{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.0, "global_step": 12176, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 2.999753613666229e-05, "loss": 5.613, "step": 1 }, { "epoch": 0.0, "learning_rate": 2.9995072273324573e-05, "loss": 5.5627, "step": 2 }, { "epoch": 0.0, "learning_rate": 2.999260840998686e-05, "loss": 5.3647, "step": 3 }, { "epoch": 0.0, "learning_rate": 2.9990144546649145e-05, "loss": 5.41, "step": 4 }, { "epoch": 0.0, "learning_rate": 2.9987680683311432e-05, "loss": 5.1766, "step": 5 }, { "epoch": 0.0, "learning_rate": 2.998521681997372e-05, "loss": 5.1487, "step": 6 }, { "epoch": 0.0, "learning_rate": 2.9982752956636008e-05, "loss": 4.8779, "step": 7 }, { "epoch": 0.0, "learning_rate": 2.9982752956636008e-05, "loss": 5.1973, "step": 8 }, { "epoch": 0.0, "learning_rate": 2.9980289093298292e-05, "loss": 4.8997, "step": 9 }, { "epoch": 0.0, "learning_rate": 2.9980289093298292e-05, "loss": 4.6373, "step": 10 }, { "epoch": 0.0, "learning_rate": 2.997782522996058e-05, "loss": 4.6343, "step": 11 }, { "epoch": 0.0, "learning_rate": 2.9975361366622864e-05, "loss": 4.435, "step": 12 }, { "epoch": 0.0, "learning_rate": 2.997289750328515e-05, "loss": 4.5695, "step": 13 }, { "epoch": 0.0, "learning_rate": 2.997043363994744e-05, "loss": 4.7774, "step": 14 }, { "epoch": 0.0, "learning_rate": 2.9967969776609724e-05, "loss": 4.523, "step": 15 }, { "epoch": 0.0, "learning_rate": 2.996550591327201e-05, "loss": 4.4065, "step": 16 }, { "epoch": 0.0, "learning_rate": 2.9963042049934296e-05, "loss": 4.0782, "step": 17 }, { "epoch": 0.0, "learning_rate": 2.9960578186596587e-05, "loss": 4.4717, "step": 18 }, { "epoch": 0.0, "learning_rate": 2.995811432325887e-05, "loss": 4.2679, "step": 19 }, { "epoch": 0.0, "learning_rate": 2.995565045992116e-05, "loss": 4.19, "step": 20 }, { "epoch": 0.0, "learning_rate": 2.9953186596583443e-05, "loss": 4.1944, "step": 21 }, { "epoch": 0.0, "learning_rate": 2.995072273324573e-05, "loss": 3.7767, "step": 22 }, { "epoch": 0.0, "learning_rate": 2.9948258869908015e-05, "loss": 3.9377, "step": 23 }, { "epoch": 0.0, "learning_rate": 2.9945795006570303e-05, "loss": 4.1989, "step": 24 }, { "epoch": 0.0, "learning_rate": 2.9943331143232587e-05, "loss": 3.9863, "step": 25 }, { "epoch": 0.0, "learning_rate": 2.9940867279894875e-05, "loss": 3.8013, "step": 26 }, { "epoch": 0.0, "learning_rate": 2.9938403416557162e-05, "loss": 3.4084, "step": 27 }, { "epoch": 0.0, "learning_rate": 2.993593955321945e-05, "loss": 4.1058, "step": 28 }, { "epoch": 0.0, "learning_rate": 2.9933475689881738e-05, "loss": 3.8939, "step": 29 }, { "epoch": 0.0, "learning_rate": 2.9931011826544022e-05, "loss": 3.7308, "step": 30 }, { "epoch": 0.01, "learning_rate": 2.992854796320631e-05, "loss": 3.6145, "step": 31 }, { "epoch": 0.01, "learning_rate": 2.9926084099868594e-05, "loss": 3.8082, "step": 32 }, { "epoch": 0.01, "learning_rate": 2.992362023653088e-05, "loss": 3.5671, "step": 33 }, { "epoch": 0.01, "learning_rate": 2.9921156373193166e-05, "loss": 3.4881, "step": 34 }, { "epoch": 0.01, "learning_rate": 2.9918692509855453e-05, "loss": 4.3365, "step": 35 }, { "epoch": 0.01, "learning_rate": 2.9918692509855453e-05, "loss": 4.1011, "step": 36 }, { "epoch": 0.01, "learning_rate": 2.9916228646517738e-05, "loss": 4.2891, "step": 37 }, { "epoch": 0.01, "learning_rate": 2.9916228646517738e-05, "loss": 3.8693, "step": 38 }, { "epoch": 0.01, "learning_rate": 2.9913764783180025e-05, "loss": 3.9704, "step": 39 }, { "epoch": 0.01, "learning_rate": 2.9911300919842317e-05, "loss": 3.7918, "step": 40 }, { "epoch": 0.01, "learning_rate": 2.99088370565046e-05, "loss": 3.2322, "step": 41 }, { "epoch": 0.01, "learning_rate": 2.990637319316689e-05, "loss": 2.9786, "step": 42 }, { "epoch": 0.01, "learning_rate": 2.990637319316689e-05, "loss": 3.1351, "step": 43 }, { "epoch": 0.01, "learning_rate": 2.9903909329829173e-05, "loss": 2.8754, "step": 44 }, { "epoch": 0.01, "learning_rate": 2.990144546649146e-05, "loss": 3.0178, "step": 45 }, { "epoch": 0.01, "learning_rate": 2.9898981603153745e-05, "loss": 3.1582, "step": 46 }, { "epoch": 0.01, "learning_rate": 2.9896517739816032e-05, "loss": 2.5829, "step": 47 }, { "epoch": 0.01, "learning_rate": 2.9894053876478317e-05, "loss": 3.5349, "step": 48 }, { "epoch": 0.01, "learning_rate": 2.9891590013140604e-05, "loss": 2.7132, "step": 49 }, { "epoch": 0.01, "learning_rate": 2.988912614980289e-05, "loss": 3.4191, "step": 50 }, { "epoch": 0.01, "learning_rate": 2.988666228646518e-05, "loss": 3.3485, "step": 51 }, { "epoch": 0.01, "learning_rate": 2.9884198423127464e-05, "loss": 2.4988, "step": 52 }, { "epoch": 0.01, "learning_rate": 2.9881734559789752e-05, "loss": 2.5185, "step": 53 }, { "epoch": 0.01, "learning_rate": 2.987927069645204e-05, "loss": 2.7453, "step": 54 }, { "epoch": 0.01, "learning_rate": 2.9876806833114324e-05, "loss": 2.1805, "step": 55 }, { "epoch": 0.01, "learning_rate": 2.987434296977661e-05, "loss": 2.0793, "step": 56 }, { "epoch": 0.01, "learning_rate": 2.9871879106438896e-05, "loss": 2.744, "step": 57 }, { "epoch": 0.01, "learning_rate": 2.9869415243101183e-05, "loss": 2.3458, "step": 58 }, { "epoch": 0.01, "learning_rate": 2.9866951379763468e-05, "loss": 2.5306, "step": 59 }, { "epoch": 0.01, "learning_rate": 2.9864487516425755e-05, "loss": 2.309, "step": 60 }, { "epoch": 0.01, "learning_rate": 2.9862023653088043e-05, "loss": 1.9296, "step": 61 }, { "epoch": 0.01, "learning_rate": 2.985955978975033e-05, "loss": 3.2789, "step": 62 }, { "epoch": 0.01, "learning_rate": 2.9857095926412615e-05, "loss": 2.9339, "step": 63 }, { "epoch": 0.01, "learning_rate": 2.9854632063074903e-05, "loss": 2.0555, "step": 64 }, { "epoch": 0.01, "learning_rate": 2.985216819973719e-05, "loss": 2.2389, "step": 65 }, { "epoch": 0.01, "learning_rate": 2.9849704336399475e-05, "loss": 2.3347, "step": 66 }, { "epoch": 0.01, "learning_rate": 2.9847240473061762e-05, "loss": 1.7429, "step": 67 }, { "epoch": 0.01, "learning_rate": 2.9844776609724047e-05, "loss": 2.2837, "step": 68 }, { "epoch": 0.01, "learning_rate": 2.9842312746386334e-05, "loss": 2.0198, "step": 69 }, { "epoch": 0.01, "learning_rate": 2.983984888304862e-05, "loss": 1.6605, "step": 70 }, { "epoch": 0.01, "learning_rate": 2.983738501971091e-05, "loss": 1.8976, "step": 71 }, { "epoch": 0.01, "learning_rate": 2.9834921156373194e-05, "loss": 2.3144, "step": 72 }, { "epoch": 0.01, "learning_rate": 2.983245729303548e-05, "loss": 2.2852, "step": 73 }, { "epoch": 0.01, "learning_rate": 2.9829993429697766e-05, "loss": 2.6955, "step": 74 }, { "epoch": 0.01, "learning_rate": 2.9827529566360054e-05, "loss": 2.4953, "step": 75 }, { "epoch": 0.01, "learning_rate": 2.9825065703022338e-05, "loss": 1.7951, "step": 76 }, { "epoch": 0.01, "learning_rate": 2.9822601839684626e-05, "loss": 2.0138, "step": 77 }, { "epoch": 0.01, "learning_rate": 2.9820137976346913e-05, "loss": 1.6357, "step": 78 }, { "epoch": 0.01, "learning_rate": 2.9817674113009197e-05, "loss": 1.6607, "step": 79 }, { "epoch": 0.01, "learning_rate": 2.9815210249671485e-05, "loss": 2.2612, "step": 80 }, { "epoch": 0.01, "learning_rate": 2.9812746386333773e-05, "loss": 1.5532, "step": 81 }, { "epoch": 0.01, "learning_rate": 2.981028252299606e-05, "loss": 1.889, "step": 82 }, { "epoch": 0.01, "learning_rate": 2.9807818659658345e-05, "loss": 1.3409, "step": 83 }, { "epoch": 0.01, "learning_rate": 2.9805354796320633e-05, "loss": 1.4024, "step": 84 }, { "epoch": 0.01, "learning_rate": 2.9802890932982917e-05, "loss": 1.6738, "step": 85 }, { "epoch": 0.01, "learning_rate": 2.9800427069645204e-05, "loss": 2.4277, "step": 86 }, { "epoch": 0.01, "learning_rate": 2.979796320630749e-05, "loss": 2.4734, "step": 87 }, { "epoch": 0.01, "learning_rate": 2.9795499342969776e-05, "loss": 1.9106, "step": 88 }, { "epoch": 0.01, "learning_rate": 2.9793035479632064e-05, "loss": 2.0191, "step": 89 }, { "epoch": 0.01, "learning_rate": 2.979057161629435e-05, "loss": 1.2115, "step": 90 }, { "epoch": 0.01, "learning_rate": 2.978810775295664e-05, "loss": 1.1691, "step": 91 }, { "epoch": 0.02, "learning_rate": 2.9785643889618924e-05, "loss": 1.6064, "step": 92 }, { "epoch": 0.02, "learning_rate": 2.978318002628121e-05, "loss": 1.987, "step": 93 }, { "epoch": 0.02, "learning_rate": 2.9780716162943496e-05, "loss": 1.9506, "step": 94 }, { "epoch": 0.02, "learning_rate": 2.9778252299605783e-05, "loss": 1.6552, "step": 95 }, { "epoch": 0.02, "learning_rate": 2.9775788436268068e-05, "loss": 1.7473, "step": 96 }, { "epoch": 0.02, "learning_rate": 2.9773324572930355e-05, "loss": 1.5853, "step": 97 }, { "epoch": 0.02, "learning_rate": 2.977086070959264e-05, "loss": 2.0725, "step": 98 }, { "epoch": 0.02, "learning_rate": 2.9768396846254927e-05, "loss": 2.0765, "step": 99 }, { "epoch": 0.02, "learning_rate": 2.976593298291721e-05, "loss": 1.3549, "step": 100 }, { "epoch": 0.02, "learning_rate": 2.9763469119579503e-05, "loss": 1.4429, "step": 101 }, { "epoch": 0.02, "learning_rate": 2.976100525624179e-05, "loss": 1.9011, "step": 102 }, { "epoch": 0.02, "learning_rate": 2.9758541392904075e-05, "loss": 2.0202, "step": 103 }, { "epoch": 0.02, "learning_rate": 2.9756077529566362e-05, "loss": 1.7087, "step": 104 }, { "epoch": 0.02, "learning_rate": 2.9753613666228647e-05, "loss": 1.6599, "step": 105 }, { "epoch": 0.02, "learning_rate": 2.9751149802890934e-05, "loss": 1.6461, "step": 106 }, { "epoch": 0.02, "learning_rate": 2.974868593955322e-05, "loss": 1.7663, "step": 107 }, { "epoch": 0.02, "learning_rate": 2.9746222076215506e-05, "loss": 1.6139, "step": 108 }, { "epoch": 0.02, "learning_rate": 2.974375821287779e-05, "loss": 1.8496, "step": 109 }, { "epoch": 0.02, "learning_rate": 2.9741294349540078e-05, "loss": 2.1026, "step": 110 }, { "epoch": 0.02, "learning_rate": 2.9738830486202366e-05, "loss": 1.5729, "step": 111 }, { "epoch": 0.02, "learning_rate": 2.9736366622864654e-05, "loss": 1.3395, "step": 112 }, { "epoch": 0.02, "learning_rate": 2.973390275952694e-05, "loss": 1.8211, "step": 113 }, { "epoch": 0.02, "learning_rate": 2.9731438896189226e-05, "loss": 1.0586, "step": 114 }, { "epoch": 0.02, "learning_rate": 2.9728975032851513e-05, "loss": 1.2585, "step": 115 }, { "epoch": 0.02, "learning_rate": 2.9726511169513798e-05, "loss": 1.3772, "step": 116 }, { "epoch": 0.02, "learning_rate": 2.9724047306176085e-05, "loss": 1.3552, "step": 117 }, { "epoch": 0.02, "learning_rate": 2.972158344283837e-05, "loss": 1.2773, "step": 118 }, { "epoch": 0.02, "learning_rate": 2.9719119579500657e-05, "loss": 1.0449, "step": 119 }, { "epoch": 0.02, "learning_rate": 2.971665571616294e-05, "loss": 2.1721, "step": 120 }, { "epoch": 0.02, "learning_rate": 2.9714191852825233e-05, "loss": 1.1943, "step": 121 }, { "epoch": 0.02, "learning_rate": 2.9711727989487517e-05, "loss": 1.5844, "step": 122 }, { "epoch": 0.02, "learning_rate": 2.9709264126149805e-05, "loss": 1.2861, "step": 123 }, { "epoch": 0.02, "learning_rate": 2.970680026281209e-05, "loss": 2.0321, "step": 124 }, { "epoch": 0.02, "learning_rate": 2.9704336399474377e-05, "loss": 1.1777, "step": 125 }, { "epoch": 0.02, "learning_rate": 2.9701872536136664e-05, "loss": 1.4063, "step": 126 }, { "epoch": 0.02, "learning_rate": 2.969940867279895e-05, "loss": 1.717, "step": 127 }, { "epoch": 0.02, "learning_rate": 2.9696944809461236e-05, "loss": 1.4763, "step": 128 }, { "epoch": 0.02, "learning_rate": 2.969448094612352e-05, "loss": 1.1058, "step": 129 }, { "epoch": 0.02, "learning_rate": 2.9692017082785808e-05, "loss": 2.0719, "step": 130 }, { "epoch": 0.02, "learning_rate": 2.9689553219448096e-05, "loss": 1.5556, "step": 131 }, { "epoch": 0.02, "learning_rate": 2.9687089356110383e-05, "loss": 1.3173, "step": 132 }, { "epoch": 0.02, "learning_rate": 2.9684625492772668e-05, "loss": 2.1661, "step": 133 }, { "epoch": 0.02, "learning_rate": 2.9682161629434955e-05, "loss": 1.3581, "step": 134 }, { "epoch": 0.02, "learning_rate": 2.967969776609724e-05, "loss": 1.6914, "step": 135 }, { "epoch": 0.02, "learning_rate": 2.9677233902759527e-05, "loss": 1.41, "step": 136 }, { "epoch": 0.02, "learning_rate": 2.9674770039421815e-05, "loss": 1.699, "step": 137 }, { "epoch": 0.02, "learning_rate": 2.96723061760841e-05, "loss": 1.4571, "step": 138 }, { "epoch": 0.02, "learning_rate": 2.9669842312746387e-05, "loss": 0.9583, "step": 139 }, { "epoch": 0.02, "learning_rate": 2.966737844940867e-05, "loss": 1.512, "step": 140 }, { "epoch": 0.02, "learning_rate": 2.9664914586070962e-05, "loss": 1.8905, "step": 141 }, { "epoch": 0.02, "learning_rate": 2.9662450722733247e-05, "loss": 2.0449, "step": 142 }, { "epoch": 0.02, "learning_rate": 2.9659986859395534e-05, "loss": 1.4759, "step": 143 }, { "epoch": 0.02, "learning_rate": 2.965752299605782e-05, "loss": 0.6436, "step": 144 }, { "epoch": 0.02, "learning_rate": 2.9655059132720106e-05, "loss": 2.3458, "step": 145 }, { "epoch": 0.02, "learning_rate": 2.965259526938239e-05, "loss": 1.147, "step": 146 }, { "epoch": 0.02, "learning_rate": 2.965013140604468e-05, "loss": 1.5097, "step": 147 }, { "epoch": 0.02, "learning_rate": 2.9647667542706966e-05, "loss": 1.4269, "step": 148 }, { "epoch": 0.02, "learning_rate": 2.964520367936925e-05, "loss": 1.0698, "step": 149 }, { "epoch": 0.02, "learning_rate": 2.9642739816031538e-05, "loss": 0.934, "step": 150 }, { "epoch": 0.02, "learning_rate": 2.9640275952693826e-05, "loss": 1.9969, "step": 151 }, { "epoch": 0.02, "learning_rate": 2.9637812089356113e-05, "loss": 1.1684, "step": 152 }, { "epoch": 0.03, "learning_rate": 2.9635348226018398e-05, "loss": 0.5575, "step": 153 }, { "epoch": 0.03, "learning_rate": 2.9632884362680685e-05, "loss": 1.2889, "step": 154 }, { "epoch": 0.03, "learning_rate": 2.963042049934297e-05, "loss": 1.3624, "step": 155 }, { "epoch": 0.03, "learning_rate": 2.9627956636005257e-05, "loss": 1.2967, "step": 156 }, { "epoch": 0.03, "learning_rate": 2.962549277266754e-05, "loss": 1.1815, "step": 157 }, { "epoch": 0.03, "learning_rate": 2.962302890932983e-05, "loss": 1.194, "step": 158 }, { "epoch": 0.03, "learning_rate": 2.9620565045992114e-05, "loss": 1.7376, "step": 159 }, { "epoch": 0.03, "learning_rate": 2.96181011826544e-05, "loss": 1.3502, "step": 160 }, { "epoch": 0.03, "learning_rate": 2.9615637319316692e-05, "loss": 1.5024, "step": 161 }, { "epoch": 0.03, "learning_rate": 2.9613173455978977e-05, "loss": 1.0409, "step": 162 }, { "epoch": 0.03, "learning_rate": 2.9610709592641264e-05, "loss": 1.1403, "step": 163 }, { "epoch": 0.03, "learning_rate": 2.960824572930355e-05, "loss": 1.6162, "step": 164 }, { "epoch": 0.03, "learning_rate": 2.9605781865965836e-05, "loss": 1.3413, "step": 165 }, { "epoch": 0.03, "learning_rate": 2.960331800262812e-05, "loss": 2.0855, "step": 166 }, { "epoch": 0.03, "learning_rate": 2.9600854139290408e-05, "loss": 1.8101, "step": 167 }, { "epoch": 0.03, "learning_rate": 2.9598390275952692e-05, "loss": 1.512, "step": 168 }, { "epoch": 0.03, "learning_rate": 2.959592641261498e-05, "loss": 1.7987, "step": 169 }, { "epoch": 0.03, "learning_rate": 2.9593462549277264e-05, "loss": 1.5372, "step": 170 }, { "epoch": 0.03, "learning_rate": 2.9590998685939556e-05, "loss": 1.6816, "step": 171 }, { "epoch": 0.03, "learning_rate": 2.9588534822601843e-05, "loss": 1.1994, "step": 172 }, { "epoch": 0.03, "learning_rate": 2.9586070959264127e-05, "loss": 1.3506, "step": 173 }, { "epoch": 0.03, "learning_rate": 2.9583607095926415e-05, "loss": 2.0524, "step": 174 }, { "epoch": 0.03, "learning_rate": 2.95811432325887e-05, "loss": 0.6996, "step": 175 }, { "epoch": 0.03, "learning_rate": 2.9578679369250987e-05, "loss": 1.2257, "step": 176 }, { "epoch": 0.03, "learning_rate": 2.957621550591327e-05, "loss": 1.9383, "step": 177 }, { "epoch": 0.03, "learning_rate": 2.957375164257556e-05, "loss": 1.4816, "step": 178 }, { "epoch": 0.03, "learning_rate": 2.9571287779237843e-05, "loss": 0.9425, "step": 179 }, { "epoch": 0.03, "learning_rate": 2.956882391590013e-05, "loss": 2.0005, "step": 180 }, { "epoch": 0.03, "learning_rate": 2.956636005256242e-05, "loss": 1.1513, "step": 181 }, { "epoch": 0.03, "learning_rate": 2.9563896189224706e-05, "loss": 2.0165, "step": 182 }, { "epoch": 0.03, "learning_rate": 2.956143232588699e-05, "loss": 0.8973, "step": 183 }, { "epoch": 0.03, "learning_rate": 2.955896846254928e-05, "loss": 1.6481, "step": 184 }, { "epoch": 0.03, "learning_rate": 2.9556504599211566e-05, "loss": 1.4393, "step": 185 }, { "epoch": 0.03, "learning_rate": 2.955404073587385e-05, "loss": 1.8698, "step": 186 }, { "epoch": 0.03, "learning_rate": 2.9551576872536138e-05, "loss": 1.1532, "step": 187 }, { "epoch": 0.03, "learning_rate": 2.9549113009198422e-05, "loss": 1.9241, "step": 188 }, { "epoch": 0.03, "learning_rate": 2.954664914586071e-05, "loss": 1.1042, "step": 189 }, { "epoch": 0.03, "learning_rate": 2.9544185282522994e-05, "loss": 1.6859, "step": 190 }, { "epoch": 0.03, "learning_rate": 2.9541721419185285e-05, "loss": 1.0519, "step": 191 }, { "epoch": 0.03, "learning_rate": 2.953925755584757e-05, "loss": 1.1971, "step": 192 }, { "epoch": 0.03, "learning_rate": 2.9536793692509857e-05, "loss": 0.997, "step": 193 }, { "epoch": 0.03, "learning_rate": 2.953432982917214e-05, "loss": 1.1098, "step": 194 }, { "epoch": 0.03, "learning_rate": 2.953186596583443e-05, "loss": 1.2443, "step": 195 }, { "epoch": 0.03, "learning_rate": 2.9529402102496717e-05, "loss": 1.7785, "step": 196 }, { "epoch": 0.03, "learning_rate": 2.9526938239159e-05, "loss": 1.3223, "step": 197 }, { "epoch": 0.03, "learning_rate": 2.952447437582129e-05, "loss": 1.4588, "step": 198 }, { "epoch": 0.03, "learning_rate": 2.9522010512483573e-05, "loss": 1.6279, "step": 199 }, { "epoch": 0.03, "learning_rate": 2.951954664914586e-05, "loss": 1.0509, "step": 200 }, { "epoch": 0.03, "learning_rate": 2.951708278580815e-05, "loss": 1.7157, "step": 201 }, { "epoch": 0.03, "learning_rate": 2.9514618922470436e-05, "loss": 1.4684, "step": 202 }, { "epoch": 0.03, "learning_rate": 2.951215505913272e-05, "loss": 1.8632, "step": 203 }, { "epoch": 0.03, "learning_rate": 2.9509691195795008e-05, "loss": 1.5065, "step": 204 }, { "epoch": 0.03, "learning_rate": 2.9507227332457293e-05, "loss": 1.0612, "step": 205 }, { "epoch": 0.03, "learning_rate": 2.950476346911958e-05, "loss": 1.1766, "step": 206 }, { "epoch": 0.03, "learning_rate": 2.9502299605781865e-05, "loss": 0.9833, "step": 207 }, { "epoch": 0.03, "learning_rate": 2.9499835742444152e-05, "loss": 2.0134, "step": 208 }, { "epoch": 0.03, "learning_rate": 2.949737187910644e-05, "loss": 1.4348, "step": 209 }, { "epoch": 0.03, "learning_rate": 2.9494908015768724e-05, "loss": 0.9713, "step": 210 }, { "epoch": 0.03, "learning_rate": 2.9492444152431015e-05, "loss": 1.8663, "step": 211 }, { "epoch": 0.03, "learning_rate": 2.94899802890933e-05, "loss": 1.3405, "step": 212 }, { "epoch": 0.03, "learning_rate": 2.9487516425755587e-05, "loss": 2.011, "step": 213 }, { "epoch": 0.04, "learning_rate": 2.948505256241787e-05, "loss": 1.4388, "step": 214 }, { "epoch": 0.04, "learning_rate": 2.948258869908016e-05, "loss": 0.9548, "step": 215 }, { "epoch": 0.04, "learning_rate": 2.9480124835742443e-05, "loss": 1.9227, "step": 216 }, { "epoch": 0.04, "learning_rate": 2.947766097240473e-05, "loss": 1.244, "step": 217 }, { "epoch": 0.04, "learning_rate": 2.9475197109067015e-05, "loss": 1.4106, "step": 218 }, { "epoch": 0.04, "learning_rate": 2.9472733245729303e-05, "loss": 2.222, "step": 219 }, { "epoch": 0.04, "learning_rate": 2.947026938239159e-05, "loss": 1.7573, "step": 220 }, { "epoch": 0.04, "learning_rate": 2.946780551905388e-05, "loss": 1.2871, "step": 221 }, { "epoch": 0.04, "learning_rate": 2.9465341655716166e-05, "loss": 1.1661, "step": 222 }, { "epoch": 0.04, "learning_rate": 2.946287779237845e-05, "loss": 1.0055, "step": 223 }, { "epoch": 0.04, "learning_rate": 2.9460413929040738e-05, "loss": 0.9175, "step": 224 }, { "epoch": 0.04, "learning_rate": 2.9457950065703022e-05, "loss": 1.2167, "step": 225 }, { "epoch": 0.04, "learning_rate": 2.945548620236531e-05, "loss": 1.1094, "step": 226 }, { "epoch": 0.04, "learning_rate": 2.9453022339027594e-05, "loss": 0.8983, "step": 227 }, { "epoch": 0.04, "learning_rate": 2.9450558475689882e-05, "loss": 1.2412, "step": 228 }, { "epoch": 0.04, "learning_rate": 2.9448094612352166e-05, "loss": 1.8591, "step": 229 }, { "epoch": 0.04, "learning_rate": 2.9445630749014454e-05, "loss": 1.3222, "step": 230 }, { "epoch": 0.04, "learning_rate": 2.944316688567674e-05, "loss": 1.5771, "step": 231 }, { "epoch": 0.04, "learning_rate": 2.944070302233903e-05, "loss": 1.9854, "step": 232 }, { "epoch": 0.04, "learning_rate": 2.9438239159001317e-05, "loss": 1.6529, "step": 233 }, { "epoch": 0.04, "learning_rate": 2.94357752956636e-05, "loss": 1.0921, "step": 234 }, { "epoch": 0.04, "learning_rate": 2.943331143232589e-05, "loss": 1.9225, "step": 235 }, { "epoch": 0.04, "learning_rate": 2.9430847568988173e-05, "loss": 1.2007, "step": 236 }, { "epoch": 0.04, "learning_rate": 2.942838370565046e-05, "loss": 1.1584, "step": 237 }, { "epoch": 0.04, "learning_rate": 2.9425919842312745e-05, "loss": 1.8232, "step": 238 }, { "epoch": 0.04, "learning_rate": 2.9423455978975033e-05, "loss": 0.8979, "step": 239 }, { "epoch": 0.04, "learning_rate": 2.9420992115637317e-05, "loss": 1.0985, "step": 240 }, { "epoch": 0.04, "learning_rate": 2.941852825229961e-05, "loss": 1.3905, "step": 241 }, { "epoch": 0.04, "learning_rate": 2.9416064388961893e-05, "loss": 0.7731, "step": 242 }, { "epoch": 0.04, "learning_rate": 2.941360052562418e-05, "loss": 1.2509, "step": 243 }, { "epoch": 0.04, "learning_rate": 2.9411136662286468e-05, "loss": 1.304, "step": 244 }, { "epoch": 0.04, "learning_rate": 2.9408672798948752e-05, "loss": 1.1065, "step": 245 }, { "epoch": 0.04, "learning_rate": 2.940620893561104e-05, "loss": 1.6938, "step": 246 }, { "epoch": 0.04, "learning_rate": 2.9403745072273324e-05, "loss": 1.5015, "step": 247 }, { "epoch": 0.04, "learning_rate": 2.9401281208935612e-05, "loss": 1.8482, "step": 248 }, { "epoch": 0.04, "learning_rate": 2.9398817345597896e-05, "loss": 1.9024, "step": 249 }, { "epoch": 0.04, "learning_rate": 2.9396353482260184e-05, "loss": 2.1763, "step": 250 }, { "epoch": 0.04, "learning_rate": 2.939388961892247e-05, "loss": 1.0615, "step": 251 }, { "epoch": 0.04, "learning_rate": 2.939142575558476e-05, "loss": 0.6544, "step": 252 }, { "epoch": 0.04, "learning_rate": 2.9388961892247044e-05, "loss": 1.2969, "step": 253 }, { "epoch": 0.04, "learning_rate": 2.938649802890933e-05, "loss": 1.7233, "step": 254 }, { "epoch": 0.04, "learning_rate": 2.9384034165571615e-05, "loss": 1.6714, "step": 255 }, { "epoch": 0.04, "learning_rate": 2.9381570302233903e-05, "loss": 1.2242, "step": 256 }, { "epoch": 0.04, "learning_rate": 2.937910643889619e-05, "loss": 1.1217, "step": 257 }, { "epoch": 0.04, "learning_rate": 2.9376642575558475e-05, "loss": 0.892, "step": 258 }, { "epoch": 0.04, "learning_rate": 2.9374178712220763e-05, "loss": 1.5419, "step": 259 }, { "epoch": 0.04, "learning_rate": 2.9374178712220763e-05, "loss": 1.2492, "step": 260 }, { "epoch": 0.04, "learning_rate": 2.9371714848883047e-05, "loss": 1.5849, "step": 261 }, { "epoch": 0.04, "learning_rate": 2.9369250985545338e-05, "loss": 1.4199, "step": 262 }, { "epoch": 0.04, "learning_rate": 2.9366787122207622e-05, "loss": 1.0445, "step": 263 }, { "epoch": 0.04, "learning_rate": 2.936432325886991e-05, "loss": 1.9365, "step": 264 }, { "epoch": 0.04, "learning_rate": 2.9361859395532194e-05, "loss": 2.0008, "step": 265 }, { "epoch": 0.04, "learning_rate": 2.9359395532194482e-05, "loss": 0.9934, "step": 266 }, { "epoch": 0.04, "learning_rate": 2.9356931668856766e-05, "loss": 1.3184, "step": 267 }, { "epoch": 0.04, "learning_rate": 2.9354467805519054e-05, "loss": 1.8827, "step": 268 }, { "epoch": 0.04, "learning_rate": 2.9352003942181342e-05, "loss": 0.6761, "step": 269 }, { "epoch": 0.04, "learning_rate": 2.9349540078843626e-05, "loss": 0.7958, "step": 270 }, { "epoch": 0.04, "learning_rate": 2.9347076215505914e-05, "loss": 1.2786, "step": 271 }, { "epoch": 0.04, "learning_rate": 2.93446123521682e-05, "loss": 1.5218, "step": 272 }, { "epoch": 0.04, "learning_rate": 2.934214848883049e-05, "loss": 1.0812, "step": 273 }, { "epoch": 0.05, "learning_rate": 2.9339684625492773e-05, "loss": 0.854, "step": 274 }, { "epoch": 0.05, "learning_rate": 2.933722076215506e-05, "loss": 1.0649, "step": 275 }, { "epoch": 0.05, "learning_rate": 2.9334756898817345e-05, "loss": 1.1081, "step": 276 }, { "epoch": 0.05, "learning_rate": 2.9332293035479633e-05, "loss": 1.492, "step": 277 }, { "epoch": 0.05, "learning_rate": 2.9329829172141917e-05, "loss": 0.7702, "step": 278 }, { "epoch": 0.05, "learning_rate": 2.9327365308804205e-05, "loss": 2.3401, "step": 279 }, { "epoch": 0.05, "learning_rate": 2.9324901445466493e-05, "loss": 0.7919, "step": 280 }, { "epoch": 0.05, "learning_rate": 2.9322437582128777e-05, "loss": 1.2821, "step": 281 }, { "epoch": 0.05, "learning_rate": 2.9319973718791068e-05, "loss": 1.6744, "step": 282 }, { "epoch": 0.05, "learning_rate": 2.9317509855453352e-05, "loss": 1.4367, "step": 283 }, { "epoch": 0.05, "learning_rate": 2.931504599211564e-05, "loss": 0.7937, "step": 284 }, { "epoch": 0.05, "learning_rate": 2.9312582128777924e-05, "loss": 0.9165, "step": 285 }, { "epoch": 0.05, "learning_rate": 2.9310118265440212e-05, "loss": 1.5414, "step": 286 }, { "epoch": 0.05, "learning_rate": 2.9307654402102496e-05, "loss": 1.4382, "step": 287 }, { "epoch": 0.05, "learning_rate": 2.9305190538764784e-05, "loss": 1.2912, "step": 288 }, { "epoch": 0.05, "learning_rate": 2.9302726675427068e-05, "loss": 2.0542, "step": 289 }, { "epoch": 0.05, "learning_rate": 2.9300262812089356e-05, "loss": 1.285, "step": 290 }, { "epoch": 0.05, "learning_rate": 2.929779894875164e-05, "loss": 1.8859, "step": 291 }, { "epoch": 0.05, "learning_rate": 2.929533508541393e-05, "loss": 1.1253, "step": 292 }, { "epoch": 0.05, "learning_rate": 2.929287122207622e-05, "loss": 0.8511, "step": 293 }, { "epoch": 0.05, "learning_rate": 2.9290407358738503e-05, "loss": 1.0992, "step": 294 }, { "epoch": 0.05, "learning_rate": 2.928794349540079e-05, "loss": 1.7559, "step": 295 }, { "epoch": 0.05, "learning_rate": 2.9285479632063075e-05, "loss": 1.9301, "step": 296 }, { "epoch": 0.05, "learning_rate": 2.9283015768725363e-05, "loss": 1.629, "step": 297 }, { "epoch": 0.05, "learning_rate": 2.9280551905387647e-05, "loss": 1.0987, "step": 298 }, { "epoch": 0.05, "learning_rate": 2.9278088042049935e-05, "loss": 1.7741, "step": 299 }, { "epoch": 0.05, "learning_rate": 2.927562417871222e-05, "loss": 1.3351, "step": 300 }, { "epoch": 0.05, "learning_rate": 2.9273160315374507e-05, "loss": 0.9433, "step": 301 }, { "epoch": 0.05, "learning_rate": 2.9270696452036794e-05, "loss": 1.0657, "step": 302 }, { "epoch": 0.05, "learning_rate": 2.9268232588699082e-05, "loss": 0.9794, "step": 303 }, { "epoch": 0.05, "learning_rate": 2.926576872536137e-05, "loss": 0.5483, "step": 304 }, { "epoch": 0.05, "learning_rate": 2.9263304862023654e-05, "loss": 1.0026, "step": 305 }, { "epoch": 0.05, "learning_rate": 2.9260840998685942e-05, "loss": 0.9974, "step": 306 }, { "epoch": 0.05, "learning_rate": 2.9258377135348226e-05, "loss": 0.432, "step": 307 }, { "epoch": 0.05, "learning_rate": 2.9255913272010514e-05, "loss": 1.2962, "step": 308 }, { "epoch": 0.05, "learning_rate": 2.9253449408672798e-05, "loss": 0.8486, "step": 309 }, { "epoch": 0.05, "learning_rate": 2.9250985545335086e-05, "loss": 0.7695, "step": 310 }, { "epoch": 0.05, "learning_rate": 2.924852168199737e-05, "loss": 2.0453, "step": 311 }, { "epoch": 0.05, "learning_rate": 2.924605781865966e-05, "loss": 0.7856, "step": 312 }, { "epoch": 0.05, "learning_rate": 2.9243593955321945e-05, "loss": 0.9886, "step": 313 }, { "epoch": 0.05, "learning_rate": 2.9241130091984233e-05, "loss": 1.6088, "step": 314 }, { "epoch": 0.05, "learning_rate": 2.9238666228646517e-05, "loss": 0.8507, "step": 315 }, { "epoch": 0.05, "learning_rate": 2.9236202365308805e-05, "loss": 0.6214, "step": 316 }, { "epoch": 0.05, "learning_rate": 2.9233738501971093e-05, "loss": 1.7678, "step": 317 }, { "epoch": 0.05, "learning_rate": 2.9231274638633377e-05, "loss": 0.7283, "step": 318 }, { "epoch": 0.05, "learning_rate": 2.9228810775295665e-05, "loss": 1.1133, "step": 319 }, { "epoch": 0.05, "learning_rate": 2.922634691195795e-05, "loss": 0.7142, "step": 320 }, { "epoch": 0.05, "learning_rate": 2.9223883048620237e-05, "loss": 1.2425, "step": 321 }, { "epoch": 0.05, "learning_rate": 2.9221419185282524e-05, "loss": 1.6269, "step": 322 }, { "epoch": 0.05, "learning_rate": 2.9218955321944812e-05, "loss": 1.2296, "step": 323 }, { "epoch": 0.05, "learning_rate": 2.9216491458607096e-05, "loss": 1.05, "step": 324 }, { "epoch": 0.05, "learning_rate": 2.9214027595269384e-05, "loss": 1.2589, "step": 325 }, { "epoch": 0.05, "learning_rate": 2.9211563731931668e-05, "loss": 1.4605, "step": 326 }, { "epoch": 0.05, "learning_rate": 2.9209099868593956e-05, "loss": 1.6695, "step": 327 }, { "epoch": 0.05, "learning_rate": 2.9206636005256244e-05, "loss": 1.4938, "step": 328 }, { "epoch": 0.05, "learning_rate": 2.9204172141918528e-05, "loss": 1.9297, "step": 329 }, { "epoch": 0.05, "learning_rate": 2.9201708278580816e-05, "loss": 0.8367, "step": 330 }, { "epoch": 0.05, "learning_rate": 2.91992444152431e-05, "loss": 0.8591, "step": 331 }, { "epoch": 0.05, "learning_rate": 2.919678055190539e-05, "loss": 2.0879, "step": 332 }, { "epoch": 0.05, "learning_rate": 2.9194316688567675e-05, "loss": 0.7472, "step": 333 }, { "epoch": 0.05, "learning_rate": 2.9191852825229963e-05, "loss": 1.518, "step": 334 }, { "epoch": 0.06, "learning_rate": 2.9189388961892247e-05, "loss": 0.651, "step": 335 }, { "epoch": 0.06, "learning_rate": 2.9186925098554535e-05, "loss": 1.299, "step": 336 }, { "epoch": 0.06, "learning_rate": 2.918446123521682e-05, "loss": 1.4712, "step": 337 }, { "epoch": 0.06, "learning_rate": 2.9181997371879107e-05, "loss": 1.5481, "step": 338 }, { "epoch": 0.06, "learning_rate": 2.917953350854139e-05, "loss": 1.6309, "step": 339 }, { "epoch": 0.06, "learning_rate": 2.917706964520368e-05, "loss": 1.3014, "step": 340 }, { "epoch": 0.06, "learning_rate": 2.9174605781865967e-05, "loss": 1.2697, "step": 341 }, { "epoch": 0.06, "learning_rate": 2.9172141918528254e-05, "loss": 1.6237, "step": 342 }, { "epoch": 0.06, "learning_rate": 2.9169678055190542e-05, "loss": 1.624, "step": 343 }, { "epoch": 0.06, "learning_rate": 2.9167214191852826e-05, "loss": 0.6345, "step": 344 }, { "epoch": 0.06, "learning_rate": 2.9164750328515114e-05, "loss": 0.9934, "step": 345 }, { "epoch": 0.06, "learning_rate": 2.9162286465177398e-05, "loss": 1.1848, "step": 346 }, { "epoch": 0.06, "learning_rate": 2.9159822601839686e-05, "loss": 1.6846, "step": 347 }, { "epoch": 0.06, "learning_rate": 2.915735873850197e-05, "loss": 1.7252, "step": 348 }, { "epoch": 0.06, "learning_rate": 2.9154894875164258e-05, "loss": 1.5484, "step": 349 }, { "epoch": 0.06, "learning_rate": 2.9152431011826542e-05, "loss": 0.9007, "step": 350 }, { "epoch": 0.06, "learning_rate": 2.914996714848883e-05, "loss": 1.7089, "step": 351 }, { "epoch": 0.06, "learning_rate": 2.914750328515112e-05, "loss": 1.1894, "step": 352 }, { "epoch": 0.06, "learning_rate": 2.9145039421813405e-05, "loss": 0.851, "step": 353 }, { "epoch": 0.06, "learning_rate": 2.9142575558475693e-05, "loss": 0.8944, "step": 354 }, { "epoch": 0.06, "learning_rate": 2.9140111695137977e-05, "loss": 0.9075, "step": 355 }, { "epoch": 0.06, "learning_rate": 2.9137647831800265e-05, "loss": 0.7797, "step": 356 }, { "epoch": 0.06, "learning_rate": 2.913518396846255e-05, "loss": 1.1206, "step": 357 }, { "epoch": 0.06, "learning_rate": 2.9132720105124837e-05, "loss": 0.8099, "step": 358 }, { "epoch": 0.06, "learning_rate": 2.913025624178712e-05, "loss": 1.4334, "step": 359 }, { "epoch": 0.06, "learning_rate": 2.912779237844941e-05, "loss": 1.1721, "step": 360 }, { "epoch": 0.06, "learning_rate": 2.9125328515111693e-05, "loss": 0.6484, "step": 361 }, { "epoch": 0.06, "learning_rate": 2.9122864651773984e-05, "loss": 1.7553, "step": 362 }, { "epoch": 0.06, "learning_rate": 2.912040078843627e-05, "loss": 1.2432, "step": 363 }, { "epoch": 0.06, "learning_rate": 2.9117936925098556e-05, "loss": 1.3628, "step": 364 }, { "epoch": 0.06, "learning_rate": 2.9115473061760844e-05, "loss": 1.6864, "step": 365 }, { "epoch": 0.06, "learning_rate": 2.9113009198423128e-05, "loss": 1.7139, "step": 366 }, { "epoch": 0.06, "learning_rate": 2.9110545335085416e-05, "loss": 1.0931, "step": 367 }, { "epoch": 0.06, "learning_rate": 2.91080814717477e-05, "loss": 0.9533, "step": 368 }, { "epoch": 0.06, "learning_rate": 2.9105617608409988e-05, "loss": 1.496, "step": 369 }, { "epoch": 0.06, "learning_rate": 2.9103153745072272e-05, "loss": 1.4205, "step": 370 }, { "epoch": 0.06, "learning_rate": 2.910068988173456e-05, "loss": 1.1171, "step": 371 }, { "epoch": 0.06, "learning_rate": 2.9098226018396847e-05, "loss": 1.6028, "step": 372 }, { "epoch": 0.06, "learning_rate": 2.9095762155059135e-05, "loss": 1.4397, "step": 373 }, { "epoch": 0.06, "learning_rate": 2.909329829172142e-05, "loss": 0.8734, "step": 374 }, { "epoch": 0.06, "learning_rate": 2.9090834428383707e-05, "loss": 1.0934, "step": 375 }, { "epoch": 0.06, "learning_rate": 2.9088370565045995e-05, "loss": 1.4256, "step": 376 }, { "epoch": 0.06, "learning_rate": 2.908590670170828e-05, "loss": 1.0201, "step": 377 }, { "epoch": 0.06, "learning_rate": 2.9083442838370567e-05, "loss": 1.4259, "step": 378 }, { "epoch": 0.06, "learning_rate": 2.908097897503285e-05, "loss": 1.4806, "step": 379 }, { "epoch": 0.06, "learning_rate": 2.907851511169514e-05, "loss": 1.2875, "step": 380 }, { "epoch": 0.06, "learning_rate": 2.9076051248357423e-05, "loss": 1.3134, "step": 381 }, { "epoch": 0.06, "learning_rate": 2.9073587385019714e-05, "loss": 1.3721, "step": 382 }, { "epoch": 0.06, "learning_rate": 2.9071123521681998e-05, "loss": 1.2902, "step": 383 }, { "epoch": 0.06, "learning_rate": 2.9068659658344286e-05, "loss": 1.1563, "step": 384 }, { "epoch": 0.06, "learning_rate": 2.906619579500657e-05, "loss": 1.452, "step": 385 }, { "epoch": 0.06, "learning_rate": 2.9063731931668858e-05, "loss": 1.383, "step": 386 }, { "epoch": 0.06, "learning_rate": 2.9061268068331142e-05, "loss": 0.9398, "step": 387 }, { "epoch": 0.06, "learning_rate": 2.905880420499343e-05, "loss": 1.3311, "step": 388 }, { "epoch": 0.06, "learning_rate": 2.9056340341655717e-05, "loss": 1.4402, "step": 389 }, { "epoch": 0.06, "learning_rate": 2.9053876478318002e-05, "loss": 0.7577, "step": 390 }, { "epoch": 0.06, "learning_rate": 2.905141261498029e-05, "loss": 1.3753, "step": 391 }, { "epoch": 0.06, "learning_rate": 2.9048948751642577e-05, "loss": 1.2924, "step": 392 }, { "epoch": 0.06, "learning_rate": 2.9046484888304865e-05, "loss": 1.0436, "step": 393 }, { "epoch": 0.06, "learning_rate": 2.904402102496715e-05, "loss": 0.9178, "step": 394 }, { "epoch": 0.06, "learning_rate": 2.9041557161629437e-05, "loss": 1.6917, "step": 395 }, { "epoch": 0.07, "learning_rate": 2.903909329829172e-05, "loss": 1.3887, "step": 396 }, { "epoch": 0.07, "learning_rate": 2.903662943495401e-05, "loss": 1.2219, "step": 397 }, { "epoch": 0.07, "learning_rate": 2.9034165571616293e-05, "loss": 1.0642, "step": 398 }, { "epoch": 0.07, "learning_rate": 2.903170170827858e-05, "loss": 1.2995, "step": 399 }, { "epoch": 0.07, "learning_rate": 2.902923784494087e-05, "loss": 1.1754, "step": 400 }, { "epoch": 0.07, "learning_rate": 2.9026773981603153e-05, "loss": 0.6427, "step": 401 }, { "epoch": 0.07, "learning_rate": 2.9024310118265444e-05, "loss": 1.0766, "step": 402 }, { "epoch": 0.07, "learning_rate": 2.9021846254927728e-05, "loss": 1.5193, "step": 403 }, { "epoch": 0.07, "learning_rate": 2.9019382391590016e-05, "loss": 1.0774, "step": 404 }, { "epoch": 0.07, "learning_rate": 2.90169185282523e-05, "loss": 1.0513, "step": 405 }, { "epoch": 0.07, "learning_rate": 2.9014454664914588e-05, "loss": 0.7174, "step": 406 }, { "epoch": 0.07, "learning_rate": 2.9011990801576872e-05, "loss": 1.1822, "step": 407 }, { "epoch": 0.07, "learning_rate": 2.900952693823916e-05, "loss": 0.6466, "step": 408 }, { "epoch": 0.07, "learning_rate": 2.9007063074901444e-05, "loss": 0.7274, "step": 409 }, { "epoch": 0.07, "learning_rate": 2.900459921156373e-05, "loss": 0.7577, "step": 410 }, { "epoch": 0.07, "learning_rate": 2.900213534822602e-05, "loss": 1.3084, "step": 411 }, { "epoch": 0.07, "learning_rate": 2.8999671484888307e-05, "loss": 0.9318, "step": 412 }, { "epoch": 0.07, "learning_rate": 2.8997207621550595e-05, "loss": 2.5401, "step": 413 }, { "epoch": 0.07, "learning_rate": 2.899474375821288e-05, "loss": 1.2108, "step": 414 }, { "epoch": 0.07, "learning_rate": 2.8992279894875167e-05, "loss": 1.8027, "step": 415 }, { "epoch": 0.07, "learning_rate": 2.898981603153745e-05, "loss": 1.1708, "step": 416 }, { "epoch": 0.07, "learning_rate": 2.898735216819974e-05, "loss": 1.2507, "step": 417 }, { "epoch": 0.07, "learning_rate": 2.8984888304862023e-05, "loss": 0.6022, "step": 418 }, { "epoch": 0.07, "learning_rate": 2.898242444152431e-05, "loss": 0.479, "step": 419 }, { "epoch": 0.07, "learning_rate": 2.8979960578186595e-05, "loss": 1.6475, "step": 420 }, { "epoch": 0.07, "learning_rate": 2.8977496714848883e-05, "loss": 1.0561, "step": 421 }, { "epoch": 0.07, "learning_rate": 2.897503285151117e-05, "loss": 1.4836, "step": 422 }, { "epoch": 0.07, "learning_rate": 2.8972568988173458e-05, "loss": 1.1845, "step": 423 }, { "epoch": 0.07, "learning_rate": 2.8970105124835746e-05, "loss": 1.468, "step": 424 }, { "epoch": 0.07, "learning_rate": 2.896764126149803e-05, "loss": 0.979, "step": 425 }, { "epoch": 0.07, "learning_rate": 2.8965177398160318e-05, "loss": 1.5559, "step": 426 }, { "epoch": 0.07, "learning_rate": 2.8962713534822602e-05, "loss": 1.3856, "step": 427 }, { "epoch": 0.07, "learning_rate": 2.896024967148489e-05, "loss": 1.2274, "step": 428 }, { "epoch": 0.07, "learning_rate": 2.8957785808147174e-05, "loss": 0.922, "step": 429 }, { "epoch": 0.07, "learning_rate": 2.895532194480946e-05, "loss": 1.3715, "step": 430 }, { "epoch": 0.07, "learning_rate": 2.8952858081471746e-05, "loss": 1.21, "step": 431 }, { "epoch": 0.07, "learning_rate": 2.8950394218134037e-05, "loss": 0.9414, "step": 432 }, { "epoch": 0.07, "learning_rate": 2.894793035479632e-05, "loss": 1.0718, "step": 433 }, { "epoch": 0.07, "learning_rate": 2.894546649145861e-05, "loss": 0.7604, "step": 434 }, { "epoch": 0.07, "learning_rate": 2.8943002628120897e-05, "loss": 0.9877, "step": 435 }, { "epoch": 0.07, "learning_rate": 2.894053876478318e-05, "loss": 0.5179, "step": 436 }, { "epoch": 0.07, "learning_rate": 2.893807490144547e-05, "loss": 1.1629, "step": 437 }, { "epoch": 0.07, "learning_rate": 2.8935611038107753e-05, "loss": 0.7465, "step": 438 }, { "epoch": 0.07, "learning_rate": 2.893314717477004e-05, "loss": 0.8319, "step": 439 }, { "epoch": 0.07, "learning_rate": 2.8930683311432325e-05, "loss": 0.779, "step": 440 }, { "epoch": 0.07, "learning_rate": 2.8928219448094612e-05, "loss": 1.0111, "step": 441 }, { "epoch": 0.07, "learning_rate": 2.89257555847569e-05, "loss": 0.9458, "step": 442 }, { "epoch": 0.07, "learning_rate": 2.8923291721419188e-05, "loss": 0.8105, "step": 443 }, { "epoch": 0.07, "learning_rate": 2.8920827858081472e-05, "loss": 1.47, "step": 444 }, { "epoch": 0.07, "learning_rate": 2.891836399474376e-05, "loss": 1.9379, "step": 445 }, { "epoch": 0.07, "learning_rate": 2.8915900131406044e-05, "loss": 2.2176, "step": 446 }, { "epoch": 0.07, "learning_rate": 2.8913436268068332e-05, "loss": 0.9009, "step": 447 }, { "epoch": 0.07, "learning_rate": 2.891097240473062e-05, "loss": 1.3305, "step": 448 }, { "epoch": 0.07, "learning_rate": 2.8908508541392904e-05, "loss": 1.2928, "step": 449 }, { "epoch": 0.07, "learning_rate": 2.890604467805519e-05, "loss": 1.0957, "step": 450 }, { "epoch": 0.07, "learning_rate": 2.8903580814717476e-05, "loss": 1.0203, "step": 451 }, { "epoch": 0.07, "learning_rate": 2.8901116951379767e-05, "loss": 0.7857, "step": 452 }, { "epoch": 0.07, "learning_rate": 2.889865308804205e-05, "loss": 1.826, "step": 453 }, { "epoch": 0.07, "learning_rate": 2.889618922470434e-05, "loss": 1.2642, "step": 454 }, { "epoch": 0.07, "learning_rate": 2.8893725361366623e-05, "loss": 1.4957, "step": 455 }, { "epoch": 0.07, "learning_rate": 2.889126149802891e-05, "loss": 0.9562, "step": 456 }, { "epoch": 0.08, "learning_rate": 2.8888797634691195e-05, "loss": 0.7878, "step": 457 }, { "epoch": 0.08, "learning_rate": 2.8886333771353483e-05, "loss": 1.6215, "step": 458 }, { "epoch": 0.08, "learning_rate": 2.888386990801577e-05, "loss": 1.4139, "step": 459 }, { "epoch": 0.08, "learning_rate": 2.8881406044678055e-05, "loss": 1.127, "step": 460 }, { "epoch": 0.08, "learning_rate": 2.8878942181340342e-05, "loss": 1.0329, "step": 461 }, { "epoch": 0.08, "learning_rate": 2.887647831800263e-05, "loss": 1.0333, "step": 462 }, { "epoch": 0.08, "learning_rate": 2.8874014454664918e-05, "loss": 0.782, "step": 463 }, { "epoch": 0.08, "learning_rate": 2.8871550591327202e-05, "loss": 2.1639, "step": 464 }, { "epoch": 0.08, "learning_rate": 2.886908672798949e-05, "loss": 1.3169, "step": 465 }, { "epoch": 0.08, "learning_rate": 2.8866622864651774e-05, "loss": 0.7861, "step": 466 }, { "epoch": 0.08, "learning_rate": 2.886415900131406e-05, "loss": 1.8341, "step": 467 }, { "epoch": 0.08, "learning_rate": 2.8861695137976346e-05, "loss": 1.4203, "step": 468 }, { "epoch": 0.08, "learning_rate": 2.8859231274638634e-05, "loss": 0.8094, "step": 469 }, { "epoch": 0.08, "learning_rate": 2.8856767411300918e-05, "loss": 1.8007, "step": 470 }, { "epoch": 0.08, "learning_rate": 2.8854303547963206e-05, "loss": 0.8305, "step": 471 }, { "epoch": 0.08, "learning_rate": 2.8851839684625497e-05, "loss": 1.2837, "step": 472 }, { "epoch": 0.08, "learning_rate": 2.884937582128778e-05, "loss": 1.1394, "step": 473 }, { "epoch": 0.08, "learning_rate": 2.884691195795007e-05, "loss": 1.1518, "step": 474 }, { "epoch": 0.08, "learning_rate": 2.8844448094612353e-05, "loss": 1.9021, "step": 475 }, { "epoch": 0.08, "learning_rate": 2.884198423127464e-05, "loss": 1.2336, "step": 476 }, { "epoch": 0.08, "learning_rate": 2.8839520367936925e-05, "loss": 1.4569, "step": 477 }, { "epoch": 0.08, "learning_rate": 2.8837056504599212e-05, "loss": 1.5745, "step": 478 }, { "epoch": 0.08, "learning_rate": 2.8834592641261497e-05, "loss": 1.4622, "step": 479 }, { "epoch": 0.08, "learning_rate": 2.8832128777923784e-05, "loss": 1.2522, "step": 480 }, { "epoch": 0.08, "learning_rate": 2.882966491458607e-05, "loss": 0.8936, "step": 481 }, { "epoch": 0.08, "learning_rate": 2.882720105124836e-05, "loss": 0.8593, "step": 482 }, { "epoch": 0.08, "learning_rate": 2.8824737187910647e-05, "loss": 1.3308, "step": 483 }, { "epoch": 0.08, "learning_rate": 2.8822273324572932e-05, "loss": 1.1284, "step": 484 }, { "epoch": 0.08, "learning_rate": 2.881980946123522e-05, "loss": 1.5149, "step": 485 }, { "epoch": 0.08, "learning_rate": 2.8817345597897504e-05, "loss": 1.1512, "step": 486 }, { "epoch": 0.08, "learning_rate": 2.881488173455979e-05, "loss": 0.7396, "step": 487 }, { "epoch": 0.08, "learning_rate": 2.8812417871222076e-05, "loss": 1.237, "step": 488 }, { "epoch": 0.08, "learning_rate": 2.8809954007884363e-05, "loss": 0.7245, "step": 489 }, { "epoch": 0.08, "learning_rate": 2.8807490144546648e-05, "loss": 1.4718, "step": 490 }, { "epoch": 0.08, "learning_rate": 2.8805026281208935e-05, "loss": 1.6235, "step": 491 }, { "epoch": 0.08, "learning_rate": 2.8802562417871223e-05, "loss": 0.9615, "step": 492 }, { "epoch": 0.08, "learning_rate": 2.880009855453351e-05, "loss": 1.2731, "step": 493 }, { "epoch": 0.08, "learning_rate": 2.8797634691195795e-05, "loss": 1.0147, "step": 494 }, { "epoch": 0.08, "learning_rate": 2.8795170827858083e-05, "loss": 0.9899, "step": 495 }, { "epoch": 0.08, "learning_rate": 2.879270696452037e-05, "loss": 0.9457, "step": 496 }, { "epoch": 0.08, "learning_rate": 2.8790243101182655e-05, "loss": 1.0697, "step": 497 }, { "epoch": 0.08, "learning_rate": 2.8787779237844942e-05, "loss": 1.4996, "step": 498 }, { "epoch": 0.08, "learning_rate": 2.8785315374507227e-05, "loss": 0.5988, "step": 499 }, { "epoch": 0.08, "learning_rate": 2.8782851511169514e-05, "loss": 0.9739, "step": 500 }, { "epoch": 0.08, "eval_exact_match": 79.38505203405866, "eval_f1": 87.64995975938528, "step": 500 }, { "epoch": 0.08, "learning_rate": 2.87803876478318e-05, "loss": 1.0745, "step": 501 }, { "epoch": 0.08, "learning_rate": 2.877792378449409e-05, "loss": 1.0376, "step": 502 }, { "epoch": 0.08, "learning_rate": 2.8775459921156374e-05, "loss": 1.1992, "step": 503 }, { "epoch": 0.08, "learning_rate": 2.877299605781866e-05, "loss": 1.0653, "step": 504 }, { "epoch": 0.08, "learning_rate": 2.8770532194480946e-05, "loss": 1.1274, "step": 505 }, { "epoch": 0.08, "learning_rate": 2.8768068331143234e-05, "loss": 0.7093, "step": 506 }, { "epoch": 0.08, "learning_rate": 2.876560446780552e-05, "loss": 0.9284, "step": 507 }, { "epoch": 0.08, "learning_rate": 2.8763140604467806e-05, "loss": 1.1819, "step": 508 }, { "epoch": 0.08, "learning_rate": 2.8760676741130093e-05, "loss": 1.7536, "step": 509 }, { "epoch": 0.08, "learning_rate": 2.8758212877792378e-05, "loss": 1.041, "step": 510 }, { "epoch": 0.08, "learning_rate": 2.8755749014454665e-05, "loss": 0.9445, "step": 511 }, { "epoch": 0.08, "learning_rate": 2.8753285151116953e-05, "loss": 1.5631, "step": 512 }, { "epoch": 0.08, "learning_rate": 2.875082128777924e-05, "loss": 1.5261, "step": 513 }, { "epoch": 0.08, "learning_rate": 2.8748357424441525e-05, "loss": 0.8104, "step": 514 }, { "epoch": 0.08, "learning_rate": 2.8745893561103813e-05, "loss": 0.6957, "step": 515 }, { "epoch": 0.08, "learning_rate": 2.8743429697766097e-05, "loss": 0.82, "step": 516 }, { "epoch": 0.08, "learning_rate": 2.8740965834428385e-05, "loss": 1.4663, "step": 517 }, { "epoch": 0.09, "learning_rate": 2.873850197109067e-05, "loss": 0.9377, "step": 518 }, { "epoch": 0.09, "learning_rate": 2.8736038107752956e-05, "loss": 1.6736, "step": 519 }, { "epoch": 0.09, "learning_rate": 2.8733574244415244e-05, "loss": 1.4062, "step": 520 }, { "epoch": 0.09, "learning_rate": 2.873111038107753e-05, "loss": 1.1679, "step": 521 }, { "epoch": 0.09, "learning_rate": 2.872864651773982e-05, "loss": 1.3227, "step": 522 }, { "epoch": 0.09, "learning_rate": 2.8726182654402104e-05, "loss": 1.2534, "step": 523 }, { "epoch": 0.09, "learning_rate": 2.872371879106439e-05, "loss": 1.0301, "step": 524 }, { "epoch": 0.09, "learning_rate": 2.8721254927726676e-05, "loss": 1.1136, "step": 525 }, { "epoch": 0.09, "learning_rate": 2.8718791064388963e-05, "loss": 1.5083, "step": 526 }, { "epoch": 0.09, "learning_rate": 2.8716327201051248e-05, "loss": 1.5336, "step": 527 }, { "epoch": 0.09, "learning_rate": 2.8713863337713535e-05, "loss": 1.1044, "step": 528 }, { "epoch": 0.09, "learning_rate": 2.871139947437582e-05, "loss": 0.8156, "step": 529 }, { "epoch": 0.09, "learning_rate": 2.8708935611038107e-05, "loss": 0.7987, "step": 530 }, { "epoch": 0.09, "learning_rate": 2.8706471747700395e-05, "loss": 1.1491, "step": 531 }, { "epoch": 0.09, "learning_rate": 2.8704007884362683e-05, "loss": 0.7182, "step": 532 }, { "epoch": 0.09, "learning_rate": 2.870154402102497e-05, "loss": 1.3494, "step": 533 }, { "epoch": 0.09, "learning_rate": 2.8699080157687255e-05, "loss": 1.0979, "step": 534 }, { "epoch": 0.09, "learning_rate": 2.8696616294349542e-05, "loss": 0.8254, "step": 535 }, { "epoch": 0.09, "learning_rate": 2.8694152431011827e-05, "loss": 0.7137, "step": 536 }, { "epoch": 0.09, "learning_rate": 2.8691688567674114e-05, "loss": 1.026, "step": 537 }, { "epoch": 0.09, "learning_rate": 2.86892247043364e-05, "loss": 0.5062, "step": 538 }, { "epoch": 0.09, "learning_rate": 2.8686760840998686e-05, "loss": 1.5282, "step": 539 }, { "epoch": 0.09, "learning_rate": 2.868429697766097e-05, "loss": 0.5695, "step": 540 }, { "epoch": 0.09, "learning_rate": 2.8681833114323258e-05, "loss": 1.1712, "step": 541 }, { "epoch": 0.09, "learning_rate": 2.8679369250985546e-05, "loss": 0.9216, "step": 542 }, { "epoch": 0.09, "learning_rate": 2.8676905387647834e-05, "loss": 1.5995, "step": 543 }, { "epoch": 0.09, "learning_rate": 2.867444152431012e-05, "loss": 1.3558, "step": 544 }, { "epoch": 0.09, "learning_rate": 2.8671977660972406e-05, "loss": 1.8332, "step": 545 }, { "epoch": 0.09, "learning_rate": 2.8669513797634693e-05, "loss": 2.0461, "step": 546 }, { "epoch": 0.09, "learning_rate": 2.8667049934296978e-05, "loss": 1.0855, "step": 547 }, { "epoch": 0.09, "learning_rate": 2.8664586070959265e-05, "loss": 2.0104, "step": 548 }, { "epoch": 0.09, "learning_rate": 2.866212220762155e-05, "loss": 0.6853, "step": 549 }, { "epoch": 0.09, "learning_rate": 2.8659658344283837e-05, "loss": 1.5134, "step": 550 }, { "epoch": 0.09, "learning_rate": 2.865719448094612e-05, "loss": 0.8178, "step": 551 }, { "epoch": 0.09, "learning_rate": 2.8654730617608413e-05, "loss": 0.9337, "step": 552 }, { "epoch": 0.09, "learning_rate": 2.8652266754270697e-05, "loss": 0.7919, "step": 553 }, { "epoch": 0.09, "learning_rate": 2.8649802890932985e-05, "loss": 0.8846, "step": 554 }, { "epoch": 0.09, "learning_rate": 2.8647339027595272e-05, "loss": 0.6042, "step": 555 }, { "epoch": 0.09, "learning_rate": 2.8644875164257557e-05, "loss": 0.9714, "step": 556 }, { "epoch": 0.09, "learning_rate": 2.8642411300919844e-05, "loss": 1.7974, "step": 557 }, { "epoch": 0.09, "learning_rate": 2.863994743758213e-05, "loss": 1.2991, "step": 558 }, { "epoch": 0.09, "learning_rate": 2.8637483574244416e-05, "loss": 1.4016, "step": 559 }, { "epoch": 0.09, "learning_rate": 2.86350197109067e-05, "loss": 0.6895, "step": 560 }, { "epoch": 0.09, "learning_rate": 2.8632555847568988e-05, "loss": 1.0007, "step": 561 }, { "epoch": 0.09, "learning_rate": 2.8630091984231276e-05, "loss": 0.8729, "step": 562 }, { "epoch": 0.09, "learning_rate": 2.8627628120893564e-05, "loss": 0.5946, "step": 563 }, { "epoch": 0.09, "learning_rate": 2.8625164257555848e-05, "loss": 1.166, "step": 564 }, { "epoch": 0.09, "learning_rate": 2.8622700394218135e-05, "loss": 1.3096, "step": 565 }, { "epoch": 0.09, "learning_rate": 2.8620236530880423e-05, "loss": 1.0597, "step": 566 }, { "epoch": 0.09, "learning_rate": 2.8617772667542707e-05, "loss": 2.3586, "step": 567 }, { "epoch": 0.09, "learning_rate": 2.8615308804204995e-05, "loss": 0.8027, "step": 568 }, { "epoch": 0.09, "learning_rate": 2.861284494086728e-05, "loss": 1.027, "step": 569 }, { "epoch": 0.09, "learning_rate": 2.8610381077529567e-05, "loss": 1.403, "step": 570 }, { "epoch": 0.09, "learning_rate": 2.860791721419185e-05, "loss": 0.5589, "step": 571 }, { "epoch": 0.09, "learning_rate": 2.8605453350854142e-05, "loss": 0.7614, "step": 572 }, { "epoch": 0.09, "learning_rate": 2.8602989487516427e-05, "loss": 1.1638, "step": 573 }, { "epoch": 0.09, "learning_rate": 2.8600525624178714e-05, "loss": 1.0349, "step": 574 }, { "epoch": 0.09, "learning_rate": 2.8598061760841e-05, "loss": 0.7175, "step": 575 }, { "epoch": 0.09, "learning_rate": 2.8595597897503286e-05, "loss": 0.8731, "step": 576 }, { "epoch": 0.09, "learning_rate": 2.859313403416557e-05, "loss": 1.1519, "step": 577 }, { "epoch": 0.09, "learning_rate": 2.859067017082786e-05, "loss": 1.4691, "step": 578 }, { "epoch": 0.1, "learning_rate": 2.8588206307490146e-05, "loss": 1.2039, "step": 579 }, { "epoch": 0.1, "learning_rate": 2.858574244415243e-05, "loss": 0.8241, "step": 580 }, { "epoch": 0.1, "learning_rate": 2.8583278580814718e-05, "loss": 0.798, "step": 581 }, { "epoch": 0.1, "learning_rate": 2.8580814717477006e-05, "loss": 1.179, "step": 582 }, { "epoch": 0.1, "learning_rate": 2.8578350854139293e-05, "loss": 1.0883, "step": 583 }, { "epoch": 0.1, "learning_rate": 2.8575886990801578e-05, "loss": 1.1698, "step": 584 }, { "epoch": 0.1, "learning_rate": 2.8573423127463865e-05, "loss": 0.6135, "step": 585 }, { "epoch": 0.1, "learning_rate": 2.857095926412615e-05, "loss": 0.7012, "step": 586 }, { "epoch": 0.1, "learning_rate": 2.8568495400788437e-05, "loss": 1.6529, "step": 587 }, { "epoch": 0.1, "learning_rate": 2.856603153745072e-05, "loss": 1.3329, "step": 588 }, { "epoch": 0.1, "learning_rate": 2.856356767411301e-05, "loss": 0.9488, "step": 589 }, { "epoch": 0.1, "learning_rate": 2.8561103810775297e-05, "loss": 1.0522, "step": 590 }, { "epoch": 0.1, "learning_rate": 2.855863994743758e-05, "loss": 1.3119, "step": 591 }, { "epoch": 0.1, "learning_rate": 2.8556176084099872e-05, "loss": 1.1279, "step": 592 }, { "epoch": 0.1, "learning_rate": 2.8553712220762157e-05, "loss": 0.8294, "step": 593 }, { "epoch": 0.1, "learning_rate": 2.8551248357424444e-05, "loss": 0.4553, "step": 594 }, { "epoch": 0.1, "learning_rate": 2.854878449408673e-05, "loss": 0.7791, "step": 595 }, { "epoch": 0.1, "learning_rate": 2.8546320630749016e-05, "loss": 1.1957, "step": 596 }, { "epoch": 0.1, "learning_rate": 2.85438567674113e-05, "loss": 1.0819, "step": 597 }, { "epoch": 0.1, "learning_rate": 2.8541392904073588e-05, "loss": 0.9647, "step": 598 }, { "epoch": 0.1, "learning_rate": 2.8538929040735873e-05, "loss": 1.2715, "step": 599 }, { "epoch": 0.1, "learning_rate": 2.853646517739816e-05, "loss": 1.6667, "step": 600 }, { "epoch": 0.1, "learning_rate": 2.8534001314060444e-05, "loss": 0.382, "step": 601 }, { "epoch": 0.1, "learning_rate": 2.8531537450722736e-05, "loss": 0.6628, "step": 602 }, { "epoch": 0.1, "learning_rate": 2.8529073587385023e-05, "loss": 1.3605, "step": 603 }, { "epoch": 0.1, "learning_rate": 2.8526609724047308e-05, "loss": 1.1038, "step": 604 }, { "epoch": 0.1, "learning_rate": 2.8524145860709595e-05, "loss": 1.0302, "step": 605 }, { "epoch": 0.1, "learning_rate": 2.852168199737188e-05, "loss": 0.6551, "step": 606 }, { "epoch": 0.1, "learning_rate": 2.8519218134034167e-05, "loss": 2.23, "step": 607 }, { "epoch": 0.1, "learning_rate": 2.851675427069645e-05, "loss": 1.0234, "step": 608 }, { "epoch": 0.1, "learning_rate": 2.851429040735874e-05, "loss": 1.6931, "step": 609 }, { "epoch": 0.1, "learning_rate": 2.8511826544021023e-05, "loss": 1.2517, "step": 610 }, { "epoch": 0.1, "learning_rate": 2.850936268068331e-05, "loss": 0.8677, "step": 611 }, { "epoch": 0.1, "learning_rate": 2.85068988173456e-05, "loss": 1.3373, "step": 612 }, { "epoch": 0.1, "learning_rate": 2.8504434954007886e-05, "loss": 1.1633, "step": 613 }, { "epoch": 0.1, "learning_rate": 2.8501971090670174e-05, "loss": 0.9405, "step": 614 }, { "epoch": 0.1, "learning_rate": 2.849950722733246e-05, "loss": 1.1589, "step": 615 }, { "epoch": 0.1, "learning_rate": 2.8497043363994746e-05, "loss": 0.792, "step": 616 }, { "epoch": 0.1, "learning_rate": 2.849457950065703e-05, "loss": 1.1573, "step": 617 }, { "epoch": 0.1, "learning_rate": 2.8492115637319318e-05, "loss": 1.0839, "step": 618 }, { "epoch": 0.1, "learning_rate": 2.8489651773981602e-05, "loss": 1.2012, "step": 619 }, { "epoch": 0.1, "learning_rate": 2.848718791064389e-05, "loss": 1.2754, "step": 620 }, { "epoch": 0.1, "learning_rate": 2.8484724047306174e-05, "loss": 0.9277, "step": 621 }, { "epoch": 0.1, "learning_rate": 2.8482260183968465e-05, "loss": 1.3732, "step": 622 }, { "epoch": 0.1, "learning_rate": 2.847979632063075e-05, "loss": 1.0452, "step": 623 }, { "epoch": 0.1, "learning_rate": 2.8477332457293037e-05, "loss": 1.4234, "step": 624 }, { "epoch": 0.1, "learning_rate": 2.847486859395532e-05, "loss": 1.4242, "step": 625 }, { "epoch": 0.1, "learning_rate": 2.847240473061761e-05, "loss": 1.4683, "step": 626 }, { "epoch": 0.1, "learning_rate": 2.8469940867279897e-05, "loss": 1.041, "step": 627 }, { "epoch": 0.1, "learning_rate": 2.846747700394218e-05, "loss": 1.0748, "step": 628 }, { "epoch": 0.1, "learning_rate": 2.846501314060447e-05, "loss": 0.4563, "step": 629 }, { "epoch": 0.1, "learning_rate": 2.8462549277266753e-05, "loss": 1.013, "step": 630 }, { "epoch": 0.1, "learning_rate": 2.846008541392904e-05, "loss": 1.6532, "step": 631 }, { "epoch": 0.1, "learning_rate": 2.845762155059133e-05, "loss": 1.0909, "step": 632 }, { "epoch": 0.1, "learning_rate": 2.8455157687253616e-05, "loss": 1.2641, "step": 633 }, { "epoch": 0.1, "learning_rate": 2.84526938239159e-05, "loss": 0.854, "step": 634 }, { "epoch": 0.1, "learning_rate": 2.8450229960578188e-05, "loss": 0.6238, "step": 635 }, { "epoch": 0.1, "learning_rate": 2.8447766097240473e-05, "loss": 1.674, "step": 636 }, { "epoch": 0.1, "learning_rate": 2.844530223390276e-05, "loss": 1.0773, "step": 637 }, { "epoch": 0.1, "learning_rate": 2.8442838370565048e-05, "loss": 1.3336, "step": 638 }, { "epoch": 0.1, "learning_rate": 2.8440374507227332e-05, "loss": 0.978, "step": 639 }, { "epoch": 0.11, "learning_rate": 2.843791064388962e-05, "loss": 1.4073, "step": 640 }, { "epoch": 0.11, "learning_rate": 2.8435446780551904e-05, "loss": 1.3689, "step": 641 }, { "epoch": 0.11, "learning_rate": 2.8432982917214195e-05, "loss": 0.4616, "step": 642 }, { "epoch": 0.11, "learning_rate": 2.843051905387648e-05, "loss": 1.3217, "step": 643 }, { "epoch": 0.11, "learning_rate": 2.8428055190538767e-05, "loss": 1.2428, "step": 644 }, { "epoch": 0.11, "learning_rate": 2.842559132720105e-05, "loss": 0.7807, "step": 645 }, { "epoch": 0.11, "learning_rate": 2.842312746386334e-05, "loss": 1.1457, "step": 646 }, { "epoch": 0.11, "learning_rate": 2.8420663600525623e-05, "loss": 1.7786, "step": 647 }, { "epoch": 0.11, "learning_rate": 2.841819973718791e-05, "loss": 1.0502, "step": 648 }, { "epoch": 0.11, "learning_rate": 2.8415735873850195e-05, "loss": 1.1133, "step": 649 }, { "epoch": 0.11, "learning_rate": 2.8413272010512483e-05, "loss": 0.7879, "step": 650 }, { "epoch": 0.11, "learning_rate": 2.841080814717477e-05, "loss": 0.7386, "step": 651 }, { "epoch": 0.11, "learning_rate": 2.840834428383706e-05, "loss": 1.0368, "step": 652 }, { "epoch": 0.11, "learning_rate": 2.8405880420499346e-05, "loss": 0.599, "step": 653 }, { "epoch": 0.11, "learning_rate": 2.840341655716163e-05, "loss": 0.5334, "step": 654 }, { "epoch": 0.11, "learning_rate": 2.8400952693823918e-05, "loss": 1.7335, "step": 655 }, { "epoch": 0.11, "learning_rate": 2.8398488830486202e-05, "loss": 0.8484, "step": 656 }, { "epoch": 0.11, "learning_rate": 2.839602496714849e-05, "loss": 1.4214, "step": 657 }, { "epoch": 0.11, "learning_rate": 2.8393561103810774e-05, "loss": 1.2177, "step": 658 }, { "epoch": 0.11, "learning_rate": 2.8391097240473062e-05, "loss": 0.6984, "step": 659 }, { "epoch": 0.11, "learning_rate": 2.8388633377135346e-05, "loss": 0.8878, "step": 660 }, { "epoch": 0.11, "learning_rate": 2.8386169513797634e-05, "loss": 1.3494, "step": 661 }, { "epoch": 0.11, "learning_rate": 2.8383705650459925e-05, "loss": 0.6979, "step": 662 }, { "epoch": 0.11, "learning_rate": 2.838124178712221e-05, "loss": 2.4061, "step": 663 }, { "epoch": 0.11, "learning_rate": 2.8378777923784497e-05, "loss": 1.6558, "step": 664 }, { "epoch": 0.11, "learning_rate": 2.837631406044678e-05, "loss": 1.6898, "step": 665 }, { "epoch": 0.11, "learning_rate": 2.837385019710907e-05, "loss": 1.7568, "step": 666 }, { "epoch": 0.11, "learning_rate": 2.8371386333771353e-05, "loss": 1.3831, "step": 667 }, { "epoch": 0.11, "learning_rate": 2.836892247043364e-05, "loss": 1.0639, "step": 668 }, { "epoch": 0.11, "learning_rate": 2.8366458607095925e-05, "loss": 0.4158, "step": 669 }, { "epoch": 0.11, "learning_rate": 2.8363994743758213e-05, "loss": 1.0783, "step": 670 }, { "epoch": 0.11, "learning_rate": 2.8361530880420497e-05, "loss": 0.6934, "step": 671 }, { "epoch": 0.11, "learning_rate": 2.835906701708279e-05, "loss": 0.8287, "step": 672 }, { "epoch": 0.11, "learning_rate": 2.8356603153745073e-05, "loss": 1.0721, "step": 673 }, { "epoch": 0.11, "learning_rate": 2.835413929040736e-05, "loss": 0.9159, "step": 674 }, { "epoch": 0.11, "learning_rate": 2.8351675427069648e-05, "loss": 0.7539, "step": 675 }, { "epoch": 0.11, "learning_rate": 2.8349211563731932e-05, "loss": 0.8435, "step": 676 }, { "epoch": 0.11, "learning_rate": 2.834674770039422e-05, "loss": 1.3055, "step": 677 }, { "epoch": 0.11, "learning_rate": 2.8344283837056504e-05, "loss": 0.778, "step": 678 }, { "epoch": 0.11, "learning_rate": 2.8341819973718792e-05, "loss": 0.8722, "step": 679 }, { "epoch": 0.11, "learning_rate": 2.8339356110381076e-05, "loss": 1.0712, "step": 680 }, { "epoch": 0.11, "learning_rate": 2.8336892247043364e-05, "loss": 1.8182, "step": 681 }, { "epoch": 0.11, "learning_rate": 2.833442838370565e-05, "loss": 1.5741, "step": 682 }, { "epoch": 0.11, "learning_rate": 2.833196452036794e-05, "loss": 0.9461, "step": 683 }, { "epoch": 0.11, "learning_rate": 2.8329500657030224e-05, "loss": 1.8381, "step": 684 }, { "epoch": 0.11, "learning_rate": 2.832703679369251e-05, "loss": 0.8687, "step": 685 }, { "epoch": 0.11, "learning_rate": 2.83245729303548e-05, "loss": 1.1072, "step": 686 }, { "epoch": 0.11, "learning_rate": 2.8322109067017083e-05, "loss": 0.429, "step": 687 }, { "epoch": 0.11, "learning_rate": 2.831964520367937e-05, "loss": 1.1305, "step": 688 }, { "epoch": 0.11, "learning_rate": 2.8317181340341655e-05, "loss": 0.8403, "step": 689 }, { "epoch": 0.11, "learning_rate": 2.8314717477003943e-05, "loss": 0.6914, "step": 690 }, { "epoch": 0.11, "learning_rate": 2.8312253613666227e-05, "loss": 0.6865, "step": 691 }, { "epoch": 0.11, "learning_rate": 2.8309789750328518e-05, "loss": 1.0129, "step": 692 }, { "epoch": 0.11, "learning_rate": 2.8307325886990802e-05, "loss": 2.6153, "step": 693 }, { "epoch": 0.11, "learning_rate": 2.830486202365309e-05, "loss": 2.2355, "step": 694 }, { "epoch": 0.11, "learning_rate": 2.8302398160315374e-05, "loss": 1.0352, "step": 695 }, { "epoch": 0.11, "learning_rate": 2.8299934296977662e-05, "loss": 1.248, "step": 696 }, { "epoch": 0.11, "learning_rate": 2.8297470433639946e-05, "loss": 1.2256, "step": 697 }, { "epoch": 0.11, "learning_rate": 2.8295006570302234e-05, "loss": 1.3105, "step": 698 }, { "epoch": 0.11, "learning_rate": 2.8292542706964522e-05, "loss": 0.9607, "step": 699 }, { "epoch": 0.11, "learning_rate": 2.8290078843626806e-05, "loss": 1.372, "step": 700 }, { "epoch": 0.12, "learning_rate": 2.8287614980289094e-05, "loss": 1.3448, "step": 701 }, { "epoch": 0.12, "learning_rate": 2.828515111695138e-05, "loss": 1.1603, "step": 702 }, { "epoch": 0.12, "learning_rate": 2.828268725361367e-05, "loss": 1.4955, "step": 703 }, { "epoch": 0.12, "learning_rate": 2.8280223390275953e-05, "loss": 0.5753, "step": 704 }, { "epoch": 0.12, "learning_rate": 2.827775952693824e-05, "loss": 1.3197, "step": 705 }, { "epoch": 0.12, "learning_rate": 2.8275295663600525e-05, "loss": 1.3707, "step": 706 }, { "epoch": 0.12, "learning_rate": 2.8272831800262813e-05, "loss": 1.2469, "step": 707 }, { "epoch": 0.12, "learning_rate": 2.8270367936925097e-05, "loss": 1.1443, "step": 708 }, { "epoch": 0.12, "learning_rate": 2.8267904073587385e-05, "loss": 1.2479, "step": 709 }, { "epoch": 0.12, "learning_rate": 2.8265440210249673e-05, "loss": 1.4, "step": 710 }, { "epoch": 0.12, "learning_rate": 2.8262976346911957e-05, "loss": 0.8158, "step": 711 }, { "epoch": 0.12, "learning_rate": 2.8260512483574248e-05, "loss": 1.4863, "step": 712 }, { "epoch": 0.12, "learning_rate": 2.8258048620236532e-05, "loss": 2.2667, "step": 713 }, { "epoch": 0.12, "learning_rate": 2.825558475689882e-05, "loss": 1.6604, "step": 714 }, { "epoch": 0.12, "learning_rate": 2.8253120893561104e-05, "loss": 1.4085, "step": 715 }, { "epoch": 0.12, "learning_rate": 2.8250657030223392e-05, "loss": 0.6341, "step": 716 }, { "epoch": 0.12, "learning_rate": 2.8248193166885676e-05, "loss": 0.669, "step": 717 }, { "epoch": 0.12, "learning_rate": 2.8245729303547964e-05, "loss": 0.5157, "step": 718 }, { "epoch": 0.12, "learning_rate": 2.8243265440210248e-05, "loss": 1.319, "step": 719 }, { "epoch": 0.12, "learning_rate": 2.8240801576872536e-05, "loss": 0.8693, "step": 720 }, { "epoch": 0.12, "learning_rate": 2.8238337713534824e-05, "loss": 1.0718, "step": 721 }, { "epoch": 0.12, "learning_rate": 2.823587385019711e-05, "loss": 0.7467, "step": 722 }, { "epoch": 0.12, "learning_rate": 2.82334099868594e-05, "loss": 1.385, "step": 723 }, { "epoch": 0.12, "learning_rate": 2.8230946123521683e-05, "loss": 1.0589, "step": 724 }, { "epoch": 0.12, "learning_rate": 2.822848226018397e-05, "loss": 1.5533, "step": 725 }, { "epoch": 0.12, "learning_rate": 2.8226018396846255e-05, "loss": 0.6746, "step": 726 }, { "epoch": 0.12, "learning_rate": 2.8223554533508543e-05, "loss": 1.8931, "step": 727 }, { "epoch": 0.12, "learning_rate": 2.8221090670170827e-05, "loss": 1.7458, "step": 728 }, { "epoch": 0.12, "learning_rate": 2.8218626806833115e-05, "loss": 0.9543, "step": 729 }, { "epoch": 0.12, "learning_rate": 2.82161629434954e-05, "loss": 1.2363, "step": 730 }, { "epoch": 0.12, "learning_rate": 2.8213699080157687e-05, "loss": 1.0461, "step": 731 }, { "epoch": 0.12, "learning_rate": 2.8211235216819975e-05, "loss": 1.0338, "step": 732 }, { "epoch": 0.12, "learning_rate": 2.8208771353482262e-05, "loss": 1.3699, "step": 733 }, { "epoch": 0.12, "learning_rate": 2.820630749014455e-05, "loss": 0.6414, "step": 734 }, { "epoch": 0.12, "learning_rate": 2.8203843626806834e-05, "loss": 1.0422, "step": 735 }, { "epoch": 0.12, "learning_rate": 2.8201379763469122e-05, "loss": 1.3628, "step": 736 }, { "epoch": 0.12, "learning_rate": 2.8198915900131406e-05, "loss": 0.8112, "step": 737 }, { "epoch": 0.12, "learning_rate": 2.8196452036793694e-05, "loss": 0.7378, "step": 738 }, { "epoch": 0.12, "learning_rate": 2.8193988173455978e-05, "loss": 1.0887, "step": 739 }, { "epoch": 0.12, "learning_rate": 2.8191524310118266e-05, "loss": 0.5235, "step": 740 }, { "epoch": 0.12, "learning_rate": 2.818906044678055e-05, "loss": 1.2785, "step": 741 }, { "epoch": 0.12, "learning_rate": 2.818659658344284e-05, "loss": 0.6517, "step": 742 }, { "epoch": 0.12, "learning_rate": 2.8184132720105125e-05, "loss": 1.1646, "step": 743 }, { "epoch": 0.12, "learning_rate": 2.8181668856767413e-05, "loss": 0.8699, "step": 744 }, { "epoch": 0.12, "learning_rate": 2.81792049934297e-05, "loss": 1.7102, "step": 745 }, { "epoch": 0.12, "learning_rate": 2.8176741130091985e-05, "loss": 0.7137, "step": 746 }, { "epoch": 0.12, "learning_rate": 2.8174277266754273e-05, "loss": 1.0202, "step": 747 }, { "epoch": 0.12, "learning_rate": 2.8171813403416557e-05, "loss": 1.0117, "step": 748 }, { "epoch": 0.12, "learning_rate": 2.8169349540078845e-05, "loss": 0.8118, "step": 749 }, { "epoch": 0.12, "learning_rate": 2.816688567674113e-05, "loss": 1.0315, "step": 750 }, { "epoch": 0.12, "learning_rate": 2.8164421813403417e-05, "loss": 0.8855, "step": 751 }, { "epoch": 0.12, "learning_rate": 2.8161957950065704e-05, "loss": 1.1382, "step": 752 }, { "epoch": 0.12, "learning_rate": 2.8159494086727992e-05, "loss": 0.963, "step": 753 }, { "epoch": 0.12, "learning_rate": 2.8157030223390276e-05, "loss": 1.1682, "step": 754 }, { "epoch": 0.12, "learning_rate": 2.8154566360052564e-05, "loss": 1.0166, "step": 755 }, { "epoch": 0.12, "learning_rate": 2.815210249671485e-05, "loss": 0.5729, "step": 756 }, { "epoch": 0.12, "learning_rate": 2.8149638633377136e-05, "loss": 1.227, "step": 757 }, { "epoch": 0.12, "learning_rate": 2.8147174770039424e-05, "loss": 1.0404, "step": 758 }, { "epoch": 0.12, "learning_rate": 2.8144710906701708e-05, "loss": 1.2421, "step": 759 }, { "epoch": 0.12, "learning_rate": 2.8142247043363996e-05, "loss": 0.5766, "step": 760 }, { "epoch": 0.12, "learning_rate": 2.813978318002628e-05, "loss": 0.644, "step": 761 }, { "epoch": 0.13, "learning_rate": 2.813731931668857e-05, "loss": 0.7833, "step": 762 }, { "epoch": 0.13, "learning_rate": 2.8134855453350855e-05, "loss": 0.8563, "step": 763 }, { "epoch": 0.13, "learning_rate": 2.8132391590013143e-05, "loss": 0.8619, "step": 764 }, { "epoch": 0.13, "learning_rate": 2.8129927726675427e-05, "loss": 0.7236, "step": 765 }, { "epoch": 0.13, "learning_rate": 2.8127463863337715e-05, "loss": 1.0939, "step": 766 }, { "epoch": 0.13, "learning_rate": 2.8125e-05, "loss": 0.7446, "step": 767 }, { "epoch": 0.13, "learning_rate": 2.8122536136662287e-05, "loss": 1.4918, "step": 768 }, { "epoch": 0.13, "learning_rate": 2.8120072273324575e-05, "loss": 0.9699, "step": 769 }, { "epoch": 0.13, "learning_rate": 2.811760840998686e-05, "loss": 0.6485, "step": 770 }, { "epoch": 0.13, "learning_rate": 2.8115144546649147e-05, "loss": 1.2579, "step": 771 }, { "epoch": 0.13, "learning_rate": 2.811268068331143e-05, "loss": 1.749, "step": 772 }, { "epoch": 0.13, "learning_rate": 2.8110216819973722e-05, "loss": 0.9557, "step": 773 }, { "epoch": 0.13, "learning_rate": 2.8107752956636006e-05, "loss": 1.599, "step": 774 }, { "epoch": 0.13, "learning_rate": 2.8105289093298294e-05, "loss": 1.4112, "step": 775 }, { "epoch": 0.13, "learning_rate": 2.8102825229960578e-05, "loss": 0.8947, "step": 776 }, { "epoch": 0.13, "learning_rate": 2.8100361366622866e-05, "loss": 1.2861, "step": 777 }, { "epoch": 0.13, "learning_rate": 2.809789750328515e-05, "loss": 1.0096, "step": 778 }, { "epoch": 0.13, "learning_rate": 2.8095433639947438e-05, "loss": 0.7876, "step": 779 }, { "epoch": 0.13, "learning_rate": 2.8092969776609722e-05, "loss": 1.1922, "step": 780 }, { "epoch": 0.13, "learning_rate": 2.809050591327201e-05, "loss": 1.4402, "step": 781 }, { "epoch": 0.13, "learning_rate": 2.8088042049934297e-05, "loss": 0.8565, "step": 782 }, { "epoch": 0.13, "learning_rate": 2.8085578186596585e-05, "loss": 1.4919, "step": 783 }, { "epoch": 0.13, "learning_rate": 2.8083114323258873e-05, "loss": 1.0018, "step": 784 }, { "epoch": 0.13, "learning_rate": 2.8080650459921157e-05, "loss": 1.2194, "step": 785 }, { "epoch": 0.13, "learning_rate": 2.8078186596583445e-05, "loss": 1.4827, "step": 786 }, { "epoch": 0.13, "learning_rate": 2.807572273324573e-05, "loss": 1.0639, "step": 787 }, { "epoch": 0.13, "learning_rate": 2.8073258869908017e-05, "loss": 0.8469, "step": 788 }, { "epoch": 0.13, "learning_rate": 2.80707950065703e-05, "loss": 1.5151, "step": 789 }, { "epoch": 0.13, "learning_rate": 2.806833114323259e-05, "loss": 0.9383, "step": 790 }, { "epoch": 0.13, "learning_rate": 2.8065867279894873e-05, "loss": 1.6352, "step": 791 }, { "epoch": 0.13, "learning_rate": 2.806340341655716e-05, "loss": 0.9471, "step": 792 }, { "epoch": 0.13, "learning_rate": 2.8060939553219452e-05, "loss": 1.3281, "step": 793 }, { "epoch": 0.13, "learning_rate": 2.8058475689881736e-05, "loss": 0.6683, "step": 794 }, { "epoch": 0.13, "learning_rate": 2.8056011826544024e-05, "loss": 0.6958, "step": 795 }, { "epoch": 0.13, "learning_rate": 2.8053547963206308e-05, "loss": 1.7453, "step": 796 }, { "epoch": 0.13, "learning_rate": 2.8051084099868596e-05, "loss": 1.631, "step": 797 }, { "epoch": 0.13, "learning_rate": 2.804862023653088e-05, "loss": 0.5248, "step": 798 }, { "epoch": 0.13, "learning_rate": 2.8046156373193168e-05, "loss": 0.7651, "step": 799 }, { "epoch": 0.13, "learning_rate": 2.8043692509855452e-05, "loss": 1.4693, "step": 800 }, { "epoch": 0.13, "learning_rate": 2.804122864651774e-05, "loss": 1.0902, "step": 801 }, { "epoch": 0.13, "learning_rate": 2.8038764783180024e-05, "loss": 1.5918, "step": 802 }, { "epoch": 0.13, "learning_rate": 2.8036300919842315e-05, "loss": 0.95, "step": 803 }, { "epoch": 0.13, "learning_rate": 2.80338370565046e-05, "loss": 0.628, "step": 804 }, { "epoch": 0.13, "learning_rate": 2.8031373193166887e-05, "loss": 1.4302, "step": 805 }, { "epoch": 0.13, "learning_rate": 2.8028909329829175e-05, "loss": 1.5538, "step": 806 }, { "epoch": 0.13, "learning_rate": 2.802644546649146e-05, "loss": 0.9655, "step": 807 }, { "epoch": 0.13, "learning_rate": 2.8023981603153747e-05, "loss": 1.2151, "step": 808 }, { "epoch": 0.13, "learning_rate": 2.802151773981603e-05, "loss": 0.6196, "step": 809 }, { "epoch": 0.13, "learning_rate": 2.801905387647832e-05, "loss": 1.0769, "step": 810 }, { "epoch": 0.13, "learning_rate": 2.8016590013140603e-05, "loss": 1.0661, "step": 811 }, { "epoch": 0.13, "learning_rate": 2.801412614980289e-05, "loss": 2.1925, "step": 812 }, { "epoch": 0.13, "learning_rate": 2.8011662286465178e-05, "loss": 2.0904, "step": 813 }, { "epoch": 0.13, "learning_rate": 2.8009198423127466e-05, "loss": 1.2482, "step": 814 }, { "epoch": 0.13, "learning_rate": 2.800673455978975e-05, "loss": 1.8986, "step": 815 }, { "epoch": 0.13, "learning_rate": 2.8004270696452038e-05, "loss": 1.3371, "step": 816 }, { "epoch": 0.13, "learning_rate": 2.8001806833114326e-05, "loss": 1.3944, "step": 817 }, { "epoch": 0.13, "learning_rate": 2.799934296977661e-05, "loss": 0.6429, "step": 818 }, { "epoch": 0.13, "learning_rate": 2.7996879106438898e-05, "loss": 0.9135, "step": 819 }, { "epoch": 0.13, "learning_rate": 2.7994415243101182e-05, "loss": 0.675, "step": 820 }, { "epoch": 0.13, "learning_rate": 2.799195137976347e-05, "loss": 1.0523, "step": 821 }, { "epoch": 0.14, "learning_rate": 2.7989487516425754e-05, "loss": 0.8648, "step": 822 }, { "epoch": 0.14, "learning_rate": 2.7987023653088045e-05, "loss": 0.7714, "step": 823 }, { "epoch": 0.14, "learning_rate": 2.798455978975033e-05, "loss": 1.2099, "step": 824 }, { "epoch": 0.14, "learning_rate": 2.7982095926412617e-05, "loss": 1.0948, "step": 825 }, { "epoch": 0.14, "learning_rate": 2.79796320630749e-05, "loss": 1.1896, "step": 826 }, { "epoch": 0.14, "learning_rate": 2.797716819973719e-05, "loss": 1.0033, "step": 827 }, { "epoch": 0.14, "learning_rate": 2.7974704336399473e-05, "loss": 1.3568, "step": 828 }, { "epoch": 0.14, "learning_rate": 2.797224047306176e-05, "loss": 0.9458, "step": 829 }, { "epoch": 0.14, "learning_rate": 2.796977660972405e-05, "loss": 1.704, "step": 830 }, { "epoch": 0.14, "learning_rate": 2.7967312746386333e-05, "loss": 0.7647, "step": 831 }, { "epoch": 0.14, "learning_rate": 2.796484888304862e-05, "loss": 1.6309, "step": 832 }, { "epoch": 0.14, "learning_rate": 2.7962385019710908e-05, "loss": 1.1344, "step": 833 }, { "epoch": 0.14, "learning_rate": 2.7959921156373196e-05, "loss": 0.8704, "step": 834 }, { "epoch": 0.14, "learning_rate": 2.795745729303548e-05, "loss": 0.8651, "step": 835 }, { "epoch": 0.14, "learning_rate": 2.7954993429697768e-05, "loss": 1.0228, "step": 836 }, { "epoch": 0.14, "learning_rate": 2.7952529566360052e-05, "loss": 1.2159, "step": 837 }, { "epoch": 0.14, "learning_rate": 2.795006570302234e-05, "loss": 1.2285, "step": 838 }, { "epoch": 0.14, "learning_rate": 2.7947601839684624e-05, "loss": 0.7172, "step": 839 }, { "epoch": 0.14, "learning_rate": 2.794513797634691e-05, "loss": 1.2794, "step": 840 }, { "epoch": 0.14, "learning_rate": 2.79426741130092e-05, "loss": 1.5549, "step": 841 }, { "epoch": 0.14, "learning_rate": 2.7940210249671484e-05, "loss": 0.4587, "step": 842 }, { "epoch": 0.14, "learning_rate": 2.7937746386333775e-05, "loss": 1.3179, "step": 843 }, { "epoch": 0.14, "learning_rate": 2.793528252299606e-05, "loss": 1.4869, "step": 844 }, { "epoch": 0.14, "learning_rate": 2.7932818659658347e-05, "loss": 1.4687, "step": 845 }, { "epoch": 0.14, "learning_rate": 2.793035479632063e-05, "loss": 1.376, "step": 846 }, { "epoch": 0.14, "learning_rate": 2.792789093298292e-05, "loss": 1.201, "step": 847 }, { "epoch": 0.14, "learning_rate": 2.7925427069645203e-05, "loss": 1.0171, "step": 848 }, { "epoch": 0.14, "learning_rate": 2.792296320630749e-05, "loss": 1.2069, "step": 849 }, { "epoch": 0.14, "learning_rate": 2.7920499342969775e-05, "loss": 0.6736, "step": 850 }, { "epoch": 0.14, "learning_rate": 2.7918035479632063e-05, "loss": 0.5794, "step": 851 }, { "epoch": 0.14, "learning_rate": 2.791557161629435e-05, "loss": 0.5819, "step": 852 }, { "epoch": 0.14, "learning_rate": 2.7913107752956638e-05, "loss": 1.0775, "step": 853 }, { "epoch": 0.14, "learning_rate": 2.7910643889618926e-05, "loss": 0.5749, "step": 854 }, { "epoch": 0.14, "learning_rate": 2.790818002628121e-05, "loss": 1.0229, "step": 855 }, { "epoch": 0.14, "learning_rate": 2.7905716162943498e-05, "loss": 1.0362, "step": 856 }, { "epoch": 0.14, "learning_rate": 2.7903252299605782e-05, "loss": 0.5974, "step": 857 }, { "epoch": 0.14, "learning_rate": 2.790078843626807e-05, "loss": 0.7796, "step": 858 }, { "epoch": 0.14, "learning_rate": 2.7898324572930354e-05, "loss": 1.5991, "step": 859 }, { "epoch": 0.14, "learning_rate": 2.789586070959264e-05, "loss": 1.3785, "step": 860 }, { "epoch": 0.14, "learning_rate": 2.7893396846254926e-05, "loss": 1.0878, "step": 861 }, { "epoch": 0.14, "learning_rate": 2.7890932982917214e-05, "loss": 1.0976, "step": 862 }, { "epoch": 0.14, "learning_rate": 2.78884691195795e-05, "loss": 1.5214, "step": 863 }, { "epoch": 0.14, "learning_rate": 2.788600525624179e-05, "loss": 1.1494, "step": 864 }, { "epoch": 0.14, "learning_rate": 2.7883541392904077e-05, "loss": 1.9463, "step": 865 }, { "epoch": 0.14, "learning_rate": 2.788107752956636e-05, "loss": 1.0126, "step": 866 }, { "epoch": 0.14, "learning_rate": 2.787861366622865e-05, "loss": 0.6536, "step": 867 }, { "epoch": 0.14, "learning_rate": 2.7876149802890933e-05, "loss": 0.9436, "step": 868 }, { "epoch": 0.14, "learning_rate": 2.787368593955322e-05, "loss": 1.0664, "step": 869 }, { "epoch": 0.14, "learning_rate": 2.7871222076215505e-05, "loss": 0.6735, "step": 870 }, { "epoch": 0.14, "learning_rate": 2.7868758212877792e-05, "loss": 1.0307, "step": 871 }, { "epoch": 0.14, "learning_rate": 2.7866294349540077e-05, "loss": 0.7281, "step": 872 }, { "epoch": 0.14, "learning_rate": 2.7863830486202368e-05, "loss": 1.0893, "step": 873 }, { "epoch": 0.14, "learning_rate": 2.7861366622864652e-05, "loss": 1.1749, "step": 874 }, { "epoch": 0.14, "learning_rate": 2.785890275952694e-05, "loss": 0.599, "step": 875 }, { "epoch": 0.14, "learning_rate": 2.7856438896189227e-05, "loss": 0.421, "step": 876 }, { "epoch": 0.14, "learning_rate": 2.7853975032851512e-05, "loss": 1.0551, "step": 877 }, { "epoch": 0.14, "learning_rate": 2.78515111695138e-05, "loss": 0.894, "step": 878 }, { "epoch": 0.14, "learning_rate": 2.7849047306176084e-05, "loss": 0.6223, "step": 879 }, { "epoch": 0.14, "learning_rate": 2.784658344283837e-05, "loss": 0.38, "step": 880 }, { "epoch": 0.14, "learning_rate": 2.7844119579500656e-05, "loss": 0.9677, "step": 881 }, { "epoch": 0.14, "learning_rate": 2.7841655716162943e-05, "loss": 0.7907, "step": 882 }, { "epoch": 0.15, "learning_rate": 2.783919185282523e-05, "loss": 2.4646, "step": 883 }, { "epoch": 0.15, "learning_rate": 2.783672798948752e-05, "loss": 1.6078, "step": 884 }, { "epoch": 0.15, "learning_rate": 2.7834264126149803e-05, "loss": 0.6021, "step": 885 }, { "epoch": 0.15, "learning_rate": 2.783180026281209e-05, "loss": 0.1699, "step": 886 }, { "epoch": 0.15, "learning_rate": 2.7829336399474375e-05, "loss": 0.8799, "step": 887 }, { "epoch": 0.15, "learning_rate": 2.7826872536136663e-05, "loss": 0.7721, "step": 888 }, { "epoch": 0.15, "learning_rate": 2.782440867279895e-05, "loss": 1.207, "step": 889 }, { "epoch": 0.15, "learning_rate": 2.7821944809461235e-05, "loss": 1.0278, "step": 890 }, { "epoch": 0.15, "learning_rate": 2.7819480946123522e-05, "loss": 0.7975, "step": 891 }, { "epoch": 0.15, "learning_rate": 2.7817017082785807e-05, "loss": 0.8698, "step": 892 }, { "epoch": 0.15, "learning_rate": 2.7814553219448098e-05, "loss": 1.3716, "step": 893 }, { "epoch": 0.15, "learning_rate": 2.7812089356110382e-05, "loss": 1.5946, "step": 894 }, { "epoch": 0.15, "learning_rate": 2.780962549277267e-05, "loss": 0.967, "step": 895 }, { "epoch": 0.15, "learning_rate": 2.7807161629434954e-05, "loss": 2.0939, "step": 896 }, { "epoch": 0.15, "learning_rate": 2.780469776609724e-05, "loss": 1.121, "step": 897 }, { "epoch": 0.15, "learning_rate": 2.7802233902759526e-05, "loss": 0.7473, "step": 898 }, { "epoch": 0.15, "learning_rate": 2.7799770039421814e-05, "loss": 1.0519, "step": 899 }, { "epoch": 0.15, "learning_rate": 2.77973061760841e-05, "loss": 0.8566, "step": 900 }, { "epoch": 0.15, "learning_rate": 2.7794842312746386e-05, "loss": 1.211, "step": 901 }, { "epoch": 0.15, "learning_rate": 2.7792378449408673e-05, "loss": 0.6875, "step": 902 }, { "epoch": 0.15, "learning_rate": 2.778991458607096e-05, "loss": 0.5598, "step": 903 }, { "epoch": 0.15, "learning_rate": 2.778745072273325e-05, "loss": 0.8839, "step": 904 }, { "epoch": 0.15, "learning_rate": 2.7784986859395533e-05, "loss": 1.3592, "step": 905 }, { "epoch": 0.15, "learning_rate": 2.778252299605782e-05, "loss": 1.7711, "step": 906 }, { "epoch": 0.15, "learning_rate": 2.7780059132720105e-05, "loss": 1.5759, "step": 907 }, { "epoch": 0.15, "learning_rate": 2.7777595269382393e-05, "loss": 1.2517, "step": 908 }, { "epoch": 0.15, "learning_rate": 2.7775131406044677e-05, "loss": 0.7211, "step": 909 }, { "epoch": 0.15, "learning_rate": 2.7772667542706964e-05, "loss": 0.9498, "step": 910 }, { "epoch": 0.15, "learning_rate": 2.777020367936925e-05, "loss": 2.5419, "step": 911 }, { "epoch": 0.15, "learning_rate": 2.7767739816031536e-05, "loss": 0.4425, "step": 912 }, { "epoch": 0.15, "learning_rate": 2.7765275952693828e-05, "loss": 1.3185, "step": 913 }, { "epoch": 0.15, "learning_rate": 2.7762812089356112e-05, "loss": 0.9509, "step": 914 }, { "epoch": 0.15, "learning_rate": 2.77603482260184e-05, "loss": 1.0964, "step": 915 }, { "epoch": 0.15, "learning_rate": 2.7757884362680684e-05, "loss": 1.0518, "step": 916 }, { "epoch": 0.15, "learning_rate": 2.775542049934297e-05, "loss": 1.9708, "step": 917 }, { "epoch": 0.15, "learning_rate": 2.7752956636005256e-05, "loss": 1.2273, "step": 918 }, { "epoch": 0.15, "learning_rate": 2.7750492772667543e-05, "loss": 0.6681, "step": 919 }, { "epoch": 0.15, "learning_rate": 2.7748028909329828e-05, "loss": 0.5415, "step": 920 }, { "epoch": 0.15, "learning_rate": 2.7745565045992115e-05, "loss": 0.6105, "step": 921 }, { "epoch": 0.15, "learning_rate": 2.77431011826544e-05, "loss": 1.3665, "step": 922 }, { "epoch": 0.15, "learning_rate": 2.774063731931669e-05, "loss": 0.6212, "step": 923 }, { "epoch": 0.15, "learning_rate": 2.773817345597898e-05, "loss": 0.5896, "step": 924 }, { "epoch": 0.15, "learning_rate": 2.7735709592641263e-05, "loss": 0.7314, "step": 925 }, { "epoch": 0.15, "learning_rate": 2.773324572930355e-05, "loss": 1.3491, "step": 926 }, { "epoch": 0.15, "learning_rate": 2.7730781865965835e-05, "loss": 2.0861, "step": 927 }, { "epoch": 0.15, "learning_rate": 2.7728318002628122e-05, "loss": 1.7448, "step": 928 }, { "epoch": 0.15, "learning_rate": 2.7725854139290407e-05, "loss": 0.7185, "step": 929 }, { "epoch": 0.15, "learning_rate": 2.7723390275952694e-05, "loss": 1.2996, "step": 930 }, { "epoch": 0.15, "learning_rate": 2.772092641261498e-05, "loss": 0.8487, "step": 931 }, { "epoch": 0.15, "learning_rate": 2.7718462549277266e-05, "loss": 1.193, "step": 932 }, { "epoch": 0.15, "learning_rate": 2.7715998685939554e-05, "loss": 0.8046, "step": 933 }, { "epoch": 0.15, "learning_rate": 2.771353482260184e-05, "loss": 1.3481, "step": 934 }, { "epoch": 0.15, "learning_rate": 2.7711070959264126e-05, "loss": 1.59, "step": 935 }, { "epoch": 0.15, "learning_rate": 2.7708607095926414e-05, "loss": 1.0773, "step": 936 }, { "epoch": 0.15, "learning_rate": 2.77061432325887e-05, "loss": 1.2462, "step": 937 }, { "epoch": 0.15, "learning_rate": 2.7703679369250986e-05, "loss": 1.3471, "step": 938 }, { "epoch": 0.15, "learning_rate": 2.7701215505913273e-05, "loss": 1.2134, "step": 939 }, { "epoch": 0.15, "learning_rate": 2.7698751642575558e-05, "loss": 1.4782, "step": 940 }, { "epoch": 0.15, "learning_rate": 2.7696287779237845e-05, "loss": 1.4339, "step": 941 }, { "epoch": 0.15, "learning_rate": 2.769382391590013e-05, "loss": 0.8022, "step": 942 }, { "epoch": 0.15, "learning_rate": 2.769136005256242e-05, "loss": 0.8266, "step": 943 }, { "epoch": 0.16, "learning_rate": 2.7688896189224705e-05, "loss": 0.6233, "step": 944 }, { "epoch": 0.16, "learning_rate": 2.7686432325886993e-05, "loss": 1.2796, "step": 945 }, { "epoch": 0.16, "learning_rate": 2.7683968462549277e-05, "loss": 0.6567, "step": 946 }, { "epoch": 0.16, "learning_rate": 2.7681504599211565e-05, "loss": 1.5206, "step": 947 }, { "epoch": 0.16, "learning_rate": 2.7679040735873852e-05, "loss": 0.8458, "step": 948 }, { "epoch": 0.16, "learning_rate": 2.7676576872536137e-05, "loss": 1.0448, "step": 949 }, { "epoch": 0.16, "learning_rate": 2.7674113009198424e-05, "loss": 0.7424, "step": 950 }, { "epoch": 0.16, "learning_rate": 2.767164914586071e-05, "loss": 1.5427, "step": 951 }, { "epoch": 0.16, "learning_rate": 2.7669185282522996e-05, "loss": 1.381, "step": 952 }, { "epoch": 0.16, "learning_rate": 2.7666721419185284e-05, "loss": 0.6213, "step": 953 }, { "epoch": 0.16, "learning_rate": 2.766425755584757e-05, "loss": 0.9565, "step": 954 }, { "epoch": 0.16, "learning_rate": 2.7661793692509856e-05, "loss": 1.2001, "step": 955 }, { "epoch": 0.16, "learning_rate": 2.7659329829172143e-05, "loss": 1.2856, "step": 956 }, { "epoch": 0.16, "learning_rate": 2.7656865965834428e-05, "loss": 1.1702, "step": 957 }, { "epoch": 0.16, "learning_rate": 2.7654402102496715e-05, "loss": 1.6915, "step": 958 }, { "epoch": 0.16, "learning_rate": 2.7651938239159e-05, "loss": 1.0817, "step": 959 }, { "epoch": 0.16, "learning_rate": 2.7649474375821287e-05, "loss": 1.3805, "step": 960 }, { "epoch": 0.16, "learning_rate": 2.7647010512483575e-05, "loss": 2.3847, "step": 961 }, { "epoch": 0.16, "learning_rate": 2.764454664914586e-05, "loss": 2.0973, "step": 962 }, { "epoch": 0.16, "learning_rate": 2.764208278580815e-05, "loss": 0.7903, "step": 963 }, { "epoch": 0.16, "learning_rate": 2.7639618922470435e-05, "loss": 1.2453, "step": 964 }, { "epoch": 0.16, "learning_rate": 2.7637155059132722e-05, "loss": 1.0403, "step": 965 }, { "epoch": 0.16, "learning_rate": 2.7634691195795007e-05, "loss": 1.1633, "step": 966 }, { "epoch": 0.16, "learning_rate": 2.7632227332457294e-05, "loss": 0.9976, "step": 967 }, { "epoch": 0.16, "learning_rate": 2.762976346911958e-05, "loss": 0.8175, "step": 968 }, { "epoch": 0.16, "learning_rate": 2.7627299605781866e-05, "loss": 1.3664, "step": 969 }, { "epoch": 0.16, "learning_rate": 2.762483574244415e-05, "loss": 1.1196, "step": 970 }, { "epoch": 0.16, "learning_rate": 2.762237187910644e-05, "loss": 0.8868, "step": 971 }, { "epoch": 0.16, "learning_rate": 2.7619908015768726e-05, "loss": 1.1748, "step": 972 }, { "epoch": 0.16, "learning_rate": 2.7617444152431014e-05, "loss": 0.8151, "step": 973 }, { "epoch": 0.16, "learning_rate": 2.76149802890933e-05, "loss": 0.7893, "step": 974 }, { "epoch": 0.16, "learning_rate": 2.7612516425755586e-05, "loss": 1.0991, "step": 975 }, { "epoch": 0.16, "learning_rate": 2.7610052562417873e-05, "loss": 0.6047, "step": 976 }, { "epoch": 0.16, "learning_rate": 2.7607588699080158e-05, "loss": 1.1979, "step": 977 }, { "epoch": 0.16, "learning_rate": 2.7605124835742445e-05, "loss": 0.5871, "step": 978 }, { "epoch": 0.16, "learning_rate": 2.760266097240473e-05, "loss": 1.5696, "step": 979 }, { "epoch": 0.16, "learning_rate": 2.7600197109067017e-05, "loss": 0.848, "step": 980 }, { "epoch": 0.16, "learning_rate": 2.75977332457293e-05, "loss": 0.569, "step": 981 }, { "epoch": 0.16, "learning_rate": 2.759526938239159e-05, "loss": 1.4395, "step": 982 }, { "epoch": 0.16, "learning_rate": 2.7592805519053877e-05, "loss": 1.2373, "step": 983 }, { "epoch": 0.16, "learning_rate": 2.7590341655716165e-05, "loss": 0.8938, "step": 984 }, { "epoch": 0.16, "learning_rate": 2.7587877792378452e-05, "loss": 0.8242, "step": 985 }, { "epoch": 0.16, "learning_rate": 2.7585413929040737e-05, "loss": 1.5073, "step": 986 }, { "epoch": 0.16, "learning_rate": 2.7582950065703024e-05, "loss": 0.4551, "step": 987 }, { "epoch": 0.16, "learning_rate": 2.758048620236531e-05, "loss": 0.7709, "step": 988 }, { "epoch": 0.16, "learning_rate": 2.7578022339027596e-05, "loss": 1.3708, "step": 989 }, { "epoch": 0.16, "learning_rate": 2.757555847568988e-05, "loss": 1.0931, "step": 990 }, { "epoch": 0.16, "learning_rate": 2.7573094612352168e-05, "loss": 1.104, "step": 991 }, { "epoch": 0.16, "learning_rate": 2.7570630749014452e-05, "loss": 1.2556, "step": 992 }, { "epoch": 0.16, "learning_rate": 2.7568166885676744e-05, "loss": 0.926, "step": 993 }, { "epoch": 0.16, "learning_rate": 2.7565703022339028e-05, "loss": 0.5358, "step": 994 }, { "epoch": 0.16, "learning_rate": 2.7563239159001316e-05, "loss": 0.8956, "step": 995 }, { "epoch": 0.16, "learning_rate": 2.7560775295663603e-05, "loss": 0.72, "step": 996 }, { "epoch": 0.16, "learning_rate": 2.7558311432325887e-05, "loss": 0.6857, "step": 997 }, { "epoch": 0.16, "learning_rate": 2.7555847568988175e-05, "loss": 1.1249, "step": 998 }, { "epoch": 0.16, "learning_rate": 2.755338370565046e-05, "loss": 0.7296, "step": 999 }, { "epoch": 0.16, "learning_rate": 2.7550919842312747e-05, "loss": 0.6481, "step": 1000 }, { "epoch": 0.16, "eval_exact_match": 81.58940397350993, "eval_f1": 89.1930215678807, "step": 1000 }, { "epoch": 0.16, "learning_rate": 2.754845597897503e-05, "loss": 0.9617, "step": 1001 }, { "epoch": 0.16, "learning_rate": 2.754599211563732e-05, "loss": 1.3809, "step": 1002 }, { "epoch": 0.16, "learning_rate": 2.7543528252299607e-05, "loss": 0.4635, "step": 1003 }, { "epoch": 0.16, "learning_rate": 2.7541064388961894e-05, "loss": 1.0282, "step": 1004 }, { "epoch": 0.17, "learning_rate": 2.753860052562418e-05, "loss": 0.7584, "step": 1005 }, { "epoch": 0.17, "learning_rate": 2.7536136662286466e-05, "loss": 1.0143, "step": 1006 }, { "epoch": 0.17, "learning_rate": 2.7533672798948754e-05, "loss": 0.7592, "step": 1007 }, { "epoch": 0.17, "learning_rate": 2.753120893561104e-05, "loss": 0.9518, "step": 1008 }, { "epoch": 0.17, "learning_rate": 2.7528745072273326e-05, "loss": 0.8308, "step": 1009 }, { "epoch": 0.17, "learning_rate": 2.752628120893561e-05, "loss": 0.655, "step": 1010 }, { "epoch": 0.17, "learning_rate": 2.7523817345597898e-05, "loss": 1.3997, "step": 1011 }, { "epoch": 0.17, "learning_rate": 2.7521353482260182e-05, "loss": 0.4638, "step": 1012 }, { "epoch": 0.17, "learning_rate": 2.7518889618922473e-05, "loss": 1.3468, "step": 1013 }, { "epoch": 0.17, "learning_rate": 2.7516425755584758e-05, "loss": 1.1655, "step": 1014 }, { "epoch": 0.17, "learning_rate": 2.7513961892247045e-05, "loss": 1.26, "step": 1015 }, { "epoch": 0.17, "learning_rate": 2.751149802890933e-05, "loss": 0.8783, "step": 1016 }, { "epoch": 0.17, "learning_rate": 2.7509034165571617e-05, "loss": 1.1367, "step": 1017 }, { "epoch": 0.17, "learning_rate": 2.75065703022339e-05, "loss": 0.7084, "step": 1018 }, { "epoch": 0.17, "learning_rate": 2.750410643889619e-05, "loss": 1.6747, "step": 1019 }, { "epoch": 0.17, "learning_rate": 2.7501642575558477e-05, "loss": 0.8265, "step": 1020 }, { "epoch": 0.17, "learning_rate": 2.749917871222076e-05, "loss": 0.9173, "step": 1021 }, { "epoch": 0.17, "learning_rate": 2.749671484888305e-05, "loss": 0.6892, "step": 1022 }, { "epoch": 0.17, "learning_rate": 2.7494250985545337e-05, "loss": 0.9444, "step": 1023 }, { "epoch": 0.17, "learning_rate": 2.7491787122207624e-05, "loss": 0.9561, "step": 1024 }, { "epoch": 0.17, "learning_rate": 2.748932325886991e-05, "loss": 1.1531, "step": 1025 }, { "epoch": 0.17, "learning_rate": 2.7486859395532196e-05, "loss": 0.6632, "step": 1026 }, { "epoch": 0.17, "learning_rate": 2.748439553219448e-05, "loss": 1.122, "step": 1027 }, { "epoch": 0.17, "learning_rate": 2.7481931668856768e-05, "loss": 1.0492, "step": 1028 }, { "epoch": 0.17, "learning_rate": 2.7479467805519053e-05, "loss": 1.2373, "step": 1029 }, { "epoch": 0.17, "learning_rate": 2.747700394218134e-05, "loss": 1.015, "step": 1030 }, { "epoch": 0.17, "learning_rate": 2.7474540078843628e-05, "loss": 0.9198, "step": 1031 }, { "epoch": 0.17, "learning_rate": 2.7472076215505912e-05, "loss": 1.3943, "step": 1032 }, { "epoch": 0.17, "learning_rate": 2.7469612352168203e-05, "loss": 1.1295, "step": 1033 }, { "epoch": 0.17, "learning_rate": 2.7467148488830488e-05, "loss": 0.7294, "step": 1034 }, { "epoch": 0.17, "learning_rate": 2.7464684625492775e-05, "loss": 0.6994, "step": 1035 }, { "epoch": 0.17, "learning_rate": 2.746222076215506e-05, "loss": 0.6316, "step": 1036 }, { "epoch": 0.17, "learning_rate": 2.7459756898817347e-05, "loss": 1.1626, "step": 1037 }, { "epoch": 0.17, "learning_rate": 2.745729303547963e-05, "loss": 0.8056, "step": 1038 }, { "epoch": 0.17, "learning_rate": 2.745482917214192e-05, "loss": 0.7515, "step": 1039 }, { "epoch": 0.17, "learning_rate": 2.7452365308804203e-05, "loss": 1.2618, "step": 1040 }, { "epoch": 0.17, "learning_rate": 2.744990144546649e-05, "loss": 0.8652, "step": 1041 }, { "epoch": 0.17, "learning_rate": 2.7447437582128775e-05, "loss": 0.7513, "step": 1042 }, { "epoch": 0.17, "learning_rate": 2.7444973718791066e-05, "loss": 1.303, "step": 1043 }, { "epoch": 0.17, "learning_rate": 2.7442509855453354e-05, "loss": 0.9189, "step": 1044 }, { "epoch": 0.17, "learning_rate": 2.744004599211564e-05, "loss": 0.7979, "step": 1045 }, { "epoch": 0.17, "learning_rate": 2.7437582128777926e-05, "loss": 1.0465, "step": 1046 }, { "epoch": 0.17, "learning_rate": 2.743511826544021e-05, "loss": 0.7068, "step": 1047 }, { "epoch": 0.17, "learning_rate": 2.7432654402102498e-05, "loss": 1.055, "step": 1048 }, { "epoch": 0.17, "learning_rate": 2.7430190538764782e-05, "loss": 1.2463, "step": 1049 }, { "epoch": 0.17, "learning_rate": 2.742772667542707e-05, "loss": 1.1511, "step": 1050 }, { "epoch": 0.17, "learning_rate": 2.7425262812089354e-05, "loss": 1.3001, "step": 1051 }, { "epoch": 0.17, "learning_rate": 2.7422798948751642e-05, "loss": 1.4776, "step": 1052 }, { "epoch": 0.17, "learning_rate": 2.742033508541393e-05, "loss": 0.5963, "step": 1053 }, { "epoch": 0.17, "learning_rate": 2.7417871222076217e-05, "loss": 0.8422, "step": 1054 }, { "epoch": 0.17, "learning_rate": 2.7415407358738505e-05, "loss": 1.5241, "step": 1055 }, { "epoch": 0.17, "learning_rate": 2.741294349540079e-05, "loss": 1.8706, "step": 1056 }, { "epoch": 0.17, "learning_rate": 2.7410479632063077e-05, "loss": 0.9731, "step": 1057 }, { "epoch": 0.17, "learning_rate": 2.740801576872536e-05, "loss": 0.9982, "step": 1058 }, { "epoch": 0.17, "learning_rate": 2.740555190538765e-05, "loss": 1.3805, "step": 1059 }, { "epoch": 0.17, "learning_rate": 2.7403088042049933e-05, "loss": 1.2767, "step": 1060 }, { "epoch": 0.17, "learning_rate": 2.740062417871222e-05, "loss": 1.2273, "step": 1061 }, { "epoch": 0.17, "learning_rate": 2.7398160315374505e-05, "loss": 1.5448, "step": 1062 }, { "epoch": 0.17, "learning_rate": 2.7395696452036796e-05, "loss": 1.1108, "step": 1063 }, { "epoch": 0.17, "learning_rate": 2.739323258869908e-05, "loss": 1.6493, "step": 1064 }, { "epoch": 0.17, "learning_rate": 2.739076872536137e-05, "loss": 1.5974, "step": 1065 }, { "epoch": 0.18, "learning_rate": 2.7388304862023653e-05, "loss": 0.9318, "step": 1066 }, { "epoch": 0.18, "learning_rate": 2.738584099868594e-05, "loss": 1.2998, "step": 1067 }, { "epoch": 0.18, "learning_rate": 2.7383377135348228e-05, "loss": 1.1513, "step": 1068 }, { "epoch": 0.18, "learning_rate": 2.7380913272010512e-05, "loss": 1.0938, "step": 1069 }, { "epoch": 0.18, "learning_rate": 2.73784494086728e-05, "loss": 1.5002, "step": 1070 }, { "epoch": 0.18, "learning_rate": 2.7375985545335084e-05, "loss": 0.9977, "step": 1071 }, { "epoch": 0.18, "learning_rate": 2.7373521681997372e-05, "loss": 1.0625, "step": 1072 }, { "epoch": 0.18, "learning_rate": 2.737105781865966e-05, "loss": 1.734, "step": 1073 }, { "epoch": 0.18, "learning_rate": 2.7368593955321947e-05, "loss": 0.7898, "step": 1074 }, { "epoch": 0.18, "learning_rate": 2.736613009198423e-05, "loss": 1.1098, "step": 1075 }, { "epoch": 0.18, "learning_rate": 2.736366622864652e-05, "loss": 0.7954, "step": 1076 }, { "epoch": 0.18, "learning_rate": 2.7361202365308804e-05, "loss": 0.9254, "step": 1077 }, { "epoch": 0.18, "learning_rate": 2.735873850197109e-05, "loss": 2.1715, "step": 1078 }, { "epoch": 0.18, "learning_rate": 2.735627463863338e-05, "loss": 0.7299, "step": 1079 }, { "epoch": 0.18, "learning_rate": 2.7353810775295663e-05, "loss": 0.853, "step": 1080 }, { "epoch": 0.18, "learning_rate": 2.735134691195795e-05, "loss": 0.8009, "step": 1081 }, { "epoch": 0.18, "learning_rate": 2.7348883048620235e-05, "loss": 1.1808, "step": 1082 }, { "epoch": 0.18, "learning_rate": 2.7346419185282526e-05, "loss": 1.3527, "step": 1083 }, { "epoch": 0.18, "learning_rate": 2.734395532194481e-05, "loss": 1.1321, "step": 1084 }, { "epoch": 0.18, "learning_rate": 2.7341491458607098e-05, "loss": 0.714, "step": 1085 }, { "epoch": 0.18, "learning_rate": 2.7339027595269382e-05, "loss": 0.5502, "step": 1086 }, { "epoch": 0.18, "learning_rate": 2.733656373193167e-05, "loss": 1.0551, "step": 1087 }, { "epoch": 0.18, "learning_rate": 2.7334099868593954e-05, "loss": 1.0055, "step": 1088 }, { "epoch": 0.18, "learning_rate": 2.7331636005256242e-05, "loss": 1.1463, "step": 1089 }, { "epoch": 0.18, "learning_rate": 2.7329172141918526e-05, "loss": 1.3408, "step": 1090 }, { "epoch": 0.18, "learning_rate": 2.7326708278580814e-05, "loss": 0.8108, "step": 1091 }, { "epoch": 0.18, "learning_rate": 2.7324244415243102e-05, "loss": 0.8855, "step": 1092 }, { "epoch": 0.18, "learning_rate": 2.732178055190539e-05, "loss": 0.8348, "step": 1093 }, { "epoch": 0.18, "learning_rate": 2.7319316688567677e-05, "loss": 1.335, "step": 1094 }, { "epoch": 0.18, "learning_rate": 2.731685282522996e-05, "loss": 1.2889, "step": 1095 }, { "epoch": 0.18, "learning_rate": 2.731438896189225e-05, "loss": 1.6015, "step": 1096 }, { "epoch": 0.18, "learning_rate": 2.7311925098554533e-05, "loss": 1.4428, "step": 1097 }, { "epoch": 0.18, "learning_rate": 2.730946123521682e-05, "loss": 1.5169, "step": 1098 }, { "epoch": 0.18, "learning_rate": 2.7306997371879105e-05, "loss": 0.813, "step": 1099 }, { "epoch": 0.18, "learning_rate": 2.7304533508541393e-05, "loss": 0.5845, "step": 1100 }, { "epoch": 0.18, "learning_rate": 2.7302069645203677e-05, "loss": 0.7626, "step": 1101 }, { "epoch": 0.18, "learning_rate": 2.7299605781865965e-05, "loss": 1.207, "step": 1102 }, { "epoch": 0.18, "learning_rate": 2.7297141918528256e-05, "loss": 1.9474, "step": 1103 }, { "epoch": 0.18, "learning_rate": 2.729467805519054e-05, "loss": 1.1229, "step": 1104 }, { "epoch": 0.18, "learning_rate": 2.7292214191852828e-05, "loss": 1.0175, "step": 1105 }, { "epoch": 0.18, "learning_rate": 2.7289750328515112e-05, "loss": 1.2495, "step": 1106 }, { "epoch": 0.18, "learning_rate": 2.72872864651774e-05, "loss": 0.7777, "step": 1107 }, { "epoch": 0.18, "learning_rate": 2.7284822601839684e-05, "loss": 0.5998, "step": 1108 }, { "epoch": 0.18, "learning_rate": 2.7282358738501972e-05, "loss": 1.5434, "step": 1109 }, { "epoch": 0.18, "learning_rate": 2.7279894875164256e-05, "loss": 0.6802, "step": 1110 }, { "epoch": 0.18, "learning_rate": 2.7277431011826544e-05, "loss": 1.167, "step": 1111 }, { "epoch": 0.18, "learning_rate": 2.7274967148488828e-05, "loss": 0.7891, "step": 1112 }, { "epoch": 0.18, "learning_rate": 2.727250328515112e-05, "loss": 1.2338, "step": 1113 }, { "epoch": 0.18, "learning_rate": 2.7270039421813404e-05, "loss": 0.6378, "step": 1114 }, { "epoch": 0.18, "learning_rate": 2.726757555847569e-05, "loss": 1.0962, "step": 1115 }, { "epoch": 0.18, "learning_rate": 2.726511169513798e-05, "loss": 0.7456, "step": 1116 }, { "epoch": 0.18, "learning_rate": 2.7262647831800263e-05, "loss": 0.9379, "step": 1117 }, { "epoch": 0.18, "learning_rate": 2.726018396846255e-05, "loss": 1.0894, "step": 1118 }, { "epoch": 0.18, "learning_rate": 2.7257720105124835e-05, "loss": 0.9408, "step": 1119 }, { "epoch": 0.18, "learning_rate": 2.7255256241787123e-05, "loss": 0.7907, "step": 1120 }, { "epoch": 0.18, "learning_rate": 2.7252792378449407e-05, "loss": 0.4933, "step": 1121 }, { "epoch": 0.18, "learning_rate": 2.7250328515111695e-05, "loss": 0.9678, "step": 1122 }, { "epoch": 0.18, "learning_rate": 2.7247864651773983e-05, "loss": 1.0705, "step": 1123 }, { "epoch": 0.18, "learning_rate": 2.724540078843627e-05, "loss": 0.4438, "step": 1124 }, { "epoch": 0.18, "learning_rate": 2.7242936925098554e-05, "loss": 1.4069, "step": 1125 }, { "epoch": 0.18, "learning_rate": 2.7240473061760842e-05, "loss": 1.832, "step": 1126 }, { "epoch": 0.19, "learning_rate": 2.723800919842313e-05, "loss": 0.6202, "step": 1127 }, { "epoch": 0.19, "learning_rate": 2.7235545335085414e-05, "loss": 0.9983, "step": 1128 }, { "epoch": 0.19, "learning_rate": 2.7233081471747702e-05, "loss": 0.7437, "step": 1129 }, { "epoch": 0.19, "learning_rate": 2.7230617608409986e-05, "loss": 1.8151, "step": 1130 }, { "epoch": 0.19, "learning_rate": 2.7228153745072274e-05, "loss": 1.0212, "step": 1131 }, { "epoch": 0.19, "learning_rate": 2.7225689881734558e-05, "loss": 1.0382, "step": 1132 }, { "epoch": 0.19, "learning_rate": 2.722322601839685e-05, "loss": 0.6097, "step": 1133 }, { "epoch": 0.19, "learning_rate": 2.7220762155059133e-05, "loss": 1.0521, "step": 1134 }, { "epoch": 0.19, "learning_rate": 2.721829829172142e-05, "loss": 0.9651, "step": 1135 }, { "epoch": 0.19, "learning_rate": 2.7215834428383705e-05, "loss": 1.075, "step": 1136 }, { "epoch": 0.19, "learning_rate": 2.7213370565045993e-05, "loss": 1.0471, "step": 1137 }, { "epoch": 0.19, "learning_rate": 2.721090670170828e-05, "loss": 1.1362, "step": 1138 }, { "epoch": 0.19, "learning_rate": 2.7208442838370565e-05, "loss": 0.6555, "step": 1139 }, { "epoch": 0.19, "learning_rate": 2.7205978975032853e-05, "loss": 0.7623, "step": 1140 }, { "epoch": 0.19, "learning_rate": 2.7203515111695137e-05, "loss": 0.964, "step": 1141 }, { "epoch": 0.19, "learning_rate": 2.7201051248357425e-05, "loss": 1.3638, "step": 1142 }, { "epoch": 0.19, "learning_rate": 2.7198587385019712e-05, "loss": 1.3265, "step": 1143 }, { "epoch": 0.19, "learning_rate": 2.7196123521682e-05, "loss": 1.1131, "step": 1144 }, { "epoch": 0.19, "learning_rate": 2.7193659658344284e-05, "loss": 1.1179, "step": 1145 }, { "epoch": 0.19, "learning_rate": 2.7191195795006572e-05, "loss": 1.2417, "step": 1146 }, { "epoch": 0.19, "learning_rate": 2.7188731931668856e-05, "loss": 1.3509, "step": 1147 }, { "epoch": 0.19, "learning_rate": 2.7186268068331144e-05, "loss": 0.9418, "step": 1148 }, { "epoch": 0.19, "learning_rate": 2.7183804204993428e-05, "loss": 0.8492, "step": 1149 }, { "epoch": 0.19, "learning_rate": 2.7181340341655716e-05, "loss": 1.2216, "step": 1150 }, { "epoch": 0.19, "learning_rate": 2.7178876478318004e-05, "loss": 1.255, "step": 1151 }, { "epoch": 0.19, "learning_rate": 2.7176412614980288e-05, "loss": 1.906, "step": 1152 }, { "epoch": 0.19, "learning_rate": 2.717394875164258e-05, "loss": 0.9828, "step": 1153 }, { "epoch": 0.19, "learning_rate": 2.7171484888304863e-05, "loss": 1.137, "step": 1154 }, { "epoch": 0.19, "learning_rate": 2.716902102496715e-05, "loss": 1.1412, "step": 1155 }, { "epoch": 0.19, "learning_rate": 2.7166557161629435e-05, "loss": 1.8038, "step": 1156 }, { "epoch": 0.19, "learning_rate": 2.7164093298291723e-05, "loss": 1.1736, "step": 1157 }, { "epoch": 0.19, "learning_rate": 2.7161629434954007e-05, "loss": 1.0214, "step": 1158 }, { "epoch": 0.19, "learning_rate": 2.7159165571616295e-05, "loss": 0.6839, "step": 1159 }, { "epoch": 0.19, "learning_rate": 2.715670170827858e-05, "loss": 0.7822, "step": 1160 }, { "epoch": 0.19, "learning_rate": 2.7154237844940867e-05, "loss": 0.5177, "step": 1161 }, { "epoch": 0.19, "learning_rate": 2.7151773981603155e-05, "loss": 0.9457, "step": 1162 }, { "epoch": 0.19, "learning_rate": 2.7149310118265442e-05, "loss": 0.4699, "step": 1163 }, { "epoch": 0.19, "learning_rate": 2.714684625492773e-05, "loss": 1.0757, "step": 1164 }, { "epoch": 0.19, "learning_rate": 2.7144382391590014e-05, "loss": 0.5956, "step": 1165 }, { "epoch": 0.19, "learning_rate": 2.7141918528252302e-05, "loss": 0.8407, "step": 1166 }, { "epoch": 0.19, "learning_rate": 2.7139454664914586e-05, "loss": 1.6524, "step": 1167 }, { "epoch": 0.19, "learning_rate": 2.7136990801576874e-05, "loss": 0.8822, "step": 1168 }, { "epoch": 0.19, "learning_rate": 2.7134526938239158e-05, "loss": 1.32, "step": 1169 }, { "epoch": 0.19, "learning_rate": 2.7132063074901446e-05, "loss": 1.2159, "step": 1170 }, { "epoch": 0.19, "learning_rate": 2.712959921156373e-05, "loss": 1.5013, "step": 1171 }, { "epoch": 0.19, "learning_rate": 2.7127135348226018e-05, "loss": 0.8532, "step": 1172 }, { "epoch": 0.19, "learning_rate": 2.7124671484888305e-05, "loss": 0.8446, "step": 1173 }, { "epoch": 0.19, "learning_rate": 2.7122207621550593e-05, "loss": 1.0185, "step": 1174 }, { "epoch": 0.19, "learning_rate": 2.711974375821288e-05, "loss": 0.9908, "step": 1175 }, { "epoch": 0.19, "learning_rate": 2.7117279894875165e-05, "loss": 0.937, "step": 1176 }, { "epoch": 0.19, "learning_rate": 2.7114816031537453e-05, "loss": 1.1381, "step": 1177 }, { "epoch": 0.19, "learning_rate": 2.7112352168199737e-05, "loss": 0.7615, "step": 1178 }, { "epoch": 0.19, "learning_rate": 2.7109888304862025e-05, "loss": 1.0304, "step": 1179 }, { "epoch": 0.19, "learning_rate": 2.710742444152431e-05, "loss": 1.059, "step": 1180 }, { "epoch": 0.19, "learning_rate": 2.7104960578186597e-05, "loss": 1.0621, "step": 1181 }, { "epoch": 0.19, "learning_rate": 2.710249671484888e-05, "loss": 0.7814, "step": 1182 }, { "epoch": 0.19, "learning_rate": 2.7100032851511172e-05, "loss": 1.1369, "step": 1183 }, { "epoch": 0.19, "learning_rate": 2.7097568988173456e-05, "loss": 1.1226, "step": 1184 }, { "epoch": 0.19, "learning_rate": 2.7095105124835744e-05, "loss": 0.9232, "step": 1185 }, { "epoch": 0.19, "learning_rate": 2.7092641261498032e-05, "loss": 0.6121, "step": 1186 }, { "epoch": 0.19, "learning_rate": 2.7090177398160316e-05, "loss": 1.0036, "step": 1187 }, { "epoch": 0.2, "learning_rate": 2.7087713534822604e-05, "loss": 1.3816, "step": 1188 }, { "epoch": 0.2, "learning_rate": 2.7085249671484888e-05, "loss": 1.2177, "step": 1189 }, { "epoch": 0.2, "learning_rate": 2.7082785808147176e-05, "loss": 0.8791, "step": 1190 }, { "epoch": 0.2, "learning_rate": 2.708032194480946e-05, "loss": 0.9496, "step": 1191 }, { "epoch": 0.2, "learning_rate": 2.7077858081471748e-05, "loss": 0.9074, "step": 1192 }, { "epoch": 0.2, "learning_rate": 2.7075394218134035e-05, "loss": 0.8424, "step": 1193 }, { "epoch": 0.2, "learning_rate": 2.7072930354796323e-05, "loss": 0.9991, "step": 1194 }, { "epoch": 0.2, "learning_rate": 2.7070466491458607e-05, "loss": 1.3559, "step": 1195 }, { "epoch": 0.2, "learning_rate": 2.7068002628120895e-05, "loss": 1.1075, "step": 1196 }, { "epoch": 0.2, "learning_rate": 2.706553876478318e-05, "loss": 1.4268, "step": 1197 }, { "epoch": 0.2, "learning_rate": 2.7063074901445467e-05, "loss": 0.5554, "step": 1198 }, { "epoch": 0.2, "learning_rate": 2.7060611038107755e-05, "loss": 0.4198, "step": 1199 }, { "epoch": 0.2, "learning_rate": 2.705814717477004e-05, "loss": 1.9683, "step": 1200 }, { "epoch": 0.2, "learning_rate": 2.7055683311432327e-05, "loss": 1.2057, "step": 1201 }, { "epoch": 0.2, "learning_rate": 2.705321944809461e-05, "loss": 0.9032, "step": 1202 }, { "epoch": 0.2, "learning_rate": 2.7050755584756902e-05, "loss": 0.5799, "step": 1203 }, { "epoch": 0.2, "learning_rate": 2.7048291721419186e-05, "loss": 0.7188, "step": 1204 }, { "epoch": 0.2, "learning_rate": 2.7045827858081474e-05, "loss": 0.5315, "step": 1205 }, { "epoch": 0.2, "learning_rate": 2.7043363994743758e-05, "loss": 0.9173, "step": 1206 }, { "epoch": 0.2, "learning_rate": 2.7040900131406046e-05, "loss": 1.4041, "step": 1207 }, { "epoch": 0.2, "learning_rate": 2.703843626806833e-05, "loss": 0.7104, "step": 1208 }, { "epoch": 0.2, "learning_rate": 2.7035972404730618e-05, "loss": 0.9137, "step": 1209 }, { "epoch": 0.2, "learning_rate": 2.7033508541392906e-05, "loss": 1.161, "step": 1210 }, { "epoch": 0.2, "learning_rate": 2.703104467805519e-05, "loss": 1.3188, "step": 1211 }, { "epoch": 0.2, "learning_rate": 2.7028580814717478e-05, "loss": 0.8505, "step": 1212 }, { "epoch": 0.2, "learning_rate": 2.7026116951379765e-05, "loss": 0.3133, "step": 1213 }, { "epoch": 0.2, "learning_rate": 2.7023653088042053e-05, "loss": 1.1941, "step": 1214 }, { "epoch": 0.2, "learning_rate": 2.7021189224704337e-05, "loss": 0.9607, "step": 1215 }, { "epoch": 0.2, "learning_rate": 2.7018725361366625e-05, "loss": 0.9101, "step": 1216 }, { "epoch": 0.2, "learning_rate": 2.701626149802891e-05, "loss": 1.2159, "step": 1217 }, { "epoch": 0.2, "learning_rate": 2.7013797634691197e-05, "loss": 0.4137, "step": 1218 }, { "epoch": 0.2, "learning_rate": 2.701133377135348e-05, "loss": 0.8611, "step": 1219 }, { "epoch": 0.2, "learning_rate": 2.700886990801577e-05, "loss": 0.5809, "step": 1220 }, { "epoch": 0.2, "learning_rate": 2.7006406044678053e-05, "loss": 1.2651, "step": 1221 }, { "epoch": 0.2, "learning_rate": 2.700394218134034e-05, "loss": 1.2482, "step": 1222 }, { "epoch": 0.2, "learning_rate": 2.7001478318002632e-05, "loss": 1.473, "step": 1223 }, { "epoch": 0.2, "learning_rate": 2.6999014454664916e-05, "loss": 1.2325, "step": 1224 }, { "epoch": 0.2, "learning_rate": 2.6996550591327204e-05, "loss": 0.6752, "step": 1225 }, { "epoch": 0.2, "learning_rate": 2.6994086727989488e-05, "loss": 1.1857, "step": 1226 }, { "epoch": 0.2, "learning_rate": 2.6991622864651776e-05, "loss": 0.6687, "step": 1227 }, { "epoch": 0.2, "learning_rate": 2.698915900131406e-05, "loss": 0.4214, "step": 1228 }, { "epoch": 0.2, "learning_rate": 2.6986695137976348e-05, "loss": 0.8255, "step": 1229 }, { "epoch": 0.2, "learning_rate": 2.6984231274638632e-05, "loss": 0.6789, "step": 1230 }, { "epoch": 0.2, "learning_rate": 2.698176741130092e-05, "loss": 0.6325, "step": 1231 }, { "epoch": 0.2, "learning_rate": 2.6979303547963204e-05, "loss": 0.8092, "step": 1232 }, { "epoch": 0.2, "learning_rate": 2.6976839684625495e-05, "loss": 0.9016, "step": 1233 }, { "epoch": 0.2, "learning_rate": 2.6974375821287783e-05, "loss": 0.6388, "step": 1234 }, { "epoch": 0.2, "learning_rate": 2.6971911957950067e-05, "loss": 0.8393, "step": 1235 }, { "epoch": 0.2, "learning_rate": 2.6969448094612355e-05, "loss": 1.2522, "step": 1236 }, { "epoch": 0.2, "learning_rate": 2.696698423127464e-05, "loss": 0.4999, "step": 1237 }, { "epoch": 0.2, "learning_rate": 2.6964520367936927e-05, "loss": 0.8073, "step": 1238 }, { "epoch": 0.2, "learning_rate": 2.696205650459921e-05, "loss": 0.7507, "step": 1239 }, { "epoch": 0.2, "learning_rate": 2.69595926412615e-05, "loss": 0.9608, "step": 1240 }, { "epoch": 0.2, "learning_rate": 2.6957128777923783e-05, "loss": 0.739, "step": 1241 }, { "epoch": 0.2, "learning_rate": 2.695466491458607e-05, "loss": 0.8902, "step": 1242 }, { "epoch": 0.2, "learning_rate": 2.6952201051248358e-05, "loss": 0.8878, "step": 1243 }, { "epoch": 0.2, "learning_rate": 2.6949737187910646e-05, "loss": 1.6388, "step": 1244 }, { "epoch": 0.2, "learning_rate": 2.694727332457293e-05, "loss": 0.9015, "step": 1245 }, { "epoch": 0.2, "learning_rate": 2.6944809461235218e-05, "loss": 1.3053, "step": 1246 }, { "epoch": 0.2, "learning_rate": 2.6942345597897506e-05, "loss": 1.6942, "step": 1247 }, { "epoch": 0.2, "learning_rate": 2.693988173455979e-05, "loss": 1.2546, "step": 1248 }, { "epoch": 0.21, "learning_rate": 2.6937417871222078e-05, "loss": 1.2107, "step": 1249 }, { "epoch": 0.21, "learning_rate": 2.6934954007884362e-05, "loss": 0.8194, "step": 1250 }, { "epoch": 0.21, "learning_rate": 2.693249014454665e-05, "loss": 0.7031, "step": 1251 }, { "epoch": 0.21, "learning_rate": 2.6930026281208934e-05, "loss": 0.9322, "step": 1252 }, { "epoch": 0.21, "learning_rate": 2.6927562417871225e-05, "loss": 2.3737, "step": 1253 }, { "epoch": 0.21, "learning_rate": 2.692509855453351e-05, "loss": 0.7332, "step": 1254 }, { "epoch": 0.21, "learning_rate": 2.6922634691195797e-05, "loss": 0.9251, "step": 1255 }, { "epoch": 0.21, "learning_rate": 2.692017082785808e-05, "loss": 0.8061, "step": 1256 }, { "epoch": 0.21, "learning_rate": 2.691770696452037e-05, "loss": 0.4006, "step": 1257 }, { "epoch": 0.21, "learning_rate": 2.6915243101182657e-05, "loss": 1.1223, "step": 1258 }, { "epoch": 0.21, "learning_rate": 2.691277923784494e-05, "loss": 0.8407, "step": 1259 }, { "epoch": 0.21, "learning_rate": 2.691031537450723e-05, "loss": 1.1031, "step": 1260 }, { "epoch": 0.21, "learning_rate": 2.6907851511169513e-05, "loss": 0.6961, "step": 1261 }, { "epoch": 0.21, "learning_rate": 2.69053876478318e-05, "loss": 0.7876, "step": 1262 }, { "epoch": 0.21, "learning_rate": 2.6902923784494088e-05, "loss": 0.8779, "step": 1263 }, { "epoch": 0.21, "learning_rate": 2.6900459921156376e-05, "loss": 1.0379, "step": 1264 }, { "epoch": 0.21, "learning_rate": 2.689799605781866e-05, "loss": 1.0942, "step": 1265 }, { "epoch": 0.21, "learning_rate": 2.6895532194480948e-05, "loss": 1.5712, "step": 1266 }, { "epoch": 0.21, "learning_rate": 2.6893068331143232e-05, "loss": 0.6788, "step": 1267 }, { "epoch": 0.21, "learning_rate": 2.689060446780552e-05, "loss": 1.3865, "step": 1268 }, { "epoch": 0.21, "learning_rate": 2.6888140604467807e-05, "loss": 1.3884, "step": 1269 }, { "epoch": 0.21, "learning_rate": 2.6885676741130092e-05, "loss": 1.5622, "step": 1270 }, { "epoch": 0.21, "learning_rate": 2.688321287779238e-05, "loss": 1.4931, "step": 1271 }, { "epoch": 0.21, "learning_rate": 2.6880749014454664e-05, "loss": 0.6644, "step": 1272 }, { "epoch": 0.21, "learning_rate": 2.6878285151116955e-05, "loss": 0.7692, "step": 1273 }, { "epoch": 0.21, "learning_rate": 2.687582128777924e-05, "loss": 0.806, "step": 1274 }, { "epoch": 0.21, "learning_rate": 2.6873357424441527e-05, "loss": 1.3846, "step": 1275 }, { "epoch": 0.21, "learning_rate": 2.687089356110381e-05, "loss": 1.0894, "step": 1276 }, { "epoch": 0.21, "learning_rate": 2.68684296977661e-05, "loss": 1.1861, "step": 1277 }, { "epoch": 0.21, "learning_rate": 2.6865965834428383e-05, "loss": 0.9874, "step": 1278 }, { "epoch": 0.21, "learning_rate": 2.686350197109067e-05, "loss": 1.2964, "step": 1279 }, { "epoch": 0.21, "learning_rate": 2.6861038107752955e-05, "loss": 0.7853, "step": 1280 }, { "epoch": 0.21, "learning_rate": 2.6858574244415243e-05, "loss": 1.1228, "step": 1281 }, { "epoch": 0.21, "learning_rate": 2.685611038107753e-05, "loss": 1.704, "step": 1282 }, { "epoch": 0.21, "learning_rate": 2.6853646517739818e-05, "loss": 1.1361, "step": 1283 }, { "epoch": 0.21, "learning_rate": 2.6851182654402106e-05, "loss": 1.1387, "step": 1284 }, { "epoch": 0.21, "learning_rate": 2.684871879106439e-05, "loss": 1.3014, "step": 1285 }, { "epoch": 0.21, "learning_rate": 2.6846254927726678e-05, "loss": 0.5756, "step": 1286 }, { "epoch": 0.21, "learning_rate": 2.6843791064388962e-05, "loss": 0.9946, "step": 1287 }, { "epoch": 0.21, "learning_rate": 2.684132720105125e-05, "loss": 0.4496, "step": 1288 }, { "epoch": 0.21, "learning_rate": 2.6838863337713534e-05, "loss": 1.081, "step": 1289 }, { "epoch": 0.21, "learning_rate": 2.683639947437582e-05, "loss": 1.033, "step": 1290 }, { "epoch": 0.21, "learning_rate": 2.6833935611038106e-05, "loss": 0.8012, "step": 1291 }, { "epoch": 0.21, "learning_rate": 2.6831471747700394e-05, "loss": 1.2193, "step": 1292 }, { "epoch": 0.21, "learning_rate": 2.6829007884362685e-05, "loss": 0.7622, "step": 1293 }, { "epoch": 0.21, "learning_rate": 2.682654402102497e-05, "loss": 1.4396, "step": 1294 }, { "epoch": 0.21, "learning_rate": 2.6824080157687257e-05, "loss": 0.8036, "step": 1295 }, { "epoch": 0.21, "learning_rate": 2.682161629434954e-05, "loss": 1.6122, "step": 1296 }, { "epoch": 0.21, "learning_rate": 2.681915243101183e-05, "loss": 1.1824, "step": 1297 }, { "epoch": 0.21, "learning_rate": 2.6816688567674113e-05, "loss": 0.6127, "step": 1298 }, { "epoch": 0.21, "learning_rate": 2.68142247043364e-05, "loss": 0.5166, "step": 1299 }, { "epoch": 0.21, "learning_rate": 2.6811760840998685e-05, "loss": 1.01, "step": 1300 }, { "epoch": 0.21, "learning_rate": 2.6809296977660972e-05, "loss": 1.1561, "step": 1301 }, { "epoch": 0.21, "learning_rate": 2.6806833114323257e-05, "loss": 1.0746, "step": 1302 }, { "epoch": 0.21, "learning_rate": 2.6804369250985548e-05, "loss": 1.4561, "step": 1303 }, { "epoch": 0.21, "learning_rate": 2.6801905387647832e-05, "loss": 0.5896, "step": 1304 }, { "epoch": 0.21, "learning_rate": 2.679944152431012e-05, "loss": 1.5741, "step": 1305 }, { "epoch": 0.21, "learning_rate": 2.6796977660972407e-05, "loss": 0.8944, "step": 1306 }, { "epoch": 0.21, "learning_rate": 2.6794513797634692e-05, "loss": 0.6783, "step": 1307 }, { "epoch": 0.21, "learning_rate": 2.679204993429698e-05, "loss": 1.4754, "step": 1308 }, { "epoch": 0.22, "learning_rate": 2.6789586070959264e-05, "loss": 0.8562, "step": 1309 }, { "epoch": 0.22, "learning_rate": 2.678712220762155e-05, "loss": 1.0456, "step": 1310 }, { "epoch": 0.22, "learning_rate": 2.6784658344283836e-05, "loss": 0.7288, "step": 1311 }, { "epoch": 0.22, "learning_rate": 2.6782194480946123e-05, "loss": 1.4243, "step": 1312 }, { "epoch": 0.22, "learning_rate": 2.677973061760841e-05, "loss": 0.8157, "step": 1313 }, { "epoch": 0.22, "learning_rate": 2.67772667542707e-05, "loss": 0.8448, "step": 1314 }, { "epoch": 0.22, "learning_rate": 2.6774802890932983e-05, "loss": 1.1054, "step": 1315 }, { "epoch": 0.22, "learning_rate": 2.677233902759527e-05, "loss": 0.4508, "step": 1316 }, { "epoch": 0.22, "learning_rate": 2.676987516425756e-05, "loss": 1.2157, "step": 1317 }, { "epoch": 0.22, "learning_rate": 2.6767411300919843e-05, "loss": 0.5921, "step": 1318 }, { "epoch": 0.22, "learning_rate": 2.676494743758213e-05, "loss": 0.7754, "step": 1319 }, { "epoch": 0.22, "learning_rate": 2.6762483574244415e-05, "loss": 0.7337, "step": 1320 }, { "epoch": 0.22, "learning_rate": 2.6760019710906702e-05, "loss": 1.0514, "step": 1321 }, { "epoch": 0.22, "learning_rate": 2.6757555847568987e-05, "loss": 1.4485, "step": 1322 }, { "epoch": 0.22, "learning_rate": 2.6755091984231278e-05, "loss": 0.5657, "step": 1323 }, { "epoch": 0.22, "learning_rate": 2.6752628120893562e-05, "loss": 0.8393, "step": 1324 }, { "epoch": 0.22, "learning_rate": 2.675016425755585e-05, "loss": 0.6759, "step": 1325 }, { "epoch": 0.22, "learning_rate": 2.6747700394218134e-05, "loss": 0.8269, "step": 1326 }, { "epoch": 0.22, "learning_rate": 2.674523653088042e-05, "loss": 0.8513, "step": 1327 }, { "epoch": 0.22, "learning_rate": 2.6742772667542706e-05, "loss": 0.3998, "step": 1328 }, { "epoch": 0.22, "learning_rate": 2.6740308804204994e-05, "loss": 1.7156, "step": 1329 }, { "epoch": 0.22, "learning_rate": 2.673784494086728e-05, "loss": 1.2105, "step": 1330 }, { "epoch": 0.22, "learning_rate": 2.6735381077529566e-05, "loss": 1.1626, "step": 1331 }, { "epoch": 0.22, "learning_rate": 2.6732917214191853e-05, "loss": 0.9983, "step": 1332 }, { "epoch": 0.22, "learning_rate": 2.673045335085414e-05, "loss": 0.7855, "step": 1333 }, { "epoch": 0.22, "learning_rate": 2.672798948751643e-05, "loss": 0.5021, "step": 1334 }, { "epoch": 0.22, "learning_rate": 2.6725525624178713e-05, "loss": 0.838, "step": 1335 }, { "epoch": 0.22, "learning_rate": 2.6723061760841e-05, "loss": 2.1443, "step": 1336 }, { "epoch": 0.22, "learning_rate": 2.6720597897503285e-05, "loss": 0.6456, "step": 1337 }, { "epoch": 0.22, "learning_rate": 2.6718134034165573e-05, "loss": 1.1428, "step": 1338 }, { "epoch": 0.22, "learning_rate": 2.6715670170827857e-05, "loss": 0.9023, "step": 1339 }, { "epoch": 0.22, "learning_rate": 2.6713206307490145e-05, "loss": 0.8753, "step": 1340 }, { "epoch": 0.22, "learning_rate": 2.6710742444152432e-05, "loss": 1.0618, "step": 1341 }, { "epoch": 0.22, "learning_rate": 2.6708278580814716e-05, "loss": 1.1891, "step": 1342 }, { "epoch": 0.22, "learning_rate": 2.6705814717477008e-05, "loss": 1.4596, "step": 1343 }, { "epoch": 0.22, "learning_rate": 2.6703350854139292e-05, "loss": 0.5502, "step": 1344 }, { "epoch": 0.22, "learning_rate": 2.670088699080158e-05, "loss": 1.0484, "step": 1345 }, { "epoch": 0.22, "learning_rate": 2.6698423127463864e-05, "loss": 0.9179, "step": 1346 }, { "epoch": 0.22, "learning_rate": 2.669595926412615e-05, "loss": 0.8479, "step": 1347 }, { "epoch": 0.22, "learning_rate": 2.6693495400788436e-05, "loss": 1.562, "step": 1348 }, { "epoch": 0.22, "learning_rate": 2.6691031537450723e-05, "loss": 0.9084, "step": 1349 }, { "epoch": 0.22, "learning_rate": 2.6688567674113008e-05, "loss": 0.8976, "step": 1350 }, { "epoch": 0.22, "learning_rate": 2.6686103810775295e-05, "loss": 1.1407, "step": 1351 }, { "epoch": 0.22, "learning_rate": 2.668363994743758e-05, "loss": 0.8202, "step": 1352 }, { "epoch": 0.22, "learning_rate": 2.668117608409987e-05, "loss": 0.8823, "step": 1353 }, { "epoch": 0.22, "learning_rate": 2.667871222076216e-05, "loss": 0.5843, "step": 1354 }, { "epoch": 0.22, "learning_rate": 2.6676248357424443e-05, "loss": 1.1591, "step": 1355 }, { "epoch": 0.22, "learning_rate": 2.667378449408673e-05, "loss": 0.6562, "step": 1356 }, { "epoch": 0.22, "learning_rate": 2.6671320630749015e-05, "loss": 1.1038, "step": 1357 }, { "epoch": 0.22, "learning_rate": 2.6668856767411302e-05, "loss": 0.7512, "step": 1358 }, { "epoch": 0.22, "learning_rate": 2.6666392904073587e-05, "loss": 0.9344, "step": 1359 }, { "epoch": 0.22, "learning_rate": 2.6663929040735874e-05, "loss": 0.4883, "step": 1360 }, { "epoch": 0.22, "learning_rate": 2.666146517739816e-05, "loss": 1.0188, "step": 1361 }, { "epoch": 0.22, "learning_rate": 2.6659001314060446e-05, "loss": 0.5525, "step": 1362 }, { "epoch": 0.22, "learning_rate": 2.6656537450722734e-05, "loss": 0.649, "step": 1363 }, { "epoch": 0.22, "learning_rate": 2.6654073587385022e-05, "loss": 1.5391, "step": 1364 }, { "epoch": 0.22, "learning_rate": 2.665160972404731e-05, "loss": 1.8633, "step": 1365 }, { "epoch": 0.22, "learning_rate": 2.6649145860709594e-05, "loss": 0.8092, "step": 1366 }, { "epoch": 0.22, "learning_rate": 2.664668199737188e-05, "loss": 0.7147, "step": 1367 }, { "epoch": 0.22, "learning_rate": 2.6644218134034166e-05, "loss": 1.0524, "step": 1368 }, { "epoch": 0.22, "learning_rate": 2.6641754270696453e-05, "loss": 1.0072, "step": 1369 }, { "epoch": 0.23, "learning_rate": 2.6639290407358738e-05, "loss": 1.4327, "step": 1370 }, { "epoch": 0.23, "learning_rate": 2.6636826544021025e-05, "loss": 1.3, "step": 1371 }, { "epoch": 0.23, "learning_rate": 2.663436268068331e-05, "loss": 1.3635, "step": 1372 }, { "epoch": 0.23, "learning_rate": 2.66318988173456e-05, "loss": 1.1828, "step": 1373 }, { "epoch": 0.23, "learning_rate": 2.6629434954007885e-05, "loss": 1.4062, "step": 1374 }, { "epoch": 0.23, "learning_rate": 2.6626971090670173e-05, "loss": 1.0914, "step": 1375 }, { "epoch": 0.23, "learning_rate": 2.6624507227332457e-05, "loss": 0.658, "step": 1376 }, { "epoch": 0.23, "learning_rate": 2.6622043363994745e-05, "loss": 1.2046, "step": 1377 }, { "epoch": 0.23, "learning_rate": 2.6619579500657032e-05, "loss": 0.7684, "step": 1378 }, { "epoch": 0.23, "learning_rate": 2.6617115637319317e-05, "loss": 0.4941, "step": 1379 }, { "epoch": 0.23, "learning_rate": 2.6614651773981604e-05, "loss": 1.1986, "step": 1380 }, { "epoch": 0.23, "learning_rate": 2.661218791064389e-05, "loss": 1.2278, "step": 1381 }, { "epoch": 0.23, "learning_rate": 2.6609724047306176e-05, "loss": 1.1164, "step": 1382 }, { "epoch": 0.23, "learning_rate": 2.6607260183968464e-05, "loss": 1.2423, "step": 1383 }, { "epoch": 0.23, "learning_rate": 2.660479632063075e-05, "loss": 0.5907, "step": 1384 }, { "epoch": 0.23, "learning_rate": 2.6602332457293036e-05, "loss": 0.7513, "step": 1385 }, { "epoch": 0.23, "learning_rate": 2.6599868593955324e-05, "loss": 1.2014, "step": 1386 }, { "epoch": 0.23, "learning_rate": 2.6597404730617608e-05, "loss": 0.9712, "step": 1387 }, { "epoch": 0.23, "learning_rate": 2.6594940867279895e-05, "loss": 0.6683, "step": 1388 }, { "epoch": 0.23, "learning_rate": 2.6592477003942183e-05, "loss": 0.6322, "step": 1389 }, { "epoch": 0.23, "learning_rate": 2.6590013140604467e-05, "loss": 1.124, "step": 1390 }, { "epoch": 0.23, "learning_rate": 2.6587549277266755e-05, "loss": 0.7739, "step": 1391 }, { "epoch": 0.23, "learning_rate": 2.658508541392904e-05, "loss": 1.2393, "step": 1392 }, { "epoch": 0.23, "learning_rate": 2.658262155059133e-05, "loss": 1.452, "step": 1393 }, { "epoch": 0.23, "learning_rate": 2.6580157687253615e-05, "loss": 1.1651, "step": 1394 }, { "epoch": 0.23, "learning_rate": 2.6577693823915902e-05, "loss": 0.9499, "step": 1395 }, { "epoch": 0.23, "learning_rate": 2.6575229960578187e-05, "loss": 1.4977, "step": 1396 }, { "epoch": 0.23, "learning_rate": 2.6572766097240474e-05, "loss": 0.8196, "step": 1397 }, { "epoch": 0.23, "learning_rate": 2.657030223390276e-05, "loss": 1.6783, "step": 1398 }, { "epoch": 0.23, "learning_rate": 2.6567838370565046e-05, "loss": 1.2822, "step": 1399 }, { "epoch": 0.23, "learning_rate": 2.6565374507227334e-05, "loss": 0.8345, "step": 1400 }, { "epoch": 0.23, "learning_rate": 2.656291064388962e-05, "loss": 0.7176, "step": 1401 }, { "epoch": 0.23, "learning_rate": 2.6560446780551906e-05, "loss": 1.0395, "step": 1402 }, { "epoch": 0.23, "learning_rate": 2.6557982917214194e-05, "loss": 0.8417, "step": 1403 }, { "epoch": 0.23, "learning_rate": 2.655551905387648e-05, "loss": 0.9331, "step": 1404 }, { "epoch": 0.23, "learning_rate": 2.6553055190538766e-05, "loss": 1.1286, "step": 1405 }, { "epoch": 0.23, "learning_rate": 2.6550591327201053e-05, "loss": 0.8535, "step": 1406 }, { "epoch": 0.23, "learning_rate": 2.6548127463863338e-05, "loss": 0.9212, "step": 1407 }, { "epoch": 0.23, "learning_rate": 2.6545663600525625e-05, "loss": 0.8897, "step": 1408 }, { "epoch": 0.23, "learning_rate": 2.654319973718791e-05, "loss": 0.3736, "step": 1409 }, { "epoch": 0.23, "learning_rate": 2.6540735873850197e-05, "loss": 0.5193, "step": 1410 }, { "epoch": 0.23, "learning_rate": 2.653827201051248e-05, "loss": 0.5544, "step": 1411 }, { "epoch": 0.23, "learning_rate": 2.653580814717477e-05, "loss": 1.083, "step": 1412 }, { "epoch": 0.23, "learning_rate": 2.653334428383706e-05, "loss": 1.0738, "step": 1413 }, { "epoch": 0.23, "learning_rate": 2.6530880420499345e-05, "loss": 1.0231, "step": 1414 }, { "epoch": 0.23, "learning_rate": 2.6528416557161632e-05, "loss": 0.9381, "step": 1415 }, { "epoch": 0.23, "learning_rate": 2.6525952693823917e-05, "loss": 0.6583, "step": 1416 }, { "epoch": 0.23, "learning_rate": 2.6523488830486204e-05, "loss": 1.3679, "step": 1417 }, { "epoch": 0.23, "learning_rate": 2.652102496714849e-05, "loss": 1.3432, "step": 1418 }, { "epoch": 0.23, "learning_rate": 2.6518561103810776e-05, "loss": 1.0439, "step": 1419 }, { "epoch": 0.23, "learning_rate": 2.651609724047306e-05, "loss": 1.3915, "step": 1420 }, { "epoch": 0.23, "learning_rate": 2.6513633377135348e-05, "loss": 0.5523, "step": 1421 }, { "epoch": 0.23, "learning_rate": 2.6511169513797633e-05, "loss": 1.5752, "step": 1422 }, { "epoch": 0.23, "learning_rate": 2.6508705650459924e-05, "loss": 1.1014, "step": 1423 }, { "epoch": 0.23, "learning_rate": 2.650624178712221e-05, "loss": 0.9703, "step": 1424 }, { "epoch": 0.23, "learning_rate": 2.6503777923784496e-05, "loss": 0.9626, "step": 1425 }, { "epoch": 0.23, "learning_rate": 2.6501314060446783e-05, "loss": 0.3011, "step": 1426 }, { "epoch": 0.23, "learning_rate": 2.6498850197109068e-05, "loss": 0.7908, "step": 1427 }, { "epoch": 0.23, "learning_rate": 2.6496386333771355e-05, "loss": 1.3893, "step": 1428 }, { "epoch": 0.23, "learning_rate": 2.649392247043364e-05, "loss": 1.2847, "step": 1429 }, { "epoch": 0.23, "learning_rate": 2.6491458607095927e-05, "loss": 1.2715, "step": 1430 }, { "epoch": 0.24, "learning_rate": 2.648899474375821e-05, "loss": 1.5713, "step": 1431 }, { "epoch": 0.24, "learning_rate": 2.64865308804205e-05, "loss": 1.2417, "step": 1432 }, { "epoch": 0.24, "learning_rate": 2.6484067017082787e-05, "loss": 1.145, "step": 1433 }, { "epoch": 0.24, "learning_rate": 2.6481603153745074e-05, "loss": 1.0076, "step": 1434 }, { "epoch": 0.24, "learning_rate": 2.647913929040736e-05, "loss": 0.5119, "step": 1435 }, { "epoch": 0.24, "learning_rate": 2.6476675427069646e-05, "loss": 0.8369, "step": 1436 }, { "epoch": 0.24, "learning_rate": 2.6474211563731934e-05, "loss": 1.6731, "step": 1437 }, { "epoch": 0.24, "learning_rate": 2.647174770039422e-05, "loss": 0.66, "step": 1438 }, { "epoch": 0.24, "learning_rate": 2.6469283837056506e-05, "loss": 0.6705, "step": 1439 }, { "epoch": 0.24, "learning_rate": 2.646681997371879e-05, "loss": 0.83, "step": 1440 }, { "epoch": 0.24, "learning_rate": 2.6464356110381078e-05, "loss": 0.9645, "step": 1441 }, { "epoch": 0.24, "learning_rate": 2.6461892247043362e-05, "loss": 0.8903, "step": 1442 }, { "epoch": 0.24, "learning_rate": 2.6459428383705653e-05, "loss": 0.8414, "step": 1443 }, { "epoch": 0.24, "learning_rate": 2.6456964520367938e-05, "loss": 1.0287, "step": 1444 }, { "epoch": 0.24, "learning_rate": 2.6454500657030225e-05, "loss": 0.5836, "step": 1445 }, { "epoch": 0.24, "learning_rate": 2.645203679369251e-05, "loss": 0.8829, "step": 1446 }, { "epoch": 0.24, "learning_rate": 2.6449572930354797e-05, "loss": 0.2822, "step": 1447 }, { "epoch": 0.24, "learning_rate": 2.6447109067017085e-05, "loss": 0.7042, "step": 1448 }, { "epoch": 0.24, "learning_rate": 2.644464520367937e-05, "loss": 0.7429, "step": 1449 }, { "epoch": 0.24, "learning_rate": 2.6442181340341657e-05, "loss": 1.1278, "step": 1450 }, { "epoch": 0.24, "learning_rate": 2.643971747700394e-05, "loss": 1.622, "step": 1451 }, { "epoch": 0.24, "learning_rate": 2.643725361366623e-05, "loss": 1.6329, "step": 1452 }, { "epoch": 0.24, "learning_rate": 2.6434789750328517e-05, "loss": 1.4785, "step": 1453 }, { "epoch": 0.24, "learning_rate": 2.6432325886990804e-05, "loss": 1.1949, "step": 1454 }, { "epoch": 0.24, "learning_rate": 2.642986202365309e-05, "loss": 1.3001, "step": 1455 }, { "epoch": 0.24, "learning_rate": 2.6427398160315376e-05, "loss": 1.0397, "step": 1456 }, { "epoch": 0.24, "learning_rate": 2.642493429697766e-05, "loss": 0.8847, "step": 1457 }, { "epoch": 0.24, "learning_rate": 2.6422470433639948e-05, "loss": 0.376, "step": 1458 }, { "epoch": 0.24, "learning_rate": 2.6420006570302233e-05, "loss": 1.1853, "step": 1459 }, { "epoch": 0.24, "learning_rate": 2.641754270696452e-05, "loss": 0.872, "step": 1460 }, { "epoch": 0.24, "learning_rate": 2.6415078843626808e-05, "loss": 0.6643, "step": 1461 }, { "epoch": 0.24, "learning_rate": 2.6412614980289092e-05, "loss": 0.8036, "step": 1462 }, { "epoch": 0.24, "learning_rate": 2.6410151116951383e-05, "loss": 1.1659, "step": 1463 }, { "epoch": 0.24, "learning_rate": 2.6407687253613668e-05, "loss": 1.3671, "step": 1464 }, { "epoch": 0.24, "learning_rate": 2.6405223390275955e-05, "loss": 1.1454, "step": 1465 }, { "epoch": 0.24, "learning_rate": 2.640275952693824e-05, "loss": 0.8928, "step": 1466 }, { "epoch": 0.24, "learning_rate": 2.6400295663600527e-05, "loss": 1.1203, "step": 1467 }, { "epoch": 0.24, "learning_rate": 2.639783180026281e-05, "loss": 0.8773, "step": 1468 }, { "epoch": 0.24, "learning_rate": 2.63953679369251e-05, "loss": 1.2127, "step": 1469 }, { "epoch": 0.24, "learning_rate": 2.6392904073587383e-05, "loss": 1.2903, "step": 1470 }, { "epoch": 0.24, "learning_rate": 2.639044021024967e-05, "loss": 0.9083, "step": 1471 }, { "epoch": 0.24, "learning_rate": 2.638797634691196e-05, "loss": 1.0514, "step": 1472 }, { "epoch": 0.24, "learning_rate": 2.6385512483574247e-05, "loss": 1.9423, "step": 1473 }, { "epoch": 0.24, "learning_rate": 2.6383048620236534e-05, "loss": 1.2919, "step": 1474 }, { "epoch": 0.24, "learning_rate": 2.638058475689882e-05, "loss": 0.6176, "step": 1475 }, { "epoch": 0.24, "learning_rate": 2.6378120893561106e-05, "loss": 0.8721, "step": 1476 }, { "epoch": 0.24, "learning_rate": 2.637565703022339e-05, "loss": 0.6262, "step": 1477 }, { "epoch": 0.24, "learning_rate": 2.6373193166885678e-05, "loss": 0.9239, "step": 1478 }, { "epoch": 0.24, "learning_rate": 2.6370729303547962e-05, "loss": 0.6432, "step": 1479 }, { "epoch": 0.24, "learning_rate": 2.636826544021025e-05, "loss": 1.5738, "step": 1480 }, { "epoch": 0.24, "learning_rate": 2.6365801576872534e-05, "loss": 1.3576, "step": 1481 }, { "epoch": 0.24, "learning_rate": 2.6363337713534822e-05, "loss": 0.7368, "step": 1482 }, { "epoch": 0.24, "learning_rate": 2.636087385019711e-05, "loss": 1.631, "step": 1483 }, { "epoch": 0.24, "learning_rate": 2.6358409986859397e-05, "loss": 0.841, "step": 1484 }, { "epoch": 0.24, "learning_rate": 2.6355946123521685e-05, "loss": 0.9265, "step": 1485 }, { "epoch": 0.24, "learning_rate": 2.635348226018397e-05, "loss": 1.0412, "step": 1486 }, { "epoch": 0.24, "learning_rate": 2.6351018396846257e-05, "loss": 0.8645, "step": 1487 }, { "epoch": 0.24, "learning_rate": 2.634855453350854e-05, "loss": 0.7971, "step": 1488 }, { "epoch": 0.24, "learning_rate": 2.634609067017083e-05, "loss": 0.8626, "step": 1489 }, { "epoch": 0.24, "learning_rate": 2.6343626806833113e-05, "loss": 1.6044, "step": 1490 }, { "epoch": 0.24, "learning_rate": 2.63411629434954e-05, "loss": 1.2333, "step": 1491 }, { "epoch": 0.25, "learning_rate": 2.6338699080157685e-05, "loss": 1.2055, "step": 1492 }, { "epoch": 0.25, "learning_rate": 2.6336235216819976e-05, "loss": 0.9613, "step": 1493 }, { "epoch": 0.25, "learning_rate": 2.633377135348226e-05, "loss": 1.1945, "step": 1494 }, { "epoch": 0.25, "learning_rate": 2.633130749014455e-05, "loss": 0.9364, "step": 1495 }, { "epoch": 0.25, "learning_rate": 2.6328843626806836e-05, "loss": 0.9637, "step": 1496 }, { "epoch": 0.25, "learning_rate": 2.632637976346912e-05, "loss": 0.7075, "step": 1497 }, { "epoch": 0.25, "learning_rate": 2.6323915900131408e-05, "loss": 0.5461, "step": 1498 }, { "epoch": 0.25, "learning_rate": 2.6321452036793692e-05, "loss": 1.224, "step": 1499 }, { "epoch": 0.25, "learning_rate": 2.631898817345598e-05, "loss": 1.7291, "step": 1500 }, { "epoch": 0.25, "eval_exact_match": 83.39640491958373, "eval_f1": 90.66937720089753, "step": 1500 }, { "epoch": 0.25, "learning_rate": 2.6316524310118264e-05, "loss": 0.6586, "step": 1501 }, { "epoch": 0.25, "learning_rate": 2.6314060446780552e-05, "loss": 0.84, "step": 1502 }, { "epoch": 0.25, "learning_rate": 2.631159658344284e-05, "loss": 0.8193, "step": 1503 }, { "epoch": 0.25, "learning_rate": 2.6309132720105127e-05, "loss": 1.2276, "step": 1504 }, { "epoch": 0.25, "learning_rate": 2.630666885676741e-05, "loss": 1.2382, "step": 1505 }, { "epoch": 0.25, "learning_rate": 2.63042049934297e-05, "loss": 0.5923, "step": 1506 }, { "epoch": 0.25, "learning_rate": 2.6301741130091984e-05, "loss": 1.5834, "step": 1507 }, { "epoch": 0.25, "learning_rate": 2.629927726675427e-05, "loss": 1.4217, "step": 1508 }, { "epoch": 0.25, "learning_rate": 2.629681340341656e-05, "loss": 0.8394, "step": 1509 }, { "epoch": 0.25, "learning_rate": 2.6294349540078843e-05, "loss": 0.7254, "step": 1510 }, { "epoch": 0.25, "learning_rate": 2.629188567674113e-05, "loss": 0.4619, "step": 1511 }, { "epoch": 0.25, "learning_rate": 2.6289421813403415e-05, "loss": 1.2803, "step": 1512 }, { "epoch": 0.25, "learning_rate": 2.6286957950065706e-05, "loss": 1.2873, "step": 1513 }, { "epoch": 0.25, "learning_rate": 2.628449408672799e-05, "loss": 1.2098, "step": 1514 }, { "epoch": 0.25, "learning_rate": 2.6282030223390278e-05, "loss": 0.3824, "step": 1515 }, { "epoch": 0.25, "learning_rate": 2.6279566360052562e-05, "loss": 0.6983, "step": 1516 }, { "epoch": 0.25, "learning_rate": 2.627710249671485e-05, "loss": 0.8749, "step": 1517 }, { "epoch": 0.25, "learning_rate": 2.6274638633377134e-05, "loss": 0.4777, "step": 1518 }, { "epoch": 0.25, "learning_rate": 2.6272174770039422e-05, "loss": 0.7101, "step": 1519 }, { "epoch": 0.25, "learning_rate": 2.626971090670171e-05, "loss": 0.6726, "step": 1520 }, { "epoch": 0.25, "learning_rate": 2.6267247043363994e-05, "loss": 0.7403, "step": 1521 }, { "epoch": 0.25, "learning_rate": 2.6264783180026282e-05, "loss": 0.8589, "step": 1522 }, { "epoch": 0.25, "learning_rate": 2.626231931668857e-05, "loss": 1.4518, "step": 1523 }, { "epoch": 0.25, "learning_rate": 2.6259855453350857e-05, "loss": 0.6784, "step": 1524 }, { "epoch": 0.25, "learning_rate": 2.625739159001314e-05, "loss": 1.5141, "step": 1525 }, { "epoch": 0.25, "learning_rate": 2.625492772667543e-05, "loss": 1.2034, "step": 1526 }, { "epoch": 0.25, "learning_rate": 2.6252463863337713e-05, "loss": 0.8231, "step": 1527 }, { "epoch": 0.25, "learning_rate": 2.625e-05, "loss": 0.8725, "step": 1528 }, { "epoch": 0.25, "learning_rate": 2.6247536136662285e-05, "loss": 0.9929, "step": 1529 }, { "epoch": 0.25, "learning_rate": 2.6245072273324573e-05, "loss": 0.6537, "step": 1530 }, { "epoch": 0.25, "learning_rate": 2.624260840998686e-05, "loss": 1.0275, "step": 1531 }, { "epoch": 0.25, "learning_rate": 2.6240144546649145e-05, "loss": 0.6724, "step": 1532 }, { "epoch": 0.25, "learning_rate": 2.6237680683311433e-05, "loss": 0.8934, "step": 1533 }, { "epoch": 0.25, "learning_rate": 