": 0.8499005964214712, "grad_norm": 0.015138604678213596, "learning_rate": 2.317294154463976e-06, "loss": 0.0005, "step": 15390 }, { "epoch": 0.849955820631765, "grad_norm": 5.276131629943848, "learning_rate": 2.315623007815988e-06, "loss": 1.5957, "step": 15391 }, { "epoch": 0.8500110448420588, "grad_norm": 3.4984796047210693, "learning_rate": 2.3139524269415637e-06, "loss": 0.3711, "step": 15392 }, { "epoch": 0.8500662690523525, "grad_norm": 1.1217337846755981, "learning_rate": 2.312282411894151e-06, "loss": 0.1471, "step": 15393 }, { "epoch": 0.8501214932626463, "grad_norm": 0.23585529625415802, "learning_rate": 2.3106129627271767e-06, "loss": 0.0056, "step": 15394 }, { "epoch": 0.8501767174729401, "grad_norm": 5.8540167808532715, "learning_rate": 2.308944079494055e-06, "loss": 1.1834, "step": 15395 }, { "epoch": 0.8502319416832339, "grad_norm": 2.8327486515045166, "learning_rate": 2.307275762248178e-06, "loss": 0.5378, "step": 15396 }, { "epoch": 0.8502871658935277, "grad_norm": 1.6104754209518433, "learning_rate": 2.305608011042917e-06, "loss": 0.0161, "step": 15397 }, { "epoch": 0.8503423901038215, "grad_norm": 0.5497261881828308, "learning_rate": 2.3039408259316255e-06, "loss": 0.0124, "step": 15398 }, { "epoch": 0.8503976143141153, "grad_norm": 2.6935529708862305, "learning_rate": 2.302274206967654e-06, "loss": 0.1291, "step": 15399 }, { "epoch": 0.8504528385244091, "grad_norm": 0.7211751937866211, "learning_rate": 2.3006081542043067e-06, "loss": 0.0234, "step": 15400 }, { "epoch": 0.8505080627347029, "grad_norm": 0.24832499027252197, "learning_rate": 2.2989426676948944e-06, "loss": 0.0088, "step": 15401 }, { "epoch": 0.8505632869449967, "grad_norm": 2.72461199760437, "learning_rate": 2.297277747492701e-06, "loss": 0.3431, "step": 15402 }, { "epoch": 0.8506185111552905, "grad_norm": 0.03325621038675308, "learning_rate": 2.2956133936509883e-06, "loss": 0.0011, "step": 15403 }, { "epoch": 0.8506737353655843, "grad_norm": 0.8074852824211121, "learning_rate": 2.293949606223007e-06, "loss": 0.0156, "step": 15404 }, { "epoch": 0.850728959575878, "grad_norm": 0.4458621144294739, "learning_rate": 2.2922863852619836e-06, "loss": 0.0134, "step": 15405 }, { "epoch": 0.8507841837861718, "grad_norm": 4.672191619873047, "learning_rate": 2.290623730821131e-06, "loss": 0.5471, "step": 15406 }, { "epoch": 0.8508394079964656, "grad_norm": 0.055172838270664215, "learning_rate": 2.2889616429536354e-06, "loss": 0.001, "step": 15407 }, { "epoch": 0.8508946322067594, "grad_norm": 2.271245002746582, "learning_rate": 2.2873001217126834e-06, "loss": 0.522, "step": 15408 }, { "epoch": 0.8509498564170532, "grad_norm": 3.5403428077697754, "learning_rate": 2.2856391671514275e-06, "loss": 0.2247, "step": 15409 }, { "epoch": 0.851005080627347, "grad_norm": 0.023989982903003693, "learning_rate": 2.283978779323004e-06, "loss": 0.0008, "step": 15410 }, { "epoch": 0.8510603048376408, "grad_norm": 1.6042439937591553, "learning_rate": 2.2823189582805294e-06, "loss": 0.0741, "step": 15411 }, { "epoch": 0.8511155290479346, "grad_norm": 0.09532124549150467, "learning_rate": 2.2806597040771215e-06, "loss": 0.0021, "step": 15412 }, { "epoch": 0.8511707532582284, "grad_norm": 0.05533144623041153, "learning_rate": 2.279001016765845e-06, "loss": 0.0011, "step": 15413 }, { "epoch": 0.8512259774685222, "grad_norm": 0.06003974378108978, "learning_rate": 2.2773428963997813e-06, "loss": 0.0019, "step": 15414 }, { "epoch": 0.851281201678816, "grad_norm": 0.2733663320541382, "learning_rate": 2.2756853430319704e-06, "loss": 0.008, "step": 15415 }, { "epoch": 0.8513364258891097, "grad_norm": 2.6168901920318604, "learning_rate": 2.2740283567154452e-06, "loss": 0.3173, "step": 15416 }, { "epoch": 0.8513916500994035, "grad_norm": 0.012595030479133129, "learning_rate": 2.2723719375032127e-06, "loss": 0.0005, "step": 15417 }, { "epoch": 0.8514468743096973, "grad_norm": 3.9574337005615234, "learning_rate": 2.270716085448272e-06, "loss": 1.0224, "step": 15418 }, { "epoch": 0.8515020985199911, "grad_norm": 7.143768310546875, "learning_rate": 2.2690608006035996e-06, "loss": 0.3729, "step": 15419 }, { "epoch": 0.851557322730285, "grad_norm": 2.5388381481170654, "learning_rate": 2.26740608302215e-06, "loss": 0.2187, "step": 15420 }, { "epoch": 0.8516125469405788, "grad_norm": 0.05488951876759529, "learning_rate": 2.2657519327568566e-06, "loss": 0.0017, "step": 15421 }, { "epoch": 0.8516677711508726, "grad_norm": 3.245814085006714, "learning_rate": 2.264098349860655e-06, "loss": 0.7789, "step": 15422 }, { "epoch": 0.8517229953611664, "grad_norm": 0.03269685432314873, "learning_rate": 2.2624453343864296e-06, "loss": 0.0011, "step": 15423 }, { "epoch": 0.8517782195714602, "grad_norm": 0.13493606448173523, "learning_rate": 2.26079288638708e-06, "loss": 0.0036, "step": 15424 }, { "epoch": 0.851833443781754, "grad_norm": 0.08686335384845734, "learning_rate": 2.259141005915466e-06, "loss": 0.0033, "step": 15425 }, { "epoch": 0.8518886679920478, "grad_norm": 0.08500191569328308, "learning_rate": 2.2574896930244396e-06, "loss": 0.0018, "step": 15426 }, { "epoch": 0.8519438922023415, "grad_norm": 0.07765905559062958, "learning_rate": 2.255838947766822e-06, "loss": 0.002, "step": 15427 }, { "epoch": 0.8519991164126353, "grad_norm": 1.6467738151550293, "learning_rate": 2.2541887701954423e-06, "loss": 0.3735, "step": 15428 }, { "epoch": 0.8520543406229291, "grad_norm": 1.2296862602233887, "learning_rate": 2.252539160363074e-06, "loss": 0.043, "step": 15429 }, { "epoch": 0.8521095648332229, "grad_norm": 0.06498567014932632, "learning_rate": 2.2508901183225064e-06, "loss": 0.0026, "step": 15430 }, { "epoch": 0.8521647890435167, "grad_norm": 2.455008029937744, "learning_rate": 2.249241644126494e-06, "loss": 0.1094, "step": 15431 }, { "epoch": 0.8522200132538105, "grad_norm": 1.0890936851501465, "learning_rate": 2.2475937378277756e-06, "loss": 0.0223, "step": 15432 }, { "epoch": 0.8522752374641043, "grad_norm": 3.0560734272003174, "learning_rate": 2.2459463994790685e-06, "loss": 0.0943, "step": 15433 }, { "epoch": 0.8523304616743981, "grad_norm": 2.615593194961548, "learning_rate": 2.244299629133084e-06, "loss": 0.0739, "step": 15434 }, { "epoch": 0.8523856858846919, "grad_norm": 0.46326085925102234, "learning_rate": 2.2426534268425026e-06, "loss": 0.0134, "step": 15435 }, { "epoch": 0.8524409100949857, "grad_norm": 0.03831696882843971, "learning_rate": 2.2410077926599904e-06, "loss": 0.0014, "step": 15436 }, { "epoch": 0.8524961343052795, "grad_norm": 0.08874902874231339, "learning_rate": 2.2393627266381946e-06, "loss": 0.0016, "step": 15437 }, { "epoch": 0.8525513585155732, "grad_norm": 0.7044294476509094, "learning_rate": 2.237718228829753e-06, "loss": 0.1234, "step": 15438 }, { "epoch": 0.852606582725867, "grad_norm": 1.5196433067321777, "learning_rate": 2.2360742992872654e-06, "loss": 0.1421, "step": 15439 }, { "epoch": 0.8526618069361608, "grad_norm": 0.03410212695598602, "learning_rate": 2.234430938063337e-06, "loss": 0.0008, "step": 15440 }, { "epoch": 0.8527170311464546, "grad_norm": 3.7266886234283447, "learning_rate": 2.232788145210538e-06, "loss": 0.6327, "step": 15441 }, { "epoch": 0.8527722553567484, "grad_norm": 0.4032573401927948, "learning_rate": 2.231145920781428e-06, "loss": 0.0119, "step": 15442 }, { "epoch": 0.8528274795670422, "grad_norm": 0.7408192157745361, "learning_rate": 2.229504264828539e-06, "loss": 0.0328, "step": 15443 }, { "epoch": 0.852882703777336, "grad_norm": 5.298764705657959, "learning_rate": 2.22786317740441e-06, "loss": 0.486, "step": 15444 }, { "epoch": 0.8529379279876298, "grad_norm": 1.990442156791687, "learning_rate": 2.2262226585615255e-06, "loss": 0.0967, "step": 15445 }, { "epoch": 0.8529931521979236, "grad_norm": 0.651020348072052, "learning_rate": 2.2245827083523807e-06, "loss": 0.0217, "step": 15446 }, { "epoch": 0.8530483764082174, "grad_norm": 0.029621930792927742, "learning_rate": 2.2229433268294386e-06, "loss": 0.001, "step": 15447 }, { "epoch": 0.8531036006185112, "grad_norm": 2.875157594680786, "learning_rate": 2.2213045140451484e-06, "loss": 0.5442, "step": 15448 }, { "epoch": 0.8531588248288049, "grad_norm": 3.3864541053771973, "learning_rate": 2.2196662700519387e-06, "loss": 0.3839, "step": 15449 }, { "epoch": 0.8532140490390987, "grad_norm": 2.5228114128112793, "learning_rate": 2.2180285949022264e-06, "loss": 0.6022, "step": 15450 }, { "epoch": 0.8532692732493925, "grad_norm": 2.499802350997925, "learning_rate": 2.2163914886484017e-06, "loss": 0.2575, "step": 15451 }, { "epoch": 0.8533244974596863, "grad_norm": 0.5994765758514404, "learning_rate": 2.2147549513428414e-06, "loss": 0.0152, "step": 15452 }, { "epoch": 0.8533797216699801, "grad_norm": 3.7715916633605957, "learning_rate": 2.2131189830378983e-06, "loss": 0.3026, "step": 15453 }, { "epoch": 0.8534349458802739, "grad_norm": 0.07169506698846817, "learning_rate": 2.2114835837859227e-06, "loss": 0.002, "step": 15454 }, { "epoch": 0.8534901700905677, "grad_norm": 5.717674732208252, "learning_rate": 2.2098487536392233e-06, "loss": 1.2863, "step": 15455 }, { "epoch": 0.8535453943008615, "grad_norm": 0.12517084181308746, "learning_rate": 2.2082144926501113e-06, "loss": 0.002, "step": 15456 }, { "epoch": 0.8536006185111553, "grad_norm": 0.01153706293553114, "learning_rate": 2.2065808008708676e-06, "loss": 0.0004, "step": 15457 }, { "epoch": 0.8536558427214491, "grad_norm": 5.327590465545654, "learning_rate": 2.2049476783537614e-06, "loss": 0.6737, "step": 15458 }, { "epoch": 0.8537110669317429, "grad_norm": 0.01481775101274252, "learning_rate": 2.2033151251510356e-06, "loss": 0.0005, "step": 15459 }, { "epoch": 0.8537662911420366, "grad_norm": 1.3383294343948364, "learning_rate": 2.2016831413149274e-06, "loss": 0.1112, "step": 15460 }, { "epoch": 0.8538215153523304, "grad_norm": 6.4759626388549805, "learning_rate": 2.200051726897645e-06, "loss": 1.3904, "step": 15461 }, { "epoch": 0.8538767395626242, "grad_norm": 3.106250762939453, "learning_rate": 2.1984208819513817e-06, "loss": 0.8661, "step": 15462 }, { "epoch": 0.853931963772918, "grad_norm": 2.209151268005371, "learning_rate": 2.196790606528314e-06, "loss": 0.1377, "step": 15463 }, { "epoch": 0.8539871879832118, "grad_norm": 0.1009831354022026, "learning_rate": 2.1951609006805975e-06, "loss": 0.0025, "step": 15464 }, { "epoch": 0.8540424121935056, "grad_norm": 2.949643611907959, "learning_rate": 2.1935317644603703e-06, "loss": 0.2637, "step": 15465 }, { "epoch": 0.8540976364037994, "grad_norm": 0.22459305822849274, "learning_rate": 2.1919031979197535e-06, "loss": 0.0028, "step": 15466 }, { "epoch": 0.8541528606140932, "grad_norm": 4.006080150604248, "learning_rate": 2.1902752011108586e-06, "loss": 0.879, "step": 15467 }, { "epoch": 0.854208084824387, "grad_norm": 0.007953914813697338, "learning_rate": 2.1886477740857527e-06, "loss": 0.0002, "step": 15468 }, { "epoch": 0.8542633090346808, "grad_norm": 1.5730397701263428, "learning_rate": 2.1870209168965162e-06, "loss": 0.0439, "step": 15469 }, { "epoch": 0.8543185332449746, "grad_norm": 2.2945797443389893, "learning_rate": 2.18539462959519e-06, "loss": 0.0587, "step": 15470 }, { "epoch": 0.8543737574552683, "grad_norm": 0.07532960921525955, "learning_rate": 2.183768912233808e-06, "loss": 0.0021, "step": 15471 }, { "epoch": 0.8544289816655621, "grad_norm": 3.735987424850464, "learning_rate": 2.1821437648643727e-06, "loss": 0.3699, "step": 15472 }, { "epoch": 0.8544842058758559, "grad_norm": 0.08075276762247086, "learning_rate": 2.18051918753889e-06, "loss": 0.0026, "step": 15473 }, { "epoch": 0.8545394300861497, "grad_norm": 5.410016059875488, "learning_rate": 2.178895180309326e-06, "loss": 0.1733, "step": 15474 }, { "epoch": 0.8545946542964435, "grad_norm": 2.2643144130706787, "learning_rate": 2.1772717432276426e-06, "loss": 0.1275, "step": 15475 }, { "epoch": 0.8546498785067373, "grad_norm": 0.35753726959228516, "learning_rate": 2.1756488763457684e-06, "loss": 0.0141, "step": 15476 }, { "epoch": 0.8547051027170312, "grad_norm": 0.008593348786234856, "learning_rate": 2.17402657971564e-06, "loss": 0.0002, "step": 15477 }, { "epoch": 0.854760326927325, "grad_norm": 1.439414143562317, "learning_rate": 2.1724048533891408e-06, "loss": 0.0744, "step": 15478 }, { "epoch": 0.8548155511376188, "grad_norm": 0.029190795496106148, "learning_rate": 2.1707836974181663e-06, "loss": 0.0012, "step": 15479 }, { "epoch": 0.8548707753479126, "grad_norm": 0.3273520767688751, "learning_rate": 2.1691631118545796e-06, "loss": 0.008, "step": 15480 }, { "epoch": 0.8549259995582064, "grad_norm": 0.4174741208553314, "learning_rate": 2.1675430967502286e-06, "loss": 0.0094, "step": 15481 }, { "epoch": 0.8549812237685002, "grad_norm": 4.240013599395752, "learning_rate": 2.1659236521569337e-06, "loss": 0.2793, "step": 15482 }, { "epoch": 0.8550364479787939, "grad_norm": 0.10590841621160507, "learning_rate": 2.1643047781265204e-06, "loss": 0.0025, "step": 15483 }, { "epoch": 0.8550916721890877, "grad_norm": 1.7606823444366455, "learning_rate": 2.162686474710769e-06, "loss": 0.0881, "step": 15484 }, { "epoch": 0.8551468963993815, "grad_norm": 0.1348351538181305, "learning_rate": 2.1610687419614607e-06, "loss": 0.0034, "step": 15485 }, { "epoch": 0.8552021206096753, "grad_norm": 2.1551051139831543, "learning_rate": 2.159451579930347e-06, "loss": 0.1587, "step": 15486 }, { "epoch": 0.8552573448199691, "grad_norm": 0.31098589301109314, "learning_rate": 2.1578349886691698e-06, "loss": 0.0053, "step": 15487 }, { "epoch": 0.8553125690302629, "grad_norm": 0.17063243687152863, "learning_rate": 2.1562189682296395e-06, "loss": 0.004, "step": 15488 }, { "epoch": 0.8553677932405567, "grad_norm": 0.18422691524028778, "learning_rate": 2.1546035186634673e-06, "loss": 0.0042, "step": 15489 }, { "epoch": 0.8554230174508505, "grad_norm": 3.2321784496307373, "learning_rate": 2.152988640022331e-06, "loss": 0.3012, "step": 15490 }, { "epoch": 0.8554782416611443, "grad_norm": 0.0770014151930809, "learning_rate": 2.1513743323578984e-06, "loss": 0.0028, "step": 15491 }, { "epoch": 0.8555334658714381, "grad_norm": 0.041952431201934814, "learning_rate": 2.1497605957218106e-06, "loss": 0.001, "step": 15492 }, { "epoch": 0.8555886900817319, "grad_norm": 0.31908223032951355, "learning_rate": 2.1481474301657035e-06, "loss": 0.0034, "step": 15493 }, { "epoch": 0.8556439142920256, "grad_norm": 0.052527736872434616, "learning_rate": 2.1465348357411762e-06, "loss": 0.0012, "step": 15494 }, { "epoch": 0.8556991385023194, "grad_norm": 0.20726647973060608, "learning_rate": 2.14492281249983e-06, "loss": 0.0037, "step": 15495 }, { "epoch": 0.8557543627126132, "grad_norm": 3.611433506011963, "learning_rate": 2.1433113604932345e-06, "loss": 0.2734, "step": 15496 }, { "epoch": 0.855809586922907, "grad_norm": 0.03351301699876785, "learning_rate": 2.1417004797729433e-06, "loss": 0.0008, "step": 15497 }, { "epoch": 0.8558648111332008, "grad_norm": 0.037682946771383286, "learning_rate": 2.1400901703904896e-06, "loss": 0.0012, "step": 15498 }, { "epoch": 0.8559200353434946, "grad_norm": 0.0681912750005722, "learning_rate": 2.138480432397401e-06, "loss": 0.0014, "step": 15499 }, { "epoch": 0.8559752595537884, "grad_norm": 0.28314441442489624, "learning_rate": 2.136871265845173e-06, "loss": 0.0071, "step": 15500 }, { "epoch": 0.8560304837640822, "grad_norm": 3.486407995223999, "learning_rate": 2.1352626707852877e-06, "loss": 0.3962, "step": 15501 }, { "epoch": 0.856085707974376, "grad_norm": 0.5754814147949219, "learning_rate": 2.133654647269203e-06, "loss": 0.0166, "step": 15502 }, { "epoch": 0.8561409321846698, "grad_norm": 6.942110538482666, "learning_rate": 2.132047195348379e-06, "loss": 1.7243, "step": 15503 }, { "epoch": 0.8561961563949636, "grad_norm": 2.8576698303222656, "learning_rate": 2.1304403150742227e-06, "loss": 0.2613, "step": 15504 }, { "epoch": 0.8562513806052573, "grad_norm": 0.24988213181495667, "learning_rate": 2.1288340064981593e-06, "loss": 0.0079, "step": 15505 }, { "epoch": 0.8563066048155511, "grad_norm": 1.0253098011016846, "learning_rate": 2.1272282696715727e-06, "loss": 0.0347, "step": 15506 }, { "epoch": 0.8563618290258449, "grad_norm": 0.11982877552509308, "learning_rate": 2.125623104645833e-06, "loss": 0.0036, "step": 15507 }, { "epoch": 0.8564170532361387, "grad_norm": 0.030123667791485786, "learning_rate": 2.1240185114722944e-06, "loss": 0.0007, "step": 15508 }, { "epoch": 0.8564722774464325, "grad_norm": 4.590925216674805, "learning_rate": 2.1224144902023024e-06, "loss": 0.5903, "step": 15509 }, { "epoch": 0.8565275016567263, "grad_norm": 4.747382640838623, "learning_rate": 2.1208110408871585e-06, "loss": 1.1963, "step": 15510 }, { "epoch": 0.8565827258670201, "grad_norm": 3.5293326377868652, "learning_rate": 2.1192081635781724e-06, "loss": 0.7303, "step": 15511 }, { "epoch": 0.8566379500773139, "grad_norm": 1.8976927995681763, "learning_rate": 2.117605858326621e-06, "loss": 0.0846, "step": 15512 }, { "epoch": 0.8566931742876077, "grad_norm": 5.135984897613525, "learning_rate": 2.116004125183766e-06, "loss": 0.5369, "step": 15513 }, { "epoch": 0.8567483984979015, "grad_norm": 3.5806620121002197, "learning_rate": 2.11440296420085e-06, "loss": 0.7203, "step": 15514 }, { "epoch": 0.8568036227081953, "grad_norm": 5.830954074859619, "learning_rate": 2.112802375429106e-06, "loss": 0.244, "step": 15515 }, { "epoch": 0.856858846918489, "grad_norm": 0.035060398280620575, "learning_rate": 2.111202358919735e-06, "loss": 0.0013, "step": 15516 }, { "epoch": 0.8569140711287828, "grad_norm": 0.017212465405464172, "learning_rate": 2.1096029147239293e-06, "loss": 0.0005, "step": 15517 }, { "epoch": 0.8569692953390766, "grad_norm": 1.6080833673477173, "learning_rate": 2.108004042892853e-06, "loss": 0.0499, "step": 15518 }, { "epoch": 0.8570245195493704, "grad_norm": 0.14603598415851593, "learning_rate": 2.106405743477673e-06, "loss": 0.0026, "step": 15519 }, { "epoch": 0.8570797437596642, "grad_norm": 0.37970367074012756, "learning_rate": 2.104808016529505e-06, "loss": 0.0095, "step": 15520 }, { "epoch": 0.857134967969958, "grad_norm": 0.1760961264371872, "learning_rate": 2.1032108620994762e-06, "loss": 0.0054, "step": 15521 }, { "epoch": 0.8571901921802518, "grad_norm": 0.08496812731027603, "learning_rate": 2.101614280238684e-06, "loss": 0.0027, "step": 15522 }, { "epoch": 0.8572454163905456, "grad_norm": 1.7550373077392578, "learning_rate": 2.1000182709982053e-06, "loss": 0.092, "step": 15523 }, { "epoch": 0.8573006406008394, "grad_norm": 1.1255481243133545, "learning_rate": 2.0984228344291015e-06, "loss": 0.0148, "step": 15524 }, { "epoch": 0.8573558648111332, "grad_norm": 0.05346788093447685, "learning_rate": 2.0968279705824135e-06, "loss": 0.0012, "step": 15525 }, { "epoch": 0.857411089021427, "grad_norm": 0.051720667630434036, "learning_rate": 2.0952336795091678e-06, "loss": 0.0011, "step": 15526 }, { "epoch": 0.8574663132317207, "grad_norm": 0.25451526045799255, "learning_rate": 2.093639961260363e-06, "loss": 0.0057, "step": 15527 }, { "epoch": 0.8575215374420145, "grad_norm": 0.26720699667930603, "learning_rate": 2.092046815886999e-06, "loss": 0.004, "step": 15528 }, { "epoch": 0.8575767616523083, "grad_norm": 4.0437211990356445, "learning_rate": 2.090454243440039e-06, "loss": 0.4209, "step": 15529 }, { "epoch": 0.8576319858626021, "grad_norm": 8.511957168579102, "learning_rate": 2.0888622439704333e-06, "loss": 0.601, "step": 15530 }, { "epoch": 0.857687210072896, "grad_norm": 1.7322124242782593, "learning_rate": 2.0872708175291125e-06, "loss": 0.0233, "step": 15531 }, { "epoch": 0.8577424342831897, "grad_norm": 2.627370595932007, "learning_rate": 2.085679964167e-06, "loss": 0.187, "step": 15532 }, { "epoch": 0.8577976584934836, "grad_norm": 0.1261969804763794, "learning_rate": 2.084089683934978e-06, "loss": 0.0037, "step": 15533 }, { "epoch": 0.8578528827037774, "grad_norm": 0.08209967613220215, "learning_rate": 2.082499976883936e-06, "loss": 0.0019, "step": 15534 }, { "epoch": 0.8579081069140712, "grad_norm": 3.559394598007202, "learning_rate": 2.080910843064727e-06, "loss": 0.1421, "step": 15535 }, { "epoch": 0.857963331124365, "grad_norm": 0.7509279251098633, "learning_rate": 2.0793222825281956e-06, "loss": 0.0209, "step": 15536 }, { "epoch": 0.8580185553346588, "grad_norm": 0.5042617917060852, "learning_rate": 2.0777342953251556e-06, "loss": 0.0106, "step": 15537 }, { "epoch": 0.8580737795449525, "grad_norm": 1.802289605140686, "learning_rate": 2.0761468815064245e-06, "loss": 0.0581, "step": 15538 }, { "epoch": 0.8581290037552463, "grad_norm": 0.3006610870361328, "learning_rate": 2.0745600411227793e-06, "loss": 0.0059, "step": 15539 }, { "epoch": 0.8581842279655401, "grad_norm": 1.175750732421875, "learning_rate": 2.0729737742249913e-06, "loss": 0.0455, "step": 15540 }, { "epoch": 0.8582394521758339, "grad_norm": 7.5183868408203125, "learning_rate": 2.071388080863805e-06, "loss": 1.9934, "step": 15541 }, { "epoch": 0.8582946763861277, "grad_norm": 3.5758042335510254, "learning_rate": 2.069802961089962e-06, "loss": 0.4739, "step": 15542 }, { "epoch": 0.8583499005964215, "grad_norm": 1.15469491481781, "learning_rate": 2.0682184149541572e-06, "loss": 0.0253, "step": 15543 }, { "epoch": 0.8584051248067153, "grad_norm": 2.5745060443878174, "learning_rate": 2.0666344425071005e-06, "loss": 0.0557, "step": 15544 }, { "epoch": 0.8584603490170091, "grad_norm": 1.9718950986862183, "learning_rate": 2.0650510437994618e-06, "loss": 0.4437, "step": 15545 }, { "epoch": 0.8585155732273029, "grad_norm": 0.01356276124715805, "learning_rate": 2.063468218881899e-06, "loss": 0.0004, "step": 15546 }, { "epoch": 0.8585707974375967, "grad_norm": 3.8584771156311035, "learning_rate": 2.061885967805046e-06, "loss": 0.7217, "step": 15547 }, { "epoch": 0.8586260216478905, "grad_norm": 0.016125965863466263, "learning_rate": 2.060304290619537e-06, "loss": 0.0004, "step": 15548 }, { "epoch": 0.8586812458581843, "grad_norm": 0.09035490453243256, "learning_rate": 2.0587231873759596e-06, "loss": 0.0026, "step": 15549 }, { "epoch": 0.858736470068478, "grad_norm": 4.685970783233643, "learning_rate": 2.0571426581249066e-06, "loss": 0.9788, "step": 15550 }, { "epoch": 0.8587916942787718, "grad_norm": 5.1117048263549805, "learning_rate": 2.05556270291694e-06, "loss": 0.9041, "step": 15551 }, { "epoch": 0.8588469184890656, "grad_norm": 3.132939577102661, "learning_rate": 2.0539833218026083e-06, "loss": 0.1369, "step": 15552 }, { "epoch": 0.8589021426993594, "grad_norm": 0.27742210030555725, "learning_rate": 2.052404514832438e-06, "loss": 0.005, "step": 15553 }, { "epoch": 0.8589573669096532, "grad_norm": 0.05184604600071907, "learning_rate": 2.0508262820569437e-06, "loss": 0.0012, "step": 15554 }, { "epoch": 0.859012591119947, "grad_norm": 6.730493545532227, "learning_rate": 2.049248623526616e-06, "loss": 1.5782, "step": 15555 }, { "epoch": 0.8590678153302408, "grad_norm": 2.4198455810546875, "learning_rate": 2.0476715392919287e-06, "loss": 0.0397, "step": 15556 }, { "epoch": 0.8591230395405346, "grad_norm": 6.196959495544434, "learning_rate": 2.0460950294033345e-06, "loss": 1.208, "step": 15557 }, { "epoch": 0.8591782637508284, "grad_norm": 4.322030067443848, "learning_rate": 2.0445190939112793e-06, "loss": 0.7926, "step": 15558 }, { "epoch": 0.8592334879611222, "grad_norm": 2.032094955444336, "learning_rate": 2.042943732866165e-06, "loss": 0.076, "step": 15559 }, { "epoch": 0.859288712171416, "grad_norm": 1.5918217897415161, "learning_rate": 2.0413689463184093e-06, "loss": 0.1587, "step": 15560 }, { "epoch": 0.8593439363817097, "grad_norm": 0.3621250092983246, "learning_rate": 2.0397947343183854e-06, "loss": 0.0105, "step": 15561 }, { "epoch": 0.8593991605920035, "grad_norm": 0.004994586575776339, "learning_rate": 2.0382210969164597e-06, "loss": 0.0001, "step": 15562 }, { "epoch": 0.8594543848022973, "grad_norm": 2.9953200817108154, "learning_rate": 2.0366480341629713e-06, "loss": 0.6094, "step": 15563 }, { "epoch": 0.8595096090125911, "grad_norm": 4.890127658843994, "learning_rate": 2.0350755461082604e-06, "loss": 0.8364, "step": 15564 }, { "epoch": 0.8595648332228849, "grad_norm": 0.06478001177310944, "learning_rate": 2.033503632802618e-06, "loss": 0.0013, "step": 15565 }, { "epoch": 0.8596200574331787, "grad_norm": 2.2061550617218018, "learning_rate": 2.031932294296346e-06, "loss": 0.2834, "step": 15566 }, { "epoch": 0.8596752816434725, "grad_norm": 0.0204987321048975, "learning_rate": 2.030361530639715e-06, "loss": 0.0008, "step": 15567 }, { "epoch": 0.8597305058537663, "grad_norm": 0.2831436097621918, "learning_rate": 2.028791341882974e-06, "loss": 0.0064, "step": 15568 }, { "epoch": 0.8597857300640601, "grad_norm": 3.610762596130371, "learning_rate": 2.027221728076356e-06, "loss": 0.257, "step": 15569 }, { "epoch": 0.8598409542743539, "grad_norm": 0.0723259225487709, "learning_rate": 2.0256526892700855e-06, "loss": 0.0021, "step": 15570 }, { "epoch": 0.8598961784846477, "grad_norm": 0.03677219897508621, "learning_rate": 2.0240842255143558e-06, "loss": 0.001, "step": 15571 }, { "epoch": 0.8599514026949414, "grad_norm": 0.08977164328098297, "learning_rate": 2.022516336859346e-06, "loss": 0.0027, "step": 15572 }, { "epoch": 0.8600066269052352, "grad_norm": 2.2181267738342285, "learning_rate": 2.0209490233552165e-06, "loss": 0.2056, "step": 15573 }, { "epoch": 0.860061851115529, "grad_norm": 0.14704836905002594, "learning_rate": 2.0193822850521185e-06, "loss": 0.0044, "step": 15574 }, { "epoch": 0.8601170753258228, "grad_norm": 3.1459007263183594, "learning_rate": 2.0178161220001624e-06, "loss": 0.2576, "step": 15575 }, { "epoch": 0.8601722995361166, "grad_norm": 2.2469379901885986, "learning_rate": 2.0162505342494643e-06, "loss": 0.2063, "step": 15576 }, { "epoch": 0.8602275237464104, "grad_norm": 0.3938620090484619, "learning_rate": 2.0146855218501105e-06, "loss": 0.0117, "step": 15577 }, { "epoch": 0.8602827479567042, "grad_norm": 3.80446720123291, "learning_rate": 2.0131210848521677e-06, "loss": 0.6053, "step": 15578 }, { "epoch": 0.860337972166998, "grad_norm": 4.57697057723999, "learning_rate": 2.0115572233056847e-06, "loss": 0.9153, "step": 15579 }, { "epoch": 0.8603931963772918, "grad_norm": 0.438162237405777, "learning_rate": 2.009993937260699e-06, "loss": 0.0098, "step": 15580 }, { "epoch": 0.8604484205875856, "grad_norm": 2.2687184810638428, "learning_rate": 2.0084312267672248e-06, "loss": 0.0419, "step": 15581 }, { "epoch": 0.8605036447978794, "grad_norm": 0.007458497304469347, "learning_rate": 2.0068690918752544e-06, "loss": 0.0002, "step": 15582 }, { "epoch": 0.8605588690081731, "grad_norm": 0.23449592292308807, "learning_rate": 2.005307532634766e-06, "loss": 0.0059, "step": 15583 }, { "epoch": 0.8606140932184669, "grad_norm": 0.04542301595211029, "learning_rate": 2.0037465490957174e-06, "loss": 0.0014, "step": 15584 }, { "epoch": 0.8606693174287607, "grad_norm": 3.247022867202759, "learning_rate": 2.002186141308051e-06, "loss": 0.4129, "step": 15585 }, { "epoch": 0.8607245416390545, "grad_norm": 0.031076254323124886, "learning_rate": 2.0006263093216828e-06, "loss": 0.001, "step": 15586 }, { "epoch": 0.8607797658493483, "grad_norm": 0.1389993578195572, "learning_rate": 1.9990670531865296e-06, "loss": 0.003, "step": 15587 }, { "epoch": 0.8608349900596421, "grad_norm": 1.8596750497817993, "learning_rate": 1.997508372952459e-06, "loss": 0.1723, "step": 15588 }, { "epoch": 0.860890214269936, "grad_norm": 2.131033182144165, "learning_rate": 1.995950268669351e-06, "loss": 0.231, "step": 15589 }, { "epoch": 0.8609454384802298, "grad_norm": 6.17417573928833, "learning_rate": 1.99439274038705e-06, "loss": 0.7644, "step": 15590 }, { "epoch": 0.8610006626905236, "grad_norm": 5.0554423332214355, "learning_rate": 1.9928357881553827e-06, "loss": 0.6839, "step": 15591 }, { "epoch": 0.8610558869008174, "grad_norm": 0.7391842603683472, "learning_rate": 1.991279412024161e-06, "loss": 0.0148, "step": 15592 }, { "epoch": 0.8611111111111112, "grad_norm": 1.8302087783813477, "learning_rate": 1.9897236120431816e-06, "loss": 0.1451, "step": 15593 }, { "epoch": 0.8611663353214049, "grad_norm": 4.620147705078125, "learning_rate": 1.9881683882622172e-06, "loss": 0.9157, "step": 15594 }, { "epoch": 0.8612215595316987, "grad_norm": 1.314553141593933, "learning_rate": 1.9866137407310225e-06, "loss": 0.0232, "step": 15595 }, { "epoch": 0.8612767837419925, "grad_norm": 1.6278589963912964, "learning_rate": 1.985059669499334e-06, "loss": 0.0365, "step": 15596 }, { "epoch": 0.8613320079522863, "grad_norm": 6.565035820007324, "learning_rate": 1.9835061746168804e-06, "loss": 1.2444, "step": 15597 }, { "epoch": 0.8613872321625801, "grad_norm": 0.05653058737516403, "learning_rate": 1.9819532561333464e-06, "loss": 0.0011, "step": 15598 }, { "epoch": 0.8614424563728739, "grad_norm": 0.1683797687292099, "learning_rate": 1.980400914098428e-06, "loss": 0.0041, "step": 15599 }, { "epoch": 0.8614976805831677, "grad_norm": 0.019480103626847267, "learning_rate": 1.978849148561783e-06, "loss": 0.0006, "step": 15600 }, { "epoch": 0.8615529047934615, "grad_norm": 4.201094150543213, "learning_rate": 1.9772979595730568e-06, "loss": 0.5149, "step": 15601 }, { "epoch": 0.8616081290037553, "grad_norm": 4.511704921722412, "learning_rate": 1.9757473471818757e-06, "loss": 0.1822, "step": 15602 }, { "epoch": 0.8616633532140491, "grad_norm": 0.16162613034248352, "learning_rate": 1.974197311437851e-06, "loss": 0.0051, "step": 15603 }, { "epoch": 0.8617185774243429, "grad_norm": 0.1938680112361908, "learning_rate": 1.9726478523905723e-06, "loss": 0.0046, "step": 15604 }, { "epoch": 0.8617738016346366, "grad_norm": 2.4947288036346436, "learning_rate": 1.971098970089611e-06, "loss": 0.1368, "step": 15605 }, { "epoch": 0.8618290258449304, "grad_norm": 2.0252928733825684, "learning_rate": 1.969550664584521e-06, "loss": 0.4146, "step": 15606 }, { "epoch": 0.8618842500552242, "grad_norm": 0.06483403593301773, "learning_rate": 1.968002935924833e-06, "loss": 0.0014, "step": 15607 }, { "epoch": 0.861939474265518, "grad_norm": 0.10987160354852676, "learning_rate": 1.966455784160064e-06, "loss": 0.0031, "step": 15608 }, { "epoch": 0.8619946984758118, "grad_norm": 3.0002224445343018, "learning_rate": 1.964909209339716e-06, "loss": 0.1258, "step": 15609 }, { "epoch": 0.8620499226861056, "grad_norm": 0.08588401973247528, "learning_rate": 1.9633632115132674e-06, "loss": 0.002, "step": 15610 }, { "epoch": 0.8621051468963994, "grad_norm": 0.10304205119609833, "learning_rate": 1.9618177907301762e-06, "loss": 0.0015, "step": 15611 }, { "epoch": 0.8621603711066932, "grad_norm": 1.98405122756958, "learning_rate": 1.960272947039883e-06, "loss": 0.0904, "step": 15612 }, { "epoch": 0.862215595316987, "grad_norm": 1.6132084131240845, "learning_rate": 1.9587286804918236e-06, "loss": 0.0799, "step": 15613 }, { "epoch": 0.8622708195272808, "grad_norm": 1.2932523488998413, "learning_rate": 1.957184991135386e-06, "loss": 0.0546, "step": 15614 }, { "epoch": 0.8623260437375746, "grad_norm": 2.1041464805603027, "learning_rate": 1.9556418790199717e-06, "loss": 0.0937, "step": 15615 }, { "epoch": 0.8623812679478683, "grad_norm": 0.45337536931037903, "learning_rate": 1.954099344194942e-06, "loss": 0.0057, "step": 15616 }, { "epoch": 0.8624364921581621, "grad_norm": 0.0697173997759819, "learning_rate": 1.952557386709648e-06, "loss": 0.0015, "step": 15617 }, { "epoch": 0.8624917163684559, "grad_norm": 0.3313640058040619, "learning_rate": 1.95101600661342e-06, "loss": 0.0074, "step": 15618 }, { "epoch": 0.8625469405787497, "grad_norm": 0.02869342640042305, "learning_rate": 1.9494752039555773e-06, "loss": 0.001, "step": 15619 }, { "epoch": 0.8626021647890435, "grad_norm": 0.4164469838142395, "learning_rate": 1.9479349787854084e-06, "loss": 0.0088, "step": 15620 }, { "epoch": 0.8626573889993373, "grad_norm": 2.911789655685425, "learning_rate": 1.9463953311521934e-06, "loss": 0.2139, "step": 15621 }, { "epoch": 0.8627126132096311, "grad_norm": 4.998863697052002, "learning_rate": 1.9448562611051835e-06, "loss": 1.9637, "step": 15622 }, { "epoch": 0.8627678374199249, "grad_norm": 4.717667579650879, "learning_rate": 1.9433177686936312e-06, "loss": 0.7849, "step": 15623 }, { "epoch": 0.8628230616302187, "grad_norm": 2.6310911178588867, "learning_rate": 1.941779853966739e-06, "loss": 0.2608, "step": 15624 }, { "epoch": 0.8628782858405125, "grad_norm": 0.5367952585220337, "learning_rate": 1.9402425169737225e-06, "loss": 0.0043, "step": 15625 }, { "epoch": 0.8629335100508063, "grad_norm": 3.5682408809661865, "learning_rate": 1.9387057577637635e-06, "loss": 0.1256, "step": 15626 }, { "epoch": 0.8629887342611001, "grad_norm": 0.8088900446891785, "learning_rate": 1.9371695763860243e-06, "loss": 0.022, "step": 15627 }, { "epoch": 0.8630439584713938, "grad_norm": 0.048820510506629944, "learning_rate": 1.93563397288965e-06, "loss": 0.0013, "step": 15628 }, { "epoch": 0.8630991826816876, "grad_norm": 5.226568222045898, "learning_rate": 1.934098947323779e-06, "loss": 0.7917, "step": 15629 }, { "epoch": 0.8631544068919814, "grad_norm": 0.493158221244812, "learning_rate": 1.932564499737506e-06, "loss": 0.0107, "step": 15630 }, { "epoch": 0.8632096311022752, "grad_norm": 3.2459919452667236, "learning_rate": 1.9310306301799354e-06, "loss": 0.0694, "step": 15631 }, { "epoch": 0.863264855312569, "grad_norm": 0.01896473579108715, "learning_rate": 1.9294973387001326e-06, "loss": 0.0003, "step": 15632 }, { "epoch": 0.8633200795228628, "grad_norm": 6.831548690795898, "learning_rate": 1.9279646253471564e-06, "loss": 0.8965, "step": 15633 }, { "epoch": 0.8633753037331566, "grad_norm": 0.018814073875546455, "learning_rate": 1.926432490170036e-06, "loss": 0.0007, "step": 15634 }, { "epoch": 0.8634305279434504, "grad_norm": 2.18163800239563, "learning_rate": 1.924900933217799e-06, "loss": 0.1332, "step": 15635 }, { "epoch": 0.8634857521537442, "grad_norm": 1.4213683605194092, "learning_rate": 1.9233699545394356e-06, "loss": 0.062, "step": 15636 }, { "epoch": 0.863540976364038, "grad_norm": 2.264671564102173, "learning_rate": 1.921839554183933e-06, "loss": 0.2546, "step": 15637 }, { "epoch": 0.8635962005743318, "grad_norm": 0.16663910448551178, "learning_rate": 1.920309732200243e-06, "loss": 0.0023, "step": 15638 }, { "epoch": 0.8636514247846255, "grad_norm": 2.283757448196411, "learning_rate": 1.9187804886373217e-06, "loss": 0.2216, "step": 15639 }, { "epoch": 0.8637066489949193, "grad_norm": 0.4156188368797302, "learning_rate": 1.917251823544082e-06, "loss": 0.0113, "step": 15640 }, { "epoch": 0.8637618732052131, "grad_norm": 2.8999009132385254, "learning_rate": 1.9157237369694392e-06, "loss": 0.2429, "step": 15641 }, { "epoch": 0.8638170974155069, "grad_norm": 2.6924004554748535, "learning_rate": 1.9141962289622774e-06, "loss": 0.4053, "step": 15642 }, { "epoch": 0.8638723216258007, "grad_norm": 0.00778864836320281, "learning_rate": 1.9126692995714678e-06, "loss": 0.0002, "step": 15643 }, { "epoch": 0.8639275458360945, "grad_norm": 3.277182102203369, "learning_rate": 1.9111429488458566e-06, "loss": 0.2275, "step": 15644 }, { "epoch": 0.8639827700463883, "grad_norm": 0.8863444328308105, "learning_rate": 1.909617176834282e-06, "loss": 0.0246, "step": 15645 }, { "epoch": 0.8640379942566822, "grad_norm": 0.5276095867156982, "learning_rate": 1.9080919835855537e-06, "loss": 0.007, "step": 15646 }, { "epoch": 0.864093218466976, "grad_norm": 1.0656310319900513, "learning_rate": 1.9065673691484643e-06, "loss": 0.0249, "step": 15647 }, { "epoch": 0.8641484426772698, "grad_norm": 0.9626398086547852, "learning_rate": 1.9050433335717988e-06, "loss": 0.0162, "step": 15648 }, { "epoch": 0.8642036668875636, "grad_norm": 2.8913161754608154, "learning_rate": 1.9035198769043095e-06, "loss": 0.1507, "step": 15649 }, { "epoch": 0.8642588910978573, "grad_norm": 3.1363513469696045, "learning_rate": 1.9019969991947396e-06, "loss": 0.1732, "step": 15650 }, { "epoch": 0.864314115308151, "grad_norm": 6.257568836212158, "learning_rate": 1.9004747004918034e-06, "loss": 0.222, "step": 15651 }, { "epoch": 0.8643693395184449, "grad_norm": 0.06873016059398651, "learning_rate": 1.8989529808442175e-06, "loss": 0.0025, "step": 15652 }, { "epoch": 0.8644245637287387, "grad_norm": 1.0739669799804688, "learning_rate": 1.8974318403006498e-06, "loss": 0.0279, "step": 15653 }, { "epoch": 0.8644797879390325, "grad_norm": 0.952272355556488, "learning_rate": 1.8959112789097745e-06, "loss": 0.031, "step": 15654 }, { "epoch": 0.8645350121493263, "grad_norm": 2.9552536010742188, "learning_rate": 1.8943912967202393e-06, "loss": 0.1019, "step": 15655 }, { "epoch": 0.8645902363596201, "grad_norm": 0.024920858442783356, "learning_rate": 1.8928718937806723e-06, "loss": 0.0005, "step": 15656 }, { "epoch": 0.8646454605699139, "grad_norm": 2.9705514907836914, "learning_rate": 1.8913530701396766e-06, "loss": 0.2575, "step": 15657 }, { "epoch": 0.8647006847802077, "grad_norm": 0.3463212251663208, "learning_rate": 1.8898348258458531e-06, "loss": 0.0087, "step": 15658 }, { "epoch": 0.8647559089905015, "grad_norm": 4.924363613128662, "learning_rate": 1.8883171609477701e-06, "loss": 0.6271, "step": 15659 }, { "epoch": 0.8648111332007953, "grad_norm": 1.8649767637252808, "learning_rate": 1.8868000754939842e-06, "loss": 0.3764, "step": 15660 }, { "epoch": 0.864866357411089, "grad_norm": 0.2120765894651413, "learning_rate": 1.8852835695330251e-06, "loss": 0.0058, "step": 15661 }, { "epoch": 0.8649215816213828, "grad_norm": 0.23096032440662384, "learning_rate": 1.8837676431134233e-06, "loss": 0.0054, "step": 15662 }, { "epoch": 0.8649768058316766, "grad_norm": 1.040062665939331, "learning_rate": 1.8822522962836598e-06, "loss": 0.0306, "step": 15663 }, { "epoch": 0.8650320300419704, "grad_norm": 0.05974270775914192, "learning_rate": 1.880737529092229e-06, "loss": 0.002, "step": 15664 }, { "epoch": 0.8650872542522642, "grad_norm": 0.013668505474925041, "learning_rate": 1.8792233415875904e-06, "loss": 0.0004, "step": 15665 }, { "epoch": 0.865142478462558, "grad_norm": 0.1494569331407547, "learning_rate": 1.8777097338181827e-06, "loss": 0.0039, "step": 15666 }, { "epoch": 0.8651977026728518, "grad_norm": 0.19680722057819366, "learning_rate": 1.876196705832427e-06, "loss": 0.0043, "step": 15667 }, { "epoch": 0.8652529268831456, "grad_norm": 5.547281742095947, "learning_rate": 1.8746842576787449e-06, "loss": 0.7906, "step": 15668 }, { "epoch": 0.8653081510934394, "grad_norm": 2.1100666522979736, "learning_rate": 1.8731723894055065e-06, "loss": 0.1773, "step": 15669 }, { "epoch": 0.8653633753037332, "grad_norm": 1.8810251951217651, "learning_rate": 1.8716611010610908e-06, "loss": 0.1203, "step": 15670 }, { "epoch": 0.865418599514027, "grad_norm": 2.435882568359375, "learning_rate": 1.8701503926938457e-06, "loss": 0.0723, "step": 15671 }, { "epoch": 0.8654738237243207, "grad_norm": 1.5267672538757324, "learning_rate": 1.8686402643521018e-06, "loss": 0.0893, "step": 15672 }, { "epoch": 0.8655290479346145, "grad_norm": 0.45221588015556335, "learning_rate": 1.8671307160841713e-06, "loss": 0.0087, "step": 15673 }, { "epoch": 0.8655842721449083, "grad_norm": 5.749191761016846, "learning_rate": 1.8656217479383554e-06, "loss": 0.9959, "step": 15674 }, { "epoch": 0.8656394963552021, "grad_norm": 1.0565065145492554, "learning_rate": 1.8641133599629246e-06, "loss": 0.1173, "step": 15675 }, { "epoch": 0.8656947205654959, "grad_norm": 4.370924472808838, "learning_rate": 1.8626055522061382e-06, "loss": 0.0676, "step": 15676 }, { "epoch": 0.8657499447757897, "grad_norm": 3.9416799545288086, "learning_rate": 1.8610983247162306e-06, "loss": 0.9502, "step": 15677 }, { "epoch": 0.8658051689860835, "grad_norm": 0.036954350769519806, "learning_rate": 1.859591677541437e-06, "loss": 0.0006, "step": 15678 }, { "epoch": 0.8658603931963773, "grad_norm": 1.5800026655197144, "learning_rate": 1.8580856107299384e-06, "loss": 0.0232, "step": 15679 }, { "epoch": 0.8659156174066711, "grad_norm": 0.09084448963403702, "learning_rate": 1.8565801243299342e-06, "loss": 0.0027, "step": 15680 }, { "epoch": 0.8659708416169649, "grad_norm": 2.4297614097595215, "learning_rate": 1.8550752183895836e-06, "loss": 0.2665, "step": 15681 }, { "epoch": 0.8660260658272587, "grad_norm": 0.38642367720603943, "learning_rate": 1.853570892957035e-06, "loss": 0.0067, "step": 15682 }, { "epoch": 0.8660812900375524, "grad_norm": 2.629429578781128, "learning_rate": 1.8520671480804076e-06, "loss": 0.1243, "step": 15683 }, { "epoch": 0.8661365142478462, "grad_norm": 0.2765021324157715, "learning_rate": 1.8505639838078249e-06, "loss": 0.006, "step": 15684 }, { "epoch": 0.86619173845814, "grad_norm": 0.2255360335111618, "learning_rate": 1.849061400187364e-06, "loss": 0.0105, "step": 15685 }, { "epoch": 0.8662469626684338, "grad_norm": 3.093240737915039, "learning_rate": 1.8475593972671047e-06, "loss": 0.0604, "step": 15686 }, { "epoch": 0.8663021868787276, "grad_norm": 0.17154142260551453, "learning_rate": 1.846057975095097e-06, "loss": 0.004, "step": 15687 }, { "epoch": 0.8663574110890214, "grad_norm": 3.9048690795898438, "learning_rate": 1.844557133719378e-06, "loss": 0.9566, "step": 15688 }, { "epoch": 0.8664126352993152, "grad_norm": 3.650707960128784, "learning_rate": 1.8430568731879584e-06, "loss": 0.4432, "step": 15689 }, { "epoch": 0.866467859509609, "grad_norm": 0.1828947514295578, "learning_rate": 1.841557193548844e-06, "loss": 0.0044, "step": 15690 }, { "epoch": 0.8665230837199028, "grad_norm": 0.012991536408662796, "learning_rate": 1.8400580948500103e-06, "loss": 0.0003, "step": 15691 }, { "epoch": 0.8665783079301966, "grad_norm": 0.48211991786956787, "learning_rate": 1.838559577139416e-06, "loss": 0.1294, "step": 15692 }, { "epoch": 0.8666335321404904, "grad_norm": 6.246865749359131, "learning_rate": 1.8370616404650011e-06, "loss": 0.6016, "step": 15693 }, { "epoch": 0.8666887563507841, "grad_norm": 3.1548564434051514, "learning_rate": 1.835564284874698e-06, "loss": 0.1274, "step": 15694 }, { "epoch": 0.8667439805610779, "grad_norm": 3.9018514156341553, "learning_rate": 1.8340675104163997e-06, "loss": 0.8451, "step": 15695 }, { "epoch": 0.8667992047713717, "grad_norm": 5.013021469116211, "learning_rate": 1.832571317138001e-06, "loss": 0.1133, "step": 15696 }, { "epoch": 0.8668544289816655, "grad_norm": 0.6618801951408386, "learning_rate": 1.8310757050873661e-06, "loss": 0.0182, "step": 15697 }, { "epoch": 0.8669096531919593, "grad_norm": 4.4962005615234375, "learning_rate": 1.8295806743123434e-06, "loss": 1.17, "step": 15698 }, { "epoch": 0.8669648774022531, "grad_norm": 1.711932897567749, "learning_rate": 1.8280862248607611e-06, "loss": 0.0395, "step": 15699 }, { "epoch": 0.867020101612547, "grad_norm": 3.344162940979004, "learning_rate": 1.8265923567804367e-06, "loss": 0.3865, "step": 15700 }, { "epoch": 0.8670753258228407, "grad_norm": 0.07958120107650757, "learning_rate": 1.8250990701191607e-06, "loss": 0.002, "step": 15701 }, { "epoch": 0.8671305500331346, "grad_norm": 0.04942022264003754, "learning_rate": 1.8236063649247082e-06, "loss": 0.0015, "step": 15702 }, { "epoch": 0.8671857742434284, "grad_norm": 5.296263694763184, "learning_rate": 1.8221142412448323e-06, "loss": 0.5254, "step": 15703 }, { "epoch": 0.8672409984537222, "grad_norm": 0.4241904020309448, "learning_rate": 1.8206226991272725e-06, "loss": 0.0111, "step": 15704 }, { "epoch": 0.867296222664016, "grad_norm": 0.023105280473828316, "learning_rate": 1.819131738619746e-06, "loss": 0.0007, "step": 15705 }, { "epoch": 0.8673514468743097, "grad_norm": 0.23624424636363983, "learning_rate": 1.8176413597699506e-06, "loss": 0.0075, "step": 15706 }, { "epoch": 0.8674066710846035, "grad_norm": 2.5009708404541016, "learning_rate": 1.8161515626255789e-06, "loss": 0.1294, "step": 15707 }, { "epoch": 0.8674618952948973, "grad_norm": 0.004410476423799992, "learning_rate": 1.8146623472342773e-06, "loss": 0.0001, "step": 15708 }, { "epoch": 0.8675171195051911, "grad_norm": 0.06018362194299698, "learning_rate": 1.8131737136437032e-06, "loss": 0.0023, "step": 15709 }, { "epoch": 0.8675723437154849, "grad_norm": 0.08169053494930267, "learning_rate": 1.8116856619014789e-06, "loss": 0.003, "step": 15710 }, { "epoch": 0.8676275679257787, "grad_norm": 0.016923388466238976, "learning_rate": 1.8101981920552082e-06, "loss": 0.0005, "step": 15711 }, { "epoch": 0.8676827921360725, "grad_norm": 3.257211208343506, "learning_rate": 1.8087113041524772e-06, "loss": 0.5959, "step": 15712 }, { "epoch": 0.8677380163463663, "grad_norm": 0.01871391013264656, "learning_rate": 1.8072249982408662e-06, "loss": 0.0005, "step": 15713 }, { "epoch": 0.8677932405566601, "grad_norm": 2.8965508937835693, "learning_rate": 1.8057392743679192e-06, "loss": 0.3368, "step": 15714 }, { "epoch": 0.8678484647669539, "grad_norm": 0.11086869984865189, "learning_rate": 1.804254132581167e-06, "loss": 0.003, "step": 15715 }, { "epoch": 0.8679036889772477, "grad_norm": 2.1705493927001953, "learning_rate": 1.8027695729281248e-06, "loss": 0.363, "step": 15716 }, { "epoch": 0.8679589131875414, "grad_norm": 0.8507813215255737, "learning_rate": 1.8012855954562968e-06, "loss": 0.0062, "step": 15717 }, { "epoch": 0.8680141373978352, "grad_norm": 2.7723755836486816, "learning_rate": 1.7998022002131432e-06, "loss": 0.2555, "step": 15718 }, { "epoch": 0.868069361608129, "grad_norm": 0.0666801929473877, "learning_rate": 1.7983193872461346e-06, "loss": 0.0013, "step": 15719 }, { "epoch": 0.8681245858184228, "grad_norm": 3.186063051223755, "learning_rate": 1.7968371566027088e-06, "loss": 0.081, "step": 15720 }, { "epoch": 0.8681798100287166, "grad_norm": 0.08933010697364807, "learning_rate": 1.795355508330283e-06, "loss": 0.0025, "step": 15721 }, { "epoch": 0.8682350342390104, "grad_norm": 3.320558547973633, "learning_rate": 1.7938744424762556e-06, "loss": 0.0881, "step": 15722 }, { "epoch": 0.8682902584493042, "grad_norm": 0.23034267127513885, "learning_rate": 1.7923939590880213e-06, "loss": 0.0047, "step": 15723 }, { "epoch": 0.868345482659598, "grad_norm": 2.260892868041992, "learning_rate": 1.790914058212938e-06, "loss": 0.5614, "step": 15724 }, { "epoch": 0.8684007068698918, "grad_norm": 0.10599824786186218, "learning_rate": 1.7894347398983548e-06, "loss": 0.0041, "step": 15725 }, { "epoch": 0.8684559310801856, "grad_norm": 3.699164628982544, "learning_rate": 1.7879560041915956e-06, "loss": 0.6574, "step": 15726 }, { "epoch": 0.8685111552904794, "grad_norm": 0.07987913489341736, "learning_rate": 1.7864778511399715e-06, "loss": 0.0025, "step": 15727 }, { "epoch": 0.8685663795007731, "grad_norm": 0.2166433483362198, "learning_rate": 1.7850002807907673e-06, "loss": 0.0057, "step": 15728 }, { "epoch": 0.8686216037110669, "grad_norm": 0.2498965710401535, "learning_rate": 1.783523293191265e-06, "loss": 