diff --git "a/trainer_state.json" "b/trainer_state.json" new file mode 100644--- /dev/null +++ "b/trainer_state.json" @@ -0,0 +1,93769 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.9998719999999999, + "global_step": 15624, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 2.1321961620469085e-08, + "loss": 0.9579, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 4.264392324093817e-08, + "loss": 0.9153, + "step": 2 + }, + { + "epoch": 0.0, + "learning_rate": 6.396588486140725e-08, + "loss": 0.9019, + "step": 3 + }, + { + "epoch": 0.0, + "learning_rate": 8.528784648187634e-08, + "loss": 0.9238, + "step": 4 + }, + { + "epoch": 0.0, + "learning_rate": 1.0660980810234542e-07, + "loss": 0.9516, + "step": 5 + }, + { + "epoch": 0.0, + "learning_rate": 1.279317697228145e-07, + "loss": 0.9454, + "step": 6 + }, + { + "epoch": 0.0, + "learning_rate": 1.4925373134328358e-07, + "loss": 0.9571, + "step": 7 + }, + { + "epoch": 0.0, + "learning_rate": 1.7057569296375268e-07, + "loss": 0.9188, + "step": 8 + }, + { + "epoch": 0.0, + "learning_rate": 1.918976545842218e-07, + "loss": 0.9378, + "step": 9 + }, + { + "epoch": 0.0, + "learning_rate": 2.1321961620469084e-07, + "loss": 0.9641, + "step": 10 + }, + { + "epoch": 0.0, + "learning_rate": 2.3454157782515995e-07, + "loss": 0.9175, + "step": 11 + }, + { + "epoch": 0.0, + "learning_rate": 2.55863539445629e-07, + "loss": 0.9226, + "step": 12 + }, + { + "epoch": 0.0, + "learning_rate": 2.771855010660981e-07, + "loss": 0.9357, + "step": 13 + }, + { + "epoch": 0.0, + "learning_rate": 2.9850746268656716e-07, + "loss": 0.911, + "step": 14 + }, + { + "epoch": 0.0, + "learning_rate": 3.1982942430703626e-07, + "loss": 0.8362, + "step": 15 + }, + { + "epoch": 0.0, + "learning_rate": 3.4115138592750537e-07, + "loss": 0.8924, + "step": 16 + }, + { + "epoch": 0.0, + "learning_rate": 3.624733475479744e-07, + "loss": 0.8253, + "step": 17 + }, + { + "epoch": 0.0, + "learning_rate": 3.837953091684436e-07, + "loss": 0.8629, + "step": 18 + }, + { + "epoch": 0.0, + "learning_rate": 4.0511727078891263e-07, + "loss": 0.8907, + "step": 19 + }, + { + "epoch": 0.0, + "learning_rate": 4.264392324093817e-07, + "loss": 0.8205, + "step": 20 + }, + { + "epoch": 0.0, + "learning_rate": 4.4776119402985074e-07, + "loss": 0.7541, + "step": 21 + }, + { + "epoch": 0.0, + "learning_rate": 4.690831556503199e-07, + "loss": 0.7853, + "step": 22 + }, + { + "epoch": 0.0, + "learning_rate": 4.904051172707889e-07, + "loss": 0.7299, + "step": 23 + }, + { + "epoch": 0.0, + "learning_rate": 5.11727078891258e-07, + "loss": 0.7106, + "step": 24 + }, + { + "epoch": 0.0, + "learning_rate": 5.33049040511727e-07, + "loss": 0.734, + "step": 25 + }, + { + "epoch": 0.0, + "learning_rate": 5.543710021321962e-07, + "loss": 0.681, + "step": 26 + }, + { + "epoch": 0.0, + "learning_rate": 5.756929637526653e-07, + "loss": 0.7213, + "step": 27 + }, + { + "epoch": 0.0, + "learning_rate": 5.970149253731343e-07, + "loss": 0.7316, + "step": 28 + }, + { + "epoch": 0.0, + "learning_rate": 6.183368869936035e-07, + "loss": 0.646, + "step": 29 + }, + { + "epoch": 0.0, + "learning_rate": 6.396588486140725e-07, + "loss": 0.6185, + "step": 30 + }, + { + "epoch": 0.0, + "learning_rate": 6.609808102345417e-07, + "loss": 0.6537, + "step": 31 + }, + { + "epoch": 0.0, + "learning_rate": 6.823027718550107e-07, + "loss": 0.5987, + "step": 32 + }, + { + "epoch": 0.0, + "learning_rate": 7.036247334754798e-07, + "loss": 0.5934, + "step": 33 + }, + { + "epoch": 0.0, + "learning_rate": 7.249466950959488e-07, + "loss": 0.6085, + "step": 34 + }, + { + "epoch": 0.0, + "learning_rate": 7.462686567164179e-07, + "loss": 0.5872, + "step": 35 + }, + { + "epoch": 0.0, + "learning_rate": 7.675906183368872e-07, + "loss": 0.5959, + "step": 36 + }, + { + "epoch": 0.0, + "learning_rate": 7.889125799573562e-07, + "loss": 0.5975, + "step": 37 + }, + { + "epoch": 0.0, + "learning_rate": 8.102345415778253e-07, + "loss": 0.5893, + "step": 38 + }, + { + "epoch": 0.0, + "learning_rate": 8.315565031982943e-07, + "loss": 0.5752, + "step": 39 + }, + { + "epoch": 0.01, + "learning_rate": 8.528784648187634e-07, + "loss": 0.5879, + "step": 40 + }, + { + "epoch": 0.01, + "learning_rate": 8.742004264392324e-07, + "loss": 0.5712, + "step": 41 + }, + { + "epoch": 0.01, + "learning_rate": 8.955223880597015e-07, + "loss": 0.5651, + "step": 42 + }, + { + "epoch": 0.01, + "learning_rate": 9.168443496801707e-07, + "loss": 0.5519, + "step": 43 + }, + { + "epoch": 0.01, + "learning_rate": 9.381663113006398e-07, + "loss": 0.5608, + "step": 44 + }, + { + "epoch": 0.01, + "learning_rate": 9.594882729211088e-07, + "loss": 0.5261, + "step": 45 + }, + { + "epoch": 0.01, + "learning_rate": 9.808102345415779e-07, + "loss": 0.5142, + "step": 46 + }, + { + "epoch": 0.01, + "learning_rate": 1.002132196162047e-06, + "loss": 0.5413, + "step": 47 + }, + { + "epoch": 0.01, + "learning_rate": 1.023454157782516e-06, + "loss": 0.5467, + "step": 48 + }, + { + "epoch": 0.01, + "learning_rate": 1.044776119402985e-06, + "loss": 0.5377, + "step": 49 + }, + { + "epoch": 0.01, + "learning_rate": 1.066098081023454e-06, + "loss": 0.5056, + "step": 50 + }, + { + "epoch": 0.01, + "learning_rate": 1.0874200426439234e-06, + "loss": 0.5049, + "step": 51 + }, + { + "epoch": 0.01, + "learning_rate": 1.1087420042643924e-06, + "loss": 0.5003, + "step": 52 + }, + { + "epoch": 0.01, + "learning_rate": 1.1300639658848615e-06, + "loss": 0.53, + "step": 53 + }, + { + "epoch": 0.01, + "learning_rate": 1.1513859275053305e-06, + "loss": 0.4893, + "step": 54 + }, + { + "epoch": 0.01, + "learning_rate": 1.1727078891257996e-06, + "loss": 0.4984, + "step": 55 + }, + { + "epoch": 0.01, + "learning_rate": 1.1940298507462686e-06, + "loss": 0.5052, + "step": 56 + }, + { + "epoch": 0.01, + "learning_rate": 1.2153518123667379e-06, + "loss": 0.5221, + "step": 57 + }, + { + "epoch": 0.01, + "learning_rate": 1.236673773987207e-06, + "loss": 0.502, + "step": 58 + }, + { + "epoch": 0.01, + "learning_rate": 1.257995735607676e-06, + "loss": 0.454, + "step": 59 + }, + { + "epoch": 0.01, + "learning_rate": 1.279317697228145e-06, + "loss": 0.493, + "step": 60 + }, + { + "epoch": 0.01, + "learning_rate": 1.300639658848614e-06, + "loss": 0.4776, + "step": 61 + }, + { + "epoch": 0.01, + "learning_rate": 1.3219616204690834e-06, + "loss": 0.5006, + "step": 62 + }, + { + "epoch": 0.01, + "learning_rate": 1.3432835820895524e-06, + "loss": 0.5024, + "step": 63 + }, + { + "epoch": 0.01, + "learning_rate": 1.3646055437100215e-06, + "loss": 0.4957, + "step": 64 + }, + { + "epoch": 0.01, + "learning_rate": 1.3859275053304905e-06, + "loss": 0.4682, + "step": 65 + }, + { + "epoch": 0.01, + "learning_rate": 1.4072494669509596e-06, + "loss": 0.4848, + "step": 66 + }, + { + "epoch": 0.01, + "learning_rate": 1.4285714285714286e-06, + "loss": 0.4931, + "step": 67 + }, + { + "epoch": 0.01, + "learning_rate": 1.4498933901918977e-06, + "loss": 0.4889, + "step": 68 + }, + { + "epoch": 0.01, + "learning_rate": 1.4712153518123667e-06, + "loss": 0.4352, + "step": 69 + }, + { + "epoch": 0.01, + "learning_rate": 1.4925373134328358e-06, + "loss": 0.4729, + "step": 70 + }, + { + "epoch": 0.01, + "learning_rate": 1.5138592750533053e-06, + "loss": 0.4655, + "step": 71 + }, + { + "epoch": 0.01, + "learning_rate": 1.5351812366737743e-06, + "loss": 0.4911, + "step": 72 + }, + { + "epoch": 0.01, + "learning_rate": 1.5565031982942434e-06, + "loss": 0.4477, + "step": 73 + }, + { + "epoch": 0.01, + "learning_rate": 1.5778251599147124e-06, + "loss": 0.4714, + "step": 74 + }, + { + "epoch": 0.01, + "learning_rate": 1.5991471215351815e-06, + "loss": 0.4765, + "step": 75 + }, + { + "epoch": 0.01, + "learning_rate": 1.6204690831556505e-06, + "loss": 0.5144, + "step": 76 + }, + { + "epoch": 0.01, + "learning_rate": 1.6417910447761196e-06, + "loss": 0.4435, + "step": 77 + }, + { + "epoch": 0.01, + "learning_rate": 1.6631130063965886e-06, + "loss": 0.4335, + "step": 78 + }, + { + "epoch": 0.01, + "learning_rate": 1.6844349680170577e-06, + "loss": 0.4613, + "step": 79 + }, + { + "epoch": 0.01, + "learning_rate": 1.7057569296375267e-06, + "loss": 0.4532, + "step": 80 + }, + { + "epoch": 0.01, + "learning_rate": 1.7270788912579958e-06, + "loss": 0.4377, + "step": 81 + }, + { + "epoch": 0.01, + "learning_rate": 1.7484008528784648e-06, + "loss": 0.454, + "step": 82 + }, + { + "epoch": 0.01, + "learning_rate": 1.7697228144989339e-06, + "loss": 0.4564, + "step": 83 + }, + { + "epoch": 0.01, + "learning_rate": 1.791044776119403e-06, + "loss": 0.4547, + "step": 84 + }, + { + "epoch": 0.01, + "learning_rate": 1.812366737739872e-06, + "loss": 0.4332, + "step": 85 + }, + { + "epoch": 0.01, + "learning_rate": 1.8336886993603415e-06, + "loss": 0.4575, + "step": 86 + }, + { + "epoch": 0.01, + "learning_rate": 1.8550106609808105e-06, + "loss": 0.4745, + "step": 87 + }, + { + "epoch": 0.01, + "learning_rate": 