2.623521681997372e-05, "loss": 0.4852, "step": 1534 }, { "epoch": 0.25, "learning_rate": 2.6232752956636008e-05, "loss": 0.7138, "step": 1535 }, { "epoch": 0.25, "learning_rate": 2.6230289093298292e-05, "loss": 0.9244, "step": 1536 }, { "epoch": 0.25, "learning_rate": 2.622782522996058e-05, "loss": 1.0105, "step": 1537 }, { "epoch": 0.25, "learning_rate": 2.6225361366622864e-05, "loss": 0.6192, "step": 1538 }, { "epoch": 0.25, "learning_rate": 2.6222897503285152e-05, "loss": 0.3097, "step": 1539 }, { "epoch": 0.25, "learning_rate": 2.6220433639947436e-05, "loss": 0.4789, "step": 1540 }, { "epoch": 0.25, "learning_rate": 2.6217969776609724e-05, "loss": 1.1884, "step": 1541 }, { "epoch": 0.25, "learning_rate": 2.6215505913272008e-05, "loss": 0.6861, "step": 1542 }, { "epoch": 0.25, "learning_rate": 2.6213042049934296e-05, "loss": 0.524, "step": 1543 }, { "epoch": 0.25, "learning_rate": 2.6210578186596587e-05, "loss": 1.2433, "step": 1544 }, { "epoch": 0.25, "learning_rate": 2.620811432325887e-05, "loss": 0.8138, "step": 1545 }, { "epoch": 0.25, "learning_rate": 2.620565045992116e-05, "loss": 1.5293, "step": 1546 }, { "epoch": 0.25, "learning_rate": 2.6203186596583443e-05, "loss": 1.6248, "step": 1547 }, { "epoch": 0.25, "learning_rate": 2.620072273324573e-05, "loss": 1.1203, "step": 1548 }, { "epoch": 0.25, "learning_rate": 2.6198258869908015e-05, "loss": 1.1515, "step": 1549 }, { "epoch": 0.25, "learning_rate": 2.6195795006570303e-05, "loss": 0.9765, "step": 1550 }, { "epoch": 0.25, "learning_rate": 2.6193331143232587e-05, "loss": 1.0682, "step": 1551 }, { "epoch": 0.25, "learning_rate": 2.6190867279894875e-05, "loss": 0.9775, "step": 1552 }, { "epoch": 0.26, "learning_rate": 2.618840341655716e-05, "loss": 0.7477, "step": 1553 }, { "epoch": 0.26, "learning_rate": 2.618593955321945e-05, "loss": 0.6525, "step": 1554 }, { "epoch": 0.26, "learning_rate": 2.6183475689881738e-05, "loss": 0.8527, "step": 1555 }, { "epoch": 0.26, "learning_rate": 2.6181011826544022e-05, "loss": 0.6934, "step": 1556 }, { "epoch": 0.26, "learning_rate": 2.617854796320631e-05, "loss": 0.7345, "step": 1557 }, { "epoch": 0.26, "learning_rate": 2.6176084099868594e-05, "loss": 0.7705, "step": 1558 }, { "epoch": 0.26, "learning_rate": 2.6173620236530882e-05, "loss": 0.7311, "step": 1559 }, { "epoch": 0.26, "learning_rate": 2.6171156373193166e-05, "loss": 0.7117, "step": 1560 }, { "epoch": 0.26, "learning_rate": 2.6168692509855454e-05, "loss": 0.8225, "step": 1561 }, { "epoch": 0.26, "learning_rate": 2.6166228646517738e-05, "loss": 1.1568, "step": 1562 }, { "epoch": 0.26, "learning_rate": 2.6163764783180026e-05, "loss": 1.7732, "step": 1563 }, { "epoch": 0.26, "learning_rate": 2.6161300919842313e-05, "loss": 0.9416, "step": 1564 }, { "epoch": 0.26, "learning_rate": 2.61588370565046e-05, "loss": 1.09, "step": 1565 }, { "epoch": 0.26, "learning_rate": 2.6156373193166885e-05, "loss": 1.2489, "step": 1566 }, { "epoch": 0.26, "learning_rate": 2.6153909329829173e-05, "loss": 0.6495, "step": 1567 }, { "epoch": 0.26, "learning_rate": 2.615144546649146e-05, "loss": 0.7222, "step": 1568 }, { "epoch": 0.26, "learning_rate": 2.6148981603153745e-05, "loss": 0.9682, "step": 1569 }, { "epoch": 0.26, "learning_rate": 2.6146517739816033e-05, "loss": 0.8071, "step": 1570 }, { "epoch": 0.26, "learning_rate": 2.6144053876478317e-05, "loss": 0.6517, "step": 1571 }, { "epoch": 0.26, "learning_rate": 2.6141590013140605e-05, "loss": 1.3899, "step": 1572 }, { "epoch": 0.26, "learning_rate": 2.613912614980289e-05, "loss": 1.0658, "step": 1573 }, { "epoch": 0.26, "learning_rate": 2.613666228646518e-05, "loss": 1.2147, "step": 1574 }, { "epoch": 0.26, "learning_rate": 2.6134198423127464e-05, "loss": 1.1732, "step": 1575 }, { "epoch": 0.26, "learning_rate": 2.6131734559789752e-05, "loss": 1.2112, "step": 1576 }, { "epoch": 0.26, "learning_rate": 2.6129270696452036e-05, "loss": 1.3575, "step": 1577 }, { "epoch": 0.26, "learning_rate": 2.6126806833114324e-05, "loss": 1.5799, "step": 1578 }, { "epoch": 0.26, "learning_rate": 2.6124342969776612e-05, "loss": 0.6049, "step": 1579 }, { "epoch": 0.26, "learning_rate": 2.6121879106438896e-05, "loss": 1.2455, "step": 1580 }, { "epoch": 0.26, "learning_rate": 2.6119415243101184e-05, "loss": 1.1291, "step": 1581 }, { "epoch": 0.26, "learning_rate": 2.6116951379763468e-05, "loss": 1.2251, "step": 1582 }, { "epoch": 0.26, "learning_rate": 2.6114487516425756e-05, "loss": 0.742, "step": 1583 }, { "epoch": 0.26, "learning_rate": 2.6112023653088043e-05, "loss": 0.4763, "step": 1584 }, { "epoch": 0.26, "learning_rate": 2.610955978975033e-05, "loss": 1.1808, "step": 1585 }, { "epoch": 0.26, "learning_rate": 2.6107095926412615e-05, "loss": 0.8731, "step": 1586 }, { "epoch": 0.26, "learning_rate": 2.6104632063074903e-05, "loss": 1.1287, "step": 1587 }, { "epoch": 0.26, "learning_rate": 2.6102168199737187e-05, "loss": 0.6423, "step": 1588 }, { "epoch": 0.26, "learning_rate": 2.6099704336399475e-05, "loss": 1.0039, "step": 1589 }, { "epoch": 0.26, "learning_rate": 2.609724047306176e-05, "loss": 1.3893, "step": 1590 }, { "epoch": 0.26, "learning_rate": 2.6094776609724047e-05, "loss": 0.8981, "step": 1591 }, { "epoch": 0.26, "learning_rate": 2.6092312746386335e-05, "loss": 1.2424, "step": 1592 }, { "epoch": 0.26, "learning_rate": 2.608984888304862e-05, "loss": 1.1549, "step": 1593 }, { "epoch": 0.26, "learning_rate": 2.608738501971091e-05, "loss": 0.696, "step": 1594 }, { "epoch": 0.26, "learning_rate": 2.6084921156373194e-05, "loss": 0.902, "step": 1595 }, { "epoch": 0.26, "learning_rate": 2.6082457293035482e-05, "loss": 0.9947, "step": 1596 }, { "epoch": 0.26, "learning_rate": 2.6079993429697766e-05, "loss": 0.9207, "step": 1597 }, { "epoch": 0.26, "learning_rate": 2.6077529566360054e-05, "loss": 1.143, "step": 1598 }, { "epoch": 0.26, "learning_rate": 2.6075065703022338e-05, "loss": 1.2408, "step": 1599 }, { "epoch": 0.26, "learning_rate": 2.6072601839684626e-05, "loss": 1.4775, "step": 1600 }, { "epoch": 0.26, "learning_rate": 2.607013797634691e-05, "loss": 1.3449, "step": 1601 }, { "epoch": 0.26, "learning_rate": 2.6067674113009198e-05, "loss": 0.6635, "step": 1602 }, { "epoch": 0.26, "learning_rate": 2.6065210249671486e-05, "loss": 1.5835, "step": 1603 }, { "epoch": 0.26, "learning_rate": 2.6062746386333773e-05, "loss": 0.584, "step": 1604 }, { "epoch": 0.26, "learning_rate": 2.606028252299606e-05, "loss": 0.8651, "step": 1605 }, { "epoch": 0.26, "learning_rate": 2.6057818659658345e-05, "loss": 1.0052, "step": 1606 }, { "epoch": 0.26, "learning_rate": 2.6055354796320633e-05, "loss": 1.2643, "step": 1607 }, { "epoch": 0.26, "learning_rate": 2.6052890932982917e-05, "loss": 1.3948, "step": 1608 }, { "epoch": 0.26, "learning_rate": 2.6050427069645205e-05, "loss": 0.5684, "step": 1609 }, { "epoch": 0.26, "learning_rate": 2.604796320630749e-05, "loss": 1.0329, "step": 1610 }, { "epoch": 0.26, "learning_rate": 2.6045499342969777e-05, "loss": 0.9159, "step": 1611 }, { "epoch": 0.26, "learning_rate": 2.604303547963206e-05, "loss": 0.8978, "step": 1612 }, { "epoch": 0.26, "learning_rate": 2.604057161629435e-05, "loss": 0.8956, "step": 1613 }, { "epoch": 0.27, "learning_rate": 2.6038107752956636e-05, "loss": 0.7234, "step": 1614 }, { "epoch": 0.27, "learning_rate": 2.6035643889618924e-05, "loss": 1.4001, "step": 1615 }, { "epoch": 0.27, "learning_rate": 2.6033180026281212e-05, "loss": 1.265, "step": 1616 }, { "epoch": 0.27, "learning_rate": 2.6030716162943496e-05, "loss": 0.5159, "step": 1617 }, { "epoch": 0.27, "learning_rate": 2.6028252299605784e-05, "loss": 0.9687, "step": 1618 }, { "epoch": 0.27, "learning_rate": 2.6025788436268068e-05, "loss": 0.6172, "step": 1619 }, { "epoch": 0.27, "learning_rate": 2.6023324572930356e-05, "loss": 0.6411, "step": 1620 }, { "epoch": 0.27, "learning_rate": 2.602086070959264e-05, "loss": 1.4498, "step": 1621 }, { "epoch": 0.27, "learning_rate": 2.6018396846254928e-05, "loss": 0.7118, "step": 1622 }, { "epoch": 0.27, "learning_rate": 2.6015932982917212e-05, "loss": 1.0063, "step": 1623 }, { "epoch": 0.27, "learning_rate": 2.6013469119579503e-05, "loss": 0.8837, "step": 1624 }, { "epoch": 0.27, "learning_rate": 2.6011005256241787e-05, "loss": 1.0945, "step": 1625 }, { "epoch": 0.27, "learning_rate": 2.6008541392904075e-05, "loss": 0.698, "step": 1626 }, { "epoch": 0.27, "learning_rate": 2.6006077529566363e-05, "loss": 0.6534, "step": 1627 }, { "epoch": 0.27, "learning_rate": 2.6003613666228647e-05, "loss": 1.1556, "step": 1628 }, { "epoch": 0.27, "learning_rate": 2.6001149802890935e-05, "loss": 0.5088, "step": 1629 }, { "epoch": 0.27, "learning_rate": 2.599868593955322e-05, "loss": 1.3232, "step": 1630 }, { "epoch": 0.27, "learning_rate": 2.5996222076215507e-05, "loss": 0.804, "step": 1631 }, { "epoch": 0.27, "learning_rate": 2.599375821287779e-05, "loss": 0.7825, "step": 1632 }, { "epoch": 0.27, "learning_rate": 2.599129434954008e-05, "loss": 1.0496, "step": 1633 }, { "epoch": 0.27, "learning_rate": 2.5988830486202366e-05, "loss": 1.5846, "step": 1634 }, { "epoch": 0.27, "learning_rate": 2.5986366622864654e-05, "loss": 0.8958, "step": 1635 }, { "epoch": 0.27, "learning_rate": 2.5983902759526938e-05, "loss": 1.3237, "step": 1636 }, { "epoch": 0.27, "learning_rate": 2.5981438896189226e-05, "loss": 0.5204, "step": 1637 }, { "epoch": 0.27, "learning_rate": 2.597897503285151e-05, "loss": 0.7631, "step": 1638 }, { "epoch": 0.27, "learning_rate": 2.5976511169513798e-05, "loss": 0.8546, "step": 1639 }, { "epoch": 0.27, "learning_rate": 2.5974047306176086e-05, "loss": 0.6797, "step": 1640 }, { "epoch": 0.27, "learning_rate": 2.597158344283837e-05, "loss": 0.4929, "step": 1641 }, { "epoch": 0.27, "learning_rate": 2.5969119579500658e-05, "loss": 1.2844, "step": 1642 }, { "epoch": 0.27, "learning_rate": 2.5966655716162942e-05, "loss": 0.7164, "step": 1643 }, { "epoch": 0.27, "learning_rate": 2.5964191852825233e-05, "loss": 0.4341, "step": 1644 }, { "epoch": 0.27, "learning_rate": 2.5961727989487517e-05, "loss": 1.0791, "step": 1645 }, { "epoch": 0.27, "learning_rate": 2.5959264126149805e-05, "loss": 0.7089, "step": 1646 }, { "epoch": 0.27, "learning_rate": 2.595680026281209e-05, "loss": 1.002, "step": 1647 }, { "epoch": 0.27, "learning_rate": 2.5954336399474377e-05, "loss": 1.2496, "step": 1648 }, { "epoch": 0.27, "learning_rate": 2.595187253613666e-05, "loss": 0.8052, "step": 1649 }, { "epoch": 0.27, "learning_rate": 2.594940867279895e-05, "loss": 0.253, "step": 1650 }, { "epoch": 0.27, "learning_rate": 2.5946944809461236e-05, "loss": 1.0529, "step": 1651 }, { "epoch": 0.27, "learning_rate": 2.594448094612352e-05, "loss": 1.0673, "step": 1652 }, { "epoch": 0.27, "learning_rate": 2.594201708278581e-05, "loss": 1.7538, "step": 1653 }, { "epoch": 0.27, "learning_rate": 2.5939553219448096e-05, "loss": 0.6141, "step": 1654 }, { "epoch": 0.27, "learning_rate": 2.5937089356110384e-05, "loss": 0.7755, "step": 1655 }, { "epoch": 0.27, "learning_rate": 2.5934625492772668e-05, "loss": 1.5767, "step": 1656 }, { "epoch": 0.27, "learning_rate": 2.5932161629434956e-05, "loss": 0.518, "step": 1657 }, { "epoch": 0.27, "learning_rate": 2.592969776609724e-05, "loss": 0.6706, "step": 1658 }, { "epoch": 0.27, "learning_rate": 2.5927233902759528e-05, "loss": 0.7105, "step": 1659 }, { "epoch": 0.27, "learning_rate": 2.5924770039421812e-05, "loss": 0.7577, "step": 1660 }, { "epoch": 0.27, "learning_rate": 2.59223061760841e-05, "loss": 0.7935, "step": 1661 }, { "epoch": 0.27, "learning_rate": 2.5919842312746387e-05, "loss": 1.1238, "step": 1662 }, { "epoch": 0.27, "learning_rate": 2.591737844940867e-05, "loss": 0.7332, "step": 1663 }, { "epoch": 0.27, "learning_rate": 2.5914914586070963e-05, "loss": 2.1, "step": 1664 }, { "epoch": 0.27, "learning_rate": 2.5912450722733247e-05, "loss": 1.1227, "step": 1665 }, { "epoch": 0.27, "learning_rate": 2.5909986859395535e-05, "loss": 0.5953, "step": 1666 }, { "epoch": 0.27, "learning_rate": 2.590752299605782e-05, "loss": 0.7286, "step": 1667 }, { "epoch": 0.27, "learning_rate": 2.5905059132720107e-05, "loss": 1.229, "step": 1668 }, { "epoch": 0.27, "learning_rate": 2.590259526938239e-05, "loss": 0.7627, "step": 1669 }, { "epoch": 0.27, "learning_rate": 2.590013140604468e-05, "loss": 0.6738, "step": 1670 }, { "epoch": 0.27, "learning_rate": 2.5897667542706963e-05, "loss": 0.8633, "step": 1671 }, { "epoch": 0.27, "learning_rate": 2.589520367936925e-05, "loss": 0.6114, "step": 1672 }, { "epoch": 0.27, "learning_rate": 2.5892739816031535e-05, "loss": 0.8912, "step": 1673 }, { "epoch": 0.27, "learning_rate": 2.5890275952693826e-05, "loss": 0.9795, "step": 1674 }, { "epoch": 0.28, "learning_rate": 2.5887812089356114e-05, "loss": 1.134, "step": 1675 }, { "epoch": 0.28, "learning_rate": 2.5885348226018398e-05, "loss": 1.1437, "step": 1676 }, { "epoch": 0.28, "learning_rate": 2.5882884362680686e-05, "loss": 0.5918, "step": 1677 }, { "epoch": 0.28, "learning_rate": 2.588042049934297e-05, "loss": 0.7004, "step": 1678 }, { "epoch": 0.28, "learning_rate": 2.5877956636005258e-05, "loss": 1.2781, "step": 1679 }, { "epoch": 0.28, "learning_rate": 2.5875492772667542e-05, "loss": 0.5334, "step": 1680 }, { "epoch": 0.28, "learning_rate": 2.587302890932983e-05, "loss": 0.6847, "step": 1681 }, { "epoch": 0.28, "learning_rate": 2.5870565045992114e-05, "loss": 0.532, "step": 1682 }, { "epoch": 0.28, "learning_rate": 2.58681011826544e-05, "loss": 1.4316, "step": 1683 }, { "epoch": 0.28, "learning_rate": 2.586563731931669e-05, "loss": 1.448, "step": 1684 }, { "epoch": 0.28, "learning_rate": 2.5863173455978977e-05, "loss": 0.7086, "step": 1685 }, { "epoch": 0.28, "learning_rate": 2.5860709592641265e-05, "loss": 0.8334, "step": 1686 }, { "epoch": 0.28, "learning_rate": 2.585824572930355e-05, "loss": 0.9995, "step": 1687 }, { "epoch": 0.28, "learning_rate": 2.5855781865965837e-05, "loss": 1.8185, "step": 1688 }, { "epoch": 0.28, "learning_rate": 2.585331800262812e-05, "loss": 1.0456, "step": 1689 }, { "epoch": 0.28, "learning_rate": 2.585085413929041e-05, "loss": 0.7869, "step": 1690 }, { "epoch": 0.28, "learning_rate": 2.5848390275952693e-05, "loss": 0.9561, "step": 1691 }, { "epoch": 0.28, "learning_rate": 2.584592641261498e-05, "loss": 1.2884, "step": 1692 }, { "epoch": 0.28, "learning_rate": 2.5843462549277265e-05, "loss": 1.3801, "step": 1693 }, { "epoch": 0.28, "learning_rate": 2.5840998685939556e-05, "loss": 1.1747, "step": 1694 }, { "epoch": 0.28, "learning_rate": 2.583853482260184e-05, "loss": 0.3532, "step": 1695 }, { "epoch": 0.28, "learning_rate": 2.5836070959264128e-05, "loss": 1.2486, "step": 1696 }, { "epoch": 0.28, "learning_rate": 2.5833607095926412e-05, "loss": 0.8642, "step": 1697 }, { "epoch": 0.28, "learning_rate": 2.58311432325887e-05, "loss": 1.84, "step": 1698 }, { "epoch": 0.28, "learning_rate": 2.5828679369250987e-05, "loss": 1.2673, "step": 1699 }, { "epoch": 0.28, "learning_rate": 2.5826215505913272e-05, "loss": 0.8901, "step": 1700 }, { "epoch": 0.28, "learning_rate": 2.582375164257556e-05, "loss": 0.9956, "step": 1701 }, { "epoch": 0.28, "learning_rate": 2.5821287779237844e-05, "loss": 0.9182, "step": 1702 }, { "epoch": 0.28, "learning_rate": 2.581882391590013e-05, "loss": 0.7051, "step": 1703 }, { "epoch": 0.28, "learning_rate": 2.581636005256242e-05, "loss": 1.3262, "step": 1704 }, { "epoch": 0.28, "learning_rate": 2.5813896189224707e-05, "loss": 1.0101, "step": 1705 }, { "epoch": 0.28, "learning_rate": 2.581143232588699e-05, "loss": 1.0085, "step": 1706 }, { "epoch": 0.28, "learning_rate": 2.580896846254928e-05, "loss": 1.5421, "step": 1707 }, { "epoch": 0.28, "learning_rate": 2.5806504599211563e-05, "loss": 0.7075, "step": 1708 }, { "epoch": 0.28, "learning_rate": 2.580404073587385e-05, "loss": 0.753, "step": 1709 }, { "epoch": 0.28, "learning_rate": 2.580157687253614e-05, "loss": 0.8706, "step": 1710 }, { "epoch": 0.28, "learning_rate": 2.5799113009198423e-05, "loss": 0.5472, "step": 1711 }, { "epoch": 0.28, "learning_rate": 2.579664914586071e-05, "loss": 0.7941, "step": 1712 }, { "epoch": 0.28, "learning_rate": 2.5794185282522995e-05, "loss": 0.9317, "step": 1713 }, { "epoch": 0.28, "learning_rate": 2.5791721419185286e-05, "loss": 1.2201, "step": 1714 }, { "epoch": 0.28, "learning_rate": 2.578925755584757e-05, "loss": 0.9303, "step": 1715 }, { "epoch": 0.28, "learning_rate": 2.5786793692509858e-05, "loss": 0.5729, "step": 1716 }, { "epoch": 0.28, "learning_rate": 2.5784329829172142e-05, "loss": 1.2652, "step": 1717 }, { "epoch": 0.28, "learning_rate": 2.578186596583443e-05, "loss": 0.9609, "step": 1718 }, { "epoch": 0.28, "learning_rate": 2.5779402102496714e-05, "loss": 0.6582, "step": 1719 }, { "epoch": 0.28, "learning_rate": 2.5776938239159e-05, "loss": 1.1423, "step": 1720 }, { "epoch": 0.28, "learning_rate": 2.5774474375821286e-05, "loss": 1.0839, "step": 1721 }, { "epoch": 0.28, "learning_rate": 2.5772010512483574e-05, "loss": 1.4084, "step": 1722 }, { "epoch": 0.28, "learning_rate": 2.576954664914586e-05, "loss": 0.7872, "step": 1723 }, { "epoch": 0.28, "learning_rate": 2.576708278580815e-05, "loss": 0.9525, "step": 1724 }, { "epoch": 0.28, "learning_rate": 2.5764618922470437e-05, "loss": 0.9078, "step": 1725 }, { "epoch": 0.28, "learning_rate": 2.576215505913272e-05, "loss": 1.2174, "step": 1726 }, { "epoch": 0.28, "learning_rate": 2.575969119579501e-05, "loss": 1.4457, "step": 1727 }, { "epoch": 0.28, "learning_rate": 2.5757227332457293e-05, "loss": 0.8779, "step": 1728 }, { "epoch": 0.28, "learning_rate": 2.575476346911958e-05, "loss": 0.7937, "step": 1729 }, { "epoch": 0.28, "learning_rate": 2.5752299605781865e-05, "loss": 0.9375, "step": 1730 }, { "epoch": 0.28, "learning_rate": 2.5749835742444153e-05, "loss": 0.7814, "step": 1731 }, { "epoch": 0.28, "learning_rate": 2.5747371879106437e-05, "loss": 0.75, "step": 1732 }, { "epoch": 0.28, "learning_rate": 2.5744908015768724e-05, "loss": 0.9034, "step": 1733 }, { "epoch": 0.28, "learning_rate": 2.5742444152431016e-05, "loss": 1.5903, "step": 1734 }, { "epoch": 0.28, "learning_rate": 2.57399802890933e-05, "loss": 0.8869, "step": 1735 }, { "epoch": 0.29, "learning_rate": 2.5737516425755588e-05, "loss": 0.6231, "step": 1736 }, { "epoch": 0.29, "learning_rate": 2.5735052562417872e-05, "loss": 1.0419, "step": 1737 }, { "epoch": 0.29, "learning_rate": 2.573258869908016e-05, "loss": 1.6667, "step": 1738 }, { "epoch": 0.29, "learning_rate": 2.5730124835742444e-05, "loss": 0.5901, "step": 1739 }, { "epoch": 0.29, "learning_rate": 2.572766097240473e-05, "loss": 1.1073, "step": 1740 }, { "epoch": 0.29, "learning_rate": 2.5725197109067016e-05, "loss": 0.8563, "step": 1741 }, { "epoch": 0.29, "learning_rate": 2.5722733245729303e-05, "loss": 0.8215, "step": 1742 }, { "epoch": 0.29, "learning_rate": 2.5720269382391588e-05, "loss": 0.8862, "step": 1743 }, { "epoch": 0.29, "learning_rate": 2.571780551905388e-05, "loss": 0.3782, "step": 1744 }, { "epoch": 0.29, "learning_rate": 2.5715341655716163e-05, "loss": 1.2181, "step": 1745 }, { "epoch": 0.29, "learning_rate": 2.571287779237845e-05, "loss": 1.1385, "step": 1746 }, { "epoch": 0.29, "learning_rate": 2.571041392904074e-05, "loss": 1.2156, "step": 1747 }, { "epoch": 0.29, "learning_rate": 2.5707950065703023e-05, "loss": 0.7305, "step": 1748 }, { "epoch": 0.29, "learning_rate": 2.570548620236531e-05, "loss": 0.8237, "step": 1749 }, { "epoch": 0.29, "learning_rate": 2.5703022339027595e-05, "loss": 0.56, "step": 1750 }, { "epoch": 0.29, "learning_rate": 2.5700558475689882e-05, "loss": 1.3878, "step": 1751 }, { "epoch": 0.29, "learning_rate": 2.5698094612352167e-05, "loss": 1.0624, "step": 1752 }, { "epoch": 0.29, "learning_rate": 2.5695630749014454e-05, "loss": 0.8277, "step": 1753 }, { "epoch": 0.29, "learning_rate": 2.5693166885676742e-05, "loss": 1.3384, "step": 1754 }, { "epoch": 0.29, "learning_rate": 2.569070302233903e-05, "loss": 0.7255, "step": 1755 }, { "epoch": 0.29, "learning_rate": 2.5688239159001314e-05, "loss": 1.1457, "step": 1756 }, { "epoch": 0.29, "learning_rate": 2.56857752956636e-05, "loss": 1.463, "step": 1757 }, { "epoch": 0.29, "learning_rate": 2.568331143232589e-05, "loss": 1.3759, "step": 1758 }, { "epoch": 0.29, "learning_rate": 2.5680847568988174e-05, "loss": 0.6042, "step": 1759 }, { "epoch": 0.29, "learning_rate": 2.567838370565046e-05, "loss": 1.3673, "step": 1760 }, { "epoch": 0.29, "learning_rate": 2.5675919842312746e-05, "loss": 0.9448, "step": 1761 }, { "epoch": 0.29, "learning_rate": 2.5673455978975033e-05, "loss": 0.6419, "step": 1762 }, { "epoch": 0.29, "learning_rate": 2.5670992115637318e-05, "loss": 0.6439, "step": 1763 }, { "epoch": 0.29, "learning_rate": 2.566852825229961e-05, "loss": 0.6884, "step": 1764 }, { "epoch": 0.29, "learning_rate": 2.5666064388961893e-05, "loss": 0.9388, "step": 1765 }, { "epoch": 0.29, "learning_rate": 2.566360052562418e-05, "loss": 1.4251, "step": 1766 }, { "epoch": 0.29, "learning_rate": 2.5661136662286465e-05, "loss": 1.4525, "step": 1767 }, { "epoch": 0.29, "learning_rate": 2.5658672798948753e-05, "loss": 1.4841, "step": 1768 }, { "epoch": 0.29, "learning_rate": 2.5656208935611037e-05, "loss": 1.1572, "step": 1769 }, { "epoch": 0.29, "learning_rate": 2.5653745072273325e-05, "loss": 1.1812, "step": 1770 }, { "epoch": 0.29, "learning_rate": 2.5651281208935612e-05, "loss": 1.1729, "step": 1771 }, { "epoch": 0.29, "learning_rate": 2.5648817345597897e-05, "loss": 0.6235, "step": 1772 }, { "epoch": 0.29, "learning_rate": 2.5646353482260184e-05, "loss": 1.3523, "step": 1773 }, { "epoch": 0.29, "learning_rate": 2.5643889618922472e-05, "loss": 0.2449, "step": 1774 }, { "epoch": 0.29, "learning_rate": 2.564142575558476e-05, "loss": 0.7884, "step": 1775 }, { "epoch": 0.29, "learning_rate": 2.5638961892247044e-05, "loss": 1.0821, "step": 1776 }, { "epoch": 0.29, "learning_rate": 2.563649802890933e-05, "loss": 1.4186, "step": 1777 }, { "epoch": 0.29, "learning_rate": 2.5634034165571616e-05, "loss": 1.2276, "step": 1778 }, { "epoch": 0.29, "learning_rate": 2.5631570302233903e-05, "loss": 1.2898, "step": 1779 }, { "epoch": 0.29, "learning_rate": 2.5629106438896188e-05, "loss": 0.8694, "step": 1780 }, { "epoch": 0.29, "learning_rate": 2.5626642575558475e-05, "loss": 0.9086, "step": 1781 }, { "epoch": 0.29, "learning_rate": 2.5624178712220763e-05, "loss": 1.2825, "step": 1782 }, { "epoch": 0.29, "learning_rate": 2.5621714848883047e-05, "loss": 1.0486, "step": 1783 }, { "epoch": 0.29, "learning_rate": 2.561925098554534e-05, "loss": 0.7165, "step": 1784 }, { "epoch": 0.29, "learning_rate": 2.5616787122207623e-05, "loss": 0.8397, "step": 1785 }, { "epoch": 0.29, "learning_rate": 2.561432325886991e-05, "loss": 1.0679, "step": 1786 }, { "epoch": 0.29, "learning_rate": 2.5611859395532195e-05, "loss": 0.9103, "step": 1787 }, { "epoch": 0.29, "learning_rate": 2.5609395532194482e-05, "loss": 1.033, "step": 1788 }, { "epoch": 0.29, "learning_rate": 2.5606931668856767e-05, "loss": 0.4348, "step": 1789 }, { "epoch": 0.29, "learning_rate": 2.5604467805519054e-05, "loss": 0.4578, "step": 1790 }, { "epoch": 0.29, "learning_rate": 2.560200394218134e-05, "loss": 0.7642, "step": 1791 }, { "epoch": 0.29, "learning_rate": 2.5599540078843626e-05, "loss": 1.2491, "step": 1792 }, { "epoch": 0.29, "learning_rate": 2.5597076215505914e-05, "loss": 0.8143, "step": 1793 }, { "epoch": 0.29, "learning_rate": 2.5594612352168202e-05, "loss": 0.492, "step": 1794 }, { "epoch": 0.29, "learning_rate": 2.559214848883049e-05, "loss": 0.6483, "step": 1795 }, { "epoch": 0.3, "learning_rate": 2.5589684625492774e-05, "loss": 0.8442, "step": 1796 }, { "epoch": 0.3, "learning_rate": 2.558722076215506e-05, "loss": 0.4387, "step": 1797 }, { "epoch": 0.3, "learning_rate": 2.5584756898817346e-05, "loss": 1.2813, "step": 1798 }, { "epoch": 0.3, "learning_rate": 2.5582293035479633e-05, "loss": 1.2439, "step": 1799 }, { "epoch": 0.3, "learning_rate": 2.5579829172141918e-05, "loss": 0.7514, "step": 1800 }, { "epoch": 0.3, "learning_rate": 2.5577365308804205e-05, "loss": 0.7251, "step": 1801 }, { "epoch": 0.3, "learning_rate": 2.557490144546649e-05, "loss": 0.9783, "step": 1802 }, { "epoch": 0.3, "learning_rate": 2.5572437582128777e-05, "loss": 0.813, "step": 1803 }, { "epoch": 0.3, "learning_rate": 2.5569973718791065e-05, "loss": 0.4428, "step": 1804 }, { "epoch": 0.3, "learning_rate": 2.5567509855453353e-05, "loss": 0.7294, "step": 1805 }, { "epoch": 0.3, "learning_rate": 2.556504599211564e-05, "loss": 1.6274, "step": 1806 }, { "epoch": 0.3, "learning_rate": 2.5562582128777925e-05, "loss": 0.722, "step": 1807 }, { "epoch": 0.3, "learning_rate": 2.5560118265440212e-05, "loss": 1.2837, "step": 1808 }, { "epoch": 0.3, "learning_rate": 2.5557654402102497e-05, "loss": 0.6785, "step": 1809 }, { "epoch": 0.3, "learning_rate": 2.5555190538764784e-05, "loss": 1.6774, "step": 1810 }, { "epoch": 0.3, "learning_rate": 2.555272667542707e-05, "loss": 0.7729, "step": 1811 }, { "epoch": 0.3, "learning_rate": 2.5550262812089356e-05, "loss": 0.5839, "step": 1812 }, { "epoch": 0.3, "learning_rate": 2.554779894875164e-05, "loss": 0.9475, "step": 1813 }, { "epoch": 0.3, "learning_rate": 2.554533508541393e-05, "loss": 0.9053, "step": 1814 }, { "epoch": 0.3, "learning_rate": 2.5542871222076216e-05, "loss": 1.5427, "step": 1815 }, { "epoch": 0.3, "learning_rate": 2.5540407358738504e-05, "loss": 1.2563, "step": 1816 }, { "epoch": 0.3, "learning_rate": 2.553794349540079e-05, "loss": 1.3211, "step": 1817 }, { "epoch": 0.3, "learning_rate": 2.5535479632063076e-05, "loss": 1.5064, "step": 1818 }, { "epoch": 0.3, "learning_rate": 2.5533015768725363e-05, "loss": 1.0237, "step": 1819 }, { "epoch": 0.3, "learning_rate": 2.5530551905387647e-05, "loss": 0.9707, "step": 1820 }, { "epoch": 0.3, "learning_rate": 2.5528088042049935e-05, "loss": 1.0256, "step": 1821 }, { "epoch": 0.3, "learning_rate": 2.552562417871222e-05, "loss": 0.6486, "step": 1822 }, { "epoch": 0.3, "learning_rate": 2.5523160315374507e-05, "loss": 0.9575, "step": 1823 }, { "epoch": 0.3, "learning_rate": 2.5520696452036795e-05, "loss": 0.8661, "step": 1824 }, { "epoch": 0.3, "learning_rate": 2.5518232588699082e-05, "loss": 0.6575, "step": 1825 }, { "epoch": 0.3, "learning_rate": 2.5515768725361367e-05, "loss": 0.9708, "step": 1826 }, { "epoch": 0.3, "learning_rate": 2.5513304862023654e-05, "loss": 1.2452, "step": 1827 }, { "epoch": 0.3, "learning_rate": 2.551084099868594e-05, "loss": 0.8675, "step": 1828 }, { "epoch": 0.3, "learning_rate": 2.5508377135348226e-05, "loss": 0.7883, "step": 1829 }, { "epoch": 0.3, "learning_rate": 2.5505913272010514e-05, "loss": 1.8169, "step": 1830 }, { "epoch": 0.3, "learning_rate": 2.55034494086728e-05, "loss": 0.5803, "step": 1831 }, { "epoch": 0.3, "learning_rate": 2.5500985545335086e-05, "loss": 0.9322, "step": 1832 }, { "epoch": 0.3, "learning_rate": 2.549852168199737e-05, "loss": 0.6713, "step": 1833 }, { "epoch": 0.3, "learning_rate": 2.549605781865966e-05, "loss": 1.5015, "step": 1834 }, { "epoch": 0.3, "learning_rate": 2.5493593955321946e-05, "loss": 1.295, "step": 1835 }, { "epoch": 0.3, "learning_rate": 2.5491130091984233e-05, "loss": 1.0358, "step": 1836 }, { "epoch": 0.3, "learning_rate": 2.5488666228646518e-05, "loss": 1.4, "step": 1837 }, { "epoch": 0.3, "learning_rate": 2.5486202365308805e-05, "loss": 1.575, "step": 1838 }, { "epoch": 0.3, "learning_rate": 2.548373850197109e-05, "loss": 1.0496, "step": 1839 }, { "epoch": 0.3, "learning_rate": 2.5481274638633377e-05, "loss": 1.366, "step": 1840 }, { "epoch": 0.3, "learning_rate": 2.5478810775295665e-05, "loss": 0.5948, "step": 1841 }, { "epoch": 0.3, "learning_rate": 2.547634691195795e-05, "loss": 1.4855, "step": 1842 }, { "epoch": 0.3, "learning_rate": 2.5473883048620237e-05, "loss": 1.5713, "step": 1843 }, { "epoch": 0.3, "learning_rate": 2.5471419185282525e-05, "loss": 0.8491, "step": 1844 }, { "epoch": 0.3, "learning_rate": 2.5468955321944812e-05, "loss": 1.7395, "step": 1845 }, { "epoch": 0.3, "learning_rate": 2.5466491458607097e-05, "loss": 1.1257, "step": 1846 }, { "epoch": 0.3, "learning_rate": 2.5464027595269384e-05, "loss": 0.6883, "step": 1847 }, { "epoch": 0.3, "learning_rate": 2.546156373193167e-05, "loss": 0.8112, "step": 1848 }, { "epoch": 0.3, "learning_rate": 2.5459099868593956e-05, "loss": 0.7666, "step": 1849 }, { "epoch": 0.3, "learning_rate": 2.545663600525624e-05, "loss": 0.8171, "step": 1850 }, { "epoch": 0.3, "learning_rate": 2.5454172141918528e-05, "loss": 0.6326, "step": 1851 }, { "epoch": 0.3, "learning_rate": 2.5451708278580813e-05, "loss": 0.7562, "step": 1852 }, { "epoch": 0.3, "learning_rate": 2.54492444152431e-05, "loss": 1.8639, "step": 1853 }, { "epoch": 0.3, "learning_rate": 2.544678055190539e-05, "loss": 0.6276, "step": 1854 }, { "epoch": 0.3, "learning_rate": 2.5444316688567676e-05, "loss": 0.7973, "step": 1855 }, { "epoch": 0.3, "learning_rate": 2.5441852825229963e-05, "loss": 0.9187, "step": 1856 }, { "epoch": 0.31, "learning_rate": 2.5439388961892248e-05, "loss": 1.7996, "step": 1857 }, { "epoch": 0.31, "learning_rate": 2.5436925098554535e-05, "loss": 1.3219, "step": 1858 }, { "epoch": 0.31, "learning_rate": 2.543446123521682e-05, "loss": 0.6135, "step": 1859 }, { "epoch": 0.31, "learning_rate": 2.5431997371879107e-05, "loss": 0.5821, "step": 1860 }, { "epoch": 0.31, "learning_rate": 2.542953350854139e-05, "loss": 1.5906, "step": 1861 }, { "epoch": 0.31, "learning_rate": 2.542706964520368e-05, "loss": 1.362, "step": 1862 }, { "epoch": 0.31, "learning_rate": 2.5424605781865963e-05, "loss": 0.6925, "step": 1863 }, { "epoch": 0.31, "learning_rate": 2.5422141918528255e-05, "loss": 1.411, "step": 1864 }, { "epoch": 0.31, "learning_rate": 2.5419678055190542e-05, "loss": 0.8406, "step": 1865 }, { "epoch": 0.31, "learning_rate": 2.5417214191852826e-05, "loss": 0.5668, "step": 1866 }, { "epoch": 0.31, "learning_rate": 2.5414750328515114e-05, "loss": 0.5362, "step": 1867 }, { "epoch": 0.31, "learning_rate": 2.54122864651774e-05, "loss": 0.6887, "step": 1868 }, { "epoch": 0.31, "learning_rate": 2.5409822601839686e-05, "loss": 1.3977, "step": 1869 }, { "epoch": 0.31, "learning_rate": 2.540735873850197e-05, "loss": 1.5835, "step": 1870 }, { "epoch": 0.31, "learning_rate": 2.5404894875164258e-05, "loss": 1.1257, "step": 1871 }, { "epoch": 0.31, "learning_rate": 2.5402431011826542e-05, "loss": 2.1035, "step": 1872 }, { "epoch": 0.31, "learning_rate": 2.539996714848883e-05, "loss": 1.2401, "step": 1873 }, { "epoch": 0.31, "learning_rate": 2.5397503285151118e-05, "loss": 1.7987, "step": 1874 }, { "epoch": 0.31, "learning_rate": 2.5395039421813405e-05, "loss": 1.133, "step": 1875 }, { "epoch": 0.31, "learning_rate": 2.539257555847569e-05, "loss": 0.311, "step": 1876 }, { "epoch": 0.31, "learning_rate": 2.5390111695137977e-05, "loss": 0.9078, "step": 1877 }, { "epoch": 0.31, "learning_rate": 2.5387647831800265e-05, "loss": 0.5775, "step": 1878 }, { "epoch": 0.31, "learning_rate": 2.538518396846255e-05, "loss": 0.7369, "step": 1879 }, { "epoch": 0.31, "learning_rate": 2.5382720105124837e-05, "loss": 1.0383, "step": 1880 }, { "epoch": 0.31, "learning_rate": 2.538025624178712e-05, "loss": 1.0322, "step": 1881 }, { "epoch": 0.31, "learning_rate": 2.537779237844941e-05, "loss": 0.8272, "step": 1882 }, { "epoch": 0.31, "learning_rate": 2.5375328515111693e-05, "loss": 0.6153, "step": 1883 }, { "epoch": 0.31, "learning_rate": 2.5372864651773984e-05, "loss": 0.3886, "step": 1884 }, { "epoch": 0.31, "learning_rate": 2.537040078843627e-05, "loss": 1.4256, "step": 1885 }, { "epoch": 0.31, "learning_rate": 2.5367936925098556e-05, "loss": 1.0317, "step": 1886 }, { "epoch": 0.31, "learning_rate": 2.536547306176084e-05, "loss": 0.7186, "step": 1887 }, { "epoch": 0.31, "learning_rate": 2.536300919842313e-05, "loss": 1.4291, "step": 1888 }, { "epoch": 0.31, "learning_rate": 2.5360545335085416e-05, "loss": 0.8893, "step": 1889 }, { "epoch": 0.31, "learning_rate": 2.53580814717477e-05, "loss": 0.5986, "step": 1890 }, { "epoch": 0.31, "learning_rate": 2.5355617608409988e-05, "loss": 0.9853, "step": 1891 }, { "epoch": 0.31, "learning_rate": 2.5353153745072272e-05, "loss": 0.4931, "step": 1892 }, { "epoch": 0.31, "learning_rate": 2.535068988173456e-05, "loss": 0.96, "step": 1893 }, { "epoch": 0.31, "learning_rate": 2.5348226018396848e-05, "loss": 1.2373, "step": 1894 }, { "epoch": 0.31, "learning_rate": 2.5345762155059135e-05, "loss": 1.8229, "step": 1895 }, { "epoch": 0.31, "learning_rate": 2.534329829172142e-05, "loss": 1.1763, "step": 1896 }, { "epoch": 0.31, "learning_rate": 2.5340834428383707e-05, "loss": 0.5221, "step": 1897 }, { "epoch": 0.31, "learning_rate": 2.533837056504599e-05, "loss": 1.1836, "step": 1898 }, { "epoch": 0.31, "learning_rate": 2.533590670170828e-05, "loss": 1.3016, "step": 1899 }, { "epoch": 0.31, "learning_rate": 2.5333442838370564e-05, "loss": 0.4532, "step": 1900 }, { "epoch": 0.31, "learning_rate": 2.533097897503285e-05, "loss": 1.3899, "step": 1901 }, { "epoch": 0.31, "learning_rate": 2.532851511169514e-05, "loss": 0.9173, "step": 1902 }, { "epoch": 0.31, "learning_rate": 2.5326051248357423e-05, "loss": 0.7509, "step": 1903 }, { "epoch": 0.31, "learning_rate": 2.5323587385019714e-05, "loss": 1.1104, "step": 1904 }, { "epoch": 0.31, "learning_rate": 2.5321123521682e-05, "loss": 0.8042, "step": 1905 }, { "epoch": 0.31, "learning_rate": 2.5318659658344286e-05, "loss": 1.1434, "step": 1906 }, { "epoch": 0.31, "learning_rate": 2.531619579500657e-05, "loss": 0.4916, "step": 1907 }, { "epoch": 0.31, "learning_rate": 2.5313731931668858e-05, "loss": 1.0504, "step": 1908 }, { "epoch": 0.31, "learning_rate": 2.5311268068331142e-05, "loss": 1.3342, "step": 1909 }, { "epoch": 0.31, "learning_rate": 2.530880420499343e-05, "loss": 0.8419, "step": 1910 }, { "epoch": 0.31, "learning_rate": 2.5306340341655714e-05, "loss": 0.2475, "step": 1911 }, { "epoch": 0.31, "learning_rate": 2.5303876478318002e-05, "loss": 1.4258, "step": 1912 }, { "epoch": 0.31, "learning_rate": 2.530141261498029e-05, "loss": 1.2074, "step": 1913 }, { "epoch": 0.31, "learning_rate": 2.5298948751642577e-05, "loss": 1.0598, "step": 1914 }, { "epoch": 0.31, "learning_rate": 2.5296484888304865e-05, "loss": 1.1266, "step": 1915 }, { "epoch": 0.31, "learning_rate": 2.529402102496715e-05, "loss": 0.5829, "step": 1916 }, { "epoch": 0.31, "learning_rate": 2.5291557161629437e-05, "loss": 0.6817, "step": 1917 }, { "epoch": 0.32, "learning_rate": 2.528909329829172e-05, "loss": 0.6141, "step": 1918 }, { "epoch": 0.32, "learning_rate": 2.528662943495401e-05, "loss": 0.967, "step": 1919 }, { "epoch": 0.32, "learning_rate": 2.5284165571616293e-05, "loss": 0.7447, "step": 1920 }, { "epoch": 0.32, "learning_rate": 2.528170170827858e-05, "loss": 1.022, "step": 1921 }, { "epoch": 0.32, "learning_rate": 2.5279237844940865e-05, "loss": 0.74, "step": 1922 }, { "epoch": 0.32, "learning_rate": 2.5276773981603153e-05, "loss": 2.2768, "step": 1923 }, { "epoch": 0.32, "learning_rate": 2.527431011826544e-05, "loss": 1.0931, "step": 1924 }, { "epoch": 0.32, "learning_rate": 2.527184625492773e-05, "loss": 1.2945, "step": 1925 }, { "epoch": 0.32, "learning_rate": 2.5269382391590016e-05, "loss": 1.1559, "step": 1926 }, { "epoch": 0.32, "learning_rate": 2.52669185282523e-05, "loss": 1.1576, "step": 1927 }, { "epoch": 0.32, "learning_rate": 2.5264454664914588e-05, "loss": 0.676, "step": 1928 }, { "epoch": 0.32, "learning_rate": 2.5261990801576872e-05, "loss": 1.1736, "step": 1929 }, { "epoch": 0.32, "learning_rate": 2.525952693823916e-05, "loss": 0.7444, "step": 1930 }, { "epoch": 0.32, "learning_rate": 2.5257063074901444e-05, "loss": 1.082, "step": 1931 }, { "epoch": 0.32, "learning_rate": 2.5254599211563732e-05, "loss": 1.0599, "step": 1932 }, { "epoch": 0.32, "learning_rate": 2.5252135348226016e-05, "loss": 0.8247, "step": 1933 }, { "epoch": 0.32, "learning_rate": 2.5249671484888307e-05, "loss": 1.203, "step": 1934 }, { "epoch": 0.32, "learning_rate": 2.524720762155059e-05, "loss": 0.908, "step": 1935 }, { "epoch": 0.32, "learning_rate": 2.524474375821288e-05, "loss": 1.0832, "step": 1936 }, { "epoch": 0.32, "learning_rate": 2.5242279894875167e-05, "loss": 1.758, "step": 1937 }, { "epoch": 0.32, "learning_rate": 2.523981603153745e-05, "loss": 0.556, "step": 1938 }, { "epoch": 0.32, "learning_rate": 2.523735216819974e-05, "loss": 0.8685, "step": 1939 }, { "epoch": 0.32, "learning_rate": 2.5234888304862023e-05, "loss": 1.095, "step": 1940 }, { "epoch": 0.32, "learning_rate": 2.523242444152431e-05, "loss": 1.1241, "step": 1941 }, { "epoch": 0.32, "learning_rate": 2.5229960578186595e-05, "loss": 0.5397, "step": 1942 }, { "epoch": 0.32, "learning_rate": 2.5227496714848883e-05, "loss": 0.8162, "step": 1943 }, { "epoch": 0.32, "learning_rate": 2.522503285151117e-05, "loss": 0.9176, "step": 1944 }, { "epoch": 0.32, "learning_rate": 2.5222568988173458e-05, "loss": 0.5886, "step": 1945 }, { "epoch": 0.32, "learning_rate": 2.5220105124835743e-05, "loss": 0.8986, "step": 1946 }, { "epoch": 0.32, "learning_rate": 2.521764126149803e-05, "loss": 0.7284, "step": 1947 }, { "epoch": 0.32, "learning_rate": 2.5215177398160318e-05, "loss": 1.6017, "step": 1948 }, { "epoch": 0.32, "learning_rate": 2.5212713534822602e-05, "loss": 0.3358, "step": 1949 }, { "epoch": 0.32, "learning_rate": 2.521024967148489e-05, "loss": 1.2996, "step": 1950 }, { "epoch": 0.32, "learning_rate": 2.5207785808147174e-05, "loss": 0.4647, "step": 1951 }, { "epoch": 0.32, "learning_rate": 2.5205321944809462e-05, "loss": 0.58, "step": 1952 }, { "epoch": 0.32, "learning_rate": 2.5202858081471746e-05, "loss": 0.9055, "step": 1953 }, { "epoch": 0.32, "learning_rate": 2.5200394218134037e-05, "loss": 1.3202, "step": 1954 }, { "epoch": 0.32, "learning_rate": 2.519793035479632e-05, "loss": 1.1949, "step": 1955 }, { "epoch": 0.32, "learning_rate": 2.519546649145861e-05, "loss": 1.2431, "step": 1956 }, { "epoch": 0.32, "learning_rate": 2.5193002628120893e-05, "loss": 0.4458, "step": 1957 }, { "epoch": 0.32, "learning_rate": 2.519053876478318e-05, "loss": 1.4063, "step": 1958 }, { "epoch": 0.32, "learning_rate": 2.5188074901445465e-05, "loss": 0.5632, "step": 1959 }, { "epoch": 0.32, "learning_rate": 2.5185611038107753e-05, "loss": 1.6254, "step": 1960 }, { "epoch": 0.32, "learning_rate": 2.518314717477004e-05, "loss": 0.8518, "step": 1961 }, { "epoch": 0.32, "learning_rate": 2.5180683311432325e-05, "loss": 0.9382, "step": 1962 }, { "epoch": 0.32, "learning_rate": 2.5178219448094613e-05, "loss": 0.9577, "step": 1963 }, { "epoch": 0.32, "learning_rate": 2.51757555847569e-05, "loss": 0.7137, "step": 1964 }, { "epoch": 0.32, "learning_rate": 2.5173291721419188e-05, "loss": 1.5503, "step": 1965 }, { "epoch": 0.32, "learning_rate": 2.5170827858081472e-05, "loss": 0.9475, "step": 1966 }, { "epoch": 0.32, "learning_rate": 2.516836399474376e-05, "loss": 0.7513, "step": 1967 }, { "epoch": 0.32, "learning_rate": 2.5165900131406044e-05, "loss": 1.4894, "step": 1968 }, { "epoch": 0.32, "learning_rate": 2.5163436268068332e-05, "loss": 0.8838, "step": 1969 }, { "epoch": 0.32, "learning_rate": 2.5160972404730616e-05, "loss": 0.9161, "step": 1970 }, { "epoch": 0.32, "learning_rate": 2.5158508541392904e-05, "loss": 0.7295, "step": 1971 }, { "epoch": 0.32, "learning_rate": 2.515604467805519e-05, "loss": 0.7972, "step": 1972 }, { "epoch": 0.32, "learning_rate": 2.5153580814717476e-05, "loss": 0.9498, "step": 1973 }, { "epoch": 0.32, "learning_rate": 2.5151116951379767e-05, "loss": 0.9074, "step": 1974 }, { "epoch": 0.32, "learning_rate": 2.514865308804205e-05, "loss": 1.4284, "step": 1975 }, { "epoch": 0.32, "learning_rate": 2.514618922470434e-05, "loss": 1.4212, "step": 1976 }, { "epoch": 0.32, "learning_rate": 2.5143725361366623e-05, "loss": 0.7948, "step": 1977 }, { "epoch": 0.32, "learning_rate": 2.514126149802891e-05, "loss": 1.5652, "step": 1978 }, { "epoch": 0.33, "learning_rate": 2.5138797634691195e-05, "loss": 1.1107, "step": 1979 }, { "epoch": 0.33, "learning_rate": 2.5136333771353483e-05, "loss": 0.9499, "step": 1980 }, { "epoch": 0.33, "learning_rate": 2.5133869908015767e-05, "loss": 1.0099, "step": 1981 }, { "epoch": 0.33, "learning_rate": 2.5131406044678055e-05, "loss": 0.7595, "step": 1982 }, { "epoch": 0.33, "learning_rate": 2.512894218134034e-05, "loss": 0.3879, "step": 1983 }, { "epoch": 0.33, "learning_rate": 2.512647831800263e-05, "loss": 0.8496, "step": 1984 }, { "epoch": 0.33, "learning_rate": 2.5124014454664918e-05, "loss": 0.5035, "step": 1985 }, { "epoch": 0.33, "learning_rate": 2.5121550591327202e-05, "loss": 0.749, "step": 1986 }, { "epoch": 0.33, "learning_rate": 2.511908672798949e-05, "loss": 0.9792, "step": 1987 }, { "epoch": 0.33, "learning_rate": 2.5116622864651774e-05, "loss": 1.5903, "step": 1988 }, { "epoch": 0.33, "learning_rate": 2.5114159001314062e-05, "loss": 1.1819, "step": 1989 }, { "epoch": 0.33, "learning_rate": 2.5111695137976346e-05, "loss": 0.7997, "step": 1990 }, { "epoch": 0.33, "learning_rate": 2.5109231274638634e-05, "loss": 1.1846, "step": 1991 }, { "epoch": 0.33, "learning_rate": 2.5106767411300918e-05, "loss": 1.351, "step": 1992 }, { "epoch": 0.33, "learning_rate": 2.5104303547963206e-05, "loss": 1.0596, "step": 1993 }, { "epoch": 0.33, "learning_rate": 2.5101839684625494e-05, "loss": 1.8525, "step": 1994 }, { "epoch": 0.33, "learning_rate": 2.509937582128778e-05, "loss": 0.8043, "step": 1995 }, { "epoch": 0.33, "learning_rate": 2.509691195795007e-05, "loss": 0.9866, "step": 1996 }, { "epoch": 0.33, "learning_rate": 2.5094448094612353e-05, "loss": 1.3432, "step": 1997 }, { "epoch": 0.33, "learning_rate": 2.509198423127464e-05, "loss": 1.0801, "step": 1998 }, { "epoch": 0.33, "learning_rate": 2.5089520367936925e-05, "loss": 0.9431, "step": 1999 }, { "epoch": 0.33, "learning_rate": 2.5087056504599213e-05, "loss": 1.0279, "step": 2000 }, { "epoch": 0.33, "eval_exact_match": 83.2639545884579, "eval_f1": 90.70888210249525, "step": 2000 }, { "epoch": 0.33, "learning_rate": 2.5084592641261497e-05, "loss": 0.8965, "step": 2001 }, { "epoch": 0.33, "learning_rate": 2.5082128777923785e-05, "loss": 0.6552, "step": 2002 }, { "epoch": 0.33, "learning_rate": 2.507966491458607e-05, "loss": 0.7173, "step": 2003 }, { "epoch": 0.33, "learning_rate": 2.507720105124836e-05, "loss": 1.0167, "step": 2004 }, { "epoch": 0.33, "learning_rate": 2.5074737187910644e-05, "loss": 0.8441, "step": 2005 }, { "epoch": 0.33, "learning_rate": 2.5072273324572932e-05, "loss": 0.7183, "step": 2006 }, { "epoch": 0.33, "learning_rate": 2.5069809461235216e-05, "loss": 0.7711, "step": 2007 }, { "epoch": 0.33, "learning_rate": 2.5067345597897504e-05, "loss": 1.0946, "step": 2008 }, { "epoch": 0.33, "learning_rate": 2.5064881734559792e-05, "loss": 1.214, "step": 2009 }, { "epoch": 0.33, "learning_rate": 2.5062417871222076e-05, "loss": 0.4726, "step": 2010 }, { "epoch": 0.33, "learning_rate": 2.5059954007884364e-05, "loss": 1.3892, "step": 2011 }, { "epoch": 0.33, "learning_rate": 2.5057490144546648e-05, "loss": 1.151, "step": 2012 }, { "epoch": 0.33, "learning_rate": 2.5055026281208936e-05, "loss": 1.3232, "step": 2013 }, { "epoch": 0.33, "learning_rate": 2.5052562417871223e-05, "loss": 0.9393, "step": 2014 }, { "epoch": 0.33, "learning_rate": 2.505009855453351e-05, "loss": 0.828, "step": 2015 }, { "epoch": 0.33, "learning_rate": 2.5047634691195795e-05, "loss": 0.8239, "step": 2016 }, { "epoch": 0.33, "learning_rate": 2.5045170827858083e-05, "loss": 0.5029, "step": 2017 }, { "epoch": 0.33, "learning_rate": 2.5042706964520367e-05, "loss": 0.8398, "step": 2018 }, { "epoch": 0.33, "learning_rate": 2.5040243101182655e-05, "loss": 0.8907, "step": 2019 }, { "epoch": 0.33, "learning_rate": 2.5037779237844943e-05, "loss": 1.608, "step": 2020 }, { "epoch": 0.33, "learning_rate": 2.5035315374507227e-05, "loss": 1.2314, "step": 2021 }, { "epoch": 0.33, "learning_rate": 2.5032851511169515e-05, "loss": 0.8927, "step": 2022 }, { "epoch": 0.33, "learning_rate": 2.50303876478318e-05, "loss": 1.0105, "step": 2023 }, { "epoch": 0.33, "learning_rate": 2.502792378449409e-05, "loss": 0.7404, "step": 2024 }, { "epoch": 0.33, "learning_rate": 2.5025459921156374e-05, "loss": 1.4253, "step": 2025 }, { "epoch": 0.33, "learning_rate": 2.5022996057818662e-05, "loss": 1.0206, "step": 2026 }, { "epoch": 0.33, "learning_rate": 2.5020532194480946e-05, "loss": 0.7184, "step": 2027 }, { "epoch": 0.33, "learning_rate": 2.5018068331143234e-05, "loss": 0.6491, "step": 2028 }, { "epoch": 0.33, "learning_rate": 2.5015604467805518e-05, "loss": 0.9132, "step": 2029 }, { "epoch": 0.33, "learning_rate": 2.5013140604467806e-05, "loss": 0.5, "step": 2030 }, { "epoch": 0.33, "learning_rate": 2.501067674113009e-05, "loss": 0.712, "step": 2031 }, { "epoch": 0.33, "learning_rate": 2.5008212877792378e-05, "loss": 0.7071, "step": 2032 }, { "epoch": 0.33, "learning_rate": 2.5005749014454666e-05, "loss": 0.6266, "step": 2033 }, { "epoch": 0.33, "learning_rate": 2.5003285151116953e-05, "loss": 1.0104, "step": 2034 }, { "epoch": 0.33, "learning_rate": 2.500082128777924e-05, "loss": 0.9649, "step": 2035 }, { "epoch": 0.33, "learning_rate": 2.4998357424441525e-05, "loss": 1.433, "step": 2036 }, { "epoch": 0.33, "learning_rate": 2.4995893561103813e-05, "loss": 0.9394, "step": 2037 }, { "epoch": 0.33, "learning_rate": 2.4993429697766097e-05, "loss": 0.6673, "step": 2038 }, { "epoch": 0.33, "learning_rate": 2.4990965834428385e-05, "loss": 0.826, "step": 2039 }, { "epoch": 0.34, "learning_rate": 2.498850197109067e-05, "loss": 0.7642, "step": 2040 }, { "epoch": 0.34, "learning_rate": 2.4986038107752957e-05, "loss": 0.7614, "step": 2041 }, { "epoch": 0.34, "learning_rate": 2.498357424441524e-05, "loss": 0.5411, "step": 2042 }, { "epoch": 0.34, "learning_rate": 2.498111038107753e-05, "loss": 1.1741, "step": 2043 }, { "epoch": 0.34, "learning_rate": 2.497864651773982e-05, "loss": 0.553, "step": 2044 }, { "epoch": 0.34, "learning_rate": 2.4976182654402104e-05, "loss": 0.6796, "step": 2045 }, { "epoch": 0.34, "learning_rate": 2.4973718791064392e-05, "loss": 0.6508, "step": 2046 }, { "epoch": 0.34, "learning_rate": 2.4971254927726676e-05, "loss": 1.5688, "step": 2047 }, { "epoch": 0.34, "learning_rate": 2.4968791064388964e-05, "loss": 0.5651, "step": 2048 }, { "epoch": 0.34, "learning_rate": 2.4966327201051248e-05, "loss": 0.6802, "step": 2049 }, { "epoch": 0.34, "learning_rate": 2.4963863337713536e-05, "loss": 1.2873, "step": 2050 }, { "epoch": 0.34, "learning_rate": 2.496139947437582e-05, "loss": 1.3694, "step": 2051 }, { "epoch": 0.34, "learning_rate": 2.4958935611038108e-05, "loss": 0.9113, "step": 2052 }, { "epoch": 0.34, "learning_rate": 2.4956471747700392e-05, "loss": 0.7601, "step": 2053 }, { "epoch": 0.34, "learning_rate": 2.4954007884362683e-05, "loss": 0.7836, "step": 2054 }, { "epoch": 0.34, "learning_rate": 2.4951544021024967e-05, "loss": 0.974, "step": 2055 }, { "epoch": 0.34, "learning_rate": 2.4949080157687255e-05, "loss": 0.4003, "step": 2056 }, { "epoch": 0.34, "learning_rate": 2.4946616294349543e-05, "loss": 0.3917, "step": 2057 }, { "epoch": 0.34, "learning_rate": 2.4944152431011827e-05, "loss": 0.7386, "step": 2058 }, { "epoch": 0.34, "learning_rate": 2.4941688567674115e-05, "loss": 0.7754, "step": 2059 }, { "epoch": 0.34, "learning_rate": 2.49392247043364e-05, "loss": 1.0882, "step": 2060 }, { "epoch": 0.34, "learning_rate": 2.4936760840998687e-05, "loss": 0.8229, "step": 2061 }, { "epoch": 0.34, "learning_rate": 2.493429697766097e-05, "loss": 1.066, "step": 2062 }, { "epoch": 0.34, "learning_rate": 2.493183311432326e-05, "loss": 1.2248, "step": 2063 }, { "epoch": 0.34, "learning_rate": 2.4929369250985546e-05, "loss": 0.3715, "step": 2064 }, { "epoch": 0.34, "learning_rate": 2.4926905387647834e-05, "loss": 1.0159, "step": 2065 }, { "epoch": 0.34, "learning_rate": 2.4924441524310118e-05, "loss": 0.3205, "step": 2066 }, { "epoch": 0.34, "learning_rate": 2.4921977660972406e-05, "loss": 1.2781, "step": 2067 }, { "epoch": 0.34, "learning_rate": 2.4919513797634694e-05, "loss": 0.7693, "step": 2068 }, { "epoch": 0.34, "learning_rate": 2.4917049934296978e-05, "loss": 0.8066, "step": 2069 }, { "epoch": 0.34, "learning_rate": 2.4914586070959266e-05, "loss": 0.6928, "step": 2070 }, { "epoch": 0.34, "learning_rate": 2.491212220762155e-05, "loss": 0.7452, "step": 2071 }, { "epoch": 0.34, "learning_rate": 2.4909658344283838e-05, "loss": 0.867, "step": 2072 }, { "epoch": 0.34, "learning_rate": 2.4907194480946122e-05, "loss": 0.7897, "step": 2073 }, { "epoch": 0.34, "learning_rate": 2.4904730617608413e-05, "loss": 0.7594, "step": 2074 }, { "epoch": 0.34, "learning_rate": 2.4902266754270697e-05, "loss": 1.5179, "step": 2075 }, { "epoch": 0.34, "learning_rate": 2.4899802890932985e-05, "loss": 0.5295, "step": 2076 }, { "epoch": 0.34, "learning_rate": 2.489733902759527e-05, "loss": 1.0121, "step": 2077 }, { "epoch": 0.34, "learning_rate": 2.4894875164257557e-05, "loss": 1.0707, "step": 2078 }, { "epoch": 0.34, "learning_rate": 2.489241130091984e-05, "loss": 0.9706, "step": 2079 }, { "epoch": 0.34, "learning_rate": 2.488994743758213e-05, "loss": 0.7866, "step": 2080 }, { "epoch": 0.34, "learning_rate": 2.4887483574244417e-05, "loss": 1.0805, "step": 2081 }, { "epoch": 0.34, "learning_rate": 2.48850197109067e-05, "loss": 0.9839, "step": 2082 }, { "epoch": 0.34, "learning_rate": 2.488255584756899e-05, "loss": 0.8851, "step": 2083 }, { "epoch": 0.34, "learning_rate": 2.4880091984231276e-05, "loss": 0.8261, "step": 2084 }, { "epoch": 0.34, "learning_rate": 2.4877628120893564e-05, "loss": 0.8688, "step": 2085 }, { "epoch": 0.34, "learning_rate": 2.4875164257555848e-05, "loss": 0.4864, "step": 2086 }, { "epoch": 0.34, "learning_rate": 2.4872700394218136e-05, "loss": 0.754, "step": 2087 }, { "epoch": 0.34, "learning_rate": 2.487023653088042e-05, "loss": 1.089, "step": 2088 }, { "epoch": 0.34, "learning_rate": 2.4867772667542708e-05, "loss": 1.2224, "step": 2089 }, { "epoch": 0.34, "learning_rate": 2.4865308804204992e-05, "loss": 1.4297, "step": 2090 }, { "epoch": 0.34, "learning_rate": 2.486284494086728e-05, "loss": 0.9393, "step": 2091 }, { "epoch": 0.34, "learning_rate": 2.4860381077529567e-05, "loss": 0.5022, "step": 2092 }, { "epoch": 0.34, "learning_rate": 2.4857917214191852e-05, "loss": 0.534, "step": 2093 }, { "epoch": 0.34, "learning_rate": 2.4855453350854143e-05, "loss": 1.638, "step": 2094 }, { "epoch": 0.34, "learning_rate": 2.4852989487516427e-05, "loss": 0.4941, "step": 2095 }, { "epoch": 0.34, "learning_rate": 2.4850525624178715e-05, "loss": 0.5236, "step": 2096 }, { "epoch": 0.34, "learning_rate": 2.4848061760841e-05, "loss": 0.9257, "step": 2097 }, { "epoch": 0.34, "learning_rate": 2.4845597897503287e-05, "loss": 1.7724, "step": 2098 }, { "epoch": 0.34, "learning_rate": 2.484313403416557e-05, "loss": 0.5211, "step": 2099 }, { "epoch": 0.34, "learning_rate": 2.484067017082786e-05, "loss": 0.9658, "step": 2100 }, { "epoch": 0.35, "learning_rate": 2.4838206307490143e-05, "loss": 0.9463, "step": 2101 }, { "epoch": 0.35, "learning_rate": 2.483574244415243e-05, "loss": 0.5615, "step": 2102 }, { "epoch": 0.35, "learning_rate": 2.483327858081472e-05, "loss": 0.6899, "step": 2103 }, { "epoch": 0.35, "learning_rate": 2.4830814717477006e-05, "loss": 0.8172, "step": 2104 }, { "epoch": 0.35, "learning_rate": 2.4828350854139294e-05, "loss": 0.9464, "step": 2105 }, { "epoch": 0.35, "learning_rate": 2.4825886990801578e-05, "loss": 0.6231, "step": 2106 }, { "epoch": 0.35, "learning_rate": 2.4823423127463866e-05, "loss": 1.1375, "step": 2107 }, { "epoch": 0.35, "learning_rate": 2.482095926412615e-05, "loss": 1.0396, "step": 2108 }, { "epoch": 0.35, "learning_rate": 2.4818495400788438e-05, "loss": 0.6925, "step": 2109 }, { "epoch": 0.35, "learning_rate": 2.4816031537450722e-05, "loss": 1.2411, "step": 2110 }, { "epoch": 0.35, "learning_rate": 2.481356767411301e-05, "loss": 0.8877, "step": 2111 }, { "epoch": 0.35, "learning_rate": 2.4811103810775294e-05, "loss": 0.5737, "step": 2112 }, { "epoch": 0.35, "learning_rate": 2.480863994743758e-05, "loss": 1.3384, "step": 2113 }, { "epoch": 0.35, "learning_rate": 2.480617608409987e-05, "loss": 0.506, "step": 2114 }, { "epoch": 0.35, "learning_rate": 2.4803712220762157e-05, "loss": 0.7048, "step": 2115 }, { "epoch": 0.35, "learning_rate": 2.4801248357424445e-05, "loss": 0.8533, "step": 2116 }, { "epoch": 0.35, "learning_rate": 2.479878449408673e-05, "loss": 0.7748, "step": 2117 }, { "epoch": 0.35, "learning_rate": 2.4796320630749017e-05, "loss": 1.0352, "step": 2118 }, { "epoch": 0.35, "learning_rate": 2.47938567674113e-05, "loss": 0.6719, "step": 2119 }, { "epoch": 0.35, "learning_rate": 2.479139290407359e-05, "loss": 1.8235, "step": 2120 }, { "epoch": 0.35, "learning_rate": 2.4788929040735873e-05, "loss": 0.812, "step": 2121 }, { "epoch": 0.35, "learning_rate": 2.478646517739816e-05, "loss": 0.4643, "step": 2122 }, { "epoch": 0.35, "learning_rate": 2.4784001314060445e-05, "loss": 0.6858, "step": 2123 }, { "epoch": 0.35, "learning_rate": 2.4781537450722736e-05, "loss": 0.7676, "step": 2124 }, { "epoch": 0.35, "learning_rate": 2.477907358738502e-05, "loss": 0.8989, "step": 2125 }, { "epoch": 0.35, "learning_rate": 2.4776609724047308e-05, "loss": 0.4781, "step": 2126 }, { "epoch": 0.35, "learning_rate": 2.4774145860709596e-05, "loss": 1.3972, "step": 2127 }, { "epoch": 0.35, "learning_rate": 2.477168199737188e-05, "loss": 0.6608, "step": 2128 }, { "epoch": 0.35, "learning_rate": 2.4769218134034167e-05, "loss": 1.4804, "step": 2129 }, { "epoch": 0.35, "learning_rate": 2.4766754270696452e-05, "loss": 0.5416, "step": 2130 }, { "epoch": 0.35, "learning_rate": 2.476429040735874e-05, "loss": 0.5612, "step": 2131 }, { "epoch": 0.35, "learning_rate": 2.4761826544021024e-05, "loss": 0.6757, "step": 2132 }, { "epoch": 0.35, "learning_rate": 2.475936268068331e-05, "loss": 1.0166, "step": 2133 }, { "epoch": 0.35, "learning_rate": 2.47568988173456e-05, "loss": 0.9715, "step": 2134 }, { "epoch": 0.35, "learning_rate": 2.4754434954007887e-05, "loss": 0.6784, "step": 2135 }, { "epoch": 0.35, "learning_rate": 2.475197109067017e-05, "loss": 0.6178, "step": 2136 }, { "epoch": 0.35, "learning_rate": 2.474950722733246e-05, "loss": 0.7507, "step": 2137 }, { "epoch": 0.35, "learning_rate": 2.4747043363994743e-05, "loss": 0.9003, "step": 2138 }, { "epoch": 0.35, "learning_rate": 2.474457950065703e-05, "loss": 0.976, "step": 2139 }, { "epoch": 0.35, "learning_rate": 2.474211563731932e-05, "loss": 1.3003, "step": 2140 }, { "epoch": 0.35, "learning_rate": 2.4739651773981603e-05, "loss": 0.8863, "step": 2141 }, { "epoch": 0.35, "learning_rate": 2.473718791064389e-05, "loss": 0.6777, "step": 2142 }, { "epoch": 0.35, "learning_rate": 2.4734724047306175e-05, "loss": 1.287, "step": 2143 }, { "epoch": 0.35, "learning_rate": 2.4732260183968466e-05, "loss": 1.5921, "step": 2144 }, { "epoch": 0.35, "learning_rate": 2.472979632063075e-05, "loss": 1.034, "step": 2145 }, { "epoch": 0.35, "learning_rate": 2.4727332457293038e-05, "loss": 0.9021, "step": 2146 }, { "epoch": 0.35, "learning_rate": 2.4724868593955322e-05, "loss": 1.3972, "step": 2147 }, { "epoch": 0.35, "learning_rate": 2.472240473061761e-05, "loss": 1.3719, "step": 2148 }, { "epoch": 0.35, "learning_rate": 2.4719940867279894e-05, "loss": 0.3928, "step": 2149 }, { "epoch": 0.35, "learning_rate": 2.471747700394218e-05, "loss": 0.831, "step": 2150 }, { "epoch": 0.35, "learning_rate": 2.471501314060447e-05, "loss": 0.9689, "step": 2151 }, { "epoch": 0.35, "learning_rate": 2.4712549277266754e-05, "loss": 1.4588, "step": 2152 }, { "epoch": 0.35, "learning_rate": 2.471008541392904e-05, "loss": 0.9699, "step": 2153 }, { "epoch": 0.35, "learning_rate": 2.470762155059133e-05, "loss": 0.6401, "step": 2154 }, { "epoch": 0.35, "learning_rate": 2.4705157687253617e-05, "loss": 0.6596, "step": 2155 }, { "epoch": 0.35, "learning_rate": 2.47026938239159e-05, "loss": 1.4582, "step": 2156 }, { "epoch": 0.35, "learning_rate": 2.470022996057819e-05, "loss": 1.1718, "step": 2157 }, { "epoch": 0.35, "learning_rate": 2.4697766097240473e-05, "loss": 0.7251, "step": 2158 }, { "epoch": 0.35, "learning_rate": 2.469530223390276e-05, "loss": 0.8329, "step": 2159 }, { "epoch": 0.35, "learning_rate": 2.4692838370565045e-05, "loss": 1.3516, "step": 2160 }, { "epoch": 0.35, "learning_rate": 2.4690374507227333e-05, "loss": 1.0864, "step": 2161 }, { "epoch": 0.36, "learning_rate": 2.4687910643889617e-05, "loss": 0.8791, "step": 2162 }, { "epoch": 0.36, "learning_rate": 2.4685446780551905e-05, "loss": 0.997, "step": 2163 }, { "epoch": 0.36, "learning_rate": 2.4682982917214196e-05, "loss": 0.985, "step": 2164 }, { "epoch": 0.36, "learning_rate": 2.468051905387648e-05, "loss": 0.7627, "step": 2165 }, { "epoch": 0.36, "learning_rate": 2.4678055190538768e-05, "loss": 0.5865, "step": 2166 }, { "epoch": 0.36, "learning_rate": 2.4675591327201052e-05, "loss": 0.9601, "step": 2167 }, { "epoch": 0.36, "learning_rate": 2.467312746386334e-05, "loss": 0.9653, "step": 2168 }, { "epoch": 0.36, "learning_rate": 2.4670663600525624e-05, "loss": 0.6576, "step": 2169 }, { "epoch": 0.36, "learning_rate": 2.466819973718791e-05, "loss": 1.0701, "step": 2170 }, { "epoch": 0.36, "learning_rate": 2.4665735873850196e-05, "loss": 0.5866, "step": 2171 }, { "epoch": 0.36, "learning_rate": 2.4663272010512483e-05, "loss": 0.6756, "step": 2172 }, { "epoch": 0.36, "learning_rate": 2.4660808147174768e-05, "loss": 0.5776, "step": 2173 }, { "epoch": 0.36, "learning_rate": 2.465834428383706e-05, "loss": 1.2988, "step": 2174 }, { "epoch": 0.36, "learning_rate": 2.4655880420499346e-05, "loss": 0.7074, "step": 2175 }, { "epoch": 0.36, "learning_rate": 2.465341655716163e-05, "loss": 1.2, "step": 2176 }, { "epoch": 0.36, "learning_rate": 2.465095269382392e-05, "loss": 0.6062, "step": 2177 }, { "epoch": 0.36, "learning_rate": 2.4648488830486203e-05, "loss": 0.9319, "step": 2178 }, { "epoch": 0.36, "learning_rate": 2.464602496714849e-05, "loss": 1.0832, "step": 2179 }, { "epoch": 0.36, "learning_rate": 2.4643561103810775e-05, "loss": 0.6586, "step": 2180 }, { "epoch": 0.36, "learning_rate": 2.4641097240473062e-05, "loss": 1.4271, "step": 2181 }, { "epoch": 0.36, "learning_rate": 2.4638633377135347e-05, "loss": 1.2311, "step": 2182 }, { "epoch": 0.36, "learning_rate": 2.4636169513797634e-05, "loss": 1.2458, "step": 2183 }, { "epoch": 0.36, "learning_rate": 2.4633705650459922e-05, "loss": 0.6751, "step": 2184 }, { "epoch": 0.36, "learning_rate": 2.463124178712221e-05, "loss": 0.5997, "step": 2185 }, { "epoch": 0.36, "learning_rate": 2.4628777923784494e-05, "loss": 0.9265, "step": 2186 }, { "epoch": 0.36, "learning_rate": 2.4626314060446782e-05, "loss": 0.7583, "step": 2187 }, { "epoch": 0.36, "learning_rate": 2.462385019710907e-05, "loss": 1.2821, "step": 2188 }, { "epoch": 0.36, "learning_rate": 2.4621386333771354e-05, "loss": 0.6551, "step": 2189 }, { "epoch": 0.36, "learning_rate": 2.461892247043364e-05, "loss": 1.0593, "step": 2190 }, { "epoch": 0.36, "learning_rate": 2.4616458607095926e-05, "loss": 0.9652, "step": 2191 }, { "epoch": 0.36, "learning_rate": 2.4613994743758213e-05, "loss": 0.7285, "step": 2192 }, { "epoch": 0.36, "learning_rate": 2.4611530880420498e-05, "loss": 1.2703, "step": 2193 }, { "epoch": 0.36, "learning_rate": 2.460906701708279e-05, "loss": 0.6478, "step": 2194 }, { "epoch": 0.36, "learning_rate": 2.4606603153745073e-05, "loss": 0.6211, "step": 2195 }, { "epoch": 0.36, "learning_rate": 2.460413929040736e-05, "loss": 0.9395, "step": 2196 }, { "epoch": 0.36, "learning_rate": 2.4601675427069645e-05, "loss": 1.3423, "step": 2197 }, { "epoch": 0.36, "learning_rate": 2.4599211563731933e-05, "loss": 1.4245, "step": 2198 }, { "epoch": 0.36, "learning_rate": 2.459674770039422e-05, "loss": 0.9016, "step": 2199 }, { "epoch": 0.36, "learning_rate": 2.4594283837056505e-05, "loss": 0.7758, "step": 2200 }, { "epoch": 0.36, "learning_rate": 2.4591819973718792e-05, "loss": 1.3917, "step": 2201 }, { "epoch": 0.36, "learning_rate": 2.4589356110381077e-05, "loss": 1.2394, "step": 2202 }, { "epoch": 0.36, "learning_rate": 2.4586892247043364e-05, "loss": 0.7486, "step": 2203 }, { "epoch": 0.36, "learning_rate": 2.4584428383705652e-05, "loss": 0.6533, "step": 2204 }, { "epoch": 0.36, "learning_rate": 2.458196452036794e-05, "loss": 0.7279, "step": 2205 }, { "epoch": 0.36, "learning_rate": 2.4579500657030224e-05, "loss": 0.8464, "step": 2206 }, { "epoch": 0.36, "learning_rate": 2.457703679369251e-05, "loss": 0.7865, "step": 2207 }, { "epoch": 0.36, "learning_rate": 2.4574572930354796e-05, "loss": 1.0404, "step": 2208 }, { "epoch": 0.36, "learning_rate": 2.4572109067017084e-05, "loss": 1.243, "step": 2209 }, { "epoch": 0.36, "learning_rate": 2.4569645203679368e-05, "loss": 0.9491, "step": 2210 }, { "epoch": 0.36, "learning_rate": 2.4567181340341655e-05, "loss": 0.8097, "step": 2211 }, { "epoch": 0.36, "learning_rate": 2.4564717477003943e-05, "loss": 0.816, "step": 2212 }, { "epoch": 0.36, "learning_rate": 2.4562253613666227e-05, "loss": 1.0613, "step": 2213 }, { "epoch": 0.36, "learning_rate": 2.455978975032852e-05, "loss": 0.7295, "step": 2214 }, { "epoch": 0.36, "learning_rate": 2.4557325886990803e-05, "loss": 1.0963, "step": 2215 }, { "epoch": 0.36, "learning_rate": 2.455486202365309e-05, "loss": 1.0069, "step": 2216 }, { "epoch": 0.36, "learning_rate": 2.4552398160315375e-05, "loss": 2.0015, "step": 2217 }, { "epoch": 0.36, "learning_rate": 2.4549934296977662e-05, "loss": 1.0537, "step": 2218 }, { "epoch": 0.36, "learning_rate": 2.4547470433639947e-05, "loss": 1.4678, "step": 2219 }, { "epoch": 0.36, "learning_rate": 2.4545006570302234e-05, "loss": 1.0708, "step": 2220 }, { "epoch": 0.36, "learning_rate": 2.454254270696452e-05, "loss": 1.1003, "step": 2221 }, { "epoch": 0.36, "learning_rate": 2.4540078843626806e-05, "loss": 0.9799, "step": 2222 }, { "epoch": 0.37, "learning_rate": 2.4537614980289094e-05, "loss": 1.5701, "step": 2223 }, { "epoch": 0.37, "learning_rate": 2.4535151116951382e-05, "loss": 0.8249, "step": 2224 }, { "epoch": 0.37, "learning_rate": 2.453268725361367e-05, "loss": 1.1005, "step": 2225 }, { "epoch": 0.37, "learning_rate": 2.4530223390275954e-05, "loss": 1.5099, "step": 2226 }, { "epoch": 0.37, "learning_rate": 2.452775952693824e-05, "loss": 0.6579, "step": 2227 }, { "epoch": 0.37, "learning_rate": 2.4525295663600526e-05, "loss": 1.0016, "step": 2228 }, { "epoch": 0.37, "learning_rate": 2.4522831800262813e-05, "loss": 1.3781, "step": 2229 }, { "epoch": 0.37, "learning_rate": 2.4520367936925098e-05, "loss": 0.6839, "step": 2230 }, { "epoch": 0.37, "learning_rate": 2.4517904073587385e-05, "loss": 0.7053, "step": 2231 }, { "epoch": 0.37, "learning_rate": 2.451544021024967e-05, "loss": 1.0972, "step": 2232 }, { "epoch": 0.37, "learning_rate": 2.4512976346911957e-05, "loss": 1.3597, "step": 2233 }, { "epoch": 0.37, "learning_rate": 2.4510512483574245e-05, "loss": 0.825, "step": 2234 }, { "epoch": 0.37, "learning_rate": 2.4508048620236533e-05, "loss": 0.4388, "step": 2235 }, { "epoch": 0.37, "learning_rate": 2.450558475689882e-05, "loss": 0.9531, "step": 2236 }, { "epoch": 0.37, "learning_rate": 2.4503120893561105e-05, "loss": 0.7673, "step": 2237 }, { "epoch": 0.37, "learning_rate": 2.4500657030223392e-05, "loss": 0.6977, "step": 2238 }, { "epoch": 0.37, "learning_rate": 2.4498193166885677e-05, "loss": 0.6248, "step": 2239 }, { "epoch": 0.37, "learning_rate": 2.4495729303547964e-05, "loss": 1.0878, "step": 2240 }, { "epoch": 0.37, "learning_rate": 2.449326544021025e-05, "loss": 0.8507, "step": 2241 }, { "epoch": 0.37, "learning_rate": 2.4490801576872536e-05, "loss": 0.5006, "step": 2242 }, { "epoch": 0.37, "learning_rate": 2.448833771353482e-05, "loss": 1.3228, "step": 2243 }, { "epoch": 0.37, "learning_rate": 2.448587385019711e-05, "loss": 0.5243, "step": 2244 }, { "epoch": 0.37, "learning_rate": 2.4483409986859396e-05, "loss": 0.5246, "step": 2245 }, { "epoch": 0.37, "learning_rate": 2.4480946123521684e-05, "loss": 1.1214, "step": 2246 }, { "epoch": 0.37, "learning_rate": 2.447848226018397e-05, "loss": 0.6107, "step": 2247 }, { "epoch": 0.37, "learning_rate": 2.4476018396846256e-05, "loss": 1.7135, "step": 2248 }, { "epoch": 0.37, "learning_rate": 2.4473554533508543e-05, "loss": 0.7883, "step": 2249 }, { "epoch": 0.37, "learning_rate": 2.4471090670170828e-05, "loss": 0.8383, "step": 2250 }, { "epoch": 0.37, "learning_rate": 2.4468626806833115e-05, "loss": 2.4382, "step": 2251 }, { "epoch": 0.37, "learning_rate": 2.44661629434954e-05, "loss": 0.5201, "step": 2252 }, { "epoch": 0.37, "learning_rate": 2.4463699080157687e-05, "loss": 1.2878, "step": 2253 }, { "epoch": 0.37, "learning_rate": 2.4461235216819975e-05, "loss": 0.5952, "step": 2254 }, { "epoch": 0.37, "learning_rate": 2.4458771353482263e-05, "loss": 1.2227, "step": 2255 }, { "epoch": 0.37, "learning_rate": 2.4456307490144547e-05, "loss": 0.5521, "step": 2256 }, { "epoch": 0.37, "learning_rate": 2.4453843626806835e-05, "loss": 1.0403, "step": 2257 }, { "epoch": 0.37, "learning_rate": 2.4451379763469122e-05, "loss": 1.332, "step": 2258 }, { "epoch": 0.37, "learning_rate": 2.4448915900131406e-05, "loss": 0.8621, "step": 2259 }, { "epoch": 0.37, "learning_rate": 2.4446452036793694e-05, "loss": 1.0787, "step": 2260 }, { "epoch": 0.37, "learning_rate": 2.444398817345598e-05, "loss": 0.9543, "step": 2261 }, { "epoch": 0.37, "learning_rate": 2.4441524310118266e-05, "loss": 0.5549, "step": 2262 }, { "epoch": 0.37, "learning_rate": 2.443906044678055e-05, "loss": 1.3171, "step": 2263 }, { "epoch": 0.37, "learning_rate": 2.443659658344284e-05, "loss": 0.7053, "step": 2264 }, { "epoch": 0.37, "learning_rate": 2.4434132720105126e-05, "loss": 0.5199, "step": 2265 }, { "epoch": 0.37, "learning_rate": 2.4431668856767413e-05, "loss": 0.8721, "step": 2266 }, { "epoch": 0.37, "learning_rate": 2.4429204993429698e-05, "loss": 0.8889, "step": 2267 }, { "epoch": 0.37, "learning_rate": 2.4426741130091985e-05, "loss": 1.4199, "step": 2268 }, { "epoch": 0.37, "learning_rate": 2.442427726675427e-05, "loss": 0.643, "step": 2269 }, { "epoch": 0.37, "learning_rate": 2.4421813403416557e-05, "loss": 1.6611, "step": 2270 }, { "epoch": 0.37, "learning_rate": 2.4419349540078845e-05, "loss": 1.0961, "step": 2271 }, { "epoch": 0.37, "learning_rate": 2.441688567674113e-05, "loss": 1.4243, "step": 2272 }, { "epoch": 0.37, "learning_rate": 2.4414421813403417e-05, "loss": 0.5529, "step": 2273 }, { "epoch": 0.37, "learning_rate": 2.4411957950065705e-05, "loss": 0.831, "step": 2274 }, { "epoch": 0.37, "learning_rate": 2.4409494086727992e-05, "loss": 1.2044, "step": 2275 }, { "epoch": 0.37, "learning_rate": 2.4407030223390277e-05, "loss": 0.6984, "step": 2276 }, { "epoch": 0.37, "learning_rate": 2.4404566360052564e-05, "loss": 0.838, "step": 2277 }, { "epoch": 0.37, "learning_rate": 2.440210249671485e-05, "loss": 0.555, "step": 2278 }, { "epoch": 0.37, "learning_rate": 2.4399638633377136e-05, "loss": 1.5518, "step": 2279 }, { "epoch": 0.37, "learning_rate": 2.439717477003942e-05, "loss": 0.8691, "step": 2280 }, { "epoch": 0.37, "learning_rate": 2.4394710906701708e-05, "loss": 1.5206, "step": 2281 }, { "epoch": 0.37, "learning_rate": 2.4392247043363996e-05, "loss": 1.8833, "step": 2282 }, { "epoch": 0.38, "learning_rate": 2.438978318002628e-05, "loss": 0.9751, "step": 2283 }, { "epoch": 0.38, "learning_rate": 2.438731931668857e-05, "loss": 1.3641, "step": 2284 }, { "epoch": 0.38, "learning_rate": 2.4384855453350856e-05, "loss": 0.9622, "step": 2285 }, { "epoch": 0.38, "learning_rate": 2.4382391590013143e-05, "loss": 0.9278, "step": 2286 }, { "epoch": 0.38, "learning_rate": 2.4379927726675428e-05, "loss": 0.9699, "step": 2287 }, { "epoch": 0.38, "learning_rate": 2.4377463863337715e-05, "loss": 0.8681, "step": 2288 }, { "epoch": 0.38, "learning_rate": 2.4375e-05, "loss": 1.2481, "step": 2289 }, { "epoch": 0.38, "learning_rate": 2.4372536136662287e-05, "loss": 1.0654, "step": 2290 }, { "epoch": 0.38, "learning_rate": 2.437007227332457e-05, "loss": 1.243, "step": 2291 }, { "epoch": 0.38, "learning_rate": 2.436760840998686e-05, "loss": 0.537, "step": 2292 }, { "epoch": 0.38, "learning_rate": 2.4365144546649143e-05, "loss": 0.6519, "step": 2293 }, { "epoch": 0.38, "learning_rate": 2.436268068331143e-05, "loss": 0.7895, "step": 2294 }, { "epoch": 0.38, "learning_rate": 2.4360216819973722e-05, "loss": 0.5659, "step": 2295 }, { "epoch": 0.38, "learning_rate": 2.4357752956636007e-05, "loss": 1.268, "step": 2296 }, { "epoch": 0.38, "learning_rate": 2.4355289093298294e-05, "loss": 0.7932, "step": 2297 }, { "epoch": 0.38, "learning_rate": 2.435282522996058e-05, "loss": 0.8314, "step": 2298 }, { "epoch": 0.38, "learning_rate": 2.4350361366622866e-05, "loss": 1.0101, "step": 2299 }, { "epoch": 0.38, "learning_rate": 2.434789750328515e-05, "loss": 0.9598, "step": 2300 }, { "epoch": 0.38, "learning_rate": 2.4345433639947438e-05, "loss": 0.9776, "step": 2301 }, { "epoch": 0.38, "learning_rate": 2.4342969776609722e-05, "loss": 0.6907, "step": 2302 }, { "epoch": 0.38, "learning_rate": 2.434050591327201e-05, "loss": 0.7113, "step": 2303 }, { "epoch": 0.38, "learning_rate": 2.4338042049934294e-05, "loss": 0.6361, "step": 2304 }, { "epoch": 0.38, "learning_rate": 2.4335578186596585e-05, "loss": 1.1025, "step": 2305 }, { "epoch": 0.38, "learning_rate": 2.4333114323258873e-05, "loss": 1.1313, "step": 2306 }, { "epoch": 0.38, "learning_rate": 2.4330650459921157e-05, "loss": 0.6317, "step": 2307 }, { "epoch": 0.38, "learning_rate": 2.4328186596583445e-05, "loss": 0.7508, "step": 2308 }, { "epoch": 0.38, "learning_rate": 2.432572273324573e-05, "loss": 0.511, "step": 2309 }, { "epoch": 0.38, "learning_rate": 2.4323258869908017e-05, "loss": 0.8235, "step": 2310 }, { "epoch": 0.38, "learning_rate": 2.43207950065703e-05, "loss": 1.1233, "step": 2311 }, { "epoch": 0.38, "learning_rate": 2.431833114323259e-05, "loss": 0.6473, "step": 2312 }, { "epoch": 0.38, "learning_rate": 2.4315867279894873e-05, "loss": 0.9458, "step": 2313 }, { "epoch": 0.38, "learning_rate": 2.431340341655716e-05, "loss": 1.2169, "step": 2314 }, { "epoch": 0.38, "learning_rate": 2.431093955321945e-05, "loss": 1.2293, "step": 2315 }, { "epoch": 0.38, "learning_rate": 2.4308475689881736e-05, "loss": 1.1126, "step": 2316 }, { "epoch": 0.38, "learning_rate": 2.430601182654402e-05, "loss": 1.1525, "step": 2317 }, { "epoch": 0.38, "learning_rate": 2.430354796320631e-05, "loss": 1.0079, "step": 2318 }, { "epoch": 0.38, "learning_rate": 2.4301084099868596e-05, "loss": 0.9783, "step": 2319 }, { "epoch": 0.38, "learning_rate": 2.429862023653088e-05, "loss": 0.547, "step": 2320 }, { "epoch": 0.38, "learning_rate": 2.4296156373193168e-05, "loss": 0.8127, "step": 2321 }, { "epoch": 0.38, "learning_rate": 2.4293692509855452e-05, "loss": 1.4875, "step": 2322 }, { "epoch": 0.38, "learning_rate": 2.429122864651774e-05, "loss": 1.1311, "step": 2323 }, { "epoch": 0.38, "learning_rate": 2.4288764783180024e-05, "loss": 0.6247, "step": 2324 }, { "epoch": 0.38, "learning_rate": 2.4286300919842315e-05, "loss": 0.8751, "step": 2325 }, { "epoch": 0.38, "learning_rate": 2.42838370565046e-05, "loss": 0.9214, "step": 2326 }, { "epoch": 0.38, "learning_rate": 2.4281373193166887e-05, "loss": 1.0921, "step": 2327 }, { "epoch": 0.38, "learning_rate": 2.427890932982917e-05, "loss": 0.8348, "step": 2328 }, { "epoch": 0.38, "learning_rate": 2.427644546649146e-05, "loss": 0.8558, "step": 2329 }, { "epoch": 0.38, "learning_rate": 2.4273981603153747e-05, "loss": 0.9548, "step": 2330 }, { "epoch": 0.38, "learning_rate": 2.427151773981603e-05, "loss": 1.1831, "step": 2331 }, { "epoch": 0.38, "learning_rate": 2.426905387647832e-05, "loss": 0.9169, "step": 2332 }, { "epoch": 0.38, "learning_rate": 2.4266590013140603e-05, "loss": 0.841, "step": 2333 }, { "epoch": 0.38, "learning_rate": 2.426412614980289e-05, "loss": 0.755, "step": 2334 }, { "epoch": 0.38, "learning_rate": 2.426166228646518e-05, "loss": 0.5444, "step": 2335 }, { "epoch": 0.38, "learning_rate": 2.4259198423127466e-05, "loss": 1.8992, "step": 2336 }, { "epoch": 0.38, "learning_rate": 2.425673455978975e-05, "loss": 1.6637, "step": 2337 }, { "epoch": 0.38, "learning_rate": 2.4254270696452038e-05, "loss": 0.6676, "step": 2338 }, { "epoch": 0.38, "learning_rate": 2.4251806833114323e-05, "loss": 1.7811, "step": 2339 }, { "epoch": 0.38, "learning_rate": 2.424934296977661e-05, "loss": 1.3688, "step": 2340 }, { "epoch": 0.38, "learning_rate": 2.4246879106438894e-05, "loss": 0.6715, "step": 2341 }, { "epoch": 0.38, "learning_rate": 2.4244415243101182e-05, "loss": 0.5872, "step": 2342 }, { "epoch": 0.38, "learning_rate": 2.424195137976347e-05, "loss": 0.6349, "step": 2343 }, { "epoch": 0.39, "learning_rate": 2.4239487516425754e-05, "loss": 0.8965, "step": 2344 }, { "epoch": 0.39, "learning_rate": 2.4237023653088045e-05, "loss": 0.5507, "step": 2345 }, { "epoch": 0.39, "learning_rate": 2.423455978975033e-05, "loss": 0.4737, "step": 2346 }, { "epoch": 0.39, "learning_rate": 2.4232095926412617e-05, "loss": 0.8706, "step": 2347 }, { "epoch": 0.39, "learning_rate": 2.42296320630749e-05, "loss": 0.5972, "step": 2348 }, { "epoch": 0.39, "learning_rate": 2.422716819973719e-05, "loss": 1.4253, "step": 2349 }, { "epoch": 0.39, "learning_rate": 2.4224704336399473e-05, "loss": 1.5419, "step": 2350 }, { "epoch": 0.39, "learning_rate": 2.422224047306176e-05, "loss": 0.822, "step": 2351 }, { "epoch": 0.39, "learning_rate": 2.4219776609724045e-05, "loss": 0.805, "step": 2352 }, { "epoch": 0.39, "learning_rate": 2.4217312746386333e-05, "loss": 1.032, "step": 2353 }, { "epoch": 0.39, "learning_rate": 2.421484888304862e-05, "loss": 0.5925, "step": 2354 }, { "epoch": 0.39, "learning_rate": 2.421238501971091e-05, "loss": 0.6925, "step": 2355 }, { "epoch": 0.39, "learning_rate": 2.4209921156373196e-05, "loss": 0.416, "step": 2356 }, { "epoch": 0.39, "learning_rate": 2.420745729303548e-05, "loss": 0.3567, "step": 2357 }, { "epoch": 0.39, "learning_rate": 2.4204993429697768e-05, "loss": 1.1156, "step": 2358 }, { "epoch": 0.39, "learning_rate": 2.4202529566360052e-05, "loss": 1.7667, "step": 2359 }, { "epoch": 0.39, "learning_rate": 2.420006570302234e-05, "loss": 0.8806, "step": 2360 }, { "epoch": 0.39, "learning_rate": 2.4197601839684624e-05, "loss": 0.6197, "step": 2361 }, { "epoch": 0.39, "learning_rate": 2.4195137976346912e-05, "loss": 0.9149, "step": 2362 }, { "epoch": 0.39, "learning_rate": 2.4192674113009196e-05, "loss": 1.2649, "step": 2363 }, { "epoch": 0.39, "learning_rate": 2.4190210249671484e-05, "loss": 1.3339, "step": 2364 }, { "epoch": 0.39, "learning_rate": 2.418774638633377e-05, "loss": 1.2366, "step": 2365 }, { "epoch": 0.39, "learning_rate": 2.418528252299606e-05, "loss": 1.1469, "step": 2366 }, { "epoch": 0.39, "learning_rate": 2.4182818659658347e-05, "loss": 0.8238, "step": 2367 }, { "epoch": 0.39, "learning_rate": 2.418035479632063e-05, "loss": 1.6462, "step": 2368 }, { "epoch": 0.39, "learning_rate": 2.417789093298292e-05, "loss": 1.1558, "step": 2369 }, { "epoch": 0.39, "learning_rate": 2.4175427069645203e-05, "loss": 0.5625, "step": 2370 }, { "epoch": 0.39, "learning_rate": 2.417296320630749e-05, "loss": 1.2094, "step": 2371 }, { "epoch": 0.39, "learning_rate": 2.4170499342969775e-05, "loss": 0.6777, "step": 2372 }, { "epoch": 0.39, "learning_rate": 2.4168035479632063e-05, "loss": 1.2775, "step": 2373 }, { "epoch": 0.39, "learning_rate": 2.4165571616294347e-05, "loss": 0.9487, "step": 2374 }, { "epoch": 0.39, "learning_rate": 2.4163107752956638e-05, "loss": 0.8194, "step": 2375 }, { "epoch": 0.39, "learning_rate": 2.4160643889618923e-05, "loss": 0.9455, "step": 2376 }, { "epoch": 0.39, "learning_rate": 2.415818002628121e-05, "loss": 1.0409, "step": 2377 }, { "epoch": 0.39, "learning_rate": 2.4155716162943498e-05, "loss": 1.1349, "step": 2378 }, { "epoch": 0.39, "learning_rate": 2.4153252299605782e-05, "loss": 1.2546, "step": 2379 }, { "epoch": 0.39, "learning_rate": 2.415078843626807e-05, "loss": 0.8783, "step": 2380 }, { "epoch": 0.39, "learning_rate": 2.4148324572930354e-05, "loss": 1.0459, "step": 2381 }, { "epoch": 0.39, "learning_rate": 2.4145860709592642e-05, "loss": 0.4799, "step": 2382 }, { "epoch": 0.39, "learning_rate": 2.4143396846254926e-05, "loss": 0.5034, "step": 2383 }, { "epoch": 0.39, "learning_rate": 2.4140932982917214e-05, "loss": 0.8399, "step": 2384 }, { "epoch": 0.39, "learning_rate": 2.41384691195795e-05, "loss": 1.0925, "step": 2385 }, { "epoch": 0.39, "learning_rate": 2.413600525624179e-05, "loss": 0.6292, "step": 2386 }, { "epoch": 0.39, "learning_rate": 2.4133541392904073e-05, "loss": 0.6181, "step": 2387 }, { "epoch": 0.39, "learning_rate": 2.413107752956636e-05, "loss": 1.0462, "step": 2388 }, { "epoch": 0.39, "learning_rate": 2.412861366622865e-05, "loss": 1.6676, "step": 2389 }, { "epoch": 0.39, "learning_rate": 2.4126149802890933e-05, "loss": 1.484, "step": 2390 }, { "epoch": 0.39, "learning_rate": 2.412368593955322e-05, "loss": 0.8822, "step": 2391 }, { "epoch": 0.39, "learning_rate": 2.4121222076215505e-05, "loss": 1.4323, "step": 2392 }, { "epoch": 0.39, "learning_rate": 2.4118758212877793e-05, "loss": 1.0095, "step": 2393 }, { "epoch": 0.39, "learning_rate": 2.4116294349540077e-05, "loss": 0.352, "step": 2394 }, { "epoch": 0.39, "learning_rate": 2.4113830486202368e-05, "loss": 0.5471, "step": 2395 }, { "epoch": 0.39, "learning_rate": 2.4111366622864652e-05, "loss": 0.7801, "step": 2396 }, { "epoch": 0.39, "learning_rate": 2.410890275952694e-05, "loss": 0.895, "step": 2397 }, { "epoch": 0.39, "learning_rate": 2.4106438896189224e-05, "loss": 1.0504, "step": 2398 }, { "epoch": 0.39, "learning_rate": 2.4103975032851512e-05, "loss": 1.0168, "step": 2399 }, { "epoch": 0.39, "learning_rate": 2.4101511169513796e-05, "loss": 1.5867, "step": 2400 }, { "epoch": 0.39, "learning_rate": 2.4099047306176084e-05, "loss": 0.6991, "step": 2401 }, { "epoch": 0.39, "learning_rate": 2.4096583442838372e-05, "loss": 1.6575, "step": 2402 }, { "epoch": 0.39, "learning_rate": 2.4094119579500656e-05, "loss": 0.5497, "step": 2403 }, { "epoch": 0.39, "learning_rate": 2.4091655716162944e-05, "loss": 1.9342, "step": 2404 }, { "epoch": 0.4, "learning_rate": 2.408919185282523e-05, "loss": 1.276, "step": 2405 }, { "epoch": 0.4, "learning_rate": 2.408672798948752e-05, "loss": 0.9123, "step": 2406 }, { "epoch": 0.4, "learning_rate": 2.4084264126149803e-05, "loss": 0.9181, "step": 2407 }, { "epoch": 0.4, "learning_rate": 2.408180026281209e-05, "loss": 0.4828, "step": 2408 }, { "epoch": 0.4, "learning_rate": 2.4079336399474375e-05, "loss": 0.9123, "step": 2409 }, { "epoch": 0.4, "learning_rate": 2.4076872536136663e-05, "loss": 1.0588, "step": 2410 }, { "epoch": 0.4, "learning_rate": 2.4074408672798947e-05, "loss": 1.2296, "step": 2411 }, { "epoch": 0.4, "learning_rate": 2.4071944809461235e-05, "loss": 1.1253, "step": 2412 }, { "epoch": 0.4, "learning_rate": 2.4069480946123523e-05, "loss": 1.1301, "step": 2413 }, { "epoch": 0.4, "learning_rate": 2.4067017082785807e-05, "loss": 0.8406, "step": 2414 }, { "epoch": 0.4, "learning_rate": 2.4064553219448098e-05, "loss": 1.0395, "step": 2415 }, { "epoch": 0.4, "learning_rate": 2.4062089356110382e-05, "loss": 1.2181, "step": 2416 }, { "epoch": 0.4, "learning_rate": 2.405962549277267e-05, "loss": 0.7253, "step": 2417 }, { "epoch": 0.4, "learning_rate": 2.4057161629434954e-05, "loss": 0.8319, "step": 2418 }, { "epoch": 0.4, "learning_rate": 2.4054697766097242e-05, "loss": 0.8734, "step": 2419 }, { "epoch": 0.4, "learning_rate": 2.4052233902759526e-05, "loss": 1.1141, "step": 2420 }, { "epoch": 0.4, "learning_rate": 2.4049770039421814e-05, "loss": 0.5286, "step": 2421 }, { "epoch": 0.4, "learning_rate": 2.4047306176084098e-05, "loss": 0.8383, "step": 2422 }, { "epoch": 0.4, "learning_rate": 2.4044842312746386e-05, "loss": 0.7705, "step": 2423 }, { "epoch": 0.4, "learning_rate": 2.404237844940867e-05, "loss": 0.7927, "step": 2424 }, { "epoch": 0.4, "learning_rate": 2.403991458607096e-05, "loss": 0.7201, "step": 2425 }, { "epoch": 0.4, "learning_rate": 2.403745072273325e-05, "loss": 0.8667, "step": 2426 }, { "epoch": 0.4, "learning_rate": 2.4034986859395533e-05, "loss": 1.1543, "step": 2427 }, { "epoch": 0.4, "learning_rate": 2.403252299605782e-05, "loss": 0.9064, "step": 2428 }, { "epoch": 0.4, "learning_rate": 2.4030059132720105e-05, "loss": 0.7217, "step": 2429 }, { "epoch": 0.4, "learning_rate": 2.4027595269382393e-05, "loss": 0.9676, "step": 2430 }, { "epoch": 0.4, "learning_rate": 2.4025131406044677e-05, "loss": 0.9573, "step": 2431 }, { "epoch": 0.4, "learning_rate": 2.4022667542706965e-05, "loss": 0.436, "step": 2432 }, { "epoch": 0.4, "learning_rate": 2.402020367936925e-05, "loss": 1.6942, "step": 2433 }, { "epoch": 0.4, "learning_rate": 2.4017739816031537e-05, "loss": 0.9964, "step": 2434 }, { "epoch": 0.4, "learning_rate": 2.4015275952693824e-05, "loss": 0.6469, "step": 2435 }, { "epoch": 0.4, "learning_rate": 2.4012812089356112e-05, "loss": 1.1055, "step": 2436 }, { "epoch": 0.4, "learning_rate": 2.40103482260184e-05, "loss": 0.8302, "step": 2437 }, { "epoch": 0.4, "learning_rate": 2.4007884362680684e-05, "loss": 0.6279, "step": 2438 }, { "epoch": 0.4, "learning_rate": 2.4005420499342972e-05, "loss": 0.945, "step": 2439 }, { "epoch": 0.4, "learning_rate": 2.4002956636005256e-05, "loss": 1.2291, "step": 2440 }, { "epoch": 0.4, "learning_rate": 2.4000492772667544e-05, "loss": 1.3333, "step": 2441 }, { "epoch": 0.4, "learning_rate": 2.3998028909329828e-05, "loss": 0.8163, "step": 2442 }, { "epoch": 0.4, "learning_rate": 2.3995565045992116e-05, "loss": 0.4655, "step": 2443 }, { "epoch": 0.4, "learning_rate": 2.39931011826544e-05, "loss": 1.6094, "step": 2444 }, { "epoch": 0.4, "learning_rate": 2.399063731931669e-05, "loss": 2.5792, "step": 2445 }, { "epoch": 0.4, "learning_rate": 2.3988173455978975e-05, "loss": 1.0799, "step": 2446 }, { "epoch": 0.4, "learning_rate": 2.3985709592641263e-05, "loss": 0.4612, "step": 2447 }, { "epoch": 0.4, "learning_rate": 2.3983245729303547e-05, "loss": 0.7356, "step": 2448 }, { "epoch": 0.4, "learning_rate": 2.3980781865965835e-05, "loss": 0.8301, "step": 2449 }, { "epoch": 0.4, "learning_rate": 2.3978318002628123e-05, "loss": 0.8207, "step": 2450 }, { "epoch": 0.4, "learning_rate": 2.3975854139290407e-05, "loss": 1.1625, "step": 2451 }, { "epoch": 0.4, "learning_rate": 2.3973390275952695e-05, "loss": 0.9598, "step": 2452 }, { "epoch": 0.4, "learning_rate": 2.397092641261498e-05, "loss": 0.9069, "step": 2453 }, { "epoch": 0.4, "learning_rate": 2.3968462549277267e-05, "loss": 1.2134, "step": 2454 }, { "epoch": 0.4, "learning_rate": 2.3965998685939554e-05, "loss": 1.0752, "step": 2455 }, { "epoch": 0.4, "learning_rate": 2.3963534822601842e-05, "loss": 0.6182, "step": 2456 }, { "epoch": 0.4, "learning_rate": 2.3961070959264126e-05, "loss": 0.8066, "step": 2457 }, { "epoch": 0.4, "learning_rate": 2.3958607095926414e-05, "loss": 0.8189, "step": 2458 }, { "epoch": 0.4, "learning_rate": 2.3956143232588698e-05, "loss": 1.5647, "step": 2459 }, { "epoch": 0.4, "learning_rate": 2.3953679369250986e-05, "loss": 0.967, "step": 2460 }, { "epoch": 0.4, "learning_rate": 2.3951215505913274e-05, "loss": 0.798, "step": 2461 }, { "epoch": 0.4, "learning_rate": 2.3948751642575558e-05, "loss": 0.7606, "step": 2462 }, { "epoch": 0.4, "learning_rate": 2.3946287779237846e-05, "loss": 2.2038, "step": 2463 }, { "epoch": 0.4, "learning_rate": 2.394382391590013e-05, "loss": 0.7936, "step": 2464 }, { "epoch": 0.4, "learning_rate": 2.394136005256242e-05, "loss": 0.5145, "step": 2465 }, { "epoch": 0.41, "learning_rate": 2.3938896189224705e-05, "loss": 0.8379, "step": 2466 }, { "epoch": 0.41, "learning_rate": 2.3936432325886993e-05, "loss": 1.1911, "step": 2467 }, { "epoch": 0.41, "learning_rate": 2.3933968462549277e-05, "loss": 1.2503, "step": 2468 }, { "epoch": 0.41, "learning_rate": 2.3931504599211565e-05, "loss": 0.6734, "step": 2469 }, { "epoch": 0.41, "learning_rate": 2.392904073587385e-05, "loss": 0.9046, "step": 2470 }, { "epoch": 0.41, "learning_rate": 2.3926576872536137e-05, "loss": 1.2892, "step": 2471 }, { "epoch": 0.41, "learning_rate": 2.392411300919842e-05, "loss": 1.1343, "step": 2472 }, { "epoch": 0.41, "learning_rate": 2.392164914586071e-05, "loss": 0.6798, "step": 2473 }, { "epoch": 0.41, "learning_rate": 2.3919185282522996e-05, "loss": 0.9734, "step": 2474 }, { "epoch": 0.41, "learning_rate": 2.3916721419185284e-05, "loss": 0.8035, "step": 2475 }, { "epoch": 0.41, "learning_rate": 2.3914257555847572e-05, "loss": 1.0236, "step": 2476 }, { "epoch": 0.41, "learning_rate": 2.3911793692509856e-05, "loss": 0.8652, "step": 2477 }, { "epoch": 0.41, "learning_rate": 2.3909329829172144e-05, "loss": 1.9875, "step": 2478 }, { "epoch": 0.41, "learning_rate": 2.3906865965834428e-05, "loss": 0.9096, "step": 2479 }, { "epoch": 0.41, "learning_rate": 2.3904402102496716e-05, "loss": 0.6704, "step": 2480 }, { "epoch": 0.41, "learning_rate": 2.3901938239159e-05, "loss": 0.6566, "step": 2481 }, { "epoch": 0.41, "learning_rate": 2.3899474375821288e-05, "loss": 0.8978, "step": 2482 }, { "epoch": 0.41, "learning_rate": 2.3897010512483572e-05, "loss": 0.7333, "step": 2483 }, { "epoch": 0.41, "learning_rate": 2.389454664914586e-05, "loss": 1.352, "step": 2484 }, { "epoch": 0.41, "learning_rate": 2.389208278580815e-05, "loss": 0.6041, "step": 2485 }, { "epoch": 0.41, "learning_rate": 2.3889618922470435e-05, "loss": 0.8759, "step": 2486 }, { "epoch": 0.41, "learning_rate": 2.3887155059132723e-05, "loss": 1.1887, "step": 2487 }, { "epoch": 0.41, "learning_rate": 2.3884691195795007e-05, "loss": 0.8508, "step": 2488 }, { "epoch": 0.41, "learning_rate": 2.3882227332457295e-05, "loss": 0.7459, "step": 2489 }, { "epoch": 0.41, "learning_rate": 2.387976346911958e-05, "loss": 1.128, "step": 2490 }, { "epoch": 0.41, "learning_rate": 2.3877299605781867e-05, "loss": 0.9788, "step": 2491 }, { "epoch": 0.41, "learning_rate": 2.387483574244415e-05, "loss": 1.272, "step": 2492 }, { "epoch": 0.41, "learning_rate": 2.387237187910644e-05, "loss": 0.5747, "step": 2493 }, { "epoch": 0.41, "learning_rate": 2.3869908015768723e-05, "loss": 0.7359, "step": 2494 }, { "epoch": 0.41, "learning_rate": 2.3867444152431014e-05, "loss": 0.6882, "step": 2495 }, { "epoch": 0.41, "learning_rate": 2.38649802890933e-05, "loss": 0.6564, "step": 2496 }, { "epoch": 0.41, "learning_rate": 2.3862516425755586e-05, "loss": 1.3405, "step": 2497 }, { "epoch": 0.41, "learning_rate": 2.3860052562417874e-05, "loss": 1.4141, "step": 2498 }, { "epoch": 0.41, "learning_rate": 2.3857588699080158e-05, "loss": 0.716, "step": 2499 }, { "epoch": 0.41, "learning_rate": 2.3855124835742446e-05, "loss": 1.2358, "step": 2500 }, { "epoch": 0.41, "eval_exact_match": 84.40870387890256, "eval_f1": 91.22663955040923, "step": 2500 }, { "epoch": 0.41, "learning_rate": 2.385266097240473e-05, "loss": 0.2951, "step": 2501 }, { "epoch": 0.41, "learning_rate": 2.3850197109067018e-05, "loss": 0.7487, "step": 2502 }, { "epoch": 0.41, "learning_rate": 2.3847733245729302e-05, "loss": 1.0547, "step": 2503 }, { "epoch": 0.41, "learning_rate": 2.384526938239159e-05, "loss": 1.0871, "step": 2504 }, { "epoch": 0.41, "learning_rate": 2.3842805519053877e-05, "loss": 1.2352, "step": 2505 }, { "epoch": 0.41, "learning_rate": 2.3840341655716165e-05, "loss": 1.2047, "step": 2506 }, { "epoch": 0.41, "learning_rate": 2.383787779237845e-05, "loss": 0.7916, "step": 2507 }, { "epoch": 0.41, "learning_rate": 2.3835413929040737e-05, "loss": 0.8279, "step": 2508 }, { "epoch": 0.41, "learning_rate": 2.3832950065703025e-05, "loss": 1.0549, "step": 2509 }, { "epoch": 0.41, "learning_rate": 2.383048620236531e-05, "loss": 0.9383, "step": 2510 }, { "epoch": 0.41, "learning_rate": 2.3828022339027597e-05, "loss": 0.8787, "step": 2511 }, { "epoch": 0.41, "learning_rate": 2.382555847568988e-05, "loss": 0.5781, "step": 2512 }, { "epoch": 0.41, "learning_rate": 2.382309461235217e-05, "loss": 1.1727, "step": 2513 }, { "epoch": 0.41, "learning_rate": 2.3820630749014453e-05, "loss": 0.6017, "step": 2514 }, { "epoch": 0.41, "learning_rate": 2.3818166885676744e-05, "loss": 0.6651, "step": 2515 }, { "epoch": 0.41, "learning_rate": 2.3815703022339028e-05, "loss": 1.6394, "step": 2516 }, { "epoch": 0.41, "learning_rate": 2.3813239159001316e-05, "loss": 1.176, "step": 2517 }, { "epoch": 0.41, "learning_rate": 2.38107752956636e-05, "loss": 0.9065, "step": 2518 }, { "epoch": 0.41, "learning_rate": 2.3808311432325888e-05, "loss": 0.9073, "step": 2519 }, { "epoch": 0.41, "learning_rate": 2.3805847568988175e-05, "loss": 0.8772, "step": 2520 }, { "epoch": 0.41, "learning_rate": 2.380338370565046e-05, "loss": 0.9213, "step": 2521 }, { "epoch": 0.41, "learning_rate": 2.3800919842312747e-05, "loss": 0.9787, "step": 2522 }, { "epoch": 0.41, "learning_rate": 2.3798455978975032e-05, "loss": 0.6448, "step": 2523 }, { "epoch": 0.41, "learning_rate": 2.379599211563732e-05, "loss": 0.8878, "step": 2524 }, { "epoch": 0.41, "learning_rate": 2.3793528252299607e-05, "loss": 0.7872, "step": 2525 }, { "epoch": 0.41, "learning_rate": 2.3791064388961895e-05, "loss": 0.8623, "step": 2526 }, { "epoch": 0.42, "learning_rate": 2.378860052562418e-05, "loss": 0.8842, "step": 2527 }, { "epoch": 0.42, "learning_rate": 2.3786136662286467e-05, "loss": 0.6409, "step": 2528 }, { "epoch": 0.42, "learning_rate": 2.378367279894875e-05, "loss": 1.042, "step": 2529 }, { "epoch": 0.42, "learning_rate": 2.378120893561104e-05, "loss": 0.5681, "step": 2530 }, { "epoch": 0.42, "learning_rate": 2.3778745072273323e-05, "loss": 0.9983, "step": 2531 }, { "epoch": 0.42, "learning_rate": 2.377628120893561e-05, "loss": 0.6289, "step": 2532 }, { "epoch": 0.42, "learning_rate": 2.37738173455979e-05, "loss": 0.5046, "step": 2533 }, { "epoch": 0.42, "learning_rate": 2.3771353482260183e-05, "loss": 1.3291, "step": 2534 }, { "epoch": 0.42, "learning_rate": 2.3768889618922474e-05, "loss": 1.2667, "step": 2535 }, { "epoch": 0.42, "learning_rate": 2.3766425755584758e-05, "loss": 1.1436, "step": 2536 }, { "epoch": 0.42, "learning_rate": 2.3763961892247046e-05, "loss": 0.8323, "step": 2537 }, { "epoch": 0.42, "learning_rate": 2.376149802890933e-05, "loss": 1.129, "step": 2538 }, { "epoch": 0.42, "learning_rate": 2.3759034165571618e-05, "loss": 1.1446, "step": 2539 }, { "epoch": 0.42, "learning_rate": 2.3756570302233902e-05, "loss": 0.4797, "step": 2540 }, { "epoch": 0.42, "learning_rate": 2.375410643889619e-05, "loss": 1.6392, "step": 2541 }, { "epoch": 0.42, "learning_rate": 2.3751642575558474e-05, "loss": 0.6817, "step": 2542 }, { "epoch": 0.42, "learning_rate": 2.374917871222076e-05, "loss": 0.5423, "step": 2543 }, { "epoch": 0.42, "learning_rate": 2.374671484888305e-05, "loss": 1.0187, "step": 2544 }, { "epoch": 0.42, "learning_rate": 2.3744250985545337e-05, "loss": 1.2528, "step": 2545 }, { "epoch": 0.42, "learning_rate": 2.3741787122207625e-05, "loss": 0.3203, "step": 2546 }, { "epoch": 0.42, "learning_rate": 2.373932325886991e-05, "loss": 0.5088, "step": 2547 }, { "epoch": 0.42, "learning_rate": 2.3736859395532197e-05, "loss": 1.2404, "step": 2548 }, { "epoch": 0.42, "learning_rate": 2.373439553219448e-05, "loss": 1.0289, "step": 2549 }, { "epoch": 0.42, "learning_rate": 2.373193166885677e-05, "loss": 0.9063, "step": 2550 }, { "epoch": 0.42, "learning_rate": 2.3729467805519053e-05, "loss": 1.1628, "step": 2551 }, { "epoch": 0.42, "learning_rate": 2.372700394218134e-05, "loss": 1.496, "step": 2552 }, { "epoch": 0.42, "learning_rate": 2.3724540078843625e-05, "loss": 0.7428, "step": 2553 }, { "epoch": 0.42, "learning_rate": 2.3722076215505913e-05, "loss": 0.5885, "step": 2554 }, { "epoch": 0.42, "learning_rate": 2.37196123521682e-05, "loss": 1.3393, "step": 2555 }, { "epoch": 0.42, "learning_rate": 2.3717148488830488e-05, "loss": 1.096, "step": 2556 }, { "epoch": 0.42, "learning_rate": 2.3714684625492776e-05, "loss": 0.6729, "step": 2557 }, { "epoch": 0.42, "learning_rate": 2.371222076215506e-05, "loss": 0.6586, "step": 2558 }, { "epoch": 0.42, "learning_rate": 2.3709756898817348e-05, "loss": 1.23, "step": 2559 }, { "epoch": 0.42, "learning_rate": 2.3707293035479632e-05, "loss": 0.7113, "step": 2560 }, { "epoch": 0.42, "learning_rate": 2.370482917214192e-05, "loss": 1.3213, "step": 2561 }, { "epoch": 0.42, "learning_rate": 2.3702365308804204e-05, "loss": 0.4975, "step": 2562 }, { "epoch": 0.42, "learning_rate": 2.369990144546649e-05, "loss": 1.5013, "step": 2563 }, { "epoch": 0.42, "learning_rate": 2.3697437582128776e-05, "loss": 0.6171, "step": 2564 }, { "epoch": 0.42, "learning_rate": 2.3694973718791067e-05, "loss": 0.6402, "step": 2565 }, { "epoch": 0.42, "learning_rate": 2.369250985545335e-05, "loss": 0.7578, "step": 2566 }, { "epoch": 0.42, "learning_rate": 2.369004599211564e-05, "loss": 0.5663, "step": 2567 }, { "epoch": 0.42, "learning_rate": 2.3687582128777926e-05, "loss": 1.0093, "step": 2568 }, { "epoch": 0.42, "learning_rate": 2.368511826544021e-05, "loss": 0.4331, "step": 2569 }, { "epoch": 0.42, "learning_rate": 2.36826544021025e-05, "loss": 1.9064, "step": 2570 }, { "epoch": 0.42, "learning_rate": 2.3680190538764783e-05, "loss": 1.23, "step": 2571 }, { "epoch": 0.42, "learning_rate": 2.367772667542707e-05, "loss": 1.0775, "step": 2572 }, { "epoch": 0.42, "learning_rate": 2.3675262812089355e-05, "loss": 1.4662, "step": 2573 }, { "epoch": 0.42, "learning_rate": 2.3672798948751642e-05, "loss": 2.247, "step": 2574 }, { "epoch": 0.42, "learning_rate": 2.367033508541393e-05, "loss": 1.3203, "step": 2575 }, { "epoch": 0.42, "learning_rate": 2.3667871222076218e-05, "loss": 1.1257, "step": 2576 }, { "epoch": 0.42, "learning_rate": 2.3665407358738502e-05, "loss": 0.6193, "step": 2577 }, { "epoch": 0.42, "learning_rate": 2.366294349540079e-05, "loss": 0.9961, "step": 2578 }, { "epoch": 0.42, "learning_rate": 2.3660479632063074e-05, "loss": 1.1667, "step": 2579 }, { "epoch": 0.42, "learning_rate": 2.365801576872536e-05, "loss": 0.8079, "step": 2580 }, { "epoch": 0.42, "learning_rate": 2.365555190538765e-05, "loss": 1.0263, "step": 2581 }, { "epoch": 0.42, "learning_rate": 2.3653088042049934e-05, "loss": 1.1427, "step": 2582 }, { "epoch": 0.42, "learning_rate": 2.365062417871222e-05, "loss": 0.8236, "step": 2583 }, { "epoch": 0.42, "learning_rate": 2.3648160315374506e-05, "loss": 0.727, "step": 2584 }, { "epoch": 0.42, "learning_rate": 2.3645696452036797e-05, "loss": 0.2985, "step": 2585 }, { "epoch": 0.42, "learning_rate": 2.364323258869908e-05, "loss": 1.0591, "step": 2586 }, { "epoch": 0.42, "learning_rate": 2.364076872536137e-05, "loss": 0.4046, "step": 2587 }, { "epoch": 0.43, "learning_rate": 2.3638304862023653e-05, "loss": 1.1021, "step": 2588 }, { "epoch": 0.43, "learning_rate": 2.363584099868594e-05, "loss": 1.0088, "step": 2589 }, { "epoch": 0.43, "learning_rate": 2.3633377135348225e-05, "loss": 0.7145, "step": 2590 }, { "epoch": 0.43, "learning_rate": 2.3630913272010513e-05, "loss": 0.8592, "step": 2591 }, { "epoch": 0.43, "learning_rate": 2.36284494086728e-05, "loss": 0.5665, "step": 2592 }, { "epoch": 0.43, "learning_rate": 2.3625985545335085e-05, "loss": 0.7707, "step": 2593 }, { "epoch": 0.43, "learning_rate": 2.3623521681997372e-05, "loss": 0.9089, "step": 2594 }, { "epoch": 0.43, "learning_rate": 2.362105781865966e-05, "loss": 1.0939, "step": 2595 }, { "epoch": 0.43, "learning_rate": 2.3618593955321948e-05, "loss": 1.0097, "step": 2596 }, { "epoch": 0.43, "learning_rate": 2.3616130091984232e-05, "loss": 1.1284, "step": 2597 }, { "epoch": 0.43, "learning_rate": 2.361366622864652e-05, "loss": 1.0439, "step": 2598 }, { "epoch": 0.43, "learning_rate": 2.3611202365308804e-05, "loss": 0.4919, "step": 2599 }, { "epoch": 0.43, "learning_rate": 2.360873850197109e-05, "loss": 0.5847, "step": 2600 }, { "epoch": 0.43, "learning_rate": 2.3606274638633376e-05, "loss": 0.9893, "step": 2601 }, { "epoch": 0.43, "learning_rate": 2.3603810775295663e-05, "loss": 1.5669, "step": 2602 }, { "epoch": 0.43, "learning_rate": 2.3601346911957948e-05, "loss": 0.3263, "step": 2603 }, { "epoch": 0.43, "learning_rate": 2.3598883048620235e-05, "loss": 0.8803, "step": 2604 }, { "epoch": 0.43, "learning_rate": 2.3596419185282527e-05, "loss": 1.0234, "step": 2605 }, { "epoch": 0.43, "learning_rate": 2.359395532194481e-05, "loss": 0.7127, "step": 2606 }, { "epoch": 0.43, "learning_rate": 2.35914914586071e-05, "loss": 0.6324, "step": 2607 }, { "epoch": 0.43, "learning_rate": 2.3589027595269383e-05, "loss": 1.2376, "step": 2608 }, { "epoch": 0.43, "learning_rate": 2.358656373193167e-05, "loss": 0.832, "step": 2609 }, { "epoch": 0.43, "learning_rate": 2.3584099868593955e-05, "loss": 0.4707, "step": 2610 }, { "epoch": 0.43, "learning_rate": 2.3581636005256242e-05, "loss": 0.5524, "step": 2611 }, { "epoch": 0.43, "learning_rate": 2.3579172141918527e-05, "loss": 0.7008, "step": 2612 }, { "epoch": 0.43, "learning_rate": 2.3576708278580814e-05, "loss": 0.7356, "step": 2613 }, { "epoch": 0.43, "learning_rate": 2.35742444152431e-05, "loss": 1.2684, "step": 2614 }, { "epoch": 0.43, "learning_rate": 2.357178055190539e-05, "loss": 0.4876, "step": 2615 }, { "epoch": 0.43, "learning_rate": 2.3569316688567677e-05, "loss": 0.9152, "step": 2616 }, { "epoch": 0.43, "learning_rate": 2.3566852825229962e-05, "loss": 0.4528, "step": 2617 }, { "epoch": 0.43, "learning_rate": 2.356438896189225e-05, "loss": 0.8257, "step": 2618 }, { "epoch": 0.43, "learning_rate": 2.3561925098554534e-05, "loss": 0.9285, "step": 2619 }, { "epoch": 0.43, "learning_rate": 2.355946123521682e-05, "loss": 0.8703, "step": 2620 }, { "epoch": 0.43, "learning_rate": 2.3556997371879106e-05, "loss": 1.0081, "step": 2621 }, { "epoch": 0.43, "learning_rate": 2.3554533508541393e-05, "loss": 0.5445, "step": 2622 }, { "epoch": 0.43, "learning_rate": 2.3552069645203678e-05, "loss": 0.5355, "step": 2623 }, { "epoch": 0.43, "learning_rate": 2.3549605781865965e-05, "loss": 1.1696, "step": 2624 }, { "epoch": 0.43, "learning_rate": 2.3547141918528253e-05, "loss": 1.2284, "step": 2625 }, { "epoch": 0.43, "learning_rate": 2.354467805519054e-05, "loss": 0.7772, "step": 2626 }, { "epoch": 0.43, "learning_rate": 2.3542214191852825e-05, "loss": 0.6809, "step": 2627 }, { "epoch": 0.43, "learning_rate": 2.3539750328515113e-05, "loss": 1.5774, "step": 2628 }, { "epoch": 0.43, "learning_rate": 2.35372864651774e-05, "loss": 1.3882, "step": 2629 }, { "epoch": 0.43, "learning_rate": 2.3534822601839685e-05, "loss": 0.8519, "step": 2630 }, { "epoch": 0.43, "learning_rate": 2.3532358738501972e-05, "loss": 0.7339, "step": 2631 }, { "epoch": 0.43, "learning_rate": 2.3529894875164257e-05, "loss": 1.0963, "step": 2632 }, { "epoch": 0.43, "learning_rate": 2.3527431011826544e-05, "loss": 0.5342, "step": 2633 }, { "epoch": 0.43, "learning_rate": 2.352496714848883e-05, "loss": 0.5597, "step": 2634 }, { "epoch": 0.43, "learning_rate": 2.352250328515112e-05, "loss": 0.6931, "step": 2635 }, { "epoch": 0.43, "learning_rate": 2.3520039421813404e-05, "loss": 0.6505, "step": 2636 }, { "epoch": 0.43, "learning_rate": 2.351757555847569e-05, "loss": 0.7446, "step": 2637 }, { "epoch": 0.43, "learning_rate": 2.3515111695137976e-05, "loss": 1.1949, "step": 2638 }, { "epoch": 0.43, "learning_rate": 2.3512647831800264e-05, "loss": 0.3266, "step": 2639 }, { "epoch": 0.43, "learning_rate": 2.351018396846255e-05, "loss": 1.2781, "step": 2640 }, { "epoch": 0.43, "learning_rate": 2.3507720105124836e-05, "loss": 0.5132, "step": 2641 }, { "epoch": 0.43, "learning_rate": 2.3505256241787123e-05, "loss": 0.7583, "step": 2642 }, { "epoch": 0.43, "learning_rate": 2.3502792378449407e-05, "loss": 1.3884, "step": 2643 }, { "epoch": 0.43, "learning_rate": 2.3500328515111695e-05, "loss": 1.0732, "step": 2644 }, { "epoch": 0.43, "learning_rate": 2.3497864651773983e-05, "loss": 0.7075, "step": 2645 }, { "epoch": 0.43, "learning_rate": 2.349540078843627e-05, "loss": 0.9278, "step": 2646 }, { "epoch": 0.43, "learning_rate": 2.3492936925098555e-05, "loss": 0.8069, "step": 2647 }, { "epoch": 0.43, "learning_rate": 2.3490473061760843e-05, "loss": 0.759, "step": 2648 }, { "epoch": 0.44, "learning_rate": 2.3488009198423127e-05, "loss": 0.7959, "step": 2649 }, { "epoch": 0.44, "learning_rate": 2.3485545335085414e-05, "loss": 0.5741, "step": 2650 }, { "epoch": 0.44, "learning_rate": 2.3483081471747702e-05, "loss": 1.3837, "step": 2651 }, { "epoch": 0.44, "learning_rate": 2.3480617608409986e-05, "loss": 1.2411, "step": 2652 }, { "epoch": 0.44, "learning_rate": 2.3478153745072274e-05, "loss": 0.8379, "step": 2653 }, { "epoch": 0.44, "learning_rate": 2.347568988173456e-05, "loss": 0.5815, "step": 2654 }, { "epoch": 0.44, "learning_rate": 2.347322601839685e-05, "loss": 1.4821, "step": 2655 }, { "epoch": 0.44, "learning_rate": 2.3470762155059134e-05, "loss": 0.9774, "step": 2656 }, { "epoch": 0.44, "learning_rate": 2.346829829172142e-05, "loss": 1.1023, "step": 2657 }, { "epoch": 0.44, "learning_rate": 2.3465834428383706e-05, "loss": 0.54, "step": 2658 }, { "epoch": 0.44, "learning_rate": 2.3463370565045993e-05, "loss": 0.9779, "step": 2659 }, { "epoch": 0.44, "learning_rate": 2.3460906701708278e-05, "loss": 0.7665, "step": 2660 }, { "epoch": 0.44, "learning_rate": 2.3458442838370565e-05, "loss": 0.492, "step": 2661 }, { "epoch": 0.44, "learning_rate": 2.345597897503285e-05, "loss": 1.1518, "step": 2662 }, { "epoch": 0.44, "learning_rate": 2.3453515111695137e-05, "loss": 0.5852, "step": 2663 }, { "epoch": 0.44, "learning_rate": 2.3451051248357425e-05, "loss": 0.7739, "step": 2664 }, { "epoch": 0.44, "learning_rate": 2.3448587385019713e-05, "loss": 0.6305, "step": 2665 }, { "epoch": 0.44, "learning_rate": 2.3446123521682e-05, "loss": 0.5038, "step": 2666 }, { "epoch": 0.44, "learning_rate": 2.3443659658344285e-05, "loss": 0.6635, "step": 2667 }, { "epoch": 0.44, "learning_rate": 2.3441195795006572e-05, "loss": 1.2864, "step": 2668 }, { "epoch": 0.44, "learning_rate": 2.3438731931668857e-05, "loss": 0.9064, "step": 2669 }, { "epoch": 0.44, "learning_rate": 2.3436268068331144e-05, "loss": 0.4945, "step": 2670 }, { "epoch": 0.44, "learning_rate": 2.343380420499343e-05, "loss": 0.4206, "step": 2671 }, { "epoch": 0.44, "learning_rate": 2.3431340341655716e-05, "loss": 0.9665, "step": 2672 }, { "epoch": 0.44, "learning_rate": 2.3428876478318e-05, "loss": 1.3637, "step": 2673 }, { "epoch": 0.44, "learning_rate": 2.3426412614980288e-05, "loss": 1.3116, "step": 2674 }, { "epoch": 0.44, "learning_rate": 2.342394875164258e-05, "loss": 0.6845, "step": 2675 }, { "epoch": 0.44, "learning_rate": 2.3421484888304864e-05, "loss": 0.8603, "step": 2676 }, { "epoch": 0.44, "learning_rate": 2.341902102496715e-05, "loss": 0.9136, "step": 2677 }, { "epoch": 0.44, "learning_rate": 2.3416557161629436e-05, "loss": 0.8271, "step": 2678 }, { "epoch": 0.44, "learning_rate": 2.3414093298291723e-05, "loss": 0.6512, "step": 2679 }, { "epoch": 0.44, "learning_rate": 2.3411629434954008e-05, "loss": 0.6638, "step": 2680 }, { "epoch": 0.44, "learning_rate": 2.3409165571616295e-05, "loss": 0.7271, "step": 2681 }, { "epoch": 0.44, "learning_rate": 2.340670170827858e-05, "loss": 0.9357, "step": 2682 }, { "epoch": 0.44, "learning_rate": 2.3404237844940867e-05, "loss": 0.8108, "step": 2683 }, { "epoch": 0.44, "learning_rate": 2.340177398160315e-05, "loss": 0.9153, "step": 2684 }, { "epoch": 0.44, "learning_rate": 2.3399310118265443e-05, "loss": 0.9349, "step": 2685 }, { "epoch": 0.44, "learning_rate": 2.3396846254927727e-05, "loss": 1.2076, "step": 2686 }, { "epoch": 0.44, "learning_rate": 2.3394382391590015e-05, "loss": 0.6023, "step": 2687 }, { "epoch": 0.44, "learning_rate": 2.3391918528252302e-05, "loss": 1.1786, "step": 2688 }, { "epoch": 0.44, "learning_rate": 2.3389454664914587e-05, "loss": 0.8226, "step": 2689 }, { "epoch": 0.44, "learning_rate": 2.3386990801576874e-05, "loss": 0.6688, "step": 2690 }, { "epoch": 0.44, "learning_rate": 2.338452693823916e-05, "loss": 1.4439, "step": 2691 }, { "epoch": 0.44, "learning_rate": 2.3382063074901446e-05, "loss": 0.3711, "step": 2692 }, { "epoch": 0.44, "learning_rate": 2.337959921156373e-05, "loss": 1.0917, "step": 2693 }, { "epoch": 0.44, "learning_rate": 2.3377135348226018e-05, "loss": 1.116, "step": 2694 }, { "epoch": 0.44, "learning_rate": 2.3374671484888306e-05, "loss": 1.317, "step": 2695 }, { "epoch": 0.44, "learning_rate": 2.3372207621550593e-05, "loss": 0.8513, "step": 2696 }, { "epoch": 0.44, "learning_rate": 2.3369743758212878e-05, "loss": 1.1185, "step": 2697 }, { "epoch": 0.44, "learning_rate": 2.3367279894875165e-05, "loss": 0.7906, "step": 2698 }, { "epoch": 0.44, "learning_rate": 2.3364816031537453e-05, "loss": 0.4341, "step": 2699 }, { "epoch": 0.44, "learning_rate": 2.3362352168199737e-05, "loss": 0.7769, "step": 2700 }, { "epoch": 0.44, "learning_rate": 2.3359888304862025e-05, "loss": 0.9003, "step": 2701 }, { "epoch": 0.44, "learning_rate": 2.335742444152431e-05, "loss": 1.2826, "step": 2702 }, { "epoch": 0.44, "learning_rate": 2.3354960578186597e-05, "loss": 0.9046, "step": 2703 }, { "epoch": 0.44, "learning_rate": 2.335249671484888e-05, "loss": 0.517, "step": 2704 }, { "epoch": 0.44, "learning_rate": 2.3350032851511172e-05, "loss": 0.6948, "step": 2705 }, { "epoch": 0.44, "learning_rate": 2.3347568988173457e-05, "loss": 0.7769, "step": 2706 }, { "epoch": 0.44, "learning_rate": 2.3345105124835744e-05, "loss": 1.049, "step": 2707 }, { "epoch": 0.44, "learning_rate": 2.334264126149803e-05, "loss": 1.045, "step": 2708 }, { "epoch": 0.44, "learning_rate": 2.3340177398160316e-05, "loss": 0.6566, "step": 2709 }, { "epoch": 0.45, "learning_rate": 2.33377135348226e-05, "loss": 0.4328, "step": 2710 }, { "epoch": 0.45, "learning_rate": 2.333524967148489e-05, "loss": 1.2446, "step": 2711 }, { "epoch": 0.45, "learning_rate": 2.3332785808147176e-05, "loss": 0.7471, "step": 2712 }, { "epoch": 0.45, "learning_rate": 2.333032194480946e-05, "loss": 0.4346, "step": 2713 }, { "epoch": 0.45, "learning_rate": 2.3327858081471748e-05, "loss": 0.7793, "step": 2714 }, { "epoch": 0.45, "learning_rate": 2.3325394218134036e-05, "loss": 1.3351, "step": 2715 }, { "epoch": 0.45, "learning_rate": 2.3322930354796323e-05, "loss": 0.6653, "step": 2716 }, { "epoch": 0.45, "learning_rate": 2.3320466491458608e-05, "loss": 0.852, "step": 2717 }, { "epoch": 0.45, "learning_rate": 2.3318002628120895e-05, "loss": 0.9915, "step": 2718 }, { "epoch": 0.45, "learning_rate": 2.331553876478318e-05, "loss": 0.8184, "step": 2719 }, { "epoch": 0.45, "learning_rate": 2.3313074901445467e-05, "loss": 0.7156, "step": 2720 }, { "epoch": 0.45, "learning_rate": 2.331061103810775e-05, "loss": 1.2461, "step": 2721 }, { "epoch": 0.45, "learning_rate": 2.330814717477004e-05, "loss": 1.0146, "step": 2722 }, { "epoch": 0.45, "learning_rate": 2.3305683311432327e-05, "loss": 1.2732, "step": 2723 }, { "epoch": 0.45, "learning_rate": 2.330321944809461e-05, "loss": 0.6633, "step": 2724 }, { "epoch": 0.45, "learning_rate": 2.3300755584756902e-05, "loss": 0.6422, "step": 2725 }, { "epoch": 0.45, "learning_rate": 2.3298291721419187e-05, "loss": 1.0061, "step": 2726 }, { "epoch": 0.45, "learning_rate": 2.3295827858081474e-05, "loss": 0.8565, "step": 2727 }, { "epoch": 0.45, "learning_rate": 2.329336399474376e-05, "loss": 1.3145, "step": 2728 }, { "epoch": 0.45, "learning_rate": 2.3290900131406046e-05, "loss": 0.367, "step": 2729 }, { "epoch": 0.45, "learning_rate": 2.328843626806833e-05, "loss": 0.8743, "step": 2730 }, { "epoch": 0.45, "learning_rate": 2.3285972404730618e-05, "loss": 1.3087, "step": 2731 }, { "epoch": 0.45, "learning_rate": 2.3283508541392902e-05, "loss": 1.1862, "step": 2732 }, { "epoch": 0.45, "learning_rate": 2.328104467805519e-05, "loss": 1.6568, "step": 2733 }, { "epoch": 0.45, "learning_rate": 2.3278580814717474e-05, "loss": 0.8994, "step": 2734 }, { "epoch": 0.45, "learning_rate": 2.3276116951379766e-05, "loss": 1.1115, "step": 2735 }, { "epoch": 0.45, "learning_rate": 2.3273653088042053e-05, "loss": 1.0235, "step": 2736 }, { "epoch": 0.45, "learning_rate": 2.3271189224704337e-05, "loss": 1.0635, "step": 2737 }, { "epoch": 0.45, "learning_rate": 2.3268725361366625e-05, "loss": 1.2228, "step": 2738 }, { "epoch": 0.45, "learning_rate": 2.326626149802891e-05, "loss": 0.798, "step": 2739 }, { "epoch": 0.45, "learning_rate": 2.3263797634691197e-05, "loss": 1.4972, "step": 2740 }, { "epoch": 0.45, "learning_rate": 2.326133377135348e-05, "loss": 0.9444, "step": 2741 }, { "epoch": 0.45, "learning_rate": 2.325886990801577e-05, "loss": 0.7795, "step": 2742 }, { "epoch": 0.45, "learning_rate": 2.3256406044678053e-05, "loss": 0.5574, "step": 2743 }, { "epoch": 0.45, "learning_rate": 2.325394218134034e-05, "loss": 1.3889, "step": 2744 }, { "epoch": 0.45, "learning_rate": 2.325147831800263e-05, "loss": 0.5881, "step": 2745 }, { "epoch": 0.45, "learning_rate": 2.3249014454664916e-05, "loss": 0.2885, "step": 2746 }, { "epoch": 0.45, "learning_rate": 2.3246550591327204e-05, "loss": 0.9865, "step": 2747 }, { "epoch": 0.45, "learning_rate": 2.324408672798949e-05, "loss": 0.7044, "step": 2748 }, { "epoch": 0.45, "learning_rate": 2.3241622864651776e-05, "loss": 0.7009, "step": 2749 }, { "epoch": 0.45, "learning_rate": 2.323915900131406e-05, "loss": 0.6883, "step": 2750 }, { "epoch": 0.45, "learning_rate": 2.3236695137976348e-05, "loss": 0.5489, "step": 2751 }, { "epoch": 0.45, "learning_rate": 2.3234231274638632e-05, "loss": 0.5011, "step": 2752 }, { "epoch": 0.45, "learning_rate": 2.323176741130092e-05, "loss": 0.7725, "step": 2753 }, { "epoch": 0.45, "learning_rate": 2.3229303547963204e-05, "loss": 0.7688, "step": 2754 }, { "epoch": 0.45, "learning_rate": 2.3226839684625495e-05, "loss": 1.2018, "step": 2755 }, { "epoch": 0.45, "learning_rate": 2.322437582128778e-05, "loss": 1.942, "step": 2756 }, { "epoch": 0.45, "learning_rate": 2.3221911957950067e-05, "loss": 0.7371, "step": 2757 }, { "epoch": 0.45, "learning_rate": 2.321944809461235e-05, "loss": 0.9772, "step": 2758 }, { "epoch": 0.45, "learning_rate": 2.321698423127464e-05, "loss": 1.0002, "step": 2759 }, { "epoch": 0.45, "learning_rate": 2.3214520367936927e-05, "loss": 0.5168, "step": 2760 }, { "epoch": 0.45, "learning_rate": 2.321205650459921e-05, "loss": 1.421, "step": 2761 }, { "epoch": 0.45, "learning_rate": 2.32095926412615e-05, "loss": 0.983, "step": 2762 }, { "epoch": 0.45, "learning_rate": 2.3207128777923783e-05, "loss": 0.4632, "step": 2763 }, { "epoch": 0.45, "learning_rate": 2.320466491458607e-05, "loss": 0.6686, "step": 2764 }, { "epoch": 0.45, "learning_rate": 2.320220105124836e-05, "loss": 0.5974, "step": 2765 }, { "epoch": 0.45, "learning_rate": 2.3199737187910646e-05, "loss": 0.4614, "step": 2766 }, { "epoch": 0.45, "learning_rate": 2.319727332457293e-05, "loss": 0.6584, "step": 2767 }, { "epoch": 0.45, "learning_rate": 2.3194809461235218e-05, "loss": 0.8568, "step": 2768 }, { "epoch": 0.45, "learning_rate": 2.3192345597897503e-05, "loss": 1.0409, "step": 2769 }, { "epoch": 0.45, "learning_rate": 2.318988173455979e-05, "loss": 0.6896, "step": 2770 }, { "epoch": 0.46, "learning_rate": 2.3187417871222078e-05, "loss": 0.7932, "step": 2771 }, { "epoch": 0.46, "learning_rate": 2.3184954007884362e-05, "loss": 0.5929, "step": 2772 }, { "epoch": 0.46, "learning_rate": 2.318249014454665e-05, "loss": 0.6979, "step": 2773 }, { "epoch": 0.46, "learning_rate": 2.3180026281208934e-05, "loss": 0.9592, "step": 2774 }, { "epoch": 0.46, "learning_rate": 2.3177562417871225e-05, "loss": 0.6973, "step": 2775 }, { "epoch": 0.46, "learning_rate": 2.317509855453351e-05, "loss": 0.8437, "step": 2776 }, { "epoch": 0.46, "learning_rate": 2.3172634691195797e-05, "loss": 0.9289, "step": 2777 }, { "epoch": 0.46, "learning_rate": 2.317017082785808e-05, "loss": 1.527, "step": 2778 }, { "epoch": 0.46, "learning_rate": 2.316770696452037e-05, "loss": 0.9639, "step": 2779 }, { "epoch": 0.46, "learning_rate": 2.3165243101182653e-05, "loss": 1.1378, "step": 2780 }, { "epoch": 0.46, "learning_rate": 2.316277923784494e-05, "loss": 0.8796, "step": 2781 }, { "epoch": 0.46, "learning_rate": 2.316031537450723e-05, "loss": 0.6109, "step": 2782 }, { "epoch": 0.46, "learning_rate": 2.3157851511169513e-05, "loss": 0.5961, "step": 2783 }, { "epoch": 0.46, "learning_rate": 2.31553876478318e-05, "loss": 0.6749, "step": 2784 }, { "epoch": 0.46, "learning_rate": 2.315292378449409e-05, "loss": 0.762, "step": 2785 }, { "epoch": 0.46, "learning_rate": 2.3150459921156376e-05, "loss": 1.0132, "step": 2786 }, { "epoch": 0.46, "learning_rate": 2.314799605781866e-05, "loss": 1.0368, "step": 2787 }, { "epoch": 0.46, "learning_rate": 2.3145532194480948e-05, "loss": 1.0526, "step": 2788 }, { "epoch": 0.46, "learning_rate": 2.3143068331143232e-05, "loss": 0.9031, "step": 2789 }, { "epoch": 0.46, "learning_rate": 2.314060446780552e-05, "loss": 0.9768, "step": 2790 }, { "epoch": 0.46, "learning_rate": 2.3138140604467804e-05, "loss": 1.0186, "step": 2791 }, { "epoch": 0.46, "learning_rate": 2.3135676741130092e-05, "loss": 0.7006, "step": 2792 }, { "epoch": 0.46, "learning_rate": 2.3133212877792376e-05, "loss": 1.6328, "step": 2793 }, { "epoch": 0.46, "learning_rate": 2.3130749014454664e-05, "loss": 0.5912, "step": 2794 }, { "epoch": 0.46, "learning_rate": 2.3128285151116955e-05, "loss": 0.6165, "step": 2795 }, { "epoch": 0.46, "learning_rate": 2.312582128777924e-05, "loss": 0.6591, "step": 2796 }, { "epoch": 0.46, "learning_rate": 2.3123357424441527e-05, "loss": 0.6864, "step": 2797 }, { "epoch": 0.46, "learning_rate": 2.312089356110381e-05, "loss": 0.8069, "step": 2798 }, { "epoch": 0.46, "learning_rate": 2.31184296977661e-05, "loss": 0.6553, "step": 2799 }, { "epoch": 0.46, "learning_rate": 2.3115965834428383e-05, "loss": 0.7865, "step": 2800 }, { "epoch": 0.46, "learning_rate": 2.311350197109067e-05, "loss": 0.7977, "step": 2801 }, { "epoch": 0.46, "learning_rate": 2.3111038107752955e-05, "loss": 0.737, "step": 2802 }, { "epoch": 0.46, "learning_rate": 2.3108574244415243e-05, "loss": 0.8996, "step": 2803 }, { "epoch": 0.46, "learning_rate": 2.3106110381077527e-05, "loss": 0.6195, "step": 2804 }, { "epoch": 0.46, "learning_rate": 2.310364651773982e-05, "loss": 0.8179, "step": 2805 }, { "epoch": 0.46, "learning_rate": 2.3101182654402106e-05, "loss": 0.9376, "step": 2806 }, { "epoch": 0.46, "learning_rate": 2.309871879106439e-05, "loss": 0.572, "step": 2807 }, { "epoch": 0.46, "learning_rate": 2.3096254927726678e-05, "loss": 1.5286, "step": 2808 }, { "epoch": 0.46, "learning_rate": 2.3093791064388962e-05, "loss": 0.8452, "step": 2809 }, { "epoch": 0.46, "learning_rate": 2.309132720105125e-05, "loss": 0.5754, "step": 2810 }, { "epoch": 0.46, "learning_rate": 2.3088863337713534e-05, "loss": 1.2187, "step": 2811 }, { "epoch": 0.46, "learning_rate": 2.3086399474375822e-05, "loss": 0.5801, "step": 2812 }, { "epoch": 0.46, "learning_rate": 2.3083935611038106e-05, "loss": 0.6748, "step": 2813 }, { "epoch": 0.46, "learning_rate": 2.3081471747700394e-05, "loss": 0.96, "step": 2814 }, { "epoch": 0.46, "learning_rate": 2.307900788436268e-05, "loss": 0.5619, "step": 2815 }, { "epoch": 0.46, "learning_rate": 2.307654402102497e-05, "loss": 0.731, "step": 2816 }, { "epoch": 0.46, "learning_rate": 2.3074080157687254e-05, "loss": 1.4666, "step": 2817 }, { "epoch": 0.46, "learning_rate": 2.307161629434954e-05, "loss": 0.8626, "step": 2818 }, { "epoch": 0.46, "learning_rate": 2.306915243101183e-05, "loss": 1.1673, "step": 2819 }, { "epoch": 0.46, "learning_rate": 2.3066688567674113e-05, "loss": 0.8047, "step": 2820 }, { "epoch": 0.46, "learning_rate": 2.30642247043364e-05, "loss": 1.0883, "step": 2821 }, { "epoch": 0.46, "learning_rate": 2.3061760840998685e-05, "loss": 0.7806, "step": 2822 }, { "epoch": 0.46, "learning_rate": 2.3059296977660973e-05, "loss": 0.4041, "step": 2823 }, { "epoch": 0.46, "learning_rate": 2.3056833114323257e-05, "loss": 1.386, "step": 2824 }, { "epoch": 0.46, "learning_rate": 2.3054369250985548e-05, "loss": 0.87, "step": 2825 }, { "epoch": 0.46, "learning_rate": 2.3051905387647832e-05, "loss": 0.5345, "step": 2826 }, { "epoch": 0.46, "learning_rate": 2.304944152431012e-05, "loss": 0.7644, "step": 2827 }, { "epoch": 0.46, "learning_rate": 2.3046977660972404e-05, "loss": 0.851, "step": 2828 }, { "epoch": 0.46, "learning_rate": 2.3044513797634692e-05, "loss": 0.8781, "step": 2829 }, { "epoch": 0.46, "learning_rate": 2.304204993429698e-05, "loss": 1.4304, "step": 2830 }, { "epoch": 0.47, "learning_rate": 2.3039586070959264e-05, "loss": 1.4429, "step": 2831 }, { "epoch": 0.47, "learning_rate": 2.3037122207621552e-05, "loss": 0.6005, "step": 2832 }, { "epoch": 0.47, "learning_rate": 2.3034658344283836e-05, "loss": 1.079, "step": 2833 }, { "epoch": 0.47, "learning_rate": 2.3032194480946124e-05, "loss": 0.5204, "step": 2834 }, { "epoch": 0.47, "learning_rate": 2.302973061760841e-05, "loss": 1.3694, "step": 2835 }, { "epoch": 0.47, "learning_rate": 2.30272667542707e-05, "loss": 1.8368, "step": 2836 }, { "epoch": 0.47, "learning_rate": 2.3024802890932983e-05, "loss": 1.2579, "step": 2837 }, { "epoch": 0.47, "learning_rate": 2.302233902759527e-05, "loss": 0.8809, "step": 2838 }, { "epoch": 0.47, "learning_rate": 2.3019875164257555e-05, "loss": 0.9675, "step": 2839 }, { "epoch": 0.47, "learning_rate": 2.3017411300919843e-05, "loss": 1.114, "step": 2840 }, { "epoch": 0.47, "learning_rate": 2.3014947437582127e-05, "loss": 1.8303, "step": 2841 }, { "epoch": 0.47, "learning_rate": 2.3012483574244415e-05, "loss": 1.7333, "step": 2842 }, { "epoch": 0.47, "learning_rate": 2.3010019710906703e-05, "loss": 0.9154, "step": 2843 }, { "epoch": 0.47, "learning_rate": 2.3007555847568987e-05, "loss": 0.9163, "step": 2844 }, { "epoch": 0.47, "learning_rate": 2.3005091984231278e-05, "loss": 1.0432, "step": 2845 }, { "epoch": 0.47, "learning_rate": 2.3002628120893562e-05, "loss": 0.726, "step": 2846 }, { "epoch": 0.47, "learning_rate": 2.300016425755585e-05, "loss": 0.7546, "step": 2847 }, { "epoch": 0.47, "learning_rate": 2.2997700394218134e-05, "loss": 1.096, "step": 2848 }, { "epoch": 0.47, "learning_rate": 2.2995236530880422e-05, "loss": 0.8381, "step": 2849 }, { "epoch": 0.47, "learning_rate": 2.2992772667542706e-05, "loss": 0.4816, "step": 2850 }, { "epoch": 0.47, "learning_rate": 2.2990308804204994e-05, "loss": 0.7987, "step": 2851 }, { "epoch": 0.47, "learning_rate": 2.2987844940867278e-05, "loss": 1.0831, "step": 2852 }, { "epoch": 0.47, "learning_rate": 2.2985381077529566e-05, "loss": 0.8977, "step": 2853 }, { "epoch": 0.47, "learning_rate": 2.2982917214191854e-05, "loss": 0.3499, "step": 2854 }, { "epoch": 0.47, "learning_rate": 2.298045335085414e-05, "loss": 0.965, "step": 2855 }, { "epoch": 0.47, "learning_rate": 2.297798948751643e-05, "loss": 0.831, "step": 2856 }, { "epoch": 0.47, "learning_rate": 2.2975525624178713e-05, "loss": 1.0027, "step": 2857 }, { "epoch": 0.47, "learning_rate": 2.2973061760841e-05, "loss": 1.1778, "step": 2858 }, { "epoch": 0.47, "learning_rate": 2.2970597897503285e-05, "loss": 0.5646, "step": 2859 }, { "epoch": 0.47, "learning_rate": 2.2968134034165573e-05, "loss": 0.7588, "step": 2860 }, { "epoch": 0.47, "learning_rate": 2.2965670170827857e-05, "loss": 0.8242, "step": 2861 }, { "epoch": 0.47, "learning_rate": 2.2963206307490145e-05, "loss": 0.6825, "step": 2862 }, { "epoch": 0.47, "learning_rate": 2.296074244415243e-05, "loss": 0.5924, "step": 2863 }, { "epoch": 0.47, "learning_rate": 2.2958278580814717e-05, "loss": 0.3627, "step": 2864 }, { "epoch": 0.47, "learning_rate": 2.2955814717477004e-05, "loss": 0.7866, "step": 2865 }, { "epoch": 0.47, "learning_rate": 2.2953350854139292e-05, "loss": 0.7879, "step": 2866 }, { "epoch": 0.47, "learning_rate": 2.295088699080158e-05, "loss": 0.3767, "step": 2867 }, { "epoch": 0.47, "learning_rate": 2.2948423127463864e-05, "loss": 0.8215, "step": 2868 }, { "epoch": 0.47, "learning_rate": 2.2945959264126152e-05, "loss": 0.9136, "step": 2869 }, { "epoch": 0.47, "learning_rate": 2.2943495400788436e-05, "loss": 0.7657, "step": 2870 }, { "epoch": 0.47, "learning_rate": 2.2941031537450724e-05, "loss": 2.1666, "step": 2871 }, { "epoch": 0.47, "learning_rate": 2.2938567674113008e-05, "loss": 0.5345, "step": 2872 }, { "epoch": 0.47, "learning_rate": 2.2936103810775296e-05, "loss": 0.6974, "step": 2873 }, { "epoch": 0.47, "learning_rate": 2.293363994743758e-05, "loss": 1.2352, "step": 2874 }, { "epoch": 0.47, "learning_rate": 2.293117608409987e-05, "loss": 0.7964, "step": 2875 }, { "epoch": 0.47, "learning_rate": 2.2928712220762155e-05, "loss": 1.6276, "step": 2876 }, { "epoch": 0.47, "learning_rate": 2.2926248357424443e-05, "loss": 0.5579, "step": 2877 }, { "epoch": 0.47, "learning_rate": 2.292378449408673e-05, "loss": 1.2989, "step": 2878 }, { "epoch": 0.47, "learning_rate": 2.2921320630749015e-05, "loss": 0.7163, "step": 2879 }, { "epoch": 0.47, "learning_rate": 2.2918856767411303e-05, "loss": 0.7051, "step": 2880 }, { "epoch": 0.47, "learning_rate": 2.2916392904073587e-05, "loss": 1.6507, "step": 2881 }, { "epoch": 0.47, "learning_rate": 2.2913929040735875e-05, "loss": 0.9429, "step": 2882 }, { "epoch": 0.47, "learning_rate": 2.291146517739816e-05, "loss": 1.1365, "step": 2883 }, { "epoch": 0.47, "learning_rate": 2.2909001314060447e-05, "loss": 0.8237, "step": 2884 }, { "epoch": 0.47, "learning_rate": 2.2906537450722734e-05, "loss": 0.8377, "step": 2885 }, { "epoch": 0.47, "learning_rate": 2.2904073587385022e-05, "loss": 0.5427, "step": 2886 }, { "epoch": 0.47, "learning_rate": 2.2901609724047306e-05, "loss": 0.6785, "step": 2887 }, { "epoch": 0.47, "learning_rate": 2.2899145860709594e-05, "loss": 0.5747, "step": 2888 }, { "epoch": 0.47, "learning_rate": 2.2896681997371878e-05, "loss": 0.7278, "step": 2889 }, { "epoch": 0.47, "learning_rate": 2.2894218134034166e-05, "loss": 0.3661, "step": 2890 }, { "epoch": 0.47, "learning_rate": 2.2891754270696454e-05, "loss": 0.6792, "step": 2891 }, { "epoch": 0.48, "learning_rate": 2.2889290407358738e-05, "loss": 0.7507, "step": 2892 }, { "epoch": 0.48, "learning_rate": 2.2886826544021026e-05, "loss": 0.9823, "step": 2893 }, { "epoch": 0.48, "learning_rate": 2.288436268068331e-05, "loss": 1.0173, "step": 2894 }, { "epoch": 0.48, "learning_rate": 2.28818988173456e-05, "loss": 1.1222, "step": 2895 }, { "epoch": 0.48, "learning_rate": 2.2879434954007885e-05, "loss": 0.6794, "step": 2896 }, { "epoch": 0.48, "learning_rate": 2.2876971090670173e-05, "loss": 0.7697, "step": 2897 }, { "epoch": 0.48, "learning_rate": 2.2874507227332457e-05, "loss": 0.6719, "step": 2898 }, { "epoch": 0.48, "learning_rate": 2.2872043363994745e-05, "loss": 0.5897, "step": 2899 }, { "epoch": 0.48, "learning_rate": 2.286957950065703e-05, "loss": 0.8819, "step": 2900 }, { "epoch": 0.48, "learning_rate": 2.2867115637319317e-05, "loss": 0.4854, "step": 2901 }, { "epoch": 0.48, "learning_rate": 2.2864651773981605e-05, "loss": 0.4415, "step": 2902 }, { "epoch": 0.48, "learning_rate": 2.286218791064389e-05, "loss": 1.6016, "step": 2903 }, { "epoch": 0.48, "learning_rate": 2.2859724047306177e-05, "loss": 0.7374, "step": 2904 }, { "epoch": 0.48, "learning_rate": 2.2857260183968464e-05, "loss": 1.162, "step": 2905 }, { "epoch": 0.48, "learning_rate": 2.2854796320630752e-05, "loss": 0.5338, "step": 2906 }, { "epoch": 0.48, "learning_rate": 2.2852332457293036e-05, "loss": 1.0434, "step": 2907 }, { "epoch": 0.48, "learning_rate": 2.2849868593955324e-05, "loss": 2.1431, "step": 2908 }, { "epoch": 0.48, "learning_rate": 2.2847404730617608e-05, "loss": 1.58, "step": 2909 }, { "epoch": 0.48, "learning_rate": 2.2844940867279896e-05, "loss": 1.1232, "step": 2910 }, { "epoch": 0.48, "learning_rate": 2.284247700394218e-05, "loss": 1.5089, "step": 2911 }, { "epoch": 0.48, "learning_rate": 2.2840013140604468e-05, "loss": 1.3642, "step": 2912 }, { "epoch": 0.48, "learning_rate": 2.2837549277266755e-05, "loss": 1.1453, "step": 2913 }, { "epoch": 0.48, "learning_rate": 2.283508541392904e-05, "loss": 0.318, "step": 2914 }, { "epoch": 0.48, "learning_rate": 2.283262155059133e-05, "loss": 0.4829, "step": 2915 }, { "epoch": 0.48, "learning_rate": 2.2830157687253615e-05, "loss": 0.4579, "step": 2916 }, { "epoch": 0.48, "learning_rate": 2.2827693823915903e-05, "loss": 0.7809, "step": 2917 }, { "epoch": 0.48, "learning_rate": 2.2825229960578187e-05, "loss": 0.6334, "step": 2918 }, { "epoch": 0.48, "learning_rate": 2.2822766097240475e-05, "loss": 0.8642, "step": 2919 }, { "epoch": 0.48, "learning_rate": 2.282030223390276e-05, "loss": 0.8566, "step": 2920 }, { "epoch": 0.48, "learning_rate": 2.2817838370565047e-05, "loss": 1.2677, "step": 2921 }, { "epoch": 0.48, "learning_rate": 2.281537450722733e-05, "loss": 0.9012, "step": 2922 }, { "epoch": 0.48, "learning_rate": 2.281291064388962e-05, "loss": 0.6559, "step": 2923 }, { "epoch": 0.48, "learning_rate": 2.2810446780551903e-05, "loss": 1.3885, "step": 2924 }, { "epoch": 0.48, "learning_rate": 2.2807982917214194e-05, "loss": 0.8561, "step": 2925 }, { "epoch": 0.48, "learning_rate": 2.2805519053876482e-05, "loss": 1.0548, "step": 2926 }, { "epoch": 0.48, "learning_rate": 2.2803055190538766e-05, "loss": 0.8356, "step": 2927 }, { "epoch": 0.48, "learning_rate": 2.2800591327201054e-05, "loss": 1.3567, "step": 2928 }, { "epoch": 0.48, "learning_rate": 2.2798127463863338e-05, "loss": 0.595, "step": 2929 }, { "epoch": 0.48, "learning_rate": 2.2795663600525626e-05, "loss": 0.2796, "step": 2930 }, { "epoch": 0.48, "learning_rate": 2.279319973718791e-05, "loss": 0.5391, "step": 2931 }, { "epoch": 0.48, "learning_rate": 2.2790735873850198e-05, "loss": 0.9775, "step": 2932 }, { "epoch": 0.48, "learning_rate": 2.2788272010512482e-05, "loss": 0.8257, "step": 2933 }, { "epoch": 0.48, "learning_rate": 2.278580814717477e-05, "loss": 0.8681, "step": 2934 }, { "epoch": 0.48, "learning_rate": 2.2783344283837057e-05, "loss": 1.3172, "step": 2935 }, { "epoch": 0.48, "learning_rate": 2.2780880420499345e-05, "loss": 1.5781, "step": 2936 }, { "epoch": 0.48, "learning_rate": 2.2778416557161633e-05, "loss": 1.0163, "step": 2937 }, { "epoch": 0.48, "learning_rate": 2.2775952693823917e-05, "loss": 0.9788, "step": 2938 }, { "epoch": 0.48, "learning_rate": 2.2773488830486205e-05, "loss": 0.77, "step": 2939 }, { "epoch": 0.48, "learning_rate": 2.277102496714849e-05, "loss": 0.5851, "step": 2940 }, { "epoch": 0.48, "learning_rate": 2.2768561103810777e-05, "loss": 0.6477, "step": 2941 }, { "epoch": 0.48, "learning_rate": 2.276609724047306e-05, "loss": 0.9357, "step": 2942 }, { "epoch": 0.48, "learning_rate": 2.276363337713535e-05, "loss": 0.8143, "step": 2943 }, { "epoch": 0.48, "learning_rate": 2.2761169513797633e-05, "loss": 0.8817, "step": 2944 }, { "epoch": 0.48, "learning_rate": 2.2758705650459924e-05, "loss": 0.8119, "step": 2945 }, { "epoch": 0.48, "learning_rate": 2.2756241787122208e-05, "loss": 0.5916, "step": 2946 }, { "epoch": 0.48, "learning_rate": 2.2753777923784496e-05, "loss": 0.7221, "step": 2947 }, { "epoch": 0.48, "learning_rate": 2.275131406044678e-05, "loss": 1.1176, "step": 2948 }, { "epoch": 0.48, "learning_rate": 2.2748850197109068e-05, "loss": 0.6659, "step": 2949 }, { "epoch": 0.48, "learning_rate": 2.2746386333771356e-05, "loss": 1.0848, "step": 2950 }, { "epoch": 0.48, "learning_rate": 2.274392247043364e-05, "loss": 1.6307, "step": 2951 }, { "epoch": 0.48, "learning_rate": 2.2741458607095927e-05, "loss": 1.2192, "step": 2952 }, { "epoch": 0.49, "learning_rate": 2.2738994743758212e-05, "loss": 1.1942, "step": 2953 }, { "epoch": 0.49, "learning_rate": 2.27365308804205e-05, "loss": 1.0387, "step": 2954 }, { "epoch": 0.49, "learning_rate": 2.2734067017082787e-05, "loss": 0.6567, "step": 2955 }, { "epoch": 0.49, "learning_rate": 2.2731603153745075e-05, "loss": 1.1057, "step": 2956 }, { "epoch": 0.49, "learning_rate": 2.272913929040736e-05, "loss": 0.4178, "step": 2957 }, { "epoch": 0.49, "learning_rate": 2.2726675427069647e-05, "loss": 0.7547, "step": 2958 }, { "epoch": 0.49, "learning_rate": 2.272421156373193e-05, "loss": 0.9476, "step": 2959 }, { "epoch": 0.49, "learning_rate": 2.272174770039422e-05, "loss": 1.4319, "step": 2960 }, { "epoch": 0.49, "learning_rate": 2.2719283837056506e-05, "loss": 1.116, "step": 2961 }, { "epoch": 0.49, "learning_rate": 2.271681997371879e-05, "loss": 0.8477, "step": 2962 }, { "epoch": 0.49, "learning_rate": 2.271435611038108e-05, "loss": 0.5462, "step": 2963 }, { "epoch": 0.49, "learning_rate": 2.2711892247043363e-05, "loss": 0.4499, "step": 2964 }, { "epoch": 0.49, "learning_rate": 2.2709428383705654e-05, "loss": 0.8796, "step": 2965 }, { "epoch": 0.49, "learning_rate": 2.2706964520367938e-05, "loss": 0.7308, "step": 2966 }, { "epoch": 0.49, "learning_rate": 2.2704500657030226e-05, "loss": 0.7822, "step": 2967 }, { "epoch": 0.49, "learning_rate": 2.270203679369251e-05, "loss": 1.1145, "step": 2968 }, { "epoch": 0.49, "learning_rate": 2.2699572930354798e-05, "loss": 0.8493, "step": 2969 }, { "epoch": 0.49, "learning_rate": 2.2697109067017082e-05, "loss": 0.7254, "step": 2970 }, { "epoch": 0.49, "learning_rate": 2.269464520367937e-05, "loss": 0.8894, "step": 2971 }, { "epoch": 0.49, "learning_rate": 2.2692181340341654e-05, "loss": 1.053, "step": 2972 }, { "epoch": 0.49, "learning_rate": 2.268971747700394e-05, "loss": 1.3934, "step": 2973 }, { "epoch": 0.49, "learning_rate": 2.268725361366623e-05, "loss": 0.863, "step": 2974 }, { "epoch": 0.49, "learning_rate": 2.2684789750328517e-05, "loss": 0.7579, "step": 2975 }, { "epoch": 0.49, "learning_rate": 2.2682325886990805e-05, "loss": 1.0339, "step": 2976 }, { "epoch": 0.49, "learning_rate": 2.267986202365309e-05, "loss": 0.6017, "step": 2977 }, { "epoch": 0.49, "learning_rate": 2.2677398160315377e-05, "loss": 0.8172, "step": 2978 }, { "epoch": 0.49, "learning_rate": 2.267493429697766e-05, "loss": 1.0538, "step": 2979 }, { "epoch": 0.49, "learning_rate": 2.267247043363995e-05, "loss": 0.6497, "step": 2980 }, { "epoch": 0.49, "learning_rate": 2.2670006570302233e-05, "loss": 0.8707, "step": 2981 }, { "epoch": 0.49, "learning_rate": 2.266754270696452e-05, "loss": 1.0417, "step": 2982 }, { "epoch": 0.49, "learning_rate": 2.2665078843626805e-05, "loss": 1.2449, "step": 2983 }, { "epoch": 0.49, "learning_rate": 2.2662614980289093e-05, "loss": 0.5778, "step": 2984 }, { "epoch": 0.49, "learning_rate": 2.2660151116951384e-05, "loss": 1.0083, "step": 2985 }, { "epoch": 0.49, "learning_rate": 2.2657687253613668e-05, "loss": 0.7812, "step": 2986 }, { "epoch": 0.49, "learning_rate": 2.2655223390275956e-05, "loss": 1.1652, "step": 2987 }, { "epoch": 0.49, "learning_rate": 2.265275952693824e-05, "loss": 0.7997, "step": 2988 }, { "epoch": 0.49, "learning_rate": 2.2650295663600528e-05, "loss": 0.3168, "step": 2989 }, { "epoch": 0.49, "learning_rate": 2.2647831800262812e-05, "loss": 1.0196, "step": 2990 }, { "epoch": 0.49, "learning_rate": 2.26453679369251e-05, "loss": 0.5869, "step": 2991 }, { "epoch": 0.49, "learning_rate": 2.2642904073587384e-05, "loss": 0.7907, "step": 2992 }, { "epoch": 0.49, "learning_rate": 2.264044021024967e-05, "loss": 0.9109, "step": 2993 }, { "epoch": 0.49, "learning_rate": 2.2637976346911956e-05, "loss": 1.0451, "step": 2994 }, { "epoch": 0.49, "learning_rate": 2.2635512483574247e-05, "loss": 1.0553, "step": 2995 }, { "epoch": 0.49, "learning_rate": 2.263304862023653e-05, "loss": 0.6386, "step": 2996 }, { "epoch": 0.49, "learning_rate": 2.263058475689882e-05, "loss": 0.8391, "step": 2997 }, { "epoch": 0.49, "learning_rate": 2.2628120893561107e-05, "loss": 0.441, "step": 2998 }, { "epoch": 0.49, "learning_rate": 2.262565703022339e-05, "loss": 0.4801, "step": 2999 }, { "epoch": 0.49, "learning_rate": 2.262319316688568e-05, "loss": 1.4596, "step": 3000 }, { "epoch": 0.49, "eval_exact_match": 84.00189214758751, "eval_f1": 91.1334495810888, "step": 3000 }, { "epoch": 0.49, "learning_rate": 2.2620729303547963e-05, "loss": 0.6971, "step": 3001 }, { "epoch": 0.49, "learning_rate": 2.261826544021025e-05, "loss": 0.5619, "step": 3002 }, { "epoch": 0.49, "learning_rate": 2.2615801576872535e-05, "loss": 0.7604, "step": 3003 }, { "epoch": 0.49, "learning_rate": 2.2613337713534822e-05, "loss": 0.6708, "step": 3004 }, { "epoch": 0.49, "learning_rate": 2.261087385019711e-05, "loss": 0.995, "step": 3005 }, { "epoch": 0.49, "learning_rate": 2.2608409986859398e-05, "loss": 0.6088, "step": 3006 }, { "epoch": 0.49, "learning_rate": 2.2605946123521682e-05, "loss": 0.9904, "step": 3007 }, { "epoch": 0.49, "learning_rate": 2.260348226018397e-05, "loss": 1.2528, "step": 3008 }, { "epoch": 0.49, "learning_rate": 2.2601018396846257e-05, "loss": 0.83, "step": 3009 }, { "epoch": 0.49, "learning_rate": 2.2598554533508542e-05, "loss": 1.5427, "step": 3010 }, { "epoch": 0.49, "learning_rate": 2.259609067017083e-05, "loss": 0.7113, "step": 3011 }, { "epoch": 0.49, "learning_rate": 2.2593626806833114e-05, "loss": 0.6105, "step": 3012 }, { "epoch": 0.49, "learning_rate": 2.25911629434954e-05, "loss": 0.6856, "step": 3013 }, { "epoch": 0.5, "learning_rate": 2.2588699080157686e-05, "loss": 1.3277, "step": 3014 }, { "epoch": 0.5, "learning_rate": 2.2586235216819977e-05, "loss": 0.97, "step": 3015 }, { "epoch": 0.5, "learning_rate": 2.258377135348226e-05, "loss": 1.1368, "step": 3016 }, { "epoch": 0.5, "learning_rate": 2.258130749014455e-05, "loss": 0.4037, "step": 3017 }, { "epoch": 0.5, "learning_rate": 2.2578843626806833e-05, "loss": 0.4831, "step": 3018 }, { "epoch": 0.5, "learning_rate": 2.257637976346912e-05, "loss": 1.1746, "step": 3019 }, { "epoch": 0.5, "learning_rate": 2.2573915900131405e-05, "loss": 0.8429, "step": 3020 }, { "epoch": 0.5, "learning_rate": 2.2571452036793693e-05, "loss": 1.3992, "step": 3021 }, { "epoch": 0.5, "learning_rate": 2.256898817345598e-05, "loss": 0.6935, "step": 3022 }, { "epoch": 0.5, "learning_rate": 2.2566524310118265e-05, "loss": 1.1329, "step": 3023 }, { "epoch": 0.5, "learning_rate": 2.2564060446780552e-05, "loss": 1.2463, "step": 3024 }, { "epoch": 0.5, "learning_rate": 2.256159658344284e-05, "loss": 0.7811, "step": 3025 }, { "epoch": 0.5, "learning_rate": 2.2559132720105128e-05, "loss": 1.2121, "step": 3026 }, { "epoch": 0.5, "learning_rate": 2.2556668856767412e-05, "loss": 0.7561, "step": 3027 }, { "epoch": 0.5, "learning_rate": 2.25542049934297e-05, "loss": 0.6086, "step": 3028 }, { "epoch": 0.5, "learning_rate": 2.2551741130091984e-05, "loss": 0.7817, "step": 3029 }, { "epoch": 0.5, "learning_rate": 2.254927726675427e-05, "loss": 1.4098, "step": 3030 }, { "epoch": 0.5, "learning_rate": 2.2546813403416556e-05, "loss": 1.0398, "step": 3031 }, { "epoch": 0.5, "learning_rate": 2.2544349540078844e-05, "loss": 1.3841, "step": 3032 }, { "epoch": 0.5, "learning_rate": 2.254188567674113e-05, "loss": 0.5633, "step": 3033 }, { "epoch": 0.5, "learning_rate": 2.2539421813403415e-05, "loss": 1.0724, "step": 3034 }, { "epoch": 0.5, "learning_rate": 2.2536957950065707e-05, "loss": 0.7627, "step": 3035 }, { "epoch": 0.5, "learning_rate": 2.253449408672799e-05, "loss": 0.9655, "step": 3036 }, { "epoch": 0.5, "learning_rate": 2.253203022339028e-05, "loss": 0.9124, "step": 3037 }, { "epoch": 0.5, "learning_rate": 2.2529566360052563e-05, "loss": 1.1791, "step": 3038 }, { "epoch": 0.5, "learning_rate": 2.252710249671485e-05, "loss": 0.4814, "step": 3039 }, { "epoch": 0.5, "learning_rate": 2.2524638633377135e-05, "loss": 1.0121, "step": 3040 }, { "epoch": 0.5, "learning_rate": 2.2522174770039422e-05, "loss": 1.0858, "step": 3041 }, { "epoch": 0.5, "learning_rate": 2.2519710906701707e-05, "loss": 0.9946, "step": 3042 }, { "epoch": 0.5, "learning_rate": 2.2517247043363994e-05, "loss": 0.7, "step": 3043 }, { "epoch": 0.5, "learning_rate": 2.2514783180026282e-05, "loss": 0.5521, "step": 3044 }, { "epoch": 0.5, "learning_rate": 2.251231931668857e-05, "loss": 0.6613, "step": 3045 }, { "epoch": 0.5, "learning_rate": 2.2509855453350857e-05, "loss": 0.7671, "step": 3046 }, { "epoch": 0.5, "learning_rate": 2.2507391590013142e-05, "loss": 0.9705, "step": 3047 }, { "epoch": 0.5, "learning_rate": 2.250492772667543e-05, "loss": 1.0464, "step": 3048 }, { "epoch": 0.5, "learning_rate": 2.2502463863337714e-05, "loss": 0.6518, "step": 3049 }, { "epoch": 0.5, "learning_rate": 2.25e-05, "loss": 0.5883, "step": 3050 }, { "epoch": 0.5, "learning_rate": 2.2497536136662286e-05, "loss": 1.0618, "step": 3051 }, { "epoch": 0.5, "learning_rate": 2.2495072273324573e-05, "loss": 0.7859, "step": 3052 }, { "epoch": 0.5, "learning_rate": 2.2492608409986858e-05, "loss": 0.817, "step": 3053 }, { "epoch": 0.5, "learning_rate": 2.2490144546649145e-05, "loss": 1.0551, "step": 3054 }, { "epoch": 0.5, "learning_rate": 2.248768068331143e-05, "loss": 1.6745, "step": 3055 }, { "epoch": 0.5, "learning_rate": 2.248521681997372e-05, "loss": 0.9664, "step": 