0.008, "step": 15729 }, { "epoch": 0.8686768279213607, "grad_norm": 0.0631365180015564, "learning_rate": 1.7820468883887133e-06, "loss": 0.0019, "step": 15730 }, { "epoch": 0.8687320521316545, "grad_norm": 1.3567695617675781, "learning_rate": 1.7805710664303455e-06, "loss": 0.0311, "step": 15731 }, { "epoch": 0.8687872763419483, "grad_norm": 0.29394957423210144, "learning_rate": 1.779095827363373e-06, "loss": 0.0095, "step": 15732 }, { "epoch": 0.8688425005522421, "grad_norm": 0.06467727571725845, "learning_rate": 1.7776211712350067e-06, "loss": 0.0017, "step": 15733 }, { "epoch": 0.8688977247625359, "grad_norm": 0.0308833085000515, "learning_rate": 1.7761470980924066e-06, "loss": 0.0005, "step": 15734 }, { "epoch": 0.8689529489728297, "grad_norm": 2.810041904449463, "learning_rate": 1.7746736079827465e-06, "loss": 0.0312, "step": 15735 }, { "epoch": 0.8690081731831235, "grad_norm": 0.09054234623908997, "learning_rate": 1.7732007009531639e-06, "loss": 0.0028, "step": 15736 }, { "epoch": 0.8690633973934173, "grad_norm": 0.3042324185371399, "learning_rate": 1.7717283770507788e-06, "loss": 0.0064, "step": 15737 }, { "epoch": 0.8691186216037111, "grad_norm": 0.05651605501770973, "learning_rate": 1.7702566363226936e-06, "loss": 0.0014, "step": 15738 }, { "epoch": 0.8691738458140048, "grad_norm": 0.006876991130411625, "learning_rate": 1.7687854788159997e-06, "loss": 0.0002, "step": 15739 }, { "epoch": 0.8692290700242986, "grad_norm": 0.07340192049741745, "learning_rate": 1.7673149045777593e-06, "loss": 0.0021, "step": 15740 }, { "epoch": 0.8692842942345924, "grad_norm": 0.7721190452575684, "learning_rate": 1.7658449136550238e-06, "loss": 0.0154, "step": 15741 }, { "epoch": 0.8693395184448862, "grad_norm": 0.035044122487306595, "learning_rate": 1.7643755060948153e-06, "loss": 0.0008, "step": 15742 }, { "epoch": 0.86939474265518, "grad_norm": 2.485424757003784, "learning_rate": 1.7629066819441543e-06, "loss": 0.1116, "step": 15743 }, { "epoch": 0.8694499668654738, "grad_norm": 2.3393607139587402, "learning_rate": 1.7614384412500208e-06, "loss": 0.224, "step": 15744 }, { "epoch": 0.8695051910757676, "grad_norm": 1.1102542877197266, "learning_rate": 1.7599707840593994e-06, "loss": 0.0334, "step": 15745 }, { "epoch": 0.8695604152860614, "grad_norm": 0.03419116884469986, "learning_rate": 1.7585037104192393e-06, "loss": 0.0006, "step": 15746 }, { "epoch": 0.8696156394963552, "grad_norm": 2.0886104106903076, "learning_rate": 1.7570372203764763e-06, "loss": 0.2639, "step": 15747 }, { "epoch": 0.869670863706649, "grad_norm": 0.7327823042869568, "learning_rate": 1.755571313978024e-06, "loss": 0.0203, "step": 15748 }, { "epoch": 0.8697260879169428, "grad_norm": 0.06652525812387466, "learning_rate": 1.7541059912707914e-06, "loss": 0.0016, "step": 15749 }, { "epoch": 0.8697813121272365, "grad_norm": 3.2833359241485596, "learning_rate": 1.7526412523016457e-06, "loss": 0.711, "step": 15750 }, { "epoch": 0.8698365363375303, "grad_norm": 0.4142012298107147, "learning_rate": 1.751177097117458e-06, "loss": 0.0122, "step": 15751 }, { "epoch": 0.8698917605478241, "grad_norm": 0.023827796801924706, "learning_rate": 1.7497135257650687e-06, "loss": 0.0008, "step": 15752 }, { "epoch": 0.8699469847581179, "grad_norm": 4.001142978668213, "learning_rate": 1.7482505382912984e-06, "loss": 0.3973, "step": 15753 }, { "epoch": 0.8700022089684117, "grad_norm": 0.84874027967453, "learning_rate": 1.7467881347429494e-06, "loss": 0.0242, "step": 15754 }, { "epoch": 0.8700574331787055, "grad_norm": 0.4536535143852234, "learning_rate": 1.7453263151668175e-06, "loss": 0.0039, "step": 15755 }, { "epoch": 0.8701126573889993, "grad_norm": 0.4350798428058624, "learning_rate": 1.7438650796096634e-06, "loss": 0.0086, "step": 15756 }, { "epoch": 0.8701678815992931, "grad_norm": 2.7055857181549072, "learning_rate": 1.7424044281182407e-06, "loss": 0.1524, "step": 15757 }, { "epoch": 0.870223105809587, "grad_norm": 3.689274787902832, "learning_rate": 1.7409443607392718e-06, "loss": 0.4444, "step": 15758 }, { "epoch": 0.8702783300198808, "grad_norm": 0.9000142216682434, "learning_rate": 1.739484877519484e-06, "loss": 0.1023, "step": 15759 }, { "epoch": 0.8703335542301746, "grad_norm": 3.332171678543091, "learning_rate": 1.738025978505551e-06, "loss": 0.1816, "step": 15760 }, { "epoch": 0.8703887784404682, "grad_norm": 0.22679993510246277, "learning_rate": 1.7365676637441597e-06, "loss": 0.0047, "step": 15761 }, { "epoch": 0.870444002650762, "grad_norm": 0.5045077204704285, "learning_rate": 1.7351099332819644e-06, "loss": 0.0089, "step": 15762 }, { "epoch": 0.8704992268610559, "grad_norm": 0.2893637418746948, "learning_rate": 1.7336527871655983e-06, "loss": 0.0056, "step": 15763 }, { "epoch": 0.8705544510713497, "grad_norm": 0.17563818395137787, "learning_rate": 1.7321962254416824e-06, "loss": 0.0047, "step": 15764 }, { "epoch": 0.8706096752816435, "grad_norm": 2.357515573501587, "learning_rate": 1.730740248156817e-06, "loss": 0.1296, "step": 15765 }, { "epoch": 0.8706648994919373, "grad_norm": 1.7271023988723755, "learning_rate": 1.729284855357578e-06, "loss": 0.0631, "step": 15766 }, { "epoch": 0.8707201237022311, "grad_norm": 3.225102186203003, "learning_rate": 1.7278300470905307e-06, "loss": 0.6346, "step": 15767 }, { "epoch": 0.8707753479125249, "grad_norm": 6.669691562652588, "learning_rate": 1.72637582340222e-06, "loss": 0.4931, "step": 15768 }, { "epoch": 0.8708305721228187, "grad_norm": 8.501302719116211, "learning_rate": 1.7249221843391706e-06, "loss": 0.1113, "step": 15769 }, { "epoch": 0.8708857963331125, "grad_norm": 0.10277403891086578, "learning_rate": 1.7234691299478856e-06, "loss": 0.0023, "step": 15770 }, { "epoch": 0.8709410205434063, "grad_norm": 0.008696378208696842, "learning_rate": 1.7220166602748523e-06, "loss": 0.0003, "step": 15771 }, { "epoch": 0.8709962447537001, "grad_norm": 0.07555089145898819, "learning_rate": 1.7205647753665466e-06, "loss": 0.0015, "step": 15772 }, { "epoch": 0.8710514689639938, "grad_norm": 5.786149501800537, "learning_rate": 1.7191134752694071e-06, "loss": 0.7549, "step": 15773 }, { "epoch": 0.8711066931742876, "grad_norm": 0.4388866722583771, "learning_rate": 1.7176627600298745e-06, "loss": 0.1123, "step": 15774 }, { "epoch": 0.8711619173845814, "grad_norm": 3.746293306350708, "learning_rate": 1.7162126296943582e-06, "loss": 0.252, "step": 15775 }, { "epoch": 0.8712171415948752, "grad_norm": 1.2305822372436523, "learning_rate": 1.7147630843092522e-06, "loss": 0.0441, "step": 15776 }, { "epoch": 0.871272365805169, "grad_norm": 4.424295425415039, "learning_rate": 1.713314123920924e-06, "loss": 0.4783, "step": 15777 }, { "epoch": 0.8713275900154628, "grad_norm": 0.26256346702575684, "learning_rate": 1.7118657485757428e-06, "loss": 0.0072, "step": 15778 }, { "epoch": 0.8713828142257566, "grad_norm": 0.26668936014175415, "learning_rate": 1.710417958320041e-06, "loss": 0.0076, "step": 15779 }, { "epoch": 0.8714380384360504, "grad_norm": 0.05810612067580223, "learning_rate": 1.7089707532001365e-06, "loss": 0.0007, "step": 15780 }, { "epoch": 0.8714932626463442, "grad_norm": 1.9198862314224243, "learning_rate": 1.7075241332623237e-06, "loss": 0.0757, "step": 15781 }, { "epoch": 0.871548486856638, "grad_norm": 6.374475002288818, "learning_rate": 1.706078098552899e-06, "loss": 1.3224, "step": 15782 }, { "epoch": 0.8716037110669318, "grad_norm": 3.162790298461914, "learning_rate": 1.7046326491181098e-06, "loss": 0.1046, "step": 15783 }, { "epoch": 0.8716589352772255, "grad_norm": 0.0159296877682209, "learning_rate": 1.70318778500421e-06, "loss": 0.0004, "step": 15784 }, { "epoch": 0.8717141594875193, "grad_norm": 0.01799284853041172, "learning_rate": 1.7017435062574228e-06, "loss": 0.0005, "step": 15785 }, { "epoch": 0.8717693836978131, "grad_norm": 3.803474187850952, "learning_rate": 1.7002998129239535e-06, "loss": 0.8548, "step": 15786 }, { "epoch": 0.8718246079081069, "grad_norm": 0.7514327764511108, "learning_rate": 1.6988567050499848e-06, "loss": 0.0186, "step": 15787 }, { "epoch": 0.8718798321184007, "grad_norm": 0.07897243648767471, "learning_rate": 1.697414182681698e-06, "loss": 0.0016, "step": 15788 }, { "epoch": 0.8719350563286945, "grad_norm": 3.703594207763672, "learning_rate": 1.6959722458652316e-06, "loss": 0.638, "step": 15789 }, { "epoch": 0.8719902805389883, "grad_norm": 0.2950911223888397, "learning_rate": 1.6945308946467244e-06, "loss": 0.006, "step": 15790 }, { "epoch": 0.8720455047492821, "grad_norm": 1.8912855386734009, "learning_rate": 1.693090129072288e-06, "loss": 0.1553, "step": 15791 }, { "epoch": 0.8721007289595759, "grad_norm": 4.370871067047119, "learning_rate": 1.6916499491880168e-06, "loss": 0.9341, "step": 15792 }, { "epoch": 0.8721559531698697, "grad_norm": 4.27394962310791, "learning_rate": 1.6902103550399807e-06, "loss": 0.0494, "step": 15793 }, { "epoch": 0.8722111773801635, "grad_norm": 1.7845845222473145, "learning_rate": 1.6887713466742427e-06, "loss": 0.0607, "step": 15794 }, { "epoch": 0.8722664015904572, "grad_norm": 3.0678837299346924, "learning_rate": 1.687332924136842e-06, "loss": 0.254, "step": 15795 }, { "epoch": 0.872321625800751, "grad_norm": 0.294941782951355, "learning_rate": 1.6858950874737922e-06, "loss": 0.0057, "step": 15796 }, { "epoch": 0.8723768500110448, "grad_norm": 0.073100745677948, "learning_rate": 1.684457836731095e-06, "loss": 0.0013, "step": 15797 }, { "epoch": 0.8724320742213386, "grad_norm": 0.4665345549583435, "learning_rate": 1.6830211719547396e-06, "loss": 0.0108, "step": 15798 }, { "epoch": 0.8724872984316324, "grad_norm": 0.2545838952064514, "learning_rate": 1.6815850931906764e-06, "loss": 0.0063, "step": 15799 }, { "epoch": 0.8725425226419262, "grad_norm": 3.400291681289673, "learning_rate": 1.6801496004848617e-06, "loss": 0.3776, "step": 15800 }, { "epoch": 0.87259774685222, "grad_norm": 4.4353485107421875, "learning_rate": 1.6787146938832122e-06, "loss": 0.4857, "step": 15801 }, { "epoch": 0.8726529710625138, "grad_norm": 0.011555369943380356, "learning_rate": 1.67728037343164e-06, "loss": 0.0002, "step": 15802 }, { "epoch": 0.8727081952728076, "grad_norm": 0.3851493299007416, "learning_rate": 1.6758466391760287e-06, "loss": 0.0104, "step": 15803 }, { "epoch": 0.8727634194831014, "grad_norm": 9.499726295471191, "learning_rate": 1.6744134911622546e-06, "loss": 0.3231, "step": 15804 }, { "epoch": 0.8728186436933952, "grad_norm": 7.017973899841309, "learning_rate": 1.6729809294361566e-06, "loss": 0.6029, "step": 15805 }, { "epoch": 0.8728738679036889, "grad_norm": 0.15249016880989075, "learning_rate": 1.671548954043578e-06, "loss": 0.0036, "step": 15806 }, { "epoch": 0.8729290921139827, "grad_norm": 0.23079560697078705, "learning_rate": 1.670117565030327e-06, "loss": 0.0039, "step": 15807 }, { "epoch": 0.8729843163242765, "grad_norm": 3.462440252304077, "learning_rate": 1.6686867624421976e-06, "loss": 0.7128, "step": 15808 }, { "epoch": 0.8730395405345703, "grad_norm": 0.9045606255531311, "learning_rate": 1.6672565463249623e-06, "loss": 0.0225, "step": 15809 }, { "epoch": 0.8730947647448641, "grad_norm": 0.6270462870597839, "learning_rate": 1.6658269167243845e-06, "loss": 0.0204, "step": 15810 }, { "epoch": 0.8731499889551579, "grad_norm": 0.02303045615553856, "learning_rate": 1.6643978736861987e-06, "loss": 0.0007, "step": 15811 }, { "epoch": 0.8732052131654517, "grad_norm": 1.4193594455718994, "learning_rate": 1.6629694172561262e-06, "loss": 0.0597, "step": 15812 }, { "epoch": 0.8732604373757455, "grad_norm": 2.3620057106018066, "learning_rate": 1.6615415474798591e-06, "loss": 0.1798, "step": 15813 }, { "epoch": 0.8733156615860393, "grad_norm": 1.9661897420883179, "learning_rate": 1.660114264403092e-06, "loss": 0.0816, "step": 15814 }, { "epoch": 0.8733708857963332, "grad_norm": 2.5478317737579346, "learning_rate": 1.6586875680714753e-06, "loss": 0.115, "step": 15815 }, { "epoch": 0.873426110006627, "grad_norm": 1.2204996347427368, "learning_rate": 1.6572614585306612e-06, "loss": 0.0402, "step": 15816 }, { "epoch": 0.8734813342169206, "grad_norm": 0.02675618603825569, "learning_rate": 1.6558359358262731e-06, "loss": 0.0007, "step": 15817 }, { "epoch": 0.8735365584272144, "grad_norm": 0.060361601412296295, "learning_rate": 1.654411000003917e-06, "loss": 0.0014, "step": 15818 }, { "epoch": 0.8735917826375083, "grad_norm": 0.14988158643245697, "learning_rate": 1.6529866511091763e-06, "loss": 0.002, "step": 15819 }, { "epoch": 0.873647006847802, "grad_norm": 1.6150734424591064, "learning_rate": 1.651562889187628e-06, "loss": 0.0504, "step": 15820 }, { "epoch": 0.8737022310580959, "grad_norm": 0.039616066962480545, "learning_rate": 1.6501397142848196e-06, "loss": 0.0009, "step": 15821 }, { "epoch": 0.8737574552683897, "grad_norm": 2.694411277770996, "learning_rate": 1.648717126446282e-06, "loss": 0.5124, "step": 15822 }, { "epoch": 0.8738126794786835, "grad_norm": 3.9076859951019287, "learning_rate": 1.647295125717525e-06, "loss": 0.4024, "step": 15823 }, { "epoch": 0.8738679036889773, "grad_norm": 0.10950516909360886, "learning_rate": 1.645873712144046e-06, "loss": 0.0022, "step": 15824 }, { "epoch": 0.8739231278992711, "grad_norm": 0.41992342472076416, "learning_rate": 1.6444528857713194e-06, "loss": 0.0134, "step": 15825 }, { "epoch": 0.8739783521095649, "grad_norm": 0.022647131234407425, "learning_rate": 1.6430326466447954e-06, "loss": 0.0008, "step": 15826 }, { "epoch": 0.8740335763198587, "grad_norm": 0.2122696489095688, "learning_rate": 1.6416129948099246e-06, "loss": 0.0066, "step": 15827 }, { "epoch": 0.8740888005301524, "grad_norm": 0.05914577469229698, "learning_rate": 1.6401939303121128e-06, "loss": 0.0021, "step": 15828 }, { "epoch": 0.8741440247404462, "grad_norm": 6.325455665588379, "learning_rate": 1.6387754531967682e-06, "loss": 0.5467, "step": 15829 }, { "epoch": 0.87419924895074, "grad_norm": 0.10784986615180969, "learning_rate": 1.6373575635092676e-06, "loss": 0.0032, "step": 15830 }, { "epoch": 0.8742544731610338, "grad_norm": 0.3703790307044983, "learning_rate": 1.635940261294975e-06, "loss": 0.0111, "step": 15831 }, { "epoch": 0.8743096973713276, "grad_norm": 0.018018782138824463, "learning_rate": 1.6345235465992316e-06, "loss": 0.0004, "step": 15832 }, { "epoch": 0.8743649215816214, "grad_norm": 4.420745849609375, "learning_rate": 1.6331074194673657e-06, "loss": 0.7589, "step": 15833 }, { "epoch": 0.8744201457919152, "grad_norm": 3.114966630935669, "learning_rate": 1.6316918799446834e-06, "loss": 0.3801, "step": 15834 }, { "epoch": 0.874475370002209, "grad_norm": 0.19147838652133942, "learning_rate": 1.6302769280764685e-06, "loss": 0.0043, "step": 15835 }, { "epoch": 0.8745305942125028, "grad_norm": 1.241579532623291, "learning_rate": 1.628862563907989e-06, "loss": 0.3063, "step": 15836 }, { "epoch": 0.8745858184227966, "grad_norm": 3.9808990955352783, "learning_rate": 1.6274487874845023e-06, "loss": 0.9053, "step": 15837 }, { "epoch": 0.8746410426330904, "grad_norm": 2.2913992404937744, "learning_rate": 1.6260355988512278e-06, "loss": 0.11, "step": 15838 }, { "epoch": 0.8746962668433841, "grad_norm": 0.0897894948720932, "learning_rate": 1.6246229980533845e-06, "loss": 0.0016, "step": 15839 }, { "epoch": 0.8747514910536779, "grad_norm": 0.06008099019527435, "learning_rate": 1.6232109851361655e-06, "loss": 0.0011, "step": 15840 }, { "epoch": 0.8748067152639717, "grad_norm": 5.445809364318848, "learning_rate": 1.6217995601447412e-06, "loss": 0.4323, "step": 15841 }, { "epoch": 0.8748619394742655, "grad_norm": 4.656197547912598, "learning_rate": 1.6203887231242666e-06, "loss": 0.2834, "step": 15842 }, { "epoch": 0.8749171636845593, "grad_norm": 0.015029852278530598, "learning_rate": 1.6189784741198856e-06, "loss": 0.0004, "step": 15843 }, { "epoch": 0.8749723878948531, "grad_norm": 0.5630154609680176, "learning_rate": 1.6175688131767108e-06, "loss": 0.0085, "step": 15844 }, { "epoch": 0.8750276121051469, "grad_norm": 0.027627695351839066, "learning_rate": 1.6161597403398444e-06, "loss": 0.0007, "step": 15845 }, { "epoch": 0.8750828363154407, "grad_norm": 0.9210970401763916, "learning_rate": 1.614751255654361e-06, "loss": 0.0153, "step": 15846 }, { "epoch": 0.8751380605257345, "grad_norm": 0.7781559824943542, "learning_rate": 1.6133433591653291e-06, "loss": 0.1975, "step": 15847 }, { "epoch": 0.8751932847360283, "grad_norm": 4.659416198730469, "learning_rate": 1.6119360509177817e-06, "loss": 0.9828, "step": 15848 }, { "epoch": 0.8752485089463221, "grad_norm": 0.1321375072002411, "learning_rate": 1.6105293309567516e-06, "loss": 0.0045, "step": 15849 }, { "epoch": 0.8753037331566159, "grad_norm": 2.696958065032959, "learning_rate": 1.6091231993272427e-06, "loss": 0.0632, "step": 15850 }, { "epoch": 0.8753589573669096, "grad_norm": 1.4475101232528687, "learning_rate": 1.607717656074237e-06, "loss": 0.2629, "step": 15851 }, { "epoch": 0.8754141815772034, "grad_norm": 0.04184659197926521, "learning_rate": 1.6063127012427003e-06, "loss": 0.0013, "step": 15852 }, { "epoch": 0.8754694057874972, "grad_norm": 1.6302316188812256, "learning_rate": 1.6049083348775929e-06, "loss": 0.0654, "step": 15853 }, { "epoch": 0.875524629997791, "grad_norm": 0.456489622592926, "learning_rate": 1.6035045570238295e-06, "loss": 0.0116, "step": 15854 }, { "epoch": 0.8755798542080848, "grad_norm": 2.5697124004364014, "learning_rate": 1.6021013677263319e-06, "loss": 0.4459, "step": 15855 }, { "epoch": 0.8756350784183786, "grad_norm": 0.5630342960357666, "learning_rate": 1.6006987670299867e-06, "loss": 0.0179, "step": 15856 }, { "epoch": 0.8756903026286724, "grad_norm": 1.2608920335769653, "learning_rate": 1.5992967549796713e-06, "loss": 0.0576, "step": 15857 }, { "epoch": 0.8757455268389662, "grad_norm": 1.3106876611709595, "learning_rate": 1.5978953316202294e-06, "loss": 0.0681, "step": 15858 }, { "epoch": 0.87580075104926, "grad_norm": 1.3923828601837158, "learning_rate": 1.5964944969965101e-06, "loss": 0.0631, "step": 15859 }, { "epoch": 0.8758559752595538, "grad_norm": 0.05148434638977051, "learning_rate": 1.595094251153324e-06, "loss": 0.0018, "step": 15860 }, { "epoch": 0.8759111994698476, "grad_norm": 0.40955954790115356, "learning_rate": 1.5936945941354708e-06, "loss": 0.0087, "step": 15861 }, { "epoch": 0.8759664236801413, "grad_norm": 5.053553581237793, "learning_rate": 1.5922955259877215e-06, "loss": 0.1168, "step": 15862 }, { "epoch": 0.8760216478904351, "grad_norm": 0.006479516159743071, "learning_rate": 1.5908970467548512e-06, "loss": 0.0002, "step": 15863 }, { "epoch": 0.8760768721007289, "grad_norm": 2.6716525554656982, "learning_rate": 1.5894991564815864e-06, "loss": 0.1831, "step": 15864 }, { "epoch": 0.8761320963110227, "grad_norm": 3.13569974899292, "learning_rate": 1.5881018552126581e-06, "loss": 0.4902, "step": 15865 }, { "epoch": 0.8761873205213165, "grad_norm": 1.4553571939468384, "learning_rate": 1.5867051429927705e-06, "loss": 0.2651, "step": 15866 }, { "epoch": 0.8762425447316103, "grad_norm": 3.4260175228118896, "learning_rate": 1.5853090198666033e-06, "loss": 0.0541, "step": 15867 }, { "epoch": 0.8762977689419041, "grad_norm": 0.035213496536016464, "learning_rate": 1.5839134858788207e-06, "loss": 0.0012, "step": 15868 }, { "epoch": 0.876352993152198, "grad_norm": 0.019401410594582558, "learning_rate": 1.5825185410740829e-06, "loss": 0.0004, "step": 15869 }, { "epoch": 0.8764082173624917, "grad_norm": 3.0417253971099854, "learning_rate": 1.5811241854970006e-06, "loss": 0.0834, "step": 15870 }, { "epoch": 0.8764634415727856, "grad_norm": 3.761819362640381, "learning_rate": 1.5797304191921958e-06, "loss": 0.2157, "step": 15871 }, { "epoch": 0.8765186657830794, "grad_norm": 2.489833354949951, "learning_rate": 1.5783372422042554e-06, "loss": 0.2101, "step": 15872 }, { "epoch": 0.876573889993373, "grad_norm": 3.1258888244628906, "learning_rate": 1.5769446545777522e-06, "loss": 0.661, "step": 15873 }, { "epoch": 0.8766291142036668, "grad_norm": 0.7754654288291931, "learning_rate": 1.5755526563572332e-06, "loss": 0.0232, "step": 15874 }, { "epoch": 0.8766843384139607, "grad_norm": 0.25005850195884705, "learning_rate": 1.574161247587238e-06, "loss": 0.0046, "step": 15875 }, { "epoch": 0.8767395626242545, "grad_norm": 0.007037663832306862, "learning_rate": 1.5727704283122825e-06, "loss": 0.0002, "step": 15876 }, { "epoch": 0.8767947868345483, "grad_norm": 0.8294510245323181, "learning_rate": 1.5713801985768617e-06, "loss": 0.1022, "step": 15877 }, { "epoch": 0.8768500110448421, "grad_norm": 3.255321502685547, "learning_rate": 1.5699905584254471e-06, "loss": 0.2907, "step": 15878 }, { "epoch": 0.8769052352551359, "grad_norm": 1.6686955690383911, "learning_rate": 1.5686015079025095e-06, "loss": 0.1415, "step": 15879 }, { "epoch": 0.8769604594654297, "grad_norm": 1.0499026775360107, "learning_rate": 1.567213047052476e-06, "loss": 0.0321, "step": 15880 }, { "epoch": 0.8770156836757235, "grad_norm": 0.38338977098464966, "learning_rate": 1.5658251759197751e-06, "loss": 0.0089, "step": 15881 }, { "epoch": 0.8770709078860173, "grad_norm": 1.4955434799194336, "learning_rate": 1.5644378945488092e-06, "loss": 0.2577, "step": 15882 }, { "epoch": 0.8771261320963111, "grad_norm": 2.6620514392852783, "learning_rate": 1.5630512029839562e-06, "loss": 0.1907, "step": 15883 }, { "epoch": 0.8771813563066048, "grad_norm": 5.281314373016357, "learning_rate": 1.5616651012695828e-06, "loss": 0.0757, "step": 15884 }, { "epoch": 0.8772365805168986, "grad_norm": 4.36110782623291, "learning_rate": 1.5602795894500355e-06, "loss": 0.5436, "step": 15885 }, { "epoch": 0.8772918047271924, "grad_norm": 0.5036062002182007, "learning_rate": 1.5588946675696392e-06, "loss": 0.0092, "step": 15886 }, { "epoch": 0.8773470289374862, "grad_norm": 0.03366170823574066, "learning_rate": 1.5575103356726983e-06, "loss": 0.0009, "step": 15887 }, { "epoch": 0.87740225314778, "grad_norm": 0.02183421328663826, "learning_rate": 1.5561265938035086e-06, "loss": 0.0006, "step": 15888 }, { "epoch": 0.8774574773580738, "grad_norm": 2.485773801803589, "learning_rate": 1.5547434420063368e-06, "loss": 0.5108, "step": 15889 }, { "epoch": 0.8775127015683676, "grad_norm": 0.2612857222557068, "learning_rate": 1.553360880325434e-06, "loss": 0.0027, "step": 15890 }, { "epoch": 0.8775679257786614, "grad_norm": 0.2809985280036926, "learning_rate": 1.5519789088050274e-06, "loss": 0.0052, "step": 15891 }, { "epoch": 0.8776231499889552, "grad_norm": 6.101929664611816, "learning_rate": 1.5505975274893437e-06, "loss": 0.7172, "step": 15892 }, { "epoch": 0.877678374199249, "grad_norm": 0.20469024777412415, "learning_rate": 1.5492167364225585e-06, "loss": 0.0055, "step": 15893 }, { "epoch": 0.8777335984095428, "grad_norm": 0.6817606091499329, "learning_rate": 1.5478365356488633e-06, "loss": 0.0149, "step": 15894 }, { "epoch": 0.8777888226198365, "grad_norm": 2.556532144546509, "learning_rate": 1.5464569252124073e-06, "loss": 0.0443, "step": 15895 }, { "epoch": 0.8778440468301303, "grad_norm": 0.1932211071252823, "learning_rate": 1.5450779051573284e-06, "loss": 0.0027, "step": 15896 }, { "epoch": 0.8778992710404241, "grad_norm": 0.4878310561180115, "learning_rate": 1.5436994755277424e-06, "loss": 0.0127, "step": 15897 }, { "epoch": 0.8779544952507179, "grad_norm": 0.025353634729981422, "learning_rate": 1.5423216363677563e-06, "loss": 0.0009, "step": 15898 }, { "epoch": 0.8780097194610117, "grad_norm": 4.408614158630371, "learning_rate": 1.5409443877214481e-06, "loss": 0.3744, "step": 15899 }, { "epoch": 0.8780649436713055, "grad_norm": 0.7324494123458862, "learning_rate": 1.5395677296328803e-06, "loss": 0.0243, "step": 15900 }, { "epoch": 0.8781201678815993, "grad_norm": 0.10640351474285126, "learning_rate": 1.5381916621460914e-06, "loss": 0.0027, "step": 15901 }, { "epoch": 0.8781753920918931, "grad_norm": 3.226994514465332, "learning_rate": 1.5368161853051167e-06, "loss": 0.1771, "step": 15902 }, { "epoch": 0.8782306163021869, "grad_norm": 3.1974868774414062, "learning_rate": 1.535441299153948e-06, "loss": 0.693, "step": 15903 }, { "epoch": 0.8782858405124807, "grad_norm": 0.010664056986570358, "learning_rate": 1.5340670037365812e-06, "loss": 0.0003, "step": 15904 }, { "epoch": 0.8783410647227745, "grad_norm": 0.12184923887252808, "learning_rate": 1.5326932990969811e-06, "loss": 0.0032, "step": 15905 }, { "epoch": 0.8783962889330682, "grad_norm": 6.315964221954346, "learning_rate": 1.531320185279097e-06, "loss": 0.7357, "step": 15906 }, { "epoch": 0.878451513143362, "grad_norm": 1.1109821796417236, "learning_rate": 1.529947662326854e-06, "loss": 0.0562, "step": 15907 }, { "epoch": 0.8785067373536558, "grad_norm": 0.14950738847255707, "learning_rate": 1.5285757302841742e-06, "loss": 0.0054, "step": 15908 }, { "epoch": 0.8785619615639496, "grad_norm": 2.1753041744232178, "learning_rate": 1.5272043891949363e-06, "loss": 0.1802, "step": 15909 }, { "epoch": 0.8786171857742434, "grad_norm": 0.4818791449069977, "learning_rate": 1.5258336391030227e-06, "loss": 0.1169, "step": 15910 }, { "epoch": 0.8786724099845372, "grad_norm": 0.09583821147680283, "learning_rate": 1.524463480052285e-06, "loss": 0.0035, "step": 15911 }, { "epoch": 0.878727634194831, "grad_norm": 3.6235954761505127, "learning_rate": 1.5230939120865596e-06, "loss": 0.6961, "step": 15912 }, { "epoch": 0.8787828584051248, "grad_norm": 0.10388477891683578, "learning_rate": 1.5217249352496554e-06, "loss": 0.0031, "step": 15913 }, { "epoch": 0.8788380826154186, "grad_norm": 0.11403632909059525, "learning_rate": 1.52035654958538e-06, "loss": 0.0029, "step": 15914 }, { "epoch": 0.8788933068257124, "grad_norm": 1.5336194038391113, "learning_rate": 1.518988755137507e-06, "loss": 0.0153, "step": 15915 }, { "epoch": 0.8789485310360062, "grad_norm": 0.21676963567733765, "learning_rate": 1.5176215519497995e-06, "loss": 0.0055, "step": 15916 }, { "epoch": 0.8790037552462999, "grad_norm": 0.04234009236097336, "learning_rate": 1.5162549400659888e-06, "loss": 0.0011, "step": 15917 }, { "epoch": 0.8790589794565937, "grad_norm": 0.343584805727005, "learning_rate": 1.5148889195298134e-06, "loss": 0.0038, "step": 15918 }, { "epoch": 0.8791142036668875, "grad_norm": 2.2794547080993652, "learning_rate": 1.513523490384956e-06, "loss": 0.109, "step": 15919 }, { "epoch": 0.8791694278771813, "grad_norm": 0.6085742712020874, "learning_rate": 1.5121586526751175e-06, "loss": 0.0073, "step": 15920 }, { "epoch": 0.8792246520874751, "grad_norm": 3.7828752994537354, "learning_rate": 1.510794406443954e-06, "loss": 0.2956, "step": 15921 }, { "epoch": 0.8792798762977689, "grad_norm": 0.0869811475276947, "learning_rate": 1.5094307517351149e-06, "loss": 0.0026, "step": 15922 }, { "epoch": 0.8793351005080627, "grad_norm": 0.016971979290246964, "learning_rate": 1.5080676885922229e-06, "loss": 0.0004, "step": 15923 }, { "epoch": 0.8793903247183565, "grad_norm": 0.3672263026237488, "learning_rate": 1.506705217058897e-06, "loss": 0.0091, "step": 15924 }, { "epoch": 0.8794455489286503, "grad_norm": 3.0832269191741943, "learning_rate": 1.5053433371787108e-06, "loss": 0.2583, "step": 15925 }, { "epoch": 0.8795007731389441, "grad_norm": 2.203702926635742, "learning_rate": 1.5039820489952472e-06, "loss": 0.109, "step": 15926 }, { "epoch": 0.879555997349238, "grad_norm": 0.10511922091245651, "learning_rate": 1.502621352552056e-06, "loss": 0.002, "step": 15927 }, { "epoch": 0.8796112215595318, "grad_norm": 0.4090157449245453, "learning_rate": 1.5012612478926648e-06, "loss": 0.0084, "step": 15928 }, { "epoch": 0.8796664457698254, "grad_norm": 0.6210874319076538, "learning_rate": 1.499901735060587e-06, "loss": 0.0127, "step": 15929 }, { "epoch": 0.8797216699801192, "grad_norm": 1.8849624395370483, "learning_rate": 1.4985428140993242e-06, "loss": 0.0959, "step": 15930 }, { "epoch": 0.879776894190413, "grad_norm": 0.08496636897325516, "learning_rate": 1.4971844850523477e-06, "loss": 0.0019, "step": 15931 }, { "epoch": 0.8798321184007069, "grad_norm": 0.008077508769929409, "learning_rate": 1.4958267479631138e-06, "loss": 0.0002, "step": 15932 }, { "epoch": 0.8798873426110007, "grad_norm": 5.460559368133545, "learning_rate": 1.4944696028750595e-06, "loss": 0.2904, "step": 15933 }, { "epoch": 0.8799425668212945, "grad_norm": 4.159273147583008, "learning_rate": 1.4931130498316116e-06, "loss": 1.1133, "step": 15934 }, { "epoch": 0.8799977910315883, "grad_norm": 3.5922961235046387, "learning_rate": 1.4917570888761578e-06, "loss": 0.6818, "step": 15935 }, { "epoch": 0.8800530152418821, "grad_norm": 0.0296613946557045, "learning_rate": 1.4904017200520881e-06, "loss": 0.0008, "step": 15936 }, { "epoch": 0.8801082394521759, "grad_norm": 0.2906283140182495, "learning_rate": 1.489046943402761e-06, "loss": 0.0067, "step": 15937 }, { "epoch": 0.8801634636624697, "grad_norm": 0.25348392128944397, "learning_rate": 1.4876927589715218e-06, "loss": 0.0065, "step": 15938 }, { "epoch": 0.8802186878727635, "grad_norm": 1.732453465461731, "learning_rate": 1.4863391668016892e-06, "loss": 0.1428, "step": 15939 }, { "epoch": 0.8802739120830572, "grad_norm": 3.6070070266723633, "learning_rate": 1.4849861669365772e-06, "loss": 0.2171, "step": 15940 }, { "epoch": 0.880329136293351, "grad_norm": 2.248044729232788, "learning_rate": 1.4836337594194673e-06, "loss": 0.1435, "step": 15941 }, { "epoch": 0.8803843605036448, "grad_norm": 0.02726018987596035, "learning_rate": 1.4822819442936264e-06, "loss": 0.0009, "step": 15942 }, { "epoch": 0.8804395847139386, "grad_norm": 1.9126619100570679, "learning_rate": 1.480930721602305e-06, "loss": 0.2493, "step": 15943 }, { "epoch": 0.8804948089242324, "grad_norm": 0.3919644355773926, "learning_rate": 1.4795800913887304e-06, "loss": 0.0104, "step": 15944 }, { "epoch": 0.8805500331345262, "grad_norm": 0.02236475609242916, "learning_rate": 1.4782300536961126e-06, "loss": 0.0008, "step": 15945 }, { "epoch": 0.88060525734482, "grad_norm": 0.5471106171607971, "learning_rate": 1.4768806085676435e-06, "loss": 0.0107, "step": 15946 }, { "epoch": 0.8806604815551138, "grad_norm": 0.8442736268043518, "learning_rate": 1.4755317560465022e-06, "loss": 0.0335, "step": 15947 }, { "epoch": 0.8807157057654076, "grad_norm": 0.017904460430145264, "learning_rate": 1.4741834961758295e-06, "loss": 0.0006, "step": 15948 }, { "epoch": 0.8807709299757014, "grad_norm": 2.564846992492676, "learning_rate": 1.4728358289987732e-06, "loss": 0.0697, "step": 15949 }, { "epoch": 0.8808261541859952, "grad_norm": 3.185115098953247, "learning_rate": 1.471488754558441e-06, "loss": 0.2341, "step": 15950 }, { "epoch": 0.8808813783962889, "grad_norm": 4.596408843994141, "learning_rate": 1.470142272897932e-06, "loss": 0.5738, "step": 15951 }, { "epoch": 0.8809366026065827, "grad_norm": 3.2145352363586426, "learning_rate": 1.4687963840603225e-06, "loss": 0.405, "step": 15952 }, { "epoch": 0.8809918268168765, "grad_norm": 0.02001771703362465, "learning_rate": 1.467451088088674e-06, "loss": 0.0007, "step": 15953 }, { "epoch": 0.8810470510271703, "grad_norm": 0.04614710062742233, "learning_rate": 1.4661063850260249e-06, "loss": 0.0013, "step": 15954 }, { "epoch": 0.8811022752374641, "grad_norm": 0.240867018699646, "learning_rate": 1.464762274915399e-06, "loss": 0.0057, "step": 15955 }, { "epoch": 0.8811574994477579, "grad_norm": 0.12219143658876419, "learning_rate": 1.4634187577997882e-06, "loss": 0.0025, "step": 15956 }, { "epoch": 0.8812127236580517, "grad_norm": 4.019158363342285, "learning_rate": 1.4620758337221918e-06, "loss": 0.2826, "step": 15957 }, { "epoch": 0.8812679478683455, "grad_norm": 0.19117078185081482, "learning_rate": 1.4607335027255577e-06, "loss": 0.0039, "step": 15958 }, { "epoch": 0.8813231720786393, "grad_norm": 2.6550369262695312, "learning_rate": 1.45939176485284e-06, "loss": 0.5717, "step": 15959 }, { "epoch": 0.8813783962889331, "grad_norm": 3.0932438373565674, "learning_rate": 1.4580506201469645e-06, "loss": 0.2375, "step": 15960 }, { "epoch": 0.8814336204992269, "grad_norm": 2.751931667327881, "learning_rate": 1.4567100686508352e-06, "loss": 0.1276, "step": 15961 }, { "epoch": 0.8814888447095206, "grad_norm": 1.0897444486618042, "learning_rate": 1.455370110407337e-06, "loss": 0.0598, "step": 15962 }, { "epoch": 0.8815440689198144, "grad_norm": 3.817166328430176, "learning_rate": 1.4540307454593494e-06, "loss": 0.4814, "step": 15963 }, { "epoch": 0.8815992931301082, "grad_norm": 0.028240634128451347, "learning_rate": 1.4526919738497113e-06, "loss": 0.0006, "step": 15964 }, { "epoch": 0.881654517340402, "grad_norm": 2.5351006984710693, "learning_rate": 1.451353795621262e-06, "loss": 0.5046, "step": 15965 }, { "epoch": 0.8817097415506958, "grad_norm": 0.016337545588612556, "learning_rate": 1.4500162108168091e-06, "loss": 0.0006, "step": 15966 }, { "epoch": 0.8817649657609896, "grad_norm": 2.0854721069335938, "learning_rate": 1.4486792194791478e-06, "loss": 0.0667, "step": 15967 }, { "epoch": 0.8818201899712834, "grad_norm": 6.812255859375, "learning_rate": 1.44734282165105e-06, "loss": 1.7523, "step": 15968 }, { "epoch": 0.8818754141815772, "grad_norm": 1.0313040018081665, "learning_rate": 1.4460070173752728e-06, "loss": 0.0318, "step": 15969 }, { "epoch": 0.881930638391871, "grad_norm": 1.808351755142212, "learning_rate": 1.4446718066945532e-06, "loss": 0.0283, "step": 15970 }, { "epoch": 0.8819858626021648, "grad_norm": 0.3001680076122284, "learning_rate": 1.443337189651608e-06, "loss": 0.0051, "step": 15971 }, { "epoch": 0.8820410868124586, "grad_norm": 2.850080728530884, "learning_rate": 1.4420031662891298e-06, "loss": 0.0708, "step": 15972 }, { "epoch": 0.8820963110227523, "grad_norm": 3.89947247505188, "learning_rate": 1.4406697366498112e-06, "loss": 0.5479, "step": 15973 }, { "epoch": 0.8821515352330461, "grad_norm": 0.3877802789211273, "learning_rate": 1.439336900776296e-06, "loss": 0.0059, "step": 15974 }, { "epoch": 0.8822067594433399, "grad_norm": 0.21047258377075195, "learning_rate": 1.4380046587112362e-06, "loss": 0.0049, "step": 15975 }, { "epoch": 0.8822619836536337, "grad_norm": 0.025677472352981567, "learning_rate": 1.4366730104972514e-06, "loss": 0.0005, "step": 15976 }, { "epoch": 0.8823172078639275, "grad_norm": 0.016278555616736412, "learning_rate": 1.4353419561769433e-06, "loss": 0.0006, "step": 15977 }, { "epoch": 0.8823724320742213, "grad_norm": 0.8388832807540894, "learning_rate": 1.4340114957928953e-06, "loss": 0.0155, "step": 15978 }, { "epoch": 0.8824276562845151, "grad_norm": 0.05123622342944145, "learning_rate": 1.4326816293876777e-06, "loss": 0.0011, "step": 15979 }, { "epoch": 0.8824828804948089, "grad_norm": 1.6447151899337769, "learning_rate": 1.4313523570038324e-06, "loss": 0.248, "step": 15980 }, { "epoch": 0.8825381047051027, "grad_norm": 0.16480369865894318, "learning_rate": 1.4300236786838895e-06, "loss": 0.005, "step": 15981 }, { "epoch": 0.8825933289153965, "grad_norm": 2.1236889362335205, "learning_rate": 1.4286955944703552e-06, "loss": 0.1527, "step": 15982 }, { "epoch": 0.8826485531256903, "grad_norm": 2.05342173576355, "learning_rate": 1.4273681044057197e-06, "loss": 0.0923, "step": 15983 }, { "epoch": 0.882703777335984, "grad_norm": 3.308462619781494, "learning_rate": 1.426041208532447e-06, "loss": 0.2692, "step": 15984 }, { "epoch": 0.8827590015462778, "grad_norm": 0.14906567335128784, "learning_rate": 1.4247149068929988e-06, "loss": 0.0035, "step": 15985 }, { "epoch": 0.8828142257565716, "grad_norm": 0.5481072068214417, "learning_rate": 1.423389199529801e-06, "loss": 0.0112, "step": 15986 }, { "epoch": 0.8828694499668654, "grad_norm": 0.12598289549350739, "learning_rate": 1.4220640864852686e-06, "loss": 0.0049, "step": 15987 }, { "epoch": 0.8829246741771593, "grad_norm": 2.4881632328033447, "learning_rate": 1.4207395678017921e-06, "loss": 0.0906, "step": 15988 }, { "epoch": 0.882979898387453, "grad_norm": 3.3458194732666016, "learning_rate": 1.4194156435217554e-06, "loss": 0.2491, "step": 15989 }, { "epoch": 0.8830351225977469, "grad_norm": 2.9514646530151367, "learning_rate": 1.4180923136875025e-06, "loss": 0.1237, "step": 15990 }, { "epoch": 0.8830903468080407, "grad_norm": 2.6416056156158447, "learning_rate": 1.4167695783413815e-06, "loss": 0.0788, "step": 15991 }, { "epoch": 0.8831455710183345, "grad_norm": 1.4494329690933228, "learning_rate": 1.4154474375257032e-06, "loss": 0.05, "step": 15992 }, { "epoch": 0.8832007952286283, "grad_norm": 4.614274501800537, "learning_rate": 1.4141258912827715e-06, "loss": 0.3819, "step": 15993 }, { "epoch": 0.8832560194389221, "grad_norm": 0.09272878617048264, "learning_rate": 1.4128049396548592e-06, "loss": 0.0021, "step": 15994 }, { "epoch": 0.8833112436492159, "grad_norm": 0.9734368324279785, "learning_rate": 1.4114845826842372e-06, "loss": 0.0327, "step": 15995 }, { "epoch": 0.8833664678595096, "grad_norm": 3.9541258811950684, "learning_rate": 1.4101648204131424e-06, "loss": 0.5049, "step": 15996 }, { "epoch": 0.8834216920698034, "grad_norm": 7.429755210876465, "learning_rate": 1.408845652883797e-06, "loss": 0.6158, "step": 15997 }, { "epoch": 0.8834769162800972, "grad_norm": 0.03083817847073078, "learning_rate": 1.4075270801384023e-06, "loss": 0.001, "step": 15998 }, { "epoch": 0.883532140490391, "grad_norm": 2.8783931732177734, "learning_rate": 1.4062091022191536e-06, "loss": 0.4968, "step": 15999 }, { "epoch": 0.8835873647006848, "grad_norm": 2.1414480209350586, "learning_rate": 1.4048917191682042e-06, "loss": 0.1272, "step": 16000 }, { "epoch": 0.8836425889109786, "grad_norm": 0.5286628007888794, "learning_rate": 1.4035749310277092e-06, "loss": 0.1107, "step": 16001 }, { "epoch": 0.8836978131212724, "grad_norm": 0.015286307781934738, "learning_rate": 1.4022587378397945e-06, "loss": 0.0004, "step": 16002 }, { "epoch": 0.8837530373315662, "grad_norm": 2.1727662086486816, "learning_rate": 1.4009431396465666e-06, "loss": 0.1368, "step": 16003 }, { "epoch": 0.88380826154186, "grad_norm": 6.822189807891846, "learning_rate": 1.3996281364901188e-06, "loss": 0.2114, "step": 16004 }, { "epoch": 0.8838634857521538, "grad_norm": 0.06330660730600357, "learning_rate": 1.3983137284125193e-06, "loss": 0.0014, "step": 16005 }, { "epoch": 0.8839187099624476, "grad_norm": 4.874567031860352, "learning_rate": 1.3969999154558189e-06, "loss": 1.2275, "step": 16006 }, { "epoch": 0.8839739341727413, "grad_norm": 4.251483917236328, "learning_rate": 1.3956866976620487e-06, "loss": 0.3259, "step": 16007 }, { "epoch": 0.8840291583830351, "grad_norm": 3.837458610534668, "learning_rate": 1.3943740750732305e-06, "loss": 0.2437, "step": 16008 }, { "epoch": 0.8840843825933289, "grad_norm": 5.124612331390381, "learning_rate": 1.3930620477313506e-06, "loss": 0.1701, "step": 16009 }, { "epoch": 0.8841396068036227, "grad_norm": 0.040475837886333466, "learning_rate": 1.391750615678389e-06, "loss": 0.001, "step": 16010 }, { "epoch": 0.8841948310139165, "grad_norm": 0.031065143644809723, "learning_rate": 1.3904397789562984e-06, "loss": 0.0006, "step": 16011 }, { "epoch": 0.8842500552242103, "grad_norm": 0.09321784973144531, "learning_rate": 1.3891295376070235e-06, "loss": 0.0024, "step": 16012 }, { "epoch": 0.8843052794345041, "grad_norm": 3.218409776687622, "learning_rate": 1.3878198916724706e-06, "loss": 0.7503, "step": 16013 }, { "epoch": 0.8843605036447979, "grad_norm": 3.781737804412842, "learning_rate": 1.3865108411945506e-06, "loss": 0.2467, "step": 16014 }, { "epoch": 0.8844157278550917, "grad_norm": 0.3540996313095093, "learning_rate": 1.3852023862151365e-06, "loss": 0.0096, "step": 16015 }, { "epoch": 0.8844709520653855, "grad_norm": 0.06414955109357834, "learning_rate": 1.383894526776095e-06, "loss": 0.0023, "step": 16016 }, { "epoch": 0.8845261762756793, "grad_norm": 0.021836822852492332, "learning_rate": 1.3825872629192593e-06, "loss": 0.0006, "step": 16017 }, { "epoch": 0.884581400485973, "grad_norm": 0.03628763556480408, "learning_rate": 1.3812805946864627e-06, "loss": 0.0006, "step": 16018 }, { "epoch": 0.8846366246962668, "grad_norm": 0.0707063302397728, "learning_rate": 1.379974522119505e-06, "loss": 0.0016, "step": 16019 }, { "epoch": 0.8846918489065606, "grad_norm": 0.014291760511696339, "learning_rate": 1.3786690452601726e-06, "loss": 0.0005, "step": 16020 }, { "epoch": 0.8847470731168544, "grad_norm": 1.4810582399368286, "learning_rate": 1.3773641641502255e-06, "loss": 0.0771, "step": 16021 }, { "epoch": 0.8848022973271482, "grad_norm": 0.016572557389736176, "learning_rate": 1.3760598788314217e-06, "loss": 0.0005, "step": 16022 }, { "epoch": 0.884857521537442, "grad_norm": 0.010580851696431637, "learning_rate": 1.3747561893454763e-06, "loss": 0.0002, "step": 16023 }, { "epoch": 0.8849127457477358, "grad_norm": 2.468219041824341, "learning_rate": 1.3734530957341074e-06, "loss": 0.4936, "step": 16024 }, { "epoch": 0.8849679699580296, "grad_norm": 4.954331874847412, "learning_rate": 1.3721505980390015e-06, "loss": 1.1992, "step": 16025 }, { "epoch": 0.8850231941683234, "grad_norm": 2.0403947830200195, "learning_rate": 1.3708486963018274e-06, "loss": 0.0899, "step": 16026 }, { "epoch": 0.8850784183786172, "grad_norm": 2.812525749206543, "learning_rate": 1.3695473905642365e-06, "loss": 0.3116, "step": 16027 }, { "epoch": 0.885133642588911, "grad_norm": 2.690269708633423, "learning_rate": 1.3682466808678708e-06, "loss": 0.0787, "step": 16028 }, { "epoch": 0.8851888667992047, "grad_norm": 0.5238648056983948, "learning_rate": 1.366946567254328e-06, "loss": 0.0083, "step": 16029 }, { "epoch": 0.8852440910094985, "grad_norm": 0.4227672517299652, "learning_rate": 1.365647049765213e-06, "loss": 0.0069, "step": 16030 }, { "epoch": 0.8852993152197923, "grad_norm": 4.962456703186035, "learning_rate": 1.364348128442099e-06, "loss": 1.3142, "step": 16031 }, { "epoch": 0.8853545394300861, "grad_norm": 0.0774211660027504, "learning_rate": 1.3630498033265437e-06, "loss": 0.0022, "step": 16032 }, { "epoch": 0.8854097636403799, "grad_norm": 0.029856521636247635, "learning_rate": 1.3617520744600766e-06, "loss": 0.0008, "step": 16033 }, { "epoch": 0.8854649878506737, "grad_norm": 0.08254934102296829, "learning_rate": 1.360454941884226e-06, "loss": 0.002, "step": 16034 }, { "epoch": 0.8855202120609675, "grad_norm": 0.12668152153491974, "learning_rate": 1.3591584056404861e-06, "loss": 0.0034, "step": 16035 }, { "epoch": 0.8855754362712613, "grad_norm": 2.84456205368042, "learning_rate": 1.3578624657703365e-06, "loss": 0.1946, "step": 16036 }, { "epoch": 0.8856306604815551, "grad_norm": 2.564218759536743, "learning_rate": 1.3565671223152354e-06, "loss": 0.4611, "step": 16037 }, { "epoch": 0.885685884691849, "grad_norm": 0.7538676857948303, "learning_rate": 1.355272375316632e-06, "loss": 0.0155, "step": 16038 }, { "epoch": 0.8857411089021427, "grad_norm": 0.011917341500520706, "learning_rate": 1.3539782248159416e-06, "loss": 0.0003, "step": 16039 }, { "epoch": 0.8857963331124364, "grad_norm": 0.023416610434651375, "learning_rate": 1.3526846708545716e-06, "loss": 0.0005, "step": 16040 }, { "epoch": 0.8858515573227302, "grad_norm": 7.0896148681640625, "learning_rate": 1.3513917134739063e-06, "loss": 0.6181, "step": 16041 }, { "epoch": 0.885906781533024, "grad_norm": 0.02120060846209526, "learning_rate": 1.3500993527153106e-06, "loss": 0.0007, "step": 16042 }, { "epoch": 0.8859620057433178, "grad_norm": 0.4725598096847534, "learning_rate": 1.348807588620127e-06, "loss": 0.009, "step": 16043 }, { "epoch": 0.8860172299536117, "grad_norm": 2.581118106842041, "learning_rate": 1.347516421229691e-06, "loss": 0.2087, "step": 16044 }, { "epoch": 0.8860724541639055, "grad_norm": 0.5345011949539185, "learning_rate": 1.346225850585301e-06, "loss": 0.0084, "step": 16045 }, { "epoch": 0.8861276783741993, "grad_norm": 0.39507704973220825, "learning_rate": 1.344935876728255e-06, "loss": 0.0101, "step": 16046 }, { "epoch": 0.8861829025844931, "grad_norm": 3.460759401321411, "learning_rate": 1.3436464996998177e-06, "loss": 0.9472, "step": 16047 }, { "epoch": 0.8862381267947869, "grad_norm": 3.6180784702301025, "learning_rate": 1.342357719541243e-06, "loss": 0.2727, "step": 16048 }, { "epoch": 0.8862933510050807, "grad_norm": 5.468914985656738, "learning_rate": 1.3410695362937555e-06, "loss": 1.8364, "step": 16049 }, { "epoch": 0.8863485752153745, "grad_norm": 0.2630152702331543, "learning_rate": 1.3397819499985776e-06, "loss": 0.0075, "step": 16050 }, { "epoch": 0.8864037994256682, "grad_norm": 2.9952642917633057, "learning_rate": 1.3384949606968967e-06, "loss": 0.3083, "step": 16051 }, { "epoch": 0.886459023635962, "grad_norm": 4.576406478881836, "learning_rate": 1.3372085684298909e-06, "loss": 0.4856, "step": 16052 }, { "epoch": 0.8865142478462558, "grad_norm": 0.029507508501410484, "learning_rate": 1.3359227732387093e-06, "loss": 0.0011, "step": 16053 }, { "epoch": 0.8865694720565496, "grad_norm": 0.4513685405254364, "learning_rate": 1.334637575164499e-06, "loss": 0.0131, "step": 16054 }, { "epoch": 0.8866246962668434, "grad_norm": 0.055549781769514084, "learning_rate": 1.3333529742483652e-06, "loss": 0.0018, "step": 16055 }, { "epoch": 0.8866799204771372, "grad_norm": 3.6311488151550293, "learning_rate": 1.3320689705314128e-06, "loss": 0.1464, "step": 16056 }, { "epoch": 0.886735144687431, "grad_norm": 0.26045680046081543, "learning_rate": 1.3307855640547196e-06, "loss": 0.0063, "step": 16057 }, { "epoch": 0.8867903688977248, "grad_norm": 4.359543323516846, "learning_rate": 1.3295027548593464e-06, "loss": 0.6437, "step": 16058 }, { "epoch": 0.8868455931080186, "grad_norm": 2.051074266433716, "learning_rate": 1.3282205429863292e-06, "loss": 0.0403, "step": 16059 }, { "epoch": 0.8869008173183124, "grad_norm": 2.298400402069092, "learning_rate": 1.3269389284766955e-06, "loss": 0.1436, "step": 16060 }, { "epoch": 0.8869560415286062, "grad_norm": 4.681155681610107, "learning_rate": 1.325657911371445e-06, "loss": 0.0739, "step": 16061 }, { "epoch": 0.8870112657388999, "grad_norm": 2.1856141090393066, "learning_rate": 1.3243774917115614e-06, "loss": 0.0619, "step": 16062 }, { "epoch": 0.8870664899491937, "grad_norm": 1.8701547384262085, "learning_rate": 1.3230976695380093e-06, "loss": 0.0681, "step": 16063 }, { "epoch": 0.8871217141594875, "grad_norm": 1.127651333808899, "learning_rate": 1.321818444891736e-06, "loss": 0.0491, "step": 16064 }, { "epoch": 0.8871769383697813, "grad_norm": 5.8948187828063965, "learning_rate": 1.320539817813662e-06, "loss": 0.2756, "step": 16065 }, { "epoch": 0.8872321625800751, "grad_norm": 0.02922763116657734, "learning_rate": 1.3192617883446944e-06, "loss": 0.0006, "step": 16066 }, { "epoch": 0.8872873867903689, "grad_norm": 0.6716687679290771, "learning_rate": 1.3179843565257323e-06, "loss": 0.0226, "step": 16067 }, { "epoch": 0.8873426110006627, "grad_norm": 0.12093164771795273, "learning_rate": 1.3167075223976267e-06, "loss": 0.0031, "step": 16068 }, { "epoch": 0.8873978352109565, "grad_norm": 6.639426231384277, "learning_rate": 1.3154312860012408e-06, "loss": 1.0879, "step": 16069 }, { "epoch": 0.8874530594212503, "grad_norm": 0.04437379166483879, "learning_rate": 1.3141556473774019e-06, "loss": 0.0015, "step": 16070 }, { "epoch": 0.8875082836315441, "grad_norm": 4.219102382659912, "learning_rate": 1.3128806065669176e-06, "loss": 1.0245, "step": 16071 }, { "epoch": 0.8875635078418379, "grad_norm": 0.6846582293510437, "learning_rate": 1.3116061636105815e-06, "loss": 0.1259, "step": 16072 }, { "epoch": 0.8876187320521317, "grad_norm": 3.272629976272583, "learning_rate": 1.31033231854917e-06, "loss": 0.377, "step": 16073 }, { "epoch": 0.8876739562624254, "grad_norm": 4.014062881469727, "learning_rate": 1.3090590714234353e-06, "loss": 0.1717, "step": 16074 }, { "epoch": 0.8877291804727192, "grad_norm": 4.003773212432861, "learning_rate": 1.307786422274111e-06, "loss": 0.7574, "step": 16075 }, { "epoch": 0.887784404683013, "grad_norm": 1.3934273719787598, "learning_rate": 1.3065143711419115e-06, "loss": 0.0358, "step": 16076 }, { "epoch": 0.8878396288933068, "grad_norm": 0.4459131360054016, "learning_rate": 1.3052429180675397e-06, "loss": 0.0092, "step": 16077 }, { "epoch": 0.8878948531036006, "grad_norm": 0.13679231703281403, "learning_rate": 1.3039720630916652e-06, "loss": 0.0042, "step": 16078 }, { "epoch": 0.8879500773138944, "grad_norm": 0.02411922812461853, "learning_rate": 1.3027018062549491e-06, "loss": 0.0006, "step": 16079 }, { "epoch": 0.8880053015241882, "grad_norm": 0.0761813223361969, "learning_rate": 1.301432147598034e-06, "loss": 0.0025, "step": 16080 }, { "epoch": 0.888060525734482, "grad_norm": 0.027328897267580032, "learning_rate": 1.3001630871615346e-06, "loss": 0.001, "step": 16081 }, { "epoch": 0.8881157499447758, "grad_norm": 5.479846954345703, "learning_rate": 1.2988946249860534e-06, "loss": 0.6129, "step": 16082 }, { "epoch": 0.8881709741550696, "grad_norm": 0.05583685636520386, "learning_rate": 1.2976267611121784e-06, "loss": 0.001, "step": 16083 }, { "epoch": 0.8882261983653634, "grad_norm": 0.010681001469492912, "learning_rate": 1.2963594955804593e-06, "loss": 0.0003, "step": 16084 }, { "epoch": 0.8882814225756571, "grad_norm": 5.020613670349121, "learning_rate": 1.2950928284314501e-06, "loss": 0.638, "step": 16085 }, { "epoch": 0.8883366467859509, "grad_norm": 0.12137355655431747, "learning_rate": 1.293826759705672e-06, "loss": 0.0025, "step": 16086 }, { "epoch": 0.8883918709962447, "grad_norm": 1.178433895111084, "learning_rate": 1.2925612894436301e-06, "loss": 0.1277, "step": 16087 }, { "epoch": 0.8884470952065385, "grad_norm": 0.1588710993528366, "learning_rate": 1.291296417685808e-06, "loss": 0.0034, "step": 16088 }, { "epoch": 0.8885023194168323, "grad_norm": 2.1880931854248047, "learning_rate": 1.290032144472677e-06, "loss": 0.1851, "step": 16089 }, { "epoch": 0.8885575436271261, "grad_norm": 0.07610568404197693, "learning_rate": 1.2887684698446834e-06, "loss": 0.0026, "step": 16090 }, { "epoch": 0.8886127678374199, "grad_norm": 0.8952606916427612, "learning_rate": 1.2875053938422543e-06, "loss": 0.0099, "step": 16091 }, { "epoch": 0.8886679920477137, "grad_norm": 2.3544111251831055, "learning_rate": 1.2862429165057955e-06, "loss": 0.3067, "step": 16092 }, { "epoch": 0.8887232162580075, "grad_norm": 2.455811023712158, "learning_rate": 1.28498103787571e-06, "loss": 0.0295, "step": 16093 }, { "epoch": 0.8887784404683013, "grad_norm": 3.314795732498169, "learning_rate": 1.2837197579923521e-06, "loss": 0.0882, "step": 16094 }, { "epoch": 0.8888336646785951, "grad_norm": 3.5512614250183105, "learning_rate": 1.2824590768960855e-06, "loss": 0.6378, "step": 16095 }, { "epoch": 0.8888888888888888, "grad_norm": 0.06351849436759949, "learning_rate": 1.281198994627242e-06, "loss": 0.0013, "step": 16096 }, { "epoch": 0.8889441130991826, "grad_norm": 0.024861624464392662, "learning_rate": 1.2799395112261293e-06, "loss": 0.0006, "step": 16097 }, { "epoch": 0.8889993373094764, "grad_norm": 0.23294851183891296, "learning_rate": 1.2786806267330443e-06, "loss": 0.0048, "step": 16098 }, { "epoch": 0.8890545615197702, "grad_norm": 2.39852237701416, "learning_rate": 1.2774223411882659e-06, "loss": 0.3785, "step": 16099 }, { "epoch": 0.889109785730064, "grad_norm": 2.4473557472229004, "learning_rate": 1.2761646546320482e-06, "loss": 0.1493, "step": 16100 }, { "epoch": 0.8891650099403579, "grad_norm": 0.06853937357664108, "learning_rate": 1.2749075671046262e-06, "loss": 0.0011, "step": 16101 }, { "epoch": 0.8892202341506517, "grad_norm": 0.1022481769323349, "learning_rate": 1.2736510786462186e-06, "loss": 0.0022, "step": 16102 }, { "epoch": 0.8892754583609455, "grad_norm": 0.06545064598321915, "learning_rate": 1.2723951892970266e-06, "loss": 0.0017, "step": 16103 }, { "epoch": 0.8893306825712393, "grad_norm": 0.23301871120929718, "learning_rate": 1.2711398990972245e-06, "loss": 0.0052, "step": 16104 }, { "epoch": 0.8893859067815331, "grad_norm": 0.005887272767722607, "learning_rate": 1.2698852080869782e-06, "loss": 0.0002, "step": 16105 }, { "epoch": 0.8894411309918269, "grad_norm": 3.071089506149292, "learning_rate": 1.2686311163064246e-06, "loss": 0.1663, "step": 16106 }, { "epoch": 0.8894963552021206, "grad_norm": 3.9688942432403564, "learning_rate": 1.2673776237956892e-06, "loss": 0.3556, "step": 16107 }, { "epoch": 0.8895515794124144, "grad_norm": 0.005681045353412628, "learning_rate": 1.266124730594871e-06, "loss": 0.0002, "step": 16108 }, { "epoch": 0.8896068036227082, "grad_norm": 0.02418433129787445, "learning_rate": 1.2648724367440601e-06, "loss": 0.0007, "step": 16109 }, { "epoch": 0.889662027833002, "grad_norm": 7.050334930419922, "learning_rate": 1.2636207422833113e-06, "loss": 0.177, "step": 16110 }, { "epoch": 0.8897172520432958, "grad_norm": 0.7642968893051147, "learning_rate": 1.262369647252677e-06, "loss": 0.024, "step": 16111 }, { "epoch": 0.8897724762535896, "grad_norm": 0.11029510945081711, "learning_rate": 1.2611191516921828e-06, "loss": 0.0031, "step": 16112 }, { "epoch": 0.8898277004638834, "grad_norm": 0.7025147676467896, "learning_rate": 1.2598692556418324e-06, "loss": 0.0119, "step": 16113 }, { "epoch": 0.8898829246741772, "grad_norm": 6.325240135192871, "learning_rate": 1.2586199591416137e-06, "loss": 0.271, "step": 16114 }, { "epoch": 0.889938148884471, "grad_norm": 0.031012143939733505, "learning_rate": 1.2573712622314994e-06, "loss": 0.0009, "step": 16115 }, { "epoch": 0.8899933730947648, "grad_norm": 1.1111093759536743, "learning_rate": 1.256123164951435e-06, "loss": 0.0518, "step": 16116 }, { "epoch": 0.8900485973050586, "grad_norm": 0.005994176957756281, "learning_rate": 1.2548756673413553e-06, "loss": 0.0001, "step": 16117 }, { "epoch": 0.8901038215153523, "grad_norm": 2.1556966304779053, "learning_rate": 1.2536287694411619e-06, "loss": 0.4086, "step": 16118 }, { "epoch": 0.8901590457256461, "grad_norm": 0.010428556241095066, "learning_rate": 1.2523824712907607e-06, "loss": 0.0003, "step": 16119 }, { "epoch": 0.8902142699359399, "grad_norm": 0.5906170010566711, "learning_rate": 1.2511367729300083e-06, "loss": 0.0082, "step": 16120 }, { "epoch": 0.8902694941462337, "grad_norm": 0.0569719634950161, "learning_rate": 1.249891674398771e-06, "loss": 0.0016, "step": 16121 }, { "epoch": 0.8903247183565275, "grad_norm": 0.1339815855026245, "learning_rate": 1.2486471757368769e-06, "loss": 0.0018, "step": 16122 }, { "epoch": 0.8903799425668213, "grad_norm": 0.061242472380399704, "learning_rate": 1.2474032769841427e-06, "loss": 0.0019, "step": 16123 }, { "epoch": 0.8904351667771151, "grad_norm": 3.0472512245178223, "learning_rate": 1.2461599781803656e-06, "loss": 0.3476, "step": 16124 }, { "epoch": 0.8904903909874089, "grad_norm": 4.789823055267334, "learning_rate": 1.2449172793653186e-06, "loss": 1.0843, "step": 16125 }, { "epoch": 0.8905456151977027, "grad_norm": 4.156008720397949, "learning_rate": 1.2436751805787628e-06, "loss": 0.4256, "step": 16126 }, { "epoch": 0.8906008394079965, "grad_norm": 0.26354774832725525, "learning_rate": 1.242433681860431e-06, "loss": 0.0056, "step": 16127 }, { "epoch": 0.8906560636182903, "grad_norm": 0.03234162554144859, "learning_rate": 1.2411927832500493e-06, "loss": 0.0009, "step": 16128 }, { "epoch": 0.890711287828584, "grad_norm": 5.068938255310059, "learning_rate": 1.2399524847873122e-06, "loss": 0.5797, "step": 16129 }, { "epoch": 0.8907665120388778, "grad_norm": 2.0507256984710693, "learning_rate": 1.2387127865119064e-06, "loss": 0.0461, "step": 16130 }, { "epoch": 0.8908217362491716, "grad_norm": 0.07314687967300415, "learning_rate": 1.2374736884634842e-06, "loss": 0.0022, "step": 16131 }, { "epoch": 0.8908769604594654, "grad_norm": 0.9493822455406189, "learning_rate": 1.2362351906817005e-06, "loss": 0.0176, "step": 16132 }, { "epoch": 0.8909321846697592, "grad_norm": 0.07752565294504166, "learning_rate": 1.2349972932061639e-06, "loss": 0.0015, "step": 16133 }, { "epoch": 0.890987408880053, "grad_norm": 0.6105020642280579, "learning_rate": 1.233759996076489e-06, "loss": 0.0096, "step": 16134 }, { "epoch": 0.8910426330903468, "grad_norm": 1.5668617486953735, "learning_rate": 1.2325232993322578e-06, "loss": 0.0323, "step": 16135 }, { "epoch": 0.8910978573006406, "grad_norm": 1.600075364112854, "learning_rate": 1.231287203013034e-06, "loss": 0.0761, "step": 16136 }, { "epoch": 0.8911530815109344, "grad_norm": 0.06359536945819855, "learning_rate": 1.2300517071583618e-06, "loss": 0.0018, "step": 16137 }, { "epoch": 0.8912083057212282, "grad_norm": 9.523956298828125, "learning_rate": 1.2288168118077737e-06, "loss": 0.4514, "step": 16138 }, { "epoch": 0.891263529931522, "grad_norm": 0.008944373577833176, "learning_rate": 1.227582517000776e-06, "loss": 0.0002, "step": 16139 }, { "epoch": 0.8913187541418157, "grad_norm": 3.1808648109436035, "learning_rate": 1.2263488227768549e-06, "loss": 0.3882, "step": 16140 }, { "epoch": 0.8913739783521095, "grad_norm": 0.347400039434433, "learning_rate": 1.2251157291754789e-06, "loss": 0.0097, "step": 16141 }, { "epoch": 0.8914292025624033, "grad_norm": 0.3561875820159912, "learning_rate": 1.2238832362361075e-06, "loss": 0.0058, "step": 16142 }, { "epoch": 0.8914844267726971, "grad_norm": 0.232528954744339, "learning_rate": 1.222651343998158e-06, "loss": 0.0029, "step": 16143 }, { "epoch": 0.8915396509829909, "grad_norm": 0.017729438841342926, "learning_rate": 1.22142005250105e-06, "loss": 0.0004, "step": 16144 }, { "epoch": 0.8915948751932847, "grad_norm": 0.1421961635351181, "learning_rate": 1.2201893617841764e-06, "loss": 0.0046, "step": 16145 }, { "epoch": 0.8916500994035785, "grad_norm": 1.8044945001602173, "learning_rate": 1.2189592718869081e-06, "loss": 0.0561, "step": 16146 }, { "epoch": 0.8917053236138723, "grad_norm": 3.8245978355407715, "learning_rate": 1.2177297828485979e-06, "loss": 0.14, "step": 16147 }, { "epoch": 0.8917605478241661, "grad_norm": 0.6530457139015198, "learning_rate": 1.2165008947085877e-06, "loss": 0.0064, "step": 16148 }, { "epoch": 0.8918157720344599, "grad_norm": 0.07451256364583969, "learning_rate": 1.2152726075061838e-06, "loss": 0.0021, "step": 16149 }, { "epoch": 0.8918709962447537, "grad_norm": 0.15591834485530853, "learning_rate": 1.2140449212806882e-06, "loss": 0.0042, "step": 16150 }, { "epoch": 0.8919262204550475, "grad_norm": 0.020000049844384193, "learning_rate": 1.2128178360713782e-06, "loss": 0.0005, "step": 16151 }, { "epoch": 0.8919814446653412, "grad_norm": 2.941480875015259, "learning_rate": 1.2115913519175093e-06, "loss": 0.3997, "step": 16152 }, { "epoch": 0.892036668875635, "grad_norm": 0.1676035225391388, "learning_rate": 1.2103654688583188e-06, "loss": 0.0051, "step": 16153 }, { "epoch": 0.8920918930859288, "grad_norm": 0.025406815111637115, "learning_rate": 1.209140186933031e-06, "loss": 0.0006, "step": 16154 }, { "epoch": 0.8921471172962226, "grad_norm": 2.806997299194336, "learning_rate": 1.2079155061808435e-06, "loss": 0.3117, "step": 16155 }, { "epoch": 0.8922023415065164, "grad_norm": 0.22223640978336334, "learning_rate": 1.2066914266409401e-06, "loss": 0.0066, "step": 16156 }, { "epoch": 0.8922575657168103, "grad_norm": 0.042725931853055954, "learning_rate": 1.2054679483524745e-06, "loss": 0.001, "step": 16157 }, { "epoch": 0.892312789927104, "grad_norm": 0.022965066134929657, "learning_rate": 1.2042450713546016e-06, "loss": 0.0005, "step": 16158 }, { "epoch": 0.8923680141373979, "grad_norm": 0.2607366144657135, "learning_rate": 1.2030227956864327e-06, "loss": 0.0075, "step": 16159 }, { "epoch": 0.8924232383476917, "grad_norm": 0.3197455108165741, "learning_rate": 1.2018011213870805e-06, "loss": 0.0048, "step": 16160 }, { "epoch": 0.8924784625579855, "grad_norm": 0.14738532900810242, "learning_rate": 1.2005800484956253e-06, "loss": 0.0054, "step": 16161 }, { "epoch": 0.8925336867682793, "grad_norm": 0.04023997113108635, "learning_rate": 1.1993595770511334e-06, "loss": 0.001, "step": 16162 }, { "epoch": 0.892588910978573, "grad_norm": 5.221783638000488, "learning_rate": 1.1981397070926514e-06, "loss": 1.7823, "step": 16163 }, { "epoch": 0.8926441351888668, "grad_norm": 0.0153011130169034, "learning_rate": 1.1969204386592103e-06, "loss": 0.0004, "step": 16164 }, { "epoch": 0.8926993593991606, "grad_norm": 0.10482028126716614, "learning_rate": 1.1957017717898078e-06, "loss": 0.0021, "step": 16165 }, { "epoch": 0.8927545836094544, "grad_norm": 0.05533656105399132, "learning_rate": 1.1944837065234438e-06, "loss": 0.0022, "step": 16166 }, { "epoch": 0.8928098078197482, "grad_norm": 0.05474155768752098, "learning_rate": 1.1932662428990827e-06, "loss": 0.0017, "step": 16167 }, { "epoch": 0.892865032030042, "grad_norm": 2.6153063774108887, "learning_rate": 1.1920493809556755e-06, "loss": 0.1388, "step": 16168 }, { "epoch": 0.8929202562403358, "grad_norm": 0.25348588824272156, "learning_rate": 1.1908331207321488e-06, "loss": 0.0079, "step": 16169 }, { "epoch": 0.8929754804506296, "grad_norm": 3.706411123275757, "learning_rate": 1.1896174622674206e-06, "loss": 0.2149, "step": 16170 }, { "epoch": 0.8930307046609234, "grad_norm": 0.06492628157138824, "learning_rate": 1.1884024056003796e-06, "loss": 0.0015, "step": 16171 }, { "epoch": 0.8930859288712172, "grad_norm": 6.381526470184326, "learning_rate": 1.1871879507699014e-06, "loss": 0.6612, "step": 16172 }, { "epoch": 0.893141153081511, "grad_norm": 7.201963424682617, "learning_rate": 1.1859740978148348e-06, "loss": 1.2164, "step": 16173 }, { "epoch": 0.8931963772918047, "grad_norm": 4.403562068939209, "learning_rate": 1.1847608467740246e-06, "loss": 1.1511, "step": 16174 }, { "epoch": 0.8932516015020985, "grad_norm": 2.795557975769043, "learning_rate": 1.1835481976862729e-06, "loss": 0.0649, "step": 16175 }, { "epoch": 0.8933068257123923, "grad_norm": 3.3585214614868164, "learning_rate": 1.1823361505903864e-06, "loss": 0.6044, "step": 16176 }, { "epoch": 0.8933620499226861, "grad_norm": 0.9998813271522522, "learning_rate": 1.1811247055251362e-06, "loss": 0.0258, "step": 16177 }, { "epoch": 0.8934172741329799, "grad_norm": 0.4147624373435974, "learning_rate": 1.1799138625292827e-06, "loss": 0.0082, "step": 16178 }, { "epoch": 0.8934724983432737, "grad_norm": 1.331566333770752, "learning_rate": 1.1787036216415592e-06, "loss": 0.0441, "step": 16179 }, { "epoch": 0.8935277225535675, "grad_norm": 0.14649784564971924, "learning_rate": 1.1774939829006926e-06, "loss": 0.0046, "step": 16180 }, { "epoch": 0.8935829467638613, "grad_norm": 0.20681142807006836, "learning_rate": 1.1762849463453784e-06, "loss": 0.0039, "step": 16181 }, { "epoch": 0.8936381709741551, "grad_norm": 3.6657397747039795, "learning_rate": 1.1750765120142993e-06, "loss": 0.7802, "step": 16182 }, { "epoch": 0.8936933951844489, "grad_norm": 0.0273605827242136, "learning_rate": 1.173868679946113e-06, "loss": 0.0007, "step": 16183 }, { "epoch": 0.8937486193947427, "grad_norm": 0.05171392112970352, "learning_rate": 1.172661450179462e-06, "loss": 0.001, "step": 16184 }, { "epoch": 0.8938038436050364, "grad_norm": 1.2066303491592407, "learning_rate": 1.1714548227529733e-06, "loss": 0.0273, "step": 16185 }, { "epoch": 0.8938590678153302, "grad_norm": 1.798356056213379, "learning_rate": 1.1702487977052423e-06, "loss": 0.0807, "step": 16186 }, { "epoch": 0.893914292025624, "grad_norm": 3.5654754638671875, "learning_rate": 1.1690433750748653e-06, "loss": 0.7463, "step": 16187 }, { "epoch": 0.8939695162359178, "grad_norm": 3.354384422302246, "learning_rate": 1.1678385549003934e-06, "loss": 0.47, "step": 16188 }, { "epoch": 0.8940247404462116, "grad_norm": 0.8242765069007874, "learning_rate": 1.1666343372203803e-06, "loss": 0.0045, "step": 16189 }, { "epoch": 0.8940799646565054, "grad_norm": 1.349865198135376, "learning_rate": 1.165430722073353e-06, "loss": 0.0556, "step": 16190 }, { "epoch": 0.8941351888667992, "grad_norm": 3.7161779403686523, "learning_rate": 1.1642277094978161e-06, "loss": 0.6901, "step": 16191 }, { "epoch": 0.894190413077093, "grad_norm": 0.33842501044273376, "learning_rate": 1.1630252995322544e-06, "loss": 0.0074, "step": 16192 }, { "epoch": 0.8942456372873868, "grad_norm": 3.686521530151367, "learning_rate": 1.161823492215144e-06, "loss": 0.2954, "step": 16193 }, { "epoch": 0.8943008614976806, "grad_norm": 0.038640983402729034, "learning_rate": 1.1606222875849294e-06, "loss": 0.0012, "step": 16194 }, { "epoch": 0.8943560857079744, "grad_norm": 0.1077202782034874, "learning_rate": 1.1594216856800422e-06, "loss": 0.0032, "step": 16195 }, { "epoch": 0.8944113099182681, "grad_norm": 0.018011372536420822, "learning_rate": 1.1582216865388873e-06, "loss": 0.0005, "step": 16196 }, { "epoch": 0.8944665341285619, "grad_norm": 3.7420952320098877, "learning_rate": 1.1570222901998672e-06, "loss": 0.248, "step": 16197 }, { "epoch": 0.8945217583388557, "grad_norm": 0.16747994720935822, "learning_rate": 1.1558234967013426e-06, "loss": 0.0044, "step": 16198 }, { "epoch": 0.8945769825491495, "grad_norm": 0.030483819544315338, "learning_rate": 1.1546253060816737e-06, "loss": 0.0007, "step": 16199 }, { "epoch": 0.8946322067594433, "grad_norm": 0.19423379004001617, "learning_rate": 1.1534277183791898e-06, "loss": 0.0042, "step": 16200 }, { "epoch": 0.8946874309697371, "grad_norm": 4.196177959442139, "learning_rate": 1.1522307336322092e-06, "loss": 0.6568, "step": 16201 }, { "epoch": 0.8947426551800309, "grad_norm": 0.019099406898021698, "learning_rate": 1.1510343518790212e-06, "loss": 0.0005, "step": 16202 }, { "epoch": 0.8947978793903247, "grad_norm": 0.17871302366256714, "learning_rate": 1.149838573157911e-06, "loss": 0.004, "step": 16203 }, { "epoch": 0.8948531036006185, "grad_norm": 0.01695052906870842, "learning_rate": 1.1486433975071232e-06, "loss": 0.0003, "step": 16204 }, { "epoch": 0.8949083278109123, "grad_norm": 2.190530300140381, "learning_rate": 1.147448824964903e-06, "loss": 0.3961, "step": 16205 }, { "epoch": 0.8949635520212061, "grad_norm": 0.03619153052568436, "learning_rate": 1.1462548555694664e-06, "loss": 0.0011, "step": 16206 }, { "epoch": 0.8950187762314998, "grad_norm": 2.023465156555176, "learning_rate": 1.1450614893590094e-06, "loss": 0.1899, "step": 16207 }, { "epoch": 0.8950740004417936, "grad_norm": 2.008202075958252, "learning_rate": 1.1438687263717107e-06, "loss": 0.2178, "step": 16208 }, { "epoch": 0.8951292246520874, "grad_norm": 0.06383015960454941, "learning_rate": 1.1426765666457373e-06, "loss": 0.002, "step": 16209 }, { "epoch": 0.8951844488623812, "grad_norm": 0.808876097202301, "learning_rate": 1.1414850102192232e-06, "loss": 0.0147, "step": 16210 }, { "epoch": 0.895239673072675, "grad_norm": 0.2342706322669983, "learning_rate": 1.140294057130291e-06, "loss": 0.0061, "step": 16211 }, { "epoch": 0.8952948972829688, "grad_norm": 3.832059383392334, "learning_rate": 1.139103707417042e-06, "loss": 0.0972, "step": 16212 }, { "epoch": 0.8953501214932627, "grad_norm": 0.11349114775657654, "learning_rate": 1.1379139611175649e-06, "loss": 0.0024, "step": 16213 }, { "epoch": 0.8954053457035565, "grad_norm": 0.10472790151834488, "learning_rate": 1.136724818269912e-06, "loss": 0.0031, "step": 16214 }, { "epoch": 0.8954605699138503, "grad_norm": 0.03476206958293915, "learning_rate": 1.1355362789121372e-06, "loss": 0.0006, "step": 16215 }, { "epoch": 0.8955157941241441, "grad_norm": 7.420257091522217, "learning_rate": 1.134348343082261e-06, "loss": 0.8176, "step": 16216 }, { "epoch": 0.8955710183344379, "grad_norm": 6.047230243682861, "learning_rate": 1.133161010818289e-06, "loss": 1.1355, "step": 16217 }, { "epoch": 0.8956262425447317, "grad_norm": 4.503563404083252, "learning_rate": 1.1319742821582059e-06, "loss": 1.0024, "step": 16218 }, { "epoch": 0.8956814667550254, "grad_norm": 5.119205474853516, "learning_rate": 1.1307881571399815e-06, "loss": 0.8972, "step": 16219 }, { "epoch": 0.8957366909653192, "grad_norm": 1.7615914344787598, "learning_rate": 1.1296026358015656e-06, "loss": 0.0449, "step": 16220 }, { "epoch": 0.895791915175613, "grad_norm": 0.014671971090137959, "learning_rate": 1.1284177181808809e-06, "loss": 0.0005, "step": 16221 }, { "epoch": 0.8958471393859068, "grad_norm": 0.02069723792374134, "learning_rate": 1.1272334043158372e-06, "loss": 0.0006, "step": 16222 }, { "epoch": 0.8959023635962006, "grad_norm": 3.6136293411254883, "learning_rate": 1.1260496942443266e-06, "loss": 0.1153, "step": 16223 }, { "epoch": 0.8959575878064944, "grad_norm": 0.02043377421796322, "learning_rate": 1.1248665880042141e-06, "loss": 0.0006, "step": 16224 }, { "epoch": 0.8960128120167882, "grad_norm": 0.012177910655736923, "learning_rate": 1.1236840856333586e-06, "loss": 0.0002, "step": 16225 }, { "epoch": 0.896068036227082, "grad_norm": 0.04640500992536545, "learning_rate": 1.1225021871695896e-06, "loss": 0.0011, "step": 16226 }, { "epoch": 0.8961232604373758, "grad_norm": 0.09620560705661774, "learning_rate": 1.1213208926507146e-06, "loss": 0.0028, "step": 16227 }, { "epoch": 0.8961784846476696, "grad_norm": 4.94399881362915, "learning_rate": 1.120140202114528e-06, "loss": 0.2129, "step": 16228 }, { "epoch": 0.8962337088579634, "grad_norm": 2.549867630004883, "learning_rate": 1.1189601155988083e-06, "loss": 0.0684, "step": 16229 }, { "epoch": 0.8962889330682571, "grad_norm": 0.0946439802646637, "learning_rate": 1.1177806331413032e-06, "loss": 0.0019, "step": 16230 }, { "epoch": 0.8963441572785509, "grad_norm": 0.037925586104393005, "learning_rate": 1.1166017547797536e-06, "loss": 0.0007, "step": 16231 }, { "epoch": 0.8963993814888447, "grad_norm": 0.028789835050702095, "learning_rate": 1.1154234805518716e-06, "loss": 0.0008, "step": 16232 }, { "epoch": 0.8964546056991385, "grad_norm": 2.098527431488037, "learning_rate": 1.1142458104953557e-06, "loss": 0.1728, "step": 16233 }, { "epoch": 0.8965098299094323, "grad_norm": 3.748687744140625, "learning_rate": 1.1130687446478761e-06, "loss": 0.8494, "step": 16234 }, { "epoch": 0.8965650541197261, "grad_norm": 2.3505396842956543, "learning_rate": 1.1118922830471024e-06, "loss": 0.1338, "step": 16235 }, { "epoch": 0.8966202783300199, "grad_norm": 0.0987212061882019, "learning_rate": 1.1107164257306646e-06, "loss": 0.0029, "step": 16236 }, { "epoch": 0.8966755025403137, "grad_norm": 0.1652933657169342, "learning_rate": 1.1095411727361838e-06, "loss": 0.0042, "step": 16237 }, { "epoch": 0.8967307267506075, "grad_norm": 0.053024716675281525, "learning_rate": 1.1083665241012564e-06, "loss": 0.0015, "step": 16238 }, { "epoch": 0.8967859509609013, "grad_norm": 1.9910993576049805, "learning_rate": 1.1071924798634725e-06, "loss": 0.019, "step": 16239 }, { "epoch": 0.8968411751711951, "grad_norm": 0.04250779002904892, "learning_rate": 1.1060190400603821e-06, "loss": 0.0013, "step": 16240 }, { "epoch": 0.8968963993814888, "grad_norm": 0.24129940569400787, "learning_rate": 1.1048462047295328e-06, "loss": 0.009, "step": 16241 }, { "epoch": 0.8969516235917826, "grad_norm": 0.014359519816935062, "learning_rate": 1.1036739739084456e-06, "loss": 0.0003, "step": 16242 }, { "epoch": 0.8970068478020764, "grad_norm": 0.8422724008560181, "learning_rate": 1.1025023476346242e-06, "loss": 0.0205, "step": 16243 }, { "epoch": 0.8970620720123702, "grad_norm": 0.7891147136688232, "learning_rate": 1.1013313259455494e-06, "loss": 0.015, "step": 16244 }, { "epoch": 0.897117296222664, "grad_norm": 0.10507794469594955, "learning_rate": 1.100160908878689e-06, "loss": 0.002, "step": 16245 }, { "epoch": 0.8971725204329578, "grad_norm": 0.04663974791765213, "learning_rate": 1.0989910964714868e-06, "loss": 0.0008, "step": 16246 }, { "epoch": 0.8972277446432516, "grad_norm": 0.01576894521713257, "learning_rate": 1.0978218887613656e-06, "loss": 0.0005, "step": 16247 }, { "epoch": 0.8972829688535454, "grad_norm": 2.9373233318328857, "learning_rate": 1.096653285785736e-06, "loss": 0.2661, "step": 16248 }, { "epoch": 0.8973381930638392, "grad_norm": 1.3184840679168701, "learning_rate": 1.0954852875819856e-06, "loss": 0.0595, "step": 16249 }, { "epoch": 0.897393417274133, "grad_norm": 2.5180065631866455, "learning_rate": 1.0943178941874778e-06, "loss": 0.11, "step": 16250 }, { "epoch": 0.8974486414844268, "grad_norm": 3.947551727294922, "learning_rate": 1.0931511056395583e-06, "loss": 0.317, "step": 16251 }, { "epoch": 0.8975038656947205, "grad_norm": 1.0164777040481567, "learning_rate": 1.0919849219755684e-06, "loss": 0.023, "step": 16252 }, { "epoch": 0.8975590899050143, "grad_norm": 0.01286082249134779, "learning_rate": 1.090819343232803e-06, "loss": 0.0004, "step": 16253 }, { "epoch": 0.8976143141153081, "grad_norm": 0.30056217312812805, "learning_rate": 1.089654369448563e-06, "loss": 0.0135, "step": 16254 }, { "epoch": 0.8976695383256019, "grad_norm": 0.02813897281885147, "learning_rate": 1.088490000660114e-06, "loss": 0.0008, "step": 16255 }, { "epoch": 0.8977247625358957, "grad_norm": 0.8791606426239014, "learning_rate": 1.0873262369047066e-06, "loss": 0.1387, "step": 16256 }, { "epoch": 0.8977799867461895, "grad_norm": 0.3310316503047943, "learning_rate": 1.0861630782195753e-06, "loss": 0.0079, "step": 16257 }, { "epoch": 0.8978352109564833, "grad_norm": 0.024198567494750023, "learning_rate": 1.0850005246419326e-06, "loss": 0.0008, "step": 16258 }, { "epoch": 0.8978904351667771, "grad_norm": 2.400179147720337, "learning_rate": 1.083838576208973e-06, "loss": 0.0868, "step": 16259 }, { "epoch": 0.8979456593770709, "grad_norm": 3.1492531299591064, "learning_rate": 1.0826772329578693e-06, "loss": 0.5721, "step": 16260 }, { "epoch": 0.8980008835873647, "grad_norm": 0.24497315287590027, "learning_rate": 1.081516494925774e-06, "loss": 0.005, "step": 16261 }, { "epoch": 0.8980561077976585, "grad_norm": 0.018115641549229622, "learning_rate": 1.0803563621498303e-06, "loss": 0.0004, "step": 16262 }, { "epoch": 0.8981113320079522, "grad_norm": 0.49851247668266296, "learning_rate": 1.0791968346671421e-06, "loss": 0.0091, "step": 16263 }, { "epoch": 0.898166556218246, "grad_norm": 0.018008168786764145, "learning_rate": 1.0780379125148154e-06, "loss": 0.0005, "step": 16264 }, { "epoch": 0.8982217804285398, "grad_norm": 0.03344963490962982, "learning_rate": 1.0768795957299228e-06, "loss": 0.0014, "step": 16265 }, { "epoch": 0.8982770046388336, "grad_norm": 3.3805387020111084, "learning_rate": 1.0757218843495255e-06, "loss": 0.1202, "step": 16266 }, { "epoch": 0.8983322288491274, "grad_norm": 0.07012753188610077, "learning_rate": 1.0745647784106562e-06, "loss": 0.0022, "step": 16267 }, { "epoch": 0.8983874530594212, "grad_norm": 1.89960777759552, "learning_rate": 1.0734082779503452e-06, "loss": 0.1308, "step": 16268 }, { "epoch": 0.898442677269715, "grad_norm": 1.4303441047668457, "learning_rate": 1.0722523830055765e-06, "loss": 0.0434, "step": 16269 }, { "epoch": 0.8984979014800089, "grad_norm": 2.9455409049987793, "learning_rate": 1.0710970936133448e-06, "loss": 0.2818, "step": 16270 }, { "epoch": 0.8985531256903027, "grad_norm": 2.4507124423980713, "learning_rate": 1.0699424098106026e-06, "loss": 0.2472, "step": 16271 }, { "epoch": 0.8986083499005965, "grad_norm": 5.648600101470947, "learning_rate": 1.0687883316342961e-06, "loss": 0.5222, "step": 16272 }, { "epoch": 0.8986635741108903, "grad_norm": 2.5197675228118896, "learning_rate": 1.0676348591213426e-06, "loss": 0.0458, "step": 16273 }, { "epoch": 0.898718798321184, "grad_norm": 2.7630114555358887, "learning_rate": 1.06648199230865e-06, "loss": 0.1721, "step": 16274 }, { "epoch": 0.8987740225314778, "grad_norm": 3.0713577270507812, "learning_rate": 1.0653297312331e-06, "loss": 0.1987, "step": 16275 }, { "epoch": 0.8988292467417716, "grad_norm": 0.1126985102891922, "learning_rate": 1.0641780759315589e-06, "loss": 0.0023, "step": 16276 }, { "epoch": 0.8988844709520654, "grad_norm": 0.07251409441232681, "learning_rate": 1.0630270264408637e-06, "loss": 0.0023, "step": 16277 }, { "epoch": 0.8989396951623592, "grad_norm": 0.15179356932640076, "learning_rate": 1.0618765827978516e-06, "loss": 0.0046, "step": 16278 }, { "epoch": 0.898994919372653, "grad_norm": 0.5125942826271057, "learning_rate": 1.0607267450393155e-06, "loss": 0.0101, "step": 16279 }, { "epoch": 0.8990501435829468, "grad_norm": 0.5481298565864563, "learning_rate": 1.0595775132020526e-06, "loss": 0.0119, "step": 16280 }, { "epoch": 0.8991053677932406, "grad_norm": 4.215289115905762, "learning_rate": 1.0584288873228243e-06, "loss": 0.9217, "step": 16281 }, { "epoch": 0.8991605920035344, "grad_norm": 2.725724697113037, "learning_rate": 1.0572808674383817e-06, "loss": 0.48, "step": 16282 }, { "epoch": 0.8992158162138282, "grad_norm": 2.6237728595733643, "learning_rate": 1.0561334535854485e-06, "loss": 0.1504, "step": 16283 }, { "epoch": 0.899271040424122, "grad_norm": 0.11135075241327286, "learning_rate": 1.0549866458007418e-06, "loss": 0.0023, "step": 16284 }, { "epoch": 0.8993262646344157, "grad_norm": 4.99698543548584, "learning_rate": 1.0538404441209416e-06, "loss": 1.5031, "step": 16285 }, { "epoch": 0.8993814888447095, "grad_norm": 3.0686888694763184, "learning_rate": 1.0526948485827248e-06, "loss": 0.2599, "step": 16286 }, { "epoch": 0.8994367130550033, "grad_norm": 0.3254515528678894, "learning_rate": 1.0515498592227425e-06, "loss": 0.0066, "step": 16287 }, { "epoch": 0.8994919372652971, "grad_norm": 0.050025247037410736, "learning_rate": 1.0504054760776205e-06, "loss": 0.0012, "step": 16288 }, { "epoch": 0.8995471614755909, "grad_norm": 1.7964366674423218, "learning_rate": 1.0492616991839744e-06, "loss": 0.0203, "step": 16289 }, { "epoch": 0.8996023856858847, "grad_norm": 0.00691561121493578, "learning_rate": 1.048118528578399e-06, "loss": 0.0002, "step": 16290 }, { "epoch": 0.8996576098961785, "grad_norm": 3.1830930709838867, "learning_rate": 1.0469759642974652e-06, "loss": 0.3592, "step": 16291 }, { "epoch": 0.8997128341064723, "grad_norm": 4.230614185333252, "learning_rate": 1.0458340063777283e-06, "loss": 0.3207, "step": 16292 }, { "epoch": 0.8997680583167661, "grad_norm": 2.6028990745544434, "learning_rate": 1.044692654855719e-06, "loss": 0.478, "step": 16293 }, { "epoch": 0.8998232825270599, "grad_norm": 0.4508177638053894, "learning_rate": 1.0435519097679592e-06, "loss": 0.0125, "step": 16294 }, { "epoch": 0.8998785067373537, "grad_norm": 3.5882277488708496, "learning_rate": 1.0424117711509351e-06, "loss": 0.5542, "step": 16295 }, { "epoch": 0.8999337309476475, "grad_norm": 0.6613284945487976, "learning_rate": 1.0412722390411312e-06, "loss": 0.0127, "step": 16296 }, { "epoch": 0.8999889551579412, "grad_norm": 0.17220237851142883, "learning_rate": 1.0401333134750002e-06, "loss": 0.005, "step": 16297 }, { "epoch": 0.900044179368235, "grad_norm": 3.765033483505249, "learning_rate": 1.0389949944889843e-06, "loss": 0.5733, "step": 16298 }, { "epoch": 0.9000994035785288, "grad_norm": 1.3478580713272095, "learning_rate": 1.037857282119492e-06, "loss": 0.0423, "step": 16299 }, { "epoch": 0.9001546277888226, "grad_norm": 4.824016571044922, "learning_rate": 1.0367201764029322e-06, "loss": 0.4007, "step": 16300 }, { "epoch": 0.9002098519991164, "grad_norm": 0.23547276854515076, "learning_rate": 1.03558367737568e-06, "loss": 0.004, "step": 16301 }, { "epoch": 0.9002650762094102, "grad_norm": 0.17491424083709717, "learning_rate": 1.0344477850740953e-06, "loss": 0.0049, "step": 16302 }, { "epoch": 0.900320300419704, "grad_norm": 0.003919132053852081, "learning_rate": 1.0333124995345179e-06, "loss": 0.0001, "step": 16303 }, { "epoch": 0.9003755246299978, "grad_norm": 4.586911201477051, "learning_rate": 1.0321778207932697e-06, "loss": 0.2653, "step": 16304 }, { "epoch": 0.9004307488402916, "grad_norm": 0.3699533939361572, "learning_rate": 1.0310437488866532e-06, "loss": 0.0115, "step": 16305 }, { "epoch": 0.9004859730505854, "grad_norm": 0.19887621700763702, "learning_rate": 1.0299102838509456e-06, "loss": 0.0044, "step": 16306 }, { "epoch": 0.9005411972608792, "grad_norm": 0.03779872879385948, "learning_rate": 1.028777425722418e-06, "loss": 0.0007, "step": 16307 }, { "epoch": 0.9005964214711729, "grad_norm": 1.6297061443328857, "learning_rate": 1.0276451745373061e-06, "loss": 0.17, "step": 16308 }, { "epoch": 0.9006516456814667, "grad_norm": 0.6712520718574524, "learning_rate": 1.0265135303318364e-06, "loss": 0.0106, "step": 16309 }, { "epoch": 0.9007068698917605, "grad_norm": 1.6565335988998413, "learning_rate": 1.0253824931422173e-06, "loss": 0.1353, "step": 16310 }, { "epoch": 0.9007620941020543, "grad_norm": 3.650117874145508, "learning_rate": 1.0242520630046294e-06, "loss": 0.8265, "step": 16311 }, { "epoch": 0.9008173183123481, "grad_norm": 0.14965716004371643, "learning_rate": 1.0231222399552364e-06, "loss": 0.0034, "step": 16312 }, { "epoch": 0.9008725425226419, "grad_norm": 1.063735008239746, "learning_rate": 1.02199302403019e-06, "loss": 0.0716, "step": 16313 }, { "epoch": 0.9009277667329357, "grad_norm": 0.2121572494506836, "learning_rate": 1.0208644152656166e-06, "loss": 0.0044, "step": 16314 }, { "epoch": 0.9009829909432295, "grad_norm": 0.053079020231962204, "learning_rate": 1.0197364136976206e-06, "loss": 0.002, "step": 16315 }, { "epoch": 0.9010382151535233, "grad_norm": 1.935167908668518, "learning_rate": 1.0186090193622867e-06, "loss": 0.0526, "step": 16316 }, { "epoch": 0.9010934393638171, "grad_norm": 0.061734192073345184, "learning_rate": 1.0174822322956968e-06, "loss": 0.0011, "step": 16317 }, { "epoch": 0.9011486635741109, "grad_norm": 0.09529544413089752, "learning_rate": 1.0163560525338823e-06, "loss": 0.0016, "step": 16318 }, { "epoch": 0.9012038877844046, "grad_norm": 0.026016654446721077, "learning_rate": 1.0152304801128875e-06, "loss": 0.0009, "step": 16319 }, { "epoch": 0.9012591119946984, "grad_norm": 0.6232755780220032, "learning_rate": 1.014105515068715e-06, "loss": 0.0151, "step": 16320 }, { "epoch": 0.9013143362049922, "grad_norm": 2.8339920043945312, "learning_rate": 1.0129811574373583e-06, "loss": 0.5453, "step": 16321 }, { "epoch": 0.901369560415286, "grad_norm": 3.1769890785217285, "learning_rate": 1.0118574072547837e-06, "loss": 0.1546, "step": 16322 }, { "epoch": 0.9014247846255798, "grad_norm": 0.1002679169178009, "learning_rate": 1.010734264556954e-06, "loss": 0.0022, "step": 16323 }, { "epoch": 0.9014800088358736, "grad_norm": 0.07248076796531677, "learning_rate": 1.0096117293797913e-06, "loss": 0.0019, "step": 16324 }, { "epoch": 0.9015352330461675, "grad_norm": 2.200608491897583, "learning_rate": 1.0084898017592138e-06, "loss": 0.0793, "step": 16325 }, { "epoch": 0.9015904572564613, "grad_norm": 0.012530097737908363, "learning_rate": 1.0073684817311146e-06, "loss": 0.0003, "step": 16326 }, { "epoch": 0.9016456814667551, "grad_norm": 2.783325672149658, "learning_rate": 1.0062477693313654e-06, "loss": 0.1475, "step": 16327 }, { "epoch": 0.9017009056770489, "grad_norm": 3.2260396480560303, "learning_rate": 1.005127664595822e-06, "loss": 0.0725, "step": 16328 }, { "epoch": 0.9017561298873427, "grad_norm": 3.897484540939331, "learning_rate": 1.004008167560322e-06, "loss": 0.1643, "step": 16329 }, { "epoch": 0.9018113540976364, "grad_norm": 1.0107102394104004, "learning_rate": 1.0028892782606814e-06, "loss": 0.0229, "step": 16330 }, { "epoch": 0.9018665783079302, "grad_norm": 0.1478428989648819, "learning_rate": 1.0017709967326961e-06, "loss": 0.0038, "step": 16331 }, { "epoch": 0.901921802518224, "grad_norm": 0.007626278791576624, "learning_rate": 1.0006533230121373e-06, "loss": 0.0002, "step": 16332 }, { "epoch": 0.9019770267285178, "grad_norm": 0.021992238238453865, "learning_rate": 9.995362571347723e-07, "loss": 0.0005, "step": 16333 }, { "epoch": 0.9020322509388116, "grad_norm": 2.3878273963928223, "learning_rate": 9.98419799136332e-07, "loss": 0.1035, "step": 16334 }, { "epoch": 0.9020874751491054, "grad_norm": 2.4662106037139893, "learning_rate": 9.973039490525372e-07, "loss": 0.2369, "step": 16335 }, { "epoch": 0.9021426993593992, "grad_norm": 2.8486545085906982, "learning_rate": 9.96188706919088e-07, "loss": 0.6546, "step": 16336 }, { "epoch": 0.902197923569693, "grad_norm": 2.5926899909973145, "learning_rate": 9.950740727716646e-07, "loss": 0.5026, "step": 16337 }, { "epoch": 0.9022531477799868, "grad_norm": 0.011977450922131538, "learning_rate": 9.939600466459232e-07, "loss": 0.0003, "step": 16338 }, { "epoch": 0.9023083719902806, "grad_norm": 0.4384247958660126, "learning_rate": 9.928466285775107e-07, "loss": 0.0108, "step": 16339 }, { "epoch": 0.9023635962005744, "grad_norm": 1.3365769386291504, "learning_rate": 9.91733818602043e-07, "loss": 0.151, "step": 16340 }, { "epoch": 0.9024188204108681, "grad_norm": 0.0432293601334095, "learning_rate": 9.906216167551275e-07, "loss": 0.001, "step": 16341 }, { "epoch": 0.9024740446211619, "grad_norm": 5.543570041656494, "learning_rate": 9.89510023072342e-07, "loss": 2.3933, "step": 16342 }, { "epoch": 0.9025292688314557, "grad_norm": 3.1778688430786133, "learning_rate": 9.883990375892539e-07, "loss": 0.2952, "step": 16343 }, { "epoch": 0.9025844930417495, "grad_norm": 1.9362452030181885, "learning_rate": 9.87288660341399e-07, "loss": 0.0555, "step": 16344 }, { "epoch": 0.9026397172520433, "grad_norm": 0.04479149356484413, "learning_rate": 9.861788913643088e-07, "loss": 0.0011, "step": 16345 }, { "epoch": 0.9026949414623371, "grad_norm": 3.886434555053711, "learning_rate": 9.850697306934887e-07, "loss": 0.2768, "step": 16346 }, { "epoch": 0.9027501656726309, "grad_norm": 3.9014196395874023, "learning_rate": 9.839611783644188e-07, "loss": 0.9647, "step": 16347 }, { "epoch": 0.9028053898829247, "grad_norm": 7.268589019775391, "learning_rate": 9.82853234412564e-07, "loss": 0.2947, "step": 16348 }, { "epoch": 0.9028606140932185, "grad_norm": 2.1236023902893066, "learning_rate": 9.817458988733809e-07, "loss": 0.0443, "step": 16349 }, { "epoch": 0.9029158383035123, "grad_norm": 3.3781282901763916, "learning_rate": 9.806391717822827e-07, "loss": 0.0881, "step": 16350 }, { "epoch": 0.9029710625138061, "grad_norm": 0.02115565538406372, "learning_rate": 9.79533053174686e-07, "loss": 0.0007, "step": 16351 }, { "epoch": 0.9030262867240998, "grad_norm": 0.06581436097621918, "learning_rate": 9.784275430859758e-07, "loss": 0.0015, "step": 16352 }, { "epoch": 0.9030815109343936, "grad_norm": 0.2198229283094406, "learning_rate": 9.77322641551519e-07, "loss": 0.006, "step": 16353 }, { "epoch": 0.9031367351446874, "grad_norm": 0.39352911710739136, "learning_rate": 9.762183486066657e-07, "loss": 0.0132, "step": 16354 }, { "epoch": 0.9031919593549812, "grad_norm": 3.9768075942993164, "learning_rate": 9.751146642867472e-07, "loss": 0.0818, "step": 16355 }, { "epoch": 0.903247183565275, "grad_norm": 0.5668815970420837, "learning_rate": 9.74011588627073e-07, "loss": 0.0126, "step": 16356 }, { "epoch": 0.9033024077755688, "grad_norm": 0.020534751936793327, "learning_rate": 9.729091216629326e-07, "loss": 0.0006, "step": 16357 }, { "epoch": 0.9033576319858626, "grad_norm": 0.2644785940647125, "learning_rate": 9.718072634295939e-07, "loss": 0.0067, "step": 16358 }, { "epoch": 0.9034128561961564, "grad_norm": 0.04260219261050224, "learning_rate": 9.70706013962317e-07, "loss": 0.0012, "step": 16359 }, { "epoch": 0.9034680804064502, "grad_norm": 2.8290140628814697, "learning_rate": 9.69605373296323e-07, "loss": 0.1974, "step": 16360 }, { "epoch": 0.903523304616744, "grad_norm": 1.6153489351272583, "learning_rate": 9.685053414668322e-07, "loss": 0.0488, "step": 16361 }, { "epoch": 0.9035785288270378, "grad_norm": 3.8448121547698975, "learning_rate": 9.674059185090369e-07, "loss": 1.1129, "step": 16362 }, { "epoch": 0.9036337530373315, "grad_norm": 3.222336530685425, "learning_rate": 9.663071044581107e-07, "loss": 0.3056, "step": 16363 }, { "epoch": 0.9036889772476253, "grad_norm": 1.1581733226776123, "learning_rate": 9.65208899349206e-07, "loss": 0.0688, "step": 16364 }, { "epoch": 0.9037442014579191, "grad_norm": 0.6632552742958069, "learning_rate": 9.641113032174565e-07, "loss": 0.0162, "step": 16365 }, { "epoch": 0.9037994256682129, "grad_norm": 2.1224608421325684, "learning_rate": 9.63014316097981e-07, "loss": 0.0944, "step": 16366 }, { "epoch": 0.9038546498785067, "grad_norm": 3.0873634815216064, "learning_rate": 9.619179380258691e-07, "loss": 0.2924, "step": 16367 }, { "epoch": 0.9039098740888005, "grad_norm": 1.5661147832870483, "learning_rate": 9.608221690362062e-07, "loss": 0.1747, "step": 16368 }, { "epoch": 0.9039650982990943, "grad_norm": 0.02146870084106922, "learning_rate": 9.597270091640442e-07, "loss": 0.0002, "step": 16369 }, { "epoch": 0.9040203225093881, "grad_norm": 0.050865110009908676, "learning_rate": 9.586324584444196e-07, "loss": 0.0013, "step": 16370 }, { "epoch": 0.9040755467196819, "grad_norm": 0.5480611324310303, "learning_rate": 9.575385169123486e-07, "loss": 0.0125, "step": 16371 }, { "epoch": 0.9041307709299757, "grad_norm": 0.18028202652931213, "learning_rate": 9.564451846028366e-07, "loss": 0.0057, "step": 16372 }, { "epoch": 0.9041859951402695, "grad_norm": 3.4282114505767822, "learning_rate": 9.553524615508514e-07, "loss": 0.286, "step": 16373 }, { "epoch": 0.9042412193505633, "grad_norm": 0.4801556468009949, "learning_rate": 9.542603477913625e-07, "loss": 0.0128, "step": 16374 }, { "epoch": 0.904296443560857, "grad_norm": 0.2760893702507019, "learning_rate": 9.531688433593067e-07, "loss": 0.0071, "step": 16375 }, { "epoch": 0.9043516677711508, "grad_norm": 0.048271145671606064, "learning_rate": 9.520779482896026e-07, "loss": 0.0011, "step": 16376 }, { "epoch": 0.9044068919814446, "grad_norm": 0.022576432675123215, "learning_rate": 9.509876626171511e-07, "loss": 0.0009, "step": 16377 }, { "epoch": 0.9044621161917384, "grad_norm": 0.04062993824481964, "learning_rate": 9.498979863768354e-07, "loss": 0.0017, "step": 16378 }, { "epoch": 0.9045173404020322, "grad_norm": 2.03289532661438, "learning_rate": 9.488089196035167e-07, "loss": 0.0953, "step": 16379 }, { "epoch": 0.904572564612326, "grad_norm": 0.9905019998550415, "learning_rate": 9.477204623320357e-07, "loss": 0.1159, "step": 16380 }, { "epoch": 0.9046277888226198, "grad_norm": 2.926625967025757, "learning_rate": 9.46632614597216e-07, "loss": 0.1252, "step": 16381 }, { "epoch": 0.9046830130329137, "grad_norm": 0.06569443643093109, "learning_rate": 9.455453764338652e-07, "loss": 0.0013, "step": 16382 }, { "epoch": 0.9047382372432075, "grad_norm": 0.06419356167316437, "learning_rate": 9.444587478767598e-07, "loss": 0.0011, "step": 16383 }, { "epoch": 0.9047934614535013, "grad_norm": 0.046885356307029724, "learning_rate": 9.433727289606676e-07, "loss": 0.001, "step": 16384 }, { "epoch": 0.9048486856637951, "grad_norm": 0.0911945328116417, "learning_rate": 9.422873197203364e-07, "loss": 0.0019, "step": 16385 }, { "epoch": 0.9049039098740888, "grad_norm": 0.8952396512031555, "learning_rate": 9.412025201904874e-07, "loss": 0.0278, "step": 16386 }, { "epoch": 0.9049591340843826, "grad_norm": 6.824199199676514, "learning_rate": 9.401183304058259e-07, "loss": 0.193, "step": 16387 }, { "epoch": 0.9050143582946764, "grad_norm": 1.9481250047683716, "learning_rate": 9.390347504010445e-07, "loss": 0.4908, "step": 16388 }, { "epoch": 0.9050695825049702, "grad_norm": 3.134249687194824, "learning_rate": 9.379517802108018e-07, "loss": 0.5095, "step": 16389 }, { "epoch": 0.905124806715264, "grad_norm": 2.173846483230591, "learning_rate": 9.368694198697504e-07, "loss": 0.1288, "step": 16390 }, { "epoch": 0.9051800309255578, "grad_norm": 0.35445982217788696, "learning_rate": 9.357876694125157e-07, "loss": 0.0071, "step": 16391 }, { "epoch": 0.9052352551358516, "grad_norm": 1.1836364269256592, "learning_rate": 9.347065288737078e-07, "loss": 0.0365, "step": 16392 }, { "epoch": 0.9052904793461454, "grad_norm": 2.933413028717041, "learning_rate": 9.336259982879126e-07, "loss": 0.3598, "step": 16393 }, { "epoch": 0.9053457035564392, "grad_norm": 0.061520885676145554, "learning_rate": 9.325460776897022e-07, "loss": 0.0018, "step": 16394 }, { "epoch": 0.905400927766733, "grad_norm": 5.010065078735352, "learning_rate": 9.314667671136269e-07, "loss": 0.353, "step": 16395 }, { "epoch": 0.9054561519770268, "grad_norm": 0.38739803433418274, "learning_rate": 9.303880665942144e-07, "loss": 0.0043, "step": 16396 }, { "epoch": 0.9055113761873205, "grad_norm": 0.07043562084436417, "learning_rate": 9.293099761659752e-07, "loss": 0.0026, "step": 16397 }, { "epoch": 0.9055666003976143, "grad_norm": 0.22422489523887634, "learning_rate": 9.282324958634059e-07, "loss": 0.0042, "step": 16398 }, { "epoch": 0.9056218246079081, "grad_norm": 0.7757953405380249, "learning_rate": 9.271556257209702e-07, "loss": 0.0234, "step": 16399 }, { "epoch": 0.9056770488182019, "grad_norm": 0.02952214889228344, "learning_rate": 9.260793657731249e-07, "loss": 0.0007, "step": 16400 }, { "epoch": 0.9057322730284957, "grad_norm": 0.8304288387298584, "learning_rate": 9.250037160543024e-07, "loss": 0.0251, "step": 16401 }, { "epoch": 0.9057874972387895, "grad_norm": 0.03687627613544464, "learning_rate": 9.239286765989153e-07, "loss": 0.001, "step": 16402 }, { "epoch": 0.9058427214490833, "grad_norm": 4.241804122924805, "learning_rate": 9.228542474413538e-07, "loss": 0.8096, "step": 16403 }, { "epoch": 0.9058979456593771, "grad_norm": 0.01077976357191801, "learning_rate": 9.217804286159993e-07, "loss": 0.0003, "step": 16404 }, { "epoch": 0.9059531698696709, "grad_norm": 3.407555341720581, "learning_rate": 9.207072201571976e-07, "loss": 0.4243, "step": 16405 }, { "epoch": 0.9060083940799647, "grad_norm": 5.327648639678955, "learning_rate": 9.196346220992925e-07, "loss": 0.317, "step": 16406 }, { "epoch": 0.9060636182902585, "grad_norm": 2.585843086242676, "learning_rate": 9.185626344765941e-07, "loss": 0.1475, "step": 16407 }, { "epoch": 0.9061188425005522, "grad_norm": 0.02475610561668873, "learning_rate": 