1.8763326226012796e-06, + "loss": 0.4592, + "step": 88 + }, + { + "epoch": 0.01, + "learning_rate": 1.8976545842217486e-06, + "loss": 0.4485, + "step": 89 + }, + { + "epoch": 0.01, + "learning_rate": 1.9189765458422177e-06, + "loss": 0.4288, + "step": 90 + }, + { + "epoch": 0.01, + "learning_rate": 1.9402985074626867e-06, + "loss": 0.4197, + "step": 91 + }, + { + "epoch": 0.01, + "learning_rate": 1.9616204690831558e-06, + "loss": 0.4308, + "step": 92 + }, + { + "epoch": 0.01, + "learning_rate": 1.982942430703625e-06, + "loss": 0.4645, + "step": 93 + }, + { + "epoch": 0.01, + "learning_rate": 2.004264392324094e-06, + "loss": 0.4131, + "step": 94 + }, + { + "epoch": 0.01, + "learning_rate": 2.025586353944563e-06, + "loss": 0.4443, + "step": 95 + }, + { + "epoch": 0.01, + "learning_rate": 2.046908315565032e-06, + "loss": 0.4575, + "step": 96 + }, + { + "epoch": 0.01, + "learning_rate": 2.068230277185501e-06, + "loss": 0.4311, + "step": 97 + }, + { + "epoch": 0.01, + "learning_rate": 2.08955223880597e-06, + "loss": 0.4042, + "step": 98 + }, + { + "epoch": 0.01, + "learning_rate": 2.110874200426439e-06, + "loss": 0.4697, + "step": 99 + }, + { + "epoch": 0.01, + "learning_rate": 2.132196162046908e-06, + "loss": 0.4136, + "step": 100 + }, + { + "epoch": 0.01, + "learning_rate": 2.1535181236673773e-06, + "loss": 0.4596, + "step": 101 + }, + { + "epoch": 0.01, + "learning_rate": 2.1748400852878467e-06, + "loss": 0.4396, + "step": 102 + }, + { + "epoch": 0.01, + "learning_rate": 2.1961620469083158e-06, + "loss": 0.4551, + "step": 103 + }, + { + "epoch": 0.01, + "learning_rate": 2.217484008528785e-06, + "loss": 0.4316, + "step": 104 + }, + { + "epoch": 0.01, + "learning_rate": 2.238805970149254e-06, + "loss": 0.4288, + "step": 105 + }, + { + "epoch": 0.01, + "learning_rate": 2.260127931769723e-06, + "loss": 0.4647, + "step": 106 + }, + { + "epoch": 0.01, + "learning_rate": 2.281449893390192e-06, + "loss": 0.4057, + "step": 107 + }, + { + "epoch": 0.01, + "learning_rate": 2.302771855010661e-06, + "loss": 0.4262, + "step": 108 + }, + { + "epoch": 0.01, + "learning_rate": 2.32409381663113e-06, + "loss": 0.4213, + "step": 109 + }, + { + "epoch": 0.01, + "learning_rate": 2.345415778251599e-06, + "loss": 0.4292, + "step": 110 + }, + { + "epoch": 0.01, + "learning_rate": 2.366737739872068e-06, + "loss": 0.3801, + "step": 111 + }, + { + "epoch": 0.01, + "learning_rate": 2.3880597014925373e-06, + "loss": 0.4663, + "step": 112 + }, + { + "epoch": 0.01, + "learning_rate": 2.4093816631130067e-06, + "loss": 0.4305, + "step": 113 + }, + { + "epoch": 0.01, + "learning_rate": 2.4307036247334758e-06, + "loss": 0.4609, + "step": 114 + }, + { + "epoch": 0.01, + "learning_rate": 2.452025586353945e-06, + "loss": 0.4019, + "step": 115 + }, + { + "epoch": 0.01, + "learning_rate": 2.473347547974414e-06, + "loss": 0.4452, + "step": 116 + }, + { + "epoch": 0.01, + "learning_rate": 2.494669509594883e-06, + "loss": 0.4427, + "step": 117 + }, + { + "epoch": 0.02, + "learning_rate": 2.515991471215352e-06, + "loss": 0.3908, + "step": 118 + }, + { + "epoch": 0.02, + "learning_rate": 2.537313432835821e-06, + "loss": 0.4232, + "step": 119 + }, + { + "epoch": 0.02, + "learning_rate": 2.55863539445629e-06, + "loss": 0.4406, + "step": 120 + }, + { + "epoch": 0.02, + "learning_rate": 2.579957356076759e-06, + "loss": 0.4545, + "step": 121 + }, + { + "epoch": 0.02, + "learning_rate": 2.601279317697228e-06, + "loss": 0.4179, + "step": 122 + }, + { + "epoch": 0.02, + "learning_rate": 2.6226012793176977e-06, + "loss": 0.4303, + "step": 123 + }, + { + "epoch": 0.02, + "learning_rate": 2.6439232409381667e-06, + "loss": 0.4353, + "step": 124 + }, + { + "epoch": 0.02, + "learning_rate": 2.6652452025586358e-06, + "loss": 0.417, + "step": 125 + }, + { + "epoch": 0.02, + "learning_rate": 2.686567164179105e-06, + "loss": 0.4206, + "step": 126 + }, + { + "epoch": 0.02, + "learning_rate": 2.707889125799574e-06, + "loss": 0.4321, + "step": 127 + }, + { + "epoch": 0.02, + "learning_rate": 2.729211087420043e-06, + "loss": 0.4087, + "step": 128 + }, + { + "epoch": 0.02, + "learning_rate": 2.750533049040512e-06, + "loss": 0.4423, + "step": 129 + }, + { + "epoch": 0.02, + "learning_rate": 2.771855010660981e-06, + "loss": 0.4206, + "step": 130 + }, + { + "epoch": 0.02, + "learning_rate": 2.79317697228145e-06, + "loss": 0.4291, + "step": 131 + }, + { + "epoch": 0.02, + "learning_rate": 2.814498933901919e-06, + "loss": 0.3819, + "step": 132 + }, + { + "epoch": 0.02, + "learning_rate": 2.835820895522388e-06, + "loss": 0.3929, + "step": 133 + }, + { + "epoch": 0.02, + "learning_rate": 2.8571428571428573e-06, + "loss": 0.4067, + "step": 134 + }, + { + "epoch": 0.02, + "learning_rate": 2.8784648187633263e-06, + "loss": 0.4505, + "step": 135 + }, + { + "epoch": 0.02, + "learning_rate": 2.8997867803837954e-06, + "loss": 0.3913, + "step": 136 + }, + { + "epoch": 0.02, + "learning_rate": 2.9211087420042644e-06, + "loss": 0.3981, + "step": 137 + }, + { + "epoch": 0.02, + "learning_rate": 2.9424307036247335e-06, + "loss": 0.3925, + "step": 138 + }, + { + "epoch": 0.02, + "learning_rate": 2.9637526652452025e-06, + "loss": 0.4227, + "step": 139 + }, + { + "epoch": 0.02, + "learning_rate": 2.9850746268656716e-06, + "loss": 0.4289, + "step": 140 + }, + { + "epoch": 0.02, + "learning_rate": 3.006396588486141e-06, + "loss": 0.3937, + "step": 141 + }, + { + "epoch": 0.02, + "learning_rate": 3.0277185501066105e-06, + "loss": 0.4205, + "step": 142 + }, + { + "epoch": 0.02, + "learning_rate": 3.0490405117270796e-06, + "loss": 0.4288, + "step": 143 + }, + { + "epoch": 0.02, + "learning_rate": 3.0703624733475486e-06, + "loss": 0.416, + "step": 144 + }, + { + "epoch": 0.02, + "learning_rate": 3.0916844349680177e-06, + "loss": 0.4174, + "step": 145 + }, + { + "epoch": 0.02, + "learning_rate": 3.1130063965884867e-06, + "loss": 0.4385, + "step": 146 + }, + { + "epoch": 0.02, + "learning_rate": 3.1343283582089558e-06, + "loss": 0.4069, + "step": 147 + }, + { + "epoch": 0.02, + "learning_rate": 3.155650319829425e-06, + "loss": 0.4339, + "step": 148 + }, + { + "epoch": 0.02, + "learning_rate": 3.176972281449894e-06, + "loss": 0.4128, + "step": 149 + }, + { + "epoch": 0.02, + "learning_rate": 3.198294243070363e-06, + "loss": 0.4236, + "step": 150 + }, + { + "epoch": 0.02, + "learning_rate": 3.219616204690832e-06, + "loss": 0.3713, + "step": 151 + }, + { + "epoch": 0.02, + "learning_rate": 3.240938166311301e-06, + "loss": 0.3733, + "step": 152 + }, + { + "epoch": 0.02, + "learning_rate": 3.26226012793177e-06, + "loss": 0.3969, + "step": 153 + }, + { + "epoch": 0.02, + "learning_rate": 3.283582089552239e-06, + "loss": 0.4126, + "step": 154 + }, + { + "epoch": 0.02, + "learning_rate": 3.304904051172708e-06, + "loss": 0.4088, + "step": 155 + }, + { + "epoch": 0.02, + "learning_rate": 3.3262260127931773e-06, + "loss": 0.4054, + "step": 156 + }, + { + "epoch": 0.02, + "learning_rate": 3.3475479744136463e-06, + "loss": 0.4309, + "step": 157 + }, + { + "epoch": 0.02, + "learning_rate": 3.3688699360341154e-06, + "loss": 0.3917, + "step": 158 + }, + { + "epoch": 0.02, + "learning_rate": 3.3901918976545844e-06, + "loss": 0.3765, + "step": 159 + }, + { + "epoch": 0.02, + "learning_rate": 3.4115138592750535e-06, + "loss": 0.396, + "step": 160 + }, + { + "epoch": 0.02, + "learning_rate": 3.4328358208955225e-06, + "loss": 0.3946, + "step": 161 + }, + { + "epoch": 0.02, + "learning_rate": 3.4541577825159916e-06, + "loss": 0.4101, + "step": 162 + }, + { + "epoch": 0.02, + "learning_rate": 3.4754797441364606e-06, + "loss": 0.4447, + "step": 163 + }, + { + "epoch": 0.02, + "learning_rate": 3.4968017057569297e-06, + "loss": 0.3901, + "step": 164 + }, + { + "epoch": 0.02, + "learning_rate": 3.5181236673773987e-06, + "loss": 0.4199, + "step": 165 + }, + { + "epoch": 0.02, + "learning_rate": 3.5394456289978678e-06, + "loss": 0.4078, + "step": 166 + }, + { + "epoch": 0.02, + "learning_rate": 3.560767590618337e-06, + "loss": 0.3695, + "step": 167 + }, + { + "epoch": 0.02, + "learning_rate": 3.582089552238806e-06, + "loss": 0.3686, + "step": 168 + }, + { + "epoch": 0.02, + "learning_rate": 3.603411513859275e-06, + "loss": 0.4186, + "step": 169 + }, + { + "epoch": 0.02, + "learning_rate": 3.624733475479744e-06, + "loss": 0.4185, + "step": 170 + }, + { + "epoch": 0.02, + "learning_rate": 3.6460554371002135e-06, + "loss": 0.4133, + "step": 171 + }, + { + "epoch": 0.02, + "learning_rate": 3.667377398720683e-06, + "loss": 0.3904, + "step": 172 + }, + { + "epoch": 0.02, + "learning_rate": 3.688699360341152e-06, + "loss": 0.4213, + "step": 173 + }, + { + "epoch": 0.02, + "learning_rate": 3.710021321961621e-06, + "loss": 0.381, + "step": 174 + }, + { + "epoch": 0.02, + "learning_rate": 3.73134328358209e-06, + "loss": 0.3995, + "step": 175 + }, + { + "epoch": 0.02, + "learning_rate": 3.752665245202559e-06, + "loss": 0.414, + "step": 176 + }, + { + "epoch": 0.02, + "learning_rate": 