3056 }, { "epoch": 0.5, "learning_rate": 2.248275295663601e-05, "loss": 1.4854, "step": 3057 }, { "epoch": 0.5, "learning_rate": 2.2480289093298293e-05, "loss": 0.8337, "step": 3058 }, { "epoch": 0.5, "learning_rate": 2.247782522996058e-05, "loss": 0.8537, "step": 3059 }, { "epoch": 0.5, "learning_rate": 2.2475361366622865e-05, "loss": 0.6563, "step": 3060 }, { "epoch": 0.5, "learning_rate": 2.2472897503285152e-05, "loss": 0.6133, "step": 3061 }, { "epoch": 0.5, "learning_rate": 2.2470433639947437e-05, "loss": 0.5989, "step": 3062 }, { "epoch": 0.5, "learning_rate": 2.2467969776609724e-05, "loss": 0.5131, "step": 3063 }, { "epoch": 0.5, "learning_rate": 2.246550591327201e-05, "loss": 1.6042, "step": 3064 }, { "epoch": 0.5, "learning_rate": 2.2463042049934296e-05, "loss": 0.7112, "step": 3065 }, { "epoch": 0.5, "learning_rate": 2.2460578186596584e-05, "loss": 1.1302, "step": 3066 }, { "epoch": 0.5, "learning_rate": 2.245811432325887e-05, "loss": 1.013, "step": 3067 }, { "epoch": 0.5, "learning_rate": 2.245565045992116e-05, "loss": 0.7924, "step": 3068 }, { "epoch": 0.5, "learning_rate": 2.2453186596583444e-05, "loss": 1.0889, "step": 3069 }, { "epoch": 0.5, "learning_rate": 2.245072273324573e-05, "loss": 0.8417, "step": 3070 }, { "epoch": 0.5, "learning_rate": 2.2448258869908016e-05, "loss": 0.6479, "step": 3071 }, { "epoch": 0.5, "learning_rate": 2.2445795006570303e-05, "loss": 0.823, "step": 3072 }, { "epoch": 0.5, "learning_rate": 2.2443331143232588e-05, "loss": 1.3092, "step": 3073 }, { "epoch": 0.5, "learning_rate": 2.2440867279894875e-05, "loss": 0.8206, "step": 3074 }, { "epoch": 0.51, "learning_rate": 2.243840341655716e-05, "loss": 1.3883, "step": 3075 }, { "epoch": 0.51, "learning_rate": 2.243593955321945e-05, "loss": 0.7602, "step": 3076 }, { "epoch": 0.51, "learning_rate": 2.2433475689881735e-05, "loss": 0.8208, "step": 3077 }, { "epoch": 0.51, "learning_rate": 2.2431011826544023e-05, "loss": 1.0656, "step": 3078 }, { "epoch": 0.51, "learning_rate": 2.2428547963206307e-05, "loss": 0.6125, "step": 3079 }, { "epoch": 0.51, "learning_rate": 2.2426084099868595e-05, "loss": 1.0067, "step": 3080 }, { "epoch": 0.51, "learning_rate": 2.2423620236530882e-05, "loss": 1.8451, "step": 3081 }, { "epoch": 0.51, "learning_rate": 2.2421156373193166e-05, "loss": 1.331, "step": 3082 }, { "epoch": 0.51, "learning_rate": 2.2418692509855454e-05, "loss": 0.5301, "step": 3083 }, { "epoch": 0.51, "learning_rate": 2.241622864651774e-05, "loss": 0.8677, "step": 3084 }, { "epoch": 0.51, "learning_rate": 2.2413764783180026e-05, "loss": 1.0106, "step": 3085 }, { "epoch": 0.51, "learning_rate": 2.2411300919842314e-05, "loss": 0.8898, "step": 3086 }, { "epoch": 0.51, "learning_rate": 2.24088370565046e-05, "loss": 0.8233, "step": 3087 }, { "epoch": 0.51, "learning_rate": 2.2406373193166886e-05, "loss": 0.4489, "step": 3088 }, { "epoch": 0.51, "learning_rate": 2.2403909329829173e-05, "loss": 0.732, "step": 3089 }, { "epoch": 0.51, "learning_rate": 2.2401445466491458e-05, "loss": 0.691, "step": 3090 }, { "epoch": 0.51, "learning_rate": 2.2398981603153745e-05, "loss": 0.7799, "step": 3091 }, { "epoch": 0.51, "learning_rate": 2.2396517739816033e-05, "loss": 0.9717, "step": 3092 }, { "epoch": 0.51, "learning_rate": 2.2394053876478317e-05, "loss": 0.517, "step": 3093 }, { "epoch": 0.51, "learning_rate": 2.2391590013140605e-05, "loss": 0.9408, "step": 3094 }, { "epoch": 0.51, "learning_rate": 2.238912614980289e-05, "loss": 1.3184, "step": 3095 }, { "epoch": 0.51, "learning_rate": 2.238666228646518e-05, "loss": 0.4047, "step": 3096 }, { "epoch": 0.51, "learning_rate": 2.2384198423127465e-05, "loss": 0.7998, "step": 3097 }, { "epoch": 0.51, "learning_rate": 2.2381734559789752e-05, "loss": 0.3588, "step": 3098 }, { "epoch": 0.51, "learning_rate": 2.2379270696452037e-05, "loss": 1.2131, "step": 3099 }, { "epoch": 0.51, "learning_rate": 2.2376806833114324e-05, "loss": 0.4188, "step": 3100 }, { "epoch": 0.51, "learning_rate": 2.237434296977661e-05, "loss": 0.7148, "step": 3101 }, { "epoch": 0.51, "learning_rate": 2.2371879106438896e-05, "loss": 1.0251, "step": 3102 }, { "epoch": 0.51, "learning_rate": 2.236941524310118e-05, "loss": 1.1331, "step": 3103 }, { "epoch": 0.51, "learning_rate": 2.2366951379763468e-05, "loss": 1.1833, "step": 3104 }, { "epoch": 0.51, "learning_rate": 2.2364487516425756e-05, "loss": 0.9751, "step": 3105 }, { "epoch": 0.51, "learning_rate": 2.2362023653088044e-05, "loss": 0.9704, "step": 3106 }, { "epoch": 0.51, "learning_rate": 2.235955978975033e-05, "loss": 0.3974, "step": 3107 }, { "epoch": 0.51, "learning_rate": 2.2357095926412616e-05, "loss": 0.9545, "step": 3108 }, { "epoch": 0.51, "learning_rate": 2.2354632063074903e-05, "loss": 1.3096, "step": 3109 }, { "epoch": 0.51, "learning_rate": 2.2352168199737188e-05, "loss": 0.9921, "step": 3110 }, { "epoch": 0.51, "learning_rate": 2.2349704336399475e-05, "loss": 0.5634, "step": 3111 }, { "epoch": 0.51, "learning_rate": 2.234724047306176e-05, "loss": 1.0867, "step": 3112 }, { "epoch": 0.51, "learning_rate": 2.2344776609724047e-05, "loss": 1.2584, "step": 3113 }, { "epoch": 0.51, "learning_rate": 2.234231274638633e-05, "loss": 0.7646, "step": 3114 }, { "epoch": 0.51, "learning_rate": 2.233984888304862e-05, "loss": 1.1399, "step": 3115 }, { "epoch": 0.51, "learning_rate": 2.233738501971091e-05, "loss": 0.6122, "step": 3116 }, { "epoch": 0.51, "learning_rate": 2.2334921156373195e-05, "loss": 0.9023, "step": 3117 }, { "epoch": 0.51, "learning_rate": 2.2332457293035482e-05, "loss": 1.0788, "step": 3118 }, { "epoch": 0.51, "learning_rate": 2.2329993429697767e-05, "loss": 1.4163, "step": 3119 }, { "epoch": 0.51, "learning_rate": 2.2327529566360054e-05, "loss": 1.2535, "step": 3120 }, { "epoch": 0.51, "learning_rate": 2.232506570302234e-05, "loss": 1.16, "step": 3121 }, { "epoch": 0.51, "learning_rate": 2.2322601839684626e-05, "loss": 1.355, "step": 3122 }, { "epoch": 0.51, "learning_rate": 2.232013797634691e-05, "loss": 0.7284, "step": 3123 }, { "epoch": 0.51, "learning_rate": 2.2317674113009198e-05, "loss": 0.6762, "step": 3124 }, { "epoch": 0.51, "learning_rate": 2.2315210249671482e-05, "loss": 1.275, "step": 3125 }, { "epoch": 0.51, "learning_rate": 2.2312746386333774e-05, "loss": 0.7627, "step": 3126 }, { "epoch": 0.51, "learning_rate": 2.2310282522996058e-05, "loss": 1.2451, "step": 3127 }, { "epoch": 0.51, "learning_rate": 2.2307818659658345e-05, "loss": 0.8959, "step": 3128 }, { "epoch": 0.51, "learning_rate": 2.2305354796320633e-05, "loss": 1.1335, "step": 3129 }, { "epoch": 0.51, "learning_rate": 2.2302890932982917e-05, "loss": 1.6052, "step": 3130 }, { "epoch": 0.51, "learning_rate": 2.2300427069645205e-05, "loss": 1.2545, "step": 3131 }, { "epoch": 0.51, "learning_rate": 2.229796320630749e-05, "loss": 1.3849, "step": 3132 }, { "epoch": 0.51, "learning_rate": 2.2295499342969777e-05, "loss": 1.0847, "step": 3133 }, { "epoch": 0.51, "learning_rate": 2.229303547963206e-05, "loss": 1.309, "step": 3134 }, { "epoch": 0.51, "learning_rate": 2.229057161629435e-05, "loss": 0.5136, "step": 3135 }, { "epoch": 0.52, "learning_rate": 2.2288107752956637e-05, "loss": 0.6612, "step": 3136 }, { "epoch": 0.52, "learning_rate": 2.2285643889618924e-05, "loss": 0.8309, "step": 3137 }, { "epoch": 0.52, "learning_rate": 2.228318002628121e-05, "loss": 0.9632, "step": 3138 }, { "epoch": 0.52, "learning_rate": 2.2280716162943496e-05, "loss": 1.1734, "step": 3139 }, { "epoch": 0.52, "learning_rate": 2.2278252299605784e-05, "loss": 0.4845, "step": 3140 }, { "epoch": 0.52, "learning_rate": 2.227578843626807e-05, "loss": 0.6025, "step": 3141 }, { "epoch": 0.52, "learning_rate": 2.2273324572930356e-05, "loss": 1.2241, "step": 3142 }, { "epoch": 0.52, "learning_rate": 2.227086070959264e-05, "loss": 1.1916, "step": 3143 }, { "epoch": 0.52, "learning_rate": 2.2268396846254928e-05, "loss": 0.8521, "step": 3144 }, { "epoch": 0.52, "learning_rate": 2.2265932982917212e-05, "loss": 1.2811, "step": 3145 }, { "epoch": 0.52, "learning_rate": 2.2263469119579503e-05, "loss": 0.6489, "step": 3146 }, { "epoch": 0.52, "learning_rate": 2.2261005256241788e-05, "loss": 0.4369, "step": 3147 }, { "epoch": 0.52, "learning_rate": 2.2258541392904075e-05, "loss": 0.8531, "step": 3148 }, { "epoch": 0.52, "learning_rate": 2.225607752956636e-05, "loss": 0.9676, "step": 3149 }, { "epoch": 0.52, "learning_rate": 2.2253613666228647e-05, "loss": 0.7338, "step": 3150 }, { "epoch": 0.52, "learning_rate": 2.225114980289093e-05, "loss": 0.4839, "step": 3151 }, { "epoch": 0.52, "learning_rate": 2.224868593955322e-05, "loss": 0.6732, "step": 3152 }, { "epoch": 0.52, "learning_rate": 2.2246222076215507e-05, "loss": 0.5458, "step": 3153 }, { "epoch": 0.52, "learning_rate": 2.224375821287779e-05, "loss": 0.7997, "step": 3154 }, { "epoch": 0.52, "learning_rate": 2.224129434954008e-05, "loss": 1.4218, "step": 3155 }, { "epoch": 0.52, "learning_rate": 2.2238830486202367e-05, "loss": 0.8733, "step": 3156 }, { "epoch": 0.52, "learning_rate": 2.2236366622864654e-05, "loss": 0.4612, "step": 3157 }, { "epoch": 0.52, "learning_rate": 2.223390275952694e-05, "loss": 1.3815, "step": 3158 }, { "epoch": 0.52, "learning_rate": 2.2231438896189226e-05, "loss": 1.4956, "step": 3159 }, { "epoch": 0.52, "learning_rate": 2.222897503285151e-05, "loss": 0.3469, "step": 3160 }, { "epoch": 0.52, "learning_rate": 2.2226511169513798e-05, "loss": 0.7554, "step": 3161 }, { "epoch": 0.52, "learning_rate": 2.2224047306176083e-05, "loss": 1.001, "step": 3162 }, { "epoch": 0.52, "learning_rate": 2.222158344283837e-05, "loss": 1.3627, "step": 3163 }, { "epoch": 0.52, "learning_rate": 2.2219119579500658e-05, "loss": 0.8053, "step": 3164 }, { "epoch": 0.52, "learning_rate": 2.2216655716162942e-05, "loss": 1.4742, "step": 3165 }, { "epoch": 0.52, "learning_rate": 2.2214191852825233e-05, "loss": 0.646, "step": 3166 }, { "epoch": 0.52, "learning_rate": 2.2211727989487518e-05, "loss": 0.8683, "step": 3167 }, { "epoch": 0.52, "learning_rate": 2.2209264126149805e-05, "loss": 0.522, "step": 3168 }, { "epoch": 0.52, "learning_rate": 2.220680026281209e-05, "loss": 1.3595, "step": 3169 }, { "epoch": 0.52, "learning_rate": 2.2204336399474377e-05, "loss": 0.7469, "step": 3170 }, { "epoch": 0.52, "learning_rate": 2.220187253613666e-05, "loss": 0.6074, "step": 3171 }, { "epoch": 0.52, "learning_rate": 2.219940867279895e-05, "loss": 1.0989, "step": 3172 }, { "epoch": 0.52, "learning_rate": 2.2196944809461233e-05, "loss": 1.0889, "step": 3173 }, { "epoch": 0.52, "learning_rate": 2.219448094612352e-05, "loss": 0.3404, "step": 3174 }, { "epoch": 0.52, "learning_rate": 2.219201708278581e-05, "loss": 0.5141, "step": 3175 }, { "epoch": 0.52, "learning_rate": 2.2189553219448096e-05, "loss": 0.9659, "step": 3176 }, { "epoch": 0.52, "learning_rate": 2.2187089356110384e-05, "loss": 0.7355, "step": 3177 }, { "epoch": 0.52, "learning_rate": 2.218462549277267e-05, "loss": 1.0688, "step": 3178 }, { "epoch": 0.52, "learning_rate": 2.2182161629434956e-05, "loss": 1.6606, "step": 3179 }, { "epoch": 0.52, "learning_rate": 2.217969776609724e-05, "loss": 0.8337, "step": 3180 }, { "epoch": 0.52, "learning_rate": 2.2177233902759528e-05, "loss": 0.9655, "step": 3181 }, { "epoch": 0.52, "learning_rate": 2.2174770039421812e-05, "loss": 1.1565, "step": 3182 }, { "epoch": 0.52, "learning_rate": 2.21723061760841e-05, "loss": 0.6158, "step": 3183 }, { "epoch": 0.52, "learning_rate": 2.2169842312746384e-05, "loss": 1.3556, "step": 3184 }, { "epoch": 0.52, "learning_rate": 2.2167378449408672e-05, "loss": 0.6015, "step": 3185 }, { "epoch": 0.52, "learning_rate": 2.216491458607096e-05, "loss": 0.4562, "step": 3186 }, { "epoch": 0.52, "learning_rate": 2.2162450722733247e-05, "loss": 0.6588, "step": 3187 }, { "epoch": 0.52, "learning_rate": 2.2159986859395535e-05, "loss": 1.6909, "step": 3188 }, { "epoch": 0.52, "learning_rate": 2.215752299605782e-05, "loss": 0.4816, "step": 3189 }, { "epoch": 0.52, "learning_rate": 2.2155059132720107e-05, "loss": 0.6945, "step": 3190 }, { "epoch": 0.52, "learning_rate": 2.215259526938239e-05, "loss": 0.7349, "step": 3191 }, { "epoch": 0.52, "learning_rate": 2.215013140604468e-05, "loss": 0.7103, "step": 3192 }, { "epoch": 0.52, "learning_rate": 2.2147667542706963e-05, "loss": 1.1553, "step": 3193 }, { "epoch": 0.52, "learning_rate": 2.214520367936925e-05, "loss": 0.684, "step": 3194 }, { "epoch": 0.52, "learning_rate": 2.2142739816031535e-05, "loss": 0.8577, "step": 3195 }, { "epoch": 0.52, "learning_rate": 2.2140275952693826e-05, "loss": 1.0476, "step": 3196 }, { "epoch": 0.53, "learning_rate": 2.213781208935611e-05, "loss": 1.1538, "step": 3197 }, { "epoch": 0.53, "learning_rate": 2.2135348226018398e-05, "loss": 0.8535, "step": 3198 }, { "epoch": 0.53, "learning_rate": 2.2132884362680686e-05, "loss": 0.9686, "step": 3199 }, { "epoch": 0.53, "learning_rate": 2.213042049934297e-05, "loss": 1.2973, "step": 3200 }, { "epoch": 0.53, "learning_rate": 2.2127956636005258e-05, "loss": 0.8284, "step": 3201 }, { "epoch": 0.53, "learning_rate": 2.2125492772667542e-05, "loss": 1.8053, "step": 3202 }, { "epoch": 0.53, "learning_rate": 2.212302890932983e-05, "loss": 0.6953, "step": 3203 }, { "epoch": 0.53, "learning_rate": 2.2120565045992114e-05, "loss": 0.9378, "step": 3204 }, { "epoch": 0.53, "learning_rate": 2.2118101182654402e-05, "loss": 1.2749, "step": 3205 }, { "epoch": 0.53, "learning_rate": 2.211563731931669e-05, "loss": 1.5285, "step": 3206 }, { "epoch": 0.53, "learning_rate": 2.2113173455978977e-05, "loss": 0.3658, "step": 3207 }, { "epoch": 0.53, "learning_rate": 2.211070959264126e-05, "loss": 0.6456, "step": 3208 }, { "epoch": 0.53, "learning_rate": 2.210824572930355e-05, "loss": 0.6101, "step": 3209 }, { "epoch": 0.53, "learning_rate": 2.2105781865965833e-05, "loss": 1.098, "step": 3210 }, { "epoch": 0.53, "learning_rate": 2.210331800262812e-05, "loss": 0.8964, "step": 3211 }, { "epoch": 0.53, "learning_rate": 2.210085413929041e-05, "loss": 1.1641, "step": 3212 }, { "epoch": 0.53, "learning_rate": 2.2098390275952693e-05, "loss": 1.4782, "step": 3213 }, { "epoch": 0.53, "learning_rate": 2.209592641261498e-05, "loss": 0.6846, "step": 3214 }, { "epoch": 0.53, "learning_rate": 2.2093462549277265e-05, "loss": 1.0941, "step": 3215 }, { "epoch": 0.53, "learning_rate": 2.2090998685939556e-05, "loss": 0.4927, "step": 3216 }, { "epoch": 0.53, "learning_rate": 2.208853482260184e-05, "loss": 0.7648, "step": 3217 }, { "epoch": 0.53, "learning_rate": 2.2086070959264128e-05, "loss": 0.7184, "step": 3218 }, { "epoch": 0.53, "learning_rate": 2.2083607095926412e-05, "loss": 0.4432, "step": 3219 }, { "epoch": 0.53, "learning_rate": 2.20811432325887e-05, "loss": 0.8761, "step": 3220 }, { "epoch": 0.53, "learning_rate": 2.2078679369250984e-05, "loss": 0.7106, "step": 3221 }, { "epoch": 0.53, "learning_rate": 2.2076215505913272e-05, "loss": 0.9839, "step": 3222 }, { "epoch": 0.53, "learning_rate": 2.207375164257556e-05, "loss": 1.2658, "step": 3223 }, { "epoch": 0.53, "learning_rate": 2.2071287779237844e-05, "loss": 0.7891, "step": 3224 }, { "epoch": 0.53, "learning_rate": 2.2068823915900132e-05, "loss": 1.1875, "step": 3225 }, { "epoch": 0.53, "learning_rate": 2.206636005256242e-05, "loss": 0.7639, "step": 3226 }, { "epoch": 0.53, "learning_rate": 2.2063896189224707e-05, "loss": 0.8623, "step": 3227 }, { "epoch": 0.53, "learning_rate": 2.206143232588699e-05, "loss": 0.6647, "step": 3228 }, { "epoch": 0.53, "learning_rate": 2.205896846254928e-05, "loss": 0.4456, "step": 3229 }, { "epoch": 0.53, "learning_rate": 2.2056504599211563e-05, "loss": 1.5103, "step": 3230 }, { "epoch": 0.53, "learning_rate": 2.205404073587385e-05, "loss": 1.2029, "step": 3231 }, { "epoch": 0.53, "learning_rate": 2.2051576872536135e-05, "loss": 1.3933, "step": 3232 }, { "epoch": 0.53, "learning_rate": 2.2049113009198423e-05, "loss": 0.8884, "step": 3233 }, { "epoch": 0.53, "learning_rate": 2.2046649145860707e-05, "loss": 0.6074, "step": 3234 }, { "epoch": 0.53, "learning_rate": 2.2044185282522995e-05, "loss": 1.5514, "step": 3235 }, { "epoch": 0.53, "learning_rate": 2.2041721419185286e-05, "loss": 1.0227, "step": 3236 }, { "epoch": 0.53, "learning_rate": 2.203925755584757e-05, "loss": 0.8064, "step": 3237 }, { "epoch": 0.53, "learning_rate": 2.2036793692509858e-05, "loss": 0.7289, "step": 3238 }, { "epoch": 0.53, "learning_rate": 2.2034329829172142e-05, "loss": 0.6494, "step": 3239 }, { "epoch": 0.53, "learning_rate": 2.203186596583443e-05, "loss": 1.3136, "step": 3240 }, { "epoch": 0.53, "learning_rate": 2.2029402102496714e-05, "loss": 0.5253, "step": 3241 }, { "epoch": 0.53, "learning_rate": 2.2026938239159002e-05, "loss": 0.5576, "step": 3242 }, { "epoch": 0.53, "learning_rate": 2.2024474375821286e-05, "loss": 1.5007, "step": 3243 }, { "epoch": 0.53, "learning_rate": 2.2022010512483574e-05, "loss": 1.1638, "step": 3244 }, { "epoch": 0.53, "learning_rate": 2.2019546649145858e-05, "loss": 0.5166, "step": 3245 }, { "epoch": 0.53, "learning_rate": 2.201708278580815e-05, "loss": 0.3774, "step": 3246 }, { "epoch": 0.53, "learning_rate": 2.2014618922470437e-05, "loss": 1.232, "step": 3247 }, { "epoch": 0.53, "learning_rate": 2.201215505913272e-05, "loss": 0.9522, "step": 3248 }, { "epoch": 0.53, "learning_rate": 2.200969119579501e-05, "loss": 0.7625, "step": 3249 }, { "epoch": 0.53, "learning_rate": 2.2007227332457293e-05, "loss": 1.273, "step": 3250 }, { "epoch": 0.53, "learning_rate": 2.200476346911958e-05, "loss": 0.9171, "step": 3251 }, { "epoch": 0.53, "learning_rate": 2.2002299605781865e-05, "loss": 1.0983, "step": 3252 }, { "epoch": 0.53, "learning_rate": 2.1999835742444153e-05, "loss": 0.7946, "step": 3253 }, { "epoch": 0.53, "learning_rate": 2.1997371879106437e-05, "loss": 0.7396, "step": 3254 }, { "epoch": 0.53, "learning_rate": 2.1994908015768725e-05, "loss": 0.655, "step": 3255 }, { "epoch": 0.53, "learning_rate": 2.1992444152431012e-05, "loss": 0.6789, "step": 3256 }, { "epoch": 0.53, "learning_rate": 2.19899802890933e-05, "loss": 1.3349, "step": 3257 }, { "epoch": 0.54, "learning_rate": 2.1987516425755584e-05, "loss": 0.6982, "step": 3258 }, { "epoch": 0.54, "learning_rate": 2.1985052562417872e-05, "loss": 0.7365, "step": 3259 }, { "epoch": 0.54, "learning_rate": 2.198258869908016e-05, "loss": 0.7475, "step": 3260 }, { "epoch": 0.54, "learning_rate": 2.1980124835742444e-05, "loss": 1.0614, "step": 3261 }, { "epoch": 0.54, "learning_rate": 2.1977660972404732e-05, "loss": 1.3984, "step": 3262 }, { "epoch": 0.54, "learning_rate": 2.1975197109067016e-05, "loss": 1.2771, "step": 3263 }, { "epoch": 0.54, "learning_rate": 2.1972733245729304e-05, "loss": 0.548, "step": 3264 }, { "epoch": 0.54, "learning_rate": 2.1970269382391588e-05, "loss": 0.7682, "step": 3265 }, { "epoch": 0.54, "learning_rate": 2.196780551905388e-05, "loss": 0.6682, "step": 3266 }, { "epoch": 0.54, "learning_rate": 2.1965341655716163e-05, "loss": 1.8833, "step": 3267 }, { "epoch": 0.54, "learning_rate": 2.196287779237845e-05, "loss": 0.8762, "step": 3268 }, { "epoch": 0.54, "learning_rate": 2.1960413929040735e-05, "loss": 0.9824, "step": 3269 }, { "epoch": 0.54, "learning_rate": 2.1957950065703023e-05, "loss": 0.9421, "step": 3270 }, { "epoch": 0.54, "learning_rate": 2.195548620236531e-05, "loss": 0.6065, "step": 3271 }, { "epoch": 0.54, "learning_rate": 2.1953022339027595e-05, "loss": 0.9249, "step": 3272 }, { "epoch": 0.54, "learning_rate": 2.1950558475689883e-05, "loss": 0.6872, "step": 3273 }, { "epoch": 0.54, "learning_rate": 2.1948094612352167e-05, "loss": 0.8793, "step": 3274 }, { "epoch": 0.54, "learning_rate": 2.1945630749014455e-05, "loss": 1.3431, "step": 3275 }, { "epoch": 0.54, "learning_rate": 2.1943166885676742e-05, "loss": 0.6278, "step": 3276 }, { "epoch": 0.54, "learning_rate": 2.194070302233903e-05, "loss": 0.6597, "step": 3277 }, { "epoch": 0.54, "learning_rate": 2.1938239159001314e-05, "loss": 0.8684, "step": 3278 }, { "epoch": 0.54, "learning_rate": 2.1935775295663602e-05, "loss": 0.7137, "step": 3279 }, { "epoch": 0.54, "learning_rate": 2.1933311432325886e-05, "loss": 1.306, "step": 3280 }, { "epoch": 0.54, "learning_rate": 2.1930847568988174e-05, "loss": 0.4401, "step": 3281 }, { "epoch": 0.54, "learning_rate": 2.1928383705650458e-05, "loss": 0.879, "step": 3282 }, { "epoch": 0.54, "learning_rate": 2.1925919842312746e-05, "loss": 0.4662, "step": 3283 }, { "epoch": 0.54, "learning_rate": 2.1923455978975034e-05, "loss": 0.6169, "step": 3284 }, { "epoch": 0.54, "learning_rate": 2.1920992115637318e-05, "loss": 1.422, "step": 3285 }, { "epoch": 0.54, "learning_rate": 2.191852825229961e-05, "loss": 1.019, "step": 3286 }, { "epoch": 0.54, "learning_rate": 2.1916064388961893e-05, "loss": 1.8954, "step": 3287 }, { "epoch": 0.54, "learning_rate": 2.191360052562418e-05, "loss": 0.5295, "step": 3288 }, { "epoch": 0.54, "learning_rate": 2.1911136662286465e-05, "loss": 0.8985, "step": 3289 }, { "epoch": 0.54, "learning_rate": 2.1908672798948753e-05, "loss": 1.0979, "step": 3290 }, { "epoch": 0.54, "learning_rate": 2.1906208935611037e-05, "loss": 1.2224, "step": 3291 }, { "epoch": 0.54, "learning_rate": 2.1903745072273325e-05, "loss": 0.8824, "step": 3292 }, { "epoch": 0.54, "learning_rate": 2.190128120893561e-05, "loss": 0.4003, "step": 3293 }, { "epoch": 0.54, "learning_rate": 2.1898817345597897e-05, "loss": 0.8487, "step": 3294 }, { "epoch": 0.54, "learning_rate": 2.1896353482260185e-05, "loss": 1.1159, "step": 3295 }, { "epoch": 0.54, "learning_rate": 2.1893889618922472e-05, "loss": 0.8809, "step": 3296 }, { "epoch": 0.54, "learning_rate": 2.189142575558476e-05, "loss": 0.6823, "step": 3297 }, { "epoch": 0.54, "learning_rate": 2.1888961892247044e-05, "loss": 1.0561, "step": 3298 }, { "epoch": 0.54, "learning_rate": 2.1886498028909332e-05, "loss": 0.9063, "step": 3299 }, { "epoch": 0.54, "learning_rate": 2.1884034165571616e-05, "loss": 0.936, "step": 3300 }, { "epoch": 0.54, "learning_rate": 2.1881570302233904e-05, "loss": 1.3769, "step": 3301 }, { "epoch": 0.54, "learning_rate": 2.1879106438896188e-05, "loss": 0.6406, "step": 3302 }, { "epoch": 0.54, "learning_rate": 2.1876642575558476e-05, "loss": 1.2526, "step": 3303 }, { "epoch": 0.54, "learning_rate": 2.187417871222076e-05, "loss": 1.2299, "step": 3304 }, { "epoch": 0.54, "learning_rate": 2.1871714848883048e-05, "loss": 1.0068, "step": 3305 }, { "epoch": 0.54, "learning_rate": 2.1869250985545335e-05, "loss": 1.0854, "step": 3306 }, { "epoch": 0.54, "learning_rate": 2.1866787122207623e-05, "loss": 1.2558, "step": 3307 }, { "epoch": 0.54, "learning_rate": 2.186432325886991e-05, "loss": 1.2035, "step": 3308 }, { "epoch": 0.54, "learning_rate": 2.1861859395532195e-05, "loss": 0.5414, "step": 3309 }, { "epoch": 0.54, "learning_rate": 2.1859395532194483e-05, "loss": 0.877, "step": 3310 }, { "epoch": 0.54, "learning_rate": 2.1856931668856767e-05, "loss": 0.6225, "step": 3311 }, { "epoch": 0.54, "learning_rate": 2.1854467805519055e-05, "loss": 0.5425, "step": 3312 }, { "epoch": 0.54, "learning_rate": 2.185200394218134e-05, "loss": 0.7953, "step": 3313 }, { "epoch": 0.54, "learning_rate": 2.1849540078843627e-05, "loss": 0.6311, "step": 3314 }, { "epoch": 0.54, "learning_rate": 2.184707621550591e-05, "loss": 0.4903, "step": 3315 }, { "epoch": 0.54, "learning_rate": 2.1844612352168202e-05, "loss": 0.3863, "step": 3316 }, { "epoch": 0.54, "learning_rate": 2.1842148488830486e-05, "loss": 1.0343, "step": 3317 }, { "epoch": 0.55, "learning_rate": 2.1839684625492774e-05, "loss": 1.0233, "step": 3318 }, { "epoch": 0.55, "learning_rate": 2.1837220762155062e-05, "loss": 0.8113, "step": 3319 }, { "epoch": 0.55, "learning_rate": 2.1834756898817346e-05, "loss": 0.8396, "step": 3320 }, { "epoch": 0.55, "learning_rate": 2.1832293035479634e-05, "loss": 1.3578, "step": 3321 }, { "epoch": 0.55, "learning_rate": 2.1829829172141918e-05, "loss": 0.5839, "step": 3322 }, { "epoch": 0.55, "learning_rate": 2.1827365308804206e-05, "loss": 0.5718, "step": 3323 }, { "epoch": 0.55, "learning_rate": 2.182490144546649e-05, "loss": 1.3635, "step": 3324 }, { "epoch": 0.55, "learning_rate": 2.1822437582128778e-05, "loss": 0.4639, "step": 3325 }, { "epoch": 0.55, "learning_rate": 2.1819973718791065e-05, "loss": 1.0158, "step": 3326 }, { "epoch": 0.55, "learning_rate": 2.1817509855453353e-05, "loss": 1.266, "step": 3327 }, { "epoch": 0.55, "learning_rate": 2.1815045992115637e-05, "loss": 0.3252, "step": 3328 }, { "epoch": 0.55, "learning_rate": 2.1812582128777925e-05, "loss": 0.7929, "step": 3329 }, { "epoch": 0.55, "learning_rate": 2.1810118265440213e-05, "loss": 1.0564, "step": 3330 }, { "epoch": 0.55, "learning_rate": 2.1807654402102497e-05, "loss": 0.922, "step": 3331 }, { "epoch": 0.55, "learning_rate": 2.1805190538764785e-05, "loss": 0.6795, "step": 3332 }, { "epoch": 0.55, "learning_rate": 2.180272667542707e-05, "loss": 0.8078, "step": 3333 }, { "epoch": 0.55, "learning_rate": 2.1800262812089357e-05, "loss": 0.8498, "step": 3334 }, { "epoch": 0.55, "learning_rate": 2.179779894875164e-05, "loss": 0.4422, "step": 3335 }, { "epoch": 0.55, "learning_rate": 2.1795335085413932e-05, "loss": 0.7932, "step": 3336 }, { "epoch": 0.55, "learning_rate": 2.1792871222076216e-05, "loss": 0.3781, "step": 3337 }, { "epoch": 0.55, "learning_rate": 2.1790407358738504e-05, "loss": 0.6481, "step": 3338 }, { "epoch": 0.55, "learning_rate": 2.1787943495400788e-05, "loss": 0.9157, "step": 3339 }, { "epoch": 0.55, "learning_rate": 2.1785479632063076e-05, "loss": 0.4627, "step": 3340 }, { "epoch": 0.55, "learning_rate": 2.178301576872536e-05, "loss": 0.429, "step": 3341 }, { "epoch": 0.55, "learning_rate": 2.1780551905387648e-05, "loss": 0.9031, "step": 3342 }, { "epoch": 0.55, "learning_rate": 2.1778088042049935e-05, "loss": 1.1632, "step": 3343 }, { "epoch": 0.55, "learning_rate": 2.177562417871222e-05, "loss": 1.1284, "step": 3344 }, { "epoch": 0.55, "learning_rate": 2.1773160315374507e-05, "loss": 1.1979, "step": 3345 }, { "epoch": 0.55, "learning_rate": 2.1770696452036795e-05, "loss": 1.4549, "step": 3346 }, { "epoch": 0.55, "learning_rate": 2.1768232588699083e-05, "loss": 0.868, "step": 3347 }, { "epoch": 0.55, "learning_rate": 2.1765768725361367e-05, "loss": 0.4576, "step": 3348 }, { "epoch": 0.55, "learning_rate": 2.1763304862023655e-05, "loss": 0.5718, "step": 3349 }, { "epoch": 0.55, "learning_rate": 2.176084099868594e-05, "loss": 0.7405, "step": 3350 }, { "epoch": 0.55, "learning_rate": 2.1758377135348227e-05, "loss": 1.1084, "step": 3351 }, { "epoch": 0.55, "learning_rate": 2.175591327201051e-05, "loss": 0.4046, "step": 3352 }, { "epoch": 0.55, "learning_rate": 2.17534494086728e-05, "loss": 1.0569, "step": 3353 }, { "epoch": 0.55, "learning_rate": 2.1750985545335086e-05, "loss": 0.5934, "step": 3354 }, { "epoch": 0.55, "learning_rate": 2.174852168199737e-05, "loss": 0.7478, "step": 3355 }, { "epoch": 0.55, "learning_rate": 2.1746057818659662e-05, "loss": 0.5315, "step": 3356 }, { "epoch": 0.55, "learning_rate": 2.1743593955321946e-05, "loss": 0.9699, "step": 3357 }, { "epoch": 0.55, "learning_rate": 2.1741130091984234e-05, "loss": 1.0167, "step": 3358 }, { "epoch": 0.55, "learning_rate": 2.1738666228646518e-05, "loss": 0.9308, "step": 3359 }, { "epoch": 0.55, "learning_rate": 2.1736202365308806e-05, "loss": 0.6561, "step": 3360 }, { "epoch": 0.55, "learning_rate": 2.173373850197109e-05, "loss": 1.1586, "step": 3361 }, { "epoch": 0.55, "learning_rate": 2.1731274638633378e-05, "loss": 1.2588, "step": 3362 }, { "epoch": 0.55, "learning_rate": 2.1728810775295662e-05, "loss": 0.646, "step": 3363 }, { "epoch": 0.55, "learning_rate": 2.172634691195795e-05, "loss": 1.1185, "step": 3364 }, { "epoch": 0.55, "learning_rate": 2.1723883048620234e-05, "loss": 0.7102, "step": 3365 }, { "epoch": 0.55, "learning_rate": 2.1721419185282525e-05, "loss": 1.0744, "step": 3366 }, { "epoch": 0.55, "learning_rate": 2.1718955321944813e-05, "loss": 0.8993, "step": 3367 }, { "epoch": 0.55, "learning_rate": 2.1716491458607097e-05, "loss": 1.0661, "step": 3368 }, { "epoch": 0.55, "learning_rate": 2.1714027595269385e-05, "loss": 0.7582, "step": 3369 }, { "epoch": 0.55, "learning_rate": 2.171156373193167e-05, "loss": 0.8755, "step": 3370 }, { "epoch": 0.55, "learning_rate": 2.1709099868593957e-05, "loss": 1.4688, "step": 3371 }, { "epoch": 0.55, "learning_rate": 2.170663600525624e-05, "loss": 1.0042, "step": 3372 }, { "epoch": 0.55, "learning_rate": 2.170417214191853e-05, "loss": 1.1182, "step": 3373 }, { "epoch": 0.55, "learning_rate": 2.1701708278580813e-05, "loss": 1.2702, "step": 3374 }, { "epoch": 0.55, "learning_rate": 2.16992444152431e-05, "loss": 0.757, "step": 3375 }, { "epoch": 0.55, "learning_rate": 2.1696780551905388e-05, "loss": 0.7589, "step": 3376 }, { "epoch": 0.55, "learning_rate": 2.1694316688567676e-05, "loss": 0.8128, "step": 3377 }, { "epoch": 0.55, "learning_rate": 2.1691852825229964e-05, "loss": 1.1075, "step": 3378 }, { "epoch": 0.56, "learning_rate": 2.1689388961892248e-05, "loss": 0.806, "step": 3379 }, { "epoch": 0.56, "learning_rate": 2.1686925098554536e-05, "loss": 0.8756, "step": 3380 }, { "epoch": 0.56, "learning_rate": 2.168446123521682e-05, "loss": 0.804, "step": 3381 }, { "epoch": 0.56, "learning_rate": 2.1681997371879108e-05, "loss": 0.6799, "step": 3382 }, { "epoch": 0.56, "learning_rate": 2.1679533508541392e-05, "loss": 0.9963, "step": 3383 }, { "epoch": 0.56, "learning_rate": 2.167706964520368e-05, "loss": 0.8638, "step": 3384 }, { "epoch": 0.56, "learning_rate": 2.1674605781865964e-05, "loss": 0.835, "step": 3385 }, { "epoch": 0.56, "learning_rate": 2.1672141918528255e-05, "loss": 0.7048, "step": 3386 }, { "epoch": 0.56, "learning_rate": 2.166967805519054e-05, "loss": 0.8738, "step": 3387 }, { "epoch": 0.56, "learning_rate": 2.1667214191852827e-05, "loss": 1.1514, "step": 3388 }, { "epoch": 0.56, "learning_rate": 2.166475032851511e-05, "loss": 0.6289, "step": 3389 }, { "epoch": 0.56, "learning_rate": 2.16622864651774e-05, "loss": 0.4912, "step": 3390 }, { "epoch": 0.56, "learning_rate": 2.1659822601839686e-05, "loss": 1.1945, "step": 3391 }, { "epoch": 0.56, "learning_rate": 2.165735873850197e-05, "loss": 0.9844, "step": 3392 }, { "epoch": 0.56, "learning_rate": 2.165489487516426e-05, "loss": 1.0791, "step": 3393 }, { "epoch": 0.56, "learning_rate": 2.1652431011826543e-05, "loss": 0.7081, "step": 3394 }, { "epoch": 0.56, "learning_rate": 2.164996714848883e-05, "loss": 0.4106, "step": 3395 }, { "epoch": 0.56, "learning_rate": 2.1647503285151118e-05, "loss": 0.4233, "step": 3396 }, { "epoch": 0.56, "learning_rate": 2.1645039421813406e-05, "loss": 0.7532, "step": 3397 }, { "epoch": 0.56, "learning_rate": 2.164257555847569e-05, "loss": 0.7397, "step": 3398 }, { "epoch": 0.56, "learning_rate": 2.1640111695137978e-05, "loss": 1.4067, "step": 3399 }, { "epoch": 0.56, "learning_rate": 2.1637647831800262e-05, "loss": 0.8541, "step": 3400 }, { "epoch": 0.56, "learning_rate": 2.163518396846255e-05, "loss": 0.4687, "step": 3401 }, { "epoch": 0.56, "learning_rate": 2.1632720105124837e-05, "loss": 0.7707, "step": 3402 }, { "epoch": 0.56, "learning_rate": 2.163025624178712e-05, "loss": 1.3011, "step": 3403 }, { "epoch": 0.56, "learning_rate": 2.162779237844941e-05, "loss": 0.6094, "step": 3404 }, { "epoch": 0.56, "learning_rate": 2.1625328515111694e-05, "loss": 0.8431, "step": 3405 }, { "epoch": 0.56, "learning_rate": 2.1622864651773985e-05, "loss": 1.0119, "step": 3406 }, { "epoch": 0.56, "learning_rate": 2.162040078843627e-05, "loss": 0.8705, "step": 3407 }, { "epoch": 0.56, "learning_rate": 2.1617936925098557e-05, "loss": 0.4861, "step": 3408 }, { "epoch": 0.56, "learning_rate": 2.161547306176084e-05, "loss": 0.4865, "step": 3409 }, { "epoch": 0.56, "learning_rate": 2.161300919842313e-05, "loss": 0.4405, "step": 3410 }, { "epoch": 0.56, "learning_rate": 2.1610545335085413e-05, "loss": 0.9521, "step": 3411 }, { "epoch": 0.56, "learning_rate": 2.16080814717477e-05, "loss": 0.9086, "step": 3412 }, { "epoch": 0.56, "learning_rate": 2.1605617608409985e-05, "loss": 1.3702, "step": 3413 }, { "epoch": 0.56, "learning_rate": 2.1603153745072273e-05, "loss": 0.997, "step": 3414 }, { "epoch": 0.56, "learning_rate": 2.160068988173456e-05, "loss": 1.2511, "step": 3415 }, { "epoch": 0.56, "learning_rate": 2.1598226018396848e-05, "loss": 1.2065, "step": 3416 }, { "epoch": 0.56, "learning_rate": 2.1595762155059136e-05, "loss": 0.6513, "step": 3417 }, { "epoch": 0.56, "learning_rate": 2.159329829172142e-05, "loss": 0.92, "step": 3418 }, { "epoch": 0.56, "learning_rate": 2.1590834428383708e-05, "loss": 1.0089, "step": 3419 }, { "epoch": 0.56, "learning_rate": 2.1588370565045992e-05, "loss": 1.4099, "step": 3420 }, { "epoch": 0.56, "learning_rate": 2.158590670170828e-05, "loss": 0.7948, "step": 3421 }, { "epoch": 0.56, "learning_rate": 2.1583442838370564e-05, "loss": 0.4066, "step": 3422 }, { "epoch": 0.56, "learning_rate": 2.158097897503285e-05, "loss": 0.8813, "step": 3423 }, { "epoch": 0.56, "learning_rate": 2.1578515111695136e-05, "loss": 0.5597, "step": 3424 }, { "epoch": 0.56, "learning_rate": 2.1576051248357424e-05, "loss": 0.4485, "step": 3425 }, { "epoch": 0.56, "learning_rate": 2.1573587385019715e-05, "loss": 0.5416, "step": 3426 }, { "epoch": 0.56, "learning_rate": 2.1571123521682e-05, "loss": 0.5829, "step": 3427 }, { "epoch": 0.56, "learning_rate": 2.1568659658344287e-05, "loss": 0.5861, "step": 3428 }, { "epoch": 0.56, "learning_rate": 2.156619579500657e-05, "loss": 0.8704, "step": 3429 }, { "epoch": 0.56, "learning_rate": 2.156373193166886e-05, "loss": 0.9129, "step": 3430 }, { "epoch": 0.56, "learning_rate": 2.1561268068331143e-05, "loss": 0.7923, "step": 3431 }, { "epoch": 0.56, "learning_rate": 2.155880420499343e-05, "loss": 1.126, "step": 3432 }, { "epoch": 0.56, "learning_rate": 2.1556340341655715e-05, "loss": 1.0198, "step": 3433 }, { "epoch": 0.56, "learning_rate": 2.1553876478318002e-05, "loss": 0.9223, "step": 3434 }, { "epoch": 0.56, "learning_rate": 2.1551412614980287e-05, "loss": 0.652, "step": 3435 }, { "epoch": 0.56, "learning_rate": 2.1548948751642578e-05, "loss": 1.2135, "step": 3436 }, { "epoch": 0.56, "learning_rate": 2.1546484888304862e-05, "loss": 0.8019, "step": 3437 }, { "epoch": 0.56, "learning_rate": 2.154402102496715e-05, "loss": 0.8439, "step": 3438 }, { "epoch": 0.56, "learning_rate": 2.1541557161629437e-05, "loss": 1.2803, "step": 3439 }, { "epoch": 0.57, "learning_rate": 2.1539093298291722e-05, "loss": 0.571, "step": 3440 }, { "epoch": 0.57, "learning_rate": 2.153662943495401e-05, "loss": 0.9054, "step": 3441 }, { "epoch": 0.57, "learning_rate": 2.1534165571616294e-05, "loss": 0.4754, "step": 3442 }, { "epoch": 0.57, "learning_rate": 2.153170170827858e-05, "loss": 0.5624, "step": 3443 }, { "epoch": 0.57, "learning_rate": 2.1529237844940866e-05, "loss": 0.809, "step": 3444 }, { "epoch": 0.57, "learning_rate": 2.1526773981603153e-05, "loss": 0.8872, "step": 3445 }, { "epoch": 0.57, "learning_rate": 2.152431011826544e-05, "loss": 0.6664, "step": 3446 }, { "epoch": 0.57, "learning_rate": 2.152184625492773e-05, "loss": 0.6634, "step": 3447 }, { "epoch": 0.57, "learning_rate": 2.1519382391590013e-05, "loss": 0.463, "step": 3448 }, { "epoch": 0.57, "learning_rate": 2.15169185282523e-05, "loss": 1.0725, "step": 3449 }, { "epoch": 0.57, "learning_rate": 2.151445466491459e-05, "loss": 1.1016, "step": 3450 }, { "epoch": 0.57, "learning_rate": 2.1511990801576873e-05, "loss": 0.5879, "step": 3451 }, { "epoch": 0.57, "learning_rate": 2.150952693823916e-05, "loss": 1.4495, "step": 3452 }, { "epoch": 0.57, "learning_rate": 2.1507063074901445e-05, "loss": 1.1257, "step": 3453 }, { "epoch": 0.57, "learning_rate": 2.1504599211563732e-05, "loss": 0.9449, "step": 3454 }, { "epoch": 0.57, "learning_rate": 2.1502135348226017e-05, "loss": 1.1832, "step": 3455 }, { "epoch": 0.57, "learning_rate": 2.1499671484888308e-05, "loss": 1.0839, "step": 3456 }, { "epoch": 0.57, "learning_rate": 2.1497207621550592e-05, "loss": 1.0689, "step": 3457 }, { "epoch": 0.57, "learning_rate": 2.149474375821288e-05, "loss": 0.9591, "step": 3458 }, { "epoch": 0.57, "learning_rate": 2.1492279894875164e-05, "loss": 0.9045, "step": 3459 }, { "epoch": 0.57, "learning_rate": 2.148981603153745e-05, "loss": 0.7524, "step": 3460 }, { "epoch": 0.57, "learning_rate": 2.1487352168199736e-05, "loss": 1.1972, "step": 3461 }, { "epoch": 0.57, "learning_rate": 2.1484888304862024e-05, "loss": 0.8423, "step": 3462 }, { "epoch": 0.57, "learning_rate": 2.148242444152431e-05, "loss": 0.7761, "step": 3463 }, { "epoch": 0.57, "learning_rate": 2.1479960578186596e-05, "loss": 1.0948, "step": 3464 }, { "epoch": 0.57, "learning_rate": 2.1477496714848883e-05, "loss": 0.8349, "step": 3465 }, { "epoch": 0.57, "learning_rate": 2.147503285151117e-05, "loss": 0.7785, "step": 3466 }, { "epoch": 0.57, "learning_rate": 2.147256898817346e-05, "loss": 0.6136, "step": 3467 }, { "epoch": 0.57, "learning_rate": 2.1470105124835743e-05, "loss": 0.6644, "step": 3468 }, { "epoch": 0.57, "learning_rate": 2.146764126149803e-05, "loss": 0.5879, "step": 3469 }, { "epoch": 0.57, "learning_rate": 2.1465177398160315e-05, "loss": 0.9646, "step": 3470 }, { "epoch": 0.57, "learning_rate": 2.1462713534822603e-05, "loss": 0.711, "step": 3471 }, { "epoch": 0.57, "learning_rate": 2.1460249671484887e-05, "loss": 0.5537, "step": 3472 }, { "epoch": 0.57, "learning_rate": 2.1457785808147174e-05, "loss": 0.6834, "step": 3473 }, { "epoch": 0.57, "learning_rate": 2.1455321944809462e-05, "loss": 0.5413, "step": 3474 }, { "epoch": 0.57, "learning_rate": 2.1452858081471746e-05, "loss": 0.8326, "step": 3475 }, { "epoch": 0.57, "learning_rate": 2.1450394218134038e-05, "loss": 1.0619, "step": 3476 }, { "epoch": 0.57, "learning_rate": 2.1447930354796322e-05, "loss": 0.6525, "step": 3477 }, { "epoch": 0.57, "learning_rate": 2.144546649145861e-05, "loss": 0.6448, "step": 3478 }, { "epoch": 0.57, "learning_rate": 2.1443002628120894e-05, "loss": 0.881, "step": 3479 }, { "epoch": 0.57, "learning_rate": 2.144053876478318e-05, "loss": 1.1417, "step": 3480 }, { "epoch": 0.57, "learning_rate": 2.1438074901445466e-05, "loss": 1.0085, "step": 3481 }, { "epoch": 0.57, "learning_rate": 2.1435611038107753e-05, "loss": 0.3233, "step": 3482 }, { "epoch": 0.57, "learning_rate": 2.1433147174770038e-05, "loss": 1.335, "step": 3483 }, { "epoch": 0.57, "learning_rate": 2.1430683311432325e-05, "loss": 0.8852, "step": 3484 }, { "epoch": 0.57, "learning_rate": 2.1428219448094613e-05, "loss": 1.7863, "step": 3485 }, { "epoch": 0.57, "learning_rate": 2.14257555847569e-05, "loss": 0.5146, "step": 3486 }, { "epoch": 0.57, "learning_rate": 2.142329172141919e-05, "loss": 1.9786, "step": 3487 }, { "epoch": 0.57, "learning_rate": 2.1420827858081473e-05, "loss": 0.6225, "step": 3488 }, { "epoch": 0.57, "learning_rate": 2.141836399474376e-05, "loss": 0.6189, "step": 3489 }, { "epoch": 0.57, "learning_rate": 2.1415900131406045e-05, "loss": 0.6744, "step": 3490 }, { "epoch": 0.57, "learning_rate": 2.1413436268068332e-05, "loss": 0.7325, "step": 3491 }, { "epoch": 0.57, "learning_rate": 2.1410972404730617e-05, "loss": 0.8359, "step": 3492 }, { "epoch": 0.57, "learning_rate": 2.1408508541392904e-05, "loss": 1.5606, "step": 3493 }, { "epoch": 0.57, "learning_rate": 2.140604467805519e-05, "loss": 0.8109, "step": 3494 }, { "epoch": 0.57, "learning_rate": 2.1403580814717476e-05, "loss": 0.7028, "step": 3495 }, { "epoch": 0.57, "learning_rate": 2.1401116951379764e-05, "loss": 0.6775, "step": 3496 }, { "epoch": 0.57, "learning_rate": 2.139865308804205e-05, "loss": 1.3382, "step": 3497 }, { "epoch": 0.57, "learning_rate": 2.139618922470434e-05, "loss": 1.0315, "step": 3498 }, { "epoch": 0.57, "learning_rate": 2.1393725361366624e-05, "loss": 0.9823, "step": 3499 }, { "epoch": 0.57, "learning_rate": 2.139126149802891e-05, "loss": 0.8447, "step": 3500 }, { "epoch": 0.57, "eval_exact_match": 84.46546830652791, "eval_f1": 91.34353325761974, "step": 3500 }, { "epoch": 0.58, "learning_rate": 2.1388797634691196e-05, "loss": 1.0116, "step": 3501 }, { "epoch": 0.58, "learning_rate": 2.1386333771353483e-05, "loss": 0.8117, "step": 3502 }, { "epoch": 0.58, "learning_rate": 2.1383869908015768e-05, "loss": 0.8419, "step": 3503 }, { "epoch": 0.58, "learning_rate": 2.1381406044678055e-05, "loss": 1.0385, "step": 3504 }, { "epoch": 0.58, "learning_rate": 2.137894218134034e-05, "loss": 0.4623, "step": 3505 }, { "epoch": 0.58, "learning_rate": 2.137647831800263e-05, "loss": 1.5448, "step": 3506 }, { "epoch": 0.58, "learning_rate": 2.1374014454664915e-05, "loss": 0.6973, "step": 3507 }, { "epoch": 0.58, "learning_rate": 2.1371550591327203e-05, "loss": 0.5986, "step": 3508 }, { "epoch": 0.58, "learning_rate": 2.136908672798949e-05, "loss": 0.5087, "step": 3509 }, { "epoch": 0.58, "learning_rate": 2.1366622864651775e-05, "loss": 0.845, "step": 3510 }, { "epoch": 0.58, "learning_rate": 2.1364159001314062e-05, "loss": 1.0736, "step": 3511 }, { "epoch": 0.58, "learning_rate": 2.1361695137976347e-05, "loss": 0.8476, "step": 3512 }, { "epoch": 0.58, "learning_rate": 2.1359231274638634e-05, "loss": 0.7118, "step": 3513 }, { "epoch": 0.58, "learning_rate": 2.135676741130092e-05, "loss": 1.1361, "step": 3514 }, { "epoch": 0.58, "learning_rate": 2.1354303547963206e-05, "loss": 0.7544, "step": 3515 }, { "epoch": 0.58, "learning_rate": 2.1351839684625494e-05, "loss": 1.2418, "step": 3516 }, { "epoch": 0.58, "learning_rate": 2.134937582128778e-05, "loss": 0.6639, "step": 3517 }, { "epoch": 0.58, "learning_rate": 2.1346911957950066e-05, "loss": 0.8329, "step": 3518 }, { "epoch": 0.58, "learning_rate": 2.1344448094612353e-05, "loss": 1.3901, "step": 3519 }, { "epoch": 0.58, "learning_rate": 2.1341984231274638e-05, "loss": 0.8524, "step": 3520 }, { "epoch": 0.58, "learning_rate": 2.1339520367936925e-05, "loss": 0.9976, "step": 3521 }, { "epoch": 0.58, "learning_rate": 2.1337056504599213e-05, "loss": 1.322, "step": 3522 }, { "epoch": 0.58, "learning_rate": 2.1334592641261497e-05, "loss": 1.1489, "step": 3523 }, { "epoch": 0.58, "learning_rate": 2.1332128777923785e-05, "loss": 1.0747, "step": 3524 }, { "epoch": 0.58, "learning_rate": 2.132966491458607e-05, "loss": 0.879, "step": 3525 }, { "epoch": 0.58, "learning_rate": 2.132720105124836e-05, "loss": 1.1082, "step": 3526 }, { "epoch": 0.58, "learning_rate": 2.1324737187910645e-05, "loss": 0.7731, "step": 3527 }, { "epoch": 0.58, "learning_rate": 2.1322273324572932e-05, "loss": 0.5736, "step": 3528 }, { "epoch": 0.58, "learning_rate": 2.1319809461235217e-05, "loss": 1.0707, "step": 3529 }, { "epoch": 0.58, "learning_rate": 2.1317345597897504e-05, "loss": 0.5427, "step": 3530 }, { "epoch": 0.58, "learning_rate": 2.131488173455979e-05, "loss": 0.5014, "step": 3531 }, { "epoch": 0.58, "learning_rate": 2.1312417871222076e-05, "loss": 0.7678, "step": 3532 }, { "epoch": 0.58, "learning_rate": 2.1309954007884364e-05, "loss": 0.9332, "step": 3533 }, { "epoch": 0.58, "learning_rate": 2.130749014454665e-05, "loss": 0.7133, "step": 3534 }, { "epoch": 0.58, "learning_rate": 2.1305026281208936e-05, "loss": 1.1709, "step": 3535 }, { "epoch": 0.58, "learning_rate": 2.1302562417871224e-05, "loss": 0.7224, "step": 3536 }, { "epoch": 0.58, "learning_rate": 2.130009855453351e-05, "loss": 1.3067, "step": 3537 }, { "epoch": 0.58, "learning_rate": 2.1297634691195796e-05, "loss": 1.0902, "step": 3538 }, { "epoch": 0.58, "learning_rate": 2.1295170827858083e-05, "loss": 0.773, "step": 3539 }, { "epoch": 0.58, "learning_rate": 2.1292706964520368e-05, "loss": 1.3377, "step": 3540 }, { "epoch": 0.58, "learning_rate": 2.1290243101182655e-05, "loss": 1.8955, "step": 3541 }, { "epoch": 0.58, "learning_rate": 2.128777923784494e-05, "loss": 0.8492, "step": 3542 }, { "epoch": 0.58, "learning_rate": 2.1285315374507227e-05, "loss": 1.378, "step": 3543 }, { "epoch": 0.58, "learning_rate": 2.128285151116951e-05, "loss": 0.9008, "step": 3544 }, { "epoch": 0.58, "learning_rate": 2.12803876478318e-05, "loss": 0.6363, "step": 3545 }, { "epoch": 0.58, "learning_rate": 2.127792378449409e-05, "loss": 0.563, "step": 3546 }, { "epoch": 0.58, "learning_rate": 2.1275459921156375e-05, "loss": 1.0023, "step": 3547 }, { "epoch": 0.58, "learning_rate": 2.1272996057818662e-05, "loss": 1.0929, "step": 3548 }, { "epoch": 0.58, "learning_rate": 2.1270532194480947e-05, "loss": 0.9966, "step": 3549 }, { "epoch": 0.58, "learning_rate": 2.1268068331143234e-05, "loss": 1.1679, "step": 3550 }, { "epoch": 0.58, "learning_rate": 2.126560446780552e-05, "loss": 0.8036, "step": 3551 }, { "epoch": 0.58, "learning_rate": 2.1263140604467806e-05, "loss": 1.4294, "step": 3552 }, { "epoch": 0.58, "learning_rate": 2.126067674113009e-05, "loss": 0.9264, "step": 3553 }, { "epoch": 0.58, "learning_rate": 2.1258212877792378e-05, "loss": 0.7437, "step": 3554 }, { "epoch": 0.58, "learning_rate": 2.1255749014454662e-05, "loss": 0.7284, "step": 3555 }, { "epoch": 0.58, "learning_rate": 2.1253285151116954e-05, "loss": 0.7617, "step": 3556 }, { "epoch": 0.58, "learning_rate": 2.125082128777924e-05, "loss": 0.6167, "step": 3557 }, { "epoch": 0.58, "learning_rate": 2.1248357424441526e-05, "loss": 0.4796, "step": 3558 }, { "epoch": 0.58, "learning_rate": 2.1245893561103813e-05, "loss": 0.9673, "step": 3559 }, { "epoch": 0.58, "learning_rate": 2.1243429697766097e-05, "loss": 0.964, "step": 3560 }, { "epoch": 0.58, "learning_rate": 2.1240965834428385e-05, "loss": 0.8837, "step": 3561 }, { "epoch": 0.59, "learning_rate": 2.123850197109067e-05, "loss": 0.532, "step": 3562 }, { "epoch": 0.59, "learning_rate": 2.1236038107752957e-05, "loss": 1.0738, "step": 3563 }, { "epoch": 0.59, "learning_rate": 2.123357424441524e-05, "loss": 1.5559, "step": 3564 }, { "epoch": 0.59, "learning_rate": 2.123111038107753e-05, "loss": 0.3588, "step": 3565 }, { "epoch": 0.59, "learning_rate": 2.1228646517739817e-05, "loss": 1.4428, "step": 3566 }, { "epoch": 0.59, "learning_rate": 2.1226182654402104e-05, "loss": 0.6669, "step": 3567 }, { "epoch": 0.59, "learning_rate": 2.122371879106439e-05, "loss": 0.9499, "step": 3568 }, { "epoch": 0.59, "learning_rate": 2.1221254927726676e-05, "loss": 1.2648, "step": 3569 }, { "epoch": 0.59, "learning_rate": 2.1218791064388964e-05, "loss": 0.964, "step": 3570 }, { "epoch": 0.59, "learning_rate": 2.121632720105125e-05, "loss": 0.7821, "step": 3571 }, { "epoch": 0.59, "learning_rate": 2.1213863337713536e-05, "loss": 0.5454, "step": 3572 }, { "epoch": 0.59, "learning_rate": 2.121139947437582e-05, "loss": 0.7769, "step": 3573 }, { "epoch": 0.59, "learning_rate": 2.1208935611038108e-05, "loss": 0.3933, "step": 3574 }, { "epoch": 0.59, "learning_rate": 2.1206471747700392e-05, "loss": 0.8148, "step": 3575 }, { "epoch": 0.59, "learning_rate": 2.1204007884362683e-05, "loss": 0.9712, "step": 3576 }, { "epoch": 0.59, "learning_rate": 2.1201544021024968e-05, "loss": 0.7983, "step": 3577 }, { "epoch": 0.59, "learning_rate": 2.1199080157687255e-05, "loss": 0.7842, "step": 3578 }, { "epoch": 0.59, "learning_rate": 2.119661629434954e-05, "loss": 1.283, "step": 3579 }, { "epoch": 0.59, "learning_rate": 2.1194152431011827e-05, "loss": 0.8997, "step": 3580 }, { "epoch": 0.59, "learning_rate": 2.1191688567674115e-05, "loss": 0.7963, "step": 3581 }, { "epoch": 0.59, "learning_rate": 2.11892247043364e-05, "loss": 0.8895, "step": 3582 }, { "epoch": 0.59, "learning_rate": 2.1186760840998687e-05, "loss": 0.9481, "step": 3583 }, { "epoch": 0.59, "learning_rate": 2.118429697766097e-05, "loss": 0.4535, "step": 3584 }, { "epoch": 0.59, "learning_rate": 2.118183311432326e-05, "loss": 0.3984, "step": 3585 }, { "epoch": 0.59, "learning_rate": 2.1179369250985547e-05, "loss": 1.3005, "step": 3586 }, { "epoch": 0.59, "learning_rate": 2.1176905387647834e-05, "loss": 2.1041, "step": 3587 }, { "epoch": 0.59, "learning_rate": 2.117444152431012e-05, "loss": 0.9184, "step": 3588 }, { "epoch": 0.59, "learning_rate": 2.1171977660972406e-05, "loss": 0.7194, "step": 3589 }, { "epoch": 0.59, "learning_rate": 2.116951379763469e-05, "loss": 0.8217, "step": 3590 }, { "epoch": 0.59, "learning_rate": 2.1167049934296978e-05, "loss": 1.2554, "step": 3591 }, { "epoch": 0.59, "learning_rate": 2.1164586070959263e-05, "loss": 1.2926, "step": 3592 }, { "epoch": 0.59, "learning_rate": 2.116212220762155e-05, "loss": 0.9258, "step": 3593 }, { "epoch": 0.59, "learning_rate": 2.1159658344283838e-05, "loss": 0.8226, "step": 3594 }, { "epoch": 0.59, "learning_rate": 2.1157194480946122e-05, "loss": 0.6554, "step": 3595 }, { "epoch": 0.59, "learning_rate": 2.1154730617608413e-05, "loss": 0.8984, "step": 3596 }, { "epoch": 0.59, "learning_rate": 2.1152266754270698e-05, "loss": 0.8196, "step": 3597 }, { "epoch": 0.59, "learning_rate": 2.1149802890932985e-05, "loss": 0.8958, "step": 3598 }, { "epoch": 0.59, "learning_rate": 2.114733902759527e-05, "loss": 0.7995, "step": 3599 }, { "epoch": 0.59, "learning_rate": 2.1144875164257557e-05, "loss": 0.7299, "step": 3600 }, { "epoch": 0.59, "learning_rate": 2.114241130091984e-05, "loss": 1.0684, "step": 3601 }, { "epoch": 0.59, "learning_rate": 2.113994743758213e-05, "loss": 0.6388, "step": 3602 }, { "epoch": 0.59, "learning_rate": 2.1137483574244413e-05, "loss": 0.8665, "step": 3603 }, { "epoch": 0.59, "learning_rate": 2.11350197109067e-05, "loss": 0.818, "step": 3604 }, { "epoch": 0.59, "learning_rate": 2.113255584756899e-05, "loss": 0.8815, "step": 3605 }, { "epoch": 0.59, "learning_rate": 2.1130091984231276e-05, "loss": 1.2048, "step": 3606 }, { "epoch": 0.59, "learning_rate": 2.1127628120893564e-05, "loss": 0.5152, "step": 3607 }, { "epoch": 0.59, "learning_rate": 2.112516425755585e-05, "loss": 0.7944, "step": 3608 }, { "epoch": 0.59, "learning_rate": 2.1122700394218136e-05, "loss": 0.844, "step": 3609 }, { "epoch": 0.59, "learning_rate": 2.112023653088042e-05, "loss": 1.079, "step": 3610 }, { "epoch": 0.59, "learning_rate": 2.1117772667542708e-05, "loss": 0.6283, "step": 3611 }, { "epoch": 0.59, "learning_rate": 2.1115308804204992e-05, "loss": 0.6652, "step": 3612 }, { "epoch": 0.59, "learning_rate": 2.111284494086728e-05, "loss": 0.9335, "step": 3613 }, { "epoch": 0.59, "learning_rate": 2.1110381077529564e-05, "loss": 0.4678, "step": 3614 }, { "epoch": 0.59, "learning_rate": 2.1107917214191852e-05, "loss": 0.4915, "step": 3615 }, { "epoch": 0.59, "learning_rate": 2.110545335085414e-05, "loss": 0.7267, "step": 3616 }, { "epoch": 0.59, "learning_rate": 2.1102989487516427e-05, "loss": 0.8006, "step": 3617 }, { "epoch": 0.59, "learning_rate": 2.1100525624178715e-05, "loss": 0.4614, "step": 3618 }, { "epoch": 0.59, "learning_rate": 2.1098061760841e-05, "loss": 0.6636, "step": 3619 }, { "epoch": 0.59, "learning_rate": 2.1095597897503287e-05, "loss": 0.7664, "step": 3620 }, { "epoch": 0.59, "learning_rate": 2.109313403416557e-05, "loss": 0.9704, "step": 3621 }, { "epoch": 0.59, "learning_rate": 2.109067017082786e-05, "loss": 0.7413, "step": 3622 }, { "epoch": 0.6, "learning_rate": 2.1088206307490143e-05, "loss": 0.5888, "step": 3623 }, { "epoch": 0.6, "learning_rate": 2.108574244415243e-05, "loss": 0.8782, "step": 3624 }, { "epoch": 0.6, "learning_rate": 2.1083278580814715e-05, "loss": 0.7551, "step": 3625 }, { "epoch": 0.6, "learning_rate": 2.1080814717477006e-05, "loss": 0.6539, "step": 3626 }, { "epoch": 0.6, "learning_rate": 2.107835085413929e-05, "loss": 0.4923, "step": 3627 }, { "epoch": 0.6, "learning_rate": 2.107588699080158e-05, "loss": 1.1068, "step": 3628 }, { "epoch": 0.6, "learning_rate": 2.1073423127463866e-05, "loss": 0.676, "step": 3629 }, { "epoch": 0.6, "learning_rate": 2.107095926412615e-05, "loss": 0.8474, "step": 3630 }, { "epoch": 0.6, "learning_rate": 2.1068495400788438e-05, "loss": 1.463, "step": 3631 }, { "epoch": 0.6, "learning_rate": 2.1066031537450722e-05, "loss": 1.0982, "step": 3632 }, { "epoch": 0.6, "learning_rate": 2.106356767411301e-05, "loss": 0.983, "step": 3633 }, { "epoch": 0.6, "learning_rate": 2.1061103810775294e-05, "loss": 0.8708, "step": 3634 }, { "epoch": 0.6, "learning_rate": 2.1058639947437582e-05, "loss": 0.6521, "step": 3635 }, { "epoch": 0.6, "learning_rate": 2.105617608409987e-05, "loss": 1.5233, "step": 3636 }, { "epoch": 0.6, "learning_rate": 2.1053712220762157e-05, "loss": 0.4972, "step": 3637 }, { "epoch": 0.6, "learning_rate": 2.105124835742444e-05, "loss": 0.5686, "step": 3638 }, { "epoch": 0.6, "learning_rate": 2.104878449408673e-05, "loss": 0.8469, "step": 3639 }, { "epoch": 0.6, "learning_rate": 2.1046320630749017e-05, "loss": 1.0908, "step": 3640 }, { "epoch": 0.6, "learning_rate": 2.10438567674113e-05, "loss": 1.343, "step": 3641 }, { "epoch": 0.6, "learning_rate": 2.104139290407359e-05, "loss": 1.2805, "step": 3642 }, { "epoch": 0.6, "learning_rate": 2.1038929040735873e-05, "loss": 1.0989, "step": 3643 }, { "epoch": 0.6, "learning_rate": 2.103646517739816e-05, "loss": 1.0015, "step": 3644 }, { "epoch": 0.6, "learning_rate": 2.1034001314060445e-05, "loss": 1.2029, "step": 3645 }, { "epoch": 0.6, "learning_rate": 2.1031537450722736e-05, "loss": 0.9917, "step": 3646 }, { "epoch": 0.6, "learning_rate": 2.102907358738502e-05, "loss": 1.0395, "step": 3647 }, { "epoch": 0.6, "learning_rate": 2.1026609724047308e-05, "loss": 0.8744, "step": 3648 }, { "epoch": 0.6, "learning_rate": 2.1024145860709592e-05, "loss": 0.2675, "step": 3649 }, { "epoch": 0.6, "learning_rate": 2.102168199737188e-05, "loss": 0.7858, "step": 3650 }, { "epoch": 0.6, "learning_rate": 2.1019218134034164e-05, "loss": 0.8172, "step": 3651 }, { "epoch": 0.6, "learning_rate": 2.1016754270696452e-05, "loss": 0.5709, "step": 3652 }, { "epoch": 0.6, "learning_rate": 2.101429040735874e-05, "loss": 0.7559, "step": 3653 }, { "epoch": 0.6, "learning_rate": 2.1011826544021024e-05, "loss": 0.605, "step": 3654 }, { "epoch": 0.6, "learning_rate": 2.1009362680683312e-05, "loss": 1.058, "step": 3655 }, { "epoch": 0.6, "learning_rate": 2.10068988173456e-05, "loss": 1.0721, "step": 3656 }, { "epoch": 0.6, "learning_rate": 2.1004434954007887e-05, "loss": 1.0556, "step": 3657 }, { "epoch": 0.6, "learning_rate": 2.100197109067017e-05, "loss": 1.0085, "step": 3658 }, { "epoch": 0.6, "learning_rate": 2.099950722733246e-05, "loss": 1.0488, "step": 3659 }, { "epoch": 0.6, "learning_rate": 2.0997043363994743e-05, "loss": 0.492, "step": 3660 }, { "epoch": 0.6, "learning_rate": 2.099457950065703e-05, "loss": 1.3174, "step": 3661 }, { "epoch": 0.6, "learning_rate": 2.0992115637319315e-05, "loss": 0.7818, "step": 3662 }, { "epoch": 0.6, "learning_rate": 2.0989651773981603e-05, "loss": 0.8453, "step": 3663 }, { "epoch": 0.6, "learning_rate": 2.098718791064389e-05, "loss": 0.5826, "step": 3664 }, { "epoch": 0.6, "learning_rate": 2.0984724047306175e-05, "loss": 1.0376, "step": 3665 }, { "epoch": 0.6, "learning_rate": 2.0982260183968466e-05, "loss": 0.8823, "step": 3666 }, { "epoch": 0.6, "learning_rate": 2.097979632063075e-05, "loss": 0.6533, "step": 3667 }, { "epoch": 0.6, "learning_rate": 2.0977332457293038e-05, "loss": 1.28, "step": 3668 }, { "epoch": 0.6, "learning_rate": 2.0974868593955322e-05, "loss": 0.698, "step": 3669 }, { "epoch": 0.6, "learning_rate": 2.097240473061761e-05, "loss": 1.3453, "step": 3670 }, { "epoch": 0.6, "learning_rate": 2.0969940867279894e-05, "loss": 0.4807, "step": 3671 }, { "epoch": 0.6, "learning_rate": 2.0967477003942182e-05, "loss": 1.2066, "step": 3672 }, { "epoch": 0.6, "learning_rate": 2.0965013140604466e-05, "loss": 0.5565, "step": 3673 }, { "epoch": 0.6, "learning_rate": 2.0962549277266754e-05, "loss": 0.8972, "step": 3674 }, { "epoch": 0.6, "learning_rate": 2.0960085413929038e-05, "loss": 1.6369, "step": 3675 }, { "epoch": 0.6, "learning_rate": 2.095762155059133e-05, "loss": 0.3754, "step": 3676 }, { "epoch": 0.6, "learning_rate": 2.0955157687253617e-05, "loss": 0.4608, "step": 3677 }, { "epoch": 0.6, "learning_rate": 2.09526938239159e-05, "loss": 0.8414, "step": 3678 }, { "epoch": 0.6, "learning_rate": 2.095022996057819e-05, "loss": 0.4602, "step": 3679 }, { "epoch": 0.6, "learning_rate": 2.0947766097240473e-05, "loss": 1.6359, "step": 3680 }, { "epoch": 0.6, "learning_rate": 2.094530223390276e-05, "loss": 0.5373, "step": 3681 }, { "epoch": 0.6, "learning_rate": 2.0942838370565045e-05, "loss": 0.6611, "step": 3682 }, { "epoch": 0.6, "learning_rate": 2.0940374507227333e-05, "loss": 1.2663, "step": 3683 }, { "epoch": 0.61, "learning_rate": 2.0937910643889617e-05, "loss": 0.5061, "step": 3684 }, { "epoch": 0.61, "learning_rate": 2.0935446780551905e-05, "loss": 0.6149, "step": 3685 }, { "epoch": 0.61, "learning_rate": 2.0932982917214193e-05, "loss": 0.7293, "step": 3686 }, { "epoch": 0.61, "learning_rate": 2.093051905387648e-05, "loss": 0.6348, "step": 3687 }, { "epoch": 0.61, "learning_rate": 2.0928055190538768e-05, "loss": 0.7646, "step": 3688 }, { "epoch": 0.61, "learning_rate": 2.0925591327201052e-05, "loss": 0.8318, "step": 3689 }, { "epoch": 0.61, "learning_rate": 2.092312746386334e-05, "loss": 0.8594, "step": 3690 }, { "epoch": 0.61, "learning_rate": 2.0920663600525624e-05, "loss": 1.5497, "step": 3691 }, { "epoch": 0.61, "learning_rate": 2.0918199737187912e-05, "loss": 0.7663, "step": 3692 }, { "epoch": 0.61, "learning_rate": 2.0915735873850196e-05, "loss": 0.9484, "step": 3693 }, { "epoch": 0.61, "learning_rate": 2.0913272010512484e-05, "loss": 0.642, "step": 3694 }, { "epoch": 0.61, "learning_rate": 2.0910808147174768e-05, "loss": 0.8253, "step": 3695 }, { "epoch": 0.61, "learning_rate": 2.090834428383706e-05, "loss": 1.458, "step": 3696 }, { "epoch": 0.61, "learning_rate": 2.0905880420499343e-05, "loss": 1.7049, "step": 3697 }, { "epoch": 0.61, "learning_rate": 2.090341655716163e-05, "loss": 0.7304, "step": 3698 }, { "epoch": 0.61, "learning_rate": 2.0900952693823915e-05, "loss": 0.8653, "step": 3699 }, { "epoch": 0.61, "learning_rate": 2.0898488830486203e-05, "loss": 0.9068, "step": 3700 }, { "epoch": 0.61, "learning_rate": 2.089602496714849e-05, "loss": 0.6608, "step": 3701 }, { "epoch": 0.61, "learning_rate": 2.0893561103810775e-05, "loss": 0.8666, "step": 3702 }, { "epoch": 0.61, "learning_rate": 2.0891097240473063e-05, "loss": 0.8571, "step": 3703 }, { "epoch": 0.61, "learning_rate": 2.0888633377135347e-05, "loss": 1.4959, "step": 3704 }, { "epoch": 0.61, "learning_rate": 2.0886169513797635e-05, "loss": 0.8027, "step": 3705 }, { "epoch": 0.61, "learning_rate": 2.0883705650459922e-05, "loss": 1.6374, "step": 3706 }, { "epoch": 0.61, "learning_rate": 2.088124178712221e-05, "loss": 0.8438, "step": 3707 }, { "epoch": 0.61, "learning_rate": 2.0878777923784494e-05, "loss": 0.6523, "step": 3708 }, { "epoch": 0.61, "learning_rate": 2.0876314060446782e-05, "loss": 1.5949, "step": 3709 }, { "epoch": 0.61, "learning_rate": 2.0873850197109066e-05, "loss": 0.4067, "step": 3710 }, { "epoch": 0.61, "learning_rate": 2.0871386333771354e-05, "loss": 1.2539, "step": 3711 }, { "epoch": 0.61, "learning_rate": 2.086892247043364e-05, "loss": 0.5661, "step": 3712 }, { "epoch": 0.61, "learning_rate": 2.0866458607095926e-05, "loss": 1.1061, "step": 3713 }, { "epoch": 0.61, "learning_rate": 2.0863994743758214e-05, "loss": 0.7059, "step": 3714 }, { "epoch": 0.61, "learning_rate": 2.0861530880420498e-05, "loss": 0.3871, "step": 3715 }, { "epoch": 0.61, "learning_rate": 2.085906701708279e-05, "loss": 0.9271, "step": 3716 }, { "epoch": 0.61, "learning_rate": 2.0856603153745073e-05, "loss": 1.4527, "step": 3717 }, { "epoch": 0.61, "learning_rate": 2.085413929040736e-05, "loss": 0.8451, "step": 3718 }, { "epoch": 0.61, "learning_rate": 2.0851675427069645e-05, "loss": 1.4802, "step": 3719 }, { "epoch": 0.61, "learning_rate": 2.0849211563731933e-05, "loss": 1.0398, "step": 3720 }, { "epoch": 0.61, "learning_rate": 2.0846747700394217e-05, "loss": 1.0606, "step": 3721 }, { "epoch": 0.61, "learning_rate": 2.0844283837056505e-05, "loss": 0.537, "step": 3722 }, { "epoch": 0.61, "learning_rate": 2.084181997371879e-05, "loss": 0.6591, "step": 3723 }, { "epoch": 0.61, "learning_rate": 2.0839356110381077e-05, "loss": 0.7248, "step": 3724 }, { "epoch": 0.61, "learning_rate": 2.0836892247043365e-05, "loss": 1.5661, "step": 3725 }, { "epoch": 0.61, "learning_rate": 2.0834428383705652e-05, "loss": 0.4035, "step": 3726 }, { "epoch": 0.61, "learning_rate": 2.083196452036794e-05, "loss": 1.4808, "step": 3727 }, { "epoch": 0.61, "learning_rate": 2.0829500657030224e-05, "loss": 0.6941, "step": 3728 }, { "epoch": 0.61, "learning_rate": 2.0827036793692512e-05, "loss": 1.1277, "step": 3729 }, { "epoch": 0.61, "learning_rate": 2.0824572930354796e-05, "loss": 1.2832, "step": 3730 }, { "epoch": 0.61, "learning_rate": 2.0822109067017084e-05, "loss": 1.0313, "step": 3731 }, { "epoch": 0.61, "learning_rate": 2.0819645203679368e-05, "loss": 0.7968, "step": 3732 }, { "epoch": 0.61, "learning_rate": 2.0817181340341656e-05, "loss": 1.0704, "step": 3733 }, { "epoch": 0.61, "learning_rate": 2.081471747700394e-05, "loss": 0.6281, "step": 3734 }, { "epoch": 0.61, "learning_rate": 2.0812253613666228e-05, "loss": 0.2581, "step": 3735 }, { "epoch": 0.61, "learning_rate": 2.080978975032852e-05, "loss": 1.2841, "step": 3736 }, { "epoch": 0.61, "learning_rate": 2.0807325886990803e-05, "loss": 0.4601, "step": 3737 }, { "epoch": 0.61, "learning_rate": 2.080486202365309e-05, "loss": 0.397, "step": 3738 }, { "epoch": 0.61, "learning_rate": 2.0802398160315375e-05, "loss": 1.0251, "step": 3739 }, { "epoch": 0.61, "learning_rate": 2.0799934296977663e-05, "loss": 0.9239, "step": 3740 }, { "epoch": 0.61, "learning_rate": 2.0797470433639947e-05, "loss": 1.1293, "step": 3741 }, { "epoch": 0.61, "learning_rate": 2.0795006570302235e-05, "loss": 0.3879, "step": 3742 }, { "epoch": 0.61, "learning_rate": 2.079254270696452e-05, "loss": 0.9091, "step": 3743 }, { "epoch": 0.61, "learning_rate": 2.0790078843626807e-05, "loss": 0.6149, "step": 3744 }, { "epoch": 0.62, "learning_rate": 2.078761498028909e-05, "loss": 0.5302, "step": 3745 }, { "epoch": 0.62, "learning_rate": 2.0785151116951382e-05, "loss": 1.0211, "step": 3746 }, { "epoch": 0.62, "learning_rate": 2.0782687253613666e-05, "loss": 0.5381, "step": 3747 }, { "epoch": 0.62, "learning_rate": 2.0780223390275954e-05, "loss": 0.3315, "step": 3748 }, { "epoch": 0.62, "learning_rate": 2.0777759526938242e-05, "loss": 0.5536, "step": 3749 }, { "epoch": 0.62, "learning_rate": 2.0775295663600526e-05, "loss": 1.9505, "step": 3750 }, { "epoch": 0.62, "learning_rate": 2.0772831800262814e-05, "loss": 0.6669, "step": 3751 }, { "epoch": 0.62, "learning_rate": 2.0770367936925098e-05, "loss": 0.9974, "step": 3752 }, { "epoch": 0.62, "learning_rate": 2.0767904073587386e-05, "loss": 0.8429, "step": 3753 }, { "epoch": 0.62, "learning_rate": 2.076544021024967e-05, "loss": 0.4794, "step": 3754 }, { "epoch": 0.62, "learning_rate": 2.0762976346911958e-05, "loss": 0.5266, "step": 3755 }, { "epoch": 0.62, "learning_rate": 2.0760512483574245e-05, "loss": 0.97, "step": 3756 }, { "epoch": 0.62, "learning_rate": 2.0758048620236533e-05, "loss": 0.6807, "step": 3757 }, { "epoch": 0.62, "learning_rate": 2.0755584756898817e-05, "loss": 1.1023, "step": 3758 }, { "epoch": 0.62, "learning_rate": 2.0753120893561105e-05, "loss": 0.9152, "step": 3759 }, { "epoch": 0.62, "learning_rate": 2.0750657030223393e-05, "loss": 1.1347, "step": 3760 }, { "epoch": 0.62, "learning_rate": 2.0748193166885677e-05, "loss": 0.2972, "step": 3761 }, { "epoch": 0.62, "learning_rate": 2.0745729303547965e-05, "loss": 0.5687, "step": 3762 }, { "epoch": 0.62, "learning_rate": 2.074326544021025e-05, "loss": 1.0662, "step": 3763 }, { "epoch": 0.62, "learning_rate": 2.0740801576872537e-05, "loss": 0.5407, "step": 3764 }, { "epoch": 0.62, "learning_rate": 2.073833771353482e-05, "loss": 0.5727, "step": 3765 }, { "epoch": 0.62, "learning_rate": 2.0735873850197112e-05, "loss": 0.6632, "step": 3766 }, { "epoch": 0.62, "learning_rate": 2.0733409986859396e-05, "loss": 0.6133, "step": 3767 }, { "epoch": 0.62, "learning_rate": 2.0730946123521684e-05, "loss": 0.433, "step": 3768 }, { "epoch": 0.62, "learning_rate": 2.0728482260183968e-05, "loss": 0.289, "step": 3769 }, { "epoch": 0.62, "learning_rate": 2.0726018396846256e-05, "loss": 0.8646, "step": 3770 }, { "epoch": 0.62, "learning_rate": 2.0723554533508544e-05, "loss": 0.9723, "step": 3771 }, { "epoch": 0.62, "learning_rate": 2.0721090670170828e-05, "loss": 0.6623, "step": 3772 }, { "epoch": 0.62, "learning_rate": 2.0718626806833116e-05, "loss": 0.8415, "step": 3773 }, { "epoch": 0.62, "learning_rate": 2.07161629434954e-05, "loss": 0.7191, "step": 3774 }, { "epoch": 0.62, "learning_rate": 2.0713699080157688e-05, "loss": 1.1377, "step": 3775 }, { "epoch": 0.62, "learning_rate": 2.0711235216819975e-05, "loss": 0.7057, "step": 3776 }, { "epoch": 0.62, "learning_rate": 2.0708771353482263e-05, "loss": 0.9492, "step": 3777 }, { "epoch": 0.62, "learning_rate": 2.0706307490144547e-05, "loss": 1.8556, "step": 3778 }, { "epoch": 0.62, "learning_rate": 2.0703843626806835e-05, "loss": 0.6828, "step": 3779 }, { "epoch": 0.62, "learning_rate": 2.070137976346912e-05, "loss": 1.4163, "step": 3780 }, { "epoch": 0.62, "learning_rate": 2.0698915900131407e-05, "loss": 0.8419, "step": 3781 }, { "epoch": 0.62, "learning_rate": 2.069645203679369e-05, "loss": 0.5405, "step": 3782 }, { "epoch": 0.62, "learning_rate": 2.069398817345598e-05, "loss": 0.6063, "step": 3783 }, { "epoch": 0.62, "learning_rate": 2.0691524310118266e-05, "loss": 1.0481, "step": 3784 }, { "epoch": 0.62, "learning_rate": 2.068906044678055e-05, "loss": 0.8865, "step": 3785 }, { "epoch": 0.62, "learning_rate": 2.0686596583442842e-05, "loss": 0.6361, "step": 3786 }, { "epoch": 0.62, "learning_rate": 2.0684132720105126e-05, "loss": 0.9491, "step": 3787 }, { "epoch": 0.62, "learning_rate": 2.0681668856767414e-05, "loss": 0.8505, "step": 3788 }, { "epoch": 0.62, "learning_rate": 2.0679204993429698e-05, "loss": 0.7949, "step": 3789 }, { "epoch": 0.62, "learning_rate": 2.0676741130091986e-05, "loss": 0.7365, "step": 3790 }, { "epoch": 0.62, "learning_rate": 2.067427726675427e-05, "loss": 1.3666, "step": 3791 }, { "epoch": 0.62, "learning_rate": 2.0671813403416558e-05, "loss": 0.5384, "step": 3792 }, { "epoch": 0.62, "learning_rate": 2.0669349540078842e-05, "loss": 0.7562, "step": 3793 }, { "epoch": 0.62, "learning_rate": 2.066688567674113e-05, "loss": 0.5937, "step": 3794 }, { "epoch": 0.62, "learning_rate": 2.0664421813403417e-05, "loss": 0.7081, "step": 3795 }, { "epoch": 0.62, "learning_rate": 2.0661957950065705e-05, "loss": 1.2543, "step": 3796 }, { "epoch": 0.62, "learning_rate": 2.0659494086727993e-05, "loss": 0.7403, "step": 3797 }, { "epoch": 0.62, "learning_rate": 2.0657030223390277e-05, "loss": 0.661, "step": 3798 }, { "epoch": 0.62, "learning_rate": 2.0654566360052565e-05, "loss": 0.8034, "step": 3799 }, { "epoch": 0.62, "learning_rate": 2.065210249671485e-05, "loss": 1.0041, "step": 3800 }, { "epoch": 0.62, "learning_rate": 2.0649638633377137e-05, "loss": 1.254, "step": 3801 }, { "epoch": 0.62, "learning_rate": 2.064717477003942e-05, "loss": 1.0364, "step": 3802 }, { "epoch": 0.62, "learning_rate": 2.064471090670171e-05, "loss": 0.9401, "step": 3803 }, { "epoch": 0.62, "learning_rate": 2.0642247043363993e-05, "loss": 0.8227, "step": 3804 }, { "epoch": 0.62, "learning_rate": 2.063978318002628e-05, "loss": 1.1415, "step": 3805 }, { "epoch": 0.63, "learning_rate": 2.0637319316688568e-05, "loss": 0.5286, "step": 3806 }, { "epoch": 0.63, "learning_rate": 2.0634855453350856e-05, "loss": 1.49, "step": 3807 }, { "epoch": 0.63, "learning_rate": 2.0632391590013144e-05, "loss": 0.6826, "step": 3808 }, { "epoch": 0.63, "learning_rate": 2.0629927726675428e-05, "loss": 0.8794, "step": 3809 }, { "epoch": 0.63, "learning_rate": 2.0627463863337716e-05, "loss": 0.4975, "step": 3810 }, { "epoch": 0.63, "learning_rate": 2.0625e-05, "loss": 0.8778, "step": 3811 }, { "epoch": 0.63, "learning_rate": 2.0622536136662288e-05, "loss": 1.4246, "step": 3812 }, { "epoch": 0.63, "learning_rate": 2.0620072273324572e-05, "loss": 0.9182, "step": 3813 }, { "epoch": 0.63, "learning_rate": 2.061760840998686e-05, "loss": 1.0988, "step": 3814 }, { "epoch": 0.63, "learning_rate": 2.0615144546649144e-05, "loss": 0.6126, "step": 3815 }, { "epoch": 0.63, "learning_rate": 2.061268068331143e-05, "loss": 0.5823, "step": 3816 }, { "epoch": 0.63, "learning_rate": 2.061021681997372e-05, "loss": 1.16, "step": 3817 }, { "epoch": 0.63, "learning_rate": 2.0607752956636007e-05, "loss": 0.9529, "step": 3818 }, { "epoch": 0.63, "learning_rate": 2.0605289093298295e-05, "loss": 0.8769, "step": 3819 }, { "epoch": 0.63, "learning_rate": 2.060282522996058e-05, "loss": 1.0451, "step": 3820 }, { "epoch": 0.63, "learning_rate": 2.0600361366622867e-05, "loss": 0.9325, "step": 3821 }, { "epoch": 0.63, "learning_rate": 2.059789750328515e-05, "loss": 0.724, "step": 3822 }, { "epoch": 0.63, "learning_rate": 2.059543363994744e-05, "loss": 0.5987, "step": 3823 }, { "epoch": 0.63, "learning_rate": 2.0592969776609723e-05, "loss": 0.908, "step": 3824 }, { "epoch": 0.63, "learning_rate": 2.059050591327201e-05, "loss": 0.7435, "step": 3825 }, { "epoch": 0.63, "learning_rate": 2.0588042049934295e-05, "loss": 0.7579, "step": 3826 }, { "epoch": 0.63, "learning_rate": 2.0585578186596586e-05, "loss": 1.5345, "step": 3827 }, { "epoch": 0.63, "learning_rate": 2.058311432325887e-05, "loss": 0.6695, "step": 3828 }, { "epoch": 0.63, "learning_rate": 2.0580650459921158e-05, "loss": 1.4103, "step": 3829 }, { "epoch": 0.63, "learning_rate": 2.0578186596583442e-05, "loss": 1.0504, "step": 3830 }, { "epoch": 0.63, "learning_rate": 2.057572273324573e-05, "loss": 1.0124, "step": 3831 }, { "epoch": 0.63, "learning_rate": 2.0573258869908017e-05, "loss": 0.9802, "step": 3832 }, { "epoch": 0.63, "learning_rate": 2.0570795006570302e-05, "loss": 1.0056, "step": 3833 }, { "epoch": 0.63, "learning_rate": 2.056833114323259e-05, "loss": 0.6829, "step": 3834 }, { "epoch": 0.63, "learning_rate": 2.0565867279894874e-05, "loss": 0.878, "step": 3835 }, { "epoch": 0.63, "learning_rate": 2.056340341655716e-05, "loss": 1.3803, "step": 3836 }, { "epoch": 0.63, "learning_rate": 2.056093955321945e-05, "loss": 0.9392, "step": 3837 }, { "epoch": 0.63, "learning_rate": 2.0558475689881737e-05, "loss": 0.6227, "step": 3838 }, { "epoch": 0.63, "learning_rate": 2.055601182654402e-05, "loss": 0.5908, "step": 3839 }, { "epoch": 0.63, "learning_rate": 2.055354796320631e-05, "loss": 1.321, "step": 3840 }, { "epoch": 0.63, "learning_rate": 2.0551084099868593e-05, "loss": 0.5599, "step": 3841 }, { "epoch": 0.63, "learning_rate": 2.054862023653088e-05, "loss": 0.4088, "step": 3842 }, { "epoch": 0.63, "learning_rate": 2.054615637319317e-05, "loss": 0.6967, "step": 3843 }, { "epoch": 0.63, "learning_rate": 2.0543692509855453e-05, "loss": 0.7898, "step": 3844 }, { "epoch": 0.63, "learning_rate": 2.054122864651774e-05, "loss": 0.6539, "step": 3845 }, { "epoch": 0.63, "learning_rate": 2.0538764783180025e-05, "loss": 1.0496, "step": 3846 }, { "epoch": 0.63, "learning_rate": 2.0536300919842316e-05, "loss": 0.7947, "step": 3847 }, { "epoch": 0.63, "learning_rate": 2.05338370565046e-05, "loss": 0.7897, "step": 3848 }, { "epoch": 0.63, "learning_rate": 2.0531373193166888e-05, "loss": 0.6339, "step": 3849 }, { "epoch": 0.63, "learning_rate": 2.0528909329829172e-05, "loss": 0.692, "step": 3850 }, { "epoch": 0.63, "learning_rate": 2.052644546649146e-05, "loss": 0.5199, "step": 3851 }, { "epoch": 0.63, "learning_rate": 2.0523981603153744e-05, "loss": 0.8701, "step": 3852 }, { "epoch": 0.63, "learning_rate": 2.052151773981603e-05, "loss": 0.5049, "step": 3853 }, { "epoch": 0.63, "learning_rate": 2.0519053876478316e-05, "loss": 0.8288, "step": 3854 }, { "epoch": 0.63, "learning_rate": 2.0516590013140604e-05, "loss": 0.9054, "step": 3855 }, { "epoch": 0.63, "learning_rate": 2.051412614980289e-05, "loss": 1.7901, "step": 3856 }, { "epoch": 0.63, "learning_rate": 2.051166228646518e-05, "loss": 0.6918, "step": 3857 }, { "epoch": 0.63, "learning_rate": 2.0509198423127467e-05, "loss": 0.4821, "step": 3858 }, { "epoch": 0.63, "learning_rate": 2.050673455978975e-05, "loss": 1.8224, "step": 3859 }, { "epoch": 0.63, "learning_rate": 2.050427069645204e-05, "loss": 0.5004, "step": 3860 }, { "epoch": 0.63, "learning_rate": 2.0501806833114323e-05, "loss": 0.5003, "step": 3861 }, { "epoch": 0.63, "learning_rate": 2.049934296977661e-05, "loss": 1.448, "step": 3862 }, { "epoch": 0.63, "learning_rate": 2.0496879106438895e-05, "loss": 0.7268, "step": 3863 }, { "epoch": 0.63, "learning_rate": 2.0494415243101182e-05, "loss": 0.6788, "step": 3864 }, { "epoch": 0.63, "learning_rate": 2.0491951379763467e-05, "loss": 0.8039, "step": 3865 }, { "epoch": 0.64, "learning_rate": 2.0489487516425754e-05, "loss": 1.2025, "step": 3866 }, { "epoch": 0.64, "learning_rate": 2.0487023653088046e-05, "loss": 0.8497, "step": 3867 }, { "epoch": 0.64, "learning_rate": 2.048455978975033e-05, "loss": 1.0171, "step": 3868 }, { "epoch": 0.64, "learning_rate": 2.0482095926412617e-05, "loss": 0.3853, "step": 3869 }, { "epoch": 0.64, "learning_rate": 2.0479632063074902e-05, "loss": 0.8184, "step": 3870 }, { "epoch": 0.64, "learning_rate": 2.047716819973719e-05, "loss": 1.0365, "step": 3871 }, { "epoch": 0.64, "learning_rate": 2.0474704336399474e-05, "loss": 1.3442, "step": 3872 }, { "epoch": 0.64, "learning_rate": 2.047224047306176e-05, "loss": 1.5149, "step": 3873 }, { "epoch": 0.64, "learning_rate": 2.0469776609724046e-05, "loss": 0.7221, "step": 3874 }, { "epoch": 0.64, "learning_rate": 2.0467312746386333e-05, "loss": 1.023, "step": 3875 }, { "epoch": 0.64, "learning_rate": 2.0464848883048618e-05, "loss": 0.8892, "step": 3876 }, { "epoch": 0.64, "learning_rate": 2.046238501971091e-05, "loss": 1.0652, "step": 3877 }, { "epoch": 0.64, "learning_rate": 2.0459921156373193e-05, "loss": 0.7125, "step": 3878 }, { "epoch": 0.64, "learning_rate": 2.045745729303548e-05, "loss": 0.7158, "step": 3879 }, { "epoch": 0.64, "learning_rate": 2.045499342969777e-05, "loss": 1.0856, "step": 3880 }, { "epoch": 0.64, "learning_rate": 2.0452529566360053e-05, "loss": 0.4024, "step": 3881 }, { "epoch": 0.64, "learning_rate": 2.045006570302234e-05, "loss": 0.8498, "step": 3882 }, { "epoch": 0.64, "learning_rate": 2.0447601839684625e-05, "loss": 0.9121, "step": 3883 }, { "epoch": 0.64, "learning_rate": 2.0445137976346912e-05, "loss": 1.3852, "step": 3884 }, { "epoch": 0.64, "learning_rate": 2.0442674113009197e-05, "loss": 0.792, "step": 3885 }, { "epoch": 0.64, "learning_rate": 2.0440210249671484e-05, "loss": 0.7529, "step": 3886 }, { "epoch": 0.64, "learning_rate": 2.0437746386333772e-05, "loss": 0.743, "step": 3887 }, { "epoch": 0.64, "learning_rate": 2.043528252299606e-05, "loss": 0.7446, "step": 3888 }, { "epoch": 0.64, "learning_rate": 2.0432818659658344e-05, "loss": 0.3805, "step": 3889 }, { "epoch": 0.64, "learning_rate": 2.043035479632063e-05, "loss": 0.7255, "step": 3890 }, { "epoch": 0.64, "learning_rate": 2.042789093298292e-05, "loss": 0.7292, "step": 3891 }, { "epoch": 0.64, "learning_rate": 2.0425427069645204e-05, "loss": 0.8408, "step": 3892 }, { "epoch": 0.64, "learning_rate": 2.042296320630749e-05, "loss": 0.4279, "step": 3893 }, { "epoch": 0.64, "learning_rate": 2.0420499342969776e-05, "loss": 0.4976, "step": 3894 }, { "epoch": 0.64, "learning_rate": 2.0418035479632063e-05, "loss": 1.0597, "step": 3895 }, { "epoch": 0.64, "learning_rate": 2.0415571616294348e-05, "loss": 0.6634, "step": 3896 }, { "epoch": 0.64, "learning_rate": 2.041310775295664e-05, "loss": 1.04, "step": 3897 }, { "epoch": 0.64, "learning_rate": 2.0410643889618923e-05, "loss": 0.7606, "step": 3898 }, { "epoch": 0.64, "learning_rate": 2.040818002628121e-05, "loss": 0.6207, "step": 3899 }, { "epoch": 0.64, "learning_rate": 2.0405716162943495e-05, "loss": 1.2472, "step": 3900 }, { "epoch": 0.64, "learning_rate": 2.0403252299605783e-05, "loss": 0.3646, "step": 3901 }, { "epoch": 0.64, "learning_rate": 2.040078843626807e-05, "loss": 0.418, "step": 3902 }, { "epoch": 0.64, "learning_rate": 2.0398324572930355e-05, "loss": 0.8187, "step": 3903 }, { "epoch": 0.64, "learning_rate": 2.0395860709592642e-05, "loss": 0.6881, "step": 3904 }, { "epoch": 0.64, "learning_rate": 2.0393396846254926e-05, "loss": 1.2525, "step": 3905 }, { "epoch": 0.64, "learning_rate": 2.0390932982917214e-05, "loss": 0.5045, "step": 3906 }, { "epoch": 0.64, "learning_rate": 2.0388469119579502e-05, "loss": 0.4808, "step": 3907 }, { "epoch": 0.64, "learning_rate": 2.038600525624179e-05, "loss": 1.0115, "step": 3908 }, { "epoch": 0.64, "learning_rate": 2.0383541392904074e-05, "loss": 0.9525, "step": 3909 }, { "epoch": 0.64, "learning_rate": 2.038107752956636e-05, "loss": 0.5852, "step": 3910 }, { "epoch": 0.64, "learning_rate": 2.0378613666228646e-05, "loss": 0.5503, "step": 3911 }, { "epoch": 0.64, "learning_rate": 2.0376149802890933e-05, "loss": 0.7899, "step": 3912 }, { "epoch": 0.64, "learning_rate": 2.0373685939553218e-05, "loss": 1.3003, "step": 3913 }, { "epoch": 0.64, "learning_rate": 2.0371222076215505e-05, "loss": 0.6881, "step": 3914 }, { "epoch": 0.64, "learning_rate": 2.0368758212877793e-05, "loss": 1.0203, "step": 3915 }, { "epoch": 0.64, "learning_rate": 2.0366294349540077e-05, "loss": 1.3784, "step": 3916 }, { "epoch": 0.64, "learning_rate": 2.036383048620237e-05, "loss": 1.2117, "step": 3917 }, { "epoch": 0.64, "learning_rate": 2.0361366622864653e-05, "loss": 0.702, "step": 3918 }, { "epoch": 0.64, "learning_rate": 2.035890275952694e-05, "loss": 0.9957, "step": 3919 }, { "epoch": 0.64, "learning_rate": 2.0356438896189225e-05, "loss": 1.3532, "step": 3920 }, { "epoch": 0.64, "learning_rate": 2.0353975032851512e-05, "loss": 0.3906, "step": 3921 }, { "epoch": 0.64, "learning_rate": 2.0351511169513797e-05, "loss": 1.4694, "step": 3922 }, { "epoch": 0.64, "learning_rate": 2.0349047306176084e-05, "loss": 0.7504, "step": 3923 }, { "epoch": 0.64, "learning_rate": 2.034658344283837e-05, "loss": 1.6212, "step": 3924 }, { "epoch": 0.64, "learning_rate": 2.0344119579500656e-05, "loss": 1.6575, "step": 3925 }, { "epoch": 0.64, "learning_rate": 2.0341655716162944e-05, "loss": 0.9244, "step": 3926 }, { "epoch": 0.65, "learning_rate": 2.033919185282523e-05, "loss": 1.1007, "step": 3927 }, { "epoch": 0.65, "learning_rate": 2.033672798948752e-05, "loss": 0.8042, "step": 3928 }, { "epoch": 0.65, "learning_rate": 2.0334264126149804e-05, "loss": 0.7501, "step": 3929 }, { "epoch": 0.65, "learning_rate": 2.033180026281209e-05, "loss": 0.7553, "step": 3930 }, { "epoch": 0.65, "learning_rate": 2.0329336399474376e-05, "loss": 1.2786, "step": 3931 }, { "epoch": 0.65, "learning_rate": 2.0326872536136663e-05, "loss": 0.8649, "step": 3932 }, { "epoch": 0.65, "learning_rate": 2.0324408672798948e-05, "loss": 0.463, "step": 3933 }, { "epoch": 0.65, "learning_rate": 2.0321944809461235e-05, "loss": 0.8487, "step": 3934 }, { "epoch": 0.65, "learning_rate": 2.031948094612352e-05, "loss": 0.846, "step": 3935 }, { "epoch": 0.65, "learning_rate": 2.0317017082785807e-05, "loss": 0.5646, "step": 3936 }, { "epoch": 0.65, "learning_rate": 2.0314553219448095e-05, "loss": 0.5918, "step": 3937 }, { "epoch": 0.65, "learning_rate": 2.0312089356110383e-05, "loss": 0.7033, "step": 3938 }, { "epoch": 0.65, "learning_rate": 2.030962549277267e-05, "loss": 0.3744, "step": 3939 }, { "epoch": 0.65, "learning_rate": 2.0307161629434955e-05, "loss": 0.5633, "step": 3940 }, { "epoch": 0.65, "learning_rate": 2.0304697766097242e-05, "loss": 0.7089, "step": 3941 }, { "epoch": 0.65, "learning_rate": 2.0302233902759527e-05, "loss": 0.8393, "step": 3942 }, { "epoch": 0.65, "learning_rate": 2.0299770039421814e-05, "loss": 0.5802, "step": 3943 }, { "epoch": 0.65, "learning_rate": 2.02973061760841e-05, "loss": 0.982, "step": 3944 }, { "epoch": 0.65, "learning_rate": 2.0294842312746386e-05, "loss": 1.3034, "step": 3945 }, { "epoch": 0.65, "learning_rate": 2.029237844940867e-05, "loss": 1.2517, "step": 3946 }, { "epoch": 0.65, "learning_rate": 2.028991458607096e-05, "loss": 1.4199, "step": 3947 }, { "epoch": 0.65, "learning_rate": 2.0287450722733246e-05, "loss": 1.3472, "step": 3948 }, { "epoch": 0.65, "learning_rate": 2.0284986859395534e-05, "loss": 0.5173, "step": 3949 }, { "epoch": 0.65, "learning_rate": 2.028252299605782e-05, "loss": 1.4264, "step": 3950 }, { "epoch": 0.65, "learning_rate": 2.0280059132720105e-05, "loss": 1.0191, "step": 3951 }, { "epoch": 0.65, "learning_rate": 2.0277595269382393e-05, "loss": 0.8525, "step": 3952 }, { "epoch": 0.65, "learning_rate": 2.0275131406044677e-05, "loss": 0.4365, "step": 3953 }, { "epoch": 0.65, "learning_rate": 2.0272667542706965e-05, "loss": 0.782, "step": 3954 }, { "epoch": 0.65, "learning_rate": 2.027020367936925e-05, "loss": 0.7304, "step": 3955 }, { "epoch": 0.65, "learning_rate": 2.0267739816031537e-05, "loss": 0.4502, "step": 3956 }, { "epoch": 0.65, "learning_rate": 2.0265275952693825e-05, "loss": 1.0285, "step": 3957 }, { "epoch": 0.65, "learning_rate": 2.0262812089356112e-05, "loss": 0.4827, "step": 3958 }, { "epoch": 0.65, "learning_rate": 2.0260348226018397e-05, "loss": 1.1361, "step": 3959 }, { "epoch": 0.65, "learning_rate": 2.0257884362680684e-05, "loss": 0.6519, "step": 3960 }, { "epoch": 0.65, "learning_rate": 2.025542049934297e-05, "loss": 0.8205, "step": 3961 }, { "epoch": 0.65, "learning_rate": 2.0252956636005256e-05, "loss": 1.0703, "step": 3962 }, { "epoch": 0.65, "learning_rate": 2.0250492772667544e-05, "loss": 0.8412, "step": 3963 }, { "epoch": 0.65, "learning_rate": 2.024802890932983e-05, "loss": 0.9412, "step": 3964 }, { "epoch": 0.65, "learning_rate": 2.0245565045992116e-05, "loss": 0.7105, "step": 3965 }, { "epoch": 0.65, "learning_rate": 2.02431011826544e-05, "loss": 0.7425, "step": 3966 }, { "epoch": 0.65, "learning_rate": 2.024063731931669e-05, "loss": 0.7834, "step": 3967 }, { "epoch": 0.65, "learning_rate": 2.0238173455978976e-05, "loss": 1.0499, "step": 3968 }, { "epoch": 0.65, "learning_rate": 2.0235709592641263e-05, "loss": 0.345, "step": 3969 }, { "epoch": 0.65, "learning_rate": 2.0233245729303548e-05, "loss": 0.9926, "step": 3970 }, { "epoch": 0.65, "learning_rate": 2.0230781865965835e-05, "loss": 1.1807, "step": 3971 }, { "epoch": 0.65, "learning_rate": 2.022831800262812e-05, "loss": 0.8463, "step": 3972 }, { "epoch": 0.65, "learning_rate": 2.0225854139290407e-05, "loss": 1.0665, "step": 3973 }, { "epoch": 0.65, "learning_rate": 2.0223390275952695e-05, "loss": 0.9479, "step": 3974 }, { "epoch": 0.65, "learning_rate": 2.022092641261498e-05, "loss": 0.7649, "step": 3975 }, { "epoch": 0.65, "learning_rate": 2.0218462549277267e-05, "loss": 0.7259, "step": 3976 }, { "epoch": 0.65, "learning_rate": 2.0215998685939555e-05, "loss": 1.3706, "step": 3977 }, { "epoch": 0.65, "learning_rate": 2.0213534822601842e-05, "loss": 0.8131, "step": 3978 }, { "epoch": 0.65, "learning_rate": 2.0211070959264127e-05, "loss": 1.2079, "step": 3979 }, { "epoch": 0.65, "learning_rate": 2.0208607095926414e-05, "loss": 0.7803, "step": 3980 }, { "epoch": 0.65, "learning_rate": 2.02061432325887e-05, "loss": 0.5018, "step": 3981 }, { "epoch": 0.65, "learning_rate": 2.0203679369250986e-05, "loss": 0.3665, "step": 3982 }, { "epoch": 0.65, "learning_rate": 2.020121550591327e-05, "loss": 0.5313, "step": 3983 }, { "epoch": 0.65, "learning_rate": 2.0198751642575558e-05, "loss": 0.8955, "step": 3984 }, { "epoch": 0.65, "learning_rate": 2.0196287779237843e-05, "loss": 1.0013, "step": 3985 }, { "epoch": 0.65, "learning_rate": 2.019382391590013e-05, "loss": 0.7719, "step": 3986 }, { "epoch": 0.65, "learning_rate": 2.019136005256242e-05, "loss": 0.9922, "step": 3987 }, { "epoch": 0.66, "learning_rate": 2.0188896189224706e-05, "loss": 0.4463, "step": 3988 }, { "epoch": 0.66, "learning_rate": 2.0186432325886993e-05, "loss": 0.7938, "step": 3989 }, { "epoch": 0.66, "learning_rate": 2.0183968462549278e-05, "loss": 0.776, "step": 3990 }, { "epoch": 0.66, "learning_rate": 2.0181504599211565e-05, "loss": 0.3803, "step": 3991 }, { "epoch": 0.66, "learning_rate": 2.017904073587385e-05, "loss": 1.2567, "step": 3992 }, { "epoch": 0.66, "learning_rate": 2.0176576872536137e-05, "loss": 1.0839, "step": 3993 }, { "epoch": 0.66, "learning_rate": 2.017411300919842e-05, "loss": 0.5372, "step": 3994 }, { "epoch": 0.66, "learning_rate": 2.017164914586071e-05, "loss": 0.5909, "step": 3995 }, { "epoch": 0.66, "learning_rate": 2.0169185282522993e-05, "loss": 0.8716, "step": 3996 }, { "epoch": 0.66, "learning_rate": 2.0166721419185284e-05, "loss": 0.5436, "step": 3997 }, { "epoch": 0.66, "learning_rate": 2.0164257555847572e-05, "loss": 0.8904, "step": 3998 }, { "epoch": 0.66, "learning_rate": 2.0161793692509856e-05, "loss": 1.4693, "step": 3999 }, { "epoch": 0.66, "learning_rate": 2.0159329829172144e-05, "loss": 0.4301, "step": 4000 }, { "epoch": 0.66, "eval_exact_match": 85.9035004730369, "eval_f1": 92.06670511705782, "step": 4000 }, { "epoch": 0.66, "learning_rate": 2.015686596583443e-05, "loss": 1.5697, "step": 4001 }, { "epoch": 0.66, "learning_rate": 2.0154402102496716e-05, "loss": 0.5195, "step": 4002 }, { "epoch": 0.66, "learning_rate": 2.0151938239159e-05, "loss": 0.6688, "step": 4003 }, { "epoch": 0.66, "learning_rate": 2.0149474375821288e-05, "loss": 0.5526, "step": 4004 }, { "epoch": 0.66, "learning_rate": 2.0147010512483572e-05, "loss": 0.7106, "step": 4005 }, { "epoch": 0.66, "learning_rate": 2.014454664914586e-05, "loss": 0.8512, "step": 4006 }, { "epoch": 0.66, "learning_rate": 2.0142082785808148e-05, "loss": 0.8918, "step": 4007 }, { "epoch": 0.66, "learning_rate": 2.0139618922470435e-05, "loss": 0.5635, "step": 4008 }, { "epoch": 0.66, "learning_rate": 2.013715505913272e-05, "loss": 0.6219, "step": 4009 }, { "epoch": 0.66, "learning_rate": 2.0134691195795007e-05, "loss": 1.2242, "step": 4010 }, { "epoch": 0.66, "learning_rate": 2.0132227332457295e-05, "loss": 0.7842, "step": 4011 }, { "epoch": 0.66, "learning_rate": 2.012976346911958e-05, "loss": 0.8588, "step": 4012 }, { "epoch": 0.66, "learning_rate": 2.0127299605781867e-05, "loss": 1.0039, "step": 4013 }, { "epoch": 0.66, "learning_rate": 2.012483574244415e-05, "loss": 0.7992, "step": 4014 }, { "epoch": 0.66, "learning_rate": 2.012237187910644e-05, "loss": 0.7423, "step": 4015 }, { "epoch": 0.66, "learning_rate": 2.0119908015768723e-05, "loss": 1.107, "step": 4016 }, { "epoch": 0.66, "learning_rate": 2.0117444152431014e-05, "loss": 0.2986, "step": 4017 }, { "epoch": 0.66, "learning_rate": 2.01149802890933e-05, "loss": 1.3662, "step": 4018 }, { "epoch": 0.66, "learning_rate": 2.0112516425755586e-05, "loss": 0.3838, "step": 4019 }, { "epoch": 0.66, "learning_rate": 2.011005256241787e-05, "loss": 0.6699, "step": 4020 }, { "epoch": 0.66, "learning_rate": 2.0107588699080158e-05, "loss": 1.4726, "step": 4021 }, { "epoch": 0.66, "learning_rate": 2.0105124835742446e-05, "loss": 1.1772, "step": 4022 }, { "epoch": 0.66, "learning_rate": 2.010266097240473e-05, "loss": 0.9332, "step": 4023 }, { "epoch": 0.66, "learning_rate": 2.0100197109067018e-05, "loss": 1.129, "step": 4024 }, { "epoch": 0.66, "learning_rate": 2.0097733245729302e-05, "loss": 0.401, "step": 4025 }, { "epoch": 0.66, "learning_rate": 2.009526938239159e-05, "loss": 1.5291, "step": 4026 }, { "epoch": 0.66, "learning_rate": 2.0092805519053878e-05, "loss": 0.414, "step": 4027 }, { "epoch": 0.66, "learning_rate": 2.0090341655716165e-05, "loss": 0.7141, "step": 4028 }, { "epoch": 0.66, "learning_rate": 2.008787779237845e-05, "loss": 1.0793, "step": 4029 }, { "epoch": 0.66, "learning_rate": 2.0085413929040737e-05, "loss": 1.2833, "step": 4030 }, { "epoch": 0.66, "learning_rate": 2.008295006570302e-05, "loss": 1.3264, "step": 4031 }, { "epoch": 0.66, "learning_rate": 2.008048620236531e-05, "loss": 0.7891, "step": 4032 }, { "epoch": 0.66, "learning_rate": 2.0078022339027597e-05, "loss": 0.7613, "step": 4033 }, { "epoch": 0.66, "learning_rate": 2.007555847568988e-05, "loss": 1.0214, "step": 4034 }, { "epoch": 0.66, "learning_rate": 2.007309461235217e-05, "loss": 0.9013, "step": 4035 }, { "epoch": 0.66, "learning_rate": 2.0070630749014453e-05, "loss": 1.0954, "step": 4036 }, { "epoch": 0.66, "learning_rate": 2.0068166885676744e-05, "loss": 1.0814, "step": 4037 }, { "epoch": 0.66, "learning_rate": 2.006570302233903e-05, "loss": 0.5331, "step": 4038 }, { "epoch": 0.66, "learning_rate": 2.0063239159001316e-05, "loss": 0.8143, "step": 4039 }, { "epoch": 0.66, "learning_rate": 2.00607752956636e-05, "loss": 0.5638, "step": 4040 }, { "epoch": 0.66, "learning_rate": 2.0058311432325888e-05, "loss": 0.6984, "step": 4041 }, { "epoch": 0.66, "learning_rate": 2.0055847568988172e-05, "loss": 0.8094, "step": 4042 }, { "epoch": 0.66, "learning_rate": 2.005338370565046e-05, "loss": 0.8581, "step": 4043 }, { "epoch": 0.66, "learning_rate": 2.0050919842312744e-05, "loss": 0.5347, "step": 4044 }, { "epoch": 0.66, "learning_rate": 2.0048455978975032e-05, "loss": 0.7942, "step": 4045 }, { "epoch": 0.66, "learning_rate": 2.004599211563732e-05, "loss": 0.8984, "step": 4046 }, { "epoch": 0.66, "learning_rate": 2.0043528252299607e-05, "loss": 0.9829, "step": 4047 }, { "epoch": 0.66, "learning_rate": 2.0041064388961895e-05, "loss": 1.1819, "step": 4048 }, { "epoch": 0.67, "learning_rate": 2.003860052562418e-05, "loss": 0.6562, "step": 4049 }, { "epoch": 0.67, "learning_rate": 2.0036136662286467e-05, "loss": 0.371, "step": 4050 }, { "epoch": 0.67, "learning_rate": 2.003367279894875e-05, "loss": 0.6431, "step": 4051 }, { "epoch": 0.67, "learning_rate": 2.003120893561104e-05, "loss": 0.6089, "step": 4052 }, { "epoch": 0.67, "learning_rate": 2.0028745072273323e-05, "loss": 0.9315, "step": 4053 }, { "epoch": 0.67, "learning_rate": 2.002628120893561e-05, "loss": 1.2695, "step": 4054 }, { "epoch": 0.67, "learning_rate": 2.0023817345597895e-05, "loss": 0.3977, "step": 4055 }, { "epoch": 0.67, "learning_rate": 2.0021353482260183e-05, "loss": 0.9539, "step": 4056 }, { "epoch": 0.67, "learning_rate": 2.0018889618922474e-05, "loss": 0.8073, "step": 4057 }, { "epoch": 0.67, "learning_rate": 2.001642575558476e-05, "loss": 0.433, "step": 4058 }, { "epoch": 0.67, "learning_rate": 2.0013961892247046e-05, "loss": 0.4515, "step": 4059 }, { "epoch": 0.67, "learning_rate": 2.001149802890933e-05, "loss": 1.0952, "step": 4060 }, { "epoch": 0.67, "learning_rate": 2.0009034165571618e-05, "loss": 1.1246, "step": 4061 }, { "epoch": 0.67, "learning_rate": 2.0006570302233902e-05, "loss": 1.0822, "step": 4062 }, { "epoch": 0.67, "learning_rate": 2.000410643889619e-05, "loss": 0.5841, "step": 4063 }, { "epoch": 0.67, "learning_rate": 2.0001642575558474e-05, "loss": 0.9576, "step": 4064 }, { "epoch": 0.67, "learning_rate": 1.9999178712220762e-05, "loss": 0.5691, "step": 4065 }, { "epoch": 0.67, "learning_rate": 1.9996714848883046e-05, "loss": 0.77, "step": 4066 }, { "epoch": 0.67, "learning_rate": 1.9994250985545337e-05, "loss": 1.3693, "step": 4067 }, { "epoch": 0.67, "learning_rate": 1.999178712220762e-05, "loss": 0.6519, "step": 4068 }, { "epoch": 0.67, "learning_rate": 1.998932325886991e-05, "loss": 0.5167, "step": 4069 }, { "epoch": 0.67, "learning_rate": 1.9986859395532197e-05, "loss": 0.9324, "step": 4070 }, { "epoch": 0.67, "learning_rate": 1.998439553219448e-05, "loss": 1.4389, "step": 4071 }, { "epoch": 0.67, "learning_rate": 1.998193166885677e-05, "loss": 0.5335, "step": 4072 }, { "epoch": 0.67, "learning_rate": 1.9979467805519053e-05, "loss": 0.7946, "step": 4073 }, { "epoch": 0.67, "learning_rate": 1.997700394218134e-05, "loss": 0.9198, "step": 4074 }, { "epoch": 0.67, "learning_rate": 1.9974540078843625e-05, "loss": 0.4876, "step": 4075 }, { "epoch": 0.67, "learning_rate": 1.9972076215505913e-05, "loss": 0.3003, "step": 4076 }, { "epoch": 0.67, "learning_rate": 1.99696123521682e-05, "loss": 0.6801, "step": 4077 }, { "epoch": 0.67, "learning_rate": 1.9967148488830488e-05, "loss": 0.7656, "step": 4078 }, { "epoch": 0.67, "learning_rate": 1.9964684625492772e-05, "loss": 0.8783, "step": 4079 }, { "epoch": 0.67, "learning_rate": 1.996222076215506e-05, "loss": 0.5666, "step": 4080 }, { "epoch": 0.67, "learning_rate": 1.9959756898817348e-05, "loss": 0.8021, "step": 4081 }, { "epoch": 0.67, "learning_rate": 1.9957293035479632e-05, "loss": 0.7346, "step": 4082 }, { "epoch": 0.67, "learning_rate": 1.995482917214192e-05, "loss": 0.5654, "step": 4083 }, { "epoch": 0.67, "learning_rate": 1.9952365308804204e-05, "loss": 1.4661, "step": 4084 }, { "epoch": 0.67, "learning_rate": 1.9949901445466492e-05, "loss": 0.7931, "step": 4085 }, { "epoch": 0.67, "learning_rate": 1.9947437582128776e-05, "loss": 0.4471, "step": 4086 }, { "epoch": 0.67, "learning_rate": 1.9944973718791067e-05, "loss": 0.9033, "step": 4087 }, { "epoch": 0.67, "learning_rate": 1.994250985545335e-05, "loss": 1.0778, "step": 4088 }, { "epoch": 0.67, "learning_rate": 1.994004599211564e-05, "loss": 1.1232, "step": 4089 }, { "epoch": 0.67, "learning_rate": 1.9937582128777923e-05, "loss": 0.6363, "step": 4090 }, { "epoch": 0.67, "learning_rate": 1.993511826544021e-05, "loss": 0.7066, "step": 4091 }, { "epoch": 0.67, "learning_rate": 1.9932654402102495e-05, "loss": 1.3482, "step": 4092 }, { "epoch": 0.67, "learning_rate": 1.9930190538764783e-05, "loss": 0.4712, "step": 4093 }, { "epoch": 0.67, "learning_rate": 1.992772667542707e-05, "loss": 0.213, "step": 4094 }, { "epoch": 0.67, "learning_rate": 1.9925262812089355e-05, "loss": 0.5816, "step": 4095 }, { "epoch": 0.67, "learning_rate": 1.9922798948751643e-05, "loss": 1.1016, "step": 4096 }, { "epoch": 0.67, "learning_rate": 1.992033508541393e-05, "loss": 0.8007, "step": 4097 }, { "epoch": 0.67, "learning_rate": 1.9917871222076218e-05, "loss": 0.9607, "step": 4098 }, { "epoch": 0.67, "learning_rate": 1.9915407358738502e-05, "loss": 0.5317, "step": 4099 }, { "epoch": 0.67, "learning_rate": 1.991294349540079e-05, "loss": 0.7856, "step": 4100 }, { "epoch": 0.67, "learning_rate": 1.9910479632063074e-05, "loss": 0.3901, "step": 4101 }, { "epoch": 0.67, "learning_rate": 1.9908015768725362e-05, "loss": 0.8257, "step": 4102 }, { "epoch": 0.67, "learning_rate": 1.9905551905387646e-05, "loss": 0.635, "step": 4103 }, { "epoch": 0.67, "learning_rate": 1.9903088042049934e-05, "loss": 0.9603, "step": 4104 }, { "epoch": 0.67, "learning_rate": 1.990062417871222e-05, "loss": 1.0717, "step": 4105 }, { "epoch": 0.67, "learning_rate": 1.9898160315374506e-05, "loss": 0.7551, "step": 4106 }, { "epoch": 0.67, "learning_rate": 1.9895696452036797e-05, "loss": 1.208, "step": 4107 }, { "epoch": 0.67, "learning_rate": 1.989323258869908e-05, "loss": 0.5805, "step": 4108 }, { "epoch": 0.67, "learning_rate": 1.989076872536137e-05, "loss": 1.0248, "step": 4109 }, { "epoch": 0.68, "learning_rate": 1.9888304862023653e-05, "loss": 0.9224, "step": 4110 }, { "epoch": 0.68, "learning_rate": 1.988584099868594e-05, "loss": 1.5256, "step": 4111 }, { "epoch": 0.68, "learning_rate": 1.9883377135348225e-05, "loss": 0.9624, "step": 4112 }, { "epoch": 0.68, "learning_rate": 1.9880913272010513e-05, "loss": 0.9343, "step": 4113 }, { "epoch": 0.68, "learning_rate": 1.9878449408672797e-05, "loss": 0.7245, "step": 4114 }, { "epoch": 0.68, "learning_rate": 1.9875985545335085e-05, "loss": 0.4266, "step": 4115 }, { "epoch": 0.68, "learning_rate": 1.987352168199737e-05, "loss": 1.6015, "step": 4116 }, { "epoch": 0.68, "learning_rate": 1.987105781865966e-05, "loss": 0.799, "step": 4117 }, { "epoch": 0.68, "learning_rate": 1.9868593955321948e-05, "loss": 0.8568, "step": 4118 }, { "epoch": 0.68, "learning_rate": 1.9866130091984232e-05, "loss": 1.2128, "step": 4119 }, { "epoch": 0.68, "learning_rate": 1.986366622864652e-05, "loss": 0.6573, "step": 4120 }, { "epoch": 0.68, "learning_rate": 1.9861202365308804e-05, "loss": 0.7855, "step": 4121 }, { "epoch": 0.68, "learning_rate": 1.9858738501971092e-05, "loss": 0.494, "step": 4122 }, { "epoch": 0.68, "learning_rate": 1.9856274638633376e-05, "loss": 0.9372, "step": 4123 }, { "epoch": 0.68, "learning_rate": 1.9853810775295664e-05, "loss": 1.1359, "step": 4124 }, { "epoch": 0.68, "learning_rate": 1.9851346911957948e-05, "loss": 0.8344, "step": 4125 }, { "epoch": 0.68, "learning_rate": 1.9848883048620236e-05, "loss": 0.6541, "step": 4126 }, { "epoch": 0.68, "learning_rate": 1.9846419185282523e-05, "loss": 1.2415, "step": 4127 }, { "epoch": 0.68, "learning_rate": 1.984395532194481e-05, "loss": 1.1498, "step": 4128 }, { "epoch": 0.68, "learning_rate": 1.98414914586071e-05, "loss": 0.8783, "step": 4129 }, { "epoch": 0.68, "learning_rate": 1.9839027595269383e-05, "loss": 0.5186, "step": 4130 }, { "epoch": 0.68, "learning_rate": 1.983656373193167e-05, "loss": 1.2888, "step": 4131 }, { "epoch": 0.68, "learning_rate": 1.9834099868593955e-05, "loss": 1.1524, "step": 4132 }, { "epoch": 0.68, "learning_rate": 1.9831636005256243e-05, "loss": 0.5191, "step": 4133 }, { "epoch": 0.68, "learning_rate": 1.9829172141918527e-05, "loss": 0.7682, "step": 4134 }, { "epoch": 0.68, "learning_rate": 1.9826708278580815e-05, "loss": 0.6315, "step": 4135 }, { "epoch": 0.68, "learning_rate": 1.98242444152431e-05, "loss": 0.8903, "step": 4136 }, { "epoch": 0.68, "learning_rate": 1.982178055190539e-05, "loss": 1.903, "step": 4137 }, { "epoch": 0.68, "learning_rate": 1.9819316688567674e-05, "loss": 0.8204, "step": 4138 }, { "epoch": 0.68, "learning_rate": 1.9816852825229962e-05, "loss": 1.7696, "step": 4139 }, { "epoch": 0.68, "learning_rate": 1.9814388961892246e-05, "loss": 1.214, "step": 4140 }, { "epoch": 0.68, "learning_rate": 1.9811925098554534e-05, "loss": 0.6546, "step": 4141 }, { "epoch": 0.68, "learning_rate": 1.9809461235216822e-05, "loss": 1.2005, "step": 4142 }, { "epoch": 0.68, "learning_rate": 1.9806997371879106e-05, "loss": 0.9465, "step": 4143 }, { "epoch": 0.68, "learning_rate": 1.9804533508541394e-05, "loss": 0.9329, "step": 4144 }, { "epoch": 0.68, "learning_rate": 1.9802069645203678e-05, "loss": 0.6955, "step": 4145 }, { "epoch": 0.68, "learning_rate": 1.9799605781865966e-05, "loss": 0.9706, "step": 4146 }, { "epoch": 0.68, "learning_rate": 1.9797141918528253e-05, "loss": 1.0301, "step": 4147 }, { "epoch": 0.68, "learning_rate": 1.979467805519054e-05, "loss": 1.0932, "step": 4148 }, { "epoch": 0.68, "learning_rate": 1.9792214191852825e-05, "loss": 0.7806, "step": 4149 }, { "epoch": 0.68, "learning_rate": 1.9789750328515113e-05, "loss": 1.1693, "step": 4150 }, { "epoch": 0.68, "learning_rate": 1.9787286465177397e-05, "loss": 0.7924, "step": 4151 }, { "epoch": 0.68, "learning_rate": 1.9784822601839685e-05, "loss": 0.8254, "step": 4152 }, { "epoch": 0.68, "learning_rate": 1.9782358738501973e-05, "loss": 0.9005, "step": 4153 }, { "epoch": 0.68, "learning_rate": 1.9779894875164257e-05, "loss": 0.706, "step": 4154 }, { "epoch": 0.68, "learning_rate": 1.9777431011826545e-05, "loss": 0.9361, "step": 4155 }, { "epoch": 0.68, "learning_rate": 1.977496714848883e-05, "loss": 1.4112, "step": 4156 }, { "epoch": 0.68, "learning_rate": 1.977250328515112e-05, "loss": 0.5948, "step": 4157 }, { "epoch": 0.68, "learning_rate": 1.9770039421813404e-05, "loss": 0.5711, "step": 4158 }, { "epoch": 0.68, "learning_rate": 1.9767575558475692e-05, "loss": 0.6534, "step": 4159 }, { "epoch": 0.68, "learning_rate": 1.9765111695137976e-05, "loss": 0.8522, "step": 4160 }, { "epoch": 0.68, "learning_rate": 1.9762647831800264e-05, "loss": 1.57, "step": 4161 }, { "epoch": 0.68, "learning_rate": 1.9760183968462548e-05, "loss": 0.4546, "step": 4162 }, { "epoch": 0.68, "learning_rate": 1.9757720105124836e-05, "loss": 1.0922, "step": 4163 }, { "epoch": 0.68, "learning_rate": 1.9755256241787124e-05, "loss": 0.5845, "step": 4164 }, { "epoch": 0.68, "learning_rate": 1.9752792378449408e-05, "loss": 0.9703, "step": 4165 }, { "epoch": 0.68, "learning_rate": 1.9750328515111696e-05, "loss": 1.2473, "step": 4166 }, { "epoch": 0.68, "learning_rate": 1.9747864651773983e-05, "loss": 0.8529, "step": 4167 }, { "epoch": 0.68, "learning_rate": 1.974540078843627e-05, "loss": 0.7971, "step": 4168 }, { "epoch": 0.68, "learning_rate": 1.9742936925098555e-05, "loss": 1.034, "step": 4169 }, { "epoch": 0.68, "learning_rate": 1.9740473061760843e-05, "loss": 0.6095, "step": 4170 }, { "epoch": 0.69, "learning_rate": 1.9738009198423127e-05, "loss": 0.5453, "step": 4171 }, { "epoch": 0.69, "learning_rate": 1.9735545335085415e-05, "loss": 1.0419, "step": 4172 }, { "epoch": 0.69, "learning_rate": 1.97330814717477e-05, "loss": 1.0575, "step": 4173 }, { "epoch": 0.69, "learning_rate": 1.9730617608409987e-05, "loss": 0.5026, "step": 4174 }, { "epoch": 0.69, "learning_rate": 1.972815374507227e-05, "loss": 1.0404, "step": 4175 }, { "epoch": 0.69, "learning_rate": 1.972568988173456e-05, "loss": 1.0957, "step": 4176 }, { "epoch": 0.69, "learning_rate": 1.972322601839685e-05, "loss": 0.7693, "step": 4177 }, { "epoch": 0.69, "learning_rate": 1.9720762155059134e-05, "loss": 1.5641, "step": 4178 }, { "epoch": 0.69, "learning_rate": 1.9718298291721422e-05, "loss": 0.6147, "step": 4179 }, { "epoch": 0.69, "learning_rate": 1.9715834428383706e-05, "loss": 1.3545, "step": 4180 }, { "epoch": 0.69, "learning_rate": 1.9713370565045994e-05, "loss": 1.2609, "step": 4181 }, { "epoch": 0.69, "learning_rate": 1.9710906701708278e-05, "loss": 0.5202, "step": 4182 }, { "epoch": 0.69, "learning_rate": 1.9708442838370566e-05, "loss": 0.7109, "step": 4183 }, { "epoch": 0.69, "learning_rate": 1.970597897503285e-05, "loss": 0.9715, "step": 4184 }, { "epoch": 0.69, "learning_rate": 1.9703515111695138e-05, "loss": 1.0404, "step": 4185 }, { "epoch": 0.69, "learning_rate": 1.9701051248357422e-05, "loss": 1.0368, "step": 4186 }, { "epoch": 0.69, "learning_rate": 1.9698587385019713e-05, "loss": 1.2607, "step": 4187 }, { "epoch": 0.69, "learning_rate": 1.9696123521682e-05, "loss": 0.6675, "step": 4188 }, { "epoch": 0.69, "learning_rate": 1.9693659658344285e-05, "loss": 0.8243, "step": 4189 }, { "epoch": 0.69, "learning_rate": 1.9691195795006573e-05, "loss": 0.5736, "step": 4190 }, { "epoch": 0.69, "learning_rate": 1.9688731931668857e-05, "loss": 0.7735, "step": 4191 }, { "epoch": 0.69, "learning_rate": 1.9686268068331145e-05, "loss": 0.7061, "step": 4192 }, { "epoch": 0.69, "learning_rate": 1.968380420499343e-05, "loss": 0.8798, "step": 4193 }, { "epoch": 0.69, "learning_rate": 1.9681340341655717e-05, "loss": 0.8096, "step": 4194 }, { "epoch": 0.69, "learning_rate": 1.9678876478318e-05, "loss": 0.739, "step": 4195 }, { "epoch": 0.69, "learning_rate": 1.967641261498029e-05, "loss": 0.701, "step": 4196 }, { "epoch": 0.69, "learning_rate": 1.9673948751642576e-05, "loss": 0.9251, "step": 4197 }, { "epoch": 0.69, "learning_rate": 1.9671484888304864e-05, "loss": 0.9748, "step": 4198 }, { "epoch": 0.69, "learning_rate": 1.9669021024967148e-05, "loss": 0.7702, "step": 4199 }, { "epoch": 0.69, "learning_rate": 1.9666557161629436e-05, "loss": 1.0499, "step": 4200 }, { "epoch": 0.69, "learning_rate": 1.9664093298291724e-05, "loss": 0.4971, "step": 4201 }, { "epoch": 0.69, "learning_rate": 1.9661629434954008e-05, "loss": 0.3042, "step": 4202 }, { "epoch": 0.69, "learning_rate": 1.9659165571616296e-05, "loss": 1.1575, "step": 4203 }, { "epoch": 0.69, "learning_rate": 1.965670170827858e-05, "loss": 0.57, "step": 4204 }, { "epoch": 0.69, "learning_rate": 1.9654237844940868e-05, "loss": 0.9445, "step": 4205 }, { "epoch": 0.69, "learning_rate": 1.9651773981603152e-05, "loss": 1.2979, "step": 4206 }, { "epoch": 0.69, "learning_rate": 1.9649310118265443e-05, "loss": 0.4716, "step": 4207 }, { "epoch": 0.69, "learning_rate": 1.9646846254927727e-05, "loss": 0.9872, "step": 4208 }, { "epoch": 0.69, "learning_rate": 1.9644382391590015e-05, "loss": 1.141, "step": 4209 }, { "epoch": 0.69, "learning_rate": 1.96419185282523e-05, "loss": 1.3205, "step": 4210 }, { "epoch": 0.69, "learning_rate": 1.9639454664914587e-05, "loss": 1.0701, "step": 4211 }, { "epoch": 0.69, "learning_rate": 1.9636990801576875e-05, "loss": 0.6421, "step": 4212 }, { "epoch": 0.69, "learning_rate": 1.963452693823916e-05, "loss": 0.8309, "step": 4213 }, { "epoch": 0.69, "learning_rate": 1.9632063074901446e-05, "loss": 0.5854, "step": 4214 }, { "epoch": 0.69, "learning_rate": 1.962959921156373e-05, "loss": 0.5876, "step": 4215 }, { "epoch": 0.69, "learning_rate": 1.962713534822602e-05, "loss": 0.9573, "step": 4216 }, { "epoch": 0.69, "learning_rate": 1.9624671484888306e-05, "loss": 0.688, "step": 4217 }, { "epoch": 0.69, "learning_rate": 1.9622207621550594e-05, "loss": 0.9821, "step": 4218 }, { "epoch": 0.69, "learning_rate": 1.9619743758212878e-05, "loss": 0.7957, "step": 4219 }, { "epoch": 0.69, "learning_rate": 1.9617279894875166e-05, "loss": 1.1003, "step": 4220 }, { "epoch": 0.69, "learning_rate": 1.961481603153745e-05, "loss": 0.6014, "step": 4221 }, { "epoch": 0.69, "learning_rate": 1.9612352168199738e-05, "loss": 1.0259, "step": 4222 }, { "epoch": 0.69, "learning_rate": 1.9609888304862022e-05, "loss": 0.7256, "step": 4223 }, { "epoch": 0.69, "learning_rate": 1.960742444152431e-05, "loss": 0.6979, "step": 4224 }, { "epoch": 0.69, "learning_rate": 1.9604960578186597e-05, "loss": 0.6333, "step": 4225 }, { "epoch": 0.69, "learning_rate": 1.960249671484888e-05, "loss": 1.1528, "step": 4226 }, { "epoch": 0.69, "learning_rate": 1.9600032851511173e-05, "loss": 0.6523, "step": 4227 }, { "epoch": 0.69, "learning_rate": 1.9597568988173457e-05, "loss": 1.1202, "step": 4228 }, { "epoch": 0.69, "learning_rate": 1.9595105124835745e-05, "loss": 0.8418, "step": 4229 }, { "epoch": 0.69, "learning_rate": 1.959264126149803e-05, "loss": 0.7232, "step": 4230 }, { "epoch": 0.69, "learning_rate": 1.9590177398160317e-05, "loss": 0.7003, "step": 4231 }, { "epoch": 0.7, "learning_rate": 1.95877135348226e-05, "loss": 1.297, "step": 4232 }, { "epoch": 0.7, "learning_rate": 1.958524967148489e-05, "loss": 0.8102, "step": 4233 }, { "epoch": 0.7, "learning_rate": 1.9582785808147173e-05, "loss": 0.8432, "step": 4234 }, { "epoch": 0.7, "learning_rate": 1.958032194480946e-05, "loss": 1.0731, "step": 4235 }, { "epoch": 0.7, "learning_rate": 1.9577858081471748e-05, "loss": 0.8252, "step": 4236 }, { "epoch": 0.7, "learning_rate": 1.9575394218134036e-05, "loss": 1.3181, "step": 4237 }, { "epoch": 0.7, "learning_rate": 1.9572930354796324e-05, "loss": 0.6659, "step": 4238 }, { "epoch": 0.7, "learning_rate": 1.9570466491458608e-05, "loss": 0.8789, "step": 4239 }, { "epoch": 0.7, "learning_rate": 1.9568002628120896e-05, "loss": 0.7179, "step": 4240 }, { "epoch": 0.7, "learning_rate": 1.956553876478318e-05, "loss": 0.8473, "step": 4241 }, { "epoch": 0.7, "learning_rate": 1.9563074901445468e-05, "loss": 0.4657, "step": 4242 }, { "epoch": 0.7, "learning_rate": 1.9560611038107752e-05, "loss": 1.5301, "step": 4243 }, { "epoch": 0.7, "learning_rate": 1.955814717477004e-05, "loss": 0.7849, "step": 4244 }, { "epoch": 0.7, "learning_rate": 1.9555683311432324e-05, "loss": 0.6726, "step": 4245 }, { "epoch": 0.7, "learning_rate": 1.955321944809461e-05, "loss": 0.8876, "step": 4246 }, { "epoch": 0.7, "learning_rate": 1.95507555847569e-05, "loss": 0.615, "step": 4247 }, { "epoch": 0.7, "learning_rate": 1.9548291721419187e-05, "loss": 0.839, "step": 4248 }, { "epoch": 0.7, "learning_rate": 1.9545827858081475e-05, "loss": 0.4844, "step": 4249 }, { "epoch": 0.7, "learning_rate": 1.954336399474376e-05, "loss": 0.9825, "step": 4250 }, { "epoch": 0.7, "learning_rate": 1.9540900131406047e-05, "loss": 0.5984, "step": 4251 }, { "epoch": 0.7, "learning_rate": 1.953843626806833e-05, "loss": 0.6732, "step": 4252 }, { "epoch": 0.7, "learning_rate": 1.953597240473062e-05, "loss": 1.0855, "step": 4253 }, { "epoch": 0.7, "learning_rate": 1.9533508541392903e-05, "loss": 0.9174, "step": 4254 }, { "epoch": 0.7, "learning_rate": 1.953104467805519e-05, "loss": 0.6798, "step": 4255 }, { "epoch": 0.7, "learning_rate": 1.9528580814717475e-05, "loss": 0.5557, "step": 4256 }, { "epoch": 0.7, "learning_rate": 1.9526116951379766e-05, "loss": 1.2952, "step": 4257 }, { "epoch": 0.7, "learning_rate": 1.952365308804205e-05, "loss": 0.5252, "step": 4258 }, { "epoch": 0.7, "learning_rate": 1.9521189224704338e-05, "loss": 0.2438, "step": 4259 }, { "epoch": 0.7, "learning_rate": 1.9518725361366625e-05, "loss": 1.2991, "step": 4260 }, { "epoch": 0.7, "learning_rate": 1.951626149802891e-05, "loss": 0.9763, "step": 4261 }, { "epoch": 0.7, "learning_rate": 1.9513797634691197e-05, "loss": 0.9785, "step": 4262 }, { "epoch": 0.7, "learning_rate": 1.9511333771353482e-05, "loss": 0.8617, "step": 4263 }, { "epoch": 0.7, "learning_rate": 1.950886990801577e-05, "loss": 0.6041, "step": 4264 }, { "epoch": 0.7, "learning_rate": 1.9506406044678054e-05, "loss": 0.6252, "step": 4265 }, { "epoch": 0.7, "learning_rate": 1.950394218134034e-05, "loss": 0.9185, "step": 4266 }, { "epoch": 0.7, "learning_rate": 1.950147831800263e-05, "loss": 0.3577, "step": 4267 }, { "epoch": 0.7, "learning_rate": 1.9499014454664917e-05, "loss": 0.9998, "step": 4268 }, { "epoch": 0.7, "learning_rate": 1.94965505913272e-05, "loss": 1.056, "step": 4269 }, { "epoch": 0.7, "learning_rate": 1.949408672798949e-05, "loss": 1.1003, "step": 4270 }, { "epoch": 0.7, "learning_rate": 1.9491622864651773e-05, "loss": 0.8198, "step": 4271 }, { "epoch": 0.7, "learning_rate": 1.948915900131406e-05, "loss": 1.2035, "step": 4272 }, { "epoch": 0.7, "learning_rate": 1.948669513797635e-05, "loss": 0.9502, "step": 4273 }, { "epoch": 0.7, "learning_rate": 1.9484231274638633e-05, "loss": 0.8921, "step": 4274 }, { "epoch": 0.7, "learning_rate": 1.948176741130092e-05, "loss": 0.9597, "step": 4275 }, { "epoch": 0.7, "learning_rate": 1.9479303547963205e-05, "loss": 0.9562, "step": 4276 }, { "epoch": 0.7, "learning_rate": 1.9476839684625496e-05, "loss": 0.5517, "step": 4277 }, { "epoch": 0.7, "learning_rate": 1.947437582128778e-05, "loss": 0.5403, "step": 4278 }, { "epoch": 0.7, "learning_rate": 1.9471911957950068e-05, "loss": 0.9735, "step": 4279 }, { "epoch": 0.7, "learning_rate": 1.9469448094612352e-05, "loss": 0.4969, "step": 4280 }, { "epoch": 0.7, "learning_rate": 1.946698423127464e-05, "loss": 0.9181, "step": 4281 }, { "epoch": 0.7, "learning_rate": 1.9464520367936924e-05, "loss": 0.7461, "step": 4282 }, { "epoch": 0.7, "learning_rate": 1.946205650459921e-05, "loss": 0.5057, "step": 4283 }, { "epoch": 0.7, "learning_rate": 1.94595926412615e-05, "loss": 1.0133, "step": 4284 }, { "epoch": 0.7, "learning_rate": 1.9457128777923784e-05, "loss": 1.3761, "step": 4285 }, { "epoch": 0.7, "learning_rate": 1.945466491458607e-05, "loss": 0.9695, "step": 4286 }, { "epoch": 0.7, "learning_rate": 1.945220105124836e-05, "loss": 0.588, "step": 4287 }, { "epoch": 0.7, "learning_rate": 1.9449737187910647e-05, "loss": 1.7148, "step": 4288 }, { "epoch": 0.7, "learning_rate": 1.944727332457293e-05, "loss": 0.7498, "step": 4289 }, { "epoch": 0.7, "learning_rate": 1.944480946123522e-05, "loss": 0.4568, "step": 4290 }, { "epoch": 0.7, "learning_rate": 1.9442345597897503e-05, "loss": 1.3814, "step": 4291 }, { "epoch": 0.7, "learning_rate": 1.943988173455979e-05, "loss": 0.5718, "step": 4292 }, { "epoch": 0.71, "learning_rate": 1.9437417871222075e-05, "loss": 0.3735, "step": 4293 }, { "epoch": 0.71, "learning_rate": 1.9434954007884363e-05, "loss": 1.0116, "step": 4294 }, { "epoch": 0.71, "learning_rate": 1.943249014454665e-05, "loss": 0.6889, "step": 4295 }, { "epoch": 0.71, "learning_rate": 1.9430026281208934e-05, "loss": 0.7077, "step": 4296 }, { "epoch": 0.71, "learning_rate": 1.9427562417871226e-05, "loss": 1.0035, "step": 4297 }, { "epoch": 0.71, "learning_rate": 1.942509855453351e-05, "loss": 1.1565, "step": 4298 }, { "epoch": 0.71, "learning_rate": 1.9422634691195798e-05, "loss": 1.485, "step": 4299 }, { "epoch": 0.71, "learning_rate": 1.9420170827858082e-05, "loss": 0.8178, "step": 4300 }, { "epoch": 0.71, "learning_rate": 1.941770696452037e-05, "loss": 0.9507, "step": 4301 }, { "epoch": 0.71, "learning_rate": 1.9415243101182654e-05, "loss": 1.161, "step": 4302 }, { "epoch": 0.71, "learning_rate": 1.941277923784494e-05, "loss": 0.4933, "step": 4303 }, { "epoch": 0.71, "learning_rate": 1.9410315374507226e-05, "loss": 1.2598, "step": 4304 }, { "epoch": 0.71, "learning_rate": 1.9407851511169513e-05, "loss": 0.6234, "step": 4305 }, { "epoch": 0.71, "learning_rate": 1.9405387647831798e-05, "loss": 0.5558, "step": 4306 }, { "epoch": 0.71, "learning_rate": 1.940292378449409e-05, "loss": 0.9745, "step": 4307 }, { "epoch": 0.71, "learning_rate": 1.9400459921156376e-05, "loss": 1.2293, "step": 4308 }, { "epoch": 0.71, "learning_rate": 1.939799605781866e-05, "loss": 0.4062, "step": 4309 }, { "epoch": 0.71, "learning_rate": 1.939553219448095e-05, "loss": 1.346, "step": 4310 }, { "epoch": 0.71, "learning_rate": 1.9393068331143233e-05, "loss": 1.2535, "step": 4311 }, { "epoch": 0.71, "learning_rate": 1.939060446780552e-05, "loss": 0.4289, "step": 4312 }, { "epoch": 0.71, "learning_rate": 1.9388140604467805e-05, "loss": 0.7897, "step": 4313 }, { "epoch": 0.71, "learning_rate": 1.9385676741130092e-05, "loss": 0.7517, "step": 4314 }, { "epoch": 0.71, "learning_rate": 1.9383212877792377e-05, "loss": 0.7433, "step": 4315 }, { "epoch": 0.71, "learning_rate": 1.9380749014454664e-05, "loss": 1.0752, "step": 4316 }, { "epoch": 0.71, "learning_rate": 1.9378285151116952e-05, "loss": 0.5114, "step": 4317 }, { "epoch": 0.71, "learning_rate": 1.937582128777924e-05, "loss": 0.9591, "step": 4318 }, { "epoch": 0.71, "learning_rate": 1.9373357424441527e-05, "loss": 0.7267, "step": 4319 }, { "epoch": 0.71, "learning_rate": 1.937089356110381e-05, "loss": 0.6303, "step": 4320 }, { "epoch": 0.71, "learning_rate": 1.93684296977661e-05, "loss": 0.4437, "step": 4321 }, { "epoch": 0.71, "learning_rate": 1.9365965834428384e-05, "loss": 0.7616, "step": 4322 }, { "epoch": 0.71, "learning_rate": 1.936350197109067e-05, "loss": 1.5295, "step": 4323 }, { "epoch": 0.71, "learning_rate": 1.9361038107752956e-05, "loss": 0.9419, "step": 4324 }, { "epoch": 0.71, "learning_rate": 1.9358574244415243e-05, "loss": 0.577, "step": 4325 }, { "epoch": 0.71, "learning_rate": 1.9356110381077528e-05, "loss": 0.6539, "step": 4326 }, { "epoch": 0.71, "learning_rate": 1.935364651773982e-05, "loss": 1.082, "step": 4327 }, { "epoch": 0.71, "learning_rate": 1.9351182654402103e-05, "loss": 0.701, "step": 4328 }, { "epoch": 0.71, "learning_rate": 1.934871879106439e-05, "loss": 1.0283, "step": 4329 }, { "epoch": 0.71, "learning_rate": 1.9346254927726675e-05, "loss": 0.8086, "step": 4330 }, { "epoch": 0.71, "learning_rate": 1.9343791064388963e-05, "loss": 1.1967, "step": 4331 }, { "epoch": 0.71, "learning_rate": 1.934132720105125e-05, "loss": 0.7935, "step": 4332 }, { "epoch": 0.71, "learning_rate": 1.9338863337713535e-05, "loss": 0.8988, "step": 4333 }, { "epoch": 0.71, "learning_rate": 1.9336399474375822e-05, "loss": 0.9981, "step": 4334 }, { "epoch": 0.71, "learning_rate": 1.9333935611038107e-05, "loss": 0.7902, "step": 4335 }, { "epoch": 0.71, "learning_rate": 1.9331471747700394e-05, "loss": 0.4005, "step": 4336 }, { "epoch": 0.71, "learning_rate": 1.9329007884362682e-05, "loss": 0.9231, "step": 4337 }, { "epoch": 0.71, "learning_rate": 1.932654402102497e-05, "loss": 0.9279, "step": 4338 }, { "epoch": 0.71, "learning_rate": 1.9324080157687254e-05, "loss": 0.5446, "step": 4339 }, { "epoch": 0.71, "learning_rate": 1.932161629434954e-05, "loss": 0.6427, "step": 4340 }, { "epoch": 0.71, "learning_rate": 1.9319152431011826e-05, "loss": 1.187, "step": 4341 }, { "epoch": 0.71, "learning_rate": 1.9316688567674113e-05, "loss": 1.3297, "step": 4342 }, { "epoch": 0.71, "learning_rate": 1.93142247043364e-05, "loss": 0.4694, "step": 4343 }, { "epoch": 0.71, "learning_rate": 1.9311760840998685e-05, "loss": 1.3787, "step": 4344 }, { "epoch": 0.71, "learning_rate": 1.9309296977660973e-05, "loss": 1.0054, "step": 4345 }, { "epoch": 0.71, "learning_rate": 1.9306833114323257e-05, "loss": 0.8239, "step": 4346 }, { "epoch": 0.71, "learning_rate": 1.930436925098555e-05, "loss": 0.482, "step": 4347 }, { "epoch": 0.71, "learning_rate": 1.9301905387647833e-05, "loss": 0.554, "step": 4348 }, { "epoch": 0.71, "learning_rate": 1.929944152431012e-05, "loss": 0.6769, "step": 4349 }, { "epoch": 0.71, "learning_rate": 1.9296977660972405e-05, "loss": 0.8062, "step": 4350 }, { "epoch": 0.71, "learning_rate": 1.9294513797634692e-05, "loss": 1.013, "step": 4351 }, { "epoch": 0.71, "learning_rate": 1.9292049934296977e-05, "loss": 0.7458, "step": 4352 }, { "epoch": 0.72, "learning_rate": 1.9289586070959264e-05, "loss": 1.278, "step": 4353 }, { "epoch": 0.72, "learning_rate": 1.928712220762155e-05, "loss": 1.048, "step": 4354 }, { "epoch": 0.72, "learning_rate": 1.9284658344283836e-05, "loss": 0.73, "step": 4355 }, { "epoch": 0.72, "learning_rate": 1.9282194480946124e-05, "loss": 1.0448, "step": 4356 }, { "epoch": 0.72, "learning_rate": 1.9279730617608412e-05, "loss": 1.9102, "step": 4357 }, { "epoch": 0.72, "learning_rate": 1.92772667542707e-05, "loss": 0.9641, "step": 4358 }, { "epoch": 0.72, "learning_rate": 1.9274802890932984e-05, "loss": 0.8359, "step": 4359 }, { "epoch": 0.72, "learning_rate": 1.927233902759527e-05, "loss": 0.7833, "step": 4360 }, { "epoch": 0.72, "learning_rate": 1.9269875164257556e-05, "loss": 0.6547, "step": 4361 }, { "epoch": 0.72, "learning_rate": 1.9267411300919843e-05, "loss": 1.2575, "step": 4362 }, { "epoch": 0.72, "learning_rate": 1.9264947437582128e-05, "loss": 0.9942, "step": 4363 }, { "epoch": 0.72, "learning_rate": 1.9262483574244415e-05, "loss": 1.0098, "step": 4364 }, { "epoch": 0.72, "learning_rate": 1.92600197109067e-05, "loss": 0.8313, "step": 4365 }, { "epoch": 0.72, "learning_rate": 1.9257555847568987e-05, "loss": 0.8678, "step": 4366 }, { "epoch": 0.72, "learning_rate": 1.925509198423128e-05, "loss": 0.4474, "step": 4367 }, { "epoch": 0.72, "learning_rate": 1.9252628120893563e-05, "loss": 0.8443, "step": 4368 }, { "epoch": 0.72, "learning_rate": 1.925016425755585e-05, "loss": 0.5067, "step": 4369 }, { "epoch": 0.72, "learning_rate": 1.9247700394218135e-05, "loss": 0.6384, "step": 4370 }, { "epoch": 0.72, "learning_rate": 1.9245236530880422e-05, "loss": 0.8481, "step": 4371 }, { "epoch": 0.72, "learning_rate": 1.9242772667542707e-05, "loss": 1.226, "step": 4372 }, { "epoch": 0.72, "learning_rate": 1.9240308804204994e-05, "loss": 1.3954, "step": 4373 }, { "epoch": 0.72, "learning_rate": 1.923784494086728e-05, "loss": 1.0093, "step": 4374 }, { "epoch": 0.72, "learning_rate": 1.9235381077529566e-05, "loss": 0.426, "step": 4375 }, { "epoch": 0.72, "learning_rate": 1.923291721419185e-05, "loss": 0.5973, "step": 4376 }, { "epoch": 0.72, "learning_rate": 1.923045335085414e-05, "loss": 0.7071, "step": 4377 }, { "epoch": 0.72, "learning_rate": 1.9227989487516426e-05, "loss": 0.7996, "step": 4378 }, { "epoch": 0.72, "learning_rate": 1.9225525624178714e-05, "loss": 1.0671, "step": 4379 }, { "epoch": 0.72, "learning_rate": 1.9223061760841e-05, "loss": 1.0608, "step": 4380 }, { "epoch": 0.72, "learning_rate": 1.9220597897503286e-05, "loss": 1.3088, "step": 4381 }, { "epoch": 0.72, "learning_rate": 1.9218134034165573e-05, "loss": 0.7158, "step": 4382 }, { "epoch": 0.72, "learning_rate": 1.9215670170827857e-05, "loss": 1.3183, "step": 4383 }, { "epoch": 0.72, "learning_rate": 1.9213206307490145e-05, "loss": 0.5407, "step": 4384 }, { "epoch": 0.72, "learning_rate": 1.921074244415243e-05, "loss": 0.6294, "step": 4385 }, { "epoch": 0.72, "learning_rate": 1.9208278580814717e-05, "loss": 0.7437, "step": 4386 }, { "epoch": 0.72, "learning_rate": 1.9205814717477005e-05, "loss": 1.2265, "step": 4387 }, { "epoch": 0.72, "learning_rate": 1.9203350854139292e-05, "loss": 0.5249, "step": 4388 }, { "epoch": 0.72, "learning_rate": 1.9200886990801577e-05, "loss": 0.9671, "step": 4389 }, { "epoch": 0.72, "learning_rate": 1.9198423127463864e-05, "loss": 1.0358, "step": 4390 }, { "epoch": 0.72, "learning_rate": 1.9195959264126152e-05, "loss": 0.5939, "step": 4391 }, { "epoch": 0.72, "learning_rate": 1.9193495400788436e-05, "loss": 0.693, "step": 4392 }, { "epoch": 0.72, "learning_rate": 1.9191031537450724e-05, "loss": 0.9475, "step": 4393 }, { "epoch": 0.72, "learning_rate": 1.918856767411301e-05, "loss": 0.8523, "step": 4394 }, { "epoch": 0.72, "learning_rate": 1.9186103810775296e-05, "loss": 0.5548, "step": 4395 }, { "epoch": 0.72, "learning_rate": 1.918363994743758e-05, "loss": 0.6807, "step": 4396 }, { "epoch": 0.72, "learning_rate": 1.918117608409987e-05, "loss": 0.6607, "step": 4397 }, { "epoch": 0.72, "learning_rate": 1.9178712220762156e-05, "loss": 1.2393, "step": 4398 }, { "epoch": 0.72, "learning_rate": 1.9176248357424443e-05, "loss": 0.8723, "step": 4399 }, { "epoch": 0.72, "learning_rate": 1.9173784494086728e-05, "loss": 0.8859, "step": 4400 }, { "epoch": 0.72, "learning_rate": 1.9171320630749015e-05, "loss": 0.9668, "step": 4401 }, { "epoch": 0.72, "learning_rate": 1.91688567674113e-05, "loss": 1.0676, "step": 4402 }, { "epoch": 0.72, "learning_rate": 1.9166392904073587e-05, "loss": 0.7166, "step": 4403 }, { "epoch": 0.72, "learning_rate": 1.9163929040735875e-05, "loss": 0.5978, "step": 4404 }, { "epoch": 0.72, "learning_rate": 1.916146517739816e-05, "loss": 1.0376, "step": 4405 }, { "epoch": 0.72, "learning_rate": 1.9159001314060447e-05, "loss": 1.2037, "step": 4406 }, { "epoch": 0.72, "learning_rate": 1.9156537450722735e-05, "loss": 0.9724, "step": 4407 }, { "epoch": 0.72, "learning_rate": 1.9154073587385022e-05, "loss": 1.2791, "step": 4408 }, { "epoch": 0.72, "learning_rate": 1.9151609724047307e-05, "loss": 0.7038, "step": 4409 }, { "epoch": 0.72, "learning_rate": 1.9149145860709594e-05, "loss": 0.9167, "step": 4410 }, { "epoch": 0.72, "learning_rate": 1.914668199737188e-05, "loss": 0.6511, "step": 4411 }, { "epoch": 0.72, "learning_rate": 1.9144218134034166e-05, "loss": 0.6478, "step": 4412 }, { "epoch": 0.72, "learning_rate": 1.914175427069645e-05, "loss": 1.2444, "step": 4413 }, { "epoch": 0.73, "learning_rate": 1.9139290407358738e-05, "loss": 0.5599, "step": 4414 }, { "epoch": 0.73, "learning_rate": 1.9136826544021026e-05, "loss": 0.4468, "step": 4415 }, { "epoch": 0.73, "learning_rate": 1.913436268068331e-05, "loss": 0.5891, "step": 4416 }, { "epoch": 0.73, "learning_rate": 1.91318988173456e-05, "loss": 0.5788, "step": 4417 }, { "epoch": 0.73, "learning_rate": 1.9129434954007886e-05, "loss": 0.7723, "step": 4418 }, { "epoch": 0.73, "learning_rate": 1.9126971090670173e-05, "loss": 1.016, "step": 4419 }, { "epoch": 0.73, "learning_rate": 1.9124507227332458e-05, "loss": 0.7515, "step": 4420 }, { "epoch": 0.73, "learning_rate": 1.9122043363994745e-05, "loss": 1.1886, "step": 4421 }, { "epoch": 0.73, "learning_rate": 1.911957950065703e-05, "loss": 0.7597, "step": 4422 }, { "epoch": 0.73, "learning_rate": 1.9117115637319317e-05, "loss": 1.7922, "step": 4423 }, { "epoch": 0.73, "learning_rate": 1.91146517739816e-05, "loss": 0.6112, "step": 4424 }, { "epoch": 0.73, "learning_rate": 1.911218791064389e-05, "loss": 0.8857, "step": 4425 }, { "epoch": 0.73, "learning_rate": 1.9109724047306177e-05, "loss": 0.9622, "step": 4426 }, { "epoch": 0.73, "learning_rate": 1.9107260183968465e-05, "loss": 0.6275, "step": 4427 }, { "epoch": 0.73, "learning_rate": 1.9104796320630752e-05, "loss": 0.4944, "step": 4428 }, { "epoch": 0.73, "learning_rate": 1.9102332457293036e-05, "loss": 0.9552, "step": 4429 }, { "epoch": 0.73, "learning_rate": 1.9099868593955324e-05, "loss": 1.2501, "step": 4430 }, { "epoch": 0.73, "learning_rate": 1.909740473061761e-05, "loss": 0.7138, "step": 4431 }, { "epoch": 0.73, "learning_rate": 1.9094940867279896e-05, "loss": 1.7876, "step": 4432 }, { "epoch": 0.73, "learning_rate": 1.909247700394218e-05, "loss": 1.5456, "step": 4433 }, { "epoch": 0.73, "learning_rate": 1.9090013140604468e-05, "loss": 0.867, "step": 4434 }, { "epoch": 0.73, "learning_rate": 1.9087549277266752e-05, "loss": 0.446, "step": 4435 }, { "epoch": 0.73, "learning_rate": 1.908508541392904e-05, "loss": 0.8428, "step": 4436 }, { "epoch": 0.73, "learning_rate": 1.9082621550591328e-05, "loss": 0.8781, "step": 4437 }, { "epoch": 0.73, "learning_rate": 1.9080157687253615e-05, "loss": 0.7944, "step": 4438 }, { "epoch": 0.73, "learning_rate": 1.9077693823915903e-05, "loss": 0.5281, "step": 4439 }, { "epoch": 0.73, "learning_rate": 1.9075229960578187e-05, "loss": 0.7621, "step": 4440 }, { "epoch": 0.73, "learning_rate": 1.9072766097240475e-05, "loss": 0.4664, "step": 4441 }, { "epoch": 0.73, "learning_rate": 1.907030223390276e-05, "loss": 0.8339, "step": 4442 }, { "epoch": 0.73, "learning_rate": 1.9067838370565047e-05, "loss": 1.1163, "step": 4443 }, { "epoch": 0.73, "learning_rate": 1.906537450722733e-05, "loss": 0.7728, "step": 4444 }, { "epoch": 0.73, "learning_rate": 1.906291064388962e-05, "loss": 0.6391, "step": 4445 }, { "epoch": 0.73, "learning_rate": 1.9060446780551903e-05, "loss": 0.8323, "step": 4446 }, { "epoch": 0.73, "learning_rate": 1.9057982917214194e-05, "loss": 0.3932, "step": 4447 }, { "epoch": 0.73, "learning_rate": 1.905551905387648e-05, "loss": 0.7471, "step": 4448 }, { "epoch": 0.73, "learning_rate": 1.9053055190538766e-05, "loss": 0.5786, "step": 4449 }, { "epoch": 0.73, "learning_rate": 1.9050591327201054e-05, "loss": 0.841, "step": 4450 }, { "epoch": 0.73, "learning_rate": 1.904812746386334e-05, "loss": 0.5946, "step": 4451 }, { "epoch": 0.73, "learning_rate": 1.9045663600525626e-05, "loss": 0.539, "step": 4452 }, { "epoch": 0.73, "learning_rate": 1.904319973718791e-05, "loss": 1.6914, "step": 4453 }, { "epoch": 0.73, "learning_rate": 1.9040735873850198e-05, "loss": 1.4488, "step": 4454 }, { "epoch": 0.73, "learning_rate": 1.9038272010512482e-05, "loss": 1.1514, "step": 4455 }, { "epoch": 0.73, "learning_rate": 1.903580814717477e-05, "loss": 0.4048, "step": 4456 }, { "epoch": 0.73, "learning_rate": 1.9033344283837058e-05, "loss": 0.2884, "step": 4457 }, { "epoch": 0.73, "learning_rate": 1.9030880420499345e-05, "loss": 0.7279, "step": 4458 }, { "epoch": 0.73, "learning_rate": 1.902841655716163e-05, "loss": 1.1549, "step": 4459 }, { "epoch": 0.73, "learning_rate": 1.9025952693823917e-05, "loss": 0.757, "step": 4460 }, { "epoch": 0.73, "learning_rate": 1.90234888304862e-05, "loss": 0.5258, "step": 4461 }, { "epoch": 0.73, "learning_rate": 1.902102496714849e-05, "loss": 0.682, "step": 4462 }, { "epoch": 0.73, "learning_rate": 1.9018561103810777e-05, "loss": 1.18, "step": 4463 }, { "epoch": 0.73, "learning_rate": 1.901609724047306e-05, "loss": 1.0187, "step": 4464 }, { "epoch": 0.73, "learning_rate": 1.901363337713535e-05, "loss": 0.2505, "step": 4465 }, { "epoch": 0.73, "learning_rate": 1.9011169513797633e-05, "loss": 0.5687, "step": 4466 }, { "epoch": 0.73, "learning_rate": 1.9008705650459924e-05, "loss": 0.3076, "step": 4467 }, { "epoch": 0.73, "learning_rate": 1.900624178712221e-05, "loss": 0.8699, "step": 4468 }, { "epoch": 0.73, "learning_rate": 1.9003777923784496e-05, "loss": 1.0848, "step": 4469 }, { "epoch": 0.73, "learning_rate": 1.900131406044678e-05, "loss": 0.5785, "step": 4470 }, { "epoch": 0.73, "learning_rate": 1.8998850197109068e-05, "loss": 0.709, "step": 4471 }, { "epoch": 0.73, "learning_rate": 1.8996386333771352e-05, "loss": 1.395, "step": 4472 }, { "epoch": 0.73, "learning_rate": 1.899392247043364e-05, "loss": 0.3602, "step": 4473 }, { "epoch": 0.73, "learning_rate": 1.8991458607095928e-05, "loss": 0.7515, "step": 4474 }, { "epoch": 0.74, "learning_rate": 1.8988994743758212e-05, "loss": 0.9316, "step": 4475 }, { "epoch": 0.74, "learning_rate": 1.89865308804205e-05, "loss": 0.3789, "step": 4476 }, { "epoch": 0.74, "learning_rate": 1.8984067017082787e-05, "loss": 1.4996, "step": 4477 }, { "epoch": 0.74, "learning_rate": 1.8981603153745075e-05, "loss": 0.7007, "step": 4478 }, { "epoch": 0.74, "learning_rate": 1.897913929040736e-05, "loss": 0.2552, "step": 4479 }, { "epoch": 0.74, "learning_rate": 1.8976675427069647e-05, "loss": 0.6415, "step": 4480 }, { "epoch": 0.74, "learning_rate": 1.897421156373193e-05, "loss": 0.7727, "step": 4481 }, { "epoch": 0.74, "learning_rate": 1.897174770039422e-05, "loss": 1.5601, "step": 4482 }, { "epoch": 0.74, "learning_rate": 1.8969283837056503e-05, "loss": 0.7029, "step": 4483 }, { "epoch": 0.74, "learning_rate": 1.896681997371879e-05, "loss": 0.5951, "step": 4484 }, { "epoch": 0.74, "learning_rate": 1.8964356110381075e-05, "loss": 0.6541, "step": 4485 }, { "epoch": 0.74, "learning_rate": 1.8961892247043363e-05, "loss": 0.8319, "step": 4486 }, { "epoch": 0.74, "learning_rate": 1.8959428383705654e-05, "loss": 0.9567, "step": 4487 }, { "epoch": 0.74, "learning_rate": 1.895696452036794e-05, "loss": 0.4944, "step": 4488 }, { "epoch": 0.74, "learning_rate": 1.8954500657030226e-05, "loss": 0.8237, "step": 4489 }, { "epoch": 0.74, "learning_rate": 1.895203679369251e-05, "loss": 0.6645, "step": 4490 }, { "epoch": 0.74, "learning_rate": 1.8949572930354798e-05, "loss": 0.2653, "step": 4491 }, { "epoch": 0.74, "learning_rate": 1.8947109067017082e-05, "loss": 0.7368, "step": 4492 }, { "epoch": 0.74, "learning_rate": 1.894464520367937e-05, "loss": 0.416, "step": 4493 }, { "epoch": 0.74, "learning_rate": 1.8942181340341654e-05, "loss": 1.3195, "step": 4494 }, { "epoch": 0.74, "learning_rate": 1.8939717477003942e-05, "loss": 1.371, "step": 4495 }, { "epoch": 0.74, "learning_rate": 1.8937253613666226e-05, "loss": 0.614, "step": 4496 }, { "epoch": 0.74, "learning_rate": 1.8934789750328517e-05, "loss": 1.1754, "step": 4497 }, { "epoch": 0.74, "learning_rate": 1.8932325886990805e-05, "loss": 1.0223, "step": 4498 }, { "epoch": 0.74, "learning_rate": 1.892986202365309e-05, "loss": 0.977, "step": 4499 }, { "epoch": 0.74, "learning_rate": 1.8927398160315377e-05, "loss": 0.2665, "step": 4500 }, { "epoch": 0.74, "eval_exact_match": 86.0643330179754, "eval_f1": 92.47373436949556, "step": 4500 }, { "epoch": 0.74, "learning_rate": 1.892493429697766e-05, "loss": 0.6299, "step": 4501 }, { "epoch": 0.74, "learning_rate": 1.892247043363995e-05, "loss": 1.8402, "step": 4502 }, { "epoch": 0.74, "learning_rate": 1.8920006570302233e-05, "loss": 0.6971, "step": 4503 }, { "epoch": 0.74, "learning_rate": 1.891754270696452e-05, "loss": 0.8395, "step": 4504 }, { "epoch": 0.74, "learning_rate": 1.8915078843626805e-05, "loss": 1.1836, "step": 4505 }, { "epoch": 0.74, "learning_rate": 1.8912614980289093e-05, "loss": 0.5312, "step": 4506 }, { "epoch": 0.74, "learning_rate": 1.891015111695138e-05, "loss": 1.0785, "step": 4507 }, { "epoch": 0.74, "learning_rate": 1.8907687253613668e-05, "loss": 0.5971, "step": 4508 }, { "epoch": 0.74, "learning_rate": 1.8905223390275953e-05, "loss": 0.7465, "step": 4509 }, { "epoch": 0.74, "learning_rate": 1.890275952693824e-05, "loss": 0.5111, "step": 4510 }, { "epoch": 0.74, "learning_rate": 1.8900295663600528e-05, "loss": 1.0242, "step": 4511 }, { "epoch": 0.74, "learning_rate": 1.8897831800262812e-05, "loss": 0.9528, "step": 4512 }, { "epoch": 0.74, "learning_rate": 1.88953679369251e-05, "loss": 0.6033, "step": 4513 }, { "epoch": 0.74, "learning_rate": 1.8892904073587384e-05, "loss": 0.5944, "step": 4514 }, { "epoch": 0.74, "learning_rate": 1.8890440210249672e-05, "loss": 1.488, "step": 4515 }, { "epoch": 0.74, "learning_rate": 1.8887976346911956e-05, "loss": 0.5502, "step": 4516 }, { "epoch": 0.74, "learning_rate": 1.8885512483574247e-05, "loss": 0.2522, "step": 4517 }, { "epoch": 0.74, "learning_rate": 1.888304862023653e-05, "loss": 0.5721, "step": 4518 }, { "epoch": 0.74, "learning_rate": 1.888058475689882e-05, "loss": 0.8577, "step": 4519 }, { "epoch": 0.74, "learning_rate": 1.8878120893561103e-05, "loss": 1.1416, "step": 4520 }, { "epoch": 0.74, "learning_rate": 1.887565703022339e-05, "loss": 0.9019, "step": 4521 }, { "epoch": 0.74, "learning_rate": 1.887319316688568e-05, "loss": 0.846, "step": 4522 }, { "epoch": 0.74, "learning_rate": 1.8870729303547963e-05, "loss": 1.0642, "step": 4523 }, { "epoch": 0.74, "learning_rate": 1.886826544021025e-05, "loss": 1.3879, "step": 4524 }, { "epoch": 0.74, "learning_rate": 1.8865801576872535e-05, "loss": 0.7002, "step": 4525 }, { "epoch": 0.74, "learning_rate": 1.8863337713534823e-05, "loss": 0.5642, "step": 4526 }, { "epoch": 0.74, "learning_rate": 1.886087385019711e-05, "loss": 0.6477, "step": 4527 }, { "epoch": 0.74, "learning_rate": 1.8858409986859398e-05, "loss": 1.12, "step": 4528 }, { "epoch": 0.74, "learning_rate": 1.8855946123521682e-05, "loss": 0.8221, "step": 4529 }, { "epoch": 0.74, "learning_rate": 1.885348226018397e-05, "loss": 0.8624, "step": 4530 }, { "epoch": 0.74, "learning_rate": 1.8851018396846254e-05, "loss": 1.0426, "step": 4531 }, { "epoch": 0.74, "learning_rate": 1.8848554533508542e-05, "loss": 1.6596, "step": 4532 }, { "epoch": 0.74, "learning_rate": 1.8846090670170826e-05, "loss": 1.0016, "step": 4533 }, { "epoch": 0.74, "learning_rate": 1.8843626806833114e-05, "loss": 0.6549, "step": 4534 }, { "epoch": 0.74, "learning_rate": 1.88411629434954e-05, "loss": 0.4008, "step": 4535 }, { "epoch": 0.75, "learning_rate": 1.8838699080157686e-05, "loss": 0.4554, "step": 4536 }, { "epoch": 0.75, "learning_rate": 1.8836235216819977e-05, "loss": 0.659, "step": 4537 }, { "epoch": 0.75, "learning_rate": 1.883377135348226e-05, "loss": 1.1455, "step": 4538 }, { "epoch": 0.75, "learning_rate": 1.883130749014455e-05, "loss": 0.6073, "step": 4539 }, { "epoch": 0.75, "learning_rate": 1.8828843626806833e-05, "loss": 0.6279, "step": 4540 }, { "epoch": 0.75, "learning_rate": 1.882637976346912e-05, "loss": 0.9272, "step": 4541 }, { "epoch": 0.75, "learning_rate": 1.8823915900131405e-05, "loss": 0.6358, "step": 4542 }, { "epoch": 0.75, "learning_rate": 1.8821452036793693e-05, "loss": 0.8671, "step": 4543 }, { "epoch": 0.75, "learning_rate": 1.8818988173455977e-05, "loss": 1.4483, "step": 4544 }, { "epoch": 0.75, "learning_rate": 1.8816524310118265e-05, "loss": 0.4435, "step": 4545 }, { "epoch": 0.75, "learning_rate": 1.8814060446780553e-05, "loss": 0.7515, "step": 4546 }, { "epoch": 0.75, "learning_rate": 1.881159658344284e-05, "loss": 0.6161, "step": 4547 }, { "epoch": 0.75, "learning_rate": 1.8809132720105128e-05, "loss": 1.0277, "step": 4548 }, { "epoch": 0.75, "learning_rate": 1.8806668856767412e-05, "loss": 0.9908, "step": 4549 }, { "epoch": 0.75, "learning_rate": 1.88042049934297e-05, "loss": 0.5659, "step": 4550 }, { "epoch": 0.75, "learning_rate": 1.8801741130091984e-05, "loss": 0.908, "step": 4551 }, { "epoch": 0.75, "learning_rate": 1.8799277266754272e-05, "loss": 0.7876, "step": 4552 }, { "epoch": 0.75, "learning_rate": 1.8796813403416556e-05, "loss": 0.8215, "step": 4553 }, { "epoch": 0.75, "learning_rate": 1.8794349540078844e-05, "loss": 0.9602, "step": 4554 }, { "epoch": 0.75, "learning_rate": 1.8791885676741128e-05, "loss": 0.7709, "step": 4555 }, { "epoch": 0.75, "learning_rate": 1.8789421813403416e-05, "loss": 0.3677, "step": 4556 }, { "epoch": 0.75, "learning_rate": 1.8786957950065704e-05, "loss": 0.9519, "step": 4557 }, { "epoch": 0.75, "learning_rate": 1.878449408672799e-05, "loss": 0.8943, "step": 4558 }, { "epoch": 0.75, "learning_rate": 1.878203022339028e-05, "loss": 0.4725, "step": 4559 }, { "epoch": 0.75, "learning_rate": 1.8779566360052563e-05, "loss": 0.8205, "step": 4560 }, { "epoch": 0.75, "learning_rate": 1.877710249671485e-05, "loss": 0.419, "step": 4561 }, { "epoch": 0.75, "learning_rate": 1.8774638633377135e-05, "loss": 0.6836, "step": 4562 }, { "epoch": 0.75, "learning_rate": 1.8772174770039423e-05, "loss": 1.6459, "step": 4563 }, { "epoch": 0.75, "learning_rate": 1.8769710906701707e-05, "loss": 0.9099, "step": 4564 }, { "epoch": 0.75, "learning_rate": 1.8767247043363995e-05, "loss": 0.7517, "step": 4565 }, { "epoch": 0.75, "learning_rate": 1.876478318002628e-05, "loss": 0.469, "step": 4566 }, { "epoch": 0.75, "learning_rate": 1.876231931668857e-05, "loss": 0.7562, "step": 4567 }, { "epoch": 0.75, "learning_rate": 1.8759855453350854e-05, "loss": 1.1285, "step": 4568 }, { "epoch": 0.75, "learning_rate": 1.8757391590013142e-05, "loss": 0.4182, "step": 4569 }, { "epoch": 0.75, "learning_rate": 1.875492772667543e-05, "loss": 0.5978, "step": 4570 }, { "epoch": 0.75, "learning_rate": 1.8752463863337714e-05, "loss": 0.889, "step": 4571 }, { "epoch": 0.75, "learning_rate": 1.8750000000000002e-05, "loss": 1.2932, "step": 4572 }, { "epoch": 0.75, "learning_rate": 1.8747536136662286e-05, "loss": 0.4328, "step": 4573 }, { "epoch": 0.75, "learning_rate": 1.8745072273324574e-05, "loss": 1.1506, "step": 4574 }, { "epoch": 0.75, "learning_rate": 1.8742608409986858e-05, "loss": 1.2444, "step": 4575 }, { "epoch": 0.75, "learning_rate": 1.8740144546649146e-05, "loss": 1.718, "step": 4576 }, { "epoch": 0.75, "learning_rate": 1.873768068331143e-05, "loss": 0.6271, "step": 4577 }, { "epoch": 0.75, "learning_rate": 1.873521681997372e-05, "loss": 