9.174912573233996e-07, "loss": 0.0007, "step": 16408 }, { "epoch": 0.906174066710846, "grad_norm": 0.07477638125419617, "learning_rate": 9.164204906739837e-07, "loss": 0.0027, "step": 16409 }, { "epoch": 0.9062292909211398, "grad_norm": 5.992946147918701, "learning_rate": 9.153503345626058e-07, "loss": 0.6337, "step": 16410 }, { "epoch": 0.9062845151314336, "grad_norm": 2.249089241027832, "learning_rate": 9.142807890235028e-07, "loss": 0.3053, "step": 16411 }, { "epoch": 0.9063397393417274, "grad_norm": 2.7411415576934814, "learning_rate": 9.132118540908918e-07, "loss": 0.2131, "step": 16412 }, { "epoch": 0.9063949635520212, "grad_norm": 0.04017893224954605, "learning_rate": 9.1214352979897e-07, "loss": 0.001, "step": 16413 }, { "epoch": 0.906450187762315, "grad_norm": 0.13625293970108032, "learning_rate": 9.110758161819211e-07, "loss": 0.0048, "step": 16414 }, { "epoch": 0.9065054119726088, "grad_norm": 0.02740238979458809, "learning_rate": 9.100087132738955e-07, "loss": 0.0009, "step": 16415 }, { "epoch": 0.9065606361829026, "grad_norm": 2.1408705711364746, "learning_rate": 9.089422211090416e-07, "loss": 0.188, "step": 16416 }, { "epoch": 0.9066158603931964, "grad_norm": 5.921758651733398, "learning_rate": 9.07876339721474e-07, "loss": 0.5236, "step": 16417 }, { "epoch": 0.9066710846034902, "grad_norm": 0.14245139062404633, "learning_rate": 9.068110691452969e-07, "loss": 0.0026, "step": 16418 }, { "epoch": 0.9067263088137839, "grad_norm": 2.25195574760437, "learning_rate": 9.057464094145873e-07, "loss": 0.1213, "step": 16419 }, { "epoch": 0.9067815330240777, "grad_norm": 3.181356191635132, "learning_rate": 9.046823605634092e-07, "loss": 0.4722, "step": 16420 }, { "epoch": 0.9068367572343715, "grad_norm": 4.017086982727051, "learning_rate": 9.036189226258063e-07, "loss": 0.7156, "step": 16421 }, { "epoch": 0.9068919814446653, "grad_norm": 5.160587787628174, "learning_rate": 9.025560956357982e-07, "loss": 0.6167, "step": 16422 }, { "epoch": 0.9069472056549591, "grad_norm": 5.350496768951416, "learning_rate": 9.014938796273908e-07, "loss": 0.5262, "step": 16423 }, { "epoch": 0.9070024298652529, "grad_norm": 4.978960037231445, "learning_rate": 9.004322746345617e-07, "loss": 1.1321, "step": 16424 }, { "epoch": 0.9070576540755467, "grad_norm": 2.200979232788086, "learning_rate": 8.993712806912813e-07, "loss": 0.1231, "step": 16425 }, { "epoch": 0.9071128782858405, "grad_norm": 2.1450328826904297, "learning_rate": 8.983108978314869e-07, "loss": 0.1776, "step": 16426 }, { "epoch": 0.9071681024961343, "grad_norm": 4.098180770874023, "learning_rate": 8.972511260891115e-07, "loss": 1.243, "step": 16427 }, { "epoch": 0.9072233267064281, "grad_norm": 0.34389013051986694, "learning_rate": 8.961919654980499e-07, "loss": 0.012, "step": 16428 }, { "epoch": 0.9072785509167219, "grad_norm": 2.4815268516540527, "learning_rate": 8.951334160921976e-07, "loss": 0.2063, "step": 16429 }, { "epoch": 0.9073337751270156, "grad_norm": 2.402696132659912, "learning_rate": 8.940754779054162e-07, "loss": 0.143, "step": 16430 }, { "epoch": 0.9073889993373094, "grad_norm": 2.298398494720459, "learning_rate": 8.930181509715518e-07, "loss": 0.0992, "step": 16431 }, { "epoch": 0.9074442235476032, "grad_norm": 0.15260519087314606, "learning_rate": 8.919614353244311e-07, "loss": 0.0054, "step": 16432 }, { "epoch": 0.907499447757897, "grad_norm": 2.152066946029663, "learning_rate": 8.909053309978644e-07, "loss": 0.249, "step": 16433 }, { "epoch": 0.9075546719681908, "grad_norm": 0.03483192250132561, "learning_rate": 8.89849838025636e-07, "loss": 0.0003, "step": 16434 }, { "epoch": 0.9076098961784846, "grad_norm": 2.27642822265625, "learning_rate": 8.887949564415143e-07, "loss": 0.128, "step": 16435 }, { "epoch": 0.9076651203887784, "grad_norm": 0.13558363914489746, "learning_rate": 8.877406862792503e-07, "loss": 0.0038, "step": 16436 }, { "epoch": 0.9077203445990722, "grad_norm": 3.4850540161132812, "learning_rate": 8.866870275725748e-07, "loss": 0.7845, "step": 16437 }, { "epoch": 0.907775568809366, "grad_norm": 0.3687472939491272, "learning_rate": 8.856339803551895e-07, "loss": 0.1059, "step": 16438 }, { "epoch": 0.9078307930196599, "grad_norm": 0.8790739178657532, "learning_rate": 8.845815446607919e-07, "loss": 0.0253, "step": 16439 }, { "epoch": 0.9078860172299537, "grad_norm": 4.318964004516602, "learning_rate": 8.835297205230487e-07, "loss": 0.9938, "step": 16440 }, { "epoch": 0.9079412414402475, "grad_norm": 0.14258919656276703, "learning_rate": 8.824785079756126e-07, "loss": 0.0022, "step": 16441 }, { "epoch": 0.9079964656505412, "grad_norm": 0.516521155834198, "learning_rate": 8.814279070521126e-07, "loss": 0.0124, "step": 16442 }, { "epoch": 0.908051689860835, "grad_norm": 0.07607874274253845, "learning_rate": 8.803779177861682e-07, "loss": 0.0013, "step": 16443 }, { "epoch": 0.9081069140711288, "grad_norm": 0.3325692117214203, "learning_rate": 8.793285402113571e-07, "loss": 0.0085, "step": 16444 }, { "epoch": 0.9081621382814226, "grad_norm": 1.6174958944320679, "learning_rate": 8.782797743612659e-07, "loss": 0.1476, "step": 16445 }, { "epoch": 0.9082173624917164, "grad_norm": 4.436160087585449, "learning_rate": 8.772316202694386e-07, "loss": 0.5399, "step": 16446 }, { "epoch": 0.9082725867020102, "grad_norm": 0.01022480521351099, "learning_rate": 8.761840779694153e-07, "loss": 0.0003, "step": 16447 }, { "epoch": 0.908327810912304, "grad_norm": 0.1189192607998848, "learning_rate": 8.751371474947024e-07, "loss": 0.0027, "step": 16448 }, { "epoch": 0.9083830351225978, "grad_norm": 4.813950538635254, "learning_rate": 8.740908288787998e-07, "loss": 0.494, "step": 16449 }, { "epoch": 0.9084382593328916, "grad_norm": 0.01210111752152443, "learning_rate": 8.730451221551806e-07, "loss": 0.0004, "step": 16450 }, { "epoch": 0.9084934835431854, "grad_norm": 4.010287761688232, "learning_rate": 8.720000273573004e-07, "loss": 0.5383, "step": 16451 }, { "epoch": 0.9085487077534792, "grad_norm": 5.470687389373779, "learning_rate": 8.709555445185924e-07, "loss": 1.0166, "step": 16452 }, { "epoch": 0.9086039319637729, "grad_norm": 4.195924758911133, "learning_rate": 8.699116736724789e-07, "loss": 0.2755, "step": 16453 }, { "epoch": 0.9086591561740667, "grad_norm": 0.07646282017230988, "learning_rate": 8.688684148523485e-07, "loss": 0.0021, "step": 16454 }, { "epoch": 0.9087143803843605, "grad_norm": 4.797476291656494, "learning_rate": 8.678257680915814e-07, "loss": 1.1411, "step": 16455 }, { "epoch": 0.9087696045946543, "grad_norm": 3.5005156993865967, "learning_rate": 8.667837334235374e-07, "loss": 0.7052, "step": 16456 }, { "epoch": 0.9088248288049481, "grad_norm": 0.13061435520648956, "learning_rate": 8.6574231088155e-07, "loss": 0.0032, "step": 16457 }, { "epoch": 0.9088800530152419, "grad_norm": 4.504271030426025, "learning_rate": 8.647015004989367e-07, "loss": 0.9155, "step": 16458 }, { "epoch": 0.9089352772255357, "grad_norm": 2.3564796447753906, "learning_rate": 8.636613023090002e-07, "loss": 0.1146, "step": 16459 }, { "epoch": 0.9089905014358295, "grad_norm": 0.03976000100374222, "learning_rate": 8.626217163450179e-07, "loss": 0.0011, "step": 16460 }, { "epoch": 0.9090457256461233, "grad_norm": 3.5810348987579346, "learning_rate": 8.615827426402479e-07, "loss": 0.7633, "step": 16461 }, { "epoch": 0.9091009498564171, "grad_norm": 0.11038129031658173, "learning_rate": 8.605443812279323e-07, "loss": 0.0031, "step": 16462 }, { "epoch": 0.9091561740667109, "grad_norm": 0.5834731459617615, "learning_rate": 8.595066321412892e-07, "loss": 0.0183, "step": 16463 }, { "epoch": 0.9092113982770046, "grad_norm": 7.32292366027832, "learning_rate": 8.584694954135164e-07, "loss": 1.1788, "step": 16464 }, { "epoch": 0.9092666224872984, "grad_norm": 0.1353296935558319, "learning_rate": 8.574329710778006e-07, "loss": 0.0025, "step": 16465 }, { "epoch": 0.9093218466975922, "grad_norm": 0.01579611375927925, "learning_rate": 8.563970591672999e-07, "loss": 0.0005, "step": 16466 }, { "epoch": 0.909377070907886, "grad_norm": 2.0642201900482178, "learning_rate": 8.553617597151565e-07, "loss": 0.1907, "step": 16467 }, { "epoch": 0.9094322951181798, "grad_norm": 3.1097757816314697, "learning_rate": 8.543270727544905e-07, "loss": 0.5352, "step": 16468 }, { "epoch": 0.9094875193284736, "grad_norm": 0.05263577774167061, "learning_rate": 8.532929983184135e-07, "loss": 0.0018, "step": 16469 }, { "epoch": 0.9095427435387674, "grad_norm": 0.03933582454919815, "learning_rate": 8.522595364399944e-07, "loss": 0.0011, "step": 16470 }, { "epoch": 0.9095979677490612, "grad_norm": 3.19490909576416, "learning_rate": 8.512266871523089e-07, "loss": 0.1978, "step": 16471 }, { "epoch": 0.909653191959355, "grad_norm": 0.4262368381023407, "learning_rate": 8.50194450488393e-07, "loss": 0.0095, "step": 16472 }, { "epoch": 0.9097084161696488, "grad_norm": 0.5181781053543091, "learning_rate": 8.491628264812756e-07, "loss": 0.0124, "step": 16473 }, { "epoch": 0.9097636403799426, "grad_norm": 0.006476848851889372, "learning_rate": 8.481318151639573e-07, "loss": 0.0002, "step": 16474 }, { "epoch": 0.9098188645902363, "grad_norm": 0.06501670926809311, "learning_rate": 8.471014165694246e-07, "loss": 0.0019, "step": 16475 }, { "epoch": 0.9098740888005301, "grad_norm": 0.02831706404685974, "learning_rate": 8.460716307306472e-07, "loss": 0.0009, "step": 16476 }, { "epoch": 0.9099293130108239, "grad_norm": 1.6016041040420532, "learning_rate": 8.45042457680565e-07, "loss": 0.0148, "step": 16477 }, { "epoch": 0.9099845372211177, "grad_norm": 0.025274740532040596, "learning_rate": 8.44013897452105e-07, "loss": 0.0005, "step": 16478 }, { "epoch": 0.9100397614314115, "grad_norm": 1.033856749534607, "learning_rate": 8.42985950078179e-07, "loss": 0.0331, "step": 16479 }, { "epoch": 0.9100949856417053, "grad_norm": 1.6842162609100342, "learning_rate": 8.419586155916649e-07, "loss": 0.2464, "step": 16480 }, { "epoch": 0.9101502098519991, "grad_norm": 3.8432257175445557, "learning_rate": 8.409318940254386e-07, "loss": 0.5134, "step": 16481 }, { "epoch": 0.9102054340622929, "grad_norm": 0.3680167496204376, "learning_rate": 8.399057854123449e-07, "loss": 0.0108, "step": 16482 }, { "epoch": 0.9102606582725867, "grad_norm": 2.380323886871338, "learning_rate": 8.388802897852111e-07, "loss": 0.2668, "step": 16483 }, { "epoch": 0.9103158824828805, "grad_norm": 1.7872655391693115, "learning_rate": 8.378554071768464e-07, "loss": 0.0916, "step": 16484 }, { "epoch": 0.9103711066931743, "grad_norm": 0.8513529300689697, "learning_rate": 8.368311376200378e-07, "loss": 0.0189, "step": 16485 }, { "epoch": 0.910426330903468, "grad_norm": 3.846815586090088, "learning_rate": 8.35807481147557e-07, "loss": 0.3937, "step": 16486 }, { "epoch": 0.9104815551137618, "grad_norm": 0.1443687528371811, "learning_rate": 8.34784437792151e-07, "loss": 0.0059, "step": 16487 }, { "epoch": 0.9105367793240556, "grad_norm": 0.09336985647678375, "learning_rate": 8.337620075865538e-07, "loss": 0.0029, "step": 16488 }, { "epoch": 0.9105920035343494, "grad_norm": 0.01551272813230753, "learning_rate": 8.327401905634747e-07, "loss": 0.0002, "step": 16489 }, { "epoch": 0.9106472277446432, "grad_norm": 0.16207319498062134, "learning_rate": 8.31718986755603e-07, "loss": 0.0031, "step": 16490 }, { "epoch": 0.910702451954937, "grad_norm": 0.004520156886428595, "learning_rate": 8.306983961956083e-07, "loss": 0.0001, "step": 16491 }, { "epoch": 0.9107576761652308, "grad_norm": 0.47062787413597107, "learning_rate": 8.296784189161489e-07, "loss": 0.0054, "step": 16492 }, { "epoch": 0.9108129003755246, "grad_norm": 0.02294391207396984, "learning_rate": 8.286590549498474e-07, "loss": 0.0005, "step": 16493 }, { "epoch": 0.9108681245858185, "grad_norm": 0.01435895636677742, "learning_rate": 8.276403043293246e-07, "loss": 0.0004, "step": 16494 }, { "epoch": 0.9109233487961123, "grad_norm": 0.2055041342973709, "learning_rate": 8.266221670871677e-07, "loss": 0.0049, "step": 16495 }, { "epoch": 0.9109785730064061, "grad_norm": 2.815293312072754, "learning_rate": 8.25604643255955e-07, "loss": 0.3439, "step": 16496 }, { "epoch": 0.9110337972166997, "grad_norm": 1.2342082262039185, "learning_rate": 8.245877328682317e-07, "loss": 0.0376, "step": 16497 }, { "epoch": 0.9110890214269936, "grad_norm": 5.094362258911133, "learning_rate": 8.235714359565405e-07, "loss": 1.1883, "step": 16498 }, { "epoch": 0.9111442456372874, "grad_norm": 2.2778522968292236, "learning_rate": 8.225557525533912e-07, "loss": 0.2029, "step": 16499 }, { "epoch": 0.9111994698475812, "grad_norm": 0.02120799385011196, "learning_rate": 8.215406826912798e-07, "loss": 0.0005, "step": 16500 }, { "epoch": 0.911254694057875, "grad_norm": 3.511687755584717, "learning_rate": 8.205262264026781e-07, "loss": 0.1589, "step": 16501 }, { "epoch": 0.9113099182681688, "grad_norm": 2.6390507221221924, "learning_rate": 8.195123837200491e-07, "loss": 0.7277, "step": 16502 }, { "epoch": 0.9113651424784626, "grad_norm": 0.029974397271871567, "learning_rate": 8.184991546758181e-07, "loss": 0.0008, "step": 16503 }, { "epoch": 0.9114203666887564, "grad_norm": 2.5320987701416016, "learning_rate": 8.174865393024078e-07, "loss": 0.4925, "step": 16504 }, { "epoch": 0.9114755908990502, "grad_norm": 0.6499503254890442, "learning_rate": 8.164745376322147e-07, "loss": 0.0152, "step": 16505 }, { "epoch": 0.911530815109344, "grad_norm": 4.001448154449463, "learning_rate": 8.154631496976129e-07, "loss": 0.6167, "step": 16506 }, { "epoch": 0.9115860393196378, "grad_norm": 2.539264678955078, "learning_rate": 8.144523755309608e-07, "loss": 0.5075, "step": 16507 }, { "epoch": 0.9116412635299315, "grad_norm": 0.4175262153148651, "learning_rate": 8.134422151645993e-07, "loss": 0.0123, "step": 16508 }, { "epoch": 0.9116964877402253, "grad_norm": 0.04010368883609772, "learning_rate": 8.124326686308381e-07, "loss": 0.001, "step": 16509 }, { "epoch": 0.9117517119505191, "grad_norm": 3.3632915019989014, "learning_rate": 8.114237359619825e-07, "loss": 0.097, "step": 16510 }, { "epoch": 0.9118069361608129, "grad_norm": 3.869713544845581, "learning_rate": 8.104154171903112e-07, "loss": 0.4706, "step": 16511 }, { "epoch": 0.9118621603711067, "grad_norm": 3.09798526763916, "learning_rate": 8.094077123480781e-07, "loss": 0.1353, "step": 16512 }, { "epoch": 0.9119173845814005, "grad_norm": 0.06155833601951599, "learning_rate": 8.084006214675244e-07, "loss": 0.0013, "step": 16513 }, { "epoch": 0.9119726087916943, "grad_norm": 3.717212438583374, "learning_rate": 8.073941445808753e-07, "loss": 0.5361, "step": 16514 }, { "epoch": 0.9120278330019881, "grad_norm": 4.455907344818115, "learning_rate": 8.063882817203228e-07, "loss": 0.2424, "step": 16515 }, { "epoch": 0.9120830572122819, "grad_norm": 2.4717867374420166, "learning_rate": 8.053830329180546e-07, "loss": 0.2797, "step": 16516 }, { "epoch": 0.9121382814225757, "grad_norm": 6.134340763092041, "learning_rate": 8.043783982062225e-07, "loss": 0.5607, "step": 16517 }, { "epoch": 0.9121935056328695, "grad_norm": 4.825462818145752, "learning_rate": 8.033743776169789e-07, "loss": 1.8766, "step": 16518 }, { "epoch": 0.9122487298431633, "grad_norm": 1.287912130355835, "learning_rate": 8.023709711824334e-07, "loss": 0.067, "step": 16519 }, { "epoch": 0.912303954053457, "grad_norm": 2.693737268447876, "learning_rate": 8.013681789346984e-07, "loss": 0.6948, "step": 16520 }, { "epoch": 0.9123591782637508, "grad_norm": 0.4342311918735504, "learning_rate": 8.003660009058501e-07, "loss": 0.0095, "step": 16521 }, { "epoch": 0.9124144024740446, "grad_norm": 0.011160649359226227, "learning_rate": 7.993644371279518e-07, "loss": 0.0004, "step": 16522 }, { "epoch": 0.9124696266843384, "grad_norm": 4.417373180389404, "learning_rate": 7.983634876330448e-07, "loss": 0.2124, "step": 16523 }, { "epoch": 0.9125248508946322, "grad_norm": 0.2807965576648712, "learning_rate": 7.973631524531611e-07, "loss": 0.005, "step": 16524 }, { "epoch": 0.912580075104926, "grad_norm": 2.392021894454956, "learning_rate": 7.963634316202906e-07, "loss": 0.443, "step": 16525 }, { "epoch": 0.9126352993152198, "grad_norm": 3.0745744705200195, "learning_rate": 7.953643251664278e-07, "loss": 0.0498, "step": 16526 }, { "epoch": 0.9126905235255136, "grad_norm": 0.4319431781768799, "learning_rate": 7.943658331235337e-07, "loss": 0.0109, "step": 16527 }, { "epoch": 0.9127457477358074, "grad_norm": 3.7565364837646484, "learning_rate": 7.933679555235518e-07, "loss": 0.0758, "step": 16528 }, { "epoch": 0.9128009719461012, "grad_norm": 1.027491569519043, "learning_rate": 7.923706923984054e-07, "loss": 0.0317, "step": 16529 }, { "epoch": 0.912856196156395, "grad_norm": 5.915794372558594, "learning_rate": 7.913740437800044e-07, "loss": 0.2799, "step": 16530 }, { "epoch": 0.9129114203666887, "grad_norm": 1.096436619758606, "learning_rate": 7.903780097002322e-07, "loss": 0.0168, "step": 16531 }, { "epoch": 0.9129666445769825, "grad_norm": 0.2740243971347809, "learning_rate": 7.893825901909569e-07, "loss": 0.0023, "step": 16532 }, { "epoch": 0.9130218687872763, "grad_norm": 4.144709587097168, "learning_rate": 7.883877852840171e-07, "loss": 0.3783, "step": 16533 }, { "epoch": 0.9130770929975701, "grad_norm": 1.0454728603363037, "learning_rate": 7.873935950112521e-07, "loss": 0.0289, "step": 16534 }, { "epoch": 0.9131323172078639, "grad_norm": 0.05011366680264473, "learning_rate": 7.864000194044563e-07, "loss": 0.001, "step": 16535 }, { "epoch": 0.9131875414181577, "grad_norm": 3.997170925140381, "learning_rate": 7.854070584954265e-07, "loss": 0.3669, "step": 16536 }, { "epoch": 0.9132427656284515, "grad_norm": 0.3022158145904541, "learning_rate": 7.84414712315924e-07, "loss": 0.0082, "step": 16537 }, { "epoch": 0.9132979898387453, "grad_norm": 2.8336455821990967, "learning_rate": 7.834229808977012e-07, "loss": 0.6988, "step": 16538 }, { "epoch": 0.9133532140490391, "grad_norm": 0.08938786387443542, "learning_rate": 7.824318642724815e-07, "loss": 0.002, "step": 16539 }, { "epoch": 0.9134084382593329, "grad_norm": 0.056365661323070526, "learning_rate": 7.814413624719774e-07, "loss": 0.0018, "step": 16540 }, { "epoch": 0.9134636624696267, "grad_norm": 0.14876361191272736, "learning_rate": 7.804514755278791e-07, "loss": 0.0037, "step": 16541 }, { "epoch": 0.9135188866799204, "grad_norm": 0.19752125442028046, "learning_rate": 7.794622034718524e-07, "loss": 0.0035, "step": 16542 }, { "epoch": 0.9135741108902142, "grad_norm": 3.224057674407959, "learning_rate": 7.784735463355475e-07, "loss": 0.1, "step": 16543 }, { "epoch": 0.913629335100508, "grad_norm": 0.17847901582717896, "learning_rate": 7.774855041505969e-07, "loss": 0.0048, "step": 16544 }, { "epoch": 0.9136845593108018, "grad_norm": 7.770857810974121, "learning_rate": 7.764980769486086e-07, "loss": 0.9021, "step": 16545 }, { "epoch": 0.9137397835210956, "grad_norm": 0.16950859129428864, "learning_rate": 7.755112647611707e-07, "loss": 0.0032, "step": 16546 }, { "epoch": 0.9137950077313894, "grad_norm": 2.7264420986175537, "learning_rate": 7.745250676198624e-07, "loss": 0.0735, "step": 16547 }, { "epoch": 0.9138502319416832, "grad_norm": 7.275596618652344, "learning_rate": 7.73539485556225e-07, "loss": 0.346, "step": 16548 }, { "epoch": 0.913905456151977, "grad_norm": 0.061581335961818695, "learning_rate": 7.725545186017957e-07, "loss": 0.0012, "step": 16549 }, { "epoch": 0.9139606803622708, "grad_norm": 5.393212795257568, "learning_rate": 7.71570166788087e-07, "loss": 0.5595, "step": 16550 }, { "epoch": 0.9140159045725647, "grad_norm": 2.9928081035614014, "learning_rate": 7.705864301465893e-07, "loss": 0.1841, "step": 16551 }, { "epoch": 0.9140711287828585, "grad_norm": 0.9885644316673279, "learning_rate": 7.696033087087729e-07, "loss": 0.0293, "step": 16552 }, { "epoch": 0.9141263529931521, "grad_norm": 1.1765904426574707, "learning_rate": 7.68620802506097e-07, "loss": 0.007, "step": 16553 }, { "epoch": 0.914181577203446, "grad_norm": 0.015194754116237164, "learning_rate": 7.676389115699878e-07, "loss": 0.0004, "step": 16554 }, { "epoch": 0.9142368014137398, "grad_norm": 2.117332935333252, "learning_rate": 7.666576359318645e-07, "loss": 0.4171, "step": 16555 }, { "epoch": 0.9142920256240336, "grad_norm": 0.025104394182562828, "learning_rate": 7.656769756231153e-07, "loss": 0.0007, "step": 16556 }, { "epoch": 0.9143472498343274, "grad_norm": 2.9190704822540283, "learning_rate": 7.646969306751217e-07, "loss": 0.3144, "step": 16557 }, { "epoch": 0.9144024740446212, "grad_norm": 0.02723613753914833, "learning_rate": 7.637175011192299e-07, "loss": 0.0007, "step": 16558 }, { "epoch": 0.914457698254915, "grad_norm": 0.008763143792748451, "learning_rate": 7.627386869867793e-07, "loss": 0.0003, "step": 16559 }, { "epoch": 0.9145129224652088, "grad_norm": 2.962801456451416, "learning_rate": 7.617604883090845e-07, "loss": 0.5897, "step": 16560 }, { "epoch": 0.9145681466755026, "grad_norm": 0.1023431196808815, "learning_rate": 7.607829051174409e-07, "loss": 0.002, "step": 16561 }, { "epoch": 0.9146233708857964, "grad_norm": 0.00566214369609952, "learning_rate": 7.598059374431232e-07, "loss": 0.0001, "step": 16562 }, { "epoch": 0.9146785950960902, "grad_norm": 2.411188840866089, "learning_rate": 7.588295853173911e-07, "loss": 0.0951, "step": 16563 }, { "epoch": 0.9147338193063839, "grad_norm": 4.037771701812744, "learning_rate": 7.578538487714726e-07, "loss": 0.8395, "step": 16564 }, { "epoch": 0.9147890435166777, "grad_norm": 2.323390483856201, "learning_rate": 7.568787278365919e-07, "loss": 0.1428, "step": 16565 }, { "epoch": 0.9148442677269715, "grad_norm": 7.169532775878906, "learning_rate": 7.559042225439439e-07, "loss": 0.5653, "step": 16566 }, { "epoch": 0.9148994919372653, "grad_norm": 0.10898909717798233, "learning_rate": 7.54930332924706e-07, "loss": 0.0033, "step": 16567 }, { "epoch": 0.9149547161475591, "grad_norm": 1.3168964385986328, "learning_rate": 7.539570590100309e-07, "loss": 0.0172, "step": 16568 }, { "epoch": 0.9150099403578529, "grad_norm": 2.0806000232696533, "learning_rate": 7.52984400831065e-07, "loss": 0.1015, "step": 16569 }, { "epoch": 0.9150651645681467, "grad_norm": 2.676344156265259, "learning_rate": 7.52012358418921e-07, "loss": 0.4063, "step": 16570 }, { "epoch": 0.9151203887784405, "grad_norm": 2.6374900341033936, "learning_rate": 7.510409318046963e-07, "loss": 0.2302, "step": 16571 }, { "epoch": 0.9151756129887343, "grad_norm": 2.2780380249023438, "learning_rate": 7.500701210194705e-07, "loss": 0.2755, "step": 16572 }, { "epoch": 0.9152308371990281, "grad_norm": 0.21504728496074677, "learning_rate": 7.490999260943099e-07, "loss": 0.0045, "step": 16573 }, { "epoch": 0.9152860614093219, "grad_norm": 0.08226614445447922, "learning_rate": 7.481303470602408e-07, "loss": 0.0018, "step": 16574 }, { "epoch": 0.9153412856196156, "grad_norm": 5.0108747482299805, "learning_rate": 7.471613839482938e-07, "loss": 0.6915, "step": 16575 }, { "epoch": 0.9153965098299094, "grad_norm": 2.301589012145996, "learning_rate": 7.461930367894643e-07, "loss": 0.3139, "step": 16576 }, { "epoch": 0.9154517340402032, "grad_norm": 3.25986909866333, "learning_rate": 7.452253056147318e-07, "loss": 0.3161, "step": 16577 }, { "epoch": 0.915506958250497, "grad_norm": 2.5895333290100098, "learning_rate": 7.442581904550539e-07, "loss": 0.0407, "step": 16578 }, { "epoch": 0.9155621824607908, "grad_norm": 0.5091737508773804, "learning_rate": 7.43291691341379e-07, "loss": 0.0071, "step": 16579 }, { "epoch": 0.9156174066710846, "grad_norm": 4.576713562011719, "learning_rate": 7.423258083046248e-07, "loss": 0.1584, "step": 16580 }, { "epoch": 0.9156726308813784, "grad_norm": 0.12502281367778778, "learning_rate": 7.41360541375693e-07, "loss": 0.0018, "step": 16581 }, { "epoch": 0.9157278550916722, "grad_norm": 2.539433479309082, "learning_rate": 7.403958905854636e-07, "loss": 0.1096, "step": 16582 }, { "epoch": 0.915783079301966, "grad_norm": 0.22871536016464233, "learning_rate": 7.394318559647984e-07, "loss": 0.0051, "step": 16583 }, { "epoch": 0.9158383035122598, "grad_norm": 2.7515509128570557, "learning_rate": 7.384684375445372e-07, "loss": 0.3074, "step": 16584 }, { "epoch": 0.9158935277225536, "grad_norm": 0.6358214616775513, "learning_rate": 7.37505635355511e-07, "loss": 0.0089, "step": 16585 }, { "epoch": 0.9159487519328473, "grad_norm": 3.719905138015747, "learning_rate": 7.36543449428515e-07, "loss": 0.7262, "step": 16586 }, { "epoch": 0.9160039761431411, "grad_norm": 0.11686144024133682, "learning_rate": 7.35581879794336e-07, "loss": 0.0046, "step": 16587 }, { "epoch": 0.9160592003534349, "grad_norm": 5.248548984527588, "learning_rate": 7.346209264837334e-07, "loss": 0.5361, "step": 16588 }, { "epoch": 0.9161144245637287, "grad_norm": 2.3926849365234375, "learning_rate": 7.336605895274585e-07, "loss": 0.2716, "step": 16589 }, { "epoch": 0.9161696487740225, "grad_norm": 0.03873482346534729, "learning_rate": 7.327008689562242e-07, "loss": 0.0015, "step": 16590 }, { "epoch": 0.9162248729843163, "grad_norm": 0.14044611155986786, "learning_rate": 7.317417648007441e-07, "loss": 0.0025, "step": 16591 }, { "epoch": 0.9162800971946101, "grad_norm": 0.08599545806646347, "learning_rate": 7.307832770917001e-07, "loss": 0.0018, "step": 16592 }, { "epoch": 0.9163353214049039, "grad_norm": 2.5584523677825928, "learning_rate": 7.298254058597542e-07, "loss": 0.1928, "step": 16593 }, { "epoch": 0.9163905456151977, "grad_norm": 3.0795810222625732, "learning_rate": 7.288681511355533e-07, "loss": 0.1802, "step": 16594 }, { "epoch": 0.9164457698254915, "grad_norm": 0.14713309705257416, "learning_rate": 7.279115129497238e-07, "loss": 0.0029, "step": 16595 }, { "epoch": 0.9165009940357853, "grad_norm": 0.04595598578453064, "learning_rate": 7.269554913328703e-07, "loss": 0.0013, "step": 16596 }, { "epoch": 0.9165562182460791, "grad_norm": 3.5123255252838135, "learning_rate": 7.26000086315577e-07, "loss": 0.2503, "step": 16597 }, { "epoch": 0.9166114424563728, "grad_norm": 4.159427642822266, "learning_rate": 7.250452979284106e-07, "loss": 0.7942, "step": 16598 }, { "epoch": 0.9166666666666666, "grad_norm": 1.7104501724243164, "learning_rate": 7.240911262019246e-07, "loss": 0.0346, "step": 16599 }, { "epoch": 0.9167218908769604, "grad_norm": 3.3934316635131836, "learning_rate": 7.231375711666322e-07, "loss": 0.4291, "step": 16600 }, { "epoch": 0.9167771150872542, "grad_norm": 1.5250170230865479, "learning_rate": 7.221846328530513e-07, "loss": 0.0562, "step": 16601 }, { "epoch": 0.916832339297548, "grad_norm": 1.7782750129699707, "learning_rate": 7.212323112916663e-07, "loss": 0.0231, "step": 16602 }, { "epoch": 0.9168875635078418, "grad_norm": 2.1187381744384766, "learning_rate": 7.202806065129419e-07, "loss": 0.0975, "step": 16603 }, { "epoch": 0.9169427877181356, "grad_norm": 5.96525764465332, "learning_rate": 7.19329518547327e-07, "loss": 0.8385, "step": 16604 }, { "epoch": 0.9169980119284294, "grad_norm": 3.223936080932617, "learning_rate": 7.18379047425255e-07, "loss": 0.3475, "step": 16605 }, { "epoch": 0.9170532361387232, "grad_norm": 0.05355917662382126, "learning_rate": 7.17429193177126e-07, "loss": 0.0015, "step": 16606 }, { "epoch": 0.917108460349017, "grad_norm": 0.13600391149520874, "learning_rate": 7.164799558333313e-07, "loss": 0.0033, "step": 16607 }, { "epoch": 0.9171636845593109, "grad_norm": 2.4312829971313477, "learning_rate": 7.155313354242421e-07, "loss": 0.1059, "step": 16608 }, { "epoch": 0.9172189087696045, "grad_norm": 0.023056266829371452, "learning_rate": 7.145833319802076e-07, "loss": 0.0005, "step": 16609 }, { "epoch": 0.9172741329798983, "grad_norm": 3.1932430267333984, "learning_rate": 7.136359455315522e-07, "loss": 0.3137, "step": 16610 }, { "epoch": 0.9173293571901922, "grad_norm": 3.814830780029297, "learning_rate": 7.126891761085897e-07, "loss": 0.0929, "step": 16611 }, { "epoch": 0.917384581400486, "grad_norm": 0.3688267171382904, "learning_rate": 7.117430237416112e-07, "loss": 0.008, "step": 16612 }, { "epoch": 0.9174398056107798, "grad_norm": 0.061332110315561295, "learning_rate": 7.107974884608815e-07, "loss": 0.0013, "step": 16613 }, { "epoch": 0.9174950298210736, "grad_norm": 5.243494033813477, "learning_rate": 7.098525702966563e-07, "loss": 0.4432, "step": 16614 }, { "epoch": 0.9175502540313674, "grad_norm": 0.02816895954310894, "learning_rate": 7.089082692791627e-07, "loss": 0.0007, "step": 16615 }, { "epoch": 0.9176054782416612, "grad_norm": 5.83675479888916, "learning_rate": 7.079645854386141e-07, "loss": 0.7312, "step": 16616 }, { "epoch": 0.917660702451955, "grad_norm": 6.5423479080200195, "learning_rate": 7.070215188051977e-07, "loss": 0.9335, "step": 16617 }, { "epoch": 0.9177159266622488, "grad_norm": 0.03822436183691025, "learning_rate": 7.060790694090891e-07, "loss": 0.0011, "step": 16618 }, { "epoch": 0.9177711508725426, "grad_norm": 3.3701419830322266, "learning_rate": 7.051372372804399e-07, "loss": 0.6572, "step": 16619 }, { "epoch": 0.9178263750828363, "grad_norm": 5.0883026123046875, "learning_rate": 7.041960224493794e-07, "loss": 0.3311, "step": 16620 }, { "epoch": 0.9178815992931301, "grad_norm": 1.116039514541626, "learning_rate": 7.03255424946021e-07, "loss": 0.1922, "step": 16621 }, { "epoch": 0.9179368235034239, "grad_norm": 3.1277284622192383, "learning_rate": 7.023154448004588e-07, "loss": 0.3795, "step": 16622 }, { "epoch": 0.9179920477137177, "grad_norm": 2.8701870441436768, "learning_rate": 7.013760820427595e-07, "loss": 0.0685, "step": 16623 }, { "epoch": 0.9180472719240115, "grad_norm": 0.03159778565168381, "learning_rate": 7.004373367029816e-07, "loss": 0.0008, "step": 16624 }, { "epoch": 0.9181024961343053, "grad_norm": 5.857203483581543, "learning_rate": 6.994992088111585e-07, "loss": 1.1017, "step": 16625 }, { "epoch": 0.9181577203445991, "grad_norm": 0.020533986389636993, "learning_rate": 6.98561698397302e-07, "loss": 0.0007, "step": 16626 }, { "epoch": 0.9182129445548929, "grad_norm": 0.021564677357673645, "learning_rate": 6.976248054914015e-07, "loss": 0.0005, "step": 16627 }, { "epoch": 0.9182681687651867, "grad_norm": 1.5921779870986938, "learning_rate": 6.966885301234394e-07, "loss": 0.0288, "step": 16628 }, { "epoch": 0.9183233929754805, "grad_norm": 0.03947928175330162, "learning_rate": 6.957528723233631e-07, "loss": 0.001, "step": 16629 }, { "epoch": 0.9183786171857743, "grad_norm": 1.5085042715072632, "learning_rate": 6.948178321211086e-07, "loss": 0.0788, "step": 16630 }, { "epoch": 0.918433841396068, "grad_norm": 2.3403103351593018, "learning_rate": 6.938834095465941e-07, "loss": 0.4106, "step": 16631 }, { "epoch": 0.9184890656063618, "grad_norm": 0.312065988779068, "learning_rate": 6.929496046297091e-07, "loss": 0.0074, "step": 16632 }, { "epoch": 0.9185442898166556, "grad_norm": 1.3667960166931152, "learning_rate": 6.920164174003296e-07, "loss": 0.03, "step": 16633 }, { "epoch": 0.9185995140269494, "grad_norm": 3.9039645195007324, "learning_rate": 6.910838478883142e-07, "loss": 0.2, "step": 16634 }, { "epoch": 0.9186547382372432, "grad_norm": 5.4981207847595215, "learning_rate": 6.901518961234965e-07, "loss": 1.0372, "step": 16635 }, { "epoch": 0.918709962447537, "grad_norm": 0.11018835008144379, "learning_rate": 6.892205621356929e-07, "loss": 0.0026, "step": 16636 }, { "epoch": 0.9187651866578308, "grad_norm": 0.4371873438358307, "learning_rate": 6.882898459546949e-07, "loss": 0.0109, "step": 16637 }, { "epoch": 0.9188204108681246, "grad_norm": 0.0330277681350708, "learning_rate": 6.8735974761029e-07, "loss": 0.0012, "step": 16638 }, { "epoch": 0.9188756350784184, "grad_norm": 0.7084099650382996, "learning_rate": 6.864302671322209e-07, "loss": 0.019, "step": 16639 }, { "epoch": 0.9189308592887122, "grad_norm": 0.07736395299434662, "learning_rate": 6.855014045502329e-07, "loss": 0.0018, "step": 16640 }, { "epoch": 0.918986083499006, "grad_norm": 3.640275478363037, "learning_rate": 6.845731598940419e-07, "loss": 0.0595, "step": 16641 }, { "epoch": 0.9190413077092997, "grad_norm": 2.9912898540496826, "learning_rate": 6.836455331933445e-07, "loss": 0.4554, "step": 16642 }, { "epoch": 0.9190965319195935, "grad_norm": 0.047191355377435684, "learning_rate": 6.827185244778145e-07, "loss": 0.0016, "step": 16643 }, { "epoch": 0.9191517561298873, "grad_norm": 0.04433136060833931, "learning_rate": 6.817921337771172e-07, "loss": 0.0011, "step": 16644 }, { "epoch": 0.9192069803401811, "grad_norm": 0.4243965148925781, "learning_rate": 6.808663611208822e-07, "loss": 0.0069, "step": 16645 }, { "epoch": 0.9192622045504749, "grad_norm": 0.035075265914201736, "learning_rate": 6.799412065387346e-07, "loss": 0.0011, "step": 16646 }, { "epoch": 0.9193174287607687, "grad_norm": 0.22063100337982178, "learning_rate": 6.790166700602685e-07, "loss": 0.0056, "step": 16647 }, { "epoch": 0.9193726529710625, "grad_norm": 2.038778305053711, "learning_rate": 6.780927517150627e-07, "loss": 0.09, "step": 16648 }, { "epoch": 0.9194278771813563, "grad_norm": 0.0789496973156929, "learning_rate": 6.771694515326754e-07, "loss": 0.0025, "step": 16649 }, { "epoch": 0.9194831013916501, "grad_norm": 1.3407849073410034, "learning_rate": 6.762467695426478e-07, "loss": 0.0551, "step": 16650 }, { "epoch": 0.9195383256019439, "grad_norm": 4.205621719360352, "learning_rate": 6.753247057745005e-07, "loss": 1.0098, "step": 16651 }, { "epoch": 0.9195935498122377, "grad_norm": 3.1016311645507812, "learning_rate": 6.744032602577299e-07, "loss": 0.1315, "step": 16652 }, { "epoch": 0.9196487740225314, "grad_norm": 2.5476393699645996, "learning_rate": 6.734824330218148e-07, "loss": 0.1204, "step": 16653 }, { "epoch": 0.9197039982328252, "grad_norm": 3.308642864227295, "learning_rate": 6.725622240962204e-07, "loss": 0.5715, "step": 16654 }, { "epoch": 0.919759222443119, "grad_norm": 0.9171958565711975, "learning_rate": 6.716426335103788e-07, "loss": 0.0333, "step": 16655 }, { "epoch": 0.9198144466534128, "grad_norm": 0.10419999063014984, "learning_rate": 6.707236612937173e-07, "loss": 0.002, "step": 16656 }, { "epoch": 0.9198696708637066, "grad_norm": 0.06199244037270546, "learning_rate": 6.69805307475635e-07, "loss": 0.0017, "step": 16657 }, { "epoch": 0.9199248950740004, "grad_norm": 0.02285827323794365, "learning_rate": 6.688875720855104e-07, "loss": 0.0004, "step": 16658 }, { "epoch": 0.9199801192842942, "grad_norm": 2.6003611087799072, "learning_rate": 6.679704551527022e-07, "loss": 0.4174, "step": 16659 }, { "epoch": 0.920035343494588, "grad_norm": 0.7040802240371704, "learning_rate": 6.670539567065604e-07, "loss": 0.0172, "step": 16660 }, { "epoch": 0.9200905677048818, "grad_norm": 3.584092378616333, "learning_rate": 6.661380767763992e-07, "loss": 0.4455, "step": 16661 }, { "epoch": 0.9201457919151756, "grad_norm": 0.05551537126302719, "learning_rate": 6.652228153915197e-07, "loss": 0.0015, "step": 16662 }, { "epoch": 0.9202010161254695, "grad_norm": 0.9769503474235535, "learning_rate": 6.643081725812095e-07, "loss": 0.0208, "step": 16663 }, { "epoch": 0.9202562403357633, "grad_norm": 0.061906516551971436, "learning_rate": 6.633941483747253e-07, "loss": 0.0016, "step": 16664 }, { "epoch": 0.920311464546057, "grad_norm": 2.5812177658081055, "learning_rate": 6.624807428013125e-07, "loss": 0.5, "step": 16665 }, { "epoch": 0.9203666887563507, "grad_norm": 6.247001647949219, "learning_rate": 6.615679558901877e-07, "loss": 0.2837, "step": 16666 }, { "epoch": 0.9204219129666446, "grad_norm": 1.393880009651184, "learning_rate": 6.606557876705655e-07, "loss": 0.0382, "step": 16667 }, { "epoch": 0.9204771371769384, "grad_norm": 3.1512529850006104, "learning_rate": 6.597442381716157e-07, "loss": 0.0296, "step": 16668 }, { "epoch": 0.9205323613872322, "grad_norm": 2.1719818115234375, "learning_rate": 6.588333074225084e-07, "loss": 0.1609, "step": 16669 }, { "epoch": 0.920587585597526, "grad_norm": 0.1526959091424942, "learning_rate": 6.579229954523847e-07, "loss": 0.0036, "step": 16670 }, { "epoch": 0.9206428098078198, "grad_norm": 0.06616459041833878, "learning_rate": 6.570133022903702e-07, "loss": 0.0017, "step": 16671 }, { "epoch": 0.9206980340181136, "grad_norm": 3.402496576309204, "learning_rate": 6.56104227965566e-07, "loss": 0.0309, "step": 16672 }, { "epoch": 0.9207532582284074, "grad_norm": 0.0719727948307991, "learning_rate": 6.551957725070579e-07, "loss": 0.002, "step": 16673 }, { "epoch": 0.9208084824387012, "grad_norm": 4.897064685821533, "learning_rate": 6.542879359439092e-07, "loss": 1.2557, "step": 16674 }, { "epoch": 0.920863706648995, "grad_norm": 0.09959422051906586, "learning_rate": 6.533807183051654e-07, "loss": 0.0018, "step": 16675 }, { "epoch": 0.9209189308592887, "grad_norm": 0.10442168265581131, "learning_rate": 6.524741196198458e-07, "loss": 0.002, "step": 16676 }, { "epoch": 0.9209741550695825, "grad_norm": 3.1250317096710205, "learning_rate": 6.515681399169649e-07, "loss": 0.2542, "step": 16677 }, { "epoch": 0.9210293792798763, "grad_norm": 1.8321651220321655, "learning_rate": 6.506627792254972e-07, "loss": 0.5259, "step": 16678 }, { "epoch": 0.9210846034901701, "grad_norm": 3.1310577392578125, "learning_rate": 6.497580375744128e-07, "loss": 0.5591, "step": 16679 }, { "epoch": 0.9211398277004639, "grad_norm": 6.760473728179932, "learning_rate": 6.488539149926576e-07, "loss": 1.012, "step": 16680 }, { "epoch": 0.9211950519107577, "grad_norm": 0.27914485335350037, "learning_rate": 6.479504115091573e-07, "loss": 0.0062, "step": 16681 }, { "epoch": 0.9212502761210515, "grad_norm": 2.863591432571411, "learning_rate": 6.470475271528132e-07, "loss": 0.2205, "step": 16682 }, { "epoch": 0.9213055003313453, "grad_norm": 0.0328885093331337, "learning_rate": 6.461452619525177e-07, "loss": 0.0007, "step": 16683 }, { "epoch": 0.9213607245416391, "grad_norm": 1.0521527528762817, "learning_rate": 6.4524361593713e-07, "loss": 0.0304, "step": 16684 }, { "epoch": 0.9214159487519329, "grad_norm": 3.349987506866455, "learning_rate": 6.443425891355004e-07, "loss": 0.3261, "step": 16685 }, { "epoch": 0.9214711729622267, "grad_norm": 3.936260223388672, "learning_rate": 6.434421815764547e-07, "loss": 0.3391, "step": 16686 }, { "epoch": 0.9215263971725204, "grad_norm": 2.9342639446258545, "learning_rate": 6.425423932888009e-07, "loss": 0.2475, "step": 16687 }, { "epoch": 0.9215816213828142, "grad_norm": 0.010808706283569336, "learning_rate": 6.416432243013204e-07, "loss": 0.0003, "step": 16688 }, { "epoch": 0.921636845593108, "grad_norm": 3.0543296337127686, "learning_rate": 6.407446746427859e-07, "loss": 0.2787, "step": 16689 }, { "epoch": 0.9216920698034018, "grad_norm": 0.19377972185611725, "learning_rate": 6.398467443419431e-07, "loss": 0.0053, "step": 16690 }, { "epoch": 0.9217472940136956, "grad_norm": 0.14816294610500336, "learning_rate": 6.389494334275204e-07, "loss": 0.0033, "step": 16691 }, { "epoch": 0.9218025182239894, "grad_norm": 0.2249024659395218, "learning_rate": 6.380527419282212e-07, "loss": 0.003, "step": 16692 }, { "epoch": 0.9218577424342832, "grad_norm": 0.16433291137218475, "learning_rate": 6.371566698727382e-07, "loss": 0.0017, "step": 16693 }, { "epoch": 0.921912966644577, "grad_norm": 4.3554277420043945, "learning_rate": 6.362612172897331e-07, "loss": 0.8098, "step": 16694 }, { "epoch": 0.9219681908548708, "grad_norm": 5.009607791900635, "learning_rate": 6.353663842078605e-07, "loss": 0.302, "step": 16695 }, { "epoch": 0.9220234150651646, "grad_norm": 1.6299195289611816, "learning_rate": 6.344721706557466e-07, "loss": 0.1462, "step": 16696 }, { "epoch": 0.9220786392754584, "grad_norm": 0.03535497933626175, "learning_rate": 6.335785766619973e-07, "loss": 0.0013, "step": 16697 }, { "epoch": 0.9221338634857521, "grad_norm": 0.2683374285697937, "learning_rate": 6.32685602255203e-07, "loss": 0.0045, "step": 16698 }, { "epoch": 0.9221890876960459, "grad_norm": 4.727549076080322, "learning_rate": 6.317932474639343e-07, "loss": 0.9995, "step": 16699 }, { "epoch": 0.9222443119063397, "grad_norm": 0.7165716886520386, "learning_rate": 6.309015123167372e-07, "loss": 0.0177, "step": 16700 }, { "epoch": 0.9222995361166335, "grad_norm": 2.310436964035034, "learning_rate": 6.300103968421445e-07, "loss": 0.1019, "step": 16701 }, { "epoch": 0.9223547603269273, "grad_norm": 0.07473864406347275, "learning_rate": 6.2911990106866e-07, "loss": 0.0027, "step": 16702 }, { "epoch": 0.9224099845372211, "grad_norm": 0.3889129161834717, "learning_rate": 6.282300250247786e-07, "loss": 0.008, "step": 16703 }, { "epoch": 0.9224652087475149, "grad_norm": 2.7226619720458984, "learning_rate": 6.273407687389643e-07, "loss": 0.5054, "step": 16704 }, { "epoch": 0.9225204329578087, "grad_norm": 1.4065732955932617, "learning_rate": 6.264521322396722e-07, "loss": 0.0653, "step": 16705 }, { "epoch": 0.9225756571681025, "grad_norm": 7.280086994171143, "learning_rate": 6.255641155553327e-07, "loss": 1.6158, "step": 16706 }, { "epoch": 0.9226308813783963, "grad_norm": 0.037016451358795166, "learning_rate": 6.246767187143521e-07, "loss": 0.001, "step": 16707 }, { "epoch": 0.9226861055886901, "grad_norm": 0.13217952847480774, "learning_rate": 6.237899417451188e-07, "loss": 0.0038, "step": 16708 }, { "epoch": 0.9227413297989838, "grad_norm": 0.04877551645040512, "learning_rate": 6.229037846760144e-07, "loss": 0.0019, "step": 16709 }, { "epoch": 0.9227965540092776, "grad_norm": 0.040871407836675644, "learning_rate": 6.220182475353764e-07, "loss": 0.001, "step": 16710 }, { "epoch": 0.9228517782195714, "grad_norm": 6.524911403656006, "learning_rate": 6.211333303515421e-07, "loss": 0.8132, "step": 16711 }, { "epoch": 0.9229070024298652, "grad_norm": 0.02015470154583454, "learning_rate": 6.202490331528221e-07, "loss": 0.0005, "step": 16712 }, { "epoch": 0.922962226640159, "grad_norm": 0.015970028936862946, "learning_rate": 6.193653559675095e-07, "loss": 0.0005, "step": 16713 }, { "epoch": 0.9230174508504528, "grad_norm": 0.1354099065065384, "learning_rate": 6.184822988238681e-07, "loss": 0.004, "step": 16714 }, { "epoch": 0.9230726750607466, "grad_norm": 4.664285182952881, "learning_rate": 6.1759986175016e-07, "loss": 1.125, "step": 16715 }, { "epoch": 0.9231278992710404, "grad_norm": 0.049034975469112396, "learning_rate": 6.167180447746091e-07, "loss": 0.0011, "step": 16716 }, { "epoch": 0.9231831234813342, "grad_norm": 0.1879921704530716, "learning_rate": 6.158368479254306e-07, "loss": 0.0047, "step": 16717 }, { "epoch": 0.923238347691628, "grad_norm": 0.4968677759170532, "learning_rate": 6.149562712308132e-07, "loss": 0.0085, "step": 16718 }, { "epoch": 0.9232935719019219, "grad_norm": 2.923978090286255, "learning_rate": 6.140763147189366e-07, "loss": 0.2103, "step": 16719 }, { "epoch": 0.9233487961122155, "grad_norm": 6.172431468963623, "learning_rate": 6.131969784179425e-07, "loss": 0.193, "step": 16720 }, { "epoch": 0.9234040203225093, "grad_norm": 0.5933625102043152, "learning_rate": 6.123182623559709e-07, "loss": 0.0172, "step": 16721 }, { "epoch": 0.9234592445328031, "grad_norm": 1.1387983560562134, "learning_rate": 6.114401665611347e-07, "loss": 0.0489, "step": 16722 }, { "epoch": 0.923514468743097, "grad_norm": 3.8385910987854004, "learning_rate": 6.105626910615225e-07, "loss": 0.9743, "step": 16723 }, { "epoch": 0.9235696929533908, "grad_norm": 2.3174097537994385, "learning_rate": 6.096858358852076e-07, "loss": 0.0092, "step": 16724 }, { "epoch": 0.9236249171636846, "grad_norm": 0.42505207657814026, "learning_rate": 6.088096010602473e-07, "loss": 0.0104, "step": 16725 }, { "epoch": 0.9236801413739784, "grad_norm": 0.3391355276107788, "learning_rate": 6.079339866146705e-07, "loss": 0.008, "step": 16726 }, { "epoch": 0.9237353655842722, "grad_norm": 3.7849316596984863, "learning_rate": 6.070589925764903e-07, "loss": 0.3977, "step": 16727 }, { "epoch": 0.923790589794566, "grad_norm": 2.6003384590148926, "learning_rate": 6.061846189737064e-07, "loss": 0.1692, "step": 16728 }, { "epoch": 0.9238458140048598, "grad_norm": 2.2139768600463867, "learning_rate": 6.053108658342854e-07, "loss": 0.1998, "step": 16729 }, { "epoch": 0.9239010382151536, "grad_norm": 0.16348768770694733, "learning_rate": 6.04437733186185e-07, "loss": 0.0065, "step": 16730 }, { "epoch": 0.9239562624254473, "grad_norm": 4.904654502868652, "learning_rate": 6.035652210573362e-07, "loss": 0.1198, "step": 16731 }, { "epoch": 0.9240114866357411, "grad_norm": 0.1469876915216446, "learning_rate": 6.02693329475661e-07, "loss": 0.0042, "step": 16732 }, { "epoch": 0.9240667108460349, "grad_norm": 0.9417790174484253, "learning_rate": 6.018220584690415e-07, "loss": 0.0141, "step": 16733 }, { "epoch": 0.9241219350563287, "grad_norm": 0.18381062150001526, "learning_rate": 6.009514080653622e-07, "loss": 0.0053, "step": 16734 }, { "epoch": 0.9241771592666225, "grad_norm": 0.13568709790706635, "learning_rate": 6.000813782924719e-07, "loss": 0.0032, "step": 16735 }, { "epoch": 0.9242323834769163, "grad_norm": 0.04580230265855789, "learning_rate": 5.992119691782083e-07, "loss": 0.0017, "step": 16736 }, { "epoch": 0.9242876076872101, "grad_norm": 0.0967702716588974, "learning_rate": 5.983431807503848e-07, "loss": 0.0023, "step": 16737 }, { "epoch": 0.9243428318975039, "grad_norm": 0.13449741899967194, "learning_rate": 5.974750130367968e-07, "loss": 0.0038, "step": 16738 }, { "epoch": 0.9243980561077977, "grad_norm": 3.6773436069488525, "learning_rate": 5.966074660652221e-07, "loss": 0.542, "step": 16739 }, { "epoch": 0.9244532803180915, "grad_norm": 0.07603444904088974, "learning_rate": 5.95740539863412e-07, "loss": 0.0023, "step": 16740 }, { "epoch": 0.9245085045283853, "grad_norm": 0.03763465955853462, "learning_rate": 5.948742344591041e-07, "loss": 0.0009, "step": 16741 }, { "epoch": 0.9245637287386791, "grad_norm": 4.5858964920043945, "learning_rate": 5.940085498800119e-07, "loss": 0.2503, "step": 16742 }, { "epoch": 0.9246189529489728, "grad_norm": 1.518598198890686, "learning_rate": 5.93143486153831e-07, "loss": 0.0685, "step": 16743 }, { "epoch": 0.9246741771592666, "grad_norm": 2.030111789703369, "learning_rate": 5.922790433082437e-07, "loss": 0.3971, "step": 16744 }, { "epoch": 0.9247294013695604, "grad_norm": 0.165886789560318, "learning_rate": 5.91415221370899e-07, "loss": 0.0018, "step": 16745 }, { "epoch": 0.9247846255798542, "grad_norm": 2.4148638248443604, "learning_rate": 5.905520203694348e-07, "loss": 0.0646, "step": 16746 }, { "epoch": 0.924839849790148, "grad_norm": 0.890432596206665, "learning_rate": 5.896894403314646e-07, "loss": 0.0372, "step": 16747 }, { "epoch": 0.9248950740004418, "grad_norm": 2.2792088985443115, "learning_rate": 5.888274812845951e-07, "loss": 0.0836, "step": 16748 }, { "epoch": 0.9249502982107356, "grad_norm": 4.496132850646973, "learning_rate": 5.879661432563887e-07, "loss": 0.8728, "step": 16749 }, { "epoch": 0.9250055224210294, "grad_norm": 