3.773987206823028e-06, + "loss": 0.4395, + "step": 177 + }, + { + "epoch": 0.02, + "learning_rate": 3.7953091684434973e-06, + "loss": 0.3714, + "step": 178 + }, + { + "epoch": 0.02, + "learning_rate": 3.816631130063966e-06, + "loss": 0.3812, + "step": 179 + }, + { + "epoch": 0.02, + "learning_rate": 3.837953091684435e-06, + "loss": 0.3923, + "step": 180 + }, + { + "epoch": 0.02, + "learning_rate": 3.859275053304904e-06, + "loss": 0.3847, + "step": 181 + }, + { + "epoch": 0.02, + "learning_rate": 3.8805970149253735e-06, + "loss": 0.3801, + "step": 182 + }, + { + "epoch": 0.02, + "learning_rate": 3.9019189765458425e-06, + "loss": 0.4131, + "step": 183 + }, + { + "epoch": 0.02, + "learning_rate": 3.9232409381663116e-06, + "loss": 0.3845, + "step": 184 + }, + { + "epoch": 0.02, + "learning_rate": 3.944562899786781e-06, + "loss": 0.4071, + "step": 185 + }, + { + "epoch": 0.02, + "learning_rate": 3.96588486140725e-06, + "loss": 0.3851, + "step": 186 + }, + { + "epoch": 0.02, + "learning_rate": 3.987206823027719e-06, + "loss": 0.3838, + "step": 187 + }, + { + "epoch": 0.02, + "learning_rate": 4.008528784648188e-06, + "loss": 0.3863, + "step": 188 + }, + { + "epoch": 0.02, + "learning_rate": 4.029850746268657e-06, + "loss": 0.3918, + "step": 189 + }, + { + "epoch": 0.02, + "learning_rate": 4.051172707889126e-06, + "loss": 0.3973, + "step": 190 + }, + { + "epoch": 0.02, + "learning_rate": 4.072494669509595e-06, + "loss": 0.4008, + "step": 191 + }, + { + "epoch": 0.02, + "learning_rate": 4.093816631130064e-06, + "loss": 0.3585, + "step": 192 + }, + { + "epoch": 0.02, + "learning_rate": 4.115138592750533e-06, + "loss": 0.4154, + "step": 193 + }, + { + "epoch": 0.02, + "learning_rate": 4.136460554371002e-06, + "loss": 0.3975, + "step": 194 + }, + { + "epoch": 0.02, + "learning_rate": 4.157782515991471e-06, + "loss": 0.3878, + "step": 195 + }, + { + "epoch": 0.03, + "learning_rate": 4.17910447761194e-06, + "loss": 0.3798, + "step": 196 + }, + { + "epoch": 0.03, + "learning_rate": 4.200426439232409e-06, + "loss": 0.3997, + "step": 197 + }, + { + "epoch": 0.03, + "learning_rate": 4.221748400852878e-06, + "loss": 0.376, + "step": 198 + }, + { + "epoch": 0.03, + "learning_rate": 4.243070362473347e-06, + "loss": 0.4091, + "step": 199 + }, + { + "epoch": 0.03, + "learning_rate": 4.264392324093816e-06, + "loss": 0.4037, + "step": 200 + }, + { + "epoch": 0.03, + "learning_rate": 4.2857142857142855e-06, + "loss": 0.4193, + "step": 201 + }, + { + "epoch": 0.03, + "learning_rate": 4.3070362473347545e-06, + "loss": 0.4275, + "step": 202 + }, + { + "epoch": 0.03, + "learning_rate": 4.3283582089552236e-06, + "loss": 0.3926, + "step": 203 + }, + { + "epoch": 0.03, + "learning_rate": 4.3496801705756935e-06, + "loss": 0.4082, + "step": 204 + }, + { + "epoch": 0.03, + "learning_rate": 4.3710021321961625e-06, + "loss": 0.4107, + "step": 205 + }, + { + "epoch": 0.03, + "learning_rate": 4.3923240938166316e-06, + "loss": 0.3861, + "step": 206 + }, + { + "epoch": 0.03, + "learning_rate": 4.413646055437101e-06, + "loss": 0.4189, + "step": 207 + }, + { + "epoch": 0.03, + "learning_rate": 4.43496801705757e-06, + "loss": 0.4051, + "step": 208 + }, + { + "epoch": 0.03, + "learning_rate": 4.456289978678039e-06, + "loss": 0.3732, + "step": 209 + }, + { + "epoch": 0.03, + "learning_rate": 4.477611940298508e-06, + "loss": 0.4, + "step": 210 + }, + { + "epoch": 0.03, + "learning_rate": 4.498933901918977e-06, + "loss": 0.3918, + "step": 211 + }, + { + "epoch": 0.03, + "learning_rate": 4.520255863539446e-06, + "loss": 0.3989, + "step": 212 + }, + { + "epoch": 0.03, + "learning_rate": 4.541577825159915e-06, + "loss": 0.3918, + "step": 213 + }, + { + "epoch": 0.03, + "learning_rate": 4.562899786780384e-06, + "loss": 0.3904, + "step": 214 + }, + { + "epoch": 0.03, + "learning_rate": 4.584221748400853e-06, + "loss": 0.3992, + "step": 215 + }, + { + "epoch": 0.03, + "learning_rate": 4.605543710021322e-06, + "loss": 0.4153, + "step": 216 + }, + { + "epoch": 0.03, + "learning_rate": 4.626865671641791e-06, + "loss": 0.3832, + "step": 217 + }, + { + "epoch": 0.03, + "learning_rate": 4.64818763326226e-06, + "loss": 0.394, + "step": 218 + }, + { + "epoch": 0.03, + "learning_rate": 4.669509594882729e-06, + "loss": 0.3792, + "step": 219 + }, + { + "epoch": 0.03, + "learning_rate": 4.690831556503198e-06, + "loss": 0.4068, + "step": 220 + }, + { + "epoch": 0.03, + "learning_rate": 4.712153518123667e-06, + "loss": 0.4062, + "step": 221 + }, + { + "epoch": 0.03, + "learning_rate": 4.733475479744136e-06, + "loss": 0.39, + "step": 222 + }, + { + "epoch": 0.03, + "learning_rate": 4.7547974413646055e-06, + "loss": 0.4036, + "step": 223 + }, + { + "epoch": 0.03, + "learning_rate": 4.7761194029850745e-06, + "loss": 0.389, + "step": 224 + }, + { + "epoch": 0.03, + "learning_rate": 4.797441364605544e-06, + "loss": 0.3869, + "step": 225 + }, + { + "epoch": 0.03, + "learning_rate": 4.8187633262260135e-06, + "loss": 0.3963, + "step": 226 + }, + { + "epoch": 0.03, + "learning_rate": 4.8400852878464825e-06, + "loss": 0.3823, + "step": 227 + }, + { + "epoch": 0.03, + "learning_rate": 4.8614072494669516e-06, + "loss": 0.3884, + "step": 228 + }, + { + "epoch": 0.03, + "learning_rate": 4.882729211087421e-06, + "loss": 0.3696, + "step": 229 + }, + { + "epoch": 0.03, + "learning_rate": 4.90405117270789e-06, + "loss": 0.3891, + "step": 230 + }, + { + "epoch": 0.03, + "learning_rate": 4.925373134328359e-06, + "loss": 0.4139, + "step": 231 + }, + { + "epoch": 0.03, + "learning_rate": 4.946695095948828e-06, + "loss": 0.3938, + "step": 232 + }, + { + "epoch": 0.03, + "learning_rate": 4.968017057569297e-06, + "loss": 0.4014, + "step": 233 + }, + { + "epoch": 0.03, + "learning_rate": 4.989339019189766e-06, + "loss": 0.407, + "step": 234 + }, + { + "epoch": 0.03, + "learning_rate": 5.010660980810235e-06, + "loss": 0.3843, + "step": 235 + }, + { + "epoch": 0.03, + "learning_rate": 5.031982942430704e-06, + "loss": 0.3758, + "step": 236 + }, + { + "epoch": 0.03, + "learning_rate": 5.053304904051173e-06, + "loss": 0.3985, + "step": 237 + }, + { + "epoch": 0.03, + "learning_rate": 5.074626865671642e-06, + "loss": 0.4069, + "step": 238 + }, + { + "epoch": 0.03, + "learning_rate": 5.095948827292111e-06, + "loss": 0.4053, + "step": 239 + }, + { + "epoch": 0.03, + "learning_rate": 5.11727078891258e-06, + "loss": 0.409, + "step": 240 + }, + { + "epoch": 0.03, + "learning_rate": 5.138592750533049e-06, + "loss": 0.3897, + "step": 241 + }, + { + "epoch": 0.03, + "learning_rate": 5.159914712153518e-06, + "loss": 0.4225, + "step": 242 + }, + { + "epoch": 0.03, + "learning_rate": 5.181236673773987e-06, + "loss": 0.4408, + "step": 243 + }, + { + "epoch": 0.03, + "learning_rate": 5.202558635394456e-06, + "loss": 0.4143, + "step": 244 + }, + { + "epoch": 0.03, + "learning_rate": 5.2238805970149255e-06, + "loss": 0.3881, + "step": 245 + }, + { + "epoch": 0.03, + "learning_rate": 5.245202558635395e-06, + "loss": 0.4101, + "step": 246 + }, + { + "epoch": 0.03, + "learning_rate": 5.2665245202558636e-06, + "loss": 0.3985, + "step": 247 + }, + { + "epoch": 0.03, + "learning_rate": 5.2878464818763335e-06, + "loss": 0.4083, + "step": 248 + }, + { + "epoch": 0.03, + "learning_rate": 5.309168443496802e-06, + "loss": 0.3884, + "step": 249 + }, + { + "epoch": 0.03, + "learning_rate": 5.3304904051172716e-06, + "loss": 0.3722, + "step": 250 + }, + { + "epoch": 0.03, + "learning_rate": 5.351812366737741e-06, + "loss": 0.4148, + "step": 251 + }, + { + "epoch": 0.03, + "learning_rate": 5.37313432835821e-06, + "loss": 0.3899, + "step": 252 + }, + { + "epoch": 0.03, + "learning_rate": 5.394456289978679e-06, + "loss": 0.406, + "step": 253 + }, + { + "epoch": 0.03, + "learning_rate": 5.415778251599148e-06, + "loss": 0.4077, + "step": 254 + }, + { + "epoch": 0.03, + "learning_rate": 5.437100213219617e-06, + "loss": 0.4215, + "step": 255 + }, + { + "epoch": 0.03, + "learning_rate": 5.458422174840086e-06, + "loss": 0.3741, + "step": 256 + }, + { + "epoch": 0.03, + "learning_rate": 5.479744136460555e-06, + "loss": 0.3908, + "step": 257 + }, + { + "epoch": 0.03, + "learning_rate": 5.501066098081024e-06, + "loss": 0.3579, + "step": 258 + }, + { + "epoch": 0.03, + "learning_rate": 5.522388059701493e-06, + "loss": 0.3994, + "step": 259 + }, + { + "epoch": 0.03, + "learning_rate": 5.543710021321962e-06, + "loss": 0.3768, + "step": 260 + }, + { + "epoch": 0.03, + "learning_rate": 5.565031982942431e-06, + "loss": 0.3793, + "step": 261 + }, + { + "epoch": 0.03, + "learning_rate": 5.5863539445629e-06, + "loss": 0.3667, + "step": 262 + }, + { + "epoch": 0.03, + "learning_rate": 5.607675906183369e-06, + "loss": 0.3918, + "step": 263 + }, + { + "epoch": 0.03, + "learning_rate": 5.628997867803838e-06, + "loss": 0.3758, + "step": 264 + }, + { + "epoch": 0.03, + "learning_rate": 5.650319829424308e-06, + "loss": 0.4226, + "step": 265 + }, + { + "epoch": 0.03, + "learning_rate": 