0.8106, "step": 4578 }, { "epoch": 0.75, "learning_rate": 1.8732752956636005e-05, "loss": 0.7883, "step": 4579 }, { "epoch": 0.75, "learning_rate": 1.8730289093298293e-05, "loss": 1.0881, "step": 4580 }, { "epoch": 0.75, "learning_rate": 1.872782522996058e-05, "loss": 0.84, "step": 4581 }, { "epoch": 0.75, "learning_rate": 1.8725361366622865e-05, "loss": 0.6029, "step": 4582 }, { "epoch": 0.75, "learning_rate": 1.8722897503285153e-05, "loss": 0.6173, "step": 4583 }, { "epoch": 0.75, "learning_rate": 1.8720433639947437e-05, "loss": 0.785, "step": 4584 }, { "epoch": 0.75, "learning_rate": 1.8717969776609725e-05, "loss": 1.0521, "step": 4585 }, { "epoch": 0.75, "learning_rate": 1.871550591327201e-05, "loss": 0.8593, "step": 4586 }, { "epoch": 0.75, "learning_rate": 1.8713042049934297e-05, "loss": 0.9857, "step": 4587 }, { "epoch": 0.75, "learning_rate": 1.8710578186596584e-05, "loss": 0.7005, "step": 4588 }, { "epoch": 0.75, "learning_rate": 1.8708114323258872e-05, "loss": 0.3422, "step": 4589 }, { "epoch": 0.75, "learning_rate": 1.8705650459921156e-05, "loss": 0.1917, "step": 4590 }, { "epoch": 0.75, "learning_rate": 1.8703186596583444e-05, "loss": 1.0141, "step": 4591 }, { "epoch": 0.75, "learning_rate": 1.8700722733245728e-05, "loss": 0.642, "step": 4592 }, { "epoch": 0.75, "learning_rate": 1.8698258869908016e-05, "loss": 0.7458, "step": 4593 }, { "epoch": 0.75, "learning_rate": 1.8695795006570304e-05, "loss": 1.1564, "step": 4594 }, { "epoch": 0.75, "learning_rate": 1.8693331143232588e-05, "loss": 0.8271, "step": 4595 }, { "epoch": 0.75, "learning_rate": 1.8690867279894876e-05, "loss": 1.1859, "step": 4596 }, { "epoch": 0.76, "learning_rate": 1.868840341655716e-05, "loss": 0.4717, "step": 4597 }, { "epoch": 0.76, "learning_rate": 1.868593955321945e-05, "loss": 1.1006, "step": 4598 }, { "epoch": 0.76, "learning_rate": 1.8683475689881735e-05, "loss": 0.7807, "step": 4599 }, { "epoch": 0.76, "learning_rate": 1.8681011826544023e-05, "loss": 0.2498, "step": 4600 }, { "epoch": 0.76, "learning_rate": 1.8678547963206307e-05, "loss": 0.5191, "step": 4601 }, { "epoch": 0.76, "learning_rate": 1.8676084099868595e-05, "loss": 0.5577, "step": 4602 }, { "epoch": 0.76, "learning_rate": 1.867362023653088e-05, "loss": 0.4049, "step": 4603 }, { "epoch": 0.76, "learning_rate": 1.8671156373193167e-05, "loss": 0.4558, "step": 4604 }, { "epoch": 0.76, "learning_rate": 1.8668692509855454e-05, "loss": 1.0448, "step": 4605 }, { "epoch": 0.76, "learning_rate": 1.866622864651774e-05, "loss": 0.379, "step": 4606 }, { "epoch": 0.76, "learning_rate": 1.8663764783180026e-05, "loss": 0.4762, "step": 4607 }, { "epoch": 0.76, "learning_rate": 1.8661300919842314e-05, "loss": 0.6386, "step": 4608 }, { "epoch": 0.76, "learning_rate": 1.8658837056504602e-05, "loss": 0.74, "step": 4609 }, { "epoch": 0.76, "learning_rate": 1.8656373193166886e-05, "loss": 0.6774, "step": 4610 }, { "epoch": 0.76, "learning_rate": 1.8653909329829174e-05, "loss": 0.9357, "step": 4611 }, { "epoch": 0.76, "learning_rate": 1.8651445466491458e-05, "loss": 1.3134, "step": 4612 }, { "epoch": 0.76, "learning_rate": 1.8648981603153746e-05, "loss": 0.5077, "step": 4613 }, { "epoch": 0.76, "learning_rate": 1.864651773981603e-05, "loss": 0.2659, "step": 4614 }, { "epoch": 0.76, "learning_rate": 1.8644053876478318e-05, "loss": 0.7142, "step": 4615 }, { "epoch": 0.76, "learning_rate": 1.8641590013140602e-05, "loss": 0.7645, "step": 4616 }, { "epoch": 0.76, "learning_rate": 1.863912614980289e-05, "loss": 0.7515, "step": 4617 }, { "epoch": 0.76, "learning_rate": 1.863666228646518e-05, "loss": 0.8986, "step": 4618 }, { "epoch": 0.76, "learning_rate": 1.8634198423127465e-05, "loss": 0.754, "step": 4619 }, { "epoch": 0.76, "learning_rate": 1.8631734559789753e-05, "loss": 0.9973, "step": 4620 }, { "epoch": 0.76, "learning_rate": 1.8629270696452037e-05, "loss": 0.3208, "step": 4621 }, { "epoch": 0.76, "learning_rate": 1.8626806833114325e-05, "loss": 0.6768, "step": 4622 }, { "epoch": 0.76, "learning_rate": 1.862434296977661e-05, "loss": 1.1973, "step": 4623 }, { "epoch": 0.76, "learning_rate": 1.8621879106438897e-05, "loss": 0.6321, "step": 4624 }, { "epoch": 0.76, "learning_rate": 1.861941524310118e-05, "loss": 0.5447, "step": 4625 }, { "epoch": 0.76, "learning_rate": 1.861695137976347e-05, "loss": 0.4209, "step": 4626 }, { "epoch": 0.76, "learning_rate": 1.8614487516425753e-05, "loss": 1.2287, "step": 4627 }, { "epoch": 0.76, "learning_rate": 1.8612023653088044e-05, "loss": 0.4132, "step": 4628 }, { "epoch": 0.76, "learning_rate": 1.860955978975033e-05, "loss": 0.4159, "step": 4629 }, { "epoch": 0.76, "learning_rate": 1.8607095926412616e-05, "loss": 0.6526, "step": 4630 }, { "epoch": 0.76, "learning_rate": 1.8604632063074904e-05, "loss": 1.2, "step": 4631 }, { "epoch": 0.76, "learning_rate": 1.8602168199737188e-05, "loss": 0.623, "step": 4632 }, { "epoch": 0.76, "learning_rate": 1.8599704336399476e-05, "loss": 0.9512, "step": 4633 }, { "epoch": 0.76, "learning_rate": 1.859724047306176e-05, "loss": 1.2566, "step": 4634 }, { "epoch": 0.76, "learning_rate": 1.8594776609724048e-05, "loss": 0.5498, "step": 4635 }, { "epoch": 0.76, "learning_rate": 1.8592312746386332e-05, "loss": 1.1905, "step": 4636 }, { "epoch": 0.76, "learning_rate": 1.858984888304862e-05, "loss": 0.752, "step": 4637 }, { "epoch": 0.76, "learning_rate": 1.8587385019710907e-05, "loss": 0.787, "step": 4638 }, { "epoch": 0.76, "learning_rate": 1.8584921156373195e-05, "loss": 0.4391, "step": 4639 }, { "epoch": 0.76, "learning_rate": 1.858245729303548e-05, "loss": 0.9851, "step": 4640 }, { "epoch": 0.76, "learning_rate": 1.8579993429697767e-05, "loss": 1.1051, "step": 4641 }, { "epoch": 0.76, "learning_rate": 1.8577529566360055e-05, "loss": 0.8987, "step": 4642 }, { "epoch": 0.76, "learning_rate": 1.857506570302234e-05, "loss": 0.9341, "step": 4643 }, { "epoch": 0.76, "learning_rate": 1.8572601839684627e-05, "loss": 0.7661, "step": 4644 }, { "epoch": 0.76, "learning_rate": 1.857013797634691e-05, "loss": 0.8723, "step": 4645 }, { "epoch": 0.76, "learning_rate": 1.85676741130092e-05, "loss": 0.7204, "step": 4646 }, { "epoch": 0.76, "learning_rate": 1.8565210249671483e-05, "loss": 0.9174, "step": 4647 }, { "epoch": 0.76, "learning_rate": 1.8562746386333774e-05, "loss": 0.5145, "step": 4648 }, { "epoch": 0.76, "learning_rate": 1.8560282522996058e-05, "loss": 0.4395, "step": 4649 }, { "epoch": 0.76, "learning_rate": 1.8557818659658346e-05, "loss": 1.2353, "step": 4650 }, { "epoch": 0.76, "learning_rate": 1.855535479632063e-05, "loss": 1.0995, "step": 4651 }, { "epoch": 0.76, "learning_rate": 1.8552890932982918e-05, "loss": 0.5314, "step": 4652 }, { "epoch": 0.76, "learning_rate": 1.8550427069645205e-05, "loss": 0.475, "step": 4653 }, { "epoch": 0.76, "learning_rate": 1.854796320630749e-05, "loss": 0.5843, "step": 4654 }, { "epoch": 0.76, "learning_rate": 1.8545499342969777e-05, "loss": 0.9184, "step": 4655 }, { "epoch": 0.76, "learning_rate": 1.8543035479632062e-05, "loss": 0.7766, "step": 4656 }, { "epoch": 0.76, "learning_rate": 1.854057161629435e-05, "loss": 0.8079, "step": 4657 }, { "epoch": 0.77, "learning_rate": 1.8538107752956637e-05, "loss": 0.8165, "step": 4658 }, { "epoch": 0.77, "learning_rate": 1.8535643889618925e-05, "loss": 1.0574, "step": 4659 }, { "epoch": 0.77, "learning_rate": 1.853318002628121e-05, "loss": 1.1335, "step": 4660 }, { "epoch": 0.77, "learning_rate": 1.8530716162943497e-05, "loss": 0.7955, "step": 4661 }, { "epoch": 0.77, "learning_rate": 1.852825229960578e-05, "loss": 1.0489, "step": 4662 }, { "epoch": 0.77, "learning_rate": 1.852578843626807e-05, "loss": 0.7514, "step": 4663 }, { "epoch": 0.77, "learning_rate": 1.8523324572930353e-05, "loss": 0.5131, "step": 4664 }, { "epoch": 0.77, "learning_rate": 1.852086070959264e-05, "loss": 0.4925, "step": 4665 }, { "epoch": 0.77, "learning_rate": 1.851839684625493e-05, "loss": 1.1012, "step": 4666 }, { "epoch": 0.77, "learning_rate": 1.8515932982917213e-05, "loss": 0.8055, "step": 4667 }, { "epoch": 0.77, "learning_rate": 1.8513469119579504e-05, "loss": 0.8073, "step": 4668 }, { "epoch": 0.77, "learning_rate": 1.8511005256241788e-05, "loss": 0.7564, "step": 4669 }, { "epoch": 0.77, "learning_rate": 1.8508541392904076e-05, "loss": 1.2258, "step": 4670 }, { "epoch": 0.77, "learning_rate": 1.850607752956636e-05, "loss": 1.0015, "step": 4671 }, { "epoch": 0.77, "learning_rate": 1.8503613666228648e-05, "loss": 0.3756, "step": 4672 }, { "epoch": 0.77, "learning_rate": 1.8501149802890932e-05, "loss": 0.9714, "step": 4673 }, { "epoch": 0.77, "learning_rate": 1.849868593955322e-05, "loss": 0.4009, "step": 4674 }, { "epoch": 0.77, "learning_rate": 1.8496222076215504e-05, "loss": 0.7959, "step": 4675 }, { "epoch": 0.77, "learning_rate": 1.849375821287779e-05, "loss": 0.7377, "step": 4676 }, { "epoch": 0.77, "learning_rate": 1.849129434954008e-05, "loss": 0.6871, "step": 4677 }, { "epoch": 0.77, "learning_rate": 1.8488830486202367e-05, "loss": 0.6908, "step": 4678 }, { "epoch": 0.77, "learning_rate": 1.8486366622864655e-05, "loss": 0.5829, "step": 4679 }, { "epoch": 0.77, "learning_rate": 1.848390275952694e-05, "loss": 1.0338, "step": 4680 }, { "epoch": 0.77, "learning_rate": 1.8481438896189227e-05, "loss": 1.111, "step": 4681 }, { "epoch": 0.77, "learning_rate": 1.847897503285151e-05, "loss": 0.8007, "step": 4682 }, { "epoch": 0.77, "learning_rate": 1.84765111695138e-05, "loss": 0.5091, "step": 4683 }, { "epoch": 0.77, "learning_rate": 1.8474047306176083e-05, "loss": 0.5157, "step": 4684 }, { "epoch": 0.77, "learning_rate": 1.847158344283837e-05, "loss": 0.8569, "step": 4685 }, { "epoch": 0.77, "learning_rate": 1.8469119579500655e-05, "loss": 0.4489, "step": 4686 }, { "epoch": 0.77, "learning_rate": 1.8466655716162942e-05, "loss": 0.7325, "step": 4687 }, { "epoch": 0.77, "learning_rate": 1.846419185282523e-05, "loss": 0.835, "step": 4688 }, { "epoch": 0.77, "learning_rate": 1.8461727989487518e-05, "loss": 0.596, "step": 4689 }, { "epoch": 0.77, "learning_rate": 1.8459264126149806e-05, "loss": 0.3558, "step": 4690 }, { "epoch": 0.77, "learning_rate": 1.845680026281209e-05, "loss": 0.7248, "step": 4691 }, { "epoch": 0.77, "learning_rate": 1.8454336399474377e-05, "loss": 1.0667, "step": 4692 }, { "epoch": 0.77, "learning_rate": 1.8451872536136662e-05, "loss": 0.7647, "step": 4693 }, { "epoch": 0.77, "learning_rate": 1.844940867279895e-05, "loss": 0.8323, "step": 4694 }, { "epoch": 0.77, "learning_rate": 1.8446944809461234e-05, "loss": 0.6503, "step": 4695 }, { "epoch": 0.77, "learning_rate": 1.844448094612352e-05, "loss": 0.7961, "step": 4696 }, { "epoch": 0.77, "learning_rate": 1.8442017082785806e-05, "loss": 1.0635, "step": 4697 }, { "epoch": 0.77, "learning_rate": 1.8439553219448097e-05, "loss": 0.88, "step": 4698 }, { "epoch": 0.77, "learning_rate": 1.843708935611038e-05, "loss": 0.5759, "step": 4699 }, { "epoch": 0.77, "learning_rate": 1.843462549277267e-05, "loss": 0.4959, "step": 4700 }, { "epoch": 0.77, "learning_rate": 1.8432161629434956e-05, "loss": 0.7436, "step": 4701 }, { "epoch": 0.77, "learning_rate": 1.842969776609724e-05, "loss": 0.3615, "step": 4702 }, { "epoch": 0.77, "learning_rate": 1.842723390275953e-05, "loss": 1.114, "step": 4703 }, { "epoch": 0.77, "learning_rate": 1.8424770039421813e-05, "loss": 0.4554, "step": 4704 }, { "epoch": 0.77, "learning_rate": 1.84223061760841e-05, "loss": 0.7441, "step": 4705 }, { "epoch": 0.77, "learning_rate": 1.8419842312746385e-05, "loss": 0.528, "step": 4706 }, { "epoch": 0.77, "learning_rate": 1.8417378449408672e-05, "loss": 1.1655, "step": 4707 }, { "epoch": 0.77, "learning_rate": 1.841491458607096e-05, "loss": 1.5331, "step": 4708 }, { "epoch": 0.77, "learning_rate": 1.8412450722733248e-05, "loss": 0.8991, "step": 4709 }, { "epoch": 0.77, "learning_rate": 1.8409986859395532e-05, "loss": 1.2999, "step": 4710 }, { "epoch": 0.77, "learning_rate": 1.840752299605782e-05, "loss": 1.0482, "step": 4711 }, { "epoch": 0.77, "learning_rate": 1.8405059132720107e-05, "loss": 0.8403, "step": 4712 }, { "epoch": 0.77, "learning_rate": 1.840259526938239e-05, "loss": 0.5891, "step": 4713 }, { "epoch": 0.77, "learning_rate": 1.840013140604468e-05, "loss": 1.1156, "step": 4714 }, { "epoch": 0.77, "learning_rate": 1.8397667542706964e-05, "loss": 0.6798, "step": 4715 }, { "epoch": 0.77, "learning_rate": 1.839520367936925e-05, "loss": 0.948, "step": 4716 }, { "epoch": 0.77, "learning_rate": 1.8392739816031536e-05, "loss": 0.917, "step": 4717 }, { "epoch": 0.77, "learning_rate": 1.8390275952693827e-05, "loss": 0.6004, "step": 4718 }, { "epoch": 0.78, "learning_rate": 1.838781208935611e-05, "loss": 0.5993, "step": 4719 }, { "epoch": 0.78, "learning_rate": 1.83853482260184e-05, "loss": 1.3618, "step": 4720 }, { "epoch": 0.78, "learning_rate": 1.8382884362680683e-05, "loss": 0.2299, "step": 4721 }, { "epoch": 0.78, "learning_rate": 1.838042049934297e-05, "loss": 0.71, "step": 4722 }, { "epoch": 0.78, "learning_rate": 1.8377956636005255e-05, "loss": 0.8216, "step": 4723 }, { "epoch": 0.78, "learning_rate": 1.8375492772667543e-05, "loss": 1.0605, "step": 4724 }, { "epoch": 0.78, "learning_rate": 1.837302890932983e-05, "loss": 0.7678, "step": 4725 }, { "epoch": 0.78, "learning_rate": 1.8370565045992115e-05, "loss": 0.6637, "step": 4726 }, { "epoch": 0.78, "learning_rate": 1.8368101182654402e-05, "loss": 0.7725, "step": 4727 }, { "epoch": 0.78, "learning_rate": 1.836563731931669e-05, "loss": 0.6137, "step": 4728 }, { "epoch": 0.78, "learning_rate": 1.8363173455978978e-05, "loss": 0.41, "step": 4729 }, { "epoch": 0.78, "learning_rate": 1.8360709592641262e-05, "loss": 1.0792, "step": 4730 }, { "epoch": 0.78, "learning_rate": 1.835824572930355e-05, "loss": 0.9931, "step": 4731 }, { "epoch": 0.78, "learning_rate": 1.8355781865965834e-05, "loss": 1.2387, "step": 4732 }, { "epoch": 0.78, "learning_rate": 1.835331800262812e-05, "loss": 0.4493, "step": 4733 }, { "epoch": 0.78, "learning_rate": 1.8350854139290406e-05, "loss": 0.6957, "step": 4734 }, { "epoch": 0.78, "learning_rate": 1.8348390275952693e-05, "loss": 0.4489, "step": 4735 }, { "epoch": 0.78, "learning_rate": 1.834592641261498e-05, "loss": 0.6171, "step": 4736 }, { "epoch": 0.78, "learning_rate": 1.8343462549277265e-05, "loss": 0.4104, "step": 4737 }, { "epoch": 0.78, "learning_rate": 1.8340998685939556e-05, "loss": 0.449, "step": 4738 }, { "epoch": 0.78, "learning_rate": 1.833853482260184e-05, "loss": 0.4861, "step": 4739 }, { "epoch": 0.78, "learning_rate": 1.833607095926413e-05, "loss": 0.5628, "step": 4740 }, { "epoch": 0.78, "learning_rate": 1.8333607095926413e-05, "loss": 1.9375, "step": 4741 }, { "epoch": 0.78, "learning_rate": 1.83311432325887e-05, "loss": 1.0447, "step": 4742 }, { "epoch": 0.78, "learning_rate": 1.8328679369250985e-05, "loss": 1.1689, "step": 4743 }, { "epoch": 0.78, "learning_rate": 1.8326215505913272e-05, "loss": 0.9022, "step": 4744 }, { "epoch": 0.78, "learning_rate": 1.8323751642575557e-05, "loss": 0.2864, "step": 4745 }, { "epoch": 0.78, "learning_rate": 1.8321287779237844e-05, "loss": 1.0263, "step": 4746 }, { "epoch": 0.78, "learning_rate": 1.831882391590013e-05, "loss": 0.7579, "step": 4747 }, { "epoch": 0.78, "learning_rate": 1.831636005256242e-05, "loss": 1.1206, "step": 4748 }, { "epoch": 0.78, "learning_rate": 1.8313896189224707e-05, "loss": 1.1163, "step": 4749 }, { "epoch": 0.78, "learning_rate": 1.8311432325886992e-05, "loss": 0.4554, "step": 4750 }, { "epoch": 0.78, "learning_rate": 1.830896846254928e-05, "loss": 0.6967, "step": 4751 }, { "epoch": 0.78, "learning_rate": 1.8306504599211564e-05, "loss": 1.3669, "step": 4752 }, { "epoch": 0.78, "learning_rate": 1.830404073587385e-05, "loss": 0.9939, "step": 4753 }, { "epoch": 0.78, "learning_rate": 1.8301576872536136e-05, "loss": 0.6757, "step": 4754 }, { "epoch": 0.78, "learning_rate": 1.8299113009198423e-05, "loss": 0.4131, "step": 4755 }, { "epoch": 0.78, "learning_rate": 1.8296649145860708e-05, "loss": 0.4582, "step": 4756 }, { "epoch": 0.78, "learning_rate": 1.8294185282522995e-05, "loss": 0.378, "step": 4757 }, { "epoch": 0.78, "learning_rate": 1.8291721419185283e-05, "loss": 1.3108, "step": 4758 }, { "epoch": 0.78, "learning_rate": 1.828925755584757e-05, "loss": 0.7267, "step": 4759 }, { "epoch": 0.78, "learning_rate": 1.828679369250986e-05, "loss": 0.538, "step": 4760 }, { "epoch": 0.78, "learning_rate": 1.8284329829172143e-05, "loss": 0.6945, "step": 4761 }, { "epoch": 0.78, "learning_rate": 1.828186596583443e-05, "loss": 0.6658, "step": 4762 }, { "epoch": 0.78, "learning_rate": 1.8279402102496715e-05, "loss": 0.916, "step": 4763 }, { "epoch": 0.78, "learning_rate": 1.8276938239159002e-05, "loss": 0.9509, "step": 4764 }, { "epoch": 0.78, "learning_rate": 1.8274474375821287e-05, "loss": 1.0128, "step": 4765 }, { "epoch": 0.78, "learning_rate": 1.8272010512483574e-05, "loss": 0.8951, "step": 4766 }, { "epoch": 0.78, "learning_rate": 1.826954664914586e-05, "loss": 0.6956, "step": 4767 }, { "epoch": 0.78, "learning_rate": 1.826708278580815e-05, "loss": 1.1286, "step": 4768 }, { "epoch": 0.78, "learning_rate": 1.8264618922470434e-05, "loss": 0.7356, "step": 4769 }, { "epoch": 0.78, "learning_rate": 1.826215505913272e-05, "loss": 1.0932, "step": 4770 }, { "epoch": 0.78, "learning_rate": 1.8259691195795006e-05, "loss": 0.9106, "step": 4771 }, { "epoch": 0.78, "learning_rate": 1.8257227332457294e-05, "loss": 0.7298, "step": 4772 }, { "epoch": 0.78, "learning_rate": 1.825476346911958e-05, "loss": 0.7916, "step": 4773 }, { "epoch": 0.78, "learning_rate": 1.8252299605781865e-05, "loss": 0.7403, "step": 4774 }, { "epoch": 0.78, "learning_rate": 1.8249835742444153e-05, "loss": 0.6106, "step": 4775 }, { "epoch": 0.78, "learning_rate": 1.8247371879106437e-05, "loss": 1.2016, "step": 4776 }, { "epoch": 0.78, "learning_rate": 1.8244908015768725e-05, "loss": 0.534, "step": 4777 }, { "epoch": 0.78, "learning_rate": 1.8242444152431013e-05, "loss": 1.2786, "step": 4778 }, { "epoch": 0.78, "learning_rate": 1.82399802890933e-05, "loss": 0.6727, "step": 4779 }, { "epoch": 0.79, "learning_rate": 1.8237516425755585e-05, "loss": 1.5533, "step": 4780 }, { "epoch": 0.79, "learning_rate": 1.8235052562417872e-05, "loss": 0.4115, "step": 4781 }, { "epoch": 0.79, "learning_rate": 1.8232588699080157e-05, "loss": 1.2514, "step": 4782 }, { "epoch": 0.79, "learning_rate": 1.8230124835742444e-05, "loss": 0.6131, "step": 4783 }, { "epoch": 0.79, "learning_rate": 1.8227660972404732e-05, "loss": 0.7062, "step": 4784 }, { "epoch": 0.79, "learning_rate": 1.8225197109067016e-05, "loss": 0.4831, "step": 4785 }, { "epoch": 0.79, "learning_rate": 1.8222733245729304e-05, "loss": 1.0925, "step": 4786 }, { "epoch": 0.79, "learning_rate": 1.822026938239159e-05, "loss": 0.8258, "step": 4787 }, { "epoch": 0.79, "learning_rate": 1.821780551905388e-05, "loss": 0.9989, "step": 4788 }, { "epoch": 0.79, "learning_rate": 1.8215341655716164e-05, "loss": 0.511, "step": 4789 }, { "epoch": 0.79, "learning_rate": 1.821287779237845e-05, "loss": 0.5714, "step": 4790 }, { "epoch": 0.79, "learning_rate": 1.8210413929040736e-05, "loss": 0.6523, "step": 4791 }, { "epoch": 0.79, "learning_rate": 1.8207950065703023e-05, "loss": 0.8976, "step": 4792 }, { "epoch": 0.79, "learning_rate": 1.8205486202365308e-05, "loss": 0.5741, "step": 4793 }, { "epoch": 0.79, "learning_rate": 1.8203022339027595e-05, "loss": 0.4608, "step": 4794 }, { "epoch": 0.79, "learning_rate": 1.820055847568988e-05, "loss": 1.2122, "step": 4795 }, { "epoch": 0.79, "learning_rate": 1.8198094612352167e-05, "loss": 0.4745, "step": 4796 }, { "epoch": 0.79, "learning_rate": 1.8195630749014455e-05, "loss": 1.0764, "step": 4797 }, { "epoch": 0.79, "learning_rate": 1.8193166885676743e-05, "loss": 0.8234, "step": 4798 }, { "epoch": 0.79, "learning_rate": 1.819070302233903e-05, "loss": 0.4276, "step": 4799 }, { "epoch": 0.79, "learning_rate": 1.8188239159001315e-05, "loss": 0.579, "step": 4800 }, { "epoch": 0.79, "learning_rate": 1.8185775295663602e-05, "loss": 1.0962, "step": 4801 }, { "epoch": 0.79, "learning_rate": 1.8183311432325887e-05, "loss": 0.6933, "step": 4802 }, { "epoch": 0.79, "learning_rate": 1.8180847568988174e-05, "loss": 0.9907, "step": 4803 }, { "epoch": 0.79, "learning_rate": 1.817838370565046e-05, "loss": 0.836, "step": 4804 }, { "epoch": 0.79, "learning_rate": 1.8175919842312746e-05, "loss": 0.7674, "step": 4805 }, { "epoch": 0.79, "learning_rate": 1.817345597897503e-05, "loss": 0.9916, "step": 4806 }, { "epoch": 0.79, "learning_rate": 1.8170992115637318e-05, "loss": 0.679, "step": 4807 }, { "epoch": 0.79, "learning_rate": 1.816852825229961e-05, "loss": 0.6724, "step": 4808 }, { "epoch": 0.79, "learning_rate": 1.8166064388961894e-05, "loss": 0.5853, "step": 4809 }, { "epoch": 0.79, "learning_rate": 1.816360052562418e-05, "loss": 1.5489, "step": 4810 }, { "epoch": 0.79, "learning_rate": 1.8161136662286466e-05, "loss": 1.1653, "step": 4811 }, { "epoch": 0.79, "learning_rate": 1.8158672798948753e-05, "loss": 0.9344, "step": 4812 }, { "epoch": 0.79, "learning_rate": 1.8156208935611038e-05, "loss": 0.4223, "step": 4813 }, { "epoch": 0.79, "learning_rate": 1.8153745072273325e-05, "loss": 0.7273, "step": 4814 }, { "epoch": 0.79, "learning_rate": 1.815128120893561e-05, "loss": 0.6098, "step": 4815 }, { "epoch": 0.79, "learning_rate": 1.8148817345597897e-05, "loss": 0.6831, "step": 4816 }, { "epoch": 0.79, "learning_rate": 1.814635348226018e-05, "loss": 0.8007, "step": 4817 }, { "epoch": 0.79, "learning_rate": 1.8143889618922473e-05, "loss": 1.2028, "step": 4818 }, { "epoch": 0.79, "learning_rate": 1.8141425755584757e-05, "loss": 0.953, "step": 4819 }, { "epoch": 0.79, "learning_rate": 1.8138961892247044e-05, "loss": 0.915, "step": 4820 }, { "epoch": 0.79, "learning_rate": 1.8136498028909332e-05, "loss": 1.1188, "step": 4821 }, { "epoch": 0.79, "learning_rate": 1.8134034165571616e-05, "loss": 0.9255, "step": 4822 }, { "epoch": 0.79, "learning_rate": 1.8131570302233904e-05, "loss": 0.9291, "step": 4823 }, { "epoch": 0.79, "learning_rate": 1.812910643889619e-05, "loss": 0.4253, "step": 4824 }, { "epoch": 0.79, "learning_rate": 1.8126642575558476e-05, "loss": 0.8889, "step": 4825 }, { "epoch": 0.79, "learning_rate": 1.812417871222076e-05, "loss": 0.5488, "step": 4826 }, { "epoch": 0.79, "learning_rate": 1.8121714848883048e-05, "loss": 0.3509, "step": 4827 }, { "epoch": 0.79, "learning_rate": 1.8119250985545336e-05, "loss": 0.2739, "step": 4828 }, { "epoch": 0.79, "learning_rate": 1.8116787122207623e-05, "loss": 1.2386, "step": 4829 }, { "epoch": 0.79, "learning_rate": 1.8114323258869908e-05, "loss": 0.4364, "step": 4830 }, { "epoch": 0.79, "learning_rate": 1.8111859395532195e-05, "loss": 0.659, "step": 4831 }, { "epoch": 0.79, "learning_rate": 1.8109395532194483e-05, "loss": 0.7969, "step": 4832 }, { "epoch": 0.79, "learning_rate": 1.8106931668856767e-05, "loss": 0.6005, "step": 4833 }, { "epoch": 0.79, "learning_rate": 1.8104467805519055e-05, "loss": 0.4243, "step": 4834 }, { "epoch": 0.79, "learning_rate": 1.810200394218134e-05, "loss": 0.485, "step": 4835 }, { "epoch": 0.79, "learning_rate": 1.8099540078843627e-05, "loss": 0.8585, "step": 4836 }, { "epoch": 0.79, "learning_rate": 1.809707621550591e-05, "loss": 1.0851, "step": 4837 }, { "epoch": 0.79, "learning_rate": 1.8094612352168202e-05, "loss": 1.1989, "step": 4838 }, { "epoch": 0.79, "learning_rate": 1.8092148488830487e-05, "loss": 0.8206, "step": 4839 }, { "epoch": 0.8, "learning_rate": 1.8089684625492774e-05, "loss": 1.4207, "step": 4840 }, { "epoch": 0.8, "learning_rate": 1.808722076215506e-05, "loss": 1.2156, "step": 4841 }, { "epoch": 0.8, "learning_rate": 1.8084756898817346e-05, "loss": 0.9729, "step": 4842 }, { "epoch": 0.8, "learning_rate": 1.808229303547963e-05, "loss": 1.0348, "step": 4843 }, { "epoch": 0.8, "learning_rate": 1.8079829172141918e-05, "loss": 0.3227, "step": 4844 }, { "epoch": 0.8, "learning_rate": 1.8077365308804206e-05, "loss": 0.5027, "step": 4845 }, { "epoch": 0.8, "learning_rate": 1.807490144546649e-05, "loss": 0.4574, "step": 4846 }, { "epoch": 0.8, "learning_rate": 1.8072437582128778e-05, "loss": 1.8964, "step": 4847 }, { "epoch": 0.8, "learning_rate": 1.8069973718791066e-05, "loss": 0.5432, "step": 4848 }, { "epoch": 0.8, "learning_rate": 1.8067509855453353e-05, "loss": 0.6106, "step": 4849 }, { "epoch": 0.8, "learning_rate": 1.8065045992115638e-05, "loss": 0.7661, "step": 4850 }, { "epoch": 0.8, "learning_rate": 1.8062582128777925e-05, "loss": 1.2525, "step": 4851 }, { "epoch": 0.8, "learning_rate": 1.806011826544021e-05, "loss": 0.435, "step": 4852 }, { "epoch": 0.8, "learning_rate": 1.8057654402102497e-05, "loss": 0.3167, "step": 4853 }, { "epoch": 0.8, "learning_rate": 1.805519053876478e-05, "loss": 0.8016, "step": 4854 }, { "epoch": 0.8, "learning_rate": 1.805272667542707e-05, "loss": 0.3281, "step": 4855 }, { "epoch": 0.8, "learning_rate": 1.8050262812089357e-05, "loss": 0.9039, "step": 4856 }, { "epoch": 0.8, "learning_rate": 1.804779894875164e-05, "loss": 0.835, "step": 4857 }, { "epoch": 0.8, "learning_rate": 1.8045335085413932e-05, "loss": 0.9824, "step": 4858 }, { "epoch": 0.8, "learning_rate": 1.8042871222076217e-05, "loss": 0.6196, "step": 4859 }, { "epoch": 0.8, "learning_rate": 1.8040407358738504e-05, "loss": 0.5959, "step": 4860 }, { "epoch": 0.8, "learning_rate": 1.803794349540079e-05, "loss": 0.3716, "step": 4861 }, { "epoch": 0.8, "learning_rate": 1.8035479632063076e-05, "loss": 0.6988, "step": 4862 }, { "epoch": 0.8, "learning_rate": 1.803301576872536e-05, "loss": 1.0799, "step": 4863 }, { "epoch": 0.8, "learning_rate": 1.8030551905387648e-05, "loss": 0.6819, "step": 4864 }, { "epoch": 0.8, "learning_rate": 1.8028088042049932e-05, "loss": 0.7829, "step": 4865 }, { "epoch": 0.8, "learning_rate": 1.802562417871222e-05, "loss": 0.391, "step": 4866 }, { "epoch": 0.8, "learning_rate": 1.8023160315374508e-05, "loss": 1.0831, "step": 4867 }, { "epoch": 0.8, "learning_rate": 1.8020696452036795e-05, "loss": 0.463, "step": 4868 }, { "epoch": 0.8, "learning_rate": 1.8018232588699083e-05, "loss": 0.5028, "step": 4869 }, { "epoch": 0.8, "learning_rate": 1.8015768725361367e-05, "loss": 0.8864, "step": 4870 }, { "epoch": 0.8, "learning_rate": 1.8013304862023655e-05, "loss": 0.9978, "step": 4871 }, { "epoch": 0.8, "learning_rate": 1.801084099868594e-05, "loss": 0.9247, "step": 4872 }, { "epoch": 0.8, "learning_rate": 1.8008377135348227e-05, "loss": 0.5528, "step": 4873 }, { "epoch": 0.8, "learning_rate": 1.800591327201051e-05, "loss": 0.4331, "step": 4874 }, { "epoch": 0.8, "learning_rate": 1.80034494086728e-05, "loss": 0.82, "step": 4875 }, { "epoch": 0.8, "learning_rate": 1.8000985545335083e-05, "loss": 0.6014, "step": 4876 }, { "epoch": 0.8, "learning_rate": 1.799852168199737e-05, "loss": 0.372, "step": 4877 }, { "epoch": 0.8, "learning_rate": 1.799605781865966e-05, "loss": 0.824, "step": 4878 }, { "epoch": 0.8, "learning_rate": 1.7993593955321946e-05, "loss": 1.4173, "step": 4879 }, { "epoch": 0.8, "learning_rate": 1.7991130091984234e-05, "loss": 0.7097, "step": 4880 }, { "epoch": 0.8, "learning_rate": 1.798866622864652e-05, "loss": 0.7384, "step": 4881 }, { "epoch": 0.8, "learning_rate": 1.7986202365308806e-05, "loss": 0.5676, "step": 4882 }, { "epoch": 0.8, "learning_rate": 1.798373850197109e-05, "loss": 0.6948, "step": 4883 }, { "epoch": 0.8, "learning_rate": 1.7981274638633378e-05, "loss": 0.9906, "step": 4884 }, { "epoch": 0.8, "learning_rate": 1.7978810775295662e-05, "loss": 1.7738, "step": 4885 }, { "epoch": 0.8, "learning_rate": 1.797634691195795e-05, "loss": 1.3399, "step": 4886 }, { "epoch": 0.8, "learning_rate": 1.7973883048620234e-05, "loss": 0.4017, "step": 4887 }, { "epoch": 0.8, "learning_rate": 1.7971419185282525e-05, "loss": 0.5076, "step": 4888 }, { "epoch": 0.8, "learning_rate": 1.796895532194481e-05, "loss": 1.1784, "step": 4889 }, { "epoch": 0.8, "learning_rate": 1.7966491458607097e-05, "loss": 0.4416, "step": 4890 }, { "epoch": 0.8, "learning_rate": 1.7964027595269385e-05, "loss": 0.7633, "step": 4891 }, { "epoch": 0.8, "learning_rate": 1.796156373193167e-05, "loss": 1.3812, "step": 4892 }, { "epoch": 0.8, "learning_rate": 1.7959099868593957e-05, "loss": 0.7562, "step": 4893 }, { "epoch": 0.8, "learning_rate": 1.795663600525624e-05, "loss": 0.8758, "step": 4894 }, { "epoch": 0.8, "learning_rate": 1.795417214191853e-05, "loss": 0.7162, "step": 4895 }, { "epoch": 0.8, "learning_rate": 1.7951708278580813e-05, "loss": 0.9924, "step": 4896 }, { "epoch": 0.8, "learning_rate": 1.79492444152431e-05, "loss": 1.1176, "step": 4897 }, { "epoch": 0.8, "learning_rate": 1.794678055190539e-05, "loss": 0.8345, "step": 4898 }, { "epoch": 0.8, "learning_rate": 1.7944316688567676e-05, "loss": 0.8516, "step": 4899 }, { "epoch": 0.8, "learning_rate": 1.794185282522996e-05, "loss": 0.7731, "step": 4900 }, { "epoch": 0.81, "learning_rate": 1.7939388961892248e-05, "loss": 0.6987, "step": 4901 }, { "epoch": 0.81, "learning_rate": 1.7936925098554533e-05, "loss": 0.433, "step": 4902 }, { "epoch": 0.81, "learning_rate": 1.793446123521682e-05, "loss": 1.0061, "step": 4903 }, { "epoch": 0.81, "learning_rate": 1.7931997371879108e-05, "loss": 0.9903, "step": 4904 }, { "epoch": 0.81, "learning_rate": 1.7929533508541392e-05, "loss": 0.7695, "step": 4905 }, { "epoch": 0.81, "learning_rate": 1.792706964520368e-05, "loss": 0.3363, "step": 4906 }, { "epoch": 0.81, "learning_rate": 1.7924605781865964e-05, "loss": 0.9384, "step": 4907 }, { "epoch": 0.81, "learning_rate": 1.7922141918528255e-05, "loss": 0.8074, "step": 4908 }, { "epoch": 0.81, "learning_rate": 1.791967805519054e-05, "loss": 0.5347, "step": 4909 }, { "epoch": 0.81, "learning_rate": 1.7917214191852827e-05, "loss": 1.4298, "step": 4910 }, { "epoch": 0.81, "learning_rate": 1.791475032851511e-05, "loss": 0.5482, "step": 4911 }, { "epoch": 0.81, "learning_rate": 1.79122864651774e-05, "loss": 1.0405, "step": 4912 }, { "epoch": 0.81, "learning_rate": 1.7909822601839683e-05, "loss": 0.908, "step": 4913 }, { "epoch": 0.81, "learning_rate": 1.790735873850197e-05, "loss": 1.0469, "step": 4914 }, { "epoch": 0.81, "learning_rate": 1.790489487516426e-05, "loss": 0.4063, "step": 4915 }, { "epoch": 0.81, "learning_rate": 1.7902431011826543e-05, "loss": 0.3563, "step": 4916 }, { "epoch": 0.81, "learning_rate": 1.789996714848883e-05, "loss": 0.8944, "step": 4917 }, { "epoch": 0.81, "learning_rate": 1.789750328515112e-05, "loss": 0.7879, "step": 4918 }, { "epoch": 0.81, "learning_rate": 1.7895039421813406e-05, "loss": 0.4573, "step": 4919 }, { "epoch": 0.81, "learning_rate": 1.789257555847569e-05, "loss": 0.8994, "step": 4920 }, { "epoch": 0.81, "learning_rate": 1.7890111695137978e-05, "loss": 0.9, "step": 4921 }, { "epoch": 0.81, "learning_rate": 1.7887647831800262e-05, "loss": 0.4257, "step": 4922 }, { "epoch": 0.81, "learning_rate": 1.788518396846255e-05, "loss": 0.6828, "step": 4923 }, { "epoch": 0.81, "learning_rate": 1.7882720105124834e-05, "loss": 0.4192, "step": 4924 }, { "epoch": 0.81, "learning_rate": 1.7880256241787122e-05, "loss": 0.8597, "step": 4925 }, { "epoch": 0.81, "learning_rate": 1.7877792378449406e-05, "loss": 0.9101, "step": 4926 }, { "epoch": 0.81, "learning_rate": 1.7875328515111694e-05, "loss": 1.203, "step": 4927 }, { "epoch": 0.81, "learning_rate": 1.7872864651773985e-05, "loss": 0.8219, "step": 4928 }, { "epoch": 0.81, "learning_rate": 1.787040078843627e-05, "loss": 1.1811, "step": 4929 }, { "epoch": 0.81, "learning_rate": 1.7867936925098557e-05, "loss": 0.9219, "step": 4930 }, { "epoch": 0.81, "learning_rate": 1.786547306176084e-05, "loss": 1.1574, "step": 4931 }, { "epoch": 0.81, "learning_rate": 1.786300919842313e-05, "loss": 1.1766, "step": 4932 }, { "epoch": 0.81, "learning_rate": 1.7860545335085413e-05, "loss": 0.6614, "step": 4933 }, { "epoch": 0.81, "learning_rate": 1.78580814717477e-05, "loss": 0.5111, "step": 4934 }, { "epoch": 0.81, "learning_rate": 1.7855617608409985e-05, "loss": 0.8208, "step": 4935 }, { "epoch": 0.81, "learning_rate": 1.7853153745072273e-05, "loss": 0.8748, "step": 4936 }, { "epoch": 0.81, "learning_rate": 1.7850689881734557e-05, "loss": 0.7239, "step": 4937 }, { "epoch": 0.81, "learning_rate": 1.7848226018396848e-05, "loss": 1.171, "step": 4938 }, { "epoch": 0.81, "learning_rate": 1.7845762155059136e-05, "loss": 0.7193, "step": 4939 }, { "epoch": 0.81, "learning_rate": 1.784329829172142e-05, "loss": 0.8068, "step": 4940 }, { "epoch": 0.81, "learning_rate": 1.7840834428383708e-05, "loss": 2.0149, "step": 4941 }, { "epoch": 0.81, "learning_rate": 1.7838370565045992e-05, "loss": 0.6206, "step": 4942 }, { "epoch": 0.81, "learning_rate": 1.783590670170828e-05, "loss": 0.4211, "step": 4943 }, { "epoch": 0.81, "learning_rate": 1.7833442838370564e-05, "loss": 1.0167, "step": 4944 }, { "epoch": 0.81, "learning_rate": 1.7830978975032852e-05, "loss": 0.9457, "step": 4945 }, { "epoch": 0.81, "learning_rate": 1.7828515111695136e-05, "loss": 0.8163, "step": 4946 }, { "epoch": 0.81, "learning_rate": 1.7826051248357424e-05, "loss": 0.7084, "step": 4947 }, { "epoch": 0.81, "learning_rate": 1.782358738501971e-05, "loss": 0.6337, "step": 4948 }, { "epoch": 0.81, "learning_rate": 1.7821123521682e-05, "loss": 1.4071, "step": 4949 }, { "epoch": 0.81, "learning_rate": 1.7818659658344283e-05, "loss": 0.7584, "step": 4950 }, { "epoch": 0.81, "learning_rate": 1.781619579500657e-05, "loss": 0.8131, "step": 4951 }, { "epoch": 0.81, "learning_rate": 1.781373193166886e-05, "loss": 0.5593, "step": 4952 }, { "epoch": 0.81, "learning_rate": 1.7811268068331143e-05, "loss": 0.8375, "step": 4953 }, { "epoch": 0.81, "learning_rate": 1.780880420499343e-05, "loss": 0.544, "step": 4954 }, { "epoch": 0.81, "learning_rate": 1.7806340341655715e-05, "loss": 1.2207, "step": 4955 }, { "epoch": 0.81, "learning_rate": 1.7803876478318003e-05, "loss": 0.4495, "step": 4956 }, { "epoch": 0.81, "learning_rate": 1.7801412614980287e-05, "loss": 0.6096, "step": 4957 }, { "epoch": 0.81, "learning_rate": 1.7798948751642578e-05, "loss": 0.5306, "step": 4958 }, { "epoch": 0.81, "learning_rate": 1.7796484888304862e-05, "loss": 1.1849, "step": 4959 }, { "epoch": 0.81, "learning_rate": 1.779402102496715e-05, "loss": 0.5095, "step": 4960 }, { "epoch": 0.81, "learning_rate": 1.7791557161629434e-05, "loss": 0.6918, "step": 4961 }, { "epoch": 0.82, "learning_rate": 1.7789093298291722e-05, "loss": 1.493, "step": 4962 }, { "epoch": 0.82, "learning_rate": 1.778662943495401e-05, "loss": 0.6951, "step": 4963 }, { "epoch": 0.82, "learning_rate": 1.7784165571616294e-05, "loss": 1.0507, "step": 4964 }, { "epoch": 0.82, "learning_rate": 1.7781701708278582e-05, "loss": 0.7807, "step": 4965 }, { "epoch": 0.82, "learning_rate": 1.7779237844940866e-05, "loss": 1.009, "step": 4966 }, { "epoch": 0.82, "learning_rate": 1.7776773981603154e-05, "loss": 1.4657, "step": 4967 }, { "epoch": 0.82, "learning_rate": 1.777431011826544e-05, "loss": 0.5535, "step": 4968 }, { "epoch": 0.82, "learning_rate": 1.777184625492773e-05, "loss": 0.6788, "step": 4969 }, { "epoch": 0.82, "learning_rate": 1.7769382391590013e-05, "loss": 0.9022, "step": 4970 }, { "epoch": 0.82, "learning_rate": 1.77669185282523e-05, "loss": 0.6425, "step": 4971 }, { "epoch": 0.82, "learning_rate": 1.7764454664914585e-05, "loss": 0.5369, "step": 4972 }, { "epoch": 0.82, "learning_rate": 1.7761990801576873e-05, "loss": 0.9217, "step": 4973 }, { "epoch": 0.82, "learning_rate": 1.7759526938239157e-05, "loss": 0.8455, "step": 4974 }, { "epoch": 0.82, "learning_rate": 1.7757063074901445e-05, "loss": 1.0146, "step": 4975 }, { "epoch": 0.82, "learning_rate": 1.7754599211563733e-05, "loss": 1.0397, "step": 4976 }, { "epoch": 0.82, "learning_rate": 1.7752135348226017e-05, "loss": 0.5809, "step": 4977 }, { "epoch": 0.82, "learning_rate": 1.7749671484888308e-05, "loss": 0.9996, "step": 4978 }, { "epoch": 0.82, "learning_rate": 1.7747207621550592e-05, "loss": 0.717, "step": 4979 }, { "epoch": 0.82, "learning_rate": 1.774474375821288e-05, "loss": 0.6979, "step": 4980 }, { "epoch": 0.82, "learning_rate": 1.7742279894875164e-05, "loss": 0.9231, "step": 4981 }, { "epoch": 0.82, "learning_rate": 1.7739816031537452e-05, "loss": 0.6924, "step": 4982 }, { "epoch": 0.82, "learning_rate": 1.7737352168199736e-05, "loss": 1.2202, "step": 4983 }, { "epoch": 0.82, "learning_rate": 1.7734888304862024e-05, "loss": 0.4407, "step": 4984 }, { "epoch": 0.82, "learning_rate": 1.7732424441524308e-05, "loss": 1.117, "step": 4985 }, { "epoch": 0.82, "learning_rate": 1.7729960578186596e-05, "loss": 0.5783, "step": 4986 }, { "epoch": 0.82, "learning_rate": 1.7727496714848884e-05, "loss": 0.8437, "step": 4987 }, { "epoch": 0.82, "learning_rate": 1.772503285151117e-05, "loss": 0.9624, "step": 4988 }, { "epoch": 0.82, "learning_rate": 1.772256898817346e-05, "loss": 0.3467, "step": 4989 }, { "epoch": 0.82, "learning_rate": 1.7720105124835743e-05, "loss": 1.0184, "step": 4990 }, { "epoch": 0.82, "learning_rate": 1.771764126149803e-05, "loss": 1.5796, "step": 4991 }, { "epoch": 0.82, "learning_rate": 1.7715177398160315e-05, "loss": 0.7996, "step": 4992 }, { "epoch": 0.82, "learning_rate": 1.7712713534822603e-05, "loss": 0.6417, "step": 4993 }, { "epoch": 0.82, "learning_rate": 1.7710249671484887e-05, "loss": 0.7501, "step": 4994 }, { "epoch": 0.82, "learning_rate": 1.7707785808147175e-05, "loss": 0.6069, "step": 4995 }, { "epoch": 0.82, "learning_rate": 1.770532194480946e-05, "loss": 0.3807, "step": 4996 }, { "epoch": 0.82, "learning_rate": 1.7702858081471747e-05, "loss": 0.77, "step": 4997 }, { "epoch": 0.82, "learning_rate": 1.7700394218134034e-05, "loss": 0.445, "step": 4998 }, { "epoch": 0.82, "learning_rate": 1.7697930354796322e-05, "loss": 0.7753, "step": 4999 }, { "epoch": 0.82, "learning_rate": 1.769546649145861e-05, "loss": 0.6401, "step": 5000 }, { "epoch": 0.82, "eval_exact_match": 86.29139072847683, "eval_f1": 92.5420717224006, "step": 5000 }, { "epoch": 0.82, "learning_rate": 1.7693002628120894e-05, "loss": 1.1508, "step": 5001 }, { "epoch": 0.82, "learning_rate": 1.7690538764783182e-05, "loss": 0.461, "step": 5002 }, { "epoch": 0.82, "learning_rate": 1.7688074901445466e-05, "loss": 0.7622, "step": 5003 }, { "epoch": 0.82, "learning_rate": 1.7685611038107754e-05, "loss": 0.8309, "step": 5004 }, { "epoch": 0.82, "learning_rate": 1.7683147174770038e-05, "loss": 1.0814, "step": 5005 }, { "epoch": 0.82, "learning_rate": 1.7680683311432326e-05, "loss": 1.1209, "step": 5006 }, { "epoch": 0.82, "learning_rate": 1.767821944809461e-05, "loss": 0.8229, "step": 5007 }, { "epoch": 0.82, "learning_rate": 1.76757555847569e-05, "loss": 0.7688, "step": 5008 }, { "epoch": 0.82, "learning_rate": 1.7673291721419185e-05, "loss": 0.6335, "step": 5009 }, { "epoch": 0.82, "learning_rate": 1.7670827858081473e-05, "loss": 1.0907, "step": 5010 }, { "epoch": 0.82, "learning_rate": 1.766836399474376e-05, "loss": 0.803, "step": 5011 }, { "epoch": 0.82, "learning_rate": 1.7665900131406045e-05, "loss": 1.1477, "step": 5012 }, { "epoch": 0.82, "learning_rate": 1.7663436268068333e-05, "loss": 1.071, "step": 5013 }, { "epoch": 0.82, "learning_rate": 1.7660972404730617e-05, "loss": 1.1984, "step": 5014 }, { "epoch": 0.82, "learning_rate": 1.7658508541392905e-05, "loss": 1.0965, "step": 5015 }, { "epoch": 0.82, "learning_rate": 1.765604467805519e-05, "loss": 0.9271, "step": 5016 }, { "epoch": 0.82, "learning_rate": 1.7653580814717477e-05, "loss": 0.9727, "step": 5017 }, { "epoch": 0.82, "learning_rate": 1.7651116951379764e-05, "loss": 0.6036, "step": 5018 }, { "epoch": 0.82, "learning_rate": 1.7648653088042052e-05, "loss": 0.6994, "step": 5019 }, { "epoch": 0.82, "learning_rate": 1.7646189224704336e-05, "loss": 0.6731, "step": 5020 }, { "epoch": 0.82, "learning_rate": 1.7643725361366624e-05, "loss": 1.0171, "step": 5021 }, { "epoch": 0.82, "learning_rate": 1.764126149802891e-05, "loss": 1.9781, "step": 5022 }, { "epoch": 0.83, "learning_rate": 1.7638797634691196e-05, "loss": 0.54, "step": 5023 }, { "epoch": 0.83, "learning_rate": 1.7636333771353484e-05, "loss": 1.018, "step": 5024 }, { "epoch": 0.83, "learning_rate": 1.7633869908015768e-05, "loss": 0.5655, "step": 5025 }, { "epoch": 0.83, "learning_rate": 1.7631406044678056e-05, "loss": 1.354, "step": 5026 }, { "epoch": 0.83, "learning_rate": 1.762894218134034e-05, "loss": 0.886, "step": 5027 }, { "epoch": 0.83, "learning_rate": 1.762647831800263e-05, "loss": 0.8516, "step": 5028 }, { "epoch": 0.83, "learning_rate": 1.7624014454664915e-05, "loss": 0.4754, "step": 5029 }, { "epoch": 0.83, "learning_rate": 1.7621550591327203e-05, "loss": 0.54, "step": 5030 }, { "epoch": 0.83, "learning_rate": 1.7619086727989487e-05, "loss": 0.7571, "step": 5031 }, { "epoch": 0.83, "learning_rate": 1.7616622864651775e-05, "loss": 0.6674, "step": 5032 }, { "epoch": 0.83, "learning_rate": 1.761415900131406e-05, "loss": 0.4286, "step": 5033 }, { "epoch": 0.83, "learning_rate": 1.7611695137976347e-05, "loss": 0.8434, "step": 5034 }, { "epoch": 0.83, "learning_rate": 1.7609231274638635e-05, "loss": 0.6131, "step": 5035 }, { "epoch": 0.83, "learning_rate": 1.760676741130092e-05, "loss": 1.2184, "step": 5036 }, { "epoch": 0.83, "learning_rate": 1.7604303547963206e-05, "loss": 0.6533, "step": 5037 }, { "epoch": 0.83, "learning_rate": 1.7601839684625494e-05, "loss": 1.6624, "step": 5038 }, { "epoch": 0.83, "learning_rate": 1.7599375821287782e-05, "loss": 0.4761, "step": 5039 }, { "epoch": 0.83, "learning_rate": 1.7596911957950066e-05, "loss": 0.4477, "step": 5040 }, { "epoch": 0.83, "learning_rate": 1.7594448094612354e-05, "loss": 0.1394, "step": 5041 }, { "epoch": 0.83, "learning_rate": 1.7591984231274638e-05, "loss": 1.1331, "step": 5042 }, { "epoch": 0.83, "learning_rate": 1.7589520367936926e-05, "loss": 0.9506, "step": 5043 }, { "epoch": 0.83, "learning_rate": 1.758705650459921e-05, "loss": 1.0906, "step": 5044 }, { "epoch": 0.83, "learning_rate": 1.7584592641261498e-05, "loss": 0.6275, "step": 5045 }, { "epoch": 0.83, "learning_rate": 1.7582128777923785e-05, "loss": 0.3526, "step": 5046 }, { "epoch": 0.83, "learning_rate": 1.757966491458607e-05, "loss": 0.4939, "step": 5047 }, { "epoch": 0.83, "learning_rate": 1.757720105124836e-05, "loss": 1.4824, "step": 5048 }, { "epoch": 0.83, "learning_rate": 1.7574737187910645e-05, "loss": 0.8766, "step": 5049 }, { "epoch": 0.83, "learning_rate": 1.7572273324572933e-05, "loss": 1.4425, "step": 5050 }, { "epoch": 0.83, "learning_rate": 1.7569809461235217e-05, "loss": 0.9501, "step": 5051 }, { "epoch": 0.83, "learning_rate": 1.7567345597897505e-05, "loss": 0.9755, "step": 5052 }, { "epoch": 0.83, "learning_rate": 1.756488173455979e-05, "loss": 0.943, "step": 5053 }, { "epoch": 0.83, "learning_rate": 1.7562417871222077e-05, "loss": 1.2311, "step": 5054 }, { "epoch": 0.83, "learning_rate": 1.755995400788436e-05, "loss": 1.1533, "step": 5055 }, { "epoch": 0.83, "learning_rate": 1.755749014454665e-05, "loss": 1.1664, "step": 5056 }, { "epoch": 0.83, "learning_rate": 1.7555026281208933e-05, "loss": 0.5172, "step": 5057 }, { "epoch": 0.83, "learning_rate": 1.7552562417871224e-05, "loss": 0.7594, "step": 5058 }, { "epoch": 0.83, "learning_rate": 1.7550098554533512e-05, "loss": 0.5313, "step": 5059 }, { "epoch": 0.83, "learning_rate": 1.7547634691195796e-05, "loss": 0.4935, "step": 5060 }, { "epoch": 0.83, "learning_rate": 1.7545170827858084e-05, "loss": 1.1148, "step": 5061 }, { "epoch": 0.83, "learning_rate": 1.7542706964520368e-05, "loss": 0.5501, "step": 5062 }, { "epoch": 0.83, "learning_rate": 1.7540243101182656e-05, "loss": 1.0115, "step": 5063 }, { "epoch": 0.83, "learning_rate": 1.753777923784494e-05, "loss": 0.675, "step": 5064 }, { "epoch": 0.83, "learning_rate": 1.7535315374507228e-05, "loss": 0.6872, "step": 5065 }, { "epoch": 0.83, "learning_rate": 1.7532851511169512e-05, "loss": 1.0923, "step": 5066 }, { "epoch": 0.83, "learning_rate": 1.75303876478318e-05, "loss": 0.9761, "step": 5067 }, { "epoch": 0.83, "learning_rate": 1.7527923784494087e-05, "loss": 1.2523, "step": 5068 }, { "epoch": 0.83, "learning_rate": 1.7525459921156375e-05, "loss": 0.5745, "step": 5069 }, { "epoch": 0.83, "learning_rate": 1.7522996057818663e-05, "loss": 0.6782, "step": 5070 }, { "epoch": 0.83, "learning_rate": 1.7520532194480947e-05, "loss": 0.7705, "step": 5071 }, { "epoch": 0.83, "learning_rate": 1.7518068331143235e-05, "loss": 0.7434, "step": 5072 }, { "epoch": 0.83, "learning_rate": 1.751560446780552e-05, "loss": 0.9996, "step": 5073 }, { "epoch": 0.83, "learning_rate": 1.7513140604467807e-05, "loss": 1.1905, "step": 5074 }, { "epoch": 0.83, "learning_rate": 1.751067674113009e-05, "loss": 0.8312, "step": 5075 }, { "epoch": 0.83, "learning_rate": 1.750821287779238e-05, "loss": 0.7529, "step": 5076 }, { "epoch": 0.83, "learning_rate": 1.7505749014454663e-05, "loss": 0.6344, "step": 5077 }, { "epoch": 0.83, "learning_rate": 1.7503285151116954e-05, "loss": 0.6954, "step": 5078 }, { "epoch": 0.83, "learning_rate": 1.7500821287779238e-05, "loss": 1.1525, "step": 5079 }, { "epoch": 0.83, "learning_rate": 1.7498357424441526e-05, "loss": 0.4426, "step": 5080 }, { "epoch": 0.83, "learning_rate": 1.749589356110381e-05, "loss": 0.8919, "step": 5081 }, { "epoch": 0.83, "learning_rate": 1.7493429697766098e-05, "loss": 1.0626, "step": 5082 }, { "epoch": 0.83, "learning_rate": 1.7490965834428385e-05, "loss": 0.8567, "step": 5083 }, { "epoch": 0.84, "learning_rate": 1.748850197109067e-05, "loss": 1.2272, "step": 5084 }, { "epoch": 0.84, "learning_rate": 1.7486038107752957e-05, "loss": 0.8397, "step": 5085 }, { "epoch": 0.84, "learning_rate": 1.7483574244415242e-05, "loss": 0.5107, "step": 5086 }, { "epoch": 0.84, "learning_rate": 1.748111038107753e-05, "loss": 0.7703, "step": 5087 }, { "epoch": 0.84, "learning_rate": 1.7478646517739817e-05, "loss": 1.36, "step": 5088 }, { "epoch": 0.84, "learning_rate": 1.7476182654402105e-05, "loss": 0.6315, "step": 5089 }, { "epoch": 0.84, "learning_rate": 1.747371879106439e-05, "loss": 1.6316, "step": 5090 }, { "epoch": 0.84, "learning_rate": 1.7471254927726677e-05, "loss": 0.9504, "step": 5091 }, { "epoch": 0.84, "learning_rate": 1.746879106438896e-05, "loss": 0.814, "step": 5092 }, { "epoch": 0.84, "learning_rate": 1.746632720105125e-05, "loss": 0.9752, "step": 5093 }, { "epoch": 0.84, "learning_rate": 1.7463863337713536e-05, "loss": 0.3927, "step": 5094 }, { "epoch": 0.84, "learning_rate": 1.746139947437582e-05, "loss": 1.2679, "step": 5095 }, { "epoch": 0.84, "learning_rate": 1.745893561103811e-05, "loss": 0.8361, "step": 5096 }, { "epoch": 0.84, "learning_rate": 1.7456471747700393e-05, "loss": 0.6155, "step": 5097 }, { "epoch": 0.84, "learning_rate": 1.7454007884362684e-05, "loss": 0.6078, "step": 5098 }, { "epoch": 0.84, "learning_rate": 1.7451544021024968e-05, "loss": 0.9069, "step": 5099 }, { "epoch": 0.84, "learning_rate": 1.7449080157687256e-05, "loss": 0.8881, "step": 5100 }, { "epoch": 0.84, "learning_rate": 1.744661629434954e-05, "loss": 1.2826, "step": 5101 }, { "epoch": 0.84, "learning_rate": 1.7444152431011828e-05, "loss": 0.6894, "step": 5102 }, { "epoch": 0.84, "learning_rate": 1.7441688567674112e-05, "loss": 1.1145, "step": 5103 }, { "epoch": 0.84, "learning_rate": 1.74392247043364e-05, "loss": 0.8635, "step": 5104 }, { "epoch": 0.84, "learning_rate": 1.7436760840998684e-05, "loss": 0.6756, "step": 5105 }, { "epoch": 0.84, "learning_rate": 1.743429697766097e-05, "loss": 1.0802, "step": 5106 }, { "epoch": 0.84, "learning_rate": 1.743183311432326e-05, "loss": 0.6879, "step": 5107 }, { "epoch": 0.84, "learning_rate": 1.7429369250985547e-05, "loss": 0.7601, "step": 5108 }, { "epoch": 0.84, "learning_rate": 1.7426905387647835e-05, "loss": 0.5078, "step": 5109 }, { "epoch": 0.84, "learning_rate": 1.742444152431012e-05, "loss": 0.8529, "step": 5110 }, { "epoch": 0.84, "learning_rate": 1.7421977660972407e-05, "loss": 0.7286, "step": 5111 }, { "epoch": 0.84, "learning_rate": 1.741951379763469e-05, "loss": 0.8544, "step": 5112 }, { "epoch": 0.84, "learning_rate": 1.741704993429698e-05, "loss": 1.1519, "step": 5113 }, { "epoch": 0.84, "learning_rate": 1.7414586070959263e-05, "loss": 0.9284, "step": 5114 }, { "epoch": 0.84, "learning_rate": 1.741212220762155e-05, "loss": 0.6869, "step": 5115 }, { "epoch": 0.84, "learning_rate": 1.7409658344283835e-05, "loss": 1.1245, "step": 5116 }, { "epoch": 0.84, "learning_rate": 1.7407194480946123e-05, "loss": 0.6209, "step": 5117 }, { "epoch": 0.84, "learning_rate": 1.7404730617608414e-05, "loss": 0.5091, "step": 5118 }, { "epoch": 0.84, "learning_rate": 1.7402266754270698e-05, "loss": 0.6942, "step": 5119 }, { "epoch": 0.84, "learning_rate": 1.7399802890932986e-05, "loss": 1.1286, "step": 5120 }, { "epoch": 0.84, "learning_rate": 1.739733902759527e-05, "loss": 0.7816, "step": 5121 }, { "epoch": 0.84, "learning_rate": 1.7394875164257558e-05, "loss": 1.2792, "step": 5122 }, { "epoch": 0.84, "learning_rate": 1.7392411300919842e-05, "loss": 0.6, "step": 5123 }, { "epoch": 0.84, "learning_rate": 1.738994743758213e-05, "loss": 0.5613, "step": 5124 }, { "epoch": 0.84, "learning_rate": 1.7387483574244414e-05, "loss": 0.7791, "step": 5125 }, { "epoch": 0.84, "learning_rate": 1.73850197109067e-05, "loss": 1.4863, "step": 5126 }, { "epoch": 0.84, "learning_rate": 1.7382555847568986e-05, "loss": 0.9085, "step": 5127 }, { "epoch": 0.84, "learning_rate": 1.7380091984231277e-05, "loss": 0.4015, "step": 5128 }, { "epoch": 0.84, "learning_rate": 1.737762812089356e-05, "loss": 0.416, "step": 5129 }, { "epoch": 0.84, "learning_rate": 1.737516425755585e-05, "loss": 0.5498, "step": 5130 }, { "epoch": 0.84, "learning_rate": 1.7372700394218136e-05, "loss": 0.3812, "step": 5131 }, { "epoch": 0.84, "learning_rate": 1.737023653088042e-05, "loss": 0.9058, "step": 5132 }, { "epoch": 0.84, "learning_rate": 1.736777266754271e-05, "loss": 1.4058, "step": 5133 }, { "epoch": 0.84, "learning_rate": 1.7365308804204993e-05, "loss": 0.3624, "step": 5134 }, { "epoch": 0.84, "learning_rate": 1.736284494086728e-05, "loss": 0.902, "step": 5135 }, { "epoch": 0.84, "learning_rate": 1.7360381077529565e-05, "loss": 0.4812, "step": 5136 }, { "epoch": 0.84, "learning_rate": 1.7357917214191852e-05, "loss": 0.4881, "step": 5137 }, { "epoch": 0.84, "learning_rate": 1.735545335085414e-05, "loss": 0.628, "step": 5138 }, { "epoch": 0.84, "learning_rate": 1.7352989487516428e-05, "loss": 0.7366, "step": 5139 }, { "epoch": 0.84, "learning_rate": 1.7350525624178712e-05, "loss": 0.4309, "step": 5140 }, { "epoch": 0.84, "learning_rate": 1.7348061760841e-05, "loss": 0.8604, "step": 5141 }, { "epoch": 0.84, "learning_rate": 1.7345597897503287e-05, "loss": 0.7579, "step": 5142 }, { "epoch": 0.84, "learning_rate": 1.734313403416557e-05, "loss": 0.5761, "step": 5143 }, { "epoch": 0.84, "learning_rate": 1.734067017082786e-05, "loss": 0.7725, "step": 5144 }, { "epoch": 0.85, "learning_rate": 1.7338206307490144e-05, "loss": 0.626, "step": 5145 }, { "epoch": 0.85, "learning_rate": 1.733574244415243e-05, "loss": 0.7928, "step": 5146 }, { "epoch": 0.85, "learning_rate": 1.7333278580814716e-05, "loss": 1.0741, "step": 5147 }, { "epoch": 0.85, "learning_rate": 1.7330814717477007e-05, "loss": 0.3791, "step": 5148 }, { "epoch": 0.85, "learning_rate": 1.732835085413929e-05, "loss": 0.5518, "step": 5149 }, { "epoch": 0.85, "learning_rate": 1.732588699080158e-05, "loss": 0.6261, "step": 5150 }, { "epoch": 0.85, "learning_rate": 1.7323423127463863e-05, "loss": 1.2472, "step": 5151 }, { "epoch": 0.85, "learning_rate": 1.732095926412615e-05, "loss": 0.7693, "step": 5152 }, { "epoch": 0.85, "learning_rate": 1.7318495400788438e-05, "loss": 0.8398, "step": 5153 }, { "epoch": 0.85, "learning_rate": 1.7316031537450723e-05, "loss": 0.6436, "step": 5154 }, { "epoch": 0.85, "learning_rate": 1.731356767411301e-05, "loss": 0.4097, "step": 5155 }, { "epoch": 0.85, "learning_rate": 1.7311103810775295e-05, "loss": 1.0881, "step": 5156 }, { "epoch": 0.85, "learning_rate": 1.7308639947437582e-05, "loss": 0.7041, "step": 5157 }, { "epoch": 0.85, "learning_rate": 1.730617608409987e-05, "loss": 0.7908, "step": 5158 }, { "epoch": 0.85, "learning_rate": 1.7303712220762158e-05, "loss": 0.662, "step": 5159 }, { "epoch": 0.85, "learning_rate": 1.7301248357424442e-05, "loss": 0.4944, "step": 5160 }, { "epoch": 0.85, "learning_rate": 1.729878449408673e-05, "loss": 1.1288, "step": 5161 }, { "epoch": 0.85, "learning_rate": 1.7296320630749014e-05, "loss": 0.3357, "step": 5162 }, { "epoch": 0.85, "learning_rate": 1.72938567674113e-05, "loss": 0.6214, "step": 5163 }, { "epoch": 0.85, "learning_rate": 1.7291392904073586e-05, "loss": 0.4835, "step": 5164 }, { "epoch": 0.85, "learning_rate": 1.7288929040735873e-05, "loss": 0.695, "step": 5165 }, { "epoch": 0.85, "learning_rate": 1.728646517739816e-05, "loss": 1.7347, "step": 5166 }, { "epoch": 0.85, "learning_rate": 1.7284001314060445e-05, "loss": 0.8279, "step": 5167 }, { "epoch": 0.85, "learning_rate": 1.7281537450722737e-05, "loss": 0.8963, "step": 5168 }, { "epoch": 0.85, "learning_rate": 1.727907358738502e-05, "loss": 1.4204, "step": 5169 }, { "epoch": 0.85, "learning_rate": 1.727660972404731e-05, "loss": 1.3769, "step": 5170 }, { "epoch": 0.85, "learning_rate": 1.7274145860709593e-05, "loss": 0.617, "step": 5171 }, { "epoch": 0.85, "learning_rate": 1.727168199737188e-05, "loss": 0.7573, "step": 5172 }, { "epoch": 0.85, "learning_rate": 1.7269218134034165e-05, "loss": 0.2912, "step": 5173 }, { "epoch": 0.85, "learning_rate": 1.7266754270696452e-05, "loss": 0.6984, "step": 5174 }, { "epoch": 0.85, "learning_rate": 1.7264290407358737e-05, "loss": 0.6153, "step": 5175 }, { "epoch": 0.85, "learning_rate": 1.7261826544021024e-05, "loss": 0.5717, "step": 5176 }, { "epoch": 0.85, "learning_rate": 1.7259362680683312e-05, "loss": 0.5051, "step": 5177 }, { "epoch": 0.85, "learning_rate": 1.72568988173456e-05, "loss": 0.7932, "step": 5178 }, { "epoch": 0.85, "learning_rate": 1.7254434954007887e-05, "loss": 1.0255, "step": 5179 }, { "epoch": 0.85, "learning_rate": 1.7251971090670172e-05, "loss": 0.6356, "step": 5180 }, { "epoch": 0.85, "learning_rate": 1.724950722733246e-05, "loss": 1.0109, "step": 5181 }, { "epoch": 0.85, "learning_rate": 1.7247043363994744e-05, "loss": 0.7454, "step": 5182 }, { "epoch": 0.85, "learning_rate": 1.724457950065703e-05, "loss": 0.8206, "step": 5183 }, { "epoch": 0.85, "learning_rate": 1.7242115637319316e-05, "loss": 1.177, "step": 5184 }, { "epoch": 0.85, "learning_rate": 1.7239651773981603e-05, "loss": 0.7222, "step": 5185 }, { "epoch": 0.85, "learning_rate": 1.7237187910643888e-05, "loss": 0.5502, "step": 5186 }, { "epoch": 0.85, "learning_rate": 1.7234724047306175e-05, "loss": 0.7383, "step": 5187 }, { "epoch": 0.85, "learning_rate": 1.7232260183968463e-05, "loss": 1.8809, "step": 5188 }, { "epoch": 0.85, "learning_rate": 1.722979632063075e-05, "loss": 1.2084, "step": 5189 }, { "epoch": 0.85, "learning_rate": 1.722733245729304e-05, "loss": 1.2026, "step": 5190 }, { "epoch": 0.85, "learning_rate": 1.7224868593955323e-05, "loss": 0.6934, "step": 5191 }, { "epoch": 0.85, "learning_rate": 1.722240473061761e-05, "loss": 0.6207, "step": 5192 }, { "epoch": 0.85, "learning_rate": 1.7219940867279895e-05, "loss": 0.8529, "step": 5193 }, { "epoch": 0.85, "learning_rate": 1.7217477003942182e-05, "loss": 1.4448, "step": 5194 }, { "epoch": 0.85, "learning_rate": 1.7215013140604467e-05, "loss": 0.9648, "step": 5195 }, { "epoch": 0.85, "learning_rate": 1.7212549277266754e-05, "loss": 0.5615, "step": 5196 }, { "epoch": 0.85, "learning_rate": 1.721008541392904e-05, "loss": 0.9346, "step": 5197 }, { "epoch": 0.85, "learning_rate": 1.720762155059133e-05, "loss": 0.8982, "step": 5198 }, { "epoch": 0.85, "learning_rate": 1.7205157687253614e-05, "loss": 1.2887, "step": 5199 }, { "epoch": 0.85, "learning_rate": 1.72026938239159e-05, "loss": 0.9743, "step": 5200 }, { "epoch": 0.85, "learning_rate": 1.720022996057819e-05, "loss": 0.3839, "step": 5201 }, { "epoch": 0.85, "learning_rate": 1.7197766097240474e-05, "loss": 0.5005, "step": 5202 }, { "epoch": 0.85, "learning_rate": 1.719530223390276e-05, "loss": 0.3219, "step": 5203 }, { "epoch": 0.85, "learning_rate": 1.7192838370565046e-05, "loss": 0.7683, "step": 5204 }, { "epoch": 0.85, "learning_rate": 1.7190374507227333e-05, "loss": 1.3715, "step": 5205 }, { "epoch": 0.86, "learning_rate": 1.7187910643889617e-05, "loss": 0.6863, "step": 5206 }, { "epoch": 0.86, "learning_rate": 1.7185446780551905e-05, "loss": 1.4621, "step": 5207 }, { "epoch": 0.86, "learning_rate": 1.7182982917214193e-05, "loss": 0.6281, "step": 5208 }, { "epoch": 0.86, "learning_rate": 1.718051905387648e-05, "loss": 0.8763, "step": 5209 }, { "epoch": 0.86, "learning_rate": 1.7178055190538765e-05, "loss": 0.9774, "step": 5210 }, { "epoch": 0.86, "learning_rate": 1.7175591327201053e-05, "loss": 0.7935, "step": 5211 }, { "epoch": 0.86, "learning_rate": 1.7173127463863337e-05, "loss": 0.9672, "step": 5212 }, { "epoch": 0.86, "learning_rate": 1.7170663600525624e-05, "loss": 1.3795, "step": 5213 }, { "epoch": 0.86, "learning_rate": 1.7168199737187912e-05, "loss": 0.733, "step": 5214 }, { "epoch": 0.86, "learning_rate": 1.7165735873850196e-05, "loss": 0.4565, "step": 5215 }, { "epoch": 0.86, "learning_rate": 1.7163272010512484e-05, "loss": 0.5801, "step": 5216 }, { "epoch": 0.86, "learning_rate": 1.716080814717477e-05, "loss": 0.6195, "step": 5217 }, { "epoch": 0.86, "learning_rate": 1.715834428383706e-05, "loss": 1.4644, "step": 5218 }, { "epoch": 0.86, "learning_rate": 1.7155880420499344e-05, "loss": 2.0801, "step": 5219 }, { "epoch": 0.86, "learning_rate": 1.715341655716163e-05, "loss": 0.7131, "step": 5220 }, { "epoch": 0.86, "learning_rate": 1.7150952693823916e-05, "loss": 0.8416, "step": 5221 }, { "epoch": 0.86, "learning_rate": 1.7148488830486203e-05, "loss": 1.3995, "step": 5222 }, { "epoch": 0.86, "learning_rate": 1.7146024967148488e-05, "loss": 0.6241, "step": 5223 }, { "epoch": 0.86, "learning_rate": 1.7143561103810775e-05, "loss": 1.1899, "step": 5224 }, { "epoch": 0.86, "learning_rate": 1.7141097240473063e-05, "loss": 0.5048, "step": 5225 }, { "epoch": 0.86, "learning_rate": 1.7138633377135347e-05, "loss": 1.2181, "step": 5226 }, { "epoch": 0.86, "learning_rate": 1.7136169513797635e-05, "loss": 0.9231, "step": 5227 }, { "epoch": 0.86, "learning_rate": 1.7133705650459923e-05, "loss": 0.8609, "step": 5228 }, { "epoch": 0.86, "learning_rate": 1.713124178712221e-05, "loss": 0.9134, "step": 5229 }, { "epoch": 0.86, "learning_rate": 1.7128777923784495e-05, "loss": 1.2206, "step": 5230 }, { "epoch": 0.86, "learning_rate": 1.7126314060446782e-05, "loss": 0.6919, "step": 5231 }, { "epoch": 0.86, "learning_rate": 1.7123850197109067e-05, "loss": 1.1161, "step": 5232 }, { "epoch": 0.86, "learning_rate": 1.7121386333771354e-05, "loss": 0.6294, "step": 5233 }, { "epoch": 0.86, "learning_rate": 1.711892247043364e-05, "loss": 1.1011, "step": 5234 }, { "epoch": 0.86, "learning_rate": 1.7116458607095926e-05, "loss": 0.3472, "step": 5235 }, { "epoch": 0.86, "learning_rate": 1.711399474375821e-05, "loss": 0.6687, "step": 5236 }, { "epoch": 0.86, "learning_rate": 1.7111530880420498e-05, "loss": 1.1926, "step": 5237 }, { "epoch": 0.86, "learning_rate": 1.710906701708279e-05, "loss": 0.7278, "step": 5238 }, { "epoch": 0.86, "learning_rate": 1.7106603153745074e-05, "loss": 0.6392, "step": 5239 }, { "epoch": 0.86, "learning_rate": 1.710413929040736e-05, "loss": 0.9461, "step": 5240 }, { "epoch": 0.86, "learning_rate": 1.7101675427069646e-05, "loss": 0.5835, "step": 5241 }, { "epoch": 0.86, "learning_rate": 1.7099211563731933e-05, "loss": 1.1151, "step": 5242 }, { "epoch": 0.86, "learning_rate": 1.7096747700394218e-05, "loss": 0.5568, "step": 5243 }, { "epoch": 0.86, "learning_rate": 1.7094283837056505e-05, "loss": 1.0553, "step": 5244 }, { "epoch": 0.86, "learning_rate": 1.709181997371879e-05, "loss": 0.7487, "step": 5245 }, { "epoch": 0.86, "learning_rate": 1.7089356110381077e-05, "loss": 0.545, "step": 5246 }, { "epoch": 0.86, "learning_rate": 1.708689224704336e-05, "loss": 0.3529, "step": 5247 }, { "epoch": 0.86, "learning_rate": 1.7084428383705653e-05, "loss": 0.5613, "step": 5248 }, { "epoch": 0.86, "learning_rate": 1.708196452036794e-05, "loss": 0.626, "step": 5249 }, { "epoch": 0.86, "learning_rate": 1.7079500657030225e-05, "loss": 0.4132, "step": 5250 }, { "epoch": 0.86, "learning_rate": 1.7077036793692512e-05, "loss": 0.7725, "step": 5251 }, { "epoch": 0.86, "learning_rate": 1.7074572930354797e-05, "loss": 1.0732, "step": 5252 }, { "epoch": 0.86, "learning_rate": 1.7072109067017084e-05, "loss": 1.1053, "step": 5253 }, { "epoch": 0.86, "learning_rate": 1.706964520367937e-05, "loss": 0.4645, "step": 5254 }, { "epoch": 0.86, "learning_rate": 1.7067181340341656e-05, "loss": 0.5047, "step": 5255 }, { "epoch": 0.86, "learning_rate": 1.706471747700394e-05, "loss": 1.1841, "step": 5256 }, { "epoch": 0.86, "learning_rate": 1.7062253613666228e-05, "loss": 0.7043, "step": 5257 }, { "epoch": 0.86, "learning_rate": 1.7059789750328516e-05, "loss": 1.0613, "step": 5258 }, { "epoch": 0.86, "learning_rate": 1.7057325886990803e-05, "loss": 1.2063, "step": 5259 }, { "epoch": 0.86, "learning_rate": 1.7054862023653088e-05, "loss": 0.7351, "step": 5260 }, { "epoch": 0.86, "learning_rate": 1.7052398160315375e-05, "loss": 1.1353, "step": 5261 }, { "epoch": 0.86, "learning_rate": 1.7049934296977663e-05, "loss": 0.6103, "step": 5262 }, { "epoch": 0.86, "learning_rate": 1.7047470433639947e-05, "loss": 1.2392, "step": 5263 }, { "epoch": 0.86, "learning_rate": 1.7045006570302235e-05, "loss": 0.4917, "step": 5264 }, { "epoch": 0.86, "learning_rate": 1.704254270696452e-05, "loss": 1.172, "step": 5265 }, { "epoch": 0.86, "learning_rate": 1.7040078843626807e-05, "loss": 0.7494, "step": 5266 }, { "epoch": 0.87, "learning_rate": 1.703761498028909e-05, "loss": 0.4692, "step": 5267 }, { "epoch": 0.87, "learning_rate": 1.7035151116951382e-05, "loss": 0.7349, "step": 5268 }, { "epoch": 0.87, "learning_rate": 1.7032687253613667e-05, "loss": 0.613, "step": 5269 }, { "epoch": 0.87, "learning_rate": 1.7030223390275954e-05, "loss": 0.5272, "step": 5270 }, { "epoch": 0.87, "learning_rate": 1.702775952693824e-05, "loss": 0.3231, "step": 5271 }, { "epoch": 0.87, "learning_rate": 1.7025295663600526e-05, "loss": 0.8876, "step": 5272 }, { "epoch": 0.87, "learning_rate": 1.7022831800262814e-05, "loss": 1.2838, "step": 5273 }, { "epoch": 0.87, "learning_rate": 1.70203679369251e-05, "loss": 0.4309, "step": 5274 }, { "epoch": 0.87, "learning_rate": 1.7017904073587386e-05, "loss": 0.4127, "step": 5275 }, { "epoch": 0.87, "learning_rate": 1.701544021024967e-05, "loss": 0.6828, "step": 5276 }, { "epoch": 0.87, "learning_rate": 1.7012976346911958e-05, "loss": 1.4396, "step": 5277 }, { "epoch": 0.87, "learning_rate": 1.7010512483574246e-05, "loss": 0.4407, "step": 5278 }, { "epoch": 0.87, "learning_rate": 1.7008048620236533e-05, "loss": 0.6734, "step": 5279 }, { "epoch": 0.87, "learning_rate": 1.7005584756898818e-05, "loss": 1.0124, "step": 5280 }, { "epoch": 0.87, "learning_rate": 1.7003120893561105e-05, "loss": 0.394, "step": 5281 }, { "epoch": 0.87, "learning_rate": 1.700065703022339e-05, "loss": 0.6847, "step": 5282 }, { "epoch": 0.87, "learning_rate": 1.6998193166885677e-05, "loss": 0.9037, "step": 5283 }, { "epoch": 0.87, "learning_rate": 1.6995729303547965e-05, "loss": 1.0265, "step": 5284 }, { "epoch": 0.87, "learning_rate": 1.699326544021025e-05, "loss": 0.5395, "step": 5285 }, { "epoch": 0.87, "learning_rate": 1.6990801576872537e-05, "loss": 0.7133, "step": 5286 }, { "epoch": 0.87, "learning_rate": 1.698833771353482e-05, "loss": 1.5897, "step": 5287 }, { "epoch": 0.87, "learning_rate": 1.6985873850197112e-05, "loss": 0.9532, "step": 5288 }, { "epoch": 0.87, "learning_rate": 1.6983409986859397e-05, "loss": 1.1445, "step": 5289 }, { "epoch": 0.87, "learning_rate": 1.6980946123521684e-05, "loss": 1.0307, "step": 5290 }, { "epoch": 0.87, "learning_rate": 1.697848226018397e-05, "loss": 0.4155, "step": 5291 }, { "epoch": 0.87, "learning_rate": 1.6976018396846256e-05, "loss": 0.9508, "step": 5292 }, { "epoch": 0.87, "learning_rate": 1.697355453350854e-05, "loss": 0.582, "step": 5293 }, { "epoch": 0.87, "learning_rate": 1.6971090670170828e-05, "loss": 0.932, "step": 5294 }, { "epoch": 0.87, "learning_rate": 1.6968626806833112e-05, "loss": 0.4736, "step": 5295 }, { "epoch": 0.87, "learning_rate": 1.69661629434954e-05, "loss": 0.8805, "step": 5296 }, { "epoch": 0.87, "learning_rate": 1.6963699080157688e-05, "loss": 0.9782, "step": 5297 }, { "epoch": 0.87, "learning_rate": 1.6961235216819976e-05, "loss": 1.1712, "step": 5298 }, { "epoch": 0.87, "learning_rate": 1.6958771353482263e-05, "loss": 0.9917, "step": 5299 }, { "epoch": 0.87, "learning_rate": 1.6956307490144547e-05, "loss": 1.0927, "step": 5300 }, { "epoch": 0.87, "learning_rate": 1.6953843626806835e-05, "loss": 1.4588, "step": 5301 }, { "epoch": 0.87, "learning_rate": 1.695137976346912e-05, "loss": 0.6364, "step": 5302 }, { "epoch": 0.87, "learning_rate": 1.6948915900131407e-05, "loss": 0.8934, "step": 5303 }, { "epoch": 0.87, "learning_rate": 1.694645203679369e-05, "loss": 0.6091, "step": 5304 }, { "epoch": 0.87, "learning_rate": 1.694398817345598e-05, "loss": 0.5118, "step": 5305 }, { "epoch": 0.87, "learning_rate": 1.6941524310118263e-05, "loss": 0.9702, "step": 5306 }, { "epoch": 0.87, "learning_rate": 1.693906044678055e-05, "loss": 0.8058, "step": 5307 }, { "epoch": 0.87, "learning_rate": 1.6936596583442842e-05, "loss": 1.0518, "step": 5308 }, { "epoch": 0.87, "learning_rate": 1.6934132720105126e-05, "loss": 0.4132, "step": 5309 }, { "epoch": 0.87, "learning_rate": 1.6931668856767414e-05, "loss": 0.6904, "step": 5310 }, { "epoch": 0.87, "learning_rate": 1.69292049934297e-05, "loss": 0.6783, "step": 5311 }, { "epoch": 0.87, "learning_rate": 1.6926741130091986e-05, "loss": 0.7287, "step": 5312 }, { "epoch": 0.87, "learning_rate": 1.692427726675427e-05, "loss": 1.042, "step": 5313 }, { "epoch": 0.87, "learning_rate": 1.6921813403416558e-05, "loss": 0.8944, "step": 5314 }, { "epoch": 0.87, "learning_rate": 1.6919349540078842e-05, "loss": 0.2695, "step": 5315 }, { "epoch": 0.87, "learning_rate": 1.691688567674113e-05, "loss": 0.475, "step": 5316 }, { "epoch": 0.87, "learning_rate": 1.6914421813403414e-05, "loss": 0.4595, "step": 5317 }, { "epoch": 0.87, "learning_rate": 1.6911957950065705e-05, "loss": 1.5849, "step": 5318 }, { "epoch": 0.87, "learning_rate": 1.690949408672799e-05, "loss": 1.1456, "step": 5319 }, { "epoch": 0.87, "learning_rate": 1.6907030223390277e-05, "loss": 0.4078, "step": 5320 }, { "epoch": 0.87, "learning_rate": 1.6904566360052565e-05, "loss": 0.802, "step": 5321 }, { "epoch": 0.87, "learning_rate": 1.690210249671485e-05, "loss": 0.9089, "step": 5322 }, { "epoch": 0.87, "learning_rate": 1.6899638633377137e-05, "loss": 1.2882, "step": 5323 }, { "epoch": 0.87, "learning_rate": 1.689717477003942e-05, "loss": 1.2496, "step": 5324 }, { "epoch": 0.87, "learning_rate": 1.689471090670171e-05, "loss": 1.0483, "step": 5325 }, { "epoch": 0.87, "learning_rate": 1.6892247043363993e-05, "loss": 0.5815, "step": 5326 }, { "epoch": 0.88, "learning_rate": 1.688978318002628e-05, "loss": 0.9688, "step": 5327 }, { "epoch": 0.88, "learning_rate": 1.688731931668857e-05, "loss": 0.8926, "step": 5328 }, { "epoch": 0.88, "learning_rate": 1.6884855453350856e-05, "loss": 0.7387, "step": 5329 }, { "epoch": 0.88, "learning_rate": 1.688239159001314e-05, "loss": 0.7343, "step": 5330 }, { "epoch": 0.88, "learning_rate": 1.6879927726675428e-05, "loss": 1.1977, "step": 5331 }, { "epoch": 0.88, "learning_rate": 1.6877463863337716e-05, "loss": 0.6621, "step": 5332 }, { "epoch": 0.88, "learning_rate": 1.6875e-05, "loss": 0.4964, "step": 5333 }, { "epoch": 0.88, "learning_rate": 1.6872536136662288e-05, "loss": 1.0358, "step": 5334 }, { "epoch": 0.88, "learning_rate": 1.6870072273324572e-05, "loss": 1.0156, "step": 5335 }, { "epoch": 0.88, "learning_rate": 1.686760840998686e-05, "loss": 0.979, "step": 5336 }, { "epoch": 0.88, "learning_rate": 1.6865144546649144e-05, "loss": 0.5563, "step": 5337 }, { "epoch": 0.88, "learning_rate": 1.6862680683311432e-05, "loss": 0.5262, "step": 5338 }, { "epoch": 0.88, "learning_rate": 1.686021681997372e-05, "loss": 0.3768, "step": 5339 }, { "epoch": 0.88, "learning_rate": 1.6857752956636007e-05, "loss": 0.7447, "step": 5340 }, { "epoch": 0.88, "learning_rate": 1.685528909329829e-05, "loss": 0.9239, "step": 5341 }, { "epoch": 0.88, "learning_rate": 1.685282522996058e-05, "loss": 1.1783, "step": 5342 }, { "epoch": 0.88, "learning_rate": 1.6850361366622863e-05, "loss": 0.3591, "step": 5343 }, { "epoch": 0.88, "learning_rate": 1.684789750328515e-05, "loss": 1.0073, "step": 5344 }, { "epoch": 0.88, "learning_rate": 1.684543363994744e-05, "loss": 1.1241, "step": 5345 }, { "epoch": 0.88, "learning_rate": 1.6842969776609723e-05, "loss": 1.4233, "step": 5346 }, { "epoch": 0.88, "learning_rate": 1.684050591327201e-05, "loss": 0.7534, "step": 5347 }, { "epoch": 0.88, "learning_rate": 1.6838042049934295e-05, "loss": 0.7544, "step": 5348 }, { "epoch": 0.88, "learning_rate": 1.6835578186596586e-05, "loss": 0.812, "step": 5349 }, { "epoch": 0.88, "learning_rate": 1.683311432325887e-05, "loss": 0.4686, "step": 5350 }, { "epoch": 0.88, "learning_rate": 1.6830650459921158e-05, "loss": 1.6887, "step": 5351 }, { "epoch": 0.88, "learning_rate": 1.6828186596583442e-05, "loss": 1.2954, "step": 5352 }, { "epoch": 0.88, "learning_rate": 1.682572273324573e-05, "loss": 1.0075, "step": 5353 }, { "epoch": 0.88, "learning_rate": 1.6823258869908014e-05, "loss": 0.8687, "step": 5354 }, { "epoch": 0.88, "learning_rate": 1.6820795006570302e-05, "loss": 0.5802, "step": 5355 }, { "epoch": 0.88, "learning_rate": 1.681833114323259e-05, "loss": 0.4535, "step": 5356 }, { "epoch": 0.88, "learning_rate": 1.6815867279894874e-05, "loss": 0.7482, "step": 5357 }, { "epoch": 0.88, "learning_rate": 1.681340341655716e-05, "loss": 0.9093, "step": 5358 }, { "epoch": 0.88, "learning_rate": 1.681093955321945e-05, "loss": 0.8167, "step": 5359 }, { "epoch": 0.88, "learning_rate": 1.6808475689881737e-05, "loss": 0.7638, "step": 5360 }, { "epoch": 0.88, "learning_rate": 1.680601182654402e-05, "loss": 0.9336, "step": 5361 }, { "epoch": 0.88, "learning_rate": 1.680354796320631e-05, "loss": 1.44, "step": 5362 }, { "epoch": 0.88, "learning_rate": 1.6801084099868593e-05, "loss": 1.186, "step": 5363 }, { "epoch": 0.88, "learning_rate": 1.679862023653088e-05, "loss": 0.5339, "step": 5364 }, { "epoch": 0.88, "learning_rate": 1.6796156373193165e-05, "loss": 0.6509, "step": 5365 }, { "epoch": 0.88, "learning_rate": 1.6793692509855453e-05, "loss": 0.8908, "step": 5366 }, { "epoch": 0.88, "learning_rate": 1.6791228646517737e-05, "loss": 0.8847, "step": 5367 }, { "epoch": 0.88, "learning_rate": 1.6788764783180025e-05, "loss": 0.49, "step": 5368 }, { "epoch": 0.88, "learning_rate": 1.6786300919842316e-05, "loss": 0.5824, "step": 5369 }, { "epoch": 0.88, "learning_rate": 1.67838370565046e-05, "loss": 0.6948, "step": 5370 }, { "epoch": 0.88, "learning_rate": 1.6781373193166888e-05, "loss": 0.9109, "step": 5371 }, { "epoch": 0.88, "learning_rate": 1.6778909329829172e-05, "loss": 1.2595, "step": 5372 }, { "epoch": 0.88, "learning_rate": 1.677644546649146e-05, "loss": 0.4524, "step": 5373 }, { "epoch": 0.88, "learning_rate": 1.6773981603153744e-05, "loss": 0.5424, "step": 5374 }, { "epoch": 0.88, "learning_rate": 1.6771517739816032e-05, "loss": 0.6637, "step": 5375 }, { "epoch": 0.88, "learning_rate": 1.6769053876478316e-05, "loss": 0.9077, "step": 5376 }, { "epoch": 0.88, "learning_rate": 1.6766590013140604e-05, "loss": 1.1537, "step": 5377 }, { "epoch": 0.88, "learning_rate": 1.6764126149802888e-05, "loss": 0.3049, "step": 5378 }, { "epoch": 0.88, "learning_rate": 1.676166228646518e-05, "loss": 1.1067, "step": 5379 }, { "epoch": 0.88, "learning_rate": 1.6759198423127467e-05, "loss": 0.3768, "step": 5380 }, { "epoch": 0.88, "learning_rate": 1.675673455978975e-05, "loss": 0.9209, "step": 5381 }, { "epoch": 0.88, "learning_rate": 1.675427069645204e-05, "loss": 0.7677, "step": 5382 }, { "epoch": 0.88, "learning_rate": 1.6751806833114323e-05, "loss": 0.9422, "step": 5383 }, { "epoch": 0.88, "learning_rate": 1.674934296977661e-05, "loss": 1.623, "step": 5384 }, { "epoch": 0.88, "learning_rate": 1.6746879106438895e-05, "loss": 0.7431, "step": 5385 }, { "epoch": 0.88, "learning_rate": 1.6744415243101183e-05, "loss": 1.6764, "step": 5386 }, { "epoch": 0.88, "learning_rate": 1.6741951379763467e-05, "loss": 0.457, "step": 5387 }, { "epoch": 0.89, "learning_rate": 1.6739487516425755e-05, "loss": 1.138, "step": 5388 }, { "epoch": 0.89, "learning_rate": 1.6737023653088042e-05, "loss": 1.0265, "step": 5389 }, { "epoch": 0.89, "learning_rate": 1.673455978975033e-05, "loss": 0.4446, "step": 5390 }, { "epoch": 0.89, "learning_rate": 1.6732095926412614e-05, "loss": 0.9874, "step": 5391 }, { "epoch": 0.89, "learning_rate": 1.6729632063074902e-05, "loss": 0.5938, "step": 5392 }, { "epoch": 0.89, "learning_rate": 1.672716819973719e-05, "loss": 0.2798, "step": 5393 }, { "epoch": 0.89, "learning_rate": 1.6724704336399474e-05, "loss": 1.2357, "step": 5394 }, { "epoch": 0.89, "learning_rate": 1.6722240473061762e-05, "loss": 0.646, "step": 5395 }, { "epoch": 0.89, "learning_rate": 1.6719776609724046e-05, "loss": 0.8639, "step": 5396 }, { "epoch": 0.89, "learning_rate": 1.6717312746386334e-05, "loss": 1.1869, "step": 5397 }, { "epoch": 0.89, "learning_rate": 1.6714848883048618e-05, "loss": 0.5143, "step": 5398 }, { "epoch": 0.89, "learning_rate": 1.671238501971091e-05, "loss": 0.5001, "step": 5399 }, { "epoch": 0.89, "learning_rate": 1.6709921156373193e-05, "loss": 0.754, "step": 5400 }, { "epoch": 0.89, "learning_rate": 1.670745729303548e-05, "loss": 0.7255, "step": 5401 }, { "epoch": 0.89, "learning_rate": 1.6704993429697765e-05, "loss": 0.6274, "step": 5402 }, { "epoch": 0.89, "learning_rate": 1.6702529566360053e-05, "loss": 0.5237, "step": 5403 }, { "epoch": 0.89, "learning_rate": 1.670006570302234e-05, "loss": 0.7216, "step": 5404 }, { "epoch": 0.89, "learning_rate": 1.6697601839684625e-05, "loss": 0.8064, "step": 5405 }, { "epoch": 0.89, "learning_rate": 1.6695137976346913e-05, "loss": 0.6266, "step": 5406 }, { "epoch": 0.89, "learning_rate": 1.6692674113009197e-05, "loss": 0.998, "step": 5407 }, { "epoch": 0.89, "learning_rate": 1.6690210249671485e-05, "loss": 0.5808, "step": 5408 }, { "epoch": 0.89, "learning_rate": 1.6687746386333772e-05, "loss": 0.9868, "step": 5409 }, { "epoch": 0.89, "learning_rate": 1.668528252299606e-05, "loss": 0.9833, "step": 5410 }, { "epoch": 0.89, "learning_rate": 1.6682818659658344e-05, "loss": 0.9969, "step": 5411 }, { "epoch": 0.89, "learning_rate": 1.6680354796320632e-05, "loss": 0.5941, "step": 5412 }, { "epoch": 0.89, "learning_rate": 1.6677890932982916e-05, "loss": 0.9089, "step": 5413 }, { "epoch": 0.89, "learning_rate": 1.6675427069645204e-05, "loss": 1.0224, "step": 5414 }, { "epoch": 0.89, "learning_rate": 1.667296320630749e-05, "loss": 0.7113, "step": 5415 }, { "epoch": 0.89, "learning_rate": 1.6670499342969776e-05, "loss": 1.161, "step": 5416 }, { "epoch": 0.89, "learning_rate": 1.6668035479632064e-05, "loss": 1.5421, "step": 5417 }, { "epoch": 0.89, "learning_rate": 1.6665571616294348e-05, "loss": 0.6337, "step": 5418 }, { "epoch": 0.89, "learning_rate": 1.666310775295664e-05, "loss": 0.8108, "step": 5419 }, { "epoch": 0.89, "learning_rate": 1.6660643889618923e-05, "loss": 1.0917, "step": 5420 }, { "epoch": 0.89, "learning_rate": 1.665818002628121e-05, "loss": 0.512, "step": 5421 }, { "epoch": 0.89, "learning_rate": 1.6655716162943495e-05, "loss": 0.4694, "step": 5422 }, { "epoch": 0.89, "learning_rate": 1.6653252299605783e-05, "loss": 0.4219, "step": 5423 }, { "epoch": 0.89, "learning_rate": 1.6650788436268067e-05, "loss": 1.2196, "step": 5424 }, { "epoch": 0.89, "learning_rate": 1.6648324572930355e-05, "loss": 0.8194, "step": 5425 }, { "epoch": 0.89, "learning_rate": 1.664586070959264e-05, "loss": 0.4631, "step": 5426 }, { "epoch": 0.89, "learning_rate": 1.6643396846254927e-05, "loss": 0.8336, "step": 5427 }, { "epoch": 0.89, "learning_rate": 1.6640932982917214e-05, "loss": 0.6925, "step": 5428 }, { "epoch": 0.89, "learning_rate": 1.6638469119579502e-05, "loss": 0.9053, "step": 5429 }, { "epoch": 0.89, "learning_rate": 1.663600525624179e-05, "loss": 0.9608, "step": 5430 }, { "epoch": 0.89, "learning_rate": 1.6633541392904074e-05, "loss": 0.7307, "step": 5431 }, { "epoch": 0.89, "learning_rate": 1.6631077529566362e-05, "loss": 1.3525, "step": 5432 }, { "epoch": 0.89, "learning_rate": 1.6628613666228646e-05, "loss": 0.5659, "step": 5433 }, { "epoch": 0.89, "learning_rate": 1.6626149802890934e-05, "loss": 1.2357, "step": 5434 }, { "epoch": 0.89, "learning_rate": 1.6623685939553218e-05, "loss": 1.3256, "step": 5435 }, { "epoch": 0.89, "learning_rate": 1.6621222076215506e-05, "loss": 0.7182, "step": 5436 }, { "epoch": 0.89, "learning_rate": 1.661875821287779e-05, "loss": 1.2705, "step": 5437 }, { "epoch": 0.89, "learning_rate": 1.6616294349540078e-05, "loss": 0.9139, "step": 5438 }, { "epoch": 0.89, "learning_rate": 1.661383048620237e-05, "loss": 1.007, "step": 5439 }, { "epoch": 0.89, "learning_rate": 1.6611366622864653e-05, "loss": 0.7176, "step": 5440 }, { "epoch": 0.89, "learning_rate": 1.660890275952694e-05, "loss": 0.7646, "step": 5441 }, { "epoch": 0.89, "learning_rate": 1.6606438896189225e-05, "loss": 0.8529, "step": 5442 }, { "epoch": 0.89, "learning_rate": 1.6603975032851513e-05, "loss": 1.4655, "step": 5443 }, { "epoch": 0.89, "learning_rate": 1.6601511169513797e-05, "loss": 0.5436, "step": 5444 }, { "epoch": 0.89, "learning_rate": 1.6599047306176085e-05, "loss": 0.4126, "step": 5445 }, { "epoch": 0.89, "learning_rate": 1.659658344283837e-05, "loss": 1.8022, "step": 5446 }, { "epoch": 0.89, "learning_rate": 1.6594119579500657e-05, "loss": 1.0051, "step": 5447 }, { "epoch": 0.89, "learning_rate": 1.659165571616294e-05, "loss": 0.6499, "step": 5448 }, { "epoch": 0.9, "learning_rate": 1.6589191852825232e-05, "loss": 0.7955, "step": 5449 }, { "epoch": 0.9, "learning_rate": 1.6586727989487516e-05, "loss": 0.4688, "step": 5450 }, { "epoch": 0.9, "learning_rate": 1.6584264126149804e-05, "loss": 0.9508, "step": 5451 }, { "epoch": 0.9, "learning_rate": 1.658180026281209e-05, "loss": 0.6333, "step": 5452 }, { "epoch": 0.9, "learning_rate": 1.6579336399474376e-05, "loss": 0.5017, "step": 5453 }, { "epoch": 0.9, "learning_rate": 1.6576872536136664e-05, "loss": 0.4224, "step": 5454 }, { "epoch": 0.9, "learning_rate": 1.6574408672798948e-05, "loss": 0.7248, "step": 5455 }, { "epoch": 0.9, "learning_rate": 1.6571944809461236e-05, "loss": 0.7306, "step": 5456 }, { "epoch": 0.9, "learning_rate": 1.656948094612352e-05, "loss": 0.715, "step": 5457 }, { "epoch": 0.9, "learning_rate": 1.6567017082785808e-05, "loss": 0.4212, "step": 5458 }, { "epoch": 0.9, "learning_rate": 1.6564553219448095e-05, "loss": 0.5567, "step": 5459 }, { "epoch": 0.9, "learning_rate": 1.6562089356110383e-05, "loss": 1.1266, "step": 5460 }, { "epoch": 0.9, "learning_rate": 1.6559625492772667e-05, "loss": 1.052, "step": 5461 }, { "epoch": 0.9, "learning_rate": 1.6557161629434955e-05, "loss": 0.4813, "step": 5462 }, { "epoch": 0.9, "learning_rate": 1.6554697766097243e-05, "loss": 1.473, "step": 5463 }, { "epoch": 0.9, "learning_rate": 1.6552233902759527e-05, "loss": 0.5265, "step": 5464 }, { "epoch": 0.9, "learning_rate": 1.6549770039421815e-05, "loss": 0.5576, "step": 5465 }, { "epoch": 0.9, "learning_rate": 1.65473061760841e-05, "loss": 0.6279, "step": 5466 }, { "epoch": 0.9, "learning_rate": 1.6544842312746387e-05, "loss": 0.6188, "step": 5467 }, { "epoch": 0.9, "learning_rate": 1.654237844940867e-05, "loss": 1.2113, "step": 5468 }, { "epoch": 0.9, "learning_rate": 1.6539914586070962e-05, "loss": 0.6023, "step": 5469 }, { "epoch": 0.9, "learning_rate": 1.6537450722733246e-05, "loss": 0.3144, "step": 5470 }, { "epoch": 0.9, "learning_rate": 1.6534986859395534e-05, "loss": 0.5842, "step": 5471 }, { "epoch": 0.9, "learning_rate": 1.6532522996057818e-05, "loss": 1.2732, "step": 5472 }, { "epoch": 0.9, "learning_rate": 1.6530059132720106e-05, "loss": 1.6711, "step": 5473 }, { "epoch": 0.9, "learning_rate": 1.652759526938239e-05, "loss": 0.8846, "step": 5474 }, { "epoch": 0.9, "learning_rate": 1.6525131406044678e-05, "loss": 0.7997, "step": 5475 }, { "epoch": 0.9, "learning_rate": 1.6522667542706965e-05, "loss": 0.7282, "step": 5476 }, { "epoch": 0.9, "learning_rate": 1.652020367936925e-05, "loss": 0.3978, "step": 5477 }, { "epoch": 0.9, "learning_rate": 1.6517739816031537e-05, "loss": 0.261, "step": 5478 }, { "epoch": 0.9, "learning_rate": 1.6515275952693825e-05, "loss": 0.5822, "step": 5479 }, { "epoch": 0.9, "learning_rate": 1.6512812089356113e-05, "loss": 0.4932, "step": 5480 }, { "epoch": 0.9, "learning_rate": 1.6510348226018397e-05, "loss": 0.8317, "step": 5481 }, { "epoch": 0.9, "learning_rate": 1.6507884362680685e-05, "loss": 0.6673, "step": 5482 }, { "epoch": 0.9, "learning_rate": 1.650542049934297e-05, "loss": 1.0759, "step": 5483 }, { "epoch": 0.9, "learning_rate": 1.6502956636005257e-05, "loss": 0.3272, "step": 5484 }, { "epoch": 0.9, "learning_rate": 1.650049277266754e-05, "loss": 0.9734, "step": 5485 }, { "epoch": 0.9, "learning_rate": 1.649802890932983e-05, "loss": 0.4158, "step": 5486 }, { "epoch": 0.9, "learning_rate": 1.6495565045992116e-05, "loss": 1.3501, "step": 5487 }, { "epoch": 0.9, "learning_rate": 1.64931011826544e-05, "loss": 0.5035, "step": 5488 }, { "epoch": 0.9, "learning_rate": 1.6490637319316692e-05, "loss": 0.4164, "step": 5489 }, { "epoch": 0.9, "learning_rate": 1.6488173455978976e-05, "loss": 0.9437, "step": 5490 }, { "epoch": 0.9, "learning_rate": 1.6485709592641264e-05, "loss": 1.1893, "step": 5491 }, { "epoch": 0.9, "learning_rate": 1.6483245729303548e-05, "loss": 0.5844, "step": 5492 }, { "epoch": 0.9, "learning_rate": 1.6480781865965836e-05, "loss": 1.5528, "step": 5493 }, { "epoch": 0.9, "learning_rate": 1.647831800262812e-05, "loss": 0.7817, "step": 5494 }, { "epoch": 0.9, "learning_rate": 1.6475854139290408e-05, "loss": 1.0706, "step": 5495 }, { "epoch": 0.9, "learning_rate": 1.6473390275952692e-05, "loss": 0.9952, "step": 5496 }, { "epoch": 0.9, "learning_rate": 1.647092641261498e-05, "loss": 0.9626, "step": 5497 }, { "epoch": 0.9, "learning_rate": 1.6468462549277264e-05, "loss": 1.1107, "step": 5498 }, { "epoch": 0.9, "learning_rate": 1.6465998685939555e-05, "loss": 0.8539, "step": 5499 }, { "epoch": 0.9, "learning_rate": 1.6463534822601843e-05, "loss": 0.5779, "step": 5500 }, { "epoch": 0.9, "eval_exact_match": 86.16840113528855, "eval_f1": 92.56740481111956, "step": 5500 }, { "epoch": 0.9, "learning_rate": 1.6461070959264127e-05, "loss": 0.8281, "step": 5501 }, { "epoch": 0.9, "learning_rate": 1.6458607095926415e-05, "loss": 0.6785, "step": 5502 }, { "epoch": 0.9, "learning_rate": 1.64561432325887e-05, "loss": 1.2642, "step": 5503 }, { "epoch": 0.9, "learning_rate": 1.6453679369250987e-05, "loss": 0.5273, "step": 5504 }, { "epoch": 0.9, "learning_rate": 1.645121550591327e-05, "loss": 0.4515, "step": 5505 }, { "epoch": 0.9, "learning_rate": 1.644875164257556e-05, "loss": 0.571, "step": 5506 }, { "epoch": 0.9, "learning_rate": 1.6446287779237843e-05, "loss": 0.6284, "step": 5507 }, { "epoch": 0.9, "learning_rate": 1.644382391590013e-05, "loss": 0.9864, "step": 5508 }, { "epoch": 0.9, "learning_rate": 1.6441360052562418e-05, "loss": 0.7293, "step": 5509 }, { "epoch": 0.91, "learning_rate": 1.6438896189224706e-05, "loss": 0.6806, "step": 5510 }, { "epoch": 0.91, "learning_rate": 1.6436432325886994e-05, "loss": 0.4175, "step": 5511 }, { "epoch": 0.91, "learning_rate": 1.6433968462549278e-05, "loss": 0.5703, "step": 5512 }, { "epoch": 0.91, "learning_rate": 1.6431504599211566e-05, "loss": 0.496, "step": 5513 }, { "epoch": 0.91, "learning_rate": 1.642904073587385e-05, "loss": 0.8013, "step": 5514 }, { "epoch": 0.91, "learning_rate": 1.6426576872536137e-05, "loss": 0.537, "step": 5515 }, { "epoch": 0.91, "learning_rate": 1.6424113009198422e-05, "loss": 0.4561, "step": 5516 }, { "epoch": 0.91, "learning_rate": 1.642164914586071e-05, "loss": 0.9115, "step": 5517 }, { "epoch": 0.91, "learning_rate": 1.6419185282522994e-05, "loss": 1.0587, "step": 5518 }, { "epoch": 0.91, "learning_rate": 1.6416721419185285e-05, "loss": 0.997, "step": 5519 }, { "epoch": 0.91, "learning_rate": 1.641425755584757e-05, "loss": 0.2953, "step": 5520 }, { "epoch": 0.91, "learning_rate": 1.6411793692509857e-05, "loss": 1.028, "step": 5521 }, { "epoch": 0.91, "learning_rate": 1.640932982917214e-05, "loss": 1.1984, "step": 5522 }, { "epoch": 0.91, "learning_rate": 1.640686596583443e-05, "loss": 0.7762, "step": 5523 }, { "epoch": 0.91, "learning_rate": 1.6404402102496716e-05, "loss": 0.9332, "step": 5524 }, { "epoch": 0.91, "learning_rate": 1.6401938239159e-05, "loss": 0.7873, "step": 5525 }, { "epoch": 0.91, "learning_rate": 1.639947437582129e-05, "loss": 0.918, "step": 5526 }, { "epoch": 0.91, "learning_rate": 1.6397010512483573e-05, "loss": 0.6622, "step": 5527 }, { "epoch": 0.91, "learning_rate": 1.639454664914586e-05, "loss": 1.0202, "step": 5528 }, { "epoch": 0.91, "learning_rate": 1.6392082785808148e-05, "loss": 0.8583, "step": 5529 }, { "epoch": 0.91, "learning_rate": 1.6389618922470436e-05, "loss": 0.6077, "step": 5530 }, { "epoch": 0.91, "learning_rate": 1.638715505913272e-05, "loss": 1.28, "step": 5531 }, { "epoch": 0.91, "learning_rate": 1.6384691195795008e-05, "loss": 1.2492, "step": 5532 }, { "epoch": 0.91, "learning_rate": 1.6382227332457292e-05, "loss": 0.4394, "step": 5533 }, { "epoch": 0.91, "learning_rate": 1.637976346911958e-05, "loss": 0.5058, "step": 5534 }, { "epoch": 0.91, "learning_rate": 1.6377299605781867e-05, "loss": 0.8114, "step": 5535 }, { "epoch": 0.91, "learning_rate": 1.637483574244415e-05, "loss": 0.7296, "step": 5536 }, { "epoch": 0.91, "learning_rate": 1.637237187910644e-05, "loss": 0.7251, "step": 5537 }, { "epoch": 0.91, "learning_rate": 1.6369908015768724e-05, "loss": 0.9911, "step": 5538 }, { "epoch": 0.91, "learning_rate": 1.6367444152431015e-05, "loss": 0.8074, "step": 5539 }, { "epoch": 0.91, "learning_rate": 1.63649802890933e-05, "loss": 0.9121, "step": 5540 }, { "epoch": 0.91, "learning_rate": 1.6362516425755587e-05, "loss": 1.0309, "step": 5541 }, { "epoch": 0.91, "learning_rate": 1.636005256241787e-05, "loss": 0.8463, "step": 5542 }, { "epoch": 0.91, "learning_rate": 1.635758869908016e-05, "loss": 0.5383, "step": 5543 }, { "epoch": 0.91, "learning_rate": 1.6355124835742443e-05, "loss": 0.904, "step": 5544 }, { "epoch": 0.91, "learning_rate": 1.635266097240473e-05, "loss": 0.8451, "step": 5545 }, { "epoch": 0.91, "learning_rate": 1.6350197109067018e-05, "loss": 0.5476, "step": 5546 }, { "epoch": 0.91, "learning_rate": 1.6347733245729303e-05, "loss": 0.8494, "step": 5547 }, { "epoch": 0.91, "learning_rate": 1.634526938239159e-05, "loss": 0.5745, "step": 5548 }, { "epoch": 0.91, "learning_rate": 1.6342805519053878e-05, "loss": 1.0639, "step": 5549 }, { "epoch": 0.91, "learning_rate": 1.6340341655716166e-05, "loss": 1.0693, "step": 5550 }, { "epoch": 0.91, "learning_rate": 1.633787779237845e-05, "loss": 1.6294, "step": 5551 }, { "epoch": 0.91, "learning_rate": 1.6335413929040738e-05, "loss": 1.498, "step": 5552 }, { "epoch": 0.91, "learning_rate": 1.6332950065703022e-05, "loss": 0.7247, "step": 5553 }, { "epoch": 0.91, "learning_rate": 1.633048620236531e-05, "loss": 0.5139, "step": 5554 }, { "epoch": 0.91, "learning_rate": 1.6328022339027594e-05, "loss": 0.8106, "step": 5555 }, { "epoch": 0.91, "learning_rate": 1.632555847568988e-05, "loss": 0.7501, "step": 5556 }, { "epoch": 0.91, "learning_rate": 1.6323094612352166e-05, "loss": 0.7508, "step": 5557 }, { "epoch": 0.91, "learning_rate": 1.6320630749014453e-05, "loss": 0.9221, "step": 5558 }, { "epoch": 0.91, "learning_rate": 1.6318166885676745e-05, "loss": 0.8355, "step": 5559 }, { "epoch": 0.91, "learning_rate": 1.631570302233903e-05, "loss": 1.32, "step": 5560 }, { "epoch": 0.91, "learning_rate": 1.6313239159001317e-05, "loss": 0.7633, "step": 5561 }, { "epoch": 0.91, "learning_rate": 1.63107752956636e-05, "loss": 1.241, "step": 5562 }, { "epoch": 0.91, "learning_rate": 1.630831143232589e-05, "loss": 1.1481, "step": 5563 }, { "epoch": 0.91, "learning_rate": 1.6305847568988173e-05, "loss": 0.4679, "step": 5564 }, { "epoch": 0.91, "learning_rate": 1.630338370565046e-05, "loss": 0.6272, "step": 5565 }, { "epoch": 0.91, "learning_rate": 1.6300919842312745e-05, "loss": 0.6415, "step": 5566 }, { "epoch": 0.91, "learning_rate": 1.6298455978975032e-05, "loss": 0.7435, "step": 5567 }, { "epoch": 0.91, "learning_rate": 1.6295992115637317e-05, "loss": 1.0979, "step": 5568 }, { "epoch": 0.91, "learning_rate": 1.6293528252299608e-05, "loss": 0.4877, "step": 5569 }, { "epoch": 0.91, "learning_rate": 1.6291064388961895e-05, "loss": 0.5731, "step": 5570 }, { "epoch": 0.92, "learning_rate": 1.628860052562418e-05, "loss": 0.7367, "step": 5571 }, { "epoch": 0.92, "learning_rate": 1.6286136662286467e-05, "loss": 1.6087, "step": 5572 }, { "epoch": 0.92, "learning_rate": 1.6283672798948752e-05, "loss": 0.3263, "step": 5573 }, { "epoch": 0.92, "learning_rate": 1.628120893561104e-05, "loss": 0.4089, "step": 5574 }, { "epoch": 0.92, "learning_rate": 1.6278745072273324e-05, "loss": 0.3986, "step": 5575 }, { "epoch": 0.92, "learning_rate": 1.627628120893561e-05, "loss": 0.7185, "step": 5576 }, { "epoch": 0.92, "learning_rate": 1.6273817345597896e-05, "loss": 1.0883, "step": 5577 }, { "epoch": 0.92, "learning_rate": 1.6271353482260183e-05, "loss": 1.0061, "step": 5578 }, { "epoch": 0.92, "learning_rate": 1.626888961892247e-05, "loss": 0.9693, "step": 5579 }, { "epoch": 0.92, "learning_rate": 1.626642575558476e-05, "loss": 0.7124, "step": 5580 }, { "epoch": 0.92, "learning_rate": 1.6263961892247043e-05, "loss": 0.4773, "step": 5581 }, { "epoch": 0.92, "learning_rate": 1.626149802890933e-05, "loss": 0.3325, "step": 5582 }, { "epoch": 0.92, "learning_rate": 1.625903416557162e-05, "loss": 0.6267, "step": 5583 }, { "epoch": 0.92, "learning_rate": 1.6256570302233903e-05, "loss": 0.5521, "step": 5584 }, { "epoch": 0.92, "learning_rate": 1.625410643889619e-05, "loss": 0.6193, "step": 5585 }, { "epoch": 0.92, "learning_rate": 1.6251642575558475e-05, "loss": 0.622, "step": 5586 }, { "epoch": 0.92, "learning_rate": 1.6249178712220762e-05, "loss": 0.5513, "step": 5587 }, { "epoch": 0.92, "learning_rate": 1.6246714848883047e-05, "loss": 0.3422, "step": 5588 }, { "epoch": 0.92, "learning_rate": 1.6244250985545338e-05, "loss": 0.9716, "step": 5589 }, { "epoch": 0.92, "learning_rate": 1.6241787122207622e-05, "loss": 1.6703, "step": 5590 }, { "epoch": 0.92, "learning_rate": 1.623932325886991e-05, "loss": 0.8649, "step": 5591 }, { "epoch": 0.92, "learning_rate": 1.6236859395532194e-05, "loss": 0.7572, "step": 5592 }, { "epoch": 0.92, "learning_rate": 1.623439553219448e-05, "loss": 0.7834, "step": 5593 }, { "epoch": 0.92, "learning_rate": 1.623193166885677e-05, "loss": 0.5672, "step": 5594 }, { "epoch": 0.92, "learning_rate": 1.6229467805519054e-05, "loss": 0.6945, "step": 5595 }, { "epoch": 0.92, "learning_rate": 1.622700394218134e-05, "loss": 0.7849, "step": 5596 }, { "epoch": 0.92, "learning_rate": 1.6224540078843625e-05, "loss": 1.1962, "step": 5597 }, { "epoch": 0.92, "learning_rate": 1.6222076215505913e-05, "loss": 0.4316, "step": 5598 }, { "epoch": 0.92, "learning_rate": 1.62196123521682e-05, "loss": 1.1367, "step": 5599 }, { "epoch": 0.92, "learning_rate": 1.621714848883049e-05, "loss": 0.3748, "step": 5600 }, { "epoch": 0.92, "learning_rate": 1.6214684625492773e-05, "loss": 1.0244, "step": 5601 }, { "epoch": 0.92, "learning_rate": 1.621222076215506e-05, "loss": 0.9075, "step": 5602 }, { "epoch": 0.92, "learning_rate": 1.6209756898817345e-05, "loss": 0.5399, "step": 5603 }, { "epoch": 0.92, "learning_rate": 1.6207293035479632e-05, "loss": 0.5241, "step": 5604 }, { "epoch": 0.92, "learning_rate": 1.6204829172141917e-05, "loss": 0.5575, "step": 5605 }, { "epoch": 0.92, "learning_rate": 1.6202365308804204e-05, "loss": 0.4186, "step": 5606 }, { "epoch": 0.92, "learning_rate": 1.6199901445466492e-05, "loss": 0.6461, "step": 5607 }, { "epoch": 0.92, "learning_rate": 1.6197437582128776e-05, "loss": 0.7867, "step": 5608 }, { "epoch": 0.92, "learning_rate": 1.6194973718791067e-05, "loss": 0.3776, "step": 5609 }, { "epoch": 0.92, "learning_rate": 1.6192509855453352e-05, "loss": 0.4996, "step": 5610 }, { "epoch": 0.92, "learning_rate": 1.619004599211564e-05, "loss": 0.3871, "step": 5611 }, { "epoch": 0.92, "learning_rate": 1.6187582128777924e-05, "loss": 1.0599, "step": 5612 }, { "epoch": 0.92, "learning_rate": 1.618511826544021e-05, "loss": 0.542, "step": 5613 }, { "epoch": 0.92, "learning_rate": 1.6182654402102496e-05, "loss": 1.054, "step": 5614 }, { "epoch": 0.92, "learning_rate": 1.6180190538764783e-05, "loss": 0.9944, "step": 5615 }, { "epoch": 0.92, "learning_rate": 1.6177726675427068e-05, "loss": 1.409, "step": 5616 }, { "epoch": 0.92, "learning_rate": 1.6175262812089355e-05, "loss": 0.7302, "step": 5617 }, { "epoch": 0.92, "learning_rate": 1.6172798948751643e-05, "loss": 1.3591, "step": 5618 }, { "epoch": 0.92, "learning_rate": 1.617033508541393e-05, "loss": 0.582, "step": 5619 }, { "epoch": 0.92, "learning_rate": 1.616787122207622e-05, "loss": 0.5005, "step": 5620 }, { "epoch": 0.92, "learning_rate": 1.6165407358738503e-05, "loss": 0.6165, "step": 5621 }, { "epoch": 0.92, "learning_rate": 1.616294349540079e-05, "loss": 0.5315, "step": 5622 }, { "epoch": 0.92, "learning_rate": 1.6160479632063075e-05, "loss": 0.3189, "step": 5623 }, { "epoch": 0.92, "learning_rate": 1.6158015768725362e-05, "loss": 1.1724, "step": 5624 }, { "epoch": 0.92, "learning_rate": 1.6155551905387647e-05, "loss": 0.6036, "step": 5625 }, { "epoch": 0.92, "learning_rate": 1.6153088042049934e-05, "loss": 1.051, "step": 5626 }, { "epoch": 0.92, "learning_rate": 1.615062417871222e-05, "loss": 1.2209, "step": 5627 }, { "epoch": 0.92, "learning_rate": 1.6148160315374506e-05, "loss": 1.1745, "step": 5628 }, { "epoch": 0.92, "learning_rate": 1.6145696452036794e-05, "loss": 0.7196, "step": 5629 }, { "epoch": 0.92, "learning_rate": 1.614323258869908e-05, "loss": 0.8943, "step": 5630 }, { "epoch": 0.92, "learning_rate": 1.614076872536137e-05, "loss": 0.5166, "step": 5631 }, { "epoch": 0.93, "learning_rate": 1.6138304862023654e-05, "loss": 1.4559, "step": 5632 }, { "epoch": 0.93, "learning_rate": 1.613584099868594e-05, "loss": 0.8927, "step": 5633 }, { "epoch": 0.93, "learning_rate": 1.6133377135348226e-05, "loss": 0.935, "step": 5634 }, { "epoch": 0.93, "learning_rate": 1.6130913272010513e-05, "loss": 0.4604, "step": 5635 }, { "epoch": 0.93, "learning_rate": 1.6128449408672798e-05, "loss": 0.7337, "step": 5636 }, { "epoch": 0.93, "learning_rate": 1.6125985545335085e-05, "loss": 0.8097, "step": 5637 }, { "epoch": 0.93, "learning_rate": 1.612352168199737e-05, "loss": 0.8572, "step": 5638 }, { "epoch": 0.93, "learning_rate": 1.612105781865966e-05, "loss": 0.9468, "step": 5639 }, { "epoch": 0.93, "learning_rate": 1.6118593955321945e-05, "loss": 0.8633, "step": 5640 }, { "epoch": 0.93, "learning_rate": 1.6116130091984233e-05, "loss": 0.7834, "step": 5641 }, { "epoch": 0.93, "learning_rate": 1.611366622864652e-05, "loss": 1.3323, "step": 5642 }, { "epoch": 0.93, "learning_rate": 1.6111202365308805e-05, "loss": 1.0907, "step": 5643 }, { "epoch": 0.93, "learning_rate": 1.6108738501971092e-05, "loss": 0.4683, "step": 5644 }, { "epoch": 0.93, "learning_rate": 1.6106274638633376e-05, "loss": 0.994, "step": 5645 }, { "epoch": 0.93, "learning_rate": 1.6103810775295664e-05, "loss": 0.8846, "step": 5646 }, { "epoch": 0.93, "learning_rate": 1.610134691195795e-05, "loss": 0.5343, "step": 5647 }, { "epoch": 0.93, "learning_rate": 1.6098883048620236e-05, "loss": 0.5947, "step": 5648 }, { "epoch": 0.93, "learning_rate": 1.6096419185282524e-05, "loss": 0.8278, "step": 5649 }, { "epoch": 0.93, "learning_rate": 1.609395532194481e-05, "loss": 1.0272, "step": 5650 }, { "epoch": 0.93, "learning_rate": 1.6091491458607096e-05, "loss": 0.5027, "step": 5651 }, { "epoch": 0.93, "learning_rate": 1.6089027595269383e-05, "loss": 0.7785, "step": 5652 }, { "epoch": 0.93, "learning_rate": 1.6086563731931668e-05, "loss": 0.7463, "step": 5653 }, { "epoch": 0.93, "learning_rate": 1.6084099868593955e-05, "loss": 0.5971, "step": 5654 }, { "epoch": 0.93, "learning_rate": 1.6081636005256243e-05, "loss": 0.8482, "step": 5655 }, { "epoch": 0.93, "learning_rate": 1.6079172141918527e-05, "loss": 0.41, "step": 5656 }, { "epoch": 0.93, "learning_rate": 1.6076708278580815e-05, "loss": 0.462, "step": 5657 }, { "epoch": 0.93, "learning_rate": 1.60742444152431e-05, "loss": 1.1035, "step": 5658 }, { "epoch": 0.93, "learning_rate": 1.607178055190539e-05, "loss": 0.3372, "step": 5659 }, { "epoch": 0.93, "learning_rate": 1.6069316688567675e-05, "loss": 0.4627, "step": 5660 }, { "epoch": 0.93, "learning_rate": 1.6066852825229962e-05, "loss": 1.3164, "step": 5661 }, { "epoch": 0.93, "learning_rate": 1.6064388961892247e-05, "loss": 0.5306, "step": 5662 }, { "epoch": 0.93, "learning_rate": 1.6061925098554534e-05, "loss": 0.5752, "step": 5663 }, { "epoch": 0.93, "learning_rate": 1.605946123521682e-05, "loss": 0.84, "step": 5664 }, { "epoch": 0.93, "learning_rate": 1.6056997371879106e-05, "loss": 1.2356, "step": 5665 }, { "epoch": 0.93, "learning_rate": 1.6054533508541394e-05, "loss": 0.5918, "step": 5666 }, { "epoch": 0.93, "learning_rate": 1.6052069645203678e-05, "loss": 1.2549, "step": 5667 }, { "epoch": 0.93, "learning_rate": 1.6049605781865966e-05, "loss": 0.7998, "step": 5668 }, { "epoch": 0.93, "learning_rate": 1.6047141918528254e-05, "loss": 0.981, "step": 5669 }, { "epoch": 0.93, "learning_rate": 1.604467805519054e-05, "loss": 1.1085, "step": 5670 }, { "epoch": 0.93, "learning_rate": 1.6042214191852826e-05, "loss": 1.7989, "step": 5671 }, { "epoch": 0.93, "learning_rate": 1.6039750328515113e-05, "loss": 0.7919, "step": 5672 }, { "epoch": 0.93, "learning_rate": 1.6037286465177398e-05, "loss": 1.1138, "step": 5673 }, { "epoch": 0.93, "learning_rate": 1.6034822601839685e-05, "loss": 0.6144, "step": 5674 }, { "epoch": 0.93, "learning_rate": 1.603235873850197e-05, "loss": 0.9513, "step": 5675 }, { "epoch": 0.93, "learning_rate": 1.6029894875164257e-05, "loss": 1.1472, "step": 5676 }, { "epoch": 0.93, "learning_rate": 1.6027431011826545e-05, "loss": 0.5317, "step": 5677 }, { "epoch": 0.93, "learning_rate": 1.602496714848883e-05, "loss": 0.6938, "step": 5678 }, { "epoch": 0.93, "learning_rate": 1.602250328515112e-05, "loss": 1.1439, "step": 5679 }, { "epoch": 0.93, "learning_rate": 1.6020039421813405e-05, "loss": 1.3297, "step": 5680 }, { "epoch": 0.93, "learning_rate": 1.6017575558475692e-05, "loss": 0.9192, "step": 5681 }, { "epoch": 0.93, "learning_rate": 1.6015111695137977e-05, "loss": 0.565, "step": 5682 }, { "epoch": 0.93, "learning_rate": 1.6012647831800264e-05, "loss": 0.8204, "step": 5683 }, { "epoch": 0.93, "learning_rate": 1.601018396846255e-05, "loss": 1.8303, "step": 5684 }, { "epoch": 0.93, "learning_rate": 1.6007720105124836e-05, "loss": 0.6597, "step": 5685 }, { "epoch": 0.93, "learning_rate": 1.600525624178712e-05, "loss": 0.76, "step": 5686 }, { "epoch": 0.93, "learning_rate": 1.6002792378449408e-05, "loss": 0.7767, "step": 5687 }, { "epoch": 0.93, "learning_rate": 1.6000328515111692e-05, "loss": 0.2815, "step": 5688 }, { "epoch": 0.93, "learning_rate": 1.5997864651773984e-05, "loss": 0.4568, "step": 5689 }, { "epoch": 0.93, "learning_rate": 1.599540078843627e-05, "loss": 1.1953, "step": 5690 }, { "epoch": 0.93, "learning_rate": 1.5992936925098555e-05, "loss": 0.5929, "step": 5691 }, { "epoch": 0.93, "learning_rate": 1.5990473061760843e-05, "loss": 0.6526, "step": 5692 }, { "epoch": 0.94, "learning_rate": 1.5988009198423127e-05, "loss": 0.9633, "step": 5693 }, { "epoch": 0.94, "learning_rate": 1.5985545335085415e-05, "loss": 0.8502, "step": 5694 }, { "epoch": 0.94, "learning_rate": 1.59830814717477e-05, "loss": 0.5854, "step": 5695 }, { "epoch": 0.94, "learning_rate": 1.5980617608409987e-05, "loss": 0.5712, "step": 5696 }, { "epoch": 0.94, "learning_rate": 1.597815374507227e-05, "loss": 0.6356, "step": 5697 }, { "epoch": 0.94, "learning_rate": 1.597568988173456e-05, "loss": 0.7716, "step": 5698 }, { "epoch": 0.94, "learning_rate": 1.5973226018396847e-05, "loss": 1.7149, "step": 5699 }, { "epoch": 0.94, "learning_rate": 1.5970762155059134e-05, "loss": 0.879, "step": 5700 }, { "epoch": 0.94, "learning_rate": 1.5968298291721422e-05, "loss": 0.5605, "step": 5701 }, { "epoch": 0.94, "learning_rate": 1.5965834428383706e-05, "loss": 0.7054, "step": 5702 }, { "epoch": 0.94, "learning_rate": 1.5963370565045994e-05, "loss": 0.9944, "step": 5703 }, { "epoch": 0.94, "learning_rate": 1.596090670170828e-05, "loss": 1.0556, "step": 5704 }, { "epoch": 0.94, "learning_rate": 1.5958442838370566e-05, "loss": 1.2097, "step": 5705 }, { "epoch": 0.94, "learning_rate": 1.595597897503285e-05, "loss": 1.2846, "step": 5706 }, { "epoch": 0.94, "learning_rate": 1.5953515111695138e-05, "loss": 0.8521, "step": 5707 }, { "epoch": 0.94, "learning_rate": 1.5951051248357422e-05, "loss": 0.7027, "step": 5708 }, { "epoch": 0.94, "learning_rate": 1.5948587385019713e-05, "loss": 1.2681, "step": 5709 }, { "epoch": 0.94, "learning_rate": 1.5946123521681998e-05, "loss": 1.8121, "step": 5710 }, { "epoch": 0.94, "learning_rate": 1.5943659658344285e-05, "loss": 0.6578, "step": 5711 }, { "epoch": 0.94, "learning_rate": 1.594119579500657e-05, "loss": 0.8852, "step": 5712 }, { "epoch": 0.94, "learning_rate": 1.5938731931668857e-05, "loss": 1.2371, "step": 5713 }, { "epoch": 0.94, "learning_rate": 1.5936268068331145e-05, "loss": 1.0519, "step": 5714 }, { "epoch": 0.94, "learning_rate": 1.593380420499343e-05, "loss": 0.5543, "step": 5715 }, { "epoch": 0.94, "learning_rate": 1.5931340341655717e-05, "loss": 0.8723, "step": 5716 }, { "epoch": 0.94, "learning_rate": 1.5928876478318e-05, "loss": 0.3849, "step": 5717 }, { "epoch": 0.94, "learning_rate": 1.592641261498029e-05, "loss": 1.0555, "step": 5718 }, { "epoch": 0.94, "learning_rate": 1.5923948751642577e-05, "loss": 0.8913, "step": 5719 }, { "epoch": 0.94, "learning_rate": 1.5921484888304864e-05, "loss": 0.5508, "step": 5720 }, { "epoch": 0.94, "learning_rate": 1.591902102496715e-05, "loss": 0.574, "step": 5721 }, { "epoch": 0.94, "learning_rate": 1.5916557161629436e-05, "loss": 0.7869, "step": 5722 }, { "epoch": 0.94, "learning_rate": 1.591409329829172e-05, "loss": 0.7587, "step": 5723 }, { "epoch": 0.94, "learning_rate": 1.5911629434954008e-05, "loss": 0.5381, "step": 5724 }, { "epoch": 0.94, "learning_rate": 1.5909165571616296e-05, "loss": 0.618, "step": 5725 }, { "epoch": 0.94, "learning_rate": 1.590670170827858e-05, "loss": 0.6415, "step": 5726 }, { "epoch": 0.94, "learning_rate": 1.5904237844940868e-05, "loss": 0.8649, "step": 5727 }, { "epoch": 0.94, "learning_rate": 1.5901773981603152e-05, "loss": 0.9698, "step": 5728 }, { "epoch": 0.94, "learning_rate": 1.5899310118265443e-05, "loss": 0.9656, "step": 5729 }, { "epoch": 0.94, "learning_rate": 1.5896846254927728e-05, "loss": 0.5641, "step": 5730 }, { "epoch": 0.94, "learning_rate": 1.5894382391590015e-05, "loss": 0.7449, "step": 5731 }, { "epoch": 0.94, "learning_rate": 1.58919185282523e-05, "loss": 1.8878, "step": 5732 }, { "epoch": 0.94, "learning_rate": 1.5889454664914587e-05, "loss": 0.9001, "step": 5733 }, { "epoch": 0.94, "learning_rate": 1.588699080157687e-05, "loss": 0.5489, "step": 5734 }, { "epoch": 0.94, "learning_rate": 1.588452693823916e-05, "loss": 0.6403, "step": 5735 }, { "epoch": 0.94, "learning_rate": 1.5882063074901443e-05, "loss": 0.9746, "step": 5736 }, { "epoch": 0.94, "learning_rate": 1.587959921156373e-05, "loss": 1.2123, "step": 5737 }, { "epoch": 0.94, "learning_rate": 1.587713534822602e-05, "loss": 0.8278, "step": 5738 }, { "epoch": 0.94, "learning_rate": 1.5874671484888306e-05, "loss": 0.6346, "step": 5739 }, { "epoch": 0.94, "learning_rate": 1.5872207621550594e-05, "loss": 0.6703, "step": 5740 }, { "epoch": 0.94, "learning_rate": 1.586974375821288e-05, "loss": 0.6552, "step": 5741 }, { "epoch": 0.94, "learning_rate": 1.5867279894875166e-05, "loss": 0.332, "step": 5742 }, { "epoch": 0.94, "learning_rate": 1.586481603153745e-05, "loss": 1.1118, "step": 5743 }, { "epoch": 0.94, "learning_rate": 1.5862352168199738e-05, "loss": 0.8631, "step": 5744 }, { "epoch": 0.94, "learning_rate": 1.5859888304862022e-05, "loss": 0.5536, "step": 5745 }, { "epoch": 0.94, "learning_rate": 1.585742444152431e-05, "loss": 1.0136, "step": 5746 }, { "epoch": 0.94, "learning_rate": 1.5854960578186594e-05, "loss": 0.8254, "step": 5747 }, { "epoch": 0.94, "learning_rate": 1.5852496714848882e-05, "loss": 0.976, "step": 5748 }, { "epoch": 0.94, "learning_rate": 1.5850032851511173e-05, "loss": 0.7393, "step": 5749 }, { "epoch": 0.94, "learning_rate": 1.5847568988173457e-05, "loss": 1.0283, "step": 5750 }, { "epoch": 0.94, "learning_rate": 1.5845105124835745e-05, "loss": 1.2942, "step": 5751 }, { "epoch": 0.94, "learning_rate": 1.584264126149803e-05, "loss": 1.1793, "step": 5752 }, { "epoch": 0.94, "learning_rate": 1.5840177398160317e-05, "loss": 0.5487, "step": 5753 }, { "epoch": 0.95, "learning_rate": 1.58377135348226e-05, "loss": 0.7358, "step": 5754 }, { "epoch": 0.95, "learning_rate": 1.583524967148489e-05, "loss": 0.8451, "step": 5755 }, { "epoch": 0.95, "learning_rate": 1.5832785808147173e-05, "loss": 1.1328, "step": 5756 }, { "epoch": 0.95, "learning_rate": 1.583032194480946e-05, "loss": 0.7379, "step": 5757 }, { "epoch": 0.95, "learning_rate": 1.5827858081471745e-05, "loss": 0.5877, "step": 5758 }, { "epoch": 0.95, "learning_rate": 1.5825394218134036e-05, "loss": 0.5909, "step": 5759 }, { "epoch": 0.95, "learning_rate": 1.582293035479632e-05, "loss": 0.8303, "step": 5760 }, { "epoch": 0.95, "learning_rate": 1.5820466491458608e-05, "loss": 0.9668, "step": 5761 }, { "epoch": 0.95, "learning_rate": 1.5818002628120896e-05, "loss": 1.2559, "step": 5762 }, { "epoch": 0.95, "learning_rate": 1.581553876478318e-05, "loss": 0.6986, "step": 5763 }, { "epoch": 0.95, "learning_rate": 1.5813074901445468e-05, "loss": 0.6383, "step": 5764 }, { "epoch": 0.95, "learning_rate": 1.5810611038107752e-05, "loss": 0.7066, "step": 5765 }, { "epoch": 0.95, "learning_rate": 1.580814717477004e-05, "loss": 0.5569, "step": 5766 }, { "epoch": 0.95, "learning_rate": 1.5805683311432324e-05, "loss": 1.6581, "step": 5767 }, { "epoch": 0.95, "learning_rate": 1.5803219448094612e-05, "loss": 0.6022, "step": 5768 }, { "epoch": 0.95, "learning_rate": 1.58007555847569e-05, "loss": 0.6698, "step": 5769 }, { "epoch": 0.95, "learning_rate": 1.5798291721419187e-05, "loss": 0.7348, "step": 5770 }, { "epoch": 0.95, "learning_rate": 1.579582785808147e-05, "loss": 0.9119, "step": 5771 }, { "epoch": 0.95, "learning_rate": 1.579336399474376e-05, "loss": 0.3681, "step": 5772 }, { "epoch": 0.95, "learning_rate": 1.5790900131406047e-05, "loss": 0.4529, "step": 5773 }, { "epoch": 0.95, "learning_rate": 1.578843626806833e-05, "loss": 0.9764, "step": 5774 }, { "epoch": 0.95, "learning_rate": 1.578597240473062e-05, "loss": 0.8698, "step": 5775 }, { "epoch": 0.95, "learning_rate": 1.5783508541392903e-05, "loss": 1.3137, "step": 5776 }, { "epoch": 0.95, "learning_rate": 1.578104467805519e-05, "loss": 0.9151, "step": 5777 }, { "epoch": 0.95, "learning_rate": 1.5778580814717475e-05, "loss": 1.0142, "step": 5778 }, { "epoch": 0.95, "learning_rate": 1.5776116951379766e-05, "loss": 0.248, "step": 5779 }, { "epoch": 0.95, "learning_rate": 1.577365308804205e-05, "loss": 0.9761, "step": 5780 }, { "epoch": 0.95, "learning_rate": 1.5771189224704338e-05, "loss": 0.6463, "step": 5781 }, { "epoch": 0.95, "learning_rate": 1.5768725361366622e-05, "loss": 0.7785, "step": 5782 }, { "epoch": 0.95, "learning_rate": 1.576626149802891e-05, "loss": 0.977, "step": 5783 }, { "epoch": 0.95, "learning_rate": 1.5763797634691194e-05, "loss": 0.9826, "step": 5784 }, { "epoch": 0.95, "learning_rate": 1.5761333771353482e-05, "loss": 1.042, "step": 5785 }, { "epoch": 0.95, "learning_rate": 1.575886990801577e-05, "loss": 0.3198, "step": 5786 }, { "epoch": 0.95, "learning_rate": 1.5756406044678054e-05, "loss": 0.6765, "step": 5787 }, { "epoch": 0.95, "learning_rate": 1.5753942181340342e-05, "loss": 1.0155, "step": 5788 }, { "epoch": 0.95, "learning_rate": 1.575147831800263e-05, "loss": 0.9546, "step": 5789 }, { "epoch": 0.95, "learning_rate": 1.5749014454664917e-05, "loss": 1.7507, "step": 5790 }, { "epoch": 0.95, "learning_rate": 1.57465505913272e-05, "loss": 0.5723, "step": 5791 }, { "epoch": 0.95, "learning_rate": 1.574408672798949e-05, "loss": 0.5778, "step": 5792 }, { "epoch": 0.95, "learning_rate": 1.5741622864651773e-05, "loss": 0.2791, "step": 5793 }, { "epoch": 0.95, "learning_rate": 1.573915900131406e-05, "loss": 1.1928, "step": 5794 }, { "epoch": 0.95, "learning_rate": 1.5736695137976345e-05, "loss": 1.1388, "step": 5795 }, { "epoch": 0.95, "learning_rate": 1.5734231274638633e-05, "loss": 1.0416, "step": 5796 }, { "epoch": 0.95, "learning_rate": 1.573176741130092e-05, "loss": 1.0318, "step": 5797 }, { "epoch": 0.95, "learning_rate": 1.5729303547963205e-05, "loss": 1.1439, "step": 5798 }, { "epoch": 0.95, "learning_rate": 1.5726839684625496e-05, "loss": 0.6606, "step": 5799 }, { "epoch": 0.95, "learning_rate": 1.572437582128778e-05, "loss": 0.669, "step": 5800 }, { "epoch": 0.95, "learning_rate": 1.5721911957950068e-05, "loss": 0.6787, "step": 5801 }, { "epoch": 0.95, "learning_rate": 1.5719448094612352e-05, "loss": 0.6661, "step": 5802 }, { "epoch": 0.95, "learning_rate": 1.571698423127464e-05, "loss": 0.7068, "step": 5803 }, { "epoch": 0.95, "learning_rate": 1.5714520367936924e-05, "loss": 0.5773, "step": 5804 }, { "epoch": 0.95, "learning_rate": 1.5712056504599212e-05, "loss": 0.9402, "step": 5805 }, { "epoch": 0.95, "learning_rate": 1.5709592641261496e-05, "loss": 0.959, "step": 5806 }, { "epoch": 0.95, "learning_rate": 1.5707128777923784e-05, "loss": 0.9054, "step": 5807 }, { "epoch": 0.95, "learning_rate": 1.570466491458607e-05, "loss": 0.675, "step": 5808 }, { "epoch": 0.95, "learning_rate": 1.570220105124836e-05, "loss": 0.7702, "step": 5809 }, { "epoch": 0.95, "learning_rate": 1.5699737187910647e-05, "loss": 0.7156, "step": 5810 }, { "epoch": 0.95, "learning_rate": 1.569727332457293e-05, "loss": 0.5806, "step": 5811 }, { "epoch": 0.95, "learning_rate": 1.569480946123522e-05, "loss": 0.281, "step": 5812 }, { "epoch": 0.95, "learning_rate": 1.5692345597897503e-05, "loss": 0.9281, "step": 5813 }, { "epoch": 0.95, "learning_rate": 1.568988173455979e-05, "loss": 0.8957, "step": 5814 }, { "epoch": 0.96, "learning_rate": 1.5687417871222075e-05, "loss": 0.4054, "step": 5815 }, { "epoch": 0.96, "learning_rate": 1.5684954007884363e-05, "loss": 0.8021, "step": 5816 }, { "epoch": 0.96, "learning_rate": 1.5682490144546647e-05, "loss": 0.4513, "step": 5817 }, { "epoch": 0.96, "learning_rate": 1.5680026281208935e-05, "loss": 0.5942, "step": 5818 }, { "epoch": 0.96, "learning_rate": 1.5677562417871222e-05, "loss": 0.6826, "step": 5819 }, { "epoch": 0.96, "learning_rate": 1.567509855453351e-05, "loss": 0.761, "step": 5820 }, { "epoch": 0.96, "learning_rate": 1.5672634691195798e-05, "loss": 0.3207, "step": 5821 }, { "epoch": 0.96, "learning_rate": 1.5670170827858082e-05, "loss": 0.6438, "step": 5822 }, { "epoch": 0.96, "learning_rate": 1.566770696452037e-05, "loss": 0.6526, "step": 5823 }, { "epoch": 0.96, "learning_rate": 1.5665243101182654e-05, "loss": 0.6805, "step": 5824 }, { "epoch": 0.96, "learning_rate": 1.5662779237844942e-05, "loss": 0.9937, "step": 5825 }, { "epoch": 0.96, "learning_rate": 1.5660315374507226e-05, "loss": 1.2081, "step": 5826 }, { "epoch": 0.96, "learning_rate": 1.5657851511169514e-05, "loss": 0.6837, "step": 5827 }, { "epoch": 0.96, "learning_rate": 1.5655387647831798e-05, "loss": 0.662, "step": 5828 }, { "epoch": 0.96, "learning_rate": 1.565292378449409e-05, "loss": 1.0635, "step": 5829 }, { "epoch": 0.96, "learning_rate": 1.5650459921156373e-05, "loss": 0.9033, "step": 5830 }, { "epoch": 0.96, "learning_rate": 1.564799605781866e-05, "loss": 0.6668, "step": 5831 }, { "epoch": 0.96, "learning_rate": 1.564553219448095e-05, "loss": 1.0212, "step": 5832 }, { "epoch": 0.96, "learning_rate": 1.5643068331143233e-05, "loss": 0.7554, "step": 5833 }, { "epoch": 0.96, "learning_rate": 1.564060446780552e-05, "loss": 1.4425, "step": 5834 }, { "epoch": 0.96, "learning_rate": 1.5638140604467805e-05, "loss": 0.5376, "step": 5835 }, { "epoch": 0.96, "learning_rate": 1.5635676741130093e-05, "loss": 0.4687, "step": 5836 }, { "epoch": 0.96, "learning_rate": 1.5633212877792377e-05, "loss": 1.2317, "step": 5837 }, { "epoch": 0.96, "learning_rate": 1.5630749014454665e-05, "loss": 0.7934, "step": 5838 }, { "epoch": 0.96, "learning_rate": 1.5628285151116952e-05, "loss": 0.5908, "step": 5839 }, { "epoch": 0.96, "learning_rate": 1.562582128777924e-05, "loss": 1.0034, "step": 5840 }, { "epoch": 0.96, "learning_rate": 1.5623357424441524e-05, "loss": 1.002, "step": 5841 }, { "epoch": 0.96, "learning_rate": 1.5620893561103812e-05, "loss": 0.807, "step": 5842 }, { "epoch": 0.96, "learning_rate": 1.5618429697766096e-05, "loss": 0.758, "step": 5843 }, { "epoch": 0.96, "learning_rate": 1.5615965834428384e-05, "loss": 0.6931, "step": 5844 }, { "epoch": 0.96, "learning_rate": 1.561350197109067e-05, "loss": 0.8217, "step": 5845 }, { "epoch": 0.96, "learning_rate": 1.5611038107752956e-05, "loss": 0.8629, "step": 5846 }, { "epoch": 0.96, "learning_rate": 1.5608574244415244e-05, "loss": 0.9444, "step": 5847 }, { "epoch": 0.96, "learning_rate": 1.5606110381077528e-05, "loss": 0.6808, "step": 5848 }, { "epoch": 0.96, "learning_rate": 1.560364651773982e-05, "loss": 0.4858, "step": 5849 }, { "epoch": 0.96, "learning_rate": 1.5601182654402103e-05, "loss": 0.9376, "step": 5850 }, { "epoch": 0.96, "learning_rate": 1.559871879106439e-05, "loss": 0.5976, "step": 5851 }, { "epoch": 0.96, "learning_rate": 1.5596254927726675e-05, "loss": 0.8577, "step": 5852 }, { "epoch": 0.96, "learning_rate": 1.5593791064388963e-05, "loss": 0.4157, "step": 5853 }, { "epoch": 0.96, "learning_rate": 1.5591327201051247e-05, "loss": 1.1761, "step": 5854 }, { "epoch": 0.96, "learning_rate": 1.5588863337713535e-05, "loss": 1.2043, "step": 5855 }, { "epoch": 0.96, "learning_rate": 1.5586399474375823e-05, "loss": 0.8727, "step": 5856 }, { "epoch": 0.96, "learning_rate": 1.5583935611038107e-05, "loss": 0.6094, "step": 5857 }, { "epoch": 0.96, "learning_rate": 1.5581471747700395e-05, "loss": 1.166, "step": 5858 }, { "epoch": 0.96, "learning_rate": 1.5579007884362682e-05, "loss": 1.3684, "step": 5859 }, { "epoch": 0.96, "learning_rate": 1.557654402102497e-05, "loss": 0.9516, "step": 5860 }, { "epoch": 0.96, "learning_rate": 1.5574080157687254e-05, "loss": 0.4931, "step": 5861 }, { "epoch": 0.96, "learning_rate": 1.5571616294349542e-05, "loss": 0.9192, "step": 5862 }, { "epoch": 0.96, "learning_rate": 1.5569152431011826e-05, "loss": 0.8378, "step": 5863 }, { "epoch": 0.96, "learning_rate": 1.5566688567674114e-05, "loss": 0.8003, "step": 5864 }, { "epoch": 0.96, "learning_rate": 1.5564224704336398e-05, "loss": 0.7582, "step": 5865 }, { "epoch": 0.96, "learning_rate": 1.5561760840998686e-05, "loss": 0.6057, "step": 5866 }, { "epoch": 0.96, "learning_rate": 1.555929697766097e-05, "loss": 0.7473, "step": 5867 }, { "epoch": 0.96, "learning_rate": 1.5556833114323258e-05, "loss": 0.6463, "step": 5868 }, { "epoch": 0.96, "learning_rate": 1.555436925098555e-05, "loss": 0.4961, "step": 5869 }, { "epoch": 0.96, "learning_rate": 1.5551905387647833e-05, "loss": 0.7407, "step": 5870 }, { "epoch": 0.96, "learning_rate": 1.554944152431012e-05, "loss": 0.8717, "step": 5871 }, { "epoch": 0.96, "learning_rate": 1.5546977660972405e-05, "loss": 0.6928, "step": 5872 }, { "epoch": 0.96, "learning_rate": 1.5544513797634693e-05, "loss": 1.0574, "step": 5873 }, { "epoch": 0.96, "learning_rate": 1.5542049934296977e-05, "loss": 0.8168, "step": 5874 }, { "epoch": 0.97, "learning_rate": 1.5539586070959265e-05, "loss": 0.7586, "step": 5875 }, { "epoch": 0.97, "learning_rate": 1.553712220762155e-05, "loss": 1.4841, "step": 5876 }, { "epoch": 0.97, "learning_rate": 1.5534658344283837e-05, "loss": 0.7359, "step": 5877 }, { "epoch": 0.97, "learning_rate": 1.553219448094612e-05, "loss": 0.8913, "step": 5878 }, { "epoch": 0.97, "learning_rate": 1.5529730617608412e-05, "loss": 0.3351, "step": 5879 }, { "epoch": 0.97, "learning_rate": 1.55272667542707e-05, "loss": 0.8219, "step": 5880 }, { "epoch": 0.97, "learning_rate": 1.5524802890932984e-05, "loss": 1.2201, "step": 5881 }, { "epoch": 0.97, "learning_rate": 1.5522339027595272e-05, "loss": 1.1518, "step": 5882 }, { "epoch": 0.97, "learning_rate": 1.5519875164257556e-05, "loss": 1.1571, "step": 5883 }, { "epoch": 0.97, "learning_rate": 1.5517411300919844e-05, "loss": 0.4793, "step": 5884 }, { "epoch": 0.97, "learning_rate": 1.5514947437582128e-05, "loss": 0.8349, "step": 5885 }, { "epoch": 0.97, "learning_rate": 1.5512483574244416e-05, "loss": 1.1903, "step": 5886 }, { "epoch": 0.97, "learning_rate": 1.55100197109067e-05, "loss": 0.8734, "step": 5887 }, { "epoch": 0.97, "learning_rate": 1.5507555847568988e-05, "loss": 1.0292, "step": 5888 }, { "epoch": 0.97, "learning_rate": 1.5505091984231275e-05, "loss": 0.8302, "step": 5889 }, { "epoch": 0.97, "learning_rate": 1.5502628120893563e-05, "loss": 1.3635, "step": 5890 }, { "epoch": 0.97, "learning_rate": 1.5500164257555847e-05, "loss": 0.5507, "step": 5891 }, { "epoch": 0.97, "learning_rate": 1.5497700394218135e-05, "loss": 0.7867, "step": 5892 }, { "epoch": 0.97, "learning_rate": 1.5495236530880423e-05, "loss": 0.9187, "step": 5893 }, { "epoch": 0.97, "learning_rate": 1.5492772667542707e-05, "loss": 0.8049, "step": 5894 }, { "epoch": 0.97, "learning_rate": 1.5490308804204995e-05, "loss": 1.0753, "step": 5895 }, { "epoch": 0.97, "learning_rate": 1.548784494086728e-05, "loss": 1.1296, "step": 5896 }, { "epoch": 0.97, "learning_rate": 1.5485381077529567e-05, "loss": 0.757, "step": 5897 }, { "epoch": 0.97, "learning_rate": 1.548291721419185e-05, "loss": 0.4345, "step": 5898 }, { "epoch": 0.97, "learning_rate": 1.5480453350854142e-05, "loss": 1.4047, "step": 5899 }, { "epoch": 0.97, "learning_rate": 1.5477989487516426e-05, "loss": 1.0588, "step": 5900 }, { "epoch": 0.97, "learning_rate": 1.5475525624178714e-05, "loss": 0.7334, "step": 5901 }, { "epoch": 0.97, "learning_rate": 1.5473061760840998e-05, "loss": 1.1247, "step": 5902 }, { "epoch": 0.97, "learning_rate": 1.5470597897503286e-05, "loss": 0.684, "step": 5903 }, { "epoch": 0.97, "learning_rate": 1.5468134034165574e-05, "loss": 0.6345, "step": 5904 }, { "epoch": 0.97, "learning_rate": 1.5465670170827858e-05, "loss": 0.868, "step": 5905 }, { "epoch": 0.97, "learning_rate": 1.5463206307490145e-05, "loss": 1.0118, "step": 5906 }, { "epoch": 0.97, "learning_rate": 1.546074244415243e-05, "loss": 1.2627, "step": 5907 }, { "epoch": 0.97, "learning_rate": 1.5458278580814717e-05, "loss": 1.4084, "step": 5908 }, { "epoch": 0.97, "learning_rate": 1.5455814717477005e-05, "loss": 0.7028, "step": 5909 }, { "epoch": 0.97, "learning_rate": 1.5453350854139293e-05, "loss": 0.8849, "step": 5910 }, { "epoch": 0.97, "learning_rate": 1.5450886990801577e-05, "loss": 0.6266, "step": 5911 }, { "epoch": 0.97, "learning_rate": 1.5448423127463865e-05, "loss": 0.7154, "step": 5912 }, { "epoch": 0.97, "learning_rate": 1.544595926412615e-05, "loss": 0.6703, "step": 5913 }, { "epoch": 0.97, "learning_rate": 1.5443495400788437e-05, "loss": 0.4992, "step": 5914 }, { "epoch": 0.97, "learning_rate": 1.544103153745072e-05, "loss": 0.6578, "step": 5915 }, { "epoch": 0.97, "learning_rate": 1.543856767411301e-05, "loss": 1.0222, "step": 5916 }, { "epoch": 0.97, "learning_rate": 1.5436103810775296e-05, "loss": 1.1009, "step": 5917 }, { "epoch": 0.97, "learning_rate": 1.543363994743758e-05, "loss": 1.1026, "step": 5918 }, { "epoch": 0.97, "learning_rate": 1.5431176084099872e-05, "loss": 0.345, "step": 5919 }, { "epoch": 0.97, "learning_rate": 1.5428712220762156e-05, "loss": 0.3815, "step": 5920 }, { "epoch": 0.97, "learning_rate": 1.5426248357424444e-05, "loss": 0.6639, "step": 5921 }, { "epoch": 0.97, "learning_rate": 1.5423784494086728e-05, "loss": 0.8486, "step": 5922 }, { "epoch": 0.97, "learning_rate": 1.5421320630749016e-05, "loss": 0.6099, "step": 5923 }, { "epoch": 0.97, "learning_rate": 1.54188567674113e-05, "loss": 0.5024, "step": 5924 }, { "epoch": 0.97, "learning_rate": 1.5416392904073588e-05, "loss": 0.9461, "step": 5925 }, { "epoch": 0.97, "learning_rate": 1.5413929040735872e-05, "loss": 0.7582, "step": 5926 }, { "epoch": 0.97, "learning_rate": 1.541146517739816e-05, "loss": 1.2651, "step": 5927 }, { "epoch": 0.97, "learning_rate": 1.5409001314060447e-05, "loss": 1.4583, "step": 5928 }, { "epoch": 0.97, "learning_rate": 1.5406537450722735e-05, "loss": 0.3119, "step": 5929 }, { "epoch": 0.97, "learning_rate": 1.5404073587385023e-05, "loss": 1.1255, "step": 5930 }, { "epoch": 0.97, "learning_rate": 1.5401609724047307e-05, "loss": 0.5449, "step": 5931 }, { "epoch": 0.97, "learning_rate": 1.5399145860709595e-05, "loss": 0.5938, "step": 5932 }, { "epoch": 0.97, "learning_rate": 1.539668199737188e-05, "loss": 1.103, "step": 5933 }, { "epoch": 0.97, "learning_rate": 1.5394218134034167e-05, "loss": 1.8029, "step": 5934 }, { "epoch": 0.97, "learning_rate": 1.539175427069645e-05, "loss": 1.402, "step": 5935 }, { "epoch": 0.98, "learning_rate": 1.538929040735874e-05, "loss": 0.6919, "step": 5936 }, { "epoch": 0.98, "learning_rate": 1.5386826544021023e-05, "loss": 0.6657, "step": 5937 }, { "epoch": 0.98, "learning_rate": 1.538436268068331e-05, "loss": 0.5237, "step": 5938 }, { "epoch": 0.98, "learning_rate": 1.5381898817345598e-05, "loss": 0.7013, "step": 5939 }, { "epoch": 0.98, "learning_rate": 1.5379434954007886e-05, "loss": 0.5543, "step": 5940 }, { "epoch": 0.98, "learning_rate": 1.5376971090670174e-05, "loss": 0.8625, "step": 5941 }, { "epoch": 0.98, "learning_rate": 1.5374507227332458e-05, "loss": 1.2011, "step": 5942 }, { "epoch": 0.98, "learning_rate": 1.5372043363994746e-05, "loss": 1.1671, "step": 5943 }, { "epoch": 0.98, "learning_rate": 1.536957950065703e-05, "loss": 1.2291, "step": 5944 }, { "epoch": 0.98, "learning_rate": 1.5367115637319318e-05, "loss": 0.8304, "step": 5945 }, { "epoch": 0.98, "learning_rate": 1.5364651773981602e-05, "loss": 0.7348, "step": 5946 }, { "epoch": 0.98, "learning_rate": 1.536218791064389e-05, "loss": 0.7392, "step": 5947 }, { "epoch": 0.98, "learning_rate": 1.5359724047306174e-05, "loss": 0.9416, "step": 5948 }, { "epoch": 0.98, "learning_rate": 1.5357260183968465e-05, "loss": 1.3062, "step": 5949 }, { "epoch": 0.98, "learning_rate": 1.535479632063075e-05, "loss": 0.7994, "step": 5950 }, { "epoch": 0.98, "learning_rate": 1.5352332457293037e-05, "loss": 0.7094, "step": 5951 }, { "epoch": 0.98, "learning_rate": 1.5349868593955325e-05, "loss": 0.71, "step": 5952 }, { "epoch": 0.98, "learning_rate": 1.534740473061761e-05, "loss": 0.5476, "step": 5953 }, { "epoch": 0.98, "learning_rate": 1.5344940867279896e-05, "loss": 0.4474, "step": 5954 }, { "epoch": 0.98, "learning_rate": 1.534247700394218e-05, "loss": 0.4654, "step": 5955 }, { "epoch": 0.98, "learning_rate": 1.534001314060447e-05, "loss": 0.6454, "step": 5956 }, { "epoch": 0.98, "learning_rate": 1.5337549277266753e-05, "loss": 0.4204, "step": 5957 }, { "epoch": 0.98, "learning_rate": 1.533508541392904e-05, "loss": 0.9022, "step": 5958 }, { "epoch": 0.98, "learning_rate": 1.5332621550591328e-05, "loss": 0.6289, "step": 5959 }, { "epoch": 0.98, "learning_rate": 1.5330157687253616e-05, "loss": 0.7598, "step": 5960 }, { "epoch": 0.98, "learning_rate": 1.53276938239159e-05, "loss": 0.8496, "step": 5961 }, { "epoch": 0.98, "learning_rate": 1.5325229960578188e-05, "loss": 0.5277, "step": 5962 }, { "epoch": 0.98, "learning_rate": 1.5322766097240475e-05, "loss": 0.795, "step": 5963 }, { "epoch": 0.98, "learning_rate": 1.532030223390276e-05, "loss": 0.7087, "step": 5964 }, { "epoch": 0.98, "learning_rate": 1.5317838370565047e-05, "loss": 0.8722, "step": 5965 }, { "epoch": 0.98, "learning_rate": 1.531537450722733e-05, "loss": 0.8489, "step": 5966 }, { "epoch": 0.98, "learning_rate": 1.531291064388962e-05, "loss": 0.7458, "step": 5967 }, { "epoch": 0.98, "learning_rate": 1.5310446780551904e-05, "loss": 0.8218, "step": 5968 }, { "epoch": 0.98, "learning_rate": 1.5307982917214195e-05, "loss": 0.9425, "step": 5969 }, { "epoch": 0.98, "learning_rate": 1.530551905387648e-05, "loss": 1.0345, "step": 5970 }, { "epoch": 0.98, "learning_rate": 1.5303055190538767e-05, "loss": 1.131, "step": 5971 }, { "epoch": 0.98, "learning_rate": 1.530059132720105e-05, "loss": 0.2323, "step": 5972 }, { "epoch": 0.98, "learning_rate": 1.529812746386334e-05, "loss": 1.1104, "step": 5973 }, { "epoch": 0.98, "learning_rate": 1.5295663600525623e-05, "loss": 0.5382, "step": 5974 }, { "epoch": 0.98, "learning_rate": 1.529319973718791e-05, "loss": 1.4406, "step": 5975 }, { "epoch": 0.98, "learning_rate": 1.5290735873850198e-05, "loss": 0.588, "step": 5976 }, { "epoch": 0.98, "learning_rate": 1.5288272010512483e-05, "loss": 0.7127, "step": 5977 }, { "epoch": 0.98, "learning_rate": 1.528580814717477e-05, "loss": 0.6196, "step": 5978 }, { "epoch": 0.98, "learning_rate": 1.5283344283837058e-05, "loss": 0.7801, "step": 5979 }, { "epoch": 0.98, "learning_rate": 1.5280880420499346e-05, "loss": 0.5503, "step": 5980 }, { "epoch": 0.98, "learning_rate": 1.527841655716163e-05, "loss": 0.5346, "step": 5981 }, { "epoch": 0.98, "learning_rate": 1.5275952693823918e-05, "loss": 0.5345, "step": 5982 }, { "epoch": 0.98, "learning_rate": 1.5273488830486202e-05, "loss": 0.7781, "step": 5983 }, { "epoch": 0.98, "learning_rate": 1.527102496714849e-05, "loss": 0.7369, "step": 5984 }, { "epoch": 0.98, "learning_rate": 1.5268561103810774e-05, "loss": 0.4645, "step": 5985 }, { "epoch": 0.98, "learning_rate": 1.526609724047306e-05, "loss": 0.7069, "step": 5986 }, { "epoch": 0.98, "learning_rate": 1.526363337713535e-05, "loss": 0.4075, "step": 5987 }, { "epoch": 0.98, "learning_rate": 1.5261169513797634e-05, "loss": 1.0077, "step": 5988 }, { "epoch": 0.98, "learning_rate": 1.5258705650459923e-05, "loss": 0.5814, "step": 5989 }, { "epoch": 0.98, "learning_rate": 1.5256241787122209e-05, "loss": 0.9318, "step": 5990 }, { "epoch": 0.98, "learning_rate": 1.5253777923784495e-05, "loss": 0.3503, "step": 5991 }, { "epoch": 0.98, "learning_rate": 1.525131406044678e-05, "loss": 1.1594, "step": 5992 }, { "epoch": 0.98, "learning_rate": 1.5248850197109069e-05, "loss": 1.4717, "step": 5993 }, { "epoch": 0.98, "learning_rate": 1.5246386333771354e-05, "loss": 0.9756, "step": 5994 }, { "epoch": 0.98, "learning_rate": 1.524392247043364e-05, "loss": 1.1662, "step": 5995 }, { "epoch": 0.98, "learning_rate": 1.5241458607095926e-05, "loss": 1.1672, "step": 5996 }, { "epoch": 0.99, "learning_rate": 1.5238994743758212e-05, "loss": 0.9305, "step": 5997 }, { "epoch": 0.99, "learning_rate": 1.5236530880420498e-05, "loss": 1.4925, "step": 5998 }, { "epoch": 0.99, "learning_rate": 1.5234067017082788e-05, "loss": 1.1068, "step": 5999 }, { "epoch": 0.99, "learning_rate": 1.5231603153745074e-05, "loss": 0.9334, "step": 6000 }, { "epoch": 0.99, "eval_exact_match": 86.5279091769158, "eval_f1": 92.79247222106285, "step": 6000 }, { "epoch": 0.99, "learning_rate": 1.522913929040736e-05, "loss": 0.4688, "step": 6001 }, { "epoch": 0.99, "learning_rate": 1.5226675427069646e-05, "loss": 1.0015, "step": 6002 }, { "epoch": 0.99, "learning_rate": 1.5224211563731932e-05, "loss": 0.8946, "step": 6003 }, { "epoch": 0.99, "learning_rate": 1.5221747700394218e-05, "loss": 0.5081, "step": 6004 }, { "epoch": 0.99, "learning_rate": 1.5219283837056505e-05, "loss": 0.7499, "step": 6005 }, { "epoch": 0.99, "learning_rate": 1.5216819973718791e-05, "loss": 1.1411, "step": 6006 }, { "epoch": 0.99, "learning_rate": 1.5214356110381077e-05, "loss": 0.7448, "step": 6007 }, { "epoch": 0.99, "learning_rate": 1.5211892247043363e-05, "loss": 1.428, "step": 6008 }, { "epoch": 0.99, "learning_rate": 1.5209428383705653e-05, "loss": 0.7245, "step": 6009 }, { "epoch": 0.99, "learning_rate": 1.5206964520367939e-05, "loss": 0.7767, "step": 6010 }, { "epoch": 0.99, "learning_rate": 1.5204500657030225e-05, "loss": 0.7492, "step": 6011 }, { "epoch": 0.99, "learning_rate": 1.520203679369251e-05, "loss": 0.5218, "step": 6012 }, { "epoch": 0.99, "learning_rate": 1.5199572930354797e-05, "loss": 0.7561, "step": 6013 }, { "epoch": 0.99, "learning_rate": 1.5197109067017083e-05, "loss": 1.2311, "step": 6014 }, { "epoch": 0.99, "learning_rate": 1.5194645203679369e-05, "loss": 0.8562, "step": 6015 }, { "epoch": 0.99, "learning_rate": 1.5192181340341655e-05, "loss": 1.1648, "step": 6016 }, { "epoch": 0.99, "learning_rate": 1.5189717477003942e-05, "loss": 0.6467, "step": 6017 }, { "epoch": 0.99, "learning_rate": 1.5187253613666228e-05, "loss": 0.7851, "step": 6018 }, { "epoch": 0.99, "learning_rate": 1.5184789750328518e-05, "loss": 0.5782, "step": 6019 }, { "epoch": 0.99, "learning_rate": 1.5182325886990804e-05, "loss": 0.7856, "step": 6020 }, { "epoch": 0.99, "learning_rate": 1.517986202365309e-05, "loss": 0.9013, "step": 6021 }, { "epoch": 0.99, "learning_rate": 1.5177398160315376e-05, "loss": 0.5996, "step": 6022 }, { "epoch": 0.99, "learning_rate": 1.5174934296977662e-05, "loss": 0.6643, "step": 6023 }, { "epoch": 0.99, "learning_rate": 1.5172470433639948e-05, "loss": 0.9032, "step": 6024 }, { "epoch": 0.99, "learning_rate": 1.5170006570302234e-05, "loss": 1.0152, "step": 6025 }, { "epoch": 0.99, "learning_rate": 1.516754270696452e-05, "loss": 0.7515, "step": 6026 }, { "epoch": 0.99, "learning_rate": 1.5165078843626806e-05, "loss": 0.7631, "step": 6027 }, { "epoch": 0.99, "learning_rate": 1.5162614980289092e-05, "loss": 0.6233, "step": 6028 }, { "epoch": 0.99, "learning_rate": 1.5160151116951383e-05, "loss": 1.0267, "step": 6029 }, { "epoch": 0.99, "learning_rate": 1.5157687253613669e-05, "loss": 0.8025, "step": 6030 }, { "epoch": 0.99, "learning_rate": 1.5155223390275955e-05, "loss": 0.4322, "step": 6031 }, { "epoch": 0.99, "learning_rate": 1.515275952693824e-05, "loss": 0.9173, "step": 6032 }, { "epoch": 0.99, "learning_rate": 1.5150295663600527e-05, "loss": 0.8616, "step": 6033 }, { "epoch": 0.99, "learning_rate": 1.5147831800262813e-05, "loss": 0.7314, "step": 6034 }, { "epoch": 0.99, "learning_rate": 1.5145367936925098e-05, "loss": 1.3153, "step": 6035 }, { "epoch": 0.99, "learning_rate": 1.5142904073587384e-05, "loss": 0.7739, "step": 6036 }, { "epoch": 0.99, "learning_rate": 1.514044021024967e-05, "loss": 0.9821, "step": 6037 }, { "epoch": 0.99, "learning_rate": 1.5137976346911956e-05, "loss": 0.8096, "step": 6038 }, { "epoch": 0.99, "learning_rate": 1.5135512483574246e-05, "loss": 0.9109, "step": 6039 }, { "epoch": 0.99, "learning_rate": 1.5133048620236532e-05, "loss": 0.8283, "step": 6040 }, { "epoch": 0.99, "learning_rate": 1.513058475689882e-05, "loss": 0.8456, "step": 6041 }, { "epoch": 0.99, "learning_rate": 1.5128120893561105e-05, "loss": 1.1799, "step": 6042 }, { "epoch": 0.99, "learning_rate": 1.5125657030223391e-05, "loss": 0.7518, "step": 6043 }, { "epoch": 0.99, "learning_rate": 1.5123193166885677e-05, "loss": 1.1707, "step": 6044 }, { "epoch": 0.99, "learning_rate": 1.5120729303547963e-05, "loss": 0.6647, "step": 6045 }, { "epoch": 0.99, "learning_rate": 1.511826544021025e-05, "loss": 0.9883, "step": 6046 }, { "epoch": 0.99, "learning_rate": 1.5115801576872535e-05, "loss": 1.1774, "step": 6047 }, { "epoch": 0.99, "learning_rate": 1.5113337713534821e-05, "loss": 1.1248, "step": 6048 }, { "epoch": 0.99, "learning_rate": 1.511087385019711e-05, "loss": 1.0895, "step": 6049 }, { "epoch": 0.99, "learning_rate": 1.5108409986859397e-05, "loss": 0.7544, "step": 6050 }, { "epoch": 0.99, "learning_rate": 1.5105946123521683e-05, "loss": 0.5396, "step": 6051 }, { "epoch": 0.99, "learning_rate": 1.5103482260183969e-05, "loss": 0.6813, "step": 6052 }, { "epoch": 0.99, "learning_rate": 1.5101018396846256e-05, "loss": 0.4542, "step": 6053 }, { "epoch": 0.99, "learning_rate": 1.5098554533508542e-05, "loss": 0.4128, "step": 6054 }, { "epoch": 0.99, "learning_rate": 1.5096090670170828e-05, "loss": 0.7293, "step": 6055 }, { "epoch": 0.99, "learning_rate": 1.5093626806833114e-05, "loss": 1.4326, "step": 6056 }, { "epoch": 0.99, "learning_rate": 1.50911629434954e-05, "loss": 1.0956, "step": 6057 }, { "epoch": 1.0, "learning_rate": 1.5088699080157686e-05, "loss": 1.0668, "step": 6058 }, { "epoch": 1.0, "learning_rate": 1.5086235216819976e-05, "loss": 0.7104, "step": 6059 }, { "epoch": 1.0, "learning_rate": 1.5083771353482262e-05, "loss": 0.718, "step": 6060 }, { "epoch": 1.0, "learning_rate": 1.5081307490144548e-05, "loss": 0.8358, "step": 6061 }, { "epoch": 1.0, "learning_rate": 1.5078843626806834e-05, "loss": 0.9608, "step": 6062 }, { "epoch": 1.0, "learning_rate": 1.507637976346912e-05, "loss": 0.641, "step": 6063 }, { "epoch": 1.0, "learning_rate": 1.5073915900131406e-05, "loss": 1.3158, "step": 6064 }, { "epoch": 1.0, "learning_rate": 1.5071452036793693e-05, "loss": 0.4413, "step": 6065 }, { "epoch": 1.0, "learning_rate": 1.506898817345598e-05, "loss": 0.9992, "step": 6066 }, { "epoch": 1.0, "learning_rate": 1.5066524310118265e-05, "loss": 0.7466, "step": 6067 }, { "epoch": 1.0, "learning_rate": 1.5064060446780551e-05, "loss": 0.3127, "step": 6068 }, { "epoch": 1.0, "learning_rate": 1.506159658344284e-05, "loss": 1.4168, "step": 6069 }, { "epoch": 1.0, "learning_rate": 1.5059132720105127e-05, "loss": 0.4491, "step": 6070 }, { "epoch": 1.0, "learning_rate": 1.5056668856767413e-05, "loss": 0.7897, "step": 6071 }, { "epoch": 1.0, "learning_rate": 1.5054204993429699e-05, "loss": 0.3956, "step": 6072 }, { "epoch": 1.0, "learning_rate": 1.5051741130091985e-05, "loss": 0.3965, "step": 6073 }, { "epoch": 1.0, "learning_rate": 1.504927726675427e-05, "loss": 0.839, "step": 6074 }, { "epoch": 1.0, "learning_rate": 1.5046813403416557e-05, "loss": 0.8507, "step": 6075 }, { "epoch": 1.0, "learning_rate": 1.5044349540078842e-05, "loss": 0.5533, "step": 6076 }, { "epoch": 1.0, "learning_rate": 1.504188567674113e-05, "loss": 0.9072, "step": 6077 }, { "epoch": 1.0, "learning_rate": 1.5039421813403416e-05, "loss": 0.8603, "step": 6078 }, { "epoch": 1.0, "learning_rate": 1.5036957950065706e-05, "loss": 0.8901, "step": 6079 }, { "epoch": 1.0, "learning_rate": 1.5034494086727992e-05, "loss": 0.807, "step": 6080 }, { "epoch": 1.0, "learning_rate": 1.5032030223390277e-05, "loss": 1.1097, "step": 6081 }, { "epoch": 1.0, "learning_rate": 1.5029566360052563e-05, "loss": 0.9417, "step": 6082 }, { "epoch": 1.0, "learning_rate": 1.502710249671485e-05, "loss": 1.526, "step": 6083 }, { "epoch": 1.0, "learning_rate": 1.5024638633377135e-05, "loss": 0.4971, "step": 6084 }, { "epoch": 1.0, "learning_rate": 1.5022174770039421e-05, "loss": 0.4376, "step": 6085 }, { "epoch": 1.0, "learning_rate": 1.5019710906701707e-05, "loss": 0.4571, "step": 6086 }, { "epoch": 1.0, "learning_rate": 1.5017247043363993e-05, "loss": 0.57, "step": 6087 }, { "epoch": 1.0, "learning_rate": 1.5014783180026281e-05, "loss": 0.9316, "step": 6088 }, { "epoch": 1.0, "learning_rate": 1.501231931668857e-05, "loss": 0.4906, "step": 6089 }, { "epoch": 1.0, "learning_rate": 1.5009855453350856e-05, "loss": 0.4957, "step": 6090 }, { "epoch": 1.0, "learning_rate": 1.5007391590013142e-05, "loss": 0.4688, "step": 6091 }, { "epoch": 1.0, "learning_rate": 1.5004927726675428e-05, "loss": 0.4238, "step": 6092 }, { "epoch": 1.0, "learning_rate": 1.5002463863337714e-05, "loss": 0.2318, "step": 6093 }, { "epoch": 1.0, "learning_rate": 1.5e-05, "loss": 0.4389, "step": 6094 }, { "epoch": 1.0, "learning_rate": 1.4997536136662286e-05, "loss": 1.1023, "step": 6095 }, { "epoch": 1.0, "learning_rate": 1.4995072273324572e-05, "loss": 0.7243, "step": 6096 }, { "epoch": 1.0, "learning_rate": 1.499260840998686e-05, "loss": 0.6262, "step": 6097 }, { "epoch": 1.0, "learning_rate": 1.4990144546649146e-05, "loss": 0.633, "step": 6098 }, { "epoch": 1.0, "learning_rate": 1.4987680683311432e-05, "loss": 0.802, "step": 6099 }, { "epoch": 1.0, "learning_rate": 1.498521681997372e-05, "loss": 0.8714, "step": 