2.2154183387756348, "learning_rate": 5.871054262744125e-07, "loss": 0.1066, "step": 16750 }, { "epoch": 0.9250607466313232, "grad_norm": 3.845121145248413, "learning_rate": 5.862453303661997e-07, "loss": 0.5351, "step": 16751 }, { "epoch": 0.925115970841617, "grad_norm": 6.776951313018799, "learning_rate": 5.853858555592662e-07, "loss": 0.331, "step": 16752 }, { "epoch": 0.9251711950519108, "grad_norm": 0.009234242141246796, "learning_rate": 5.8452700188111e-07, "loss": 0.0002, "step": 16753 }, { "epoch": 0.9252264192622045, "grad_norm": 0.42341965436935425, "learning_rate": 5.836687693592091e-07, "loss": 0.0061, "step": 16754 }, { "epoch": 0.9252816434724983, "grad_norm": 3.6058349609375, "learning_rate": 5.828111580210216e-07, "loss": 0.5359, "step": 16755 }, { "epoch": 0.9253368676827921, "grad_norm": 3.3580543994903564, "learning_rate": 5.819541678939811e-07, "loss": 0.9601, "step": 16756 }, { "epoch": 0.9253920918930859, "grad_norm": 3.993454933166504, "learning_rate": 5.810977990055078e-07, "loss": 0.6447, "step": 16757 }, { "epoch": 0.9254473161033797, "grad_norm": 2.82354998588562, "learning_rate": 5.802420513830021e-07, "loss": 0.1335, "step": 16758 }, { "epoch": 0.9255025403136735, "grad_norm": 1.9016225337982178, "learning_rate": 5.793869250538331e-07, "loss": 0.0953, "step": 16759 }, { "epoch": 0.9255577645239673, "grad_norm": 0.16570435464382172, "learning_rate": 5.78532420045368e-07, "loss": 0.0052, "step": 16760 }, { "epoch": 0.9256129887342611, "grad_norm": 1.7200113534927368, "learning_rate": 5.776785363849424e-07, "loss": 0.3692, "step": 16761 }, { "epoch": 0.9256682129445549, "grad_norm": 0.07969672232866287, "learning_rate": 5.768252740998703e-07, "loss": 0.0018, "step": 16762 }, { "epoch": 0.9257234371548487, "grad_norm": 4.524768352508545, "learning_rate": 5.759726332174542e-07, "loss": 0.2236, "step": 16763 }, { "epoch": 0.9257786613651425, "grad_norm": 0.6163269281387329, "learning_rate": 5.751206137649745e-07, "loss": 0.0144, "step": 16764 }, { "epoch": 0.9258338855754362, "grad_norm": 0.004074509721249342, "learning_rate": 5.742692157696805e-07, "loss": 0.0001, "step": 16765 }, { "epoch": 0.92588910978573, "grad_norm": 2.0577993392944336, "learning_rate": 5.734184392588216e-07, "loss": 0.3184, "step": 16766 }, { "epoch": 0.9259443339960238, "grad_norm": 11.11522102355957, "learning_rate": 5.725682842596092e-07, "loss": 0.4764, "step": 16767 }, { "epoch": 0.9259995582063176, "grad_norm": 0.09470651298761368, "learning_rate": 5.717187507992461e-07, "loss": 0.002, "step": 16768 }, { "epoch": 0.9260547824166114, "grad_norm": 0.04888560622930527, "learning_rate": 5.708698389049083e-07, "loss": 0.0011, "step": 16769 }, { "epoch": 0.9261100066269052, "grad_norm": 0.46794235706329346, "learning_rate": 5.700215486037586e-07, "loss": 0.0141, "step": 16770 }, { "epoch": 0.926165230837199, "grad_norm": 0.05884028598666191, "learning_rate": 5.691738799229351e-07, "loss": 0.0015, "step": 16771 }, { "epoch": 0.9262204550474928, "grad_norm": 1.126383662223816, "learning_rate": 5.683268328895542e-07, "loss": 0.0392, "step": 16772 }, { "epoch": 0.9262756792577866, "grad_norm": 0.434074342250824, "learning_rate": 5.674804075307183e-07, "loss": 0.0084, "step": 16773 }, { "epoch": 0.9263309034680804, "grad_norm": 0.07142035663127899, "learning_rate": 5.666346038735082e-07, "loss": 0.0027, "step": 16774 }, { "epoch": 0.9263861276783742, "grad_norm": 2.785151243209839, "learning_rate": 5.657894219449778e-07, "loss": 0.4177, "step": 16775 }, { "epoch": 0.9264413518886679, "grad_norm": 0.5861867666244507, "learning_rate": 5.64944861772172e-07, "loss": 0.012, "step": 16776 }, { "epoch": 0.9264965760989617, "grad_norm": 0.8493958115577698, "learning_rate": 5.641009233821094e-07, "loss": 0.1213, "step": 16777 }, { "epoch": 0.9265518003092555, "grad_norm": 3.2569305896759033, "learning_rate": 5.632576068017903e-07, "loss": 0.4125, "step": 16778 }, { "epoch": 0.9266070245195493, "grad_norm": 0.5806808471679688, "learning_rate": 5.624149120581912e-07, "loss": 0.0205, "step": 16779 }, { "epoch": 0.9266622487298432, "grad_norm": 1.707209825515747, "learning_rate": 5.615728391782771e-07, "loss": 0.0548, "step": 16780 }, { "epoch": 0.926717472940137, "grad_norm": 0.8113104701042175, "learning_rate": 5.607313881889886e-07, "loss": 0.0168, "step": 16781 }, { "epoch": 0.9267726971504308, "grad_norm": 2.536806583404541, "learning_rate": 5.598905591172444e-07, "loss": 0.2386, "step": 16782 }, { "epoch": 0.9268279213607246, "grad_norm": 3.6005353927612305, "learning_rate": 5.590503519899426e-07, "loss": 0.536, "step": 16783 }, { "epoch": 0.9268831455710184, "grad_norm": 0.005144637543708086, "learning_rate": 5.582107668339665e-07, "loss": 0.0001, "step": 16784 }, { "epoch": 0.9269383697813122, "grad_norm": 1.6171250343322754, "learning_rate": 5.573718036761766e-07, "loss": 0.0399, "step": 16785 }, { "epoch": 0.926993593991606, "grad_norm": 1.4236174821853638, "learning_rate": 5.565334625434116e-07, "loss": 0.1988, "step": 16786 }, { "epoch": 0.9270488182018997, "grad_norm": 2.6453535556793213, "learning_rate": 5.556957434624988e-07, "loss": 0.0718, "step": 16787 }, { "epoch": 0.9271040424121935, "grad_norm": 0.043067216873168945, "learning_rate": 5.548586464602302e-07, "loss": 0.0012, "step": 16788 }, { "epoch": 0.9271592666224873, "grad_norm": 2.5414886474609375, "learning_rate": 5.540221715633931e-07, "loss": 0.4703, "step": 16789 }, { "epoch": 0.9272144908327811, "grad_norm": 0.10673477500677109, "learning_rate": 5.531863187987463e-07, "loss": 0.0027, "step": 16790 }, { "epoch": 0.9272697150430749, "grad_norm": 0.5036810636520386, "learning_rate": 5.523510881930327e-07, "loss": 0.0171, "step": 16791 }, { "epoch": 0.9273249392533687, "grad_norm": 2.9584105014801025, "learning_rate": 5.51516479772971e-07, "loss": 0.2625, "step": 16792 }, { "epoch": 0.9273801634636625, "grad_norm": 1.4997152090072632, "learning_rate": 5.506824935652666e-07, "loss": 0.1219, "step": 16793 }, { "epoch": 0.9274353876739563, "grad_norm": 3.0680952072143555, "learning_rate": 5.49849129596598e-07, "loss": 0.2333, "step": 16794 }, { "epoch": 0.9274906118842501, "grad_norm": 2.4125492572784424, "learning_rate": 5.490163878936283e-07, "loss": 0.2022, "step": 16795 }, { "epoch": 0.9275458360945439, "grad_norm": 1.4378554821014404, "learning_rate": 5.481842684829985e-07, "loss": 0.0363, "step": 16796 }, { "epoch": 0.9276010603048377, "grad_norm": 1.314099669456482, "learning_rate": 5.473527713913318e-07, "loss": 0.0327, "step": 16797 }, { "epoch": 0.9276562845151314, "grad_norm": 2.2410333156585693, "learning_rate": 5.465218966452268e-07, "loss": 0.4149, "step": 16798 }, { "epoch": 0.9277115087254252, "grad_norm": 0.4989066421985626, "learning_rate": 5.456916442712712e-07, "loss": 0.0156, "step": 16799 }, { "epoch": 0.927766732935719, "grad_norm": 0.044022541493177414, "learning_rate": 5.448620142960215e-07, "loss": 0.001, "step": 16800 }, { "epoch": 0.9278219571460128, "grad_norm": 0.47879859805107117, "learning_rate": 5.440330067460231e-07, "loss": 0.0078, "step": 16801 }, { "epoch": 0.9278771813563066, "grad_norm": 0.10504338890314102, "learning_rate": 5.432046216477949e-07, "loss": 0.0036, "step": 16802 }, { "epoch": 0.9279324055666004, "grad_norm": 0.07974139600992203, "learning_rate": 5.423768590278466e-07, "loss": 0.0019, "step": 16803 }, { "epoch": 0.9279876297768942, "grad_norm": 4.412519454956055, "learning_rate": 5.415497189126529e-07, "loss": 0.3849, "step": 16804 }, { "epoch": 0.928042853987188, "grad_norm": 0.17592938244342804, "learning_rate": 5.407232013286811e-07, "loss": 0.0041, "step": 16805 }, { "epoch": 0.9280980781974818, "grad_norm": 0.02869502454996109, "learning_rate": 5.398973063023705e-07, "loss": 0.001, "step": 16806 }, { "epoch": 0.9281533024077756, "grad_norm": 3.9108855724334717, "learning_rate": 5.390720338601463e-07, "loss": 0.0754, "step": 16807 }, { "epoch": 0.9282085266180694, "grad_norm": 0.3917466998100281, "learning_rate": 5.382473840284097e-07, "loss": 0.0092, "step": 16808 }, { "epoch": 0.9282637508283631, "grad_norm": 2.951430320739746, "learning_rate": 5.374233568335463e-07, "loss": 0.337, "step": 16809 }, { "epoch": 0.9283189750386569, "grad_norm": 0.030709626153111458, "learning_rate": 5.36599952301915e-07, "loss": 0.0006, "step": 16810 }, { "epoch": 0.9283741992489507, "grad_norm": 1.1264346837997437, "learning_rate": 5.357771704598635e-07, "loss": 0.0285, "step": 16811 }, { "epoch": 0.9284294234592445, "grad_norm": 0.9876548647880554, "learning_rate": 5.349550113337088e-07, "loss": 0.0763, "step": 16812 }, { "epoch": 0.9284846476695383, "grad_norm": 0.09972597658634186, "learning_rate": 5.341334749497629e-07, "loss": 0.0029, "step": 16813 }, { "epoch": 0.9285398718798321, "grad_norm": 0.016470905393362045, "learning_rate": 5.333125613343005e-07, "loss": 0.0005, "step": 16814 }, { "epoch": 0.9285950960901259, "grad_norm": 0.17500260472297668, "learning_rate": 5.324922705135893e-07, "loss": 0.0052, "step": 16815 }, { "epoch": 0.9286503203004197, "grad_norm": 0.5078502297401428, "learning_rate": 5.316726025138729e-07, "loss": 0.014, "step": 16816 }, { "epoch": 0.9287055445107135, "grad_norm": 0.0809388980269432, "learning_rate": 5.308535573613727e-07, "loss": 0.0022, "step": 16817 }, { "epoch": 0.9287607687210073, "grad_norm": 3.762598752975464, "learning_rate": 5.300351350822919e-07, "loss": 0.4305, "step": 16818 }, { "epoch": 0.9288159929313011, "grad_norm": 3.0977141857147217, "learning_rate": 5.292173357028185e-07, "loss": 0.2304, "step": 16819 }, { "epoch": 0.9288712171415949, "grad_norm": 5.473130702972412, "learning_rate": 5.284001592491117e-07, "loss": 0.6588, "step": 16820 }, { "epoch": 0.9289264413518886, "grad_norm": 0.2880627512931824, "learning_rate": 5.275836057473171e-07, "loss": 0.0064, "step": 16821 }, { "epoch": 0.9289816655621824, "grad_norm": 0.11734174191951752, "learning_rate": 5.267676752235606e-07, "loss": 0.0022, "step": 16822 }, { "epoch": 0.9290368897724762, "grad_norm": 0.3846066892147064, "learning_rate": 5.259523677039413e-07, "loss": 0.0075, "step": 16823 }, { "epoch": 0.92909211398277, "grad_norm": 2.4835965633392334, "learning_rate": 5.251376832145449e-07, "loss": 0.1083, "step": 16824 }, { "epoch": 0.9291473381930638, "grad_norm": 0.10940970480442047, "learning_rate": 5.243236217814396e-07, "loss": 0.0034, "step": 16825 }, { "epoch": 0.9292025624033576, "grad_norm": 1.4731734991073608, "learning_rate": 5.235101834306666e-07, "loss": 0.0579, "step": 16826 }, { "epoch": 0.9292577866136514, "grad_norm": 0.14047592878341675, "learning_rate": 5.226973681882474e-07, "loss": 0.0044, "step": 16827 }, { "epoch": 0.9293130108239452, "grad_norm": 3.475902795791626, "learning_rate": 5.218851760801879e-07, "loss": 0.1999, "step": 16828 }, { "epoch": 0.929368235034239, "grad_norm": 0.34171685576438904, "learning_rate": 5.210736071324784e-07, "loss": 0.0067, "step": 16829 }, { "epoch": 0.9294234592445328, "grad_norm": 2.6999588012695312, "learning_rate": 5.202626613710737e-07, "loss": 0.1436, "step": 16830 }, { "epoch": 0.9294786834548266, "grad_norm": 0.09060856699943542, "learning_rate": 5.194523388219263e-07, "loss": 0.002, "step": 16831 }, { "epoch": 0.9295339076651203, "grad_norm": 4.907576560974121, "learning_rate": 5.186426395109557e-07, "loss": 0.7756, "step": 16832 }, { "epoch": 0.9295891318754141, "grad_norm": 0.8078722953796387, "learning_rate": 5.178335634640675e-07, "loss": 0.0199, "step": 16833 }, { "epoch": 0.929644356085708, "grad_norm": 3.4245619773864746, "learning_rate": 5.170251107071456e-07, "loss": 0.779, "step": 16834 }, { "epoch": 0.9296995802960017, "grad_norm": 0.2969193756580353, "learning_rate": 5.162172812660582e-07, "loss": 0.006, "step": 16835 }, { "epoch": 0.9297548045062956, "grad_norm": 3.2493340969085693, "learning_rate": 5.154100751666468e-07, "loss": 0.4597, "step": 16836 }, { "epoch": 0.9298100287165894, "grad_norm": 2.195127010345459, "learning_rate": 5.146034924347376e-07, "loss": 0.0806, "step": 16837 }, { "epoch": 0.9298652529268832, "grad_norm": 0.28630945086479187, "learning_rate": 5.137975330961342e-07, "loss": 0.0112, "step": 16838 }, { "epoch": 0.929920477137177, "grad_norm": 0.0266093872487545, "learning_rate": 5.12992197176625e-07, "loss": 0.0007, "step": 16839 }, { "epoch": 0.9299757013474708, "grad_norm": 0.07876075059175491, "learning_rate": 5.121874847019692e-07, "loss": 0.0012, "step": 16840 }, { "epoch": 0.9300309255577646, "grad_norm": 2.3270177841186523, "learning_rate": 5.113833956979176e-07, "loss": 0.4018, "step": 16841 }, { "epoch": 0.9300861497680584, "grad_norm": 0.01875515840947628, "learning_rate": 5.105799301901915e-07, "loss": 0.0006, "step": 16842 }, { "epoch": 0.9301413739783521, "grad_norm": 1.6100724935531616, "learning_rate": 5.097770882044995e-07, "loss": 0.0583, "step": 16843 }, { "epoch": 0.9301965981886459, "grad_norm": 2.38871431350708, "learning_rate": 5.089748697665209e-07, "loss": 0.3754, "step": 16844 }, { "epoch": 0.9302518223989397, "grad_norm": 0.3566567301750183, "learning_rate": 5.081732749019286e-07, "loss": 0.0072, "step": 16845 }, { "epoch": 0.9303070466092335, "grad_norm": 1.315314769744873, "learning_rate": 5.07372303636362e-07, "loss": 0.0241, "step": 16846 }, { "epoch": 0.9303622708195273, "grad_norm": 3.5047292709350586, "learning_rate": 5.065719559954474e-07, "loss": 0.4298, "step": 16847 }, { "epoch": 0.9304174950298211, "grad_norm": 0.029442016035318375, "learning_rate": 5.057722320047931e-07, "loss": 0.0009, "step": 16848 }, { "epoch": 0.9304727192401149, "grad_norm": 0.005209058057516813, "learning_rate": 5.049731316899831e-07, "loss": 0.0001, "step": 16849 }, { "epoch": 0.9305279434504087, "grad_norm": 6.418768882751465, "learning_rate": 5.041746550765814e-07, "loss": 0.7228, "step": 16850 }, { "epoch": 0.9305831676607025, "grad_norm": 1.9482120275497437, "learning_rate": 5.033768021901319e-07, "loss": 0.0374, "step": 16851 }, { "epoch": 0.9306383918709963, "grad_norm": 4.071282386779785, "learning_rate": 5.025795730561678e-07, "loss": 0.6072, "step": 16852 }, { "epoch": 0.9306936160812901, "grad_norm": 3.1239256858825684, "learning_rate": 5.017829677001862e-07, "loss": 0.5844, "step": 16853 }, { "epoch": 0.9307488402915838, "grad_norm": 4.251073360443115, "learning_rate": 5.009869861476802e-07, "loss": 0.6588, "step": 16854 }, { "epoch": 0.9308040645018776, "grad_norm": 0.4451678395271301, "learning_rate": 5.001916284241093e-07, "loss": 0.0136, "step": 16855 }, { "epoch": 0.9308592887121714, "grad_norm": 4.463320255279541, "learning_rate": 4.993968945549221e-07, "loss": 0.488, "step": 16856 }, { "epoch": 0.9309145129224652, "grad_norm": 0.013930808752775192, "learning_rate": 4.986027845655427e-07, "loss": 0.0004, "step": 16857 }, { "epoch": 0.930969737132759, "grad_norm": 0.8858140110969543, "learning_rate": 4.978092984813798e-07, "loss": 0.0174, "step": 16858 }, { "epoch": 0.9310249613430528, "grad_norm": 0.329466849565506, "learning_rate": 4.970164363278174e-07, "loss": 0.0094, "step": 16859 }, { "epoch": 0.9310801855533466, "grad_norm": 0.5916696786880493, "learning_rate": 4.962241981302218e-07, "loss": 0.0118, "step": 16860 }, { "epoch": 0.9311354097636404, "grad_norm": 5.6728081703186035, "learning_rate": 4.954325839139395e-07, "loss": 0.3007, "step": 16861 }, { "epoch": 0.9311906339739342, "grad_norm": 0.12499221414327621, "learning_rate": 4.946415937042948e-07, "loss": 0.0036, "step": 16862 }, { "epoch": 0.931245858184228, "grad_norm": 0.1099497377872467, "learning_rate": 4.938512275265939e-07, "loss": 0.0024, "step": 16863 }, { "epoch": 0.9313010823945218, "grad_norm": 2.812747001647949, "learning_rate": 4.930614854061255e-07, "loss": 0.3706, "step": 16864 }, { "epoch": 0.9313563066048155, "grad_norm": 6.5292487144470215, "learning_rate": 4.922723673681539e-07, "loss": 0.8847, "step": 16865 }, { "epoch": 0.9314115308151093, "grad_norm": 2.9849483966827393, "learning_rate": 4.914838734379235e-07, "loss": 0.5238, "step": 16866 }, { "epoch": 0.9314667550254031, "grad_norm": 6.488160610198975, "learning_rate": 4.906960036406627e-07, "loss": 0.7349, "step": 16867 }, { "epoch": 0.9315219792356969, "grad_norm": 5.1962080001831055, "learning_rate": 4.899087580015804e-07, "loss": 0.541, "step": 16868 }, { "epoch": 0.9315772034459907, "grad_norm": 4.12929630279541, "learning_rate": 4.891221365458565e-07, "loss": 0.0464, "step": 16869 }, { "epoch": 0.9316324276562845, "grad_norm": 0.7537252306938171, "learning_rate": 4.883361392986619e-07, "loss": 0.0273, "step": 16870 }, { "epoch": 0.9316876518665783, "grad_norm": 0.1274588704109192, "learning_rate": 4.875507662851409e-07, "loss": 0.0026, "step": 16871 }, { "epoch": 0.9317428760768721, "grad_norm": 2.0554988384246826, "learning_rate": 4.867660175304201e-07, "loss": 0.5676, "step": 16872 }, { "epoch": 0.9317981002871659, "grad_norm": 2.7405898571014404, "learning_rate": 4.859818930596061e-07, "loss": 0.2137, "step": 16873 }, { "epoch": 0.9318533244974597, "grad_norm": 0.1903221607208252, "learning_rate": 4.851983928977855e-07, "loss": 0.0049, "step": 16874 }, { "epoch": 0.9319085487077535, "grad_norm": 0.03196239098906517, "learning_rate": 4.844155170700249e-07, "loss": 0.0008, "step": 16875 }, { "epoch": 0.9319637729180472, "grad_norm": 0.05234686657786369, "learning_rate": 4.836332656013709e-07, "loss": 0.002, "step": 16876 }, { "epoch": 0.932018997128341, "grad_norm": 3.6632072925567627, "learning_rate": 4.828516385168458e-07, "loss": 0.4128, "step": 16877 }, { "epoch": 0.9320742213386348, "grad_norm": 0.043109189718961716, "learning_rate": 4.820706358414651e-07, "loss": 0.0008, "step": 16878 }, { "epoch": 0.9321294455489286, "grad_norm": 0.036348771303892136, "learning_rate": 4.812902576002066e-07, "loss": 0.0009, "step": 16879 }, { "epoch": 0.9321846697592224, "grad_norm": 4.298532485961914, "learning_rate": 4.805105038180413e-07, "loss": 0.4629, "step": 16880 }, { "epoch": 0.9322398939695162, "grad_norm": 0.29236429929733276, "learning_rate": 4.797313745199139e-07, "loss": 0.0101, "step": 16881 }, { "epoch": 0.93229511817981, "grad_norm": 0.1072809174656868, "learning_rate": 4.78952869730751e-07, "loss": 0.0033, "step": 16882 }, { "epoch": 0.9323503423901038, "grad_norm": 0.13241083920001984, "learning_rate": 4.781749894754594e-07, "loss": 0.0036, "step": 16883 }, { "epoch": 0.9324055666003976, "grad_norm": 2.941495418548584, "learning_rate": 4.773977337789282e-07, "loss": 0.1668, "step": 16884 }, { "epoch": 0.9324607908106914, "grad_norm": 3.166032552719116, "learning_rate": 4.766211026660195e-07, "loss": 0.1486, "step": 16885 }, { "epoch": 0.9325160150209852, "grad_norm": 0.14790402352809906, "learning_rate": 4.7584509616158457e-07, "loss": 0.0024, "step": 16886 }, { "epoch": 0.932571239231279, "grad_norm": 3.73420786857605, "learning_rate": 4.750697142904459e-07, "loss": 0.8983, "step": 16887 }, { "epoch": 0.9326264634415727, "grad_norm": 2.4740171432495117, "learning_rate": 4.742949570774125e-07, "loss": 0.5552, "step": 16888 }, { "epoch": 0.9326816876518665, "grad_norm": 0.10615197569131851, "learning_rate": 4.735208245472689e-07, "loss": 0.0032, "step": 16889 }, { "epoch": 0.9327369118621603, "grad_norm": 3.1131036281585693, "learning_rate": 4.7274731672478645e-07, "loss": 0.3152, "step": 16890 }, { "epoch": 0.9327921360724541, "grad_norm": 4.066941261291504, "learning_rate": 4.7197443363470984e-07, "loss": 1.0901, "step": 16891 }, { "epoch": 0.932847360282748, "grad_norm": 3.032862901687622, "learning_rate": 4.7120217530176373e-07, "loss": 0.099, "step": 16892 }, { "epoch": 0.9329025844930418, "grad_norm": 0.044803328812122345, "learning_rate": 4.7043054175065274e-07, "loss": 0.0012, "step": 16893 }, { "epoch": 0.9329578087033356, "grad_norm": 2.539633274078369, "learning_rate": 4.696595330060727e-07, "loss": 0.2681, "step": 16894 }, { "epoch": 0.9330130329136294, "grad_norm": 0.1612987071275711, "learning_rate": 4.688891490926795e-07, "loss": 0.0041, "step": 16895 }, { "epoch": 0.9330682571239232, "grad_norm": 0.15897156298160553, "learning_rate": 4.681193900351266e-07, "loss": 0.0026, "step": 16896 }, { "epoch": 0.933123481334217, "grad_norm": 0.02220085635781288, "learning_rate": 4.673502558580412e-07, "loss": 0.0005, "step": 16897 }, { "epoch": 0.9331787055445108, "grad_norm": 0.015805263072252274, "learning_rate": 4.6658174658602564e-07, "loss": 0.0003, "step": 16898 }, { "epoch": 0.9332339297548045, "grad_norm": 1.414103388786316, "learning_rate": 4.658138622436692e-07, "loss": 0.1033, "step": 16899 }, { "epoch": 0.9332891539650983, "grad_norm": 0.21783126890659332, "learning_rate": 4.6504660285554114e-07, "loss": 0.0048, "step": 16900 }, { "epoch": 0.9333443781753921, "grad_norm": 3.0999748706817627, "learning_rate": 4.6427996844618404e-07, "loss": 0.1239, "step": 16901 }, { "epoch": 0.9333996023856859, "grad_norm": 0.4659048318862915, "learning_rate": 4.635139590401272e-07, "loss": 0.0128, "step": 16902 }, { "epoch": 0.9334548265959797, "grad_norm": 2.5480399131774902, "learning_rate": 4.627485746618754e-07, "loss": 0.3706, "step": 16903 }, { "epoch": 0.9335100508062735, "grad_norm": 4.639107704162598, "learning_rate": 4.6198381533591795e-07, "loss": 0.5064, "step": 16904 }, { "epoch": 0.9335652750165673, "grad_norm": 0.01625746674835682, "learning_rate": 4.61219681086722e-07, "loss": 0.0004, "step": 16905 }, { "epoch": 0.9336204992268611, "grad_norm": 0.03603103384375572, "learning_rate": 4.6045617193872793e-07, "loss": 0.0009, "step": 16906 }, { "epoch": 0.9336757234371549, "grad_norm": 0.37056899070739746, "learning_rate": 4.59693287916374e-07, "loss": 0.0112, "step": 16907 }, { "epoch": 0.9337309476474487, "grad_norm": 0.04266537353396416, "learning_rate": 4.5893102904405627e-07, "loss": 0.0012, "step": 16908 }, { "epoch": 0.9337861718577425, "grad_norm": 0.007988004013895988, "learning_rate": 4.5816939534616633e-07, "loss": 0.0003, "step": 16909 }, { "epoch": 0.9338413960680362, "grad_norm": 3.3887832164764404, "learning_rate": 4.574083868470713e-07, "loss": 0.2793, "step": 16910 }, { "epoch": 0.93389662027833, "grad_norm": 3.3831803798675537, "learning_rate": 4.566480035711185e-07, "loss": 0.031, "step": 16911 }, { "epoch": 0.9339518444886238, "grad_norm": 0.034928012639284134, "learning_rate": 4.5588824554263056e-07, "loss": 0.0009, "step": 16912 }, { "epoch": 0.9340070686989176, "grad_norm": 0.1851976364850998, "learning_rate": 4.551291127859192e-07, "loss": 0.0051, "step": 16913 }, { "epoch": 0.9340622929092114, "grad_norm": 0.11017413437366486, "learning_rate": 4.543706053252694e-07, "loss": 0.0031, "step": 16914 }, { "epoch": 0.9341175171195052, "grad_norm": 4.518673419952393, "learning_rate": 4.5361272318494634e-07, "loss": 0.3921, "step": 16915 }, { "epoch": 0.934172741329799, "grad_norm": 3.5411858558654785, "learning_rate": 4.528554663891993e-07, "loss": 0.7242, "step": 16916 }, { "epoch": 0.9342279655400928, "grad_norm": 0.04546471685171127, "learning_rate": 4.520988349622557e-07, "loss": 0.0007, "step": 16917 }, { "epoch": 0.9342831897503866, "grad_norm": 5.339003086090088, "learning_rate": 4.5134282892831836e-07, "loss": 1.3599, "step": 16918 }, { "epoch": 0.9343384139606804, "grad_norm": 2.591188669204712, "learning_rate": 4.5058744831157685e-07, "loss": 0.2187, "step": 16919 }, { "epoch": 0.9343936381709742, "grad_norm": 4.934786319732666, "learning_rate": 4.498326931361985e-07, "loss": 0.5059, "step": 16920 }, { "epoch": 0.9344488623812679, "grad_norm": 4.137408256530762, "learning_rate": 4.490785634263284e-07, "loss": 0.2028, "step": 16921 }, { "epoch": 0.9345040865915617, "grad_norm": 3.420071840286255, "learning_rate": 4.4832505920609393e-07, "loss": 0.7656, "step": 16922 }, { "epoch": 0.9345593108018555, "grad_norm": 1.5134884119033813, "learning_rate": 4.475721804996047e-07, "loss": 0.0563, "step": 16923 }, { "epoch": 0.9346145350121493, "grad_norm": 3.3099470138549805, "learning_rate": 4.4681992733094146e-07, "loss": 0.2529, "step": 16924 }, { "epoch": 0.9346697592224431, "grad_norm": 2.236165761947632, "learning_rate": 4.460682997241761e-07, "loss": 0.1532, "step": 16925 }, { "epoch": 0.9347249834327369, "grad_norm": 4.2950544357299805, "learning_rate": 4.4531729770335155e-07, "loss": 0.3515, "step": 16926 }, { "epoch": 0.9347802076430307, "grad_norm": 0.015564050525426865, "learning_rate": 4.4456692129249743e-07, "loss": 0.0004, "step": 16927 }, { "epoch": 0.9348354318533245, "grad_norm": 4.329183101654053, "learning_rate": 4.4381717051561915e-07, "loss": 0.3297, "step": 16928 }, { "epoch": 0.9348906560636183, "grad_norm": 2.783238172531128, "learning_rate": 4.4306804539670403e-07, "loss": 0.1011, "step": 16929 }, { "epoch": 0.9349458802739121, "grad_norm": 0.18304505944252014, "learning_rate": 4.423195459597174e-07, "loss": 0.0047, "step": 16930 }, { "epoch": 0.9350011044842059, "grad_norm": 4.718583583831787, "learning_rate": 4.4157167222860676e-07, "loss": 1.3187, "step": 16931 }, { "epoch": 0.9350563286944996, "grad_norm": 3.1745529174804688, "learning_rate": 4.4082442422729966e-07, "loss": 0.1924, "step": 16932 }, { "epoch": 0.9351115529047934, "grad_norm": 6.601011276245117, "learning_rate": 4.400778019797014e-07, "loss": 0.8274, "step": 16933 }, { "epoch": 0.9351667771150872, "grad_norm": 8.583577156066895, "learning_rate": 4.3933180550969735e-07, "loss": 0.1559, "step": 16934 }, { "epoch": 0.935222001325381, "grad_norm": 3.6128499507904053, "learning_rate": 4.385864348411573e-07, "loss": 0.3163, "step": 16935 }, { "epoch": 0.9352772255356748, "grad_norm": 0.07558058947324753, "learning_rate": 4.378416899979265e-07, "loss": 0.0021, "step": 16936 }, { "epoch": 0.9353324497459686, "grad_norm": 0.017955629155039787, "learning_rate": 4.3709757100383054e-07, "loss": 0.0006, "step": 16937 }, { "epoch": 0.9353876739562624, "grad_norm": 0.10986360907554626, "learning_rate": 4.363540778826747e-07, "loss": 0.0037, "step": 16938 }, { "epoch": 0.9354428981665562, "grad_norm": 1.36341392993927, "learning_rate": 4.3561121065824885e-07, "loss": 0.0491, "step": 16939 }, { "epoch": 0.93549812237685, "grad_norm": 0.14442403614521027, "learning_rate": 4.3486896935431843e-07, "loss": 0.0041, "step": 16940 }, { "epoch": 0.9355533465871438, "grad_norm": 0.09009407460689545, "learning_rate": 4.3412735399462893e-07, "loss": 0.002, "step": 16941 }, { "epoch": 0.9356085707974376, "grad_norm": 0.009259361773729324, "learning_rate": 4.3338636460290575e-07, "loss": 0.0002, "step": 16942 }, { "epoch": 0.9356637950077313, "grad_norm": 0.012519908137619495, "learning_rate": 4.326460012028566e-07, "loss": 0.0003, "step": 16943 }, { "epoch": 0.9357190192180251, "grad_norm": 3.2916224002838135, "learning_rate": 4.31906263818167e-07, "loss": 0.1222, "step": 16944 }, { "epoch": 0.9357742434283189, "grad_norm": 0.0033104224130511284, "learning_rate": 4.3116715247250474e-07, "loss": 0.0001, "step": 16945 }, { "epoch": 0.9358294676386127, "grad_norm": 2.8009870052337646, "learning_rate": 4.304286671895175e-07, "loss": 0.075, "step": 16946 }, { "epoch": 0.9358846918489065, "grad_norm": 0.028753824532032013, "learning_rate": 4.2969080799282637e-07, "loss": 0.0008, "step": 16947 }, { "epoch": 0.9359399160592003, "grad_norm": 0.0992773100733757, "learning_rate": 4.2895357490603915e-07, "loss": 0.0023, "step": 16948 }, { "epoch": 0.9359951402694942, "grad_norm": 0.008405969478189945, "learning_rate": 4.2821696795274813e-07, "loss": 0.0002, "step": 16949 }, { "epoch": 0.936050364479788, "grad_norm": 5.553352355957031, "learning_rate": 4.2748098715651e-07, "loss": 1.0006, "step": 16950 }, { "epoch": 0.9361055886900818, "grad_norm": 0.021753862500190735, "learning_rate": 4.267456325408792e-07, "loss": 0.0007, "step": 16951 }, { "epoch": 0.9361608129003756, "grad_norm": 0.7792252898216248, "learning_rate": 4.2601090412937696e-07, "loss": 0.0174, "step": 16952 }, { "epoch": 0.9362160371106694, "grad_norm": 0.10014021396636963, "learning_rate": 4.252768019455111e-07, "loss": 0.0022, "step": 16953 }, { "epoch": 0.936271261320963, "grad_norm": 0.2578723728656769, "learning_rate": 4.2454332601276517e-07, "loss": 0.0084, "step": 16954 }, { "epoch": 0.9363264855312569, "grad_norm": 0.028676483780145645, "learning_rate": 4.238104763546069e-07, "loss": 0.0008, "step": 16955 }, { "epoch": 0.9363817097415507, "grad_norm": 1.158339023590088, "learning_rate": 4.2307825299448435e-07, "loss": 0.0606, "step": 16956 }, { "epoch": 0.9364369339518445, "grad_norm": 0.0894165113568306, "learning_rate": 4.223466559558209e-07, "loss": 0.0017, "step": 16957 }, { "epoch": 0.9364921581621383, "grad_norm": 0.2574143707752228, "learning_rate": 4.2161568526202234e-07, "loss": 0.0069, "step": 16958 }, { "epoch": 0.9365473823724321, "grad_norm": 3.145507335662842, "learning_rate": 4.208853409364788e-07, "loss": 0.3803, "step": 16959 }, { "epoch": 0.9366026065827259, "grad_norm": 0.4152517318725586, "learning_rate": 4.201556230025472e-07, "loss": 0.0083, "step": 16960 }, { "epoch": 0.9366578307930197, "grad_norm": 0.39566439390182495, "learning_rate": 4.1942653148358213e-07, "loss": 0.0064, "step": 16961 }, { "epoch": 0.9367130550033135, "grad_norm": 2.243748664855957, "learning_rate": 4.18698066402905e-07, "loss": 0.1533, "step": 16962 }, { "epoch": 0.9367682792136073, "grad_norm": 2.330008029937744, "learning_rate": 4.179702277838216e-07, "loss": 0.3942, "step": 16963 }, { "epoch": 0.9368235034239011, "grad_norm": 3.6355326175689697, "learning_rate": 4.1724301564961543e-07, "loss": 0.3193, "step": 16964 }, { "epoch": 0.9368787276341949, "grad_norm": 3.7000784873962402, "learning_rate": 4.1651643002356133e-07, "loss": 0.512, "step": 16965 }, { "epoch": 0.9369339518444886, "grad_norm": 5.420827388763428, "learning_rate": 4.1579047092889403e-07, "loss": 0.7018, "step": 16966 }, { "epoch": 0.9369891760547824, "grad_norm": 0.16027075052261353, "learning_rate": 4.150651383888438e-07, "loss": 0.003, "step": 16967 }, { "epoch": 0.9370444002650762, "grad_norm": 1.289406418800354, "learning_rate": 4.1434043242661425e-07, "loss": 0.014, "step": 16968 }, { "epoch": 0.93709962447537, "grad_norm": 0.05646418035030365, "learning_rate": 4.1361635306539584e-07, "loss": 0.0014, "step": 16969 }, { "epoch": 0.9371548486856638, "grad_norm": 0.08720061182975769, "learning_rate": 4.1289290032834774e-07, "loss": 0.0026, "step": 16970 }, { "epoch": 0.9372100728959576, "grad_norm": 0.03950892388820648, "learning_rate": 4.1217007423861587e-07, "loss": 0.0008, "step": 16971 }, { "epoch": 0.9372652971062514, "grad_norm": 1.7323473691940308, "learning_rate": 4.114478748193329e-07, "loss": 0.0769, "step": 16972 }, { "epoch": 0.9373205213165452, "grad_norm": 2.6931614875793457, "learning_rate": 4.1072630209359365e-07, "loss": 0.507, "step": 16973 }, { "epoch": 0.937375745526839, "grad_norm": 0.2063407152891159, "learning_rate": 4.100053560844908e-07, "loss": 0.0049, "step": 16974 }, { "epoch": 0.9374309697371328, "grad_norm": 4.769964694976807, "learning_rate": 4.092850368150858e-07, "loss": 0.7864, "step": 16975 }, { "epoch": 0.9374861939474266, "grad_norm": 2.783681869506836, "learning_rate": 4.0856534430842477e-07, "loss": 0.2495, "step": 16976 }, { "epoch": 0.9375414181577203, "grad_norm": 4.689477920532227, "learning_rate": 4.078462785875315e-07, "loss": 1.0422, "step": 16977 }, { "epoch": 0.9375966423680141, "grad_norm": 0.014721659012138844, "learning_rate": 4.0712783967541414e-07, "loss": 0.0004, "step": 16978 }, { "epoch": 0.9376518665783079, "grad_norm": 0.10040435194969177, "learning_rate": 4.064100275950567e-07, "loss": 0.0033, "step": 16979 }, { "epoch": 0.9377070907886017, "grad_norm": 4.4514336585998535, "learning_rate": 4.056928423694206e-07, "loss": 1.1016, "step": 16980 }, { "epoch": 0.9377623149988955, "grad_norm": 0.3352073132991791, "learning_rate": 4.049762840214544e-07, "loss": 0.0085, "step": 16981 }, { "epoch": 0.9378175392091893, "grad_norm": 3.398736000061035, "learning_rate": 4.042603525740818e-07, "loss": 0.584, "step": 16982 }, { "epoch": 0.9378727634194831, "grad_norm": 0.2176562249660492, "learning_rate": 4.0354504805020456e-07, "loss": 0.0066, "step": 16983 }, { "epoch": 0.9379279876297769, "grad_norm": 2.35504412651062, "learning_rate": 4.02830370472711e-07, "loss": 0.0758, "step": 16984 }, { "epoch": 0.9379832118400707, "grad_norm": 0.12002776563167572, "learning_rate": 4.021163198644651e-07, "loss": 0.0041, "step": 16985 }, { "epoch": 0.9380384360503645, "grad_norm": 2.4158365726470947, "learning_rate": 4.0140289624831073e-07, "loss": 0.1608, "step": 16986 }, { "epoch": 0.9380936602606583, "grad_norm": 0.13800209760665894, "learning_rate": 4.0069009964707193e-07, "loss": 0.0033, "step": 16987 }, { "epoch": 0.938148884470952, "grad_norm": 0.013313324190676212, "learning_rate": 3.999779300835549e-07, "loss": 0.0005, "step": 16988 }, { "epoch": 0.9382041086812458, "grad_norm": 2.925959825515747, "learning_rate": 3.9926638758054137e-07, "loss": 0.1833, "step": 16989 }, { "epoch": 0.9382593328915396, "grad_norm": 0.16946834325790405, "learning_rate": 3.985554721607976e-07, "loss": 0.0055, "step": 16990 }, { "epoch": 0.9383145571018334, "grad_norm": 0.17018166184425354, "learning_rate": 3.978451838470676e-07, "loss": 0.0034, "step": 16991 }, { "epoch": 0.9383697813121272, "grad_norm": 0.846013605594635, "learning_rate": 3.971355226620732e-07, "loss": 0.0258, "step": 16992 }, { "epoch": 0.938425005522421, "grad_norm": 3.5832104682922363, "learning_rate": 3.964264886285207e-07, "loss": 0.3442, "step": 16993 }, { "epoch": 0.9384802297327148, "grad_norm": 6.734426021575928, "learning_rate": 3.957180817690942e-07, "loss": 0.8131, "step": 16994 }, { "epoch": 0.9385354539430086, "grad_norm": 2.421644449234009, "learning_rate": 3.950103021064577e-07, "loss": 0.1083, "step": 16995 }, { "epoch": 0.9385906781533024, "grad_norm": 0.3094727694988251, "learning_rate": 3.9430314966325546e-07, "loss": 0.0112, "step": 16996 }, { "epoch": 0.9386459023635962, "grad_norm": 2.46118426322937, "learning_rate": 3.93596624462107e-07, "loss": 0.2072, "step": 16997 }, { "epoch": 0.93870112657389, "grad_norm": 0.03649665787816048, "learning_rate": 3.9289072652562323e-07, "loss": 0.0011, "step": 16998 }, { "epoch": 0.9387563507841837, "grad_norm": 0.14809679985046387, "learning_rate": 3.921854558763816e-07, "loss": 0.0038, "step": 16999 }, { "epoch": 0.9388115749944775, "grad_norm": 0.2921593487262726, "learning_rate": 3.914808125369507e-07, "loss": 0.0102, "step": 17000 }, { "epoch": 0.9388667992047713, "grad_norm": 0.6089822053909302, "learning_rate": 3.9077679652987033e-07, "loss": 0.0166, "step": 17001 }, { "epoch": 0.9389220234150651, "grad_norm": 3.5899720191955566, "learning_rate": 3.900734078776647e-07, "loss": 0.2495, "step": 17002 }, { "epoch": 0.938977247625359, "grad_norm": 1.0066460371017456, "learning_rate": 3.8937064660283574e-07, "loss": 0.0368, "step": 17003 }, { "epoch": 0.9390324718356527, "grad_norm": 2.8425981998443604, "learning_rate": 3.886685127278744e-07, "loss": 0.1284, "step": 17004 }, { "epoch": 0.9390876960459466, "grad_norm": 0.00767384422942996, "learning_rate": 3.8796700627523387e-07, "loss": 0.0002, "step": 17005 }, { "epoch": 0.9391429202562404, "grad_norm": 0.04213200509548187, "learning_rate": 3.872661272673628e-07, "loss": 0.0011, "step": 17006 }, { "epoch": 0.9391981444665342, "grad_norm": 2.3886892795562744, "learning_rate": 3.8656587572668324e-07, "loss": 0.1335, "step": 17007 }, { "epoch": 0.939253368676828, "grad_norm": 0.6689061522483826, "learning_rate": 3.858662516755995e-07, "loss": 0.011, "step": 17008 }, { "epoch": 0.9393085928871218, "grad_norm": 0.4860921800136566, "learning_rate": 3.8516725513648935e-07, "loss": 0.0086, "step": 17009 }, { "epoch": 0.9393638170974155, "grad_norm": 5.762813091278076, "learning_rate": 3.844688861317236e-07, "loss": 0.4071, "step": 17010 }, { "epoch": 0.9394190413077093, "grad_norm": 0.8016196489334106, "learning_rate": 3.8377114468364005e-07, "loss": 0.0241, "step": 17011 }, { "epoch": 0.9394742655180031, "grad_norm": 4.5220818519592285, "learning_rate": 3.8307403081456306e-07, "loss": 0.8138, "step": 17012 }, { "epoch": 0.9395294897282969, "grad_norm": 2.394162654876709, "learning_rate": 3.8237754454679254e-07, "loss": 0.1262, "step": 17013 }, { "epoch": 0.9395847139385907, "grad_norm": 0.489080548286438, "learning_rate": 3.8168168590261735e-07, "loss": 0.0142, "step": 17014 }, { "epoch": 0.9396399381488845, "grad_norm": 0.03547515347599983, "learning_rate": 3.8098645490429076e-07, "loss": 0.0012, "step": 17015 }, { "epoch": 0.9396951623591783, "grad_norm": 0.26700153946876526, "learning_rate": 3.802918515740639e-07, "loss": 0.0089, "step": 17016 }, { "epoch": 0.9397503865694721, "grad_norm": 0.023590194061398506, "learning_rate": 3.795978759341545e-07, "loss": 0.0006, "step": 17017 }, { "epoch": 0.9398056107797659, "grad_norm": 3.9432647228240967, "learning_rate": 3.7890452800676716e-07, "loss": 0.7543, "step": 17018 }, { "epoch": 0.9398608349900597, "grad_norm": 5.936300277709961, "learning_rate": 3.782118078140795e-07, "loss": 0.7016, "step": 17019 }, { "epoch": 0.9399160592003535, "grad_norm": 0.236210435628891, "learning_rate": 3.775197153782606e-07, "loss": 0.0051, "step": 17020 }, { "epoch": 0.9399712834106472, "grad_norm": 3.1544084548950195, "learning_rate": 3.7682825072144604e-07, "loss": 0.2305, "step": 17021 }, { "epoch": 0.940026507620941, "grad_norm": 2.4127464294433594, "learning_rate": 3.761374138657625e-07, "loss": 0.0917, "step": 17022 }, { "epoch": 0.9400817318312348, "grad_norm": 0.06713774055242538, "learning_rate": 3.7544720483331023e-07, "loss": 0.0022, "step": 17023 }, { "epoch": 0.9401369560415286, "grad_norm": 1.6750917434692383, "learning_rate": 3.747576236461692e-07, "loss": 0.0611, "step": 17024 }, { "epoch": 0.9401921802518224, "grad_norm": 2.838277816772461, "learning_rate": 3.740686703263996e-07, "loss": 0.0858, "step": 17025 }, { "epoch": 0.9402474044621162, "grad_norm": 6.049238204956055, "learning_rate": 3.7338034489604826e-07, "loss": 0.1448, "step": 17026 }, { "epoch": 0.94030262867241, "grad_norm": 0.6854156851768494, "learning_rate": 3.726926473771375e-07, "loss": 0.0216, "step": 17027 }, { "epoch": 0.9403578528827038, "grad_norm": 0.8962863087654114, "learning_rate": 3.720055777916609e-07, "loss": 0.1302, "step": 17028 }, { "epoch": 0.9404130770929976, "grad_norm": 3.929717779159546, "learning_rate": 3.713191361616053e-07, "loss": 0.6355, "step": 17029 }, { "epoch": 0.9404683013032914, "grad_norm": 4.630805492401123, "learning_rate": 3.706333225089309e-07, "loss": 0.5466, "step": 17030 }, { "epoch": 0.9405235255135852, "grad_norm": 2.702739953994751, "learning_rate": 3.6994813685558016e-07, "loss": 0.1024, "step": 17031 }, { "epoch": 0.940578749723879, "grad_norm": 0.25652509927749634, "learning_rate": 3.6926357922347114e-07, "loss": 0.0055, "step": 17032 }, { "epoch": 0.9406339739341727, "grad_norm": 0.016872243955731392, "learning_rate": 3.685796496345062e-07, "loss": 0.0003, "step": 17033 }, { "epoch": 0.9406891981444665, "grad_norm": 0.09972137957811356, "learning_rate": 3.6789634811056797e-07, "loss": 0.0024, "step": 17034 }, { "epoch": 0.9407444223547603, "grad_norm": 3.8610756397247314, "learning_rate": 3.6721367467351666e-07, "loss": 0.1213, "step": 17035 }, { "epoch": 0.9407996465650541, "grad_norm": 0.008805003017187119, "learning_rate": 3.665316293451882e-07, "loss": 0.0002, "step": 17036 }, { "epoch": 0.9408548707753479, "grad_norm": 6.681959629058838, "learning_rate": 3.6585021214741167e-07, "loss": 1.5462, "step": 17037 }, { "epoch": 0.9409100949856417, "grad_norm": 0.00786946713924408, "learning_rate": 3.651694231019787e-07, "loss": 0.0002, "step": 17038 }, { "epoch": 0.9409653191959355, "grad_norm": 0.09018989652395248, "learning_rate": 3.6448926223067616e-07, "loss": 0.0018, "step": 17039 }, { "epoch": 0.9410205434062293, "grad_norm": 0.2314569056034088, "learning_rate": 3.6380972955526006e-07, "loss": 0.007, "step": 17040 }, { "epoch": 0.9410757676165231, "grad_norm": 0.034474845975637436, "learning_rate": 3.631308250974752e-07, "loss": 0.0008, "step": 17041 }, { "epoch": 0.9411309918268169, "grad_norm": 1.9058841466903687, "learning_rate": 3.624525488790354e-07, "loss": 0.2131, "step": 17042 }, { "epoch": 0.9411862160371107, "grad_norm": 2.9839000701904297, "learning_rate": 3.617749009216476e-07, "loss": 0.2561, "step": 17043 }, { "epoch": 0.9412414402474044, "grad_norm": 0.0683053731918335, "learning_rate": 3.6109788124698566e-07, "loss": 0.0014, "step": 17044 }, { "epoch": 0.9412966644576982, "grad_norm": 3.768589973449707, "learning_rate": 3.6042148987671224e-07, "loss": 0.2281, "step": 17045 }, { "epoch": 0.941351888667992, "grad_norm": 1.8616119623184204, "learning_rate": 3.597457268324678e-07, "loss": 0.1043, "step": 17046 }, { "epoch": 0.9414071128782858, "grad_norm": 3.8771655559539795, "learning_rate": 3.5907059213587057e-07, "loss": 0.2471, "step": 17047 }, { "epoch": 0.9414623370885796, "grad_norm": 3.4149606227874756, "learning_rate": 3.583960858085189e-07, "loss": 0.6588, "step": 17048 }, { "epoch": 0.9415175612988734, "grad_norm": 0.10001782327890396, "learning_rate": 3.577222078719955e-07, "loss": 0.0011, "step": 17049 }, { "epoch": 0.9415727855091672, "grad_norm": 2.345463991165161, "learning_rate": 3.570489583478587e-07, "loss": 0.3739, "step": 17050 }, { "epoch": 0.941628009719461, "grad_norm": 0.4377128779888153, "learning_rate": 3.563763372576445e-07, "loss": 0.0119, "step": 17051 }, { "epoch": 0.9416832339297548, "grad_norm": 7.017940998077393, "learning_rate": 3.5570434462287364e-07, "loss": 0.5513, "step": 17052 }, { "epoch": 0.9417384581400486, "grad_norm": 4.017397880554199, "learning_rate": 3.55032980465051e-07, "loss": 0.442, "step": 17053 }, { "epoch": 0.9417936823503424, "grad_norm": 0.16081123054027557, "learning_rate": 3.5436224480564384e-07, "loss": 0.0033, "step": 17054 }, { "epoch": 0.9418489065606361, "grad_norm": 4.846009731292725, "learning_rate": 3.5369213766611953e-07, "loss": 0.8341, "step": 17055 }, { "epoch": 0.9419041307709299, "grad_norm": 2.579352617263794, "learning_rate": 3.5302265906791423e-07, "loss": 0.6419, "step": 17056 }, { "epoch": 0.9419593549812237, "grad_norm": 2.0573618412017822, "learning_rate": 3.5235380903244634e-07, "loss": 0.3691, "step": 17057 }, { "epoch": 0.9420145791915175, "grad_norm": 0.06291329115629196, "learning_rate": 3.516855875811143e-07, "loss": 0.0017, "step": 17058 }, { "epoch": 0.9420698034018113, "grad_norm": 2.0256075859069824, "learning_rate": 3.510179947352965e-07, "loss": 0.0952, "step": 17059 }, { "epoch": 0.9421250276121051, "grad_norm": 0.9970172643661499, "learning_rate": 3.5035103051635154e-07, "loss": 0.0285, "step": 17060 }, { "epoch": 0.942180251822399, "grad_norm": 0.025080185383558273, "learning_rate": 3.4968469494561787e-07, "loss": 0.0007, "step": 17061 }, { "epoch": 0.9422354760326928, "grad_norm": 0.10220377892255783, "learning_rate": 3.490189880444117e-07, "loss": 0.0029, "step": 17062 }, { "epoch": 0.9422907002429866, "grad_norm": 4.922679424285889, "learning_rate": 3.483539098340338e-07, "loss": 0.1902, "step": 17063 }, { "epoch": 0.9423459244532804, "grad_norm": 2.3789031505584717, "learning_rate": 3.4768946033575614e-07, "loss": 0.4551, "step": 17064 }, { "epoch": 0.9424011486635742, "grad_norm": 2.850710153579712, "learning_rate": 3.470256395708438e-07, "loss": 0.2643, "step": 17065 }, { "epoch": 0.9424563728738679, "grad_norm": 0.10564431548118591, "learning_rate": 3.4636244756053096e-07, "loss": 0.0016, "step": 17066 }, { "epoch": 0.9425115970841617, "grad_norm": 4.036843776702881, "learning_rate": 3.45699884326034e-07, "loss": 0.6841, "step": 17067 }, { "epoch": 0.9425668212944555, "grad_norm": 0.7624524235725403, "learning_rate": 3.450379498885492e-07, "loss": 0.0234, "step": 17068 }, { "epoch": 0.9426220455047493, "grad_norm": 0.7189327478408813, "learning_rate": 3.4437664426925755e-07, "loss": 0.0186, "step": 17069 }, { "epoch": 0.9426772697150431, "grad_norm": 0.34204065799713135, "learning_rate": 3.4371596748931314e-07, "loss": 0.0062, "step": 17070 }, { "epoch": 0.9427324939253369, "grad_norm": 1.9812991619110107, "learning_rate": 3.430559195698546e-07, "loss": 0.1153, "step": 17071 }, { "epoch": 0.9427877181356307, "grad_norm": 0.05604070425033569, "learning_rate": 3.423965005319985e-07, "loss": 0.0018, "step": 17072 }, { "epoch": 0.9428429423459245, "grad_norm": 0.28528037667274475, "learning_rate": 3.417377103968411e-07, "loss": 0.0042, "step": 17073 }, { "epoch": 0.9428981665562183, "grad_norm": 2.771139144897461, "learning_rate": 3.4107954918545684e-07, "loss": 0.1247, "step": 17074 }, { "epoch": 0.9429533907665121, "grad_norm": 4.193994045257568, "learning_rate": 3.404220169189043e-07, "loss": 0.7, "step": 17075 }, { "epoch": 0.9430086149768059, "grad_norm": 0.6947222948074341, "learning_rate": 3.397651136182223e-07, "loss": 0.0151, "step": 17076 }, { "epoch": 0.9430638391870996, "grad_norm": 0.29742544889450073, "learning_rate": 3.3910883930442284e-07, "loss": 0.0089, "step": 17077 }, { "epoch": 0.9431190633973934, "grad_norm": 0.09641114622354507, "learning_rate": 3.3845319399850473e-07, "loss": 0.0023, "step": 17078 }, { "epoch": 0.9431742876076872, "grad_norm": 0.21959403157234192, "learning_rate": 3.377981777214423e-07, "loss": 0.0077, "step": 17079 }, { "epoch": 0.943229511817981, "grad_norm": 1.6674708127975464, "learning_rate": 3.371437904941921e-07, "loss": 0.0411, "step": 17080 }, { "epoch": 0.9432847360282748, "grad_norm": 0.03446155786514282, "learning_rate": 3.3649003233769073e-07, "loss": 0.0008, "step": 17081 }, { "epoch": 0.9433399602385686, "grad_norm": 0.0596199594438076, "learning_rate": 3.3583690327285034e-07, "loss": 0.0012, "step": 17082 }, { "epoch": 0.9433951844488624, "grad_norm": 7.93519401550293, "learning_rate": 3.35184403320572e-07, "loss": 0.1048, "step": 17083 }, { "epoch": 0.9434504086591562, "grad_norm": 0.00876297801733017, "learning_rate": 3.3453253250172344e-07, "loss": 0.0002, "step": 17084 }, { "epoch": 0.94350563286945, "grad_norm": 0.9773429036140442, "learning_rate": 3.33881290837168e-07, "loss": 0.0412, "step": 17085 }, { "epoch": 0.9435608570797438, "grad_norm": 1.450392723083496, "learning_rate": 3.3323067834773794e-07, "loss": 0.0248, "step": 17086 }, { "epoch": 0.9436160812900376, "grad_norm": 5.29890775680542, "learning_rate": 3.3258069505424315e-07, "loss": 0.9303, "step": 17087 }, { "epoch": 0.9436713055003313, "grad_norm": 1.6797202825546265, "learning_rate": 3.3193134097748494e-07, "loss": 0.0117, "step": 17088 }, { "epoch": 0.9437265297106251, "grad_norm": 0.0213033277541399, "learning_rate": 3.312826161382354e-07, "loss": 0.0005, "step": 17089 }, { "epoch": 0.9437817539209189, "grad_norm": 0.013473845086991787, "learning_rate": 3.306345205572492e-07, "loss": 