5.671641791044776e-06, + "loss": 0.3825, + "step": 266 + }, + { + "epoch": 0.03, + "learning_rate": 5.692963752665246e-06, + "loss": 0.3952, + "step": 267 + }, + { + "epoch": 0.03, + "learning_rate": 5.7142857142857145e-06, + "loss": 0.3672, + "step": 268 + }, + { + "epoch": 0.03, + "learning_rate": 5.735607675906184e-06, + "loss": 0.4001, + "step": 269 + }, + { + "epoch": 0.03, + "learning_rate": 5.756929637526653e-06, + "loss": 0.4058, + "step": 270 + }, + { + "epoch": 0.03, + "learning_rate": 5.7782515991471225e-06, + "loss": 0.3972, + "step": 271 + }, + { + "epoch": 0.03, + "learning_rate": 5.799573560767591e-06, + "loss": 0.391, + "step": 272 + }, + { + "epoch": 0.03, + "learning_rate": 5.820895522388061e-06, + "loss": 0.4164, + "step": 273 + }, + { + "epoch": 0.04, + "learning_rate": 5.842217484008529e-06, + "loss": 0.3616, + "step": 274 + }, + { + "epoch": 0.04, + "learning_rate": 5.863539445628999e-06, + "loss": 0.378, + "step": 275 + }, + { + "epoch": 0.04, + "learning_rate": 5.884861407249467e-06, + "loss": 0.4287, + "step": 276 + }, + { + "epoch": 0.04, + "learning_rate": 5.906183368869937e-06, + "loss": 0.3672, + "step": 277 + }, + { + "epoch": 0.04, + "learning_rate": 5.927505330490405e-06, + "loss": 0.3965, + "step": 278 + }, + { + "epoch": 0.04, + "learning_rate": 5.948827292110875e-06, + "loss": 0.3878, + "step": 279 + }, + { + "epoch": 0.04, + "learning_rate": 5.970149253731343e-06, + "loss": 0.3712, + "step": 280 + }, + { + "epoch": 0.04, + "learning_rate": 5.991471215351813e-06, + "loss": 0.3932, + "step": 281 + }, + { + "epoch": 0.04, + "learning_rate": 6.012793176972282e-06, + "loss": 0.3524, + "step": 282 + }, + { + "epoch": 0.04, + "learning_rate": 6.034115138592751e-06, + "loss": 0.3892, + "step": 283 + }, + { + "epoch": 0.04, + "learning_rate": 6.055437100213221e-06, + "loss": 0.3743, + "step": 284 + }, + { + "epoch": 0.04, + "learning_rate": 6.076759061833689e-06, + "loss": 0.3715, + "step": 285 + }, + { + "epoch": 0.04, + "learning_rate": 6.098081023454159e-06, + "loss": 0.3795, + "step": 286 + }, + { + "epoch": 0.04, + "learning_rate": 6.119402985074627e-06, + "loss": 0.3848, + "step": 287 + }, + { + "epoch": 0.04, + "learning_rate": 6.140724946695097e-06, + "loss": 0.3691, + "step": 288 + }, + { + "epoch": 0.04, + "learning_rate": 6.1620469083155655e-06, + "loss": 0.3815, + "step": 289 + }, + { + "epoch": 0.04, + "learning_rate": 6.183368869936035e-06, + "loss": 0.3849, + "step": 290 + }, + { + "epoch": 0.04, + "learning_rate": 6.2046908315565036e-06, + "loss": 0.4113, + "step": 291 + }, + { + "epoch": 0.04, + "learning_rate": 6.2260127931769735e-06, + "loss": 0.3863, + "step": 292 + }, + { + "epoch": 0.04, + "learning_rate": 6.247334754797442e-06, + "loss": 0.3463, + "step": 293 + }, + { + "epoch": 0.04, + "learning_rate": 6.2686567164179116e-06, + "loss": 0.3824, + "step": 294 + }, + { + "epoch": 0.04, + "learning_rate": 6.28997867803838e-06, + "loss": 0.3812, + "step": 295 + }, + { + "epoch": 0.04, + "learning_rate": 6.31130063965885e-06, + "loss": 0.4101, + "step": 296 + }, + { + "epoch": 0.04, + "learning_rate": 6.332622601279318e-06, + "loss": 0.3953, + "step": 297 + }, + { + "epoch": 0.04, + "learning_rate": 6.353944562899788e-06, + "loss": 0.3804, + "step": 298 + }, + { + "epoch": 0.04, + "learning_rate": 6.375266524520256e-06, + "loss": 0.433, + "step": 299 + }, + { + "epoch": 0.04, + "learning_rate": 6.396588486140726e-06, + "loss": 0.402, + "step": 300 + }, + { + "epoch": 0.04, + "learning_rate": 6.417910447761194e-06, + "loss": 0.3633, + "step": 301 + }, + { + "epoch": 0.04, + "learning_rate": 6.439232409381664e-06, + "loss": 0.3886, + "step": 302 + }, + { + "epoch": 0.04, + "learning_rate": 6.460554371002132e-06, + "loss": 0.3807, + "step": 303 + }, + { + "epoch": 0.04, + "learning_rate": 6.481876332622602e-06, + "loss": 0.374, + "step": 304 + }, + { + "epoch": 0.04, + "learning_rate": 6.50319829424307e-06, + "loss": 0.3732, + "step": 305 + }, + { + "epoch": 0.04, + "learning_rate": 6.52452025586354e-06, + "loss": 0.3703, + "step": 306 + }, + { + "epoch": 0.04, + "learning_rate": 6.545842217484008e-06, + "loss": 0.4032, + "step": 307 + }, + { + "epoch": 0.04, + "learning_rate": 6.567164179104478e-06, + "loss": 0.4105, + "step": 308 + }, + { + "epoch": 0.04, + "learning_rate": 6.5884861407249465e-06, + "loss": 0.4153, + "step": 309 + }, + { + "epoch": 0.04, + "learning_rate": 6.609808102345416e-06, + "loss": 0.4176, + "step": 310 + }, + { + "epoch": 0.04, + "learning_rate": 6.631130063965885e-06, + "loss": 0.3826, + "step": 311 + }, + { + "epoch": 0.04, + "learning_rate": 6.6524520255863545e-06, + "loss": 0.3816, + "step": 312 + }, + { + "epoch": 0.04, + "learning_rate": 6.673773987206824e-06, + "loss": 0.3886, + "step": 313 + }, + { + "epoch": 0.04, + "learning_rate": 6.695095948827293e-06, + "loss": 0.3618, + "step": 314 + }, + { + "epoch": 0.04, + "learning_rate": 6.7164179104477625e-06, + "loss": 0.3733, + "step": 315 + }, + { + "epoch": 0.04, + "learning_rate": 6.737739872068231e-06, + "loss": 0.3943, + "step": 316 + }, + { + "epoch": 0.04, + "learning_rate": 6.759061833688701e-06, + "loss": 0.3796, + "step": 317 + }, + { + "epoch": 0.04, + "learning_rate": 6.780383795309169e-06, + "loss": 0.3716, + "step": 318 + }, + { + "epoch": 0.04, + "learning_rate": 6.801705756929639e-06, + "loss": 0.4077, + "step": 319 + }, + { + "epoch": 0.04, + "learning_rate": 6.823027718550107e-06, + "loss": 0.3894, + "step": 320 + }, + { + "epoch": 0.04, + "learning_rate": 6.844349680170577e-06, + "loss": 0.3966, + "step": 321 + }, + { + "epoch": 0.04, + "learning_rate": 6.865671641791045e-06, + "loss": 0.4282, + "step": 322 + }, + { + "epoch": 0.04, + "learning_rate": 6.886993603411515e-06, + "loss": 0.3981, + "step": 323 + }, + { + "epoch": 0.04, + "learning_rate": 6.908315565031983e-06, + "loss": 0.3733, + "step": 324 + }, + { + "epoch": 0.04, + "learning_rate": 6.929637526652453e-06, + "loss": 0.3731, + "step": 325 + }, + { + "epoch": 0.04, + "learning_rate": 6.950959488272921e-06, + "loss": 0.421, + "step": 326 + }, + { + "epoch": 0.04, + "learning_rate": 6.972281449893391e-06, + "loss": 0.3975, + "step": 327 + }, + { + "epoch": 0.04, + "learning_rate": 6.993603411513859e-06, + "loss": 0.3688, + "step": 328 + }, + { + "epoch": 0.04, + "learning_rate": 7.014925373134329e-06, + "loss": 0.3964, + "step": 329 + }, + { + "epoch": 0.04, + "learning_rate": 7.0362473347547975e-06, + "loss": 0.3817, + "step": 330 + }, + { + "epoch": 0.04, + "learning_rate": 7.057569296375267e-06, + "loss": 0.3801, + "step": 331 + }, + { + "epoch": 0.04, + "learning_rate": 7.0788912579957356e-06, + "loss": 0.3779, + "step": 332 + }, + { + "epoch": 0.04, + "learning_rate": 7.1002132196162055e-06, + "loss": 0.3445, + "step": 333 + }, + { + "epoch": 0.04, + "learning_rate": 7.121535181236674e-06, + "loss": 0.375, + "step": 334 + }, + { + "epoch": 0.04, + "learning_rate": 7.1428571428571436e-06, + "loss": 0.3861, + "step": 335 + }, + { + "epoch": 0.04, + "learning_rate": 7.164179104477612e-06, + "loss": 0.4023, + "step": 336 + }, + { + "epoch": 0.04, + "learning_rate": 7.185501066098082e-06, + "loss": 0.3895, + "step": 337 + }, + { + "epoch": 0.04, + "learning_rate": 7.20682302771855e-06, + "loss": 0.405, + "step": 338 + }, + { + "epoch": 0.04, + "learning_rate": 7.22814498933902e-06, + "loss": 0.4093, + "step": 339 + }, + { + "epoch": 0.04, + "learning_rate": 7.249466950959488e-06, + "loss": 0.37, + "step": 340 + }, + { + "epoch": 0.04, + "learning_rate": 7.270788912579958e-06, + "loss": 0.382, + "step": 341 + }, + { + "epoch": 0.04, + "learning_rate": 7.292110874200427e-06, + "loss": 0.3906, + "step": 342 + }, + { + "epoch": 0.04, + "learning_rate": 7.313432835820896e-06, + "loss": 0.3624, + "step": 343 + }, + { + "epoch": 0.04, + "learning_rate": 7.334754797441366e-06, + "loss": 0.3978, + "step": 344 + }, + { + "epoch": 0.04, + "learning_rate": 7.356076759061834e-06, + "loss": 0.383, + "step": 345 + }, + { + "epoch": 0.04, + "learning_rate": 7.377398720682304e-06, + "loss": 0.389, + "step": 346 + }, + { + "epoch": 0.04, + "learning_rate": 7.398720682302772e-06, + "loss": 0.3594, + "step": 347 + }, + { + "epoch": 0.04, + "learning_rate": 7.420042643923242e-06, + "loss": 0.3698, + "step": 348 + }, + { + "epoch": 0.04, + "learning_rate": 7.44136460554371e-06, + "loss": 0.4003, + "step": 349 + }, + { + "epoch": 0.04, + "learning_rate": 7.46268656716418e-06, + "loss": 0.3544, + "step": 350 + }, + { + "epoch": 0.04, + "learning_rate": 7.484008528784648e-06, + "loss": 0.357, + "step": 351 + }, + { + "epoch": 0.05, + "learning_rate": 7.505330490405118e-06, + "loss": 0.3899, + "step": 352 + }, + { + "epoch": 0.05, + "learning_rate": 7.5266524520255865e-06, + "loss": 0.3645, + "step": 353 + }, + { + "epoch": 0.05, + "learning_rate": 7.547974413646056e-06, + "loss": 0.3559, + "step": 354 + }, + { + "epoch": 0.05, + "learning_rate": 