6100 }, { "epoch": 1.0, "learning_rate": 1.4982752956636006e-05, "loss": 1.3288, "step": 6101 }, { "epoch": 1.0, "learning_rate": 1.4980289093298293e-05, "loss": 0.6884, "step": 6102 }, { "epoch": 1.0, "learning_rate": 1.497782522996058e-05, "loss": 0.3741, "step": 6103 }, { "epoch": 1.0, "learning_rate": 1.4975361366622865e-05, "loss": 0.1814, "step": 6104 }, { "epoch": 1.0, "learning_rate": 1.4972897503285151e-05, "loss": 0.6273, "step": 6105 }, { "epoch": 1.0, "learning_rate": 1.4970433639947437e-05, "loss": 0.6581, "step": 6106 }, { "epoch": 1.0, "learning_rate": 1.4967969776609725e-05, "loss": 0.7827, "step": 6107 }, { "epoch": 1.0, "learning_rate": 1.4965505913272011e-05, "loss": 0.2293, "step": 6108 }, { "epoch": 1.0, "learning_rate": 1.4963042049934297e-05, "loss": 0.2834, "step": 6109 }, { "epoch": 1.0, "learning_rate": 1.4960578186596583e-05, "loss": 0.4148, "step": 6110 }, { "epoch": 1.0, "learning_rate": 1.4958114323258869e-05, "loss": 0.8789, "step": 6111 }, { "epoch": 1.0, "learning_rate": 1.4955650459921158e-05, "loss": 0.8696, "step": 6112 }, { "epoch": 1.0, "learning_rate": 1.4953186596583444e-05, "loss": 0.8366, "step": 6113 }, { "epoch": 1.0, "learning_rate": 1.495072273324573e-05, "loss": 0.4886, "step": 6114 }, { "epoch": 1.0, "learning_rate": 1.4948258869908016e-05, "loss": 0.7577, "step": 6115 }, { "epoch": 1.0, "learning_rate": 1.4945795006570302e-05, "loss": 0.7344, "step": 6116 }, { "epoch": 1.0, "learning_rate": 1.494333114323259e-05, "loss": 0.4306, "step": 6117 }, { "epoch": 1.0, "learning_rate": 1.4940867279894876e-05, "loss": 0.2549, "step": 6118 }, { "epoch": 1.01, "learning_rate": 1.4938403416557162e-05, "loss": 1.0184, "step": 6119 }, { "epoch": 1.01, "learning_rate": 1.4935939553219448e-05, "loss": 0.3699, "step": 6120 }, { "epoch": 1.01, "learning_rate": 1.4933475689881734e-05, "loss": 0.5709, "step": 6121 }, { "epoch": 1.01, "learning_rate": 1.4931011826544022e-05, "loss": 0.4794, "step": 6122 }, { "epoch": 1.01, "learning_rate": 1.4928547963206307e-05, "loss": 0.4551, "step": 6123 }, { "epoch": 1.01, "learning_rate": 1.4926084099868595e-05, "loss": 0.6375, "step": 6124 }, { "epoch": 1.01, "learning_rate": 1.4923620236530881e-05, "loss": 0.6464, "step": 6125 }, { "epoch": 1.01, "learning_rate": 1.4921156373193167e-05, "loss": 0.3951, "step": 6126 }, { "epoch": 1.01, "learning_rate": 1.4918692509855455e-05, "loss": 1.1257, "step": 6127 }, { "epoch": 1.01, "learning_rate": 1.491622864651774e-05, "loss": 0.8947, "step": 6128 }, { "epoch": 1.01, "learning_rate": 1.4913764783180027e-05, "loss": 0.3386, "step": 6129 }, { "epoch": 1.01, "learning_rate": 1.4911300919842313e-05, "loss": 0.479, "step": 6130 }, { "epoch": 1.01, "learning_rate": 1.4908837056504599e-05, "loss": 0.484, "step": 6131 }, { "epoch": 1.01, "learning_rate": 1.4906373193166886e-05, "loss": 0.3506, "step": 6132 }, { "epoch": 1.01, "learning_rate": 1.4903909329829172e-05, "loss": 1.2622, "step": 6133 }, { "epoch": 1.01, "learning_rate": 1.4901445466491458e-05, "loss": 1.0706, "step": 6134 }, { "epoch": 1.01, "learning_rate": 1.4898981603153744e-05, "loss": 0.7037, "step": 6135 }, { "epoch": 1.01, "learning_rate": 1.4896517739816032e-05, "loss": 0.6944, "step": 6136 }, { "epoch": 1.01, "learning_rate": 1.489405387647832e-05, "loss": 0.9122, "step": 6137 }, { "epoch": 1.01, "learning_rate": 1.4891590013140606e-05, "loss": 0.8924, "step": 6138 }, { "epoch": 1.01, "learning_rate": 1.4889126149802892e-05, "loss": 0.5031, "step": 6139 }, { "epoch": 1.01, "learning_rate": 1.4886662286465178e-05, "loss": 0.6204, "step": 6140 }, { "epoch": 1.01, "learning_rate": 1.4884198423127464e-05, "loss": 0.403, "step": 6141 }, { "epoch": 1.01, "learning_rate": 1.4881734559789751e-05, "loss": 0.5148, "step": 6142 }, { "epoch": 1.01, "learning_rate": 1.4879270696452037e-05, "loss": 0.4241, "step": 6143 }, { "epoch": 1.01, "learning_rate": 1.4876806833114323e-05, "loss": 0.6395, "step": 6144 }, { "epoch": 1.01, "learning_rate": 1.487434296977661e-05, "loss": 0.6198, "step": 6145 }, { "epoch": 1.01, "learning_rate": 1.4871879106438895e-05, "loss": 0.9945, "step": 6146 }, { "epoch": 1.01, "learning_rate": 1.4869415243101183e-05, "loss": 0.4452, "step": 6147 }, { "epoch": 1.01, "learning_rate": 1.486695137976347e-05, "loss": 0.8836, "step": 6148 }, { "epoch": 1.01, "learning_rate": 1.4864487516425757e-05, "loss": 0.7481, "step": 6149 }, { "epoch": 1.01, "learning_rate": 1.4862023653088043e-05, "loss": 0.492, "step": 6150 }, { "epoch": 1.01, "learning_rate": 1.4859559789750329e-05, "loss": 0.6012, "step": 6151 }, { "epoch": 1.01, "learning_rate": 1.4857095926412616e-05, "loss": 0.7484, "step": 6152 }, { "epoch": 1.01, "learning_rate": 1.4854632063074902e-05, "loss": 1.1358, "step": 6153 }, { "epoch": 1.01, "learning_rate": 1.4852168199737188e-05, "loss": 0.4408, "step": 6154 }, { "epoch": 1.01, "learning_rate": 1.4849704336399474e-05, "loss": 0.2692, "step": 6155 }, { "epoch": 1.01, "learning_rate": 1.484724047306176e-05, "loss": 0.2234, "step": 6156 }, { "epoch": 1.01, "learning_rate": 1.4844776609724048e-05, "loss": 0.472, "step": 6157 }, { "epoch": 1.01, "learning_rate": 1.4842312746386334e-05, "loss": 0.7789, "step": 6158 }, { "epoch": 1.01, "learning_rate": 1.483984888304862e-05, "loss": 0.396, "step": 6159 }, { "epoch": 1.01, "learning_rate": 1.4837385019710908e-05, "loss": 0.4632, "step": 6160 }, { "epoch": 1.01, "learning_rate": 1.4834921156373194e-05, "loss": 0.4856, "step": 6161 }, { "epoch": 1.01, "learning_rate": 1.4832457293035481e-05, "loss": 0.7802, "step": 6162 }, { "epoch": 1.01, "learning_rate": 1.4829993429697767e-05, "loss": 0.3204, "step": 6163 }, { "epoch": 1.01, "learning_rate": 1.4827529566360053e-05, "loss": 0.3341, "step": 6164 }, { "epoch": 1.01, "learning_rate": 1.482506570302234e-05, "loss": 0.7851, "step": 6165 }, { "epoch": 1.01, "learning_rate": 1.4822601839684625e-05, "loss": 0.3882, "step": 6166 }, { "epoch": 1.01, "learning_rate": 1.4820137976346913e-05, "loss": 0.8247, "step": 6167 }, { "epoch": 1.01, "learning_rate": 1.4817674113009199e-05, "loss": 0.5259, "step": 6168 }, { "epoch": 1.01, "learning_rate": 1.4815210249671485e-05, "loss": 0.8792, "step": 6169 }, { "epoch": 1.01, "learning_rate": 1.481274638633377e-05, "loss": 0.7867, "step": 6170 }, { "epoch": 1.01, "learning_rate": 1.4810282522996057e-05, "loss": 0.3895, "step": 6171 }, { "epoch": 1.01, "learning_rate": 1.4807818659658346e-05, "loss": 0.5996, "step": 6172 }, { "epoch": 1.01, "learning_rate": 1.4805354796320632e-05, "loss": 0.4585, "step": 6173 }, { "epoch": 1.01, "learning_rate": 1.4802890932982918e-05, "loss": 0.6042, "step": 6174 }, { "epoch": 1.01, "learning_rate": 1.4800427069645204e-05, "loss": 0.242, "step": 6175 }, { "epoch": 1.01, "learning_rate": 1.479796320630749e-05, "loss": 0.6233, "step": 6176 }, { "epoch": 1.01, "learning_rate": 1.4795499342969778e-05, "loss": 0.3366, "step": 6177 }, { "epoch": 1.01, "learning_rate": 1.4793035479632064e-05, "loss": 0.5251, "step": 6178 }, { "epoch": 1.01, "learning_rate": 1.479057161629435e-05, "loss": 0.4174, "step": 6179 }, { "epoch": 1.02, "learning_rate": 1.4788107752956636e-05, "loss": 0.7413, "step": 6180 }, { "epoch": 1.02, "learning_rate": 1.4785643889618922e-05, "loss": 0.5824, "step": 6181 }, { "epoch": 1.02, "learning_rate": 1.478318002628121e-05, "loss": 0.7415, "step": 6182 }, { "epoch": 1.02, "learning_rate": 1.4780716162943495e-05, "loss": 0.5825, "step": 6183 }, { "epoch": 1.02, "learning_rate": 1.4778252299605783e-05, "loss": 0.2961, "step": 6184 }, { "epoch": 1.02, "learning_rate": 1.4775788436268069e-05, "loss": 0.5364, "step": 6185 }, { "epoch": 1.02, "learning_rate": 1.4773324572930355e-05, "loss": 0.2495, "step": 6186 }, { "epoch": 1.02, "learning_rate": 1.4770860709592643e-05, "loss": 0.4387, "step": 6187 }, { "epoch": 1.02, "learning_rate": 1.4768396846254929e-05, "loss": 0.3007, "step": 6188 }, { "epoch": 1.02, "learning_rate": 1.4765932982917215e-05, "loss": 0.9962, "step": 6189 }, { "epoch": 1.02, "learning_rate": 1.47634691195795e-05, "loss": 0.5024, "step": 6190 }, { "epoch": 1.02, "learning_rate": 1.4761005256241787e-05, "loss": 0.7868, "step": 6191 }, { "epoch": 1.02, "learning_rate": 1.4758541392904074e-05, "loss": 0.7169, "step": 6192 }, { "epoch": 1.02, "learning_rate": 1.475607752956636e-05, "loss": 0.2919, "step": 6193 }, { "epoch": 1.02, "learning_rate": 1.4753613666228646e-05, "loss": 0.2365, "step": 6194 }, { "epoch": 1.02, "learning_rate": 1.4751149802890932e-05, "loss": 0.5154, "step": 6195 }, { "epoch": 1.02, "learning_rate": 1.474868593955322e-05, "loss": 1.2799, "step": 6196 }, { "epoch": 1.02, "learning_rate": 1.4746222076215508e-05, "loss": 0.369, "step": 6197 }, { "epoch": 1.02, "learning_rate": 1.4743758212877794e-05, "loss": 0.4232, "step": 6198 }, { "epoch": 1.02, "learning_rate": 1.474129434954008e-05, "loss": 0.5544, "step": 6199 }, { "epoch": 1.02, "learning_rate": 1.4738830486202366e-05, "loss": 0.5563, "step": 6200 }, { "epoch": 1.02, "learning_rate": 1.4736366622864652e-05, "loss": 0.5683, "step": 6201 }, { "epoch": 1.02, "learning_rate": 1.473390275952694e-05, "loss": 0.3162, "step": 6202 }, { "epoch": 1.02, "learning_rate": 1.4731438896189225e-05, "loss": 0.1889, "step": 6203 }, { "epoch": 1.02, "learning_rate": 1.4728975032851511e-05, "loss": 0.5188, "step": 6204 }, { "epoch": 1.02, "learning_rate": 1.4726511169513797e-05, "loss": 0.5982, "step": 6205 }, { "epoch": 1.02, "learning_rate": 1.4724047306176083e-05, "loss": 0.5, "step": 6206 }, { "epoch": 1.02, "learning_rate": 1.472158344283837e-05, "loss": 0.3405, "step": 6207 }, { "epoch": 1.02, "learning_rate": 1.4719119579500659e-05, "loss": 0.8093, "step": 6208 }, { "epoch": 1.02, "learning_rate": 1.4716655716162945e-05, "loss": 0.5578, "step": 6209 }, { "epoch": 1.02, "learning_rate": 1.471419185282523e-05, "loss": 0.5031, "step": 6210 }, { "epoch": 1.02, "learning_rate": 1.4711727989487516e-05, "loss": 0.4828, "step": 6211 }, { "epoch": 1.02, "learning_rate": 1.4709264126149804e-05, "loss": 0.5005, "step": 6212 }, { "epoch": 1.02, "learning_rate": 1.470680026281209e-05, "loss": 0.1178, "step": 6213 }, { "epoch": 1.02, "learning_rate": 1.4704336399474376e-05, "loss": 0.6173, "step": 6214 }, { "epoch": 1.02, "learning_rate": 1.4701872536136662e-05, "loss": 0.1689, "step": 6215 }, { "epoch": 1.02, "learning_rate": 1.4699408672798948e-05, "loss": 0.6521, "step": 6216 }, { "epoch": 1.02, "learning_rate": 1.4696944809461236e-05, "loss": 0.6545, "step": 6217 }, { "epoch": 1.02, "learning_rate": 1.4694480946123522e-05, "loss": 0.3537, "step": 6218 }, { "epoch": 1.02, "learning_rate": 1.4692017082785808e-05, "loss": 0.3796, "step": 6219 }, { "epoch": 1.02, "learning_rate": 1.4689553219448095e-05, "loss": 0.9074, "step": 6220 }, { "epoch": 1.02, "learning_rate": 1.4687089356110381e-05, "loss": 0.6782, "step": 6221 }, { "epoch": 1.02, "learning_rate": 1.4684625492772669e-05, "loss": 0.4423, "step": 6222 }, { "epoch": 1.02, "learning_rate": 1.4682161629434955e-05, "loss": 0.4893, "step": 6223 }, { "epoch": 1.02, "learning_rate": 1.4679697766097241e-05, "loss": 0.7058, "step": 6224 }, { "epoch": 1.02, "learning_rate": 1.4677233902759527e-05, "loss": 0.3166, "step": 6225 }, { "epoch": 1.02, "learning_rate": 1.4674770039421813e-05, "loss": 0.7677, "step": 6226 }, { "epoch": 1.02, "learning_rate": 1.46723061760841e-05, "loss": 0.4599, "step": 6227 }, { "epoch": 1.02, "learning_rate": 1.4669842312746387e-05, "loss": 0.5011, "step": 6228 }, { "epoch": 1.02, "learning_rate": 1.4667378449408673e-05, "loss": 0.5757, "step": 6229 }, { "epoch": 1.02, "learning_rate": 1.4664914586070959e-05, "loss": 0.7049, "step": 6230 }, { "epoch": 1.02, "learning_rate": 1.4662450722733246e-05, "loss": 0.6508, "step": 6231 }, { "epoch": 1.02, "learning_rate": 1.4659986859395534e-05, "loss": 0.5923, "step": 6232 }, { "epoch": 1.02, "learning_rate": 1.465752299605782e-05, "loss": 0.5786, "step": 6233 }, { "epoch": 1.02, "learning_rate": 1.4655059132720106e-05, "loss": 0.6385, "step": 6234 }, { "epoch": 1.02, "learning_rate": 1.4652595269382392e-05, "loss": 0.753, "step": 6235 }, { "epoch": 1.02, "learning_rate": 1.4650131406044678e-05, "loss": 0.6101, "step": 6236 }, { "epoch": 1.02, "learning_rate": 1.4647667542706966e-05, "loss": 0.6146, "step": 6237 }, { "epoch": 1.02, "learning_rate": 1.4645203679369252e-05, "loss": 0.8417, "step": 6238 }, { "epoch": 1.02, "learning_rate": 1.4642739816031538e-05, "loss": 0.2523, "step": 6239 }, { "epoch": 1.02, "learning_rate": 1.4640275952693824e-05, "loss": 0.6138, "step": 6240 }, { "epoch": 1.03, "learning_rate": 1.463781208935611e-05, "loss": 0.3744, "step": 6241 }, { "epoch": 1.03, "learning_rate": 1.4635348226018397e-05, "loss": 0.6665, "step": 6242 }, { "epoch": 1.03, "learning_rate": 1.4632884362680685e-05, "loss": 0.7848, "step": 6243 }, { "epoch": 1.03, "learning_rate": 1.4630420499342971e-05, "loss": 0.6477, "step": 6244 }, { "epoch": 1.03, "learning_rate": 1.4627956636005257e-05, "loss": 0.6107, "step": 6245 }, { "epoch": 1.03, "learning_rate": 1.4625492772667543e-05, "loss": 0.5367, "step": 6246 }, { "epoch": 1.03, "learning_rate": 1.462302890932983e-05, "loss": 0.458, "step": 6247 }, { "epoch": 1.03, "learning_rate": 1.4620565045992117e-05, "loss": 0.3051, "step": 6248 }, { "epoch": 1.03, "learning_rate": 1.4618101182654403e-05, "loss": 0.8775, "step": 6249 }, { "epoch": 1.03, "learning_rate": 1.4615637319316689e-05, "loss": 0.6942, "step": 6250 }, { "epoch": 1.03, "learning_rate": 1.4613173455978974e-05, "loss": 0.6966, "step": 6251 }, { "epoch": 1.03, "learning_rate": 1.4610709592641262e-05, "loss": 0.4549, "step": 6252 }, { "epoch": 1.03, "learning_rate": 1.4608245729303548e-05, "loss": 0.4507, "step": 6253 }, { "epoch": 1.03, "learning_rate": 1.4605781865965834e-05, "loss": 0.6475, "step": 6254 }, { "epoch": 1.03, "learning_rate": 1.4603318002628122e-05, "loss": 0.4761, "step": 6255 }, { "epoch": 1.03, "learning_rate": 1.4600854139290408e-05, "loss": 0.9772, "step": 6256 }, { "epoch": 1.03, "learning_rate": 1.4598390275952695e-05, "loss": 0.5881, "step": 6257 }, { "epoch": 1.03, "learning_rate": 1.4595926412614981e-05, "loss": 0.6373, "step": 6258 }, { "epoch": 1.03, "learning_rate": 1.4593462549277267e-05, "loss": 0.2624, "step": 6259 }, { "epoch": 1.03, "learning_rate": 1.4590998685939553e-05, "loss": 0.5721, "step": 6260 }, { "epoch": 1.03, "learning_rate": 1.458853482260184e-05, "loss": 0.2204, "step": 6261 }, { "epoch": 1.03, "learning_rate": 1.4586070959264127e-05, "loss": 0.6291, "step": 6262 }, { "epoch": 1.03, "learning_rate": 1.4583607095926413e-05, "loss": 0.6079, "step": 6263 }, { "epoch": 1.03, "learning_rate": 1.4581143232588699e-05, "loss": 0.6106, "step": 6264 }, { "epoch": 1.03, "learning_rate": 1.4578679369250985e-05, "loss": 0.3882, "step": 6265 }, { "epoch": 1.03, "learning_rate": 1.4576215505913271e-05, "loss": 0.5589, "step": 6266 }, { "epoch": 1.03, "learning_rate": 1.457375164257556e-05, "loss": 0.8268, "step": 6267 }, { "epoch": 1.03, "learning_rate": 1.4571287779237846e-05, "loss": 0.976, "step": 6268 }, { "epoch": 1.03, "learning_rate": 1.4568823915900132e-05, "loss": 0.4464, "step": 6269 }, { "epoch": 1.03, "learning_rate": 1.4566360052562418e-05, "loss": 0.6835, "step": 6270 }, { "epoch": 1.03, "learning_rate": 1.4563896189224704e-05, "loss": 0.9053, "step": 6271 }, { "epoch": 1.03, "learning_rate": 1.4561432325886992e-05, "loss": 0.4058, "step": 6272 }, { "epoch": 1.03, "learning_rate": 1.4558968462549278e-05, "loss": 0.8216, "step": 6273 }, { "epoch": 1.03, "learning_rate": 1.4556504599211564e-05, "loss": 0.7372, "step": 6274 }, { "epoch": 1.03, "learning_rate": 1.455404073587385e-05, "loss": 0.6008, "step": 6275 }, { "epoch": 1.03, "learning_rate": 1.4551576872536136e-05, "loss": 0.2723, "step": 6276 }, { "epoch": 1.03, "learning_rate": 1.4549113009198424e-05, "loss": 0.2355, "step": 6277 }, { "epoch": 1.03, "learning_rate": 1.454664914586071e-05, "loss": 0.6334, "step": 6278 }, { "epoch": 1.03, "learning_rate": 1.4544185282522997e-05, "loss": 0.3273, "step": 6279 }, { "epoch": 1.03, "learning_rate": 1.4541721419185283e-05, "loss": 0.5813, "step": 6280 }, { "epoch": 1.03, "learning_rate": 1.453925755584757e-05, "loss": 0.1634, "step": 6281 }, { "epoch": 1.03, "learning_rate": 1.4536793692509857e-05, "loss": 0.5213, "step": 6282 }, { "epoch": 1.03, "learning_rate": 1.4534329829172143e-05, "loss": 0.3756, "step": 6283 }, { "epoch": 1.03, "learning_rate": 1.4531865965834429e-05, "loss": 0.4906, "step": 6284 }, { "epoch": 1.03, "learning_rate": 1.4529402102496715e-05, "loss": 0.9253, "step": 6285 }, { "epoch": 1.03, "learning_rate": 1.4526938239159001e-05, "loss": 0.8062, "step": 6286 }, { "epoch": 1.03, "learning_rate": 1.4524474375821289e-05, "loss": 0.3941, "step": 6287 }, { "epoch": 1.03, "learning_rate": 1.4522010512483575e-05, "loss": 0.4411, "step": 6288 }, { "epoch": 1.03, "learning_rate": 1.451954664914586e-05, "loss": 0.8214, "step": 6289 }, { "epoch": 1.03, "learning_rate": 1.4517082785808147e-05, "loss": 0.4226, "step": 6290 }, { "epoch": 1.03, "learning_rate": 1.4514618922470434e-05, "loss": 0.729, "step": 6291 }, { "epoch": 1.03, "learning_rate": 1.4512155059132722e-05, "loss": 0.6482, "step": 6292 }, { "epoch": 1.03, "learning_rate": 1.4509691195795008e-05, "loss": 1.1188, "step": 6293 }, { "epoch": 1.03, "learning_rate": 1.4507227332457294e-05, "loss": 0.8396, "step": 6294 }, { "epoch": 1.03, "learning_rate": 1.450476346911958e-05, "loss": 0.5709, "step": 6295 }, { "epoch": 1.03, "learning_rate": 1.4502299605781866e-05, "loss": 1.0017, "step": 6296 }, { "epoch": 1.03, "learning_rate": 1.4499835742444154e-05, "loss": 0.2821, "step": 6297 }, { "epoch": 1.03, "learning_rate": 1.449737187910644e-05, "loss": 0.3227, "step": 6298 }, { "epoch": 1.03, "learning_rate": 1.4494908015768725e-05, "loss": 0.2414, "step": 6299 }, { "epoch": 1.03, "learning_rate": 1.4492444152431011e-05, "loss": 0.5578, "step": 6300 }, { "epoch": 1.03, "learning_rate": 1.4489980289093297e-05, "loss": 0.1659, "step": 6301 }, { "epoch": 1.04, "learning_rate": 1.4487516425755585e-05, "loss": 0.469, "step": 6302 }, { "epoch": 1.04, "learning_rate": 1.4485052562417873e-05, "loss": 0.536, "step": 6303 }, { "epoch": 1.04, "learning_rate": 1.4482588699080159e-05, "loss": 0.5039, "step": 6304 }, { "epoch": 1.04, "learning_rate": 1.4480124835742445e-05, "loss": 0.3729, "step": 6305 }, { "epoch": 1.04, "learning_rate": 1.447766097240473e-05, "loss": 0.2531, "step": 6306 }, { "epoch": 1.04, "learning_rate": 1.4475197109067018e-05, "loss": 0.4466, "step": 6307 }, { "epoch": 1.04, "learning_rate": 1.4472733245729304e-05, "loss": 0.5098, "step": 6308 }, { "epoch": 1.04, "learning_rate": 1.447026938239159e-05, "loss": 0.5414, "step": 6309 }, { "epoch": 1.04, "learning_rate": 1.4467805519053876e-05, "loss": 0.4431, "step": 6310 }, { "epoch": 1.04, "learning_rate": 1.4465341655716162e-05, "loss": 0.4033, "step": 6311 }, { "epoch": 1.04, "learning_rate": 1.446287779237845e-05, "loss": 0.7016, "step": 6312 }, { "epoch": 1.04, "learning_rate": 1.4460413929040736e-05, "loss": 1.0213, "step": 6313 }, { "epoch": 1.04, "learning_rate": 1.4457950065703022e-05, "loss": 0.7405, "step": 6314 }, { "epoch": 1.04, "learning_rate": 1.445548620236531e-05, "loss": 0.8404, "step": 6315 }, { "epoch": 1.04, "learning_rate": 1.4453022339027596e-05, "loss": 0.3012, "step": 6316 }, { "epoch": 1.04, "learning_rate": 1.4450558475689883e-05, "loss": 1.0083, "step": 6317 }, { "epoch": 1.04, "learning_rate": 1.444809461235217e-05, "loss": 0.4693, "step": 6318 }, { "epoch": 1.04, "learning_rate": 1.4445630749014455e-05, "loss": 0.4981, "step": 6319 }, { "epoch": 1.04, "learning_rate": 1.4443166885676741e-05, "loss": 0.2961, "step": 6320 }, { "epoch": 1.04, "learning_rate": 1.4440703022339027e-05, "loss": 0.3729, "step": 6321 }, { "epoch": 1.04, "learning_rate": 1.4438239159001315e-05, "loss": 0.4758, "step": 6322 }, { "epoch": 1.04, "learning_rate": 1.4435775295663601e-05, "loss": 0.3448, "step": 6323 }, { "epoch": 1.04, "learning_rate": 1.4433311432325887e-05, "loss": 0.5062, "step": 6324 }, { "epoch": 1.04, "learning_rate": 1.4430847568988173e-05, "loss": 0.3294, "step": 6325 }, { "epoch": 1.04, "learning_rate": 1.4428383705650459e-05, "loss": 1.1251, "step": 6326 }, { "epoch": 1.04, "learning_rate": 1.4425919842312748e-05, "loss": 0.5275, "step": 6327 }, { "epoch": 1.04, "learning_rate": 1.4423455978975034e-05, "loss": 0.2914, "step": 6328 }, { "epoch": 1.04, "learning_rate": 1.442099211563732e-05, "loss": 0.33, "step": 6329 }, { "epoch": 1.04, "learning_rate": 1.4418528252299606e-05, "loss": 0.522, "step": 6330 }, { "epoch": 1.04, "learning_rate": 1.4416064388961892e-05, "loss": 1.3229, "step": 6331 }, { "epoch": 1.04, "learning_rate": 1.441360052562418e-05, "loss": 0.5562, "step": 6332 }, { "epoch": 1.04, "learning_rate": 1.4411136662286466e-05, "loss": 0.4668, "step": 6333 }, { "epoch": 1.04, "learning_rate": 1.4408672798948752e-05, "loss": 0.5903, "step": 6334 }, { "epoch": 1.04, "learning_rate": 1.4406208935611038e-05, "loss": 0.4352, "step": 6335 }, { "epoch": 1.04, "learning_rate": 1.4403745072273324e-05, "loss": 0.6425, "step": 6336 }, { "epoch": 1.04, "learning_rate": 1.4401281208935612e-05, "loss": 0.7173, "step": 6337 }, { "epoch": 1.04, "learning_rate": 1.4398817345597898e-05, "loss": 0.6625, "step": 6338 }, { "epoch": 1.04, "learning_rate": 1.4396353482260185e-05, "loss": 0.5907, "step": 6339 }, { "epoch": 1.04, "learning_rate": 1.4393889618922471e-05, "loss": 0.5222, "step": 6340 }, { "epoch": 1.04, "learning_rate": 1.4391425755584757e-05, "loss": 0.2757, "step": 6341 }, { "epoch": 1.04, "learning_rate": 1.4388961892247045e-05, "loss": 0.5981, "step": 6342 }, { "epoch": 1.04, "learning_rate": 1.438649802890933e-05, "loss": 0.326, "step": 6343 }, { "epoch": 1.04, "learning_rate": 1.4384034165571617e-05, "loss": 0.6488, "step": 6344 }, { "epoch": 1.04, "learning_rate": 1.4381570302233903e-05, "loss": 0.3329, "step": 6345 }, { "epoch": 1.04, "learning_rate": 1.4379106438896189e-05, "loss": 0.5813, "step": 6346 }, { "epoch": 1.04, "learning_rate": 1.4376642575558476e-05, "loss": 0.5884, "step": 6347 }, { "epoch": 1.04, "learning_rate": 1.4374178712220762e-05, "loss": 0.9537, "step": 6348 }, { "epoch": 1.04, "learning_rate": 1.4371714848883048e-05, "loss": 0.3555, "step": 6349 }, { "epoch": 1.04, "learning_rate": 1.4369250985545334e-05, "loss": 1.1499, "step": 6350 }, { "epoch": 1.04, "learning_rate": 1.4366787122207622e-05, "loss": 0.3496, "step": 6351 }, { "epoch": 1.04, "learning_rate": 1.436432325886991e-05, "loss": 0.5647, "step": 6352 }, { "epoch": 1.04, "learning_rate": 1.4361859395532196e-05, "loss": 0.5734, "step": 6353 }, { "epoch": 1.04, "learning_rate": 1.4359395532194482e-05, "loss": 1.1619, "step": 6354 }, { "epoch": 1.04, "learning_rate": 1.4356931668856768e-05, "loss": 0.7083, "step": 6355 }, { "epoch": 1.04, "learning_rate": 1.4354467805519054e-05, "loss": 0.4962, "step": 6356 }, { "epoch": 1.04, "learning_rate": 1.4352003942181341e-05, "loss": 0.4958, "step": 6357 }, { "epoch": 1.04, "learning_rate": 1.4349540078843627e-05, "loss": 0.5402, "step": 6358 }, { "epoch": 1.04, "learning_rate": 1.4347076215505913e-05, "loss": 0.5985, "step": 6359 }, { "epoch": 1.04, "learning_rate": 1.43446123521682e-05, "loss": 0.9383, "step": 6360 }, { "epoch": 1.04, "learning_rate": 1.4342148488830485e-05, "loss": 0.4155, "step": 6361 }, { "epoch": 1.05, "learning_rate": 1.4339684625492773e-05, "loss": 1.4217, "step": 6362 }, { "epoch": 1.05, "learning_rate": 1.433722076215506e-05, "loss": 0.4455, "step": 6363 }, { "epoch": 1.05, "learning_rate": 1.4334756898817347e-05, "loss": 0.5032, "step": 6364 }, { "epoch": 1.05, "learning_rate": 1.4332293035479633e-05, "loss": 0.5358, "step": 6365 }, { "epoch": 1.05, "learning_rate": 1.4329829172141919e-05, "loss": 0.4171, "step": 6366 }, { "epoch": 1.05, "learning_rate": 1.4327365308804206e-05, "loss": 0.2793, "step": 6367 }, { "epoch": 1.05, "learning_rate": 1.4324901445466492e-05, "loss": 0.2461, "step": 6368 }, { "epoch": 1.05, "learning_rate": 1.4322437582128778e-05, "loss": 0.9519, "step": 6369 }, { "epoch": 1.05, "learning_rate": 1.4319973718791064e-05, "loss": 0.2263, "step": 6370 }, { "epoch": 1.05, "learning_rate": 1.431750985545335e-05, "loss": 0.5825, "step": 6371 }, { "epoch": 1.05, "learning_rate": 1.4315045992115638e-05, "loss": 0.3613, "step": 6372 }, { "epoch": 1.05, "learning_rate": 1.4312582128777924e-05, "loss": 0.2853, "step": 6373 }, { "epoch": 1.05, "learning_rate": 1.4310118265440212e-05, "loss": 0.6025, "step": 6374 }, { "epoch": 1.05, "learning_rate": 1.4307654402102498e-05, "loss": 0.3253, "step": 6375 }, { "epoch": 1.05, "learning_rate": 1.4305190538764784e-05, "loss": 0.4513, "step": 6376 }, { "epoch": 1.05, "learning_rate": 1.4302726675427071e-05, "loss": 0.633, "step": 6377 }, { "epoch": 1.05, "learning_rate": 1.4300262812089357e-05, "loss": 0.2064, "step": 6378 }, { "epoch": 1.05, "learning_rate": 1.4297798948751643e-05, "loss": 1.1942, "step": 6379 }, { "epoch": 1.05, "learning_rate": 1.429533508541393e-05, "loss": 0.6489, "step": 6380 }, { "epoch": 1.05, "learning_rate": 1.4292871222076215e-05, "loss": 0.1984, "step": 6381 }, { "epoch": 1.05, "learning_rate": 1.4290407358738503e-05, "loss": 0.3381, "step": 6382 }, { "epoch": 1.05, "learning_rate": 1.4287943495400789e-05, "loss": 0.425, "step": 6383 }, { "epoch": 1.05, "learning_rate": 1.4285479632063075e-05, "loss": 0.2367, "step": 6384 }, { "epoch": 1.05, "learning_rate": 1.428301576872536e-05, "loss": 0.584, "step": 6385 }, { "epoch": 1.05, "learning_rate": 1.4280551905387648e-05, "loss": 0.2887, "step": 6386 }, { "epoch": 1.05, "learning_rate": 1.4278088042049936e-05, "loss": 1.0665, "step": 6387 }, { "epoch": 1.05, "learning_rate": 1.4275624178712222e-05, "loss": 1.2917, "step": 6388 }, { "epoch": 1.05, "learning_rate": 1.4273160315374508e-05, "loss": 0.3017, "step": 6389 }, { "epoch": 1.05, "learning_rate": 1.4270696452036794e-05, "loss": 0.6984, "step": 6390 }, { "epoch": 1.05, "learning_rate": 1.426823258869908e-05, "loss": 0.3849, "step": 6391 }, { "epoch": 1.05, "learning_rate": 1.4265768725361368e-05, "loss": 1.5712, "step": 6392 }, { "epoch": 1.05, "learning_rate": 1.4263304862023654e-05, "loss": 0.4924, "step": 6393 }, { "epoch": 1.05, "learning_rate": 1.426084099868594e-05, "loss": 0.3229, "step": 6394 }, { "epoch": 1.05, "learning_rate": 1.4258377135348226e-05, "loss": 1.0599, "step": 6395 }, { "epoch": 1.05, "learning_rate": 1.4255913272010512e-05, "loss": 0.6509, "step": 6396 }, { "epoch": 1.05, "learning_rate": 1.42534494086728e-05, "loss": 0.4408, "step": 6397 }, { "epoch": 1.05, "learning_rate": 1.4250985545335087e-05, "loss": 0.396, "step": 6398 }, { "epoch": 1.05, "learning_rate": 1.4248521681997373e-05, "loss": 0.5106, "step": 6399 }, { "epoch": 1.05, "learning_rate": 1.4246057818659659e-05, "loss": 0.407, "step": 6400 }, { "epoch": 1.05, "learning_rate": 1.4243593955321945e-05, "loss": 0.5005, "step": 6401 }, { "epoch": 1.05, "learning_rate": 1.4241130091984233e-05, "loss": 0.5673, "step": 6402 }, { "epoch": 1.05, "learning_rate": 1.4238666228646519e-05, "loss": 0.4899, "step": 6403 }, { "epoch": 1.05, "learning_rate": 1.4236202365308805e-05, "loss": 0.5328, "step": 6404 }, { "epoch": 1.05, "learning_rate": 1.423373850197109e-05, "loss": 0.372, "step": 6405 }, { "epoch": 1.05, "learning_rate": 1.4231274638633377e-05, "loss": 0.7839, "step": 6406 }, { "epoch": 1.05, "learning_rate": 1.4228810775295664e-05, "loss": 0.3968, "step": 6407 }, { "epoch": 1.05, "learning_rate": 1.422634691195795e-05, "loss": 0.878, "step": 6408 }, { "epoch": 1.05, "learning_rate": 1.4223883048620236e-05, "loss": 0.412, "step": 6409 }, { "epoch": 1.05, "learning_rate": 1.4221419185282524e-05, "loss": 0.5263, "step": 6410 }, { "epoch": 1.05, "learning_rate": 1.421895532194481e-05, "loss": 0.8993, "step": 6411 }, { "epoch": 1.05, "learning_rate": 1.4216491458607098e-05, "loss": 0.4167, "step": 6412 }, { "epoch": 1.05, "learning_rate": 1.4214027595269384e-05, "loss": 0.4132, "step": 6413 }, { "epoch": 1.05, "learning_rate": 1.421156373193167e-05, "loss": 0.3711, "step": 6414 }, { "epoch": 1.05, "learning_rate": 1.4209099868593956e-05, "loss": 0.5628, "step": 6415 }, { "epoch": 1.05, "learning_rate": 1.4206636005256242e-05, "loss": 0.4115, "step": 6416 }, { "epoch": 1.05, "learning_rate": 1.420417214191853e-05, "loss": 0.3677, "step": 6417 }, { "epoch": 1.05, "learning_rate": 1.4201708278580815e-05, "loss": 0.8087, "step": 6418 }, { "epoch": 1.05, "learning_rate": 1.4199244415243101e-05, "loss": 0.4105, "step": 6419 }, { "epoch": 1.05, "learning_rate": 1.4196780551905387e-05, "loss": 0.4419, "step": 6420 }, { "epoch": 1.05, "learning_rate": 1.4194316688567673e-05, "loss": 0.432, "step": 6421 }, { "epoch": 1.05, "learning_rate": 1.4191852825229963e-05, "loss": 1.1795, "step": 6422 }, { "epoch": 1.06, "learning_rate": 1.4189388961892249e-05, "loss": 0.3074, "step": 6423 }, { "epoch": 1.06, "learning_rate": 1.4186925098554535e-05, "loss": 0.477, "step": 6424 }, { "epoch": 1.06, "learning_rate": 1.418446123521682e-05, "loss": 1.1643, "step": 6425 }, { "epoch": 1.06, "learning_rate": 1.4181997371879106e-05, "loss": 1.363, "step": 6426 }, { "epoch": 1.06, "learning_rate": 1.4179533508541394e-05, "loss": 0.2975, "step": 6427 }, { "epoch": 1.06, "learning_rate": 1.417706964520368e-05, "loss": 0.7794, "step": 6428 }, { "epoch": 1.06, "learning_rate": 1.4174605781865966e-05, "loss": 0.3582, "step": 6429 }, { "epoch": 1.06, "learning_rate": 1.4172141918528252e-05, "loss": 0.3953, "step": 6430 }, { "epoch": 1.06, "learning_rate": 1.4169678055190538e-05, "loss": 0.2468, "step": 6431 }, { "epoch": 1.06, "learning_rate": 1.4167214191852826e-05, "loss": 0.8133, "step": 6432 }, { "epoch": 1.06, "learning_rate": 1.4164750328515112e-05, "loss": 0.2647, "step": 6433 }, { "epoch": 1.06, "learning_rate": 1.41622864651774e-05, "loss": 0.4888, "step": 6434 }, { "epoch": 1.06, "learning_rate": 1.4159822601839685e-05, "loss": 0.5809, "step": 6435 }, { "epoch": 1.06, "learning_rate": 1.4157358738501971e-05, "loss": 0.4062, "step": 6436 }, { "epoch": 1.06, "learning_rate": 1.4154894875164259e-05, "loss": 0.3873, "step": 6437 }, { "epoch": 1.06, "learning_rate": 1.4152431011826545e-05, "loss": 0.3005, "step": 6438 }, { "epoch": 1.06, "learning_rate": 1.4149967148488831e-05, "loss": 0.3287, "step": 6439 }, { "epoch": 1.06, "learning_rate": 1.4147503285151117e-05, "loss": 0.3261, "step": 6440 }, { "epoch": 1.06, "learning_rate": 1.4145039421813403e-05, "loss": 0.2316, "step": 6441 }, { "epoch": 1.06, "learning_rate": 1.414257555847569e-05, "loss": 1.1636, "step": 6442 }, { "epoch": 1.06, "learning_rate": 1.4140111695137977e-05, "loss": 0.6065, "step": 6443 }, { "epoch": 1.06, "learning_rate": 1.4137647831800263e-05, "loss": 0.4202, "step": 6444 }, { "epoch": 1.06, "learning_rate": 1.4135183968462549e-05, "loss": 0.4883, "step": 6445 }, { "epoch": 1.06, "learning_rate": 1.4132720105124836e-05, "loss": 0.548, "step": 6446 }, { "epoch": 1.06, "learning_rate": 1.4130256241787124e-05, "loss": 0.4424, "step": 6447 }, { "epoch": 1.06, "learning_rate": 1.412779237844941e-05, "loss": 0.9304, "step": 6448 }, { "epoch": 1.06, "learning_rate": 1.4125328515111696e-05, "loss": 0.6213, "step": 6449 }, { "epoch": 1.06, "learning_rate": 1.4122864651773982e-05, "loss": 0.4996, "step": 6450 }, { "epoch": 1.06, "learning_rate": 1.4120400788436268e-05, "loss": 0.567, "step": 6451 }, { "epoch": 1.06, "learning_rate": 1.4117936925098556e-05, "loss": 0.3821, "step": 6452 }, { "epoch": 1.06, "learning_rate": 1.4115473061760842e-05, "loss": 0.2982, "step": 6453 }, { "epoch": 1.06, "learning_rate": 1.4113009198423128e-05, "loss": 0.3096, "step": 6454 }, { "epoch": 1.06, "learning_rate": 1.4110545335085414e-05, "loss": 0.258, "step": 6455 }, { "epoch": 1.06, "learning_rate": 1.41080814717477e-05, "loss": 0.8338, "step": 6456 }, { "epoch": 1.06, "learning_rate": 1.4105617608409987e-05, "loss": 0.4004, "step": 6457 }, { "epoch": 1.06, "learning_rate": 1.4103153745072275e-05, "loss": 0.3213, "step": 6458 }, { "epoch": 1.06, "learning_rate": 1.4100689881734561e-05, "loss": 0.2695, "step": 6459 }, { "epoch": 1.06, "learning_rate": 1.4098226018396847e-05, "loss": 0.5279, "step": 6460 }, { "epoch": 1.06, "learning_rate": 1.4095762155059133e-05, "loss": 0.2543, "step": 6461 }, { "epoch": 1.06, "learning_rate": 1.409329829172142e-05, "loss": 0.617, "step": 6462 }, { "epoch": 1.06, "learning_rate": 1.4090834428383707e-05, "loss": 0.279, "step": 6463 }, { "epoch": 1.06, "learning_rate": 1.4088370565045993e-05, "loss": 0.3027, "step": 6464 }, { "epoch": 1.06, "learning_rate": 1.4085906701708279e-05, "loss": 0.428, "step": 6465 }, { "epoch": 1.06, "learning_rate": 1.4083442838370565e-05, "loss": 0.5451, "step": 6466 }, { "epoch": 1.06, "learning_rate": 1.4080978975032852e-05, "loss": 0.2933, "step": 6467 }, { "epoch": 1.06, "learning_rate": 1.4078515111695138e-05, "loss": 0.9812, "step": 6468 }, { "epoch": 1.06, "learning_rate": 1.4076051248357424e-05, "loss": 0.452, "step": 6469 }, { "epoch": 1.06, "learning_rate": 1.4073587385019712e-05, "loss": 0.4019, "step": 6470 }, { "epoch": 1.06, "learning_rate": 1.4071123521681998e-05, "loss": 0.9822, "step": 6471 }, { "epoch": 1.06, "learning_rate": 1.4068659658344286e-05, "loss": 0.5573, "step": 6472 }, { "epoch": 1.06, "learning_rate": 1.4066195795006571e-05, "loss": 0.259, "step": 6473 }, { "epoch": 1.06, "learning_rate": 1.4063731931668857e-05, "loss": 0.407, "step": 6474 }, { "epoch": 1.06, "learning_rate": 1.4061268068331143e-05, "loss": 0.7223, "step": 6475 }, { "epoch": 1.06, "learning_rate": 1.405880420499343e-05, "loss": 0.6905, "step": 6476 }, { "epoch": 1.06, "learning_rate": 1.4056340341655715e-05, "loss": 0.5228, "step": 6477 }, { "epoch": 1.06, "learning_rate": 1.4053876478318003e-05, "loss": 0.4843, "step": 6478 }, { "epoch": 1.06, "learning_rate": 1.4051412614980289e-05, "loss": 0.3546, "step": 6479 }, { "epoch": 1.06, "learning_rate": 1.4048948751642575e-05, "loss": 0.3038, "step": 6480 }, { "epoch": 1.06, "learning_rate": 1.4046484888304861e-05, "loss": 0.4297, "step": 6481 }, { "epoch": 1.06, "learning_rate": 1.4044021024967149e-05, "loss": 0.4429, "step": 6482 }, { "epoch": 1.06, "learning_rate": 1.4041557161629436e-05, "loss": 0.2336, "step": 6483 }, { "epoch": 1.07, "learning_rate": 1.4039093298291722e-05, "loss": 0.4093, "step": 6484 }, { "epoch": 1.07, "learning_rate": 1.4036629434954008e-05, "loss": 0.3497, "step": 6485 }, { "epoch": 1.07, "learning_rate": 1.4034165571616294e-05, "loss": 0.9594, "step": 6486 }, { "epoch": 1.07, "learning_rate": 1.403170170827858e-05, "loss": 0.418, "step": 6487 }, { "epoch": 1.07, "learning_rate": 1.4029237844940868e-05, "loss": 0.4654, "step": 6488 }, { "epoch": 1.07, "learning_rate": 1.4026773981603154e-05, "loss": 0.7535, "step": 6489 }, { "epoch": 1.07, "learning_rate": 1.402431011826544e-05, "loss": 0.6222, "step": 6490 }, { "epoch": 1.07, "learning_rate": 1.4021846254927726e-05, "loss": 0.684, "step": 6491 }, { "epoch": 1.07, "learning_rate": 1.4019382391590012e-05, "loss": 0.1675, "step": 6492 }, { "epoch": 1.07, "learning_rate": 1.40169185282523e-05, "loss": 0.9605, "step": 6493 }, { "epoch": 1.07, "learning_rate": 1.4014454664914587e-05, "loss": 0.4516, "step": 6494 }, { "epoch": 1.07, "learning_rate": 1.4011990801576873e-05, "loss": 0.1724, "step": 6495 }, { "epoch": 1.07, "learning_rate": 1.400952693823916e-05, "loss": 0.4369, "step": 6496 }, { "epoch": 1.07, "learning_rate": 1.4007063074901445e-05, "loss": 0.8253, "step": 6497 }, { "epoch": 1.07, "learning_rate": 1.4004599211563733e-05, "loss": 0.4756, "step": 6498 }, { "epoch": 1.07, "learning_rate": 1.4002135348226019e-05, "loss": 0.51, "step": 6499 }, { "epoch": 1.07, "learning_rate": 1.3999671484888305e-05, "loss": 0.1613, "step": 6500 }, { "epoch": 1.07, "eval_exact_match": 86.54683065279092, "eval_f1": 92.68315113748487, "step": 6500 }, { "epoch": 1.07, "learning_rate": 1.3997207621550591e-05, "loss": 0.5692, "step": 6501 }, { "epoch": 1.07, "learning_rate": 1.3994743758212877e-05, "loss": 0.7462, "step": 6502 }, { "epoch": 1.07, "learning_rate": 1.3992279894875165e-05, "loss": 0.5705, "step": 6503 }, { "epoch": 1.07, "learning_rate": 1.398981603153745e-05, "loss": 0.7171, "step": 6504 }, { "epoch": 1.07, "learning_rate": 1.3987352168199737e-05, "loss": 0.7631, "step": 6505 }, { "epoch": 1.07, "learning_rate": 1.3984888304862024e-05, "loss": 0.3365, "step": 6506 }, { "epoch": 1.07, "learning_rate": 1.398242444152431e-05, "loss": 0.7382, "step": 6507 }, { "epoch": 1.07, "learning_rate": 1.3979960578186598e-05, "loss": 0.6776, "step": 6508 }, { "epoch": 1.07, "learning_rate": 1.3977496714848884e-05, "loss": 0.9259, "step": 6509 }, { "epoch": 1.07, "learning_rate": 1.397503285151117e-05, "loss": 0.7133, "step": 6510 }, { "epoch": 1.07, "learning_rate": 1.3972568988173456e-05, "loss": 0.6959, "step": 6511 }, { "epoch": 1.07, "learning_rate": 1.3970105124835742e-05, "loss": 0.3543, "step": 6512 }, { "epoch": 1.07, "learning_rate": 1.396764126149803e-05, "loss": 0.8633, "step": 6513 }, { "epoch": 1.07, "learning_rate": 1.3965177398160315e-05, "loss": 0.4855, "step": 6514 }, { "epoch": 1.07, "learning_rate": 1.3962713534822601e-05, "loss": 0.4252, "step": 6515 }, { "epoch": 1.07, "learning_rate": 1.3960249671484887e-05, "loss": 0.4603, "step": 6516 }, { "epoch": 1.07, "learning_rate": 1.3957785808147175e-05, "loss": 0.5409, "step": 6517 }, { "epoch": 1.07, "learning_rate": 1.3955321944809463e-05, "loss": 0.8868, "step": 6518 }, { "epoch": 1.07, "learning_rate": 1.3952858081471749e-05, "loss": 0.1839, "step": 6519 }, { "epoch": 1.07, "learning_rate": 1.3950394218134035e-05, "loss": 0.4559, "step": 6520 }, { "epoch": 1.07, "learning_rate": 1.394793035479632e-05, "loss": 0.1787, "step": 6521 }, { "epoch": 1.07, "learning_rate": 1.3945466491458607e-05, "loss": 0.697, "step": 6522 }, { "epoch": 1.07, "learning_rate": 1.3943002628120894e-05, "loss": 1.2061, "step": 6523 }, { "epoch": 1.07, "learning_rate": 1.394053876478318e-05, "loss": 0.2269, "step": 6524 }, { "epoch": 1.07, "learning_rate": 1.3938074901445466e-05, "loss": 0.4905, "step": 6525 }, { "epoch": 1.07, "learning_rate": 1.3935611038107752e-05, "loss": 0.4141, "step": 6526 }, { "epoch": 1.07, "learning_rate": 1.3933147174770038e-05, "loss": 0.383, "step": 6527 }, { "epoch": 1.07, "learning_rate": 1.3930683311432326e-05, "loss": 0.4312, "step": 6528 }, { "epoch": 1.07, "learning_rate": 1.3928219448094614e-05, "loss": 0.5254, "step": 6529 }, { "epoch": 1.07, "learning_rate": 1.39257555847569e-05, "loss": 0.6837, "step": 6530 }, { "epoch": 1.07, "learning_rate": 1.3923291721419186e-05, "loss": 0.4695, "step": 6531 }, { "epoch": 1.07, "learning_rate": 1.3920827858081472e-05, "loss": 0.5757, "step": 6532 }, { "epoch": 1.07, "learning_rate": 1.391836399474376e-05, "loss": 0.6056, "step": 6533 }, { "epoch": 1.07, "learning_rate": 1.3915900131406045e-05, "loss": 0.4932, "step": 6534 }, { "epoch": 1.07, "learning_rate": 1.3913436268068331e-05, "loss": 0.2142, "step": 6535 }, { "epoch": 1.07, "learning_rate": 1.3910972404730617e-05, "loss": 0.3831, "step": 6536 }, { "epoch": 1.07, "learning_rate": 1.3908508541392903e-05, "loss": 0.9658, "step": 6537 }, { "epoch": 1.07, "learning_rate": 1.3906044678055191e-05, "loss": 0.663, "step": 6538 }, { "epoch": 1.07, "learning_rate": 1.3903580814717477e-05, "loss": 0.8261, "step": 6539 }, { "epoch": 1.07, "learning_rate": 1.3901116951379763e-05, "loss": 0.5569, "step": 6540 }, { "epoch": 1.07, "learning_rate": 1.389865308804205e-05, "loss": 0.6852, "step": 6541 }, { "epoch": 1.07, "learning_rate": 1.3896189224704337e-05, "loss": 0.7296, "step": 6542 }, { "epoch": 1.07, "learning_rate": 1.3893725361366624e-05, "loss": 0.731, "step": 6543 }, { "epoch": 1.07, "learning_rate": 1.389126149802891e-05, "loss": 0.3878, "step": 6544 }, { "epoch": 1.08, "learning_rate": 1.3888797634691196e-05, "loss": 0.536, "step": 6545 }, { "epoch": 1.08, "learning_rate": 1.3886333771353482e-05, "loss": 0.4572, "step": 6546 }, { "epoch": 1.08, "learning_rate": 1.3883869908015768e-05, "loss": 0.5717, "step": 6547 }, { "epoch": 1.08, "learning_rate": 1.3881406044678056e-05, "loss": 0.5292, "step": 6548 }, { "epoch": 1.08, "learning_rate": 1.3878942181340342e-05, "loss": 1.0881, "step": 6549 }, { "epoch": 1.08, "learning_rate": 1.3876478318002628e-05, "loss": 0.1479, "step": 6550 }, { "epoch": 1.08, "learning_rate": 1.3874014454664914e-05, "loss": 0.5317, "step": 6551 }, { "epoch": 1.08, "learning_rate": 1.38715505913272e-05, "loss": 0.3345, "step": 6552 }, { "epoch": 1.08, "learning_rate": 1.386908672798949e-05, "loss": 0.8694, "step": 6553 }, { "epoch": 1.08, "learning_rate": 1.3866622864651775e-05, "loss": 0.5213, "step": 6554 }, { "epoch": 1.08, "learning_rate": 1.3864159001314061e-05, "loss": 0.1609, "step": 6555 }, { "epoch": 1.08, "learning_rate": 1.3861695137976347e-05, "loss": 0.5015, "step": 6556 }, { "epoch": 1.08, "learning_rate": 1.3859231274638633e-05, "loss": 0.6163, "step": 6557 }, { "epoch": 1.08, "learning_rate": 1.385676741130092e-05, "loss": 0.3809, "step": 6558 }, { "epoch": 1.08, "learning_rate": 1.3854303547963207e-05, "loss": 0.4581, "step": 6559 }, { "epoch": 1.08, "learning_rate": 1.3851839684625493e-05, "loss": 0.2123, "step": 6560 }, { "epoch": 1.08, "learning_rate": 1.3849375821287779e-05, "loss": 1.1623, "step": 6561 }, { "epoch": 1.08, "learning_rate": 1.3846911957950065e-05, "loss": 0.2342, "step": 6562 }, { "epoch": 1.08, "learning_rate": 1.3844448094612352e-05, "loss": 0.5888, "step": 6563 }, { "epoch": 1.08, "learning_rate": 1.3841984231274638e-05, "loss": 0.3524, "step": 6564 }, { "epoch": 1.08, "learning_rate": 1.3839520367936926e-05, "loss": 0.8033, "step": 6565 }, { "epoch": 1.08, "learning_rate": 1.3837056504599212e-05, "loss": 0.7613, "step": 6566 }, { "epoch": 1.08, "learning_rate": 1.3834592641261498e-05, "loss": 0.3257, "step": 6567 }, { "epoch": 1.08, "learning_rate": 1.3832128777923786e-05, "loss": 0.344, "step": 6568 }, { "epoch": 1.08, "learning_rate": 1.3829664914586072e-05, "loss": 0.4028, "step": 6569 }, { "epoch": 1.08, "learning_rate": 1.3827201051248358e-05, "loss": 0.5478, "step": 6570 }, { "epoch": 1.08, "learning_rate": 1.3824737187910644e-05, "loss": 0.985, "step": 6571 }, { "epoch": 1.08, "learning_rate": 1.382227332457293e-05, "loss": 0.3076, "step": 6572 }, { "epoch": 1.08, "learning_rate": 1.3819809461235217e-05, "loss": 0.358, "step": 6573 }, { "epoch": 1.08, "learning_rate": 1.3817345597897503e-05, "loss": 0.5485, "step": 6574 }, { "epoch": 1.08, "learning_rate": 1.381488173455979e-05, "loss": 0.4174, "step": 6575 }, { "epoch": 1.08, "learning_rate": 1.3812417871222075e-05, "loss": 0.6343, "step": 6576 }, { "epoch": 1.08, "learning_rate": 1.3809954007884363e-05, "loss": 0.4562, "step": 6577 }, { "epoch": 1.08, "learning_rate": 1.380749014454665e-05, "loss": 0.3049, "step": 6578 }, { "epoch": 1.08, "learning_rate": 1.3805026281208937e-05, "loss": 0.8926, "step": 6579 }, { "epoch": 1.08, "learning_rate": 1.3802562417871223e-05, "loss": 1.0364, "step": 6580 }, { "epoch": 1.08, "learning_rate": 1.3800098554533509e-05, "loss": 0.3311, "step": 6581 }, { "epoch": 1.08, "learning_rate": 1.3797634691195795e-05, "loss": 0.3247, "step": 6582 }, { "epoch": 1.08, "learning_rate": 1.3795170827858082e-05, "loss": 0.4757, "step": 6583 }, { "epoch": 1.08, "learning_rate": 1.3792706964520368e-05, "loss": 0.6307, "step": 6584 }, { "epoch": 1.08, "learning_rate": 1.3790243101182654e-05, "loss": 0.2857, "step": 6585 }, { "epoch": 1.08, "learning_rate": 1.378777923784494e-05, "loss": 0.3005, "step": 6586 }, { "epoch": 1.08, "learning_rate": 1.3785315374507226e-05, "loss": 0.174, "step": 6587 }, { "epoch": 1.08, "learning_rate": 1.3782851511169514e-05, "loss": 0.4637, "step": 6588 }, { "epoch": 1.08, "learning_rate": 1.3780387647831802e-05, "loss": 0.5167, "step": 6589 }, { "epoch": 1.08, "learning_rate": 1.3777923784494088e-05, "loss": 0.5203, "step": 6590 }, { "epoch": 1.08, "learning_rate": 1.3775459921156374e-05, "loss": 0.4343, "step": 6591 }, { "epoch": 1.08, "learning_rate": 1.377299605781866e-05, "loss": 0.4342, "step": 6592 }, { "epoch": 1.08, "learning_rate": 1.3770532194480947e-05, "loss": 0.502, "step": 6593 }, { "epoch": 1.08, "learning_rate": 1.3768068331143233e-05, "loss": 0.822, "step": 6594 }, { "epoch": 1.08, "learning_rate": 1.376560446780552e-05, "loss": 0.1315, "step": 6595 }, { "epoch": 1.08, "learning_rate": 1.3763140604467805e-05, "loss": 0.6071, "step": 6596 }, { "epoch": 1.08, "learning_rate": 1.3760676741130091e-05, "loss": 0.6964, "step": 6597 }, { "epoch": 1.08, "learning_rate": 1.3758212877792379e-05, "loss": 0.2014, "step": 6598 }, { "epoch": 1.08, "learning_rate": 1.3755749014454665e-05, "loss": 0.4501, "step": 6599 }, { "epoch": 1.08, "learning_rate": 1.375328515111695e-05, "loss": 1.175, "step": 6600 }, { "epoch": 1.08, "learning_rate": 1.3750821287779238e-05, "loss": 0.6899, "step": 6601 }, { "epoch": 1.08, "learning_rate": 1.3748357424441524e-05, "loss": 0.6177, "step": 6602 }, { "epoch": 1.08, "learning_rate": 1.3745893561103812e-05, "loss": 0.4102, "step": 6603 }, { "epoch": 1.08, "learning_rate": 1.3743429697766098e-05, "loss": 0.6579, "step": 6604 }, { "epoch": 1.08, "learning_rate": 1.3740965834428384e-05, "loss": 0.232, "step": 6605 }, { "epoch": 1.09, "learning_rate": 1.373850197109067e-05, "loss": 0.2333, "step": 6606 }, { "epoch": 1.09, "learning_rate": 1.3736038107752956e-05, "loss": 0.4034, "step": 6607 }, { "epoch": 1.09, "learning_rate": 1.3733574244415244e-05, "loss": 0.5159, "step": 6608 }, { "epoch": 1.09, "learning_rate": 1.373111038107753e-05, "loss": 0.1857, "step": 6609 }, { "epoch": 1.09, "learning_rate": 1.3728646517739816e-05, "loss": 0.4479, "step": 6610 }, { "epoch": 1.09, "learning_rate": 1.3726182654402102e-05, "loss": 1.0216, "step": 6611 }, { "epoch": 1.09, "learning_rate": 1.3723718791064388e-05, "loss": 0.35, "step": 6612 }, { "epoch": 1.09, "learning_rate": 1.3721254927726677e-05, "loss": 0.2667, "step": 6613 }, { "epoch": 1.09, "learning_rate": 1.3718791064388963e-05, "loss": 0.607, "step": 6614 }, { "epoch": 1.09, "learning_rate": 1.3716327201051249e-05, "loss": 0.6147, "step": 6615 }, { "epoch": 1.09, "learning_rate": 1.3713863337713535e-05, "loss": 1.1456, "step": 6616 }, { "epoch": 1.09, "learning_rate": 1.3711399474375821e-05, "loss": 0.8506, "step": 6617 }, { "epoch": 1.09, "learning_rate": 1.3708935611038109e-05, "loss": 0.829, "step": 6618 }, { "epoch": 1.09, "learning_rate": 1.3706471747700395e-05, "loss": 0.5197, "step": 6619 }, { "epoch": 1.09, "learning_rate": 1.370400788436268e-05, "loss": 0.4405, "step": 6620 }, { "epoch": 1.09, "learning_rate": 1.3701544021024967e-05, "loss": 0.7229, "step": 6621 }, { "epoch": 1.09, "learning_rate": 1.3699080157687253e-05, "loss": 1.0393, "step": 6622 }, { "epoch": 1.09, "learning_rate": 1.369661629434954e-05, "loss": 0.693, "step": 6623 }, { "epoch": 1.09, "learning_rate": 1.3694152431011826e-05, "loss": 0.3763, "step": 6624 }, { "epoch": 1.09, "learning_rate": 1.3691688567674114e-05, "loss": 0.5537, "step": 6625 }, { "epoch": 1.09, "learning_rate": 1.36892247043364e-05, "loss": 0.6097, "step": 6626 }, { "epoch": 1.09, "learning_rate": 1.3686760840998686e-05, "loss": 0.2954, "step": 6627 }, { "epoch": 1.09, "learning_rate": 1.3684296977660974e-05, "loss": 0.2532, "step": 6628 }, { "epoch": 1.09, "learning_rate": 1.368183311432326e-05, "loss": 0.5981, "step": 6629 }, { "epoch": 1.09, "learning_rate": 1.3679369250985546e-05, "loss": 1.3176, "step": 6630 }, { "epoch": 1.09, "learning_rate": 1.3676905387647832e-05, "loss": 0.2401, "step": 6631 }, { "epoch": 1.09, "learning_rate": 1.3674441524310118e-05, "loss": 0.3987, "step": 6632 }, { "epoch": 1.09, "learning_rate": 1.3671977660972405e-05, "loss": 0.3746, "step": 6633 }, { "epoch": 1.09, "learning_rate": 1.3669513797634691e-05, "loss": 0.665, "step": 6634 }, { "epoch": 1.09, "learning_rate": 1.3667049934296977e-05, "loss": 0.7451, "step": 6635 }, { "epoch": 1.09, "learning_rate": 1.3664586070959263e-05, "loss": 0.4958, "step": 6636 }, { "epoch": 1.09, "learning_rate": 1.3662122207621551e-05, "loss": 1.0815, "step": 6637 }, { "epoch": 1.09, "learning_rate": 1.3659658344283839e-05, "loss": 1.2714, "step": 6638 }, { "epoch": 1.09, "learning_rate": 1.3657194480946125e-05, "loss": 0.5762, "step": 6639 }, { "epoch": 1.09, "learning_rate": 1.365473061760841e-05, "loss": 0.8545, "step": 6640 }, { "epoch": 1.09, "learning_rate": 1.3652266754270697e-05, "loss": 0.8267, "step": 6641 }, { "epoch": 1.09, "learning_rate": 1.3649802890932982e-05, "loss": 0.4775, "step": 6642 }, { "epoch": 1.09, "learning_rate": 1.364733902759527e-05, "loss": 0.3787, "step": 6643 }, { "epoch": 1.09, "learning_rate": 1.3644875164257556e-05, "loss": 0.2458, "step": 6644 }, { "epoch": 1.09, "learning_rate": 1.3642411300919842e-05, "loss": 0.4366, "step": 6645 }, { "epoch": 1.09, "learning_rate": 1.3639947437582128e-05, "loss": 0.3802, "step": 6646 }, { "epoch": 1.09, "learning_rate": 1.3637483574244414e-05, "loss": 0.2159, "step": 6647 }, { "epoch": 1.09, "learning_rate": 1.3635019710906702e-05, "loss": 0.1147, "step": 6648 }, { "epoch": 1.09, "learning_rate": 1.363255584756899e-05, "loss": 0.2034, "step": 6649 }, { "epoch": 1.09, "learning_rate": 1.3630091984231275e-05, "loss": 0.8878, "step": 6650 }, { "epoch": 1.09, "learning_rate": 1.3627628120893561e-05, "loss": 0.5307, "step": 6651 }, { "epoch": 1.09, "learning_rate": 1.3625164257555847e-05, "loss": 0.5565, "step": 6652 }, { "epoch": 1.09, "learning_rate": 1.3622700394218135e-05, "loss": 0.7553, "step": 6653 }, { "epoch": 1.09, "learning_rate": 1.3620236530880421e-05, "loss": 0.5118, "step": 6654 }, { "epoch": 1.09, "learning_rate": 1.3617772667542707e-05, "loss": 0.2702, "step": 6655 }, { "epoch": 1.09, "learning_rate": 1.3615308804204993e-05, "loss": 0.5854, "step": 6656 }, { "epoch": 1.09, "learning_rate": 1.3612844940867279e-05, "loss": 0.4252, "step": 6657 }, { "epoch": 1.09, "learning_rate": 1.3610381077529567e-05, "loss": 0.2026, "step": 6658 }, { "epoch": 1.09, "learning_rate": 1.3607917214191853e-05, "loss": 0.7732, "step": 6659 }, { "epoch": 1.09, "learning_rate": 1.360545335085414e-05, "loss": 0.657, "step": 6660 }, { "epoch": 1.09, "learning_rate": 1.3602989487516426e-05, "loss": 0.4883, "step": 6661 }, { "epoch": 1.09, "learning_rate": 1.3600525624178712e-05, "loss": 0.5456, "step": 6662 }, { "epoch": 1.09, "learning_rate": 1.3598061760841e-05, "loss": 0.6498, "step": 6663 }, { "epoch": 1.09, "learning_rate": 1.3595597897503286e-05, "loss": 0.6163, "step": 6664 }, { "epoch": 1.09, "learning_rate": 1.3593134034165572e-05, "loss": 0.3412, "step": 6665 }, { "epoch": 1.09, "learning_rate": 1.3590670170827858e-05, "loss": 0.5121, "step": 6666 }, { "epoch": 1.1, "learning_rate": 1.3588206307490144e-05, "loss": 0.6049, "step": 6667 }, { "epoch": 1.1, "learning_rate": 1.3585742444152432e-05, "loss": 0.4693, "step": 6668 }, { "epoch": 1.1, "learning_rate": 1.3583278580814718e-05, "loss": 0.2893, "step": 6669 }, { "epoch": 1.1, "learning_rate": 1.3580814717477004e-05, "loss": 0.4756, "step": 6670 }, { "epoch": 1.1, "learning_rate": 1.357835085413929e-05, "loss": 0.6033, "step": 6671 }, { "epoch": 1.1, "learning_rate": 1.3575886990801577e-05, "loss": 0.4813, "step": 6672 }, { "epoch": 1.1, "learning_rate": 1.3573423127463865e-05, "loss": 0.6174, "step": 6673 }, { "epoch": 1.1, "learning_rate": 1.3570959264126151e-05, "loss": 0.3148, "step": 6674 }, { "epoch": 1.1, "learning_rate": 1.3568495400788437e-05, "loss": 0.3282, "step": 6675 }, { "epoch": 1.1, "learning_rate": 1.3566031537450723e-05, "loss": 0.5638, "step": 6676 }, { "epoch": 1.1, "learning_rate": 1.3563567674113009e-05, "loss": 0.4513, "step": 6677 }, { "epoch": 1.1, "learning_rate": 1.3561103810775297e-05, "loss": 0.2593, "step": 6678 }, { "epoch": 1.1, "learning_rate": 1.3558639947437583e-05, "loss": 0.3684, "step": 6679 }, { "epoch": 1.1, "learning_rate": 1.3556176084099869e-05, "loss": 0.7095, "step": 6680 }, { "epoch": 1.1, "learning_rate": 1.3553712220762155e-05, "loss": 0.2892, "step": 6681 }, { "epoch": 1.1, "learning_rate": 1.355124835742444e-05, "loss": 0.4056, "step": 6682 }, { "epoch": 1.1, "learning_rate": 1.3548784494086728e-05, "loss": 0.6516, "step": 6683 }, { "epoch": 1.1, "learning_rate": 1.3546320630749016e-05, "loss": 0.5056, "step": 6684 }, { "epoch": 1.1, "learning_rate": 1.3543856767411302e-05, "loss": 0.4122, "step": 6685 }, { "epoch": 1.1, "learning_rate": 1.3541392904073588e-05, "loss": 0.6853, "step": 6686 }, { "epoch": 1.1, "learning_rate": 1.3538929040735874e-05, "loss": 0.5501, "step": 6687 }, { "epoch": 1.1, "learning_rate": 1.3536465177398162e-05, "loss": 0.3962, "step": 6688 }, { "epoch": 1.1, "learning_rate": 1.3534001314060447e-05, "loss": 0.4455, "step": 6689 }, { "epoch": 1.1, "learning_rate": 1.3531537450722733e-05, "loss": 0.4169, "step": 6690 }, { "epoch": 1.1, "learning_rate": 1.352907358738502e-05, "loss": 0.2846, "step": 6691 }, { "epoch": 1.1, "learning_rate": 1.3526609724047305e-05, "loss": 1.0809, "step": 6692 }, { "epoch": 1.1, "learning_rate": 1.3524145860709593e-05, "loss": 0.4236, "step": 6693 }, { "epoch": 1.1, "learning_rate": 1.3521681997371879e-05, "loss": 0.5944, "step": 6694 }, { "epoch": 1.1, "learning_rate": 1.3519218134034165e-05, "loss": 0.1627, "step": 6695 }, { "epoch": 1.1, "learning_rate": 1.3516754270696453e-05, "loss": 0.4972, "step": 6696 }, { "epoch": 1.1, "learning_rate": 1.3514290407358739e-05, "loss": 0.705, "step": 6697 }, { "epoch": 1.1, "learning_rate": 1.3511826544021026e-05, "loss": 0.3382, "step": 6698 }, { "epoch": 1.1, "learning_rate": 1.3509362680683312e-05, "loss": 0.5556, "step": 6699 }, { "epoch": 1.1, "learning_rate": 1.3506898817345598e-05, "loss": 0.4476, "step": 6700 }, { "epoch": 1.1, "learning_rate": 1.3504434954007884e-05, "loss": 0.6381, "step": 6701 }, { "epoch": 1.1, "learning_rate": 1.350197109067017e-05, "loss": 0.8564, "step": 6702 }, { "epoch": 1.1, "learning_rate": 1.3499507227332458e-05, "loss": 0.9399, "step": 6703 }, { "epoch": 1.1, "learning_rate": 1.3497043363994744e-05, "loss": 0.4257, "step": 6704 }, { "epoch": 1.1, "learning_rate": 1.349457950065703e-05, "loss": 0.5536, "step": 6705 }, { "epoch": 1.1, "learning_rate": 1.3492115637319316e-05, "loss": 0.3657, "step": 6706 }, { "epoch": 1.1, "learning_rate": 1.3489651773981602e-05, "loss": 0.2277, "step": 6707 }, { "epoch": 1.1, "learning_rate": 1.3487187910643891e-05, "loss": 0.2428, "step": 6708 }, { "epoch": 1.1, "learning_rate": 1.3484724047306177e-05, "loss": 1.1208, "step": 6709 }, { "epoch": 1.1, "learning_rate": 1.3482260183968463e-05, "loss": 0.56, "step": 6710 }, { "epoch": 1.1, "learning_rate": 1.347979632063075e-05, "loss": 0.9101, "step": 6711 }, { "epoch": 1.1, "learning_rate": 1.3477332457293035e-05, "loss": 0.2078, "step": 6712 }, { "epoch": 1.1, "learning_rate": 1.3474868593955323e-05, "loss": 0.7178, "step": 6713 }, { "epoch": 1.1, "learning_rate": 1.3472404730617609e-05, "loss": 0.5105, "step": 6714 }, { "epoch": 1.1, "learning_rate": 1.3469940867279895e-05, "loss": 0.8172, "step": 6715 }, { "epoch": 1.1, "learning_rate": 1.3467477003942181e-05, "loss": 0.6353, "step": 6716 }, { "epoch": 1.1, "learning_rate": 1.3465013140604467e-05, "loss": 0.4569, "step": 6717 }, { "epoch": 1.1, "learning_rate": 1.3462549277266755e-05, "loss": 0.3627, "step": 6718 }, { "epoch": 1.1, "learning_rate": 1.346008541392904e-05, "loss": 0.6607, "step": 6719 }, { "epoch": 1.1, "learning_rate": 1.3457621550591328e-05, "loss": 0.4853, "step": 6720 }, { "epoch": 1.1, "learning_rate": 1.3455157687253614e-05, "loss": 0.6898, "step": 6721 }, { "epoch": 1.1, "learning_rate": 1.34526938239159e-05, "loss": 0.5282, "step": 6722 }, { "epoch": 1.1, "learning_rate": 1.3450229960578188e-05, "loss": 0.5609, "step": 6723 }, { "epoch": 1.1, "learning_rate": 1.3447766097240474e-05, "loss": 0.405, "step": 6724 }, { "epoch": 1.1, "learning_rate": 1.344530223390276e-05, "loss": 0.3275, "step": 6725 }, { "epoch": 1.1, "learning_rate": 1.3442838370565046e-05, "loss": 0.3698, "step": 6726 }, { "epoch": 1.1, "learning_rate": 1.3440374507227332e-05, "loss": 0.2656, "step": 6727 }, { "epoch": 1.11, "learning_rate": 1.343791064388962e-05, "loss": 0.3823, "step": 6728 }, { "epoch": 1.11, "learning_rate": 1.3435446780551906e-05, "loss": 0.2962, "step": 6729 }, { "epoch": 1.11, "learning_rate": 1.3432982917214191e-05, "loss": 0.4343, "step": 6730 }, { "epoch": 1.11, "learning_rate": 1.3430519053876477e-05, "loss": 0.8029, "step": 6731 }, { "epoch": 1.11, "learning_rate": 1.3428055190538765e-05, "loss": 0.3634, "step": 6732 }, { "epoch": 1.11, "learning_rate": 1.3425591327201053e-05, "loss": 0.5664, "step": 6733 }, { "epoch": 1.11, "learning_rate": 1.3423127463863339e-05, "loss": 0.4618, "step": 6734 }, { "epoch": 1.11, "learning_rate": 1.3420663600525625e-05, "loss": 0.3561, "step": 6735 }, { "epoch": 1.11, "learning_rate": 1.341819973718791e-05, "loss": 0.3959, "step": 6736 }, { "epoch": 1.11, "learning_rate": 1.3415735873850197e-05, "loss": 0.6611, "step": 6737 }, { "epoch": 1.11, "learning_rate": 1.3413272010512484e-05, "loss": 0.7747, "step": 6738 }, { "epoch": 1.11, "learning_rate": 1.341080814717477e-05, "loss": 0.4558, "step": 6739 }, { "epoch": 1.11, "learning_rate": 1.3408344283837056e-05, "loss": 0.9697, "step": 6740 }, { "epoch": 1.11, "learning_rate": 1.3405880420499342e-05, "loss": 0.506, "step": 6741 }, { "epoch": 1.11, "learning_rate": 1.3403416557161628e-05, "loss": 1.052, "step": 6742 }, { "epoch": 1.11, "learning_rate": 1.3400952693823916e-05, "loss": 0.3552, "step": 6743 }, { "epoch": 1.11, "learning_rate": 1.3398488830486204e-05, "loss": 0.3351, "step": 6744 }, { "epoch": 1.11, "learning_rate": 1.339602496714849e-05, "loss": 0.2886, "step": 6745 }, { "epoch": 1.11, "learning_rate": 1.3393561103810776e-05, "loss": 0.3895, "step": 6746 }, { "epoch": 1.11, "learning_rate": 1.3391097240473062e-05, "loss": 0.4252, "step": 6747 }, { "epoch": 1.11, "learning_rate": 1.338863337713535e-05, "loss": 0.241, "step": 6748 }, { "epoch": 1.11, "learning_rate": 1.3386169513797635e-05, "loss": 0.3984, "step": 6749 }, { "epoch": 1.11, "learning_rate": 1.3383705650459921e-05, "loss": 0.4171, "step": 6750 }, { "epoch": 1.11, "learning_rate": 1.3381241787122207e-05, "loss": 0.4209, "step": 6751 }, { "epoch": 1.11, "learning_rate": 1.3378777923784493e-05, "loss": 1.1904, "step": 6752 }, { "epoch": 1.11, "learning_rate": 1.3376314060446781e-05, "loss": 0.4815, "step": 6753 }, { "epoch": 1.11, "learning_rate": 1.3373850197109067e-05, "loss": 0.2806, "step": 6754 }, { "epoch": 1.11, "learning_rate": 1.3371386333771353e-05, "loss": 0.7291, "step": 6755 }, { "epoch": 1.11, "learning_rate": 1.336892247043364e-05, "loss": 0.5128, "step": 6756 }, { "epoch": 1.11, "learning_rate": 1.3366458607095927e-05, "loss": 0.2448, "step": 6757 }, { "epoch": 1.11, "learning_rate": 1.3363994743758214e-05, "loss": 0.5958, "step": 6758 }, { "epoch": 1.11, "learning_rate": 1.33615308804205e-05, "loss": 0.5955, "step": 6759 }, { "epoch": 1.11, "learning_rate": 1.3359067017082786e-05, "loss": 0.7802, "step": 6760 }, { "epoch": 1.11, "learning_rate": 1.3356603153745072e-05, "loss": 1.0004, "step": 6761 }, { "epoch": 1.11, "learning_rate": 1.3354139290407358e-05, "loss": 0.2781, "step": 6762 }, { "epoch": 1.11, "learning_rate": 1.3351675427069646e-05, "loss": 0.8929, "step": 6763 }, { "epoch": 1.11, "learning_rate": 1.3349211563731932e-05, "loss": 0.4477, "step": 6764 }, { "epoch": 1.11, "learning_rate": 1.3346747700394218e-05, "loss": 0.545, "step": 6765 }, { "epoch": 1.11, "learning_rate": 1.3344283837056504e-05, "loss": 0.5445, "step": 6766 }, { "epoch": 1.11, "learning_rate": 1.334181997371879e-05, "loss": 0.2286, "step": 6767 }, { "epoch": 1.11, "learning_rate": 1.333935611038108e-05, "loss": 0.5934, "step": 6768 }, { "epoch": 1.11, "learning_rate": 1.3336892247043365e-05, "loss": 0.2048, "step": 6769 }, { "epoch": 1.11, "learning_rate": 1.3334428383705651e-05, "loss": 0.4187, "step": 6770 }, { "epoch": 1.11, "learning_rate": 1.3331964520367937e-05, "loss": 0.6399, "step": 6771 }, { "epoch": 1.11, "learning_rate": 1.3329500657030223e-05, "loss": 0.7681, "step": 6772 }, { "epoch": 1.11, "learning_rate": 1.3327036793692511e-05, "loss": 0.6639, "step": 6773 }, { "epoch": 1.11, "learning_rate": 1.3324572930354797e-05, "loss": 0.3587, "step": 6774 }, { "epoch": 1.11, "learning_rate": 1.3322109067017083e-05, "loss": 0.7273, "step": 6775 }, { "epoch": 1.11, "learning_rate": 1.3319645203679369e-05, "loss": 0.7489, "step": 6776 }, { "epoch": 1.11, "learning_rate": 1.3317181340341655e-05, "loss": 0.7835, "step": 6777 }, { "epoch": 1.11, "learning_rate": 1.3314717477003942e-05, "loss": 0.467, "step": 6778 }, { "epoch": 1.11, "learning_rate": 1.3312253613666228e-05, "loss": 0.5121, "step": 6779 }, { "epoch": 1.11, "learning_rate": 1.3309789750328516e-05, "loss": 0.7813, "step": 6780 }, { "epoch": 1.11, "learning_rate": 1.3307325886990802e-05, "loss": 1.0433, "step": 6781 }, { "epoch": 1.11, "learning_rate": 1.3304862023653088e-05, "loss": 0.3452, "step": 6782 }, { "epoch": 1.11, "learning_rate": 1.3302398160315376e-05, "loss": 0.4867, "step": 6783 }, { "epoch": 1.11, "learning_rate": 1.3299934296977662e-05, "loss": 0.2427, "step": 6784 }, { "epoch": 1.11, "learning_rate": 1.3297470433639948e-05, "loss": 0.5718, "step": 6785 }, { "epoch": 1.11, "learning_rate": 1.3295006570302234e-05, "loss": 0.9997, "step": 6786 }, { "epoch": 1.11, "learning_rate": 1.329254270696452e-05, "loss": 0.4121, "step": 6787 }, { "epoch": 1.11, "learning_rate": 1.3290078843626807e-05, "loss": 0.1171, "step": 6788 }, { "epoch": 1.12, "learning_rate": 1.3287614980289093e-05, "loss": 0.6492, "step": 6789 }, { "epoch": 1.12, "learning_rate": 1.328515111695138e-05, "loss": 0.3502, "step": 6790 }, { "epoch": 1.12, "learning_rate": 1.3282687253613667e-05, "loss": 0.4355, "step": 6791 }, { "epoch": 1.12, "learning_rate": 1.3280223390275953e-05, "loss": 0.307, "step": 6792 }, { "epoch": 1.12, "learning_rate": 1.327775952693824e-05, "loss": 0.4267, "step": 6793 }, { "epoch": 1.12, "learning_rate": 1.3275295663600527e-05, "loss": 0.6174, "step": 6794 }, { "epoch": 1.12, "learning_rate": 1.3272831800262813e-05, "loss": 0.2814, "step": 6795 }, { "epoch": 1.12, "learning_rate": 1.3270367936925099e-05, "loss": 0.384, "step": 6796 }, { "epoch": 1.12, "learning_rate": 1.3267904073587385e-05, "loss": 0.2786, "step": 6797 }, { "epoch": 1.12, "learning_rate": 1.3265440210249672e-05, "loss": 0.5197, "step": 6798 }, { "epoch": 1.12, "learning_rate": 1.3262976346911958e-05, "loss": 0.5657, "step": 6799 }, { "epoch": 1.12, "learning_rate": 1.3260512483574244e-05, "loss": 0.1482, "step": 6800 }, { "epoch": 1.12, "learning_rate": 1.325804862023653e-05, "loss": 0.586, "step": 6801 }, { "epoch": 1.12, "learning_rate": 1.3255584756898816e-05, "loss": 0.3109, "step": 6802 }, { "epoch": 1.12, "learning_rate": 1.3253120893561106e-05, "loss": 0.4752, "step": 6803 }, { "epoch": 1.12, "learning_rate": 1.3250657030223392e-05, "loss": 0.6227, "step": 6804 }, { "epoch": 1.12, "learning_rate": 1.3248193166885678e-05, "loss": 0.5579, "step": 6805 }, { "epoch": 1.12, "learning_rate": 1.3245729303547964e-05, "loss": 0.6688, "step": 6806 }, { "epoch": 1.12, "learning_rate": 1.324326544021025e-05, "loss": 0.6099, "step": 6807 }, { "epoch": 1.12, "learning_rate": 1.3240801576872537e-05, "loss": 0.5371, "step": 6808 }, { "epoch": 1.12, "learning_rate": 1.3238337713534823e-05, "loss": 0.2689, "step": 6809 }, { "epoch": 1.12, "learning_rate": 1.323587385019711e-05, "loss": 0.3978, "step": 6810 }, { "epoch": 1.12, "learning_rate": 1.3233409986859395e-05, "loss": 0.4038, "step": 6811 }, { "epoch": 1.12, "learning_rate": 1.3230946123521681e-05, "loss": 0.6005, "step": 6812 }, { "epoch": 1.12, "learning_rate": 1.3228482260183969e-05, "loss": 0.8563, "step": 6813 }, { "epoch": 1.12, "learning_rate": 1.3226018396846255e-05, "loss": 0.8653, "step": 6814 }, { "epoch": 1.12, "learning_rate": 1.3223554533508543e-05, "loss": 0.7879, "step": 6815 }, { "epoch": 1.12, "learning_rate": 1.3221090670170829e-05, "loss": 0.3214, "step": 6816 }, { "epoch": 1.12, "learning_rate": 1.3218626806833114e-05, "loss": 1.1498, "step": 6817 }, { "epoch": 1.12, "learning_rate": 1.3216162943495402e-05, "loss": 0.9417, "step": 6818 }, { "epoch": 1.12, "learning_rate": 1.3213699080157688e-05, "loss": 0.5676, "step": 6819 }, { "epoch": 1.12, "learning_rate": 1.3211235216819974e-05, "loss": 0.5588, "step": 6820 }, { "epoch": 1.12, "learning_rate": 1.320877135348226e-05, "loss": 0.4559, "step": 6821 }, { "epoch": 1.12, "learning_rate": 1.3206307490144546e-05, "loss": 0.3074, "step": 6822 }, { "epoch": 1.12, "learning_rate": 1.3203843626806834e-05, "loss": 0.5283, "step": 6823 }, { "epoch": 1.12, "learning_rate": 1.320137976346912e-05, "loss": 0.2622, "step": 6824 }, { "epoch": 1.12, "learning_rate": 1.3198915900131406e-05, "loss": 0.5897, "step": 6825 }, { "epoch": 1.12, "learning_rate": 1.3196452036793692e-05, "loss": 0.9166, "step": 6826 }, { "epoch": 1.12, "learning_rate": 1.319398817345598e-05, "loss": 0.5273, "step": 6827 }, { "epoch": 1.12, "learning_rate": 1.3191524310118267e-05, "loss": 0.5374, "step": 6828 }, { "epoch": 1.12, "learning_rate": 1.3189060446780553e-05, "loss": 0.3461, "step": 6829 }, { "epoch": 1.12, "learning_rate": 1.3186596583442839e-05, "loss": 0.6016, "step": 6830 }, { "epoch": 1.12, "learning_rate": 1.3184132720105125e-05, "loss": 0.3965, "step": 6831 }, { "epoch": 1.12, "learning_rate": 1.3181668856767411e-05, "loss": 0.8969, "step": 6832 }, { "epoch": 1.12, "learning_rate": 1.3179204993429699e-05, "loss": 0.3756, "step": 6833 }, { "epoch": 1.12, "learning_rate": 1.3176741130091985e-05, "loss": 0.4831, "step": 6834 }, { "epoch": 1.12, "learning_rate": 1.317427726675427e-05, "loss": 0.6901, "step": 6835 }, { "epoch": 1.12, "learning_rate": 1.3171813403416557e-05, "loss": 0.6426, "step": 6836 }, { "epoch": 1.12, "learning_rate": 1.3169349540078843e-05, "loss": 0.5033, "step": 6837 }, { "epoch": 1.12, "learning_rate": 1.316688567674113e-05, "loss": 0.2419, "step": 6838 }, { "epoch": 1.12, "learning_rate": 1.3164421813403418e-05, "loss": 0.2292, "step": 6839 }, { "epoch": 1.12, "learning_rate": 1.3161957950065704e-05, "loss": 0.91, "step": 6840 }, { "epoch": 1.12, "learning_rate": 1.315949408672799e-05, "loss": 0.3302, "step": 6841 }, { "epoch": 1.12, "learning_rate": 1.3157030223390276e-05, "loss": 0.7196, "step": 6842 }, { "epoch": 1.12, "learning_rate": 1.3154566360052564e-05, "loss": 0.3774, "step": 6843 }, { "epoch": 1.12, "learning_rate": 1.315210249671485e-05, "loss": 0.2426, "step": 6844 }, { "epoch": 1.12, "learning_rate": 1.3149638633377136e-05, "loss": 0.518, "step": 6845 }, { "epoch": 1.12, "learning_rate": 1.3147174770039422e-05, "loss": 0.3652, "step": 6846 }, { "epoch": 1.12, "learning_rate": 1.3144710906701708e-05, "loss": 1.028, "step": 6847 }, { "epoch": 1.12, "learning_rate": 1.3142247043363995e-05, "loss": 0.3173, "step": 6848 }, { "epoch": 1.12, "learning_rate": 1.3139783180026281e-05, "loss": 0.3105, "step": 6849 }, { "epoch": 1.13, "learning_rate": 1.3137319316688567e-05, "loss": 0.3312, "step": 6850 }, { "epoch": 1.13, "learning_rate": 1.3134855453350855e-05, "loss": 0.2243, "step": 6851 }, { "epoch": 1.13, "learning_rate": 1.3132391590013141e-05, "loss": 0.6167, "step": 6852 }, { "epoch": 1.13, "learning_rate": 1.3129927726675429e-05, "loss": 0.378, "step": 6853 }, { "epoch": 1.13, "learning_rate": 1.3127463863337715e-05, "loss": 0.249, "step": 6854 }, { "epoch": 1.13, "learning_rate": 1.3125e-05, "loss": 0.4514, "step": 6855 }, { "epoch": 1.13, "learning_rate": 1.3122536136662287e-05, "loss": 0.8013, "step": 6856 }, { "epoch": 1.13, "learning_rate": 1.3120072273324573e-05, "loss": 0.3493, "step": 6857 }, { "epoch": 1.13, "learning_rate": 1.311760840998686e-05, "loss": 0.4154, "step": 6858 }, { "epoch": 1.13, "learning_rate": 1.3115144546649146e-05, "loss": 0.4262, "step": 6859 }, { "epoch": 1.13, "learning_rate": 1.3112680683311432e-05, "loss": 0.358, "step": 6860 }, { "epoch": 1.13, "learning_rate": 1.3110216819973718e-05, "loss": 0.6014, "step": 6861 }, { "epoch": 1.13, "learning_rate": 1.3107752956636004e-05, "loss": 0.5676, "step": 6862 }, { "epoch": 1.13, "learning_rate": 1.3105289093298294e-05, "loss": 0.1131, "step": 6863 }, { "epoch": 1.13, "learning_rate": 1.310282522996058e-05, "loss": 0.2738, "step": 6864 }, { "epoch": 1.13, "learning_rate": 1.3100361366622865e-05, "loss": 0.3859, "step": 6865 }, { "epoch": 1.13, "learning_rate": 1.3097897503285151e-05, "loss": 0.3501, "step": 6866 }, { "epoch": 1.13, "learning_rate": 1.3095433639947437e-05, "loss": 0.2496, "step": 6867 }, { "epoch": 1.13, "learning_rate": 1.3092969776609725e-05, "loss": 0.6658, "step": 6868 }, { "epoch": 1.13, "learning_rate": 1.3090505913272011e-05, "loss": 0.4948, "step": 6869 }, { "epoch": 1.13, "learning_rate": 1.3088042049934297e-05, "loss": 0.4633, "step": 6870 }, { "epoch": 1.13, "learning_rate": 1.3085578186596583e-05, "loss": 0.2798, "step": 6871 }, { "epoch": 1.13, "learning_rate": 1.3083114323258869e-05, "loss": 1.0505, "step": 6872 }, { "epoch": 1.13, "learning_rate": 1.3080650459921157e-05, "loss": 0.1717, "step": 6873 }, { "epoch": 1.13, "learning_rate": 1.3078186596583443e-05, "loss": 0.5167, "step": 6874 }, { "epoch": 1.13, "learning_rate": 1.307572273324573e-05, "loss": 0.3545, "step": 6875 }, { "epoch": 1.13, "learning_rate": 1.3073258869908016e-05, "loss": 0.4655, "step": 6876 }, { "epoch": 1.13, "learning_rate": 1.3070795006570302e-05, "loss": 0.4277, "step": 6877 }, { "epoch": 1.13, "learning_rate": 1.306833114323259e-05, "loss": 0.4805, "step": 6878 }, { "epoch": 1.13, "learning_rate": 1.3065867279894876e-05, "loss": 0.3565, "step": 6879 }, { "epoch": 1.13, "learning_rate": 1.3063403416557162e-05, "loss": 0.5138, "step": 6880 }, { "epoch": 1.13, "learning_rate": 1.3060939553219448e-05, "loss": 0.8635, "step": 6881 }, { "epoch": 1.13, "learning_rate": 1.3058475689881734e-05, "loss": 0.3868, "step": 6882 }, { "epoch": 1.13, "learning_rate": 1.3056011826544022e-05, "loss": 0.6349, "step": 6883 }, { "epoch": 1.13, "learning_rate": 1.3053547963206308e-05, "loss": 0.4129, "step": 6884 }, { "epoch": 1.13, "learning_rate": 1.3051084099868594e-05, "loss": 0.404, "step": 6885 }, { "epoch": 1.13, "learning_rate": 1.304862023653088e-05, "loss": 0.4607, "step": 6886 }, { "epoch": 1.13, "learning_rate": 1.3046156373193167e-05, "loss": 0.4013, "step": 6887 }, { "epoch": 1.13, "learning_rate": 1.3043692509855455e-05, "loss": 0.6092, "step": 6888 }, { "epoch": 1.13, "learning_rate": 1.3041228646517741e-05, "loss": 0.4454, "step": 6889 }, { "epoch": 1.13, "learning_rate": 1.3038764783180027e-05, "loss": 1.0651, "step": 6890 }, { "epoch": 1.13, "learning_rate": 1.3036300919842313e-05, "loss": 0.6053, "step": 6891 }, { "epoch": 1.13, "learning_rate": 1.3033837056504599e-05, "loss": 0.1794, "step": 6892 }, { "epoch": 1.13, "learning_rate": 1.3031373193166887e-05, "loss": 0.6556, "step": 6893 }, { "epoch": 1.13, "learning_rate": 1.3028909329829173e-05, "loss": 0.3196, "step": 6894 }, { "epoch": 1.13, "learning_rate": 1.3026445466491459e-05, "loss": 0.5789, "step": 6895 }, { "epoch": 1.13, "learning_rate": 1.3023981603153745e-05, "loss": 0.2856, "step": 6896 }, { "epoch": 1.13, "learning_rate": 1.302151773981603e-05, "loss": 0.6632, "step": 6897 }, { "epoch": 1.13, "learning_rate": 1.3019053876478318e-05, "loss": 0.3103, "step": 6898 }, { "epoch": 1.13, "learning_rate": 1.3016590013140606e-05, "loss": 0.5519, "step": 6899 }, { "epoch": 1.13, "learning_rate": 1.3014126149802892e-05, "loss": 0.3522, "step": 6900 }, { "epoch": 1.13, "learning_rate": 1.3011662286465178e-05, "loss": 0.2896, "step": 6901 }, { "epoch": 1.13, "learning_rate": 1.3009198423127464e-05, "loss": 0.4571, "step": 6902 }, { "epoch": 1.13, "learning_rate": 1.3006734559789752e-05, "loss": 0.5004, "step": 6903 }, { "epoch": 1.13, "learning_rate": 1.3004270696452038e-05, "loss": 0.5372, "step": 6904 }, { "epoch": 1.13, "learning_rate": 1.3001806833114323e-05, "loss": 0.2554, "step": 6905 }, { "epoch": 1.13, "learning_rate": 1.299934296977661e-05, "loss": 0.4152, "step": 6906 }, { "epoch": 1.13, "learning_rate": 1.2996879106438895e-05, "loss": 0.4076, "step": 6907 }, { "epoch": 1.13, "learning_rate": 1.2994415243101183e-05, "loss": 0.443, "step": 6908 }, { "epoch": 1.13, "learning_rate": 1.2991951379763469e-05, "loss": 1.0759, "step": 6909 }, { "epoch": 1.14, "learning_rate": 1.2989487516425755e-05, "loss": 0.7558, "step": 6910 }, { "epoch": 1.14, "learning_rate": 1.2987023653088043e-05, "loss": 0.396, "step": 6911 }, { "epoch": 1.14, "learning_rate": 1.2984559789750329e-05, "loss": 0.2417, "step": 6912 }, { "epoch": 1.14, "learning_rate": 1.2982095926412616e-05, "loss": 0.3643, "step": 6913 }, { "epoch": 1.14, "learning_rate": 1.2979632063074902e-05, "loss": 0.1898, "step": 6914 }, { "epoch": 1.14, "learning_rate": 1.2977168199737188e-05, "loss": 0.8352, "step": 6915 }, { "epoch": 1.14, "learning_rate": 1.2974704336399474e-05, "loss": 0.5759, "step": 6916 }, { "epoch": 1.14, "learning_rate": 1.297224047306176e-05, "loss": 0.6821, "step": 6917 }, { "epoch": 1.14, "learning_rate": 1.2969776609724048e-05, "loss": 0.5503, "step": 6918 }, { "epoch": 1.14, "learning_rate": 1.2967312746386334e-05, "loss": 0.6625, "step": 6919 }, { "epoch": 1.14, "learning_rate": 1.296484888304862e-05, "loss": 0.4017, "step": 6920 }, { "epoch": 1.14, "learning_rate": 1.2962385019710906e-05, "loss": 0.3884, "step": 6921 }, { "epoch": 1.14, "learning_rate": 1.2959921156373194e-05, "loss": 0.4699, "step": 6922 }, { "epoch": 1.14, "learning_rate": 1.2957457293035481e-05, "loss": 0.2804, "step": 6923 }, { "epoch": 1.14, "learning_rate": 1.2954993429697767e-05, "loss": 0.5751, "step": 6924 }, { "epoch": 1.14, "learning_rate": 1.2952529566360053e-05, "loss": 0.4739, "step": 6925 }, { "epoch": 1.14, "learning_rate": 1.295006570302234e-05, "loss": 0.4594, "step": 6926 }, { "epoch": 1.14, "learning_rate": 1.2947601839684625e-05, "loss": 0.9802, "step": 6927 }, { "epoch": 1.14, "learning_rate": 1.2945137976346913e-05, "loss": 0.178, "step": 6928 }, { "epoch": 1.14, "learning_rate": 1.2942674113009199e-05, "loss": 0.3415, "step": 6929 }, { "epoch": 1.14, "learning_rate": 1.2940210249671485e-05, "loss": 0.5677, "step": 6930 }, { "epoch": 1.14, "learning_rate": 1.2937746386333771e-05, "loss": 0.2149, "step": 6931 }, { "epoch": 1.14, "learning_rate": 1.2935282522996057e-05, "loss": 0.3392, "step": 6932 }, { "epoch": 1.14, "learning_rate": 1.2932818659658345e-05, "loss": 0.3467, "step": 6933 }, { "epoch": 1.14, "learning_rate": 1.2930354796320632e-05, "loss": 0.6494, "step": 6934 }, { "epoch": 1.14, "learning_rate": 1.2927890932982918e-05, "loss": 0.42, "step": 6935 }, { "epoch": 1.14, "learning_rate": 1.2925427069645204e-05, "loss": 0.4603, "step": 6936 }, { "epoch": 1.14, "learning_rate": 1.292296320630749e-05, "loss": 0.4566, "step": 6937 }, { "epoch": 1.14, "learning_rate": 1.2920499342969778e-05, "loss": 0.352, "step": 6938 }, { "epoch": 1.14, "learning_rate": 1.2918035479632064e-05, "loss": 0.5372, "step": 6939 }, { "epoch": 1.14, "learning_rate": 1.291557161629435e-05, "loss": 0.2298, "step": 6940 }, { "epoch": 1.14, "learning_rate": 1.2913107752956636e-05, "loss": 0.6969, "step": 6941 }, { "epoch": 1.14, "learning_rate": 1.2910643889618922e-05, "loss": 0.4042, "step": 6942 }, { "epoch": 1.14, "learning_rate": 1.290818002628121e-05, "loss": 0.5865, "step": 6943 }, { "epoch": 1.14, "learning_rate": 1.2905716162943496e-05, "loss": 0.2874, "step": 6944 }, { "epoch": 1.14, "learning_rate": 1.2903252299605782e-05, "loss": 0.3789, "step": 6945 }, { "epoch": 1.14, "learning_rate": 1.290078843626807e-05, "loss": 0.2075, "step": 6946 }, { "epoch": 1.14, "learning_rate": 1.2898324572930355e-05, "loss": 1.151, "step": 6947 }, { "epoch": 1.14, "learning_rate": 1.2895860709592643e-05, "loss": 0.3181, "step": 6948 }, { "epoch": 1.14, "learning_rate": 1.2893396846254929e-05, "loss": 0.4195, "step": 6949 }, { "epoch": 1.14, "learning_rate": 1.2890932982917215e-05, "loss": 0.3683, "step": 6950 }, { "epoch": 1.14, "learning_rate": 1.28884691195795e-05, "loss": 0.4996, "step": 6951 }, { "epoch": 1.14, "learning_rate": 1.2886005256241787e-05, "loss": 0.6884, "step": 6952 }, { "epoch": 1.14, "learning_rate": 1.2883541392904074e-05, "loss": 0.2399, "step": 6953 }, { "epoch": 1.14, "learning_rate": 1.288107752956636e-05, "loss": 0.7319, "step": 6954 }, { "epoch": 1.14, "learning_rate": 1.2878613666228646e-05, "loss": 0.5007, "step": 6955 }, { "epoch": 1.14, "learning_rate": 1.2876149802890932e-05, "loss": 0.4772, "step": 6956 }, { "epoch": 1.14, "learning_rate": 1.2873685939553218e-05, "loss": 0.5046, "step": 6957 }, { "epoch": 1.14, "learning_rate": 1.2871222076215508e-05, "loss": 0.4407, "step": 6958 }, { "epoch": 1.14, "learning_rate": 1.2868758212877794e-05, "loss": 0.5095, "step": 6959 }, { "epoch": 1.14, "learning_rate": 1.286629434954008e-05, "loss": 0.2056, "step": 6960 }, { "epoch": 1.14, "learning_rate": 1.2863830486202366e-05, "loss": 0.653, "step": 6961 }, { "epoch": 1.14, "learning_rate": 1.2861366622864652e-05, "loss": 0.2734, "step": 6962 }, { "epoch": 1.14, "learning_rate": 1.285890275952694e-05, "loss": 0.2553, "step": 6963 }, { "epoch": 1.14, "learning_rate": 1.2856438896189225e-05, "loss": 0.3429, "step": 6964 }, { "epoch": 1.14, "learning_rate": 1.2853975032851511e-05, "loss": 0.2057, "step": 6965 }, { "epoch": 1.14, "learning_rate": 1.2851511169513797e-05, "loss": 0.4982, "step": 6966 }, { "epoch": 1.14, "learning_rate": 1.2849047306176083e-05, "loss": 0.946, "step": 6967 }, { "epoch": 1.14, "learning_rate": 1.2846583442838371e-05, "loss": 0.5001, "step": 6968 }, { "epoch": 1.14, "learning_rate": 1.2844119579500657e-05, "loss": 0.4569, "step": 6969 }, { "epoch": 1.14, "learning_rate": 1.2841655716162945e-05, "loss": 0.5983, "step": 6970 }, { "epoch": 1.15, "learning_rate": 1.283919185282523e-05, "loss": 0.6375, "step": 6971 }, { "epoch": 1.15, "learning_rate": 1.2836727989487517e-05, "loss": 0.5983, "step": 6972 }, { "epoch": 1.15, "learning_rate": 1.2834264126149804e-05, "loss": 0.2762, "step": 6973 }, { "epoch": 1.15, "learning_rate": 1.283180026281209e-05, "loss": 0.7562, "step": 6974 }, { "epoch": 1.15, "learning_rate": 1.2829336399474376e-05, "loss": 0.436, "step": 6975 }, { "epoch": 1.15, "learning_rate": 1.2826872536136662e-05, "loss": 0.6048, "step": 6976 }, { "epoch": 1.15, "learning_rate": 1.2824408672798948e-05, "loss": 0.6042, "step": 6977 }, { "epoch": 1.15, "learning_rate": 1.2821944809461236e-05, "loss": 0.3962, "step": 6978 }, { "epoch": 1.15, "learning_rate": 1.2819480946123522e-05, "loss": 0.9216, "step": 6979 }, { "epoch": 1.15, "learning_rate": 1.2817017082785808e-05, "loss": 0.3404, "step": 6980 }, { "epoch": 1.15, "learning_rate": 1.2814553219448094e-05, "loss": 0.4271, "step": 6981 }, { "epoch": 1.15, "learning_rate": 1.2812089356110382e-05, "loss": 0.5008, "step": 6982 }, { "epoch": 1.15, "learning_rate": 1.280962549277267e-05, "loss": 0.2119, "step": 6983 }, { "epoch": 1.15, "learning_rate": 1.2807161629434955e-05, "loss": 0.7299, "step": 6984 }, { "epoch": 1.15, "learning_rate": 1.2804697766097241e-05, "loss": 0.8199, "step": 6985 }, { "epoch": 1.15, "learning_rate": 1.2802233902759527e-05, "loss": 0.3493, "step": 6986 }, { "epoch": 1.15, "learning_rate": 1.2799770039421813e-05, "loss": 0.2969, "step": 6987 }, { "epoch": 1.15, "learning_rate": 1.2797306176084101e-05, "loss": 0.3258, "step": 6988 }, { "epoch": 1.15, "learning_rate": 1.2794842312746387e-05, "loss": 0.3701, "step": 6989 }, { "epoch": 1.15, "learning_rate": 1.2792378449408673e-05, "loss": 0.7203, "step": 6990 }, { "epoch": 1.15, "learning_rate": 1.2789914586070959e-05, "loss": 1.1127, "step": 6991 }, { "epoch": 1.15, "learning_rate": 1.2787450722733245e-05, "loss": 0.6401, "step": 6992 }, { "epoch": 1.15, "learning_rate": 1.2784986859395532e-05, "loss": 0.2994, "step": 6993 }, { "epoch": 1.15, "learning_rate": 1.278252299605782e-05, "loss": 0.5267, "step": 6994 }, { "epoch": 1.15, "learning_rate": 1.2780059132720106e-05, "loss": 0.3121, "step": 6995 }, { "epoch": 1.15, "learning_rate": 1.2777595269382392e-05, "loss": 0.659, "step": 6996 }, { "epoch": 1.15, "learning_rate": 1.2775131406044678e-05, "loss": 0.6561, "step": 6997 }, { "epoch": 1.15, "learning_rate": 1.2772667542706966e-05, "loss": 0.5508, "step": 6998 }, { "epoch": 1.15, "learning_rate": 1.2770203679369252e-05, "loss": 0.4003, "step": 6999 }, { "epoch": 1.15, "learning_rate": 1.2767739816031538e-05, "loss": 0.4931, "step": 7000 }, { "epoch": 1.15, "eval_exact_match": 85.99810785241249, "eval_f1": 92.49687595450662, "step": 7000 }, { "epoch": 1.15, "learning_rate": 1.2765275952693824e-05, "loss": 1.2271, "step": 7001 }, { "epoch": 1.15, "learning_rate": 1.276281208935611e-05, "loss": 0.5059, "step": 7002 }, { "epoch": 1.15, "learning_rate": 1.2760348226018397e-05, "loss": 0.5513, "step": 7003 }, { "epoch": 1.15, "learning_rate": 1.2757884362680683e-05, "loss": 0.6964, "step": 7004 }, { "epoch": 1.15, "learning_rate": 1.275542049934297e-05, "loss": 1.0436, "step": 7005 }, { "epoch": 1.15, "learning_rate": 1.2752956636005257e-05, "loss": 0.5363, "step": 7006 }, { "epoch": 1.15, "learning_rate": 1.2750492772667543e-05, "loss": 0.243, "step": 7007 }, { "epoch": 1.15, "learning_rate": 1.274802890932983e-05, "loss": 0.6885, "step": 7008 }, { "epoch": 1.15, "learning_rate": 1.2745565045992117e-05, "loss": 0.458, "step": 7009 }, { "epoch": 1.15, "learning_rate": 1.2743101182654403e-05, "loss": 0.3927, "step": 7010 }, { "epoch": 1.15, "learning_rate": 1.2740637319316689e-05, "loss": 0.3814, "step": 7011 }, { "epoch": 1.15, "learning_rate": 1.2738173455978975e-05, "loss": 0.7263, "step": 7012 }, { "epoch": 1.15, "learning_rate": 1.2735709592641262e-05, "loss": 0.6354, "step": 7013 }, { "epoch": 1.15, "learning_rate": 1.2733245729303548e-05, "loss": 0.386, "step": 7014 }, { "epoch": 1.15, "learning_rate": 1.2730781865965834e-05, "loss": 0.6148, "step": 7015 }, { "epoch": 1.15, "learning_rate": 1.272831800262812e-05, "loss": 0.7215, "step": 7016 }, { "epoch": 1.15, "learning_rate": 1.2725854139290406e-05, "loss": 1.0868, "step": 7017 }, { "epoch": 1.15, "learning_rate": 1.2723390275952696e-05, "loss": 0.3276, "step": 7018 }, { "epoch": 1.15, "learning_rate": 1.2720926412614982e-05, "loss": 0.3726, "step": 7019 }, { "epoch": 1.15, "learning_rate": 1.2718462549277268e-05, "loss": 0.5137, "step": 7020 }, { "epoch": 1.15, "learning_rate": 1.2715998685939554e-05, "loss": 0.3969, "step": 7021 }, { "epoch": 1.15, "learning_rate": 1.271353482260184e-05, "loss": 0.6905, "step": 7022 }, { "epoch": 1.15, "learning_rate": 1.2711070959264127e-05, "loss": 0.4214, "step": 7023 }, { "epoch": 1.15, "learning_rate": 1.2708607095926413e-05, "loss": 0.4384, "step": 7024 }, { "epoch": 1.15, "learning_rate": 1.27061432325887e-05, "loss": 0.8072, "step": 7025 }, { "epoch": 1.15, "learning_rate": 1.2703679369250985e-05, "loss": 0.7829, "step": 7026 }, { "epoch": 1.15, "learning_rate": 1.2701215505913271e-05, "loss": 0.5336, "step": 7027 }, { "epoch": 1.15, "learning_rate": 1.2698751642575559e-05, "loss": 0.624, "step": 7028 }, { "epoch": 1.15, "learning_rate": 1.2696287779237845e-05, "loss": 0.2264, "step": 7029 }, { "epoch": 1.15, "learning_rate": 1.2693823915900133e-05, "loss": 0.3998, "step": 7030 }, { "epoch": 1.15, "learning_rate": 1.2691360052562419e-05, "loss": 0.6106, "step": 7031 }, { "epoch": 1.16, "learning_rate": 1.2688896189224705e-05, "loss": 0.3899, "step": 7032 }, { "epoch": 1.16, "learning_rate": 1.2686432325886992e-05, "loss": 0.3961, "step": 7033 }, { "epoch": 1.16, "learning_rate": 1.2683968462549278e-05, "loss": 0.4201, "step": 7034 }, { "epoch": 1.16, "learning_rate": 1.2681504599211564e-05, "loss": 0.6143, "step": 7035 }, { "epoch": 1.16, "learning_rate": 1.267904073587385e-05, "loss": 0.4395, "step": 7036 }, { "epoch": 1.16, "learning_rate": 1.2676576872536136e-05, "loss": 0.5606, "step": 7037 }, { "epoch": 1.16, "learning_rate": 1.2674113009198424e-05, "loss": 0.3079, "step": 7038 }, { "epoch": 1.16, "learning_rate": 1.267164914586071e-05, "loss": 0.3977, "step": 7039 }, { "epoch": 1.16, "learning_rate": 1.2669185282522996e-05, "loss": 0.4294, "step": 7040 }, { "epoch": 1.16, "learning_rate": 1.2666721419185282e-05, "loss": 1.5103, "step": 7041 }, { "epoch": 1.16, "learning_rate": 1.266425755584757e-05, "loss": 0.3031, "step": 7042 }, { "epoch": 1.16, "learning_rate": 1.2661793692509857e-05, "loss": 0.8219, "step": 7043 }, { "epoch": 1.16, "learning_rate": 1.2659329829172143e-05, "loss": 0.3077, "step": 7044 }, { "epoch": 1.16, "learning_rate": 1.2656865965834429e-05, "loss": 0.7376, "step": 7045 }, { "epoch": 1.16, "learning_rate": 1.2654402102496715e-05, "loss": 0.3905, "step": 7046 }, { "epoch": 1.16, "learning_rate": 1.2651938239159001e-05, "loss": 0.314, "step": 7047 }, { "epoch": 1.16, "learning_rate": 1.2649474375821289e-05, "loss": 0.3063, "step": 7048 }, { "epoch": 1.16, "learning_rate": 1.2647010512483575e-05, "loss": 0.6416, "step": 7049 }, { "epoch": 1.16, "learning_rate": 1.264454664914586e-05, "loss": 0.4761, "step": 7050 }, { "epoch": 1.16, "learning_rate": 1.2642082785808147e-05, "loss": 0.7154, "step": 7051 }, { "epoch": 1.16, "learning_rate": 1.2639618922470433e-05, "loss": 0.5246, "step": 7052 }, { "epoch": 1.16, "learning_rate": 1.263715505913272e-05, "loss": 0.3692, "step": 7053 }, { "epoch": 1.16, "learning_rate": 1.2634691195795008e-05, "loss": 0.3472, "step": 7054 }, { "epoch": 1.16, "learning_rate": 1.2632227332457294e-05, "loss": 0.7561, "step": 7055 }, { "epoch": 1.16, "learning_rate": 1.262976346911958e-05, "loss": 0.3165, "step": 7056 }, { "epoch": 1.16, "learning_rate": 1.2627299605781866e-05, "loss": 1.005, "step": 7057 }, { "epoch": 1.16, "learning_rate": 1.2624835742444154e-05, "loss": 0.8894, "step": 7058 }, { "epoch": 1.16, "learning_rate": 1.262237187910644e-05, "loss": 0.2242, "step": 7059 }, { "epoch": 1.16, "learning_rate": 1.2619908015768726e-05, "loss": 0.7695, "step": 7060 }, { "epoch": 1.16, "learning_rate": 1.2617444152431012e-05, "loss": 0.2511, "step": 7061 }, { "epoch": 1.16, "learning_rate": 1.2614980289093298e-05, "loss": 0.3385, "step": 7062 }, { "epoch": 1.16, "learning_rate": 1.2612516425755585e-05, "loss": 0.2938, "step": 7063 }, { "epoch": 1.16, "learning_rate": 1.2610052562417871e-05, "loss": 0.3285, "step": 7064 }, { "epoch": 1.16, "learning_rate": 1.2607588699080159e-05, "loss": 0.4844, "step": 7065 }, { "epoch": 1.16, "learning_rate": 1.2605124835742445e-05, "loss": 0.6106, "step": 7066 }, { "epoch": 1.16, "learning_rate": 1.2602660972404731e-05, "loss": 0.2913, "step": 7067 }, { "epoch": 1.16, "learning_rate": 1.2600197109067019e-05, "loss": 0.3585, "step": 7068 }, { "epoch": 1.16, "learning_rate": 1.2597733245729305e-05, "loss": 0.1782, "step": 7069 }, { "epoch": 1.16, "learning_rate": 1.259526938239159e-05, "loss": 0.9576, "step": 7070 }, { "epoch": 1.16, "learning_rate": 1.2592805519053877e-05, "loss": 0.4518, "step": 7071 }, { "epoch": 1.16, "learning_rate": 1.2590341655716163e-05, "loss": 0.645, "step": 7072 }, { "epoch": 1.16, "learning_rate": 1.258787779237845e-05, "loss": 0.6926, "step": 7073 }, { "epoch": 1.16, "learning_rate": 1.2585413929040736e-05, "loss": 0.2509, "step": 7074 }, { "epoch": 1.16, "learning_rate": 1.2582950065703022e-05, "loss": 1.0611, "step": 7075 }, { "epoch": 1.16, "learning_rate": 1.2580486202365308e-05, "loss": 0.1881, "step": 7076 }, { "epoch": 1.16, "learning_rate": 1.2578022339027596e-05, "loss": 0.6292, "step": 7077 }, { "epoch": 1.16, "learning_rate": 1.2575558475689884e-05, "loss": 0.7537, "step": 7078 }, { "epoch": 1.16, "learning_rate": 1.257309461235217e-05, "loss": 0.2645, "step": 7079 }, { "epoch": 1.16, "learning_rate": 1.2570630749014455e-05, "loss": 0.8105, "step": 7080 }, { "epoch": 1.16, "learning_rate": 1.2568166885676741e-05, "loss": 0.6946, "step": 7081 }, { "epoch": 1.16, "learning_rate": 1.2565703022339027e-05, "loss": 0.4847, "step": 7082 }, { "epoch": 1.16, "learning_rate": 1.2563239159001315e-05, "loss": 0.2992, "step": 7083 }, { "epoch": 1.16, "learning_rate": 1.2560775295663601e-05, "loss": 0.5015, "step": 7084 }, { "epoch": 1.16, "learning_rate": 1.2558311432325887e-05, "loss": 0.3134, "step": 7085 }, { "epoch": 1.16, "learning_rate": 1.2555847568988173e-05, "loss": 0.3407, "step": 7086 }, { "epoch": 1.16, "learning_rate": 1.2553383705650459e-05, "loss": 0.6094, "step": 7087 }, { "epoch": 1.16, "learning_rate": 1.2550919842312747e-05, "loss": 0.7188, "step": 7088 }, { "epoch": 1.16, "learning_rate": 1.2548455978975034e-05, "loss": 0.7635, "step": 7089 }, { "epoch": 1.16, "learning_rate": 1.254599211563732e-05, "loss": 0.4658, "step": 7090 }, { "epoch": 1.16, "learning_rate": 1.2543528252299606e-05, "loss": 0.5437, "step": 7091 }, { "epoch": 1.16, "learning_rate": 1.2541064388961892e-05, "loss": 0.7137, "step": 7092 }, { "epoch": 1.17, "learning_rate": 1.253860052562418e-05, "loss": 0.6968, "step": 7093 }, { "epoch": 1.17, "learning_rate": 1.2536136662286466e-05, "loss": 0.3617, "step": 7094 }, { "epoch": 1.17, "learning_rate": 1.2533672798948752e-05, "loss": 0.7031, "step": 7095 }, { "epoch": 1.17, "learning_rate": 1.2531208935611038e-05, "loss": 0.3757, "step": 7096 }, { "epoch": 1.17, "learning_rate": 1.2528745072273324e-05, "loss": 0.4802, "step": 7097 }, { "epoch": 1.17, "learning_rate": 1.2526281208935612e-05, "loss": 1.3913, "step": 7098 }, { "epoch": 1.17, "learning_rate": 1.2523817345597898e-05, "loss": 0.5063, "step": 7099 }, { "epoch": 1.17, "learning_rate": 1.2521353482260184e-05, "loss": 0.3336, "step": 7100 }, { "epoch": 1.17, "learning_rate": 1.2518889618922471e-05, "loss": 0.5743, "step": 7101 }, { "epoch": 1.17, "learning_rate": 1.2516425755584757e-05, "loss": 0.1648, "step": 7102 }, { "epoch": 1.17, "learning_rate": 1.2513961892247045e-05, "loss": 0.3369, "step": 7103 }, { "epoch": 1.17, "learning_rate": 1.2511498028909331e-05, "loss": 0.8312, "step": 7104 }, { "epoch": 1.17, "learning_rate": 1.2509034165571617e-05, "loss": 0.9667, "step": 7105 }, { "epoch": 1.17, "learning_rate": 1.2506570302233903e-05, "loss": 0.3435, "step": 7106 }, { "epoch": 1.17, "learning_rate": 1.2504106438896189e-05, "loss": 0.4613, "step": 7107 }, { "epoch": 1.17, "learning_rate": 1.2501642575558477e-05, "loss": 0.6968, "step": 7108 }, { "epoch": 1.17, "learning_rate": 1.2499178712220763e-05, "loss": 0.5156, "step": 7109 }, { "epoch": 1.17, "learning_rate": 1.2496714848883049e-05, "loss": 0.1778, "step": 7110 }, { "epoch": 1.17, "learning_rate": 1.2494250985545335e-05, "loss": 1.0936, "step": 7111 }, { "epoch": 1.17, "learning_rate": 1.249178712220762e-05, "loss": 0.4444, "step": 7112 }, { "epoch": 1.17, "learning_rate": 1.248932325886991e-05, "loss": 0.3752, "step": 7113 }, { "epoch": 1.17, "learning_rate": 1.2486859395532196e-05, "loss": 0.3875, "step": 7114 }, { "epoch": 1.17, "learning_rate": 1.2484395532194482e-05, "loss": 0.8238, "step": 7115 }, { "epoch": 1.17, "learning_rate": 1.2481931668856768e-05, "loss": 0.8435, "step": 7116 }, { "epoch": 1.17, "learning_rate": 1.2479467805519054e-05, "loss": 0.3903, "step": 7117 }, { "epoch": 1.17, "learning_rate": 1.2477003942181342e-05, "loss": 0.8199, "step": 7118 }, { "epoch": 1.17, "learning_rate": 1.2474540078843628e-05, "loss": 0.5541, "step": 7119 }, { "epoch": 1.17, "learning_rate": 1.2472076215505914e-05, "loss": 0.4261, "step": 7120 }, { "epoch": 1.17, "learning_rate": 1.24696123521682e-05, "loss": 0.3612, "step": 7121 }, { "epoch": 1.17, "learning_rate": 1.2467148488830485e-05, "loss": 0.6167, "step": 7122 }, { "epoch": 1.17, "learning_rate": 1.2464684625492773e-05, "loss": 0.3172, "step": 7123 }, { "epoch": 1.17, "learning_rate": 1.2462220762155059e-05, "loss": 0.825, "step": 7124 }, { "epoch": 1.17, "learning_rate": 1.2459756898817347e-05, "loss": 0.4163, "step": 7125 }, { "epoch": 1.17, "learning_rate": 1.2457293035479633e-05, "loss": 0.3885, "step": 7126 }, { "epoch": 1.17, "learning_rate": 1.2454829172141919e-05, "loss": 0.349, "step": 7127 }, { "epoch": 1.17, "learning_rate": 1.2452365308804206e-05, "loss": 0.6542, "step": 7128 }, { "epoch": 1.17, "learning_rate": 1.2449901445466492e-05, "loss": 0.3424, "step": 7129 }, { "epoch": 1.17, "learning_rate": 1.2447437582128778e-05, "loss": 0.2888, "step": 7130 }, { "epoch": 1.17, "learning_rate": 1.2444973718791064e-05, "loss": 0.78, "step": 7131 }, { "epoch": 1.17, "learning_rate": 1.244250985545335e-05, "loss": 0.4911, "step": 7132 }, { "epoch": 1.17, "learning_rate": 1.2440045992115638e-05, "loss": 0.2196, "step": 7133 }, { "epoch": 1.17, "learning_rate": 1.2437582128777924e-05, "loss": 0.3526, "step": 7134 }, { "epoch": 1.17, "learning_rate": 1.243511826544021e-05, "loss": 0.411, "step": 7135 }, { "epoch": 1.17, "learning_rate": 1.2432654402102496e-05, "loss": 0.2599, "step": 7136 }, { "epoch": 1.17, "learning_rate": 1.2430190538764784e-05, "loss": 0.4905, "step": 7137 }, { "epoch": 1.17, "learning_rate": 1.2430190538764784e-05, "loss": 0.3875, "step": 7138 }, { "epoch": 1.17, "learning_rate": 1.2427726675427071e-05, "loss": 0.3945, "step": 7139 }, { "epoch": 1.17, "learning_rate": 1.2425262812089357e-05, "loss": 0.4062, "step": 7140 }, { "epoch": 1.17, "learning_rate": 1.2422798948751643e-05, "loss": 0.6595, "step": 7141 }, { "epoch": 1.17, "learning_rate": 1.242033508541393e-05, "loss": 0.8238, "step": 7142 }, { "epoch": 1.17, "learning_rate": 1.2417871222076215e-05, "loss": 0.4387, "step": 7143 }, { "epoch": 1.17, "learning_rate": 1.2415407358738503e-05, "loss": 0.8094, "step": 7144 }, { "epoch": 1.17, "learning_rate": 1.2412943495400789e-05, "loss": 0.636, "step": 7145 }, { "epoch": 1.17, "learning_rate": 1.2410479632063075e-05, "loss": 0.8944, "step": 7146 }, { "epoch": 1.17, "learning_rate": 1.2408015768725361e-05, "loss": 0.6414, "step": 7147 }, { "epoch": 1.17, "learning_rate": 1.2405551905387647e-05, "loss": 0.3762, "step": 7148 }, { "epoch": 1.17, "learning_rate": 1.2403088042049935e-05, "loss": 0.5503, "step": 7149 }, { "epoch": 1.17, "learning_rate": 1.2400624178712222e-05, "loss": 0.6899, "step": 7150 }, { "epoch": 1.17, "learning_rate": 1.2398160315374508e-05, "loss": 0.3532, "step": 7151 }, { "epoch": 1.17, "learning_rate": 1.2395696452036794e-05, "loss": 0.4253, "step": 7152 }, { "epoch": 1.17, "learning_rate": 1.239323258869908e-05, "loss": 0.3191, "step": 7153 }, { "epoch": 1.18, "learning_rate": 1.2390768725361368e-05, "loss": 0.4892, "step": 7154 }, { "epoch": 1.18, "learning_rate": 1.2388304862023654e-05, "loss": 0.5369, "step": 7155 }, { "epoch": 1.18, "learning_rate": 1.238584099868594e-05, "loss": 0.6103, "step": 7156 }, { "epoch": 1.18, "learning_rate": 1.2383377135348226e-05, "loss": 0.4356, "step": 7157 }, { "epoch": 1.18, "learning_rate": 1.2380913272010512e-05, "loss": 0.8705, "step": 7158 }, { "epoch": 1.18, "learning_rate": 1.23784494086728e-05, "loss": 0.2555, "step": 7159 }, { "epoch": 1.18, "learning_rate": 1.2375985545335086e-05, "loss": 0.2966, "step": 7160 }, { "epoch": 1.18, "learning_rate": 1.2373521681997372e-05, "loss": 0.8571, "step": 7161 }, { "epoch": 1.18, "learning_rate": 1.237105781865966e-05, "loss": 0.2659, "step": 7162 }, { "epoch": 1.18, "learning_rate": 1.2368593955321945e-05, "loss": 0.3836, "step": 7163 }, { "epoch": 1.18, "learning_rate": 1.2366130091984233e-05, "loss": 0.6066, "step": 7164 }, { "epoch": 1.18, "learning_rate": 1.2363666228646519e-05, "loss": 0.7267, "step": 7165 }, { "epoch": 1.18, "learning_rate": 1.2361202365308805e-05, "loss": 0.6711, "step": 7166 }, { "epoch": 1.18, "learning_rate": 1.235873850197109e-05, "loss": 0.4635, "step": 7167 }, { "epoch": 1.18, "learning_rate": 1.2356274638633377e-05, "loss": 0.4194, "step": 7168 }, { "epoch": 1.18, "learning_rate": 1.2353810775295664e-05, "loss": 0.3585, "step": 7169 }, { "epoch": 1.18, "learning_rate": 1.235134691195795e-05, "loss": 0.3325, "step": 7170 }, { "epoch": 1.18, "learning_rate": 1.2348883048620236e-05, "loss": 0.1799, "step": 7171 }, { "epoch": 1.18, "learning_rate": 1.2346419185282522e-05, "loss": 0.457, "step": 7172 }, { "epoch": 1.18, "learning_rate": 1.2343955321944808e-05, "loss": 0.5673, "step": 7173 }, { "epoch": 1.18, "learning_rate": 1.2341491458607098e-05, "loss": 0.4647, "step": 7174 }, { "epoch": 1.18, "learning_rate": 1.2339027595269384e-05, "loss": 0.4033, "step": 7175 }, { "epoch": 1.18, "learning_rate": 1.233656373193167e-05, "loss": 0.6099, "step": 7176 }, { "epoch": 1.18, "learning_rate": 1.2334099868593956e-05, "loss": 0.3048, "step": 7177 }, { "epoch": 1.18, "learning_rate": 1.2331636005256242e-05, "loss": 0.4806, "step": 7178 }, { "epoch": 1.18, "learning_rate": 1.232917214191853e-05, "loss": 0.34, "step": 7179 }, { "epoch": 1.18, "learning_rate": 1.2326708278580815e-05, "loss": 0.3364, "step": 7180 }, { "epoch": 1.18, "learning_rate": 1.2324244415243101e-05, "loss": 0.5228, "step": 7181 }, { "epoch": 1.18, "learning_rate": 1.2321780551905387e-05, "loss": 0.947, "step": 7182 }, { "epoch": 1.18, "learning_rate": 1.2319316688567673e-05, "loss": 0.3287, "step": 7183 }, { "epoch": 1.18, "learning_rate": 1.2316852825229961e-05, "loss": 0.5096, "step": 7184 }, { "epoch": 1.18, "learning_rate": 1.2314388961892247e-05, "loss": 0.5309, "step": 7185 }, { "epoch": 1.18, "learning_rate": 1.2311925098554535e-05, "loss": 0.4405, "step": 7186 }, { "epoch": 1.18, "learning_rate": 1.230946123521682e-05, "loss": 0.5561, "step": 7187 }, { "epoch": 1.18, "learning_rate": 1.2306997371879107e-05, "loss": 0.8467, "step": 7188 }, { "epoch": 1.18, "learning_rate": 1.2304533508541394e-05, "loss": 0.1421, "step": 7189 }, { "epoch": 1.18, "learning_rate": 1.230206964520368e-05, "loss": 1.3742, "step": 7190 }, { "epoch": 1.18, "learning_rate": 1.2299605781865966e-05, "loss": 0.6063, "step": 7191 }, { "epoch": 1.18, "learning_rate": 1.2297141918528252e-05, "loss": 0.3069, "step": 7192 }, { "epoch": 1.18, "learning_rate": 1.2294678055190538e-05, "loss": 0.7504, "step": 7193 }, { "epoch": 1.18, "learning_rate": 1.2292214191852826e-05, "loss": 0.5202, "step": 7194 }, { "epoch": 1.18, "learning_rate": 1.2289750328515112e-05, "loss": 0.7265, "step": 7195 }, { "epoch": 1.18, "learning_rate": 1.2287286465177398e-05, "loss": 0.9511, "step": 7196 }, { "epoch": 1.18, "learning_rate": 1.2284822601839684e-05, "loss": 0.5327, "step": 7197 }, { "epoch": 1.18, "learning_rate": 1.2282358738501972e-05, "loss": 0.8036, "step": 7198 }, { "epoch": 1.18, "learning_rate": 1.227989487516426e-05, "loss": 0.5015, "step": 7199 }, { "epoch": 1.18, "learning_rate": 1.2277431011826545e-05, "loss": 0.8035, "step": 7200 }, { "epoch": 1.18, "learning_rate": 1.2274967148488831e-05, "loss": 0.5769, "step": 7201 }, { "epoch": 1.18, "learning_rate": 1.2272503285151117e-05, "loss": 0.5546, "step": 7202 }, { "epoch": 1.18, "learning_rate": 1.2270039421813403e-05, "loss": 0.5842, "step": 7203 }, { "epoch": 1.18, "learning_rate": 1.2267575558475691e-05, "loss": 0.6983, "step": 7204 }, { "epoch": 1.18, "learning_rate": 1.2265111695137977e-05, "loss": 0.2978, "step": 7205 }, { "epoch": 1.18, "learning_rate": 1.2262647831800263e-05, "loss": 0.4358, "step": 7206 }, { "epoch": 1.18, "learning_rate": 1.2260183968462549e-05, "loss": 0.5915, "step": 7207 }, { "epoch": 1.18, "learning_rate": 1.2257720105124835e-05, "loss": 0.9668, "step": 7208 }, { "epoch": 1.18, "learning_rate": 1.2255256241787122e-05, "loss": 0.705, "step": 7209 }, { "epoch": 1.18, "learning_rate": 1.225279237844941e-05, "loss": 1.087, "step": 7210 }, { "epoch": 1.18, "learning_rate": 1.2250328515111696e-05, "loss": 0.6194, "step": 7211 }, { "epoch": 1.18, "learning_rate": 1.2247864651773982e-05, "loss": 0.6149, "step": 7212 }, { "epoch": 1.18, "learning_rate": 1.2245400788436268e-05, "loss": 0.7423, "step": 7213 }, { "epoch": 1.18, "learning_rate": 1.2242936925098556e-05, "loss": 0.9829, "step": 7214 }, { "epoch": 1.19, "learning_rate": 1.2240473061760842e-05, "loss": 0.8235, "step": 7215 }, { "epoch": 1.19, "learning_rate": 1.2238009198423128e-05, "loss": 0.7899, "step": 7216 }, { "epoch": 1.19, "learning_rate": 1.2235545335085414e-05, "loss": 0.6758, "step": 7217 }, { "epoch": 1.19, "learning_rate": 1.22330814717477e-05, "loss": 0.421, "step": 7218 }, { "epoch": 1.19, "learning_rate": 1.2230617608409987e-05, "loss": 0.8234, "step": 7219 }, { "epoch": 1.19, "learning_rate": 1.2228153745072273e-05, "loss": 0.518, "step": 7220 }, { "epoch": 1.19, "learning_rate": 1.2225689881734561e-05, "loss": 0.6718, "step": 7221 }, { "epoch": 1.19, "learning_rate": 1.2223226018396847e-05, "loss": 0.4948, "step": 7222 }, { "epoch": 1.19, "learning_rate": 1.2220762155059133e-05, "loss": 0.4459, "step": 7223 }, { "epoch": 1.19, "learning_rate": 1.221829829172142e-05, "loss": 0.4368, "step": 7224 }, { "epoch": 1.19, "learning_rate": 1.2215834428383707e-05, "loss": 0.5091, "step": 7225 }, { "epoch": 1.19, "learning_rate": 1.2213370565045993e-05, "loss": 0.564, "step": 7226 }, { "epoch": 1.19, "learning_rate": 1.2210906701708279e-05, "loss": 0.4483, "step": 7227 }, { "epoch": 1.19, "learning_rate": 1.2208442838370565e-05, "loss": 0.476, "step": 7228 }, { "epoch": 1.19, "learning_rate": 1.2205978975032852e-05, "loss": 0.4744, "step": 7229 }, { "epoch": 1.19, "learning_rate": 1.2203515111695138e-05, "loss": 0.2854, "step": 7230 }, { "epoch": 1.19, "learning_rate": 1.2201051248357424e-05, "loss": 0.5577, "step": 7231 }, { "epoch": 1.19, "learning_rate": 1.219858738501971e-05, "loss": 0.6028, "step": 7232 }, { "epoch": 1.19, "learning_rate": 1.2196123521681998e-05, "loss": 0.6079, "step": 7233 }, { "epoch": 1.19, "learning_rate": 1.2193659658344286e-05, "loss": 0.5031, "step": 7234 }, { "epoch": 1.19, "learning_rate": 1.2191195795006572e-05, "loss": 0.2968, "step": 7235 }, { "epoch": 1.19, "learning_rate": 1.2188731931668858e-05, "loss": 0.7951, "step": 7236 }, { "epoch": 1.19, "learning_rate": 1.2186268068331144e-05, "loss": 0.5607, "step": 7237 }, { "epoch": 1.19, "learning_rate": 1.218380420499343e-05, "loss": 1.0343, "step": 7238 }, { "epoch": 1.19, "learning_rate": 1.2181340341655716e-05, "loss": 0.444, "step": 7239 }, { "epoch": 1.19, "learning_rate": 1.2178876478318003e-05, "loss": 0.2742, "step": 7240 }, { "epoch": 1.19, "learning_rate": 1.217641261498029e-05, "loss": 0.5389, "step": 7241 }, { "epoch": 1.19, "learning_rate": 1.2173948751642575e-05, "loss": 0.3639, "step": 7242 }, { "epoch": 1.19, "learning_rate": 1.2171484888304861e-05, "loss": 0.3758, "step": 7243 }, { "epoch": 1.19, "learning_rate": 1.2169021024967147e-05, "loss": 0.9058, "step": 7244 }, { "epoch": 1.19, "learning_rate": 1.2166557161629437e-05, "loss": 1.0215, "step": 7245 }, { "epoch": 1.19, "learning_rate": 1.2164093298291723e-05, "loss": 0.4927, "step": 7246 }, { "epoch": 1.19, "learning_rate": 1.2161629434954009e-05, "loss": 0.47, "step": 7247 }, { "epoch": 1.19, "learning_rate": 1.2159165571616295e-05, "loss": 0.4729, "step": 7248 }, { "epoch": 1.19, "learning_rate": 1.215670170827858e-05, "loss": 0.354, "step": 7249 }, { "epoch": 1.19, "learning_rate": 1.2154237844940868e-05, "loss": 1.0203, "step": 7250 }, { "epoch": 1.19, "learning_rate": 1.2151773981603154e-05, "loss": 0.5903, "step": 7251 }, { "epoch": 1.19, "learning_rate": 1.214931011826544e-05, "loss": 0.2387, "step": 7252 }, { "epoch": 1.19, "learning_rate": 1.2146846254927726e-05, "loss": 0.2452, "step": 7253 }, { "epoch": 1.19, "learning_rate": 1.2144382391590012e-05, "loss": 0.5065, "step": 7254 }, { "epoch": 1.19, "learning_rate": 1.21419185282523e-05, "loss": 0.3265, "step": 7255 }, { "epoch": 1.19, "learning_rate": 1.2139454664914586e-05, "loss": 0.4316, "step": 7256 }, { "epoch": 1.19, "learning_rate": 1.2136990801576873e-05, "loss": 0.4965, "step": 7257 }, { "epoch": 1.19, "learning_rate": 1.213452693823916e-05, "loss": 0.2776, "step": 7258 }, { "epoch": 1.19, "learning_rate": 1.2132063074901445e-05, "loss": 0.2863, "step": 7259 }, { "epoch": 1.19, "learning_rate": 1.2129599211563733e-05, "loss": 0.5037, "step": 7260 }, { "epoch": 1.19, "learning_rate": 1.2127135348226019e-05, "loss": 0.353, "step": 7261 }, { "epoch": 1.19, "learning_rate": 1.2124671484888305e-05, "loss": 0.2945, "step": 7262 }, { "epoch": 1.19, "learning_rate": 1.2122207621550591e-05, "loss": 0.3377, "step": 7263 }, { "epoch": 1.19, "learning_rate": 1.2119743758212877e-05, "loss": 0.7042, "step": 7264 }, { "epoch": 1.19, "learning_rate": 1.2117279894875165e-05, "loss": 0.457, "step": 7265 }, { "epoch": 1.19, "learning_rate": 1.211481603153745e-05, "loss": 0.3894, "step": 7266 }, { "epoch": 1.19, "learning_rate": 1.2112352168199737e-05, "loss": 0.4589, "step": 7267 }, { "epoch": 1.19, "learning_rate": 1.2109888304862023e-05, "loss": 0.4463, "step": 7268 }, { "epoch": 1.19, "learning_rate": 1.210742444152431e-05, "loss": 0.3659, "step": 7269 }, { "epoch": 1.19, "learning_rate": 1.2104960578186598e-05, "loss": 0.3422, "step": 7270 }, { "epoch": 1.19, "learning_rate": 1.2102496714848884e-05, "loss": 0.5636, "step": 7271 }, { "epoch": 1.19, "learning_rate": 1.210003285151117e-05, "loss": 0.5118, "step": 7272 }, { "epoch": 1.19, "learning_rate": 1.2097568988173456e-05, "loss": 0.9072, "step": 7273 }, { "epoch": 1.19, "learning_rate": 1.2095105124835742e-05, "loss": 0.5578, "step": 7274 }, { "epoch": 1.19, "learning_rate": 1.209264126149803e-05, "loss": 0.461, "step": 7275 }, { "epoch": 1.2, "learning_rate": 1.2090177398160316e-05, "loss": 0.4557, "step": 7276 }, { "epoch": 1.2, "learning_rate": 1.2087713534822602e-05, "loss": 0.869, "step": 7277 }, { "epoch": 1.2, "learning_rate": 1.2085249671484888e-05, "loss": 0.9127, "step": 7278 }, { "epoch": 1.2, "learning_rate": 1.2082785808147174e-05, "loss": 0.5805, "step": 7279 }, { "epoch": 1.2, "learning_rate": 1.2080321944809461e-05, "loss": 0.4506, "step": 7280 }, { "epoch": 1.2, "learning_rate": 1.2077858081471749e-05, "loss": 0.257, "step": 7281 }, { "epoch": 1.2, "learning_rate": 1.2075394218134035e-05, "loss": 0.7132, "step": 7282 }, { "epoch": 1.2, "learning_rate": 1.2072930354796321e-05, "loss": 0.4665, "step": 7283 }, { "epoch": 1.2, "learning_rate": 1.2070466491458607e-05, "loss": 0.2734, "step": 7284 }, { "epoch": 1.2, "learning_rate": 1.2068002628120895e-05, "loss": 1.1114, "step": 7285 }, { "epoch": 1.2, "learning_rate": 1.206553876478318e-05, "loss": 0.3295, "step": 7286 }, { "epoch": 1.2, "learning_rate": 1.2063074901445467e-05, "loss": 0.7484, "step": 7287 }, { "epoch": 1.2, "learning_rate": 1.2060611038107753e-05, "loss": 0.5044, "step": 7288 }, { "epoch": 1.2, "learning_rate": 1.2058147174770039e-05, "loss": 0.5444, "step": 7289 }, { "epoch": 1.2, "learning_rate": 1.2055683311432326e-05, "loss": 0.3418, "step": 7290 }, { "epoch": 1.2, "learning_rate": 1.2053219448094612e-05, "loss": 0.6001, "step": 7291 }, { "epoch": 1.2, "learning_rate": 1.2050755584756898e-05, "loss": 1.043, "step": 7292 }, { "epoch": 1.2, "learning_rate": 1.2048291721419186e-05, "loss": 0.7381, "step": 7293 }, { "epoch": 1.2, "learning_rate": 1.2045827858081472e-05, "loss": 0.548, "step": 7294 }, { "epoch": 1.2, "learning_rate": 1.204336399474376e-05, "loss": 0.2625, "step": 7295 }, { "epoch": 1.2, "learning_rate": 1.2040900131406046e-05, "loss": 0.6498, "step": 7296 }, { "epoch": 1.2, "learning_rate": 1.2038436268068331e-05, "loss": 0.6114, "step": 7297 }, { "epoch": 1.2, "learning_rate": 1.2035972404730617e-05, "loss": 0.6325, "step": 7298 }, { "epoch": 1.2, "learning_rate": 1.2033508541392903e-05, "loss": 0.3753, "step": 7299 }, { "epoch": 1.2, "learning_rate": 1.2031044678055191e-05, "loss": 0.4567, "step": 7300 }, { "epoch": 1.2, "learning_rate": 1.2028580814717477e-05, "loss": 0.2844, "step": 7301 }, { "epoch": 1.2, "learning_rate": 1.2026116951379763e-05, "loss": 0.2698, "step": 7302 }, { "epoch": 1.2, "learning_rate": 1.2023653088042049e-05, "loss": 0.5948, "step": 7303 }, { "epoch": 1.2, "learning_rate": 1.2021189224704335e-05, "loss": 0.9229, "step": 7304 }, { "epoch": 1.2, "learning_rate": 1.2018725361366624e-05, "loss": 0.3742, "step": 7305 }, { "epoch": 1.2, "learning_rate": 1.201626149802891e-05, "loss": 0.571, "step": 7306 }, { "epoch": 1.2, "learning_rate": 1.2013797634691196e-05, "loss": 0.5462, "step": 7307 }, { "epoch": 1.2, "learning_rate": 1.2011333771353482e-05, "loss": 0.4475, "step": 7308 }, { "epoch": 1.2, "learning_rate": 1.2008869908015768e-05, "loss": 0.4241, "step": 7309 }, { "epoch": 1.2, "learning_rate": 1.2006406044678056e-05, "loss": 0.5339, "step": 7310 }, { "epoch": 1.2, "learning_rate": 1.2003942181340342e-05, "loss": 0.6502, "step": 7311 }, { "epoch": 1.2, "learning_rate": 1.2001478318002628e-05, "loss": 0.4808, "step": 7312 }, { "epoch": 1.2, "learning_rate": 1.1999014454664914e-05, "loss": 0.3114, "step": 7313 }, { "epoch": 1.2, "learning_rate": 1.19965505913272e-05, "loss": 0.3629, "step": 7314 }, { "epoch": 1.2, "learning_rate": 1.1994086727989488e-05, "loss": 0.1985, "step": 7315 }, { "epoch": 1.2, "learning_rate": 1.1991622864651774e-05, "loss": 0.2431, "step": 7316 }, { "epoch": 1.2, "learning_rate": 1.1989159001314061e-05, "loss": 0.1083, "step": 7317 }, { "epoch": 1.2, "learning_rate": 1.1986695137976347e-05, "loss": 0.4015, "step": 7318 }, { "epoch": 1.2, "learning_rate": 1.1984231274638633e-05, "loss": 0.1127, "step": 7319 }, { "epoch": 1.2, "learning_rate": 1.1981767411300921e-05, "loss": 0.8892, "step": 7320 }, { "epoch": 1.2, "learning_rate": 1.1979303547963207e-05, "loss": 0.7437, "step": 7321 }, { "epoch": 1.2, "learning_rate": 1.1976839684625493e-05, "loss": 0.4518, "step": 7322 }, { "epoch": 1.2, "learning_rate": 1.1974375821287779e-05, "loss": 0.7761, "step": 7323 }, { "epoch": 1.2, "learning_rate": 1.1971911957950065e-05, "loss": 0.2853, "step": 7324 }, { "epoch": 1.2, "learning_rate": 1.1969448094612353e-05, "loss": 0.095, "step": 7325 }, { "epoch": 1.2, "learning_rate": 1.1966984231274639e-05, "loss": 0.4967, "step": 7326 }, { "epoch": 1.2, "learning_rate": 1.1964520367936925e-05, "loss": 0.1944, "step": 7327 }, { "epoch": 1.2, "learning_rate": 1.196205650459921e-05, "loss": 1.0511, "step": 7328 }, { "epoch": 1.2, "learning_rate": 1.1959592641261498e-05, "loss": 0.4668, "step": 7329 }, { "epoch": 1.2, "learning_rate": 1.1957128777923786e-05, "loss": 0.8859, "step": 7330 }, { "epoch": 1.2, "learning_rate": 1.1954664914586072e-05, "loss": 0.292, "step": 7331 }, { "epoch": 1.2, "learning_rate": 1.1952201051248358e-05, "loss": 0.5894, "step": 7332 }, { "epoch": 1.2, "learning_rate": 1.1949737187910644e-05, "loss": 0.2735, "step": 7333 }, { "epoch": 1.2, "learning_rate": 1.194727332457293e-05, "loss": 0.6679, "step": 7334 }, { "epoch": 1.2, "learning_rate": 1.1944809461235218e-05, "loss": 0.5551, "step": 7335 }, { "epoch": 1.2, "learning_rate": 1.1942345597897504e-05, "loss": 1.231, "step": 7336 }, { "epoch": 1.21, "learning_rate": 1.193988173455979e-05, "loss": 0.3305, "step": 7337 }, { "epoch": 1.21, "learning_rate": 1.1937417871222075e-05, "loss": 0.4709, "step": 7338 }, { "epoch": 1.21, "learning_rate": 1.1934954007884361e-05, "loss": 0.7314, "step": 7339 }, { "epoch": 1.21, "learning_rate": 1.193249014454665e-05, "loss": 0.2378, "step": 7340 }, { "epoch": 1.21, "learning_rate": 1.1930026281208937e-05, "loss": 0.6988, "step": 7341 }, { "epoch": 1.21, "learning_rate": 1.1927562417871223e-05, "loss": 0.9159, "step": 7342 }, { "epoch": 1.21, "learning_rate": 1.1925098554533509e-05, "loss": 0.4243, "step": 7343 }, { "epoch": 1.21, "learning_rate": 1.1922634691195795e-05, "loss": 0.8674, "step": 7344 }, { "epoch": 1.21, "learning_rate": 1.1920170827858082e-05, "loss": 0.2499, "step": 7345 }, { "epoch": 1.21, "learning_rate": 1.1917706964520368e-05, "loss": 0.8144, "step": 7346 }, { "epoch": 1.21, "learning_rate": 1.1915243101182654e-05, "loss": 1.0837, "step": 7347 }, { "epoch": 1.21, "learning_rate": 1.191277923784494e-05, "loss": 0.519, "step": 7348 }, { "epoch": 1.21, "learning_rate": 1.1910315374507226e-05, "loss": 0.5592, "step": 7349 }, { "epoch": 1.21, "learning_rate": 1.1907851511169514e-05, "loss": 0.8457, "step": 7350 }, { "epoch": 1.21, "learning_rate": 1.19053876478318e-05, "loss": 0.5901, "step": 7351 }, { "epoch": 1.21, "learning_rate": 1.1902923784494088e-05, "loss": 0.5819, "step": 7352 }, { "epoch": 1.21, "learning_rate": 1.1900459921156374e-05, "loss": 0.2868, "step": 7353 }, { "epoch": 1.21, "learning_rate": 1.189799605781866e-05, "loss": 1.0884, "step": 7354 }, { "epoch": 1.21, "learning_rate": 1.1895532194480947e-05, "loss": 0.349, "step": 7355 }, { "epoch": 1.21, "learning_rate": 1.1893068331143233e-05, "loss": 0.4998, "step": 7356 }, { "epoch": 1.21, "learning_rate": 1.189060446780552e-05, "loss": 0.3623, "step": 7357 }, { "epoch": 1.21, "learning_rate": 1.1888140604467805e-05, "loss": 0.7592, "step": 7358 }, { "epoch": 1.21, "learning_rate": 1.1885676741130091e-05, "loss": 0.8381, "step": 7359 }, { "epoch": 1.21, "learning_rate": 1.1883212877792379e-05, "loss": 0.6001, "step": 7360 }, { "epoch": 1.21, "learning_rate": 1.1880749014454665e-05, "loss": 0.2543, "step": 7361 }, { "epoch": 1.21, "learning_rate": 1.1878285151116951e-05, "loss": 0.6067, "step": 7362 }, { "epoch": 1.21, "learning_rate": 1.1875821287779237e-05, "loss": 0.7169, "step": 7363 }, { "epoch": 1.21, "learning_rate": 1.1873357424441525e-05, "loss": 0.7754, "step": 7364 }, { "epoch": 1.21, "learning_rate": 1.1870893561103812e-05, "loss": 0.4964, "step": 7365 }, { "epoch": 1.21, "learning_rate": 1.1868429697766098e-05, "loss": 0.84, "step": 7366 }, { "epoch": 1.21, "learning_rate": 1.1865965834428384e-05, "loss": 0.5701, "step": 7367 }, { "epoch": 1.21, "learning_rate": 1.186350197109067e-05, "loss": 0.4376, "step": 7368 }, { "epoch": 1.21, "learning_rate": 1.1861038107752956e-05, "loss": 0.9337, "step": 7369 }, { "epoch": 1.21, "learning_rate": 1.1858574244415244e-05, "loss": 0.2856, "step": 7370 }, { "epoch": 1.21, "learning_rate": 1.185611038107753e-05, "loss": 0.5079, "step": 7371 }, { "epoch": 1.21, "learning_rate": 1.1853646517739816e-05, "loss": 0.2552, "step": 7372 }, { "epoch": 1.21, "learning_rate": 1.1851182654402102e-05, "loss": 0.6465, "step": 7373 }, { "epoch": 1.21, "learning_rate": 1.1848718791064388e-05, "loss": 0.2621, "step": 7374 }, { "epoch": 1.21, "learning_rate": 1.1846254927726676e-05, "loss": 0.6297, "step": 7375 }, { "epoch": 1.21, "learning_rate": 1.1843791064388963e-05, "loss": 0.5541, "step": 7376 }, { "epoch": 1.21, "learning_rate": 1.184132720105125e-05, "loss": 0.7389, "step": 7377 }, { "epoch": 1.21, "learning_rate": 1.1838863337713535e-05, "loss": 0.6313, "step": 7378 }, { "epoch": 1.21, "learning_rate": 1.1836399474375821e-05, "loss": 0.3012, "step": 7379 }, { "epoch": 1.21, "learning_rate": 1.1833935611038109e-05, "loss": 0.6104, "step": 7380 }, { "epoch": 1.21, "learning_rate": 1.1831471747700395e-05, "loss": 0.8016, "step": 7381 }, { "epoch": 1.21, "learning_rate": 1.182900788436268e-05, "loss": 0.4508, "step": 7382 }, { "epoch": 1.21, "learning_rate": 1.1826544021024967e-05, "loss": 0.776, "step": 7383 }, { "epoch": 1.21, "learning_rate": 1.1824080157687253e-05, "loss": 0.6386, "step": 7384 }, { "epoch": 1.21, "learning_rate": 1.182161629434954e-05, "loss": 0.6963, "step": 7385 }, { "epoch": 1.21, "learning_rate": 1.1819152431011826e-05, "loss": 0.7388, "step": 7386 }, { "epoch": 1.21, "learning_rate": 1.1816688567674112e-05, "loss": 0.6175, "step": 7387 }, { "epoch": 1.21, "learning_rate": 1.18142247043364e-05, "loss": 0.5974, "step": 7388 }, { "epoch": 1.21, "learning_rate": 1.1811760840998686e-05, "loss": 0.5932, "step": 7389 }, { "epoch": 1.21, "learning_rate": 1.1809296977660974e-05, "loss": 0.4026, "step": 7390 }, { "epoch": 1.21, "learning_rate": 1.180683311432326e-05, "loss": 1.1497, "step": 7391 }, { "epoch": 1.21, "learning_rate": 1.1804369250985546e-05, "loss": 0.337, "step": 7392 }, { "epoch": 1.21, "learning_rate": 1.1801905387647832e-05, "loss": 0.8761, "step": 7393 }, { "epoch": 1.21, "learning_rate": 1.1799441524310118e-05, "loss": 0.7664, "step": 7394 }, { "epoch": 1.21, "learning_rate": 1.1796977660972405e-05, "loss": 0.2405, "step": 7395 }, { "epoch": 1.21, "learning_rate": 1.1794513797634691e-05, "loss": 0.4525, "step": 7396 }, { "epoch": 1.22, "learning_rate": 1.1792049934296977e-05, "loss": 0.1546, "step": 7397 }, { "epoch": 1.22, "learning_rate": 1.1789586070959263e-05, "loss": 0.5685, "step": 7398 }, { "epoch": 1.22, "learning_rate": 1.178712220762155e-05, "loss": 0.3085, "step": 7399 }, { "epoch": 1.22, "learning_rate": 1.1784658344283839e-05, "loss": 0.5228, "step": 7400 }, { "epoch": 1.22, "learning_rate": 1.1782194480946125e-05, "loss": 0.1829, "step": 7401 }, { "epoch": 1.22, "learning_rate": 1.177973061760841e-05, "loss": 0.3637, "step": 7402 }, { "epoch": 1.22, "learning_rate": 1.1777266754270697e-05, "loss": 0.3051, "step": 7403 }, { "epoch": 1.22, "learning_rate": 1.1774802890932983e-05, "loss": 0.4264, "step": 7404 }, { "epoch": 1.22, "learning_rate": 1.177233902759527e-05, "loss": 0.4049, "step": 7405 }, { "epoch": 1.22, "learning_rate": 1.1769875164257556e-05, "loss": 0.5963, "step": 7406 }, { "epoch": 1.22, "learning_rate": 1.1767411300919842e-05, "loss": 0.542, "step": 7407 }, { "epoch": 1.22, "learning_rate": 1.1764947437582128e-05, "loss": 0.5804, "step": 7408 }, { "epoch": 1.22, "learning_rate": 1.1762483574244414e-05, "loss": 1.2517, "step": 7409 }, { "epoch": 1.22, "learning_rate": 1.1760019710906702e-05, "loss": 0.633, "step": 7410 }, { "epoch": 1.22, "learning_rate": 1.1757555847568988e-05, "loss": 0.9186, "step": 7411 }, { "epoch": 1.22, "learning_rate": 1.1755091984231276e-05, "loss": 1.0232, "step": 7412 }, { "epoch": 1.22, "learning_rate": 1.1752628120893562e-05, "loss": 1.6995, "step": 7413 }, { "epoch": 1.22, "learning_rate": 1.1750164257555848e-05, "loss": 0.4554, "step": 7414 }, { "epoch": 1.22, "learning_rate": 1.1747700394218135e-05, "loss": 0.4595, "step": 7415 }, { "epoch": 1.22, "learning_rate": 1.1745236530880421e-05, "loss": 0.2916, "step": 7416 }, { "epoch": 1.22, "learning_rate": 1.1742772667542707e-05, "loss": 0.5463, "step": 7417 }, { "epoch": 1.22, "learning_rate": 1.1740308804204993e-05, "loss": 0.9267, "step": 7418 }, { "epoch": 1.22, "learning_rate": 1.173784494086728e-05, "loss": 0.4855, "step": 7419 }, { "epoch": 1.22, "learning_rate": 1.1735381077529567e-05, "loss": 0.3999, "step": 7420 }, { "epoch": 1.22, "learning_rate": 1.1732917214191853e-05, "loss": 0.5613, "step": 7421 }, { "epoch": 1.22, "learning_rate": 1.1730453350854139e-05, "loss": 0.594, "step": 7422 }, { "epoch": 1.22, "learning_rate": 1.1727989487516425e-05, "loss": 0.4302, "step": 7423 }, { "epoch": 1.22, "learning_rate": 1.1725525624178713e-05, "loss": 0.5436, "step": 7424 }, { "epoch": 1.22, "learning_rate": 1.1723061760841e-05, "loss": 0.6958, "step": 7425 }, { "epoch": 1.22, "learning_rate": 1.1720597897503286e-05, "loss": 0.682, "step": 7426 }, { "epoch": 1.22, "learning_rate": 1.1718134034165572e-05, "loss": 0.9082, "step": 7427 }, { "epoch": 1.22, "learning_rate": 1.1715670170827858e-05, "loss": 0.6387, "step": 7428 }, { "epoch": 1.22, "learning_rate": 1.1713206307490144e-05, "loss": 0.3453, "step": 7429 }, { "epoch": 1.22, "learning_rate": 1.1710742444152432e-05, "loss": 0.8874, "step": 7430 }, { "epoch": 1.22, "learning_rate": 1.1708278580814718e-05, "loss": 0.4505, "step": 7431 }, { "epoch": 1.22, "learning_rate": 1.1705814717477004e-05, "loss": 0.5773, "step": 7432 }, { "epoch": 1.22, "learning_rate": 1.170335085413929e-05, "loss": 0.2676, "step": 7433 }, { "epoch": 1.22, "learning_rate": 1.1700886990801576e-05, "loss": 0.7328, "step": 7434 }, { "epoch": 1.22, "learning_rate": 1.1698423127463863e-05, "loss": 0.4529, "step": 7435 }, { "epoch": 1.22, "learning_rate": 1.1695959264126151e-05, "loss": 0.6793, "step": 7436 }, { "epoch": 1.22, "learning_rate": 1.1693495400788437e-05, "loss": 0.291, "step": 7437 }, { "epoch": 1.22, "learning_rate": 1.1691031537450723e-05, "loss": 0.406, "step": 7438 }, { "epoch": 1.22, "learning_rate": 1.1688567674113009e-05, "loss": 0.2884, "step": 7439 }, { "epoch": 1.22, "learning_rate": 1.1686103810775297e-05, "loss": 0.743, "step": 7440 }, { "epoch": 1.22, "learning_rate": 1.1683639947437583e-05, "loss": 0.6371, "step": 7441 }, { "epoch": 1.22, "learning_rate": 1.1681176084099869e-05, "loss": 0.2971, "step": 7442 }, { "epoch": 1.22, "learning_rate": 1.1678712220762155e-05, "loss": 0.8066, "step": 7443 }, { "epoch": 1.22, "learning_rate": 1.167624835742444e-05, "loss": 0.8228, "step": 7444 }, { "epoch": 1.22, "learning_rate": 1.1673784494086728e-05, "loss": 0.4247, "step": 7445 }, { "epoch": 1.22, "learning_rate": 1.1671320630749014e-05, "loss": 0.7227, "step": 7446 }, { "epoch": 1.22, "learning_rate": 1.16688567674113e-05, "loss": 0.3069, "step": 7447 }, { "epoch": 1.22, "learning_rate": 1.1666392904073588e-05, "loss": 0.716, "step": 7448 }, { "epoch": 1.22, "learning_rate": 1.1663929040735874e-05, "loss": 0.2924, "step": 7449 }, { "epoch": 1.22, "learning_rate": 1.1661465177398162e-05, "loss": 0.3069, "step": 7450 }, { "epoch": 1.22, "learning_rate": 1.1659001314060448e-05, "loss": 0.2709, "step": 7451 }, { "epoch": 1.22, "learning_rate": 1.1656537450722734e-05, "loss": 0.4226, "step": 7452 }, { "epoch": 1.22, "learning_rate": 1.165407358738502e-05, "loss": 0.2836, "step": 7453 }, { "epoch": 1.22, "learning_rate": 1.1651609724047306e-05, "loss": 1.0522, "step": 7454 }, { "epoch": 1.22, "learning_rate": 1.1649145860709593e-05, "loss": 0.7608, "step": 7455 }, { "epoch": 1.22, "learning_rate": 1.164668199737188e-05, "loss": 0.447, "step": 7456 }, { "epoch": 1.22, "learning_rate": 1.1644218134034165e-05, "loss": 0.2883, "step": 7457 }, { "epoch": 1.23, "learning_rate": 1.1641754270696451e-05, "loss": 0.3063, "step": 7458 }, { "epoch": 1.23, "learning_rate": 1.1639290407358737e-05, "loss": 0.5715, "step": 7459 }, { "epoch": 1.23, "learning_rate": 1.1636826544021027e-05, "loss": 0.1985, "step": 7460 }, { "epoch": 1.23, "learning_rate": 1.1634362680683313e-05, "loss": 0.1451, "step": 7461 }, { "epoch": 1.23, "learning_rate": 1.1631898817345599e-05, "loss": 0.1999, "step": 7462 }, { "epoch": 1.23, "learning_rate": 1.1629434954007885e-05, "loss": 0.6384, "step": 7463 }, { "epoch": 1.23, "learning_rate": 1.162697109067017e-05, "loss": 0.4955, "step": 7464 }, { "epoch": 1.23, "learning_rate": 1.1624507227332458e-05, "loss": 0.1521, "step": 7465 }, { "epoch": 1.23, "learning_rate": 1.1622043363994744e-05, "loss": 0.6975, "step": 7466 }, { "epoch": 1.23, "learning_rate": 1.161957950065703e-05, "loss": 0.3944, "step": 7467 }, { "epoch": 1.23, "learning_rate": 1.1617115637319316e-05, "loss": 0.5205, "step": 7468 }, { "epoch": 1.23, "learning_rate": 1.1614651773981602e-05, "loss": 0.7304, "step": 7469 }, { "epoch": 1.23, "learning_rate": 1.161218791064389e-05, "loss": 0.7179, "step": 7470 }, { "epoch": 1.23, "learning_rate": 1.1609724047306176e-05, "loss": 0.6238, "step": 7471 }, { "epoch": 1.23, "learning_rate": 1.1607260183968463e-05, "loss": 0.2416, "step": 7472 }, { "epoch": 1.23, "learning_rate": 1.160479632063075e-05, "loss": 0.4024, "step": 7473 }, { "epoch": 1.23, "learning_rate": 1.1602332457293035e-05, "loss": 1.2983, "step": 7474 }, { "epoch": 1.23, "learning_rate": 1.1599868593955323e-05, "loss": 0.8037, "step": 7475 }, { "epoch": 1.23, "learning_rate": 1.1597404730617609e-05, "loss": 1.013, "step": 7476 }, { "epoch": 1.23, "learning_rate": 1.1594940867279895e-05, "loss": 0.4147, "step": 7477 }, { "epoch": 1.23, "learning_rate": 1.1592477003942181e-05, "loss": 1.0734, "step": 7478 }, { "epoch": 1.23, "learning_rate": 1.1590013140604467e-05, "loss": 1.2035, "step": 7479 }, { "epoch": 1.23, "learning_rate": 1.1587549277266755e-05, "loss": 1.0618, "step": 7480 }, { "epoch": 1.23, "learning_rate": 1.158508541392904e-05, "loss": 0.3869, "step": 7481 }, { "epoch": 1.23, "learning_rate": 1.1582621550591327e-05, "loss": 0.3521, "step": 7482 }, { "epoch": 1.23, "learning_rate": 1.1580157687253614e-05, "loss": 0.4163, "step": 7483 }, { "epoch": 1.23, "learning_rate": 1.15776938239159e-05, "loss": 0.697, "step": 7484 }, { "epoch": 1.23, "learning_rate": 1.1575229960578188e-05, "loss": 0.8566, "step": 7485 }, { "epoch": 1.23, "learning_rate": 1.1572766097240474e-05, "loss": 0.5979, "step": 7486 }, { "epoch": 1.23, "learning_rate": 1.157030223390276e-05, "loss": 0.3891, "step": 7487 }, { "epoch": 1.23, "learning_rate": 1.1567838370565046e-05, "loss": 0.4417, "step": 7488 }, { "epoch": 1.23, "learning_rate": 1.1565374507227332e-05, "loss": 0.4799, "step": 7489 }, { "epoch": 1.23, "learning_rate": 1.156291064388962e-05, "loss": 0.7166, "step": 7490 }, { "epoch": 1.23, "learning_rate": 1.1560446780551906e-05, "loss": 0.6436, "step": 7491 }, { "epoch": 1.23, "learning_rate": 1.1557982917214192e-05, "loss": 0.3046, "step": 7492 }, { "epoch": 1.23, "learning_rate": 1.1555519053876478e-05, "loss": 0.3728, "step": 7493 }, { "epoch": 1.23, "learning_rate": 1.1553055190538764e-05, "loss": 0.5213, "step": 7494 }, { "epoch": 1.23, "learning_rate": 1.1550591327201053e-05, "loss": 0.6229, "step": 7495 }, { "epoch": 1.23, "learning_rate": 1.1548127463863339e-05, "loss": 0.5729, "step": 7496 }, { "epoch": 1.23, "learning_rate": 1.1545663600525625e-05, "loss": 0.6598, "step": 7497 }, { "epoch": 1.23, "learning_rate": 1.1543199737187911e-05, "loss": 0.6412, "step": 7498 }, { "epoch": 1.23, "learning_rate": 1.1540735873850197e-05, "loss": 0.6335, "step": 7499 }, { "epoch": 1.23, "learning_rate": 1.1538272010512485e-05, "loss": 0.3394, "step": 7500 }, { "epoch": 1.23, "eval_exact_match": 86.71712393566698, "eval_f1": 92.77498673388104, "step": 7500 }, { "epoch": 1.23, "learning_rate": 1.153580814717477e-05, "loss": 0.1648, "step": 7501 }, { "epoch": 1.23, "learning_rate": 1.1533344283837057e-05, "loss": 0.4156, "step": 7502 }, { "epoch": 1.23, "learning_rate": 1.1530880420499343e-05, "loss": 0.4285, "step": 7503 }, { "epoch": 1.23, "learning_rate": 1.1528416557161629e-05, "loss": 0.7221, "step": 7504 }, { "epoch": 1.23, "learning_rate": 1.1525952693823916e-05, "loss": 0.3091, "step": 7505 }, { "epoch": 1.23, "learning_rate": 1.1523488830486202e-05, "loss": 0.6573, "step": 7506 }, { "epoch": 1.23, "learning_rate": 1.152102496714849e-05, "loss": 0.8552, "step": 7507 }, { "epoch": 1.23, "learning_rate": 1.1518561103810776e-05, "loss": 0.5931, "step": 7508 }, { "epoch": 1.23, "learning_rate": 1.1516097240473062e-05, "loss": 0.389, "step": 7509 }, { "epoch": 1.23, "learning_rate": 1.151363337713535e-05, "loss": 0.491, "step": 7510 }, { "epoch": 1.23, "learning_rate": 1.1511169513797636e-05, "loss": 0.8083, "step": 7511 }, { "epoch": 1.23, "learning_rate": 1.1508705650459922e-05, "loss": 0.4522, "step": 7512 }, { "epoch": 1.23, "learning_rate": 1.1506241787122207e-05, "loss": 0.7895, "step": 7513 }, { "epoch": 1.23, "learning_rate": 1.1503777923784493e-05, "loss": 0.7168, "step": 7514 }, { "epoch": 1.23, "learning_rate": 1.1501314060446781e-05, "loss": 0.9415, "step": 7515 }, { "epoch": 1.23, "learning_rate": 1.1498850197109067e-05, "loss": 0.3483, "step": 7516 }, { "epoch": 1.23, "learning_rate": 1.1496386333771353e-05, "loss": 0.6018, "step": 7517 }, { "epoch": 1.23, "learning_rate": 1.1493922470433639e-05, "loss": 0.6446, "step": 7518 }, { "epoch": 1.24, "learning_rate": 1.1491458607095927e-05, "loss": 0.9117, "step": 7519 }, { "epoch": 1.24, "learning_rate": 1.1488994743758214e-05, "loss": 0.2241, "step": 7520 }, { "epoch": 1.24, "learning_rate": 1.14865308804205e-05, "loss": 0.4808, "step": 7521 }, { "epoch": 1.24, "learning_rate": 1.1484067017082786e-05, "loss": 0.4762, "step": 7522 }, { "epoch": 1.24, "learning_rate": 1.1481603153745072e-05, "loss": 0.3272, "step": 7523 }, { "epoch": 1.24, "learning_rate": 1.1479139290407358e-05, "loss": 0.377, "step": 7524 }, { "epoch": 1.24, "learning_rate": 1.1476675427069646e-05, "loss": 0.4563, "step": 7525 }, { "epoch": 1.24, "learning_rate": 1.1474211563731932e-05, "loss": 0.5161, "step": 7526 }, { "epoch": 1.24, "learning_rate": 1.1471747700394218e-05, "loss": 0.749, "step": 7527 }, { "epoch": 1.24, "learning_rate": 1.1469283837056504e-05, "loss": 0.7531, "step": 7528 }, { "epoch": 1.24, "learning_rate": 1.146681997371879e-05, "loss": 0.3233, "step": 7529 }, { "epoch": 1.24, "learning_rate": 1.1464356110381078e-05, "loss": 0.3754, "step": 7530 }, { "epoch": 1.24, "learning_rate": 1.1461892247043365e-05, "loss": 0.6452, "step": 7531 }, { "epoch": 1.24, "learning_rate": 1.1459428383705651e-05, "loss": 0.4478, "step": 7532 }, { "epoch": 1.24, "learning_rate": 1.1456964520367937e-05, "loss": 0.3357, "step": 7533 }, { "epoch": 1.24, "learning_rate": 1.1454500657030223e-05, "loss": 1.116, "step": 7534 }, { "epoch": 1.24, "learning_rate": 1.1452036793692511e-05, "loss": 0.3749, "step": 7535 }, { "epoch": 1.24, "learning_rate": 1.1449572930354797e-05, "loss": 0.7426, "step": 7536 }, { "epoch": 1.24, "learning_rate": 1.1447109067017083e-05, "loss": 0.7865, "step": 7537 }, { "epoch": 1.24, "learning_rate": 1.1444645203679369e-05, "loss": 0.5469, "step": 7538 }, { "epoch": 1.24, "learning_rate": 1.1442181340341655e-05, "loss": 0.4519, "step": 7539 }, { "epoch": 1.24, "learning_rate": 1.1439717477003943e-05, "loss": 0.4225, "step": 7540 }, { "epoch": 1.24, "learning_rate": 1.1437253613666229e-05, "loss": 0.7334, "step": 7541 }, { "epoch": 1.24, "learning_rate": 1.1434789750328515e-05, "loss": 0.3343, "step": 7542 }, { "epoch": 1.24, "learning_rate": 1.1432325886990802e-05, "loss": 0.6136, "step": 7543 }, { "epoch": 1.24, "learning_rate": 1.1429862023653088e-05, "loss": 0.5943, "step": 7544 }, { "epoch": 1.24, "learning_rate": 1.1427398160315376e-05, "loss": 0.2951, "step": 7545 }, { "epoch": 1.24, "learning_rate": 1.1424934296977662e-05, "loss": 0.5877, "step": 7546 }, { "epoch": 1.24, "learning_rate": 1.1422470433639948e-05, "loss": 0.4174, "step": 7547 }, { "epoch": 1.24, "learning_rate": 1.1420006570302234e-05, "loss": 0.7424, "step": 7548 }, { "epoch": 1.24, "learning_rate": 1.141754270696452e-05, "loss": 0.3552, "step": 7549 }, { "epoch": 1.24, "learning_rate": 1.1415078843626808e-05, "loss": 0.3939, "step": 7550 }, { "epoch": 1.24, "learning_rate": 1.1412614980289094e-05, "loss": 0.2947, "step": 7551 }, { "epoch": 1.24, "learning_rate": 1.141015111695138e-05, "loss": 0.7768, "step": 7552 }, { "epoch": 1.24, "learning_rate": 1.1407687253613666e-05, "loss": 0.4756, "step": 7553 }, { "epoch": 1.24, "learning_rate": 1.1405223390275951e-05, "loss": 0.3207, "step": 7554 }, { "epoch": 1.24, "learning_rate": 1.1402759526938241e-05, "loss": 0.288, "step": 7555 }, { "epoch": 1.24, "learning_rate": 1.1400295663600527e-05, "loss": 0.2721, "step": 7556 }, { "epoch": 1.24, "learning_rate": 1.1397831800262813e-05, "loss": 0.3186, "step": 7557 }, { "epoch": 1.24, "learning_rate": 1.1395367936925099e-05, "loss": 0.1686, "step": 7558 }, { "epoch": 1.24, "learning_rate": 1.1392904073587385e-05, "loss": 0.2394, "step": 7559 }, { "epoch": 1.24, "learning_rate": 1.1390440210249672e-05, "loss": 0.4113, "step": 7560 }, { "epoch": 1.24, "learning_rate": 1.1387976346911958e-05, "loss": 0.4907, "step": 7561 }, { "epoch": 1.24, "learning_rate": 1.1385512483574244e-05, "loss": 0.2569, "step": 7562 }, { "epoch": 1.24, "learning_rate": 1.138304862023653e-05, "loss": 0.5834, "step": 7563 }, { "epoch": 1.24, "learning_rate": 1.1380584756898816e-05, "loss": 0.4686, "step": 7564 }, { "epoch": 1.24, "learning_rate": 1.1378120893561104e-05, "loss": 0.3797, "step": 7565 }, { "epoch": 1.24, "learning_rate": 1.137565703022339e-05, "loss": 0.5452, "step": 7566 }, { "epoch": 1.24, "learning_rate": 1.1373193166885678e-05, "loss": 0.412, "step": 7567 }, { "epoch": 1.24, "learning_rate": 1.1370729303547964e-05, "loss": 0.7099, "step": 7568 }, { "epoch": 1.24, "learning_rate": 1.136826544021025e-05, "loss": 0.3087, "step": 7569 }, { "epoch": 1.24, "learning_rate": 1.1365801576872537e-05, "loss": 0.5856, "step": 7570 }, { "epoch": 1.24, "learning_rate": 1.1363337713534823e-05, "loss": 0.6937, "step": 7571 }, { "epoch": 1.24, "learning_rate": 1.136087385019711e-05, "loss": 0.4903, "step": 7572 }, { "epoch": 1.24, "learning_rate": 1.1358409986859395e-05, "loss": 0.3912, "step": 7573 }, { "epoch": 1.24, "learning_rate": 1.1355946123521681e-05, "loss": 0.4856, "step": 7574 }, { "epoch": 1.24, "learning_rate": 1.1353482260183969e-05, "loss": 0.4025, "step": 7575 }, { "epoch": 1.24, "learning_rate": 1.1351018396846255e-05, "loss": 0.3423, "step": 7576 }, { "epoch": 1.24, "learning_rate": 1.1348554533508541e-05, "loss": 0.2713, "step": 7577 }, { "epoch": 1.24, "learning_rate": 1.1346090670170827e-05, "loss": 0.3266, "step": 7578 }, { "epoch": 1.24, "learning_rate": 1.1343626806833115e-05, "loss": 0.3078, "step": 7579 }, { "epoch": 1.25, "learning_rate": 1.1341162943495402e-05, "loss": 0.3394, "step": 7580 }, { "epoch": 1.25, "learning_rate": 1.1338699080157688e-05, "loss": 0.3548, "step": 7581 }, { "epoch": 1.25, "learning_rate": 1.1336235216819974e-05, "loss": 0.3981, "step": 7582 }, { "epoch": 1.25, "learning_rate": 1.133377135348226e-05, "loss": 0.2555, "step": 7583 }, { "epoch": 1.25, "learning_rate": 1.1331307490144546e-05, "loss": 0.7782, "step": 7584 }, { "epoch": 1.25, "learning_rate": 1.1328843626806834e-05, "loss": 0.7095, "step": 7585 }, { "epoch": 1.25, "learning_rate": 1.132637976346912e-05, "loss": 0.5134, "step": 7586 }, { "epoch": 1.25, "learning_rate": 1.1323915900131406e-05, "loss": 0.309, "step": 7587 }, { "epoch": 1.25, "learning_rate": 1.1321452036793692e-05, "loss": 0.2511, "step": 7588 }, { "epoch": 1.25, "learning_rate": 1.1318988173455978e-05, "loss": 0.1754, "step": 7589 }, { "epoch": 1.25, "learning_rate": 1.1316524310118266e-05, "loss": 1.0138, "step": 7590 }, { "epoch": 1.25, "learning_rate": 1.1314060446780553e-05, "loss": 0.4079, "step": 7591 }, { "epoch": 1.25, "learning_rate": 1.131159658344284e-05, "loss": 0.2639, "step": 7592 }, { "epoch": 1.25, "learning_rate": 1.1309132720105125e-05, "loss": 0.6805, "step": 7593 }, { "epoch": 1.25, "learning_rate": 1.1306668856767411e-05, "loss": 0.3017, "step": 7594 }, { "epoch": 1.25, "learning_rate": 1.1304204993429699e-05, "loss": 0.4482, "step": 7595 }, { "epoch": 1.25, "learning_rate": 1.1301741130091985e-05, "loss": 0.4927, "step": 7596 }, { "epoch": 1.25, "learning_rate": 1.1299277266754271e-05, "loss": 0.3303, "step": 7597 }, { "epoch": 1.25, "learning_rate": 1.1296813403416557e-05, "loss": 0.4049, "step": 7598 }, { "epoch": 1.25, "learning_rate": 1.1294349540078843e-05, "loss": 0.2415, "step": 7599 }, { "epoch": 1.25, "learning_rate": 1.129188567674113e-05, "loss": 0.5666, "step": 7600 }, { "epoch": 1.25, "learning_rate": 1.1289421813403416e-05, "loss": 0.3941, "step": 7601 }, { "epoch": 1.25, "learning_rate": 1.1286957950065702e-05, "loss": 0.4657, "step": 7602 }, { "epoch": 1.25, "learning_rate": 1.128449408672799e-05, "loss": 0.2672, "step": 7603 }, { "epoch": 1.25, "learning_rate": 1.1282030223390276e-05, "loss": 0.3613, "step": 7604 }, { "epoch": 1.25, "learning_rate": 1.1279566360052564e-05, "loss": 0.5149, "step": 7605 }, { "epoch": 1.25, "learning_rate": 1.127710249671485e-05, "loss": 0.3627, "step": 7606 }, { "epoch": 1.25, "learning_rate": 1.1274638633377136e-05, "loss": 0.2966, "step": 7607 }, { "epoch": 1.25, "learning_rate": 1.1272174770039422e-05, "loss": 0.6159, "step": 7608 }, { "epoch": 1.25, "learning_rate": 1.1269710906701708e-05, "loss": 0.4224, "step": 7609 }, { "epoch": 1.25, "learning_rate": 1.1267247043363995e-05, "loss": 0.311, "step": 7610 }, { "epoch": 1.25, "learning_rate": 1.1264783180026281e-05, "loss": 0.342, "step": 7611 }, { "epoch": 1.25, "learning_rate": 1.1262319316688567e-05, "loss": 0.721, "step": 7612 }, { "epoch": 1.25, "learning_rate": 1.1259855453350853e-05, "loss": 0.4169, "step": 7613 }, { "epoch": 1.25, "learning_rate": 1.1257391590013141e-05, "loss": 0.4373, "step": 7614 }, { "epoch": 1.25, "learning_rate": 1.1254927726675429e-05, "loss": 0.4991, "step": 7615 }, { "epoch": 1.25, "learning_rate": 1.1252463863337715e-05, "loss": 0.6111, "step": 7616 }, { "epoch": 1.25, "learning_rate": 1.125e-05, "loss": 0.3366, "step": 7617 }, { "epoch": 1.25, "learning_rate": 1.1247536136662287e-05, "loss": 0.2871, "step": 7618 }, { "epoch": 1.25, "learning_rate": 