0.0004, "step": 17090 }, { "epoch": 0.9438369781312127, "grad_norm": 3.1728599071502686, "learning_rate": 3.299870542552608e-07, "loss": 0.2517, "step": 17091 }, { "epoch": 0.9438922023415065, "grad_norm": 3.733609437942505, "learning_rate": 3.293402172529847e-07, "loss": 0.0832, "step": 17092 }, { "epoch": 0.9439474265518003, "grad_norm": 4.002838611602783, "learning_rate": 3.286940095711155e-07, "loss": 0.2362, "step": 17093 }, { "epoch": 0.9440026507620941, "grad_norm": 3.3790881633758545, "learning_rate": 3.2804843123032557e-07, "loss": 0.6774, "step": 17094 }, { "epoch": 0.9440578749723879, "grad_norm": 0.004399152938276529, "learning_rate": 3.274034822512717e-07, "loss": 0.0001, "step": 17095 }, { "epoch": 0.9441130991826817, "grad_norm": 1.6684585809707642, "learning_rate": 3.2675916265458407e-07, "loss": 0.287, "step": 17096 }, { "epoch": 0.9441683233929755, "grad_norm": 0.018290337175130844, "learning_rate": 3.261154724608773e-07, "loss": 0.0004, "step": 17097 }, { "epoch": 0.9442235476032693, "grad_norm": 0.3785993456840515, "learning_rate": 3.2547241169074597e-07, "loss": 0.0081, "step": 17098 }, { "epoch": 0.944278771813563, "grad_norm": 0.02196417562663555, "learning_rate": 3.2482998036476474e-07, "loss": 0.0006, "step": 17099 }, { "epoch": 0.9443339960238568, "grad_norm": 0.016220716759562492, "learning_rate": 3.241881785034862e-07, "loss": 0.0005, "step": 17100 }, { "epoch": 0.9443892202341506, "grad_norm": 0.196013942360878, "learning_rate": 3.235470061274404e-07, "loss": 0.004, "step": 17101 }, { "epoch": 0.9444444444444444, "grad_norm": 2.530839443206787, "learning_rate": 3.2290646325714216e-07, "loss": 0.0589, "step": 17102 }, { "epoch": 0.9444996686547382, "grad_norm": 2.4950506687164307, "learning_rate": 3.222665499130839e-07, "loss": 0.1755, "step": 17103 }, { "epoch": 0.944554892865032, "grad_norm": 6.9297099113464355, "learning_rate": 3.2162726611573825e-07, "loss": 0.1298, "step": 17104 }, { "epoch": 0.9446101170753258, "grad_norm": 0.2120836079120636, "learning_rate": 3.209886118855599e-07, "loss": 0.006, "step": 17105 }, { "epoch": 0.9446653412856196, "grad_norm": 2.6066017150878906, "learning_rate": 3.2035058724297907e-07, "loss": 0.7712, "step": 17106 }, { "epoch": 0.9447205654959134, "grad_norm": 0.049780815839767456, "learning_rate": 3.1971319220840847e-07, "loss": 0.0009, "step": 17107 }, { "epoch": 0.9447757897062072, "grad_norm": 0.441074937582016, "learning_rate": 3.190764268022406e-07, "loss": 0.0117, "step": 17108 }, { "epoch": 0.944831013916501, "grad_norm": 0.16354651749134064, "learning_rate": 3.184402910448459e-07, "loss": 0.0033, "step": 17109 }, { "epoch": 0.9448862381267948, "grad_norm": 0.2788074016571045, "learning_rate": 3.1780478495657907e-07, "loss": 0.0076, "step": 17110 }, { "epoch": 0.9449414623370885, "grad_norm": 3.451712131500244, "learning_rate": 3.171699085577684e-07, "loss": 0.6452, "step": 17111 }, { "epoch": 0.9449966865473823, "grad_norm": 0.6513404846191406, "learning_rate": 3.165356618687265e-07, "loss": 0.0149, "step": 17112 }, { "epoch": 0.9450519107576761, "grad_norm": 5.939764499664307, "learning_rate": 3.1590204490974384e-07, "loss": 0.7671, "step": 17113 }, { "epoch": 0.9451071349679699, "grad_norm": 0.03949317708611488, "learning_rate": 3.1526905770109527e-07, "loss": 0.0012, "step": 17114 }, { "epoch": 0.9451623591782637, "grad_norm": 1.2677189111709595, "learning_rate": 3.1463670026302905e-07, "loss": 0.142, "step": 17115 }, { "epoch": 0.9452175833885575, "grad_norm": 2.0910167694091797, "learning_rate": 3.140049726157779e-07, "loss": 0.1996, "step": 17116 }, { "epoch": 0.9452728075988514, "grad_norm": 0.20926277339458466, "learning_rate": 3.1337387477954785e-07, "loss": 0.004, "step": 17117 }, { "epoch": 0.9453280318091452, "grad_norm": 0.15447533130645752, "learning_rate": 3.127434067745361e-07, "loss": 0.0032, "step": 17118 }, { "epoch": 0.945383256019439, "grad_norm": 5.183260440826416, "learning_rate": 3.121135686209087e-07, "loss": 0.1595, "step": 17119 }, { "epoch": 0.9454384802297328, "grad_norm": 6.608337879180908, "learning_rate": 3.114843603388162e-07, "loss": 0.8429, "step": 17120 }, { "epoch": 0.9454937044400266, "grad_norm": 0.1124134287238121, "learning_rate": 3.108557819483915e-07, "loss": 0.0034, "step": 17121 }, { "epoch": 0.9455489286503203, "grad_norm": 0.17146363854408264, "learning_rate": 3.1022783346974284e-07, "loss": 0.0033, "step": 17122 }, { "epoch": 0.9456041528606141, "grad_norm": 4.67361307144165, "learning_rate": 3.096005149229564e-07, "loss": 0.4331, "step": 17123 }, { "epoch": 0.9456593770709079, "grad_norm": 0.04512779042124748, "learning_rate": 3.0897382632810944e-07, "loss": 0.0017, "step": 17124 }, { "epoch": 0.9457146012812017, "grad_norm": 0.8041660785675049, "learning_rate": 3.08347767705246e-07, "loss": 0.012, "step": 17125 }, { "epoch": 0.9457698254914955, "grad_norm": 0.022559702396392822, "learning_rate": 3.0772233907439884e-07, "loss": 0.0006, "step": 17126 }, { "epoch": 0.9458250497017893, "grad_norm": 0.223989799618721, "learning_rate": 3.0709754045557425e-07, "loss": 0.0054, "step": 17127 }, { "epoch": 0.9458802739120831, "grad_norm": 0.3568457365036011, "learning_rate": 3.064733718687629e-07, "loss": 0.0092, "step": 17128 }, { "epoch": 0.9459354981223769, "grad_norm": 4.070965766906738, "learning_rate": 3.05849833333931e-07, "loss": 0.723, "step": 17129 }, { "epoch": 0.9459907223326707, "grad_norm": 1.0769070386886597, "learning_rate": 3.0522692487103156e-07, "loss": 0.0227, "step": 17130 }, { "epoch": 0.9460459465429645, "grad_norm": 0.8706250786781311, "learning_rate": 3.04604646499993e-07, "loss": 0.0157, "step": 17131 }, { "epoch": 0.9461011707532583, "grad_norm": 0.04782585799694061, "learning_rate": 3.0398299824071943e-07, "loss": 0.0013, "step": 17132 }, { "epoch": 0.946156394963552, "grad_norm": 0.12428447604179382, "learning_rate": 3.033619801131038e-07, "loss": 0.0038, "step": 17133 }, { "epoch": 0.9462116191738458, "grad_norm": 0.08148602396249771, "learning_rate": 3.027415921370125e-07, "loss": 0.0019, "step": 17134 }, { "epoch": 0.9462668433841396, "grad_norm": 0.20184706151485443, "learning_rate": 3.021218343322918e-07, "loss": 0.0059, "step": 17135 }, { "epoch": 0.9463220675944334, "grad_norm": 4.218714714050293, "learning_rate": 3.0150270671877036e-07, "loss": 0.5746, "step": 17136 }, { "epoch": 0.9463772918047272, "grad_norm": 3.09057354927063, "learning_rate": 3.0088420931625897e-07, "loss": 0.0499, "step": 17137 }, { "epoch": 0.946432516015021, "grad_norm": 0.01778787188231945, "learning_rate": 3.0026634214453955e-07, "loss": 0.0006, "step": 17138 }, { "epoch": 0.9464877402253148, "grad_norm": 0.3767394721508026, "learning_rate": 2.9964910522338297e-07, "loss": 0.0079, "step": 17139 }, { "epoch": 0.9465429644356086, "grad_norm": 0.324201762676239, "learning_rate": 2.990324985725379e-07, "loss": 0.0077, "step": 17140 }, { "epoch": 0.9465981886459024, "grad_norm": 0.00853748805820942, "learning_rate": 2.9841652221172857e-07, "loss": 0.0002, "step": 17141 }, { "epoch": 0.9466534128561962, "grad_norm": 1.329892873764038, "learning_rate": 2.9780117616066363e-07, "loss": 0.0458, "step": 17142 }, { "epoch": 0.94670863706649, "grad_norm": 0.03745291754603386, "learning_rate": 2.9718646043902734e-07, "loss": 0.001, "step": 17143 }, { "epoch": 0.9467638612767837, "grad_norm": 2.714458465576172, "learning_rate": 2.965723750664884e-07, "loss": 0.4022, "step": 17144 }, { "epoch": 0.9468190854870775, "grad_norm": 0.2849056124687195, "learning_rate": 2.959589200626911e-07, "loss": 0.0081, "step": 17145 }, { "epoch": 0.9468743096973713, "grad_norm": 6.867691993713379, "learning_rate": 2.9534609544726424e-07, "loss": 0.7586, "step": 17146 }, { "epoch": 0.9469295339076651, "grad_norm": 2.234171152114868, "learning_rate": 2.9473390123981425e-07, "loss": 0.0838, "step": 17147 }, { "epoch": 0.9469847581179589, "grad_norm": 2.9606270790100098, "learning_rate": 2.9412233745992115e-07, "loss": 0.2067, "step": 17148 }, { "epoch": 0.9470399823282527, "grad_norm": 1.379431128501892, "learning_rate": 2.9351140412715584e-07, "loss": 0.0254, "step": 17149 }, { "epoch": 0.9470952065385465, "grad_norm": 0.06916897743940353, "learning_rate": 2.9290110126106276e-07, "loss": 0.0016, "step": 17150 }, { "epoch": 0.9471504307488403, "grad_norm": 0.030109312385320663, "learning_rate": 2.9229142888116845e-07, "loss": 0.0006, "step": 17151 }, { "epoch": 0.9472056549591341, "grad_norm": 0.06528866291046143, "learning_rate": 2.9168238700697516e-07, "loss": 0.0019, "step": 17152 }, { "epoch": 0.9472608791694279, "grad_norm": 0.029528524726629257, "learning_rate": 2.9107397565796947e-07, "loss": 0.0007, "step": 17153 }, { "epoch": 0.9473161033797217, "grad_norm": 0.08382923156023026, "learning_rate": 2.904661948536158e-07, "loss": 0.0028, "step": 17154 }, { "epoch": 0.9473713275900154, "grad_norm": 0.20877307653427124, "learning_rate": 2.898590446133609e-07, "loss": 0.0064, "step": 17155 }, { "epoch": 0.9474265518003092, "grad_norm": 6.217129230499268, "learning_rate": 2.892525249566247e-07, "loss": 0.673, "step": 17156 }, { "epoch": 0.947481776010603, "grad_norm": 0.010843469761312008, "learning_rate": 2.886466359028184e-07, "loss": 0.0004, "step": 17157 }, { "epoch": 0.9475370002208968, "grad_norm": 1.7767986059188843, "learning_rate": 2.8804137747131756e-07, "loss": 0.0729, "step": 17158 }, { "epoch": 0.9475922244311906, "grad_norm": 0.01934713125228882, "learning_rate": 2.874367496814934e-07, "loss": 0.0005, "step": 17159 }, { "epoch": 0.9476474486414844, "grad_norm": 6.502734661102295, "learning_rate": 2.8683275255268594e-07, "loss": 1.2852, "step": 17160 }, { "epoch": 0.9477026728517782, "grad_norm": 3.016469955444336, "learning_rate": 2.862293861042198e-07, "loss": 0.1421, "step": 17161 }, { "epoch": 0.947757897062072, "grad_norm": 1.1951284408569336, "learning_rate": 2.8562665035539503e-07, "loss": 0.0222, "step": 17162 }, { "epoch": 0.9478131212723658, "grad_norm": 0.43775099515914917, "learning_rate": 2.850245453255029e-07, "loss": 0.0108, "step": 17163 }, { "epoch": 0.9478683454826596, "grad_norm": 0.7626557946205139, "learning_rate": 2.844230710337992e-07, "loss": 0.0284, "step": 17164 }, { "epoch": 0.9479235696929534, "grad_norm": 2.3009581565856934, "learning_rate": 2.8382222749952835e-07, "loss": 0.2464, "step": 17165 }, { "epoch": 0.9479787939032471, "grad_norm": 0.0426672101020813, "learning_rate": 2.8322201474191734e-07, "loss": 0.0011, "step": 17166 }, { "epoch": 0.9480340181135409, "grad_norm": 0.004806860350072384, "learning_rate": 2.8262243278016187e-07, "loss": 0.0002, "step": 17167 }, { "epoch": 0.9480892423238347, "grad_norm": 5.347607135772705, "learning_rate": 2.8202348163344883e-07, "loss": 1.2934, "step": 17168 }, { "epoch": 0.9481444665341285, "grad_norm": 0.20789246261119843, "learning_rate": 2.814251613209384e-07, "loss": 0.0077, "step": 17169 }, { "epoch": 0.9481996907444223, "grad_norm": 7.284168243408203, "learning_rate": 2.808274718617754e-07, "loss": 0.1742, "step": 17170 }, { "epoch": 0.9482549149547161, "grad_norm": 1.0231558084487915, "learning_rate": 2.8023041327507774e-07, "loss": 0.023, "step": 17171 }, { "epoch": 0.94831013916501, "grad_norm": 0.15542499721050262, "learning_rate": 2.796339855799479e-07, "loss": 0.0042, "step": 17172 }, { "epoch": 0.9483653633753037, "grad_norm": 3.1412904262542725, "learning_rate": 2.79038188795473e-07, "loss": 0.0804, "step": 17173 }, { "epoch": 0.9484205875855976, "grad_norm": 3.199428081512451, "learning_rate": 2.7844302294070426e-07, "loss": 0.2904, "step": 17174 }, { "epoch": 0.9484758117958914, "grad_norm": 9.394145965576172, "learning_rate": 2.77848488034691e-07, "loss": 0.6387, "step": 17175 }, { "epoch": 0.9485310360061852, "grad_norm": 0.5145329833030701, "learning_rate": 2.7725458409644913e-07, "loss": 0.011, "step": 17176 }, { "epoch": 0.9485862602164788, "grad_norm": 0.022771533578634262, "learning_rate": 2.766613111449834e-07, "loss": 0.0008, "step": 17177 }, { "epoch": 0.9486414844267727, "grad_norm": 0.3293398916721344, "learning_rate": 2.760686691992698e-07, "loss": 0.0056, "step": 17178 }, { "epoch": 0.9486967086370665, "grad_norm": 0.4240869879722595, "learning_rate": 2.7547665827827306e-07, "loss": 0.0082, "step": 17179 }, { "epoch": 0.9487519328473603, "grad_norm": 0.09207180142402649, "learning_rate": 2.7488527840093147e-07, "loss": 0.0025, "step": 17180 }, { "epoch": 0.9488071570576541, "grad_norm": 0.10524354875087738, "learning_rate": 2.7429452958616323e-07, "loss": 0.0022, "step": 17181 }, { "epoch": 0.9488623812679479, "grad_norm": 0.026134677231311798, "learning_rate": 2.737044118528709e-07, "loss": 0.0005, "step": 17182 }, { "epoch": 0.9489176054782417, "grad_norm": 1.951492190361023, "learning_rate": 2.7311492521993053e-07, "loss": 0.3375, "step": 17183 }, { "epoch": 0.9489728296885355, "grad_norm": 0.22319726645946503, "learning_rate": 2.725260697062049e-07, "loss": 0.0065, "step": 17184 }, { "epoch": 0.9490280538988293, "grad_norm": 5.438122272491455, "learning_rate": 2.719378453305321e-07, "loss": 0.4316, "step": 17185 }, { "epoch": 0.9490832781091231, "grad_norm": 1.3325610160827637, "learning_rate": 2.713502521117306e-07, "loss": 0.0484, "step": 17186 }, { "epoch": 0.9491385023194169, "grad_norm": 0.04219822958111763, "learning_rate": 2.707632900686008e-07, "loss": 0.0013, "step": 17187 }, { "epoch": 0.9491937265297107, "grad_norm": 3.526139497756958, "learning_rate": 2.701769592199188e-07, "loss": 0.3831, "step": 17188 }, { "epoch": 0.9492489507400044, "grad_norm": 0.12475194782018661, "learning_rate": 2.695912595844452e-07, "loss": 0.0029, "step": 17189 }, { "epoch": 0.9493041749502982, "grad_norm": 3.643765926361084, "learning_rate": 2.6900619118091607e-07, "loss": 0.2654, "step": 17190 }, { "epoch": 0.949359399160592, "grad_norm": 2.842653274536133, "learning_rate": 2.6842175402804984e-07, "loss": 0.4479, "step": 17191 }, { "epoch": 0.9494146233708858, "grad_norm": 0.014688153751194477, "learning_rate": 2.67837948144547e-07, "loss": 0.0003, "step": 17192 }, { "epoch": 0.9494698475811796, "grad_norm": 0.11795395612716675, "learning_rate": 2.6725477354908155e-07, "loss": 0.0022, "step": 17193 }, { "epoch": 0.9495250717914734, "grad_norm": 4.809607982635498, "learning_rate": 2.6667223026031195e-07, "loss": 0.4805, "step": 17194 }, { "epoch": 0.9495802960017672, "grad_norm": 0.07503745704889297, "learning_rate": 2.660903182968788e-07, "loss": 0.0022, "step": 17195 }, { "epoch": 0.949635520212061, "grad_norm": 0.4308204650878906, "learning_rate": 2.655090376773939e-07, "loss": 0.0081, "step": 17196 }, { "epoch": 0.9496907444223548, "grad_norm": 2.6666419506073, "learning_rate": 2.649283884204579e-07, "loss": 0.1837, "step": 17197 }, { "epoch": 0.9497459686326486, "grad_norm": 0.04825396463274956, "learning_rate": 2.643483705446448e-07, "loss": 0.0013, "step": 17198 }, { "epoch": 0.9498011928429424, "grad_norm": 0.6503670811653137, "learning_rate": 2.6376898406851317e-07, "loss": 0.0171, "step": 17199 }, { "epoch": 0.9498564170532361, "grad_norm": 3.8584725856781006, "learning_rate": 2.6319022901059696e-07, "loss": 0.7598, "step": 17200 }, { "epoch": 0.9499116412635299, "grad_norm": 0.18928350508213043, "learning_rate": 2.6261210538941483e-07, "loss": 0.0053, "step": 17201 }, { "epoch": 0.9499668654738237, "grad_norm": 4.491262435913086, "learning_rate": 2.6203461322346304e-07, "loss": 0.2839, "step": 17202 }, { "epoch": 0.9500220896841175, "grad_norm": 5.93377685546875, "learning_rate": 2.6145775253121344e-07, "loss": 1.1067, "step": 17203 }, { "epoch": 0.9500773138944113, "grad_norm": 0.12795749306678772, "learning_rate": 2.608815233311224e-07, "loss": 0.0028, "step": 17204 }, { "epoch": 0.9501325381047051, "grad_norm": 4.238210201263428, "learning_rate": 2.603059256416285e-07, "loss": 0.5876, "step": 17205 }, { "epoch": 0.9501877623149989, "grad_norm": 6.631330966949463, "learning_rate": 2.5973095948114367e-07, "loss": 1.0576, "step": 17206 }, { "epoch": 0.9502429865252927, "grad_norm": 0.0700891986489296, "learning_rate": 2.5915662486806216e-07, "loss": 0.0017, "step": 17207 }, { "epoch": 0.9502982107355865, "grad_norm": 3.4794559478759766, "learning_rate": 2.585829218207603e-07, "loss": 0.2669, "step": 17208 }, { "epoch": 0.9503534349458803, "grad_norm": 1.9524985551834106, "learning_rate": 2.580098503575923e-07, "loss": 0.357, "step": 17209 }, { "epoch": 0.9504086591561741, "grad_norm": 0.01123605202883482, "learning_rate": 2.5743741049689466e-07, "loss": 0.0003, "step": 17210 }, { "epoch": 0.9504638833664678, "grad_norm": 3.0842041969299316, "learning_rate": 2.568656022569749e-07, "loss": 0.1011, "step": 17211 }, { "epoch": 0.9505191075767616, "grad_norm": 0.11957734823226929, "learning_rate": 2.5629442565613394e-07, "loss": 0.0018, "step": 17212 }, { "epoch": 0.9505743317870554, "grad_norm": 3.5662524700164795, "learning_rate": 2.557238807126394e-07, "loss": 0.0773, "step": 17213 }, { "epoch": 0.9506295559973492, "grad_norm": 0.046622660011053085, "learning_rate": 2.5515396744474783e-07, "loss": 0.0013, "step": 17214 }, { "epoch": 0.950684780207643, "grad_norm": 0.958096444606781, "learning_rate": 2.5458468587069354e-07, "loss": 0.0124, "step": 17215 }, { "epoch": 0.9507400044179368, "grad_norm": 0.010416863486170769, "learning_rate": 2.540160360086885e-07, "loss": 0.0003, "step": 17216 }, { "epoch": 0.9507952286282306, "grad_norm": 2.939777374267578, "learning_rate": 2.5344801787692055e-07, "loss": 0.5744, "step": 17217 }, { "epoch": 0.9508504528385244, "grad_norm": 2.873215436935425, "learning_rate": 2.528806314935706e-07, "loss": 0.1981, "step": 17218 }, { "epoch": 0.9509056770488182, "grad_norm": 2.3101892471313477, "learning_rate": 2.5231387687678635e-07, "loss": 0.3801, "step": 17219 }, { "epoch": 0.950960901259112, "grad_norm": 3.6063878536224365, "learning_rate": 2.5174775404469996e-07, "loss": 0.4938, "step": 17220 }, { "epoch": 0.9510161254694058, "grad_norm": 3.491669178009033, "learning_rate": 2.5118226301542146e-07, "loss": 0.5216, "step": 17221 }, { "epoch": 0.9510713496796995, "grad_norm": 0.38910824060440063, "learning_rate": 2.5061740380704744e-07, "loss": 0.0101, "step": 17222 }, { "epoch": 0.9511265738899933, "grad_norm": 2.5655837059020996, "learning_rate": 2.500531764376457e-07, "loss": 0.0387, "step": 17223 }, { "epoch": 0.9511817981002871, "grad_norm": 0.051684532314538956, "learning_rate": 2.494895809252684e-07, "loss": 0.001, "step": 17224 }, { "epoch": 0.9512370223105809, "grad_norm": 4.571887969970703, "learning_rate": 2.489266172879456e-07, "loss": 0.3348, "step": 17225 }, { "epoch": 0.9512922465208747, "grad_norm": 0.16780801117420197, "learning_rate": 2.4836428554369183e-07, "loss": 0.0036, "step": 17226 }, { "epoch": 0.9513474707311685, "grad_norm": 0.16791866719722748, "learning_rate": 2.4780258571049265e-07, "loss": 0.0041, "step": 17227 }, { "epoch": 0.9514026949414623, "grad_norm": 0.016693156212568283, "learning_rate": 2.4724151780632256e-07, "loss": 0.0003, "step": 17228 }, { "epoch": 0.9514579191517561, "grad_norm": 2.5994205474853516, "learning_rate": 2.466810818491272e-07, "loss": 0.0853, "step": 17229 }, { "epoch": 0.95151314336205, "grad_norm": 2.8082282543182373, "learning_rate": 2.461212778568411e-07, "loss": 0.2465, "step": 17230 }, { "epoch": 0.9515683675723438, "grad_norm": 0.24878095090389252, "learning_rate": 2.455621058473723e-07, "loss": 0.0069, "step": 17231 }, { "epoch": 0.9516235917826376, "grad_norm": 0.06672080606222153, "learning_rate": 2.4500356583861074e-07, "loss": 0.0015, "step": 17232 }, { "epoch": 0.9516788159929312, "grad_norm": 0.8802928924560547, "learning_rate": 2.444456578484222e-07, "loss": 0.0273, "step": 17233 }, { "epoch": 0.951734040203225, "grad_norm": 2.6194446086883545, "learning_rate": 2.4388838189466134e-07, "loss": 0.2397, "step": 17234 }, { "epoch": 0.9517892644135189, "grad_norm": 3.791346788406372, "learning_rate": 2.4333173799515386e-07, "loss": 0.2489, "step": 17235 }, { "epoch": 0.9518444886238127, "grad_norm": 0.015097570605576038, "learning_rate": 2.427757261677077e-07, "loss": 0.0004, "step": 17236 }, { "epoch": 0.9518997128341065, "grad_norm": 0.7318874001502991, "learning_rate": 2.4222034643011316e-07, "loss": 0.0085, "step": 17237 }, { "epoch": 0.9519549370444003, "grad_norm": 1.5328482389450073, "learning_rate": 2.4166559880013817e-07, "loss": 0.1757, "step": 17238 }, { "epoch": 0.9520101612546941, "grad_norm": 1.0945466756820679, "learning_rate": 2.411114832955286e-07, "loss": 0.0498, "step": 17239 }, { "epoch": 0.9520653854649879, "grad_norm": 7.542194843292236, "learning_rate": 2.4055799993401463e-07, "loss": 0.7497, "step": 17240 }, { "epoch": 0.9521206096752817, "grad_norm": 2.7266430854797363, "learning_rate": 2.400051487333044e-07, "loss": 0.1905, "step": 17241 }, { "epoch": 0.9521758338855755, "grad_norm": 1.3667093515396118, "learning_rate": 2.394529297110815e-07, "loss": 0.0344, "step": 17242 }, { "epoch": 0.9522310580958693, "grad_norm": 1.6335219144821167, "learning_rate": 2.38901342885014e-07, "loss": 0.0923, "step": 17243 }, { "epoch": 0.952286282306163, "grad_norm": 0.27928319573402405, "learning_rate": 2.3835038827275447e-07, "loss": 0.0036, "step": 17244 }, { "epoch": 0.9523415065164568, "grad_norm": 0.14164979755878448, "learning_rate": 2.3780006589191995e-07, "loss": 0.0038, "step": 17245 }, { "epoch": 0.9523967307267506, "grad_norm": 0.020317191258072853, "learning_rate": 2.3725037576012522e-07, "loss": 0.0006, "step": 17246 }, { "epoch": 0.9524519549370444, "grad_norm": 1.9356892108917236, "learning_rate": 2.3670131789495175e-07, "loss": 0.1228, "step": 17247 }, { "epoch": 0.9525071791473382, "grad_norm": 0.02603069879114628, "learning_rate": 2.3615289231396776e-07, "loss": 0.0006, "step": 17248 }, { "epoch": 0.952562403357632, "grad_norm": 1.8722227811813354, "learning_rate": 2.3560509903471696e-07, "loss": 0.0993, "step": 17249 }, { "epoch": 0.9526176275679258, "grad_norm": 0.15991638600826263, "learning_rate": 2.3505793807472533e-07, "loss": 0.0051, "step": 17250 }, { "epoch": 0.9526728517782196, "grad_norm": 0.029091855511069298, "learning_rate": 2.3451140945149887e-07, "loss": 0.0007, "step": 17251 }, { "epoch": 0.9527280759885134, "grad_norm": 2.201612710952759, "learning_rate": 2.3396551318252358e-07, "loss": 0.5928, "step": 17252 }, { "epoch": 0.9527833001988072, "grad_norm": 1.1307569742202759, "learning_rate": 2.3342024928526107e-07, "loss": 0.0621, "step": 17253 }, { "epoch": 0.952838524409101, "grad_norm": 0.29357436299324036, "learning_rate": 2.3287561777715963e-07, "loss": 0.0094, "step": 17254 }, { "epoch": 0.9528937486193948, "grad_norm": 0.08751490712165833, "learning_rate": 2.323316186756386e-07, "loss": 0.0022, "step": 17255 }, { "epoch": 0.9529489728296885, "grad_norm": 3.0822041034698486, "learning_rate": 2.317882519981085e-07, "loss": 0.3315, "step": 17256 }, { "epoch": 0.9530041970399823, "grad_norm": 0.11555381864309311, "learning_rate": 2.312455177619488e-07, "loss": 0.0027, "step": 17257 }, { "epoch": 0.9530594212502761, "grad_norm": 0.025051243603229523, "learning_rate": 2.3070341598452338e-07, "loss": 0.0006, "step": 17258 }, { "epoch": 0.9531146454605699, "grad_norm": 2.607666254043579, "learning_rate": 2.3016194668317615e-07, "loss": 0.151, "step": 17259 }, { "epoch": 0.9531698696708637, "grad_norm": 3.9372196197509766, "learning_rate": 2.2962110987523323e-07, "loss": 0.1797, "step": 17260 }, { "epoch": 0.9532250938811575, "grad_norm": 0.2609809637069702, "learning_rate": 2.2908090557798967e-07, "loss": 0.0064, "step": 17261 }, { "epoch": 0.9532803180914513, "grad_norm": 0.5494136214256287, "learning_rate": 2.2854133380873832e-07, "loss": 0.0126, "step": 17262 }, { "epoch": 0.9533355423017451, "grad_norm": 1.5375884771347046, "learning_rate": 2.2800239458473427e-07, "loss": 0.0447, "step": 17263 }, { "epoch": 0.9533907665120389, "grad_norm": 6.141870498657227, "learning_rate": 2.274640879232215e-07, "loss": 0.9045, "step": 17264 }, { "epoch": 0.9534459907223327, "grad_norm": 3.100667953491211, "learning_rate": 2.2692641384142177e-07, "loss": 0.138, "step": 17265 }, { "epoch": 0.9535012149326265, "grad_norm": 5.570688724517822, "learning_rate": 2.2638937235653912e-07, "loss": 0.6118, "step": 17266 }, { "epoch": 0.9535564391429202, "grad_norm": 5.515901565551758, "learning_rate": 2.2585296348575537e-07, "loss": 0.6696, "step": 17267 }, { "epoch": 0.953611663353214, "grad_norm": 0.991385281085968, "learning_rate": 2.2531718724622564e-07, "loss": 0.0374, "step": 17268 }, { "epoch": 0.9536668875635078, "grad_norm": 3.0459110736846924, "learning_rate": 2.247820436550985e-07, "loss": 0.1182, "step": 17269 }, { "epoch": 0.9537221117738016, "grad_norm": 5.413150787353516, "learning_rate": 2.2424753272948908e-07, "loss": 0.9426, "step": 17270 }, { "epoch": 0.9537773359840954, "grad_norm": 0.05942723900079727, "learning_rate": 2.237136544865015e-07, "loss": 0.0015, "step": 17271 }, { "epoch": 0.9538325601943892, "grad_norm": 3.815687894821167, "learning_rate": 2.2318040894321324e-07, "loss": 0.1995, "step": 17272 }, { "epoch": 0.953887784404683, "grad_norm": 0.04780207574367523, "learning_rate": 2.2264779611668842e-07, "loss": 0.0009, "step": 17273 }, { "epoch": 0.9539430086149768, "grad_norm": 5.322606563568115, "learning_rate": 2.2211581602396227e-07, "loss": 0.6383, "step": 17274 }, { "epoch": 0.9539982328252706, "grad_norm": 1.074166178703308, "learning_rate": 2.2158446868205675e-07, "loss": 0.0307, "step": 17275 }, { "epoch": 0.9540534570355644, "grad_norm": 0.027604080736637115, "learning_rate": 2.2105375410796935e-07, "loss": 0.0006, "step": 17276 }, { "epoch": 0.9541086812458582, "grad_norm": 2.454632043838501, "learning_rate": 2.205236723186843e-07, "loss": 0.2495, "step": 17277 }, { "epoch": 0.9541639054561519, "grad_norm": 0.33478137850761414, "learning_rate": 2.199942233311525e-07, "loss": 0.0105, "step": 17278 }, { "epoch": 0.9542191296664457, "grad_norm": 0.02753710374236107, "learning_rate": 2.1946540716231812e-07, "loss": 0.0006, "step": 17279 }, { "epoch": 0.9542743538767395, "grad_norm": 2.8824384212493896, "learning_rate": 2.1893722382909876e-07, "loss": 0.315, "step": 17280 }, { "epoch": 0.9543295780870333, "grad_norm": 0.01887485757470131, "learning_rate": 2.1840967334839202e-07, "loss": 0.0006, "step": 17281 }, { "epoch": 0.9543848022973271, "grad_norm": 2.2396013736724854, "learning_rate": 2.178827557370733e-07, "loss": 0.1788, "step": 17282 }, { "epoch": 0.9544400265076209, "grad_norm": 2.467478036880493, "learning_rate": 2.1735647101200462e-07, "loss": 0.5756, "step": 17283 }, { "epoch": 0.9544952507179147, "grad_norm": 2.4607977867126465, "learning_rate": 2.1683081919001924e-07, "loss": 0.0759, "step": 17284 }, { "epoch": 0.9545504749282085, "grad_norm": 4.84468936920166, "learning_rate": 2.1630580028793924e-07, "loss": 0.4033, "step": 17285 }, { "epoch": 0.9546056991385024, "grad_norm": 5.230868816375732, "learning_rate": 2.157814143225556e-07, "loss": 0.1305, "step": 17286 }, { "epoch": 0.9546609233487962, "grad_norm": 4.802735328674316, "learning_rate": 2.152576613106483e-07, "loss": 0.7012, "step": 17287 }, { "epoch": 0.95471614755909, "grad_norm": 2.605746269226074, "learning_rate": 2.1473454126897274e-07, "loss": 0.1834, "step": 17288 }, { "epoch": 0.9547713717693836, "grad_norm": 0.2931741774082184, "learning_rate": 2.1421205421426672e-07, "loss": 0.0069, "step": 17289 }, { "epoch": 0.9548265959796775, "grad_norm": 6.086247444152832, "learning_rate": 2.1369020016324349e-07, "loss": 0.5194, "step": 17290 }, { "epoch": 0.9548818201899713, "grad_norm": 0.029640834778547287, "learning_rate": 2.131689791326008e-07, "loss": 0.0006, "step": 17291 }, { "epoch": 0.9549370444002651, "grad_norm": 4.291384220123291, "learning_rate": 2.1264839113901203e-07, "loss": 0.8136, "step": 17292 }, { "epoch": 0.9549922686105589, "grad_norm": 5.372227191925049, "learning_rate": 2.1212843619913493e-07, "loss": 0.6476, "step": 17293 }, { "epoch": 0.9550474928208527, "grad_norm": 0.0411662720143795, "learning_rate": 2.1160911432960063e-07, "loss": 0.0007, "step": 17294 }, { "epoch": 0.9551027170311465, "grad_norm": 3.6794655323028564, "learning_rate": 2.1109042554702698e-07, "loss": 0.5114, "step": 17295 }, { "epoch": 0.9551579412414403, "grad_norm": 3.5295538902282715, "learning_rate": 2.1057236986800734e-07, "loss": 0.6498, "step": 17296 }, { "epoch": 0.9552131654517341, "grad_norm": 0.11377457529306412, "learning_rate": 2.1005494730911512e-07, "loss": 0.0038, "step": 17297 }, { "epoch": 0.9552683896620279, "grad_norm": 0.04207479581236839, "learning_rate": 2.095381578869038e-07, "loss": 0.0012, "step": 17298 }, { "epoch": 0.9553236138723217, "grad_norm": 1.1753448247909546, "learning_rate": 2.0902200161790898e-07, "loss": 0.0193, "step": 17299 }, { "epoch": 0.9553788380826154, "grad_norm": 0.467011034488678, "learning_rate": 2.0850647851864191e-07, "loss": 0.0122, "step": 17300 }, { "epoch": 0.9554340622929092, "grad_norm": 1.5087835788726807, "learning_rate": 2.0799158860559832e-07, "loss": 0.049, "step": 17301 }, { "epoch": 0.955489286503203, "grad_norm": 2.1796743869781494, "learning_rate": 2.074773318952472e-07, "loss": 0.0512, "step": 17302 }, { "epoch": 0.9555445107134968, "grad_norm": 2.8254854679107666, "learning_rate": 2.0696370840404435e-07, "loss": 0.301, "step": 17303 }, { "epoch": 0.9555997349237906, "grad_norm": 0.0076531050726771355, "learning_rate": 2.0645071814841876e-07, "loss": 0.0003, "step": 17304 }, { "epoch": 0.9556549591340844, "grad_norm": 3.2729616165161133, "learning_rate": 2.0593836114478627e-07, "loss": 0.0445, "step": 17305 }, { "epoch": 0.9557101833443782, "grad_norm": 2.623026132583618, "learning_rate": 2.0542663740953594e-07, "loss": 0.2295, "step": 17306 }, { "epoch": 0.955765407554672, "grad_norm": 3.159456729888916, "learning_rate": 2.0491554695904136e-07, "loss": 0.2933, "step": 17307 }, { "epoch": 0.9558206317649658, "grad_norm": 0.2418748289346695, "learning_rate": 2.0440508980965168e-07, "loss": 0.0075, "step": 17308 }, { "epoch": 0.9558758559752596, "grad_norm": 5.924674987792969, "learning_rate": 2.0389526597770048e-07, "loss": 0.6301, "step": 17309 }, { "epoch": 0.9559310801855534, "grad_norm": 0.03664330393075943, "learning_rate": 2.0338607547949251e-07, "loss": 0.001, "step": 17310 }, { "epoch": 0.9559863043958471, "grad_norm": 0.04930984601378441, "learning_rate": 2.0287751833132585e-07, "loss": 0.0014, "step": 17311 }, { "epoch": 0.9560415286061409, "grad_norm": 0.13114073872566223, "learning_rate": 2.0236959454946748e-07, "loss": 0.0024, "step": 17312 }, { "epoch": 0.9560967528164347, "grad_norm": 1.9127097129821777, "learning_rate": 2.0186230415016439e-07, "loss": 0.042, "step": 17313 }, { "epoch": 0.9561519770267285, "grad_norm": 3.7342424392700195, "learning_rate": 2.0135564714965027e-07, "loss": 1.0321, "step": 17314 }, { "epoch": 0.9562072012370223, "grad_norm": 3.6404497623443604, "learning_rate": 2.008496235641344e-07, "loss": 0.6382, "step": 17315 }, { "epoch": 0.9562624254473161, "grad_norm": 2.547760486602783, "learning_rate": 2.003442334098038e-07, "loss": 0.0599, "step": 17316 }, { "epoch": 0.9563176496576099, "grad_norm": 7.550005912780762, "learning_rate": 1.9983947670282778e-07, "loss": 0.6825, "step": 17317 }, { "epoch": 0.9563728738679037, "grad_norm": 0.3003140985965729, "learning_rate": 1.9933535345935562e-07, "loss": 0.0056, "step": 17318 }, { "epoch": 0.9564280980781975, "grad_norm": 1.2663078308105469, "learning_rate": 1.9883186369551667e-07, "loss": 0.0134, "step": 17319 }, { "epoch": 0.9564833222884913, "grad_norm": 3.2389214038848877, "learning_rate": 1.9832900742741801e-07, "loss": 0.5283, "step": 17320 }, { "epoch": 0.9565385464987851, "grad_norm": 2.8572099208831787, "learning_rate": 1.978267846711468e-07, "loss": 0.4113, "step": 17321 }, { "epoch": 0.9565937707090788, "grad_norm": 2.3764922618865967, "learning_rate": 1.973251954427702e-07, "loss": 0.3718, "step": 17322 }, { "epoch": 0.9566489949193726, "grad_norm": 2.479933023452759, "learning_rate": 1.9682423975833754e-07, "loss": 0.0933, "step": 17323 }, { "epoch": 0.9567042191296664, "grad_norm": 0.04271508380770683, "learning_rate": 1.963239176338716e-07, "loss": 0.001, "step": 17324 }, { "epoch": 0.9567594433399602, "grad_norm": 0.011209032498300076, "learning_rate": 1.9582422908538622e-07, "loss": 0.0003, "step": 17325 }, { "epoch": 0.956814667550254, "grad_norm": 0.4866073727607727, "learning_rate": 1.9532517412885976e-07, "loss": 0.0122, "step": 17326 }, { "epoch": 0.9568698917605478, "grad_norm": 0.21027213335037231, "learning_rate": 1.9482675278026608e-07, "loss": 0.0054, "step": 17327 }, { "epoch": 0.9569251159708416, "grad_norm": 4.146854400634766, "learning_rate": 1.9432896505554577e-07, "loss": 0.553, "step": 17328 }, { "epoch": 0.9569803401811354, "grad_norm": 0.00865065399557352, "learning_rate": 1.9383181097062608e-07, "loss": 0.0002, "step": 17329 }, { "epoch": 0.9570355643914292, "grad_norm": 1.607460618019104, "learning_rate": 1.933352905414121e-07, "loss": 0.067, "step": 17330 }, { "epoch": 0.957090788601723, "grad_norm": 0.12352991849184036, "learning_rate": 1.9283940378378884e-07, "loss": 0.0027, "step": 17331 }, { "epoch": 0.9571460128120168, "grad_norm": 0.03197397291660309, "learning_rate": 1.9234415071362368e-07, "loss": 0.001, "step": 17332 }, { "epoch": 0.9572012370223106, "grad_norm": 0.5088618993759155, "learning_rate": 1.9184953134675722e-07, "loss": 0.0122, "step": 17333 }, { "epoch": 0.9572564612326043, "grad_norm": 0.011632260866463184, "learning_rate": 1.9135554569901683e-07, "loss": 0.0004, "step": 17334 }, { "epoch": 0.9573116854428981, "grad_norm": 0.21251270174980164, "learning_rate": 1.908621937862032e-07, "loss": 0.0052, "step": 17335 }, { "epoch": 0.9573669096531919, "grad_norm": 1.7494252920150757, "learning_rate": 1.9036947562410367e-07, "loss": 0.2382, "step": 17336 }, { "epoch": 0.9574221338634857, "grad_norm": 3.624969244003296, "learning_rate": 1.8987739122847903e-07, "loss": 0.093, "step": 17337 }, { "epoch": 0.9574773580737795, "grad_norm": 1.8368550539016724, "learning_rate": 1.8938594061507442e-07, "loss": 0.4691, "step": 17338 }, { "epoch": 0.9575325822840733, "grad_norm": 0.5516083836555481, "learning_rate": 1.8889512379961283e-07, "loss": 0.0086, "step": 17339 }, { "epoch": 0.9575878064943671, "grad_norm": 0.4149361550807953, "learning_rate": 1.8840494079779502e-07, "loss": 0.0115, "step": 17340 }, { "epoch": 0.957643030704661, "grad_norm": 2.575653553009033, "learning_rate": 1.8791539162530404e-07, "loss": 0.2149, "step": 17341 }, { "epoch": 0.9576982549149547, "grad_norm": 1.0510138273239136, "learning_rate": 1.8742647629780287e-07, "loss": 0.0133, "step": 17342 }, { "epoch": 0.9577534791252486, "grad_norm": 4.6956048011779785, "learning_rate": 1.8693819483093013e-07, "loss": 0.099, "step": 17343 }, { "epoch": 0.9578087033355424, "grad_norm": 4.088378429412842, "learning_rate": 1.8645054724031109e-07, "loss": 0.6385, "step": 17344 }, { "epoch": 0.957863927545836, "grad_norm": 2.75638747215271, "learning_rate": 1.859635335415466e-07, "loss": 0.33, "step": 17345 }, { "epoch": 0.9579191517561298, "grad_norm": 4.767889499664307, "learning_rate": 1.8547715375021757e-07, "loss": 0.4799, "step": 17346 }, { "epoch": 0.9579743759664237, "grad_norm": 0.1477074772119522, "learning_rate": 1.8499140788188042e-07, "loss": 0.0023, "step": 17347 }, { "epoch": 0.9580296001767175, "grad_norm": 0.018882576376199722, "learning_rate": 1.845062959520827e-07, "loss": 0.0006, "step": 17348 }, { "epoch": 0.9580848243870113, "grad_norm": 0.938119113445282, "learning_rate": 1.8402181797633867e-07, "loss": 0.0461, "step": 17349 }, { "epoch": 0.9581400485973051, "grad_norm": 0.04059215635061264, "learning_rate": 1.8353797397015148e-07, "loss": 0.0012, "step": 17350 }, { "epoch": 0.9581952728075989, "grad_norm": 3.024746894836426, "learning_rate": 1.830547639489999e-07, "loss": 0.0258, "step": 17351 }, { "epoch": 0.9582504970178927, "grad_norm": 3.9689486026763916, "learning_rate": 1.8257218792834265e-07, "loss": 0.2514, "step": 17352 }, { "epoch": 0.9583057212281865, "grad_norm": 0.08992062509059906, "learning_rate": 1.8209024592361624e-07, "loss": 0.0019, "step": 17353 }, { "epoch": 0.9583609454384803, "grad_norm": 4.361025810241699, "learning_rate": 1.8160893795024392e-07, "loss": 0.0773, "step": 17354 }, { "epoch": 0.9584161696487741, "grad_norm": 0.8158984780311584, "learning_rate": 1.8112826402362228e-07, "loss": 0.0234, "step": 17355 }, { "epoch": 0.9584713938590678, "grad_norm": 5.943154335021973, "learning_rate": 1.8064822415912785e-07, "loss": 1.2613, "step": 17356 }, { "epoch": 0.9585266180693616, "grad_norm": 0.042111679911613464, "learning_rate": 1.8016881837212175e-07, "loss": 0.0011, "step": 17357 }, { "epoch": 0.9585818422796554, "grad_norm": 3.9172260761260986, "learning_rate": 1.7969004667793833e-07, "loss": 0.2858, "step": 17358 }, { "epoch": 0.9586370664899492, "grad_norm": 1.9229639768600464, "learning_rate": 1.7921190909189645e-07, "loss": 0.1192, "step": 17359 }, { "epoch": 0.958692290700243, "grad_norm": 0.053200140595436096, "learning_rate": 1.78734405629295e-07, "loss": 0.0012, "step": 17360 }, { "epoch": 0.9587475149105368, "grad_norm": 0.1046806201338768, "learning_rate": 1.7825753630540622e-07, "loss": 0.0021, "step": 17361 }, { "epoch": 0.9588027391208306, "grad_norm": 3.524409294128418, "learning_rate": 1.7778130113548898e-07, "loss": 0.3029, "step": 17362 }, { "epoch": 0.9588579633311244, "grad_norm": 0.08668572455644608, "learning_rate": 1.7730570013478e-07, "loss": 0.0015, "step": 17363 }, { "epoch": 0.9589131875414182, "grad_norm": 0.1933221071958542, "learning_rate": 1.7683073331849377e-07, "loss": 0.0029, "step": 17364 }, { "epoch": 0.958968411751712, "grad_norm": 5.23690938949585, "learning_rate": 1.7635640070182703e-07, "loss": 0.5465, "step": 17365 }, { "epoch": 0.9590236359620058, "grad_norm": 0.15597768127918243, "learning_rate": 1.758827022999543e-07, "loss": 0.0046, "step": 17366 }, { "epoch": 0.9590788601722995, "grad_norm": 3.647789478302002, "learning_rate": 1.7540963812803013e-07, "loss": 0.301, "step": 17367 }, { "epoch": 0.9591340843825933, "grad_norm": 0.254872590303421, "learning_rate": 1.749372082011913e-07, "loss": 0.0064, "step": 17368 }, { "epoch": 0.9591893085928871, "grad_norm": 0.5301182866096497, "learning_rate": 1.7446541253454797e-07, "loss": 0.0186, "step": 17369 }, { "epoch": 0.9592445328031809, "grad_norm": 0.023184759542346, "learning_rate": 1.7399425114319913e-07, "loss": 0.0006, "step": 17370 }, { "epoch": 0.9592997570134747, "grad_norm": 0.05778229981660843, "learning_rate": 1.7352372404221495e-07, "loss": 0.0016, "step": 17371 }, { "epoch": 0.9593549812237685, "grad_norm": 1.7296497821807861, "learning_rate": 1.7305383124665232e-07, "loss": 0.0492, "step": 17372 }, { "epoch": 0.9594102054340623, "grad_norm": 0.021168911829590797, "learning_rate": 1.7258457277153917e-07, "loss": 0.0008, "step": 17373 }, { "epoch": 0.9594654296443561, "grad_norm": 2.8485984802246094, "learning_rate": 1.7211594863189463e-07, "loss": 0.2394, "step": 17374 }, { "epoch": 0.9595206538546499, "grad_norm": 7.726167678833008, "learning_rate": 1.7164795884270668e-07, "loss": 1.4191, "step": 17375 }, { "epoch": 0.9595758780649437, "grad_norm": 2.2774291038513184, "learning_rate": 1.7118060341895003e-07, "loss": 0.1178, "step": 17376 }, { "epoch": 0.9596311022752375, "grad_norm": 11.073592185974121, "learning_rate": 1.7071388237557719e-07, "loss": 0.1376, "step": 17377 }, { "epoch": 0.9596863264855312, "grad_norm": 5.07259464263916, "learning_rate": 1.7024779572751837e-07, "loss": 0.2809, "step": 17378 }, { "epoch": 0.959741550695825, "grad_norm": 4.563211917877197, "learning_rate": 1.697823434896839e-07, "loss": 1.1661, "step": 17379 }, { "epoch": 0.9597967749061188, "grad_norm": 4.205546855926514, "learning_rate": 1.6931752567696856e-07, "loss": 0.2986, "step": 17380 }, { "epoch": 0.9598519991164126, "grad_norm": 1.3588465452194214, "learning_rate": 1.6885334230423823e-07, "loss": 0.0565, "step": 17381 }, { "epoch": 0.9599072233267064, "grad_norm": 0.08639034628868103, "learning_rate": 1.6838979338634764e-07, "loss": 0.0035, "step": 17382 }, { "epoch": 0.9599624475370002, "grad_norm": 0.08623220771551132, "learning_rate": 1.67926878938125e-07, "loss": 0.0019, "step": 17383 }, { "epoch": 0.960017671747294, "grad_norm": 2.856020212173462, "learning_rate": 1.6746459897438284e-07, "loss": 0.0936, "step": 17384 }, { "epoch": 0.9600728959575878, "grad_norm": 2.245084047317505, "learning_rate": 1.6700295350990493e-07, "loss": 0.1369, "step": 17385 }, { "epoch": 0.9601281201678816, "grad_norm": 6.352586269378662, "learning_rate": 1.6654194255946832e-07, "loss": 0.5382, "step": 17386 }, { "epoch": 0.9601833443781754, "grad_norm": 1.563657522201538, "learning_rate": 1.6608156613781902e-07, "loss": 0.1051, "step": 17387 }, { "epoch": 0.9602385685884692, "grad_norm": 0.05922272801399231, "learning_rate": 1.6562182425968076e-07, "loss": 0.0021, "step": 17388 }, { "epoch": 0.9602937927987629, "grad_norm": 0.12352712452411652, "learning_rate": 1.651627169397707e-07, "loss": 0.0042, "step": 17389 }, { "epoch": 0.9603490170090567, "grad_norm": 0.04858951270580292, "learning_rate": 1.6470424419277043e-07, "loss": 0.0014, "step": 17390 }, { "epoch": 0.9604042412193505, "grad_norm": 0.05488792806863785, "learning_rate": 1.642464060333504e-07, "loss": 0.0015, "step": 17391 }, { "epoch": 0.9604594654296443, "grad_norm": 3.1695287227630615, "learning_rate": 1.6378920247615672e-07, "loss": 0.6004, "step": 17392 }, { "epoch": 0.9605146896399381, "grad_norm": 0.7668440341949463, "learning_rate": 1.6333263353581763e-07, "loss": 0.0284, "step": 17393 }, { "epoch": 0.9605699138502319, "grad_norm": 0.05376110598444939, "learning_rate": 1.628766992269415e-07, "loss": 0.001, "step": 17394 }, { "epoch": 0.9606251380605257, "grad_norm": 0.16615372896194458, "learning_rate": 1.6242139956411218e-07, "loss": 0.0028, "step": 17395 }, { "epoch": 0.9606803622708195, "grad_norm": 1.5031647682189941, "learning_rate": 1.6196673456189804e-07, "loss": 0.1559, "step": 17396 }, { "epoch": 0.9607355864811133, "grad_norm": 0.5185900926589966, "learning_rate": 1.6151270423484522e-07, "loss": 0.0142, "step": 17397 }, { "epoch": 0.9607908106914071, "grad_norm": 5.629923343658447, "learning_rate": 1.6105930859747766e-07, "loss": 0.9348, "step": 17398 }, { "epoch": 0.960846034901701, "grad_norm": 4.080100059509277, "learning_rate": 1.606065476643015e-07, "loss": 0.4392, "step": 17399 }, { "epoch": 0.9609012591119946, "grad_norm": 0.04689042270183563, "learning_rate": 1.60154421449803e-07, "loss": 0.0008, "step": 17400 }, { "epoch": 0.9609564833222884, "grad_norm": 0.1737901121377945, "learning_rate": 1.5970292996844606e-07, "loss": 0.005, "step": 17401 }, { "epoch": 0.9610117075325822, "grad_norm": 2.016005277633667, "learning_rate": 1.5925207323467474e-07, "loss": 0.1082, "step": 17402 }, { "epoch": 0.961066931742876, "grad_norm": 3.7837202548980713, "learning_rate": 1.5880185126291525e-07, "loss": 0.3369, "step": 17403 }, { "epoch": 0.9611221559531699, "grad_norm": 2.789966106414795, "learning_rate": 1.583522640675672e-07, "loss": 0.4433, "step": 17404 }, { "epoch": 0.9611773801634637, "grad_norm": 5.928807258605957, "learning_rate": 1.579033116630191e-07, "loss": 1.5281, "step": 17405 }, { "epoch": 0.9612326043737575, "grad_norm": 0.08333393186330795, "learning_rate": 1.5745499406363053e-07, "loss": 0.0023, "step": 17406 }, { "epoch": 0.9612878285840513, "grad_norm": 7.335682392120361, "learning_rate": 1.570073112837478e-07, "loss": 0.9959, "step": 17407 }, { "epoch": 0.9613430527943451, "grad_norm": 1.968621015548706, "learning_rate": 1.5656026333768837e-07, "loss": 0.2321, "step": 17408 }, { "epoch": 0.9613982770046389, "grad_norm": 0.2419314682483673, "learning_rate": 1.5611385023976078e-07, "loss": 0.0051, "step": 17409 }, { "epoch": 0.9614535012149327, "grad_norm": 0.7013644576072693, "learning_rate": 1.5566807200424473e-07, "loss": 0.0207, "step": 17410 }, { "epoch": 0.9615087254252265, "grad_norm": 1.19621741771698, "learning_rate": 1.552229286453999e-07, "loss": 0.0444, "step": 17411 }, { "epoch": 0.9615639496355202, "grad_norm": 2.568026065826416, "learning_rate": 1.5477842017746825e-07, "loss": 0.2671, "step": 17412 }, { "epoch": 0.961619173845814, "grad_norm": 0.03668108582496643, "learning_rate": 1.5433454661467395e-07, "loss": 0.0013, "step": 17413 }, { "epoch": 0.9616743980561078, "grad_norm": 2.650139570236206, "learning_rate": 1.5389130797121233e-07, "loss": 0.4777, "step": 17414 }, { "epoch": 0.9617296222664016, "grad_norm": 0.0345768965780735, "learning_rate": 1.534487042612698e-07, "loss": 0.0013, "step": 17415 }, { "epoch": 0.9617848464766954, "grad_norm": 0.06074170768260956, "learning_rate": 1.5300673549900392e-07, "loss": 0.0014, "step": 17416 }, { "epoch": 0.9618400706869892, "grad_norm": 2.4714388847351074, "learning_rate": 1.525654016985545e-07, "loss": 0.4369, "step": 17417 }, { "epoch": 0.961895294897283, "grad_norm": 0.17832928895950317, "learning_rate": 1.5212470287403914e-07, "loss": 0.0024, "step": 17418 }, { "epoch": 0.9619505191075768, "grad_norm": 0.8431175351142883, "learning_rate": 1.5168463903955987e-07, "loss": 0.0222, "step": 17419 }, { "epoch": 0.9620057433178706, "grad_norm": 0.024555956944823265, "learning_rate": 1.5124521020919437e-07, "loss": 0.0007, "step": 17420 }, { "epoch": 0.9620609675281644, "grad_norm": 0.015399829484522343, "learning_rate": 1.5080641639700244e-07, "loss": 0.0002, "step": 17421 }, { "epoch": 0.9621161917384582, "grad_norm": 0.08414950966835022, "learning_rate": 1.5036825761702178e-07, "loss": 0.0017, "step": 17422 }, { "epoch": 0.9621714159487519, "grad_norm": 0.01882888190448284, "learning_rate": 1.4993073388327005e-07, "loss": 0.0004, "step": 17423 }, { "epoch": 0.9622266401590457, "grad_norm": 0.040579888969659805, "learning_rate": 1.4949384520974274e-07, "loss": 0.0011, "step": 17424 }, { "epoch": 0.9622818643693395, "grad_norm": 0.036704495549201965, "learning_rate": 1.4905759161041978e-07, "loss": 0.0006, "step": 17425 }, { "epoch": 0.9623370885796333, "grad_norm": 0.15871676802635193, "learning_rate": 1.4862197309925884e-07, "loss": 0.0053, "step": 17426 }, { "epoch": 0.9623923127899271, "grad_norm": 0.11364021897315979, "learning_rate": 1.4818698969019552e-07, "loss": 0.0043, "step": 17427 }, { "epoch": 0.9624475370002209, "grad_norm": 0.9581013321876526, "learning_rate": 1.4775264139714308e-07, "loss": 0.0179, "step": 17428 }, { "epoch": 0.9625027612105147, "grad_norm": 0.492503821849823, "learning_rate": 1.4731892823400373e-07, "loss": 0.0182, "step": 17429 }, { "epoch": 0.9625579854208085, "grad_norm": 0.0669068843126297, "learning_rate": 