7.569296375266525e-06, + "loss": 0.3921, + "step": 355 + }, + { + "epoch": 0.05, + "learning_rate": 7.5906183368869945e-06, + "loss": 0.3652, + "step": 356 + }, + { + "epoch": 0.05, + "learning_rate": 7.611940298507463e-06, + "loss": 0.3966, + "step": 357 + }, + { + "epoch": 0.05, + "learning_rate": 7.633262260127933e-06, + "loss": 0.3789, + "step": 358 + }, + { + "epoch": 0.05, + "learning_rate": 7.654584221748402e-06, + "loss": 0.4139, + "step": 359 + }, + { + "epoch": 0.05, + "learning_rate": 7.67590618336887e-06, + "loss": 0.3914, + "step": 360 + }, + { + "epoch": 0.05, + "learning_rate": 7.69722814498934e-06, + "loss": 0.3987, + "step": 361 + }, + { + "epoch": 0.05, + "learning_rate": 7.718550106609809e-06, + "loss": 0.4223, + "step": 362 + }, + { + "epoch": 0.05, + "learning_rate": 7.739872068230278e-06, + "loss": 0.3771, + "step": 363 + }, + { + "epoch": 0.05, + "learning_rate": 7.761194029850747e-06, + "loss": 0.4191, + "step": 364 + }, + { + "epoch": 0.05, + "learning_rate": 7.782515991471216e-06, + "loss": 0.3934, + "step": 365 + }, + { + "epoch": 0.05, + "learning_rate": 7.803837953091685e-06, + "loss": 0.3924, + "step": 366 + }, + { + "epoch": 0.05, + "learning_rate": 7.825159914712154e-06, + "loss": 0.4078, + "step": 367 + }, + { + "epoch": 0.05, + "learning_rate": 7.846481876332623e-06, + "loss": 0.4093, + "step": 368 + }, + { + "epoch": 0.05, + "learning_rate": 7.867803837953092e-06, + "loss": 0.3821, + "step": 369 + }, + { + "epoch": 0.05, + "learning_rate": 7.889125799573561e-06, + "loss": 0.3733, + "step": 370 + }, + { + "epoch": 0.05, + "learning_rate": 7.91044776119403e-06, + "loss": 0.3552, + "step": 371 + }, + { + "epoch": 0.05, + "learning_rate": 7.9317697228145e-06, + "loss": 0.352, + "step": 372 + }, + { + "epoch": 0.05, + "learning_rate": 7.953091684434968e-06, + "loss": 0.3606, + "step": 373 + }, + { + "epoch": 0.05, + "learning_rate": 7.974413646055437e-06, + "loss": 0.3819, + "step": 374 + }, + { + "epoch": 0.05, + "learning_rate": 7.995735607675907e-06, + "loss": 0.3679, + "step": 375 + }, + { + "epoch": 0.05, + "learning_rate": 8.017057569296376e-06, + "loss": 0.3839, + "step": 376 + }, + { + "epoch": 0.05, + "learning_rate": 8.038379530916846e-06, + "loss": 0.4034, + "step": 377 + }, + { + "epoch": 0.05, + "learning_rate": 8.059701492537314e-06, + "loss": 0.3957, + "step": 378 + }, + { + "epoch": 0.05, + "learning_rate": 8.081023454157784e-06, + "loss": 0.3922, + "step": 379 + }, + { + "epoch": 0.05, + "learning_rate": 8.102345415778252e-06, + "loss": 0.4032, + "step": 380 + }, + { + "epoch": 0.05, + "learning_rate": 8.123667377398723e-06, + "loss": 0.4065, + "step": 381 + }, + { + "epoch": 0.05, + "learning_rate": 8.14498933901919e-06, + "loss": 0.3868, + "step": 382 + }, + { + "epoch": 0.05, + "learning_rate": 8.16631130063966e-06, + "loss": 0.417, + "step": 383 + }, + { + "epoch": 0.05, + "learning_rate": 8.187633262260128e-06, + "loss": 0.3989, + "step": 384 + }, + { + "epoch": 0.05, + "learning_rate": 8.208955223880599e-06, + "loss": 0.3798, + "step": 385 + }, + { + "epoch": 0.05, + "learning_rate": 8.230277185501066e-06, + "loss": 0.378, + "step": 386 + }, + { + "epoch": 0.05, + "learning_rate": 8.251599147121537e-06, + "loss": 0.3844, + "step": 387 + }, + { + "epoch": 0.05, + "learning_rate": 8.272921108742004e-06, + "loss": 0.3721, + "step": 388 + }, + { + "epoch": 0.05, + "learning_rate": 8.294243070362475e-06, + "loss": 0.3961, + "step": 389 + }, + { + "epoch": 0.05, + "learning_rate": 8.315565031982942e-06, + "loss": 0.3925, + "step": 390 + }, + { + "epoch": 0.05, + "learning_rate": 8.336886993603413e-06, + "loss": 0.3903, + "step": 391 + }, + { + "epoch": 0.05, + "learning_rate": 8.35820895522388e-06, + "loss": 0.4168, + "step": 392 + }, + { + "epoch": 0.05, + "learning_rate": 8.379530916844351e-06, + "loss": 0.3826, + "step": 393 + }, + { + "epoch": 0.05, + "learning_rate": 8.400852878464819e-06, + "loss": 0.4075, + "step": 394 + }, + { + "epoch": 0.05, + "learning_rate": 8.42217484008529e-06, + "loss": 0.3804, + "step": 395 + }, + { + "epoch": 0.05, + "learning_rate": 8.443496801705757e-06, + "loss": 0.404, + "step": 396 + }, + { + "epoch": 0.05, + "learning_rate": 8.464818763326227e-06, + "loss": 0.3855, + "step": 397 + }, + { + "epoch": 0.05, + "learning_rate": 8.486140724946695e-06, + "loss": 0.3695, + "step": 398 + }, + { + "epoch": 0.05, + "learning_rate": 8.507462686567165e-06, + "loss": 0.4327, + "step": 399 + }, + { + "epoch": 0.05, + "learning_rate": 8.528784648187633e-06, + "loss": 0.3871, + "step": 400 + }, + { + "epoch": 0.05, + "learning_rate": 8.550106609808104e-06, + "loss": 0.402, + "step": 401 + }, + { + "epoch": 0.05, + "learning_rate": 8.571428571428571e-06, + "loss": 0.4051, + "step": 402 + }, + { + "epoch": 0.05, + "learning_rate": 8.592750533049042e-06, + "loss": 0.3764, + "step": 403 + }, + { + "epoch": 0.05, + "learning_rate": 8.614072494669509e-06, + "loss": 0.385, + "step": 404 + }, + { + "epoch": 0.05, + "learning_rate": 8.63539445628998e-06, + "loss": 0.3901, + "step": 405 + }, + { + "epoch": 0.05, + "learning_rate": 8.656716417910447e-06, + "loss": 0.3575, + "step": 406 + }, + { + "epoch": 0.05, + "learning_rate": 8.678038379530918e-06, + "loss": 0.3885, + "step": 407 + }, + { + "epoch": 0.05, + "learning_rate": 8.699360341151387e-06, + "loss": 0.368, + "step": 408 + }, + { + "epoch": 0.05, + "learning_rate": 8.720682302771856e-06, + "loss": 0.3858, + "step": 409 + }, + { + "epoch": 0.05, + "learning_rate": 8.742004264392325e-06, + "loss": 0.3824, + "step": 410 + }, + { + "epoch": 0.05, + "learning_rate": 8.763326226012794e-06, + "loss": 0.3675, + "step": 411 + }, + { + "epoch": 0.05, + "learning_rate": 8.784648187633263e-06, + "loss": 0.3986, + "step": 412 + }, + { + "epoch": 0.05, + "learning_rate": 8.805970149253732e-06, + "loss": 0.3637, + "step": 413 + }, + { + "epoch": 0.05, + "learning_rate": 8.827292110874201e-06, + "loss": 0.3755, + "step": 414 + }, + { + "epoch": 0.05, + "learning_rate": 8.84861407249467e-06, + "loss": 0.3744, + "step": 415 + }, + { + "epoch": 0.05, + "learning_rate": 8.86993603411514e-06, + "loss": 0.3658, + "step": 416 + }, + { + "epoch": 0.05, + "learning_rate": 8.891257995735608e-06, + "loss": 0.3903, + "step": 417 + }, + { + "epoch": 0.05, + "learning_rate": 8.912579957356077e-06, + "loss": 0.4125, + "step": 418 + }, + { + "epoch": 0.05, + "learning_rate": 8.933901918976547e-06, + "loss": 0.3822, + "step": 419 + }, + { + "epoch": 0.05, + "learning_rate": 8.955223880597016e-06, + "loss": 0.3952, + "step": 420 + }, + { + "epoch": 0.05, + "learning_rate": 8.976545842217485e-06, + "loss": 0.3719, + "step": 421 + }, + { + "epoch": 0.05, + "learning_rate": 8.997867803837954e-06, + "loss": 0.3694, + "step": 422 + }, + { + "epoch": 0.05, + "learning_rate": 9.019189765458423e-06, + "loss": 0.3883, + "step": 423 + }, + { + "epoch": 0.05, + "learning_rate": 9.040511727078892e-06, + "loss": 0.3617, + "step": 424 + }, + { + "epoch": 0.05, + "learning_rate": 9.06183368869936e-06, + "loss": 0.4023, + "step": 425 + }, + { + "epoch": 0.05, + "learning_rate": 9.08315565031983e-06, + "loss": 0.3627, + "step": 426 + }, + { + "epoch": 0.05, + "learning_rate": 9.104477611940299e-06, + "loss": 0.3566, + "step": 427 + }, + { + "epoch": 0.05, + "learning_rate": 9.125799573560768e-06, + "loss": 0.3688, + "step": 428 + }, + { + "epoch": 0.05, + "learning_rate": 9.147121535181237e-06, + "loss": 0.3748, + "step": 429 + }, + { + "epoch": 0.06, + "learning_rate": 9.168443496801706e-06, + "loss": 0.3826, + "step": 430 + }, + { + "epoch": 0.06, + "learning_rate": 9.189765458422175e-06, + "loss": 0.3878, + "step": 431 + }, + { + "epoch": 0.06, + "learning_rate": 9.211087420042644e-06, + "loss": 0.3783, + "step": 432 + }, + { + "epoch": 0.06, + "learning_rate": 9.232409381663113e-06, + "loss": 0.4119, + "step": 433 + }, + { + "epoch": 0.06, + "learning_rate": 9.253731343283582e-06, + "loss": 0.376, + "step": 434 + }, + { + "epoch": 0.06, + "learning_rate": 9.275053304904051e-06, + "loss": 0.3974, + "step": 435 + }, + { + "epoch": 0.06, + "learning_rate": 9.29637526652452e-06, + "loss": 0.3802, + "step": 436 + }, + { + "epoch": 0.06, + "learning_rate": 9.31769722814499e-06, + "loss": 0.4008, + "step": 437 + }, + { + "epoch": 0.06, + "learning_rate": 9.339019189765458e-06, + "loss": 0.3699, + "step": 438 + }, + { + "epoch": 0.06, + "learning_rate": 9.36034115138593e-06, + "loss": 0.3812, + "step": 439 + }, + { + "epoch": 0.06, + "learning_rate": 9.381663113006397e-06, + "loss": 0.3826, + "step": 440 + }, + { + "epoch": 0.06, + "learning_rate": 9.402985074626867e-06, + "loss": 0.3728, + "step": 441 + }, + { + "epoch": 0.06, + "learning_rate": 9.424307036247335e-06, + "loss": 0.4028, + "step": 442 + }, + { + "epoch": 0.06, + "learning_rate": 9.445628997867805e-06, + "loss": 0.3556, + "step": 443 + }, + { + "epoch": 0.06, + "learning_rate": 