1.1245072273324573e-05, "loss": 0.2142, "step": 7619 }, { "epoch": 1.25, "learning_rate": 1.124260840998686e-05, "loss": 0.2978, "step": 7620 }, { "epoch": 1.25, "learning_rate": 1.1240144546649146e-05, "loss": 0.6809, "step": 7621 }, { "epoch": 1.25, "learning_rate": 1.1237680683311432e-05, "loss": 0.6335, "step": 7622 }, { "epoch": 1.25, "learning_rate": 1.1235216819973718e-05, "loss": 0.4036, "step": 7623 }, { "epoch": 1.25, "learning_rate": 1.1232752956636004e-05, "loss": 0.4486, "step": 7624 }, { "epoch": 1.25, "learning_rate": 1.1230289093298292e-05, "loss": 0.6875, "step": 7625 }, { "epoch": 1.25, "learning_rate": 1.122782522996058e-05, "loss": 0.5945, "step": 7626 }, { "epoch": 1.25, "learning_rate": 1.1225361366622866e-05, "loss": 0.3894, "step": 7627 }, { "epoch": 1.25, "learning_rate": 1.1222897503285152e-05, "loss": 0.4561, "step": 7628 }, { "epoch": 1.25, "learning_rate": 1.1220433639947438e-05, "loss": 0.6522, "step": 7629 }, { "epoch": 1.25, "learning_rate": 1.1217969776609725e-05, "loss": 0.291, "step": 7630 }, { "epoch": 1.25, "learning_rate": 1.1215505913272011e-05, "loss": 0.3242, "step": 7631 }, { "epoch": 1.25, "learning_rate": 1.1213042049934297e-05, "loss": 0.4759, "step": 7632 }, { "epoch": 1.25, "learning_rate": 1.1210578186596583e-05, "loss": 0.7027, "step": 7633 }, { "epoch": 1.25, "learning_rate": 1.120811432325887e-05, "loss": 0.0996, "step": 7634 }, { "epoch": 1.25, "learning_rate": 1.1205650459921157e-05, "loss": 0.4844, "step": 7635 }, { "epoch": 1.25, "learning_rate": 1.1203186596583443e-05, "loss": 0.7733, "step": 7636 }, { "epoch": 1.25, "learning_rate": 1.1200722733245729e-05, "loss": 0.859, "step": 7637 }, { "epoch": 1.25, "learning_rate": 1.1198258869908017e-05, "loss": 0.5636, "step": 7638 }, { "epoch": 1.25, "learning_rate": 1.1195795006570303e-05, "loss": 0.3662, "step": 7639 }, { "epoch": 1.25, "learning_rate": 1.119333114323259e-05, "loss": 0.3178, "step": 7640 }, { "epoch": 1.26, "learning_rate": 1.1190867279894876e-05, "loss": 0.2494, "step": 7641 }, { "epoch": 1.26, "learning_rate": 1.1188403416557162e-05, "loss": 0.4406, "step": 7642 }, { "epoch": 1.26, "learning_rate": 1.1185939553219448e-05, "loss": 0.5818, "step": 7643 }, { "epoch": 1.26, "learning_rate": 1.1183475689881734e-05, "loss": 0.4135, "step": 7644 }, { "epoch": 1.26, "learning_rate": 1.1181011826544022e-05, "loss": 0.4265, "step": 7645 }, { "epoch": 1.26, "learning_rate": 1.1178547963206308e-05, "loss": 0.8713, "step": 7646 }, { "epoch": 1.26, "learning_rate": 1.1176084099868594e-05, "loss": 0.7799, "step": 7647 }, { "epoch": 1.26, "learning_rate": 1.117362023653088e-05, "loss": 0.5076, "step": 7648 }, { "epoch": 1.26, "learning_rate": 1.1171156373193166e-05, "loss": 0.8169, "step": 7649 }, { "epoch": 1.26, "learning_rate": 1.1168692509855455e-05, "loss": 0.3184, "step": 7650 }, { "epoch": 1.26, "learning_rate": 1.1166228646517741e-05, "loss": 0.5208, "step": 7651 }, { "epoch": 1.26, "learning_rate": 1.1163764783180027e-05, "loss": 0.2468, "step": 7652 }, { "epoch": 1.26, "learning_rate": 1.1161300919842313e-05, "loss": 0.7738, "step": 7653 }, { "epoch": 1.26, "learning_rate": 1.1158837056504599e-05, "loss": 0.5526, "step": 7654 }, { "epoch": 1.26, "learning_rate": 1.1156373193166887e-05, "loss": 0.4025, "step": 7655 }, { "epoch": 1.26, "learning_rate": 1.1153909329829173e-05, "loss": 0.4914, "step": 7656 }, { "epoch": 1.26, "learning_rate": 1.1151445466491459e-05, "loss": 1.4621, "step": 7657 }, { "epoch": 1.26, "learning_rate": 1.1148981603153745e-05, "loss": 0.8076, "step": 7658 }, { "epoch": 1.26, "learning_rate": 1.114651773981603e-05, "loss": 0.6321, "step": 7659 }, { "epoch": 1.26, "learning_rate": 1.1144053876478318e-05, "loss": 0.7357, "step": 7660 }, { "epoch": 1.26, "learning_rate": 1.1141590013140604e-05, "loss": 0.4904, "step": 7661 }, { "epoch": 1.26, "learning_rate": 1.1139126149802892e-05, "loss": 0.2902, "step": 7662 }, { "epoch": 1.26, "learning_rate": 1.1136662286465178e-05, "loss": 0.5286, "step": 7663 }, { "epoch": 1.26, "learning_rate": 1.1134198423127464e-05, "loss": 0.8313, "step": 7664 }, { "epoch": 1.26, "learning_rate": 1.1131734559789752e-05, "loss": 0.5087, "step": 7665 }, { "epoch": 1.26, "learning_rate": 1.1129270696452038e-05, "loss": 0.9796, "step": 7666 }, { "epoch": 1.26, "learning_rate": 1.1126806833114324e-05, "loss": 1.2884, "step": 7667 }, { "epoch": 1.26, "learning_rate": 1.112434296977661e-05, "loss": 0.2408, "step": 7668 }, { "epoch": 1.26, "learning_rate": 1.1121879106438896e-05, "loss": 0.2673, "step": 7669 }, { "epoch": 1.26, "learning_rate": 1.1119415243101183e-05, "loss": 0.5196, "step": 7670 }, { "epoch": 1.26, "learning_rate": 1.111695137976347e-05, "loss": 0.4662, "step": 7671 }, { "epoch": 1.26, "learning_rate": 1.1114487516425755e-05, "loss": 0.2984, "step": 7672 }, { "epoch": 1.26, "learning_rate": 1.1112023653088041e-05, "loss": 0.4987, "step": 7673 }, { "epoch": 1.26, "learning_rate": 1.1109559789750329e-05, "loss": 0.8647, "step": 7674 }, { "epoch": 1.26, "learning_rate": 1.1107095926412617e-05, "loss": 0.3418, "step": 7675 }, { "epoch": 1.26, "learning_rate": 1.1104632063074903e-05, "loss": 0.5921, "step": 7676 }, { "epoch": 1.26, "learning_rate": 1.1102168199737189e-05, "loss": 0.7792, "step": 7677 }, { "epoch": 1.26, "learning_rate": 1.1099704336399475e-05, "loss": 0.7432, "step": 7678 }, { "epoch": 1.26, "learning_rate": 1.109724047306176e-05, "loss": 0.3723, "step": 7679 }, { "epoch": 1.26, "learning_rate": 1.1094776609724048e-05, "loss": 0.4723, "step": 7680 }, { "epoch": 1.26, "learning_rate": 1.1092312746386334e-05, "loss": 0.1038, "step": 7681 }, { "epoch": 1.26, "learning_rate": 1.108984888304862e-05, "loss": 0.511, "step": 7682 }, { "epoch": 1.26, "learning_rate": 1.1087385019710906e-05, "loss": 0.5881, "step": 7683 }, { "epoch": 1.26, "learning_rate": 1.1084921156373192e-05, "loss": 0.8289, "step": 7684 }, { "epoch": 1.26, "learning_rate": 1.108245729303548e-05, "loss": 0.4947, "step": 7685 }, { "epoch": 1.26, "learning_rate": 1.1079993429697768e-05, "loss": 0.5354, "step": 7686 }, { "epoch": 1.26, "learning_rate": 1.1077529566360054e-05, "loss": 0.246, "step": 7687 }, { "epoch": 1.26, "learning_rate": 1.107506570302234e-05, "loss": 0.2661, "step": 7688 }, { "epoch": 1.26, "learning_rate": 1.1072601839684625e-05, "loss": 0.8914, "step": 7689 }, { "epoch": 1.26, "learning_rate": 1.1070137976346913e-05, "loss": 0.6778, "step": 7690 }, { "epoch": 1.26, "learning_rate": 1.1067674113009199e-05, "loss": 0.5484, "step": 7691 }, { "epoch": 1.26, "learning_rate": 1.1065210249671485e-05, "loss": 1.1704, "step": 7692 }, { "epoch": 1.26, "learning_rate": 1.1062746386333771e-05, "loss": 0.5187, "step": 7693 }, { "epoch": 1.26, "learning_rate": 1.1060282522996057e-05, "loss": 0.4179, "step": 7694 }, { "epoch": 1.26, "learning_rate": 1.1057818659658345e-05, "loss": 0.7256, "step": 7695 }, { "epoch": 1.26, "learning_rate": 1.105535479632063e-05, "loss": 0.2515, "step": 7696 }, { "epoch": 1.26, "learning_rate": 1.1052890932982917e-05, "loss": 0.6429, "step": 7697 }, { "epoch": 1.26, "learning_rate": 1.1050427069645204e-05, "loss": 0.5969, "step": 7698 }, { "epoch": 1.26, "learning_rate": 1.104796320630749e-05, "loss": 0.4306, "step": 7699 }, { "epoch": 1.26, "learning_rate": 1.1045499342969778e-05, "loss": 0.4312, "step": 7700 }, { "epoch": 1.26, "learning_rate": 1.1043035479632064e-05, "loss": 0.3537, "step": 7701 }, { "epoch": 1.27, "learning_rate": 1.104057161629435e-05, "loss": 0.6549, "step": 7702 }, { "epoch": 1.27, "learning_rate": 1.1038107752956636e-05, "loss": 1.0319, "step": 7703 }, { "epoch": 1.27, "learning_rate": 1.1035643889618922e-05, "loss": 0.2511, "step": 7704 }, { "epoch": 1.27, "learning_rate": 1.103318002628121e-05, "loss": 0.2, "step": 7705 }, { "epoch": 1.27, "learning_rate": 1.1030716162943496e-05, "loss": 0.1651, "step": 7706 }, { "epoch": 1.27, "learning_rate": 1.1028252299605782e-05, "loss": 0.428, "step": 7707 }, { "epoch": 1.27, "learning_rate": 1.1025788436268068e-05, "loss": 0.5974, "step": 7708 }, { "epoch": 1.27, "learning_rate": 1.1023324572930354e-05, "loss": 0.523, "step": 7709 }, { "epoch": 1.27, "learning_rate": 1.1020860709592643e-05, "loss": 0.5585, "step": 7710 }, { "epoch": 1.27, "learning_rate": 1.1018396846254929e-05, "loss": 1.1357, "step": 7711 }, { "epoch": 1.27, "learning_rate": 1.1015932982917215e-05, "loss": 0.4193, "step": 7712 }, { "epoch": 1.27, "learning_rate": 1.1013469119579501e-05, "loss": 1.1206, "step": 7713 }, { "epoch": 1.27, "learning_rate": 1.1011005256241787e-05, "loss": 0.4924, "step": 7714 }, { "epoch": 1.27, "learning_rate": 1.1008541392904075e-05, "loss": 0.6877, "step": 7715 }, { "epoch": 1.27, "learning_rate": 1.100607752956636e-05, "loss": 0.3682, "step": 7716 }, { "epoch": 1.27, "learning_rate": 1.1003613666228647e-05, "loss": 0.6186, "step": 7717 }, { "epoch": 1.27, "learning_rate": 1.1001149802890933e-05, "loss": 0.4058, "step": 7718 }, { "epoch": 1.27, "learning_rate": 1.0998685939553219e-05, "loss": 0.3142, "step": 7719 }, { "epoch": 1.27, "learning_rate": 1.0996222076215506e-05, "loss": 0.3687, "step": 7720 }, { "epoch": 1.27, "learning_rate": 1.0993758212877792e-05, "loss": 0.3823, "step": 7721 }, { "epoch": 1.27, "learning_rate": 1.099129434954008e-05, "loss": 0.7744, "step": 7722 }, { "epoch": 1.27, "learning_rate": 1.0988830486202366e-05, "loss": 0.2716, "step": 7723 }, { "epoch": 1.27, "learning_rate": 1.0986366622864652e-05, "loss": 0.5907, "step": 7724 }, { "epoch": 1.27, "learning_rate": 1.098390275952694e-05, "loss": 0.3848, "step": 7725 }, { "epoch": 1.27, "learning_rate": 1.0981438896189226e-05, "loss": 0.5439, "step": 7726 }, { "epoch": 1.27, "learning_rate": 1.0978975032851512e-05, "loss": 0.3426, "step": 7727 }, { "epoch": 1.27, "learning_rate": 1.0976511169513798e-05, "loss": 0.5861, "step": 7728 }, { "epoch": 1.27, "learning_rate": 1.0974047306176083e-05, "loss": 0.1645, "step": 7729 }, { "epoch": 1.27, "learning_rate": 1.0971583442838371e-05, "loss": 0.3124, "step": 7730 }, { "epoch": 1.27, "learning_rate": 1.0969119579500657e-05, "loss": 0.1814, "step": 7731 }, { "epoch": 1.27, "learning_rate": 1.0966655716162943e-05, "loss": 0.267, "step": 7732 }, { "epoch": 1.27, "learning_rate": 1.0964191852825229e-05, "loss": 0.662, "step": 7733 }, { "epoch": 1.27, "learning_rate": 1.0961727989487517e-05, "loss": 0.9294, "step": 7734 }, { "epoch": 1.27, "learning_rate": 1.0959264126149804e-05, "loss": 0.7006, "step": 7735 }, { "epoch": 1.27, "learning_rate": 1.095680026281209e-05, "loss": 0.8584, "step": 7736 }, { "epoch": 1.27, "learning_rate": 1.0954336399474376e-05, "loss": 0.2276, "step": 7737 }, { "epoch": 1.27, "learning_rate": 1.0951872536136662e-05, "loss": 0.7616, "step": 7738 }, { "epoch": 1.27, "learning_rate": 1.0949408672798948e-05, "loss": 0.2791, "step": 7739 }, { "epoch": 1.27, "learning_rate": 1.0946944809461236e-05, "loss": 0.3611, "step": 7740 }, { "epoch": 1.27, "learning_rate": 1.0944480946123522e-05, "loss": 0.4709, "step": 7741 }, { "epoch": 1.27, "learning_rate": 1.0942017082785808e-05, "loss": 0.4595, "step": 7742 }, { "epoch": 1.27, "learning_rate": 1.0939553219448094e-05, "loss": 1.4068, "step": 7743 }, { "epoch": 1.27, "learning_rate": 1.093708935611038e-05, "loss": 0.5159, "step": 7744 }, { "epoch": 1.27, "learning_rate": 1.0934625492772668e-05, "loss": 0.2571, "step": 7745 }, { "epoch": 1.27, "learning_rate": 1.0932161629434955e-05, "loss": 0.7241, "step": 7746 }, { "epoch": 1.27, "learning_rate": 1.0929697766097241e-05, "loss": 0.7136, "step": 7747 }, { "epoch": 1.27, "learning_rate": 1.0927233902759527e-05, "loss": 0.5238, "step": 7748 }, { "epoch": 1.27, "learning_rate": 1.0924770039421813e-05, "loss": 0.5449, "step": 7749 }, { "epoch": 1.27, "learning_rate": 1.0922306176084101e-05, "loss": 0.5166, "step": 7750 }, { "epoch": 1.27, "learning_rate": 1.0919842312746387e-05, "loss": 0.2923, "step": 7751 }, { "epoch": 1.27, "learning_rate": 1.0917378449408673e-05, "loss": 0.3788, "step": 7752 }, { "epoch": 1.27, "learning_rate": 1.0914914586070959e-05, "loss": 1.2691, "step": 7753 }, { "epoch": 1.27, "learning_rate": 1.0912450722733245e-05, "loss": 0.3851, "step": 7754 }, { "epoch": 1.27, "learning_rate": 1.0909986859395533e-05, "loss": 0.3415, "step": 7755 }, { "epoch": 1.27, "learning_rate": 1.0907522996057819e-05, "loss": 0.1734, "step": 7756 }, { "epoch": 1.27, "learning_rate": 1.0905059132720106e-05, "loss": 0.7457, "step": 7757 }, { "epoch": 1.27, "learning_rate": 1.0902595269382392e-05, "loss": 0.5034, "step": 7758 }, { "epoch": 1.27, "learning_rate": 1.0900131406044678e-05, "loss": 0.6769, "step": 7759 }, { "epoch": 1.27, "learning_rate": 1.0897667542706966e-05, "loss": 0.4966, "step": 7760 }, { "epoch": 1.27, "learning_rate": 1.0895203679369252e-05, "loss": 0.7836, "step": 7761 }, { "epoch": 1.27, "learning_rate": 1.0892739816031538e-05, "loss": 0.3188, "step": 7762 }, { "epoch": 1.28, "learning_rate": 1.0890275952693824e-05, "loss": 0.6225, "step": 7763 }, { "epoch": 1.28, "learning_rate": 1.088781208935611e-05, "loss": 0.4343, "step": 7764 }, { "epoch": 1.28, "learning_rate": 1.0885348226018398e-05, "loss": 0.5126, "step": 7765 }, { "epoch": 1.28, "learning_rate": 1.0882884362680684e-05, "loss": 0.2116, "step": 7766 }, { "epoch": 1.28, "learning_rate": 1.088042049934297e-05, "loss": 0.4578, "step": 7767 }, { "epoch": 1.28, "learning_rate": 1.0877956636005256e-05, "loss": 0.396, "step": 7768 }, { "epoch": 1.28, "learning_rate": 1.0875492772667543e-05, "loss": 0.348, "step": 7769 }, { "epoch": 1.28, "learning_rate": 1.0873028909329831e-05, "loss": 0.7176, "step": 7770 }, { "epoch": 1.28, "learning_rate": 1.0870565045992117e-05, "loss": 0.8176, "step": 7771 }, { "epoch": 1.28, "learning_rate": 1.0868101182654403e-05, "loss": 0.691, "step": 7772 }, { "epoch": 1.28, "learning_rate": 1.0865637319316689e-05, "loss": 0.2973, "step": 7773 }, { "epoch": 1.28, "learning_rate": 1.0863173455978975e-05, "loss": 0.7374, "step": 7774 }, { "epoch": 1.28, "learning_rate": 1.0860709592641263e-05, "loss": 0.3304, "step": 7775 }, { "epoch": 1.28, "learning_rate": 1.0858245729303548e-05, "loss": 0.3656, "step": 7776 }, { "epoch": 1.28, "learning_rate": 1.0855781865965834e-05, "loss": 0.4938, "step": 7777 }, { "epoch": 1.28, "learning_rate": 1.085331800262812e-05, "loss": 0.2548, "step": 7778 }, { "epoch": 1.28, "learning_rate": 1.0850854139290406e-05, "loss": 1.666, "step": 7779 }, { "epoch": 1.28, "learning_rate": 1.0848390275952694e-05, "loss": 0.2541, "step": 7780 }, { "epoch": 1.28, "learning_rate": 1.0845926412614982e-05, "loss": 0.8907, "step": 7781 }, { "epoch": 1.28, "learning_rate": 1.0843462549277268e-05, "loss": 0.4609, "step": 7782 }, { "epoch": 1.28, "learning_rate": 1.0840998685939554e-05, "loss": 0.797, "step": 7783 }, { "epoch": 1.28, "learning_rate": 1.083853482260184e-05, "loss": 0.2511, "step": 7784 }, { "epoch": 1.28, "learning_rate": 1.0836070959264127e-05, "loss": 1.2752, "step": 7785 }, { "epoch": 1.28, "learning_rate": 1.0833607095926413e-05, "loss": 0.316, "step": 7786 }, { "epoch": 1.28, "learning_rate": 1.08311432325887e-05, "loss": 0.3423, "step": 7787 }, { "epoch": 1.28, "learning_rate": 1.0828679369250985e-05, "loss": 0.7039, "step": 7788 }, { "epoch": 1.28, "learning_rate": 1.0826215505913271e-05, "loss": 0.3883, "step": 7789 }, { "epoch": 1.28, "learning_rate": 1.0823751642575559e-05, "loss": 0.4581, "step": 7790 }, { "epoch": 1.28, "learning_rate": 1.0821287779237845e-05, "loss": 0.5203, "step": 7791 }, { "epoch": 1.28, "learning_rate": 1.0818823915900131e-05, "loss": 0.5414, "step": 7792 }, { "epoch": 1.28, "learning_rate": 1.0816360052562419e-05, "loss": 0.4797, "step": 7793 }, { "epoch": 1.28, "learning_rate": 1.0813896189224705e-05, "loss": 0.7191, "step": 7794 }, { "epoch": 1.28, "learning_rate": 1.0811432325886992e-05, "loss": 0.2673, "step": 7795 }, { "epoch": 1.28, "learning_rate": 1.0808968462549278e-05, "loss": 0.4791, "step": 7796 }, { "epoch": 1.28, "learning_rate": 1.0806504599211564e-05, "loss": 0.5712, "step": 7797 }, { "epoch": 1.28, "learning_rate": 1.080404073587385e-05, "loss": 1.1357, "step": 7798 }, { "epoch": 1.28, "learning_rate": 1.0801576872536136e-05, "loss": 0.3179, "step": 7799 }, { "epoch": 1.28, "learning_rate": 1.0799113009198424e-05, "loss": 0.483, "step": 7800 }, { "epoch": 1.28, "learning_rate": 1.079664914586071e-05, "loss": 0.6658, "step": 7801 }, { "epoch": 1.28, "learning_rate": 1.0794185282522996e-05, "loss": 0.7342, "step": 7802 }, { "epoch": 1.28, "learning_rate": 1.0791721419185282e-05, "loss": 0.1418, "step": 7803 }, { "epoch": 1.28, "learning_rate": 1.0789257555847568e-05, "loss": 0.7865, "step": 7804 }, { "epoch": 1.28, "learning_rate": 1.0786793692509857e-05, "loss": 0.5034, "step": 7805 }, { "epoch": 1.28, "learning_rate": 1.0784329829172143e-05, "loss": 0.4313, "step": 7806 }, { "epoch": 1.28, "learning_rate": 1.078186596583443e-05, "loss": 0.2328, "step": 7807 }, { "epoch": 1.28, "learning_rate": 1.0779402102496715e-05, "loss": 0.4484, "step": 7808 }, { "epoch": 1.28, "learning_rate": 1.0776938239159001e-05, "loss": 0.5347, "step": 7809 }, { "epoch": 1.28, "learning_rate": 1.0774474375821289e-05, "loss": 0.2757, "step": 7810 }, { "epoch": 1.28, "learning_rate": 1.0772010512483575e-05, "loss": 0.4741, "step": 7811 }, { "epoch": 1.28, "learning_rate": 1.0769546649145861e-05, "loss": 0.3586, "step": 7812 }, { "epoch": 1.28, "learning_rate": 1.0767082785808147e-05, "loss": 0.4722, "step": 7813 }, { "epoch": 1.28, "learning_rate": 1.0764618922470433e-05, "loss": 0.494, "step": 7814 }, { "epoch": 1.28, "learning_rate": 1.076215505913272e-05, "loss": 0.5771, "step": 7815 }, { "epoch": 1.28, "learning_rate": 1.0759691195795007e-05, "loss": 0.6716, "step": 7816 }, { "epoch": 1.28, "learning_rate": 1.0757227332457294e-05, "loss": 1.246, "step": 7817 }, { "epoch": 1.28, "learning_rate": 1.075476346911958e-05, "loss": 0.5109, "step": 7818 }, { "epoch": 1.28, "learning_rate": 1.0752299605781866e-05, "loss": 0.3852, "step": 7819 }, { "epoch": 1.28, "learning_rate": 1.0749835742444154e-05, "loss": 0.9948, "step": 7820 }, { "epoch": 1.28, "learning_rate": 1.074737187910644e-05, "loss": 0.4858, "step": 7821 }, { "epoch": 1.28, "learning_rate": 1.0744908015768726e-05, "loss": 0.3848, "step": 7822 }, { "epoch": 1.28, "learning_rate": 1.0742444152431012e-05, "loss": 0.7096, "step": 7823 }, { "epoch": 1.29, "learning_rate": 1.0739980289093298e-05, "loss": 0.4092, "step": 7824 }, { "epoch": 1.29, "learning_rate": 1.0737516425755585e-05, "loss": 0.6101, "step": 7825 }, { "epoch": 1.29, "learning_rate": 1.0735052562417871e-05, "loss": 0.1557, "step": 7826 }, { "epoch": 1.29, "learning_rate": 1.0732588699080157e-05, "loss": 0.7477, "step": 7827 }, { "epoch": 1.29, "learning_rate": 1.0730124835742443e-05, "loss": 1.0988, "step": 7828 }, { "epoch": 1.29, "learning_rate": 1.0727660972404731e-05, "loss": 0.6634, "step": 7829 }, { "epoch": 1.29, "learning_rate": 1.0725197109067019e-05, "loss": 0.4509, "step": 7830 }, { "epoch": 1.29, "learning_rate": 1.0722733245729305e-05, "loss": 0.4895, "step": 7831 }, { "epoch": 1.29, "learning_rate": 1.072026938239159e-05, "loss": 0.2751, "step": 7832 }, { "epoch": 1.29, "learning_rate": 1.0717805519053877e-05, "loss": 0.4591, "step": 7833 }, { "epoch": 1.29, "learning_rate": 1.0715341655716163e-05, "loss": 0.3045, "step": 7834 }, { "epoch": 1.29, "learning_rate": 1.071287779237845e-05, "loss": 0.4502, "step": 7835 }, { "epoch": 1.29, "learning_rate": 1.0710413929040736e-05, "loss": 0.4814, "step": 7836 }, { "epoch": 1.29, "learning_rate": 1.0707950065703022e-05, "loss": 0.4514, "step": 7837 }, { "epoch": 1.29, "learning_rate": 1.0705486202365308e-05, "loss": 0.7436, "step": 7838 }, { "epoch": 1.29, "learning_rate": 1.0703022339027594e-05, "loss": 0.9377, "step": 7839 }, { "epoch": 1.29, "learning_rate": 1.0700558475689882e-05, "loss": 0.2026, "step": 7840 }, { "epoch": 1.29, "learning_rate": 1.069809461235217e-05, "loss": 0.5427, "step": 7841 }, { "epoch": 1.29, "learning_rate": 1.0695630749014456e-05, "loss": 0.8548, "step": 7842 }, { "epoch": 1.29, "learning_rate": 1.0693166885676742e-05, "loss": 0.4748, "step": 7843 }, { "epoch": 1.29, "learning_rate": 1.0690703022339028e-05, "loss": 0.5918, "step": 7844 }, { "epoch": 1.29, "learning_rate": 1.0688239159001315e-05, "loss": 0.8152, "step": 7845 }, { "epoch": 1.29, "learning_rate": 1.0685775295663601e-05, "loss": 0.6381, "step": 7846 }, { "epoch": 1.29, "learning_rate": 1.0683311432325887e-05, "loss": 0.8693, "step": 7847 }, { "epoch": 1.29, "learning_rate": 1.0680847568988173e-05, "loss": 0.5972, "step": 7848 }, { "epoch": 1.29, "learning_rate": 1.067838370565046e-05, "loss": 0.4999, "step": 7849 }, { "epoch": 1.29, "learning_rate": 1.0675919842312747e-05, "loss": 0.4331, "step": 7850 }, { "epoch": 1.29, "learning_rate": 1.0673455978975033e-05, "loss": 0.4937, "step": 7851 }, { "epoch": 1.29, "learning_rate": 1.0670992115637319e-05, "loss": 0.2229, "step": 7852 }, { "epoch": 1.29, "learning_rate": 1.0668528252299607e-05, "loss": 0.2679, "step": 7853 }, { "epoch": 1.29, "learning_rate": 1.0666064388961893e-05, "loss": 0.9289, "step": 7854 }, { "epoch": 1.29, "learning_rate": 1.066360052562418e-05, "loss": 0.5483, "step": 7855 }, { "epoch": 1.29, "learning_rate": 1.0661136662286466e-05, "loss": 0.3761, "step": 7856 }, { "epoch": 1.29, "learning_rate": 1.0658672798948752e-05, "loss": 0.6601, "step": 7857 }, { "epoch": 1.29, "learning_rate": 1.0656208935611038e-05, "loss": 0.4071, "step": 7858 }, { "epoch": 1.29, "learning_rate": 1.0653745072273324e-05, "loss": 0.3174, "step": 7859 }, { "epoch": 1.29, "learning_rate": 1.0651281208935612e-05, "loss": 0.7096, "step": 7860 }, { "epoch": 1.29, "learning_rate": 1.0648817345597898e-05, "loss": 0.5672, "step": 7861 }, { "epoch": 1.29, "learning_rate": 1.0646353482260184e-05, "loss": 0.3759, "step": 7862 }, { "epoch": 1.29, "learning_rate": 1.064388961892247e-05, "loss": 0.6994, "step": 7863 }, { "epoch": 1.29, "learning_rate": 1.0641425755584756e-05, "loss": 0.201, "step": 7864 }, { "epoch": 1.29, "learning_rate": 1.0638961892247045e-05, "loss": 0.3516, "step": 7865 }, { "epoch": 1.29, "learning_rate": 1.0636498028909331e-05, "loss": 0.7054, "step": 7866 }, { "epoch": 1.29, "learning_rate": 1.0634034165571617e-05, "loss": 0.3503, "step": 7867 }, { "epoch": 1.29, "learning_rate": 1.0631570302233903e-05, "loss": 0.8266, "step": 7868 }, { "epoch": 1.29, "learning_rate": 1.0629106438896189e-05, "loss": 1.4273, "step": 7869 }, { "epoch": 1.29, "learning_rate": 1.0626642575558477e-05, "loss": 0.5653, "step": 7870 }, { "epoch": 1.29, "learning_rate": 1.0624178712220763e-05, "loss": 0.3846, "step": 7871 }, { "epoch": 1.29, "learning_rate": 1.0621714848883049e-05, "loss": 0.4892, "step": 7872 }, { "epoch": 1.29, "learning_rate": 1.0619250985545335e-05, "loss": 0.9603, "step": 7873 }, { "epoch": 1.29, "learning_rate": 1.061678712220762e-05, "loss": 0.5585, "step": 7874 }, { "epoch": 1.29, "learning_rate": 1.0614323258869908e-05, "loss": 0.3283, "step": 7875 }, { "epoch": 1.29, "learning_rate": 1.0611859395532194e-05, "loss": 0.7539, "step": 7876 }, { "epoch": 1.29, "learning_rate": 1.0609395532194482e-05, "loss": 0.3943, "step": 7877 }, { "epoch": 1.29, "learning_rate": 1.0606931668856768e-05, "loss": 0.2776, "step": 7878 }, { "epoch": 1.29, "learning_rate": 1.0604467805519054e-05, "loss": 0.2168, "step": 7879 }, { "epoch": 1.29, "learning_rate": 1.0602003942181342e-05, "loss": 0.3751, "step": 7880 }, { "epoch": 1.29, "learning_rate": 1.0599540078843628e-05, "loss": 0.6854, "step": 7881 }, { "epoch": 1.29, "learning_rate": 1.0597076215505914e-05, "loss": 0.3384, "step": 7882 }, { "epoch": 1.29, "learning_rate": 1.05946123521682e-05, "loss": 0.317, "step": 7883 }, { "epoch": 1.3, "learning_rate": 1.0592148488830486e-05, "loss": 0.2586, "step": 7884 }, { "epoch": 1.3, "learning_rate": 1.0589684625492773e-05, "loss": 0.4976, "step": 7885 }, { "epoch": 1.3, "learning_rate": 1.058722076215506e-05, "loss": 0.3444, "step": 7886 }, { "epoch": 1.3, "learning_rate": 1.0584756898817345e-05, "loss": 0.876, "step": 7887 }, { "epoch": 1.3, "learning_rate": 1.0582293035479631e-05, "loss": 0.4397, "step": 7888 }, { "epoch": 1.3, "learning_rate": 1.0579829172141919e-05, "loss": 0.3994, "step": 7889 }, { "epoch": 1.3, "learning_rate": 1.0577365308804207e-05, "loss": 0.7356, "step": 7890 }, { "epoch": 1.3, "learning_rate": 1.0574901445466493e-05, "loss": 0.9177, "step": 7891 }, { "epoch": 1.3, "learning_rate": 1.0572437582128779e-05, "loss": 0.6749, "step": 7892 }, { "epoch": 1.3, "learning_rate": 1.0569973718791065e-05, "loss": 0.5754, "step": 7893 }, { "epoch": 1.3, "learning_rate": 1.056750985545335e-05, "loss": 0.1472, "step": 7894 }, { "epoch": 1.3, "learning_rate": 1.0565045992115638e-05, "loss": 0.6346, "step": 7895 }, { "epoch": 1.3, "learning_rate": 1.0562582128777924e-05, "loss": 0.5938, "step": 7896 }, { "epoch": 1.3, "learning_rate": 1.056011826544021e-05, "loss": 0.4272, "step": 7897 }, { "epoch": 1.3, "learning_rate": 1.0557654402102496e-05, "loss": 0.5724, "step": 7898 }, { "epoch": 1.3, "learning_rate": 1.0555190538764782e-05, "loss": 0.8639, "step": 7899 }, { "epoch": 1.3, "learning_rate": 1.055272667542707e-05, "loss": 0.6892, "step": 7900 }, { "epoch": 1.3, "learning_rate": 1.0550262812089358e-05, "loss": 0.5636, "step": 7901 }, { "epoch": 1.3, "learning_rate": 1.0547798948751644e-05, "loss": 0.4654, "step": 7902 }, { "epoch": 1.3, "learning_rate": 1.054533508541393e-05, "loss": 0.1806, "step": 7903 }, { "epoch": 1.3, "learning_rate": 1.0542871222076215e-05, "loss": 0.2196, "step": 7904 }, { "epoch": 1.3, "learning_rate": 1.0540407358738503e-05, "loss": 0.4734, "step": 7905 }, { "epoch": 1.3, "learning_rate": 1.053794349540079e-05, "loss": 0.2593, "step": 7906 }, { "epoch": 1.3, "learning_rate": 1.0535479632063075e-05, "loss": 0.6665, "step": 7907 }, { "epoch": 1.3, "learning_rate": 1.0533015768725361e-05, "loss": 0.5707, "step": 7908 }, { "epoch": 1.3, "learning_rate": 1.0530551905387647e-05, "loss": 0.5769, "step": 7909 }, { "epoch": 1.3, "learning_rate": 1.0528088042049935e-05, "loss": 0.7742, "step": 7910 }, { "epoch": 1.3, "learning_rate": 1.052562417871222e-05, "loss": 0.4665, "step": 7911 }, { "epoch": 1.3, "learning_rate": 1.0523160315374508e-05, "loss": 0.1921, "step": 7912 }, { "epoch": 1.3, "learning_rate": 1.0520696452036794e-05, "loss": 0.753, "step": 7913 }, { "epoch": 1.3, "learning_rate": 1.051823258869908e-05, "loss": 0.5256, "step": 7914 }, { "epoch": 1.3, "learning_rate": 1.0515768725361368e-05, "loss": 0.4659, "step": 7915 }, { "epoch": 1.3, "learning_rate": 1.0513304862023654e-05, "loss": 0.2503, "step": 7916 }, { "epoch": 1.3, "learning_rate": 1.051084099868594e-05, "loss": 0.836, "step": 7917 }, { "epoch": 1.3, "learning_rate": 1.0508377135348226e-05, "loss": 0.2804, "step": 7918 }, { "epoch": 1.3, "learning_rate": 1.0505913272010512e-05, "loss": 0.6443, "step": 7919 }, { "epoch": 1.3, "learning_rate": 1.05034494086728e-05, "loss": 0.5899, "step": 7920 }, { "epoch": 1.3, "learning_rate": 1.0500985545335086e-05, "loss": 0.5175, "step": 7921 }, { "epoch": 1.3, "learning_rate": 1.0498521681997372e-05, "loss": 0.3008, "step": 7922 }, { "epoch": 1.3, "learning_rate": 1.0496057818659658e-05, "loss": 0.198, "step": 7923 }, { "epoch": 1.3, "learning_rate": 1.0493593955321945e-05, "loss": 0.3424, "step": 7924 }, { "epoch": 1.3, "learning_rate": 1.0491130091984233e-05, "loss": 0.5995, "step": 7925 }, { "epoch": 1.3, "learning_rate": 1.0488666228646519e-05, "loss": 0.5651, "step": 7926 }, { "epoch": 1.3, "learning_rate": 1.0486202365308805e-05, "loss": 0.4568, "step": 7927 }, { "epoch": 1.3, "learning_rate": 1.0483738501971091e-05, "loss": 0.2867, "step": 7928 }, { "epoch": 1.3, "learning_rate": 1.0481274638633377e-05, "loss": 0.5183, "step": 7929 }, { "epoch": 1.3, "learning_rate": 1.0478810775295665e-05, "loss": 0.805, "step": 7930 }, { "epoch": 1.3, "learning_rate": 1.047634691195795e-05, "loss": 0.528, "step": 7931 }, { "epoch": 1.3, "learning_rate": 1.0473883048620237e-05, "loss": 1.1067, "step": 7932 }, { "epoch": 1.3, "learning_rate": 1.0471419185282523e-05, "loss": 0.4237, "step": 7933 }, { "epoch": 1.3, "learning_rate": 1.0468955321944809e-05, "loss": 0.3453, "step": 7934 }, { "epoch": 1.3, "learning_rate": 1.0466491458607096e-05, "loss": 0.4943, "step": 7935 }, { "epoch": 1.3, "learning_rate": 1.0464027595269384e-05, "loss": 0.1277, "step": 7936 }, { "epoch": 1.3, "learning_rate": 1.046156373193167e-05, "loss": 0.6953, "step": 7937 }, { "epoch": 1.3, "learning_rate": 1.0459099868593956e-05, "loss": 0.1759, "step": 7938 }, { "epoch": 1.3, "learning_rate": 1.0456636005256242e-05, "loss": 0.5731, "step": 7939 }, { "epoch": 1.3, "learning_rate": 1.045417214191853e-05, "loss": 0.48, "step": 7940 }, { "epoch": 1.3, "learning_rate": 1.0451708278580816e-05, "loss": 0.6926, "step": 7941 }, { "epoch": 1.3, "learning_rate": 1.0449244415243102e-05, "loss": 0.2653, "step": 7942 }, { "epoch": 1.3, "learning_rate": 1.0446780551905388e-05, "loss": 0.4929, "step": 7943 }, { "epoch": 1.3, "learning_rate": 1.0444316688567674e-05, "loss": 0.5497, "step": 7944 }, { "epoch": 1.31, "learning_rate": 1.0441852825229961e-05, "loss": 0.5818, "step": 7945 }, { "epoch": 1.31, "learning_rate": 1.0439388961892247e-05, "loss": 0.2779, "step": 7946 }, { "epoch": 1.31, "learning_rate": 1.0436925098554533e-05, "loss": 0.4837, "step": 7947 }, { "epoch": 1.31, "learning_rate": 1.043446123521682e-05, "loss": 0.169, "step": 7948 }, { "epoch": 1.31, "learning_rate": 1.0431997371879107e-05, "loss": 0.3608, "step": 7949 }, { "epoch": 1.31, "learning_rate": 1.0429533508541395e-05, "loss": 0.3675, "step": 7950 }, { "epoch": 1.31, "learning_rate": 1.042706964520368e-05, "loss": 0.5203, "step": 7951 }, { "epoch": 1.31, "learning_rate": 1.0424605781865966e-05, "loss": 0.4283, "step": 7952 }, { "epoch": 1.31, "learning_rate": 1.0422141918528252e-05, "loss": 0.4212, "step": 7953 }, { "epoch": 1.31, "learning_rate": 1.0419678055190538e-05, "loss": 0.8091, "step": 7954 }, { "epoch": 1.31, "learning_rate": 1.0417214191852826e-05, "loss": 0.6903, "step": 7955 }, { "epoch": 1.31, "learning_rate": 1.0414750328515112e-05, "loss": 0.3446, "step": 7956 }, { "epoch": 1.31, "learning_rate": 1.0412286465177398e-05, "loss": 0.3694, "step": 7957 }, { "epoch": 1.31, "learning_rate": 1.0409822601839684e-05, "loss": 0.5609, "step": 7958 }, { "epoch": 1.31, "learning_rate": 1.040735873850197e-05, "loss": 0.9097, "step": 7959 }, { "epoch": 1.31, "learning_rate": 1.040489487516426e-05, "loss": 0.3004, "step": 7960 }, { "epoch": 1.31, "learning_rate": 1.0402431011826545e-05, "loss": 0.5988, "step": 7961 }, { "epoch": 1.31, "learning_rate": 1.0399967148488831e-05, "loss": 0.579, "step": 7962 }, { "epoch": 1.31, "learning_rate": 1.0397503285151117e-05, "loss": 0.7685, "step": 7963 }, { "epoch": 1.31, "learning_rate": 1.0395039421813403e-05, "loss": 0.6331, "step": 7964 }, { "epoch": 1.31, "learning_rate": 1.0392575558475691e-05, "loss": 0.528, "step": 7965 }, { "epoch": 1.31, "learning_rate": 1.0390111695137977e-05, "loss": 0.2683, "step": 7966 }, { "epoch": 1.31, "learning_rate": 1.0387647831800263e-05, "loss": 0.4333, "step": 7967 }, { "epoch": 1.31, "learning_rate": 1.0385183968462549e-05, "loss": 0.5448, "step": 7968 }, { "epoch": 1.31, "learning_rate": 1.0382720105124835e-05, "loss": 1.1251, "step": 7969 }, { "epoch": 1.31, "learning_rate": 1.0380256241787123e-05, "loss": 0.2764, "step": 7970 }, { "epoch": 1.31, "learning_rate": 1.0377792378449409e-05, "loss": 0.4426, "step": 7971 }, { "epoch": 1.31, "learning_rate": 1.0375328515111696e-05, "loss": 0.3573, "step": 7972 }, { "epoch": 1.31, "learning_rate": 1.0372864651773982e-05, "loss": 0.3583, "step": 7973 }, { "epoch": 1.31, "learning_rate": 1.0370400788436268e-05, "loss": 0.3382, "step": 7974 }, { "epoch": 1.31, "learning_rate": 1.0367936925098556e-05, "loss": 0.4703, "step": 7975 }, { "epoch": 1.31, "learning_rate": 1.0365473061760842e-05, "loss": 0.1728, "step": 7976 }, { "epoch": 1.31, "learning_rate": 1.0363009198423128e-05, "loss": 0.6458, "step": 7977 }, { "epoch": 1.31, "learning_rate": 1.0360545335085414e-05, "loss": 1.1359, "step": 7978 }, { "epoch": 1.31, "learning_rate": 1.03580814717477e-05, "loss": 0.2593, "step": 7979 }, { "epoch": 1.31, "learning_rate": 1.0355617608409988e-05, "loss": 0.372, "step": 7980 }, { "epoch": 1.31, "learning_rate": 1.0353153745072274e-05, "loss": 0.8546, "step": 7981 }, { "epoch": 1.31, "learning_rate": 1.035068988173456e-05, "loss": 0.258, "step": 7982 }, { "epoch": 1.31, "learning_rate": 1.0348226018396846e-05, "loss": 0.7368, "step": 7983 }, { "epoch": 1.31, "learning_rate": 1.0345762155059133e-05, "loss": 0.4471, "step": 7984 }, { "epoch": 1.31, "learning_rate": 1.0343298291721421e-05, "loss": 0.1595, "step": 7985 }, { "epoch": 1.31, "learning_rate": 1.0340834428383707e-05, "loss": 0.4646, "step": 7986 }, { "epoch": 1.31, "learning_rate": 1.0338370565045993e-05, "loss": 0.5747, "step": 7987 }, { "epoch": 1.31, "learning_rate": 1.0335906701708279e-05, "loss": 0.6658, "step": 7988 }, { "epoch": 1.31, "learning_rate": 1.0333442838370565e-05, "loss": 1.0907, "step": 7989 }, { "epoch": 1.31, "learning_rate": 1.0330978975032853e-05, "loss": 0.5471, "step": 7990 }, { "epoch": 1.31, "learning_rate": 1.0328515111695139e-05, "loss": 0.6858, "step": 7991 }, { "epoch": 1.31, "learning_rate": 1.0326051248357424e-05, "loss": 0.5021, "step": 7992 }, { "epoch": 1.31, "learning_rate": 1.032358738501971e-05, "loss": 0.474, "step": 7993 }, { "epoch": 1.31, "learning_rate": 1.0321123521681996e-05, "loss": 0.4336, "step": 7994 }, { "epoch": 1.31, "learning_rate": 1.0318659658344284e-05, "loss": 0.5977, "step": 7995 }, { "epoch": 1.31, "learning_rate": 1.0316195795006572e-05, "loss": 0.2532, "step": 7996 }, { "epoch": 1.31, "learning_rate": 1.0313731931668858e-05, "loss": 0.6316, "step": 7997 }, { "epoch": 1.31, "learning_rate": 1.0311268068331144e-05, "loss": 0.936, "step": 7998 }, { "epoch": 1.31, "learning_rate": 1.030880420499343e-05, "loss": 0.2667, "step": 7999 }, { "epoch": 1.31, "learning_rate": 1.0306340341655716e-05, "loss": 0.2877, "step": 8000 }, { "epoch": 1.31, "eval_exact_match": 86.39545884578997, "eval_f1": 92.83780025116009, "step": 8000 }, { "epoch": 1.31, "learning_rate": 1.0303876478318003e-05, "loss": 0.7382, "step": 8001 }, { "epoch": 1.31, "learning_rate": 1.030141261498029e-05, "loss": 0.3722, "step": 8002 }, { "epoch": 1.31, "learning_rate": 1.0298948751642575e-05, "loss": 0.6892, "step": 8003 }, { "epoch": 1.31, "learning_rate": 1.0296484888304861e-05, "loss": 0.5069, "step": 8004 }, { "epoch": 1.31, "learning_rate": 1.0294021024967147e-05, "loss": 0.2626, "step": 8005 }, { "epoch": 1.32, "learning_rate": 1.0291557161629435e-05, "loss": 0.7171, "step": 8006 }, { "epoch": 1.32, "learning_rate": 1.0289093298291721e-05, "loss": 0.6853, "step": 8007 }, { "epoch": 1.32, "learning_rate": 1.0286629434954009e-05, "loss": 0.4423, "step": 8008 }, { "epoch": 1.32, "learning_rate": 1.0284165571616295e-05, "loss": 0.1544, "step": 8009 }, { "epoch": 1.32, "learning_rate": 1.028170170827858e-05, "loss": 0.4061, "step": 8010 }, { "epoch": 1.32, "learning_rate": 1.0279237844940868e-05, "loss": 0.502, "step": 8011 }, { "epoch": 1.32, "learning_rate": 1.0276773981603154e-05, "loss": 0.3954, "step": 8012 }, { "epoch": 1.32, "learning_rate": 1.027431011826544e-05, "loss": 0.6239, "step": 8013 }, { "epoch": 1.32, "learning_rate": 1.0271846254927726e-05, "loss": 0.2609, "step": 8014 }, { "epoch": 1.32, "learning_rate": 1.0269382391590012e-05, "loss": 0.3304, "step": 8015 }, { "epoch": 1.32, "learning_rate": 1.02669185282523e-05, "loss": 1.0589, "step": 8016 }, { "epoch": 1.32, "learning_rate": 1.0264454664914586e-05, "loss": 0.2943, "step": 8017 }, { "epoch": 1.32, "learning_rate": 1.0261990801576872e-05, "loss": 0.4947, "step": 8018 }, { "epoch": 1.32, "learning_rate": 1.0259526938239158e-05, "loss": 0.5463, "step": 8019 }, { "epoch": 1.32, "learning_rate": 1.0257063074901446e-05, "loss": 0.2905, "step": 8020 }, { "epoch": 1.32, "learning_rate": 1.0254599211563733e-05, "loss": 0.3479, "step": 8021 }, { "epoch": 1.32, "learning_rate": 1.025213534822602e-05, "loss": 0.457, "step": 8022 }, { "epoch": 1.32, "learning_rate": 1.0249671484888305e-05, "loss": 0.3843, "step": 8023 }, { "epoch": 1.32, "learning_rate": 1.0247207621550591e-05, "loss": 0.2263, "step": 8024 }, { "epoch": 1.32, "learning_rate": 1.0244743758212877e-05, "loss": 0.5194, "step": 8025 }, { "epoch": 1.32, "learning_rate": 1.0242279894875165e-05, "loss": 0.5718, "step": 8026 }, { "epoch": 1.32, "learning_rate": 1.0239816031537451e-05, "loss": 0.2166, "step": 8027 }, { "epoch": 1.32, "learning_rate": 1.0237352168199737e-05, "loss": 0.3589, "step": 8028 }, { "epoch": 1.32, "learning_rate": 1.0234888304862023e-05, "loss": 0.4124, "step": 8029 }, { "epoch": 1.32, "learning_rate": 1.0232424441524309e-05, "loss": 0.3377, "step": 8030 }, { "epoch": 1.32, "learning_rate": 1.0229960578186597e-05, "loss": 0.2721, "step": 8031 }, { "epoch": 1.32, "learning_rate": 1.0227496714848884e-05, "loss": 0.3151, "step": 8032 }, { "epoch": 1.32, "learning_rate": 1.022503285151117e-05, "loss": 0.404, "step": 8033 }, { "epoch": 1.32, "learning_rate": 1.0222568988173456e-05, "loss": 0.3006, "step": 8034 }, { "epoch": 1.32, "learning_rate": 1.0220105124835742e-05, "loss": 0.546, "step": 8035 }, { "epoch": 1.32, "learning_rate": 1.0220105124835742e-05, "loss": 0.4388, "step": 8036 }, { "epoch": 1.32, "learning_rate": 1.021764126149803e-05, "loss": 0.6892, "step": 8037 }, { "epoch": 1.32, "learning_rate": 1.0215177398160316e-05, "loss": 0.6714, "step": 8038 }, { "epoch": 1.32, "learning_rate": 1.0212713534822602e-05, "loss": 0.3915, "step": 8039 }, { "epoch": 1.32, "learning_rate": 1.0210249671484888e-05, "loss": 0.3657, "step": 8040 }, { "epoch": 1.32, "learning_rate": 1.0207785808147174e-05, "loss": 0.5023, "step": 8041 }, { "epoch": 1.32, "learning_rate": 1.0205321944809461e-05, "loss": 0.8012, "step": 8042 }, { "epoch": 1.32, "learning_rate": 1.0202858081471747e-05, "loss": 0.4836, "step": 8043 }, { "epoch": 1.32, "learning_rate": 1.0200394218134035e-05, "loss": 0.7861, "step": 8044 }, { "epoch": 1.32, "learning_rate": 1.0197930354796321e-05, "loss": 0.5734, "step": 8045 }, { "epoch": 1.32, "learning_rate": 1.0195466491458607e-05, "loss": 0.5929, "step": 8046 }, { "epoch": 1.32, "learning_rate": 1.0193002628120895e-05, "loss": 0.6172, "step": 8047 }, { "epoch": 1.32, "learning_rate": 1.019053876478318e-05, "loss": 1.287, "step": 8048 }, { "epoch": 1.32, "learning_rate": 1.0188074901445467e-05, "loss": 0.5804, "step": 8049 }, { "epoch": 1.32, "learning_rate": 1.0185611038107753e-05, "loss": 0.234, "step": 8050 }, { "epoch": 1.32, "learning_rate": 1.0183147174770039e-05, "loss": 0.5853, "step": 8051 }, { "epoch": 1.32, "learning_rate": 1.0180683311432326e-05, "loss": 0.6369, "step": 8052 }, { "epoch": 1.32, "learning_rate": 1.0178219448094612e-05, "loss": 0.8459, "step": 8053 }, { "epoch": 1.32, "learning_rate": 1.0175755584756898e-05, "loss": 0.7224, "step": 8054 }, { "epoch": 1.32, "learning_rate": 1.0173291721419184e-05, "loss": 0.518, "step": 8055 }, { "epoch": 1.32, "learning_rate": 1.0170827858081472e-05, "loss": 0.7483, "step": 8056 }, { "epoch": 1.32, "learning_rate": 1.016836399474376e-05, "loss": 0.2934, "step": 8057 }, { "epoch": 1.32, "learning_rate": 1.0165900131406046e-05, "loss": 0.6357, "step": 8058 }, { "epoch": 1.32, "learning_rate": 1.0163436268068332e-05, "loss": 0.3363, "step": 8059 }, { "epoch": 1.32, "learning_rate": 1.0160972404730618e-05, "loss": 0.3171, "step": 8060 }, { "epoch": 1.32, "learning_rate": 1.0158508541392904e-05, "loss": 0.4219, "step": 8061 }, { "epoch": 1.32, "learning_rate": 1.0156044678055191e-05, "loss": 0.4367, "step": 8062 }, { "epoch": 1.32, "learning_rate": 1.0153580814717477e-05, "loss": 0.2603, "step": 8063 }, { "epoch": 1.32, "learning_rate": 1.0151116951379763e-05, "loss": 0.7117, "step": 8064 }, { "epoch": 1.32, "learning_rate": 1.014865308804205e-05, "loss": 0.7874, "step": 8065 }, { "epoch": 1.32, "learning_rate": 1.0146189224704335e-05, "loss": 0.5252, "step": 8066 }, { "epoch": 1.33, "learning_rate": 1.0143725361366623e-05, "loss": 0.353, "step": 8067 }, { "epoch": 1.33, "learning_rate": 1.014126149802891e-05, "loss": 1.2463, "step": 8068 }, { "epoch": 1.33, "learning_rate": 1.0138797634691197e-05, "loss": 0.3796, "step": 8069 }, { "epoch": 1.33, "learning_rate": 1.0136333771353483e-05, "loss": 0.9603, "step": 8070 }, { "epoch": 1.33, "learning_rate": 1.0133869908015769e-05, "loss": 0.4152, "step": 8071 }, { "epoch": 1.33, "learning_rate": 1.0131406044678056e-05, "loss": 0.5697, "step": 8072 }, { "epoch": 1.33, "learning_rate": 1.0128942181340342e-05, "loss": 0.5395, "step": 8073 }, { "epoch": 1.33, "learning_rate": 1.0126478318002628e-05, "loss": 0.3669, "step": 8074 }, { "epoch": 1.33, "learning_rate": 1.0124014454664914e-05, "loss": 0.1557, "step": 8075 }, { "epoch": 1.33, "learning_rate": 1.01215505913272e-05, "loss": 0.2675, "step": 8076 }, { "epoch": 1.33, "learning_rate": 1.0119086727989488e-05, "loss": 0.5496, "step": 8077 }, { "epoch": 1.33, "learning_rate": 1.0116622864651774e-05, "loss": 0.5267, "step": 8078 }, { "epoch": 1.33, "learning_rate": 1.011415900131406e-05, "loss": 0.6166, "step": 8079 }, { "epoch": 1.33, "learning_rate": 1.0111695137976347e-05, "loss": 0.2492, "step": 8080 }, { "epoch": 1.33, "learning_rate": 1.0109231274638633e-05, "loss": 0.6187, "step": 8081 }, { "epoch": 1.33, "learning_rate": 1.0106767411300921e-05, "loss": 0.3356, "step": 8082 }, { "epoch": 1.33, "learning_rate": 1.0104303547963207e-05, "loss": 0.1721, "step": 8083 }, { "epoch": 1.33, "learning_rate": 1.0101839684625493e-05, "loss": 0.926, "step": 8084 }, { "epoch": 1.33, "learning_rate": 1.0099375821287779e-05, "loss": 0.3598, "step": 8085 }, { "epoch": 1.33, "learning_rate": 1.0096911957950065e-05, "loss": 0.4189, "step": 8086 }, { "epoch": 1.33, "learning_rate": 1.0094448094612353e-05, "loss": 0.4616, "step": 8087 }, { "epoch": 1.33, "learning_rate": 1.0091984231274639e-05, "loss": 0.6753, "step": 8088 }, { "epoch": 1.33, "learning_rate": 1.0089520367936925e-05, "loss": 0.1294, "step": 8089 }, { "epoch": 1.33, "learning_rate": 1.008705650459921e-05, "loss": 0.3711, "step": 8090 }, { "epoch": 1.33, "learning_rate": 1.0084592641261497e-05, "loss": 0.3893, "step": 8091 }, { "epoch": 1.33, "learning_rate": 1.0082128777923786e-05, "loss": 0.4728, "step": 8092 }, { "epoch": 1.33, "learning_rate": 1.0079664914586072e-05, "loss": 0.2787, "step": 8093 }, { "epoch": 1.33, "learning_rate": 1.0077201051248358e-05, "loss": 0.3073, "step": 8094 }, { "epoch": 1.33, "learning_rate": 1.0074737187910644e-05, "loss": 0.5085, "step": 8095 }, { "epoch": 1.33, "learning_rate": 1.007227332457293e-05, "loss": 1.2428, "step": 8096 }, { "epoch": 1.33, "learning_rate": 1.0069809461235218e-05, "loss": 0.5684, "step": 8097 }, { "epoch": 1.33, "learning_rate": 1.0067345597897504e-05, "loss": 0.5252, "step": 8098 }, { "epoch": 1.33, "learning_rate": 1.006488173455979e-05, "loss": 0.1703, "step": 8099 }, { "epoch": 1.33, "learning_rate": 1.0062417871222076e-05, "loss": 0.783, "step": 8100 }, { "epoch": 1.33, "learning_rate": 1.0059954007884362e-05, "loss": 0.3426, "step": 8101 }, { "epoch": 1.33, "learning_rate": 1.005749014454665e-05, "loss": 0.2829, "step": 8102 }, { "epoch": 1.33, "learning_rate": 1.0055026281208935e-05, "loss": 0.4333, "step": 8103 }, { "epoch": 1.33, "learning_rate": 1.0052562417871223e-05, "loss": 0.5903, "step": 8104 }, { "epoch": 1.33, "learning_rate": 1.0050098554533509e-05, "loss": 0.1847, "step": 8105 }, { "epoch": 1.33, "learning_rate": 1.0047634691195795e-05, "loss": 0.4796, "step": 8106 }, { "epoch": 1.33, "learning_rate": 1.0045170827858083e-05, "loss": 0.4123, "step": 8107 }, { "epoch": 1.33, "learning_rate": 1.0042706964520369e-05, "loss": 0.4635, "step": 8108 }, { "epoch": 1.33, "learning_rate": 1.0040243101182655e-05, "loss": 0.2146, "step": 8109 }, { "epoch": 1.33, "learning_rate": 1.003777923784494e-05, "loss": 0.6873, "step": 8110 }, { "epoch": 1.33, "learning_rate": 1.0035315374507227e-05, "loss": 0.8019, "step": 8111 }, { "epoch": 1.33, "learning_rate": 1.0032851511169514e-05, "loss": 0.267, "step": 8112 }, { "epoch": 1.33, "learning_rate": 1.00303876478318e-05, "loss": 1.2527, "step": 8113 }, { "epoch": 1.33, "learning_rate": 1.0027923784494086e-05, "loss": 0.4534, "step": 8114 }, { "epoch": 1.33, "learning_rate": 1.0025459921156372e-05, "loss": 0.8785, "step": 8115 }, { "epoch": 1.33, "learning_rate": 1.002299605781866e-05, "loss": 0.4859, "step": 8116 }, { "epoch": 1.33, "learning_rate": 1.0020532194480948e-05, "loss": 0.6597, "step": 8117 }, { "epoch": 1.33, "learning_rate": 1.0018068331143234e-05, "loss": 0.4565, "step": 8118 }, { "epoch": 1.33, "learning_rate": 1.001560446780552e-05, "loss": 0.7415, "step": 8119 }, { "epoch": 1.33, "learning_rate": 1.0013140604467806e-05, "loss": 0.2746, "step": 8120 }, { "epoch": 1.33, "learning_rate": 1.0010676741130091e-05, "loss": 0.2107, "step": 8121 }, { "epoch": 1.33, "learning_rate": 1.000821287779238e-05, "loss": 0.473, "step": 8122 }, { "epoch": 1.33, "learning_rate": 1.0005749014454665e-05, "loss": 0.3986, "step": 8123 }, { "epoch": 1.33, "learning_rate": 1.0003285151116951e-05, "loss": 0.2093, "step": 8124 }, { "epoch": 1.33, "learning_rate": 1.0000821287779237e-05, "loss": 0.7109, "step": 8125 }, { "epoch": 1.33, "learning_rate": 9.998357424441523e-06, "loss": 0.446, "step": 8126 }, { "epoch": 1.33, "learning_rate": 9.99589356110381e-06, "loss": 0.6738, "step": 8127 }, { "epoch": 1.34, "learning_rate": 9.993429697766098e-06, "loss": 0.9854, "step": 8128 }, { "epoch": 1.34, "learning_rate": 9.990965834428384e-06, "loss": 0.3455, "step": 8129 }, { "epoch": 1.34, "learning_rate": 9.98850197109067e-06, "loss": 0.2926, "step": 8130 }, { "epoch": 1.34, "learning_rate": 9.986038107752956e-06, "loss": 0.7038, "step": 8131 }, { "epoch": 1.34, "learning_rate": 9.983574244415244e-06, "loss": 0.4483, "step": 8132 }, { "epoch": 1.34, "learning_rate": 9.98111038107753e-06, "loss": 0.5765, "step": 8133 }, { "epoch": 1.34, "learning_rate": 9.978646517739816e-06, "loss": 1.1424, "step": 8134 }, { "epoch": 1.34, "learning_rate": 9.976182654402102e-06, "loss": 0.4994, "step": 8135 }, { "epoch": 1.34, "learning_rate": 9.973718791064388e-06, "loss": 0.2949, "step": 8136 }, { "epoch": 1.34, "learning_rate": 9.971254927726676e-06, "loss": 0.9139, "step": 8137 }, { "epoch": 1.34, "learning_rate": 9.968791064388962e-06, "loss": 0.2834, "step": 8138 }, { "epoch": 1.34, "learning_rate": 9.966327201051248e-06, "loss": 0.4789, "step": 8139 }, { "epoch": 1.34, "learning_rate": 9.963863337713535e-06, "loss": 0.3637, "step": 8140 }, { "epoch": 1.34, "learning_rate": 9.961399474375821e-06, "loss": 0.3734, "step": 8141 }, { "epoch": 1.34, "learning_rate": 9.958935611038109e-06, "loss": 0.4651, "step": 8142 }, { "epoch": 1.34, "learning_rate": 9.956471747700395e-06, "loss": 0.4285, "step": 8143 }, { "epoch": 1.34, "learning_rate": 9.954007884362681e-06, "loss": 0.5808, "step": 8144 }, { "epoch": 1.34, "learning_rate": 9.951544021024967e-06, "loss": 0.6628, "step": 8145 }, { "epoch": 1.34, "learning_rate": 9.949080157687253e-06, "loss": 0.381, "step": 8146 }, { "epoch": 1.34, "learning_rate": 9.94661629434954e-06, "loss": 0.6885, "step": 8147 }, { "epoch": 1.34, "learning_rate": 9.944152431011827e-06, "loss": 0.3835, "step": 8148 }, { "epoch": 1.34, "learning_rate": 9.941688567674113e-06, "loss": 0.7449, "step": 8149 }, { "epoch": 1.34, "learning_rate": 9.939224704336399e-06, "loss": 0.6242, "step": 8150 }, { "epoch": 1.34, "learning_rate": 9.936760840998685e-06, "loss": 0.8756, "step": 8151 }, { "epoch": 1.34, "learning_rate": 9.934296977660974e-06, "loss": 0.1722, "step": 8152 }, { "epoch": 1.34, "learning_rate": 9.93183311432326e-06, "loss": 0.2589, "step": 8153 }, { "epoch": 1.34, "learning_rate": 9.929369250985546e-06, "loss": 0.7928, "step": 8154 }, { "epoch": 1.34, "learning_rate": 9.926905387647832e-06, "loss": 0.5463, "step": 8155 }, { "epoch": 1.34, "learning_rate": 9.924441524310118e-06, "loss": 0.5014, "step": 8156 }, { "epoch": 1.34, "learning_rate": 9.921977660972406e-06, "loss": 0.2182, "step": 8157 }, { "epoch": 1.34, "learning_rate": 9.919513797634692e-06, "loss": 0.1764, "step": 8158 }, { "epoch": 1.34, "learning_rate": 9.917049934296978e-06, "loss": 0.5559, "step": 8159 }, { "epoch": 1.34, "learning_rate": 9.914586070959264e-06, "loss": 0.2348, "step": 8160 }, { "epoch": 1.34, "learning_rate": 9.91212220762155e-06, "loss": 0.6812, "step": 8161 }, { "epoch": 1.34, "learning_rate": 9.909658344283837e-06, "loss": 0.4278, "step": 8162 }, { "epoch": 1.34, "learning_rate": 9.907194480946123e-06, "loss": 0.5766, "step": 8163 }, { "epoch": 1.34, "learning_rate": 9.904730617608411e-06, "loss": 0.3865, "step": 8164 }, { "epoch": 1.34, "learning_rate": 9.902266754270697e-06, "loss": 0.4979, "step": 8165 }, { "epoch": 1.34, "learning_rate": 9.899802890932983e-06, "loss": 0.4862, "step": 8166 }, { "epoch": 1.34, "learning_rate": 9.89733902759527e-06, "loss": 0.5747, "step": 8167 }, { "epoch": 1.34, "learning_rate": 9.894875164257556e-06, "loss": 0.7, "step": 8168 }, { "epoch": 1.34, "learning_rate": 9.892411300919842e-06, "loss": 0.9098, "step": 8169 }, { "epoch": 1.34, "learning_rate": 9.889947437582128e-06, "loss": 0.4705, "step": 8170 }, { "epoch": 1.34, "learning_rate": 9.887483574244414e-06, "loss": 0.5186, "step": 8171 }, { "epoch": 1.34, "learning_rate": 9.885019710906702e-06, "loss": 0.6549, "step": 8172 }, { "epoch": 1.34, "learning_rate": 9.882555847568988e-06, "loss": 0.2657, "step": 8173 }, { "epoch": 1.34, "learning_rate": 9.880091984231274e-06, "loss": 0.1942, "step": 8174 }, { "epoch": 1.34, "learning_rate": 9.877628120893562e-06, "loss": 0.5155, "step": 8175 }, { "epoch": 1.34, "learning_rate": 9.875164257555848e-06, "loss": 0.4747, "step": 8176 }, { "epoch": 1.34, "learning_rate": 9.872700394218135e-06, "loss": 0.5424, "step": 8177 }, { "epoch": 1.34, "learning_rate": 9.870236530880421e-06, "loss": 0.5759, "step": 8178 }, { "epoch": 1.34, "learning_rate": 9.867772667542707e-06, "loss": 0.6915, "step": 8179 }, { "epoch": 1.34, "learning_rate": 9.865308804204993e-06, "loss": 0.5288, "step": 8180 }, { "epoch": 1.34, "learning_rate": 9.86284494086728e-06, "loss": 0.284, "step": 8181 }, { "epoch": 1.34, "learning_rate": 9.860381077529567e-06, "loss": 0.5418, "step": 8182 }, { "epoch": 1.34, "learning_rate": 9.857917214191853e-06, "loss": 0.2961, "step": 8183 }, { "epoch": 1.34, "learning_rate": 9.855453350854139e-06, "loss": 0.2222, "step": 8184 }, { "epoch": 1.34, "learning_rate": 9.852989487516425e-06, "loss": 0.5153, "step": 8185 }, { "epoch": 1.34, "learning_rate": 9.850525624178711e-06, "loss": 1.387, "step": 8186 }, { "epoch": 1.34, "learning_rate": 9.848061760841e-06, "loss": 0.4121, "step": 8187 }, { "epoch": 1.34, "learning_rate": 9.845597897503286e-06, "loss": 0.1074, "step": 8188 }, { "epoch": 1.35, "learning_rate": 9.843134034165572e-06, "loss": 0.6454, "step": 8189 }, { "epoch": 1.35, "learning_rate": 9.840670170827858e-06, "loss": 0.3974, "step": 8190 }, { "epoch": 1.35, "learning_rate": 9.838206307490144e-06, "loss": 0.1886, "step": 8191 }, { "epoch": 1.35, "learning_rate": 9.835742444152432e-06, "loss": 0.397, "step": 8192 }, { "epoch": 1.35, "learning_rate": 9.833278580814718e-06, "loss": 0.3997, "step": 8193 }, { "epoch": 1.35, "learning_rate": 9.830814717477004e-06, "loss": 0.5725, "step": 8194 }, { "epoch": 1.35, "learning_rate": 9.82835085413929e-06, "loss": 0.6667, "step": 8195 }, { "epoch": 1.35, "learning_rate": 9.825886990801576e-06, "loss": 0.9953, "step": 8196 }, { "epoch": 1.35, "learning_rate": 9.823423127463864e-06, "loss": 0.7124, "step": 8197 }, { "epoch": 1.35, "learning_rate": 9.82095926412615e-06, "loss": 0.5419, "step": 8198 }, { "epoch": 1.35, "learning_rate": 9.818495400788437e-06, "loss": 0.5171, "step": 8199 }, { "epoch": 1.35, "learning_rate": 9.816031537450723e-06, "loss": 0.4398, "step": 8200 }, { "epoch": 1.35, "learning_rate": 9.81356767411301e-06, "loss": 0.4148, "step": 8201 }, { "epoch": 1.35, "learning_rate": 9.811103810775297e-06, "loss": 0.5927, "step": 8202 }, { "epoch": 1.35, "learning_rate": 9.808639947437583e-06, "loss": 0.301, "step": 8203 }, { "epoch": 1.35, "learning_rate": 9.806176084099869e-06, "loss": 0.4227, "step": 8204 }, { "epoch": 1.35, "learning_rate": 9.803712220762155e-06, "loss": 0.4478, "step": 8205 }, { "epoch": 1.35, "learning_rate": 9.80124835742444e-06, "loss": 0.7608, "step": 8206 }, { "epoch": 1.35, "learning_rate": 9.798784494086729e-06, "loss": 0.556, "step": 8207 }, { "epoch": 1.35, "learning_rate": 9.796320630749015e-06, "loss": 0.3214, "step": 8208 }, { "epoch": 1.35, "learning_rate": 9.7938567674113e-06, "loss": 0.4411, "step": 8209 }, { "epoch": 1.35, "learning_rate": 9.791392904073586e-06, "loss": 0.1893, "step": 8210 }, { "epoch": 1.35, "learning_rate": 9.788929040735874e-06, "loss": 0.3058, "step": 8211 }, { "epoch": 1.35, "learning_rate": 9.786465177398162e-06, "loss": 0.4747, "step": 8212 }, { "epoch": 1.35, "learning_rate": 9.784001314060448e-06, "loss": 0.6339, "step": 8213 }, { "epoch": 1.35, "learning_rate": 9.781537450722734e-06, "loss": 0.2279, "step": 8214 }, { "epoch": 1.35, "learning_rate": 9.77907358738502e-06, "loss": 0.3999, "step": 8215 }, { "epoch": 1.35, "learning_rate": 9.776609724047306e-06, "loss": 0.5522, "step": 8216 }, { "epoch": 1.35, "learning_rate": 9.774145860709593e-06, "loss": 0.6455, "step": 8217 }, { "epoch": 1.35, "learning_rate": 9.77168199737188e-06, "loss": 0.3124, "step": 8218 }, { "epoch": 1.35, "learning_rate": 9.769218134034165e-06, "loss": 0.3034, "step": 8219 }, { "epoch": 1.35, "learning_rate": 9.766754270696451e-06, "loss": 0.4949, "step": 8220 }, { "epoch": 1.35, "learning_rate": 9.764290407358737e-06, "loss": 0.5034, "step": 8221 }, { "epoch": 1.35, "learning_rate": 9.761826544021025e-06, "loss": 0.7986, "step": 8222 }, { "epoch": 1.35, "learning_rate": 9.759362680683313e-06, "loss": 0.2844, "step": 8223 }, { "epoch": 1.35, "learning_rate": 9.756898817345599e-06, "loss": 0.6237, "step": 8224 }, { "epoch": 1.35, "learning_rate": 9.754434954007885e-06, "loss": 0.5062, "step": 8225 }, { "epoch": 1.35, "learning_rate": 9.75197109067017e-06, "loss": 1.2806, "step": 8226 }, { "epoch": 1.35, "learning_rate": 9.749507227332458e-06, "loss": 0.4639, "step": 8227 }, { "epoch": 1.35, "learning_rate": 9.747043363994744e-06, "loss": 0.2787, "step": 8228 }, { "epoch": 1.35, "learning_rate": 9.74457950065703e-06, "loss": 0.762, "step": 8229 }, { "epoch": 1.35, "learning_rate": 9.742115637319316e-06, "loss": 0.4531, "step": 8230 }, { "epoch": 1.35, "learning_rate": 9.739651773981602e-06, "loss": 0.2169, "step": 8231 }, { "epoch": 1.35, "learning_rate": 9.73718791064389e-06, "loss": 0.4672, "step": 8232 }, { "epoch": 1.35, "learning_rate": 9.734724047306176e-06, "loss": 0.7608, "step": 8233 }, { "epoch": 1.35, "learning_rate": 9.732260183968462e-06, "loss": 0.2145, "step": 8234 }, { "epoch": 1.35, "learning_rate": 9.72979632063075e-06, "loss": 0.705, "step": 8235 }, { "epoch": 1.35, "learning_rate": 9.727332457293036e-06, "loss": 0.8144, "step": 8236 }, { "epoch": 1.35, "learning_rate": 9.724868593955323e-06, "loss": 0.3673, "step": 8237 }, { "epoch": 1.35, "learning_rate": 9.72240473061761e-06, "loss": 0.7138, "step": 8238 }, { "epoch": 1.35, "learning_rate": 9.719940867279895e-06, "loss": 0.8179, "step": 8239 }, { "epoch": 1.35, "learning_rate": 9.717477003942181e-06, "loss": 0.7729, "step": 8240 }, { "epoch": 1.35, "learning_rate": 9.715013140604467e-06, "loss": 0.2686, "step": 8241 }, { "epoch": 1.35, "learning_rate": 9.712549277266755e-06, "loss": 0.3003, "step": 8242 }, { "epoch": 1.35, "learning_rate": 9.710085413929041e-06, "loss": 0.4976, "step": 8243 }, { "epoch": 1.35, "learning_rate": 9.707621550591327e-06, "loss": 0.5285, "step": 8244 }, { "epoch": 1.35, "learning_rate": 9.705157687253613e-06, "loss": 0.5177, "step": 8245 }, { "epoch": 1.35, "learning_rate": 9.702693823915899e-06, "loss": 0.4789, "step": 8246 }, { "epoch": 1.35, "learning_rate": 9.700229960578188e-06, "loss": 1.5944, "step": 8247 }, { "epoch": 1.35, "learning_rate": 9.697766097240474e-06, "loss": 0.5811, "step": 8248 }, { "epoch": 1.35, "learning_rate": 9.69530223390276e-06, "loss": 0.597, "step": 8249 }, { "epoch": 1.36, "learning_rate": 9.692838370565046e-06, "loss": 0.921, "step": 8250 }, { "epoch": 1.36, "learning_rate": 9.690374507227332e-06, "loss": 0.4365, "step": 8251 }, { "epoch": 1.36, "learning_rate": 9.68791064388962e-06, "loss": 0.4851, "step": 8252 }, { "epoch": 1.36, "learning_rate": 9.685446780551906e-06, "loss": 0.3641, "step": 8253 }, { "epoch": 1.36, "learning_rate": 9.682982917214192e-06, "loss": 0.9604, "step": 8254 }, { "epoch": 1.36, "learning_rate": 9.680519053876478e-06, "loss": 0.2394, "step": 8255 }, { "epoch": 1.36, "learning_rate": 9.678055190538764e-06, "loss": 0.4733, "step": 8256 }, { "epoch": 1.36, "learning_rate": 9.675591327201051e-06, "loss": 0.5631, "step": 8257 }, { "epoch": 1.36, "learning_rate": 9.673127463863337e-06, "loss": 0.9867, "step": 8258 }, { "epoch": 1.36, "learning_rate": 9.670663600525625e-06, "loss": 1.0401, "step": 8259 }, { "epoch": 1.36, "learning_rate": 9.668199737187911e-06, "loss": 0.2506, "step": 8260 }, { "epoch": 1.36, "learning_rate": 9.665735873850197e-06, "loss": 0.4014, "step": 8261 }, { "epoch": 1.36, "learning_rate": 9.663272010512485e-06, "loss": 1.0411, "step": 8262 }, { "epoch": 1.36, "learning_rate": 9.66080814717477e-06, "loss": 1.0205, "step": 8263 }, { "epoch": 1.36, "learning_rate": 9.658344283837057e-06, "loss": 0.2723, "step": 8264 }, { "epoch": 1.36, "learning_rate": 9.655880420499343e-06, "loss": 0.319, "step": 8265 }, { "epoch": 1.36, "learning_rate": 9.653416557161629e-06, "loss": 0.2437, "step": 8266 }, { "epoch": 1.36, "learning_rate": 9.650952693823916e-06, "loss": 0.0999, "step": 8267 }, { "epoch": 1.36, "learning_rate": 9.648488830486202e-06, "loss": 0.2738, "step": 8268 }, { "epoch": 1.36, "learning_rate": 9.646024967148488e-06, "loss": 0.4738, "step": 8269 }, { "epoch": 1.36, "learning_rate": 9.643561103810774e-06, "loss": 0.2974, "step": 8270 }, { "epoch": 1.36, "learning_rate": 9.641097240473062e-06, "loss": 0.5652, "step": 8271 }, { "epoch": 1.36, "learning_rate": 9.63863337713535e-06, "loss": 0.3186, "step": 8272 }, { "epoch": 1.36, "learning_rate": 9.636169513797636e-06, "loss": 0.5197, "step": 8273 }, { "epoch": 1.36, "learning_rate": 9.633705650459922e-06, "loss": 0.3706, "step": 8274 }, { "epoch": 1.36, "learning_rate": 9.631241787122208e-06, "loss": 0.5578, "step": 8275 }, { "epoch": 1.36, "learning_rate": 9.628777923784494e-06, "loss": 0.1257, "step": 8276 }, { "epoch": 1.36, "learning_rate": 9.626314060446781e-06, "loss": 0.3872, "step": 8277 }, { "epoch": 1.36, "learning_rate": 9.623850197109067e-06, "loss": 0.5662, "step": 8278 }, { "epoch": 1.36, "learning_rate": 9.621386333771353e-06, "loss": 0.4138, "step": 8279 }, { "epoch": 1.36, "learning_rate": 9.61892247043364e-06, "loss": 0.3686, "step": 8280 }, { "epoch": 1.36, "learning_rate": 9.616458607095925e-06, "loss": 0.1775, "step": 8281 }, { "epoch": 1.36, "learning_rate": 9.613994743758213e-06, "loss": 0.3754, "step": 8282 }, { "epoch": 1.36, "learning_rate": 9.6115308804205e-06, "loss": 0.5477, "step": 8283 }, { "epoch": 1.36, "learning_rate": 9.609067017082787e-06, "loss": 0.8027, "step": 8284 }, { "epoch": 1.36, "learning_rate": 9.606603153745073e-06, "loss": 0.5326, "step": 8285 }, { "epoch": 1.36, "learning_rate": 9.604139290407359e-06, "loss": 0.1934, "step": 8286 }, { "epoch": 1.36, "learning_rate": 9.601675427069646e-06, "loss": 0.482, "step": 8287 }, { "epoch": 1.36, "learning_rate": 9.599211563731932e-06, "loss": 0.3393, "step": 8288 }, { "epoch": 1.36, "learning_rate": 9.596747700394218e-06, "loss": 0.3347, "step": 8289 }, { "epoch": 1.36, "learning_rate": 9.594283837056504e-06, "loss": 0.7579, "step": 8290 }, { "epoch": 1.36, "learning_rate": 9.59181997371879e-06, "loss": 0.4101, "step": 8291 }, { "epoch": 1.36, "learning_rate": 9.589356110381078e-06, "loss": 0.2767, "step": 8292 }, { "epoch": 1.36, "learning_rate": 9.586892247043364e-06, "loss": 0.394, "step": 8293 }, { "epoch": 1.36, "learning_rate": 9.58442838370565e-06, "loss": 0.1779, "step": 8294 }, { "epoch": 1.36, "learning_rate": 9.581964520367938e-06, "loss": 0.3436, "step": 8295 }, { "epoch": 1.36, "learning_rate": 9.579500657030223e-06, "loss": 0.8174, "step": 8296 }, { "epoch": 1.36, "learning_rate": 9.577036793692511e-06, "loss": 0.3836, "step": 8297 }, { "epoch": 1.36, "learning_rate": 9.574572930354797e-06, "loss": 0.0993, "step": 8298 }, { "epoch": 1.36, "learning_rate": 9.572109067017083e-06, "loss": 0.3303, "step": 8299 }, { "epoch": 1.36, "learning_rate": 9.569645203679369e-06, "loss": 0.9142, "step": 8300 }, { "epoch": 1.36, "learning_rate": 9.567181340341655e-06, "loss": 0.6059, "step": 8301 }, { "epoch": 1.36, "learning_rate": 9.564717477003943e-06, "loss": 0.4041, "step": 8302 }, { "epoch": 1.36, "learning_rate": 9.562253613666229e-06, "loss": 0.1438, "step": 8303 }, { "epoch": 1.36, "learning_rate": 9.559789750328515e-06, "loss": 0.483, "step": 8304 }, { "epoch": 1.36, "learning_rate": 9.5573258869908e-06, "loss": 0.1812, "step": 8305 }, { "epoch": 1.36, "learning_rate": 9.554862023653088e-06, "loss": 0.4134, "step": 8306 }, { "epoch": 1.36, "learning_rate": 9.552398160315376e-06, "loss": 0.1974, "step": 8307 }, { "epoch": 1.36, "learning_rate": 9.549934296977662e-06, "loss": 0.4944, "step": 8308 }, { "epoch": 1.36, "learning_rate": 9.547470433639948e-06, "loss": 0.5092, "step": 8309 }, { "epoch": 1.36, "learning_rate": 9.545006570302234e-06, "loss": 0.6531, "step": 8310 }, { "epoch": 1.37, "learning_rate": 9.54254270696452e-06, "loss": 0.2028, "step": 8311 }, { "epoch": 1.37, "learning_rate": 9.540078843626808e-06, "loss": 0.3832, "step": 8312 }, { "epoch": 1.37, "learning_rate": 9.537614980289094e-06, "loss": 0.7742, "step": 8313 }, { "epoch": 1.37, "learning_rate": 9.53515111695138e-06, "loss": 0.1937, "step": 8314 }, { "epoch": 1.37, "learning_rate": 9.532687253613666e-06, "loss": 0.5674, "step": 8315 }, { "epoch": 1.37, "learning_rate": 9.530223390275952e-06, "loss": 0.6056, "step": 8316 }, { "epoch": 1.37, "learning_rate": 9.52775952693824e-06, "loss": 1.0352, "step": 8317 }, { "epoch": 1.37, "learning_rate": 9.525295663600527e-06, "loss": 0.4953, "step": 8318 }, { "epoch": 1.37, "learning_rate": 9.522831800262813e-06, "loss": 0.4244, "step": 8319 }, { "epoch": 1.37, "learning_rate": 9.520367936925099e-06, "loss": 0.663, "step": 8320 }, { "epoch": 1.37, "learning_rate": 9.517904073587385e-06, "loss": 0.4261, "step": 8321 }, { "epoch": 1.37, "learning_rate": 9.515440210249673e-06, "loss": 0.614, "step": 8322 }, { "epoch": 1.37, "learning_rate": 9.512976346911959e-06, "loss": 0.9644, "step": 8323 }, { "epoch": 1.37, "learning_rate": 9.510512483574245e-06, "loss": 0.3455, "step": 8324 }, { "epoch": 1.37, "learning_rate": 9.50804862023653e-06, "loss": 0.238, "step": 8325 }, { "epoch": 1.37, "learning_rate": 9.505584756898817e-06, "loss": 0.6491, "step": 8326 }, { "epoch": 1.37, "learning_rate": 9.503120893561104e-06, "loss": 0.1517, "step": 8327 }, { "epoch": 1.37, "learning_rate": 9.50065703022339e-06, "loss": 0.3354, "step": 8328 }, { "epoch": 1.37, "learning_rate": 9.498193166885676e-06, "loss": 0.7172, "step": 8329 }, { "epoch": 1.37, "learning_rate": 9.495729303547964e-06, "loss": 0.3312, "step": 8330 }, { "epoch": 1.37, "learning_rate": 9.49326544021025e-06, "loss": 0.4652, "step": 8331 }, { "epoch": 1.37, "learning_rate": 9.490801576872538e-06, "loss": 0.6953, "step": 8332 }, { "epoch": 1.37, "learning_rate": 9.488337713534824e-06, "loss": 0.6599, "step": 8333 }, { "epoch": 1.37, "learning_rate": 9.48587385019711e-06, "loss": 0.5414, "step": 8334 }, { "epoch": 1.37, "learning_rate": 9.483409986859396e-06, "loss": 0.44, "step": 8335 }, { "epoch": 1.37, "learning_rate": 9.480946123521682e-06, "loss": 1.031, "step": 8336 }, { "epoch": 1.37, "learning_rate": 9.47848226018397e-06, "loss": 0.5124, "step": 8337 }, { "epoch": 1.37, "learning_rate": 9.476018396846255e-06, "loss": 0.4161, "step": 8338 }, { "epoch": 1.37, "learning_rate": 9.473554533508541e-06, "loss": 0.3564, "step": 8339 }, { "epoch": 1.37, "learning_rate": 9.471090670170827e-06, "loss": 0.7189, "step": 8340 }, { "epoch": 1.37, "learning_rate": 9.468626806833113e-06, "loss": 0.8968, "step": 8341 }, { "epoch": 1.37, "learning_rate": 9.466162943495403e-06, "loss": 0.2792, "step": 8342 }, { "epoch": 1.37, "learning_rate": 9.463699080157688e-06, "loss": 0.3867, "step": 8343 }, { "epoch": 1.37, "learning_rate": 9.461235216819974e-06, "loss": 0.5633, "step": 8344 }, { "epoch": 1.37, "learning_rate": 9.45877135348226e-06, "loss": 0.4485, "step": 8345 }, { "epoch": 1.37, "learning_rate": 9.456307490144546e-06, "loss": 0.3264, "step": 8346 }, { "epoch": 1.37, "learning_rate": 9.453843626806834e-06, "loss": 1.0922, "step": 8347 }, { "epoch": 1.37, "learning_rate": 9.45137976346912e-06, "loss": 0.3259, "step": 8348 }, { "epoch": 1.37, "learning_rate": 9.448915900131406e-06, "loss": 0.2873, "step": 8349 }, { "epoch": 1.37, "learning_rate": 9.446452036793692e-06, "loss": 0.6702, "step": 8350 }, { "epoch": 1.37, "learning_rate": 9.443988173455978e-06, "loss": 0.6523, "step": 8351 }, { "epoch": 1.37, "learning_rate": 9.441524310118266e-06, "loss": 0.6144, "step": 8352 }, { "epoch": 1.37, "learning_rate": 9.439060446780552e-06, "loss": 0.3788, "step": 8353 }, { "epoch": 1.37, "learning_rate": 9.43659658344284e-06, "loss": 0.7728, "step": 8354 }, { "epoch": 1.37, "learning_rate": 9.434132720105125e-06, "loss": 0.3401, "step": 8355 }, { "epoch": 1.37, "learning_rate": 9.431668856767411e-06, "loss": 0.4724, "step": 8356 }, { "epoch": 1.37, "learning_rate": 9.429204993429699e-06, "loss": 0.4117, "step": 8357 }, { "epoch": 1.37, "learning_rate": 9.426741130091985e-06, "loss": 0.9094, "step": 8358 }, { "epoch": 1.37, "learning_rate": 9.424277266754271e-06, "loss": 0.3108, "step": 8359 }, { "epoch": 1.37, "learning_rate": 9.421813403416557e-06, "loss": 0.6008, "step": 8360 }, { "epoch": 1.37, "learning_rate": 9.419349540078843e-06, "loss": 0.2847, "step": 8361 }, { "epoch": 1.37, "learning_rate": 9.41688567674113e-06, "loss": 0.49, "step": 8362 }, { "epoch": 1.37, "learning_rate": 9.414421813403417e-06, "loss": 0.2659, "step": 8363 }, { "epoch": 1.37, "learning_rate": 9.411957950065703e-06, "loss": 0.3181, "step": 8364 }, { "epoch": 1.37, "learning_rate": 9.409494086727989e-06, "loss": 0.4773, "step": 8365 }, { "epoch": 1.37, "learning_rate": 9.407030223390276e-06, "loss": 0.3589, "step": 8366 }, { "epoch": 1.37, "learning_rate": 9.404566360052564e-06, "loss": 0.4337, "step": 8367 }, { "epoch": 1.37, "learning_rate": 9.40210249671485e-06, "loss": 0.5879, "step": 8368 }, { "epoch": 1.37, "learning_rate": 9.399638633377136e-06, "loss": 0.6167, "step": 8369 }, { "epoch": 1.37, "learning_rate": 9.397174770039422e-06, "loss": 0.1624, "step": 8370 }, { "epoch": 1.38, "learning_rate": 9.394710906701708e-06, "loss": 0.503, "step": 8371 }, { "epoch": 1.38, "learning_rate": 9.392247043363996e-06, "loss": 0.4905, "step": 8372 }, { "epoch": 1.38, "learning_rate": 9.389783180026282e-06, "loss": 0.575, "step": 8373 }, { "epoch": 1.38, "learning_rate": 9.387319316688568e-06, "loss": 0.7115, "step": 8374 }, { "epoch": 1.38, "learning_rate": 9.384855453350854e-06, "loss": 0.5838, "step": 8375 }, { "epoch": 1.38, "learning_rate": 9.38239159001314e-06, "loss": 0.2168, "step": 8376 }, { "epoch": 1.38, "learning_rate": 9.379927726675427e-06, "loss": 0.3113, "step": 8377 }, { "epoch": 1.38, "learning_rate": 9.377463863337715e-06, "loss": 0.9174, "step": 8378 }, { "epoch": 1.38, "learning_rate": 9.375000000000001e-06, "loss": 0.6054, "step": 8379 }, { "epoch": 1.38, "learning_rate": 9.372536136662287e-06, "loss": 0.8011, "step": 8380 }, { "epoch": 1.38, "learning_rate": 9.370072273324573e-06, "loss": 0.4941, "step": 8381 }, { "epoch": 1.38, "learning_rate": 9.36760840998686e-06, "loss": 0.3953, "step": 8382 }, { "epoch": 1.38, "learning_rate": 9.365144546649147e-06, "loss": 0.3306, "step": 8383 }, { "epoch": 1.38, "learning_rate": 9.362680683311432e-06, "loss": 0.314, "step": 8384 }, { "epoch": 1.38, "learning_rate": 9.360216819973718e-06, "loss": 0.4495, "step": 8385 }, { "epoch": 1.38, "learning_rate": 9.357752956636004e-06, "loss": 1.0872, "step": 8386 }, { "epoch": 1.38, "learning_rate": 9.355289093298292e-06, "loss": 0.4912, "step": 8387 }, { "epoch": 1.38, "learning_rate": 9.352825229960578e-06, "loss": 0.343, "step": 8388 }, { "epoch": 1.38, "learning_rate": 9.350361366622864e-06, "loss": 0.6077, "step": 8389 }, { "epoch": 1.38, "learning_rate": 9.347897503285152e-06, "loss": 0.5339, "step": 8390 }, { "epoch": 1.38, "learning_rate": 9.345433639947438e-06, "loss": 0.6441, "step": 8391 }, { "epoch": 1.38, "learning_rate": 9.342969776609725e-06, "loss": 0.3327, "step": 8392 }, { "epoch": 1.38, "learning_rate": 9.340505913272011e-06, "loss": 0.3969, "step": 8393 }, { "epoch": 1.38, "learning_rate": 9.338042049934297e-06, "loss": 0.2971, "step": 8394 }, { "epoch": 1.38, "learning_rate": 9.335578186596583e-06, "loss": 0.7139, "step": 8395 }, { "epoch": 1.38, "learning_rate": 9.33311432325887e-06, "loss": 0.3287, "step": 8396 }, { "epoch": 1.38, "learning_rate": 9.330650459921157e-06, "loss": 0.8407, "step": 8397 }, { "epoch": 1.38, "learning_rate": 9.328186596583443e-06, "loss": 0.5898, "step": 8398 }, { "epoch": 1.38, "learning_rate": 9.325722733245729e-06, "loss": 0.7241, "step": 8399 }, { "epoch": 1.38, "learning_rate": 9.323258869908015e-06, "loss": 0.3276, "step": 8400 }, { "epoch": 1.38, "learning_rate": 9.320795006570301e-06, "loss": 0.3783, "step": 8401 }, { "epoch": 1.38, "learning_rate": 9.31833114323259e-06, "loss": 0.3336, "step": 8402 }, { "epoch": 1.38, "learning_rate": 9.315867279894876e-06, "loss": 0.656, "step": 8403 }, { "epoch": 1.38, "learning_rate": 9.313403416557162e-06, "loss": 0.5987, "step": 8404 }, { "epoch": 1.38, "learning_rate": 9.310939553219448e-06, "loss": 0.2532, "step": 8405 }, { "epoch": 1.38, "learning_rate": 9.308475689881734e-06, "loss": 0.4661, "step": 8406 }, { "epoch": 1.38, "learning_rate": 9.306011826544022e-06, "loss": 0.7382, "step": 8407 }, { "epoch": 1.38, "learning_rate": 9.303547963206308e-06, "loss": 0.3652, "step": 8408 }, { "epoch": 1.38, "learning_rate": 9.301084099868594e-06, "loss": 0.4266, "step": 8409 }, { "epoch": 1.38, "learning_rate": 9.29862023653088e-06, "loss": 0.7067, "step": 8410 }, { "epoch": 1.38, "learning_rate": 9.296156373193166e-06, "loss": 0.8309, "step": 8411 }, { "epoch": 1.38, "learning_rate": 9.293692509855454e-06, "loss": 0.4244, "step": 8412 }, { "epoch": 1.38, "learning_rate": 9.29122864651774e-06, "loss": 1.0069, "step": 8413 }, { "epoch": 1.38, "learning_rate": 9.288764783180027e-06, "loss": 0.6913, "step": 8414 }, { "epoch": 1.38, "learning_rate": 9.286300919842313e-06, "loss": 0.3591, "step": 8415 }, { "epoch": 1.38, "learning_rate": 9.2838370565046e-06, "loss": 0.7126, "step": 8416 }, { "epoch": 1.38, "learning_rate": 9.281373193166887e-06, "loss": 0.4623, "step": 8417 }, { "epoch": 1.38, "learning_rate": 9.278909329829173e-06, "loss": 0.5964, "step": 8418 }, { "epoch": 1.38, "learning_rate": 9.276445466491459e-06, "loss": 0.3938, "step": 8419 }, { "epoch": 1.38, "learning_rate": 9.273981603153745e-06, "loss": 0.4142, "step": 8420 }, { "epoch": 1.38, "learning_rate": 9.271517739816031e-06, "loss": 0.476, "step": 8421 }, { "epoch": 1.38, "learning_rate": 9.269053876478319e-06, "loss": 0.7148, "step": 8422 }, { "epoch": 1.38, "learning_rate": 9.266590013140605e-06, "loss": 0.5564, "step": 8423 }, { "epoch": 1.38, "learning_rate": 9.26412614980289e-06, "loss": 0.6048, "step": 8424 }, { "epoch": 1.38, "learning_rate": 9.261662286465176e-06, "loss": 1.4919, "step": 8425 }, { "epoch": 1.38, "learning_rate": 9.259198423127464e-06, "loss": 0.2973, "step": 8426 }, { "epoch": 1.38, "learning_rate": 9.256734559789752e-06, "loss": 0.6604, "step": 8427 }, { "epoch": 1.38, "learning_rate": 9.254270696452038e-06, "loss": 0.309, "step": 8428 }, { "epoch": 1.38, "learning_rate": 9.251806833114324e-06, "loss": 0.7628, "step": 8429 }, { "epoch": 1.38, "learning_rate": 9.24934296977661e-06, "loss": 0.5155, "step": 8430 }, { "epoch": 1.38, "learning_rate": 9.246879106438896e-06, "loss": 0.2249, "step": 8431 }, { "epoch": 1.39, "learning_rate": 9.244415243101183e-06, "loss": 0.4363, "step": 8432 }, { "epoch": 1.39, "learning_rate": 9.24195137976347e-06, "loss": 0.701, "step": 8433 }, { "epoch": 1.39, "learning_rate": 9.239487516425755e-06, "loss": 0.696, "step": 8434 }, { "epoch": 1.39, "learning_rate": 9.237023653088041e-06, "loss": 0.2745, "step": 8435 }, { "epoch": 1.39, "learning_rate": 9.234559789750327e-06, "loss": 0.2761, "step": 8436 }, { "epoch": 1.39, "learning_rate": 9.232095926412615e-06, "loss": 0.2319, "step": 8437 }, { "epoch": 1.39, "learning_rate": 9.229632063074903e-06, "loss": 0.2173, "step": 8438 }, { "epoch": 1.39, "learning_rate": 9.227168199737189e-06, "loss": 0.51, "step": 8439 }, { "epoch": 1.39, "learning_rate": 9.224704336399475e-06, "loss": 0.3882, "step": 8440 }, { "epoch": 1.39, "learning_rate": 9.22224047306176e-06, "loss": 0.2492, "step": 8441 }, { "epoch": 1.39, "learning_rate": 9.219776609724048e-06, "loss": 0.5837, "step": 8442 }, { "epoch": 1.39, "learning_rate": 9.217312746386334e-06, "loss": 0.7224, "step": 8443 }, { "epoch": 1.39, "learning_rate": 9.21484888304862e-06, "loss": 1.1165, "step": 8444 }, { "epoch": 1.39, "learning_rate": 9.212385019710906e-06, "loss": 0.3579, "step": 8445 }, { "epoch": 1.39, "learning_rate": 9.209921156373192e-06, "loss": 1.6462, "step": 8446 }, { "epoch": 1.39, "learning_rate": 9.20745729303548e-06, "loss": 0.4476, "step": 8447 }, { "epoch": 1.39, "learning_rate": 9.204993429697766e-06, "loss": 0.3598, "step": 8448 }, { "epoch": 1.39, "learning_rate": 9.202529566360054e-06, "loss": 0.4106, "step": 8449 }, { "epoch": 1.39, "learning_rate": 9.20006570302234e-06, "loss": 0.3811, "step": 8450 }, { "epoch": 1.39, "learning_rate": 9.197601839684626e-06, "loss": 0.5982, "step": 8451 }, { "epoch": 1.39, "learning_rate": 9.195137976346913e-06, "loss": 0.7569, "step": 8452 }, { "epoch": 1.39, "learning_rate": 9.1926741130092e-06, "loss": 0.426, "step": 8453 }, { "epoch": 1.39, "learning_rate": 9.190210249671485e-06, "loss": 0.4307, "step": 8454 }, { "epoch": 1.39, "learning_rate": 9.187746386333771e-06, "loss": 0.4693, "step": 8455 }, { "epoch": 1.39, "learning_rate": 9.185282522996057e-06, "loss": 0.4375, "step": 8456 }, { "epoch": 1.39, "learning_rate": 9.182818659658345e-06, "loss": 0.3384, "step": 8457 }, { "epoch": 1.39, "learning_rate": 9.180354796320631e-06, "loss": 0.3097, "step": 8458 }, { "epoch": 1.39, "learning_rate": 9.177890932982917e-06, "loss": 0.5116, "step": 8459 }, { "epoch": 1.39, "learning_rate": 9.175427069645203e-06, "loss": 1.4984, "step": 8460 }, { "epoch": 1.39, "learning_rate": 9.17296320630749e-06, "loss": 0.8974, "step": 8461 }, { "epoch": 1.39, "learning_rate": 9.170499342969778e-06, "loss": 0.5494, "step": 8462 }, { "epoch": 1.39, "learning_rate": 9.168035479632064e-06, "loss": 0.6453, "step": 8463 }, { "epoch": 1.39, "learning_rate": 9.16557161629435e-06, "loss": 0.6519, "step": 8464 }, { "epoch": 1.39, "learning_rate": 9.163107752956636e-06, "loss": 1.1128, "step": 8465 }, { "epoch": 1.39, "learning_rate": 9.160643889618922e-06, "loss": 1.0582, "step": 8466 }, { "epoch": 1.39, "learning_rate": 9.15818002628121e-06, "loss": 0.5946, "step": 8467 }, { "epoch": 1.39, "learning_rate": 9.155716162943496e-06, "loss": 0.278, "step": 8468 }, { "epoch": 1.39, "learning_rate": 9.153252299605782e-06, "loss": 0.5726, "step": 8469 }, { "epoch": 1.39, "learning_rate": 9.150788436268068e-06, "loss": 0.8537, "step": 8470 }, { "epoch": 1.39, "learning_rate": 9.148324572930354e-06, "loss": 0.5335, "step": 8471 }, { "epoch": 1.39, "learning_rate": 9.145860709592641e-06, "loss": 0.6141, "step": 8472 }, { "epoch": 1.39, "learning_rate": 9.14339684625493e-06, "loss": 0.3699, "step": 8473 }, { "epoch": 1.39, "learning_rate": 9.140932982917215e-06, "loss": 0.3931, "step": 8474 }, { "epoch": 1.39, "learning_rate": 9.138469119579501e-06, "loss": 0.5237, "step": 8475 }, { "epoch": 1.39, "learning_rate": 9.136005256241787e-06, "loss": 0.4452, "step": 8476 }, { "epoch": 1.39, "learning_rate": 9.133541392904075e-06, "loss": 0.3509, "step": 8477 }, { "epoch": 1.39, "learning_rate": 9.13107752956636e-06, "loss": 0.4021, "step": 8478 }, { "epoch": 1.39, "learning_rate": 9.128613666228647e-06, "loss": 0.7703, "step": 8479 }, { "epoch": 1.39, "learning_rate": 9.126149802890933e-06, "loss": 0.3648, "step": 8480 }, { "epoch": 1.39, "learning_rate": 9.123685939553219e-06, "loss": 0.2789, "step": 8481 }, { "epoch": 1.39, "learning_rate": 9.121222076215506e-06, "loss": 0.4071, "step": 8482 }, { "epoch": 1.39, "learning_rate": 9.118758212877792e-06, "loss": 0.3809, "step": 8483 }, { "epoch": 1.39, "learning_rate": 9.116294349540078e-06, "loss": 0.4513, "step": 8484 }, { "epoch": 1.39, "learning_rate": 9.113830486202366e-06, "loss": 0.2567, "step": 8485 }, { "epoch": 1.39, "learning_rate": 9.111366622864652e-06, "loss": 0.5689, "step": 8486 }, { "epoch": 1.39, "learning_rate": 9.10890275952694e-06, "loss": 0.3986, "step": 8487 }, { "epoch": 1.39, "learning_rate": 9.106438896189226e-06, "loss": 0.439, "step": 8488 }, { "epoch": 1.39, "learning_rate": 9.103975032851512e-06, "loss": 0.4932, "step": 8489 }, { "epoch": 1.39, "learning_rate": 9.101511169513798e-06, "loss": 0.4595, "step": 8490 }, { "epoch": 1.39, "learning_rate": 9.099047306176084e-06, "loss": 0.3979, "step": 8491 }, { "epoch": 1.39, "learning_rate": 9.096583442838371e-06, "loss": 0.256, "step": 8492 }, { "epoch": 1.4, "learning_rate": 9.094119579500657e-06, "loss": 0.3037, "step": 8493 }, { "epoch": 1.4, "learning_rate": 9.091655716162943e-06, "loss": 0.3894, "step": 8494 }, { "epoch": 1.4, "learning_rate": 9.08919185282523e-06, "loss": 0.7861, "step": 8495 }, { "epoch": 1.4, "learning_rate": 9.086727989487515e-06, "loss": 0.4044, "step": 8496 }, { "epoch": 1.4, "learning_rate": 9.084264126149805e-06, "loss": 0.3775, "step": 8497 }, { "epoch": 1.4, "learning_rate": 9.08180026281209e-06, "loss": 0.19, "step": 8498 }, { "epoch": 1.4, "learning_rate": 9.079336399474377e-06, "loss": 0.2119, "step": 8499 }, { "epoch": 1.4, "learning_rate": 9.076872536136663e-06, "loss": 0.1747, "step": 8500 }, { "epoch": 1.4, "eval_exact_match": 86.87795648060549, "eval_f1": 92.90293557918207, "step": 8500 }, { "epoch": 1.4, "learning_rate": 9.074408672798949e-06, "loss": 0.3728, "step": 8501 }, { "epoch": 1.4, "learning_rate": 9.071944809461236e-06, "loss": 0.4925, "step": 8502 }, { "epoch": 1.4, "learning_rate": 9.069480946123522e-06, "loss": 0.4252, "step": 8503 }, { "epoch": 1.4, "learning_rate": 9.067017082785808e-06, "loss": 1.2692, "step": 8504 }, { "epoch": 1.4, "learning_rate": 9.064553219448094e-06, "loss": 0.87, "step": 8505 }, { "epoch": 1.4, "learning_rate": 9.06208935611038e-06, "loss": 0.6745, "step": 8506 }, { "epoch": 1.4, "learning_rate": 9.059625492772668e-06, "loss": 0.2742, "step": 8507 }, { "epoch": 1.4, "learning_rate": 9.057161629434954e-06, "loss": 0.3458, "step": 8508 }, { "epoch": 1.4, "learning_rate": 9.054697766097242e-06, "loss": 0.4103, "step": 8509 }, { "epoch": 1.4, "learning_rate": 9.052233902759528e-06, "loss": 0.438, "step": 8510 }, { "epoch": 1.4, "learning_rate": 9.049770039421814e-06, "loss": 0.1578, "step": 8511 }, { "epoch": 1.4, "learning_rate": 9.047306176084101e-06, "loss": 0.573, "step": 8512 }, { "epoch": 1.4, "learning_rate": 9.044842312746387e-06, "loss": 0.7101, "step": 8513 }, { "epoch": 1.4, "learning_rate": 9.042378449408673e-06, "loss": 0.4329, "step": 8514 }, { "epoch": 1.4, "learning_rate": 9.039914586070959e-06, "loss": 0.5482, "step": 8515 }, { "epoch": 1.4, "learning_rate": 9.037450722733245e-06, "loss": 0.5276, "step": 8516 }, { "epoch": 1.4, "learning_rate": 9.034986859395533e-06, "loss": 0.8616, "step": 8517 }, { "epoch": 1.4, "learning_rate": 9.032522996057819e-06, "loss": 0.6338, "step": 8518 }, { "epoch": 1.4, "learning_rate": 9.030059132720105e-06, "loss": 0.3149, "step": 8519 }, { "epoch": 1.4, "learning_rate": 9.02759526938239e-06, "loss": 0.5696, "step": 8520 }, { "epoch": 1.4, "learning_rate": 9.025131406044678e-06, "loss": 0.4575, "step": 8521 }, { "epoch": 1.4, "learning_rate": 9.022667542706966e-06, "loss": 0.4586, "step": 8522 }, { "epoch": 1.4, "learning_rate": 9.020203679369252e-06, "loss": 0.1966, "step": 8523 }, { "epoch": 1.4, "learning_rate": 9.017739816031538e-06, "loss": 0.4778, "step": 8524 }, { "epoch": 1.4, "learning_rate": 9.015275952693824e-06, "loss": 0.5423, "step": 8525 }, { "epoch": 1.4, "learning_rate": 9.01281208935611e-06, "loss": 0.6558, "step": 8526 }, { "epoch": 1.4, "learning_rate": 9.010348226018398e-06, "loss": 0.4125, "step": 8527 }, { "epoch": 1.4, "learning_rate": 9.007884362680684e-06, "loss": 0.554, "step": 8528 }, { "epoch": 1.4, "learning_rate": 9.00542049934297e-06, "loss": 0.5276, "step": 8529 }, { "epoch": 1.4, "learning_rate": 9.002956636005256e-06, "loss": 0.226, "step": 8530 }, { "epoch": 1.4, "learning_rate": 9.000492772667542e-06, "loss": 0.4966, "step": 8531 }, { "epoch": 1.4, "learning_rate": 8.99802890932983e-06, "loss": 0.777, "step": 8532 }, { "epoch": 1.4, "learning_rate": 8.995565045992117e-06, "loss": 0.4506, "step": 8533 }, { "epoch": 1.4, "learning_rate": 8.993101182654403e-06, "loss": 0.5531, "step": 8534 }, { "epoch": 1.4, "learning_rate": 8.990637319316689e-06, "loss": 0.3525, "step": 8535 }, { "epoch": 1.4, "learning_rate": 8.988173455978975e-06, "loss": 0.5256, "step": 8536 }, { "epoch": 1.4, "learning_rate": 8.985709592641263e-06, "loss": 0.6725, "step": 8537 }, { "epoch": 1.4, "learning_rate": 8.983245729303549e-06, "loss": 0.3466, "step": 8538 }, { "epoch": 1.4, "learning_rate": 8.980781865965835e-06, "loss": 0.5145, "step": 8539 }, { "epoch": 1.4, "learning_rate": 8.97831800262812e-06, "loss": 0.3188, "step": 8540 }, { "epoch": 1.4, "learning_rate": 8.975854139290407e-06, "loss": 0.2179, "step": 8541 }, { "epoch": 1.4, "learning_rate": 8.973390275952694e-06, "loss": 0.3686, "step": 8542 }, { "epoch": 1.4, "learning_rate": 8.97092641261498e-06, "loss": 0.628, "step": 8543 }, { "epoch": 1.4, "learning_rate": 8.968462549277266e-06, "loss": 0.6607, "step": 8544 }, { "epoch": 1.4, "learning_rate": 8.965998685939554e-06, "loss": 1.0491, "step": 8545 }, { "epoch": 1.4, "learning_rate": 8.96353482260184e-06, "loss": 0.3904, "step": 8546 }, { "epoch": 1.4, "learning_rate": 8.961070959264128e-06, "loss": 0.7358, "step": 8547 }, { "epoch": 1.4, "learning_rate": 8.958607095926414e-06, "loss": 0.2106, "step": 8548 }, { "epoch": 1.4, "learning_rate": 8.9561432325887e-06, "loss": 0.3298, "step": 8549 }, { "epoch": 1.4, "learning_rate": 8.953679369250986e-06, "loss": 0.3902, "step": 8550 }, { "epoch": 1.4, "learning_rate": 8.951215505913272e-06, "loss": 0.305, "step": 8551 }, { "epoch": 1.4, "learning_rate": 8.94875164257556e-06, "loss": 0.3552, "step": 8552 }, { "epoch": 1.4, "learning_rate": 8.946287779237845e-06, "loss": 0.4241, "step": 8553 }, { "epoch": 1.41, "learning_rate": 8.943823915900131e-06, "loss": 0.5761, "step": 8554 }, { "epoch": 1.41, "learning_rate": 8.941360052562417e-06, "loss": 0.4419, "step": 8555 }, { "epoch": 1.41, "learning_rate": 8.938896189224703e-06, "loss": 0.3753, "step": 8556 }, { "epoch": 1.41, "learning_rate": 8.936432325886993e-06, "loss": 0.5738, "step": 8557 }, { "epoch": 1.41, "learning_rate": 8.933968462549279e-06, "loss": 0.2322, "step": 8558 }, { "epoch": 1.41, "learning_rate": 8.931504599211564e-06, "loss": 0.2312, "step": 8559 }, { "epoch": 1.41, "learning_rate": 8.92904073587385e-06, "loss": 0.1853, "step": 8560 }, { "epoch": 1.41, "learning_rate": 8.926576872536136e-06, "loss": 0.4372, "step": 8561 }, { "epoch": 1.41, "learning_rate": 8.924113009198424e-06, "loss": 0.671, "step": 8562 }, { "epoch": 1.41, "learning_rate": 8.92164914586071e-06, "loss": 0.3331, "step": 8563 }, { "epoch": 1.41, "learning_rate": 8.919185282522996e-06, "loss": 0.9135, "step": 8564 }, { "epoch": 1.41, "learning_rate": 8.916721419185282e-06, "loss": 0.4788, "step": 8565 }, { "epoch": 1.41, "learning_rate": 8.914257555847568e-06, "loss": 0.3476, "step": 8566 }, { "epoch": 1.41, "learning_rate": 8.911793692509856e-06, "loss": 0.3522, "step": 8567 }, { "epoch": 1.41, "learning_rate": 8.909329829172142e-06, "loss": 0.6427, "step": 8568 }, { "epoch": 1.41, "learning_rate": 8.90686596583443e-06, "loss": 0.3314, "step": 8569 }, { "epoch": 1.41, "learning_rate": 8.904402102496715e-06, "loss": 0.2996, "step": 8570 }, { "epoch": 1.41, "learning_rate": 8.901938239159001e-06, "loss": 0.2265, "step": 8571 }, { "epoch": 1.41, "learning_rate": 8.899474375821289e-06, "loss": 0.4735, "step": 8572 }, { "epoch": 1.41, "learning_rate": 8.897010512483575e-06, "loss": 0.364, "step": 8573 }, { "epoch": 1.41, "learning_rate": 8.894546649145861e-06, "loss": 0.1409, "step": 8574 }, { "epoch": 1.41, "learning_rate": 8.892082785808147e-06, "loss": 0.5368, "step": 8575 }, { "epoch": 1.41, "learning_rate": 8.889618922470433e-06, "loss": 0.8182, "step": 8576 }, { "epoch": 1.41, "learning_rate": 8.88715505913272e-06, "loss": 0.7283, "step": 8577 }, { "epoch": 1.41, "learning_rate": 8.884691195795007e-06, "loss": 0.9247, "step": 8578 }, { "epoch": 1.41, "learning_rate": 8.882227332457293e-06, "loss": 0.3875, "step": 8579 }, { "epoch": 1.41, "learning_rate": 8.879763469119579e-06, "loss": 0.4188, "step": 8580 }, { "epoch": 1.41, "learning_rate": 8.877299605781866e-06, "loss": 0.4521, "step": 8581 }, { "epoch": 1.41, "learning_rate": 8.874835742444154e-06, "loss": 0.359, "step": 8582 }, { "epoch": 1.41, "learning_rate": 8.87237187910644e-06, "loss": 1.0429, "step": 8583 }, { "epoch": 1.41, "learning_rate": 8.869908015768726e-06, "loss": 0.5173, "step": 8584 }, { "epoch": 1.41, "learning_rate": 8.867444152431012e-06, "loss": 1.1211, "step": 8585 }, { "epoch": 1.41, "learning_rate": 8.864980289093298e-06, "loss": 0.5576, "step": 8586 }, { "epoch": 1.41, "learning_rate": 8.862516425755586e-06, "loss": 0.8716, "step": 8587 }, { "epoch": 1.41, "learning_rate": 8.860052562417872e-06, "loss": 0.2674, "step": 8588 }, { "epoch": 1.41, "learning_rate": 8.857588699080158e-06, "loss": 0.9384, "step": 8589 }, { "epoch": 1.41, "learning_rate": 8.855124835742444e-06, "loss": 0.5768, "step": 8590 }, { "epoch": 1.41, "learning_rate": 8.85266097240473e-06, "loss": 0.6525, "step": 8591 }, { "epoch": 1.41, "learning_rate": 8.850197109067017e-06, "loss": 0.4783, "step": 8592 }, { "epoch": 1.41, "learning_rate": 8.847733245729305e-06, "loss": 0.4545, "step": 8593 }, { "epoch": 1.41, "learning_rate": 8.845269382391591e-06, "loss": 0.53, "step": 8594 }, { "epoch": 1.41, "learning_rate": 8.842805519053877e-06, "loss": 0.3785, "step": 8595 }, { "epoch": 1.41, "learning_rate": 8.840341655716163e-06, "loss": 0.521, "step": 8596 }, { "epoch": 1.41, "learning_rate": 8.83787779237845e-06, "loss": 0.301, "step": 8597 }, { "epoch": 1.41, "learning_rate": 8.835413929040737e-06, "loss": 0.5102, "step": 8598 }, { "epoch": 1.41, "learning_rate": 8.832950065703023e-06, "loss": 0.6836, "step": 8599 }, { "epoch": 1.41, "learning_rate": 8.830486202365308e-06, "loss": 0.316, "step": 8600 }, { "epoch": 1.41, "learning_rate": 8.828022339027594e-06, "loss": 0.2598, "step": 8601 }, { "epoch": 1.41, "learning_rate": 8.825558475689882e-06, "loss": 0.6215, "step": 8602 }, { "epoch": 1.41, "learning_rate": 8.823094612352168e-06, "loss": 0.4599, "step": 8603 }, { "epoch": 1.41, "learning_rate": 8.820630749014456e-06, "loss": 0.2668, "step": 8604 }, { "epoch": 1.41, "learning_rate": 8.818166885676742e-06, "loss": 0.6107, "step": 8605 }, { "epoch": 1.41, "learning_rate": 8.815703022339028e-06, "loss": 0.2034, "step": 8606 }, { "epoch": 1.41, "learning_rate": 8.813239159001315e-06, "loss": 0.4186, "step": 8607 }, { "epoch": 1.41, "learning_rate": 8.810775295663601e-06, "loss": 0.6786, "step": 8608 }, { "epoch": 1.41, "learning_rate": 8.808311432325887e-06, "loss": 1.4868, "step": 8609 }, { "epoch": 1.41, "learning_rate": 8.805847568988173e-06, "loss": 0.522, "step": 8610 }, { "epoch": 1.41, "learning_rate": 8.80338370565046e-06, "loss": 0.3199, "step": 8611 }, { "epoch": 1.41, "learning_rate": 8.800919842312747e-06, "loss": 0.9659, "step": 8612 }, { "epoch": 1.41, "learning_rate": 8.798455978975033e-06, "loss": 0.2655, "step": 8613 }, { "epoch": 1.41, "learning_rate": 8.795992115637319e-06, "loss": 0.371, "step": 8614 }, { "epoch": 1.42, "learning_rate": 8.793528252299605e-06, "loss": 0.3217, "step": 8615 }, { "epoch": 1.42, "learning_rate": 8.791064388961893e-06, "loss": 0.6574, "step": 8616 }, { "epoch": 1.42, "learning_rate": 8.78860052562418e-06, "loss": 0.5387, "step": 8617 }, { "epoch": 1.42, "learning_rate": 8.786136662286466e-06, "loss": 0.2708, "step": 8618 }, { "epoch": 1.42, "learning_rate": 8.783672798948752e-06, "loss": 0.5121, "step": 8619 }, { "epoch": 1.42, "learning_rate": 8.781208935611038e-06, "loss": 0.9787, "step": 8620 }, { "epoch": 1.42, "learning_rate": 8.778745072273324e-06, "loss": 0.2485, "step": 8621 }, { "epoch": 1.42, "learning_rate": 8.776281208935612e-06, "loss": 0.549, "step": 8622 }, { "epoch": 1.42, "learning_rate": 8.773817345597898e-06, "loss": 0.7686, "step": 8623 }, { "epoch": 1.42, "learning_rate": 8.771353482260184e-06, "loss": 0.5906, "step": 8624 }, { "epoch": 1.42, "learning_rate": 8.76888961892247e-06, "loss": 0.2655, "step": 8625 }, { "epoch": 1.42, "learning_rate": 8.766425755584756e-06, "loss": 0.4866, "step": 8626 }, { "epoch": 1.42, "learning_rate": 8.763961892247044e-06, "loss": 0.6336, "step": 8627 }, { "epoch": 1.42, "learning_rate": 8.761498028909331e-06, "loss": 0.3761, "step": 8628 }, { "epoch": 1.42, "learning_rate": 8.759034165571617e-06, "loss": 0.5191, "step": 8629 }, { "epoch": 1.42, "learning_rate": 8.756570302233903e-06, "loss": 0.2735, "step": 8630 }, { "epoch": 1.42, "learning_rate": 8.75410643889619e-06, "loss": 0.5289, "step": 8631 }, { "epoch": 1.42, "learning_rate": 8.751642575558477e-06, "loss": 0.8374, "step": 8632 }, { "epoch": 1.42, "learning_rate": 8.749178712220763e-06, "loss": 0.8434, "step": 8633 }, { "epoch": 1.42, "learning_rate": 8.746714848883049e-06, "loss": 0.3145, "step": 8634 }, { "epoch": 1.42, "learning_rate": 8.744250985545335e-06, "loss": 0.2148, "step": 8635 }, { "epoch": 1.42, "learning_rate": 8.741787122207621e-06, "loss": 0.9255, "step": 8636 }, { "epoch": 1.42, "learning_rate": 8.739323258869909e-06, "loss": 0.37, "step": 8637 }, { "epoch": 1.42, "learning_rate": 8.736859395532195e-06, "loss": 0.718, "step": 8638 }, { "epoch": 1.42, "learning_rate": 8.73439553219448e-06, "loss": 0.5827, "step": 8639 }, { "epoch": 1.42, "learning_rate": 8.731931668856768e-06, "loss": 0.7673, "step": 8640 }, { "epoch": 1.42, "learning_rate": 8.729467805519054e-06, "loss": 0.6253, "step": 8641 }, { "epoch": 1.42, "learning_rate": 8.727003942181342e-06, "loss": 0.3352, "step": 8642 }, { "epoch": 1.42, "learning_rate": 8.724540078843628e-06, "loss": 0.3812, "step": 8643 }, { "epoch": 1.42, "learning_rate": 8.722076215505914e-06, "loss": 0.5805, "step": 8644 }, { "epoch": 1.42, "learning_rate": 8.7196123521682e-06, "loss": 0.3694, "step": 8645 }, { "epoch": 1.42, "learning_rate": 8.717148488830486e-06, "loss": 0.6253, "step": 8646 }, { "epoch": 1.42, "learning_rate": 8.714684625492773e-06, "loss": 0.3645, "step": 8647 }, { "epoch": 1.42, "learning_rate": 8.71222076215506e-06, "loss": 0.5148, "step": 8648 }, { "epoch": 1.42, "learning_rate": 8.709756898817345e-06, "loss": 0.6079, "step": 8649 }, { "epoch": 1.42, "learning_rate": 8.707293035479631e-06, "loss": 0.477, "step": 8650 }, { "epoch": 1.42, "learning_rate": 8.704829172141917e-06, "loss": 0.4135, "step": 8651 }, { "epoch": 1.42, "learning_rate": 8.702365308804207e-06, "loss": 0.9209, "step": 8652 }, { "epoch": 1.42, "learning_rate": 8.699901445466493e-06, "loss": 0.3581, "step": 8653 }, { "epoch": 1.42, "learning_rate": 8.697437582128779e-06, "loss": 0.5678, "step": 8654 }, { "epoch": 1.42, "learning_rate": 8.694973718791065e-06, "loss": 0.1944, "step": 8655 }, { "epoch": 1.42, "learning_rate": 8.69250985545335e-06, "loss": 0.3674, "step": 8656 }, { "epoch": 1.42, "learning_rate": 8.690045992115638e-06, "loss": 1.142, "step": 8657 }, { "epoch": 1.42, "learning_rate": 8.687582128777924e-06, "loss": 0.7556, "step": 8658 }, { "epoch": 1.42, "learning_rate": 8.68511826544021e-06, "loss": 0.1831, "step": 8659 }, { "epoch": 1.42, "learning_rate": 8.682654402102496e-06, "loss": 1.0692, "step": 8660 }, { "epoch": 1.42, "learning_rate": 8.680190538764782e-06, "loss": 0.582, "step": 8661 }, { "epoch": 1.42, "learning_rate": 8.67772667542707e-06, "loss": 0.8027, "step": 8662 }, { "epoch": 1.42, "learning_rate": 8.675262812089356e-06, "loss": 0.6138, "step": 8663 }, { "epoch": 1.42, "learning_rate": 8.672798948751644e-06, "loss": 0.4956, "step": 8664 }, { "epoch": 1.42, "learning_rate": 8.67033508541393e-06, "loss": 0.5558, "step": 8665 }, { "epoch": 1.42, "learning_rate": 8.667871222076216e-06, "loss": 0.4588, "step": 8666 }, { "epoch": 1.42, "learning_rate": 8.665407358738503e-06, "loss": 0.8875, "step": 8667 }, { "epoch": 1.42, "learning_rate": 8.66294349540079e-06, "loss": 0.6304, "step": 8668 }, { "epoch": 1.42, "learning_rate": 8.660479632063075e-06, "loss": 0.7571, "step": 8669 }, { "epoch": 1.42, "learning_rate": 8.658015768725361e-06, "loss": 0.3221, "step": 8670 }, { "epoch": 1.42, "learning_rate": 8.655551905387647e-06, "loss": 0.2436, "step": 8671 }, { "epoch": 1.42, "learning_rate": 8.653088042049935e-06, "loss": 0.3559, "step": 8672 }, { "epoch": 1.42, "learning_rate": 8.650624178712221e-06, "loss": 0.341, "step": 8673 }, { "epoch": 1.42, "learning_rate": 8.648160315374507e-06, "loss": 0.3608, "step": 8674 }, { "epoch": 1.42, "learning_rate": 8.645696452036793e-06, "loss": 0.8738, "step": 8675 }, { "epoch": 1.43, "learning_rate": 8.64323258869908e-06, "loss": 0.309, "step": 8676 }, { "epoch": 1.43, "learning_rate": 8.640768725361368e-06, "loss": 0.7501, "step": 8677 }, { "epoch": 1.43, "learning_rate": 8.638304862023654e-06, "loss": 0.2762, "step": 8678 }, { "epoch": 1.43, "learning_rate": 8.63584099868594e-06, "loss": 0.5064, "step": 8679 }, { "epoch": 1.43, "learning_rate": 8.633377135348226e-06, "loss": 0.3926, "step": 8680 }, { "epoch": 1.43, "learning_rate": 8.630913272010512e-06, "loss": 0.7244, "step": 8681 }, { "epoch": 1.43, "learning_rate": 8.6284494086728e-06, "loss": 0.4273, "step": 8682 }, { "epoch": 1.43, "learning_rate": 8.625985545335086e-06, "loss": 0.7982, "step": 8683 }, { "epoch": 1.43, "learning_rate": 8.623521681997372e-06, "loss": 0.2804, "step": 8684 }, { "epoch": 1.43, "learning_rate": 8.621057818659658e-06, "loss": 0.5065, "step": 8685 }, { "epoch": 1.43, "learning_rate": 8.618593955321944e-06, "loss": 1.1816, "step": 8686 }, { "epoch": 1.43, "learning_rate": 8.616130091984231e-06, "loss": 0.2066, "step": 8687 }, { "epoch": 1.43, "learning_rate": 8.61366622864652e-06, "loss": 0.5139, "step": 8688 }, { "epoch": 1.43, "learning_rate": 8.611202365308805e-06, "loss": 0.3593, "step": 8689 }, { "epoch": 1.43, "learning_rate": 8.608738501971091e-06, "loss": 0.2948, "step": 8690 }, { "epoch": 1.43, "learning_rate": 8.606274638633377e-06, "loss": 0.3817, "step": 8691 }, { "epoch": 1.43, "learning_rate": 8.603810775295665e-06, "loss": 0.3641, "step": 8692 }, { "epoch": 1.43, "learning_rate": 8.60134691195795e-06, "loss": 0.5191, "step": 8693 }, { "epoch": 1.43, "learning_rate": 8.598883048620237e-06, "loss": 0.7496, "step": 8694 }, { "epoch": 1.43, "learning_rate": 8.596419185282523e-06, "loss": 0.318, "step": 8695 }, { "epoch": 1.43, "learning_rate": 8.593955321944809e-06, "loss": 0.2703, "step": 8696 }, { "epoch": 1.43, "learning_rate": 8.591491458607096e-06, "loss": 0.4446, "step": 8697 }, { "epoch": 1.43, "learning_rate": 8.589027595269382e-06, "loss": 0.4412, "step": 8698 }, { "epoch": 1.43, "learning_rate": 8.586563731931668e-06, "loss": 0.2775, "step": 8699 }, { "epoch": 1.43, "learning_rate": 8.584099868593956e-06, "loss": 0.7248, "step": 8700 }, { "epoch": 1.43, "learning_rate": 8.581636005256242e-06, "loss": 0.5801, "step": 8701 }, { "epoch": 1.43, "learning_rate": 8.57917214191853e-06, "loss": 0.5173, "step": 8702 }, { "epoch": 1.43, "learning_rate": 8.576708278580816e-06, "loss": 0.8422, "step": 8703 }, { "epoch": 1.43, "learning_rate": 8.574244415243102e-06, "loss": 0.3494, "step": 8704 }, { "epoch": 1.43, "learning_rate": 8.571780551905388e-06, "loss": 0.5128, "step": 8705 }, { "epoch": 1.43, "learning_rate": 8.569316688567674e-06, "loss": 0.8002, "step": 8706 }, { "epoch": 1.43, "learning_rate": 8.566852825229961e-06, "loss": 0.561, "step": 8707 }, { "epoch": 1.43, "learning_rate": 8.564388961892247e-06, "loss": 0.4031, "step": 8708 }, { "epoch": 1.43, "learning_rate": 8.561925098554533e-06, "loss": 0.211, "step": 8709 }, { "epoch": 1.43, "learning_rate": 8.55946123521682e-06, "loss": 0.238, "step": 8710 }, { "epoch": 1.43, "learning_rate": 8.556997371879105e-06, "loss": 0.3411, "step": 8711 }, { "epoch": 1.43, "learning_rate": 8.554533508541395e-06, "loss": 0.8585, "step": 8712 }, { "epoch": 1.43, "learning_rate": 8.55206964520368e-06, "loss": 0.545, "step": 8713 }, { "epoch": 1.43, "learning_rate": 8.549605781865967e-06, "loss": 0.4143, "step": 8714 }, { "epoch": 1.43, "learning_rate": 8.547141918528253e-06, "loss": 0.281, "step": 8715 }, { "epoch": 1.43, "learning_rate": 8.544678055190539e-06, "loss": 0.5828, "step": 8716 }, { "epoch": 1.43, "learning_rate": 8.542214191852826e-06, "loss": 0.3544, "step": 8717 }, { "epoch": 1.43, "learning_rate": 8.539750328515112e-06, "loss": 0.3259, "step": 8718 }, { "epoch": 1.43, "learning_rate": 8.537286465177398e-06, "loss": 0.3216, "step": 8719 }, { "epoch": 1.43, "learning_rate": 8.534822601839684e-06, "loss": 0.4651, "step": 8720 }, { "epoch": 1.43, "learning_rate": 8.53235873850197e-06, "loss": 0.3846, "step": 8721 }, { "epoch": 1.43, "learning_rate": 8.529894875164258e-06, "loss": 0.3204, "step": 8722 }, { "epoch": 1.43, "learning_rate": 8.527431011826544e-06, "loss": 0.3197, "step": 8723 }, { "epoch": 1.43, "learning_rate": 8.524967148488832e-06, "loss": 1.3765, "step": 8724 }, { "epoch": 1.43, "learning_rate": 8.522503285151118e-06, "loss": 0.2931, "step": 8725 }, { "epoch": 1.43, "learning_rate": 8.520039421813404e-06, "loss": 0.4402, "step": 8726 }, { "epoch": 1.43, "learning_rate": 8.517575558475691e-06, "loss": 0.6501, "step": 8727 }, { "epoch": 1.43, "learning_rate": 8.515111695137977e-06, "loss": 0.5249, "step": 8728 }, { "epoch": 1.43, "learning_rate": 8.512647831800263e-06, "loss": 0.6908, "step": 8729 }, { "epoch": 1.43, "learning_rate": 8.51018396846255e-06, "loss": 0.2992, "step": 8730 }, { "epoch": 1.43, "learning_rate": 8.507720105124835e-06, "loss": 0.4271, "step": 8731 }, { "epoch": 1.43, "learning_rate": 8.505256241787123e-06, "loss": 0.5928, "step": 8732 }, { "epoch": 1.43, "learning_rate": 8.502792378449409e-06, "loss": 0.7585, "step": 8733 }, { "epoch": 1.43, "learning_rate": 8.500328515111695e-06, "loss": 0.4953, "step": 8734 }, { "epoch": 1.43, "learning_rate": 8.497864651773982e-06, "loss": 0.3105, "step": 8735 }, { "epoch": 1.43, "learning_rate": 8.495400788436268e-06, "loss": 0.538, "step": 8736 }, { "epoch": 1.44, "learning_rate": 8.492936925098556e-06, "loss": 0.7884, "step": 8737 }, { "epoch": 1.44, "learning_rate": 8.490473061760842e-06, "loss": 0.2126, "step": 8738 }, { "epoch": 1.44, "learning_rate": 8.488009198423128e-06, "loss": 0.904, "step": 8739 }, { "epoch": 1.44, "learning_rate": 8.485545335085414e-06, "loss": 0.2225, "step": 8740 }, { "epoch": 1.44, "learning_rate": 8.4830814717477e-06, "loss": 0.2532, "step": 8741 }, { "epoch": 1.44, "learning_rate": 8.480617608409988e-06, "loss": 0.3903, "step": 8742 }, { "epoch": 1.44, "learning_rate": 8.478153745072274e-06, "loss": 0.5086, "step": 8743 }, { "epoch": 1.44, "learning_rate": 8.47568988173456e-06, "loss": 0.6266, "step": 8744 }, { "epoch": 1.44, "learning_rate": 8.473226018396846e-06, "loss": 0.6612, "step": 8745 }, { "epoch": 1.44, "learning_rate": 8.470762155059132e-06, "loss": 0.4553, "step": 8746 }, { "epoch": 1.44, "learning_rate": 8.468298291721421e-06, "loss": 0.7348, "step": 8747 }, { "epoch": 1.44, "learning_rate": 8.465834428383707e-06, "loss": 0.2984, "step": 8748 }, { "epoch": 1.44, "learning_rate": 8.463370565045993e-06, "loss": 0.5347, "step": 8749 }, { "epoch": 1.44, "learning_rate": 8.460906701708279e-06, "loss": 0.3547, "step": 8750 }, { "epoch": 1.44, "learning_rate": 8.458442838370565e-06, "loss": 0.6964, "step": 8751 }, { "epoch": 1.44, "learning_rate": 8.455978975032853e-06, "loss": 0.3239, "step": 8752 }, { "epoch": 1.44, "learning_rate": 8.453515111695139e-06, "loss": 0.3473, "step": 8753 }, { "epoch": 1.44, "learning_rate": 8.451051248357425e-06, "loss": 0.6679, "step": 8754 }, { "epoch": 1.44, "learning_rate": 8.44858738501971e-06, "loss": 0.1818, "step": 8755 }, { "epoch": 1.44, "learning_rate": 8.446123521681997e-06, "loss": 0.7164, "step": 8756 }, { "epoch": 1.44, "learning_rate": 8.443659658344284e-06, "loss": 0.3605, "step": 8757 }, { "epoch": 1.44, "learning_rate": 8.44119579500657e-06, "loss": 0.6097, "step": 8758 }, { "epoch": 1.44, "learning_rate": 8.438731931668858e-06, "loss": 0.6543, "step": 8759 }, { "epoch": 1.44, "learning_rate": 8.436268068331144e-06, "loss": 0.4319, "step": 8760 }, { "epoch": 1.44, "learning_rate": 8.43380420499343e-06, "loss": 0.4603, "step": 8761 }, { "epoch": 1.44, "learning_rate": 8.431340341655716e-06, "loss": 0.3427, "step": 8762 }, { "epoch": 1.44, "learning_rate": 8.428876478318004e-06, "loss": 0.5225, "step": 8763 }, { "epoch": 1.44, "learning_rate": 8.42641261498029e-06, "loss": 0.637, "step": 8764 }, { "epoch": 1.44, "learning_rate": 8.423948751642576e-06, "loss": 0.5012, "step": 8765 }, { "epoch": 1.44, "learning_rate": 8.421484888304862e-06, "loss": 0.4095, "step": 8766 }, { "epoch": 1.44, "learning_rate": 8.419021024967148e-06, "loss": 0.637, "step": 8767 }, { "epoch": 1.44, "learning_rate": 8.416557161629435e-06, "loss": 1.2871, "step": 8768 }, { "epoch": 1.44, "learning_rate": 8.414093298291721e-06, "loss": 0.573, "step": 8769 }, { "epoch": 1.44, "learning_rate": 8.411629434954007e-06, "loss": 0.5515, "step": 8770 }, { "epoch": 1.44, "learning_rate": 8.409165571616295e-06, "loss": 0.6595, "step": 8771 }, { "epoch": 1.44, "learning_rate": 8.40670170827858e-06, "loss": 0.6048, "step": 8772 }, { "epoch": 1.44, "learning_rate": 8.404237844940869e-06, "loss": 0.3161, "step": 8773 }, { "epoch": 1.44, "learning_rate": 8.401773981603155e-06, "loss": 0.647, "step": 8774 }, { "epoch": 1.44, "learning_rate": 8.39931011826544e-06, "loss": 0.3657, "step": 8775 }, { "epoch": 1.44, "learning_rate": 8.396846254927726e-06, "loss": 0.5393, "step": 8776 }, { "epoch": 1.44, "learning_rate": 8.394382391590012e-06, "loss": 0.6513, "step": 8777 }, { "epoch": 1.44, "learning_rate": 8.3919185282523e-06, "loss": 0.5103, "step": 8778 }, { "epoch": 1.44, "learning_rate": 8.389454664914586e-06, "loss": 0.7537, "step": 8779 }, { "epoch": 1.44, "learning_rate": 8.386990801576872e-06, "loss": 0.9855, "step": 8780 }, { "epoch": 1.44, "learning_rate": 8.384526938239158e-06, "loss": 0.5936, "step": 8781 }, { "epoch": 1.44, "learning_rate": 8.382063074901444e-06, "loss": 0.4397, "step": 8782 }, { "epoch": 1.44, "learning_rate": 8.379599211563733e-06, "loss": 0.1822, "step": 8783 }, { "epoch": 1.44, "learning_rate": 8.37713534822602e-06, "loss": 0.3211, "step": 8784 }, { "epoch": 1.44, "learning_rate": 8.374671484888305e-06, "loss": 0.4315, "step": 8785 }, { "epoch": 1.44, "learning_rate": 8.372207621550591e-06, "loss": 0.7475, "step": 8786 }, { "epoch": 1.44, "learning_rate": 8.369743758212877e-06, "loss": 0.6037, "step": 8787 }, { "epoch": 1.44, "learning_rate": 8.367279894875165e-06, "loss": 0.4434, "step": 8788 }, { "epoch": 1.44, "learning_rate": 8.364816031537451e-06, "loss": 0.205, "step": 8789 }, { "epoch": 1.44, "learning_rate": 8.362352168199737e-06, "loss": 0.4378, "step": 8790 }, { "epoch": 1.44, "learning_rate": 8.359888304862023e-06, "loss": 0.4039, "step": 8791 }, { "epoch": 1.44, "learning_rate": 8.357424441524309e-06, "loss": 0.3814, "step": 8792 }, { "epoch": 1.44, "learning_rate": 8.354960578186597e-06, "loss": 0.7383, "step": 8793 }, { "epoch": 1.44, "learning_rate": 8.352496714848883e-06, "loss": 0.5747, "step": 8794 }, { "epoch": 1.44, "learning_rate": 8.35003285151117e-06, "loss": 0.4414, "step": 8795 }, { "epoch": 1.44, "learning_rate": 8.347568988173456e-06, "loss": 0.8751, "step": 8796 }, { "epoch": 1.44, "learning_rate": 8.345105124835742e-06, "loss": 0.4904, "step": 8797 }, { "epoch": 1.45, "learning_rate": 8.34264126149803e-06, "loss": 0.4203, "step": 8798 }, { "epoch": 1.45, "learning_rate": 8.340177398160316e-06, "loss": 0.2413, "step": 8799 }, { "epoch": 1.45, "learning_rate": 8.337713534822602e-06, "loss": 0.1888, "step": 8800 }, { "epoch": 1.45, "learning_rate": 8.335249671484888e-06, "loss": 0.4025, "step": 8801 }, { "epoch": 1.45, "learning_rate": 8.332785808147174e-06, "loss": 0.6348, "step": 8802 }, { "epoch": 1.45, "learning_rate": 8.330321944809462e-06, "loss": 0.9837, "step": 8803 }, { "epoch": 1.45, "learning_rate": 8.327858081471748e-06, "loss": 0.4497, "step": 8804 }, { "epoch": 1.45, "learning_rate": 8.325394218134034e-06, "loss": 0.8165, "step": 8805 }, { "epoch": 1.45, "learning_rate": 8.32293035479632e-06, "loss": 0.8701, "step": 8806 }, { "epoch": 1.45, "learning_rate": 8.320466491458607e-06, "loss": 0.5171, "step": 8807 }, { "epoch": 1.45, "learning_rate": 8.318002628120895e-06, "loss": 0.6197, "step": 8808 }, { "epoch": 1.45, "learning_rate": 8.315538764783181e-06, "loss": 0.2136, "step": 8809 }, { "epoch": 1.45, "learning_rate": 8.313074901445467e-06, "loss": 0.4563, "step": 8810 }, { "epoch": 1.45, "learning_rate": 8.310611038107753e-06, "loss": 0.7019, "step": 8811 }, { "epoch": 1.45, "learning_rate": 8.308147174770039e-06, "loss": 0.6029, "step": 8812 }, { "epoch": 1.45, "learning_rate": 8.305683311432327e-06, "loss": 0.4644, "step": 8813 }, { "epoch": 1.45, "learning_rate": 8.303219448094613e-06, "loss": 0.7811, "step": 8814 }, { "epoch": 1.45, "learning_rate": 8.300755584756899e-06, "loss": 0.3215, "step": 8815 }, { "epoch": 1.45, "learning_rate": 8.298291721419184e-06, "loss": 0.6593, "step": 8816 }, { "epoch": 1.45, "learning_rate": 8.29582785808147e-06, "loss": 0.6133, "step": 8817 }, { "epoch": 1.45, "learning_rate": 8.293363994743758e-06, "loss": 0.6005, "step": 8818 }, { "epoch": 1.45, "learning_rate": 8.290900131406046e-06, "loss": 0.3286, "step": 8819 }, { "epoch": 1.45, "learning_rate": 8.288436268068332e-06, "loss": 0.2766, "step": 8820 }, { "epoch": 1.45, "learning_rate": 8.285972404730618e-06, "loss": 0.3498, "step": 8821 }, { "epoch": 1.45, "learning_rate": 8.283508541392904e-06, "loss": 0.2364, "step": 8822 }, { "epoch": 1.45, "learning_rate": 8.281044678055191e-06, "loss": 1.0239, "step": 8823 }, { "epoch": 1.45, "learning_rate": 8.278580814717477e-06, "loss": 0.3997, "step": 8824 }, { "epoch": 1.45, "learning_rate": 8.276116951379763e-06, "loss": 0.3934, "step": 8825 }, { "epoch": 1.45, "learning_rate": 8.27365308804205e-06, "loss": 0.8318, "step": 8826 }, { "epoch": 1.45, "learning_rate": 8.271189224704335e-06, "loss": 0.5029, "step": 8827 }, { "epoch": 1.45, "learning_rate": 8.268725361366623e-06, "loss": 0.4875, "step": 8828 }, { "epoch": 1.45, "learning_rate": 8.266261498028909e-06, "loss": 0.6364, "step": 8829 }, { "epoch": 1.45, "learning_rate": 8.263797634691195e-06, "loss": 0.2666, "step": 8830 }, { "epoch": 1.45, "learning_rate": 8.261333771353483e-06, "loss": 0.474, "step": 8831 }, { "epoch": 1.45, "learning_rate": 8.258869908015769e-06, "loss": 0.8381, "step": 8832 }, { "epoch": 1.45, "learning_rate": 8.256406044678056e-06, "loss": 0.961, "step": 8833 }, { "epoch": 1.45, "learning_rate": 8.253942181340342e-06, "loss": 0.1703, "step": 8834 }, { "epoch": 1.45, "learning_rate": 8.251478318002628e-06, "loss": 0.7408, "step": 8835 }, { "epoch": 1.45, "learning_rate": 8.249014454664914e-06, "loss": 0.7942, "step": 8836 }, { "epoch": 1.45, "learning_rate": 8.2465505913272e-06, "loss": 0.8637, "step": 8837 }, { "epoch": 1.45, "learning_rate": 8.244086727989488e-06, "loss": 0.2105, "step": 8838 }, { "epoch": 1.45, "learning_rate": 8.241622864651774e-06, "loss": 0.7232, "step": 8839 }, { "epoch": 1.45, "learning_rate": 8.23915900131406e-06, "loss": 0.9876, "step": 8840 }, { "epoch": 1.45, "learning_rate": 8.236695137976346e-06, "loss": 0.3893, "step": 8841 }, { "epoch": 1.45, "learning_rate": 8.234231274638632e-06, "loss": 0.8192, "step": 8842 }, { "epoch": 1.45, "learning_rate": 8.231767411300921e-06, "loss": 0.6052, "step": 8843 }, { "epoch": 1.45, "learning_rate": 8.229303547963207e-06, "loss": 0.6211, "step": 8844 }, { "epoch": 1.45, "learning_rate": 8.226839684625493e-06, "loss": 0.2769, "step": 8845 }, { "epoch": 1.45, "learning_rate": 8.22437582128778e-06, "loss": 0.4274, "step": 8846 }, { "epoch": 1.45, "learning_rate": 8.221911957950065e-06, "loss": 0.2001, "step": 8847 }, { "epoch": 1.45, "learning_rate": 8.219448094612353e-06, "loss": 0.8139, "step": 8848 }, { "epoch": 1.45, "learning_rate": 8.216984231274639e-06, "loss": 0.3454, "step": 8849 }, { "epoch": 1.45, "learning_rate": 8.214520367936925e-06, "loss": 0.5577, "step": 8850 }, { "epoch": 1.45, "learning_rate": 8.212056504599211e-06, "loss": 0.1523, "step": 8851 }, { "epoch": 1.45, "learning_rate": 8.209592641261497e-06, "loss": 0.4575, "step": 8852 }, { "epoch": 1.45, "learning_rate": 8.207128777923785e-06, "loss": 0.8985, "step": 8853 }, { "epoch": 1.45, "learning_rate": 8.20466491458607e-06, "loss": 0.4102, "step": 8854 }, { "epoch": 1.45, "learning_rate": 8.202201051248358e-06, "loss": 0.9016, "step": 8855 }, { "epoch": 1.45, "learning_rate": 8.199737187910644e-06, "loss": 1.06, "step": 8856 }, { "epoch": 1.45, "learning_rate": 8.19727332457293e-06, "loss": 0.5147, "step": 8857 }, { "epoch": 1.45, "learning_rate": 8.194809461235218e-06, "loss": 0.3313, "step": 8858 }, { "epoch": 1.46, "learning_rate": 8.192345597897504e-06, "loss": 0.2707, "step": 8859 }, { "epoch": 1.46, "learning_rate": 8.18988173455979e-06, "loss": 0.1955, "step": 8860 }, { "epoch": 1.46, "learning_rate": 8.187417871222076e-06, "loss": 0.5554, "step": 8861 }, { "epoch": 1.46, "learning_rate": 8.184954007884362e-06, "loss": 0.3342, "step": 8862 }, { "epoch": 1.46, "learning_rate": 8.18249014454665e-06, "loss": 0.6346, "step": 8863 }, { "epoch": 1.46, "learning_rate": 8.180026281208935e-06, "loss": 0.3481, "step": 8864 }, { "epoch": 1.46, "learning_rate": 8.177562417871221e-06, "loss": 0.7018, "step": 8865 }, { "epoch": 1.46, "learning_rate": 8.175098554533509e-06, "loss": 0.5113, "step": 8866 }, { "epoch": 1.46, "learning_rate": 8.172634691195795e-06, "loss": 0.6164, "step": 8867 }, { "epoch": 1.46, "learning_rate": 8.170170827858083e-06, "loss": 0.6464, "step": 8868 }, { "epoch": 1.46, "learning_rate": 8.167706964520369e-06, "loss": 0.3079, "step": 8869 }, { "epoch": 1.46, "learning_rate": 8.165243101182655e-06, "loss": 0.5643, "step": 8870 }, { "epoch": 1.46, "learning_rate": 8.16277923784494e-06, "loss": 0.3553, "step": 8871 }, { "epoch": 1.46, "learning_rate": 8.160315374507227e-06, "loss": 0.4961, "step": 8872 }, { "epoch": 1.46, "learning_rate": 8.157851511169514e-06, "loss": 0.2833, "step": 8873 }, { "epoch": 1.46, "learning_rate": 8.1553876478318e-06, "loss": 0.4089, "step": 8874 }, { "epoch": 1.46, "learning_rate": 8.152923784494086e-06, "loss": 0.2463, "step": 8875 }, { "epoch": 1.46, "learning_rate": 8.150459921156372e-06, "loss": 0.6636, "step": 8876 }, { "epoch": 1.46, "learning_rate": 8.147996057818658e-06, "loss": 0.7815, "step": 8877 }, { "epoch": 1.46, "learning_rate": 8.145532194480948e-06, "loss": 0.5923, "step": 8878 }, { "epoch": 1.46, "learning_rate": 8.143068331143234e-06, "loss": 0.0935, "step": 8879 }, { "epoch": 1.46, "learning_rate": 8.14060446780552e-06, "loss": 0.2518, "step": 8880 }, { "epoch": 1.46, "learning_rate": 8.138140604467806e-06, "loss": 0.3472, "step": 8881 }, { "epoch": 1.46, "learning_rate": 8.135676741130092e-06, "loss": 0.5268, "step": 8882 }, { "epoch": 1.46, "learning_rate": 8.13321287779238e-06, "loss": 0.7611, "step": 8883 }, { "epoch": 1.46, "learning_rate": 8.130749014454665e-06, "loss": 0.3707, "step": 8884 }, { "epoch": 1.46, "learning_rate": 8.128285151116951e-06, "loss": 0.3556, "step": 8885 }, { "epoch": 1.46, "learning_rate": 8.125821287779237e-06, "loss": 0.2921, "step": 8886 }, { "epoch": 1.46, "learning_rate": 8.123357424441523e-06, "loss": 0.3548, "step": 8887 }, { "epoch": 1.46, "learning_rate": 8.120893561103811e-06, "loss": 0.6219, "step": 8888 }, { "epoch": 1.46, "learning_rate": 8.118429697766097e-06, "loss": 0.5407, "step": 8889 }, { "epoch": 1.46, "learning_rate": 8.115965834428385e-06, "loss": 0.6977, "step": 8890 }, { "epoch": 1.46, "learning_rate": 8.11350197109067e-06, "loss": 0.3857, "step": 8891 }, { "epoch": 1.46, "learning_rate": 8.111038107752957e-06, "loss": 0.501, "step": 8892 }, { "epoch": 1.46, "learning_rate": 8.108574244415244e-06, "loss": 0.7974, "step": 8893 }, { "epoch": 1.46, "learning_rate": 8.10611038107753e-06, "loss": 0.8147, "step": 8894 }, { "epoch": 1.46, "learning_rate": 8.103646517739816e-06, "loss": 0.4475, "step": 8895 }, { "epoch": 1.46, "learning_rate": 8.101182654402102e-06, "loss": 0.5832, "step": 8896 }, { "epoch": 1.46, "learning_rate": 8.098718791064388e-06, "loss": 0.2933, "step": 8897 }, { "epoch": 1.46, "learning_rate": 8.096254927726676e-06, "loss": 0.3122, "step": 8898 }, { "epoch": 1.46, "learning_rate": 8.093791064388962e-06, "loss": 0.1871, "step": 8899 }, { "epoch": 1.46, "learning_rate": 8.091327201051248e-06, "loss": 0.3546, "step": 8900 }, { "epoch": 1.46, "learning_rate": 8.088863337713534e-06, "loss": 0.5906, "step": 8901 }, { "epoch": 1.46, "learning_rate": 8.086399474375822e-06, "loss": 0.2961, "step": 8902 }, { "epoch": 1.46, "learning_rate": 8.08393561103811e-06, "loss": 0.4395, "step": 8903 }, { "epoch": 1.46, "learning_rate": 8.081471747700395e-06, "loss": 0.8052, "step": 8904 }, { "epoch": 1.46, "learning_rate": 8.079007884362681e-06, "loss": 0.6395, "step": 8905 }, { "epoch": 1.46, "learning_rate": 8.076544021024967e-06, "loss": 0.3758, "step": 8906 }, { "epoch": 1.46, "learning_rate": 8.074080157687253e-06, "loss": 0.8259, "step": 8907 }, { "epoch": 1.46, "learning_rate": 8.07161629434954e-06, "loss": 0.6759, "step": 8908 }, { "epoch": 1.46, "learning_rate": 8.069152431011827e-06, "loss": 0.5014, "step": 8909 }, { "epoch": 1.46, "learning_rate": 8.066688567674113e-06, "loss": 0.2214, "step": 8910 }, { "epoch": 1.46, "learning_rate": 8.064224704336399e-06, "loss": 0.9026, "step": 8911 }, { "epoch": 1.46, "learning_rate": 8.061760840998685e-06, "loss": 0.3842, "step": 8912 }, { "epoch": 1.46, "learning_rate": 8.059296977660972e-06, "loss": 1.0014, "step": 8913 }, { "epoch": 1.46, "learning_rate": 8.05683311432326e-06, "loss": 0.3775, "step": 8914 }, { "epoch": 1.46, "learning_rate": 8.054369250985546e-06, "loss": 0.4962, "step": 8915 }, { "epoch": 1.46, "learning_rate": 8.051905387647832e-06, "loss": 0.3784, "step": 8916 }, { "epoch": 1.46, "learning_rate": 8.049441524310118e-06, "loss": 0.5995, "step": 8917 }, { "epoch": 1.46, "learning_rate": 8.046977660972406e-06, "loss": 0.2287, "step": 8918 }, { "epoch": 1.47, "learning_rate": 8.044513797634692e-06, "loss": 0.8947, "step": 8919 }, { "epoch": 1.47, "learning_rate": 8.042049934296978e-06, "loss": 0.5081, "step": 8920 }, { "epoch": 1.47, "learning_rate": 8.039586070959264e-06, "loss": 1.2048, "step": 8921 }, { "epoch": 1.47, "learning_rate": 8.03712220762155e-06, "loss": 0.4799, "step": 8922 }, { "epoch": 1.47, "learning_rate": 8.034658344283837e-06, "loss": 0.6409, "step": 8923 }, { "epoch": 1.47, "learning_rate": 8.032194480946123e-06, "loss": 0.4949, "step": 8924 }, { "epoch": 1.47, "learning_rate": 8.02973061760841e-06, "loss": 1.372, "step": 8925 }, { "epoch": 1.47, "learning_rate": 8.027266754270697e-06, "loss": 0.5733, "step": 8926 }, { "epoch": 1.47, "learning_rate": 8.024802890932983e-06, "loss": 0.2217, "step": 8927 }, { "epoch": 1.47, "learning_rate": 8.02233902759527e-06, "loss": 0.7722, "step": 8928 }, { "epoch": 1.47, "learning_rate": 8.019875164257557e-06, "loss": 0.9323, "step": 8929 }, { "epoch": 1.47, "learning_rate": 8.017411300919843e-06, "loss": 0.0787, "step": 8930 }, { "epoch": 1.47, "learning_rate": 8.014947437582129e-06, "loss": 0.5485, "step": 8931 }, { "epoch": 1.47, "learning_rate": 8.012483574244415e-06, "loss": 0.7229, "step": 8932 }, { "epoch": 1.47, "learning_rate": 8.010019710906702e-06, "loss": 0.6313, "step": 8933 }, { "epoch": 1.47, "learning_rate": 8.007555847568988e-06, "loss": 0.4753, "step": 8934 }, { "epoch": 1.47, "learning_rate": 8.005091984231274e-06, "loss": 0.3729, "step": 8935 }, { "epoch": 1.47, "learning_rate": 8.00262812089356e-06, "loss": 0.318, "step": 8936 }, { "epoch": 1.47, "learning_rate": 8.000164257555846e-06, "loss": 0.3461, "step": 8937 }, { "epoch": 1.47, "learning_rate": 7.997700394218136e-06, "loss": 0.3751, "step": 8938 }, { "epoch": 1.47, "learning_rate": 7.995236530880422e-06, "loss": 0.352, "step": 8939 }, { "epoch": 1.47, "learning_rate": 7.992772667542708e-06, "loss": 0.7803, "step": 8940 }, { "epoch": 1.47, "learning_rate": 7.990308804204994e-06, "loss": 0.1917, "step": 8941 }, { "epoch": 1.47, "learning_rate": 7.98784494086728e-06, "loss": 0.7358, "step": 8942 }, { "epoch": 1.47, "learning_rate": 7.985381077529567e-06, "loss": 0.5754, "step": 8943 }, { "epoch": 1.47, "learning_rate": 7.982917214191853e-06, "loss": 0.4029, "step": 8944 }, { "epoch": 1.47, "learning_rate": 7.98045335085414e-06, "loss": 0.3275, "step": 8945 }, { "epoch": 1.47, "learning_rate": 7.977989487516425e-06, "loss": 0.1699, "step": 8946 }, { "epoch": 1.47, "learning_rate": 7.975525624178711e-06, "loss": 0.2109, "step": 8947 }, { "epoch": 1.47, "learning_rate": 7.973061760840999e-06, "loss": 0.3795, "step": 8948 }, { "epoch": 1.47, "learning_rate": 7.970597897503285e-06, "loss": 0.9526, "step": 8949 }, { "epoch": 1.47, "learning_rate": 7.968134034165572e-06, "loss": 0.4725, "step": 8950 }, { "epoch": 1.47, "learning_rate": 7.965670170827858e-06, "loss": 0.2731, "step": 8951 }, { "epoch": 1.47, "learning_rate": 7.963206307490144e-06, "loss": 0.4065, "step": 8952 }, { "epoch": 1.47, "learning_rate": 7.960742444152432e-06, "loss": 0.3831, "step": 8953 }, { "epoch": 1.47, "learning_rate": 7.958278580814718e-06, "loss": 0.3289, "step": 8954 }, { "epoch": 1.47, "learning_rate": 7.955814717477004e-06, "loss": 1.1041, "step": 8955 }, { "epoch": 1.47, "learning_rate": 7.95335085413929e-06, "loss": 0.7632, "step": 8956 }, { "epoch": 1.47, "learning_rate": 7.950886990801576e-06, "loss": 0.4505, "step": 8957 }, { "epoch": 1.47, "learning_rate": 7.948423127463864e-06, "loss": 0.6121, "step": 8958 }, { "epoch": 1.47, "learning_rate": 7.94595926412615e-06, "loss": 0.3165, "step": 8959 }, { "epoch": 1.47, "learning_rate": 7.943495400788436e-06, "loss": 0.5591, "step": 8960 }, { "epoch": 1.47, "learning_rate": 7.941031537450722e-06, "loss": 0.1722, "step": 8961 }, { "epoch": 1.47, "learning_rate": 7.93856767411301e-06, "loss": 0.5327, "step": 8962 }, { "epoch": 1.47, "learning_rate": 7.936103810775297e-06, "loss": 0.2729, "step": 8963 }, { "epoch": 1.47, "learning_rate": 7.933639947437583e-06, "loss": 0.1755, "step": 8964 }, { "epoch": 1.47, "learning_rate": 7.931176084099869e-06, "loss": 1.0059, "step": 8965 }, { "epoch": 1.47, "learning_rate": 7.928712220762155e-06, "loss": 0.6616, "step": 8966 }, { "epoch": 1.47, "learning_rate": 7.926248357424441e-06, "loss": 0.2922, "step": 8967 }, { "epoch": 1.47, "learning_rate": 7.923784494086729e-06, "loss": 0.426, "step": 8968 }, { "epoch": 1.47, "learning_rate": 7.921320630749015e-06, "loss": 0.9496, "step": 8969 }, { "epoch": 1.47, "learning_rate": 7.9188567674113e-06, "loss": 0.947, "step": 8970 }, { "epoch": 1.47, "learning_rate": 7.916392904073587e-06, "loss": 0.4236, "step": 8971 }, { "epoch": 1.47, "learning_rate": 7.913929040735873e-06, "loss": 0.4049, "step": 8972 }, { "epoch": 1.47, "learning_rate": 7.91146517739816e-06, "loss": 0.1954, "step": 8973 }, { "epoch": 1.47, "learning_rate": 7.909001314060448e-06, "loss": 0.7075, "step": 8974 }, { "epoch": 1.47, "learning_rate": 7.906537450722734e-06, "loss": 1.0791, "step": 8975 }, { "epoch": 1.47, "learning_rate": 7.90407358738502e-06, "loss": 0.6919, "step": 8976 }, { "epoch": 1.47, "learning_rate": 7.901609724047306e-06, "loss": 0.7577, "step": 8977 }, { "epoch": 1.47, "learning_rate": 7.899145860709594e-06, "loss": 0.4754, "step": 8978 }, { "epoch": 1.47, "learning_rate": 7.89668199737188e-06, "loss": 0.8209, "step": 8979 }, { "epoch": 1.48, "learning_rate": 7.894218134034166e-06, "loss": 0.5536, "step": 8980 }, { "epoch": 1.48, "learning_rate": 7.891754270696452e-06, "loss": 0.4909, "step": 8981 }, { "epoch": 1.48, "learning_rate": 7.889290407358738e-06, "loss": 0.3174, "step": 8982 }, { "epoch": 1.48, "learning_rate": 7.886826544021025e-06, "loss": 0.5108, "step": 8983 }, { "epoch": 1.48, "learning_rate": 7.884362680683311e-06, "loss": 0.3728, "step": 8984 }, { "epoch": 1.48, "learning_rate": 7.881898817345597e-06, "loss": 0.3204, "step": 8985 }, { "epoch": 1.48, "learning_rate": 7.879434954007885e-06, "loss": 0.4833, "step": 8986 }, { "epoch": 1.48, "learning_rate": 7.876971090670171e-06, "loss": 0.6335, "step": 8987 }, { "epoch": 1.48, "learning_rate": 7.874507227332459e-06, "loss": 0.5396, "step": 8988 }, { "epoch": 1.48, "learning_rate": 7.872043363994745e-06, "loss": 0.4721, "step": 8989 }, { "epoch": 1.48, "learning_rate": 7.86957950065703e-06, "loss": 0.5741, "step": 8990 }, { "epoch": 1.48, "learning_rate": 7.867115637319316e-06, "loss": 0.2749, "step": 8991 }, { "epoch": 1.48, "learning_rate": 7.864651773981602e-06, "loss": 1.0175, "step": 8992 }, { "epoch": 1.48, "learning_rate": 7.86218791064389e-06, "loss": 0.9227, "step": 8993 }, { "epoch": 1.48, "learning_rate": 7.859724047306176e-06, "loss": 0.6362, "step": 8994 }, { "epoch": 1.48, "learning_rate": 7.857260183968462e-06, "loss": 0.2484, "step": 8995 }, { "epoch": 1.48, "learning_rate": 7.854796320630748e-06, "loss": 0.9908, "step": 8996 }, { "epoch": 1.48, "learning_rate": 7.852332457293036e-06, "loss": 0.2188, "step": 8997 }, { "epoch": 1.48, "learning_rate": 7.849868593955323e-06, "loss": 0.9275, "step": 8998 }, { "epoch": 1.48, "learning_rate": 7.84740473061761e-06, "loss": 0.525, "step": 8999 }, { "epoch": 1.48, "learning_rate": 7.844940867279895e-06, "loss": 0.516, "step": 9000 }, { "epoch": 1.48, "eval_exact_match": 86.30085146641439, "eval_f1": 92.77980026935433, "step": 9000 }, { "epoch": 1.48, "learning_rate": 7.842477003942181e-06, "loss": 0.7567, "step": 9001 }, { "epoch": 1.48, "learning_rate": 7.840013140604467e-06, "loss": 0.3295, "step": 9002 }, { "epoch": 1.48, "learning_rate": 7.837549277266755e-06, "loss": 0.7191, "step": 9003 }, { "epoch": 1.48, "learning_rate": 7.835085413929041e-06, "loss": 0.713, "step": 9004 }, { "epoch": 1.48, "learning_rate": 7.832621550591327e-06, "loss": 0.4822, "step": 9005 }, { "epoch": 1.48, "learning_rate": 7.830157687253613e-06, "loss": 0.5483, "step": 9006 }, { "epoch": 1.48, "learning_rate": 7.827693823915899e-06, "loss": 0.2758, "step": 9007 }, { "epoch": 1.48, "learning_rate": 7.825229960578187e-06, "loss": 0.5295, "step": 9008 }, { "epoch": 1.48, "learning_rate": 7.822766097240474e-06, "loss": 0.567, "step": 9009 }, { "epoch": 1.48, "learning_rate": 7.82030223390276e-06, "loss": 0.5941, "step": 9010 }, { "epoch": 1.48, "learning_rate": 7.817838370565046e-06, "loss": 0.5635, "step": 9011 }, { "epoch": 1.48, "learning_rate": 7.815374507227332e-06, "loss": 0.7082, "step": 9012 }, { "epoch": 1.48, "learning_rate": 7.81291064388962e-06, "loss": 0.401, "step": 9013 }, { "epoch": 1.48, "learning_rate": 7.810446780551906e-06, "loss": 0.4247, "step": 9014 }, { "epoch": 1.48, "learning_rate": 7.807982917214192e-06, "loss": 0.3564, "step": 9015 }, { "epoch": 1.48, "learning_rate": 7.805519053876478e-06, "loss": 0.4758, "step": 9016 }, { "epoch": 1.48, "learning_rate": 7.803055190538764e-06, "loss": 0.7116, "step": 9017 }, { "epoch": 1.48, "learning_rate": 7.800591327201052e-06, "loss": 0.5873, "step": 9018 }, { "epoch": 1.48, "learning_rate": 7.798127463863338e-06, "loss": 0.8795, "step": 9019 }, { "epoch": 1.48, "learning_rate": 7.795663600525624e-06, "loss": 0.2684, "step": 9020 }, { "epoch": 1.48, "learning_rate": 7.793199737187911e-06, "loss": 0.6187, "step": 9021 }, { "epoch": 1.48, "learning_rate": 7.790735873850197e-06, "loss": 0.6129, "step": 9022 }, { "epoch": 1.48, "learning_rate": 7.788272010512485e-06, "loss": 0.9196, "step": 9023 }, { "epoch": 1.48, "learning_rate": 7.785808147174771e-06, "loss": 0.5576, "step": 9024 }, { "epoch": 1.48, "learning_rate": 7.783344283837057e-06, "loss": 0.5482, "step": 9025 }, { "epoch": 1.48, "learning_rate": 7.780880420499343e-06, "loss": 0.6438, "step": 9026 }, { "epoch": 1.48, "learning_rate": 7.778416557161629e-06, "loss": 0.6867, "step": 9027 }, { "epoch": 1.48, "learning_rate": 7.775952693823917e-06, "loss": 0.483, "step": 9028 }, { "epoch": 1.48, "learning_rate": 7.773488830486203e-06, "loss": 0.2844, "step": 9029 }, { "epoch": 1.48, "learning_rate": 7.771024967148489e-06, "loss": 0.2632, "step": 9030 }, { "epoch": 1.48, "learning_rate": 7.768561103810775e-06, "loss": 1.1828, "step": 9031 }, { "epoch": 1.48, "learning_rate": 7.76609724047306e-06, "loss": 0.2986, "step": 9032 }, { "epoch": 1.48, "learning_rate": 7.76363337713535e-06, "loss": 0.6061, "step": 9033 }, { "epoch": 1.48, "learning_rate": 7.761169513797636e-06, "loss": 0.2347, "step": 9034 }, { "epoch": 1.48, "learning_rate": 7.758705650459922e-06, "loss": 0.2572, "step": 9035 }, { "epoch": 1.48, "learning_rate": 7.756241787122208e-06, "loss": 0.3687, "step": 9036 }, { "epoch": 1.48, "learning_rate": 7.753777923784494e-06, "loss": 0.4677, "step": 9037 }, { "epoch": 1.48, "learning_rate": 7.751314060446781e-06, "loss": 0.3886, "step": 9038 }, { "epoch": 1.48, "learning_rate": 7.748850197109067e-06, "loss": 0.2357, "step": 9039 }, { "epoch": 1.48, "learning_rate": 7.746386333771353e-06, "loss": 0.518, "step": 9040 }, { "epoch": 1.49, "learning_rate": 7.74392247043364e-06, "loss": 0.667, "step": 9041 }, { "epoch": 1.49, "learning_rate": 7.741458607095925e-06, "loss": 1.5161, "step": 9042 }, { "epoch": 1.49, "learning_rate": 7.738994743758213e-06, "loss": 0.1398, "step": 9043 }, { "epoch": 1.49, "learning_rate": 7.736530880420499e-06, "loss": 0.3144, "step": 9044 }, { "epoch": 1.49, "learning_rate": 7.734067017082787e-06, "loss": 0.5447, "step": 9045 }, { "epoch": 1.49, "learning_rate": 7.731603153745073e-06, "loss": 0.5405, "step": 9046 }, { "epoch": 1.49, "learning_rate": 7.729139290407359e-06, "loss": 0.1754, "step": 9047 }, { "epoch": 1.49, "learning_rate": 7.726675427069646e-06, "loss": 0.4255, "step": 9048 }, { "epoch": 1.49, "learning_rate": 7.724211563731932e-06, "loss": 0.2315, "step": 9049 }, { "epoch": 1.49, "learning_rate": 7.721747700394218e-06, "loss": 0.4773, "step": 9050 }, { "epoch": 1.49, "learning_rate": 7.719283837056504e-06, "loss": 0.3722, "step": 9051 }, { "epoch": 1.49, "learning_rate": 7.71681997371879e-06, "loss": 1.1009, "step": 9052 }, { "epoch": 1.49, "learning_rate": 7.714356110381078e-06, "loss": 0.2407, "step": 9053 }, { "epoch": 1.49, "learning_rate": 7.711892247043364e-06, "loss": 0.3947, "step": 9054 }, { "epoch": 1.49, "learning_rate": 7.70942838370565e-06, "loss": 0.3723, "step": 9055 }, { "epoch": 1.49, "learning_rate": 7.706964520367936e-06, "loss": 0.6599, "step": 9056 }, { "epoch": 1.49, "learning_rate": 7.704500657030224e-06, "loss": 0.2595, "step": 9057 }, { "epoch": 1.49, "learning_rate": 7.702036793692511e-06, "loss": 0.3063, "step": 9058 }, { "epoch": 1.49, "learning_rate": 7.699572930354797e-06, "loss": 0.8487, "step": 9059 }, { "epoch": 1.49, "learning_rate": 7.697109067017083e-06, "loss": 0.3995, "step": 9060 }, { "epoch": 1.49, "learning_rate": 7.69464520367937e-06, "loss": 0.2297, "step": 9061 }, { "epoch": 1.49, "learning_rate": 7.692181340341655e-06, "loss": 0.5966, "step": 9062 }, { "epoch": 1.49, "learning_rate": 7.689717477003943e-06, "loss": 1.0255, "step": 9063 }, { "epoch": 1.49, "learning_rate": 7.687253613666229e-06, "loss": 1.0613, "step": 9064 }, { "epoch": 1.49, "learning_rate": 7.684789750328515e-06, "loss": 0.3466, "step": 9065 }, { "epoch": 1.49, "learning_rate": 7.682325886990801e-06, "loss": 0.2357, "step": 9066 }, { "epoch": 1.49, "learning_rate": 7.679862023653087e-06, "loss": 0.4177, "step": 9067 }, { "epoch": 1.49, "learning_rate": 7.677398160315375e-06, "loss": 0.2619, "step": 9068 }, { "epoch": 1.49, "learning_rate": 7.674934296977662e-06, "loss": 0.5288, "step": 9069 }, { "epoch": 1.49, "learning_rate": 7.672470433639948e-06, "loss": 0.3007, "step": 9070 }, { "epoch": 1.49, "learning_rate": 7.670006570302234e-06, "loss": 0.2371, "step": 9071 }, { "epoch": 1.49, "learning_rate": 7.66754270696452e-06, "loss": 0.6173, "step": 9072 }, { "epoch": 1.49, "learning_rate": 7.665078843626808e-06, "loss": 0.4543, "step": 9073 }, { "epoch": 1.49, "learning_rate": 7.662614980289094e-06, "loss": 0.375, "step": 9074 }, { "epoch": 1.49, "learning_rate": 7.66015111695138e-06, "loss": 0.8599, "step": 9075 }, { "epoch": 1.49, "learning_rate": 7.657687253613666e-06, "loss": 0.4146, "step": 9076 }, { "epoch": 1.49, "learning_rate": 7.655223390275952e-06, "loss": 0.7699, "step": 9077 }, { "epoch": 1.49, "learning_rate": 7.65275952693824e-06, "loss": 0.2555, "step": 9078 }, { "epoch": 1.49, "learning_rate": 7.650295663600525e-06, "loss": 0.0952, "step": 9079 }, { "epoch": 1.49, "learning_rate": 7.647831800262811e-06, "loss": 0.7093, "step": 9080 }, { "epoch": 1.49, "learning_rate": 7.645367936925099e-06, "loss": 0.5629, "step": 9081 }, { "epoch": 1.49, "learning_rate": 7.642904073587385e-06, "loss": 0.329, "step": 9082 }, { "epoch": 1.49, "learning_rate": 7.640440210249673e-06, "loss": 0.2951, "step": 9083 }, { "epoch": 1.49, "learning_rate": 7.637976346911959e-06, "loss": 0.3715, "step": 9084 }, { "epoch": 1.49, "learning_rate": 7.635512483574245e-06, "loss": 0.2904, "step": 9085 }, { "epoch": 1.49, "learning_rate": 7.63304862023653e-06, "loss": 1.5003, "step": 9086 }, { "epoch": 1.49, "learning_rate": 7.630584756898817e-06, "loss": 1.1001, "step": 9087 }, { "epoch": 1.49, "learning_rate": 7.6281208935611044e-06, "loss": 1.0146, "step": 9088 }, { "epoch": 1.49, "learning_rate": 7.62565703022339e-06, "loss": 0.448, "step": 9089 }, { "epoch": 1.49, "learning_rate": 7.623193166885677e-06, "loss": 0.1834, "step": 9090 }, { "epoch": 1.49, "learning_rate": 7.620729303547963e-06, "loss": 0.6997, "step": 9091 }, { "epoch": 1.49, "learning_rate": 7.618265440210249e-06, "loss": 0.332, "step": 9092 }, { "epoch": 1.49, "learning_rate": 7.615801576872537e-06, "loss": 0.2823, "step": 9093 }, { "epoch": 1.49, "learning_rate": 7.613337713534823e-06, "loss": 0.4128, "step": 9094 }, { "epoch": 1.49, "learning_rate": 7.610873850197109e-06, "loss": 0.157, "step": 9095 }, { "epoch": 1.49, "learning_rate": 7.608409986859396e-06, "loss": 0.303, "step": 9096 }, { "epoch": 1.49, "learning_rate": 7.605946123521682e-06, "loss": 0.1982, "step": 9097 }, { "epoch": 1.49, "learning_rate": 7.603482260183969e-06, "loss": 1.1154, "step": 9098 }, { "epoch": 1.49, "learning_rate": 7.601018396846255e-06, "loss": 0.2026, "step": 9099 }, { "epoch": 1.49, "learning_rate": 7.598554533508541e-06, "loss": 0.6506, "step": 9100 }, { "epoch": 1.49, "learning_rate": 7.596090670170827e-06, "loss": 0.3928, "step": 9101 }, { "epoch": 1.5, "learning_rate": 7.593626806833114e-06, "loss": 0.6266, "step": 9102 }, { "epoch": 1.5, "learning_rate": 7.591162943495402e-06, "loss": 0.1667, "step": 9103 }, { "epoch": 1.5, "learning_rate": 7.588699080157688e-06, "loss": 0.3955, "step": 9104 }, { "epoch": 1.5, "learning_rate": 7.586235216819974e-06, "loss": 1.1887, "step": 9105 }, { "epoch": 1.5, "learning_rate": 7.58377135348226e-06, "loss": 0.7337, "step": 9106 }, { "epoch": 1.5, "learning_rate": 7.581307490144546e-06, "loss": 0.5294, "step": 9107 }, { "epoch": 1.5, "learning_rate": 7.578843626806834e-06, "loss": 0.5731, "step": 9108 }, { "epoch": 1.5, "learning_rate": 7.57637976346912e-06, "loss": 0.543, "step": 9109 }, { "epoch": 1.5, "learning_rate": 7.573915900131406e-06, "loss": 0.3424, "step": 9110 }, { "epoch": 1.5, "learning_rate": 7.571452036793692e-06, "loss": 0.3371, "step": 9111 }, { "epoch": 1.5, "learning_rate": 7.568988173455978e-06, "loss": 0.1411, "step": 9112 }, { "epoch": 1.5, "learning_rate": 7.566524310118266e-06, "loss": 0.3802, "step": 9113 }, { "epoch": 1.5, "learning_rate": 7.564060446780553e-06, "loss": 0.6974, "step": 9114 }, { "epoch": 1.5, "learning_rate": 7.561596583442839e-06, "loss": 0.3869, "step": 9115 }, { "epoch": 1.5, "learning_rate": 7.559132720105125e-06, "loss": 0.5381, "step": 9116 }, { "epoch": 1.5, "learning_rate": 7.556668856767411e-06, "loss": 0.3684, "step": 9117 }, { "epoch": 1.5, "learning_rate": 7.554204993429698e-06, "loss": 0.8441, "step": 9118 }, { "epoch": 1.5, "learning_rate": 7.551741130091984e-06, "loss": 0.2257, "step": 9119 }, { "epoch": 1.5, "learning_rate": 7.549277266754271e-06, "loss": 0.3715, "step": 9120 }, { "epoch": 1.5, "learning_rate": 7.546813403416557e-06, "loss": 0.3212, "step": 9121 }, { "epoch": 1.5, "learning_rate": 7.544349540078843e-06, "loss": 0.3843, "step": 9122 }, { "epoch": 1.5, "learning_rate": 7.541885676741131e-06, "loss": 0.3952, "step": 9123 }, { "epoch": 1.5, "learning_rate": 7.539421813403417e-06, "loss": 0.7974, "step": 9124 }, { "epoch": 1.5, "learning_rate": 7.536957950065703e-06, "loss": 0.3308, "step": 9125 }, { "epoch": 1.5, "learning_rate": 7.53449408672799e-06, "loss": 0.4245, "step": 9126 }, { "epoch": 1.5, "learning_rate": 7.532030223390276e-06, "loss": 0.4665, "step": 9127 }, { "epoch": 1.5, "learning_rate": 7.529566360052563e-06, "loss": 0.3804, "step": 9128 }, { "epoch": 1.5, "learning_rate": 7.527102496714849e-06, "loss": 0.2976, "step": 9129 }, { "epoch": 1.5, "learning_rate": 7.524638633377135e-06, "loss": 0.1697, "step": 9130 }, { "epoch": 1.5, "learning_rate": 7.522174770039421e-06, "loss": 0.5242, "step": 9131 }, { "epoch": 1.5, "learning_rate": 7.519710906701708e-06, "loss": 0.338, "step": 9132 }, { "epoch": 1.5, "learning_rate": 7.517247043363996e-06, "loss": 0.3844, "step": 9133 }, { "epoch": 1.5, "learning_rate": 7.514783180026282e-06, "loss": 0.4267, "step": 9134 }, { "epoch": 1.5, "learning_rate": 7.512319316688568e-06, "loss": 0.8532, "step": 9135 }, { "epoch": 1.5, "learning_rate": 7.509855453350854e-06, "loss": 0.6196, "step": 9136 }, { "epoch": 1.5, "learning_rate": 7.5073915900131405e-06, "loss": 0.5425, "step": 9137 }, { "epoch": 1.5, "learning_rate": 7.504927726675428e-06, "loss": 0.345, "step": 9138 }, { "epoch": 1.5, "learning_rate": 7.502463863337714e-06, "loss": 0.545, "step": 9139 }, { "epoch": 1.5, "learning_rate": 7.5e-06, "loss": 0.5006, "step": 9140 }, { "epoch": 1.5, "learning_rate": 7.497536136662286e-06, "loss": 0.223, "step": 9141 }, { "epoch": 1.5, "learning_rate": 7.495072273324573e-06, "loss": 0.4322, "step": 9142 }, { "epoch": 1.5, "learning_rate": 7.49260840998686e-06, "loss": 0.3606, "step": 9143 }, { "epoch": 1.5, "learning_rate": 7.490144546649147e-06, "loss": 0.959, "step": 9144 }, { "epoch": 1.5, "learning_rate": 7.487680683311433e-06, "loss": 0.2151, "step": 9145 }, { "epoch": 1.5, "learning_rate": 7.485216819973719e-06, "loss": 0.4571, "step": 9146 }, { "epoch": 1.5, "learning_rate": 7.4827529566360055e-06, "loss": 0.384, "step": 9147 }, { "epoch": 1.5, "learning_rate": 7.4802890932982915e-06, "loss": 0.191, "step": 9148 }, { "epoch": 1.5, "learning_rate": 7.477825229960579e-06, "loss": 