1.4688585021464863e-07, "loss": 0.0016, "step": 17430 }, { "epoch": 0.9626132096311023, "grad_norm": 2.9691519737243652, "learning_rate": 1.4645340735293556e-07, "loss": 0.2237, "step": 17431 }, { "epoch": 0.9626684338413961, "grad_norm": 0.5368924736976624, "learning_rate": 1.4602159966269792e-07, "loss": 0.0135, "step": 17432 }, { "epoch": 0.9627236580516899, "grad_norm": 0.08682020753622055, "learning_rate": 1.4559042715774907e-07, "loss": 0.0016, "step": 17433 }, { "epoch": 0.9627788822619836, "grad_norm": 0.014764189720153809, "learning_rate": 1.451598898518869e-07, "loss": 0.0003, "step": 17434 }, { "epoch": 0.9628341064722774, "grad_norm": 0.005992291960865259, "learning_rate": 1.447299877588848e-07, "loss": 0.0001, "step": 17435 }, { "epoch": 0.9628893306825712, "grad_norm": 3.2231528759002686, "learning_rate": 1.4430072089249626e-07, "loss": 0.076, "step": 17436 }, { "epoch": 0.962944554892865, "grad_norm": 3.678797960281372, "learning_rate": 1.4387208926645246e-07, "loss": 0.3797, "step": 17437 }, { "epoch": 0.9629997791031588, "grad_norm": 0.006430828012526035, "learning_rate": 1.4344409289446913e-07, "loss": 0.0001, "step": 17438 }, { "epoch": 0.9630550033134526, "grad_norm": 3.4371182918548584, "learning_rate": 1.4301673179023978e-07, "loss": 0.3209, "step": 17439 }, { "epoch": 0.9631102275237464, "grad_norm": 3.844680070877075, "learning_rate": 1.4259000596743344e-07, "loss": 0.7839, "step": 17440 }, { "epoch": 0.9631654517340402, "grad_norm": 5.0178985595703125, "learning_rate": 1.4216391543970588e-07, "loss": 0.9939, "step": 17441 }, { "epoch": 0.963220675944334, "grad_norm": 5.0286455154418945, "learning_rate": 1.4173846022068615e-07, "loss": 0.2267, "step": 17442 }, { "epoch": 0.9632759001546278, "grad_norm": 3.7217490673065186, "learning_rate": 1.4131364032398786e-07, "loss": 0.8545, "step": 17443 }, { "epoch": 0.9633311243649216, "grad_norm": 4.441430568695068, "learning_rate": 1.4088945576320013e-07, "loss": 0.912, "step": 17444 }, { "epoch": 0.9633863485752153, "grad_norm": 3.091168165206909, "learning_rate": 1.4046590655189873e-07, "loss": 0.4113, "step": 17445 }, { "epoch": 0.9634415727855091, "grad_norm": 1.2286748886108398, "learning_rate": 1.400429927036262e-07, "loss": 0.1381, "step": 17446 }, { "epoch": 0.9634967969958029, "grad_norm": 3.068570613861084, "learning_rate": 1.3962071423191836e-07, "loss": 0.2071, "step": 17447 }, { "epoch": 0.9635520212060967, "grad_norm": 3.3614301681518555, "learning_rate": 1.3919907115028442e-07, "loss": 0.377, "step": 17448 }, { "epoch": 0.9636072454163905, "grad_norm": 0.02465614303946495, "learning_rate": 1.3877806347221355e-07, "loss": 0.0005, "step": 17449 }, { "epoch": 0.9636624696266843, "grad_norm": 0.17389240860939026, "learning_rate": 1.3835769121117505e-07, "loss": 0.0031, "step": 17450 }, { "epoch": 0.9637176938369781, "grad_norm": 4.694025993347168, "learning_rate": 1.3793795438061809e-07, "loss": 0.4943, "step": 17451 }, { "epoch": 0.9637729180472719, "grad_norm": 2.1718995571136475, "learning_rate": 1.3751885299396973e-07, "loss": 0.2538, "step": 17452 }, { "epoch": 0.9638281422575657, "grad_norm": 1.7315312623977661, "learning_rate": 1.3710038706463923e-07, "loss": 0.0522, "step": 17453 }, { "epoch": 0.9638833664678595, "grad_norm": 2.504845380783081, "learning_rate": 1.366825566060137e-07, "loss": 0.3916, "step": 17454 }, { "epoch": 0.9639385906781534, "grad_norm": 3.428607940673828, "learning_rate": 1.3626536163146242e-07, "loss": 0.4513, "step": 17455 }, { "epoch": 0.963993814888447, "grad_norm": 0.04283468425273895, "learning_rate": 1.3584880215433248e-07, "loss": 0.001, "step": 17456 }, { "epoch": 0.9640490390987408, "grad_norm": 2.666882276535034, "learning_rate": 1.354328781879488e-07, "loss": 0.1919, "step": 17457 }, { "epoch": 0.9641042633090346, "grad_norm": 3.8348724842071533, "learning_rate": 1.3501758974562073e-07, "loss": 0.4544, "step": 17458 }, { "epoch": 0.9641594875193285, "grad_norm": 6.970417499542236, "learning_rate": 1.346029368406332e-07, "loss": 1.4822, "step": 17459 }, { "epoch": 0.9642147117296223, "grad_norm": 0.025900334119796753, "learning_rate": 1.3418891948625113e-07, "loss": 0.0008, "step": 17460 }, { "epoch": 0.9642699359399161, "grad_norm": 0.022985102608799934, "learning_rate": 1.337755376957195e-07, "loss": 0.0008, "step": 17461 }, { "epoch": 0.9643251601502099, "grad_norm": 0.7567604184150696, "learning_rate": 1.3336279148226772e-07, "loss": 0.0153, "step": 17462 }, { "epoch": 0.9643803843605037, "grad_norm": 0.5153679847717285, "learning_rate": 1.3295068085909635e-07, "loss": 0.0126, "step": 17463 }, { "epoch": 0.9644356085707975, "grad_norm": 3.348177194595337, "learning_rate": 1.325392058393904e-07, "loss": 0.2518, "step": 17464 }, { "epoch": 0.9644908327810913, "grad_norm": 0.18836501240730286, "learning_rate": 1.3212836643631933e-07, "loss": 0.0044, "step": 17465 }, { "epoch": 0.9645460569913851, "grad_norm": 0.46758127212524414, "learning_rate": 1.317181626630193e-07, "loss": 0.0108, "step": 17466 }, { "epoch": 0.9646012812016788, "grad_norm": 5.107415676116943, "learning_rate": 1.3130859453261978e-07, "loss": 0.8542, "step": 17467 }, { "epoch": 0.9646565054119726, "grad_norm": 3.4662623405456543, "learning_rate": 1.3089966205822148e-07, "loss": 0.6063, "step": 17468 }, { "epoch": 0.9647117296222664, "grad_norm": 1.2000775337219238, "learning_rate": 1.3049136525290718e-07, "loss": 0.0587, "step": 17469 }, { "epoch": 0.9647669538325602, "grad_norm": 3.979098320007324, "learning_rate": 1.3008370412974202e-07, "loss": 0.1257, "step": 17470 }, { "epoch": 0.964822178042854, "grad_norm": 0.3996807038784027, "learning_rate": 1.2967667870176447e-07, "loss": 0.0081, "step": 17471 }, { "epoch": 0.9648774022531478, "grad_norm": 0.14789217710494995, "learning_rate": 1.2927028898199966e-07, "loss": 0.0056, "step": 17472 }, { "epoch": 0.9649326264634416, "grad_norm": 2.8444066047668457, "learning_rate": 1.2886453498344608e-07, "loss": 0.8115, "step": 17473 }, { "epoch": 0.9649878506737354, "grad_norm": 2.7518129348754883, "learning_rate": 1.284594167190867e-07, "loss": 0.3907, "step": 17474 }, { "epoch": 0.9650430748840292, "grad_norm": 0.016307521611452103, "learning_rate": 1.2805493420188442e-07, "loss": 0.0004, "step": 17475 }, { "epoch": 0.965098299094323, "grad_norm": 0.018550677224993706, "learning_rate": 1.276510874447756e-07, "loss": 0.0003, "step": 17476 }, { "epoch": 0.9651535233046168, "grad_norm": 0.09276396036148071, "learning_rate": 1.2724787646068325e-07, "loss": 0.0033, "step": 17477 }, { "epoch": 0.9652087475149106, "grad_norm": 3.691075563430786, "learning_rate": 1.2684530126250816e-07, "loss": 0.1188, "step": 17478 }, { "epoch": 0.9652639717252043, "grad_norm": 0.6400064826011658, "learning_rate": 1.2644336186312668e-07, "loss": 0.0152, "step": 17479 }, { "epoch": 0.9653191959354981, "grad_norm": 2.4562981128692627, "learning_rate": 1.2604205827539962e-07, "loss": 0.0729, "step": 17480 }, { "epoch": 0.9653744201457919, "grad_norm": 0.07141686230897903, "learning_rate": 1.256413905121656e-07, "loss": 0.0018, "step": 17481 }, { "epoch": 0.9654296443560857, "grad_norm": 0.5979609489440918, "learning_rate": 1.252413585862433e-07, "loss": 0.0148, "step": 17482 }, { "epoch": 0.9654848685663795, "grad_norm": 1.0186405181884766, "learning_rate": 1.2484196251043134e-07, "loss": 0.0174, "step": 17483 }, { "epoch": 0.9655400927766733, "grad_norm": 0.03144540637731552, "learning_rate": 1.244432022975084e-07, "loss": 0.0009, "step": 17484 }, { "epoch": 0.9655953169869671, "grad_norm": 0.06143035367131233, "learning_rate": 1.2404507796022647e-07, "loss": 0.0013, "step": 17485 }, { "epoch": 0.9656505411972609, "grad_norm": 0.03578682988882065, "learning_rate": 1.2364758951133093e-07, "loss": 0.0006, "step": 17486 }, { "epoch": 0.9657057654075547, "grad_norm": 0.039142485707998276, "learning_rate": 1.2325073696353163e-07, "loss": 0.0011, "step": 17487 }, { "epoch": 0.9657609896178485, "grad_norm": 2.801668405532837, "learning_rate": 1.228545203295295e-07, "loss": 0.108, "step": 17488 }, { "epoch": 0.9658162138281423, "grad_norm": 2.640401601791382, "learning_rate": 1.2245893962199883e-07, "loss": 0.1222, "step": 17489 }, { "epoch": 0.965871438038436, "grad_norm": 5.724954128265381, "learning_rate": 1.2206399485359621e-07, "loss": 0.9138, "step": 17490 }, { "epoch": 0.9659266622487298, "grad_norm": 1.7452163696289062, "learning_rate": 1.2166968603695594e-07, "loss": 0.0402, "step": 17491 }, { "epoch": 0.9659818864590236, "grad_norm": 3.0355188846588135, "learning_rate": 1.2127601318469239e-07, "loss": 0.5787, "step": 17492 }, { "epoch": 0.9660371106693174, "grad_norm": 0.25968989729881287, "learning_rate": 1.2088297630940216e-07, "loss": 0.0058, "step": 17493 }, { "epoch": 0.9660923348796112, "grad_norm": 1.0863323211669922, "learning_rate": 1.204905754236596e-07, "loss": 0.0243, "step": 17494 }, { "epoch": 0.966147559089905, "grad_norm": 2.822983980178833, "learning_rate": 1.200988105400147e-07, "loss": 0.7266, "step": 17495 }, { "epoch": 0.9662027833001988, "grad_norm": 2.1619536876678467, "learning_rate": 1.1970768167100855e-07, "loss": 0.274, "step": 17496 }, { "epoch": 0.9662580075104926, "grad_norm": 3.262244939804077, "learning_rate": 1.1931718882914888e-07, "loss": 0.296, "step": 17497 }, { "epoch": 0.9663132317207864, "grad_norm": 0.049873415380716324, "learning_rate": 1.1892733202693019e-07, "loss": 0.0012, "step": 17498 }, { "epoch": 0.9663684559310802, "grad_norm": 0.243150994181633, "learning_rate": 1.1853811127682247e-07, "loss": 0.006, "step": 17499 }, { "epoch": 0.966423680141374, "grad_norm": 0.6360136270523071, "learning_rate": 1.1814952659128465e-07, "loss": 0.1379, "step": 17500 }, { "epoch": 0.9664789043516677, "grad_norm": 0.7203343510627747, "learning_rate": 1.1776157798274235e-07, "loss": 0.0144, "step": 17501 }, { "epoch": 0.9665341285619615, "grad_norm": 2.3106606006622314, "learning_rate": 1.1737426546361009e-07, "loss": 0.151, "step": 17502 }, { "epoch": 0.9665893527722553, "grad_norm": 2.4023656845092773, "learning_rate": 1.1698758904627794e-07, "loss": 0.1101, "step": 17503 }, { "epoch": 0.9666445769825491, "grad_norm": 0.04158025607466698, "learning_rate": 1.1660154874311825e-07, "loss": 0.0016, "step": 17504 }, { "epoch": 0.9666998011928429, "grad_norm": 0.2121286243200302, "learning_rate": 1.162161445664789e-07, "loss": 0.0033, "step": 17505 }, { "epoch": 0.9667550254031367, "grad_norm": 2.5152201652526855, "learning_rate": 1.1583137652869225e-07, "loss": 0.388, "step": 17506 }, { "epoch": 0.9668102496134305, "grad_norm": 3.3996307849884033, "learning_rate": 1.1544724464206847e-07, "loss": 0.2744, "step": 17507 }, { "epoch": 0.9668654738237243, "grad_norm": 4.0137104988098145, "learning_rate": 1.1506374891889549e-07, "loss": 0.0986, "step": 17508 }, { "epoch": 0.9669206980340181, "grad_norm": 0.012144767679274082, "learning_rate": 1.1468088937144351e-07, "loss": 0.0004, "step": 17509 }, { "epoch": 0.966975922244312, "grad_norm": 0.06111835688352585, "learning_rate": 1.1429866601196049e-07, "loss": 0.0017, "step": 17510 }, { "epoch": 0.9670311464546058, "grad_norm": 1.3135175704956055, "learning_rate": 1.1391707885267667e-07, "loss": 0.0835, "step": 17511 }, { "epoch": 0.9670863706648994, "grad_norm": 0.12526679039001465, "learning_rate": 1.135361279057956e-07, "loss": 0.0028, "step": 17512 }, { "epoch": 0.9671415948751932, "grad_norm": 0.08998769521713257, "learning_rate": 1.1315581318350976e-07, "loss": 0.0019, "step": 17513 }, { "epoch": 0.967196819085487, "grad_norm": 2.770526170730591, "learning_rate": 1.1277613469798498e-07, "loss": 0.1071, "step": 17514 }, { "epoch": 0.9672520432957809, "grad_norm": 0.016701137647032738, "learning_rate": 1.1239709246136932e-07, "loss": 0.0005, "step": 17515 }, { "epoch": 0.9673072675060747, "grad_norm": 0.4037381708621979, "learning_rate": 1.1201868648578417e-07, "loss": 0.0117, "step": 17516 }, { "epoch": 0.9673624917163685, "grad_norm": 4.961474895477295, "learning_rate": 1.1164091678334433e-07, "loss": 0.1816, "step": 17517 }, { "epoch": 0.9674177159266623, "grad_norm": 0.27284130454063416, "learning_rate": 1.1126378336612898e-07, "loss": 0.0075, "step": 17518 }, { "epoch": 0.9674729401369561, "grad_norm": 4.431385040283203, "learning_rate": 1.1088728624620626e-07, "loss": 0.5094, "step": 17519 }, { "epoch": 0.9675281643472499, "grad_norm": 0.32711905241012573, "learning_rate": 1.1051142543561988e-07, "loss": 0.0058, "step": 17520 }, { "epoch": 0.9675833885575437, "grad_norm": 0.0635712519288063, "learning_rate": 1.1013620094639798e-07, "loss": 0.0017, "step": 17521 }, { "epoch": 0.9676386127678375, "grad_norm": 0.46389585733413696, "learning_rate": 1.0976161279053987e-07, "loss": 0.0076, "step": 17522 }, { "epoch": 0.9676938369781312, "grad_norm": 4.905228614807129, "learning_rate": 1.0938766098003595e-07, "loss": 0.3058, "step": 17523 }, { "epoch": 0.967749061188425, "grad_norm": 3.3574728965759277, "learning_rate": 1.0901434552684553e-07, "loss": 0.0427, "step": 17524 }, { "epoch": 0.9678042853987188, "grad_norm": 2.5533714294433594, "learning_rate": 1.0864166644291463e-07, "loss": 0.0716, "step": 17525 }, { "epoch": 0.9678595096090126, "grad_norm": 0.05938750505447388, "learning_rate": 1.0826962374016259e-07, "loss": 0.0013, "step": 17526 }, { "epoch": 0.9679147338193064, "grad_norm": 0.02849162556231022, "learning_rate": 1.0789821743049766e-07, "loss": 0.0007, "step": 17527 }, { "epoch": 0.9679699580296002, "grad_norm": 1.2132673263549805, "learning_rate": 1.075274475257948e-07, "loss": 0.0464, "step": 17528 }, { "epoch": 0.968025182239894, "grad_norm": 1.9032304286956787, "learning_rate": 1.0715731403792451e-07, "loss": 0.0751, "step": 17529 }, { "epoch": 0.9680804064501878, "grad_norm": 1.9071159362792969, "learning_rate": 1.0678781697872175e-07, "loss": 0.0632, "step": 17530 }, { "epoch": 0.9681356306604816, "grad_norm": 0.667900562286377, "learning_rate": 1.0641895636001042e-07, "loss": 0.0292, "step": 17531 }, { "epoch": 0.9681908548707754, "grad_norm": 0.022144753485918045, "learning_rate": 1.0605073219358997e-07, "loss": 0.0005, "step": 17532 }, { "epoch": 0.9682460790810692, "grad_norm": 0.04942150413990021, "learning_rate": 1.056831444912465e-07, "loss": 0.001, "step": 17533 }, { "epoch": 0.9683013032913629, "grad_norm": 3.007660388946533, "learning_rate": 1.0531619326473063e-07, "loss": 0.3524, "step": 17534 }, { "epoch": 0.9683565275016567, "grad_norm": 0.9297536611557007, "learning_rate": 1.0494987852579074e-07, "loss": 0.0411, "step": 17535 }, { "epoch": 0.9684117517119505, "grad_norm": 0.18935440480709076, "learning_rate": 1.0458420028614191e-07, "loss": 0.0039, "step": 17536 }, { "epoch": 0.9684669759222443, "grad_norm": 0.06328563392162323, "learning_rate": 1.0421915855748366e-07, "loss": 0.0012, "step": 17537 }, { "epoch": 0.9685222001325381, "grad_norm": 2.537700891494751, "learning_rate": 1.0385475335149553e-07, "loss": 0.4284, "step": 17538 }, { "epoch": 0.9685774243428319, "grad_norm": 4.030620574951172, "learning_rate": 1.0349098467983709e-07, "loss": 0.1853, "step": 17539 }, { "epoch": 0.9686326485531257, "grad_norm": 6.477035999298096, "learning_rate": 1.0312785255414349e-07, "loss": 0.1774, "step": 17540 }, { "epoch": 0.9686878727634195, "grad_norm": 3.8328685760498047, "learning_rate": 1.027653569860343e-07, "loss": 0.3817, "step": 17541 }, { "epoch": 0.9687430969737133, "grad_norm": 0.12484346330165863, "learning_rate": 1.0240349798710691e-07, "loss": 0.002, "step": 17542 }, { "epoch": 0.9687983211840071, "grad_norm": 0.19317950308322906, "learning_rate": 1.0204227556893653e-07, "loss": 0.003, "step": 17543 }, { "epoch": 0.9688535453943009, "grad_norm": 0.6970598697662354, "learning_rate": 1.0168168974308057e-07, "loss": 0.0176, "step": 17544 }, { "epoch": 0.9689087696045946, "grad_norm": 0.01703745312988758, "learning_rate": 1.0132174052107647e-07, "loss": 0.0004, "step": 17545 }, { "epoch": 0.9689639938148884, "grad_norm": 1.4039958715438843, "learning_rate": 1.0096242791443722e-07, "loss": 0.0391, "step": 17546 }, { "epoch": 0.9690192180251822, "grad_norm": 0.009068007580935955, "learning_rate": 1.0060375193466032e-07, "loss": 0.0003, "step": 17547 }, { "epoch": 0.969074442235476, "grad_norm": 2.117961883544922, "learning_rate": 1.0024571259322102e-07, "loss": 0.0379, "step": 17548 }, { "epoch": 0.9691296664457698, "grad_norm": 0.04408280923962593, "learning_rate": 9.988830990157461e-08, "loss": 0.0015, "step": 17549 }, { "epoch": 0.9691848906560636, "grad_norm": 0.6729722619056702, "learning_rate": 9.953154387115194e-08, "loss": 0.0095, "step": 17550 }, { "epoch": 0.9692401148663574, "grad_norm": 0.07679782807826996, "learning_rate": 9.917541451337054e-08, "loss": 0.0019, "step": 17551 }, { "epoch": 0.9692953390766512, "grad_norm": 3.4492390155792236, "learning_rate": 9.881992183962353e-08, "loss": 0.342, "step": 17552 }, { "epoch": 0.969350563286945, "grad_norm": 5.736237049102783, "learning_rate": 9.846506586128179e-08, "loss": 0.2141, "step": 17553 }, { "epoch": 0.9694057874972388, "grad_norm": 0.9719985723495483, "learning_rate": 9.811084658970072e-08, "loss": 0.0204, "step": 17554 }, { "epoch": 0.9694610117075326, "grad_norm": 1.8559973239898682, "learning_rate": 9.775726403621123e-08, "loss": 0.0842, "step": 17555 }, { "epoch": 0.9695162359178264, "grad_norm": 0.27963823080062866, "learning_rate": 9.740431821212648e-08, "loss": 0.0059, "step": 17556 }, { "epoch": 0.9695714601281201, "grad_norm": 0.022968946024775505, "learning_rate": 9.705200912873968e-08, "loss": 0.0006, "step": 17557 }, { "epoch": 0.9696266843384139, "grad_norm": 2.5357866287231445, "learning_rate": 9.670033679731738e-08, "loss": 0.0737, "step": 17558 }, { "epoch": 0.9696819085487077, "grad_norm": 1.7601215839385986, "learning_rate": 9.6349301229115e-08, "loss": 0.0208, "step": 17559 }, { "epoch": 0.9697371327590015, "grad_norm": 0.06565242260694504, "learning_rate": 9.599890243535915e-08, "loss": 0.0017, "step": 17560 }, { "epoch": 0.9697923569692953, "grad_norm": 0.015416617505252361, "learning_rate": 9.564914042726525e-08, "loss": 0.0005, "step": 17561 }, { "epoch": 0.9698475811795891, "grad_norm": 1.4158720970153809, "learning_rate": 9.530001521601995e-08, "loss": 0.0399, "step": 17562 }, { "epoch": 0.9699028053898829, "grad_norm": 0.26851439476013184, "learning_rate": 9.495152681279429e-08, "loss": 0.007, "step": 17563 }, { "epoch": 0.9699580296001767, "grad_norm": 0.039113134145736694, "learning_rate": 9.460367522873492e-08, "loss": 0.0014, "step": 17564 }, { "epoch": 0.9700132538104705, "grad_norm": 1.3746839761734009, "learning_rate": 9.425646047497294e-08, "loss": 0.0388, "step": 17565 }, { "epoch": 0.9700684780207643, "grad_norm": 4.338685512542725, "learning_rate": 9.390988256261501e-08, "loss": 0.4992, "step": 17566 }, { "epoch": 0.9701237022310581, "grad_norm": 2.234295606613159, "learning_rate": 9.356394150275005e-08, "loss": 0.1232, "step": 17567 }, { "epoch": 0.9701789264413518, "grad_norm": 3.7931368350982666, "learning_rate": 9.321863730644698e-08, "loss": 0.675, "step": 17568 }, { "epoch": 0.9702341506516456, "grad_norm": 2.6026246547698975, "learning_rate": 9.28739699847503e-08, "loss": 0.3185, "step": 17569 }, { "epoch": 0.9702893748619394, "grad_norm": 0.005214501637965441, "learning_rate": 9.252993954869116e-08, "loss": 0.0001, "step": 17570 }, { "epoch": 0.9703445990722332, "grad_norm": 3.1460044384002686, "learning_rate": 9.218654600926969e-08, "loss": 0.4417, "step": 17571 }, { "epoch": 0.970399823282527, "grad_norm": 1.584104061126709, "learning_rate": 9.184378937747928e-08, "loss": 0.0864, "step": 17572 }, { "epoch": 0.9704550474928209, "grad_norm": 6.1603474617004395, "learning_rate": 9.150166966427787e-08, "loss": 0.5909, "step": 17573 }, { "epoch": 0.9705102717031147, "grad_norm": 4.098119258880615, "learning_rate": 9.116018688061889e-08, "loss": 0.7299, "step": 17574 }, { "epoch": 0.9705654959134085, "grad_norm": 0.01807871274650097, "learning_rate": 9.08193410374203e-08, "loss": 0.0006, "step": 17575 }, { "epoch": 0.9706207201237023, "grad_norm": 4.184638023376465, "learning_rate": 9.047913214559334e-08, "loss": 0.2397, "step": 17576 }, { "epoch": 0.9706759443339961, "grad_norm": 4.664056777954102, "learning_rate": 9.0139560216016e-08, "loss": 0.7059, "step": 17577 }, { "epoch": 0.9707311685442899, "grad_norm": 3.5347578525543213, "learning_rate": 8.980062525955513e-08, "loss": 0.2093, "step": 17578 }, { "epoch": 0.9707863927545836, "grad_norm": 0.12596087157726288, "learning_rate": 8.94623272870554e-08, "loss": 0.0028, "step": 17579 }, { "epoch": 0.9708416169648774, "grad_norm": 4.376523494720459, "learning_rate": 8.912466630933703e-08, "loss": 0.8547, "step": 17580 }, { "epoch": 0.9708968411751712, "grad_norm": 3.0839524269104004, "learning_rate": 8.878764233720694e-08, "loss": 0.3098, "step": 17581 }, { "epoch": 0.970952065385465, "grad_norm": 0.04680472984910011, "learning_rate": 8.845125538144317e-08, "loss": 0.0011, "step": 17582 }, { "epoch": 0.9710072895957588, "grad_norm": 0.05818329378962517, "learning_rate": 8.811550545280822e-08, "loss": 0.0012, "step": 17583 }, { "epoch": 0.9710625138060526, "grad_norm": 0.13265743851661682, "learning_rate": 8.778039256204685e-08, "loss": 0.0041, "step": 17584 }, { "epoch": 0.9711177380163464, "grad_norm": 3.426811933517456, "learning_rate": 8.744591671987712e-08, "loss": 0.6782, "step": 17585 }, { "epoch": 0.9711729622266402, "grad_norm": 4.565216064453125, "learning_rate": 8.71120779370016e-08, "loss": 1.4058, "step": 17586 }, { "epoch": 0.971228186436934, "grad_norm": 4.52297306060791, "learning_rate": 8.677887622410064e-08, "loss": 0.4102, "step": 17587 }, { "epoch": 0.9712834106472278, "grad_norm": 2.6097960472106934, "learning_rate": 8.644631159183458e-08, "loss": 0.5833, "step": 17588 }, { "epoch": 0.9713386348575216, "grad_norm": 6.23928689956665, "learning_rate": 8.611438405083938e-08, "loss": 0.3565, "step": 17589 }, { "epoch": 0.9713938590678153, "grad_norm": 3.1367080211639404, "learning_rate": 8.578309361173986e-08, "loss": 0.2527, "step": 17590 }, { "epoch": 0.9714490832781091, "grad_norm": 0.021293867379426956, "learning_rate": 8.5452440285132e-08, "loss": 0.0007, "step": 17591 }, { "epoch": 0.9715043074884029, "grad_norm": 1.0181806087493896, "learning_rate": 8.512242408159398e-08, "loss": 0.0218, "step": 17592 }, { "epoch": 0.9715595316986967, "grad_norm": 0.19398818910121918, "learning_rate": 8.479304501168407e-08, "loss": 0.0038, "step": 17593 }, { "epoch": 0.9716147559089905, "grad_norm": 2.287123441696167, "learning_rate": 8.446430308594267e-08, "loss": 0.2852, "step": 17594 }, { "epoch": 0.9716699801192843, "grad_norm": 0.016978641971945763, "learning_rate": 8.413619831488584e-08, "loss": 0.0004, "step": 17595 }, { "epoch": 0.9717252043295781, "grad_norm": 0.2137695699930191, "learning_rate": 8.380873070900741e-08, "loss": 0.0058, "step": 17596 }, { "epoch": 0.9717804285398719, "grad_norm": 0.03999718278646469, "learning_rate": 8.348190027878789e-08, "loss": 0.0014, "step": 17597 }, { "epoch": 0.9718356527501657, "grad_norm": 0.04220976680517197, "learning_rate": 8.315570703468334e-08, "loss": 0.0011, "step": 17598 }, { "epoch": 0.9718908769604595, "grad_norm": 0.3418954610824585, "learning_rate": 8.283015098712543e-08, "loss": 0.0073, "step": 17599 }, { "epoch": 0.9719461011707533, "grad_norm": 4.455694198608398, "learning_rate": 8.250523214653472e-08, "loss": 0.8726, "step": 17600 }, { "epoch": 0.972001325381047, "grad_norm": 4.686065673828125, "learning_rate": 8.21809505233051e-08, "loss": 0.3992, "step": 17601 }, { "epoch": 0.9720565495913408, "grad_norm": 2.917654037475586, "learning_rate": 8.185730612780829e-08, "loss": 0.3189, "step": 17602 }, { "epoch": 0.9721117738016346, "grad_norm": 1.801389455795288, "learning_rate": 8.153429897040044e-08, "loss": 0.0851, "step": 17603 }, { "epoch": 0.9721669980119284, "grad_norm": 1.1501582860946655, "learning_rate": 8.121192906141773e-08, "loss": 0.0277, "step": 17604 }, { "epoch": 0.9722222222222222, "grad_norm": 0.6756824851036072, "learning_rate": 8.089019641117191e-08, "loss": 0.0177, "step": 17605 }, { "epoch": 0.972277446432516, "grad_norm": 0.10085880756378174, "learning_rate": 8.056910102995475e-08, "loss": 0.0032, "step": 17606 }, { "epoch": 0.9723326706428098, "grad_norm": 1.393599033355713, "learning_rate": 8.024864292804024e-08, "loss": 0.0341, "step": 17607 }, { "epoch": 0.9723878948531036, "grad_norm": 0.019020749256014824, "learning_rate": 7.99288221156802e-08, "loss": 0.0003, "step": 17608 }, { "epoch": 0.9724431190633974, "grad_norm": 6.0731201171875, "learning_rate": 7.960963860310644e-08, "loss": 0.3508, "step": 17609 }, { "epoch": 0.9724983432736912, "grad_norm": 0.027992580085992813, "learning_rate": 7.929109240053301e-08, "loss": 0.0007, "step": 17610 }, { "epoch": 0.972553567483985, "grad_norm": 2.352922201156616, "learning_rate": 7.897318351814953e-08, "loss": 0.0767, "step": 17611 }, { "epoch": 0.9726087916942787, "grad_norm": 0.16096599400043488, "learning_rate": 7.865591196612566e-08, "loss": 0.0038, "step": 17612 }, { "epoch": 0.9726640159045725, "grad_norm": 3.2651679515838623, "learning_rate": 7.833927775461103e-08, "loss": 0.1241, "step": 17613 }, { "epoch": 0.9727192401148663, "grad_norm": 1.990648865699768, "learning_rate": 7.802328089373978e-08, "loss": 0.1229, "step": 17614 }, { "epoch": 0.9727744643251601, "grad_norm": 2.2555091381073, "learning_rate": 7.770792139361716e-08, "loss": 0.1598, "step": 17615 }, { "epoch": 0.9728296885354539, "grad_norm": 0.03414103761315346, "learning_rate": 7.739319926433731e-08, "loss": 0.0005, "step": 17616 }, { "epoch": 0.9728849127457477, "grad_norm": 3.2738149166107178, "learning_rate": 7.707911451596328e-08, "loss": 0.2724, "step": 17617 }, { "epoch": 0.9729401369560415, "grad_norm": 1.8401134014129639, "learning_rate": 7.676566715854928e-08, "loss": 0.0692, "step": 17618 }, { "epoch": 0.9729953611663353, "grad_norm": 0.3103553354740143, "learning_rate": 7.645285720211614e-08, "loss": 0.0083, "step": 17619 }, { "epoch": 0.9730505853766291, "grad_norm": 4.985377788543701, "learning_rate": 7.614068465668034e-08, "loss": 0.4738, "step": 17620 }, { "epoch": 0.9731058095869229, "grad_norm": 0.02596154995262623, "learning_rate": 7.582914953222276e-08, "loss": 0.0006, "step": 17621 }, { "epoch": 0.9731610337972167, "grad_norm": 2.909193515777588, "learning_rate": 7.55182518387132e-08, "loss": 0.3377, "step": 17622 }, { "epoch": 0.9732162580075104, "grad_norm": 2.9676742553710938, "learning_rate": 7.520799158609481e-08, "loss": 0.1817, "step": 17623 }, { "epoch": 0.9732714822178042, "grad_norm": 0.2106252908706665, "learning_rate": 7.489836878429967e-08, "loss": 0.0045, "step": 17624 }, { "epoch": 0.973326706428098, "grad_norm": 0.07308322191238403, "learning_rate": 7.458938344322653e-08, "loss": 0.0021, "step": 17625 }, { "epoch": 0.9733819306383918, "grad_norm": 9.437429428100586, "learning_rate": 7.428103557276522e-08, "loss": 1.4524, "step": 17626 }, { "epoch": 0.9734371548486856, "grad_norm": 2.242063045501709, "learning_rate": 7.397332518278122e-08, "loss": 0.1181, "step": 17627 }, { "epoch": 0.9734923790589795, "grad_norm": 0.07551275193691254, "learning_rate": 7.366625228311553e-08, "loss": 0.0022, "step": 17628 }, { "epoch": 0.9735476032692733, "grad_norm": 2.746586561203003, "learning_rate": 7.335981688359584e-08, "loss": 0.3004, "step": 17629 }, { "epoch": 0.9736028274795671, "grad_norm": 0.35939934849739075, "learning_rate": 7.30540189940232e-08, "loss": 0.0116, "step": 17630 }, { "epoch": 0.9736580516898609, "grad_norm": 0.22162489593029022, "learning_rate": 7.274885862418313e-08, "loss": 0.0064, "step": 17631 }, { "epoch": 0.9737132759001547, "grad_norm": 0.03931131958961487, "learning_rate": 7.244433578383448e-08, "loss": 0.0007, "step": 17632 }, { "epoch": 0.9737685001104485, "grad_norm": 0.0992387905716896, "learning_rate": 7.2140450482725e-08, "loss": 0.0027, "step": 17633 }, { "epoch": 0.9738237243207423, "grad_norm": 0.3090742826461792, "learning_rate": 7.183720273057582e-08, "loss": 0.0063, "step": 17634 }, { "epoch": 0.973878948531036, "grad_norm": 3.0598981380462646, "learning_rate": 7.153459253708583e-08, "loss": 0.0804, "step": 17635 }, { "epoch": 0.9739341727413298, "grad_norm": 0.01856660097837448, "learning_rate": 7.123261991193842e-08, "loss": 0.0006, "step": 17636 }, { "epoch": 0.9739893969516236, "grad_norm": 0.24709483981132507, "learning_rate": 7.093128486479472e-08, "loss": 0.0057, "step": 17637 }, { "epoch": 0.9740446211619174, "grad_norm": 0.19378988444805145, "learning_rate": 7.063058740529149e-08, "loss": 0.007, "step": 17638 }, { "epoch": 0.9740998453722112, "grad_norm": 1.4248287677764893, "learning_rate": 7.033052754305658e-08, "loss": 0.0544, "step": 17639 }, { "epoch": 0.974155069582505, "grad_norm": 0.0642450675368309, "learning_rate": 7.003110528768231e-08, "loss": 0.0016, "step": 17640 }, { "epoch": 0.9742102937927988, "grad_norm": 4.403304576873779, "learning_rate": 6.973232064875213e-08, "loss": 0.5736, "step": 17641 }, { "epoch": 0.9742655180030926, "grad_norm": 0.060679398477077484, "learning_rate": 6.943417363582505e-08, "loss": 0.0018, "step": 17642 }, { "epoch": 0.9743207422133864, "grad_norm": 4.347990989685059, "learning_rate": 6.91366642584379e-08, "loss": 0.9481, "step": 17643 }, { "epoch": 0.9743759664236802, "grad_norm": 4.726245880126953, "learning_rate": 6.883979252610973e-08, "loss": 0.7154, "step": 17644 }, { "epoch": 0.974431190633974, "grad_norm": 4.400907516479492, "learning_rate": 6.854355844833738e-08, "loss": 0.5284, "step": 17645 }, { "epoch": 0.9744864148442677, "grad_norm": 0.18660753965377808, "learning_rate": 6.824796203459772e-08, "loss": 0.0036, "step": 17646 }, { "epoch": 0.9745416390545615, "grad_norm": 0.11601509153842926, "learning_rate": 6.795300329435206e-08, "loss": 0.0037, "step": 17647 }, { "epoch": 0.9745968632648553, "grad_norm": 0.016399279236793518, "learning_rate": 6.765868223703065e-08, "loss": 0.0005, "step": 17648 }, { "epoch": 0.9746520874751491, "grad_norm": 4.577884197235107, "learning_rate": 6.736499887205483e-08, "loss": 0.1393, "step": 17649 }, { "epoch": 0.9747073116854429, "grad_norm": 4.770570755004883, "learning_rate": 6.70719532088171e-08, "loss": 0.4688, "step": 17650 }, { "epoch": 0.9747625358957367, "grad_norm": 2.664630651473999, "learning_rate": 6.677954525669661e-08, "loss": 0.1293, "step": 17651 }, { "epoch": 0.9748177601060305, "grad_norm": 0.19863024353981018, "learning_rate": 6.648777502504366e-08, "loss": 0.0047, "step": 17652 }, { "epoch": 0.9748729843163243, "grad_norm": 0.04139125719666481, "learning_rate": 6.619664252319524e-08, "loss": 0.0013, "step": 17653 }, { "epoch": 0.9749282085266181, "grad_norm": 0.4478338062763214, "learning_rate": 6.590614776046611e-08, "loss": 0.0139, "step": 17654 }, { "epoch": 0.9749834327369119, "grad_norm": 6.821849346160889, "learning_rate": 6.561629074614661e-08, "loss": 2.607, "step": 17655 }, { "epoch": 0.9750386569472057, "grad_norm": 4.2179059982299805, "learning_rate": 6.5327071489516e-08, "loss": 1.0197, "step": 17656 }, { "epoch": 0.9750938811574994, "grad_norm": 4.4587883949279785, "learning_rate": 6.503848999982243e-08, "loss": 0.5433, "step": 17657 }, { "epoch": 0.9751491053677932, "grad_norm": 0.14867016673088074, "learning_rate": 6.475054628629852e-08, "loss": 0.0024, "step": 17658 }, { "epoch": 0.975204329578087, "grad_norm": 1.3269174098968506, "learning_rate": 6.446324035815909e-08, "loss": 0.0184, "step": 17659 }, { "epoch": 0.9752595537883808, "grad_norm": 1.1075375080108643, "learning_rate": 6.417657222459461e-08, "loss": 0.1274, "step": 17660 }, { "epoch": 0.9753147779986746, "grad_norm": 0.18143177032470703, "learning_rate": 6.389054189477772e-08, "loss": 0.0057, "step": 17661 }, { "epoch": 0.9753700022089684, "grad_norm": 5.935561656951904, "learning_rate": 6.360514937785666e-08, "loss": 0.6477, "step": 17662 }, { "epoch": 0.9754252264192622, "grad_norm": 2.619565010070801, "learning_rate": 6.332039468296413e-08, "loss": 0.1066, "step": 17663 }, { "epoch": 0.975480450629556, "grad_norm": 0.8639189004898071, "learning_rate": 6.303627781920618e-08, "loss": 0.0161, "step": 17664 }, { "epoch": 0.9755356748398498, "grad_norm": 0.005534263327717781, "learning_rate": 6.275279879567997e-08, "loss": 0.0002, "step": 17665 }, { "epoch": 0.9755908990501436, "grad_norm": 0.1049836277961731, "learning_rate": 6.246995762144714e-08, "loss": 0.0028, "step": 17666 }, { "epoch": 0.9756461232604374, "grad_norm": 0.011002801358699799, "learning_rate": 6.218775430556267e-08, "loss": 0.0004, "step": 17667 }, { "epoch": 0.9757013474707311, "grad_norm": 0.07862028479576111, "learning_rate": 6.190618885705047e-08, "loss": 0.0019, "step": 17668 }, { "epoch": 0.9757565716810249, "grad_norm": 0.10069822520017624, "learning_rate": 6.162526128492108e-08, "loss": 0.0024, "step": 17669 }, { "epoch": 0.9758117958913187, "grad_norm": 5.023879051208496, "learning_rate": 6.134497159816066e-08, "loss": 0.7498, "step": 17670 }, { "epoch": 0.9758670201016125, "grad_norm": 0.03912702202796936, "learning_rate": 6.106531980573982e-08, "loss": 0.0011, "step": 17671 }, { "epoch": 0.9759222443119063, "grad_norm": 0.02183414436876774, "learning_rate": 6.078630591660251e-08, "loss": 0.0004, "step": 17672 }, { "epoch": 0.9759774685222001, "grad_norm": 0.1030433177947998, "learning_rate": 6.050792993967491e-08, "loss": 0.0014, "step": 17673 }, { "epoch": 0.9760326927324939, "grad_norm": 6.136131763458252, "learning_rate": 6.023019188386326e-08, "loss": 0.8544, "step": 17674 }, { "epoch": 0.9760879169427877, "grad_norm": 0.21140724420547485, "learning_rate": 5.995309175805374e-08, "loss": 0.0048, "step": 17675 }, { "epoch": 0.9761431411530815, "grad_norm": 0.03225236386060715, "learning_rate": 5.967662957111264e-08, "loss": 0.0008, "step": 17676 }, { "epoch": 0.9761983653633753, "grad_norm": 2.339299201965332, "learning_rate": 5.940080533188397e-08, "loss": 0.2999, "step": 17677 }, { "epoch": 0.9762535895736691, "grad_norm": 0.12993843853473663, "learning_rate": 5.912561904918956e-08, "loss": 0.0047, "step": 17678 }, { "epoch": 0.9763088137839628, "grad_norm": 3.207603931427002, "learning_rate": 5.8851070731837933e-08, "loss": 0.4474, "step": 17679 }, { "epoch": 0.9763640379942566, "grad_norm": 5.959377288818359, "learning_rate": 5.857716038861094e-08, "loss": 0.699, "step": 17680 }, { "epoch": 0.9764192622045504, "grad_norm": 2.543612480163574, "learning_rate": 5.8303888028270474e-08, "loss": 0.1405, "step": 17681 }, { "epoch": 0.9764744864148442, "grad_norm": 6.052437782287598, "learning_rate": 5.803125365956064e-08, "loss": 0.1222, "step": 17682 }, { "epoch": 0.976529710625138, "grad_norm": 0.07744281738996506, "learning_rate": 5.775925729120113e-08, "loss": 0.0019, "step": 17683 }, { "epoch": 0.9765849348354319, "grad_norm": 1.689948558807373, "learning_rate": 5.748789893189832e-08, "loss": 0.0673, "step": 17684 }, { "epoch": 0.9766401590457257, "grad_norm": 0.07700218260288239, "learning_rate": 5.721717859032971e-08, "loss": 0.0018, "step": 17685 }, { "epoch": 0.9766953832560195, "grad_norm": 4.355529308319092, "learning_rate": 5.6947096275159485e-08, "loss": 0.7013, "step": 17686 }, { "epoch": 0.9767506074663133, "grad_norm": 1.9378336668014526, "learning_rate": 5.6677651995027395e-08, "loss": 0.0886, "step": 17687 }, { "epoch": 0.9768058316766071, "grad_norm": 1.271297574043274, "learning_rate": 5.640884575855099e-08, "loss": 0.0196, "step": 17688 }, { "epoch": 0.9768610558869009, "grad_norm": 0.42603057622909546, "learning_rate": 5.61406775743345e-08, "loss": 0.0099, "step": 17689 }, { "epoch": 0.9769162800971946, "grad_norm": 0.12715071439743042, "learning_rate": 5.5873147450955514e-08, "loss": 0.0027, "step": 17690 }, { "epoch": 0.9769715043074884, "grad_norm": 0.009902657009661198, "learning_rate": 5.560625539697162e-08, "loss": 0.0002, "step": 17691 }, { "epoch": 0.9770267285177822, "grad_norm": 0.027903029695153236, "learning_rate": 5.5340001420924885e-08, "loss": 0.0004, "step": 17692 }, { "epoch": 0.977081952728076, "grad_norm": 0.08591330051422119, "learning_rate": 5.507438553132849e-08, "loss": 0.0016, "step": 17693 }, { "epoch": 0.9771371769383698, "grad_norm": 3.4042162895202637, "learning_rate": 5.480940773668675e-08, "loss": 0.2124, "step": 17694 }, { "epoch": 0.9771924011486636, "grad_norm": 3.931807279586792, "learning_rate": 5.454506804547066e-08, "loss": 0.5678, "step": 17695 }, { "epoch": 0.9772476253589574, "grad_norm": 3.2758030891418457, "learning_rate": 5.428136646614013e-08, "loss": 0.1491, "step": 17696 }, { "epoch": 0.9773028495692512, "grad_norm": 0.5368672609329224, "learning_rate": 5.4018303007132846e-08, "loss": 0.0106, "step": 17697 }, { "epoch": 0.977358073779545, "grad_norm": 0.8179764151573181, "learning_rate": 5.37558776768643e-08, "loss": 0.0142, "step": 17698 }, { "epoch": 0.9774132979898388, "grad_norm": 0.19177497923374176, "learning_rate": 5.3494090483727776e-08, "loss": 0.0036, "step": 17699 }, { "epoch": 0.9774685222001326, "grad_norm": 3.533008575439453, "learning_rate": 5.323294143610103e-08, "loss": 0.7516, "step": 17700 }, { "epoch": 0.9775237464104264, "grad_norm": 4.1559858322143555, "learning_rate": 5.297243054233958e-08, "loss": 0.9196, "step": 17701 }, { "epoch": 0.9775789706207201, "grad_norm": 3.3128621578216553, "learning_rate": 5.271255781077678e-08, "loss": 0.5507, "step": 17702 }, { "epoch": 0.9776341948310139, "grad_norm": 2.843372106552124, "learning_rate": 5.245332324972374e-08, "loss": 0.0903, "step": 17703 }, { "epoch": 0.9776894190413077, "grad_norm": 0.015556269325315952, "learning_rate": 5.2194726867480505e-08, "loss": 0.0004, "step": 17704 }, { "epoch": 0.9777446432516015, "grad_norm": 0.11258745938539505, "learning_rate": 5.1936768672316006e-08, "loss": 0.003, "step": 17705 }, { "epoch": 0.9777998674618953, "grad_norm": 2.133014678955078, "learning_rate": 5.167944867248364e-08, "loss": 0.5801, "step": 17706 }, { "epoch": 0.9778550916721891, "grad_norm": 1.5498133897781372, "learning_rate": 5.142276687621462e-08, "loss": 0.0627, "step": 17707 }, { "epoch": 0.9779103158824829, "grad_norm": 0.08825792372226715, "learning_rate": 5.1166723291724565e-08, "loss": 0.0014, "step": 17708 }, { "epoch": 0.9779655400927767, "grad_norm": 0.07691659033298492, "learning_rate": 5.091131792720028e-08, "loss": 0.0021, "step": 17709 }, { "epoch": 0.9780207643030705, "grad_norm": 0.09709238260984421, "learning_rate": 5.065655079081744e-08, "loss": 0.0017, "step": 17710 }, { "epoch": 0.9780759885133643, "grad_norm": 4.440876483917236, "learning_rate": 5.0402421890725086e-08, "loss": 0.8282, "step": 17711 }, { "epoch": 0.9781312127236581, "grad_norm": 0.0160092581063509, "learning_rate": 5.014893123505227e-08, "loss": 0.0004, "step": 17712 }, { "epoch": 0.9781864369339518, "grad_norm": 1.2543069124221802, "learning_rate": 4.989607883190806e-08, "loss": 0.0314, "step": 17713 }, { "epoch": 0.9782416611442456, "grad_norm": 7.789258003234863, "learning_rate": 4.964386468938598e-08, "loss": 0.3545, "step": 17714 }, { "epoch": 0.9782968853545394, "grad_norm": 0.019936876371502876, "learning_rate": 4.939228881555291e-08, "loss": 0.0006, "step": 17715 }, { "epoch": 0.9783521095648332, "grad_norm": 0.5973031520843506, "learning_rate": 4.9141351218457975e-08, "loss": 0.0118, "step": 17716 }, { "epoch": 0.978407333775127, "grad_norm": 1.6061124801635742, "learning_rate": 4.8891051906128084e-08, "loss": 0.0857, "step": 17717 }, { "epoch": 0.9784625579854208, "grad_norm": 0.028432825580239296, "learning_rate": 4.864139088657016e-08, "loss": 0.001, "step": 17718 }, { "epoch": 0.9785177821957146, "grad_norm": 1.3024121522903442, "learning_rate": 4.8392368167775593e-08, "loss": 0.029, "step": 17719 }, { "epoch": 0.9785730064060084, "grad_norm": 0.03851500526070595, "learning_rate": 4.81439837577069e-08, "loss": 0.0011, "step": 17720 }, { "epoch": 0.9786282306163022, "grad_norm": 0.0951073095202446, "learning_rate": 4.789623766431328e-08, "loss": 0.0028, "step": 17721 }, { "epoch": 0.978683454826596, "grad_norm": 0.09167973697185516, "learning_rate": 4.764912989552173e-08, "loss": 0.0024, "step": 17722 }, { "epoch": 0.9787386790368898, "grad_norm": 0.021627042442560196, "learning_rate": 4.740266045923481e-08, "loss": 0.0004, "step": 17723 }, { "epoch": 0.9787939032471835, "grad_norm": 2.11533784866333, "learning_rate": 4.715682936333954e-08, "loss": 0.0448, "step": 17724 }, { "epoch": 0.9788491274574773, "grad_norm": 1.8694710731506348, "learning_rate": 4.691163661569853e-08, "loss": 0.0718, "step": 17725 }, { "epoch": 0.9789043516677711, "grad_norm": 0.016058698296546936, "learning_rate": 4.666708222416105e-08, "loss": 0.0004, "step": 17726 }, { "epoch": 0.9789595758780649, "grad_norm": 0.02163838967680931, "learning_rate": 4.642316619654752e-08, "loss": 0.0006, "step": 17727 }, { "epoch": 0.9790148000883587, "grad_norm": 3.423515796661377, "learning_rate": 4.6179888540662796e-08, "loss": 0.378, "step": 17728 }, { "epoch": 0.9790700242986525, "grad_norm": 5.3231706619262695, "learning_rate": 4.593724926428733e-08, "loss": 0.8545, "step": 17729 }, { "epoch": 0.9791252485089463, "grad_norm": 3.5833117961883545, "learning_rate": 4.569524837518602e-08, "loss": 0.5845, "step": 17730 }, { "epoch": 0.9791804727192401, "grad_norm": 2.593008041381836, "learning_rate": 4.545388588110377e-08, "loss": 0.1852, "step": 17731 }, { "epoch": 0.9792356969295339, "grad_norm": 0.21750302612781525, "learning_rate": 4.521316178975887e-08, "loss": 0.0018, "step": 17732 }, { "epoch": 0.9792909211398277, "grad_norm": 0.09109465032815933, "learning_rate": 4.497307610885182e-08, "loss": 0.0024, "step": 17733 }, { "epoch": 0.9793461453501215, "grad_norm": 0.3796170949935913, "learning_rate": 4.473362884606758e-08, "loss": 0.0086, "step": 17734 }, { "epoch": 0.9794013695604152, "grad_norm": 0.06008677929639816, "learning_rate": 4.4494820009062245e-08, "loss": 0.0013, "step": 17735 }, { "epoch": 0.979456593770709, "grad_norm": 3.7578108310699463, "learning_rate": 4.425664960548082e-08, "loss": 0.519, "step": 17736 }, { "epoch": 0.9795118179810028, "grad_norm": 2.0573079586029053, "learning_rate": 4.4019117642939425e-08, "loss": 0.1251, "step": 17737 }, { "epoch": 0.9795670421912966, "grad_norm": 0.13595974445343018, "learning_rate": 4.378222412904087e-08, "loss": 0.0025, "step": 17738 }, { "epoch": 0.9796222664015904, "grad_norm": 0.09899088740348816, "learning_rate": 4.354596907135911e-08, "loss": 0.0027, "step": 17739 }, { "epoch": 0.9796774906118842, "grad_norm": 3.7895658016204834, "learning_rate": 4.331035247745696e-08, "loss": 0.3811, "step": 17740 }, { "epoch": 0.979732714822178, "grad_norm": 0.9039182662963867, "learning_rate": 4.307537435486842e-08, "loss": 0.0291, "step": 17741 }, { "epoch": 0.9797879390324719, "grad_norm": 2.469468593597412, "learning_rate": 4.284103471111634e-08, "loss": 0.4254, "step": 17742 }, { "epoch": 0.9798431632427657, "grad_norm": 2.017620801925659, "learning_rate": 4.260733355369251e-08, "loss": 0.081, "step": 17743 }, { "epoch": 0.9798983874530595, "grad_norm": 1.583922028541565, "learning_rate": 4.237427089007762e-08, "loss": 0.0733, "step": 17744 }, { "epoch": 0.9799536116633533, "grad_norm": 3.472104549407959, "learning_rate": 4.214184672772792e-08, "loss": 0.3321, "step": 17745 }, { "epoch": 0.980008835873647, "grad_norm": 2.8928565979003906, "learning_rate": 4.191006107407525e-08, "loss": 0.5399, "step": 17746 }, { "epoch": 0.9800640600839408, "grad_norm": 5.882924556732178, "learning_rate": 4.1678913936540336e-08, "loss": 0.3902, "step": 17747 }, { "epoch": 0.9801192842942346, "grad_norm": 2.0326883792877197, "learning_rate": 4.144840532251504e-08, "loss": 0.2578, "step": 17748 }, { "epoch": 0.9801745085045284, "grad_norm": 3.8161087036132812, "learning_rate": 4.121853523937347e-08, "loss": 0.3998, "step": 17749 }, { "epoch": 0.9802297327148222, "grad_norm": 3.5798614025115967, "learning_rate": 4.098930369447418e-08, "loss": 1.2283, "step": 17750 }, { "epoch": 0.980284956925116, "grad_norm": 0.06401244550943375, "learning_rate": 4.0760710695144644e-08, "loss": 0.0016, "step": 17751 }, { "epoch": 0.9803401811354098, "grad_norm": 2.9232237339019775, "learning_rate": 4.0532756248703456e-08, "loss": 0.2657, "step": 17752 }, { "epoch": 0.9803954053457036, "grad_norm": 0.5344045758247375, "learning_rate": 4.0305440362440326e-08, "loss": 0.0152, "step": 17753 }, { "epoch": 0.9804506295559974, "grad_norm": 5.494823932647705, "learning_rate": 4.0078763043629454e-08, "loss": 0.5942, "step": 17754 }, { "epoch": 0.9805058537662912, "grad_norm": 0.2321363091468811, "learning_rate": 3.985272429952058e-08, "loss": 0.0057, "step": 17755 }, { "epoch": 0.980561077976585, "grad_norm": 4.131449222564697, "learning_rate": 3.962732413734793e-08, "loss": 0.1672, "step": 17756 }, { "epoch": 0.9806163021868787, "grad_norm": 0.15573570132255554, "learning_rate": 3.940256256432351e-08, "loss": 0.0037, "step": 17757 }, { "epoch": 0.9806715263971725, "grad_norm": 1.617053508758545, "learning_rate": 3.91784395876349e-08, "loss": 0.0778, "step": 17758 }, { "epoch": 0.9807267506074663, "grad_norm": 1.199574589729309, "learning_rate": 3.895495521445414e-08, "loss": 0.062, "step": 17759 }, { "epoch": 0.9807819748177601, "grad_norm": 0.011890835128724575, "learning_rate": 3.873210945193329e-08, "loss": 0.0003, "step": 17760 }, { "epoch": 0.9808371990280539, "grad_norm": 0.02711465395987034, "learning_rate": 3.850990230719554e-08, "loss": 0.0008, "step": 17761 }, { "epoch": 0.9808924232383477, "grad_norm": 0.03475768864154816, "learning_rate": 3.828833378735519e-08, "loss": 0.0007, "step": 17762 }, { "epoch": 0.9809476474486415, "grad_norm": 0.3605561852455139, "learning_rate": 3.8067403899502144e-08, "loss": 0.0088, "step": 17763 }, { "epoch": 0.9810028716589353, "grad_norm": 0.5048273205757141, "learning_rate": 3.784711265069963e-08, "loss": 0.1092, "step": 17764 }, { "epoch": 0.9810580958692291, "grad_norm": 3.1501641273498535, "learning_rate": 3.7627460047997556e-08, "loss": 0.4994, "step": 17765 }, { "epoch": 0.9811133200795229, "grad_norm": 0.49504369497299194, "learning_rate": 3.7408446098423643e-08, "loss": 0.0097, "step": 17766 }, { "epoch": 0.9811685442898167, "grad_norm": 0.3300568163394928, "learning_rate": 3.71900708089834e-08, "loss": 0.0074, "step": 17767 }, { "epoch": 0.9812237685001104, "grad_norm": 0.13522979617118835, "learning_rate": 3.6972334186666794e-08, "loss": 0.0036, "step": 17768 }, { "epoch": 0.9812789927104042, "grad_norm": 2.1544289588928223, "learning_rate": 3.675523623843491e-08, "loss": 0.1368, "step": 17769 }, { "epoch": 0.981334216920698, "grad_norm": 0.31291449069976807, "learning_rate": 3.653877697123776e-08, "loss": 