9.466950959488273e-06, + "loss": 0.386, + "step": 444 + }, + { + "epoch": 0.06, + "learning_rate": 9.488272921108744e-06, + "loss": 0.4249, + "step": 445 + }, + { + "epoch": 0.06, + "learning_rate": 9.509594882729211e-06, + "loss": 0.3572, + "step": 446 + }, + { + "epoch": 0.06, + "learning_rate": 9.530916844349682e-06, + "loss": 0.3811, + "step": 447 + }, + { + "epoch": 0.06, + "learning_rate": 9.552238805970149e-06, + "loss": 0.3783, + "step": 448 + }, + { + "epoch": 0.06, + "learning_rate": 9.57356076759062e-06, + "loss": 0.3703, + "step": 449 + }, + { + "epoch": 0.06, + "learning_rate": 9.594882729211089e-06, + "loss": 0.3797, + "step": 450 + }, + { + "epoch": 0.06, + "learning_rate": 9.616204690831558e-06, + "loss": 0.3865, + "step": 451 + }, + { + "epoch": 0.06, + "learning_rate": 9.637526652452027e-06, + "loss": 0.3913, + "step": 452 + }, + { + "epoch": 0.06, + "learning_rate": 9.658848614072496e-06, + "loss": 0.3895, + "step": 453 + }, + { + "epoch": 0.06, + "learning_rate": 9.680170575692965e-06, + "loss": 0.3775, + "step": 454 + }, + { + "epoch": 0.06, + "learning_rate": 9.701492537313434e-06, + "loss": 0.3984, + "step": 455 + }, + { + "epoch": 0.06, + "learning_rate": 9.722814498933903e-06, + "loss": 0.3875, + "step": 456 + }, + { + "epoch": 0.06, + "learning_rate": 9.744136460554372e-06, + "loss": 0.3913, + "step": 457 + }, + { + "epoch": 0.06, + "learning_rate": 9.765458422174841e-06, + "loss": 0.3861, + "step": 458 + }, + { + "epoch": 0.06, + "learning_rate": 9.78678038379531e-06, + "loss": 0.381, + "step": 459 + }, + { + "epoch": 0.06, + "learning_rate": 9.80810234541578e-06, + "loss": 0.3855, + "step": 460 + }, + { + "epoch": 0.06, + "learning_rate": 9.829424307036248e-06, + "loss": 0.3723, + "step": 461 + }, + { + "epoch": 0.06, + "learning_rate": 9.850746268656717e-06, + "loss": 0.4093, + "step": 462 + }, + { + "epoch": 0.06, + "learning_rate": 9.872068230277187e-06, + "loss": 0.3573, + "step": 463 + }, + { + "epoch": 0.06, + "learning_rate": 9.893390191897656e-06, + "loss": 0.4052, + "step": 464 + }, + { + "epoch": 0.06, + "learning_rate": 9.914712153518125e-06, + "loss": 0.3867, + "step": 465 + }, + { + "epoch": 0.06, + "learning_rate": 9.936034115138594e-06, + "loss": 0.3864, + "step": 466 + }, + { + "epoch": 0.06, + "learning_rate": 9.957356076759063e-06, + "loss": 0.3893, + "step": 467 + }, + { + "epoch": 0.06, + "learning_rate": 9.978678038379532e-06, + "loss": 0.3764, + "step": 468 + }, + { + "epoch": 0.06, + "learning_rate": 1e-05, + "loss": 0.3982, + "step": 469 + }, + { + "epoch": 0.06, + "learning_rate": 9.999999892569433e-06, + "loss": 0.4006, + "step": 470 + }, + { + "epoch": 0.06, + "learning_rate": 9.999999570277734e-06, + "loss": 0.4099, + "step": 471 + }, + { + "epoch": 0.06, + "learning_rate": 9.999999033124919e-06, + "loss": 0.3916, + "step": 472 + }, + { + "epoch": 0.06, + "learning_rate": 9.999998281111008e-06, + "loss": 0.3683, + "step": 473 + }, + { + "epoch": 0.06, + "learning_rate": 9.999997314236036e-06, + "loss": 0.4086, + "step": 474 + }, + { + "epoch": 0.06, + "learning_rate": 9.999996132500046e-06, + "loss": 0.388, + "step": 475 + }, + { + "epoch": 0.06, + "learning_rate": 9.999994735903083e-06, + "loss": 0.3708, + "step": 476 + }, + { + "epoch": 0.06, + "learning_rate": 9.999993124445213e-06, + "loss": 0.3769, + "step": 477 + }, + { + "epoch": 0.06, + "learning_rate": 9.999991298126501e-06, + "loss": 0.3989, + "step": 478 + }, + { + "epoch": 0.06, + "learning_rate": 9.999989256947029e-06, + "loss": 0.4099, + "step": 479 + }, + { + "epoch": 0.06, + "learning_rate": 9.999987000906883e-06, + "loss": 0.4508, + "step": 480 + }, + { + "epoch": 0.06, + "learning_rate": 9.99998453000616e-06, + "loss": 0.3843, + "step": 481 + }, + { + "epoch": 0.06, + "learning_rate": 9.999981844244966e-06, + "loss": 0.3627, + "step": 482 + }, + { + "epoch": 0.06, + "learning_rate": 9.999978943623417e-06, + "loss": 0.3855, + "step": 483 + }, + { + "epoch": 0.06, + "learning_rate": 9.999975828141635e-06, + "loss": 0.3795, + "step": 484 + }, + { + "epoch": 0.06, + "learning_rate": 9.999972497799758e-06, + "loss": 0.3982, + "step": 485 + }, + { + "epoch": 0.06, + "learning_rate": 9.999968952597926e-06, + "loss": 0.3869, + "step": 486 + }, + { + "epoch": 0.06, + "learning_rate": 9.999965192536295e-06, + "loss": 0.4247, + "step": 487 + }, + { + "epoch": 0.06, + "learning_rate": 9.999961217615022e-06, + "loss": 0.3896, + "step": 488 + }, + { + "epoch": 0.06, + "learning_rate": 9.999957027834282e-06, + "loss": 0.376, + "step": 489 + }, + { + "epoch": 0.06, + "learning_rate": 9.999952623194252e-06, + "loss": 0.4164, + "step": 490 + }, + { + "epoch": 0.06, + "learning_rate": 9.99994800369512e-06, + "loss": 0.3852, + "step": 491 + }, + { + "epoch": 0.06, + "learning_rate": 9.99994316933709e-06, + "loss": 0.3716, + "step": 492 + }, + { + "epoch": 0.06, + "learning_rate": 9.999938120120364e-06, + "loss": 0.3675, + "step": 493 + }, + { + "epoch": 0.06, + "learning_rate": 9.999932856045164e-06, + "loss": 0.3753, + "step": 494 + }, + { + "epoch": 0.06, + "learning_rate": 9.999927377111712e-06, + "loss": 0.3777, + "step": 495 + }, + { + "epoch": 0.06, + "learning_rate": 9.999921683320247e-06, + "loss": 0.3925, + "step": 496 + }, + { + "epoch": 0.06, + "learning_rate": 9.999915774671009e-06, + "loss": 0.3864, + "step": 497 + }, + { + "epoch": 0.06, + "learning_rate": 9.999909651164258e-06, + "loss": 0.3833, + "step": 498 + }, + { + "epoch": 0.06, + "learning_rate": 9.99990331280025e-06, + "loss": 0.3818, + "step": 499 + }, + { + "epoch": 0.06, + "learning_rate": 9.999896759579263e-06, + "loss": 0.4021, + "step": 500 + }, + { + "epoch": 0.06, + "learning_rate": 9.99988999150158e-06, + "loss": 0.3845, + "step": 501 + }, + { + "epoch": 0.06, + "learning_rate": 9.999883008567487e-06, + "loss": 0.4025, + "step": 502 + }, + { + "epoch": 0.06, + "learning_rate": 9.999875810777283e-06, + "loss": 0.4148, + "step": 503 + }, + { + "epoch": 0.06, + "learning_rate": 9.999868398131282e-06, + "loss": 0.3845, + "step": 504 + }, + { + "epoch": 0.06, + "learning_rate": 9.9998607706298e-06, + "loss": 0.3782, + "step": 505 + }, + { + "epoch": 0.06, + "learning_rate": 9.999852928273166e-06, + "loss": 0.3986, + "step": 506 + }, + { + "epoch": 0.06, + "learning_rate": 9.999844871061718e-06, + "loss": 0.3587, + "step": 507 + }, + { + "epoch": 0.07, + "learning_rate": 9.999836598995799e-06, + "loss": 0.413, + "step": 508 + }, + { + "epoch": 0.07, + "learning_rate": 9.999828112075764e-06, + "loss": 0.3462, + "step": 509 + }, + { + "epoch": 0.07, + "learning_rate": 9.999819410301983e-06, + "loss": 0.3874, + "step": 510 + }, + { + "epoch": 0.07, + "learning_rate": 9.999810493674826e-06, + "loss": 0.353, + "step": 511 + }, + { + "epoch": 0.07, + "learning_rate": 9.999801362194676e-06, + "loss": 0.37, + "step": 512 + }, + { + "epoch": 0.07, + "learning_rate": 9.999792015861927e-06, + "loss": 0.3724, + "step": 513 + }, + { + "epoch": 0.07, + "learning_rate": 9.99978245467698e-06, + "loss": 0.3995, + "step": 514 + }, + { + "epoch": 0.07, + "learning_rate": 9.999772678640245e-06, + "loss": 0.4118, + "step": 515 + }, + { + "epoch": 0.07, + "learning_rate": 9.999762687752143e-06, + "loss": 0.3802, + "step": 516 + }, + { + "epoch": 0.07, + "learning_rate": 9.999752482013105e-06, + "loss": 0.364, + "step": 517 + }, + { + "epoch": 0.07, + "learning_rate": 9.999742061423567e-06, + "loss": 0.3913, + "step": 518 + }, + { + "epoch": 0.07, + "learning_rate": 9.999731425983975e-06, + "loss": 0.3704, + "step": 519 + }, + { + "epoch": 0.07, + "learning_rate": 9.999720575694792e-06, + "loss": 0.3664, + "step": 520 + }, + { + "epoch": 0.07, + "learning_rate": 9.99970951055648e-06, + "loss": 0.4073, + "step": 521 + }, + { + "epoch": 0.07, + "learning_rate": 9.999698230569515e-06, + "loss": 0.3694, + "step": 522 + }, + { + "epoch": 0.07, + "learning_rate": 9.999686735734382e-06, + "loss": 0.4237, + "step": 523 + }, + { + "epoch": 0.07, + "learning_rate": 9.999675026051576e-06, + "loss": 0.3529, + "step": 524 + }, + { + "epoch": 0.07, + "learning_rate": 9.999663101521599e-06, + "loss": 0.3779, + "step": 525 + }, + { + "epoch": 0.07, + "learning_rate": 9.999650962144962e-06, + "loss": 0.3661, + "step": 526 + }, + { + "epoch": 0.07, + "learning_rate": 9.999638607922191e-06, + "loss": 0.3641, + "step": 527 + }, + { + "epoch": 0.07, + "learning_rate": 9.99962603885381e-06, + "loss": 0.3634, + "step": 528 + }, + { + "epoch": 0.07, + "learning_rate": 9.999613254940368e-06, + "loss": 0.3556, + "step": 529 + }, + { + "epoch": 0.07, + "learning_rate": 9.999600256182408e-06, + "loss": 0.3731, + "step": 530 + }, + { + "epoch": 0.07, + "learning_rate": 9.99958704258049e-06, + "loss": 0.3937, + "step": 531 + }, + { + "epoch": 0.07, + "learning_rate": 9.999573614135183e-06, + "loss": 0.4033, + "step": 532 + }, + { + "epoch": 0.07, + "learning_rate": 9.999559970847061e-06, + "loss": 