0.1572, "step": 9149 }, { "epoch": 1.5, "learning_rate": 7.475361366622865e-06, "loss": 0.9359, "step": 9150 }, { "epoch": 1.5, "learning_rate": 7.472897503285151e-06, "loss": 0.5056, "step": 9151 }, { "epoch": 1.5, "learning_rate": 7.470433639947438e-06, "loss": 0.4496, "step": 9152 }, { "epoch": 1.5, "learning_rate": 7.467969776609724e-06, "loss": 0.3795, "step": 9153 }, { "epoch": 1.5, "learning_rate": 7.465505913272011e-06, "loss": 0.5906, "step": 9154 }, { "epoch": 1.5, "learning_rate": 7.463042049934298e-06, "loss": 0.4792, "step": 9155 }, { "epoch": 1.5, "learning_rate": 7.4605781865965836e-06, "loss": 0.6908, "step": 9156 }, { "epoch": 1.5, "learning_rate": 7.45811432325887e-06, "loss": 0.3471, "step": 9157 }, { "epoch": 1.5, "learning_rate": 7.455650459921156e-06, "loss": 0.6653, "step": 9158 }, { "epoch": 1.5, "learning_rate": 7.453186596583443e-06, "loss": 0.5106, "step": 9159 }, { "epoch": 1.5, "learning_rate": 7.450722733245729e-06, "loss": 0.551, "step": 9160 }, { "epoch": 1.5, "learning_rate": 7.448258869908016e-06, "loss": 0.7384, "step": 9161 }, { "epoch": 1.5, "learning_rate": 7.445795006570303e-06, "loss": 0.5151, "step": 9162 }, { "epoch": 1.51, "learning_rate": 7.443331143232589e-06, "loss": 0.4494, "step": 9163 }, { "epoch": 1.51, "learning_rate": 7.440867279894876e-06, "loss": 0.3167, "step": 9164 }, { "epoch": 1.51, "learning_rate": 7.438403416557162e-06, "loss": 0.5468, "step": 9165 }, { "epoch": 1.51, "learning_rate": 7.435939553219448e-06, "loss": 0.794, "step": 9166 }, { "epoch": 1.51, "learning_rate": 7.433475689881735e-06, "loss": 0.1291, "step": 9167 }, { "epoch": 1.51, "learning_rate": 7.431011826544021e-06, "loss": 0.3377, "step": 9168 }, { "epoch": 1.51, "learning_rate": 7.428547963206308e-06, "loss": 0.132, "step": 9169 }, { "epoch": 1.51, "learning_rate": 7.426084099868594e-06, "loss": 0.2511, "step": 9170 }, { "epoch": 1.51, "learning_rate": 7.42362023653088e-06, "loss": 0.5668, "step": 9171 }, { "epoch": 1.51, "learning_rate": 7.421156373193167e-06, "loss": 0.775, "step": 9172 }, { "epoch": 1.51, "learning_rate": 7.418692509855454e-06, "loss": 0.4113, "step": 9173 }, { "epoch": 1.51, "learning_rate": 7.416228646517741e-06, "loss": 0.2839, "step": 9174 }, { "epoch": 1.51, "learning_rate": 7.413764783180027e-06, "loss": 0.8486, "step": 9175 }, { "epoch": 1.51, "learning_rate": 7.4113009198423126e-06, "loss": 0.9205, "step": 9176 }, { "epoch": 1.51, "learning_rate": 7.408837056504599e-06, "loss": 0.2488, "step": 9177 }, { "epoch": 1.51, "learning_rate": 7.406373193166885e-06, "loss": 0.2617, "step": 9178 }, { "epoch": 1.51, "learning_rate": 7.403909329829173e-06, "loss": 1.0079, "step": 9179 }, { "epoch": 1.51, "learning_rate": 7.401445466491459e-06, "loss": 0.4828, "step": 9180 }, { "epoch": 1.51, "learning_rate": 7.398981603153745e-06, "loss": 0.5531, "step": 9181 }, { "epoch": 1.51, "learning_rate": 7.396517739816032e-06, "loss": 0.4141, "step": 9182 }, { "epoch": 1.51, "learning_rate": 7.394053876478318e-06, "loss": 0.2217, "step": 9183 }, { "epoch": 1.51, "learning_rate": 7.391590013140605e-06, "loss": 0.4907, "step": 9184 }, { "epoch": 1.51, "learning_rate": 7.3891261498028915e-06, "loss": 0.3488, "step": 9185 }, { "epoch": 1.51, "learning_rate": 7.3866622864651775e-06, "loss": 0.6523, "step": 9186 }, { "epoch": 1.51, "learning_rate": 7.384198423127464e-06, "loss": 0.2823, "step": 9187 }, { "epoch": 1.51, "learning_rate": 7.38173455978975e-06, "loss": 0.9414, "step": 9188 }, { "epoch": 1.51, "learning_rate": 7.379270696452037e-06, "loss": 0.6415, "step": 9189 }, { "epoch": 1.51, "learning_rate": 7.376806833114323e-06, "loss": 0.5145, "step": 9190 }, { "epoch": 1.51, "learning_rate": 7.37434296977661e-06, "loss": 0.961, "step": 9191 }, { "epoch": 1.51, "learning_rate": 7.371879106438897e-06, "loss": 0.2185, "step": 9192 }, { "epoch": 1.51, "learning_rate": 7.369415243101183e-06, "loss": 0.254, "step": 9193 }, { "epoch": 1.51, "learning_rate": 7.36695137976347e-06, "loss": 0.1276, "step": 9194 }, { "epoch": 1.51, "learning_rate": 7.364487516425756e-06, "loss": 0.4351, "step": 9195 }, { "epoch": 1.51, "learning_rate": 7.362023653088042e-06, "loss": 0.9884, "step": 9196 }, { "epoch": 1.51, "learning_rate": 7.359559789750329e-06, "loss": 0.7791, "step": 9197 }, { "epoch": 1.51, "learning_rate": 7.357095926412615e-06, "loss": 1.4045, "step": 9198 }, { "epoch": 1.51, "learning_rate": 7.354632063074902e-06, "loss": 0.4987, "step": 9199 }, { "epoch": 1.51, "learning_rate": 7.352168199737188e-06, "loss": 0.2432, "step": 9200 }, { "epoch": 1.51, "learning_rate": 7.349704336399474e-06, "loss": 0.4803, "step": 9201 }, { "epoch": 1.51, "learning_rate": 7.347240473061761e-06, "loss": 0.3231, "step": 9202 }, { "epoch": 1.51, "learning_rate": 7.344776609724048e-06, "loss": 0.6226, "step": 9203 }, { "epoch": 1.51, "learning_rate": 7.3423127463863345e-06, "loss": 0.481, "step": 9204 }, { "epoch": 1.51, "learning_rate": 7.3398488830486205e-06, "loss": 0.5034, "step": 9205 }, { "epoch": 1.51, "learning_rate": 7.3373850197109065e-06, "loss": 0.1617, "step": 9206 }, { "epoch": 1.51, "learning_rate": 7.334921156373193e-06, "loss": 0.1885, "step": 9207 }, { "epoch": 1.51, "learning_rate": 7.332457293035479e-06, "loss": 0.112, "step": 9208 }, { "epoch": 1.51, "learning_rate": 7.329993429697767e-06, "loss": 0.3478, "step": 9209 }, { "epoch": 1.51, "learning_rate": 7.327529566360053e-06, "loss": 0.5319, "step": 9210 }, { "epoch": 1.51, "learning_rate": 7.325065703022339e-06, "loss": 0.3129, "step": 9211 }, { "epoch": 1.51, "learning_rate": 7.322601839684626e-06, "loss": 1.1133, "step": 9212 }, { "epoch": 1.51, "learning_rate": 7.320137976346912e-06, "loss": 1.4295, "step": 9213 }, { "epoch": 1.51, "learning_rate": 7.317674113009199e-06, "loss": 0.4684, "step": 9214 }, { "epoch": 1.51, "learning_rate": 7.3152102496714855e-06, "loss": 0.3271, "step": 9215 }, { "epoch": 1.51, "learning_rate": 7.3127463863337714e-06, "loss": 1.1208, "step": 9216 }, { "epoch": 1.51, "learning_rate": 7.310282522996058e-06, "loss": 0.2781, "step": 9217 }, { "epoch": 1.51, "learning_rate": 7.307818659658344e-06, "loss": 0.2907, "step": 9218 }, { "epoch": 1.51, "learning_rate": 7.305354796320631e-06, "loss": 0.3663, "step": 9219 }, { "epoch": 1.51, "learning_rate": 7.302890932982917e-06, "loss": 0.4214, "step": 9220 }, { "epoch": 1.51, "learning_rate": 7.300427069645204e-06, "loss": 0.6295, "step": 9221 }, { "epoch": 1.51, "learning_rate": 7.297963206307491e-06, "loss": 0.3691, "step": 9222 }, { "epoch": 1.51, "learning_rate": 7.295499342969777e-06, "loss": 0.2735, "step": 9223 }, { "epoch": 1.52, "learning_rate": 7.2930354796320636e-06, "loss": 0.5502, "step": 9224 }, { "epoch": 1.52, "learning_rate": 7.2905716162943495e-06, "loss": 0.4037, "step": 9225 }, { "epoch": 1.52, "learning_rate": 7.2881077529566355e-06, "loss": 0.4735, "step": 9226 }, { "epoch": 1.52, "learning_rate": 7.285643889618923e-06, "loss": 0.1867, "step": 9227 }, { "epoch": 1.52, "learning_rate": 7.283180026281209e-06, "loss": 0.1071, "step": 9228 }, { "epoch": 1.52, "learning_rate": 7.280716162943496e-06, "loss": 0.6313, "step": 9229 }, { "epoch": 1.52, "learning_rate": 7.278252299605782e-06, "loss": 0.4588, "step": 9230 }, { "epoch": 1.52, "learning_rate": 7.275788436268068e-06, "loss": 0.2811, "step": 9231 }, { "epoch": 1.52, "learning_rate": 7.273324572930355e-06, "loss": 0.3951, "step": 9232 }, { "epoch": 1.52, "learning_rate": 7.270860709592642e-06, "loss": 0.5636, "step": 9233 }, { "epoch": 1.52, "learning_rate": 7.2683968462549285e-06, "loss": 0.7713, "step": 9234 }, { "epoch": 1.52, "learning_rate": 7.2659329829172145e-06, "loss": 0.9358, "step": 9235 }, { "epoch": 1.52, "learning_rate": 7.2634691195795004e-06, "loss": 0.2422, "step": 9236 }, { "epoch": 1.52, "learning_rate": 7.261005256241787e-06, "loss": 0.9666, "step": 9237 }, { "epoch": 1.52, "learning_rate": 7.258541392904073e-06, "loss": 0.2813, "step": 9238 }, { "epoch": 1.52, "learning_rate": 7.256077529566361e-06, "loss": 0.4697, "step": 9239 }, { "epoch": 1.52, "learning_rate": 7.253613666228647e-06, "loss": 0.6023, "step": 9240 }, { "epoch": 1.52, "learning_rate": 7.251149802890933e-06, "loss": 0.2545, "step": 9241 }, { "epoch": 1.52, "learning_rate": 7.24868593955322e-06, "loss": 0.5244, "step": 9242 }, { "epoch": 1.52, "learning_rate": 7.246222076215506e-06, "loss": 0.5177, "step": 9243 }, { "epoch": 1.52, "learning_rate": 7.2437582128777926e-06, "loss": 0.5281, "step": 9244 }, { "epoch": 1.52, "learning_rate": 7.241294349540079e-06, "loss": 0.1931, "step": 9245 }, { "epoch": 1.52, "learning_rate": 7.238830486202365e-06, "loss": 0.2358, "step": 9246 }, { "epoch": 1.52, "learning_rate": 7.236366622864652e-06, "loss": 0.5165, "step": 9247 }, { "epoch": 1.52, "learning_rate": 7.233902759526938e-06, "loss": 0.2056, "step": 9248 }, { "epoch": 1.52, "learning_rate": 7.231438896189225e-06, "loss": 0.5605, "step": 9249 }, { "epoch": 1.52, "learning_rate": 7.228975032851511e-06, "loss": 0.2949, "step": 9250 }, { "epoch": 1.52, "learning_rate": 7.226511169513798e-06, "loss": 1.3245, "step": 9251 }, { "epoch": 1.52, "learning_rate": 7.224047306176085e-06, "loss": 0.6226, "step": 9252 }, { "epoch": 1.52, "learning_rate": 7.221583442838371e-06, "loss": 0.1975, "step": 9253 }, { "epoch": 1.52, "learning_rate": 7.2191195795006575e-06, "loss": 0.4689, "step": 9254 }, { "epoch": 1.52, "learning_rate": 7.2166557161629435e-06, "loss": 0.2868, "step": 9255 }, { "epoch": 1.52, "learning_rate": 7.2141918528252295e-06, "loss": 0.4511, "step": 9256 }, { "epoch": 1.52, "learning_rate": 7.211727989487517e-06, "loss": 0.3512, "step": 9257 }, { "epoch": 1.52, "learning_rate": 7.209264126149803e-06, "loss": 0.7557, "step": 9258 }, { "epoch": 1.52, "learning_rate": 7.20680026281209e-06, "loss": 0.4498, "step": 9259 }, { "epoch": 1.52, "learning_rate": 7.204336399474376e-06, "loss": 0.588, "step": 9260 }, { "epoch": 1.52, "learning_rate": 7.201872536136662e-06, "loss": 0.3985, "step": 9261 }, { "epoch": 1.52, "learning_rate": 7.199408672798949e-06, "loss": 0.1775, "step": 9262 }, { "epoch": 1.52, "learning_rate": 7.196944809461236e-06, "loss": 0.2391, "step": 9263 }, { "epoch": 1.52, "learning_rate": 7.194480946123522e-06, "loss": 0.3675, "step": 9264 }, { "epoch": 1.52, "learning_rate": 7.192017082785808e-06, "loss": 0.3881, "step": 9265 }, { "epoch": 1.52, "learning_rate": 7.189553219448094e-06, "loss": 1.2817, "step": 9266 }, { "epoch": 1.52, "learning_rate": 7.187089356110381e-06, "loss": 0.1804, "step": 9267 }, { "epoch": 1.52, "learning_rate": 7.184625492772667e-06, "loss": 0.9449, "step": 9268 }, { "epoch": 1.52, "learning_rate": 7.182161629434955e-06, "loss": 1.2465, "step": 9269 }, { "epoch": 1.52, "learning_rate": 7.179697766097241e-06, "loss": 0.2087, "step": 9270 }, { "epoch": 1.52, "learning_rate": 7.177233902759527e-06, "loss": 0.3261, "step": 9271 }, { "epoch": 1.52, "learning_rate": 7.174770039421814e-06, "loss": 0.64, "step": 9272 }, { "epoch": 1.52, "learning_rate": 7.1723061760841e-06, "loss": 0.6071, "step": 9273 }, { "epoch": 1.52, "learning_rate": 7.1698423127463865e-06, "loss": 1.0824, "step": 9274 }, { "epoch": 1.52, "learning_rate": 7.167378449408673e-06, "loss": 0.3227, "step": 9275 }, { "epoch": 1.52, "learning_rate": 7.164914586070959e-06, "loss": 0.2893, "step": 9276 }, { "epoch": 1.52, "learning_rate": 7.162450722733246e-06, "loss": 0.684, "step": 9277 }, { "epoch": 1.52, "learning_rate": 7.159986859395532e-06, "loss": 0.5101, "step": 9278 }, { "epoch": 1.52, "learning_rate": 7.157522996057819e-06, "loss": 0.6849, "step": 9279 }, { "epoch": 1.52, "learning_rate": 7.155059132720106e-06, "loss": 0.265, "step": 9280 }, { "epoch": 1.52, "learning_rate": 7.152595269382392e-06, "loss": 0.2916, "step": 9281 }, { "epoch": 1.52, "learning_rate": 7.150131406044679e-06, "loss": 0.2823, "step": 9282 }, { "epoch": 1.52, "learning_rate": 7.147667542706965e-06, "loss": 1.3253, "step": 9283 }, { "epoch": 1.52, "learning_rate": 7.145203679369251e-06, "loss": 0.4464, "step": 9284 }, { "epoch": 1.53, "learning_rate": 7.142739816031537e-06, "loss": 0.6982, "step": 9285 }, { "epoch": 1.53, "learning_rate": 7.140275952693824e-06, "loss": 0.3305, "step": 9286 }, { "epoch": 1.53, "learning_rate": 7.137812089356111e-06, "loss": 0.6688, "step": 9287 }, { "epoch": 1.53, "learning_rate": 7.135348226018397e-06, "loss": 0.4652, "step": 9288 }, { "epoch": 1.53, "learning_rate": 7.132884362680684e-06, "loss": 0.5056, "step": 9289 }, { "epoch": 1.53, "learning_rate": 7.13042049934297e-06, "loss": 0.5056, "step": 9290 }, { "epoch": 1.53, "learning_rate": 7.127956636005256e-06, "loss": 0.4001, "step": 9291 }, { "epoch": 1.53, "learning_rate": 7.1254927726675435e-06, "loss": 0.4361, "step": 9292 }, { "epoch": 1.53, "learning_rate": 7.1230289093298295e-06, "loss": 0.3851, "step": 9293 }, { "epoch": 1.53, "learning_rate": 7.120565045992116e-06, "loss": 0.8594, "step": 9294 }, { "epoch": 1.53, "learning_rate": 7.118101182654402e-06, "loss": 0.465, "step": 9295 }, { "epoch": 1.53, "learning_rate": 7.115637319316688e-06, "loss": 0.6665, "step": 9296 }, { "epoch": 1.53, "learning_rate": 7.113173455978975e-06, "loss": 0.5943, "step": 9297 }, { "epoch": 1.53, "learning_rate": 7.110709592641262e-06, "loss": 0.5668, "step": 9298 }, { "epoch": 1.53, "learning_rate": 7.108245729303549e-06, "loss": 0.4322, "step": 9299 }, { "epoch": 1.53, "learning_rate": 7.105781865965835e-06, "loss": 0.4668, "step": 9300 }, { "epoch": 1.53, "learning_rate": 7.103318002628121e-06, "loss": 0.3591, "step": 9301 }, { "epoch": 1.53, "learning_rate": 7.100854139290408e-06, "loss": 0.8835, "step": 9302 }, { "epoch": 1.53, "learning_rate": 7.098390275952694e-06, "loss": 0.6432, "step": 9303 }, { "epoch": 1.53, "learning_rate": 7.095926412614981e-06, "loss": 0.3008, "step": 9304 }, { "epoch": 1.53, "learning_rate": 7.093462549277267e-06, "loss": 0.6115, "step": 9305 }, { "epoch": 1.53, "learning_rate": 7.090998685939553e-06, "loss": 0.4111, "step": 9306 }, { "epoch": 1.53, "learning_rate": 7.08853482260184e-06, "loss": 0.2656, "step": 9307 }, { "epoch": 1.53, "learning_rate": 7.086070959264126e-06, "loss": 0.7268, "step": 9308 }, { "epoch": 1.53, "learning_rate": 7.083607095926413e-06, "loss": 0.6537, "step": 9309 }, { "epoch": 1.53, "learning_rate": 7.0811432325887e-06, "loss": 0.9351, "step": 9310 }, { "epoch": 1.53, "learning_rate": 7.078679369250986e-06, "loss": 0.3529, "step": 9311 }, { "epoch": 1.53, "learning_rate": 7.0762155059132725e-06, "loss": 0.7049, "step": 9312 }, { "epoch": 1.53, "learning_rate": 7.0737516425755585e-06, "loss": 0.3638, "step": 9313 }, { "epoch": 1.53, "learning_rate": 7.071287779237845e-06, "loss": 0.519, "step": 9314 }, { "epoch": 1.53, "learning_rate": 7.068823915900131e-06, "loss": 0.3434, "step": 9315 }, { "epoch": 1.53, "learning_rate": 7.066360052562418e-06, "loss": 0.3895, "step": 9316 }, { "epoch": 1.53, "learning_rate": 7.063896189224705e-06, "loss": 0.4371, "step": 9317 }, { "epoch": 1.53, "learning_rate": 7.061432325886991e-06, "loss": 0.4261, "step": 9318 }, { "epoch": 1.53, "learning_rate": 7.058968462549278e-06, "loss": 0.4216, "step": 9319 }, { "epoch": 1.53, "learning_rate": 7.056504599211564e-06, "loss": 0.6534, "step": 9320 }, { "epoch": 1.53, "learning_rate": 7.05404073587385e-06, "loss": 0.646, "step": 9321 }, { "epoch": 1.53, "learning_rate": 7.0515768725361375e-06, "loss": 0.296, "step": 9322 }, { "epoch": 1.53, "learning_rate": 7.0491130091984235e-06, "loss": 0.8091, "step": 9323 }, { "epoch": 1.53, "learning_rate": 7.04664914586071e-06, "loss": 0.4565, "step": 9324 }, { "epoch": 1.53, "learning_rate": 7.044185282522996e-06, "loss": 0.5567, "step": 9325 }, { "epoch": 1.53, "learning_rate": 7.041721419185282e-06, "loss": 0.4748, "step": 9326 }, { "epoch": 1.53, "learning_rate": 7.039257555847569e-06, "loss": 0.3198, "step": 9327 }, { "epoch": 1.53, "learning_rate": 7.036793692509856e-06, "loss": 1.1273, "step": 9328 }, { "epoch": 1.53, "learning_rate": 7.034329829172143e-06, "loss": 0.2923, "step": 9329 }, { "epoch": 1.53, "learning_rate": 7.031865965834429e-06, "loss": 1.0081, "step": 9330 }, { "epoch": 1.53, "learning_rate": 7.029402102496715e-06, "loss": 0.4918, "step": 9331 }, { "epoch": 1.53, "learning_rate": 7.0269382391590016e-06, "loss": 0.3128, "step": 9332 }, { "epoch": 1.53, "learning_rate": 7.0244743758212875e-06, "loss": 0.3702, "step": 9333 }, { "epoch": 1.53, "learning_rate": 7.022010512483574e-06, "loss": 0.213, "step": 9334 }, { "epoch": 1.53, "learning_rate": 7.019546649145861e-06, "loss": 0.2427, "step": 9335 }, { "epoch": 1.53, "learning_rate": 7.017082785808147e-06, "loss": 0.5059, "step": 9336 }, { "epoch": 1.53, "learning_rate": 7.014618922470434e-06, "loss": 0.2876, "step": 9337 }, { "epoch": 1.53, "learning_rate": 7.01215505913272e-06, "loss": 0.5387, "step": 9338 }, { "epoch": 1.53, "learning_rate": 7.009691195795006e-06, "loss": 0.6549, "step": 9339 }, { "epoch": 1.53, "learning_rate": 7.007227332457294e-06, "loss": 0.4405, "step": 9340 }, { "epoch": 1.53, "learning_rate": 7.00476346911958e-06, "loss": 1.2775, "step": 9341 }, { "epoch": 1.53, "learning_rate": 7.0022996057818665e-06, "loss": 0.5199, "step": 9342 }, { "epoch": 1.53, "learning_rate": 6.9998357424441525e-06, "loss": 0.5707, "step": 9343 }, { "epoch": 1.53, "learning_rate": 6.9973718791064384e-06, "loss": 0.5427, "step": 9344 }, { "epoch": 1.53, "learning_rate": 6.994908015768725e-06, "loss": 0.6975, "step": 9345 }, { "epoch": 1.54, "learning_rate": 6.992444152431012e-06, "loss": 0.7759, "step": 9346 }, { "epoch": 1.54, "learning_rate": 6.989980289093299e-06, "loss": 1.1179, "step": 9347 }, { "epoch": 1.54, "learning_rate": 6.987516425755585e-06, "loss": 0.2648, "step": 9348 }, { "epoch": 1.54, "learning_rate": 6.985052562417871e-06, "loss": 0.4118, "step": 9349 }, { "epoch": 1.54, "learning_rate": 6.982588699080158e-06, "loss": 0.3007, "step": 9350 }, { "epoch": 1.54, "learning_rate": 6.980124835742444e-06, "loss": 0.4602, "step": 9351 }, { "epoch": 1.54, "learning_rate": 6.977660972404731e-06, "loss": 0.6908, "step": 9352 }, { "epoch": 1.54, "learning_rate": 6.975197109067017e-06, "loss": 0.6037, "step": 9353 }, { "epoch": 1.54, "learning_rate": 6.972733245729303e-06, "loss": 1.0995, "step": 9354 }, { "epoch": 1.54, "learning_rate": 6.97026938239159e-06, "loss": 0.4351, "step": 9355 }, { "epoch": 1.54, "learning_rate": 6.967805519053876e-06, "loss": 0.3313, "step": 9356 }, { "epoch": 1.54, "learning_rate": 6.965341655716163e-06, "loss": 0.3373, "step": 9357 }, { "epoch": 1.54, "learning_rate": 6.96287779237845e-06, "loss": 0.3369, "step": 9358 }, { "epoch": 1.54, "learning_rate": 6.960413929040736e-06, "loss": 0.6003, "step": 9359 }, { "epoch": 1.54, "learning_rate": 6.957950065703023e-06, "loss": 0.3322, "step": 9360 }, { "epoch": 1.54, "learning_rate": 6.955486202365309e-06, "loss": 0.5446, "step": 9361 }, { "epoch": 1.54, "learning_rate": 6.9530223390275955e-06, "loss": 0.8304, "step": 9362 }, { "epoch": 1.54, "learning_rate": 6.9505584756898815e-06, "loss": 0.2078, "step": 9363 }, { "epoch": 1.54, "learning_rate": 6.948094612352168e-06, "loss": 0.2743, "step": 9364 }, { "epoch": 1.54, "learning_rate": 6.945630749014455e-06, "loss": 0.3927, "step": 9365 }, { "epoch": 1.54, "learning_rate": 6.943166885676741e-06, "loss": 0.5687, "step": 9366 }, { "epoch": 1.54, "learning_rate": 6.940703022339028e-06, "loss": 0.5104, "step": 9367 }, { "epoch": 1.54, "learning_rate": 6.938239159001314e-06, "loss": 0.0402, "step": 9368 }, { "epoch": 1.54, "learning_rate": 6.9357752956636e-06, "loss": 0.3741, "step": 9369 }, { "epoch": 1.54, "learning_rate": 6.933311432325888e-06, "loss": 0.6823, "step": 9370 }, { "epoch": 1.54, "learning_rate": 6.930847568988174e-06, "loss": 0.3699, "step": 9371 }, { "epoch": 1.54, "learning_rate": 6.92838370565046e-06, "loss": 0.2225, "step": 9372 }, { "epoch": 1.54, "learning_rate": 6.925919842312746e-06, "loss": 0.5441, "step": 9373 }, { "epoch": 1.54, "learning_rate": 6.923455978975032e-06, "loss": 0.4445, "step": 9374 }, { "epoch": 1.54, "learning_rate": 6.920992115637319e-06, "loss": 0.621, "step": 9375 }, { "epoch": 1.54, "learning_rate": 6.918528252299606e-06, "loss": 0.956, "step": 9376 }, { "epoch": 1.54, "learning_rate": 6.916064388961893e-06, "loss": 0.4387, "step": 9377 }, { "epoch": 1.54, "learning_rate": 6.913600525624179e-06, "loss": 0.9209, "step": 9378 }, { "epoch": 1.54, "learning_rate": 6.911136662286465e-06, "loss": 0.4992, "step": 9379 }, { "epoch": 1.54, "learning_rate": 6.908672798948752e-06, "loss": 0.3545, "step": 9380 }, { "epoch": 1.54, "learning_rate": 6.906208935611038e-06, "loss": 0.2916, "step": 9381 }, { "epoch": 1.54, "learning_rate": 6.903745072273325e-06, "loss": 0.593, "step": 9382 }, { "epoch": 1.54, "learning_rate": 6.901281208935611e-06, "loss": 0.5198, "step": 9383 }, { "epoch": 1.54, "learning_rate": 6.898817345597897e-06, "loss": 0.5578, "step": 9384 }, { "epoch": 1.54, "learning_rate": 6.896353482260184e-06, "loss": 0.8105, "step": 9385 }, { "epoch": 1.54, "learning_rate": 6.89388961892247e-06, "loss": 0.2817, "step": 9386 }, { "epoch": 1.54, "learning_rate": 6.891425755584757e-06, "loss": 0.386, "step": 9387 }, { "epoch": 1.54, "learning_rate": 6.888961892247044e-06, "loss": 0.5901, "step": 9388 }, { "epoch": 1.54, "learning_rate": 6.88649802890933e-06, "loss": 0.7594, "step": 9389 }, { "epoch": 1.54, "learning_rate": 6.884034165571617e-06, "loss": 1.0443, "step": 9390 }, { "epoch": 1.54, "learning_rate": 6.881570302233903e-06, "loss": 0.5601, "step": 9391 }, { "epoch": 1.54, "learning_rate": 6.879106438896189e-06, "loss": 0.569, "step": 9392 }, { "epoch": 1.54, "learning_rate": 6.876642575558475e-06, "loss": 0.3842, "step": 9393 }, { "epoch": 1.54, "learning_rate": 6.874178712220762e-06, "loss": 0.5866, "step": 9394 }, { "epoch": 1.54, "learning_rate": 6.871714848883049e-06, "loss": 0.2247, "step": 9395 }, { "epoch": 1.54, "learning_rate": 6.869250985545335e-06, "loss": 0.5255, "step": 9396 }, { "epoch": 1.54, "learning_rate": 6.866787122207622e-06, "loss": 0.5316, "step": 9397 }, { "epoch": 1.54, "learning_rate": 6.864323258869908e-06, "loss": 0.852, "step": 9398 }, { "epoch": 1.54, "learning_rate": 6.861859395532194e-06, "loss": 0.3809, "step": 9399 }, { "epoch": 1.54, "learning_rate": 6.8593955321944815e-06, "loss": 0.4199, "step": 9400 }, { "epoch": 1.54, "learning_rate": 6.8569316688567675e-06, "loss": 0.2925, "step": 9401 }, { "epoch": 1.54, "learning_rate": 6.854467805519054e-06, "loss": 0.6765, "step": 9402 }, { "epoch": 1.54, "learning_rate": 6.85200394218134e-06, "loss": 0.9137, "step": 9403 }, { "epoch": 1.54, "learning_rate": 6.849540078843626e-06, "loss": 0.5026, "step": 9404 }, { "epoch": 1.54, "learning_rate": 6.847076215505913e-06, "loss": 0.3061, "step": 9405 }, { "epoch": 1.55, "learning_rate": 6.8446123521682e-06, "loss": 0.4125, "step": 9406 }, { "epoch": 1.55, "learning_rate": 6.842148488830487e-06, "loss": 0.6871, "step": 9407 }, { "epoch": 1.55, "learning_rate": 6.839684625492773e-06, "loss": 0.2966, "step": 9408 }, { "epoch": 1.55, "learning_rate": 6.837220762155059e-06, "loss": 0.4174, "step": 9409 }, { "epoch": 1.55, "learning_rate": 6.834756898817346e-06, "loss": 0.7061, "step": 9410 }, { "epoch": 1.55, "learning_rate": 6.832293035479632e-06, "loss": 0.7276, "step": 9411 }, { "epoch": 1.55, "learning_rate": 6.829829172141919e-06, "loss": 0.7609, "step": 9412 }, { "epoch": 1.55, "learning_rate": 6.827365308804205e-06, "loss": 0.8489, "step": 9413 }, { "epoch": 1.55, "learning_rate": 6.824901445466491e-06, "loss": 0.3767, "step": 9414 }, { "epoch": 1.55, "learning_rate": 6.822437582128778e-06, "loss": 0.5879, "step": 9415 }, { "epoch": 1.55, "learning_rate": 6.819973718791064e-06, "loss": 0.2908, "step": 9416 }, { "epoch": 1.55, "learning_rate": 6.817509855453351e-06, "loss": 0.6287, "step": 9417 }, { "epoch": 1.55, "learning_rate": 6.815045992115638e-06, "loss": 1.3282, "step": 9418 }, { "epoch": 1.55, "learning_rate": 6.812582128777924e-06, "loss": 1.0504, "step": 9419 }, { "epoch": 1.55, "learning_rate": 6.8101182654402105e-06, "loss": 0.5958, "step": 9420 }, { "epoch": 1.55, "learning_rate": 6.8076544021024965e-06, "loss": 0.2196, "step": 9421 }, { "epoch": 1.55, "learning_rate": 6.805190538764783e-06, "loss": 0.7112, "step": 9422 }, { "epoch": 1.55, "learning_rate": 6.80272667542707e-06, "loss": 0.4477, "step": 9423 }, { "epoch": 1.55, "learning_rate": 6.800262812089356e-06, "loss": 0.8155, "step": 9424 }, { "epoch": 1.55, "learning_rate": 6.797798948751643e-06, "loss": 0.5119, "step": 9425 }, { "epoch": 1.55, "learning_rate": 6.795335085413929e-06, "loss": 0.661, "step": 9426 }, { "epoch": 1.55, "learning_rate": 6.792871222076216e-06, "loss": 0.6136, "step": 9427 }, { "epoch": 1.55, "learning_rate": 6.790407358738502e-06, "loss": 0.3273, "step": 9428 }, { "epoch": 1.55, "learning_rate": 6.787943495400789e-06, "loss": 0.4654, "step": 9429 }, { "epoch": 1.55, "learning_rate": 6.7854796320630755e-06, "loss": 0.5707, "step": 9430 }, { "epoch": 1.55, "learning_rate": 6.7830157687253615e-06, "loss": 0.5009, "step": 9431 }, { "epoch": 1.55, "learning_rate": 6.780551905387648e-06, "loss": 1.4718, "step": 9432 }, { "epoch": 1.55, "learning_rate": 6.778088042049934e-06, "loss": 0.6656, "step": 9433 }, { "epoch": 1.55, "learning_rate": 6.77562417871222e-06, "loss": 0.6116, "step": 9434 }, { "epoch": 1.55, "learning_rate": 6.773160315374508e-06, "loss": 0.4388, "step": 9435 }, { "epoch": 1.55, "learning_rate": 6.770696452036794e-06, "loss": 0.6493, "step": 9436 }, { "epoch": 1.55, "learning_rate": 6.768232588699081e-06, "loss": 0.2722, "step": 9437 }, { "epoch": 1.55, "learning_rate": 6.765768725361367e-06, "loss": 0.8281, "step": 9438 }, { "epoch": 1.55, "learning_rate": 6.763304862023653e-06, "loss": 0.5463, "step": 9439 }, { "epoch": 1.55, "learning_rate": 6.7608409986859396e-06, "loss": 0.2039, "step": 9440 }, { "epoch": 1.55, "learning_rate": 6.758377135348226e-06, "loss": 0.8256, "step": 9441 }, { "epoch": 1.55, "learning_rate": 6.755913272010513e-06, "loss": 0.9177, "step": 9442 }, { "epoch": 1.55, "learning_rate": 6.753449408672799e-06, "loss": 0.3632, "step": 9443 }, { "epoch": 1.55, "learning_rate": 6.750985545335085e-06, "loss": 0.8238, "step": 9444 }, { "epoch": 1.55, "learning_rate": 6.748521681997372e-06, "loss": 0.2633, "step": 9445 }, { "epoch": 1.55, "learning_rate": 6.746057818659658e-06, "loss": 0.4544, "step": 9446 }, { "epoch": 1.55, "learning_rate": 6.743593955321946e-06, "loss": 0.3883, "step": 9447 }, { "epoch": 1.55, "learning_rate": 6.741130091984232e-06, "loss": 0.7116, "step": 9448 }, { "epoch": 1.55, "learning_rate": 6.738666228646518e-06, "loss": 0.3166, "step": 9449 }, { "epoch": 1.55, "learning_rate": 6.7362023653088045e-06, "loss": 0.3723, "step": 9450 }, { "epoch": 1.55, "learning_rate": 6.7337385019710905e-06, "loss": 0.234, "step": 9451 }, { "epoch": 1.55, "learning_rate": 6.731274638633377e-06, "loss": 0.8183, "step": 9452 }, { "epoch": 1.55, "learning_rate": 6.728810775295664e-06, "loss": 0.4532, "step": 9453 }, { "epoch": 1.55, "learning_rate": 6.72634691195795e-06, "loss": 0.6484, "step": 9454 }, { "epoch": 1.55, "learning_rate": 6.723883048620237e-06, "loss": 0.1963, "step": 9455 }, { "epoch": 1.55, "learning_rate": 6.721419185282523e-06, "loss": 0.3462, "step": 9456 }, { "epoch": 1.55, "learning_rate": 6.71895532194481e-06, "loss": 0.3303, "step": 9457 }, { "epoch": 1.55, "learning_rate": 6.716491458607096e-06, "loss": 0.1574, "step": 9458 }, { "epoch": 1.55, "learning_rate": 6.7140275952693826e-06, "loss": 0.3979, "step": 9459 }, { "epoch": 1.55, "learning_rate": 6.711563731931669e-06, "loss": 0.1329, "step": 9460 }, { "epoch": 1.55, "learning_rate": 6.709099868593955e-06, "loss": 0.2459, "step": 9461 }, { "epoch": 1.55, "learning_rate": 6.706636005256242e-06, "loss": 1.026, "step": 9462 }, { "epoch": 1.55, "learning_rate": 6.704172141918528e-06, "loss": 0.2964, "step": 9463 }, { "epoch": 1.55, "learning_rate": 6.701708278580814e-06, "loss": 0.2492, "step": 9464 }, { "epoch": 1.55, "learning_rate": 6.699244415243102e-06, "loss": 0.4233, "step": 9465 }, { "epoch": 1.55, "learning_rate": 6.696780551905388e-06, "loss": 1.2541, "step": 9466 }, { "epoch": 1.56, "learning_rate": 6.694316688567675e-06, "loss": 0.6447, "step": 9467 }, { "epoch": 1.56, "learning_rate": 6.691852825229961e-06, "loss": 0.5096, "step": 9468 }, { "epoch": 1.56, "learning_rate": 6.689388961892247e-06, "loss": 0.608, "step": 9469 }, { "epoch": 1.56, "learning_rate": 6.6869250985545335e-06, "loss": 0.3894, "step": 9470 }, { "epoch": 1.56, "learning_rate": 6.68446123521682e-06, "loss": 0.4986, "step": 9471 }, { "epoch": 1.56, "learning_rate": 6.681997371879107e-06, "loss": 0.5635, "step": 9472 }, { "epoch": 1.56, "learning_rate": 6.679533508541393e-06, "loss": 0.5459, "step": 9473 }, { "epoch": 1.56, "learning_rate": 6.677069645203679e-06, "loss": 0.6592, "step": 9474 }, { "epoch": 1.56, "learning_rate": 6.674605781865966e-06, "loss": 0.3117, "step": 9475 }, { "epoch": 1.56, "learning_rate": 6.672141918528252e-06, "loss": 0.6308, "step": 9476 }, { "epoch": 1.56, "learning_rate": 6.66967805519054e-06, "loss": 0.7919, "step": 9477 }, { "epoch": 1.56, "learning_rate": 6.667214191852826e-06, "loss": 0.8872, "step": 9478 }, { "epoch": 1.56, "learning_rate": 6.664750328515112e-06, "loss": 0.426, "step": 9479 }, { "epoch": 1.56, "learning_rate": 6.662286465177398e-06, "loss": 0.2714, "step": 9480 }, { "epoch": 1.56, "learning_rate": 6.659822601839684e-06, "loss": 0.9388, "step": 9481 }, { "epoch": 1.56, "learning_rate": 6.657358738501971e-06, "loss": 0.3024, "step": 9482 }, { "epoch": 1.56, "learning_rate": 6.654894875164258e-06, "loss": 0.6288, "step": 9483 }, { "epoch": 1.56, "learning_rate": 6.652431011826544e-06, "loss": 0.6565, "step": 9484 }, { "epoch": 1.56, "learning_rate": 6.649967148488831e-06, "loss": 0.2839, "step": 9485 }, { "epoch": 1.56, "learning_rate": 6.647503285151117e-06, "loss": 0.6219, "step": 9486 }, { "epoch": 1.56, "learning_rate": 6.645039421813404e-06, "loss": 0.8101, "step": 9487 }, { "epoch": 1.56, "learning_rate": 6.64257555847569e-06, "loss": 0.5018, "step": 9488 }, { "epoch": 1.56, "learning_rate": 6.6401116951379765e-06, "loss": 0.7639, "step": 9489 }, { "epoch": 1.56, "learning_rate": 6.637647831800263e-06, "loss": 0.4892, "step": 9490 }, { "epoch": 1.56, "learning_rate": 6.635183968462549e-06, "loss": 0.3549, "step": 9491 }, { "epoch": 1.56, "learning_rate": 6.632720105124836e-06, "loss": 0.2421, "step": 9492 }, { "epoch": 1.56, "learning_rate": 6.630256241787122e-06, "loss": 0.8402, "step": 9493 }, { "epoch": 1.56, "learning_rate": 6.627792378449408e-06, "loss": 0.4819, "step": 9494 }, { "epoch": 1.56, "learning_rate": 6.625328515111696e-06, "loss": 0.4947, "step": 9495 }, { "epoch": 1.56, "learning_rate": 6.622864651773982e-06, "loss": 0.6206, "step": 9496 }, { "epoch": 1.56, "learning_rate": 6.620400788436269e-06, "loss": 0.2563, "step": 9497 }, { "epoch": 1.56, "learning_rate": 6.617936925098555e-06, "loss": 0.3747, "step": 9498 }, { "epoch": 1.56, "learning_rate": 6.615473061760841e-06, "loss": 0.5189, "step": 9499 }, { "epoch": 1.56, "learning_rate": 6.6130091984231274e-06, "loss": 0.5419, "step": 9500 }, { "epoch": 1.56, "eval_exact_match": 86.47114474929045, "eval_f1": 92.94550045307338, "step": 9500 }, { "epoch": 1.56, "learning_rate": 6.610545335085414e-06, "loss": 0.5214, "step": 9501 }, { "epoch": 1.56, "learning_rate": 6.608081471747701e-06, "loss": 0.2413, "step": 9502 }, { "epoch": 1.56, "learning_rate": 6.605617608409987e-06, "loss": 0.7032, "step": 9503 }, { "epoch": 1.56, "learning_rate": 6.603153745072273e-06, "loss": 0.5713, "step": 9504 }, { "epoch": 1.56, "learning_rate": 6.60068988173456e-06, "loss": 0.6931, "step": 9505 }, { "epoch": 1.56, "learning_rate": 6.598226018396846e-06, "loss": 0.5567, "step": 9506 }, { "epoch": 1.56, "learning_rate": 6.5957621550591336e-06, "loss": 0.4311, "step": 9507 }, { "epoch": 1.56, "learning_rate": 6.5932982917214195e-06, "loss": 0.4854, "step": 9508 }, { "epoch": 1.56, "learning_rate": 6.5908344283837055e-06, "loss": 0.5145, "step": 9509 }, { "epoch": 1.56, "learning_rate": 6.588370565045992e-06, "loss": 0.3724, "step": 9510 }, { "epoch": 1.56, "learning_rate": 6.585906701708278e-06, "loss": 0.3469, "step": 9511 }, { "epoch": 1.56, "learning_rate": 6.583442838370565e-06, "loss": 0.8218, "step": 9512 }, { "epoch": 1.56, "learning_rate": 6.580978975032852e-06, "loss": 0.3962, "step": 9513 }, { "epoch": 1.56, "learning_rate": 6.578515111695138e-06, "loss": 0.5231, "step": 9514 }, { "epoch": 1.56, "learning_rate": 6.576051248357425e-06, "loss": 0.8466, "step": 9515 }, { "epoch": 1.56, "learning_rate": 6.573587385019711e-06, "loss": 0.8531, "step": 9516 }, { "epoch": 1.56, "learning_rate": 6.571123521681998e-06, "loss": 0.4186, "step": 9517 }, { "epoch": 1.56, "learning_rate": 6.568659658344284e-06, "loss": 0.3829, "step": 9518 }, { "epoch": 1.56, "learning_rate": 6.5661957950065704e-06, "loss": 0.1733, "step": 9519 }, { "epoch": 1.56, "learning_rate": 6.563731931668857e-06, "loss": 0.4748, "step": 9520 }, { "epoch": 1.56, "learning_rate": 6.561268068331143e-06, "loss": 1.0239, "step": 9521 }, { "epoch": 1.56, "learning_rate": 6.55880420499343e-06, "loss": 0.5666, "step": 9522 }, { "epoch": 1.56, "learning_rate": 6.556340341655716e-06, "loss": 0.279, "step": 9523 }, { "epoch": 1.56, "learning_rate": 6.553876478318002e-06, "loss": 0.7734, "step": 9524 }, { "epoch": 1.56, "learning_rate": 6.55141261498029e-06, "loss": 0.9292, "step": 9525 }, { "epoch": 1.56, "learning_rate": 6.548948751642576e-06, "loss": 0.5531, "step": 9526 }, { "epoch": 1.56, "learning_rate": 6.5464848883048626e-06, "loss": 0.1498, "step": 9527 }, { "epoch": 1.57, "learning_rate": 6.5440210249671485e-06, "loss": 0.3735, "step": 9528 }, { "epoch": 1.57, "learning_rate": 6.5415571616294345e-06, "loss": 0.1181, "step": 9529 }, { "epoch": 1.57, "learning_rate": 6.539093298291721e-06, "loss": 0.507, "step": 9530 }, { "epoch": 1.57, "learning_rate": 6.536629434954008e-06, "loss": 0.1739, "step": 9531 }, { "epoch": 1.57, "learning_rate": 6.534165571616295e-06, "loss": 0.3871, "step": 9532 }, { "epoch": 1.57, "learning_rate": 6.531701708278581e-06, "loss": 0.4345, "step": 9533 }, { "epoch": 1.57, "learning_rate": 6.529237844940867e-06, "loss": 0.5159, "step": 9534 }, { "epoch": 1.57, "learning_rate": 6.526773981603154e-06, "loss": 0.4664, "step": 9535 }, { "epoch": 1.57, "learning_rate": 6.52431011826544e-06, "loss": 0.321, "step": 9536 }, { "epoch": 1.57, "learning_rate": 6.5218462549277275e-06, "loss": 0.4645, "step": 9537 }, { "epoch": 1.57, "learning_rate": 6.5193823915900135e-06, "loss": 0.6565, "step": 9538 }, { "epoch": 1.57, "learning_rate": 6.5169185282522995e-06, "loss": 0.7934, "step": 9539 }, { "epoch": 1.57, "learning_rate": 6.514454664914586e-06, "loss": 1.0329, "step": 9540 }, { "epoch": 1.57, "learning_rate": 6.511990801576872e-06, "loss": 0.585, "step": 9541 }, { "epoch": 1.57, "learning_rate": 6.509526938239159e-06, "loss": 0.4859, "step": 9542 }, { "epoch": 1.57, "learning_rate": 6.507063074901446e-06, "loss": 0.3544, "step": 9543 }, { "epoch": 1.57, "learning_rate": 6.504599211563732e-06, "loss": 0.4146, "step": 9544 }, { "epoch": 1.57, "learning_rate": 6.502135348226019e-06, "loss": 0.2053, "step": 9545 }, { "epoch": 1.57, "learning_rate": 6.499671484888305e-06, "loss": 0.4143, "step": 9546 }, { "epoch": 1.57, "learning_rate": 6.4972076215505916e-06, "loss": 0.1356, "step": 9547 }, { "epoch": 1.57, "learning_rate": 6.4947437582128776e-06, "loss": 0.4229, "step": 9548 }, { "epoch": 1.57, "learning_rate": 6.492279894875164e-06, "loss": 0.3754, "step": 9549 }, { "epoch": 1.57, "learning_rate": 6.489816031537451e-06, "loss": 1.1321, "step": 9550 }, { "epoch": 1.57, "learning_rate": 6.487352168199737e-06, "loss": 0.3613, "step": 9551 }, { "epoch": 1.57, "learning_rate": 6.484888304862024e-06, "loss": 1.1615, "step": 9552 }, { "epoch": 1.57, "learning_rate": 6.48242444152431e-06, "loss": 0.7984, "step": 9553 }, { "epoch": 1.57, "learning_rate": 6.479960578186597e-06, "loss": 0.0927, "step": 9554 }, { "epoch": 1.57, "learning_rate": 6.477496714848884e-06, "loss": 0.65, "step": 9555 }, { "epoch": 1.57, "learning_rate": 6.47503285151117e-06, "loss": 0.3532, "step": 9556 }, { "epoch": 1.57, "learning_rate": 6.4725689881734565e-06, "loss": 0.8609, "step": 9557 }, { "epoch": 1.57, "learning_rate": 6.4701051248357425e-06, "loss": 0.5523, "step": 9558 }, { "epoch": 1.57, "learning_rate": 6.4676412614980285e-06, "loss": 0.469, "step": 9559 }, { "epoch": 1.57, "learning_rate": 6.465177398160316e-06, "loss": 0.3681, "step": 9560 }, { "epoch": 1.57, "learning_rate": 6.462713534822602e-06, "loss": 0.4775, "step": 9561 }, { "epoch": 1.57, "learning_rate": 6.460249671484889e-06, "loss": 0.4546, "step": 9562 }, { "epoch": 1.57, "learning_rate": 6.457785808147175e-06, "loss": 0.6419, "step": 9563 }, { "epoch": 1.57, "learning_rate": 6.455321944809461e-06, "loss": 0.6218, "step": 9564 }, { "epoch": 1.57, "learning_rate": 6.452858081471748e-06, "loss": 0.7067, "step": 9565 }, { "epoch": 1.57, "learning_rate": 6.450394218134035e-06, "loss": 0.9578, "step": 9566 }, { "epoch": 1.57, "learning_rate": 6.4479303547963214e-06, "loss": 0.5096, "step": 9567 }, { "epoch": 1.57, "learning_rate": 6.445466491458607e-06, "loss": 0.5715, "step": 9568 }, { "epoch": 1.57, "learning_rate": 6.443002628120893e-06, "loss": 0.494, "step": 9569 }, { "epoch": 1.57, "learning_rate": 6.44053876478318e-06, "loss": 0.6785, "step": 9570 }, { "epoch": 1.57, "learning_rate": 6.438074901445466e-06, "loss": 0.5292, "step": 9571 }, { "epoch": 1.57, "learning_rate": 6.435611038107754e-06, "loss": 0.4443, "step": 9572 }, { "epoch": 1.57, "learning_rate": 6.43314717477004e-06, "loss": 0.3261, "step": 9573 }, { "epoch": 1.57, "learning_rate": 6.430683311432326e-06, "loss": 0.3026, "step": 9574 }, { "epoch": 1.57, "learning_rate": 6.428219448094613e-06, "loss": 0.5168, "step": 9575 }, { "epoch": 1.57, "learning_rate": 6.425755584756899e-06, "loss": 0.4353, "step": 9576 }, { "epoch": 1.57, "learning_rate": 6.4232917214191855e-06, "loss": 0.3166, "step": 9577 }, { "epoch": 1.57, "learning_rate": 6.420827858081472e-06, "loss": 0.4735, "step": 9578 }, { "epoch": 1.57, "learning_rate": 6.418363994743758e-06, "loss": 0.4203, "step": 9579 }, { "epoch": 1.57, "learning_rate": 6.415900131406045e-06, "loss": 1.152, "step": 9580 }, { "epoch": 1.57, "learning_rate": 6.413436268068331e-06, "loss": 0.3825, "step": 9581 }, { "epoch": 1.57, "learning_rate": 6.410972404730618e-06, "loss": 1.0939, "step": 9582 }, { "epoch": 1.57, "learning_rate": 6.408508541392904e-06, "loss": 0.2725, "step": 9583 }, { "epoch": 1.57, "learning_rate": 6.406044678055191e-06, "loss": 0.4814, "step": 9584 }, { "epoch": 1.57, "learning_rate": 6.403580814717478e-06, "loss": 0.2793, "step": 9585 }, { "epoch": 1.57, "learning_rate": 6.401116951379764e-06, "loss": 0.3401, "step": 9586 }, { "epoch": 1.57, "learning_rate": 6.3986530880420504e-06, "loss": 0.7796, "step": 9587 }, { "epoch": 1.57, "learning_rate": 6.396189224704336e-06, "loss": 0.649, "step": 9588 }, { "epoch": 1.58, "learning_rate": 6.393725361366622e-06, "loss": 0.6939, "step": 9589 }, { "epoch": 1.58, "learning_rate": 6.39126149802891e-06, "loss": 0.5153, "step": 9590 }, { "epoch": 1.58, "learning_rate": 6.388797634691196e-06, "loss": 0.233, "step": 9591 }, { "epoch": 1.58, "learning_rate": 6.386333771353483e-06, "loss": 0.3327, "step": 9592 }, { "epoch": 1.58, "learning_rate": 6.383869908015769e-06, "loss": 0.6851, "step": 9593 }, { "epoch": 1.58, "learning_rate": 6.381406044678055e-06, "loss": 0.4635, "step": 9594 }, { "epoch": 1.58, "learning_rate": 6.378942181340342e-06, "loss": 0.43, "step": 9595 }, { "epoch": 1.58, "learning_rate": 6.3764783180026285e-06, "loss": 0.3157, "step": 9596 }, { "epoch": 1.58, "learning_rate": 6.374014454664915e-06, "loss": 0.9516, "step": 9597 }, { "epoch": 1.58, "learning_rate": 6.371550591327201e-06, "loss": 0.2819, "step": 9598 }, { "epoch": 1.58, "learning_rate": 6.369086727989487e-06, "loss": 0.5573, "step": 9599 }, { "epoch": 1.58, "learning_rate": 6.366622864651774e-06, "loss": 0.1995, "step": 9600 }, { "epoch": 1.58, "learning_rate": 6.36415900131406e-06, "loss": 0.3282, "step": 9601 }, { "epoch": 1.58, "learning_rate": 6.361695137976348e-06, "loss": 0.4568, "step": 9602 }, { "epoch": 1.58, "learning_rate": 6.359231274638634e-06, "loss": 0.2232, "step": 9603 }, { "epoch": 1.58, "learning_rate": 6.35676741130092e-06, "loss": 0.4021, "step": 9604 }, { "epoch": 1.58, "learning_rate": 6.354303547963207e-06, "loss": 0.5495, "step": 9605 }, { "epoch": 1.58, "learning_rate": 6.351839684625493e-06, "loss": 0.6259, "step": 9606 }, { "epoch": 1.58, "learning_rate": 6.3493758212877794e-06, "loss": 0.328, "step": 9607 }, { "epoch": 1.58, "learning_rate": 6.346911957950066e-06, "loss": 0.5009, "step": 9608 }, { "epoch": 1.58, "learning_rate": 6.344448094612352e-06, "loss": 0.6752, "step": 9609 }, { "epoch": 1.58, "learning_rate": 6.341984231274639e-06, "loss": 0.3215, "step": 9610 }, { "epoch": 1.58, "learning_rate": 6.339520367936925e-06, "loss": 0.6974, "step": 9611 }, { "epoch": 1.58, "learning_rate": 6.337056504599212e-06, "loss": 0.2243, "step": 9612 }, { "epoch": 1.58, "learning_rate": 6.334592641261498e-06, "loss": 0.3824, "step": 9613 }, { "epoch": 1.58, "learning_rate": 6.332128777923785e-06, "loss": 0.4878, "step": 9614 }, { "epoch": 1.58, "learning_rate": 6.3296649145860716e-06, "loss": 0.5697, "step": 9615 }, { "epoch": 1.58, "learning_rate": 6.3272010512483575e-06, "loss": 0.6771, "step": 9616 }, { "epoch": 1.58, "learning_rate": 6.324737187910644e-06, "loss": 0.374, "step": 9617 }, { "epoch": 1.58, "learning_rate": 6.32227332457293e-06, "loss": 0.4053, "step": 9618 }, { "epoch": 1.58, "learning_rate": 6.319809461235216e-06, "loss": 0.6224, "step": 9619 }, { "epoch": 1.58, "learning_rate": 6.317345597897504e-06, "loss": 0.2972, "step": 9620 }, { "epoch": 1.58, "learning_rate": 6.31488173455979e-06, "loss": 0.6106, "step": 9621 }, { "epoch": 1.58, "learning_rate": 6.312417871222077e-06, "loss": 0.6998, "step": 9622 }, { "epoch": 1.58, "learning_rate": 6.309954007884363e-06, "loss": 0.7479, "step": 9623 }, { "epoch": 1.58, "learning_rate": 6.307490144546649e-06, "loss": 0.4249, "step": 9624 }, { "epoch": 1.58, "learning_rate": 6.305026281208936e-06, "loss": 0.4809, "step": 9625 }, { "epoch": 1.58, "learning_rate": 6.3025624178712225e-06, "loss": 0.6278, "step": 9626 }, { "epoch": 1.58, "learning_rate": 6.300098554533509e-06, "loss": 0.3381, "step": 9627 }, { "epoch": 1.58, "learning_rate": 6.297634691195795e-06, "loss": 0.4209, "step": 9628 }, { "epoch": 1.58, "learning_rate": 6.295170827858081e-06, "loss": 0.4188, "step": 9629 }, { "epoch": 1.58, "learning_rate": 6.292706964520368e-06, "loss": 0.5465, "step": 9630 }, { "epoch": 1.58, "learning_rate": 6.290243101182654e-06, "loss": 0.3549, "step": 9631 }, { "epoch": 1.58, "learning_rate": 6.287779237844942e-06, "loss": 0.2702, "step": 9632 }, { "epoch": 1.58, "learning_rate": 6.285315374507228e-06, "loss": 0.4008, "step": 9633 }, { "epoch": 1.58, "learning_rate": 6.282851511169514e-06, "loss": 0.382, "step": 9634 }, { "epoch": 1.58, "learning_rate": 6.2803876478318006e-06, "loss": 0.553, "step": 9635 }, { "epoch": 1.58, "learning_rate": 6.2779237844940865e-06, "loss": 0.8346, "step": 9636 }, { "epoch": 1.58, "learning_rate": 6.275459921156373e-06, "loss": 0.8667, "step": 9637 }, { "epoch": 1.58, "learning_rate": 6.27299605781866e-06, "loss": 0.4216, "step": 9638 }, { "epoch": 1.58, "learning_rate": 6.270532194480946e-06, "loss": 0.5832, "step": 9639 }, { "epoch": 1.58, "learning_rate": 6.268068331143233e-06, "loss": 0.8857, "step": 9640 }, { "epoch": 1.58, "learning_rate": 6.265604467805519e-06, "loss": 0.4651, "step": 9641 }, { "epoch": 1.58, "learning_rate": 6.263140604467806e-06, "loss": 0.424, "step": 9642 }, { "epoch": 1.58, "learning_rate": 6.260676741130092e-06, "loss": 0.2184, "step": 9643 }, { "epoch": 1.58, "learning_rate": 6.258212877792379e-06, "loss": 0.6732, "step": 9644 }, { "epoch": 1.58, "learning_rate": 6.2557490144546655e-06, "loss": 0.2178, "step": 9645 }, { "epoch": 1.58, "learning_rate": 6.2532851511169515e-06, "loss": 0.3532, "step": 9646 }, { "epoch": 1.58, "learning_rate": 6.250821287779238e-06, "loss": 0.3082, "step": 9647 }, { "epoch": 1.58, "learning_rate": 6.248357424441524e-06, "loss": 0.6131, "step": 9648 }, { "epoch": 1.58, "learning_rate": 6.24589356110381e-06, "loss": 0.8241, "step": 9649 }, { "epoch": 1.59, "learning_rate": 6.243429697766098e-06, "loss": 0.7054, "step": 9650 }, { "epoch": 1.59, "learning_rate": 6.240965834428384e-06, "loss": 0.628, "step": 9651 }, { "epoch": 1.59, "learning_rate": 6.238501971090671e-06, "loss": 0.2425, "step": 9652 }, { "epoch": 1.59, "learning_rate": 6.236038107752957e-06, "loss": 0.5417, "step": 9653 }, { "epoch": 1.59, "learning_rate": 6.233574244415243e-06, "loss": 0.2599, "step": 9654 }, { "epoch": 1.59, "learning_rate": 6.2311103810775296e-06, "loss": 0.2218, "step": 9655 }, { "epoch": 1.59, "learning_rate": 6.228646517739816e-06, "loss": 0.5858, "step": 9656 }, { "epoch": 1.59, "learning_rate": 6.226182654402103e-06, "loss": 0.6026, "step": 9657 }, { "epoch": 1.59, "learning_rate": 6.223718791064389e-06, "loss": 0.497, "step": 9658 }, { "epoch": 1.59, "learning_rate": 6.221254927726675e-06, "loss": 0.3478, "step": 9659 }, { "epoch": 1.59, "learning_rate": 6.218791064388962e-06, "loss": 0.4031, "step": 9660 }, { "epoch": 1.59, "learning_rate": 6.216327201051248e-06, "loss": 0.9331, "step": 9661 }, { "epoch": 1.59, "learning_rate": 6.213863337713536e-06, "loss": 0.351, "step": 9662 }, { "epoch": 1.59, "learning_rate": 6.211399474375822e-06, "loss": 0.8504, "step": 9663 }, { "epoch": 1.59, "learning_rate": 6.208935611038108e-06, "loss": 0.2457, "step": 9664 }, { "epoch": 1.59, "learning_rate": 6.2064717477003945e-06, "loss": 0.3864, "step": 9665 }, { "epoch": 1.59, "learning_rate": 6.2040078843626805e-06, "loss": 0.465, "step": 9666 }, { "epoch": 1.59, "learning_rate": 6.201544021024967e-06, "loss": 0.6287, "step": 9667 }, { "epoch": 1.59, "learning_rate": 6.199080157687254e-06, "loss": 0.2951, "step": 9668 }, { "epoch": 1.59, "learning_rate": 6.19661629434954e-06, "loss": 0.5663, "step": 9669 }, { "epoch": 1.59, "learning_rate": 6.194152431011827e-06, "loss": 0.3788, "step": 9670 }, { "epoch": 1.59, "learning_rate": 6.191688567674113e-06, "loss": 0.7511, "step": 9671 }, { "epoch": 1.59, "learning_rate": 6.1892247043364e-06, "loss": 0.5542, "step": 9672 }, { "epoch": 1.59, "learning_rate": 6.186760840998686e-06, "loss": 0.8618, "step": 9673 }, { "epoch": 1.59, "learning_rate": 6.184296977660973e-06, "loss": 0.1771, "step": 9674 }, { "epoch": 1.59, "learning_rate": 6.1818331143232594e-06, "loss": 0.7719, "step": 9675 }, { "epoch": 1.59, "learning_rate": 6.179369250985545e-06, "loss": 0.3574, "step": 9676 }, { "epoch": 1.59, "learning_rate": 6.176905387647832e-06, "loss": 0.4893, "step": 9677 }, { "epoch": 1.59, "learning_rate": 6.174441524310118e-06, "loss": 1.18, "step": 9678 }, { "epoch": 1.59, "learning_rate": 6.171977660972404e-06, "loss": 0.441, "step": 9679 }, { "epoch": 1.59, "learning_rate": 6.169513797634692e-06, "loss": 0.2262, "step": 9680 }, { "epoch": 1.59, "learning_rate": 6.167049934296978e-06, "loss": 0.4304, "step": 9681 }, { "epoch": 1.59, "learning_rate": 6.164586070959265e-06, "loss": 0.7646, "step": 9682 }, { "epoch": 1.59, "learning_rate": 6.162122207621551e-06, "loss": 0.299, "step": 9683 }, { "epoch": 1.59, "learning_rate": 6.159658344283837e-06, "loss": 0.6527, "step": 9684 }, { "epoch": 1.59, "learning_rate": 6.1571944809461235e-06, "loss": 0.3943, "step": 9685 }, { "epoch": 1.59, "learning_rate": 6.15473061760841e-06, "loss": 0.5129, "step": 9686 }, { "epoch": 1.59, "learning_rate": 6.152266754270697e-06, "loss": 0.4225, "step": 9687 }, { "epoch": 1.59, "learning_rate": 6.149802890932983e-06, "loss": 0.2963, "step": 9688 }, { "epoch": 1.59, "learning_rate": 6.147339027595269e-06, "loss": 0.2552, "step": 9689 }, { "epoch": 1.59, "learning_rate": 6.144875164257556e-06, "loss": 0.2865, "step": 9690 }, { "epoch": 1.59, "learning_rate": 6.142411300919842e-06, "loss": 0.2484, "step": 9691 }, { "epoch": 1.59, "learning_rate": 6.13994743758213e-06, "loss": 0.6572, "step": 9692 }, { "epoch": 1.59, "learning_rate": 6.137483574244416e-06, "loss": 0.4791, "step": 9693 }, { "epoch": 1.59, "learning_rate": 6.135019710906702e-06, "loss": 0.2539, "step": 9694 }, { "epoch": 1.59, "learning_rate": 6.1325558475689884e-06, "loss": 0.814, "step": 9695 }, { "epoch": 1.59, "learning_rate": 6.130091984231274e-06, "loss": 0.884, "step": 9696 }, { "epoch": 1.59, "learning_rate": 6.127628120893561e-06, "loss": 0.3073, "step": 9697 }, { "epoch": 1.59, "learning_rate": 6.125164257555848e-06, "loss": 0.4525, "step": 9698 }, { "epoch": 1.59, "learning_rate": 6.122700394218134e-06, "loss": 0.6012, "step": 9699 }, { "epoch": 1.59, "learning_rate": 6.120236530880421e-06, "loss": 0.0741, "step": 9700 }, { "epoch": 1.59, "learning_rate": 6.117772667542707e-06, "loss": 0.3808, "step": 9701 }, { "epoch": 1.59, "learning_rate": 6.115308804204994e-06, "loss": 0.7062, "step": 9702 }, { "epoch": 1.59, "learning_rate": 6.1128449408672805e-06, "loss": 0.3349, "step": 9703 }, { "epoch": 1.59, "learning_rate": 6.1103810775295665e-06, "loss": 0.2267, "step": 9704 }, { "epoch": 1.59, "learning_rate": 6.107917214191853e-06, "loss": 0.4733, "step": 9705 }, { "epoch": 1.59, "learning_rate": 6.105453350854139e-06, "loss": 0.6228, "step": 9706 }, { "epoch": 1.59, "learning_rate": 6.102989487516426e-06, "loss": 0.5569, "step": 9707 }, { "epoch": 1.59, "learning_rate": 6.100525624178712e-06, "loss": 0.3507, "step": 9708 }, { "epoch": 1.59, "learning_rate": 6.098061760840999e-06, "loss": 0.8981, "step": 9709 }, { "epoch": 1.59, "learning_rate": 6.095597897503286e-06, "loss": 0.3217, "step": 9710 }, { "epoch": 1.6, "learning_rate": 6.093134034165572e-06, "loss": 0.7193, "step": 9711 }, { "epoch": 1.6, "learning_rate": 6.090670170827858e-06, "loss": 0.3443, "step": 9712 }, { "epoch": 1.6, "learning_rate": 6.088206307490145e-06, "loss": 0.4048, "step": 9713 }, { "epoch": 1.6, "learning_rate": 6.085742444152431e-06, "loss": 0.3412, "step": 9714 }, { "epoch": 1.6, "learning_rate": 6.083278580814718e-06, "loss": 1.1742, "step": 9715 }, { "epoch": 1.6, "learning_rate": 6.080814717477004e-06, "loss": 0.3838, "step": 9716 }, { "epoch": 1.6, "learning_rate": 6.07835085413929e-06, "loss": 0.4695, "step": 9717 }, { "epoch": 1.6, "learning_rate": 6.075886990801577e-06, "loss": 0.9168, "step": 9718 }, { "epoch": 1.6, "learning_rate": 6.073423127463863e-06, "loss": 0.1507, "step": 9719 }, { "epoch": 1.6, "learning_rate": 6.07095926412615e-06, "loss": 0.6169, "step": 9720 }, { "epoch": 1.6, "learning_rate": 6.068495400788437e-06, "loss": 0.8576, "step": 9721 }, { "epoch": 1.6, "learning_rate": 6.066031537450723e-06, "loss": 0.5795, "step": 9722 }, { "epoch": 1.6, "learning_rate": 6.0635676741130096e-06, "loss": 0.4907, "step": 9723 }, { "epoch": 1.6, "learning_rate": 6.0611038107752955e-06, "loss": 0.4271, "step": 9724 }, { "epoch": 1.6, "learning_rate": 6.058639947437582e-06, "loss": 0.3926, "step": 9725 }, { "epoch": 1.6, "learning_rate": 6.056176084099868e-06, "loss": 0.6215, "step": 9726 }, { "epoch": 1.6, "learning_rate": 6.053712220762155e-06, "loss": 0.5906, "step": 9727 }, { "epoch": 1.6, "learning_rate": 6.051248357424442e-06, "loss": 0.49, "step": 9728 }, { "epoch": 1.6, "learning_rate": 6.048784494086728e-06, "loss": 0.321, "step": 9729 }, { "epoch": 1.6, "learning_rate": 6.046320630749015e-06, "loss": 0.6449, "step": 9730 }, { "epoch": 1.6, "learning_rate": 6.043856767411301e-06, "loss": 0.4006, "step": 9731 }, { "epoch": 1.6, "learning_rate": 6.041392904073587e-06, "loss": 0.3032, "step": 9732 }, { "epoch": 1.6, "learning_rate": 6.0389290407358745e-06, "loss": 0.3421, "step": 9733 }, { "epoch": 1.6, "learning_rate": 6.0364651773981605e-06, "loss": 0.3801, "step": 9734 }, { "epoch": 1.6, "learning_rate": 6.034001314060447e-06, "loss": 0.4166, "step": 9735 }, { "epoch": 1.6, "learning_rate": 6.031537450722733e-06, "loss": 0.7382, "step": 9736 }, { "epoch": 1.6, "learning_rate": 6.029073587385019e-06, "loss": 0.3417, "step": 9737 }, { "epoch": 1.6, "learning_rate": 6.026609724047306e-06, "loss": 1.448, "step": 9738 }, { "epoch": 1.6, "learning_rate": 6.024145860709593e-06, "loss": 0.5782, "step": 9739 }, { "epoch": 1.6, "learning_rate": 6.02168199737188e-06, "loss": 0.992, "step": 9740 }, { "epoch": 1.6, "learning_rate": 6.019218134034166e-06, "loss": 0.1958, "step": 9741 }, { "epoch": 1.6, "learning_rate": 6.016754270696452e-06, "loss": 0.8916, "step": 9742 }, { "epoch": 1.6, "learning_rate": 6.0142904073587386e-06, "loss": 0.4827, "step": 9743 }, { "epoch": 1.6, "learning_rate": 6.0118265440210245e-06, "loss": 0.2478, "step": 9744 }, { "epoch": 1.6, "learning_rate": 6.009362680683312e-06, "loss": 0.4729, "step": 9745 }, { "epoch": 1.6, "learning_rate": 6.006898817345598e-06, "loss": 0.6729, "step": 9746 }, { "epoch": 1.6, "learning_rate": 6.004434954007884e-06, "loss": 0.1814, "step": 9747 }, { "epoch": 1.6, "learning_rate": 6.001971090670171e-06, "loss": 0.4251, "step": 9748 }, { "epoch": 1.6, "learning_rate": 5.999507227332457e-06, "loss": 0.6377, "step": 9749 }, { "epoch": 1.6, "learning_rate": 5.997043363994744e-06, "loss": 0.5107, "step": 9750 }, { "epoch": 1.6, "learning_rate": 5.994579500657031e-06, "loss": 0.4381, "step": 9751 }, { "epoch": 1.6, "learning_rate": 5.992115637319317e-06, "loss": 0.5157, "step": 9752 }, { "epoch": 1.6, "learning_rate": 5.9896517739816035e-06, "loss": 0.371, "step": 9753 }, { "epoch": 1.6, "learning_rate": 5.9871879106438895e-06, "loss": 1.2305, "step": 9754 }, { "epoch": 1.6, "learning_rate": 5.984724047306176e-06, "loss": 0.587, "step": 9755 }, { "epoch": 1.6, "learning_rate": 5.982260183968462e-06, "loss": 0.7006, "step": 9756 }, { "epoch": 1.6, "learning_rate": 5.979796320630749e-06, "loss": 1.1266, "step": 9757 }, { "epoch": 1.6, "learning_rate": 5.977332457293036e-06, "loss": 0.6936, "step": 9758 }, { "epoch": 1.6, "learning_rate": 5.974868593955322e-06, "loss": 0.6059, "step": 9759 }, { "epoch": 1.6, "learning_rate": 5.972404730617609e-06, "loss": 0.9926, "step": 9760 }, { "epoch": 1.6, "learning_rate": 5.969940867279895e-06, "loss": 0.5588, "step": 9761 }, { "epoch": 1.6, "learning_rate": 5.967477003942181e-06, "loss": 0.666, "step": 9762 }, { "epoch": 1.6, "learning_rate": 5.965013140604468e-06, "loss": 0.5058, "step": 9763 }, { "epoch": 1.6, "learning_rate": 5.962549277266754e-06, "loss": 0.4956, "step": 9764 }, { "epoch": 1.6, "learning_rate": 5.960085413929041e-06, "loss": 0.2397, "step": 9765 }, { "epoch": 1.6, "learning_rate": 5.957621550591327e-06, "loss": 0.3709, "step": 9766 }, { "epoch": 1.6, "learning_rate": 5.955157687253613e-06, "loss": 0.5228, "step": 9767 }, { "epoch": 1.6, "learning_rate": 5.9526938239159e-06, "loss": 0.5669, "step": 9768 }, { "epoch": 1.6, "learning_rate": 5.950229960578187e-06, "loss": 0.4364, "step": 9769 }, { "epoch": 1.6, "learning_rate": 5.947766097240474e-06, "loss": 0.2958, "step": 9770 }, { "epoch": 1.6, "learning_rate": 5.94530223390276e-06, "loss": 0.5652, "step": 9771 }, { "epoch": 1.61, "learning_rate": 5.942838370565046e-06, "loss": 0.3106, "step": 9772 }, { "epoch": 1.61, "learning_rate": 5.9403745072273325e-06, "loss": 0.7493, "step": 9773 }, { "epoch": 1.61, "learning_rate": 5.9379106438896185e-06, "loss": 0.7274, "step": 9774 }, { "epoch": 1.61, "learning_rate": 5.935446780551906e-06, "loss": 0.9884, "step": 9775 }, { "epoch": 1.61, "learning_rate": 5.932982917214192e-06, "loss": 0.5835, "step": 9776 }, { "epoch": 1.61, "learning_rate": 5.930519053876478e-06, "loss": 0.304, "step": 9777 }, { "epoch": 1.61, "learning_rate": 5.928055190538765e-06, "loss": 0.5559, "step": 9778 }, { "epoch": 1.61, "learning_rate": 5.925591327201051e-06, "loss": 0.2825, "step": 9779 }, { "epoch": 1.61, "learning_rate": 5.923127463863338e-06, "loss": 0.9252, "step": 9780 }, { "epoch": 1.61, "learning_rate": 5.920663600525625e-06, "loss": 0.7452, "step": 9781 }, { "epoch": 1.61, "learning_rate": 5.918199737187911e-06, "loss": 0.733, "step": 9782 }, { "epoch": 1.61, "learning_rate": 5.9157358738501974e-06, "loss": 0.4728, "step": 9783 }, { "epoch": 1.61, "learning_rate": 5.913272010512483e-06, "loss": 0.4822, "step": 9784 }, { "epoch": 1.61, "learning_rate": 5.91080814717477e-06, "loss": 0.6201, "step": 9785 }, { "epoch": 1.61, "learning_rate": 5.908344283837056e-06, "loss": 0.9761, "step": 9786 }, { "epoch": 1.61, "learning_rate": 5.905880420499343e-06, "loss": 0.6699, "step": 9787 }, { "epoch": 1.61, "learning_rate": 5.90341655716163e-06, "loss": 0.1646, "step": 9788 }, { "epoch": 1.61, "learning_rate": 5.900952693823916e-06, "loss": 0.4646, "step": 9789 }, { "epoch": 1.61, "learning_rate": 5.898488830486203e-06, "loss": 0.4088, "step": 9790 }, { "epoch": 1.61, "learning_rate": 5.896024967148489e-06, "loss": 0.4843, "step": 9791 }, { "epoch": 1.61, "learning_rate": 5.893561103810775e-06, "loss": 0.5975, "step": 9792 }, { "epoch": 1.61, "learning_rate": 5.891097240473062e-06, "loss": 0.2681, "step": 9793 }, { "epoch": 1.61, "learning_rate": 5.888633377135348e-06, "loss": 0.7325, "step": 9794 }, { "epoch": 1.61, "learning_rate": 5.886169513797635e-06, "loss": 0.6421, "step": 9795 }, { "epoch": 1.61, "learning_rate": 5.883705650459921e-06, "loss": 0.2252, "step": 9796 }, { "epoch": 1.61, "learning_rate": 5.881241787122207e-06, "loss": 0.4603, "step": 9797 }, { "epoch": 1.61, "learning_rate": 5.878777923784494e-06, "loss": 0.2837, "step": 9798 }, { "epoch": 1.61, "learning_rate": 5.876314060446781e-06, "loss": 0.4916, "step": 9799 }, { "epoch": 1.61, "learning_rate": 5.873850197109068e-06, "loss": 0.7535, "step": 9800 }, { "epoch": 1.61, "learning_rate": 5.871386333771354e-06, "loss": 0.3981, "step": 9801 }, { "epoch": 1.61, "learning_rate": 5.86892247043364e-06, "loss": 0.4084, "step": 9802 }, { "epoch": 1.61, "learning_rate": 5.8664586070959264e-06, "loss": 0.6589, "step": 9803 }, { "epoch": 1.61, "learning_rate": 5.863994743758212e-06, "loss": 0.2658, "step": 9804 }, { "epoch": 1.61, "learning_rate": 5.8615308804205e-06, "loss": 0.756, "step": 9805 }, { "epoch": 1.61, "learning_rate": 5.859067017082786e-06, "loss": 0.193, "step": 9806 }, { "epoch": 1.61, "learning_rate": 5.856603153745072e-06, "loss": 0.4588, "step": 9807 }, { "epoch": 1.61, "learning_rate": 5.854139290407359e-06, "loss": 0.3833, "step": 9808 }, { "epoch": 1.61, "learning_rate": 5.851675427069645e-06, "loss": 0.3666, "step": 9809 }, { "epoch": 1.61, "learning_rate": 5.849211563731932e-06, "loss": 0.7166, "step": 9810 }, { "epoch": 1.61, "learning_rate": 5.8467477003942185e-06, "loss": 0.4789, "step": 9811 }, { "epoch": 1.61, "learning_rate": 5.8442838370565045e-06, "loss": 0.6088, "step": 9812 }, { "epoch": 1.61, "learning_rate": 5.841819973718791e-06, "loss": 0.6565, "step": 9813 }, { "epoch": 1.61, "learning_rate": 5.839356110381077e-06, "loss": 0.4057, "step": 9814 }, { "epoch": 1.61, "learning_rate": 5.836892247043364e-06, "loss": 0.8643, "step": 9815 }, { "epoch": 1.61, "learning_rate": 5.83442838370565e-06, "loss": 0.6317, "step": 9816 }, { "epoch": 1.61, "learning_rate": 5.831964520367937e-06, "loss": 0.7341, "step": 9817 }, { "epoch": 1.61, "learning_rate": 5.829500657030224e-06, "loss": 0.3322, "step": 9818 }, { "epoch": 1.61, "learning_rate": 5.82703679369251e-06, "loss": 0.4868, "step": 9819 }, { "epoch": 1.61, "learning_rate": 5.824572930354797e-06, "loss": 0.3367, "step": 9820 }, { "epoch": 1.61, "learning_rate": 5.822109067017083e-06, "loss": 0.5162, "step": 9821 }, { "epoch": 1.61, "learning_rate": 5.819645203679369e-06, "loss": 0.5718, "step": 9822 }, { "epoch": 1.61, "learning_rate": 5.817181340341656e-06, "loss": 0.5223, "step": 9823 }, { "epoch": 1.61, "learning_rate": 5.814717477003942e-06, "loss": 0.2749, "step": 9824 }, { "epoch": 1.61, "learning_rate": 5.812253613666229e-06, "loss": 0.5371, "step": 9825 }, { "epoch": 1.61, "learning_rate": 5.809789750328515e-06, "loss": 1.0594, "step": 9826 }, { "epoch": 1.61, "learning_rate": 5.807325886990801e-06, "loss": 0.5426, "step": 9827 }, { "epoch": 1.61, "learning_rate": 5.804862023653088e-06, "loss": 0.7089, "step": 9828 }, { "epoch": 1.61, "learning_rate": 5.802398160315375e-06, "loss": 0.4116, "step": 9829 }, { "epoch": 1.61, "learning_rate": 5.7999342969776616e-06, "loss": 0.3266, "step": 9830 }, { "epoch": 1.61, "learning_rate": 5.7974704336399476e-06, "loss": 0.7841, "step": 9831 }, { "epoch": 1.61, "learning_rate": 5.7950065703022335e-06, "loss": 0.5134, "step": 9832 }, { "epoch": 1.62, "learning_rate": 5.79254270696452e-06, "loss": 0.8878, "step": 9833 }, { "epoch": 1.62, "learning_rate": 5.790078843626807e-06, "loss": 0.3243, "step": 9834 }, { "epoch": 1.62, "learning_rate": 5.787614980289094e-06, "loss": 0.6542, "step": 9835 }, { "epoch": 1.62, "learning_rate": 5.78515111695138e-06, "loss": 0.6422, "step": 9836 }, { "epoch": 1.62, "learning_rate": 5.782687253613666e-06, "loss": 1.1439, "step": 9837 }, { "epoch": 1.62, "learning_rate": 5.780223390275953e-06, "loss": 0.6497, "step": 9838 }, { "epoch": 1.62, "learning_rate": 5.777759526938239e-06, "loss": 0.3409, "step": 9839 }, { "epoch": 1.62, "learning_rate": 5.7752956636005265e-06, "loss": 0.2692, "step": 9840 }, { "epoch": 1.62, "learning_rate": 5.7728318002628125e-06, "loss": 0.6889, "step": 9841 }, { "epoch": 1.62, "learning_rate": 5.7703679369250985e-06, "loss": 0.6473, "step": 9842 }, { "epoch": 1.62, "learning_rate": 5.767904073587385e-06, "loss": 1.1511, "step": 9843 }, { "epoch": 1.62, "learning_rate": 5.765440210249671e-06, "loss": 0.5284, "step": 9844 }, { "epoch": 1.62, "learning_rate": 5.762976346911958e-06, "loss": 0.5568, "step": 9845 }, { "epoch": 1.62, "learning_rate": 5.760512483574245e-06, "loss": 0.2709, "step": 9846 }, { "epoch": 1.62, "learning_rate": 5.758048620236531e-06, "loss": 0.6465, "step": 9847 }, { "epoch": 1.62, "learning_rate": 5.755584756898818e-06, "loss": 0.526, "step": 9848 }, { "epoch": 1.62, "learning_rate": 5.753120893561104e-06, "loss": 0.7112, "step": 9849 }, { "epoch": 1.62, "learning_rate": 5.750657030223391e-06, "loss": 0.307, "step": 9850 }, { "epoch": 1.62, "learning_rate": 5.7481931668856766e-06, "loss": 0.4838, "step": 9851 }, { "epoch": 1.62, "learning_rate": 5.745729303547963e-06, "loss": 0.9475, "step": 9852 }, { "epoch": 1.62, "learning_rate": 5.74326544021025e-06, "loss": 0.6971, "step": 9853 }, { "epoch": 1.62, "learning_rate": 5.740801576872536e-06, "loss": 0.6483, "step": 9854 }, { "epoch": 1.62, "learning_rate": 5.738337713534823e-06, "loss": 0.4641, "step": 9855 }, { "epoch": 1.62, "learning_rate": 5.735873850197109e-06, "loss": 1.1812, "step": 9856 }, { "epoch": 1.62, "learning_rate": 5.733409986859395e-06, "loss": 0.9871, "step": 9857 }, { "epoch": 1.62, "learning_rate": 5.730946123521683e-06, "loss": 0.6141, "step": 9858 }, { "epoch": 1.62, "learning_rate": 5.728482260183969e-06, "loss": 1.0441, "step": 9859 }, { "epoch": 1.62, "learning_rate": 5.7260183968462555e-06, "loss": 0.1931, "step": 9860 }, { "epoch": 1.62, "learning_rate": 5.7235545335085415e-06, "loss": 0.7621, "step": 9861 }, { "epoch": 1.62, "learning_rate": 5.7210906701708275e-06, "loss": 0.2064, "step": 9862 }, { "epoch": 1.62, "learning_rate": 5.718626806833114e-06, "loss": 0.6388, "step": 9863 }, { "epoch": 1.62, "learning_rate": 5.716162943495401e-06, "loss": 0.5591, "step": 9864 }, { "epoch": 1.62, "learning_rate": 5.713699080157688e-06, "loss": 0.3652, "step": 9865 }, { "epoch": 1.62, "learning_rate": 5.711235216819974e-06, "loss": 0.5166, "step": 9866 }, { "epoch": 1.62, "learning_rate": 5.70877135348226e-06, "loss": 0.576, "step": 9867 }, { "epoch": 1.62, "learning_rate": 5.706307490144547e-06, "loss": 1.2788, "step": 9868 }, { "epoch": 1.62, "learning_rate": 5.703843626806833e-06, "loss": 0.271, "step": 9869 }, { "epoch": 1.62, "learning_rate": 5.7013797634691204e-06, "loss": 0.3882, "step": 9870 }, { "epoch": 1.62, "learning_rate": 5.698915900131406e-06, "loss": 0.7966, "step": 9871 }, { "epoch": 1.62, "learning_rate": 5.696452036793692e-06, "loss": 0.946, "step": 9872 }, { "epoch": 1.62, "learning_rate": 5.693988173455979e-06, "loss": 0.3978, "step": 9873 }, { "epoch": 1.62, "learning_rate": 5.691524310118265e-06, "loss": 0.4619, "step": 9874 }, { "epoch": 1.62, "learning_rate": 5.689060446780552e-06, "loss": 0.2777, "step": 9875 }, { "epoch": 1.62, "learning_rate": 5.686596583442839e-06, "loss": 0.209, "step": 9876 }, { "epoch": 1.62, "learning_rate": 5.684132720105125e-06, "loss": 0.3432, "step": 9877 }, { "epoch": 1.62, "learning_rate": 5.681668856767412e-06, "loss": 0.7799, "step": 9878 }, { "epoch": 1.62, "learning_rate": 5.679204993429698e-06, "loss": 0.634, "step": 9879 }, { "epoch": 1.62, "learning_rate": 5.6767411300919845e-06, "loss": 0.0927, "step": 9880 }, { "epoch": 1.62, "learning_rate": 5.6742772667542705e-06, "loss": 0.4632, "step": 9881 }, { "epoch": 1.62, "learning_rate": 5.671813403416557e-06, "loss": 0.2676, "step": 9882 }, { "epoch": 1.62, "learning_rate": 5.669349540078844e-06, "loss": 0.4484, "step": 9883 }, { "epoch": 1.62, "learning_rate": 5.66688567674113e-06, "loss": 0.5039, "step": 9884 }, { "epoch": 1.62, "learning_rate": 5.664421813403417e-06, "loss": 0.4419, "step": 9885 }, { "epoch": 1.62, "learning_rate": 5.661957950065703e-06, "loss": 0.4097, "step": 9886 }, { "epoch": 1.62, "learning_rate": 5.659494086727989e-06, "loss": 0.584, "step": 9887 }, { "epoch": 1.62, "learning_rate": 5.657030223390277e-06, "loss": 0.3903, "step": 9888 }, { "epoch": 1.62, "learning_rate": 5.654566360052563e-06, "loss": 0.3433, "step": 9889 }, { "epoch": 1.62, "learning_rate": 5.6521024967148494e-06, "loss": 0.449, "step": 9890 }, { "epoch": 1.62, "learning_rate": 5.6496386333771354e-06, "loss": 0.3399, "step": 9891 }, { "epoch": 1.62, "learning_rate": 5.647174770039421e-06, "loss": 0.2682, "step": 9892 }, { "epoch": 1.62, "learning_rate": 5.644710906701708e-06, "loss": 0.4636, "step": 9893 }, { "epoch": 1.63, "learning_rate": 5.642247043363995e-06, "loss": 0.6872, "step": 9894 }, { "epoch": 1.63, "learning_rate": 5.639783180026282e-06, "loss": 0.2906, "step": 9895 }, { "epoch": 1.63, "learning_rate": 5.637319316688568e-06, "loss": 0.7748, "step": 9896 }, { "epoch": 1.63, "learning_rate": 5.634855453350854e-06, "loss": 0.2917, "step": 9897 }, { "epoch": 1.63, "learning_rate": 5.632391590013141e-06, "loss": 0.8006, "step": 9898 }, { "epoch": 1.63, "learning_rate": 5.629927726675427e-06, "loss": 0.3758, "step": 9899 }, { "epoch": 1.63, "learning_rate": 5.627463863337714e-06, "loss": 0.2305, "step": 9900 }, { "epoch": 1.63, "learning_rate": 5.625e-06, "loss": 0.1808, "step": 9901 }, { "epoch": 1.63, "learning_rate": 5.622536136662286e-06, "loss": 0.3235, "step": 9902 }, { "epoch": 1.63, "learning_rate": 5.620072273324573e-06, "loss": 0.5661, "step": 9903 }, { "epoch": 1.63, "learning_rate": 5.617608409986859e-06, "loss": 0.293, "step": 9904 }, { "epoch": 1.63, "learning_rate": 5.615144546649146e-06, "loss": 0.3269, "step": 9905 }, { "epoch": 1.63, "learning_rate": 5.612680683311433e-06, "loss": 0.4001, "step": 9906 }, { "epoch": 1.63, "learning_rate": 5.610216819973719e-06, "loss": 0.7787, "step": 9907 }, { "epoch": 1.63, "learning_rate": 5.607752956636006e-06, "loss": 0.2538, "step": 9908 }, { "epoch": 1.63, "learning_rate": 5.605289093298292e-06, "loss": 0.7208, "step": 9909 }, { "epoch": 1.63, "learning_rate": 5.6028252299605785e-06, "loss": 0.5506, "step": 9910 }, { "epoch": 1.63, "learning_rate": 5.6003613666228644e-06, "loss": 0.874, "step": 9911 }, { "epoch": 1.63, "learning_rate": 5.597897503285151e-06, "loss": 0.5271, "step": 9912 }, { "epoch": 1.63, "learning_rate": 5.595433639947438e-06, "loss": 0.4853, "step": 9913 }, { "epoch": 1.63, "learning_rate": 5.592969776609724e-06, "loss": 0.7089, "step": 9914 }, { "epoch": 1.63, "learning_rate": 5.590505913272011e-06, "loss": 0.5148, "step": 9915 }, { "epoch": 1.63, "learning_rate": 5.588042049934297e-06, "loss": 0.5264, "step": 9916 }, { "epoch": 1.63, "learning_rate": 5.585578186596583e-06, "loss": 0.8065, "step": 9917 }, { "epoch": 1.63, "learning_rate": 5.5831143232588706e-06, "loss": 0.718, "step": 9918 }, { "epoch": 1.63, "learning_rate": 5.5806504599211565e-06, "loss": 0.9172, "step": 9919 }, { "epoch": 1.63, "learning_rate": 5.578186596583443e-06, "loss": 0.4939, "step": 9920 }, { "epoch": 1.63, "learning_rate": 5.575722733245729e-06, "loss": 0.3793, "step": 9921 }, { "epoch": 1.63, "learning_rate": 5.573258869908015e-06, "loss": 0.7877, "step": 9922 }, { "epoch": 1.63, "learning_rate": 5.570795006570302e-06, "loss": 0.6096, "step": 9923 }, { "epoch": 1.63, "learning_rate": 5.568331143232589e-06, "loss": 0.4411, "step": 9924 }, { "epoch": 1.63, "learning_rate": 5.565867279894876e-06, "loss": 0.5631, "step": 9925 }, { "epoch": 1.63, "learning_rate": 5.563403416557162e-06, "loss": 0.2961, "step": 9926 }, { "epoch": 1.63, "learning_rate": 5.560939553219448e-06, "loss": 0.4575, "step": 9927 }, { "epoch": 1.63, "learning_rate": 5.558475689881735e-06, "loss": 0.5376, "step": 9928 }, { "epoch": 1.63, "learning_rate": 5.556011826544021e-06, "loss": 0.8521, "step": 9929 }, { "epoch": 1.63, "learning_rate": 5.553547963206308e-06, "loss": 0.1597, "step": 9930 }, { "epoch": 1.63, "learning_rate": 5.551084099868594e-06, "loss": 0.3193, "step": 9931 }, { "epoch": 1.63, "learning_rate": 5.54862023653088e-06, "loss": 0.5422, "step": 9932 }, { "epoch": 1.63, "learning_rate": 5.546156373193167e-06, "loss": 0.6262, "step": 9933 }, { "epoch": 1.63, "learning_rate": 5.543692509855453e-06, "loss": 0.385, "step": 9934 }, { "epoch": 1.63, "learning_rate": 5.54122864651774e-06, "loss": 0.3334, "step": 9935 }, { "epoch": 1.63, "learning_rate": 5.538764783180027e-06, "loss": 0.1893, "step": 9936 }, { "epoch": 1.63, "learning_rate": 5.536300919842313e-06, "loss": 0.3278, "step": 9937 }, { "epoch": 1.63, "learning_rate": 5.5338370565045996e-06, "loss": 0.3722, "step": 9938 }, { "epoch": 1.63, "learning_rate": 5.5313731931668856e-06, "loss": 0.8136, "step": 9939 }, { "epoch": 1.63, "learning_rate": 5.528909329829172e-06, "loss": 0.475, "step": 9940 }, { "epoch": 1.63, "learning_rate": 5.526445466491458e-06, "loss": 0.3154, "step": 9941 }, { "epoch": 1.63, "learning_rate": 5.523981603153745e-06, "loss": 0.227, "step": 9942 }, { "epoch": 1.63, "learning_rate": 5.521517739816032e-06, "loss": 0.5097, "step": 9943 }, { "epoch": 1.63, "learning_rate": 5.519053876478318e-06, "loss": 0.9386, "step": 9944 }, { "epoch": 1.63, "learning_rate": 5.516590013140605e-06, "loss": 0.2507, "step": 9945 }, { "epoch": 1.63, "learning_rate": 5.514126149802891e-06, "loss": 0.4785, "step": 9946 }, { "epoch": 1.63, "learning_rate": 5.511662286465177e-06, "loss": 0.4633, "step": 9947 }, { "epoch": 1.63, "learning_rate": 5.5091984231274645e-06, "loss": 0.4472, "step": 9948 }, { "epoch": 1.63, "learning_rate": 5.5067345597897505e-06, "loss": 0.8573, "step": 9949 }, { "epoch": 1.63, "learning_rate": 5.504270696452037e-06, "loss": 0.7079, "step": 9950 }, { "epoch": 1.63, "learning_rate": 5.501806833114323e-06, "loss": 0.3717, "step": 9951 }, { "epoch": 1.63, "learning_rate": 5.499342969776609e-06, "loss": 0.5119, "step": 9952 }, { "epoch": 1.63, "learning_rate": 5.496879106438896e-06, "loss": 0.7026, "step": 9953 }, { "epoch": 1.64, "learning_rate": 5.494415243101183e-06, "loss": 0.5049, "step": 9954 }, { "epoch": 1.64, "learning_rate": 5.49195137976347e-06, "loss": 0.9697, "step": 9955 }, { "epoch": 1.64, "learning_rate": 5.489487516425756e-06, "loss": 0.476, "step": 9956 }, { "epoch": 1.64, "learning_rate": 5.487023653088042e-06, "loss": 0.2898, "step": 9957 }, { "epoch": 1.64, "learning_rate": 5.484559789750329e-06, "loss": 0.5663, "step": 9958 }, { "epoch": 1.64, "learning_rate": 5.4820959264126146e-06, "loss": 0.5087, "step": 9959 }, { "epoch": 1.64, "learning_rate": 5.479632063074902e-06, "loss": 0.4581, "step": 9960 }, { "epoch": 1.64, "learning_rate": 5.477168199737188e-06, "loss": 0.2745, "step": 9961 }, { "epoch": 1.64, "learning_rate": 5.474704336399474e-06, "loss": 0.8007, "step": 9962 }, { "epoch": 1.64, "learning_rate": 5.472240473061761e-06, "loss": 0.7881, "step": 9963 }, { "epoch": 1.64, "learning_rate": 5.469776609724047e-06, "loss": 0.365, "step": 9964 }, { "epoch": 1.64, "learning_rate": 5.467312746386334e-06, "loss": 0.3684, "step": 9965 }, { "epoch": 1.64, "learning_rate": 5.464848883048621e-06, "loss": 0.2036, "step": 9966 }, { "epoch": 1.64, "learning_rate": 5.462385019710907e-06, "loss": 0.6756, "step": 9967 }, { "epoch": 1.64, "learning_rate": 5.4599211563731935e-06, "loss": 0.8109, "step": 9968 }, { "epoch": 1.64, "learning_rate": 5.4574572930354795e-06, "loss": 0.3346, "step": 9969 }, { "epoch": 1.64, "learning_rate": 5.454993429697766e-06, "loss": 0.9363, "step": 9970 }, { "epoch": 1.64, "learning_rate": 5.452529566360053e-06, "loss": 1.2026, "step": 9971 }, { "epoch": 1.64, "learning_rate": 5.450065703022339e-06, "loss": 0.4427, "step": 9972 }, { "epoch": 1.64, "learning_rate": 5.447601839684626e-06, "loss": 0.4008, "step": 9973 }, { "epoch": 1.64, "learning_rate": 5.445137976346912e-06, "loss": 0.2267, "step": 9974 }, { "epoch": 1.64, "learning_rate": 5.442674113009199e-06, "loss": 0.3512, "step": 9975 }, { "epoch": 1.64, "learning_rate": 5.440210249671485e-06, "loss": 0.5879, "step": 9976 }, { "epoch": 1.64, "learning_rate": 5.437746386333772e-06, "loss": 0.4702, "step": 9977 }, { "epoch": 1.64, "learning_rate": 5.4352825229960584e-06, "loss": 0.5465, "step": 9978 }, { "epoch": 1.64, "learning_rate": 5.432818659658344e-06, "loss": 0.5532, "step": 9979 }, { "epoch": 1.64, "learning_rate": 5.430354796320631e-06, "loss": 0.2843, "step": 9980 }, { "epoch": 1.64, "learning_rate": 5.427890932982917e-06, "loss": 0.5779, "step": 9981 }, { "epoch": 1.64, "learning_rate": 5.425427069645203e-06, "loss": 0.6483, "step": 9982 }, { "epoch": 1.64, "learning_rate": 5.422963206307491e-06, "loss": 0.3108, "step": 9983 }, { "epoch": 1.64, "learning_rate": 5.420499342969777e-06, "loss": 0.2297, "step": 9984 }, { "epoch": 1.64, "learning_rate": 5.418035479632064e-06, "loss": 0.4319, "step": 9985 }, { "epoch": 1.64, "learning_rate": 5.41557161629435e-06, "loss": 0.537, "step": 9986 }, { "epoch": 1.64, "learning_rate": 5.413107752956636e-06, "loss": 1.2143, "step": 9987 }, { "epoch": 1.64, "learning_rate": 5.4106438896189225e-06, "loss": 1.0828, "step": 9988 }, { "epoch": 1.64, "learning_rate": 5.408180026281209e-06, "loss": 0.2817, "step": 9989 }, { "epoch": 1.64, "learning_rate": 5.405716162943496e-06, "loss": 0.679, "step": 9990 }, { "epoch": 1.64, "learning_rate": 5.403252299605782e-06, "loss": 0.4669, "step": 9991 }, { "epoch": 1.64, "learning_rate": 5.400788436268068e-06, "loss": 0.4126, "step": 9992 }, { "epoch": 1.64, "learning_rate": 5.398324572930355e-06, "loss": 0.4174, "step": 9993 }, { "epoch": 1.64, "learning_rate": 5.395860709592641e-06, "loss": 0.4868, "step": 9994 }, { "epoch": 1.64, "learning_rate": 5.393396846254929e-06, "loss": 0.3875, "step": 9995 }, { "epoch": 1.64, "learning_rate": 5.390932982917215e-06, "loss": 0.4577, "step": 9996 }, { "epoch": 1.64, "learning_rate": 5.388469119579501e-06, "loss": 0.4607, "step": 9997 }, { "epoch": 1.64, "learning_rate": 5.3860052562417874e-06, "loss": 0.9368, "step": 9998 }, { "epoch": 1.64, "learning_rate": 5.3835413929040734e-06, "loss": 0.4825, "step": 9999 }, { "epoch": 1.64, "learning_rate": 5.38107752956636e-06, "loss": 0.3978, "step": 10000 }, { "epoch": 1.64, "eval_exact_match": 86.29139072847683, "eval_f1": 92.93763164536074, "step": 10000 }, { "epoch": 1.64, "learning_rate": 5.378613666228647e-06, "loss": 0.1555, "step": 10001 }, { "epoch": 1.64, "learning_rate": 5.376149802890933e-06, "loss": 0.6591, "step": 10002 }, { "epoch": 1.64, "learning_rate": 5.37368593955322e-06, "loss": 0.5863, "step": 10003 }, { "epoch": 1.64, "learning_rate": 5.371222076215506e-06, "loss": 0.6305, "step": 10004 }, { "epoch": 1.64, "learning_rate": 5.368758212877793e-06, "loss": 0.8641, "step": 10005 }, { "epoch": 1.64, "learning_rate": 5.366294349540079e-06, "loss": 0.6006, "step": 10006 }, { "epoch": 1.64, "learning_rate": 5.3638304862023655e-06, "loss": 0.3859, "step": 10007 }, { "epoch": 1.64, "learning_rate": 5.361366622864652e-06, "loss": 0.4512, "step": 10008 }, { "epoch": 1.64, "learning_rate": 5.358902759526938e-06, "loss": 0.5909, "step": 10009 }, { "epoch": 1.64, "learning_rate": 5.356438896189225e-06, "loss": 0.635, "step": 10010 }, { "epoch": 1.64, "learning_rate": 5.353975032851511e-06, "loss": 0.7415, "step": 10011 }, { "epoch": 1.64, "learning_rate": 5.351511169513797e-06, "loss": 0.7337, "step": 10012 }, { "epoch": 1.64, "learning_rate": 5.349047306176085e-06, "loss": 0.9217, "step": 10013 }, { "epoch": 1.64, "learning_rate": 5.346583442838371e-06, "loss": 0.2921, "step": 10014 }, { "epoch": 1.65, "learning_rate": 5.344119579500658e-06, "loss": 0.5356, "step": 10015 }, { "epoch": 1.65, "learning_rate": 5.341655716162944e-06, "loss": 0.2122, "step": 10016 }, { "epoch": 1.65, "learning_rate": 5.33919185282523e-06, "loss": 0.2531, "step": 10017 }, { "epoch": 1.65, "learning_rate": 5.3367279894875165e-06, "loss": 0.5794, "step": 10018 }, { "epoch": 1.65, "learning_rate": 5.334264126149803e-06, "loss": 0.5336, "step": 10019 }, { "epoch": 1.65, "learning_rate": 5.33180026281209e-06, "loss": 0.7795, "step": 10020 }, { "epoch": 1.65, "learning_rate": 5.329336399474376e-06, "loss": 0.6617, "step": 10021 }, { "epoch": 1.65, "learning_rate": 5.326872536136662e-06, "loss": 0.226, "step": 10022 }, { "epoch": 1.65, "learning_rate": 5.324408672798949e-06, "loss": 0.3087, "step": 10023 }, { "epoch": 1.65, "learning_rate": 5.321944809461235e-06, "loss": 0.8549, "step": 10024 }, { "epoch": 1.65, "learning_rate": 5.319480946123523e-06, "loss": 0.3613, "step": 10025 }, { "epoch": 1.65, "learning_rate": 5.3170170827858086e-06, "loss": 0.5346, "step": 10026 }, { "epoch": 1.65, "learning_rate": 5.3145532194480945e-06, "loss": 0.2468, "step": 10027 }, { "epoch": 1.65, "learning_rate": 5.312089356110381e-06, "loss": 0.3642, "step": 10028 }, { "epoch": 1.65, "learning_rate": 5.309625492772667e-06, "loss": 0.3462, "step": 10029 }, { "epoch": 1.65, "learning_rate": 5.307161629434954e-06, "loss": 0.2798, "step": 10030 }, { "epoch": 1.65, "learning_rate": 5.304697766097241e-06, "loss": 0.3169, "step": 10031 }, { "epoch": 1.65, "learning_rate": 5.302233902759527e-06, "loss": 0.7902, "step": 10032 }, { "epoch": 1.65, "learning_rate": 5.299770039421814e-06, "loss": 0.2912, "step": 10033 }, { "epoch": 1.65, "learning_rate": 5.2973061760841e-06, "loss": 0.8812, "step": 10034 }, { "epoch": 1.65, "learning_rate": 5.294842312746387e-06, "loss": 0.2956, "step": 10035 }, { "epoch": 1.65, "learning_rate": 5.292378449408673e-06, "loss": 0.5627, "step": 10036 }, { "epoch": 1.65, "learning_rate": 5.2899145860709595e-06, "loss": 0.2993, "step": 10037 }, { "epoch": 1.65, "learning_rate": 5.287450722733246e-06, "loss": 0.4858, "step": 10038 }, { "epoch": 1.65, "learning_rate": 5.284986859395532e-06, "loss": 0.5641, "step": 10039 }, { "epoch": 1.65, "learning_rate": 5.282522996057819e-06, "loss": 0.5325, "step": 10040 }, { "epoch": 1.65, "learning_rate": 5.280059132720105e-06, "loss": 0.2546, "step": 10041 }, { "epoch": 1.65, "learning_rate": 5.277595269382391e-06, "loss": 0.6736, "step": 10042 }, { "epoch": 1.65, "learning_rate": 5.275131406044679e-06, "loss": 0.387, "step": 10043 }, { "epoch": 1.65, "learning_rate": 5.272667542706965e-06, "loss": 0.2769, "step": 10044 }, { "epoch": 1.65, "learning_rate": 5.270203679369252e-06, "loss": 0.3253, "step": 10045 }, { "epoch": 1.65, "learning_rate": 5.2677398160315376e-06, "loss": 1.1838, "step": 10046 }, { "epoch": 1.65, "learning_rate": 5.2652759526938236e-06, "loss": 0.7005, "step": 10047 }, { "epoch": 1.65, "learning_rate": 5.26281208935611e-06, "loss": 0.3367, "step": 10048 }, { "epoch": 1.65, "learning_rate": 5.260348226018397e-06, "loss": 0.602, "step": 10049 }, { "epoch": 1.65, "learning_rate": 5.257884362680684e-06, "loss": 0.4557, "step": 10050 }, { "epoch": 1.65, "learning_rate": 5.25542049934297e-06, "loss": 0.7046, "step": 10051 }, { "epoch": 1.65, "learning_rate": 5.252956636005256e-06, "loss": 0.3897, "step": 10052 }, { "epoch": 1.65, "learning_rate": 5.250492772667543e-06, "loss": 0.7947, "step": 10053 }, { "epoch": 1.65, "learning_rate": 5.248028909329829e-06, "loss": 0.2994, "step": 10054 }, { "epoch": 1.65, "learning_rate": 5.2455650459921165e-06, "loss": 0.1912, "step": 10055 }, { "epoch": 1.65, "learning_rate": 5.2431011826544025e-06, "loss": 0.4101, "step": 10056 }, { "epoch": 1.65, "learning_rate": 5.2406373193166885e-06, "loss": 0.22, "step": 10057 }, { "epoch": 1.65, "learning_rate": 5.238173455978975e-06, "loss": 0.5106, "step": 10058 }, { "epoch": 1.65, "learning_rate": 5.235709592641261e-06, "loss": 0.4717, "step": 10059 }, { "epoch": 1.65, "learning_rate": 5.233245729303548e-06, "loss": 1.0979, "step": 10060 }, { "epoch": 1.65, "learning_rate": 5.230781865965835e-06, "loss": 0.3451, "step": 10061 }, { "epoch": 1.65, "learning_rate": 5.228318002628121e-06, "loss": 0.4568, "step": 10062 }, { "epoch": 1.65, "learning_rate": 5.225854139290408e-06, "loss": 0.4493, "step": 10063 }, { "epoch": 1.65, "learning_rate": 5.223390275952694e-06, "loss": 0.4092, "step": 10064 }, { "epoch": 1.65, "learning_rate": 5.220926412614981e-06, "loss": 0.3166, "step": 10065 }, { "epoch": 1.65, "learning_rate": 5.218462549277267e-06, "loss": 0.4382, "step": 10066 }, { "epoch": 1.65, "learning_rate": 5.215998685939553e-06, "loss": 0.9314, "step": 10067 }, { "epoch": 1.65, "learning_rate": 5.21353482260184e-06, "loss": 0.5253, "step": 10068 }, { "epoch": 1.65, "learning_rate": 5.211070959264126e-06, "loss": 0.6532, "step": 10069 }, { "epoch": 1.65, "learning_rate": 5.208607095926413e-06, "loss": 0.4416, "step": 10070 }, { "epoch": 1.65, "learning_rate": 5.206143232588699e-06, "loss": 0.5606, "step": 10071 }, { "epoch": 1.65, "learning_rate": 5.203679369250985e-06, "loss": 0.6483, "step": 10072 }, { "epoch": 1.65, "learning_rate": 5.201215505913273e-06, "loss": 0.4154, "step": 10073 }, { "epoch": 1.65, "learning_rate": 5.198751642575559e-06, "loss": 0.4634, "step": 10074 }, { "epoch": 1.65, "learning_rate": 5.1962877792378455e-06, "loss": 0.2238, "step": 10075 }, { "epoch": 1.66, "learning_rate": 5.1938239159001315e-06, "loss": 0.5382, "step": 10076 }, { "epoch": 1.66, "learning_rate": 5.1913600525624175e-06, "loss": 0.8415, "step": 10077 }, { "epoch": 1.66, "learning_rate": 5.188896189224704e-06, "loss": 0.6822, "step": 10078 }, { "epoch": 1.66, "learning_rate": 5.186432325886991e-06, "loss": 0.4223, "step": 10079 }, { "epoch": 1.66, "learning_rate": 5.183968462549278e-06, "loss": 0.5189, "step": 10080 }, { "epoch": 1.66, "learning_rate": 5.181504599211564e-06, "loss": 0.3506, "step": 10081 }, { "epoch": 1.66, "learning_rate": 5.17904073587385e-06, "loss": 0.368, "step": 10082 }, { "epoch": 1.66, "learning_rate": 5.176576872536137e-06, "loss": 0.9761, "step": 10083 }, { "epoch": 1.66, "learning_rate": 5.174113009198423e-06, "loss": 0.324, "step": 10084 }, { "epoch": 1.66, "learning_rate": 5.1716491458607105e-06, "loss": 0.6817, "step": 10085 }, { "epoch": 1.66, "learning_rate": 5.1691852825229964e-06, "loss": 0.392, "step": 10086 }, { "epoch": 1.66, "learning_rate": 5.166721419185282e-06, "loss": 0.3372, "step": 10087 }, { "epoch": 1.66, "learning_rate": 5.164257555847569e-06, "loss": 0.7099, "step": 10088 }, { "epoch": 1.66, "learning_rate": 5.161793692509855e-06, "loss": 0.3637, "step": 10089 }, { "epoch": 1.66, "learning_rate": 5.159329829172142e-06, "loss": 0.2519, "step": 10090 }, { "epoch": 1.66, "learning_rate": 5.156865965834429e-06, "loss": 0.5487, "step": 10091 }, { "epoch": 1.66, "learning_rate": 5.154402102496715e-06, "loss": 0.4878, "step": 10092 }, { "epoch": 1.66, "learning_rate": 5.151938239159002e-06, "loss": 0.9736, "step": 10093 }, { "epoch": 1.66, "learning_rate": 5.149474375821288e-06, "loss": 0.4161, "step": 10094 }, { "epoch": 1.66, "learning_rate": 5.147010512483574e-06, "loss": 0.3465, "step": 10095 }, { "epoch": 1.66, "learning_rate": 5.1445466491458605e-06, "loss": 0.0912, "step": 10096 }, { "epoch": 1.66, "learning_rate": 5.142082785808147e-06, "loss": 0.6037, "step": 10097 }, { "epoch": 1.66, "learning_rate": 5.139618922470434e-06, "loss": 0.2168, "step": 10098 }, { "epoch": 1.66, "learning_rate": 5.13715505913272e-06, "loss": 0.4614, "step": 10099 }, { "epoch": 1.66, "learning_rate": 5.134691195795006e-06, "loss": 0.7559, "step": 10100 }, { "epoch": 1.66, "learning_rate": 5.132227332457293e-06, "loss": 0.4482, "step": 10101 }, { "epoch": 1.66, "learning_rate": 5.129763469119579e-06, "loss": 0.6659, "step": 10102 }, { "epoch": 1.66, "learning_rate": 5.127299605781867e-06, "loss": 0.3128, "step": 10103 }, { "epoch": 1.66, "learning_rate": 5.124835742444153e-06, "loss": 1.1821, "step": 10104 }, { "epoch": 1.66, "learning_rate": 5.122371879106439e-06, "loss": 0.1695, "step": 10105 }, { "epoch": 1.66, "learning_rate": 5.1199080157687254e-06, "loss": 0.4789, "step": 10106 }, { "epoch": 1.66, "learning_rate": 5.1174441524310114e-06, "loss": 0.1858, "step": 10107 }, { "epoch": 1.66, "learning_rate": 5.114980289093298e-06, "loss": 0.4537, "step": 10108 }, { "epoch": 1.66, "learning_rate": 5.112516425755585e-06, "loss": 0.6725, "step": 10109 }, { "epoch": 1.66, "learning_rate": 5.110052562417871e-06, "loss": 0.4273, "step": 10110 }, { "epoch": 1.66, "learning_rate": 5.107588699080158e-06, "loss": 0.4863, "step": 10111 }, { "epoch": 1.66, "learning_rate": 5.105124835742444e-06, "loss": 0.6303, "step": 10112 }, { "epoch": 1.66, "learning_rate": 5.102660972404731e-06, "loss": 0.363, "step": 10113 }, { "epoch": 1.66, "learning_rate": 5.1001971090670176e-06, "loss": 0.6365, "step": 10114 }, { "epoch": 1.66, "learning_rate": 5.0977332457293035e-06, "loss": 0.5064, "step": 10115 }, { "epoch": 1.66, "learning_rate": 5.09526938239159e-06, "loss": 0.6412, "step": 10116 }, { "epoch": 1.66, "learning_rate": 5.092805519053876e-06, "loss": 0.4039, "step": 10117 }, { "epoch": 1.66, "learning_rate": 5.090341655716163e-06, "loss": 0.2039, "step": 10118 }, { "epoch": 1.66, "learning_rate": 5.087877792378449e-06, "loss": 0.196, "step": 10119 }, { "epoch": 1.66, "learning_rate": 5.085413929040736e-06, "loss": 0.2987, "step": 10120 }, { "epoch": 1.66, "learning_rate": 5.082950065703023e-06, "loss": 0.7167, "step": 10121 }, { "epoch": 1.66, "learning_rate": 5.080486202365309e-06, "loss": 0.4717, "step": 10122 }, { "epoch": 1.66, "learning_rate": 5.078022339027596e-06, "loss": 0.7575, "step": 10123 }, { "epoch": 1.66, "learning_rate": 5.075558475689882e-06, "loss": 0.9236, "step": 10124 }, { "epoch": 1.66, "learning_rate": 5.073094612352168e-06, "loss": 0.3115, "step": 10125 }, { "epoch": 1.66, "learning_rate": 5.070630749014455e-06, "loss": 0.5784, "step": 10126 }, { "epoch": 1.66, "learning_rate": 5.068166885676741e-06, "loss": 0.745, "step": 10127 }, { "epoch": 1.66, "learning_rate": 5.065703022339028e-06, "loss": 1.1904, "step": 10128 }, { "epoch": 1.66, "learning_rate": 5.063239159001314e-06, "loss": 0.3358, "step": 10129 }, { "epoch": 1.66, "learning_rate": 5.0607752956636e-06, "loss": 0.7378, "step": 10130 }, { "epoch": 1.66, "learning_rate": 5.058311432325887e-06, "loss": 0.5903, "step": 10131 }, { "epoch": 1.66, "learning_rate": 5.055847568988174e-06, "loss": 0.3242, "step": 10132 }, { "epoch": 1.66, "learning_rate": 5.053383705650461e-06, "loss": 0.1472, "step": 10133 }, { "epoch": 1.66, "learning_rate": 5.0509198423127466e-06, "loss": 0.3296, "step": 10134 }, { "epoch": 1.66, "learning_rate": 5.0484559789750325e-06, "loss": 0.5168, "step": 10135 }, { "epoch": 1.66, "learning_rate": 5.045992115637319e-06, "loss": 0.6462, "step": 10136 }, { "epoch": 1.67, "learning_rate": 5.043528252299605e-06, "loss": 0.3254, "step": 10137 }, { "epoch": 1.67, "learning_rate": 5.041064388961893e-06, "loss": 0.4236, "step": 10138 }, { "epoch": 1.67, "learning_rate": 5.038600525624179e-06, "loss": 0.5886, "step": 10139 }, { "epoch": 1.67, "learning_rate": 5.036136662286465e-06, "loss": 0.7164, "step": 10140 }, { "epoch": 1.67, "learning_rate": 5.033672798948752e-06, "loss": 0.6402, "step": 10141 }, { "epoch": 1.67, "learning_rate": 5.031208935611038e-06, "loss": 0.3341, "step": 10142 }, { "epoch": 1.67, "learning_rate": 5.028745072273325e-06, "loss": 1.1077, "step": 10143 }, { "epoch": 1.67, "learning_rate": 5.0262812089356115e-06, "loss": 0.3965, "step": 10144 }, { "epoch": 1.67, "learning_rate": 5.0238173455978975e-06, "loss": 0.8046, "step": 10145 }, { "epoch": 1.67, "learning_rate": 5.021353482260184e-06, "loss": 0.4981, "step": 10146 }, { "epoch": 1.67, "learning_rate": 5.01888961892247e-06, "loss": 0.6487, "step": 10147 }, { "epoch": 1.67, "learning_rate": 5.016425755584757e-06, "loss": 0.2642, "step": 10148 }, { "epoch": 1.67, "learning_rate": 5.013961892247043e-06, "loss": 0.3178, "step": 10149 }, { "epoch": 1.67, "learning_rate": 5.01149802890933e-06, "loss": 0.4762, "step": 10150 }, { "epoch": 1.67, "learning_rate": 5.009034165571617e-06, "loss": 0.4841, "step": 10151 }, { "epoch": 1.67, "learning_rate": 5.006570302233903e-06, "loss": 0.336, "step": 10152 }, { "epoch": 1.67, "learning_rate": 5.00410643889619e-06, "loss": 0.5792, "step": 10153 }, { "epoch": 1.67, "learning_rate": 5.0016425755584756e-06, "loss": 1.1199, "step": 10154 }, { "epoch": 1.67, "learning_rate": 4.9991787122207616e-06, "loss": 0.7324, "step": 10155 }, { "epoch": 1.67, "learning_rate": 4.996714848883049e-06, "loss": 0.7489, "step": 10156 }, { "epoch": 1.67, "learning_rate": 4.994250985545335e-06, "loss": 0.6385, "step": 10157 }, { "epoch": 1.67, "learning_rate": 4.991787122207622e-06, "loss": 0.5727, "step": 10158 }, { "epoch": 1.67, "learning_rate": 4.989323258869908e-06, "loss": 0.6374, "step": 10159 }, { "epoch": 1.67, "learning_rate": 4.986859395532194e-06, "loss": 0.8322, "step": 10160 }, { "epoch": 1.67, "learning_rate": 4.984395532194481e-06, "loss": 0.3512, "step": 10161 }, { "epoch": 1.67, "learning_rate": 4.981931668856768e-06, "loss": 0.4111, "step": 10162 }, { "epoch": 1.67, "learning_rate": 4.9794678055190545e-06, "loss": 0.4266, "step": 10163 }, { "epoch": 1.67, "learning_rate": 4.9770039421813405e-06, "loss": 0.4136, "step": 10164 }, { "epoch": 1.67, "learning_rate": 4.9745400788436265e-06, "loss": 0.3236, "step": 10165 }, { "epoch": 1.67, "learning_rate": 4.972076215505913e-06, "loss": 0.335, "step": 10166 }, { "epoch": 1.67, "learning_rate": 4.969612352168199e-06, "loss": 0.4528, "step": 10167 }, { "epoch": 1.67, "learning_rate": 4.967148488830487e-06, "loss": 1.1212, "step": 10168 }, { "epoch": 1.67, "learning_rate": 4.964684625492773e-06, "loss": 0.4519, "step": 10169 }, { "epoch": 1.67, "learning_rate": 4.962220762155059e-06, "loss": 0.7941, "step": 10170 }, { "epoch": 1.67, "learning_rate": 4.959756898817346e-06, "loss": 0.1374, "step": 10171 }, { "epoch": 1.67, "learning_rate": 4.957293035479632e-06, "loss": 0.4718, "step": 10172 }, { "epoch": 1.67, "learning_rate": 4.954829172141919e-06, "loss": 0.4979, "step": 10173 }, { "epoch": 1.67, "learning_rate": 4.9523653088042054e-06, "loss": 1.1197, "step": 10174 }, { "epoch": 1.67, "learning_rate": 4.949901445466491e-06, "loss": 0.2995, "step": 10175 }, { "epoch": 1.67, "learning_rate": 4.947437582128778e-06, "loss": 0.5377, "step": 10176 }, { "epoch": 1.67, "learning_rate": 4.944973718791064e-06, "loss": 0.3107, "step": 10177 }, { "epoch": 1.67, "learning_rate": 4.942509855453351e-06, "loss": 0.3179, "step": 10178 }, { "epoch": 1.67, "learning_rate": 4.940045992115637e-06, "loss": 0.3257, "step": 10179 }, { "epoch": 1.67, "learning_rate": 4.937582128777924e-06, "loss": 0.6052, "step": 10180 }, { "epoch": 1.67, "learning_rate": 4.935118265440211e-06, "loss": 0.5041, "step": 10181 }, { "epoch": 1.67, "learning_rate": 4.932654402102497e-06, "loss": 0.3335, "step": 10182 }, { "epoch": 1.67, "learning_rate": 4.9301905387647835e-06, "loss": 0.372, "step": 10183 }, { "epoch": 1.67, "learning_rate": 4.9277266754270695e-06, "loss": 0.4796, "step": 10184 }, { "epoch": 1.67, "learning_rate": 4.9252628120893555e-06, "loss": 0.194, "step": 10185 }, { "epoch": 1.67, "learning_rate": 4.922798948751643e-06, "loss": 0.7891, "step": 10186 }, { "epoch": 1.67, "learning_rate": 4.920335085413929e-06, "loss": 0.7422, "step": 10187 }, { "epoch": 1.67, "learning_rate": 4.917871222076216e-06, "loss": 0.4054, "step": 10188 }, { "epoch": 1.67, "learning_rate": 4.915407358738502e-06, "loss": 0.4236, "step": 10189 }, { "epoch": 1.67, "learning_rate": 4.912943495400788e-06, "loss": 0.2927, "step": 10190 }, { "epoch": 1.67, "learning_rate": 4.910479632063075e-06, "loss": 0.3126, "step": 10191 }, { "epoch": 1.67, "learning_rate": 4.908015768725362e-06, "loss": 0.0453, "step": 10192 }, { "epoch": 1.67, "learning_rate": 4.9055519053876485e-06, "loss": 0.3892, "step": 10193 }, { "epoch": 1.67, "learning_rate": 4.9030880420499344e-06, "loss": 0.3646, "step": 10194 }, { "epoch": 1.67, "learning_rate": 4.90062417871222e-06, "loss": 0.2697, "step": 10195 }, { "epoch": 1.67, "learning_rate": 4.898160315374507e-06, "loss": 0.2352, "step": 10196 }, { "epoch": 1.67, "learning_rate": 4.895696452036793e-06, "loss": 0.1148, "step": 10197 }, { "epoch": 1.68, "learning_rate": 4.893232588699081e-06, "loss": 0.5326, "step": 10198 }, { "epoch": 1.68, "learning_rate": 4.890768725361367e-06, "loss": 0.7982, "step": 10199 }, { "epoch": 1.68, "learning_rate": 4.888304862023653e-06, "loss": 0.4643, "step": 10200 }, { "epoch": 1.68, "learning_rate": 4.88584099868594e-06, "loss": 0.4069, "step": 10201 }, { "epoch": 1.68, "learning_rate": 4.883377135348226e-06, "loss": 0.3354, "step": 10202 }, { "epoch": 1.68, "learning_rate": 4.8809132720105125e-06, "loss": 0.3146, "step": 10203 }, { "epoch": 1.68, "learning_rate": 4.878449408672799e-06, "loss": 0.4807, "step": 10204 }, { "epoch": 1.68, "learning_rate": 4.875985545335085e-06, "loss": 0.1594, "step": 10205 }, { "epoch": 1.68, "learning_rate": 4.873521681997372e-06, "loss": 0.5842, "step": 10206 }, { "epoch": 1.68, "learning_rate": 4.871057818659658e-06, "loss": 0.5147, "step": 10207 }, { "epoch": 1.68, "learning_rate": 4.868593955321945e-06, "loss": 0.409, "step": 10208 }, { "epoch": 1.68, "learning_rate": 4.866130091984231e-06, "loss": 0.3141, "step": 10209 }, { "epoch": 1.68, "learning_rate": 4.863666228646518e-06, "loss": 1.0009, "step": 10210 }, { "epoch": 1.68, "learning_rate": 4.861202365308805e-06, "loss": 0.4892, "step": 10211 }, { "epoch": 1.68, "learning_rate": 4.858738501971091e-06, "loss": 0.401, "step": 10212 }, { "epoch": 1.68, "learning_rate": 4.8562746386333775e-06, "loss": 0.4298, "step": 10213 }, { "epoch": 1.68, "learning_rate": 4.8538107752956634e-06, "loss": 0.4148, "step": 10214 }, { "epoch": 1.68, "learning_rate": 4.8513469119579494e-06, "loss": 0.8166, "step": 10215 }, { "epoch": 1.68, "learning_rate": 4.848883048620237e-06, "loss": 0.6141, "step": 10216 }, { "epoch": 1.68, "learning_rate": 4.846419185282523e-06, "loss": 0.5252, "step": 10217 }, { "epoch": 1.68, "learning_rate": 4.84395532194481e-06, "loss": 0.2837, "step": 10218 }, { "epoch": 1.68, "learning_rate": 4.841491458607096e-06, "loss": 0.5777, "step": 10219 }, { "epoch": 1.68, "learning_rate": 4.839027595269382e-06, "loss": 1.0005, "step": 10220 }, { "epoch": 1.68, "learning_rate": 4.836563731931669e-06, "loss": 1.216, "step": 10221 }, { "epoch": 1.68, "learning_rate": 4.8340998685939556e-06, "loss": 0.4708, "step": 10222 }, { "epoch": 1.68, "learning_rate": 4.831636005256242e-06, "loss": 0.9286, "step": 10223 }, { "epoch": 1.68, "learning_rate": 4.829172141918528e-06, "loss": 0.317, "step": 10224 }, { "epoch": 1.68, "learning_rate": 4.826708278580814e-06, "loss": 0.5627, "step": 10225 }, { "epoch": 1.68, "learning_rate": 4.824244415243101e-06, "loss": 0.6271, "step": 10226 }, { "epoch": 1.68, "learning_rate": 4.821780551905387e-06, "loss": 0.2657, "step": 10227 }, { "epoch": 1.68, "learning_rate": 4.819316688567675e-06, "loss": 0.3899, "step": 10228 }, { "epoch": 1.68, "learning_rate": 4.816852825229961e-06, "loss": 0.3158, "step": 10229 }, { "epoch": 1.68, "learning_rate": 4.814388961892247e-06, "loss": 0.1517, "step": 10230 }, { "epoch": 1.68, "learning_rate": 4.811925098554534e-06, "loss": 0.6751, "step": 10231 }, { "epoch": 1.68, "learning_rate": 4.80946123521682e-06, "loss": 0.5104, "step": 10232 }, { "epoch": 1.68, "learning_rate": 4.8069973718791065e-06, "loss": 0.4957, "step": 10233 }, { "epoch": 1.68, "learning_rate": 4.804533508541393e-06, "loss": 0.1162, "step": 10234 }, { "epoch": 1.68, "learning_rate": 4.802069645203679e-06, "loss": 0.2871, "step": 10235 }, { "epoch": 1.68, "learning_rate": 4.799605781865966e-06, "loss": 0.1763, "step": 10236 }, { "epoch": 1.68, "learning_rate": 4.797141918528252e-06, "loss": 0.972, "step": 10237 }, { "epoch": 1.68, "learning_rate": 4.794678055190539e-06, "loss": 0.472, "step": 10238 }, { "epoch": 1.68, "learning_rate": 4.792214191852825e-06, "loss": 0.4191, "step": 10239 }, { "epoch": 1.68, "learning_rate": 4.789750328515112e-06, "loss": 0.7059, "step": 10240 }, { "epoch": 1.68, "learning_rate": 4.787286465177399e-06, "loss": 0.2162, "step": 10241 }, { "epoch": 1.68, "learning_rate": 4.7848226018396846e-06, "loss": 0.2135, "step": 10242 }, { "epoch": 1.68, "learning_rate": 4.782358738501971e-06, "loss": 0.3561, "step": 10243 }, { "epoch": 1.68, "learning_rate": 4.779894875164257e-06, "loss": 0.2801, "step": 10244 }, { "epoch": 1.68, "learning_rate": 4.777431011826544e-06, "loss": 1.0426, "step": 10245 }, { "epoch": 1.68, "learning_rate": 4.774967148488831e-06, "loss": 0.3859, "step": 10246 }, { "epoch": 1.68, "learning_rate": 4.772503285151117e-06, "loss": 0.6568, "step": 10247 }, { "epoch": 1.68, "learning_rate": 4.770039421813404e-06, "loss": 0.443, "step": 10248 }, { "epoch": 1.68, "learning_rate": 4.76757555847569e-06, "loss": 0.352, "step": 10249 }, { "epoch": 1.68, "learning_rate": 4.765111695137976e-06, "loss": 0.6572, "step": 10250 }, { "epoch": 1.68, "learning_rate": 4.7626478318002635e-06, "loss": 0.938, "step": 10251 }, { "epoch": 1.68, "learning_rate": 4.7601839684625495e-06, "loss": 0.5928, "step": 10252 }, { "epoch": 1.68, "learning_rate": 4.757720105124836e-06, "loss": 0.7156, "step": 10253 }, { "epoch": 1.68, "learning_rate": 4.755256241787122e-06, "loss": 0.3416, "step": 10254 }, { "epoch": 1.68, "learning_rate": 4.752792378449408e-06, "loss": 1.1746, "step": 10255 }, { "epoch": 1.68, "learning_rate": 4.750328515111695e-06, "loss": 0.2839, "step": 10256 }, { "epoch": 1.68, "learning_rate": 4.747864651773982e-06, "loss": 0.4312, "step": 10257 }, { "epoch": 1.68, "learning_rate": 4.745400788436269e-06, "loss": 0.432, "step": 10258 }, { "epoch": 1.69, "learning_rate": 4.742936925098555e-06, "loss": 0.9306, "step": 10259 }, { "epoch": 1.69, "learning_rate": 4.740473061760841e-06, "loss": 0.4041, "step": 10260 }, { "epoch": 1.69, "learning_rate": 4.738009198423128e-06, "loss": 0.623, "step": 10261 }, { "epoch": 1.69, "learning_rate": 4.7355453350854136e-06, "loss": 0.8219, "step": 10262 }, { "epoch": 1.69, "learning_rate": 4.733081471747701e-06, "loss": 0.3933, "step": 10263 }, { "epoch": 1.69, "learning_rate": 4.730617608409987e-06, "loss": 0.2524, "step": 10264 }, { "epoch": 1.69, "learning_rate": 4.728153745072273e-06, "loss": 0.4485, "step": 10265 }, { "epoch": 1.69, "learning_rate": 4.72568988173456e-06, "loss": 0.5301, "step": 10266 }, { "epoch": 1.69, "learning_rate": 4.723226018396846e-06, "loss": 0.9619, "step": 10267 }, { "epoch": 1.69, "learning_rate": 4.720762155059133e-06, "loss": 0.4327, "step": 10268 }, { "epoch": 1.69, "learning_rate": 4.71829829172142e-06, "loss": 0.5904, "step": 10269 }, { "epoch": 1.69, "learning_rate": 4.715834428383706e-06, "loss": 0.4657, "step": 10270 }, { "epoch": 1.69, "learning_rate": 4.7133705650459925e-06, "loss": 0.293, "step": 10271 }, { "epoch": 1.69, "learning_rate": 4.7109067017082785e-06, "loss": 0.8205, "step": 10272 }, { "epoch": 1.69, "learning_rate": 4.708442838370565e-06, "loss": 0.638, "step": 10273 }, { "epoch": 1.69, "learning_rate": 4.705978975032851e-06, "loss": 0.5569, "step": 10274 }, { "epoch": 1.69, "learning_rate": 4.703515111695138e-06, "loss": 0.6994, "step": 10275 }, { "epoch": 1.69, "learning_rate": 4.701051248357425e-06, "loss": 0.3444, "step": 10276 }, { "epoch": 1.69, "learning_rate": 4.698587385019711e-06, "loss": 0.6783, "step": 10277 }, { "epoch": 1.69, "learning_rate": 4.696123521681998e-06, "loss": 0.284, "step": 10278 }, { "epoch": 1.69, "learning_rate": 4.693659658344284e-06, "loss": 0.2756, "step": 10279 }, { "epoch": 1.69, "learning_rate": 4.69119579500657e-06, "loss": 0.7854, "step": 10280 }, { "epoch": 1.69, "learning_rate": 4.6887319316688574e-06, "loss": 0.1845, "step": 10281 }, { "epoch": 1.69, "learning_rate": 4.6862680683311434e-06, "loss": 0.4147, "step": 10282 }, { "epoch": 1.69, "learning_rate": 4.68380420499343e-06, "loss": 0.6203, "step": 10283 }, { "epoch": 1.69, "learning_rate": 4.681340341655716e-06, "loss": 0.3443, "step": 10284 }, { "epoch": 1.69, "learning_rate": 4.678876478318002e-06, "loss": 0.3571, "step": 10285 }, { "epoch": 1.69, "learning_rate": 4.676412614980289e-06, "loss": 0.7596, "step": 10286 }, { "epoch": 1.69, "learning_rate": 4.673948751642576e-06, "loss": 0.4232, "step": 10287 }, { "epoch": 1.69, "learning_rate": 4.671484888304863e-06, "loss": 0.3424, "step": 10288 }, { "epoch": 1.69, "learning_rate": 4.669021024967149e-06, "loss": 0.3928, "step": 10289 }, { "epoch": 1.69, "learning_rate": 4.666557161629435e-06, "loss": 0.219, "step": 10290 }, { "epoch": 1.69, "learning_rate": 4.6640932982917215e-06, "loss": 1.003, "step": 10291 }, { "epoch": 1.69, "learning_rate": 4.6616294349540075e-06, "loss": 0.4859, "step": 10292 }, { "epoch": 1.69, "learning_rate": 4.659165571616295e-06, "loss": 0.524, "step": 10293 }, { "epoch": 1.69, "learning_rate": 4.656701708278581e-06, "loss": 0.6924, "step": 10294 }, { "epoch": 1.69, "learning_rate": 4.654237844940867e-06, "loss": 0.3918, "step": 10295 }, { "epoch": 1.69, "learning_rate": 4.651773981603154e-06, "loss": 0.351, "step": 10296 }, { "epoch": 1.69, "learning_rate": 4.64931011826544e-06, "loss": 0.3408, "step": 10297 }, { "epoch": 1.69, "learning_rate": 4.646846254927727e-06, "loss": 0.1136, "step": 10298 }, { "epoch": 1.69, "learning_rate": 4.644382391590014e-06, "loss": 0.5499, "step": 10299 }, { "epoch": 1.69, "learning_rate": 4.6419185282523e-06, "loss": 0.3754, "step": 10300 }, { "epoch": 1.69, "learning_rate": 4.6394546649145865e-06, "loss": 0.6255, "step": 10301 }, { "epoch": 1.69, "learning_rate": 4.6369908015768724e-06, "loss": 0.4446, "step": 10302 }, { "epoch": 1.69, "learning_rate": 4.634526938239159e-06, "loss": 0.6449, "step": 10303 }, { "epoch": 1.69, "learning_rate": 4.632063074901445e-06, "loss": 0.6619, "step": 10304 }, { "epoch": 1.69, "learning_rate": 4.629599211563732e-06, "loss": 0.4986, "step": 10305 }, { "epoch": 1.69, "learning_rate": 4.627135348226019e-06, "loss": 0.4524, "step": 10306 }, { "epoch": 1.69, "learning_rate": 4.624671484888305e-06, "loss": 0.3739, "step": 10307 }, { "epoch": 1.69, "learning_rate": 4.622207621550592e-06, "loss": 0.2272, "step": 10308 }, { "epoch": 1.69, "learning_rate": 4.619743758212878e-06, "loss": 0.5533, "step": 10309 }, { "epoch": 1.69, "learning_rate": 4.617279894875164e-06, "loss": 0.2964, "step": 10310 }, { "epoch": 1.69, "learning_rate": 4.614816031537451e-06, "loss": 0.6466, "step": 10311 }, { "epoch": 1.69, "learning_rate": 4.612352168199737e-06, "loss": 0.8167, "step": 10312 }, { "epoch": 1.69, "learning_rate": 4.609888304862024e-06, "loss": 0.3798, "step": 10313 }, { "epoch": 1.69, "learning_rate": 4.60742444152431e-06, "loss": 0.9059, "step": 10314 }, { "epoch": 1.69, "learning_rate": 4.604960578186596e-06, "loss": 0.4977, "step": 10315 }, { "epoch": 1.69, "learning_rate": 4.602496714848883e-06, "loss": 0.3315, "step": 10316 }, { "epoch": 1.69, "learning_rate": 4.60003285151117e-06, "loss": 0.5249, "step": 10317 }, { "epoch": 1.69, "learning_rate": 4.597568988173457e-06, "loss": 0.2222, "step": 10318 }, { "epoch": 1.69, "learning_rate": 4.595105124835743e-06, "loss": 0.507, "step": 10319 }, { "epoch": 1.7, "learning_rate": 4.592641261498029e-06, "loss": 0.4581, "step": 10320 }, { "epoch": 1.7, "learning_rate": 4.5901773981603155e-06, "loss": 0.938, "step": 10321 }, { "epoch": 1.7, "learning_rate": 4.5877135348226014e-06, "loss": 0.2734, "step": 10322 }, { "epoch": 1.7, "learning_rate": 4.585249671484889e-06, "loss": 0.2982, "step": 10323 }, { "epoch": 1.7, "learning_rate": 4.582785808147175e-06, "loss": 0.4971, "step": 10324 }, { "epoch": 1.7, "learning_rate": 4.580321944809461e-06, "loss": 0.3403, "step": 10325 }, { "epoch": 1.7, "learning_rate": 4.577858081471748e-06, "loss": 0.3772, "step": 10326 }, { "epoch": 1.7, "learning_rate": 4.575394218134034e-06, "loss": 0.7332, "step": 10327 }, { "epoch": 1.7, "learning_rate": 4.572930354796321e-06, "loss": 0.863, "step": 10328 }, { "epoch": 1.7, "learning_rate": 4.5704664914586076e-06, "loss": 0.2588, "step": 10329 }, { "epoch": 1.7, "learning_rate": 4.5680026281208936e-06, "loss": 0.7436, "step": 10330 }, { "epoch": 1.7, "learning_rate": 4.56553876478318e-06, "loss": 0.2355, "step": 10331 }, { "epoch": 1.7, "learning_rate": 4.563074901445466e-06, "loss": 0.5294, "step": 10332 }, { "epoch": 1.7, "learning_rate": 4.560611038107753e-06, "loss": 0.6919, "step": 10333 }, { "epoch": 1.7, "learning_rate": 4.558147174770039e-06, "loss": 0.4217, "step": 10334 }, { "epoch": 1.7, "learning_rate": 4.555683311432326e-06, "loss": 0.6001, "step": 10335 }, { "epoch": 1.7, "learning_rate": 4.553219448094613e-06, "loss": 0.3305, "step": 10336 }, { "epoch": 1.7, "learning_rate": 4.550755584756899e-06, "loss": 0.2789, "step": 10337 }, { "epoch": 1.7, "learning_rate": 4.548291721419186e-06, "loss": 0.3621, "step": 10338 }, { "epoch": 1.7, "learning_rate": 4.545827858081472e-06, "loss": 0.5638, "step": 10339 }, { "epoch": 1.7, "learning_rate": 4.543363994743758e-06, "loss": 0.3302, "step": 10340 }, { "epoch": 1.7, "learning_rate": 4.540900131406045e-06, "loss": 0.658, "step": 10341 }, { "epoch": 1.7, "learning_rate": 4.538436268068331e-06, "loss": 0.3253, "step": 10342 }, { "epoch": 1.7, "learning_rate": 4.535972404730618e-06, "loss": 0.8147, "step": 10343 }, { "epoch": 1.7, "learning_rate": 4.533508541392904e-06, "loss": 0.6065, "step": 10344 }, { "epoch": 1.7, "learning_rate": 4.53104467805519e-06, "loss": 0.4569, "step": 10345 }, { "epoch": 1.7, "learning_rate": 4.528580814717477e-06, "loss": 0.4856, "step": 10346 }, { "epoch": 1.7, "learning_rate": 4.526116951379764e-06, "loss": 0.4397, "step": 10347 }, { "epoch": 1.7, "learning_rate": 4.523653088042051e-06, "loss": 0.4367, "step": 10348 }, { "epoch": 1.7, "learning_rate": 4.521189224704337e-06, "loss": 0.4159, "step": 10349 }, { "epoch": 1.7, "learning_rate": 4.5187253613666226e-06, "loss": 0.5032, "step": 10350 }, { "epoch": 1.7, "learning_rate": 4.516261498028909e-06, "loss": 0.5032, "step": 10351 }, { "epoch": 1.7, "learning_rate": 4.513797634691195e-06, "loss": 0.2624, "step": 10352 }, { "epoch": 1.7, "learning_rate": 4.511333771353483e-06, "loss": 0.5815, "step": 10353 }, { "epoch": 1.7, "learning_rate": 4.508869908015769e-06, "loss": 0.2376, "step": 10354 }, { "epoch": 1.7, "learning_rate": 4.506406044678055e-06, "loss": 0.3955, "step": 10355 }, { "epoch": 1.7, "learning_rate": 4.503942181340342e-06, "loss": 0.4812, "step": 10356 }, { "epoch": 1.7, "learning_rate": 4.501478318002628e-06, "loss": 0.4644, "step": 10357 }, { "epoch": 1.7, "learning_rate": 4.499014454664915e-06, "loss": 0.6469, "step": 10358 }, { "epoch": 1.7, "learning_rate": 4.4965505913272015e-06, "loss": 0.5013, "step": 10359 }, { "epoch": 1.7, "learning_rate": 4.4940867279894875e-06, "loss": 0.3038, "step": 10360 }, { "epoch": 1.7, "learning_rate": 4.491622864651774e-06, "loss": 0.4182, "step": 10361 }, { "epoch": 1.7, "learning_rate": 4.48915900131406e-06, "loss": 0.5911, "step": 10362 }, { "epoch": 1.7, "learning_rate": 4.486695137976347e-06, "loss": 0.4749, "step": 10363 }, { "epoch": 1.7, "learning_rate": 4.484231274638633e-06, "loss": 0.5833, "step": 10364 }, { "epoch": 1.7, "learning_rate": 4.48176741130092e-06, "loss": 0.4018, "step": 10365 }, { "epoch": 1.7, "learning_rate": 4.479303547963207e-06, "loss": 0.2917, "step": 10366 }, { "epoch": 1.7, "learning_rate": 4.476839684625493e-06, "loss": 1.1083, "step": 10367 }, { "epoch": 1.7, "learning_rate": 4.47437582128778e-06, "loss": 0.4511, "step": 10368 }, { "epoch": 1.7, "learning_rate": 4.471911957950066e-06, "loss": 0.4195, "step": 10369 }, { "epoch": 1.7, "learning_rate": 4.4694480946123516e-06, "loss": 0.5474, "step": 10370 }, { "epoch": 1.7, "learning_rate": 4.466984231274639e-06, "loss": 0.3581, "step": 10371 }, { "epoch": 1.7, "learning_rate": 4.464520367936925e-06, "loss": 0.4808, "step": 10372 }, { "epoch": 1.7, "learning_rate": 4.462056504599212e-06, "loss": 0.3156, "step": 10373 }, { "epoch": 1.7, "learning_rate": 4.459592641261498e-06, "loss": 0.3001, "step": 10374 }, { "epoch": 1.7, "learning_rate": 4.457128777923784e-06, "loss": 0.4112, "step": 10375 }, { "epoch": 1.7, "learning_rate": 4.454664914586071e-06, "loss": 0.1649, "step": 10376 }, { "epoch": 1.7, "learning_rate": 4.452201051248358e-06, "loss": 0.2387, "step": 10377 }, { "epoch": 1.7, "learning_rate": 4.4497371879106445e-06, "loss": 1.1282, "step": 10378 }, { "epoch": 1.7, "learning_rate": 4.4472733245729305e-06, "loss": 0.3543, "step": 10379 }, { "epoch": 1.7, "learning_rate": 4.4448094612352165e-06, "loss": 0.2956, "step": 10380 }, { "epoch": 1.71, "learning_rate": 4.442345597897503e-06, "loss": 0.4644, "step": 10381 }, { "epoch": 1.71, "learning_rate": 4.439881734559789e-06, "loss": 0.3518, "step": 10382 }, { "epoch": 1.71, "learning_rate": 4.437417871222077e-06, "loss": 0.3885, "step": 10383 }, { "epoch": 1.71, "learning_rate": 4.434954007884363e-06, "loss": 0.5057, "step": 10384 }, { "epoch": 1.71, "learning_rate": 4.432490144546649e-06, "loss": 0.9686, "step": 10385 }, { "epoch": 1.71, "learning_rate": 4.430026281208936e-06, "loss": 0.4783, "step": 10386 }, { "epoch": 1.71, "learning_rate": 4.427562417871222e-06, "loss": 0.246, "step": 10387 }, { "epoch": 1.71, "learning_rate": 4.425098554533509e-06, "loss": 0.302, "step": 10388 }, { "epoch": 1.71, "learning_rate": 4.4226346911957954e-06, "loss": 0.8044, "step": 10389 }, { "epoch": 1.71, "learning_rate": 4.4201708278580814e-06, "loss": 0.7153, "step": 10390 }, { "epoch": 1.71, "learning_rate": 4.417706964520368e-06, "loss": 0.2333, "step": 10391 }, { "epoch": 1.71, "learning_rate": 4.415243101182654e-06, "loss": 0.3547, "step": 10392 }, { "epoch": 1.71, "learning_rate": 4.412779237844941e-06, "loss": 0.3087, "step": 10393 }, { "epoch": 1.71, "learning_rate": 4.410315374507228e-06, "loss": 0.2584, "step": 10394 }, { "epoch": 1.71, "learning_rate": 4.407851511169514e-06, "loss": 0.1377, "step": 10395 }, { "epoch": 1.71, "learning_rate": 4.405387647831801e-06, "loss": 0.2106, "step": 10396 }, { "epoch": 1.71, "learning_rate": 4.402923784494087e-06, "loss": 0.9256, "step": 10397 }, { "epoch": 1.71, "learning_rate": 4.4004599211563735e-06, "loss": 0.5833, "step": 10398 }, { "epoch": 1.71, "learning_rate": 4.3979960578186595e-06, "loss": 0.4164, "step": 10399 }, { "epoch": 1.71, "learning_rate": 4.395532194480946e-06, "loss": 0.462, "step": 10400 }, { "epoch": 1.71, "learning_rate": 4.393068331143233e-06, "loss": 0.5805, "step": 10401 }, { "epoch": 1.71, "learning_rate": 4.390604467805519e-06, "loss": 0.752, "step": 10402 }, { "epoch": 1.71, "learning_rate": 4.388140604467806e-06, "loss": 0.3762, "step": 10403 }, { "epoch": 1.71, "learning_rate": 4.385676741130092e-06, "loss": 0.3771, "step": 10404 }, { "epoch": 1.71, "learning_rate": 4.383212877792378e-06, "loss": 0.4739, "step": 10405 }, { "epoch": 1.71, "learning_rate": 4.380749014454666e-06, "loss": 0.4177, "step": 10406 }, { "epoch": 1.71, "learning_rate": 4.378285151116952e-06, "loss": 0.5851, "step": 10407 }, { "epoch": 1.71, "learning_rate": 4.3758212877792385e-06, "loss": 0.2492, "step": 10408 }, { "epoch": 1.71, "learning_rate": 4.3733574244415245e-06, "loss": 0.6576, "step": 10409 }, { "epoch": 1.71, "learning_rate": 4.3708935611038104e-06, "loss": 0.389, "step": 10410 }, { "epoch": 1.71, "learning_rate": 4.368429697766097e-06, "loss": 0.5147, "step": 10411 }, { "epoch": 1.71, "learning_rate": 4.365965834428384e-06, "loss": 0.5702, "step": 10412 }, { "epoch": 1.71, "learning_rate": 4.363501971090671e-06, "loss": 0.3806, "step": 10413 }, { "epoch": 1.71, "learning_rate": 4.361038107752957e-06, "loss": 0.741, "step": 10414 }, { "epoch": 1.71, "learning_rate": 4.358574244415243e-06, "loss": 0.6759, "step": 10415 }, { "epoch": 1.71, "learning_rate": 4.35611038107753e-06, "loss": 0.5232, "step": 10416 }, { "epoch": 1.71, "learning_rate": 4.353646517739816e-06, "loss": 0.7515, "step": 10417 }, { "epoch": 1.71, "learning_rate": 4.351182654402103e-06, "loss": 0.8419, "step": 10418 }, { "epoch": 1.71, "learning_rate": 4.348718791064389e-06, "loss": 0.6894, "step": 10419 }, { "epoch": 1.71, "learning_rate": 4.346254927726675e-06, "loss": 0.3536, "step": 10420 }, { "epoch": 1.71, "learning_rate": 4.343791064388962e-06, "loss": 0.3405, "step": 10421 }, { "epoch": 1.71, "learning_rate": 4.341327201051248e-06, "loss": 0.2415, "step": 10422 }, { "epoch": 1.71, "learning_rate": 4.338863337713535e-06, "loss": 0.6659, "step": 10423 }, { "epoch": 1.71, "learning_rate": 4.336399474375822e-06, "loss": 0.2051, "step": 10424 }, { "epoch": 1.71, "learning_rate": 4.333935611038108e-06, "loss": 0.9094, "step": 10425 }, { "epoch": 1.71, "learning_rate": 4.331471747700395e-06, "loss": 0.4083, "step": 10426 }, { "epoch": 1.71, "learning_rate": 4.329007884362681e-06, "loss": 0.452, "step": 10427 }, { "epoch": 1.71, "learning_rate": 4.3265440210249675e-06, "loss": 0.376, "step": 10428 }, { "epoch": 1.71, "learning_rate": 4.3240801576872535e-06, "loss": 0.447, "step": 10429 }, { "epoch": 1.71, "learning_rate": 4.32161629434954e-06, "loss": 0.2541, "step": 10430 }, { "epoch": 1.71, "learning_rate": 4.319152431011827e-06, "loss": 0.3606, "step": 10431 }, { "epoch": 1.71, "learning_rate": 4.316688567674113e-06, "loss": 0.4841, "step": 10432 }, { "epoch": 1.71, "learning_rate": 4.3142247043364e-06, "loss": 0.3048, "step": 10433 }, { "epoch": 1.71, "learning_rate": 4.311760840998686e-06, "loss": 0.3697, "step": 10434 }, { "epoch": 1.71, "learning_rate": 4.309296977660972e-06, "loss": 0.3776, "step": 10435 }, { "epoch": 1.71, "learning_rate": 4.30683311432326e-06, "loss": 0.398, "step": 10436 }, { "epoch": 1.71, "learning_rate": 4.3043692509855456e-06, "loss": 0.5807, "step": 10437 }, { "epoch": 1.71, "learning_rate": 4.301905387647832e-06, "loss": 0.1488, "step": 10438 }, { "epoch": 1.71, "learning_rate": 4.299441524310118e-06, "loss": 0.2251, "step": 10439 }, { "epoch": 1.71, "learning_rate": 4.296977660972404e-06, "loss": 0.7152, "step": 10440 }, { "epoch": 1.72, "learning_rate": 4.294513797634691e-06, "loss": 0.8123, "step": 10441 }, { "epoch": 1.72, "learning_rate": 4.292049934296978e-06, "loss": 0.5763, "step": 10442 }, { "epoch": 1.72, "learning_rate": 4.289586070959265e-06, "loss": 0.3145, "step": 10443 }, { "epoch": 1.72, "learning_rate": 4.287122207621551e-06, "loss": 0.6272, "step": 10444 }, { "epoch": 1.72, "learning_rate": 4.284658344283837e-06, "loss": 0.3636, "step": 10445 }, { "epoch": 1.72, "learning_rate": 4.282194480946124e-06, "loss": 0.4905, "step": 10446 }, { "epoch": 1.72, "learning_rate": 4.27973061760841e-06, "loss": 0.3661, "step": 10447 }, { "epoch": 1.72, "learning_rate": 4.277266754270697e-06, "loss": 0.9252, "step": 10448 }, { "epoch": 1.72, "learning_rate": 4.274802890932983e-06, "loss": 0.4821, "step": 10449 }, { "epoch": 1.72, "learning_rate": 4.272339027595269e-06, "loss": 0.6917, "step": 10450 }, { "epoch": 1.72, "learning_rate": 4.269875164257556e-06, "loss": 0.1709, "step": 10451 }, { "epoch": 1.72, "learning_rate": 4.267411300919842e-06, "loss": 0.7778, "step": 10452 }, { "epoch": 1.72, "learning_rate": 4.264947437582129e-06, "loss": 0.4771, "step": 10453 }, { "epoch": 1.72, "learning_rate": 4.262483574244416e-06, "loss": 0.2518, "step": 10454 }, { "epoch": 1.72, "learning_rate": 4.260019710906702e-06, "loss": 0.7448, "step": 10455 }, { "epoch": 1.72, "learning_rate": 4.257555847568989e-06, "loss": 0.7018, "step": 10456 }, { "epoch": 1.72, "learning_rate": 4.255091984231275e-06, "loss": 0.1838, "step": 10457 }, { "epoch": 1.72, "learning_rate": 4.252628120893561e-06, "loss": 0.8226, "step": 10458 }, { "epoch": 1.72, "learning_rate": 4.250164257555847e-06, "loss": 0.2919, "step": 10459 }, { "epoch": 1.72, "learning_rate": 4.247700394218134e-06, "loss": 0.4692, "step": 10460 }, { "epoch": 1.72, "learning_rate": 4.245236530880421e-06, "loss": 0.4612, "step": 10461 }, { "epoch": 1.72, "learning_rate": 4.242772667542707e-06, "loss": 0.5904, "step": 10462 }, { "epoch": 1.72, "learning_rate": 4.240308804204994e-06, "loss": 0.1519, "step": 10463 }, { "epoch": 1.72, "learning_rate": 4.23784494086728e-06, "loss": 0.7133, "step": 10464 }, { "epoch": 1.72, "learning_rate": 4.235381077529566e-06, "loss": 0.3717, "step": 10465 }, { "epoch": 1.72, "learning_rate": 4.2329172141918535e-06, "loss": 0.6653, "step": 10466 }, { "epoch": 1.72, "learning_rate": 4.2304533508541395e-06, "loss": 0.3554, "step": 10467 }, { "epoch": 1.72, "learning_rate": 4.227989487516426e-06, "loss": 0.3801, "step": 10468 }, { "epoch": 1.72, "learning_rate": 4.225525624178712e-06, "loss": 0.5787, "step": 10469 }, { "epoch": 1.72, "learning_rate": 4.223061760840998e-06, "loss": 0.3682, "step": 10470 }, { "epoch": 1.72, "learning_rate": 4.220597897503285e-06, "loss": 0.3218, "step": 10471 }, { "epoch": 1.72, "learning_rate": 4.218134034165572e-06, "loss": 0.3418, "step": 10472 }, { "epoch": 1.72, "learning_rate": 4.215670170827858e-06, "loss": 0.3973, "step": 10473 }, { "epoch": 1.72, "learning_rate": 4.213206307490145e-06, "loss": 0.5667, "step": 10474 }, { "epoch": 1.72, "learning_rate": 4.210742444152431e-06, "loss": 0.3838, "step": 10475 }, { "epoch": 1.72, "learning_rate": 4.208278580814718e-06, "loss": 0.6061, "step": 10476 }, { "epoch": 1.72, "learning_rate": 4.205814717477004e-06, "loss": 0.7021, "step": 10477 }, { "epoch": 1.72, "learning_rate": 4.20335085413929e-06, "loss": 0.4636, "step": 10478 }, { "epoch": 1.72, "learning_rate": 4.200886990801577e-06, "loss": 0.3083, "step": 10479 }, { "epoch": 1.72, "learning_rate": 4.198423127463863e-06, "loss": 0.2808, "step": 10480 }, { "epoch": 1.72, "learning_rate": 4.19595926412615e-06, "loss": 0.3533, "step": 10481 }, { "epoch": 1.72, "learning_rate": 4.193495400788436e-06, "loss": 0.5652, "step": 10482 }, { "epoch": 1.72, "learning_rate": 4.191031537450722e-06, "loss": 0.4159, "step": 10483 }, { "epoch": 1.72, "learning_rate": 4.18856767411301e-06, "loss": 0.7404, "step": 10484 }, { "epoch": 1.72, "learning_rate": 4.186103810775296e-06, "loss": 1.0483, "step": 10485 }, { "epoch": 1.72, "learning_rate": 4.1836399474375825e-06, "loss": 0.6101, "step": 10486 }, { "epoch": 1.72, "learning_rate": 4.1811760840998685e-06, "loss": 0.6908, "step": 10487 }, { "epoch": 1.72, "learning_rate": 4.1787122207621545e-06, "loss": 0.1771, "step": 10488 }, { "epoch": 1.72, "learning_rate": 4.176248357424441e-06, "loss": 0.5532, "step": 10489 }, { "epoch": 1.72, "learning_rate": 4.173784494086728e-06, "loss": 0.4425, "step": 10490 }, { "epoch": 1.72, "learning_rate": 4.171320630749015e-06, "loss": 0.3799, "step": 10491 }, { "epoch": 1.72, "learning_rate": 4.168856767411301e-06, "loss": 1.0121, "step": 10492 }, { "epoch": 1.72, "learning_rate": 4.166392904073587e-06, "loss": 0.3776, "step": 10493 }, { "epoch": 1.72, "learning_rate": 4.163929040735874e-06, "loss": 0.2722, "step": 10494 }, { "epoch": 1.72, "learning_rate": 4.16146517739816e-06, "loss": 0.5188, "step": 10495 }, { "epoch": 1.72, "learning_rate": 4.1590013140604475e-06, "loss": 0.6821, "step": 10496 }, { "epoch": 1.72, "learning_rate": 4.1565374507227334e-06, "loss": 0.3824, "step": 10497 }, { "epoch": 1.72, "learning_rate": 4.1540735873850194e-06, "loss": 0.8567, "step": 10498 }, { "epoch": 1.72, "learning_rate": 4.151609724047306e-06, "loss": 0.5625, "step": 10499 }, { "epoch": 1.72, "learning_rate": 4.149145860709592e-06, "loss": 0.7485, "step": 10500 }, { "epoch": 1.72, "eval_exact_match": 86.92526017029329, "eval_f1": 92.98476014431553, "step": 10500 }, { "epoch": 1.72, "learning_rate": 4.146681997371879e-06, "loss": 0.2844, "step": 10501 }, { "epoch": 1.73, "learning_rate": 4.144218134034166e-06, "loss": 0.1574, "step": 10502 }, { "epoch": 1.73, "learning_rate": 4.141754270696452e-06, "loss": 0.3801, "step": 10503 }, { "epoch": 1.73, "learning_rate": 4.139290407358739e-06, "loss": 0.5593, "step": 10504 }, { "epoch": 1.73, "learning_rate": 4.136826544021025e-06, "loss": 0.3107, "step": 10505 }, { "epoch": 1.73, "learning_rate": 4.1343626806833115e-06, "loss": 0.3094, "step": 10506 }, { "epoch": 1.73, "learning_rate": 4.1318988173455975e-06, "loss": 0.3487, "step": 10507 }, { "epoch": 1.73, "learning_rate": 4.129434954007884e-06, "loss": 0.7156, "step": 10508 }, { "epoch": 1.73, "learning_rate": 4.126971090670171e-06, "loss": 0.5381, "step": 10509 }, { "epoch": 1.73, "learning_rate": 4.124507227332457e-06, "loss": 0.2329, "step": 10510 }, { "epoch": 1.73, "learning_rate": 4.122043363994744e-06, "loss": 0.6173, "step": 10511 }, { "epoch": 1.73, "learning_rate": 4.11957950065703e-06, "loss": 0.5449, "step": 10512 }, { "epoch": 1.73, "learning_rate": 4.117115637319316e-06, "loss": 0.1767, "step": 10513 }, { "epoch": 1.73, "learning_rate": 4.114651773981604e-06, "loss": 0.5413, "step": 10514 }, { "epoch": 1.73, "learning_rate": 4.11218791064389e-06, "loss": 0.4507, "step": 10515 }, { "epoch": 1.73, "learning_rate": 4.1097240473061765e-06, "loss": 0.7188, "step": 10516 }, { "epoch": 1.73, "learning_rate": 4.1072601839684625e-06, "loss": 0.3515, "step": 10517 }, { "epoch": 1.73, "learning_rate": 4.1047963206307484e-06, "loss": 0.3127, "step": 10518 }, { "epoch": 1.73, "learning_rate": 4.102332457293035e-06, "loss": 0.4433, "step": 10519 }, { "epoch": 1.73, "learning_rate": 4.099868593955322e-06, "loss": 0.6669, "step": 10520 }, { "epoch": 1.73, "learning_rate": 4.097404730617609e-06, "loss": 0.4278, "step": 10521 }, { "epoch": 1.73, "learning_rate": 4.094940867279895e-06, "loss": 0.1175, "step": 10522 }, { "epoch": 1.73, "learning_rate": 4.092477003942181e-06, "loss": 0.6661, "step": 10523 }, { "epoch": 1.73, "learning_rate": 4.090013140604468e-06, "loss": 0.939, "step": 10524 }, { "epoch": 1.73, "learning_rate": 4.0875492772667546e-06, "loss": 0.443, "step": 10525 }, { "epoch": 1.73, "learning_rate": 4.085085413929041e-06, "loss": 0.1921, "step": 10526 }, { "epoch": 1.73, "learning_rate": 4.082621550591327e-06, "loss": 0.0955, "step": 10527 }, { "epoch": 1.73, "learning_rate": 4.080157687253613e-06, "loss": 0.6154, "step": 10528 }, { "epoch": 1.73, "learning_rate": 4.0776938239159e-06, "loss": 0.8351, "step": 10529 }, { "epoch": 1.73, "learning_rate": 4.075229960578186e-06, "loss": 0.916, "step": 10530 }, { "epoch": 1.73, "learning_rate": 4.072766097240474e-06, "loss": 0.5136, "step": 10531 }, { "epoch": 1.73, "learning_rate": 4.07030223390276e-06, "loss": 0.3852, "step": 10532 }, { "epoch": 1.73, "learning_rate": 4.067838370565046e-06, "loss": 0.5886, "step": 10533 }, { "epoch": 1.73, "learning_rate": 4.065374507227333e-06, "loss": 0.3523, "step": 10534 }, { "epoch": 1.73, "learning_rate": 4.062910643889619e-06, "loss": 0.3585, "step": 10535 }, { "epoch": 1.73, "learning_rate": 4.0604467805519055e-06, "loss": 0.9429, "step": 10536 }, { "epoch": 1.73, "learning_rate": 4.057982917214192e-06, "loss": 0.8761, "step": 10537 }, { "epoch": 1.73, "learning_rate": 4.055519053876478e-06, "loss": 0.3427, "step": 10538 }, { "epoch": 1.73, "learning_rate": 4.053055190538765e-06, "loss": 0.3826, "step": 10539 }, { "epoch": 1.73, "learning_rate": 4.050591327201051e-06, "loss": 0.5072, "step": 10540 }, { "epoch": 1.73, "learning_rate": 4.048127463863338e-06, "loss": 1.0473, "step": 10541 }, { "epoch": 1.73, "learning_rate": 4.045663600525624e-06, "loss": 0.4359, "step": 10542 }, { "epoch": 1.73, "learning_rate": 4.043199737187911e-06, "loss": 0.6188, "step": 10543 }, { "epoch": 1.73, "learning_rate": 4.040735873850198e-06, "loss": 0.6657, "step": 10544 }, { "epoch": 1.73, "learning_rate": 4.0382720105124836e-06, "loss": 0.5408, "step": 10545 }, { "epoch": 1.73, "learning_rate": 4.03580814717477e-06, "loss": 0.2555, "step": 10546 }, { "epoch": 1.73, "learning_rate": 4.033344283837056e-06, "loss": 0.3252, "step": 10547 }, { "epoch": 1.73, "learning_rate": 4.030880420499342e-06, "loss": 0.4817, "step": 10548 }, { "epoch": 1.73, "learning_rate": 4.02841655716163e-06, "loss": 0.2676, "step": 10549 }, { "epoch": 1.73, "learning_rate": 4.025952693823916e-06, "loss": 0.3927, "step": 10550 }, { "epoch": 1.73, "learning_rate": 4.023488830486203e-06, "loss": 0.8578, "step": 10551 }, { "epoch": 1.73, "learning_rate": 4.021024967148489e-06, "loss": 0.4905, "step": 10552 }, { "epoch": 1.73, "learning_rate": 4.018561103810775e-06, "loss": 0.4117, "step": 10553 }, { "epoch": 1.73, "learning_rate": 4.016097240473062e-06, "loss": 0.5506, "step": 10554 }, { "epoch": 1.73, "learning_rate": 4.0136333771353485e-06, "loss": 0.2861, "step": 10555 }, { "epoch": 1.73, "learning_rate": 4.011169513797635e-06, "loss": 0.7039, "step": 10556 }, { "epoch": 1.73, "learning_rate": 4.008705650459921e-06, "loss": 0.244, "step": 10557 }, { "epoch": 1.73, "learning_rate": 4.006241787122207e-06, "loss": 0.2713, "step": 10558 }, { "epoch": 1.73, "learning_rate": 4.003777923784494e-06, "loss": 0.7973, "step": 10559 }, { "epoch": 1.73, "learning_rate": 4.00131406044678e-06, "loss": 0.3628, "step": 10560 }, { "epoch": 1.73, "learning_rate": 3.998850197109068e-06, "loss": 0.1727, "step": 10561 }, { "epoch": 1.73, "learning_rate": 3.996386333771354e-06, "loss": 0.7841, "step": 10562 }, { "epoch": 1.74, "learning_rate": 3.99392247043364e-06, "loss": 0.7546, "step": 10563 }, { "epoch": 1.74, "learning_rate": 3.991458607095927e-06, "loss": 0.2615, "step": 10564 }, { "epoch": 1.74, "learning_rate": 3.988994743758213e-06, "loss": 0.3478, "step": 10565 }, { "epoch": 1.74, "learning_rate": 3.986530880420499e-06, "loss": 0.5984, "step": 10566 }, { "epoch": 1.74, "learning_rate": 3.984067017082786e-06, "loss": 0.4287, "step": 10567 }, { "epoch": 1.74, "learning_rate": 3.981603153745072e-06, "loss": 0.8042, "step": 10568 }, { "epoch": 1.74, "learning_rate": 3.979139290407359e-06, "loss": 0.4202, "step": 10569 }, { "epoch": 1.74, "learning_rate": 3.976675427069645e-06, "loss": 0.7573, "step": 10570 }, { "epoch": 1.74, "learning_rate": 3.974211563731932e-06, "loss": 0.2177, "step": 10571 }, { "epoch": 1.74, "learning_rate": 3.971747700394218e-06, "loss": 0.2562, "step": 10572 }, { "epoch": 1.74, "learning_rate": 3.969283837056505e-06, "loss": 0.2237, "step": 10573 }, { "epoch": 1.74, "learning_rate": 3.9668199737187915e-06, "loss": 0.396, "step": 10574 }, { "epoch": 1.74, "learning_rate": 3.9643561103810775e-06, "loss": 0.2735, "step": 10575 }, { "epoch": 1.74, "learning_rate": 3.961892247043364e-06, "loss": 0.3276, "step": 10576 }, { "epoch": 1.74, "learning_rate": 3.95942838370565e-06, "loss": 0.7557, "step": 10577 }, { "epoch": 1.74, "learning_rate": 3.956964520367936e-06, "loss": 0.5199, "step": 10578 }, { "epoch": 1.74, "learning_rate": 3.954500657030224e-06, "loss": 0.4408, "step": 10579 }, { "epoch": 1.74, "learning_rate": 3.95203679369251e-06, "loss": 0.6027, "step": 10580 }, { "epoch": 1.74, "learning_rate": 3.949572930354797e-06, "loss": 0.4623, "step": 10581 }, { "epoch": 1.74, "learning_rate": 3.947109067017083e-06, "loss": 1.0575, "step": 10582 }, { "epoch": 1.74, "learning_rate": 3.944645203679369e-06, "loss": 0.6684, "step": 10583 }, { "epoch": 1.74, "learning_rate": 3.942181340341656e-06, "loss": 0.2455, "step": 10584 }, { "epoch": 1.74, "learning_rate": 3.9397174770039424e-06, "loss": 0.8722, "step": 10585 }, { "epoch": 1.74, "learning_rate": 3.937253613666229e-06, "loss": 0.5009, "step": 10586 }, { "epoch": 1.74, "learning_rate": 3.934789750328515e-06, "loss": 0.1943, "step": 10587 }, { "epoch": 1.74, "learning_rate": 3.932325886990801e-06, "loss": 0.2253, "step": 10588 }, { "epoch": 1.74, "learning_rate": 3.929862023653088e-06, "loss": 0.5598, "step": 10589 }, { "epoch": 1.74, "learning_rate": 3.927398160315374e-06, "loss": 0.4699, "step": 10590 }, { "epoch": 1.74, "learning_rate": 3.924934296977662e-06, "loss": 0.6096, "step": 10591 }, { "epoch": 1.74, "learning_rate": 3.922470433639948e-06, "loss": 0.3551, "step": 10592 }, { "epoch": 1.74, "learning_rate": 3.920006570302234e-06, "loss": 0.8471, "step": 10593 }, { "epoch": 1.74, "learning_rate": 3.9175427069645205e-06, "loss": 0.8483, "step": 10594 }, { "epoch": 1.74, "learning_rate": 3.9150788436268065e-06, "loss": 0.3873, "step": 10595 }, { "epoch": 1.74, "learning_rate": 3.912614980289093e-06, "loss": 0.6594, "step": 10596 }, { "epoch": 1.74, "learning_rate": 3.91015111695138e-06, "loss": 0.4238, "step": 10597 }, { "epoch": 1.74, "learning_rate": 3.907687253613666e-06, "loss": 0.4852, "step": 10598 }, { "epoch": 1.74, "learning_rate": 3.905223390275953e-06, "loss": 0.3574, "step": 10599 }, { "epoch": 1.74, "learning_rate": 3.902759526938239e-06, "loss": 0.5573, "step": 10600 }, { "epoch": 1.74, "learning_rate": 3.900295663600526e-06, "loss": 1.1437, "step": 10601 }, { "epoch": 1.74, "learning_rate": 3.897831800262812e-06, "loss": 0.1863, "step": 10602 }, { "epoch": 1.74, "learning_rate": 3.895367936925099e-06, "loss": 0.4138, "step": 10603 }, { "epoch": 1.74, "learning_rate": 3.8929040735873855e-06, "loss": 0.5087, "step": 10604 }, { "epoch": 1.74, "learning_rate": 3.8904402102496714e-06, "loss": 0.6211, "step": 10605 }, { "epoch": 1.74, "learning_rate": 3.887976346911958e-06, "loss": 0.255, "step": 10606 }, { "epoch": 1.74, "learning_rate": 3.885512483574244e-06, "loss": 0.48, "step": 10607 }, { "epoch": 1.74, "learning_rate": 3.88304862023653e-06, "loss": 0.9858, "step": 10608 }, { "epoch": 1.74, "learning_rate": 3.880584756898818e-06, "loss": 0.6354, "step": 10609 }, { "epoch": 1.74, "learning_rate": 3.878120893561104e-06, "loss": 0.4593, "step": 10610 }, { "epoch": 1.74, "learning_rate": 3.875657030223391e-06, "loss": 0.4017, "step": 10611 }, { "epoch": 1.74, "learning_rate": 3.873193166885677e-06, "loss": 0.4866, "step": 10612 }, { "epoch": 1.74, "learning_rate": 3.870729303547963e-06, "loss": 0.6557, "step": 10613 }, { "epoch": 1.74, "learning_rate": 3.8682654402102495e-06, "loss": 0.2334, "step": 10614 }, { "epoch": 1.74, "learning_rate": 3.865801576872536e-06, "loss": 0.3939, "step": 10615 }, { "epoch": 1.74, "learning_rate": 3.863337713534823e-06, "loss": 0.451, "step": 10616 }, { "epoch": 1.74, "learning_rate": 3.860873850197109e-06, "loss": 0.6589, "step": 10617 }, { "epoch": 1.74, "learning_rate": 3.858409986859395e-06, "loss": 0.3711, "step": 10618 }, { "epoch": 1.74, "learning_rate": 3.855946123521682e-06, "loss": 0.7574, "step": 10619 }, { "epoch": 1.74, "learning_rate": 3.853482260183968e-06, "loss": 1.1384, "step": 10620 }, { "epoch": 1.74, "learning_rate": 3.851018396846256e-06, "loss": 0.4623, "step": 10621 }, { "epoch": 1.74, "learning_rate": 3.848554533508542e-06, "loss": 0.3923, "step": 10622 }, { "epoch": 1.74, "learning_rate": 3.846090670170828e-06, "loss": 0.6602, "step": 10623 }, { "epoch": 1.75, "learning_rate": 3.8436268068331145e-06, "loss": 0.3707, "step": 10624 }, { "epoch": 1.75, "learning_rate": 3.8411629434954005e-06, "loss": 0.4326, "step": 10625 }, { "epoch": 1.75, "learning_rate": 3.838699080157687e-06, "loss": 0.6877, "step": 10626 }, { "epoch": 1.75, "learning_rate": 3.836235216819974e-06, "loss": 0.6686, "step": 10627 }, { "epoch": 1.75, "learning_rate": 3.83377135348226e-06, "loss": 0.5923, "step": 10628 }, { "epoch": 1.75, "learning_rate": 3.83377135348226e-06, "loss": 0.7259, "step": 10629 }, { "epoch": 1.75, "learning_rate": 3.831307490144547e-06, "loss": 0.1812, "step": 10630 }, { "epoch": 1.75, "learning_rate": 3.828843626806833e-06, "loss": 0.412, "step": 10631 }, { "epoch": 1.75, "learning_rate": 3.82637976346912e-06, "loss": 0.6622, "step": 10632 }, { "epoch": 1.75, "learning_rate": 3.823915900131406e-06, "loss": 0.5735, "step": 10633 }, { "epoch": 1.75, "learning_rate": 3.8214520367936926e-06, "loss": 1.1102, "step": 10634 }, { "epoch": 1.75, "learning_rate": 3.818988173455979e-06, "loss": 0.3543, "step": 10635 }, { "epoch": 1.75, "learning_rate": 3.816524310118265e-06, "loss": 0.4465, "step": 10636 }, { "epoch": 1.75, "learning_rate": 3.8140604467805522e-06, "loss": 0.619, "step": 10637 }, { "epoch": 1.75, "learning_rate": 3.8115965834428386e-06, "loss": 0.2468, "step": 10638 }, { "epoch": 1.75, "learning_rate": 3.8091327201051246e-06, "loss": 0.8862, "step": 10639 }, { "epoch": 1.75, "learning_rate": 3.8066688567674114e-06, "loss": 0.1851, "step": 10640 }, { "epoch": 1.75, "learning_rate": 3.804204993429698e-06, "loss": 0.4272, "step": 10641 }, { "epoch": 1.75, "learning_rate": 3.8017411300919847e-06, "loss": 0.7902, "step": 10642 }, { "epoch": 1.75, "learning_rate": 3.7992772667542707e-06, "loss": 0.2973, "step": 10643 }, { "epoch": 1.75, "learning_rate": 3.796813403416557e-06, "loss": 0.3668, "step": 10644 }, { "epoch": 1.75, "learning_rate": 3.794349540078844e-06, "loss": 0.3808, "step": 10645 }, { "epoch": 1.75, "learning_rate": 3.79188567674113e-06, "loss": 0.3416, "step": 10646 }, { "epoch": 1.75, "learning_rate": 3.789421813403417e-06, "loss": 1.0185, "step": 10647 }, { "epoch": 1.75, "learning_rate": 3.786957950065703e-06, "loss": 0.2335, "step": 10648 }, { "epoch": 1.75, "learning_rate": 3.784494086727989e-06, "loss": 0.6131, "step": 10649 }, { "epoch": 1.75, "learning_rate": 3.7820302233902764e-06, "loss": 0.9412, "step": 10650 }, { "epoch": 1.75, "learning_rate": 3.7795663600525624e-06, "loss": 0.7913, "step": 10651 }, { "epoch": 1.75, "learning_rate": 3.777102496714849e-06, "loss": 0.1925, "step": 10652 }, { "epoch": 1.75, "learning_rate": 3.7746386333771356e-06, "loss": 0.6033, "step": 10653 }, { "epoch": 1.75, "learning_rate": 3.7721747700394216e-06, "loss": 0.455, "step": 10654 }, { "epoch": 1.75, "learning_rate": 3.7697109067017084e-06, "loss": 0.3649, "step": 10655 }, { "epoch": 1.75, "learning_rate": 3.767247043363995e-06, "loss": 0.4471, "step": 10656 }, { "epoch": 1.75, "learning_rate": 3.7647831800262816e-06, "loss": 0.8443, "step": 10657 }, { "epoch": 1.75, "learning_rate": 3.7623193166885676e-06, "loss": 0.2486, "step": 10658 }, { "epoch": 1.75, "learning_rate": 3.759855453350854e-06, "loss": 0.65, "step": 10659 }, { "epoch": 1.75, "learning_rate": 3.757391590013141e-06, "loss": 0.4203, "step": 10660 }, { "epoch": 1.75, "learning_rate": 3.754927726675427e-06, "loss": 0.3729, "step": 10661 }, { "epoch": 1.75, "learning_rate": 3.752463863337714e-06, "loss": 0.5142, "step": 10662 }, { "epoch": 1.75, "learning_rate": 3.75e-06, "loss": 0.3215, "step": 10663 }, { "epoch": 1.75, "learning_rate": 3.7475361366622865e-06, "loss": 0.4466, "step": 10664 }, { "epoch": 1.75, "learning_rate": 3.7450722733245733e-06, "loss": 0.1662, "step": 10665 }, { "epoch": 1.75, "learning_rate": 3.7426084099868593e-06, "loss": 0.103, "step": 10666 }, { "epoch": 1.75, "learning_rate": 3.7401445466491457e-06, "loss": 0.388, "step": 10667 }, { "epoch": 1.75, "learning_rate": 3.7376806833114326e-06, "loss": 0.1941, "step": 10668 }, { "epoch": 1.75, "learning_rate": 3.735216819973719e-06, "loss": 0.6178, "step": 10669 }, { "epoch": 1.75, "learning_rate": 3.7327529566360054e-06, "loss": 0.2713, "step": 10670 }, { "epoch": 1.75, "learning_rate": 3.7302890932982918e-06, "loss": 0.1716, "step": 10671 }, { "epoch": 1.75, "learning_rate": 3.727825229960578e-06, "loss": 0.3451, "step": 10672 }, { "epoch": 