0.0068, "step": 17770 }, { "epoch": 0.9813894411309918, "grad_norm": 0.40717214345932007, "learning_rate": 3.6322956391998675e-08, "loss": 0.0103, "step": 17771 }, { "epoch": 0.9814446653412856, "grad_norm": 6.221249580383301, "learning_rate": 3.610777450762104e-08, "loss": 1.0061, "step": 17772 }, { "epoch": 0.9814998895515794, "grad_norm": 2.2729828357696533, "learning_rate": 3.5893231324990455e-08, "loss": 0.0587, "step": 17773 }, { "epoch": 0.9815551137618732, "grad_norm": 1.106932282447815, "learning_rate": 3.567932685097253e-08, "loss": 0.0321, "step": 17774 }, { "epoch": 0.981610337972167, "grad_norm": 0.33462435007095337, "learning_rate": 3.546606109240624e-08, "loss": 0.0067, "step": 17775 }, { "epoch": 0.9816655621824608, "grad_norm": 3.0718014240264893, "learning_rate": 3.525343405611947e-08, "loss": 0.5255, "step": 17776 }, { "epoch": 0.9817207863927546, "grad_norm": 0.03367968648672104, "learning_rate": 3.504144574891122e-08, "loss": 0.0012, "step": 17777 }, { "epoch": 0.9817760106030484, "grad_norm": 2.0881478786468506, "learning_rate": 3.4830096177564945e-08, "loss": 0.0727, "step": 17778 }, { "epoch": 0.9818312348133422, "grad_norm": 4.689620494842529, "learning_rate": 3.4619385348841904e-08, "loss": 0.6169, "step": 17779 }, { "epoch": 0.9818864590236359, "grad_norm": 3.5398552417755127, "learning_rate": 3.440931326948338e-08, "loss": 0.3658, "step": 17780 }, { "epoch": 0.9819416832339297, "grad_norm": 0.05626706779003143, "learning_rate": 3.4199879946212875e-08, "loss": 0.0012, "step": 17781 }, { "epoch": 0.9819969074442235, "grad_norm": 0.04635333642363548, "learning_rate": 3.399108538572504e-08, "loss": 0.0014, "step": 17782 }, { "epoch": 0.9820521316545173, "grad_norm": 0.059680867940187454, "learning_rate": 3.3782929594705637e-08, "loss": 0.0019, "step": 17783 }, { "epoch": 0.9821073558648111, "grad_norm": 0.1997106820344925, "learning_rate": 3.357541257980934e-08, "loss": 0.0047, "step": 17784 }, { "epoch": 0.9821625800751049, "grad_norm": 2.495863437652588, "learning_rate": 3.3368534347679724e-08, "loss": 0.2724, "step": 17785 }, { "epoch": 0.9822178042853987, "grad_norm": 0.1521483063697815, "learning_rate": 3.3162294904931504e-08, "loss": 0.0029, "step": 17786 }, { "epoch": 0.9822730284956925, "grad_norm": 0.022099940106272697, "learning_rate": 3.295669425816606e-08, "loss": 0.0005, "step": 17787 }, { "epoch": 0.9823282527059863, "grad_norm": 2.364579916000366, "learning_rate": 3.2751732413958125e-08, "loss": 0.1804, "step": 17788 }, { "epoch": 0.9823834769162801, "grad_norm": 4.748025417327881, "learning_rate": 3.2547409378866913e-08, "loss": 0.7591, "step": 17789 }, { "epoch": 0.9824387011265739, "grad_norm": 0.007121444679796696, "learning_rate": 3.2343725159429405e-08, "loss": 0.0002, "step": 17790 }, { "epoch": 0.9824939253368676, "grad_norm": 0.005460721906274557, "learning_rate": 3.21406797621604e-08, "loss": 0.0001, "step": 17791 }, { "epoch": 0.9825491495471614, "grad_norm": 0.44266095757484436, "learning_rate": 3.1938273193559134e-08, "loss": 0.011, "step": 17792 }, { "epoch": 0.9826043737574552, "grad_norm": 0.053223609924316406, "learning_rate": 3.173650546009821e-08, "loss": 0.0017, "step": 17793 }, { "epoch": 0.982659597967749, "grad_norm": 0.22775310277938843, "learning_rate": 3.153537656823247e-08, "loss": 0.0062, "step": 17794 }, { "epoch": 0.9827148221780428, "grad_norm": 1.7547245025634766, "learning_rate": 3.133488652439898e-08, "loss": 0.0923, "step": 17795 }, { "epoch": 0.9827700463883366, "grad_norm": 2.706444025039673, "learning_rate": 3.1135035335010387e-08, "loss": 0.165, "step": 17796 }, { "epoch": 0.9828252705986305, "grad_norm": 0.7494860887527466, "learning_rate": 3.093582300645937e-08, "loss": 0.0118, "step": 17797 }, { "epoch": 0.9828804948089243, "grad_norm": 0.03358914703130722, "learning_rate": 3.0737249545123024e-08, "loss": 0.0009, "step": 17798 }, { "epoch": 0.9829357190192181, "grad_norm": 0.014164411462843418, "learning_rate": 3.053931495735185e-08, "loss": 0.0004, "step": 17799 }, { "epoch": 0.9829909432295119, "grad_norm": 0.08814410120248795, "learning_rate": 3.034201924947633e-08, "loss": 0.0024, "step": 17800 }, { "epoch": 0.9830461674398057, "grad_norm": 3.2360949516296387, "learning_rate": 3.0145362427811406e-08, "loss": 0.6791, "step": 17801 }, { "epoch": 0.9831013916500994, "grad_norm": 1.3479173183441162, "learning_rate": 2.9949344498649834e-08, "loss": 0.0261, "step": 17802 }, { "epoch": 0.9831566158603932, "grad_norm": 6.621438980102539, "learning_rate": 2.9753965468259925e-08, "loss": 1.079, "step": 17803 }, { "epoch": 0.983211840070687, "grad_norm": 3.577772378921509, "learning_rate": 2.955922534289224e-08, "loss": 0.7562, "step": 17804 }, { "epoch": 0.9832670642809808, "grad_norm": 0.09350363165140152, "learning_rate": 2.9365124128779566e-08, "loss": 0.0016, "step": 17805 }, { "epoch": 0.9833222884912746, "grad_norm": 0.03881809487938881, "learning_rate": 2.9171661832130272e-08, "loss": 0.0012, "step": 17806 }, { "epoch": 0.9833775127015684, "grad_norm": 3.0578699111938477, "learning_rate": 2.8978838459134962e-08, "loss": 0.435, "step": 17807 }, { "epoch": 0.9834327369118622, "grad_norm": 0.2544875741004944, "learning_rate": 2.8786654015959815e-08, "loss": 0.0086, "step": 17808 }, { "epoch": 0.983487961122156, "grad_norm": 0.09399494528770447, "learning_rate": 2.8595108508755464e-08, "loss": 0.0021, "step": 17809 }, { "epoch": 0.9835431853324498, "grad_norm": 0.27543553709983826, "learning_rate": 2.8404201943650345e-08, "loss": 0.0037, "step": 17810 }, { "epoch": 0.9835984095427436, "grad_norm": 3.6513638496398926, "learning_rate": 2.821393432675068e-08, "loss": 0.2684, "step": 17811 }, { "epoch": 0.9836536337530374, "grad_norm": 4.787515163421631, "learning_rate": 2.8024305664144936e-08, "loss": 0.6976, "step": 17812 }, { "epoch": 0.9837088579633311, "grad_norm": 0.15534624457359314, "learning_rate": 2.783531596189937e-08, "loss": 0.0037, "step": 17813 }, { "epoch": 0.9837640821736249, "grad_norm": 0.056054286658763885, "learning_rate": 2.764696522606025e-08, "loss": 0.0015, "step": 17814 }, { "epoch": 0.9838193063839187, "grad_norm": 2.6277949810028076, "learning_rate": 2.7459253462653878e-08, "loss": 0.433, "step": 17815 }, { "epoch": 0.9838745305942125, "grad_norm": 0.10615336894989014, "learning_rate": 2.7272180677684335e-08, "loss": 0.0034, "step": 17816 }, { "epoch": 0.9839297548045063, "grad_norm": 0.694102942943573, "learning_rate": 2.708574687713794e-08, "loss": 0.0209, "step": 17817 }, { "epoch": 0.9839849790148001, "grad_norm": 1.051835060119629, "learning_rate": 2.689995206697882e-08, "loss": 0.1396, "step": 17818 }, { "epoch": 0.9840402032250939, "grad_norm": 3.3810269832611084, "learning_rate": 2.6714796253151098e-08, "loss": 0.1798, "step": 17819 }, { "epoch": 0.9840954274353877, "grad_norm": 1.4395008087158203, "learning_rate": 2.653027944157893e-08, "loss": 0.0647, "step": 17820 }, { "epoch": 0.9841506516456815, "grad_norm": 2.6479651927948, "learning_rate": 2.6346401638164266e-08, "loss": 0.1845, "step": 17821 }, { "epoch": 0.9842058758559753, "grad_norm": 3.0171353816986084, "learning_rate": 2.6163162848791278e-08, "loss": 0.5801, "step": 17822 }, { "epoch": 0.9842611000662691, "grad_norm": 1.3339364528656006, "learning_rate": 2.598056307932195e-08, "loss": 0.0416, "step": 17823 }, { "epoch": 0.9843163242765628, "grad_norm": 0.022808555513620377, "learning_rate": 2.5798602335598276e-08, "loss": 0.0005, "step": 17824 }, { "epoch": 0.9843715484868566, "grad_norm": 0.3995191752910614, "learning_rate": 2.5617280623440042e-08, "loss": 0.0129, "step": 17825 }, { "epoch": 0.9844267726971504, "grad_norm": 0.0285198874771595, "learning_rate": 2.543659794864928e-08, "loss": 0.0009, "step": 17826 }, { "epoch": 0.9844819969074442, "grad_norm": 0.11891543120145798, "learning_rate": 2.525655431700802e-08, "loss": 0.004, "step": 17827 }, { "epoch": 0.984537221117738, "grad_norm": 0.7856960296630859, "learning_rate": 2.5077149734276108e-08, "loss": 0.0113, "step": 17828 }, { "epoch": 0.9845924453280318, "grad_norm": 0.8229139447212219, "learning_rate": 2.489838420619117e-08, "loss": 0.0233, "step": 17829 }, { "epoch": 0.9846476695383256, "grad_norm": 0.03411717712879181, "learning_rate": 2.4720257738473087e-08, "loss": 0.0006, "step": 17830 }, { "epoch": 0.9847028937486194, "grad_norm": 0.08202801644802094, "learning_rate": 2.454277033682173e-08, "loss": 0.0018, "step": 17831 }, { "epoch": 0.9847581179589132, "grad_norm": 6.509383678436279, "learning_rate": 2.436592200691257e-08, "loss": 1.1049, "step": 17832 }, { "epoch": 0.984813342169207, "grad_norm": 0.044221438467502594, "learning_rate": 2.4189712754407735e-08, "loss": 0.0012, "step": 17833 }, { "epoch": 0.9848685663795008, "grad_norm": 1.9429506063461304, "learning_rate": 2.4014142584942724e-08, "loss": 0.1419, "step": 17834 }, { "epoch": 0.9849237905897945, "grad_norm": 2.423466205596924, "learning_rate": 2.3839211504133043e-08, "loss": 0.1525, "step": 17835 }, { "epoch": 0.9849790148000883, "grad_norm": 3.353259801864624, "learning_rate": 2.3664919517578656e-08, "loss": 0.319, "step": 17836 }, { "epoch": 0.9850342390103821, "grad_norm": 0.013615496456623077, "learning_rate": 2.349126663085066e-08, "loss": 0.0003, "step": 17837 }, { "epoch": 0.9850894632206759, "grad_norm": 4.0833048820495605, "learning_rate": 2.331825284951128e-08, "loss": 0.5381, "step": 17838 }, { "epoch": 0.9851446874309697, "grad_norm": 0.08369755744934082, "learning_rate": 2.3145878179089422e-08, "loss": 0.002, "step": 17839 }, { "epoch": 0.9851999116412635, "grad_norm": 4.129953384399414, "learning_rate": 2.297414262510289e-08, "loss": 0.8899, "step": 17840 }, { "epoch": 0.9852551358515573, "grad_norm": 2.705759048461914, "learning_rate": 2.2803046193047296e-08, "loss": 0.6478, "step": 17841 }, { "epoch": 0.9853103600618511, "grad_norm": 0.10105801373720169, "learning_rate": 2.2632588888393813e-08, "loss": 0.0023, "step": 17842 }, { "epoch": 0.9853655842721449, "grad_norm": 0.05577114596962929, "learning_rate": 2.2462770716595862e-08, "loss": 0.0022, "step": 17843 }, { "epoch": 0.9854208084824387, "grad_norm": 1.2555826902389526, "learning_rate": 2.2293591683089088e-08, "loss": 0.1759, "step": 17844 }, { "epoch": 0.9854760326927325, "grad_norm": 0.10107619315385818, "learning_rate": 2.2125051793282504e-08, "loss": 0.0032, "step": 17845 }, { "epoch": 0.9855312569030262, "grad_norm": 5.556631088256836, "learning_rate": 2.195715105256957e-08, "loss": 1.0532, "step": 17846 }, { "epoch": 0.98558648111332, "grad_norm": 1.334886074066162, "learning_rate": 2.1789889466323765e-08, "loss": 0.3537, "step": 17847 }, { "epoch": 0.9856417053236138, "grad_norm": 1.542760968208313, "learning_rate": 2.1623267039896367e-08, "loss": 0.012, "step": 17848 }, { "epoch": 0.9856969295339076, "grad_norm": 0.0063533172942698, "learning_rate": 2.1457283778614224e-08, "loss": 0.0002, "step": 17849 }, { "epoch": 0.9857521537442014, "grad_norm": 0.2454349249601364, "learning_rate": 2.1291939687790862e-08, "loss": 0.0088, "step": 17850 }, { "epoch": 0.9858073779544952, "grad_norm": 0.6942640542984009, "learning_rate": 2.1127234772715388e-08, "loss": 0.0213, "step": 17851 }, { "epoch": 0.985862602164789, "grad_norm": 0.05644502863287926, "learning_rate": 2.0963169038654697e-08, "loss": 0.0012, "step": 17852 }, { "epoch": 0.9859178263750829, "grad_norm": 0.04689765349030495, "learning_rate": 2.0799742490862364e-08, "loss": 0.0012, "step": 17853 }, { "epoch": 0.9859730505853767, "grad_norm": 0.16325907409191132, "learning_rate": 2.063695513456532e-08, "loss": 0.0043, "step": 17854 }, { "epoch": 0.9860282747956705, "grad_norm": 0.03600549325346947, "learning_rate": 2.0474806974968285e-08, "loss": 0.0011, "step": 17855 }, { "epoch": 0.9860834990059643, "grad_norm": 0.028589410707354546, "learning_rate": 2.0313298017262674e-08, "loss": 0.001, "step": 17856 }, { "epoch": 0.9861387232162581, "grad_norm": 0.018192937597632408, "learning_rate": 2.0152428266615454e-08, "loss": 0.0005, "step": 17857 }, { "epoch": 0.9861939474265518, "grad_norm": 2.0964999198913574, "learning_rate": 1.9992197728169182e-08, "loss": 0.2201, "step": 17858 }, { "epoch": 0.9862491716368456, "grad_norm": 0.1785217970609665, "learning_rate": 1.983260640705531e-08, "loss": 0.0036, "step": 17859 }, { "epoch": 0.9863043958471394, "grad_norm": 0.13582561910152435, "learning_rate": 1.9673654308378643e-08, "loss": 0.0034, "step": 17860 }, { "epoch": 0.9863596200574332, "grad_norm": 0.2613413631916046, "learning_rate": 1.951534143721956e-08, "loss": 0.0092, "step": 17861 }, { "epoch": 0.986414844267727, "grad_norm": 0.05490336939692497, "learning_rate": 1.935766779864956e-08, "loss": 0.0012, "step": 17862 }, { "epoch": 0.9864700684780208, "grad_norm": 3.1230993270874023, "learning_rate": 1.9200633397709057e-08, "loss": 0.1139, "step": 17863 }, { "epoch": 0.9865252926883146, "grad_norm": 2.9274091720581055, "learning_rate": 1.904423823942292e-08, "loss": 0.4561, "step": 17864 }, { "epoch": 0.9865805168986084, "grad_norm": 0.051752250641584396, "learning_rate": 1.8888482328796033e-08, "loss": 0.0017, "step": 17865 }, { "epoch": 0.9866357411089022, "grad_norm": 6.538938045501709, "learning_rate": 1.8733365670808858e-08, "loss": 1.9841, "step": 17866 }, { "epoch": 0.986690965319196, "grad_norm": 0.13145136833190918, "learning_rate": 1.857888827042631e-08, "loss": 0.0032, "step": 17867 }, { "epoch": 0.9867461895294898, "grad_norm": 0.4963688254356384, "learning_rate": 1.8425050132588884e-08, "loss": 0.0115, "step": 17868 }, { "epoch": 0.9868014137397835, "grad_norm": 0.009718487970530987, "learning_rate": 1.827185126221931e-08, "loss": 0.0003, "step": 17869 }, { "epoch": 0.9868566379500773, "grad_norm": 0.19456236064434052, "learning_rate": 1.811929166422033e-08, "loss": 0.0047, "step": 17870 }, { "epoch": 0.9869118621603711, "grad_norm": 0.02796385996043682, "learning_rate": 1.7967371343468042e-08, "loss": 0.0008, "step": 17871 }, { "epoch": 0.9869670863706649, "grad_norm": 0.05906869098544121, "learning_rate": 1.781609030482745e-08, "loss": 0.0011, "step": 17872 }, { "epoch": 0.9870223105809587, "grad_norm": 0.45411190390586853, "learning_rate": 1.76654485531369e-08, "loss": 0.0124, "step": 17873 }, { "epoch": 0.9870775347912525, "grad_norm": 0.0297820046544075, "learning_rate": 1.751544609321698e-08, "loss": 0.0007, "step": 17874 }, { "epoch": 0.9871327590015463, "grad_norm": 0.15809515118598938, "learning_rate": 1.736608292986386e-08, "loss": 0.0053, "step": 17875 }, { "epoch": 0.9871879832118401, "grad_norm": 6.060820579528809, "learning_rate": 1.7217359067858152e-08, "loss": 0.0806, "step": 17876 }, { "epoch": 0.9872432074221339, "grad_norm": 3.221311092376709, "learning_rate": 1.7069274511958277e-08, "loss": 0.212, "step": 17877 }, { "epoch": 0.9872984316324277, "grad_norm": 0.015199054963886738, "learning_rate": 1.6921829266900448e-08, "loss": 0.0003, "step": 17878 }, { "epoch": 0.9873536558427215, "grad_norm": 1.5218720436096191, "learning_rate": 1.6775023337403108e-08, "loss": 0.1497, "step": 17879 }, { "epoch": 0.9874088800530152, "grad_norm": 0.185544952750206, "learning_rate": 1.66288567281625e-08, "loss": 0.0044, "step": 17880 }, { "epoch": 0.987464104263309, "grad_norm": 0.23492743074893951, "learning_rate": 1.648332944385489e-08, "loss": 0.0062, "step": 17881 }, { "epoch": 0.9875193284736028, "grad_norm": 0.2680605947971344, "learning_rate": 1.6338441489136548e-08, "loss": 0.0084, "step": 17882 }, { "epoch": 0.9875745526838966, "grad_norm": 0.0075384387746453285, "learning_rate": 1.6194192868641546e-08, "loss": 0.0002, "step": 17883 }, { "epoch": 0.9876297768941904, "grad_norm": 0.13804368674755096, "learning_rate": 1.605058358698619e-08, "loss": 0.003, "step": 17884 }, { "epoch": 0.9876850011044842, "grad_norm": 3.446207284927368, "learning_rate": 1.5907613648764585e-08, "loss": 0.2532, "step": 17885 }, { "epoch": 0.987740225314778, "grad_norm": 3.14894700050354, "learning_rate": 1.576528305855085e-08, "loss": 0.3914, "step": 17886 }, { "epoch": 0.9877954495250718, "grad_norm": 0.4606878459453583, "learning_rate": 1.56235918208969e-08, "loss": 0.0117, "step": 17887 }, { "epoch": 0.9878506737353656, "grad_norm": 0.25058889389038086, "learning_rate": 1.548253994033688e-08, "loss": 0.007, "step": 17888 }, { "epoch": 0.9879058979456594, "grad_norm": 0.4581136703491211, "learning_rate": 1.5342127421384968e-08, "loss": 0.0061, "step": 17889 }, { "epoch": 0.9879611221559532, "grad_norm": 0.12791956961154938, "learning_rate": 1.5202354268533115e-08, "loss": 0.0042, "step": 17890 }, { "epoch": 0.9880163463662469, "grad_norm": 2.3337209224700928, "learning_rate": 1.5063220486251083e-08, "loss": 0.1849, "step": 17891 }, { "epoch": 0.9880715705765407, "grad_norm": 2.5739080905914307, "learning_rate": 1.492472607899087e-08, "loss": 0.4239, "step": 17892 }, { "epoch": 0.9881267947868345, "grad_norm": 4.333490371704102, "learning_rate": 1.4786871051184481e-08, "loss": 0.9302, "step": 17893 }, { "epoch": 0.9881820189971283, "grad_norm": 2.256422281265259, "learning_rate": 1.4649655407241725e-08, "loss": 0.3976, "step": 17894 }, { "epoch": 0.9882372432074221, "grad_norm": 2.523073673248291, "learning_rate": 1.4513079151552423e-08, "loss": 0.1501, "step": 17895 }, { "epoch": 0.9882924674177159, "grad_norm": 5.282288074493408, "learning_rate": 1.4377142288484191e-08, "loss": 1.0636, "step": 17896 }, { "epoch": 0.9883476916280097, "grad_norm": 0.9534844756126404, "learning_rate": 1.4241844822389105e-08, "loss": 0.1165, "step": 17897 }, { "epoch": 0.9884029158383035, "grad_norm": 0.3149679899215698, "learning_rate": 1.4107186757592594e-08, "loss": 0.0103, "step": 17898 }, { "epoch": 0.9884581400485973, "grad_norm": 5.480820178985596, "learning_rate": 1.3973168098406764e-08, "loss": 0.1912, "step": 17899 }, { "epoch": 0.9885133642588911, "grad_norm": 3.4374427795410156, "learning_rate": 1.3839788849114855e-08, "loss": 0.4565, "step": 17900 }, { "epoch": 0.9885685884691849, "grad_norm": 0.06399533152580261, "learning_rate": 1.3707049013989005e-08, "loss": 0.0012, "step": 17901 }, { "epoch": 0.9886238126794786, "grad_norm": 0.1847575604915619, "learning_rate": 1.3574948597270265e-08, "loss": 0.004, "step": 17902 }, { "epoch": 0.9886790368897724, "grad_norm": 2.300931453704834, "learning_rate": 1.3443487603188588e-08, "loss": 0.0579, "step": 17903 }, { "epoch": 0.9887342611000662, "grad_norm": 5.324090480804443, "learning_rate": 1.3312666035949495e-08, "loss": 1.1731, "step": 17904 }, { "epoch": 0.98878948531036, "grad_norm": 13.852096557617188, "learning_rate": 1.3182483899738529e-08, "loss": 0.3833, "step": 17905 }, { "epoch": 0.9888447095206538, "grad_norm": 2.3806710243225098, "learning_rate": 1.3052941198719027e-08, "loss": 0.077, "step": 17906 }, { "epoch": 0.9888999337309476, "grad_norm": 2.2795004844665527, "learning_rate": 1.292403793703656e-08, "loss": 0.0654, "step": 17907 }, { "epoch": 0.9889551579412414, "grad_norm": 0.1380952149629593, "learning_rate": 1.2795774118812276e-08, "loss": 0.0031, "step": 17908 }, { "epoch": 0.9890103821515353, "grad_norm": 0.053799960762262344, "learning_rate": 1.2668149748156221e-08, "loss": 0.0014, "step": 17909 }, { "epoch": 0.989065606361829, "grad_norm": 2.5080649852752686, "learning_rate": 1.2541164829145136e-08, "loss": 0.1493, "step": 17910 }, { "epoch": 0.9891208305721229, "grad_norm": 1.714913010597229, "learning_rate": 1.2414819365844655e-08, "loss": 0.3922, "step": 17911 }, { "epoch": 0.9891760547824167, "grad_norm": 0.7715604305267334, "learning_rate": 1.228911336229599e-08, "loss": 0.1219, "step": 17912 }, { "epoch": 0.9892312789927104, "grad_norm": 0.2673082947731018, "learning_rate": 1.216404682252037e-08, "loss": 0.0081, "step": 17913 }, { "epoch": 0.9892865032030042, "grad_norm": 1.97005033493042, "learning_rate": 1.2039619750519039e-08, "loss": 0.0248, "step": 17914 }, { "epoch": 0.989341727413298, "grad_norm": 0.03102165460586548, "learning_rate": 1.1915832150275475e-08, "loss": 0.0011, "step": 17915 }, { "epoch": 0.9893969516235918, "grad_norm": 0.013384119607508183, "learning_rate": 1.1792684025748735e-08, "loss": 0.0003, "step": 17916 }, { "epoch": 0.9894521758338856, "grad_norm": 2.9098143577575684, "learning_rate": 1.167017538087567e-08, "loss": 0.2155, "step": 17917 }, { "epoch": 0.9895074000441794, "grad_norm": 3.3088865280151367, "learning_rate": 1.1548306219579809e-08, "loss": 0.2144, "step": 17918 }, { "epoch": 0.9895626242544732, "grad_norm": 0.15536153316497803, "learning_rate": 1.1427076545755811e-08, "loss": 0.0037, "step": 17919 }, { "epoch": 0.989617848464767, "grad_norm": 2.237396240234375, "learning_rate": 1.130648636328724e-08, "loss": 0.1, "step": 17920 }, { "epoch": 0.9896730726750608, "grad_norm": 0.020888792350888252, "learning_rate": 1.1186535676026566e-08, "loss": 0.0006, "step": 17921 }, { "epoch": 0.9897282968853546, "grad_norm": 0.23558922111988068, "learning_rate": 1.1067224487817384e-08, "loss": 0.0058, "step": 17922 }, { "epoch": 0.9897835210956484, "grad_norm": 3.3101890087127686, "learning_rate": 1.09485528024722e-08, "loss": 0.546, "step": 17923 }, { "epoch": 0.9898387453059422, "grad_norm": 0.03723742812871933, "learning_rate": 1.0830520623787976e-08, "loss": 0.0007, "step": 17924 }, { "epoch": 0.9898939695162359, "grad_norm": 0.26569369435310364, "learning_rate": 1.0713127955543912e-08, "loss": 0.007, "step": 17925 }, { "epoch": 0.9899491937265297, "grad_norm": 1.6071833372116089, "learning_rate": 1.059637480149256e-08, "loss": 0.0724, "step": 17926 }, { "epoch": 0.9900044179368235, "grad_norm": 6.232741832733154, "learning_rate": 1.0480261165370931e-08, "loss": 1.1565, "step": 17927 }, { "epoch": 0.9900596421471173, "grad_norm": 2.8573198318481445, "learning_rate": 1.0364787050893833e-08, "loss": 0.5431, "step": 17928 }, { "epoch": 0.9901148663574111, "grad_norm": 0.03247200325131416, "learning_rate": 1.0249952461756086e-08, "loss": 0.0011, "step": 17929 }, { "epoch": 0.9901700905677049, "grad_norm": 0.029777152463793755, "learning_rate": 1.0135757401628088e-08, "loss": 0.0009, "step": 17930 }, { "epoch": 0.9902253147779987, "grad_norm": 1.2282896041870117, "learning_rate": 1.0022201874166915e-08, "loss": 0.0376, "step": 17931 }, { "epoch": 0.9902805389882925, "grad_norm": 2.4749388694763184, "learning_rate": 9.909285883005215e-09, "loss": 0.1026, "step": 17932 }, { "epoch": 0.9903357631985863, "grad_norm": 1.621264100074768, "learning_rate": 9.797009431753435e-09, "loss": 0.0962, "step": 17933 }, { "epoch": 0.9903909874088801, "grad_norm": 3.9248318672180176, "learning_rate": 9.685372524006475e-09, "loss": 0.5583, "step": 17934 }, { "epoch": 0.9904462116191739, "grad_norm": 0.1812363564968109, "learning_rate": 9.574375163332595e-09, "loss": 0.0036, "step": 17935 }, { "epoch": 0.9905014358294676, "grad_norm": 2.7883880138397217, "learning_rate": 9.464017353286725e-09, "loss": 0.4786, "step": 17936 }, { "epoch": 0.9905566600397614, "grad_norm": 0.018859999254345894, "learning_rate": 9.354299097394937e-09, "loss": 0.0005, "step": 17937 }, { "epoch": 0.9906118842500552, "grad_norm": 0.2410186380147934, "learning_rate": 9.245220399172194e-09, "loss": 0.0048, "step": 17938 }, { "epoch": 0.990667108460349, "grad_norm": 0.04777790978550911, "learning_rate": 9.136781262104599e-09, "loss": 0.0012, "step": 17939 }, { "epoch": 0.9907223326706428, "grad_norm": 2.8867225646972656, "learning_rate": 9.02898168966493e-09, "loss": 0.6708, "step": 17940 }, { "epoch": 0.9907775568809366, "grad_norm": 0.1281300038099289, "learning_rate": 8.921821685297094e-09, "loss": 0.0054, "step": 17941 }, { "epoch": 0.9908327810912304, "grad_norm": 3.1425089836120605, "learning_rate": 8.815301252433905e-09, "loss": 0.2389, "step": 17942 }, { "epoch": 0.9908880053015242, "grad_norm": 6.177250385284424, "learning_rate": 8.709420394481526e-09, "loss": 1.0423, "step": 17943 }, { "epoch": 0.990943229511818, "grad_norm": 0.1545892059803009, "learning_rate": 8.604179114826138e-09, "loss": 0.003, "step": 17944 }, { "epoch": 0.9909984537221118, "grad_norm": 0.12174166738986969, "learning_rate": 8.499577416838379e-09, "loss": 0.0024, "step": 17945 }, { "epoch": 0.9910536779324056, "grad_norm": 0.15182767808437347, "learning_rate": 8.395615303860016e-09, "loss": 0.0032, "step": 17946 }, { "epoch": 0.9911089021426993, "grad_norm": 2.607720136642456, "learning_rate": 8.292292779221722e-09, "loss": 0.2087, "step": 17947 }, { "epoch": 0.9911641263529931, "grad_norm": 3.1723859310150146, "learning_rate": 8.1896098462253e-09, "loss": 0.1608, "step": 17948 }, { "epoch": 0.9912193505632869, "grad_norm": 0.046320222318172455, "learning_rate": 8.087566508157007e-09, "loss": 0.0013, "step": 17949 }, { "epoch": 0.9912745747735807, "grad_norm": 0.028875131160020828, "learning_rate": 7.986162768283123e-09, "loss": 0.0009, "step": 17950 }, { "epoch": 0.9913297989838745, "grad_norm": 0.12664750218391418, "learning_rate": 7.885398629847718e-09, "loss": 0.0024, "step": 17951 }, { "epoch": 0.9913850231941683, "grad_norm": 0.008190867491066456, "learning_rate": 7.785274096070438e-09, "loss": 0.0002, "step": 17952 }, { "epoch": 0.9914402474044621, "grad_norm": 0.9383424520492554, "learning_rate": 7.685789170159829e-09, "loss": 0.0373, "step": 17953 }, { "epoch": 0.9914954716147559, "grad_norm": 2.9731075763702393, "learning_rate": 7.58694385529557e-09, "loss": 0.2351, "step": 17954 }, { "epoch": 0.9915506958250497, "grad_norm": 0.004964869003742933, "learning_rate": 7.488738154641795e-09, "loss": 0.0001, "step": 17955 }, { "epoch": 0.9916059200353435, "grad_norm": 0.06247488036751747, "learning_rate": 7.391172071338215e-09, "loss": 0.0024, "step": 17956 }, { "epoch": 0.9916611442456373, "grad_norm": 0.015215138904750347, "learning_rate": 7.294245608506778e-09, "loss": 0.0005, "step": 17957 }, { "epoch": 0.991716368455931, "grad_norm": 0.038051776587963104, "learning_rate": 7.197958769251667e-09, "loss": 0.001, "step": 17958 }, { "epoch": 0.9917715926662248, "grad_norm": 0.12199567258358002, "learning_rate": 7.1023115566482e-09, "loss": 0.0038, "step": 17959 }, { "epoch": 0.9918268168765186, "grad_norm": 3.1007585525512695, "learning_rate": 7.007303973760593e-09, "loss": 0.1923, "step": 17960 }, { "epoch": 0.9918820410868124, "grad_norm": 6.7917070388793945, "learning_rate": 6.912936023626416e-09, "loss": 0.4071, "step": 17961 }, { "epoch": 0.9919372652971062, "grad_norm": 1.0512717962265015, "learning_rate": 6.819207709265474e-09, "loss": 0.0301, "step": 17962 }, { "epoch": 0.9919924895074, "grad_norm": 1.9307022094726562, "learning_rate": 6.7261190336753714e-09, "loss": 0.0783, "step": 17963 }, { "epoch": 0.9920477137176938, "grad_norm": 0.34486132860183716, "learning_rate": 6.633669999835945e-09, "loss": 0.0102, "step": 17964 }, { "epoch": 0.9921029379279876, "grad_norm": 0.18841899931430817, "learning_rate": 6.541860610704831e-09, "loss": 0.003, "step": 17965 }, { "epoch": 0.9921581621382815, "grad_norm": 5.051190376281738, "learning_rate": 6.450690869217457e-09, "loss": 0.5524, "step": 17966 }, { "epoch": 0.9922133863485753, "grad_norm": 0.547539472579956, "learning_rate": 6.3601607782914905e-09, "loss": 0.0186, "step": 17967 }, { "epoch": 0.9922686105588691, "grad_norm": 0.06388206034898758, "learning_rate": 6.270270340822393e-09, "loss": 0.0012, "step": 17968 }, { "epoch": 0.9923238347691627, "grad_norm": 6.540857315063477, "learning_rate": 6.181019559687862e-09, "loss": 0.6283, "step": 17969 }, { "epoch": 0.9923790589794566, "grad_norm": 4.039242267608643, "learning_rate": 6.0924084377433915e-09, "loss": 0.7125, "step": 17970 }, { "epoch": 0.9924342831897504, "grad_norm": 0.3858817517757416, "learning_rate": 6.004436977820049e-09, "loss": 0.0095, "step": 17971 }, { "epoch": 0.9924895074000442, "grad_norm": 0.43843474984169006, "learning_rate": 5.917105182737803e-09, "loss": 0.0087, "step": 17972 }, { "epoch": 0.992544731610338, "grad_norm": 0.4130592346191406, "learning_rate": 5.830413055287754e-09, "loss": 0.0074, "step": 17973 }, { "epoch": 0.9925999558206318, "grad_norm": 1.4848631620407104, "learning_rate": 5.744360598243237e-09, "loss": 0.0635, "step": 17974 }, { "epoch": 0.9926551800309256, "grad_norm": 0.7590606212615967, "learning_rate": 5.6589478143576075e-09, "loss": 0.0217, "step": 17975 }, { "epoch": 0.9927104042412194, "grad_norm": 2.734771966934204, "learning_rate": 5.574174706364233e-09, "loss": 0.3219, "step": 17976 }, { "epoch": 0.9927656284515132, "grad_norm": 4.339566707611084, "learning_rate": 5.4900412769742785e-09, "loss": 0.5103, "step": 17977 }, { "epoch": 0.992820852661807, "grad_norm": 0.02871810458600521, "learning_rate": 5.406547528878925e-09, "loss": 0.0011, "step": 17978 }, { "epoch": 0.9928760768721008, "grad_norm": 1.1396125555038452, "learning_rate": 5.323693464749369e-09, "loss": 0.0378, "step": 17979 }, { "epoch": 0.9929313010823945, "grad_norm": 4.9115447998046875, "learning_rate": 5.2414790872390434e-09, "loss": 0.2875, "step": 17980 }, { "epoch": 0.9929865252926883, "grad_norm": 0.02783224545419216, "learning_rate": 5.159904398976956e-09, "loss": 0.0008, "step": 17981 }, { "epoch": 0.9930417495029821, "grad_norm": 2.787004232406616, "learning_rate": 5.078969402569911e-09, "loss": 0.0736, "step": 17982 }, { "epoch": 0.9930969737132759, "grad_norm": 2.9591667652130127, "learning_rate": 4.998674100611389e-09, "loss": 0.4304, "step": 17983 }, { "epoch": 0.9931521979235697, "grad_norm": 0.049967557191848755, "learning_rate": 4.9190184956682265e-09, "loss": 0.0014, "step": 17984 }, { "epoch": 0.9932074221338635, "grad_norm": 4.0594072341918945, "learning_rate": 4.840002590289494e-09, "loss": 0.3119, "step": 17985 }, { "epoch": 0.9932626463441573, "grad_norm": 5.570340633392334, "learning_rate": 4.761626387002061e-09, "loss": 1.0453, "step": 17986 }, { "epoch": 0.9933178705544511, "grad_norm": 0.5954065918922424, "learning_rate": 4.6838898883150295e-09, "loss": 0.0141, "step": 17987 }, { "epoch": 0.9933730947647449, "grad_norm": 0.03858494758605957, "learning_rate": 4.60679309671308e-09, "loss": 0.0011, "step": 17988 }, { "epoch": 0.9934283189750387, "grad_norm": 0.01980043388903141, "learning_rate": 4.530336014665348e-09, "loss": 0.0008, "step": 17989 }, { "epoch": 0.9934835431853325, "grad_norm": 0.29022419452667236, "learning_rate": 4.454518644616545e-09, "loss": 0.0075, "step": 17990 }, { "epoch": 0.9935387673956262, "grad_norm": 0.03088228963315487, "learning_rate": 4.379340988991398e-09, "loss": 0.0009, "step": 17991 }, { "epoch": 0.99359399160592, "grad_norm": 2.343440532684326, "learning_rate": 4.304803050196871e-09, "loss": 0.454, "step": 17992 }, { "epoch": 0.9936492158162138, "grad_norm": 3.0682528018951416, "learning_rate": 4.230904830617722e-09, "loss": 0.1993, "step": 17993 }, { "epoch": 0.9937044400265076, "grad_norm": 3.619417190551758, "learning_rate": 4.1576463326165055e-09, "loss": 0.1527, "step": 17994 }, { "epoch": 0.9937596642368014, "grad_norm": 2.6193928718566895, "learning_rate": 4.085027558538013e-09, "loss": 0.2064, "step": 17995 }, { "epoch": 0.9938148884470952, "grad_norm": 4.120871543884277, "learning_rate": 4.013048510704831e-09, "loss": 0.3986, "step": 17996 }, { "epoch": 0.993870112657389, "grad_norm": 5.323844909667969, "learning_rate": 3.941709191421783e-09, "loss": 0.7691, "step": 17997 }, { "epoch": 0.9939253368676828, "grad_norm": 0.08511900156736374, "learning_rate": 3.8710096029670465e-09, "loss": 0.0019, "step": 17998 }, { "epoch": 0.9939805610779766, "grad_norm": 2.289247989654541, "learning_rate": 3.800949747607696e-09, "loss": 0.0403, "step": 17999 }, { "epoch": 0.9940357852882704, "grad_norm": 1.4334630966186523, "learning_rate": 3.731529627581943e-09, "loss": 0.0548, "step": 18000 }, { "epoch": 0.9940910094985642, "grad_norm": 3.9378421306610107, "learning_rate": 3.6627492451102307e-09, "loss": 0.3323, "step": 18001 }, { "epoch": 0.994146233708858, "grad_norm": 3.801051616668701, "learning_rate": 3.5946086023952444e-09, "loss": 0.2471, "step": 18002 }, { "epoch": 0.9942014579191517, "grad_norm": 5.811875343322754, "learning_rate": 3.52710770161746e-09, "loss": 0.8325, "step": 18003 }, { "epoch": 0.9942566821294455, "grad_norm": 0.04723396152257919, "learning_rate": 3.4602465449329327e-09, "loss": 0.0011, "step": 18004 }, { "epoch": 0.9943119063397393, "grad_norm": 4.300920486450195, "learning_rate": 3.3940251344821705e-09, "loss": 0.6877, "step": 18005 }, { "epoch": 0.9943671305500331, "grad_norm": 4.067469120025635, "learning_rate": 3.3284434723857006e-09, "loss": 0.2026, "step": 18006 }, { "epoch": 0.9944223547603269, "grad_norm": 1.4418944120407104, "learning_rate": 3.2635015607396236e-09, "loss": 0.0811, "step": 18007 }, { "epoch": 0.9944775789706207, "grad_norm": 0.0532805509865284, "learning_rate": 3.1991994016244976e-09, "loss": 0.0014, "step": 18008 }, { "epoch": 0.9945328031809145, "grad_norm": 0.020139260217547417, "learning_rate": 3.1355369970920147e-09, "loss": 0.0005, "step": 18009 }, { "epoch": 0.9945880273912083, "grad_norm": 3.8526527881622314, "learning_rate": 3.072514349184985e-09, "loss": 0.502, "step": 18010 }, { "epoch": 0.9946432516015021, "grad_norm": 1.1208540201187134, "learning_rate": 3.010131459915133e-09, "loss": 0.0362, "step": 18011 }, { "epoch": 0.9946984758117959, "grad_norm": 0.5401911735534668, "learning_rate": 2.9483883312808604e-09, "loss": 0.0092, "step": 18012 }, { "epoch": 0.9947537000220897, "grad_norm": 5.7895827293396, "learning_rate": 2.887284965256143e-09, "loss": 1.1768, "step": 18013 }, { "epoch": 0.9948089242323834, "grad_norm": 0.660081148147583, "learning_rate": 2.8268213637971943e-09, "loss": 0.0168, "step": 18014 }, { "epoch": 0.9948641484426772, "grad_norm": 0.08708894997835159, "learning_rate": 2.7669975288380226e-09, "loss": 0.0018, "step": 18015 }, { "epoch": 0.994919372652971, "grad_norm": 0.03061908856034279, "learning_rate": 2.7078134622904318e-09, "loss": 0.0011, "step": 18016 }, { "epoch": 0.9949745968632648, "grad_norm": 6.340179443359375, "learning_rate": 2.649269166050683e-09, "loss": 1.3844, "step": 18017 }, { "epoch": 0.9950298210735586, "grad_norm": 2.868117094039917, "learning_rate": 2.5913646419906122e-09, "loss": 0.1161, "step": 18018 }, { "epoch": 0.9950850452838524, "grad_norm": 2.736074447631836, "learning_rate": 2.5340998919642925e-09, "loss": 0.1493, "step": 18019 }, { "epoch": 0.9951402694941462, "grad_norm": 0.026716021820902824, "learning_rate": 2.47747491780137e-09, "loss": 0.0006, "step": 18020 }, { "epoch": 0.99519549370444, "grad_norm": 0.010004710406064987, "learning_rate": 2.42148972131373e-09, "loss": 0.0003, "step": 18021 }, { "epoch": 0.9952507179147339, "grad_norm": 1.2312626838684082, "learning_rate": 2.366144304293272e-09, "loss": 0.0586, "step": 18022 }, { "epoch": 0.9953059421250277, "grad_norm": 0.005834478884935379, "learning_rate": 2.3114386685119117e-09, "loss": 0.0002, "step": 18023 }, { "epoch": 0.9953611663353215, "grad_norm": 4.569493293762207, "learning_rate": 2.2573728157171402e-09, "loss": 1.2621, "step": 18024 }, { "epoch": 0.9954163905456151, "grad_norm": 0.009259642101824284, "learning_rate": 2.203946747640906e-09, "loss": 0.0003, "step": 18025 }, { "epoch": 0.995471614755909, "grad_norm": 0.06963866204023361, "learning_rate": 2.1511604659907313e-09, "loss": 0.0023, "step": 18026 }, { "epoch": 0.9955268389662028, "grad_norm": 2.8771464824676514, "learning_rate": 2.0990139724563764e-09, "loss": 0.3299, "step": 18027 }, { "epoch": 0.9955820631764966, "grad_norm": 0.01356466580182314, "learning_rate": 2.047507268707616e-09, "loss": 0.0004, "step": 18028 }, { "epoch": 0.9956372873867904, "grad_norm": 0.07046549767255783, "learning_rate": 1.9966403563898006e-09, "loss": 0.0008, "step": 18029 }, { "epoch": 0.9956925115970842, "grad_norm": 3.5780580043792725, "learning_rate": 1.946413237130518e-09, "loss": 0.2067, "step": 18030 }, { "epoch": 0.995747735807378, "grad_norm": 1.858417272567749, "learning_rate": 1.89682591253737e-09, "loss": 0.159, "step": 18031 }, { "epoch": 0.9958029600176718, "grad_norm": 1.132455825805664, "learning_rate": 1.8478783841979764e-09, "loss": 0.0267, "step": 18032 }, { "epoch": 0.9958581842279656, "grad_norm": 0.08992383629083633, "learning_rate": 1.7995706536755308e-09, "loss": 0.0026, "step": 18033 }, { "epoch": 0.9959134084382594, "grad_norm": 1.039139747619629, "learning_rate": 1.7519027225199049e-09, "loss": 0.0136, "step": 18034 }, { "epoch": 0.9959686326485532, "grad_norm": 0.4519200623035431, "learning_rate": 1.7048745922498832e-09, "loss": 0.0112, "step": 18035 }, { "epoch": 0.9960238568588469, "grad_norm": 2.8517682552337646, "learning_rate": 1.6584862643753696e-09, "loss": 0.1116, "step": 18036 }, { "epoch": 0.9960790810691407, "grad_norm": 1.978348970413208, "learning_rate": 1.6127377403796217e-09, "loss": 0.0764, "step": 18037 }, { "epoch": 0.9961343052794345, "grad_norm": 0.3779976963996887, "learning_rate": 1.5676290217236933e-09, "loss": 0.009, "step": 18038 }, { "epoch": 0.9961895294897283, "grad_norm": 0.04114266857504845, "learning_rate": 1.5231601098530946e-09, "loss": 0.0013, "step": 18039 }, { "epoch": 0.9962447537000221, "grad_norm": 5.117420673370361, "learning_rate": 1.4793310061911315e-09, "loss": 0.5801, "step": 18040 }, { "epoch": 0.9962999779103159, "grad_norm": 0.5902585983276367, "learning_rate": 1.436141712136685e-09, "loss": 0.0176, "step": 18041 }, { "epoch": 0.9963552021206097, "grad_norm": 0.011081262491643429, "learning_rate": 1.393592229073093e-09, "loss": 0.0003, "step": 18042 }, { "epoch": 0.9964104263309035, "grad_norm": 0.1895499974489212, "learning_rate": 1.3516825583637094e-09, "loss": 0.0044, "step": 18043 }, { "epoch": 0.9964656505411973, "grad_norm": 0.038028229027986526, "learning_rate": 1.3104127013452429e-09, "loss": 0.001, "step": 18044 }, { "epoch": 0.9965208747514911, "grad_norm": 2.7102324962615967, "learning_rate": 1.2697826593432994e-09, "loss": 0.1653, "step": 18045 }, { "epoch": 0.9965760989617849, "grad_norm": 0.30475082993507385, "learning_rate": 1.2297924336523993e-09, "loss": 0.0082, "step": 18046 }, { "epoch": 0.9966313231720786, "grad_norm": 0.01524992473423481, "learning_rate": 1.1904420255559602e-09, "loss": 0.0004, "step": 18047 }, { "epoch": 0.9966865473823724, "grad_norm": 0.019455179572105408, "learning_rate": 1.1517314363107545e-09, "loss": 0.0006, "step": 18048 }, { "epoch": 0.9967417715926662, "grad_norm": 0.31049486994743347, "learning_rate": 1.1136606671557915e-09, "loss": 0.0034, "step": 18049 }, { "epoch": 0.99679699580296, "grad_norm": 0.12305136770009995, "learning_rate": 1.0762297193100957e-09, "loss": 0.0037, "step": 18050 }, { "epoch": 0.9968522200132538, "grad_norm": 0.013493839651346207, "learning_rate": 1.0394385939682673e-09, "loss": 0.0002, "step": 18051 }, { "epoch": 0.9969074442235476, "grad_norm": 0.046454887837171555, "learning_rate": 1.0032872923115832e-09, "loss": 0.0014, "step": 18052 }, { "epoch": 0.9969626684338414, "grad_norm": 0.010616888292133808, "learning_rate": 9.677758154924554e-10, "loss": 0.0003, "step": 18053 }, { "epoch": 0.9970178926441352, "grad_norm": 0.060015033930540085, "learning_rate": 9.329041646499725e-10, "loss": 0.0019, "step": 18054 }, { "epoch": 0.997073116854429, "grad_norm": 4.669532299041748, "learning_rate": 8.986723408987985e-10, "loss": 1.2077, "step": 18055 }, { "epoch": 0.9971283410647228, "grad_norm": 5.108002185821533, "learning_rate": 8.650803453336132e-10, "loss": 0.4343, "step": 18056 }, { "epoch": 0.9971835652750166, "grad_norm": 6.386945724487305, "learning_rate": 8.321281790291124e-10, "loss": 0.9391, "step": 18057 }, { "epoch": 0.9972387894853103, "grad_norm": 4.287745475769043, "learning_rate": 7.998158430400083e-10, "loss": 0.6443, "step": 18058 }, { "epoch": 0.9972940136956041, "grad_norm": 3.4045305252075195, "learning_rate": 7.681433384010284e-10, "loss": 0.278, "step": 18059 }, { "epoch": 0.9973492379058979, "grad_norm": 0.1512269824743271, "learning_rate": 7.371106661224758e-10, "loss": 0.0039, "step": 18060 }, { "epoch": 0.9974044621161917, "grad_norm": 2.7390434741973877, "learning_rate": 7.067178272013308e-10, "loss": 0.0434, "step": 18061 }, { "epoch": 0.9974596863264855, "grad_norm": 2.6952998638153076, "learning_rate": 6.769648226079284e-10, "loss": 0.595, "step": 18062 }, { "epoch": 0.9975149105367793, "grad_norm": 2.7374460697174072, "learning_rate": 6.478516532926193e-10, "loss": 0.2982, "step": 18063 }, { "epoch": 0.9975701347470731, "grad_norm": 3.018341541290283, "learning_rate": 6.19378320187991e-10, "loss": 0.1621, "step": 18064 }, { "epoch": 0.9976253589573669, "grad_norm": 0.05693381279706955, "learning_rate": 5.915448242044264e-10, "loss": 0.0016, "step": 18065 }, { "epoch": 0.9976805831676607, "grad_norm": 0.26056960225105286, "learning_rate": 5.643511662345447e-10, "loss": 0.0058, "step": 18066 }, { "epoch": 0.9977358073779545, "grad_norm": 0.7059141993522644, "learning_rate": 5.377973471465403e-10, "loss": 0.0139, "step": 18067 }, { "epoch": 0.9977910315882483, "grad_norm": 0.15305142104625702, "learning_rate": 5.118833677908441e-10, "loss": 0.0038, "step": 18068 }, { "epoch": 0.997846255798542, "grad_norm": 0.050474829971790314, "learning_rate": 4.866092289956825e-10, "loss": 0.0011, "step": 18069 }, { "epoch": 0.9979014800088358, "grad_norm": 2.392352342605591, "learning_rate": 4.6197493156929785e-10, "loss": 0.2107, "step": 18070 }, { "epoch": 0.9979567042191296, "grad_norm": 0.7983724474906921, "learning_rate": 4.379804763021689e-10, "loss": 0.0165, "step": 18071 }, { "epoch": 0.9980119284294234, "grad_norm": 3.4146595001220703, "learning_rate": 4.1462586396034955e-10, "loss": 0.6391, "step": 18072 }, { "epoch": 0.9980671526397172, "grad_norm": 4.696758270263672, "learning_rate": 3.9191109528768924e-10, "loss": 0.0941, "step": 18073 }, { "epoch": 0.998122376850011, "grad_norm": 2.893177032470703, "learning_rate": 3.6983617101693516e-10, "loss": 0.2503, "step": 18074 }, { "epoch": 0.9981776010603048, "grad_norm": 0.16790232062339783, "learning_rate": 3.484010918519687e-10, "loss": 0.0037, "step": 18075 }, { "epoch": 0.9982328252705986, "grad_norm": 0.007954209111630917, "learning_rate": 3.276058584766872e-10, "loss": 0.0002, "step": 18076 }, { "epoch": 0.9982880494808924, "grad_norm": 0.09257874637842178, "learning_rate": 3.074504715572246e-10, "loss": 0.0029, "step": 18077 }, { "epoch": 0.9983432736911863, "grad_norm": 0.3913779854774475, "learning_rate": 2.8793493174195107e-10, "loss": 0.0081, "step": 18078 }, { "epoch": 0.99839849790148, "grad_norm": 4.048762798309326, "learning_rate": 2.6905923964815064e-10, "loss": 0.3508, "step": 18079 }, { "epoch": 0.9984537221117739, "grad_norm": 2.850491523742676, "learning_rate": 2.508233958864459e-10, "loss": 0.3196, "step": 18080 }, { "epoch": 0.9985089463220675, "grad_norm": 2.7783877849578857, "learning_rate": 2.3322740103859374e-10, "loss": 0.6127, "step": 18081 }, { "epoch": 0.9985641705323614, "grad_norm": 2.9331436157226562, "learning_rate": 2.1627125566414665e-10, "loss": 0.4068, "step": 18082 }, { "epoch": 0.9986193947426552, "grad_norm": 3.1512763500213623, "learning_rate": 1.9995496030933426e-10, "loss": 0.1861, "step": 18083 }, { "epoch": 0.998674618952949, "grad_norm": 2.865337610244751, "learning_rate": 1.8427851549596143e-10, "loss": 0.2951, "step": 18084 }, { "epoch": 0.9987298431632428, "grad_norm": 3.6631486415863037, "learning_rate": 1.6924192172140806e-10, "loss": 0.6175, "step": 18085 }, { "epoch": 0.9987850673735366, "grad_norm": 0.6219863891601562, "learning_rate": 1.5484517947195188e-10, "loss": 0.0045, "step": 18086 }, { "epoch": 0.9988402915838304, "grad_norm": 0.09954927861690521, "learning_rate": 1.4108828920722517e-10, "loss": 0.0035, "step": 18087 }, { "epoch": 0.9988955157941242, "grad_norm": 2.3563356399536133, "learning_rate": 1.2797125136465583e-10, "loss": 0.0936, "step": 18088 }, { "epoch": 0.998950740004418, "grad_norm": 2.6852779388427734, "learning_rate": 1.1549406636390815e-10, "loss": 0.1053, "step": 18089 }, { "epoch": 0.9990059642147118, "grad_norm": 0.07640326023101807, "learning_rate": 1.0365673460688286e-10, "loss": 0.0031, "step": 18090 }, { "epoch": 0.9990611884250056, "grad_norm": 6.480661392211914, "learning_rate": 9.245925647327625e-11, "loss": 1.7536, "step": 18091 }, { "epoch": 0.9991164126352993, "grad_norm": 2.679591655731201, "learning_rate": 8.190163231613924e-11, "loss": 0.5861, "step": 18092 }, { "epoch": 0.9991716368455931, "grad_norm": 0.017376918345689774, "learning_rate": 7.198386247742051e-11, "loss": 0.0004, "step": 18093 }, { "epoch": 0.9992268610558869, "grad_norm": 0.3579990863800049, "learning_rate": 6.270594727242341e-11, "loss": 0.0067, "step": 18094 }, { "epoch": 0.9992820852661807, "grad_norm": 4.125993251800537, "learning_rate": 5.40678869986877e-11, "loss": 0.3307, "step": 18095 }, { "epoch": 0.9993373094764745, "grad_norm": 2.9580118656158447, "learning_rate": 4.606968193376915e-11, "loss": 0.3454, "step": 18096 }, { "epoch": 0.9993925336867683, "grad_norm": 0.018057163804769516, "learning_rate": 3.8711332333019045e-11, "loss": 0.0005, "step": 18097 }, { "epoch": 0.9994477578970621, "grad_norm": 0.7940765023231506, "learning_rate": 3.1992838429584226e-11, "loss": 0.0152, "step": 18098 }, { "epoch": 0.9995029821073559, "grad_norm": 0.2568243741989136, "learning_rate": 2.5914200441068405e-11, "loss": 0.0039, "step": 18099 }, { "epoch": 0.9995582063176497, "grad_norm": 2.3404452800750732, "learning_rate": 2.0475418560650383e-11, "loss": 0.591, "step": 18100 }, { "epoch": 0.9996134305279435, "grad_norm": 0.015227897092700005, "learning_rate": 1.567649296152496e-11, "loss": 0.0004, "step": 18101 }, { "epoch": 0.9996686547382373, "grad_norm": 0.26709434390068054, "learning_rate": 1.151742379912335e-11, "loss": 0.0052, "step": 18102 }, { "epoch": 0.999723878948531, "grad_norm": 1.5387895107269287, "learning_rate": 7.998211206672324e-12, "loss": 0.0203, "step": 18103 }, { "epoch": 0.9997791031588248, "grad_norm": 1.7146342992782593, "learning_rate": 5.118855295194181e-12, "loss": 0.0326, "step": 18104 }, { "epoch": 0.9998343273691186, "grad_norm": 2.226917028427124, "learning_rate": 2.879356157947655e-12, "loss": 0.1568, "step": 18105 }, { "epoch": 0.9998895515794124, "grad_norm": 0.031114984303712845, "learning_rate": 1.279713863766574e-12, "loss": 0.0009, "step": 18106 }, { "epoch": 0.9999447757897062, "grad_norm": 0.27556297183036804, "learning_rate": 3.1992846816208956e-13, "loss": 0.007, "step": 18107 }, { "epoch": 1.0, "grad_norm": 2.2670366764068604, "learning_rate": 0.0, "loss": 0.1535, "step": 18108 } ], "logging_steps": 1.0, "max_steps": 18108, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 200, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 9.06600037173057e+20, "train_batch_size": 1, "trial_name": null, "trial_params": null }