1.75, "learning_rate": 3.7253613666228646e-06, "loss": 0.4554, "step": 10673 }, { "epoch": 1.75, "learning_rate": 3.7228975032851514e-06, "loss": 0.4315, "step": 10674 }, { "epoch": 1.75, "learning_rate": 3.720433639947438e-06, "loss": 0.1526, "step": 10675 }, { "epoch": 1.75, "learning_rate": 3.717969776609724e-06, "loss": 0.3649, "step": 10676 }, { "epoch": 1.75, "learning_rate": 3.7155059132720107e-06, "loss": 0.5457, "step": 10677 }, { "epoch": 1.75, "learning_rate": 3.713042049934297e-06, "loss": 0.4472, "step": 10678 }, { "epoch": 1.75, "learning_rate": 3.7105781865965835e-06, "loss": 0.559, "step": 10679 }, { "epoch": 1.75, "learning_rate": 3.7081143232588703e-06, "loss": 0.551, "step": 10680 }, { "epoch": 1.75, "learning_rate": 3.7056504599211563e-06, "loss": 0.656, "step": 10681 }, { "epoch": 1.75, "learning_rate": 3.7031865965834427e-06, "loss": 0.4112, "step": 10682 }, { "epoch": 1.75, "learning_rate": 3.7007227332457295e-06, "loss": 0.5783, "step": 10683 }, { "epoch": 1.75, "learning_rate": 3.698258869908016e-06, "loss": 0.7049, "step": 10684 }, { "epoch": 1.76, "learning_rate": 3.6957950065703023e-06, "loss": 0.5142, "step": 10685 }, { "epoch": 1.76, "learning_rate": 3.6933311432325888e-06, "loss": 0.4519, "step": 10686 }, { "epoch": 1.76, "learning_rate": 3.690867279894875e-06, "loss": 0.2419, "step": 10687 }, { "epoch": 1.76, "learning_rate": 3.6884034165571616e-06, "loss": 0.7281, "step": 10688 }, { "epoch": 1.76, "learning_rate": 3.6859395532194484e-06, "loss": 0.6242, "step": 10689 }, { "epoch": 1.76, "learning_rate": 3.683475689881735e-06, "loss": 0.1241, "step": 10690 }, { "epoch": 1.76, "learning_rate": 3.681011826544021e-06, "loss": 0.346, "step": 10691 }, { "epoch": 1.76, "learning_rate": 3.6785479632063076e-06, "loss": 0.3781, "step": 10692 }, { "epoch": 1.76, "learning_rate": 3.676084099868594e-06, "loss": 0.1978, "step": 10693 }, { "epoch": 1.76, "learning_rate": 3.6736202365308804e-06, "loss": 0.141, "step": 10694 }, { "epoch": 1.76, "learning_rate": 3.6711563731931673e-06, "loss": 0.6068, "step": 10695 }, { "epoch": 1.76, "learning_rate": 3.6686925098554533e-06, "loss": 0.727, "step": 10696 }, { "epoch": 1.76, "learning_rate": 3.6662286465177397e-06, "loss": 0.387, "step": 10697 }, { "epoch": 1.76, "learning_rate": 3.6637647831800265e-06, "loss": 0.7664, "step": 10698 }, { "epoch": 1.76, "learning_rate": 3.661300919842313e-06, "loss": 0.3012, "step": 10699 }, { "epoch": 1.76, "learning_rate": 3.6588370565045993e-06, "loss": 0.6058, "step": 10700 }, { "epoch": 1.76, "learning_rate": 3.6563731931668857e-06, "loss": 0.3694, "step": 10701 }, { "epoch": 1.76, "learning_rate": 3.653909329829172e-06, "loss": 0.4652, "step": 10702 }, { "epoch": 1.76, "learning_rate": 3.6514454664914585e-06, "loss": 0.5031, "step": 10703 }, { "epoch": 1.76, "learning_rate": 3.6489816031537454e-06, "loss": 0.8986, "step": 10704 }, { "epoch": 1.76, "learning_rate": 3.6465177398160318e-06, "loss": 0.7159, "step": 10705 }, { "epoch": 1.76, "learning_rate": 3.6440538764783178e-06, "loss": 0.6272, "step": 10706 }, { "epoch": 1.76, "learning_rate": 3.6415900131406046e-06, "loss": 0.3278, "step": 10707 }, { "epoch": 1.76, "learning_rate": 3.639126149802891e-06, "loss": 0.7688, "step": 10708 }, { "epoch": 1.76, "learning_rate": 3.6366622864651774e-06, "loss": 0.1615, "step": 10709 }, { "epoch": 1.76, "learning_rate": 3.6341984231274642e-06, "loss": 0.3546, "step": 10710 }, { "epoch": 1.76, "learning_rate": 3.6317345597897502e-06, "loss": 0.593, "step": 10711 }, { "epoch": 1.76, "learning_rate": 3.6292706964520366e-06, "loss": 0.4799, "step": 10712 }, { "epoch": 1.76, "learning_rate": 3.6268068331143235e-06, "loss": 0.791, "step": 10713 }, { "epoch": 1.76, "learning_rate": 3.62434296977661e-06, "loss": 0.4727, "step": 10714 }, { "epoch": 1.76, "learning_rate": 3.6218791064388963e-06, "loss": 0.4515, "step": 10715 }, { "epoch": 1.76, "learning_rate": 3.6194152431011827e-06, "loss": 0.4369, "step": 10716 }, { "epoch": 1.76, "learning_rate": 3.616951379763469e-06, "loss": 0.8885, "step": 10717 }, { "epoch": 1.76, "learning_rate": 3.6144875164257555e-06, "loss": 0.5558, "step": 10718 }, { "epoch": 1.76, "learning_rate": 3.6120236530880423e-06, "loss": 0.2551, "step": 10719 }, { "epoch": 1.76, "learning_rate": 3.6095597897503287e-06, "loss": 0.6365, "step": 10720 }, { "epoch": 1.76, "learning_rate": 3.6070959264126147e-06, "loss": 0.4381, "step": 10721 }, { "epoch": 1.76, "learning_rate": 3.6046320630749016e-06, "loss": 0.7103, "step": 10722 }, { "epoch": 1.76, "learning_rate": 3.602168199737188e-06, "loss": 0.5724, "step": 10723 }, { "epoch": 1.76, "learning_rate": 3.5997043363994744e-06, "loss": 0.7074, "step": 10724 }, { "epoch": 1.76, "learning_rate": 3.597240473061761e-06, "loss": 0.5682, "step": 10725 }, { "epoch": 1.76, "learning_rate": 3.594776609724047e-06, "loss": 0.4557, "step": 10726 }, { "epoch": 1.76, "learning_rate": 3.5923127463863336e-06, "loss": 1.1486, "step": 10727 }, { "epoch": 1.76, "learning_rate": 3.5898488830486204e-06, "loss": 0.2118, "step": 10728 }, { "epoch": 1.76, "learning_rate": 3.587385019710907e-06, "loss": 0.6578, "step": 10729 }, { "epoch": 1.76, "learning_rate": 3.5849211563731932e-06, "loss": 0.4478, "step": 10730 }, { "epoch": 1.76, "learning_rate": 3.5824572930354797e-06, "loss": 0.5583, "step": 10731 }, { "epoch": 1.76, "learning_rate": 3.579993429697766e-06, "loss": 0.7061, "step": 10732 }, { "epoch": 1.76, "learning_rate": 3.577529566360053e-06, "loss": 0.4984, "step": 10733 }, { "epoch": 1.76, "learning_rate": 3.5750657030223393e-06, "loss": 0.6118, "step": 10734 }, { "epoch": 1.76, "learning_rate": 3.5726018396846257e-06, "loss": 0.7976, "step": 10735 }, { "epoch": 1.76, "learning_rate": 3.570137976346912e-06, "loss": 0.6935, "step": 10736 }, { "epoch": 1.76, "learning_rate": 3.5676741130091985e-06, "loss": 0.3216, "step": 10737 }, { "epoch": 1.76, "learning_rate": 3.565210249671485e-06, "loss": 0.6869, "step": 10738 }, { "epoch": 1.76, "learning_rate": 3.5627463863337718e-06, "loss": 0.3529, "step": 10739 }, { "epoch": 1.76, "learning_rate": 3.560282522996058e-06, "loss": 0.4301, "step": 10740 }, { "epoch": 1.76, "learning_rate": 3.557818659658344e-06, "loss": 0.4658, "step": 10741 }, { "epoch": 1.76, "learning_rate": 3.555354796320631e-06, "loss": 0.5504, "step": 10742 }, { "epoch": 1.76, "learning_rate": 3.5528909329829174e-06, "loss": 0.5613, "step": 10743 }, { "epoch": 1.76, "learning_rate": 3.550427069645204e-06, "loss": 0.1387, "step": 10744 }, { "epoch": 1.76, "learning_rate": 3.5479632063074906e-06, "loss": 0.4764, "step": 10745 }, { "epoch": 1.77, "learning_rate": 3.5454993429697766e-06, "loss": 0.2568, "step": 10746 }, { "epoch": 1.77, "learning_rate": 3.543035479632063e-06, "loss": 0.527, "step": 10747 }, { "epoch": 1.77, "learning_rate": 3.54057161629435e-06, "loss": 0.6362, "step": 10748 }, { "epoch": 1.77, "learning_rate": 3.5381077529566363e-06, "loss": 0.4975, "step": 10749 }, { "epoch": 1.77, "learning_rate": 3.5356438896189227e-06, "loss": 0.5845, "step": 10750 }, { "epoch": 1.77, "learning_rate": 3.533180026281209e-06, "loss": 0.4518, "step": 10751 }, { "epoch": 1.77, "learning_rate": 3.5307161629434955e-06, "loss": 0.6037, "step": 10752 }, { "epoch": 1.77, "learning_rate": 3.528252299605782e-06, "loss": 0.4964, "step": 10753 }, { "epoch": 1.77, "learning_rate": 3.5257884362680687e-06, "loss": 0.6481, "step": 10754 }, { "epoch": 1.77, "learning_rate": 3.523324572930355e-06, "loss": 0.174, "step": 10755 }, { "epoch": 1.77, "learning_rate": 3.520860709592641e-06, "loss": 0.4068, "step": 10756 }, { "epoch": 1.77, "learning_rate": 3.518396846254928e-06, "loss": 0.4414, "step": 10757 }, { "epoch": 1.77, "learning_rate": 3.5159329829172144e-06, "loss": 0.6614, "step": 10758 }, { "epoch": 1.77, "learning_rate": 3.5134691195795008e-06, "loss": 0.6421, "step": 10759 }, { "epoch": 1.77, "learning_rate": 3.511005256241787e-06, "loss": 0.296, "step": 10760 }, { "epoch": 1.77, "learning_rate": 3.5085413929040736e-06, "loss": 0.574, "step": 10761 }, { "epoch": 1.77, "learning_rate": 3.50607752956636e-06, "loss": 0.4914, "step": 10762 }, { "epoch": 1.77, "learning_rate": 3.503613666228647e-06, "loss": 0.6182, "step": 10763 }, { "epoch": 1.77, "learning_rate": 3.5011498028909332e-06, "loss": 0.7268, "step": 10764 }, { "epoch": 1.77, "learning_rate": 3.4986859395532192e-06, "loss": 0.3633, "step": 10765 }, { "epoch": 1.77, "learning_rate": 3.496222076215506e-06, "loss": 0.5064, "step": 10766 }, { "epoch": 1.77, "learning_rate": 3.4937582128777925e-06, "loss": 0.3787, "step": 10767 }, { "epoch": 1.77, "learning_rate": 3.491294349540079e-06, "loss": 0.4365, "step": 10768 }, { "epoch": 1.77, "learning_rate": 3.4888304862023657e-06, "loss": 0.5898, "step": 10769 }, { "epoch": 1.77, "learning_rate": 3.4863666228646517e-06, "loss": 0.6376, "step": 10770 }, { "epoch": 1.77, "learning_rate": 3.483902759526938e-06, "loss": 0.4401, "step": 10771 }, { "epoch": 1.77, "learning_rate": 3.481438896189225e-06, "loss": 0.6196, "step": 10772 }, { "epoch": 1.77, "learning_rate": 3.4789750328515113e-06, "loss": 0.485, "step": 10773 }, { "epoch": 1.77, "learning_rate": 3.4765111695137977e-06, "loss": 0.4534, "step": 10774 }, { "epoch": 1.77, "learning_rate": 3.474047306176084e-06, "loss": 0.5132, "step": 10775 }, { "epoch": 1.77, "learning_rate": 3.4715834428383706e-06, "loss": 0.4174, "step": 10776 }, { "epoch": 1.77, "learning_rate": 3.469119579500657e-06, "loss": 0.3971, "step": 10777 }, { "epoch": 1.77, "learning_rate": 3.466655716162944e-06, "loss": 0.2351, "step": 10778 }, { "epoch": 1.77, "learning_rate": 3.46419185282523e-06, "loss": 0.3518, "step": 10779 }, { "epoch": 1.77, "learning_rate": 3.461727989487516e-06, "loss": 0.2998, "step": 10780 }, { "epoch": 1.77, "learning_rate": 3.459264126149803e-06, "loss": 0.6641, "step": 10781 }, { "epoch": 1.77, "learning_rate": 3.4568002628120894e-06, "loss": 0.7866, "step": 10782 }, { "epoch": 1.77, "learning_rate": 3.454336399474376e-06, "loss": 0.4936, "step": 10783 }, { "epoch": 1.77, "learning_rate": 3.4518725361366627e-06, "loss": 0.7945, "step": 10784 }, { "epoch": 1.77, "learning_rate": 3.4494086727989487e-06, "loss": 0.6445, "step": 10785 }, { "epoch": 1.77, "learning_rate": 3.446944809461235e-06, "loss": 0.2364, "step": 10786 }, { "epoch": 1.77, "learning_rate": 3.444480946123522e-06, "loss": 0.6599, "step": 10787 }, { "epoch": 1.77, "learning_rate": 3.4420170827858083e-06, "loss": 0.3921, "step": 10788 }, { "epoch": 1.77, "learning_rate": 3.4395532194480947e-06, "loss": 0.2076, "step": 10789 }, { "epoch": 1.77, "learning_rate": 3.437089356110381e-06, "loss": 0.3076, "step": 10790 }, { "epoch": 1.77, "learning_rate": 3.4346254927726675e-06, "loss": 0.8122, "step": 10791 }, { "epoch": 1.77, "learning_rate": 3.432161629434954e-06, "loss": 0.7135, "step": 10792 }, { "epoch": 1.77, "learning_rate": 3.4296977660972408e-06, "loss": 0.5509, "step": 10793 }, { "epoch": 1.77, "learning_rate": 3.427233902759527e-06, "loss": 0.5197, "step": 10794 }, { "epoch": 1.77, "learning_rate": 3.424770039421813e-06, "loss": 0.4478, "step": 10795 }, { "epoch": 1.77, "learning_rate": 3.4223061760841e-06, "loss": 0.586, "step": 10796 }, { "epoch": 1.77, "learning_rate": 3.4198423127463864e-06, "loss": 0.4003, "step": 10797 }, { "epoch": 1.77, "learning_rate": 3.417378449408673e-06, "loss": 0.4352, "step": 10798 }, { "epoch": 1.77, "learning_rate": 3.4149145860709596e-06, "loss": 0.4275, "step": 10799 }, { "epoch": 1.77, "learning_rate": 3.4124507227332456e-06, "loss": 0.7295, "step": 10800 }, { "epoch": 1.77, "learning_rate": 3.409986859395532e-06, "loss": 0.2124, "step": 10801 }, { "epoch": 1.77, "learning_rate": 3.407522996057819e-06, "loss": 0.4504, "step": 10802 }, { "epoch": 1.77, "learning_rate": 3.4050591327201053e-06, "loss": 0.2022, "step": 10803 }, { "epoch": 1.77, "learning_rate": 3.4025952693823917e-06, "loss": 0.5775, "step": 10804 }, { "epoch": 1.77, "learning_rate": 3.400131406044678e-06, "loss": 0.6827, "step": 10805 }, { "epoch": 1.77, "learning_rate": 3.3976675427069645e-06, "loss": 0.2686, "step": 10806 }, { "epoch": 1.78, "learning_rate": 3.395203679369251e-06, "loss": 0.9152, "step": 10807 }, { "epoch": 1.78, "learning_rate": 3.3927398160315377e-06, "loss": 0.4707, "step": 10808 }, { "epoch": 1.78, "learning_rate": 3.390275952693824e-06, "loss": 0.36, "step": 10809 }, { "epoch": 1.78, "learning_rate": 3.38781208935611e-06, "loss": 0.7452, "step": 10810 }, { "epoch": 1.78, "learning_rate": 3.385348226018397e-06, "loss": 0.34, "step": 10811 }, { "epoch": 1.78, "learning_rate": 3.3828843626806834e-06, "loss": 0.9046, "step": 10812 }, { "epoch": 1.78, "learning_rate": 3.3804204993429698e-06, "loss": 1.1465, "step": 10813 }, { "epoch": 1.78, "learning_rate": 3.3779566360052566e-06, "loss": 0.5411, "step": 10814 }, { "epoch": 1.78, "learning_rate": 3.3754927726675426e-06, "loss": 0.2696, "step": 10815 }, { "epoch": 1.78, "learning_rate": 3.373028909329829e-06, "loss": 0.8824, "step": 10816 }, { "epoch": 1.78, "learning_rate": 3.370565045992116e-06, "loss": 0.2153, "step": 10817 }, { "epoch": 1.78, "learning_rate": 3.3681011826544022e-06, "loss": 1.2479, "step": 10818 }, { "epoch": 1.78, "learning_rate": 3.3656373193166886e-06, "loss": 0.6445, "step": 10819 }, { "epoch": 1.78, "learning_rate": 3.363173455978975e-06, "loss": 1.3594, "step": 10820 }, { "epoch": 1.78, "learning_rate": 3.3607095926412615e-06, "loss": 0.3506, "step": 10821 }, { "epoch": 1.78, "learning_rate": 3.358245729303548e-06, "loss": 0.3771, "step": 10822 }, { "epoch": 1.78, "learning_rate": 3.3557818659658347e-06, "loss": 0.4271, "step": 10823 }, { "epoch": 1.78, "learning_rate": 3.353318002628121e-06, "loss": 0.4416, "step": 10824 }, { "epoch": 1.78, "learning_rate": 3.350854139290407e-06, "loss": 0.4329, "step": 10825 }, { "epoch": 1.78, "learning_rate": 3.348390275952694e-06, "loss": 0.4144, "step": 10826 }, { "epoch": 1.78, "learning_rate": 3.3459264126149803e-06, "loss": 0.3329, "step": 10827 }, { "epoch": 1.78, "learning_rate": 3.3434625492772667e-06, "loss": 0.6265, "step": 10828 }, { "epoch": 1.78, "learning_rate": 3.3409986859395536e-06, "loss": 0.4014, "step": 10829 }, { "epoch": 1.78, "learning_rate": 3.3385348226018396e-06, "loss": 0.3595, "step": 10830 }, { "epoch": 1.78, "learning_rate": 3.336070959264126e-06, "loss": 0.3657, "step": 10831 }, { "epoch": 1.78, "learning_rate": 3.333607095926413e-06, "loss": 0.7105, "step": 10832 }, { "epoch": 1.78, "learning_rate": 3.331143232588699e-06, "loss": 0.2167, "step": 10833 }, { "epoch": 1.78, "learning_rate": 3.3286793692509856e-06, "loss": 0.365, "step": 10834 }, { "epoch": 1.78, "learning_rate": 3.326215505913272e-06, "loss": 0.2903, "step": 10835 }, { "epoch": 1.78, "learning_rate": 3.3237516425755584e-06, "loss": 0.5549, "step": 10836 }, { "epoch": 1.78, "learning_rate": 3.321287779237845e-06, "loss": 0.3808, "step": 10837 }, { "epoch": 1.78, "learning_rate": 3.3188239159001317e-06, "loss": 0.2065, "step": 10838 }, { "epoch": 1.78, "learning_rate": 3.316360052562418e-06, "loss": 0.3107, "step": 10839 }, { "epoch": 1.78, "learning_rate": 3.313896189224704e-06, "loss": 0.4903, "step": 10840 }, { "epoch": 1.78, "learning_rate": 3.311432325886991e-06, "loss": 0.5362, "step": 10841 }, { "epoch": 1.78, "learning_rate": 3.3089684625492773e-06, "loss": 0.2143, "step": 10842 }, { "epoch": 1.78, "learning_rate": 3.3065045992115637e-06, "loss": 0.2226, "step": 10843 }, { "epoch": 1.78, "learning_rate": 3.3040407358738505e-06, "loss": 0.1871, "step": 10844 }, { "epoch": 1.78, "learning_rate": 3.3015768725361365e-06, "loss": 0.3641, "step": 10845 }, { "epoch": 1.78, "learning_rate": 3.299113009198423e-06, "loss": 0.386, "step": 10846 }, { "epoch": 1.78, "learning_rate": 3.2966491458607098e-06, "loss": 0.2253, "step": 10847 }, { "epoch": 1.78, "learning_rate": 3.294185282522996e-06, "loss": 0.5896, "step": 10848 }, { "epoch": 1.78, "learning_rate": 3.2917214191852826e-06, "loss": 0.4778, "step": 10849 }, { "epoch": 1.78, "learning_rate": 3.289257555847569e-06, "loss": 0.3455, "step": 10850 }, { "epoch": 1.78, "learning_rate": 3.2867936925098554e-06, "loss": 0.4172, "step": 10851 }, { "epoch": 1.78, "learning_rate": 3.284329829172142e-06, "loss": 0.2794, "step": 10852 }, { "epoch": 1.78, "learning_rate": 3.2818659658344286e-06, "loss": 0.519, "step": 10853 }, { "epoch": 1.78, "learning_rate": 3.279402102496715e-06, "loss": 0.4208, "step": 10854 }, { "epoch": 1.78, "learning_rate": 3.276938239159001e-06, "loss": 0.3907, "step": 10855 }, { "epoch": 1.78, "learning_rate": 3.274474375821288e-06, "loss": 0.6653, "step": 10856 }, { "epoch": 1.78, "learning_rate": 3.2720105124835743e-06, "loss": 0.3016, "step": 10857 }, { "epoch": 1.78, "learning_rate": 3.2695466491458607e-06, "loss": 0.4085, "step": 10858 }, { "epoch": 1.78, "learning_rate": 3.2670827858081475e-06, "loss": 0.5804, "step": 10859 }, { "epoch": 1.78, "learning_rate": 3.2646189224704335e-06, "loss": 0.6285, "step": 10860 }, { "epoch": 1.78, "learning_rate": 3.26215505913272e-06, "loss": 0.32, "step": 10861 }, { "epoch": 1.78, "learning_rate": 3.2596911957950067e-06, "loss": 0.3778, "step": 10862 }, { "epoch": 1.78, "learning_rate": 3.257227332457293e-06, "loss": 0.3839, "step": 10863 }, { "epoch": 1.78, "learning_rate": 3.2547634691195796e-06, "loss": 0.3847, "step": 10864 }, { "epoch": 1.78, "learning_rate": 3.252299605781866e-06, "loss": 0.364, "step": 10865 }, { "epoch": 1.78, "learning_rate": 3.2498357424441524e-06, "loss": 0.9212, "step": 10866 }, { "epoch": 1.78, "learning_rate": 3.2473718791064388e-06, "loss": 0.9764, "step": 10867 }, { "epoch": 1.79, "learning_rate": 3.2449080157687256e-06, "loss": 0.2633, "step": 10868 }, { "epoch": 1.79, "learning_rate": 3.242444152431012e-06, "loss": 0.2681, "step": 10869 }, { "epoch": 1.79, "learning_rate": 3.2399802890932984e-06, "loss": 0.5081, "step": 10870 }, { "epoch": 1.79, "learning_rate": 3.237516425755585e-06, "loss": 0.4321, "step": 10871 }, { "epoch": 1.79, "learning_rate": 3.2350525624178712e-06, "loss": 0.7353, "step": 10872 }, { "epoch": 1.79, "learning_rate": 3.232588699080158e-06, "loss": 0.5468, "step": 10873 }, { "epoch": 1.79, "learning_rate": 3.2301248357424445e-06, "loss": 0.9491, "step": 10874 }, { "epoch": 1.79, "learning_rate": 3.2276609724047305e-06, "loss": 0.3624, "step": 10875 }, { "epoch": 1.79, "learning_rate": 3.2251971090670173e-06, "loss": 0.4743, "step": 10876 }, { "epoch": 1.79, "learning_rate": 3.2227332457293037e-06, "loss": 0.398, "step": 10877 }, { "epoch": 1.79, "learning_rate": 3.22026938239159e-06, "loss": 0.327, "step": 10878 }, { "epoch": 1.79, "learning_rate": 3.217805519053877e-06, "loss": 0.3557, "step": 10879 }, { "epoch": 1.79, "learning_rate": 3.215341655716163e-06, "loss": 0.7949, "step": 10880 }, { "epoch": 1.79, "learning_rate": 3.2128777923784493e-06, "loss": 0.3776, "step": 10881 }, { "epoch": 1.79, "learning_rate": 3.210413929040736e-06, "loss": 0.5925, "step": 10882 }, { "epoch": 1.79, "learning_rate": 3.2079500657030226e-06, "loss": 0.4163, "step": 10883 }, { "epoch": 1.79, "learning_rate": 3.205486202365309e-06, "loss": 0.2463, "step": 10884 }, { "epoch": 1.79, "learning_rate": 3.2030223390275954e-06, "loss": 0.3914, "step": 10885 }, { "epoch": 1.79, "learning_rate": 3.200558475689882e-06, "loss": 0.2121, "step": 10886 }, { "epoch": 1.79, "learning_rate": 3.198094612352168e-06, "loss": 0.3987, "step": 10887 }, { "epoch": 1.79, "learning_rate": 3.195630749014455e-06, "loss": 0.9441, "step": 10888 }, { "epoch": 1.79, "learning_rate": 3.1931668856767414e-06, "loss": 0.5313, "step": 10889 }, { "epoch": 1.79, "learning_rate": 3.1907030223390274e-06, "loss": 0.5802, "step": 10890 }, { "epoch": 1.79, "learning_rate": 3.1882391590013143e-06, "loss": 0.7904, "step": 10891 }, { "epoch": 1.79, "learning_rate": 3.1857752956636007e-06, "loss": 0.4467, "step": 10892 }, { "epoch": 1.79, "learning_rate": 3.183311432325887e-06, "loss": 0.3019, "step": 10893 }, { "epoch": 1.79, "learning_rate": 3.180847568988174e-06, "loss": 0.4379, "step": 10894 }, { "epoch": 1.79, "learning_rate": 3.17838370565046e-06, "loss": 0.5191, "step": 10895 }, { "epoch": 1.79, "learning_rate": 3.1759198423127463e-06, "loss": 0.4193, "step": 10896 }, { "epoch": 1.79, "learning_rate": 3.173455978975033e-06, "loss": 0.302, "step": 10897 }, { "epoch": 1.79, "learning_rate": 3.1709921156373195e-06, "loss": 0.8408, "step": 10898 }, { "epoch": 1.79, "learning_rate": 3.168528252299606e-06, "loss": 0.6872, "step": 10899 }, { "epoch": 1.79, "learning_rate": 3.1660643889618924e-06, "loss": 0.3448, "step": 10900 }, { "epoch": 1.79, "learning_rate": 3.1636005256241788e-06, "loss": 0.3894, "step": 10901 }, { "epoch": 1.79, "learning_rate": 3.161136662286465e-06, "loss": 0.5753, "step": 10902 }, { "epoch": 1.79, "learning_rate": 3.158672798948752e-06, "loss": 0.5937, "step": 10903 }, { "epoch": 1.79, "learning_rate": 3.1562089356110384e-06, "loss": 0.6197, "step": 10904 }, { "epoch": 1.79, "learning_rate": 3.1537450722733244e-06, "loss": 0.3503, "step": 10905 }, { "epoch": 1.79, "learning_rate": 3.1512812089356112e-06, "loss": 0.2949, "step": 10906 }, { "epoch": 1.79, "learning_rate": 3.1488173455978976e-06, "loss": 0.3894, "step": 10907 }, { "epoch": 1.79, "learning_rate": 3.146353482260184e-06, "loss": 0.2828, "step": 10908 }, { "epoch": 1.79, "learning_rate": 3.143889618922471e-06, "loss": 0.6487, "step": 10909 }, { "epoch": 1.79, "learning_rate": 3.141425755584757e-06, "loss": 0.9682, "step": 10910 }, { "epoch": 1.79, "learning_rate": 3.1389618922470433e-06, "loss": 0.7449, "step": 10911 }, { "epoch": 1.79, "learning_rate": 3.13649802890933e-06, "loss": 0.534, "step": 10912 }, { "epoch": 1.79, "learning_rate": 3.1340341655716165e-06, "loss": 0.4054, "step": 10913 }, { "epoch": 1.79, "learning_rate": 3.131570302233903e-06, "loss": 0.2322, "step": 10914 }, { "epoch": 1.79, "learning_rate": 3.1291064388961893e-06, "loss": 0.2313, "step": 10915 }, { "epoch": 1.79, "learning_rate": 3.1266425755584757e-06, "loss": 0.2071, "step": 10916 }, { "epoch": 1.79, "learning_rate": 3.124178712220762e-06, "loss": 0.612, "step": 10917 }, { "epoch": 1.79, "learning_rate": 3.121714848883049e-06, "loss": 0.7701, "step": 10918 }, { "epoch": 1.79, "learning_rate": 3.1192509855453354e-06, "loss": 0.5524, "step": 10919 }, { "epoch": 1.79, "learning_rate": 3.1167871222076214e-06, "loss": 0.797, "step": 10920 }, { "epoch": 1.79, "learning_rate": 3.114323258869908e-06, "loss": 0.376, "step": 10921 }, { "epoch": 1.79, "learning_rate": 3.1118593955321946e-06, "loss": 0.4939, "step": 10922 }, { "epoch": 1.79, "learning_rate": 3.109395532194481e-06, "loss": 0.2445, "step": 10923 }, { "epoch": 1.79, "learning_rate": 3.106931668856768e-06, "loss": 0.9382, "step": 10924 }, { "epoch": 1.79, "learning_rate": 3.104467805519054e-06, "loss": 0.3108, "step": 10925 }, { "epoch": 1.79, "learning_rate": 3.1020039421813402e-06, "loss": 0.5273, "step": 10926 }, { "epoch": 1.79, "learning_rate": 3.099540078843627e-06, "loss": 0.3315, "step": 10927 }, { "epoch": 1.8, "learning_rate": 3.0970762155059135e-06, "loss": 0.3298, "step": 10928 }, { "epoch": 1.8, "learning_rate": 3.0946123521682e-06, "loss": 0.2693, "step": 10929 }, { "epoch": 1.8, "learning_rate": 3.0921484888304863e-06, "loss": 0.5864, "step": 10930 }, { "epoch": 1.8, "learning_rate": 3.0896846254927727e-06, "loss": 0.488, "step": 10931 }, { "epoch": 1.8, "learning_rate": 3.087220762155059e-06, "loss": 0.5989, "step": 10932 }, { "epoch": 1.8, "learning_rate": 3.084756898817346e-06, "loss": 0.315, "step": 10933 }, { "epoch": 1.8, "learning_rate": 3.0822930354796324e-06, "loss": 0.3649, "step": 10934 }, { "epoch": 1.8, "learning_rate": 3.0798291721419183e-06, "loss": 0.9904, "step": 10935 }, { "epoch": 1.8, "learning_rate": 3.077365308804205e-06, "loss": 0.4107, "step": 10936 }, { "epoch": 1.8, "learning_rate": 3.0749014454664916e-06, "loss": 0.3459, "step": 10937 }, { "epoch": 1.8, "learning_rate": 3.072437582128778e-06, "loss": 0.373, "step": 10938 }, { "epoch": 1.8, "learning_rate": 3.069973718791065e-06, "loss": 0.4512, "step": 10939 }, { "epoch": 1.8, "learning_rate": 3.067509855453351e-06, "loss": 0.3128, "step": 10940 }, { "epoch": 1.8, "learning_rate": 3.065045992115637e-06, "loss": 0.5154, "step": 10941 }, { "epoch": 1.8, "learning_rate": 3.062582128777924e-06, "loss": 0.3399, "step": 10942 }, { "epoch": 1.8, "learning_rate": 3.0601182654402104e-06, "loss": 0.3783, "step": 10943 }, { "epoch": 1.8, "learning_rate": 3.057654402102497e-06, "loss": 0.2555, "step": 10944 }, { "epoch": 1.8, "learning_rate": 3.0551905387647833e-06, "loss": 0.4756, "step": 10945 }, { "epoch": 1.8, "learning_rate": 3.0527266754270697e-06, "loss": 0.2059, "step": 10946 }, { "epoch": 1.8, "learning_rate": 3.050262812089356e-06, "loss": 0.3926, "step": 10947 }, { "epoch": 1.8, "learning_rate": 3.047798948751643e-06, "loss": 0.7898, "step": 10948 }, { "epoch": 1.8, "learning_rate": 3.045335085413929e-06, "loss": 0.5616, "step": 10949 }, { "epoch": 1.8, "learning_rate": 3.0428712220762153e-06, "loss": 0.9, "step": 10950 }, { "epoch": 1.8, "learning_rate": 3.040407358738502e-06, "loss": 0.5043, "step": 10951 }, { "epoch": 1.8, "learning_rate": 3.0379434954007885e-06, "loss": 0.4062, "step": 10952 }, { "epoch": 1.8, "learning_rate": 3.035479632063075e-06, "loss": 0.6538, "step": 10953 }, { "epoch": 1.8, "learning_rate": 3.0330157687253614e-06, "loss": 1.0106, "step": 10954 }, { "epoch": 1.8, "learning_rate": 3.0305519053876478e-06, "loss": 0.3037, "step": 10955 }, { "epoch": 1.8, "learning_rate": 3.028088042049934e-06, "loss": 0.3176, "step": 10956 }, { "epoch": 1.8, "learning_rate": 3.025624178712221e-06, "loss": 0.5645, "step": 10957 }, { "epoch": 1.8, "learning_rate": 3.0231603153745074e-06, "loss": 0.227, "step": 10958 }, { "epoch": 1.8, "learning_rate": 3.0206964520367934e-06, "loss": 0.3321, "step": 10959 }, { "epoch": 1.8, "learning_rate": 3.0182325886990802e-06, "loss": 0.7866, "step": 10960 }, { "epoch": 1.8, "learning_rate": 3.0157687253613666e-06, "loss": 0.3888, "step": 10961 }, { "epoch": 1.8, "learning_rate": 3.013304862023653e-06, "loss": 0.4275, "step": 10962 }, { "epoch": 1.8, "learning_rate": 3.01084099868594e-06, "loss": 0.1346, "step": 10963 }, { "epoch": 1.8, "learning_rate": 3.008377135348226e-06, "loss": 0.3386, "step": 10964 }, { "epoch": 1.8, "learning_rate": 3.0059132720105123e-06, "loss": 0.3205, "step": 10965 }, { "epoch": 1.8, "learning_rate": 3.003449408672799e-06, "loss": 0.8091, "step": 10966 }, { "epoch": 1.8, "learning_rate": 3.0009855453350855e-06, "loss": 0.6945, "step": 10967 }, { "epoch": 1.8, "learning_rate": 2.998521681997372e-06, "loss": 0.2499, "step": 10968 }, { "epoch": 1.8, "learning_rate": 2.9960578186596583e-06, "loss": 0.4014, "step": 10969 }, { "epoch": 1.8, "learning_rate": 2.9935939553219447e-06, "loss": 0.3519, "step": 10970 }, { "epoch": 1.8, "learning_rate": 2.991130091984231e-06, "loss": 0.1561, "step": 10971 }, { "epoch": 1.8, "learning_rate": 2.988666228646518e-06, "loss": 0.5034, "step": 10972 }, { "epoch": 1.8, "learning_rate": 2.9862023653088044e-06, "loss": 0.5349, "step": 10973 }, { "epoch": 1.8, "learning_rate": 2.9837385019710904e-06, "loss": 0.8642, "step": 10974 }, { "epoch": 1.8, "learning_rate": 2.981274638633377e-06, "loss": 0.6963, "step": 10975 }, { "epoch": 1.8, "learning_rate": 2.9788107752956636e-06, "loss": 0.312, "step": 10976 }, { "epoch": 1.8, "learning_rate": 2.97634691195795e-06, "loss": 0.2603, "step": 10977 }, { "epoch": 1.8, "learning_rate": 2.973883048620237e-06, "loss": 0.5965, "step": 10978 }, { "epoch": 1.8, "learning_rate": 2.971419185282523e-06, "loss": 0.5034, "step": 10979 }, { "epoch": 1.8, "learning_rate": 2.9689553219448092e-06, "loss": 0.8252, "step": 10980 }, { "epoch": 1.8, "learning_rate": 2.966491458607096e-06, "loss": 0.1547, "step": 10981 }, { "epoch": 1.8, "learning_rate": 2.9640275952693825e-06, "loss": 1.4441, "step": 10982 }, { "epoch": 1.8, "learning_rate": 2.961563731931669e-06, "loss": 0.3347, "step": 10983 }, { "epoch": 1.8, "learning_rate": 2.9590998685939553e-06, "loss": 0.4289, "step": 10984 }, { "epoch": 1.8, "learning_rate": 2.9566360052562417e-06, "loss": 0.8083, "step": 10985 }, { "epoch": 1.8, "learning_rate": 2.954172141918528e-06, "loss": 0.4587, "step": 10986 }, { "epoch": 1.8, "learning_rate": 2.951708278580815e-06, "loss": 0.3527, "step": 10987 }, { "epoch": 1.8, "learning_rate": 2.9492444152431014e-06, "loss": 0.46, "step": 10988 }, { "epoch": 1.81, "learning_rate": 2.9467805519053873e-06, "loss": 0.4576, "step": 10989 }, { "epoch": 1.81, "learning_rate": 2.944316688567674e-06, "loss": 0.2014, "step": 10990 }, { "epoch": 1.81, "learning_rate": 2.9418528252299606e-06, "loss": 0.4043, "step": 10991 }, { "epoch": 1.81, "learning_rate": 2.939388961892247e-06, "loss": 0.3904, "step": 10992 }, { "epoch": 1.81, "learning_rate": 2.936925098554534e-06, "loss": 0.5964, "step": 10993 }, { "epoch": 1.81, "learning_rate": 2.93446123521682e-06, "loss": 0.9819, "step": 10994 }, { "epoch": 1.81, "learning_rate": 2.931997371879106e-06, "loss": 0.2351, "step": 10995 }, { "epoch": 1.81, "learning_rate": 2.929533508541393e-06, "loss": 0.3448, "step": 10996 }, { "epoch": 1.81, "learning_rate": 2.9270696452036794e-06, "loss": 0.4584, "step": 10997 }, { "epoch": 1.81, "learning_rate": 2.924605781865966e-06, "loss": 1.065, "step": 10998 }, { "epoch": 1.81, "learning_rate": 2.9221419185282523e-06, "loss": 0.4315, "step": 10999 }, { "epoch": 1.81, "learning_rate": 2.9196780551905387e-06, "loss": 0.3162, "step": 11000 }, { "epoch": 1.81, "eval_exact_match": 86.86849574266793, "eval_f1": 93.10736976332365, "step": 11000 }, { "epoch": 1.81, "learning_rate": 2.917214191852825e-06, "loss": 0.8291, "step": 11001 }, { "epoch": 1.81, "learning_rate": 2.914750328515112e-06, "loss": 0.7518, "step": 11002 }, { "epoch": 1.81, "learning_rate": 2.9122864651773983e-06, "loss": 0.1862, "step": 11003 }, { "epoch": 1.81, "learning_rate": 2.9098226018396843e-06, "loss": 0.5247, "step": 11004 }, { "epoch": 1.81, "learning_rate": 2.907358738501971e-06, "loss": 0.2842, "step": 11005 }, { "epoch": 1.81, "learning_rate": 2.9048948751642575e-06, "loss": 0.3726, "step": 11006 }, { "epoch": 1.81, "learning_rate": 2.902431011826544e-06, "loss": 0.5953, "step": 11007 }, { "epoch": 1.81, "learning_rate": 2.8999671484888308e-06, "loss": 0.589, "step": 11008 }, { "epoch": 1.81, "learning_rate": 2.8975032851511168e-06, "loss": 1.0, "step": 11009 }, { "epoch": 1.81, "learning_rate": 2.8950394218134036e-06, "loss": 0.5236, "step": 11010 }, { "epoch": 1.81, "learning_rate": 2.89257555847569e-06, "loss": 0.3251, "step": 11011 }, { "epoch": 1.81, "learning_rate": 2.8901116951379764e-06, "loss": 1.1479, "step": 11012 }, { "epoch": 1.81, "learning_rate": 2.8876478318002632e-06, "loss": 0.2569, "step": 11013 }, { "epoch": 1.81, "learning_rate": 2.8851839684625492e-06, "loss": 0.2168, "step": 11014 }, { "epoch": 1.81, "learning_rate": 2.8827201051248356e-06, "loss": 0.866, "step": 11015 }, { "epoch": 1.81, "learning_rate": 2.8802562417871225e-06, "loss": 0.6887, "step": 11016 }, { "epoch": 1.81, "learning_rate": 2.877792378449409e-06, "loss": 0.418, "step": 11017 }, { "epoch": 1.81, "learning_rate": 2.8753285151116953e-06, "loss": 0.2653, "step": 11018 }, { "epoch": 1.81, "learning_rate": 2.8728646517739817e-06, "loss": 0.4292, "step": 11019 }, { "epoch": 1.81, "learning_rate": 2.870400788436268e-06, "loss": 0.3551, "step": 11020 }, { "epoch": 1.81, "learning_rate": 2.8679369250985545e-06, "loss": 0.309, "step": 11021 }, { "epoch": 1.81, "learning_rate": 2.8654730617608413e-06, "loss": 0.2938, "step": 11022 }, { "epoch": 1.81, "learning_rate": 2.8630091984231278e-06, "loss": 0.4828, "step": 11023 }, { "epoch": 1.81, "learning_rate": 2.8605453350854137e-06, "loss": 0.6198, "step": 11024 }, { "epoch": 1.81, "learning_rate": 2.8580814717477006e-06, "loss": 0.2731, "step": 11025 }, { "epoch": 1.81, "learning_rate": 2.855617608409987e-06, "loss": 0.3488, "step": 11026 }, { "epoch": 1.81, "learning_rate": 2.8531537450722734e-06, "loss": 0.5307, "step": 11027 }, { "epoch": 1.81, "learning_rate": 2.8506898817345602e-06, "loss": 0.191, "step": 11028 }, { "epoch": 1.81, "learning_rate": 2.848226018396846e-06, "loss": 0.1866, "step": 11029 }, { "epoch": 1.81, "learning_rate": 2.8457621550591326e-06, "loss": 0.3704, "step": 11030 }, { "epoch": 1.81, "learning_rate": 2.8432982917214194e-06, "loss": 0.3552, "step": 11031 }, { "epoch": 1.81, "learning_rate": 2.840834428383706e-06, "loss": 0.2056, "step": 11032 }, { "epoch": 1.81, "learning_rate": 2.8383705650459923e-06, "loss": 0.3715, "step": 11033 }, { "epoch": 1.81, "learning_rate": 2.8359067017082787e-06, "loss": 0.1722, "step": 11034 }, { "epoch": 1.81, "learning_rate": 2.833442838370565e-06, "loss": 0.4243, "step": 11035 }, { "epoch": 1.81, "learning_rate": 2.8309789750328515e-06, "loss": 0.3617, "step": 11036 }, { "epoch": 1.81, "learning_rate": 2.8285151116951383e-06, "loss": 0.6248, "step": 11037 }, { "epoch": 1.81, "learning_rate": 2.8260512483574247e-06, "loss": 0.4665, "step": 11038 }, { "epoch": 1.81, "learning_rate": 2.8235873850197107e-06, "loss": 0.5578, "step": 11039 }, { "epoch": 1.81, "learning_rate": 2.8211235216819975e-06, "loss": 0.2838, "step": 11040 }, { "epoch": 1.81, "learning_rate": 2.818659658344284e-06, "loss": 0.1971, "step": 11041 }, { "epoch": 1.81, "learning_rate": 2.8161957950065704e-06, "loss": 0.3567, "step": 11042 }, { "epoch": 1.81, "learning_rate": 2.813731931668857e-06, "loss": 0.7902, "step": 11043 }, { "epoch": 1.81, "learning_rate": 2.811268068331143e-06, "loss": 0.698, "step": 11044 }, { "epoch": 1.81, "learning_rate": 2.8088042049934296e-06, "loss": 0.3946, "step": 11045 }, { "epoch": 1.81, "learning_rate": 2.8063403416557164e-06, "loss": 0.4803, "step": 11046 }, { "epoch": 1.81, "learning_rate": 2.803876478318003e-06, "loss": 0.5569, "step": 11047 }, { "epoch": 1.81, "learning_rate": 2.8014126149802892e-06, "loss": 0.6132, "step": 11048 }, { "epoch": 1.81, "learning_rate": 2.7989487516425756e-06, "loss": 0.4061, "step": 11049 }, { "epoch": 1.82, "learning_rate": 2.796484888304862e-06, "loss": 0.3576, "step": 11050 }, { "epoch": 1.82, "learning_rate": 2.7940210249671484e-06, "loss": 0.3529, "step": 11051 }, { "epoch": 1.82, "learning_rate": 2.7915571616294353e-06, "loss": 0.2793, "step": 11052 }, { "epoch": 1.82, "learning_rate": 2.7890932982917217e-06, "loss": 0.4109, "step": 11053 }, { "epoch": 1.82, "learning_rate": 2.7866294349540077e-06, "loss": 0.5663, "step": 11054 }, { "epoch": 1.82, "learning_rate": 2.7841655716162945e-06, "loss": 0.3996, "step": 11055 }, { "epoch": 1.82, "learning_rate": 2.781701708278581e-06, "loss": 0.3458, "step": 11056 }, { "epoch": 1.82, "learning_rate": 2.7792378449408673e-06, "loss": 0.9703, "step": 11057 }, { "epoch": 1.82, "learning_rate": 2.776773981603154e-06, "loss": 0.8631, "step": 11058 }, { "epoch": 1.82, "learning_rate": 2.77431011826544e-06, "loss": 0.8984, "step": 11059 }, { "epoch": 1.82, "learning_rate": 2.7718462549277265e-06, "loss": 0.3194, "step": 11060 }, { "epoch": 1.82, "learning_rate": 2.7693823915900134e-06, "loss": 0.7945, "step": 11061 }, { "epoch": 1.82, "learning_rate": 2.7669185282522998e-06, "loss": 0.4965, "step": 11062 }, { "epoch": 1.82, "learning_rate": 2.764454664914586e-06, "loss": 0.5186, "step": 11063 }, { "epoch": 1.82, "learning_rate": 2.7619908015768726e-06, "loss": 0.9108, "step": 11064 }, { "epoch": 1.82, "learning_rate": 2.759526938239159e-06, "loss": 0.5131, "step": 11065 }, { "epoch": 1.82, "learning_rate": 2.7570630749014454e-06, "loss": 0.3953, "step": 11066 }, { "epoch": 1.82, "learning_rate": 2.7545992115637322e-06, "loss": 0.4287, "step": 11067 }, { "epoch": 1.82, "learning_rate": 2.7521353482260187e-06, "loss": 0.6071, "step": 11068 }, { "epoch": 1.82, "learning_rate": 2.7496714848883046e-06, "loss": 0.1545, "step": 11069 }, { "epoch": 1.82, "learning_rate": 2.7472076215505915e-06, "loss": 0.3149, "step": 11070 }, { "epoch": 1.82, "learning_rate": 2.744743758212878e-06, "loss": 0.4934, "step": 11071 }, { "epoch": 1.82, "learning_rate": 2.7422798948751643e-06, "loss": 0.3947, "step": 11072 }, { "epoch": 1.82, "learning_rate": 2.739816031537451e-06, "loss": 0.3711, "step": 11073 }, { "epoch": 1.82, "learning_rate": 2.737352168199737e-06, "loss": 0.4793, "step": 11074 }, { "epoch": 1.82, "learning_rate": 2.7348883048620235e-06, "loss": 0.6349, "step": 11075 }, { "epoch": 1.82, "learning_rate": 2.7324244415243103e-06, "loss": 0.2575, "step": 11076 }, { "epoch": 1.82, "learning_rate": 2.7299605781865968e-06, "loss": 0.567, "step": 11077 }, { "epoch": 1.82, "learning_rate": 2.727496714848883e-06, "loss": 0.4591, "step": 11078 }, { "epoch": 1.82, "learning_rate": 2.7250328515111696e-06, "loss": 0.7732, "step": 11079 }, { "epoch": 1.82, "learning_rate": 2.722568988173456e-06, "loss": 1.1705, "step": 11080 }, { "epoch": 1.82, "learning_rate": 2.7201051248357424e-06, "loss": 0.4815, "step": 11081 }, { "epoch": 1.82, "learning_rate": 2.7176412614980292e-06, "loss": 0.3979, "step": 11082 }, { "epoch": 1.82, "learning_rate": 2.7151773981603156e-06, "loss": 0.3065, "step": 11083 }, { "epoch": 1.82, "learning_rate": 2.7127135348226016e-06, "loss": 0.3892, "step": 11084 }, { "epoch": 1.82, "learning_rate": 2.7102496714848884e-06, "loss": 0.2691, "step": 11085 }, { "epoch": 1.82, "learning_rate": 2.707785808147175e-06, "loss": 0.282, "step": 11086 }, { "epoch": 1.82, "learning_rate": 2.7053219448094613e-06, "loss": 0.2778, "step": 11087 }, { "epoch": 1.82, "learning_rate": 2.702858081471748e-06, "loss": 0.3294, "step": 11088 }, { "epoch": 1.82, "learning_rate": 2.700394218134034e-06, "loss": 0.6904, "step": 11089 }, { "epoch": 1.82, "learning_rate": 2.6979303547963205e-06, "loss": 0.4855, "step": 11090 }, { "epoch": 1.82, "learning_rate": 2.6954664914586073e-06, "loss": 0.7028, "step": 11091 }, { "epoch": 1.82, "learning_rate": 2.6930026281208937e-06, "loss": 0.2262, "step": 11092 }, { "epoch": 1.82, "learning_rate": 2.69053876478318e-06, "loss": 1.1912, "step": 11093 }, { "epoch": 1.82, "learning_rate": 2.6880749014454665e-06, "loss": 0.7361, "step": 11094 }, { "epoch": 1.82, "learning_rate": 2.685611038107753e-06, "loss": 0.2362, "step": 11095 }, { "epoch": 1.82, "learning_rate": 2.6831471747700394e-06, "loss": 0.3378, "step": 11096 }, { "epoch": 1.82, "learning_rate": 2.680683311432326e-06, "loss": 0.5391, "step": 11097 }, { "epoch": 1.82, "learning_rate": 2.6782194480946126e-06, "loss": 0.6534, "step": 11098 }, { "epoch": 1.82, "learning_rate": 2.6757555847568986e-06, "loss": 0.2419, "step": 11099 }, { "epoch": 1.82, "learning_rate": 2.6732917214191854e-06, "loss": 0.2394, "step": 11100 }, { "epoch": 1.82, "learning_rate": 2.670827858081472e-06, "loss": 0.2206, "step": 11101 }, { "epoch": 1.82, "learning_rate": 2.6683639947437582e-06, "loss": 0.8403, "step": 11102 }, { "epoch": 1.82, "learning_rate": 2.665900131406045e-06, "loss": 0.7072, "step": 11103 }, { "epoch": 1.82, "learning_rate": 2.663436268068331e-06, "loss": 0.5739, "step": 11104 }, { "epoch": 1.82, "learning_rate": 2.6609724047306174e-06, "loss": 0.718, "step": 11105 }, { "epoch": 1.82, "learning_rate": 2.6585085413929043e-06, "loss": 0.2636, "step": 11106 }, { "epoch": 1.82, "learning_rate": 2.6560446780551907e-06, "loss": 0.4199, "step": 11107 }, { "epoch": 1.82, "learning_rate": 2.653580814717477e-06, "loss": 0.61, "step": 11108 }, { "epoch": 1.82, "learning_rate": 2.6511169513797635e-06, "loss": 0.8156, "step": 11109 }, { "epoch": 1.82, "learning_rate": 2.64865308804205e-06, "loss": 0.4243, "step": 11110 }, { "epoch": 1.83, "learning_rate": 2.6461892247043363e-06, "loss": 0.842, "step": 11111 }, { "epoch": 1.83, "learning_rate": 2.643725361366623e-06, "loss": 0.1462, "step": 11112 }, { "epoch": 1.83, "learning_rate": 2.6412614980289096e-06, "loss": 0.1692, "step": 11113 }, { "epoch": 1.83, "learning_rate": 2.6387976346911955e-06, "loss": 0.3397, "step": 11114 }, { "epoch": 1.83, "learning_rate": 2.6363337713534824e-06, "loss": 0.3164, "step": 11115 }, { "epoch": 1.83, "learning_rate": 2.6338699080157688e-06, "loss": 0.4853, "step": 11116 }, { "epoch": 1.83, "learning_rate": 2.631406044678055e-06, "loss": 0.1535, "step": 11117 }, { "epoch": 1.83, "learning_rate": 2.628942181340342e-06, "loss": 0.1532, "step": 11118 }, { "epoch": 1.83, "learning_rate": 2.626478318002628e-06, "loss": 0.3901, "step": 11119 }, { "epoch": 1.83, "learning_rate": 2.6240144546649144e-06, "loss": 0.4338, "step": 11120 }, { "epoch": 1.83, "learning_rate": 2.6215505913272012e-06, "loss": 0.7689, "step": 11121 }, { "epoch": 1.83, "learning_rate": 2.6190867279894877e-06, "loss": 0.7477, "step": 11122 }, { "epoch": 1.83, "learning_rate": 2.616622864651774e-06, "loss": 0.5725, "step": 11123 }, { "epoch": 1.83, "learning_rate": 2.6141590013140605e-06, "loss": 0.4189, "step": 11124 }, { "epoch": 1.83, "learning_rate": 2.611695137976347e-06, "loss": 0.1269, "step": 11125 }, { "epoch": 1.83, "learning_rate": 2.6092312746386333e-06, "loss": 0.6982, "step": 11126 }, { "epoch": 1.83, "learning_rate": 2.60676741130092e-06, "loss": 0.4644, "step": 11127 }, { "epoch": 1.83, "learning_rate": 2.6043035479632065e-06, "loss": 0.4131, "step": 11128 }, { "epoch": 1.83, "learning_rate": 2.6018396846254925e-06, "loss": 0.4813, "step": 11129 }, { "epoch": 1.83, "learning_rate": 2.5993758212877793e-06, "loss": 0.472, "step": 11130 }, { "epoch": 1.83, "learning_rate": 2.5969119579500658e-06, "loss": 0.4114, "step": 11131 }, { "epoch": 1.83, "learning_rate": 2.594448094612352e-06, "loss": 0.269, "step": 11132 }, { "epoch": 1.83, "learning_rate": 2.591984231274639e-06, "loss": 0.7599, "step": 11133 }, { "epoch": 1.83, "learning_rate": 2.589520367936925e-06, "loss": 0.4083, "step": 11134 }, { "epoch": 1.83, "learning_rate": 2.5870565045992114e-06, "loss": 0.3787, "step": 11135 }, { "epoch": 1.83, "learning_rate": 2.5845926412614982e-06, "loss": 0.8622, "step": 11136 }, { "epoch": 1.83, "learning_rate": 2.5821287779237846e-06, "loss": 1.1572, "step": 11137 }, { "epoch": 1.83, "learning_rate": 2.579664914586071e-06, "loss": 0.5829, "step": 11138 }, { "epoch": 1.83, "learning_rate": 2.5772010512483574e-06, "loss": 0.4827, "step": 11139 }, { "epoch": 1.83, "learning_rate": 2.574737187910644e-06, "loss": 0.5269, "step": 11140 }, { "epoch": 1.83, "learning_rate": 2.5722733245729303e-06, "loss": 1.058, "step": 11141 }, { "epoch": 1.83, "learning_rate": 2.569809461235217e-06, "loss": 0.9763, "step": 11142 }, { "epoch": 1.83, "learning_rate": 2.567345597897503e-06, "loss": 0.8754, "step": 11143 }, { "epoch": 1.83, "learning_rate": 2.5648817345597895e-06, "loss": 0.4937, "step": 11144 }, { "epoch": 1.83, "learning_rate": 2.5624178712220763e-06, "loss": 1.1864, "step": 11145 }, { "epoch": 1.83, "learning_rate": 2.5599540078843627e-06, "loss": 0.3602, "step": 11146 }, { "epoch": 1.83, "learning_rate": 2.557490144546649e-06, "loss": 0.4092, "step": 11147 }, { "epoch": 1.83, "learning_rate": 2.5550262812089355e-06, "loss": 0.6278, "step": 11148 }, { "epoch": 1.83, "learning_rate": 2.552562417871222e-06, "loss": 0.4849, "step": 11149 }, { "epoch": 1.83, "learning_rate": 2.5500985545335088e-06, "loss": 0.3987, "step": 11150 }, { "epoch": 1.83, "learning_rate": 2.547634691195795e-06, "loss": 0.3867, "step": 11151 }, { "epoch": 1.83, "learning_rate": 2.5451708278580816e-06, "loss": 0.6385, "step": 11152 }, { "epoch": 1.83, "learning_rate": 2.542706964520368e-06, "loss": 0.6387, "step": 11153 }, { "epoch": 1.83, "learning_rate": 2.5402431011826544e-06, "loss": 0.8624, "step": 11154 }, { "epoch": 1.83, "learning_rate": 2.537779237844941e-06, "loss": 0.4263, "step": 11155 }, { "epoch": 1.83, "learning_rate": 2.5353153745072276e-06, "loss": 0.3811, "step": 11156 }, { "epoch": 1.83, "learning_rate": 2.532851511169514e-06, "loss": 0.451, "step": 11157 }, { "epoch": 1.83, "learning_rate": 2.5303876478318e-06, "loss": 0.3741, "step": 11158 }, { "epoch": 1.83, "learning_rate": 2.527923784494087e-06, "loss": 1.4776, "step": 11159 }, { "epoch": 1.83, "learning_rate": 2.5254599211563733e-06, "loss": 0.5583, "step": 11160 }, { "epoch": 1.83, "learning_rate": 2.5229960578186597e-06, "loss": 0.7093, "step": 11161 }, { "epoch": 1.83, "learning_rate": 2.5205321944809465e-06, "loss": 0.6409, "step": 11162 }, { "epoch": 1.83, "learning_rate": 2.5180683311432325e-06, "loss": 0.2809, "step": 11163 }, { "epoch": 1.83, "learning_rate": 2.515604467805519e-06, "loss": 0.3314, "step": 11164 }, { "epoch": 1.83, "learning_rate": 2.5131406044678057e-06, "loss": 0.445, "step": 11165 }, { "epoch": 1.83, "learning_rate": 2.510676741130092e-06, "loss": 0.4794, "step": 11166 }, { "epoch": 1.83, "learning_rate": 2.5082128777923786e-06, "loss": 0.6054, "step": 11167 }, { "epoch": 1.83, "learning_rate": 2.505749014454665e-06, "loss": 0.3755, "step": 11168 }, { "epoch": 1.83, "learning_rate": 2.5032851511169514e-06, "loss": 0.3652, "step": 11169 }, { "epoch": 1.83, "learning_rate": 2.5008212877792378e-06, "loss": 0.5265, "step": 11170 }, { "epoch": 1.83, "learning_rate": 2.4983574244415246e-06, "loss": 0.868, "step": 11171 }, { "epoch": 1.84, "learning_rate": 2.495893561103811e-06, "loss": 0.2668, "step": 11172 }, { "epoch": 1.84, "learning_rate": 2.493429697766097e-06, "loss": 0.5172, "step": 11173 }, { "epoch": 1.84, "learning_rate": 2.490965834428384e-06, "loss": 0.6574, "step": 11174 }, { "epoch": 1.84, "learning_rate": 2.4885019710906703e-06, "loss": 0.7741, "step": 11175 }, { "epoch": 1.84, "learning_rate": 2.4860381077529567e-06, "loss": 0.3162, "step": 11176 }, { "epoch": 1.84, "learning_rate": 2.4835742444152435e-06, "loss": 0.4621, "step": 11177 }, { "epoch": 1.84, "learning_rate": 2.4811103810775295e-06, "loss": 0.4843, "step": 11178 }, { "epoch": 1.84, "learning_rate": 2.478646517739816e-06, "loss": 0.723, "step": 11179 }, { "epoch": 1.84, "learning_rate": 2.4761826544021027e-06, "loss": 0.335, "step": 11180 }, { "epoch": 1.84, "learning_rate": 2.473718791064389e-06, "loss": 0.3775, "step": 11181 }, { "epoch": 1.84, "learning_rate": 2.4712549277266755e-06, "loss": 0.6057, "step": 11182 }, { "epoch": 1.84, "learning_rate": 2.468791064388962e-06, "loss": 0.6885, "step": 11183 }, { "epoch": 1.84, "learning_rate": 2.4663272010512483e-06, "loss": 0.251, "step": 11184 }, { "epoch": 1.84, "learning_rate": 2.4638633377135348e-06, "loss": 0.4025, "step": 11185 }, { "epoch": 1.84, "learning_rate": 2.4613994743758216e-06, "loss": 0.3223, "step": 11186 }, { "epoch": 1.84, "learning_rate": 2.458935611038108e-06, "loss": 0.1729, "step": 11187 }, { "epoch": 1.84, "learning_rate": 2.456471747700394e-06, "loss": 0.1797, "step": 11188 }, { "epoch": 1.84, "learning_rate": 2.454007884362681e-06, "loss": 0.8588, "step": 11189 }, { "epoch": 1.84, "learning_rate": 2.4515440210249672e-06, "loss": 0.3604, "step": 11190 }, { "epoch": 1.84, "learning_rate": 2.4490801576872536e-06, "loss": 0.2894, "step": 11191 }, { "epoch": 1.84, "learning_rate": 2.4466162943495405e-06, "loss": 0.5143, "step": 11192 }, { "epoch": 1.84, "learning_rate": 2.4441524310118264e-06, "loss": 0.3757, "step": 11193 }, { "epoch": 1.84, "learning_rate": 2.441688567674113e-06, "loss": 0.2545, "step": 11194 }, { "epoch": 1.84, "learning_rate": 2.4392247043363997e-06, "loss": 0.5307, "step": 11195 }, { "epoch": 1.84, "learning_rate": 2.436760840998686e-06, "loss": 0.2869, "step": 11196 }, { "epoch": 1.84, "learning_rate": 2.4342969776609725e-06, "loss": 0.3712, "step": 11197 }, { "epoch": 1.84, "learning_rate": 2.431833114323259e-06, "loss": 0.3404, "step": 11198 }, { "epoch": 1.84, "learning_rate": 2.4293692509855453e-06, "loss": 0.3977, "step": 11199 }, { "epoch": 1.84, "learning_rate": 2.4269053876478317e-06, "loss": 0.5636, "step": 11200 }, { "epoch": 1.84, "learning_rate": 2.4244415243101186e-06, "loss": 0.5381, "step": 11201 }, { "epoch": 1.84, "learning_rate": 2.421977660972405e-06, "loss": 0.256, "step": 11202 }, { "epoch": 1.84, "learning_rate": 2.419513797634691e-06, "loss": 0.5116, "step": 11203 }, { "epoch": 1.84, "learning_rate": 2.4170499342969778e-06, "loss": 0.4439, "step": 11204 }, { "epoch": 1.84, "learning_rate": 2.414586070959264e-06, "loss": 0.3243, "step": 11205 }, { "epoch": 1.84, "learning_rate": 2.4121222076215506e-06, "loss": 0.5036, "step": 11206 }, { "epoch": 1.84, "learning_rate": 2.4096583442838374e-06, "loss": 0.1301, "step": 11207 }, { "epoch": 1.84, "learning_rate": 2.4071944809461234e-06, "loss": 0.8804, "step": 11208 }, { "epoch": 1.84, "learning_rate": 2.40473061760841e-06, "loss": 0.6804, "step": 11209 }, { "epoch": 1.84, "learning_rate": 2.4022667542706967e-06, "loss": 0.6299, "step": 11210 }, { "epoch": 1.84, "learning_rate": 2.399802890932983e-06, "loss": 0.3554, "step": 11211 }, { "epoch": 1.84, "learning_rate": 2.3973390275952695e-06, "loss": 0.504, "step": 11212 }, { "epoch": 1.84, "learning_rate": 2.394875164257556e-06, "loss": 0.296, "step": 11213 }, { "epoch": 1.84, "learning_rate": 2.3924113009198423e-06, "loss": 0.918, "step": 11214 }, { "epoch": 1.84, "learning_rate": 2.3899474375821287e-06, "loss": 0.2768, "step": 11215 }, { "epoch": 1.84, "learning_rate": 2.3874835742444155e-06, "loss": 0.3178, "step": 11216 }, { "epoch": 1.84, "learning_rate": 2.385019710906702e-06, "loss": 0.1687, "step": 11217 }, { "epoch": 1.84, "learning_rate": 2.382555847568988e-06, "loss": 0.1853, "step": 11218 }, { "epoch": 1.84, "learning_rate": 2.3800919842312747e-06, "loss": 0.2902, "step": 11219 }, { "epoch": 1.84, "learning_rate": 2.377628120893561e-06, "loss": 0.4625, "step": 11220 }, { "epoch": 1.84, "learning_rate": 2.3751642575558476e-06, "loss": 0.2443, "step": 11221 }, { "epoch": 1.84, "learning_rate": 2.3727003942181344e-06, "loss": 0.9749, "step": 11222 }, { "epoch": 1.84, "learning_rate": 2.3702365308804204e-06, "loss": 0.4107, "step": 11223 }, { "epoch": 1.84, "learning_rate": 2.3677726675427068e-06, "loss": 0.1412, "step": 11224 }, { "epoch": 1.84, "learning_rate": 2.3653088042049936e-06, "loss": 0.2474, "step": 11225 }, { "epoch": 1.84, "learning_rate": 2.36284494086728e-06, "loss": 0.5826, "step": 11226 }, { "epoch": 1.84, "learning_rate": 2.3603810775295664e-06, "loss": 0.4341, "step": 11227 }, { "epoch": 1.84, "learning_rate": 2.357917214191853e-06, "loss": 0.8043, "step": 11228 }, { "epoch": 1.84, "learning_rate": 2.3554533508541393e-06, "loss": 0.52, "step": 11229 }, { "epoch": 1.84, "learning_rate": 2.3529894875164257e-06, "loss": 0.2727, "step": 11230 }, { "epoch": 1.84, "learning_rate": 2.3505256241787125e-06, "loss": 0.3251, "step": 11231 }, { "epoch": 1.84, "learning_rate": 2.348061760840999e-06, "loss": 0.3705, "step": 11232 }, { "epoch": 1.85, "learning_rate": 2.345597897503285e-06, "loss": 0.4473, "step": 11233 }, { "epoch": 1.85, "learning_rate": 2.3431340341655717e-06, "loss": 0.3966, "step": 11234 }, { "epoch": 1.85, "learning_rate": 2.340670170827858e-06, "loss": 0.6272, "step": 11235 }, { "epoch": 1.85, "learning_rate": 2.3382063074901445e-06, "loss": 0.7655, "step": 11236 }, { "epoch": 1.85, "learning_rate": 2.3357424441524314e-06, "loss": 0.1992, "step": 11237 }, { "epoch": 1.85, "learning_rate": 2.3332785808147173e-06, "loss": 0.4037, "step": 11238 }, { "epoch": 1.85, "learning_rate": 2.3308147174770038e-06, "loss": 0.417, "step": 11239 }, { "epoch": 1.85, "learning_rate": 2.3283508541392906e-06, "loss": 0.5329, "step": 11240 }, { "epoch": 1.85, "learning_rate": 2.325886990801577e-06, "loss": 0.6991, "step": 11241 }, { "epoch": 1.85, "learning_rate": 2.3234231274638634e-06, "loss": 0.1971, "step": 11242 }, { "epoch": 1.85, "learning_rate": 2.32095926412615e-06, "loss": 0.5767, "step": 11243 }, { "epoch": 1.85, "learning_rate": 2.3184954007884362e-06, "loss": 1.039, "step": 11244 }, { "epoch": 1.85, "learning_rate": 2.3160315374507226e-06, "loss": 0.2597, "step": 11245 }, { "epoch": 1.85, "learning_rate": 2.3135676741130095e-06, "loss": 0.5054, "step": 11246 }, { "epoch": 1.85, "learning_rate": 2.311103810775296e-06, "loss": 0.1676, "step": 11247 }, { "epoch": 1.85, "learning_rate": 2.308639947437582e-06, "loss": 0.1591, "step": 11248 }, { "epoch": 1.85, "learning_rate": 2.3061760840998687e-06, "loss": 0.1717, "step": 11249 }, { "epoch": 1.85, "learning_rate": 2.303712220762155e-06, "loss": 0.4171, "step": 11250 }, { "epoch": 1.85, "learning_rate": 2.3012483574244415e-06, "loss": 0.5267, "step": 11251 }, { "epoch": 1.85, "learning_rate": 2.2987844940867283e-06, "loss": 0.1628, "step": 11252 }, { "epoch": 1.85, "learning_rate": 2.2963206307490143e-06, "loss": 0.3206, "step": 11253 }, { "epoch": 1.85, "learning_rate": 2.2938567674113007e-06, "loss": 0.3319, "step": 11254 }, { "epoch": 1.85, "learning_rate": 2.2913929040735876e-06, "loss": 0.5838, "step": 11255 }, { "epoch": 1.85, "learning_rate": 2.288929040735874e-06, "loss": 0.4351, "step": 11256 }, { "epoch": 1.85, "learning_rate": 2.2864651773981604e-06, "loss": 0.5667, "step": 11257 }, { "epoch": 1.85, "learning_rate": 2.2840013140604468e-06, "loss": 0.695, "step": 11258 }, { "epoch": 1.85, "learning_rate": 2.281537450722733e-06, "loss": 0.7718, "step": 11259 }, { "epoch": 1.85, "learning_rate": 2.2790735873850196e-06, "loss": 0.2756, "step": 11260 }, { "epoch": 1.85, "learning_rate": 2.2766097240473064e-06, "loss": 0.4503, "step": 11261 }, { "epoch": 1.85, "learning_rate": 2.274145860709593e-06, "loss": 0.2378, "step": 11262 }, { "epoch": 1.85, "learning_rate": 2.271681997371879e-06, "loss": 0.5477, "step": 11263 }, { "epoch": 1.85, "learning_rate": 2.2692181340341657e-06, "loss": 0.1282, "step": 11264 }, { "epoch": 1.85, "learning_rate": 2.266754270696452e-06, "loss": 0.5668, "step": 11265 }, { "epoch": 1.85, "learning_rate": 2.2642904073587385e-06, "loss": 0.7967, "step": 11266 }, { "epoch": 1.85, "learning_rate": 2.2618265440210253e-06, "loss": 0.4711, "step": 11267 }, { "epoch": 1.85, "learning_rate": 2.2593626806833113e-06, "loss": 0.9887, "step": 11268 }, { "epoch": 1.85, "learning_rate": 2.2568988173455977e-06, "loss": 0.6063, "step": 11269 }, { "epoch": 1.85, "learning_rate": 2.2544349540078845e-06, "loss": 0.2362, "step": 11270 }, { "epoch": 1.85, "learning_rate": 2.251971090670171e-06, "loss": 0.6104, "step": 11271 }, { "epoch": 1.85, "learning_rate": 2.2495072273324573e-06, "loss": 0.3393, "step": 11272 }, { "epoch": 1.85, "learning_rate": 2.2470433639947437e-06, "loss": 0.2569, "step": 11273 }, { "epoch": 1.85, "learning_rate": 2.24457950065703e-06, "loss": 0.5304, "step": 11274 }, { "epoch": 1.85, "learning_rate": 2.2421156373193166e-06, "loss": 0.4772, "step": 11275 }, { "epoch": 1.85, "learning_rate": 2.2396517739816034e-06, "loss": 0.3302, "step": 11276 }, { "epoch": 1.85, "learning_rate": 2.23718791064389e-06, "loss": 0.2569, "step": 11277 }, { "epoch": 1.85, "learning_rate": 2.2347240473061758e-06, "loss": 0.3206, "step": 11278 }, { "epoch": 1.85, "learning_rate": 2.2322601839684626e-06, "loss": 0.2769, "step": 11279 }, { "epoch": 1.85, "learning_rate": 2.229796320630749e-06, "loss": 0.6254, "step": 11280 }, { "epoch": 1.85, "learning_rate": 2.2273324572930354e-06, "loss": 1.0299, "step": 11281 }, { "epoch": 1.85, "learning_rate": 2.2248685939553223e-06, "loss": 0.5783, "step": 11282 }, { "epoch": 1.85, "learning_rate": 2.2224047306176083e-06, "loss": 0.7233, "step": 11283 }, { "epoch": 1.85, "learning_rate": 2.2199408672798947e-06, "loss": 0.6871, "step": 11284 }, { "epoch": 1.85, "learning_rate": 2.2174770039421815e-06, "loss": 1.0362, "step": 11285 }, { "epoch": 1.85, "learning_rate": 2.215013140604468e-06, "loss": 0.4942, "step": 11286 }, { "epoch": 1.85, "learning_rate": 2.2125492772667543e-06, "loss": 0.8266, "step": 11287 }, { "epoch": 1.85, "learning_rate": 2.2100854139290407e-06, "loss": 0.8202, "step": 11288 }, { "epoch": 1.85, "learning_rate": 2.207621550591327e-06, "loss": 0.3226, "step": 11289 }, { "epoch": 1.85, "learning_rate": 2.205157687253614e-06, "loss": 0.5432, "step": 11290 }, { "epoch": 1.85, "learning_rate": 2.2026938239159004e-06, "loss": 0.9815, "step": 11291 }, { "epoch": 1.85, "learning_rate": 2.2002299605781868e-06, "loss": 0.4787, "step": 11292 }, { "epoch": 1.85, "learning_rate": 2.197766097240473e-06, "loss": 0.2675, "step": 11293 }, { "epoch": 1.86, "learning_rate": 2.1953022339027596e-06, "loss": 0.451, "step": 11294 }, { "epoch": 1.86, "learning_rate": 2.192838370565046e-06, "loss": 0.6874, "step": 11295 }, { "epoch": 1.86, "learning_rate": 2.190374507227333e-06, "loss": 0.3059, "step": 11296 }, { "epoch": 1.86, "learning_rate": 2.1879106438896192e-06, "loss": 0.3836, "step": 11297 }, { "epoch": 1.86, "learning_rate": 2.1854467805519052e-06, "loss": 0.3988, "step": 11298 }, { "epoch": 1.86, "learning_rate": 2.182982917214192e-06, "loss": 0.3203, "step": 11299 }, { "epoch": 1.86, "learning_rate": 2.1805190538764785e-06, "loss": 0.9933, "step": 11300 }, { "epoch": 1.86, "learning_rate": 2.178055190538765e-06, "loss": 0.5033, "step": 11301 }, { "epoch": 1.86, "learning_rate": 2.1755913272010517e-06, "loss": 0.2276, "step": 11302 }, { "epoch": 1.86, "learning_rate": 2.1731274638633377e-06, "loss": 0.5632, "step": 11303 }, { "epoch": 1.86, "learning_rate": 2.170663600525624e-06, "loss": 0.4529, "step": 11304 }, { "epoch": 1.86, "learning_rate": 2.168199737187911e-06, "loss": 0.5398, "step": 11305 }, { "epoch": 1.86, "learning_rate": 2.1657358738501973e-06, "loss": 0.2457, "step": 11306 }, { "epoch": 1.86, "learning_rate": 2.1632720105124837e-06, "loss": 0.581, "step": 11307 }, { "epoch": 1.86, "learning_rate": 2.16080814717477e-06, "loss": 0.3762, "step": 11308 }, { "epoch": 1.86, "learning_rate": 2.1583442838370566e-06, "loss": 0.3551, "step": 11309 }, { "epoch": 1.86, "learning_rate": 2.155880420499343e-06, "loss": 0.3801, "step": 11310 }, { "epoch": 1.86, "learning_rate": 2.15341655716163e-06, "loss": 0.5331, "step": 11311 }, { "epoch": 1.86, "learning_rate": 2.150952693823916e-06, "loss": 0.7073, "step": 11312 }, { "epoch": 1.86, "learning_rate": 2.148488830486202e-06, "loss": 0.8009, "step": 11313 }, { "epoch": 1.86, "learning_rate": 2.146024967148489e-06, "loss": 0.5119, "step": 11314 }, { "epoch": 1.86, "learning_rate": 2.1435611038107754e-06, "loss": 0.5646, "step": 11315 }, { "epoch": 1.86, "learning_rate": 2.141097240473062e-06, "loss": 0.7566, "step": 11316 }, { "epoch": 1.86, "learning_rate": 2.1386333771353487e-06, "loss": 0.2387, "step": 11317 }, { "epoch": 1.86, "learning_rate": 2.1361695137976347e-06, "loss": 0.2137, "step": 11318 }, { "epoch": 1.86, "learning_rate": 2.133705650459921e-06, "loss": 0.3294, "step": 11319 }, { "epoch": 1.86, "learning_rate": 2.131241787122208e-06, "loss": 0.5086, "step": 11320 }, { "epoch": 1.86, "learning_rate": 2.1287779237844943e-06, "loss": 0.5667, "step": 11321 }, { "epoch": 1.86, "learning_rate": 2.1263140604467807e-06, "loss": 0.4135, "step": 11322 }, { "epoch": 1.86, "learning_rate": 2.123850197109067e-06, "loss": 0.6314, "step": 11323 }, { "epoch": 1.86, "learning_rate": 2.1213863337713535e-06, "loss": 0.7053, "step": 11324 }, { "epoch": 1.86, "learning_rate": 2.11892247043364e-06, "loss": 0.5246, "step": 11325 }, { "epoch": 1.86, "learning_rate": 2.1164586070959268e-06, "loss": 0.4119, "step": 11326 }, { "epoch": 1.86, "learning_rate": 2.113994743758213e-06, "loss": 0.55, "step": 11327 }, { "epoch": 1.86, "learning_rate": 2.111530880420499e-06, "loss": 1.1194, "step": 11328 }, { "epoch": 1.86, "learning_rate": 2.109067017082786e-06, "loss": 0.5526, "step": 11329 }, { "epoch": 1.86, "learning_rate": 2.1066031537450724e-06, "loss": 0.3999, "step": 11330 }, { "epoch": 1.86, "learning_rate": 2.104139290407359e-06, "loss": 0.2294, "step": 11331 }, { "epoch": 1.86, "learning_rate": 2.101675427069645e-06, "loss": 0.5302, "step": 11332 }, { "epoch": 1.86, "learning_rate": 2.0992115637319316e-06, "loss": 0.2939, "step": 11333 }, { "epoch": 1.86, "learning_rate": 2.096747700394218e-06, "loss": 0.2102, "step": 11334 }, { "epoch": 1.86, "learning_rate": 2.094283837056505e-06, "loss": 0.5766, "step": 11335 }, { "epoch": 1.86, "learning_rate": 2.0918199737187913e-06, "loss": 0.5698, "step": 11336 }, { "epoch": 1.86, "learning_rate": 2.0893561103810773e-06, "loss": 0.7825, "step": 11337 }, { "epoch": 1.86, "learning_rate": 2.086892247043364e-06, "loss": 0.1732, "step": 11338 }, { "epoch": 1.86, "learning_rate": 2.0844283837056505e-06, "loss": 0.3523, "step": 11339 }, { "epoch": 1.86, "learning_rate": 2.081964520367937e-06, "loss": 0.6482, "step": 11340 }, { "epoch": 1.86, "learning_rate": 2.0795006570302237e-06, "loss": 0.5532, "step": 11341 }, { "epoch": 1.86, "learning_rate": 2.0770367936925097e-06, "loss": 0.6815, "step": 11342 }, { "epoch": 1.86, "learning_rate": 2.074572930354796e-06, "loss": 0.4771, "step": 11343 }, { "epoch": 1.86, "learning_rate": 2.072109067017083e-06, "loss": 0.2405, "step": 11344 }, { "epoch": 1.86, "learning_rate": 2.0696452036793694e-06, "loss": 0.6738, "step": 11345 }, { "epoch": 1.86, "learning_rate": 2.0671813403416558e-06, "loss": 0.2313, "step": 11346 }, { "epoch": 1.86, "learning_rate": 2.064717477003942e-06, "loss": 0.3139, "step": 11347 }, { "epoch": 1.86, "learning_rate": 2.0622536136662286e-06, "loss": 0.5154, "step": 11348 }, { "epoch": 1.86, "learning_rate": 2.059789750328515e-06, "loss": 0.8876, "step": 11349 }, { "epoch": 1.86, "learning_rate": 2.057325886990802e-06, "loss": 0.3598, "step": 11350 }, { "epoch": 1.86, "learning_rate": 2.0548620236530882e-06, "loss": 0.2944, "step": 11351 }, { "epoch": 1.86, "learning_rate": 2.0523981603153742e-06, "loss": 0.3502, "step": 11352 }, { "epoch": 1.86, "learning_rate": 2.049934296977661e-06, "loss": 0.308, "step": 11353 }, { "epoch": 1.86, "learning_rate": 2.0474704336399475e-06, "loss": 0.8628, "step": 11354 }, { "epoch": 1.87, "learning_rate": 2.045006570302234e-06, "loss": 0.3829, "step": 11355 }, { "epoch": 1.87, "learning_rate": 2.0425427069645207e-06, "loss": 0.6819, "step": 11356 }, { "epoch": 1.87, "learning_rate": 2.0400788436268067e-06, "loss": 0.6813, "step": 11357 }, { "epoch": 1.87, "learning_rate": 2.037614980289093e-06, "loss": 0.5842, "step": 11358 }, { "epoch": 1.87, "learning_rate": 2.03515111695138e-06, "loss": 0.9962, "step": 11359 }, { "epoch": 1.87, "learning_rate": 2.0326872536136663e-06, "loss": 0.7168, "step": 11360 }, { "epoch": 1.87, "learning_rate": 2.0302233902759527e-06, "loss": 0.5159, "step": 11361 }, { "epoch": 1.87, "learning_rate": 2.027759526938239e-06, "loss": 0.5159, "step": 11362 }, { "epoch": 1.87, "learning_rate": 2.0252956636005256e-06, "loss": 0.4346, "step": 11363 }, { "epoch": 1.87, "learning_rate": 2.022831800262812e-06, "loss": 0.5183, "step": 11364 }, { "epoch": 1.87, "learning_rate": 2.020367936925099e-06, "loss": 0.7618, "step": 11365 }, { "epoch": 1.87, "learning_rate": 2.017904073587385e-06, "loss": 0.618, "step": 11366 }, { "epoch": 1.87, "learning_rate": 2.015440210249671e-06, "loss": 0.5795, "step": 11367 }, { "epoch": 1.87, "learning_rate": 2.012976346911958e-06, "loss": 0.3135, "step": 11368 }, { "epoch": 1.87, "learning_rate": 2.0105124835742444e-06, "loss": 0.5466, "step": 11369 }, { "epoch": 1.87, "learning_rate": 2.008048620236531e-06, "loss": 0.5264, "step": 11370 }, { "epoch": 1.87, "learning_rate": 2.0055847568988177e-06, "loss": 0.4071, "step": 11371 }, { "epoch": 1.87, "learning_rate": 2.0031208935611037e-06, "loss": 0.2724, "step": 11372 }, { "epoch": 1.87, "learning_rate": 2.00065703022339e-06, "loss": 0.6419, "step": 11373 }, { "epoch": 1.87, "learning_rate": 1.998193166885677e-06, "loss": 0.6817, "step": 11374 }, { "epoch": 1.87, "learning_rate": 1.9957293035479633e-06, "loss": 0.6389, "step": 11375 }, { "epoch": 1.87, "learning_rate": 1.9932654402102497e-06, "loss": 0.7663, "step": 11376 }, { "epoch": 1.87, "learning_rate": 1.990801576872536e-06, "loss": 0.532, "step": 11377 }, { "epoch": 1.87, "learning_rate": 1.9883377135348225e-06, "loss": 0.4178, "step": 11378 }, { "epoch": 1.87, "learning_rate": 1.985873850197109e-06, "loss": 0.745, "step": 11379 }, { "epoch": 1.87, "learning_rate": 1.9834099868593958e-06, "loss": 0.4764, "step": 11380 }, { "epoch": 1.87, "learning_rate": 1.980946123521682e-06, "loss": 0.2272, "step": 11381 }, { "epoch": 1.87, "learning_rate": 1.978482260183968e-06, "loss": 0.2494, "step": 11382 }, { "epoch": 1.87, "learning_rate": 1.976018396846255e-06, "loss": 0.3216, "step": 11383 }, { "epoch": 1.87, "learning_rate": 1.9735545335085414e-06, "loss": 0.2065, "step": 11384 }, { "epoch": 1.87, "learning_rate": 1.971090670170828e-06, "loss": 0.3555, "step": 11385 }, { "epoch": 1.87, "learning_rate": 1.9686268068331146e-06, "loss": 0.7183, "step": 11386 }, { "epoch": 1.87, "learning_rate": 1.9661629434954006e-06, "loss": 1.0001, "step": 11387 }, { "epoch": 1.87, "learning_rate": 1.963699080157687e-06, "loss": 0.4855, "step": 11388 }, { "epoch": 1.87, "learning_rate": 1.961235216819974e-06, "loss": 0.5185, "step": 11389 }, { "epoch": 1.87, "learning_rate": 1.9587713534822603e-06, "loss": 0.2901, "step": 11390 }, { "epoch": 1.87, "learning_rate": 1.9563074901445467e-06, "loss": 0.5562, "step": 11391 }, { "epoch": 1.87, "learning_rate": 1.953843626806833e-06, "loss": 0.2883, "step": 11392 }, { "epoch": 1.87, "learning_rate": 1.9513797634691195e-06, "loss": 0.3186, "step": 11393 }, { "epoch": 1.87, "learning_rate": 1.948915900131406e-06, "loss": 0.3324, "step": 11394 }, { "epoch": 1.87, "learning_rate": 1.9464520367936927e-06, "loss": 0.6512, "step": 11395 }, { "epoch": 1.87, "learning_rate": 1.943988173455979e-06, "loss": 0.7555, "step": 11396 }, { "epoch": 1.87, "learning_rate": 1.941524310118265e-06, "loss": 0.3788, "step": 11397 }, { "epoch": 1.87, "learning_rate": 1.939060446780552e-06, "loss": 0.354, "step": 11398 }, { "epoch": 1.87, "learning_rate": 1.9365965834428384e-06, "loss": 0.6076, "step": 11399 }, { "epoch": 1.87, "learning_rate": 1.9341327201051248e-06, "loss": 0.7474, "step": 11400 }, { "epoch": 1.87, "learning_rate": 1.9316688567674116e-06, "loss": 0.4862, "step": 11401 }, { "epoch": 1.87, "learning_rate": 1.9292049934296976e-06, "loss": 0.4348, "step": 11402 }, { "epoch": 1.87, "learning_rate": 1.926741130091984e-06, "loss": 0.8001, "step": 11403 }, { "epoch": 1.87, "learning_rate": 1.924277266754271e-06, "loss": 0.6808, "step": 11404 }, { "epoch": 1.87, "learning_rate": 1.9218134034165572e-06, "loss": 0.444, "step": 11405 }, { "epoch": 1.87, "learning_rate": 1.9193495400788436e-06, "loss": 0.3022, "step": 11406 }, { "epoch": 1.87, "learning_rate": 1.91688567674113e-06, "loss": 0.1679, "step": 11407 }, { "epoch": 1.87, "learning_rate": 1.9144218134034165e-06, "loss": 0.4824, "step": 11408 }, { "epoch": 1.87, "learning_rate": 1.911957950065703e-06, "loss": 0.8039, "step": 11409 }, { "epoch": 1.87, "learning_rate": 1.9094940867279897e-06, "loss": 0.3129, "step": 11410 }, { "epoch": 1.87, "learning_rate": 1.9070302233902761e-06, "loss": 0.2673, "step": 11411 }, { "epoch": 1.87, "learning_rate": 1.9045663600525623e-06, "loss": 0.4908, "step": 11412 }, { "epoch": 1.87, "learning_rate": 1.902102496714849e-06, "loss": 0.3988, "step": 11413 }, { "epoch": 1.87, "learning_rate": 1.8996386333771353e-06, "loss": 1.0019, "step": 11414 }, { "epoch": 1.88, "learning_rate": 1.897174770039422e-06, "loss": 0.3376, "step": 11415 }, { "epoch": 1.88, "learning_rate": 1.8947109067017086e-06, "loss": 0.5348, "step": 11416 }, { "epoch": 1.88, "learning_rate": 1.8922470433639946e-06, "loss": 0.4943, "step": 11417 }, { "epoch": 1.88, "learning_rate": 1.8897831800262812e-06, "loss": 0.482, "step": 11418 }, { "epoch": 1.88, "learning_rate": 1.8873193166885678e-06, "loss": 0.1575, "step": 11419 }, { "epoch": 1.88, "learning_rate": 1.8848554533508542e-06, "loss": 0.5014, "step": 11420 }, { "epoch": 1.88, "learning_rate": 1.8823915900131408e-06, "loss": 0.4504, "step": 11421 }, { "epoch": 1.88, "learning_rate": 1.879927726675427e-06, "loss": 0.3371, "step": 11422 }, { "epoch": 1.88, "learning_rate": 1.8774638633377134e-06, "loss": 0.3247, "step": 11423 }, { "epoch": 1.88, "learning_rate": 1.875e-06, "loss": 0.6217, "step": 11424 }, { "epoch": 1.88, "learning_rate": 1.8725361366622867e-06, "loss": 0.5655, "step": 11425 }, { "epoch": 1.88, "learning_rate": 1.8700722733245729e-06, "loss": 0.9603, "step": 11426 }, { "epoch": 1.88, "learning_rate": 1.8676084099868595e-06, "loss": 0.3078, "step": 11427 }, { "epoch": 1.88, "learning_rate": 1.8651445466491459e-06, "loss": 0.434, "step": 11428 }, { "epoch": 1.88, "learning_rate": 1.8626806833114323e-06, "loss": 0.5562, "step": 11429 }, { "epoch": 1.88, "learning_rate": 1.860216819973719e-06, "loss": 0.5396, "step": 11430 }, { "epoch": 1.88, "learning_rate": 1.8577529566360053e-06, "loss": 0.7478, "step": 11431 }, { "epoch": 1.88, "learning_rate": 1.8552890932982917e-06, "loss": 0.6762, "step": 11432 }, { "epoch": 1.88, "learning_rate": 1.8528252299605781e-06, "loss": 0.3666, "step": 11433 }, { "epoch": 1.88, "learning_rate": 1.8503613666228648e-06, "loss": 0.3953, "step": 11434 }, { "epoch": 1.88, "learning_rate": 1.8478975032851512e-06, "loss": 1.061, "step": 11435 }, { "epoch": 1.88, "learning_rate": 1.8454336399474376e-06, "loss": 0.3481, "step": 11436 }, { "epoch": 1.88, "learning_rate": 1.8429697766097242e-06, "loss": 0.241, "step": 11437 }, { "epoch": 1.88, "learning_rate": 1.8405059132720104e-06, "loss": 0.4481, "step": 11438 }, { "epoch": 1.88, "learning_rate": 1.838042049934297e-06, "loss": 0.6285, "step": 11439 }, { "epoch": 1.88, "learning_rate": 1.8355781865965836e-06, "loss": 0.4454, "step": 11440 }, { "epoch": 1.88, "learning_rate": 1.8331143232588698e-06, "loss": 0.7346, "step": 11441 }, { "epoch": 1.88, "learning_rate": 1.8306504599211565e-06, "loss": 0.5534, "step": 11442 }, { "epoch": 1.88, "learning_rate": 1.8281865965834429e-06, "loss": 1.0257, "step": 11443 }, { "epoch": 1.88, "learning_rate": 1.8257227332457293e-06, "loss": 0.614, "step": 11444 }, { "epoch": 1.88, "learning_rate": 1.8232588699080159e-06, "loss": 1.004, "step": 11445 }, { "epoch": 1.88, "learning_rate": 1.8207950065703023e-06, "loss": 0.5758, "step": 11446 }, { "epoch": 1.88, "learning_rate": 1.8183311432325887e-06, "loss": 0.5415, "step": 11447 }, { "epoch": 1.88, "learning_rate": 1.8158672798948751e-06, "loss": 0.2899, "step": 11448 }, { "epoch": 1.88, "learning_rate": 1.8134034165571617e-06, "loss": 0.4907, "step": 11449 }, { "epoch": 1.88, "learning_rate": 1.8109395532194481e-06, "loss": 0.4638, "step": 11450 }, { "epoch": 1.88, "learning_rate": 1.8084756898817345e-06, "loss": 0.574, "step": 11451 }, { "epoch": 1.88, "learning_rate": 1.8060118265440212e-06, "loss": 0.1399, "step": 11452 }, { "epoch": 1.88, "learning_rate": 1.8035479632063074e-06, "loss": 0.6794, "step": 11453 }, { "epoch": 1.88, "learning_rate": 1.801084099868594e-06, "loss": 0.2911, "step": 11454 }, { "epoch": 1.88, "learning_rate": 1.7986202365308806e-06, "loss": 0.4311, "step": 11455 }, { "epoch": 1.88, "learning_rate": 1.7961563731931668e-06, "loss": 0.1403, "step": 11456 }, { "epoch": 1.88, "learning_rate": 1.7936925098554534e-06, "loss": 0.8561, "step": 11457 }, { "epoch": 1.88, "learning_rate": 1.7912286465177398e-06, "loss": 0.6072, "step": 11458 }, { "epoch": 1.88, "learning_rate": 1.7887647831800264e-06, "loss": 0.4867, "step": 11459 }, { "epoch": 1.88, "learning_rate": 1.7863009198423129e-06, "loss": 0.6003, "step": 11460 }, { "epoch": 1.88, "learning_rate": 1.7838370565045993e-06, "loss": 0.4456, "step": 11461 }, { "epoch": 1.88, "learning_rate": 1.7813731931668859e-06, "loss": 0.3041, "step": 11462 }, { "epoch": 1.88, "learning_rate": 1.778909329829172e-06, "loss": 0.6322, "step": 11463 }, { "epoch": 1.88, "learning_rate": 1.7764454664914587e-06, "loss": 0.3002, "step": 11464 }, { "epoch": 1.88, "learning_rate": 1.7739816031537453e-06, "loss": 0.3802, "step": 11465 }, { "epoch": 1.88, "learning_rate": 1.7715177398160315e-06, "loss": 0.2911, "step": 11466 }, { "epoch": 1.88, "learning_rate": 1.7690538764783181e-06, "loss": 0.3472, "step": 11467 }, { "epoch": 1.88, "learning_rate": 1.7665900131406045e-06, "loss": 0.4854, "step": 11468 }, { "epoch": 1.88, "learning_rate": 1.764126149802891e-06, "loss": 0.3007, "step": 11469 }, { "epoch": 1.88, "learning_rate": 1.7616622864651776e-06, "loss": 0.3576, "step": 11470 }, { "epoch": 1.88, "learning_rate": 1.759198423127464e-06, "loss": 0.6299, "step": 11471 }, { "epoch": 1.88, "learning_rate": 1.7567345597897504e-06, "loss": 1.1189, "step": 11472 }, { "epoch": 1.88, "learning_rate": 1.7542706964520368e-06, "loss": 0.2964, "step": 11473 }, { "epoch": 1.88, "learning_rate": 1.7518068331143234e-06, "loss": 0.5642, "step": 11474 }, { "epoch": 1.88, "learning_rate": 1.7493429697766096e-06, "loss": 0.4308, "step": 11475 }, { "epoch": 1.89, "learning_rate": 1.7468791064388962e-06, "loss": 0.557, "step": 11476 }, { "epoch": 1.89, "learning_rate": 1.7444152431011829e-06, "loss": 0.2679, "step": 11477 }, { "epoch": 1.89, "learning_rate": 1.741951379763469e-06, "loss": 0.5679, "step": 11478 }, { "epoch": 1.89, "learning_rate": 1.7394875164257557e-06, "loss": 0.5896, "step": 11479 }, { "epoch": 1.89, "learning_rate": 1.737023653088042e-06, "loss": 0.1895, "step": 11480 }, { "epoch": 1.89, "learning_rate": 1.7345597897503285e-06, "loss": 0.2284, "step": 11481 }, { "epoch": 1.89, "learning_rate": 1.732095926412615e-06, "loss": 0.4738, "step": 11482 }, { "epoch": 1.89, "learning_rate": 1.7296320630749015e-06, "loss": 0.7499, "step": 11483 }, { "epoch": 1.89, "learning_rate": 1.727168199737188e-06, "loss": 0.5775, "step": 11484 }, { "epoch": 1.89, "learning_rate": 1.7247043363994743e-06, "loss": 0.4991, "step": 11485 }, { "epoch": 1.89, "learning_rate": 1.722240473061761e-06, "loss": 1.3425, "step": 11486 }, { "epoch": 1.89, "learning_rate": 1.7197766097240474e-06, "loss": 0.4418, "step": 11487 }, { "epoch": 1.89, "learning_rate": 1.7173127463863338e-06, "loss": 0.2121, "step": 11488 }, { "epoch": 1.89, "learning_rate": 1.7148488830486204e-06, "loss": 0.5649, "step": 11489 }, { "epoch": 1.89, "learning_rate": 1.7123850197109066e-06, "loss": 0.3718, "step": 11490 }, { "epoch": 1.89, "learning_rate": 1.7099211563731932e-06, "loss": 0.4482, "step": 11491 }, { "epoch": 1.89, "learning_rate": 1.7074572930354798e-06, "loss": 0.3691, "step": 11492 }, { "epoch": 1.89, "learning_rate": 1.704993429697766e-06, "loss": 0.1955, "step": 11493 }, { "epoch": 1.89, "learning_rate": 1.7025295663600526e-06, "loss": 1.0509, "step": 11494 }, { "epoch": 1.89, "learning_rate": 1.700065703022339e-06, "loss": 0.5487, "step": 11495 }, { "epoch": 1.89, "learning_rate": 1.6976018396846255e-06, "loss": 0.272, "step": 11496 }, { "epoch": 1.89, "learning_rate": 1.695137976346912e-06, "loss": 0.2409, "step": 11497 }, { "epoch": 1.89, "learning_rate": 1.6926741130091985e-06, "loss": 0.7354, "step": 11498 }, { "epoch": 1.89, "learning_rate": 1.6902102496714849e-06, "loss": 0.4947, "step": 11499 }, { "epoch": 1.89, "learning_rate": 1.6877463863337713e-06, "loss": 0.6018, "step": 11500 }, { "epoch": 1.89, "eval_exact_match": 87.20908230842005, "eval_f1": 93.23456576376725, "step": 11500 }, { "epoch": 1.89, "learning_rate": 1.685282522996058e-06, "loss": 0.8431, "step": 11501 }, { "epoch": 1.89, "learning_rate": 1.6828186596583443e-06, "loss": 0.2709, "step": 11502 }, { "epoch": 1.89, "learning_rate": 1.6803547963206307e-06, "loss": 0.4226, "step": 11503 }, { "epoch": 1.89, "learning_rate": 1.6778909329829174e-06, "loss": 0.7175, "step": 11504 }, { "epoch": 1.89, "learning_rate": 1.6754270696452035e-06, "loss": 0.8528, "step": 11505 }, { "epoch": 1.89, "learning_rate": 1.6729632063074902e-06, "loss": 0.4196, "step": 11506 }, { "epoch": 1.89, "learning_rate": 1.6704993429697768e-06, "loss": 0.4861, "step": 11507 }, { "epoch": 1.89, "learning_rate": 1.668035479632063e-06, "loss": 0.8107, "step": 11508 }, { "epoch": 1.89, "learning_rate": 1.6655716162943496e-06, "loss": 0.3064, "step": 11509 }, { "epoch": 1.89, "learning_rate": 1.663107752956636e-06, "loss": 0.3927, "step": 11510 }, { "epoch": 1.89, "learning_rate": 1.6606438896189224e-06, "loss": 0.3466, "step": 11511 }, { "epoch": 1.89, "learning_rate": 1.658180026281209e-06, "loss": 0.9245, "step": 11512 }, { "epoch": 1.89, "learning_rate": 1.6557161629434954e-06, "loss": 0.774, "step": 11513 }, { "epoch": 1.89, "learning_rate": 1.6532522996057819e-06, "loss": 0.9607, "step": 11514 }, { "epoch": 1.89, "learning_rate": 1.6507884362680683e-06, "loss": 0.328, "step": 11515 }, { "epoch": 1.89, "learning_rate": 1.6483245729303549e-06, "loss": 0.648, "step": 11516 }, { "epoch": 1.89, "learning_rate": 1.6458607095926413e-06, "loss": 0.465, "step": 11517 }, { "epoch": 1.89, "learning_rate": 1.6433968462549277e-06, "loss": 0.5459, "step": 11518 }, { "epoch": 1.89, "learning_rate": 1.6409329829172143e-06, "loss": 0.7694, "step": 11519 }, { "epoch": 1.89, "learning_rate": 1.6384691195795005e-06, "loss": 0.5746, "step": 11520 }, { "epoch": 1.89, "learning_rate": 1.6360052562417871e-06, "loss": 0.6146, "step": 11521 }, { "epoch": 1.89, "learning_rate": 1.6335413929040738e-06, "loss": 0.1609, "step": 11522 }, { "epoch": 1.89, "learning_rate": 1.63107752956636e-06, "loss": 0.5175, "step": 11523 }, { "epoch": 1.89, "learning_rate": 1.6286136662286466e-06, "loss": 0.5628, "step": 11524 }, { "epoch": 1.89, "learning_rate": 1.626149802890933e-06, "loss": 0.751, "step": 11525 }, { "epoch": 1.89, "learning_rate": 1.6236859395532194e-06, "loss": 0.4909, "step": 11526 }, { "epoch": 1.89, "learning_rate": 1.621222076215506e-06, "loss": 0.4327, "step": 11527 }, { "epoch": 1.89, "learning_rate": 1.6187582128777924e-06, "loss": 0.2152, "step": 11528 }, { "epoch": 1.89, "learning_rate": 1.616294349540079e-06, "loss": 0.6179, "step": 11529 }, { "epoch": 1.89, "learning_rate": 1.6138304862023652e-06, "loss": 0.5373, "step": 11530 }, { "epoch": 1.89, "learning_rate": 1.6113666228646519e-06, "loss": 0.7571, "step": 11531 }, { "epoch": 1.89, "learning_rate": 1.6089027595269385e-06, "loss": 0.4484, "step": 11532 }, { "epoch": 1.89, "learning_rate": 1.6064388961892247e-06, "loss": 0.6008, "step": 11533 }, { "epoch": 1.89, "learning_rate": 1.6039750328515113e-06, "loss": 0.7427, "step": 11534 }, { "epoch": 1.89, "learning_rate": 1.6015111695137977e-06, "loss": 0.3184, "step": 11535 }, { "epoch": 1.89, "learning_rate": 1.599047306176084e-06, "loss": 0.6837, "step": 11536 }, { "epoch": 1.9, "learning_rate": 1.5965834428383707e-06, "loss": 0.3697, "step": 11537 }, { "epoch": 1.9, "learning_rate": 1.5941195795006571e-06, "loss": 0.7245, "step": 11538 }, { "epoch": 1.9, "learning_rate": 1.5916557161629435e-06, "loss": 0.3174, "step": 11539 }, { "epoch": 1.9, "learning_rate": 1.58919185282523e-06, "loss": 0.5176, "step": 11540 }, { "epoch": 1.9, "learning_rate": 1.5867279894875166e-06, "loss": 0.4814, "step": 11541 }, { "epoch": 1.9, "learning_rate": 1.584264126149803e-06, "loss": 0.4011, "step": 11542 }, { "epoch": 1.9, "learning_rate": 1.5818002628120894e-06, "loss": 0.6462, "step": 11543 }, { "epoch": 1.9, "learning_rate": 1.579336399474376e-06, "loss": 0.5099, "step": 11544 }, { "epoch": 1.9, "learning_rate": 1.5768725361366622e-06, "loss": 0.2661, "step": 11545 }, { "epoch": 1.9, "learning_rate": 1.5744086727989488e-06, "loss": 0.529, "step": 11546 }, { "epoch": 1.9, "learning_rate": 1.5719448094612354e-06, "loss": 0.5787, "step": 11547 }, { "epoch": 1.9, "learning_rate": 1.5694809461235216e-06, "loss": 0.5788, "step": 11548 }, { "epoch": 1.9, "learning_rate": 1.5670170827858083e-06, "loss": 0.1994, "step": 11549 }, { "epoch": 1.9, "learning_rate": 1.5645532194480947e-06, "loss": 0.4984, "step": 11550 }, { "epoch": 1.9, "learning_rate": 1.562089356110381e-06, "loss": 0.3445, "step": 11551 }, { "epoch": 1.9, "learning_rate": 1.5596254927726677e-06, "loss": 0.5971, "step": 11552 }, { "epoch": 1.9, "learning_rate": 1.557161629434954e-06, "loss": 0.5648, "step": 11553 }, { "epoch": 1.9, "learning_rate": 1.5546977660972405e-06, "loss": 0.5367, "step": 11554 }, { "epoch": 1.9, "learning_rate": 1.552233902759527e-06, "loss": 0.51, "step": 11555 }, { "epoch": 1.9, "learning_rate": 1.5497700394218135e-06, "loss": 0.3771, "step": 11556 }, { "epoch": 1.9, "learning_rate": 1.5473061760841e-06, "loss": 0.5676, "step": 11557 }, { "epoch": 1.9, "learning_rate": 1.5448423127463864e-06, "loss": 0.5301, "step": 11558 }, { "epoch": 1.9, "learning_rate": 1.542378449408673e-06, "loss": 0.4426, "step": 11559 }, { "epoch": 1.9, "learning_rate": 1.5399145860709592e-06, "loss": 0.4873, "step": 11560 }, { "epoch": 1.9, "learning_rate": 1.5374507227332458e-06, "loss": 0.5679, "step": 11561 }, { "epoch": 1.9, "learning_rate": 1.5349868593955324e-06, "loss": 0.5197, "step": 11562 }, { "epoch": 1.9, "learning_rate": 1.5325229960578186e-06, "loss": 0.2859, "step": 11563 }, { "epoch": 1.9, "learning_rate": 1.5300591327201052e-06, "loss": 0.3235, "step": 11564 }, { "epoch": 1.9, "learning_rate": 1.5275952693823916e-06, "loss": 0.1729, "step": 11565 }, { "epoch": 1.9, "learning_rate": 1.525131406044678e-06, "loss": 0.3292, "step": 11566 }, { "epoch": 1.9, "learning_rate": 1.5226675427069644e-06, "loss": 0.3739, "step": 11567 }, { "epoch": 1.9, "learning_rate": 1.520203679369251e-06, "loss": 1.1999, "step": 11568 }, { "epoch": 1.9, "learning_rate": 1.5177398160315375e-06, "loss": 0.2106, "step": 11569 }, { "epoch": 1.9, "learning_rate": 1.5152759526938239e-06, "loss": 0.5612, "step": 11570 }, { "epoch": 1.9, "learning_rate": 1.5128120893561105e-06, "loss": 0.4624, "step": 11571 }, { "epoch": 1.9, "learning_rate": 1.5103482260183967e-06, "loss": 0.3821, "step": 11572 }, { "epoch": 1.9, "learning_rate": 1.5078843626806833e-06, "loss": 0.6297, "step": 11573 }, { "epoch": 1.9, "learning_rate": 1.50542049934297e-06, "loss": 0.7453, "step": 11574 }, { "epoch": 1.9, "learning_rate": 1.5029566360052561e-06, "loss": 0.3457, "step": 11575 }, { "epoch": 1.9, "learning_rate": 1.5004927726675428e-06, "loss": 0.2507, "step": 11576 }, { "epoch": 1.9, "learning_rate": 1.4980289093298292e-06, "loss": 0.3891, "step": 11577 }, { "epoch": 1.9, "learning_rate": 1.4955650459921156e-06, "loss": 0.6248, "step": 11578 }, { "epoch": 1.9, "learning_rate": 1.4931011826544022e-06, "loss": 0.3742, "step": 11579 }, { "epoch": 1.9, "learning_rate": 1.4906373193166886e-06, "loss": 0.6505, "step": 11580 }, { "epoch": 1.9, "learning_rate": 1.488173455978975e-06, "loss": 0.8819, "step": 11581 }, { "epoch": 1.9, "learning_rate": 1.4857095926412614e-06, "loss": 0.3842, "step": 11582 }, { "epoch": 1.9, "learning_rate": 1.483245729303548e-06, "loss": 0.313, "step": 11583 }, { "epoch": 1.9, "learning_rate": 1.4807818659658344e-06, "loss": 0.8043, "step": 11584 }, { "epoch": 1.9, "learning_rate": 1.4783180026281209e-06, "loss": 0.6582, "step": 11585 }, { "epoch": 1.9, "learning_rate": 1.4758541392904075e-06, "loss": 0.408, "step": 11586 }, { "epoch": 1.9, "learning_rate": 1.4733902759526937e-06, "loss": 0.4874, "step": 11587 }, { "epoch": 1.9, "learning_rate": 1.4709264126149803e-06, "loss": 0.5417, "step": 11588 }, { "epoch": 1.9, "learning_rate": 1.468462549277267e-06, "loss": 0.4144, "step": 11589 }, { "epoch": 1.9, "learning_rate": 1.465998685939553e-06, "loss": 0.6537, "step": 11590 }, { "epoch": 1.9, "learning_rate": 1.4635348226018397e-06, "loss": 0.2418, "step": 11591 }, { "epoch": 1.9, "learning_rate": 1.4610709592641261e-06, "loss": 0.3798, "step": 11592 }, { "epoch": 1.9, "learning_rate": 1.4586070959264125e-06, "loss": 0.5577, "step": 11593 }, { "epoch": 1.9, "learning_rate": 1.4561432325886992e-06, "loss": 0.4827, "step": 11594 }, { "epoch": 1.9, "learning_rate": 1.4536793692509856e-06, "loss": 0.5034, "step": 11595 }, { "epoch": 1.9, "learning_rate": 1.451215505913272e-06, "loss": 0.6562, "step": 11596 }, { "epoch": 1.9, "learning_rate": 1.4487516425755584e-06, "loss": 0.2252, "step": 11597 }, { "epoch": 1.91, "learning_rate": 1.446287779237845e-06, "loss": 0.3763, "step": 11598 }, { "epoch": 1.91, "learning_rate": 1.4438239159001316e-06, "loss": 0.5408, "step": 11599 }, { "epoch": 1.91, "learning_rate": 1.4413600525624178e-06, "loss": 0.2637, "step": 11600 }, { "epoch": 1.91, "learning_rate": 1.4388961892247044e-06, "loss": 1.1337, "step": 11601 }, { "epoch": 1.91, "learning_rate": 1.4364323258869908e-06, "loss": 0.9635, "step": 11602 }, { "epoch": 1.91, "learning_rate": 1.4339684625492773e-06, "loss": 0.2162, "step": 11603 }, { "epoch": 1.91, "learning_rate": 1.4315045992115639e-06, "loss": 0.3868, "step": 11604 }, { "epoch": 1.91, "learning_rate": 1.4290407358738503e-06, "loss": 0.4003, "step": 11605 }, { "epoch": 1.91, "learning_rate": 1.4265768725361367e-06, "loss": 0.3097, "step": 11606 }, { "epoch": 1.91, "learning_rate": 1.424113009198423e-06, "loss": 0.3754, "step": 11607 }, { "epoch": 1.91, "learning_rate": 1.4216491458607097e-06, "loss": 0.3821, "step": 11608 }, { "epoch": 1.91, "learning_rate": 1.4191852825229961e-06, "loss": 0.3646, "step": 11609 }, { "epoch": 1.91, "learning_rate": 1.4167214191852825e-06, "loss": 0.5303, "step": 11610 }, { "epoch": 1.91, "learning_rate": 1.4142575558475692e-06, "loss": 0.2044, "step": 11611 }, { "epoch": 1.91, "learning_rate": 1.4117936925098554e-06, "loss": 0.719, "step": 11612 }, { "epoch": 1.91, "learning_rate": 1.409329829172142e-06, "loss": 0.2625, "step": 11613 }, { "epoch": 1.91, "learning_rate": 1.4068659658344286e-06, "loss": 0.4191, "step": 11614 }, { "epoch": 1.91, "learning_rate": 1.4044021024967148e-06, "loss": 0.5296, "step": 11615 }, { "epoch": 1.91, "learning_rate": 1.4019382391590014e-06, "loss": 0.4283, "step": 11616 }, { "epoch": 1.91, "learning_rate": 1.3994743758212878e-06, "loss": 0.9062, "step": 11617 }, { "epoch": 1.91, "learning_rate": 1.3970105124835742e-06, "loss": 0.9078, "step": 11618 }, { "epoch": 1.91, "learning_rate": 1.3945466491458608e-06, "loss": 0.3435, "step": 11619 }, { "epoch": 1.91, "learning_rate": 1.3920827858081473e-06, "loss": 0.5334, "step": 11620 }, { "epoch": 1.91, "learning_rate": 1.3896189224704337e-06, "loss": 0.3626, "step": 11621 }, { "epoch": 1.91, "learning_rate": 1.38715505913272e-06, "loss": 1.0837, "step": 11622 }, { "epoch": 1.91, "learning_rate": 1.3846911957950067e-06, "loss": 0.6578, "step": 11623 }, { "epoch": 1.91, "learning_rate": 1.382227332457293e-06, "loss": 0.4158, "step": 11624 }, { "epoch": 1.91, "learning_rate": 1.3797634691195795e-06, "loss": 1.2768, "step": 11625 }, { "epoch": 1.91, "learning_rate": 1.3772996057818661e-06, "loss": 1.6631, "step": 11626 }, { "epoch": 1.91, "learning_rate": 1.3748357424441523e-06, "loss": 0.4914, "step": 11627 }, { "epoch": 1.91, "learning_rate": 1.372371879106439e-06, "loss": 0.4113, "step": 11628 }, { "epoch": 1.91, "learning_rate": 1.3699080157687256e-06, "loss": 0.6664, "step": 11629 }, { "epoch": 1.91, "learning_rate": 1.3674441524310118e-06, "loss": 0.35, "step": 11630 }, { "epoch": 1.91, "learning_rate": 1.3649802890932984e-06, "loss": 0.6538, "step": 11631 }, { "epoch": 1.91, "learning_rate": 1.3625164257555848e-06, "loss": 0.2927, "step": 11632 }, { "epoch": 1.91, "learning_rate": 1.3600525624178712e-06, "loss": 0.7603, "step": 11633 }, { "epoch": 1.91, "learning_rate": 1.3575886990801578e-06, "loss": 0.2965, "step": 11634 }, { "epoch": 1.91, "learning_rate": 1.3551248357424442e-06, "loss": 0.4298, "step": 11635 }, { "epoch": 1.91, "learning_rate": 1.3526609724047306e-06, "loss": 0.5656, "step": 11636 }, { "epoch": 1.91, "learning_rate": 1.350197109067017e-06, "loss": 0.3535, "step": 11637 }, { "epoch": 1.91, "learning_rate": 1.3477332457293037e-06, "loss": 0.918, "step": 11638 }, { "epoch": 1.91, "learning_rate": 1.34526938239159e-06, "loss": 0.3301, "step": 11639 }, { "epoch": 1.91, "learning_rate": 1.3428055190538765e-06, "loss": 0.4227, "step": 11640 }, { "epoch": 1.91, "learning_rate": 1.340341655716163e-06, "loss": 0.4008, "step": 11641 }, { "epoch": 1.91, "learning_rate": 1.3378777923784493e-06, "loss": 0.5188, "step": 11642 }, { "epoch": 1.91, "learning_rate": 1.335413929040736e-06, "loss": 0.3184, "step": 11643 }, { "epoch": 1.91, "learning_rate": 1.3329500657030225e-06, "loss": 0.4858, "step": 11644 }, { "epoch": 1.91, "learning_rate": 1.3304862023653087e-06, "loss": 0.4543, "step": 11645 }, { "epoch": 1.91, "learning_rate": 1.3280223390275953e-06, "loss": 0.9096, "step": 11646 }, { "epoch": 1.91, "learning_rate": 1.3255584756898818e-06, "loss": 0.5337, "step": 11647 }, { "epoch": 1.91, "learning_rate": 1.3230946123521682e-06, "loss": 0.4742, "step": 11648 }, { "epoch": 1.91, "learning_rate": 1.3206307490144548e-06, "loss": 0.4425, "step": 11649 }, { "epoch": 1.91, "learning_rate": 1.3181668856767412e-06, "loss": 0.6446, "step": 11650 }, { "epoch": 1.91, "learning_rate": 1.3157030223390276e-06, "loss": 0.3461, "step": 11651 }, { "epoch": 1.91, "learning_rate": 1.313239159001314e-06, "loss": 0.2014, "step": 11652 }, { "epoch": 1.91, "learning_rate": 1.3107752956636006e-06, "loss": 0.4387, "step": 11653 }, { "epoch": 1.91, "learning_rate": 1.308311432325887e-06, "loss": 0.2809, "step": 11654 }, { "epoch": 1.91, "learning_rate": 1.3058475689881734e-06, "loss": 0.4616, "step": 11655 }, { "epoch": 1.91, "learning_rate": 1.30338370565046e-06, "loss": 0.5282, "step": 11656 }, { "epoch": 1.91, "learning_rate": 1.3009198423127463e-06, "loss": 0.5057, "step": 11657 }, { "epoch": 1.91, "learning_rate": 1.2984559789750329e-06, "loss": 0.4976, "step": 11658 }, { "epoch": 1.92, "learning_rate": 1.2959921156373195e-06, "loss": 0.2872, "step": 11659 }, { "epoch": 1.92, "learning_rate": 1.2935282522996057e-06, "loss": 0.3309, "step": 11660 }, { "epoch": 1.92, "learning_rate": 1.2910643889618923e-06, "loss": 0.8114, "step": 11661 }, { "epoch": 1.92, "learning_rate": 1.2886005256241787e-06, "loss": 0.4644, "step": 11662 }, { "epoch": 1.92, "learning_rate": 1.2861366622864651e-06, "loss": 0.6818, "step": 11663 }, { "epoch": 1.92, "learning_rate": 1.2836727989487515e-06, "loss": 0.2574, "step": 11664 }, { "epoch": 1.92, "learning_rate": 1.2812089356110382e-06, "loss": 0.3932, "step": 11665 }, { "epoch": 1.92, "learning_rate": 1.2787450722733246e-06, "loss": 0.3647, "step": 11666 }, { "epoch": 1.92, "learning_rate": 1.276281208935611e-06, "loss": 0.3902, "step": 11667 }, { "epoch": 1.92, "learning_rate": 1.2738173455978976e-06, "loss": 0.5217, "step": 11668 }, { "epoch": 1.92, "learning_rate": 1.271353482260184e-06, "loss": 0.3928, "step": 11669 }, { "epoch": 1.92, "learning_rate": 1.2688896189224704e-06, "loss": 0.2859, "step": 11670 }, { "epoch": 1.92, "learning_rate": 1.266425755584757e-06, "loss": 0.7323, "step": 11671 }, { "epoch": 1.92, "learning_rate": 1.2639618922470434e-06, "loss": 0.4866, "step": 11672 }, { "epoch": 1.92, "learning_rate": 1.2614980289093298e-06, "loss": 0.5812, "step": 11673 }, { "epoch": 1.92, "learning_rate": 1.2590341655716163e-06, "loss": 0.6256, "step": 11674 }, { "epoch": 1.92, "learning_rate": 1.2565703022339029e-06, "loss": 0.6713, "step": 11675 }, { "epoch": 1.92, "learning_rate": 1.2541064388961893e-06, "loss": 0.5729, "step": 11676 }, { "epoch": 1.92, "learning_rate": 1.2516425755584757e-06, "loss": 0.5046, "step": 11677 }, { "epoch": 1.92, "learning_rate": 1.2491787122207623e-06, "loss": 0.5191, "step": 11678 }, { "epoch": 1.92, "learning_rate": 1.2467148488830485e-06, "loss": 0.2108, "step": 11679 }, { "epoch": 1.92, "learning_rate": 1.2442509855453351e-06, "loss": 0.3645, "step": 11680 }, { "epoch": 1.92, "learning_rate": 1.2417871222076217e-06, "loss": 0.2933, "step": 11681 }, { "epoch": 1.92, "learning_rate": 1.239323258869908e-06, "loss": 0.4404, "step": 11682 }, { "epoch": 1.92, "learning_rate": 1.2368593955321946e-06, "loss": 0.7227, "step": 11683 }, { "epoch": 1.92, "learning_rate": 1.234395532194481e-06, "loss": 0.5202, "step": 11684 }, { "epoch": 1.92, "learning_rate": 1.2319316688567674e-06, "loss": 0.5515, "step": 11685 }, { "epoch": 1.92, "learning_rate": 1.229467805519054e-06, "loss": 0.5498, "step": 11686 }, { "epoch": 1.92, "learning_rate": 1.2270039421813404e-06, "loss": 0.4091, "step": 11687 }, { "epoch": 1.92, "learning_rate": 1.2245400788436268e-06, "loss": 0.4866, "step": 11688 }, { "epoch": 1.92, "learning_rate": 1.2220762155059132e-06, "loss": 0.206, "step": 11689 }, { "epoch": 1.92, "learning_rate": 1.2196123521681998e-06, "loss": 0.702, "step": 11690 }, { "epoch": 1.92, "learning_rate": 1.2171484888304862e-06, "loss": 0.9124, "step": 11691 }, { "epoch": 1.92, "learning_rate": 1.2146846254927727e-06, "loss": 0.1766, "step": 11692 }, { "epoch": 1.92, "learning_rate": 1.2122207621550593e-06, "loss": 0.3826, "step": 11693 }, { "epoch": 1.92, "learning_rate": 1.2097568988173455e-06, "loss": 0.47, "step": 11694 }, { "epoch": 1.92, "learning_rate": 1.207293035479632e-06, "loss": 0.2924, "step": 11695 }, { "epoch": 1.92, "learning_rate": 1.2048291721419187e-06, "loss": 0.3762, "step": 11696 }, { "epoch": 1.92, "learning_rate": 1.202365308804205e-06, "loss": 0.3423, "step": 11697 }, { "epoch": 1.92, "learning_rate": 1.1999014454664915e-06, "loss": 0.3649, "step": 11698 }, { "epoch": 1.92, "learning_rate": 1.197437582128778e-06, "loss": 0.4792, "step": 11699 }, { "epoch": 1.92, "learning_rate": 1.1949737187910643e-06, "loss": 0.551, "step": 11700 }, { "epoch": 1.92, "learning_rate": 1.192509855453351e-06, "loss": 1.0255, "step": 11701 }, { "epoch": 1.92, "learning_rate": 1.1900459921156374e-06, "loss": 0.2952, "step": 11702 }, { "epoch": 1.92, "learning_rate": 1.1875821287779238e-06, "loss": 0.3101, "step": 11703 }, { "epoch": 1.92, "learning_rate": 1.1851182654402102e-06, "loss": 0.4599, "step": 11704 }, { "epoch": 1.92, "learning_rate": 1.1826544021024968e-06, "loss": 0.6272, "step": 11705 }, { "epoch": 1.92, "learning_rate": 1.1801905387647832e-06, "loss": 0.2215, "step": 11706 }, { "epoch": 1.92, "learning_rate": 1.1777266754270696e-06, "loss": 0.8638, "step": 11707 }, { "epoch": 1.92, "learning_rate": 1.1752628120893562e-06, "loss": 0.1766, "step": 11708 }, { "epoch": 1.92, "learning_rate": 1.1727989487516424e-06, "loss": 0.5617, "step": 11709 }, { "epoch": 1.92, "learning_rate": 1.170335085413929e-06, "loss": 0.1873, "step": 11710 }, { "epoch": 1.92, "learning_rate": 1.1678712220762157e-06, "loss": 0.326, "step": 11711 }, { "epoch": 1.92, "learning_rate": 1.1654073587385019e-06, "loss": 0.9762, "step": 11712 }, { "epoch": 1.92, "learning_rate": 1.1629434954007885e-06, "loss": 0.3408, "step": 11713 }, { "epoch": 1.92, "learning_rate": 1.160479632063075e-06, "loss": 0.2271, "step": 11714 }, { "epoch": 1.92, "learning_rate": 1.1580157687253613e-06, "loss": 0.8653, "step": 11715 }, { "epoch": 1.92, "learning_rate": 1.155551905387648e-06, "loss": 0.2744, "step": 11716 }, { "epoch": 1.92, "learning_rate": 1.1530880420499343e-06, "loss": 0.467, "step": 11717 }, { "epoch": 1.92, "learning_rate": 1.1506241787122207e-06, "loss": 0.3526, "step": 11718 }, { "epoch": 1.92, "learning_rate": 1.1481603153745072e-06, "loss": 0.2754, "step": 11719 }, { "epoch": 1.93, "learning_rate": 1.1456964520367938e-06, "loss": 0.5147, "step": 11720 }, { "epoch": 1.93, "learning_rate": 1.1432325886990802e-06, "loss": 0.2181, "step": 11721 }, { "epoch": 1.93, "learning_rate": 1.1407687253613666e-06, "loss": 0.7435, "step": 11722 }, { "epoch": 1.93, "learning_rate": 1.1383048620236532e-06, "loss": 0.3004, "step": 11723 }, { "epoch": 1.93, "learning_rate": 1.1358409986859394e-06, "loss": 0.4694, "step": 11724 }, { "epoch": 1.93, "learning_rate": 1.133377135348226e-06, "loss": 0.7887, "step": 11725 }, { "epoch": 1.93, "learning_rate": 1.1309132720105126e-06, "loss": 0.3376, "step": 11726 }, { "epoch": 1.93, "learning_rate": 1.1284494086727988e-06, "loss": 0.2037, "step": 11727 }, { "epoch": 1.93, "learning_rate": 1.1259855453350855e-06, "loss": 1.0978, "step": 11728 }, { "epoch": 1.93, "learning_rate": 1.1235216819973719e-06, "loss": 0.3378, "step": 11729 }, { "epoch": 1.93, "learning_rate": 1.1210578186596583e-06, "loss": 0.4596, "step": 11730 }, { "epoch": 1.93, "learning_rate": 1.118593955321945e-06, "loss": 0.2593, "step": 11731 }, { "epoch": 1.93, "learning_rate": 1.1161300919842313e-06, "loss": 0.6642, "step": 11732 }, { "epoch": 1.93, "learning_rate": 1.1136662286465177e-06, "loss": 0.0845, "step": 11733 }, { "epoch": 1.93, "learning_rate": 1.1112023653088041e-06, "loss": 0.4872, "step": 11734 }, { "epoch": 1.93, "learning_rate": 1.1087385019710907e-06, "loss": 0.8258, "step": 11735 }, { "epoch": 1.93, "learning_rate": 1.1062746386333772e-06, "loss": 0.481, "step": 11736 }, { "epoch": 1.93, "learning_rate": 1.1038107752956636e-06, "loss": 0.6581, "step": 11737 }, { "epoch": 1.93, "learning_rate": 1.1013469119579502e-06, "loss": 0.6042, "step": 11738 }, { "epoch": 1.93, "learning_rate": 1.0988830486202366e-06, "loss": 0.6059, "step": 11739 }, { "epoch": 1.93, "learning_rate": 1.096419185282523e-06, "loss": 0.7405, "step": 11740 }, { "epoch": 1.93, "learning_rate": 1.0939553219448096e-06, "loss": 0.4398, "step": 11741 }, { "epoch": 1.93, "learning_rate": 1.091491458607096e-06, "loss": 0.8533, "step": 11742 }, { "epoch": 1.93, "learning_rate": 1.0890275952693824e-06, "loss": 0.374, "step": 11743 }, { "epoch": 1.93, "learning_rate": 1.0865637319316688e-06, "loss": 0.3549, "step": 11744 }, { "epoch": 1.93, "learning_rate": 1.0840998685939555e-06, "loss": 0.1878, "step": 11745 }, { "epoch": 1.93, "learning_rate": 1.0816360052562419e-06, "loss": 0.2127, "step": 11746 }, { "epoch": 1.93, "learning_rate": 1.0791721419185283e-06, "loss": 1.1882, "step": 11747 }, { "epoch": 1.93, "learning_rate": 1.076708278580815e-06, "loss": 0.256, "step": 11748 }, { "epoch": 1.93, "learning_rate": 1.074244415243101e-06, "loss": 0.6927, "step": 11749 }, { "epoch": 1.93, "learning_rate": 1.0717805519053877e-06, "loss": 0.1214, "step": 11750 }, { "epoch": 1.93, "learning_rate": 1.0693166885676743e-06, "loss": 0.3901, "step": 11751 }, { "epoch": 1.93, "learning_rate": 1.0668528252299605e-06, "loss": 0.331, "step": 11752 }, { "epoch": 1.93, "learning_rate": 1.0643889618922471e-06, "loss": 0.284, "step": 11753 }, { "epoch": 1.93, "learning_rate": 1.0619250985545336e-06, "loss": 0.2617, "step": 11754 }, { "epoch": 1.93, "learning_rate": 1.05946123521682e-06, "loss": 0.8077, "step": 11755 }, { "epoch": 1.93, "learning_rate": 1.0569973718791066e-06, "loss": 0.453, "step": 11756 }, { "epoch": 1.93, "learning_rate": 1.054533508541393e-06, "loss": 0.7489, "step": 11757 }, { "epoch": 1.93, "learning_rate": 1.0520696452036794e-06, "loss": 0.6764, "step": 11758 }, { "epoch": 1.93, "learning_rate": 1.0496057818659658e-06, "loss": 0.3257, "step": 11759 }, { "epoch": 1.93, "learning_rate": 1.0471419185282524e-06, "loss": 0.2591, "step": 11760 }, { "epoch": 1.93, "learning_rate": 1.0446780551905386e-06, "loss": 0.603, "step": 11761 }, { "epoch": 1.93, "learning_rate": 1.0422141918528252e-06, "loss": 0.4009, "step": 11762 }, { "epoch": 1.93, "learning_rate": 1.0397503285151119e-06, "loss": 0.5749, "step": 11763 }, { "epoch": 1.93, "learning_rate": 1.037286465177398e-06, "loss": 0.1859, "step": 11764 }, { "epoch": 1.93, "learning_rate": 1.0348226018396847e-06, "loss": 0.2743, "step": 11765 }, { "epoch": 1.93, "learning_rate": 1.032358738501971e-06, "loss": 0.3989, "step": 11766 }, { "epoch": 1.93, "learning_rate": 1.0298948751642575e-06, "loss": 0.2087, "step": 11767 }, { "epoch": 1.93, "learning_rate": 1.0274310118265441e-06, "loss": 0.3225, "step": 11768 }, { "epoch": 1.93, "learning_rate": 1.0249671484888305e-06, "loss": 0.1186, "step": 11769 }, { "epoch": 1.93, "learning_rate": 1.022503285151117e-06, "loss": 0.5091, "step": 11770 }, { "epoch": 1.93, "learning_rate": 1.0200394218134033e-06, "loss": 0.2447, "step": 11771 }, { "epoch": 1.93, "learning_rate": 1.01757555847569e-06, "loss": 0.4052, "step": 11772 }, { "epoch": 1.93, "learning_rate": 1.0151116951379764e-06, "loss": 0.4905, "step": 11773 }, { "epoch": 1.93, "learning_rate": 1.0126478318002628e-06, "loss": 0.4383, "step": 11774 }, { "epoch": 1.93, "learning_rate": 1.0101839684625494e-06, "loss": 0.287, "step": 11775 }, { "epoch": 1.93, "learning_rate": 1.0077201051248356e-06, "loss": 0.3755, "step": 11776 }, { "epoch": 1.93, "learning_rate": 1.0052562417871222e-06, "loss": 0.2768, "step": 11777 }, { "epoch": 1.93, "learning_rate": 1.0027923784494088e-06, "loss": 0.2152, "step": 11778 }, { "epoch": 1.93, "learning_rate": 1.000328515111695e-06, "loss": 0.5611, "step": 11779 }, { "epoch": 1.93, "learning_rate": 9.978646517739816e-07, "loss": 0.2476, "step": 11780 }, { "epoch": 1.94, "learning_rate": 9.95400788436268e-07, "loss": 0.4171, "step": 11781 }, { "epoch": 1.94, "learning_rate": 9.929369250985545e-07, "loss": 0.3048, "step": 11782 }, { "epoch": 1.94, "learning_rate": 9.90473061760841e-07, "loss": 0.2068, "step": 11783 }, { "epoch": 1.94, "learning_rate": 9.880091984231275e-07, "loss": 0.2651, "step": 11784 }, { "epoch": 1.94, "learning_rate": 9.85545335085414e-07, "loss": 0.5892, "step": 11785 }, { "epoch": 1.94, "learning_rate": 9.830814717477003e-07, "loss": 0.4969, "step": 11786 }, { "epoch": 1.94, "learning_rate": 9.80617608409987e-07, "loss": 1.0993, "step": 11787 }, { "epoch": 1.94, "learning_rate": 9.781537450722733e-07, "loss": 0.5713, "step": 11788 }, { "epoch": 1.94, "learning_rate": 9.756898817345597e-07, "loss": 0.4913, "step": 11789 }, { "epoch": 1.94, "learning_rate": 9.732260183968464e-07, "loss": 1.1124, "step": 11790 }, { "epoch": 1.94, "learning_rate": 9.707621550591326e-07, "loss": 0.7425, "step": 11791 }, { "epoch": 1.94, "learning_rate": 9.682982917214192e-07, "loss": 0.447, "step": 11792 }, { "epoch": 1.94, "learning_rate": 9.658344283837058e-07, "loss": 0.5512, "step": 11793 }, { "epoch": 1.94, "learning_rate": 9.63370565045992e-07, "loss": 0.31, "step": 11794 }, { "epoch": 1.94, "learning_rate": 9.609067017082786e-07, "loss": 0.3323, "step": 11795 }, { "epoch": 1.94, "learning_rate": 9.58442838370565e-07, "loss": 0.2932, "step": 11796 }, { "epoch": 1.94, "learning_rate": 9.559789750328514e-07, "loss": 0.2074, "step": 11797 }, { "epoch": 1.94, "learning_rate": 9.535151116951381e-07, "loss": 0.2739, "step": 11798 }, { "epoch": 1.94, "learning_rate": 9.510512483574245e-07, "loss": 0.7874, "step": 11799 }, { "epoch": 1.94, "learning_rate": 9.48587385019711e-07, "loss": 0.3542, "step": 11800 }, { "epoch": 1.94, "learning_rate": 9.461235216819973e-07, "loss": 0.4681, "step": 11801 }, { "epoch": 1.94, "learning_rate": 9.436596583442839e-07, "loss": 0.2259, "step": 11802 }, { "epoch": 1.94, "learning_rate": 9.411957950065704e-07, "loss": 0.6641, "step": 11803 }, { "epoch": 1.94, "learning_rate": 9.387319316688567e-07, "loss": 0.405, "step": 11804 }, { "epoch": 1.94, "learning_rate": 9.362680683311433e-07, "loss": 1.3941, "step": 11805 }, { "epoch": 1.94, "learning_rate": 9.338042049934297e-07, "loss": 0.6962, "step": 11806 }, { "epoch": 1.94, "learning_rate": 9.313403416557161e-07, "loss": 0.5565, "step": 11807 }, { "epoch": 1.94, "learning_rate": 9.288764783180027e-07, "loss": 0.2475, "step": 11808 }, { "epoch": 1.94, "learning_rate": 9.264126149802891e-07, "loss": 0.4825, "step": 11809 }, { "epoch": 1.94, "learning_rate": 9.239487516425756e-07, "loss": 0.7917, "step": 11810 }, { "epoch": 1.94, "learning_rate": 9.214848883048621e-07, "loss": 1.005, "step": 11811 }, { "epoch": 1.94, "learning_rate": 9.190210249671485e-07, "loss": 0.2533, "step": 11812 }, { "epoch": 1.94, "learning_rate": 9.165571616294349e-07, "loss": 0.2681, "step": 11813 }, { "epoch": 1.94, "learning_rate": 9.140932982917214e-07, "loss": 0.1686, "step": 11814 }, { "epoch": 1.94, "learning_rate": 9.116294349540079e-07, "loss": 0.3026, "step": 11815 }, { "epoch": 1.94, "learning_rate": 9.091655716162944e-07, "loss": 0.2909, "step": 11816 }, { "epoch": 1.94, "learning_rate": 9.067017082785809e-07, "loss": 0.6128, "step": 11817 }, { "epoch": 1.94, "learning_rate": 9.042378449408673e-07, "loss": 0.1366, "step": 11818 }, { "epoch": 1.94, "learning_rate": 9.017739816031537e-07, "loss": 0.3344, "step": 11819 }, { "epoch": 1.94, "learning_rate": 8.993101182654403e-07, "loss": 0.2658, "step": 11820 }, { "epoch": 1.94, "learning_rate": 8.968462549277267e-07, "loss": 0.1373, "step": 11821 }, { "epoch": 1.94, "learning_rate": 8.943823915900132e-07, "loss": 0.4706, "step": 11822 }, { "epoch": 1.94, "learning_rate": 8.919185282522996e-07, "loss": 0.5659, "step": 11823 }, { "epoch": 1.94, "learning_rate": 8.89454664914586e-07, "loss": 0.5944, "step": 11824 }, { "epoch": 1.94, "learning_rate": 8.869908015768727e-07, "loss": 0.2262, "step": 11825 }, { "epoch": 1.94, "learning_rate": 8.845269382391591e-07, "loss": 0.333, "step": 11826 }, { "epoch": 1.94, "learning_rate": 8.820630749014455e-07, "loss": 1.2892, "step": 11827 }, { "epoch": 1.94, "learning_rate": 8.79599211563732e-07, "loss": 0.4897, "step": 11828 }, { "epoch": 1.94, "learning_rate": 8.771353482260184e-07, "loss": 0.4424, "step": 11829 }, { "epoch": 1.94, "learning_rate": 8.746714848883048e-07, "loss": 0.1854, "step": 11830 }, { "epoch": 1.94, "learning_rate": 8.722076215505914e-07, "loss": 1.4985, "step": 11831 }, { "epoch": 1.94, "learning_rate": 8.697437582128778e-07, "loss": 0.4489, "step": 11832 }, { "epoch": 1.94, "learning_rate": 8.672798948751642e-07, "loss": 0.4637, "step": 11833 }, { "epoch": 1.94, "learning_rate": 8.648160315374508e-07, "loss": 0.0825, "step": 11834 }, { "epoch": 1.94, "learning_rate": 8.623521681997372e-07, "loss": 0.4793, "step": 11835 }, { "epoch": 1.94, "learning_rate": 8.598883048620237e-07, "loss": 0.2486, "step": 11836 }, { "epoch": 1.94, "learning_rate": 8.574244415243102e-07, "loss": 0.4715, "step": 11837 }, { "epoch": 1.94, "learning_rate": 8.549605781865966e-07, "loss": 0.6677, "step": 11838 }, { "epoch": 1.94, "learning_rate": 8.52496714848883e-07, "loss": 0.4936, "step": 11839 }, { "epoch": 1.94, "learning_rate": 8.500328515111695e-07, "loss": 0.7684, "step": 11840 }, { "epoch": 1.94, "learning_rate": 8.47568988173456e-07, "loss": 0.3671, "step": 11841 }, { "epoch": 1.95, "learning_rate": 8.451051248357424e-07, "loss": 0.1528, "step": 11842 }, { "epoch": 1.95, "learning_rate": 8.42641261498029e-07, "loss": 0.2617, "step": 11843 }, { "epoch": 1.95, "learning_rate": 8.401773981603154e-07, "loss": 0.7732, "step": 11844 }, { "epoch": 1.95, "learning_rate": 8.377135348226018e-07, "loss": 1.0055, "step": 11845 }, { "epoch": 1.95, "learning_rate": 8.352496714848884e-07, "loss": 0.3343, "step": 11846 }, { "epoch": 1.95, "learning_rate": 8.327858081471748e-07, "loss": 0.3626, "step": 11847 }, { "epoch": 1.95, "learning_rate": 8.303219448094612e-07, "loss": 0.7187, "step": 11848 }, { "epoch": 1.95, "learning_rate": 8.278580814717477e-07, "loss": 0.8474, "step": 11849 }, { "epoch": 1.95, "learning_rate": 8.253942181340341e-07, "loss": 1.1115, "step": 11850 }, { "epoch": 1.95, "learning_rate": 8.229303547963206e-07, "loss": 0.8746, "step": 11851 }, { "epoch": 1.95, "learning_rate": 8.204664914586072e-07, "loss": 0.3303, "step": 11852 }, { "epoch": 1.95, "learning_rate": 8.180026281208936e-07, "loss": 0.5215, "step": 11853 }, { "epoch": 1.95, "learning_rate": 8.1553876478318e-07, "loss": 0.6185, "step": 11854 }, { "epoch": 1.95, "learning_rate": 8.130749014454665e-07, "loss": 0.7371, "step": 11855 }, { "epoch": 1.95, "learning_rate": 8.10611038107753e-07, "loss": 0.1643, "step": 11856 }, { "epoch": 1.95, "learning_rate": 8.081471747700395e-07, "loss": 0.4023, "step": 11857 }, { "epoch": 1.95, "learning_rate": 8.056833114323259e-07, "loss": 0.273, "step": 11858 }, { "epoch": 1.95, "learning_rate": 8.032194480946123e-07, "loss": 0.4459, "step": 11859 }, { "epoch": 1.95, "learning_rate": 8.007555847568988e-07, "loss": 1.0516, "step": 11860 }, { "epoch": 1.95, "learning_rate": 7.982917214191854e-07, "loss": 0.5175, "step": 11861 }, { "epoch": 1.95, "learning_rate": 7.958278580814718e-07, "loss": 0.6645, "step": 11862 }, { "epoch": 1.95, "learning_rate": 7.933639947437583e-07, "loss": 0.4381, "step": 11863 }, { "epoch": 1.95, "learning_rate": 7.909001314060447e-07, "loss": 0.3607, "step": 11864 }, { "epoch": 1.95, "learning_rate": 7.884362680683311e-07, "loss": 0.3746, "step": 11865 }, { "epoch": 1.95, "learning_rate": 7.859724047306177e-07, "loss": 0.9189, "step": 11866 }, { "epoch": 1.95, "learning_rate": 7.835085413929041e-07, "loss": 0.4802, "step": 11867 }, { "epoch": 1.95, "learning_rate": 7.810446780551905e-07, "loss": 0.1257, "step": 11868 }, { "epoch": 1.95, "learning_rate": 7.78580814717477e-07, "loss": 1.0894, "step": 11869 }, { "epoch": 1.95, "learning_rate": 7.761169513797635e-07, "loss": 0.4948, "step": 11870 }, { "epoch": 1.95, "learning_rate": 7.7365308804205e-07, "loss": 0.4062, "step": 11871 }, { "epoch": 1.95, "learning_rate": 7.711892247043365e-07, "loss": 0.5543, "step": 11872 }, { "epoch": 1.95, "learning_rate": 7.687253613666229e-07, "loss": 0.3201, "step": 11873 }, { "epoch": 1.95, "learning_rate": 7.662614980289093e-07, "loss": 0.4712, "step": 11874 }, { "epoch": 1.95, "learning_rate": 7.637976346911958e-07, "loss": 0.8842, "step": 11875 }, { "epoch": 1.95, "learning_rate": 7.613337713534822e-07, "loss": 0.8398, "step": 11876 }, { "epoch": 1.95, "learning_rate": 7.588699080157687e-07, "loss": 0.8325, "step": 11877 }, { "epoch": 1.95, "learning_rate": 7.564060446780553e-07, "loss": 0.3777, "step": 11878 }, { "epoch": 1.95, "learning_rate": 7.539421813403417e-07, "loss": 0.4101, "step": 11879 }, { "epoch": 1.95, "learning_rate": 7.514783180026281e-07, "loss": 0.2854, "step": 11880 }, { "epoch": 1.95, "learning_rate": 7.490144546649146e-07, "loss": 0.4819, "step": 11881 }, { "epoch": 1.95, "learning_rate": 7.465505913272011e-07, "loss": 0.3906, "step": 11882 }, { "epoch": 1.95, "learning_rate": 7.440867279894875e-07, "loss": 0.255, "step": 11883 }, { "epoch": 1.95, "learning_rate": 7.41622864651774e-07, "loss": 0.3547, "step": 11884 }, { "epoch": 1.95, "learning_rate": 7.391590013140604e-07, "loss": 1.3036, "step": 11885 }, { "epoch": 1.95, "learning_rate": 7.366951379763468e-07, "loss": 0.345, "step": 11886 }, { "epoch": 1.95, "learning_rate": 7.342312746386335e-07, "loss": 0.6462, "step": 11887 }, { "epoch": 1.95, "learning_rate": 7.317674113009199e-07, "loss": 0.3759, "step": 11888 }, { "epoch": 1.95, "learning_rate": 7.293035479632063e-07, "loss": 0.5437, "step": 11889 }, { "epoch": 1.95, "learning_rate": 7.268396846254928e-07, "loss": 0.3551, "step": 11890 }, { "epoch": 1.95, "learning_rate": 7.243758212877792e-07, "loss": 0.3656, "step": 11891 }, { "epoch": 1.95, "learning_rate": 7.219119579500658e-07, "loss": 0.6822, "step": 11892 }, { "epoch": 1.95, "learning_rate": 7.194480946123522e-07, "loss": 0.4129, "step": 11893 }, { "epoch": 1.95, "learning_rate": 7.169842312746386e-07, "loss": 0.413, "step": 11894 }, { "epoch": 1.95, "learning_rate": 7.145203679369251e-07, "loss": 0.6308, "step": 11895 }, { "epoch": 1.95, "learning_rate": 7.120565045992116e-07, "loss": 0.5125, "step": 11896 }, { "epoch": 1.95, "learning_rate": 7.095926412614981e-07, "loss": 0.4144, "step": 11897 }, { "epoch": 1.95, "learning_rate": 7.071287779237846e-07, "loss": 0.3024, "step": 11898 }, { "epoch": 1.95, "learning_rate": 7.04664914586071e-07, "loss": 0.5151, "step": 11899 }, { "epoch": 1.95, "learning_rate": 7.022010512483574e-07, "loss": 0.4534, "step": 11900 }, { "epoch": 1.95, "learning_rate": 6.997371879106439e-07, "loss": 0.3412, "step": 11901 }, { "epoch": 1.95, "learning_rate": 6.972733245729304e-07, "loss": 0.3794, "step": 11902 }, { "epoch": 1.96, "learning_rate": 6.948094612352168e-07, "loss": 0.5268, "step": 11903 }, { "epoch": 1.96, "learning_rate": 6.923455978975033e-07, "loss": 0.9811, "step": 11904 }, { "epoch": 1.96, "learning_rate": 6.898817345597898e-07, "loss": 0.57, "step": 11905 }, { "epoch": 1.96, "learning_rate": 6.874178712220762e-07, "loss": 0.1977, "step": 11906 }, { "epoch": 1.96, "learning_rate": 6.849540078843628e-07, "loss": 1.0189, "step": 11907 }, { "epoch": 1.96, "learning_rate": 6.824901445466492e-07, "loss": 0.4124, "step": 11908 }, { "epoch": 1.96, "learning_rate": 6.800262812089356e-07, "loss": 0.4781, "step": 11909 }, { "epoch": 1.96, "learning_rate": 6.775624178712221e-07, "loss": 0.2868, "step": 11910 }, { "epoch": 1.96, "learning_rate": 6.750985545335085e-07, "loss": 0.2937, "step": 11911 }, { "epoch": 1.96, "learning_rate": 6.72634691195795e-07, "loss": 0.4071, "step": 11912 }, { "epoch": 1.96, "learning_rate": 6.701708278580815e-07, "loss": 0.5666, "step": 11913 }, { "epoch": 1.96, "learning_rate": 6.67706964520368e-07, "loss": 0.4068, "step": 11914 }, { "epoch": 1.96, "learning_rate": 6.652431011826544e-07, "loss": 0.3691, "step": 11915 }, { "epoch": 1.96, "learning_rate": 6.627792378449409e-07, "loss": 0.6102, "step": 11916 }, { "epoch": 1.96, "learning_rate": 6.603153745072274e-07, "loss": 1.0539, "step": 11917 }, { "epoch": 1.96, "learning_rate": 6.578515111695138e-07, "loss": 0.4135, "step": 11918 }, { "epoch": 1.96, "learning_rate": 6.553876478318003e-07, "loss": 0.2606, "step": 11919 }, { "epoch": 1.96, "learning_rate": 6.529237844940867e-07, "loss": 0.9353, "step": 11920 }, { "epoch": 1.96, "learning_rate": 6.504599211563731e-07, "loss": 0.4734, "step": 11921 }, { "epoch": 1.96, "learning_rate": 6.479960578186597e-07, "loss": 0.3241, "step": 11922 }, { "epoch": 1.96, "learning_rate": 6.455321944809462e-07, "loss": 0.5108, "step": 11923 }, { "epoch": 1.96, "learning_rate": 6.430683311432326e-07, "loss": 0.2553, "step": 11924 }, { "epoch": 1.96, "learning_rate": 6.406044678055191e-07, "loss": 0.2362, "step": 11925 }, { "epoch": 1.96, "learning_rate": 6.381406044678055e-07, "loss": 0.3092, "step": 11926 }, { "epoch": 1.96, "learning_rate": 6.35676741130092e-07, "loss": 0.5119, "step": 11927 }, { "epoch": 1.96, "learning_rate": 6.332128777923785e-07, "loss": 0.4388, "step": 11928 }, { "epoch": 1.96, "learning_rate": 6.307490144546649e-07, "loss": 0.651, "step": 11929 }, { "epoch": 1.96, "learning_rate": 6.282851511169514e-07, "loss": 0.9436, "step": 11930 }, { "epoch": 1.96, "learning_rate": 6.258212877792378e-07, "loss": 0.4099, "step": 11931 }, { "epoch": 1.96, "learning_rate": 6.233574244415243e-07, "loss": 0.8394, "step": 11932 }, { "epoch": 1.96, "learning_rate": 6.208935611038109e-07, "loss": 0.4461, "step": 11933 }, { "epoch": 1.96, "learning_rate": 6.184296977660973e-07, "loss": 0.6791, "step": 11934 }, { "epoch": 1.96, "learning_rate": 6.159658344283837e-07, "loss": 0.276, "step": 11935 }, { "epoch": 1.96, "learning_rate": 6.135019710906702e-07, "loss": 0.4263, "step": 11936 }, { "epoch": 1.96, "learning_rate": 6.110381077529566e-07, "loss": 0.5699, "step": 11937 }, { "epoch": 1.96, "learning_rate": 6.085742444152431e-07, "loss": 0.3479, "step": 11938 }, { "epoch": 1.96, "learning_rate": 6.061103810775296e-07, "loss": 0.5365, "step": 11939 }, { "epoch": 1.96, "learning_rate": 6.03646517739816e-07, "loss": 0.6411, "step": 11940 }, { "epoch": 1.96, "learning_rate": 6.011826544021025e-07, "loss": 0.3656, "step": 11941 }, { "epoch": 1.96, "learning_rate": 5.98718791064389e-07, "loss": 0.2615, "step": 11942 }, { "epoch": 1.96, "learning_rate": 5.962549277266755e-07, "loss": 0.7008, "step": 11943 }, { "epoch": 1.96, "learning_rate": 5.937910643889619e-07, "loss": 0.2909, "step": 11944 }, { "epoch": 1.96, "learning_rate": 5.913272010512484e-07, "loss": 0.6371, "step": 11945 }, { "epoch": 1.96, "learning_rate": 5.888633377135348e-07, "loss": 0.208, "step": 11946 }, { "epoch": 1.96, "learning_rate": 5.863994743758212e-07, "loss": 1.082, "step": 11947 }, { "epoch": 1.96, "learning_rate": 5.839356110381078e-07, "loss": 0.7018, "step": 11948 }, { "epoch": 1.96, "learning_rate": 5.814717477003942e-07, "loss": 0.2025, "step": 11949 }, { "epoch": 1.96, "learning_rate": 5.790078843626807e-07, "loss": 0.8872, "step": 11950 }, { "epoch": 1.96, "learning_rate": 5.765440210249672e-07, "loss": 0.5587, "step": 11951 }, { "epoch": 1.96, "learning_rate": 5.740801576872536e-07, "loss": 1.4585, "step": 11952 }, { "epoch": 1.96, "learning_rate": 5.716162943495401e-07, "loss": 0.6835, "step": 11953 }, { "epoch": 1.96, "learning_rate": 5.691524310118266e-07, "loss": 0.5217, "step": 11954 }, { "epoch": 1.96, "learning_rate": 5.66688567674113e-07, "loss": 0.4248, "step": 11955 }, { "epoch": 1.96, "learning_rate": 5.642247043363994e-07, "loss": 0.2988, "step": 11956 }, { "epoch": 1.96, "learning_rate": 5.617608409986859e-07, "loss": 0.6259, "step": 11957 }, { "epoch": 1.96, "learning_rate": 5.592969776609725e-07, "loss": 0.6931, "step": 11958 }, { "epoch": 1.96, "learning_rate": 5.568331143232589e-07, "loss": 0.4199, "step": 11959 }, { "epoch": 1.96, "learning_rate": 5.543692509855454e-07, "loss": 0.4212, "step": 11960 }, { "epoch": 1.96, "learning_rate": 5.519053876478318e-07, "loss": 0.6587, "step": 11961 }, { "epoch": 1.96, "learning_rate": 5.494415243101183e-07, "loss": 0.335, "step": 11962 }, { "epoch": 1.97, "learning_rate": 5.469776609724048e-07, "loss": 0.6008, "step": 11963 }, { "epoch": 1.97, "learning_rate": 5.445137976346912e-07, "loss": 0.3437, "step": 11964 }, { "epoch": 1.97, "learning_rate": 5.420499342969777e-07, "loss": 0.4001, "step": 11965 }, { "epoch": 1.97, "learning_rate": 5.395860709592641e-07, "loss": 0.3906, "step": 11966 }, { "epoch": 1.97, "learning_rate": 5.371222076215505e-07, "loss": 0.6418, "step": 11967 }, { "epoch": 1.97, "learning_rate": 5.346583442838372e-07, "loss": 0.4355, "step": 11968 }, { "epoch": 1.97, "learning_rate": 5.321944809461236e-07, "loss": 0.9329, "step": 11969 }, { "epoch": 1.97, "learning_rate": 5.2973061760841e-07, "loss": 0.1496, "step": 11970 }, { "epoch": 1.97, "learning_rate": 5.272667542706965e-07, "loss": 0.6684, "step": 11971 }, { "epoch": 1.97, "learning_rate": 5.248028909329829e-07, "loss": 0.5611, "step": 11972 }, { "epoch": 1.97, "learning_rate": 5.223390275952693e-07, "loss": 0.2395, "step": 11973 }, { "epoch": 1.97, "learning_rate": 5.198751642575559e-07, "loss": 0.688, "step": 11974 }, { "epoch": 1.97, "learning_rate": 5.174113009198423e-07, "loss": 0.6358, "step": 11975 }, { "epoch": 1.97, "learning_rate": 5.149474375821287e-07, "loss": 0.814, "step": 11976 }, { "epoch": 1.97, "learning_rate": 5.124835742444153e-07, "loss": 0.7032, "step": 11977 }, { "epoch": 1.97, "learning_rate": 5.100197109067017e-07, "loss": 0.4814, "step": 11978 }, { "epoch": 1.97, "learning_rate": 5.075558475689882e-07, "loss": 0.5387, "step": 11979 }, { "epoch": 1.97, "learning_rate": 5.050919842312747e-07, "loss": 0.7026, "step": 11980 }, { "epoch": 1.97, "learning_rate": 5.026281208935611e-07, "loss": 0.4151, "step": 11981 }, { "epoch": 1.97, "learning_rate": 5.001642575558475e-07, "loss": 0.539, "step": 11982 }, { "epoch": 1.97, "learning_rate": 4.97700394218134e-07, "loss": 0.4676, "step": 11983 }, { "epoch": 1.97, "learning_rate": 4.952365308804205e-07, "loss": 0.3999, "step": 11984 }, { "epoch": 1.97, "learning_rate": 4.92772667542707e-07, "loss": 0.601, "step": 11985 }, { "epoch": 1.97, "learning_rate": 4.903088042049935e-07, "loss": 0.4134, "step": 11986 }, { "epoch": 1.97, "learning_rate": 4.878449408672799e-07, "loss": 0.1459, "step": 11987 }, { "epoch": 1.97, "learning_rate": 4.853810775295663e-07, "loss": 0.3641, "step": 11988 }, { "epoch": 1.97, "learning_rate": 4.829172141918529e-07, "loss": 0.2503, "step": 11989 }, { "epoch": 1.97, "learning_rate": 4.804533508541393e-07, "loss": 0.2457, "step": 11990 }, { "epoch": 1.97, "learning_rate": 4.779894875164257e-07, "loss": 0.7512, "step": 11991 }, { "epoch": 1.97, "learning_rate": 4.7552562417871223e-07, "loss": 0.3725, "step": 11992 }, { "epoch": 1.97, "learning_rate": 4.7306176084099864e-07, "loss": 0.575, "step": 11993 }, { "epoch": 1.97, "learning_rate": 4.705978975032852e-07, "loss": 0.4272, "step": 11994 }, { "epoch": 1.97, "learning_rate": 4.6813403416557167e-07, "loss": 0.7008, "step": 11995 }, { "epoch": 1.97, "learning_rate": 4.656701708278581e-07, "loss": 0.3354, "step": 11996 }, { "epoch": 1.97, "learning_rate": 4.6320630749014454e-07, "loss": 0.3413, "step": 11997 }, { "epoch": 1.97, "learning_rate": 4.6074244415243105e-07, "loss": 0.921, "step": 11998 }, { "epoch": 1.97, "learning_rate": 4.5827858081471746e-07, "loss": 0.3119, "step": 11999 }, { "epoch": 1.97, "learning_rate": 4.5581471747700397e-07, "loss": 0.2047, "step": 12000 }, { "epoch": 1.97, "eval_exact_match": 86.90633869441817, "eval_f1": 93.11520239800646, "step": 12000 }, { "epoch": 1.97, "learning_rate": 4.5335085413929043e-07, "loss": 0.629, "step": 12001 }, { "epoch": 1.97, "learning_rate": 4.5088699080157684e-07, "loss": 0.515, "step": 12002 }, { "epoch": 1.97, "learning_rate": 4.4842312746386335e-07, "loss": 0.5614, "step": 12003 }, { "epoch": 1.97, "learning_rate": 4.459592641261498e-07, "loss": 1.2459, "step": 12004 }, { "epoch": 1.97, "learning_rate": 4.4349540078843633e-07, "loss": 0.8352, "step": 12005 }, { "epoch": 1.97, "learning_rate": 4.4103153745072274e-07, "loss": 0.2614, "step": 12006 }, { "epoch": 1.97, "learning_rate": 4.385676741130092e-07, "loss": 0.3381, "step": 12007 }, { "epoch": 1.97, "learning_rate": 4.361038107752957e-07, "loss": 0.7394, "step": 12008 }, { "epoch": 1.97, "learning_rate": 4.336399474375821e-07, "loss": 0.6222, "step": 12009 }, { "epoch": 1.97, "learning_rate": 4.311760840998686e-07, "loss": 0.3831, "step": 12010 }, { "epoch": 1.97, "learning_rate": 4.287122207621551e-07, "loss": 0.5822, "step": 12011 }, { "epoch": 1.97, "learning_rate": 4.262483574244415e-07, "loss": 0.2764, "step": 12012 }, { "epoch": 1.97, "learning_rate": 4.23784494086728e-07, "loss": 0.3952, "step": 12013 }, { "epoch": 1.97, "learning_rate": 4.213206307490145e-07, "loss": 0.9288, "step": 12014 }, { "epoch": 1.97, "learning_rate": 4.188567674113009e-07, "loss": 0.2073, "step": 12015 }, { "epoch": 1.97, "learning_rate": 4.163929040735874e-07, "loss": 0.565, "step": 12016 }, { "epoch": 1.97, "learning_rate": 4.1392904073587386e-07, "loss": 0.3911, "step": 12017 }, { "epoch": 1.97, "learning_rate": 4.114651773981603e-07, "loss": 0.6528, "step": 12018 }, { "epoch": 1.97, "learning_rate": 4.090013140604468e-07, "loss": 0.8624, "step": 12019 }, { "epoch": 1.97, "learning_rate": 4.0653745072273325e-07, "loss": 0.2574, "step": 12020 }, { "epoch": 1.97, "learning_rate": 4.0407358738501976e-07, "loss": 0.7401, "step": 12021 }, { "epoch": 1.97, "learning_rate": 4.0160972404730617e-07, "loss": 0.514, "step": 12022 }, { "epoch": 1.97, "learning_rate": 3.991458607095927e-07, "loss": 0.5123, "step": 12023 }, { "epoch": 1.98, "learning_rate": 3.9668199737187914e-07, "loss": 0.5982, "step": 12024 }, { "epoch": 1.98, "learning_rate": 3.9421813403416555e-07, "loss": 0.4766, "step": 12025 }, { "epoch": 1.98, "learning_rate": 3.9175427069645206e-07, "loss": 0.354, "step": 12026 }, { "epoch": 1.98, "learning_rate": 3.892904073587385e-07, "loss": 0.2143, "step": 12027 }, { "epoch": 1.98, "learning_rate": 3.86826544021025e-07, "loss": 0.831, "step": 12028 }, { "epoch": 1.98, "learning_rate": 3.8436268068331145e-07, "loss": 0.5507, "step": 12029 }, { "epoch": 1.98, "learning_rate": 3.818988173455979e-07, "loss": 0.1341, "step": 12030 }, { "epoch": 1.98, "learning_rate": 3.7943495400788437e-07, "loss": 0.1963, "step": 12031 }, { "epoch": 1.98, "learning_rate": 3.7697109067017083e-07, "loss": 0.2694, "step": 12032 }, { "epoch": 1.98, "learning_rate": 3.745072273324573e-07, "loss": 0.5652, "step": 12033 }, { "epoch": 1.98, "learning_rate": 3.7204336399474375e-07, "loss": 0.2846, "step": 12034 }, { "epoch": 1.98, "learning_rate": 3.695795006570302e-07, "loss": 0.4076, "step": 12035 }, { "epoch": 1.98, "learning_rate": 3.6711563731931673e-07, "loss": 0.4596, "step": 12036 }, { "epoch": 1.98, "learning_rate": 3.6465177398160314e-07, "loss": 0.6566, "step": 12037 }, { "epoch": 1.98, "learning_rate": 3.621879106438896e-07, "loss": 0.5537, "step": 12038 }, { "epoch": 1.98, "learning_rate": 3.597240473061761e-07, "loss": 0.6731, "step": 12039 }, { "epoch": 1.98, "learning_rate": 3.5726018396846257e-07, "loss": 0.4332, "step": 12040 }, { "epoch": 1.98, "learning_rate": 3.5479632063074903e-07, "loss": 0.4855, "step": 12041 }, { "epoch": 1.98, "learning_rate": 3.523324572930355e-07, "loss": 0.2342, "step": 12042 }, { "epoch": 1.98, "learning_rate": 3.4986859395532195e-07, "loss": 0.4233, "step": 12043 }, { "epoch": 1.98, "learning_rate": 3.474047306176084e-07, "loss": 0.4985, "step": 12044 }, { "epoch": 1.98, "learning_rate": 3.449408672798949e-07, "loss": 0.3015, "step": 12045 }, { "epoch": 1.98, "learning_rate": 3.424770039421814e-07, "loss": 0.2295, "step": 12046 }, { "epoch": 1.98, "learning_rate": 3.400131406044678e-07, "loss": 0.5127, "step": 12047 }, { "epoch": 1.98, "learning_rate": 3.3754927726675426e-07, "loss": 0.1774, "step": 12048 }, { "epoch": 1.98, "learning_rate": 3.3508541392904077e-07, "loss": 0.2807, "step": 12049 }, { "epoch": 1.98, "learning_rate": 3.326215505913272e-07, "loss": 0.4306, "step": 12050 }, { "epoch": 1.98, "learning_rate": 3.301576872536137e-07, "loss": 0.3679, "step": 12051 }, { "epoch": 1.98, "learning_rate": 3.2769382391590016e-07, "loss": 0.5277, "step": 12052 }, { "epoch": 1.98, "learning_rate": 3.2522996057818656e-07, "loss": 0.469, "step": 12053 }, { "epoch": 1.98, "learning_rate": 3.227660972404731e-07, "loss": 0.5045, "step": 12054 }, { "epoch": 1.98, "learning_rate": 3.2030223390275954e-07, "loss": 0.5715, "step": 12055 }, { "epoch": 1.98, "learning_rate": 3.17838370565046e-07, "loss": 0.2677, "step": 12056 }, { "epoch": 1.98, "learning_rate": 3.1537450722733246e-07, "loss": 0.3002, "step": 12057 }, { "epoch": 1.98, "learning_rate": 3.129106438896189e-07, "loss": 0.3365, "step": 12058 }, { "epoch": 1.98, "learning_rate": 3.1044678055190544e-07, "loss": 0.4175, "step": 12059 }, { "epoch": 1.98, "learning_rate": 3.0798291721419184e-07, "loss": 0.5965, "step": 12060 }, { "epoch": 1.98, "learning_rate": 3.055190538764783e-07, "loss": 1.165, "step": 12061 }, { "epoch": 1.98, "learning_rate": 3.030551905387648e-07, "loss": 0.2562, "step": 12062 }, { "epoch": 1.98, "learning_rate": 3.0059132720105123e-07, "loss": 0.0886, "step": 12063 }, { "epoch": 1.98, "learning_rate": 2.9812746386333774e-07, "loss": 0.509, "step": 12064 }, { "epoch": 1.98, "learning_rate": 2.956636005256242e-07, "loss": 0.9851, "step": 12065 }, { "epoch": 1.98, "learning_rate": 2.931997371879106e-07, "loss": 0.5797, "step": 12066 }, { "epoch": 1.98, "learning_rate": 2.907358738501971e-07, "loss": 0.6058, "step": 12067 }, { "epoch": 1.98, "learning_rate": 2.882720105124836e-07, "loss": 0.7966, "step": 12068 }, { "epoch": 1.98, "learning_rate": 2.8580814717477005e-07, "loss": 0.5568, "step": 12069 }, { "epoch": 1.98, "learning_rate": 2.833442838370565e-07, "loss": 0.3088, "step": 12070 }, { "epoch": 1.98, "learning_rate": 2.8088042049934297e-07, "loss": 0.3998, "step": 12071 }, { "epoch": 1.98, "learning_rate": 2.7841655716162943e-07, "loss": 0.6462, "step": 12072 }, { "epoch": 1.98, "learning_rate": 2.759526938239159e-07, "loss": 0.3396, "step": 12073 }, { "epoch": 1.98, "learning_rate": 2.734888304862024e-07, "loss": 0.4501, "step": 12074 }, { "epoch": 1.98, "learning_rate": 2.7102496714848887e-07, "loss": 0.388, "step": 12075 }, { "epoch": 1.98, "learning_rate": 2.6856110381077527e-07, "loss": 1.0014, "step": 12076 }, { "epoch": 1.98, "learning_rate": 2.660972404730618e-07, "loss": 0.5348, "step": 12077 }, { "epoch": 1.98, "learning_rate": 2.6363337713534825e-07, "loss": 0.6143, "step": 12078 }, { "epoch": 1.98, "learning_rate": 2.6116951379763466e-07, "loss": 0.4113, "step": 12079 }, { "epoch": 1.98, "learning_rate": 2.5870565045992117e-07, "loss": 0.6781, "step": 12080 }, { "epoch": 1.98, "learning_rate": 2.5624178712220763e-07, "loss": 0.223, "step": 12081 }, { "epoch": 1.98, "learning_rate": 2.537779237844941e-07, "loss": 0.4514, "step": 12082 }, { "epoch": 1.98, "learning_rate": 2.5131406044678055e-07, "loss": 0.713, "step": 12083 }, { "epoch": 1.98, "learning_rate": 2.48850197109067e-07, "loss": 0.4298, "step": 12084 }, { "epoch": 1.99, "learning_rate": 2.463863337713535e-07, "loss": 0.2164, "step": 12085 }, { "epoch": 1.99, "learning_rate": 2.4392247043363994e-07, "loss": 0.4692, "step": 12086 }, { "epoch": 1.99, "learning_rate": 2.4145860709592645e-07, "loss": 0.2226, "step": 12087 }, { "epoch": 1.99, "learning_rate": 2.3899474375821286e-07, "loss": 0.5878, "step": 12088 }, { "epoch": 1.99, "learning_rate": 2.3653088042049932e-07, "loss": 0.2879, "step": 12089 }, { "epoch": 1.99, "learning_rate": 2.3406701708278583e-07, "loss": 0.5414, "step": 12090 }, { "epoch": 1.99, "learning_rate": 2.3160315374507227e-07, "loss": 0.2879, "step": 12091 }, { "epoch": 1.99, "learning_rate": 2.2913929040735873e-07, "loss": 0.3527, "step": 12092 }, { "epoch": 1.99, "learning_rate": 2.2667542706964522e-07, "loss": 0.1801, "step": 12093 }, { "epoch": 1.99, "learning_rate": 2.2421156373193168e-07, "loss": 0.4544, "step": 12094 }, { "epoch": 1.99, "learning_rate": 2.2174770039421816e-07, "loss": 0.4068, "step": 12095 }, { "epoch": 1.99, "learning_rate": 2.192838370565046e-07, "loss": 0.6106, "step": 12096 }, { "epoch": 1.99, "learning_rate": 2.1681997371879106e-07, "loss": 0.4287, "step": 12097 }, { "epoch": 1.99, "learning_rate": 2.1435611038107755e-07, "loss": 0.5159, "step": 12098 }, { "epoch": 1.99, "learning_rate": 2.11892247043364e-07, "loss": 0.5101, "step": 12099 }, { "epoch": 1.99, "learning_rate": 2.0942838370565044e-07, "loss": 0.6245, "step": 12100 }, { "epoch": 1.99, "learning_rate": 2.0696452036793693e-07, "loss": 0.4713, "step": 12101 }, { "epoch": 1.99, "learning_rate": 2.045006570302234e-07, "loss": 0.2753, "step": 12102 }, { "epoch": 1.99, "learning_rate": 2.0203679369250988e-07, "loss": 0.1939, "step": 12103 }, { "epoch": 1.99, "learning_rate": 1.9957293035479634e-07, "loss": 0.6843, "step": 12104 }, { "epoch": 1.99, "learning_rate": 1.9710906701708278e-07, "loss": 0.4221, "step": 12105 }, { "epoch": 1.99, "learning_rate": 1.9464520367936926e-07, "loss": 0.7928, "step": 12106 }, { "epoch": 1.99, "learning_rate": 1.9218134034165572e-07, "loss": 0.3525, "step": 12107 }, { "epoch": 1.99, "learning_rate": 1.8971747700394218e-07, "loss": 0.4608, "step": 12108 }, { "epoch": 1.99, "learning_rate": 1.8725361366622865e-07, "loss": 0.1966, "step": 12109 }, { "epoch": 1.99, "learning_rate": 1.847897503285151e-07, "loss": 0.9874, "step": 12110 }, { "epoch": 1.99, "learning_rate": 1.8232588699080157e-07, "loss": 0.9911, "step": 12111 }, { "epoch": 1.99, "learning_rate": 1.7986202365308806e-07, "loss": 0.297, "step": 12112 }, { "epoch": 1.99, "learning_rate": 1.7739816031537452e-07, "loss": 0.3135, "step": 12113 }, { "epoch": 1.99, "learning_rate": 1.7493429697766098e-07, "loss": 0.7257, "step": 12114 }, { "epoch": 1.99, "learning_rate": 1.7247043363994744e-07, "loss": 0.4352, "step": 12115 }, { "epoch": 1.99, "learning_rate": 1.700065703022339e-07, "loss": 0.7363, "step": 12116 }, { "epoch": 1.99, "learning_rate": 1.6754270696452039e-07, "loss": 0.4403, "step": 12117 }, { "epoch": 1.99, "learning_rate": 1.6507884362680685e-07, "loss": 0.529, "step": 12118 }, { "epoch": 1.99, "learning_rate": 1.6261498028909328e-07, "loss": 0.2022, "step": 12119 }, { "epoch": 1.99, "learning_rate": 1.6015111695137977e-07, "loss": 0.8517, "step": 12120 }, { "epoch": 1.99, "learning_rate": 1.5768725361366623e-07, "loss": 0.1358, "step": 12121 }, { "epoch": 1.99, "learning_rate": 1.5522339027595272e-07, "loss": 0.4166, "step": 12122 }, { "epoch": 1.99, "learning_rate": 1.5275952693823915e-07, "loss": 0.7502, "step": 12123 }, { "epoch": 1.99, "learning_rate": 1.5029566360052561e-07, "loss": 0.8278, "step": 12124 }, { "epoch": 1.99, "learning_rate": 1.478318002628121e-07, "loss": 0.4509, "step": 12125 }, { "epoch": 1.99, "learning_rate": 1.4536793692509856e-07, "loss": 0.2972, "step": 12126 }, { "epoch": 1.99, "learning_rate": 1.4290407358738502e-07, "loss": 0.4035, "step": 12127 }, { "epoch": 1.99, "learning_rate": 1.4044021024967148e-07, "loss": 0.9713, "step": 12128 }, { "epoch": 1.99, "learning_rate": 1.3797634691195795e-07, "loss": 0.2643, "step": 12129 }, { "epoch": 1.99, "learning_rate": 1.3551248357424443e-07, "loss": 0.4767, "step": 12130 }, { "epoch": 1.99, "learning_rate": 1.330486202365309e-07, "loss": 0.3886, "step": 12131 }, { "epoch": 1.99, "learning_rate": 1.3058475689881733e-07, "loss": 0.3826, "step": 12132 }, { "epoch": 1.99, "learning_rate": 1.2812089356110382e-07, "loss": 0.5461, "step": 12133 }, { "epoch": 1.99, "learning_rate": 1.2565703022339028e-07, "loss": 0.3932, "step": 12134 }, { "epoch": 1.99, "learning_rate": 1.2319316688567674e-07, "loss": 0.7522, "step": 12135 }, { "epoch": 1.99, "learning_rate": 1.2072930354796323e-07, "loss": 0.6056, "step": 12136 }, { "epoch": 1.99, "learning_rate": 1.1826544021024966e-07, "loss": 0.2487, "step": 12137 }, { "epoch": 1.99, "learning_rate": 1.1580157687253613e-07, "loss": 0.8036, "step": 12138 }, { "epoch": 1.99, "learning_rate": 1.1333771353482261e-07, "loss": 0.5142, "step": 12139 }, { "epoch": 1.99, "learning_rate": 1.1087385019710908e-07, "loss": 0.3644, "step": 12140 }, { "epoch": 1.99, "learning_rate": 1.0840998685939553e-07, "loss": 0.5168, "step": 12141 }, { "epoch": 1.99, "learning_rate": 1.05946123521682e-07, "loss": 0.7016, "step": 12142 }, { "epoch": 1.99, "learning_rate": 1.0348226018396847e-07, "loss": 0.6187, "step": 12143 }, { "epoch": 1.99, "learning_rate": 1.0101839684625494e-07, "loss": 0.6004, "step": 12144 }, { "epoch": 1.99, "learning_rate": 9.855453350854139e-08, "loss": 0.4172, "step": 12145 }, { "epoch": 2.0, "learning_rate": 9.609067017082786e-08, "loss": 0.2648, "step": 12146 }, { "epoch": 2.0, "learning_rate": 9.362680683311432e-08, "loss": 0.7417, "step": 12147 }, { "epoch": 2.0, "learning_rate": 9.116294349540078e-08, "loss": 0.5412, "step": 12148 }, { "epoch": 2.0, "learning_rate": 8.869908015768726e-08, "loss": 0.5789, "step": 12149 }, { "epoch": 2.0, "learning_rate": 8.623521681997372e-08, "loss": 0.5071, "step": 12150 }, { "epoch": 2.0, "learning_rate": 8.377135348226019e-08, "loss": 1.0017, "step": 12151 }, { "epoch": 2.0, "learning_rate": 8.130749014454664e-08, "loss": 0.6139, "step": 12152 }, { "epoch": 2.0, "learning_rate": 7.884362680683312e-08, "loss": 0.1916, "step": 12153 }, { "epoch": 2.0, "learning_rate": 7.637976346911958e-08, "loss": 0.2752, "step": 12154 }, { "epoch": 2.0, "learning_rate": 7.391590013140605e-08, "loss": 0.7283, "step": 12155 }, { "epoch": 2.0, "learning_rate": 7.145203679369251e-08, "loss": 0.3332, "step": 12156 }, { "epoch": 2.0, "learning_rate": 6.898817345597897e-08, "loss": 0.192, "step": 12157 }, { "epoch": 2.0, "learning_rate": 6.652431011826545e-08, "loss": 0.3984, "step": 12158 }, { "epoch": 2.0, "learning_rate": 6.406044678055191e-08, "loss": 1.3413, "step": 12159 }, { "epoch": 2.0, "learning_rate": 6.159658344283837e-08, "loss": 0.3807, "step": 12160 }, { "epoch": 2.0, "learning_rate": 5.913272010512483e-08, "loss": 0.4069, "step": 12161 }, { "epoch": 2.0, "learning_rate": 5.6668856767411304e-08, "loss": 0.3072, "step": 12162 }, { "epoch": 2.0, "learning_rate": 5.4204993429697765e-08, "loss": 0.8477, "step": 12163 }, { "epoch": 2.0, "learning_rate": 5.174113009198423e-08, "loss": 0.6565, "step": 12164 }, { "epoch": 2.0, "learning_rate": 4.9277266754270694e-08, "loss": 0.71, "step": 12165 }, { "epoch": 2.0, "learning_rate": 4.681340341655716e-08, "loss": 0.459, "step": 12166 }, { "epoch": 2.0, "learning_rate": 4.434954007884363e-08, "loss": 0.9748, "step": 12167 }, { "epoch": 2.0, "learning_rate": 4.1885676741130097e-08, "loss": 0.3785, "step": 12168 }, { "epoch": 2.0, "learning_rate": 3.942181340341656e-08, "loss": 0.2419, "step": 12169 }, { "epoch": 2.0, "learning_rate": 3.6957950065703025e-08, "loss": 0.3093, "step": 12170 }, { "epoch": 2.0, "learning_rate": 3.4494086727989486e-08, "loss": 0.3184, "step": 12171 }, { "epoch": 2.0, "learning_rate": 3.2030223390275954e-08, "loss": 0.5114, "step": 12172 }, { "epoch": 2.0, "learning_rate": 2.9566360052562415e-08, "loss": 0.5316, "step": 12173 }, { "epoch": 2.0, "learning_rate": 2.7102496714848883e-08, "loss": 0.4711, "step": 12174 }, { "epoch": 2.0, "learning_rate": 2.4638633377135347e-08, "loss": 0.4962, "step": 12175 }, { "epoch": 2.0, "learning_rate": 2.2174770039421815e-08, "loss": 0.7471, "step": 12176 }, { "epoch": 2.0, "step": 12176, "total_flos": 9.046349068920422e+16, "train_loss": 0.7458668444109848, "train_runtime": 3380.8109, "train_samples_per_second": 57.624, "train_steps_per_second": 3.602 } ], "max_steps": 12176, "num_train_epochs": 2, "total_flos": 9.046349068920422e+16, "trial_name": null, "trial_params": null }