0.346, + "step": 533 + }, + { + "epoch": 0.07, + "learning_rate": 9.999546112716715e-06, + "loss": 0.362, + "step": 534 + }, + { + "epoch": 0.07, + "learning_rate": 9.999532039744736e-06, + "loss": 0.4019, + "step": 535 + }, + { + "epoch": 0.07, + "learning_rate": 9.999517751931731e-06, + "loss": 0.3844, + "step": 536 + }, + { + "epoch": 0.07, + "learning_rate": 9.999503249278315e-06, + "loss": 0.3732, + "step": 537 + }, + { + "epoch": 0.07, + "learning_rate": 9.99948853178511e-06, + "loss": 0.3687, + "step": 538 + }, + { + "epoch": 0.07, + "learning_rate": 9.999473599452746e-06, + "loss": 0.3939, + "step": 539 + }, + { + "epoch": 0.07, + "learning_rate": 9.999458452281868e-06, + "loss": 0.4374, + "step": 540 + }, + { + "epoch": 0.07, + "learning_rate": 9.999443090273126e-06, + "loss": 0.3978, + "step": 541 + }, + { + "epoch": 0.07, + "learning_rate": 9.99942751342718e-06, + "loss": 0.3663, + "step": 542 + }, + { + "epoch": 0.07, + "learning_rate": 9.9994117217447e-06, + "loss": 0.3731, + "step": 543 + }, + { + "epoch": 0.07, + "learning_rate": 9.999395715226365e-06, + "loss": 0.3736, + "step": 544 + }, + { + "epoch": 0.07, + "learning_rate": 9.99937949387286e-06, + "loss": 0.3814, + "step": 545 + }, + { + "epoch": 0.07, + "learning_rate": 9.999363057684885e-06, + "loss": 0.3803, + "step": 546 + }, + { + "epoch": 0.07, + "learning_rate": 9.999346406663144e-06, + "loss": 0.3973, + "step": 547 + }, + { + "epoch": 0.07, + "learning_rate": 9.999329540808355e-06, + "loss": 0.3715, + "step": 548 + }, + { + "epoch": 0.07, + "learning_rate": 9.999312460121242e-06, + "loss": 0.3841, + "step": 549 + }, + { + "epoch": 0.07, + "learning_rate": 9.999295164602536e-06, + "loss": 0.3688, + "step": 550 + }, + { + "epoch": 0.07, + "learning_rate": 9.999277654252985e-06, + "loss": 0.36, + "step": 551 + }, + { + "epoch": 0.07, + "learning_rate": 9.999259929073339e-06, + "loss": 0.4398, + "step": 552 + }, + { + "epoch": 0.07, + "learning_rate": 9.999241989064358e-06, + "loss": 0.3737, + "step": 553 + }, + { + "epoch": 0.07, + "learning_rate": 9.999223834226817e-06, + "loss": 0.3758, + "step": 554 + }, + { + "epoch": 0.07, + "learning_rate": 9.999205464561494e-06, + "loss": 0.3658, + "step": 555 + }, + { + "epoch": 0.07, + "learning_rate": 9.999186880069178e-06, + "loss": 0.3709, + "step": 556 + }, + { + "epoch": 0.07, + "learning_rate": 9.999168080750666e-06, + "loss": 0.3919, + "step": 557 + }, + { + "epoch": 0.07, + "learning_rate": 9.99914906660677e-06, + "loss": 0.3833, + "step": 558 + }, + { + "epoch": 0.07, + "learning_rate": 9.999129837638303e-06, + "loss": 0.3733, + "step": 559 + }, + { + "epoch": 0.07, + "learning_rate": 9.999110393846097e-06, + "loss": 0.4102, + "step": 560 + }, + { + "epoch": 0.07, + "learning_rate": 9.999090735230981e-06, + "loss": 0.3991, + "step": 561 + }, + { + "epoch": 0.07, + "learning_rate": 9.999070861793803e-06, + "loss": 0.3794, + "step": 562 + }, + { + "epoch": 0.07, + "learning_rate": 9.999050773535414e-06, + "loss": 0.4048, + "step": 563 + }, + { + "epoch": 0.07, + "learning_rate": 9.999030470456684e-06, + "loss": 0.3774, + "step": 564 + }, + { + "epoch": 0.07, + "learning_rate": 9.999009952558478e-06, + "loss": 0.3677, + "step": 565 + }, + { + "epoch": 0.07, + "learning_rate": 9.998989219841684e-06, + "loss": 0.3757, + "step": 566 + }, + { + "epoch": 0.07, + "learning_rate": 9.998968272307187e-06, + "loss": 0.4058, + "step": 567 + }, + { + "epoch": 0.07, + "learning_rate": 9.998947109955892e-06, + "loss": 0.3825, + "step": 568 + }, + { + "epoch": 0.07, + "learning_rate": 9.998925732788706e-06, + "loss": 0.3925, + "step": 569 + }, + { + "epoch": 0.07, + "learning_rate": 9.998904140806547e-06, + "loss": 0.3602, + "step": 570 + }, + { + "epoch": 0.07, + "learning_rate": 9.998882334010345e-06, + "loss": 0.3823, + "step": 571 + }, + { + "epoch": 0.07, + "learning_rate": 9.998860312401035e-06, + "loss": 0.4005, + "step": 572 + }, + { + "epoch": 0.07, + "learning_rate": 9.998838075979566e-06, + "loss": 0.3641, + "step": 573 + }, + { + "epoch": 0.07, + "learning_rate": 9.99881562474689e-06, + "loss": 0.3707, + "step": 574 + }, + { + "epoch": 0.07, + "learning_rate": 9.998792958703975e-06, + "loss": 0.3893, + "step": 575 + }, + { + "epoch": 0.07, + "learning_rate": 9.998770077851794e-06, + "loss": 0.4006, + "step": 576 + }, + { + "epoch": 0.07, + "learning_rate": 9.998746982191327e-06, + "loss": 0.4036, + "step": 577 + }, + { + "epoch": 0.07, + "learning_rate": 9.998723671723572e-06, + "loss": 0.3979, + "step": 578 + }, + { + "epoch": 0.07, + "learning_rate": 9.998700146449528e-06, + "loss": 0.3763, + "step": 579 + }, + { + "epoch": 0.07, + "learning_rate": 9.998676406370205e-06, + "loss": 0.3768, + "step": 580 + }, + { + "epoch": 0.07, + "learning_rate": 9.998652451486626e-06, + "loss": 0.3943, + "step": 581 + }, + { + "epoch": 0.07, + "learning_rate": 9.998628281799816e-06, + "loss": 0.3744, + "step": 582 + }, + { + "epoch": 0.07, + "learning_rate": 9.998603897310818e-06, + "loss": 0.4088, + "step": 583 + }, + { + "epoch": 0.07, + "learning_rate": 9.998579298020676e-06, + "loss": 0.3618, + "step": 584 + }, + { + "epoch": 0.07, + "learning_rate": 9.998554483930452e-06, + "loss": 0.4009, + "step": 585 + }, + { + "epoch": 0.08, + "learning_rate": 9.998529455041209e-06, + "loss": 0.3822, + "step": 586 + }, + { + "epoch": 0.08, + "learning_rate": 9.998504211354021e-06, + "loss": 0.3835, + "step": 587 + }, + { + "epoch": 0.08, + "learning_rate": 9.998478752869976e-06, + "loss": 0.389, + "step": 588 + }, + { + "epoch": 0.08, + "learning_rate": 9.998453079590167e-06, + "loss": 0.3674, + "step": 589 + }, + { + "epoch": 0.08, + "learning_rate": 9.998427191515696e-06, + "loss": 0.3727, + "step": 590 + }, + { + "epoch": 0.08, + "learning_rate": 9.998401088647677e-06, + "loss": 0.3406, + "step": 591 + }, + { + "epoch": 0.08, + "learning_rate": 9.998374770987232e-06, + "loss": 0.4251, + "step": 592 + }, + { + "epoch": 0.08, + "learning_rate": 9.99834823853549e-06, + "loss": 0.3843, + "step": 593 + }, + { + "epoch": 0.08, + "learning_rate": 9.998321491293592e-06, + "loss": 0.3655, + "step": 594 + }, + { + "epoch": 0.08, + "learning_rate": 9.998294529262688e-06, + "loss": 0.3655, + "step": 595 + }, + { + "epoch": 0.08, + "learning_rate": 9.998267352443938e-06, + "loss": 0.3857, + "step": 596 + }, + { + "epoch": 0.08, + "learning_rate": 9.998239960838505e-06, + "loss": 0.386, + "step": 597 + }, + { + "epoch": 0.08, + "learning_rate": 9.998212354447572e-06, + "loss": 0.3676, + "step": 598 + }, + { + "epoch": 0.08, + "learning_rate": 9.998184533272321e-06, + "loss": 0.3924, + "step": 599 + }, + { + "epoch": 0.08, + "learning_rate": 9.99815649731395e-06, + "loss": 0.3764, + "step": 600 + }, + { + "epoch": 0.08, + "learning_rate": 9.998128246573663e-06, + "loss": 0.3858, + "step": 601 + }, + { + "epoch": 0.08, + "learning_rate": 9.998099781052673e-06, + "loss": 0.3948, + "step": 602 + }, + { + "epoch": 0.08, + "learning_rate": 9.998071100752203e-06, + "loss": 0.3947, + "step": 603 + }, + { + "epoch": 0.08, + "learning_rate": 9.998042205673489e-06, + "loss": 0.3582, + "step": 604 + }, + { + "epoch": 0.08, + "learning_rate": 9.998013095817768e-06, + "loss": 0.35, + "step": 605 + }, + { + "epoch": 0.08, + "learning_rate": 9.997983771186293e-06, + "loss": 0.3937, + "step": 606 + }, + { + "epoch": 0.08, + "learning_rate": 9.997954231780326e-06, + "loss": 0.4257, + "step": 607 + }, + { + "epoch": 0.08, + "learning_rate": 9.997924477601134e-06, + "loss": 0.3808, + "step": 608 + }, + { + "epoch": 0.08, + "learning_rate": 9.997894508649995e-06, + "loss": 0.3835, + "step": 609 + }, + { + "epoch": 0.08, + "learning_rate": 9.9978643249282e-06, + "loss": 0.3959, + "step": 610 + }, + { + "epoch": 0.08, + "learning_rate": 9.997833926437043e-06, + "loss": 0.3687, + "step": 611 + }, + { + "epoch": 0.08, + "learning_rate": 9.997803313177831e-06, + "loss": 0.373, + "step": 612 + }, + { + "epoch": 0.08, + "learning_rate": 9.997772485151881e-06, + "loss": 0.3993, + "step": 613 + }, + { + "epoch": 0.08, + "learning_rate": 9.997741442360515e-06, + "loss": 0.3679, + "step": 614 + }, + { + "epoch": 0.08, + "learning_rate": 9.997710184805072e-06, + "loss": 0.3852, + "step": 615 + }, + { + "epoch": 0.08, + "learning_rate": 9.997678712486889e-06, + "loss": 0.3829, + "step": 616 + }, + { + "epoch": 0.08, + "learning_rate": 9.997647025407322e-06, + "loss": 0.3855, + "step": 617 + }, + { + "epoch": 0.08, + "learning_rate": 9.997615123567733e-06, + "loss": 0.356, + "step": 618 + }, + { + "epoch": 0.08, + "learning_rate": 9.99758300696949e-06, + "loss": 0.3734, + "step": 619 + }, + { + "epoch": 0.08, + "learning_rate": 9.997550675613976e-06, + "loss": 0.3741, + "step": 620 + }, + { + "epoch": 0.08, + "learning_rate": 9.997518129502579e-06, + "loss": 0.4124, + "step": 621 + }, + { + "epoch": 0.08, + "learning_rate": 9.997485368636698e-06, + "loss": 0.383, + "step": 622 + }, + { + "epoch": 0.08, + "learning_rate": 9.99745239301774e-06, + "loss": 0.3987, + "step": 623 + }, + { + "epoch": 0.08, + "learning_rate": 9.997419202647124e-06, + "loss": 0.3799, + "step": 624 + }, + { + "epoch": 0.08, + "learning_rate": 9.997385797526275e-06, + "loss": 0.3797, + "step": 625 + }, + { + "epoch": 0.08, + "learning_rate": 9.997352177656627e-06, + "loss": 0.3788, + "step": 626 + }, + { + "epoch": 0.08, + "learning_rate": 9.997318343039629e-06, + "loss": 0.3807, + "step": 627 + }, + { + "epoch": 0.08, + "learning_rate": 9.99728429367673e-06, + "loss": 0.3719, + "step": 628 + }, + { + "epoch": 0.08, + "learning_rate": 9.997250029569395e-06, + "loss": 0.3913, + "step": 629 + }, + { + "epoch": 0.08, + "learning_rate": 9.997215550719097e-06, + "loss": 0.3999, + "step": 630 + }, + { + "epoch": 0.08, + "learning_rate": 9.997180857127318e-06, + "loss": 0.3551, + "step": 631 + }, + { + "epoch": 0.08, + "learning_rate": 9.997145948795548e-06, + "loss": 0.3691, + "step": 632 + }, + { + "epoch": 0.08, + "learning_rate": 9.997110825725288e-06, + "loss": 0.3769, + "step": 633 + }, + { + "epoch": 0.08, + "learning_rate": 9.997075487918047e-06, + "loss": 0.3619, + "step": 634 + }, + { + "epoch": 0.08, + "learning_rate": 9.99703993537534e-06, + "loss": 0.3822, + "step": 635 + }, + { + "epoch": 0.08, + "learning_rate": 9.997004168098703e-06, + "loss": 0.397, + "step": 636 + }, + { + "epoch": 0.08, + "learning_rate": 9.996968186089664e-06, + "loss": 0.3625, + "step": 637 + }, + { + "epoch": 0.08, + "learning_rate": 9.996931989349775e-06, + "loss": 0.35, + "step": 638 + }, + { + "epoch": 0.08, + "learning_rate": 9.99689557788059e-06, + "loss": 0.3706, + "step": 639 + }, + { + "epoch": 0.08, + "learning_rate": 9.996858951683672e-06, + "loss": 0.3567, + "step": 640 + }, + { + "epoch": 0.08, + "learning_rate": 9.996822110760595e-06, + "loss": 0.3693, + "step": 641 + }, + { + "epoch": 0.08, + "learning_rate": 9.996785055112947e-06, + "loss": 0.3562, + "step": 642 + }, + { + "epoch": 0.08, + "learning_rate": 9.996747784742314e-06, + "loss": 0.3648, + "step": 643 + }, + { + "epoch": 0.08, + "learning_rate": 9.996710299650302e-06, + "loss": 0.3784, + "step": 644 + }, + { + "epoch": 0.08, + "learning_rate": 9.99667259983852e-06, + "loss": 0.3723, + "step": 645 + }, + { + "epoch": 0.08, + "learning_rate": 9.996634685308586e-06, + "loss": 0.3712, + "step": 646 + }, + { + "epoch": 0.08, + "learning_rate": 9.996596556062133e-06, + "loss": 0.404, + "step": 647 + }, + { + "epoch": 0.08, + "learning_rate": 9.9965582121008e-06, + "loss": 0.3538, + "step": 648 + }, + { + "epoch": 0.08, + "learning_rate": 9.996519653426229e-06, + "loss": 0.3734, + "step": 649 + }, + { + "epoch": 0.08, + "learning_rate": 9.996480880040083e-06, + "loss": 0.3786, + "step": 650 + }, + { + "epoch": 0.08, + "learning_rate": 9.996441891944023e-06, + "loss": 0.3986, + "step": 651 + }, + { + "epoch": 0.08, + "learning_rate": 9.99640268913973e-06, + "loss": 0.4091, + "step": 652 + }, + { + "epoch": 0.08, + "learning_rate": 9.996363271628886e-06, + "loss": 0.3924, + "step": 653 + }, + { + "epoch": 0.08, + "learning_rate": 9.996323639413185e-06, + "loss": 0.3681, + "step": 654 + }, + { + "epoch": 0.08, + "learning_rate": 9.996283792494328e-06, + "loss": 0.3923, + "step": 655 + }, + { + "epoch": 0.08, + "learning_rate": 9.99624373087403e-06, + "loss": 0.3769, + "step": 656 + }, + { + "epoch": 0.08, + "learning_rate": 9.996203454554011e-06, + "loss": 0.3887, + "step": 657 + }, + { + "epoch": 0.08, + "learning_rate": 9.996162963536004e-06, + "loss": 0.4019, + "step": 658 + }, + { + "epoch": 0.08, + "learning_rate": 9.996122257821746e-06, + "loss": 0.4026, + "step": 659 + }, + { + "epoch": 0.08, + "learning_rate": 9.996081337412988e-06, + "loss": 0.3765, + "step": 660 + }, + { + "epoch": 0.08, + "learning_rate": 9.996040202311488e-06, + "loss": 0.3492, + "step": 661 + }, + { + "epoch": 0.08, + "learning_rate": 9.995998852519014e-06, + "loss": 0.3794, + "step": 662 + }, + { + "epoch": 0.08, + "learning_rate": 9.995957288037343e-06, + "loss": 0.3604, + "step": 663 + }, + { + "epoch": 0.08, + "learning_rate": 9.99591550886826e-06, + "loss": 0.4054, + "step": 664 + }, + { + "epoch": 0.09, + "learning_rate": 9.995873515013562e-06, + "loss": 0.3474, + "step": 665 + }, + { + "epoch": 0.09, + "learning_rate": 9.99583130647505e-06, + "loss": 0.3968, + "step": 666 + }, + { + "epoch": 0.09, + "learning_rate": 9.995788883254543e-06, + "loss": 0.3643, + "step": 667 + }, + { + "epoch": 0.09, + "learning_rate": 9.995746245353861e-06, + "loss": 0.3794, + "step": 668 + }, + { + "epoch": 0.09, + "learning_rate": 9.995703392774836e-06, + "loss": 0.4088, + "step": 669 + }, + { + "epoch": 0.09, + "learning_rate": 9.99566032551931e-06, + "loss": 0.3729, + "step": 670 + }, + { + "epoch": 0.09, + "learning_rate": 9.995617043589135e-06, + "loss": 0.3608, + "step": 671 + }, + { + "epoch": 0.09, + "learning_rate": 9.99557354698617e-06, + "loss": 0.3866, + "step": 672 + }, + { + "epoch": 0.09, + "learning_rate": 9.995529835712283e-06, + "loss": 0.362, + "step": 673 + }, + { + "epoch": 0.09, + "learning_rate": 9.995485909769354e-06, + "loss": 0.3939, + "step": 674 + }, + { + "epoch": 0.09, + "learning_rate": 9.995441769159269e-06, + "loss": 0.3974, + "step": 675 + }, + { + "epoch": 0.09, + "learning_rate": 9.995397413883928e-06, + "loss": 0.3924, + "step": 676 + }, + { + "epoch": 0.09, + "learning_rate": 9.995352843945232e-06, + "loss": 0.3569, + "step": 677 + }, + { + "epoch": 0.09, + "learning_rate": 9.9953080593451e-06, + "loss": 0.3902, + "step": 678 + }, + { + "epoch": 0.09, + "learning_rate": 9.995263060085456e-06, + "loss": 0.37, + "step": 679 + }, + { + "epoch": 0.09, + "learning_rate": 9.995217846168232e-06, + "loss": 0.4063, + "step": 680 + }, + { + "epoch": 0.09, + "learning_rate": 9.995172417595373e-06, + "loss": 0.3827, + "step": 681 + }, + { + "epoch": 0.09, + "learning_rate": 9.995126774368831e-06, + "loss": 0.3905, + "step": 682 + }, + { + "epoch": 0.09, + "learning_rate": 9.995080916490566e-06, + "loss": 0.382, + "step": 683 + }, + { + "epoch": 0.09, + "learning_rate": 9.99503484396255e-06, + "loss": 0.3754, + "step": 684 + }, + { + "epoch": 0.09, + "learning_rate": 9.994988556786763e-06, + "loss": 0.3631, + "step": 685 + }, + { + "epoch": 0.09, + "learning_rate": 9.99494205496519e-06, + "loss": 0.3712, + "step": 686 + }, + { + "epoch": 0.09, + "learning_rate": 9.994895338499835e-06, + "loss": 0.3792, + "step": 687 + }, + { + "epoch": 0.09, + "learning_rate": 9.994848407392703e-06, + "loss": 0.3581, + "step": 688 + }, + { + "epoch": 0.09, + "learning_rate": 9.99480126164581e-06, + "loss": 0.368, + "step": 689 + }, + { + "epoch": 0.09, + "learning_rate": 9.994753901261183e-06, + "loss": 0.3694, + "step": 690 + }, + { + "epoch": 0.09, + "learning_rate": 9.994706326240858e-06, + "loss": 0.3752, + "step": 691 + }, + { + "epoch": 0.09, + "learning_rate": 9.994658536586878e-06, + "loss": 0.3801, + "step": 692 + }, + { + "epoch": 0.09, + "learning_rate": 9.994610532301296e-06, + "loss": 0.3848, + "step": 693 + }, + { + "epoch": 0.09, + "learning_rate": 9.994562313386177e-06, + "loss": 0.3503, + "step": 694 + }, + { + "epoch": 0.09, + "learning_rate": 9.99451387984359e-06, + "loss": 0.3866, + "step": 695 + }, + { + "epoch": 0.09, + "learning_rate": 9.99446523167562e-06, + "loss": 0.3633, + "step": 696 + }, + { + "epoch": 0.09, + "learning_rate": 9.994416368884357e-06, + "loss": 0.3514, + "step": 697 + }, + { + "epoch": 0.09, + "learning_rate": 9.994367291471896e-06, + "loss": 0.3538, + "step": 698 + }, + { + "epoch": 0.09, + "learning_rate": 9.994317999440351e-06, + "loss": 0.3795, + "step": 699 + }, + { + "epoch": 0.09, + "learning_rate": 9.99426849279184e-06, + "loss": 0.363, + "step": 700 + }, + { + "epoch": 0.09, + "learning_rate": 9.994218771528487e-06, + "loss": 0.3603, + "step": 701 + }, + { + "epoch": 0.09, + "learning_rate": 9.994168835652432e-06, + "loss": 0.3731, + "step": 702 + }, + { + "epoch": 0.09, + "learning_rate": 9.994118685165819e-06, + "loss": 0.3945, + "step": 703 + }, + { + "epoch": 0.09, + "learning_rate": 9.994068320070805e-06, + "loss": 0.3523, + "step": 704 + }, + { + "epoch": 0.09, + "learning_rate": 9.99401774036955e-06, + "loss": 0.3673, + "step": 705 + }, + { + "epoch": 0.09, + "learning_rate": 9.993966946064233e-06, + "loss": 0.3786, + "step": 706 + }, + { + "epoch": 0.09, + "learning_rate": 9.993915937157033e-06, + "loss": 0.4012, + "step": 707 + }, + { + "epoch": 0.09, + "learning_rate": 9.993864713650143e-06, + "loss": 0.3899, + "step": 708 + }, + { + "epoch": 0.09, + "learning_rate": 9.993813275545764e-06, + "loss": 0.3338, + "step": 709 + }, + { + "epoch": 0.09, + "learning_rate": 9.993761622846107e-06, + "loss": 0.3841, + "step": 710 + }, + { + "epoch": 0.09, + "learning_rate": 9.99370975555339e-06, + "loss": 0.406, + "step": 711 + }, + { + "epoch": 0.09, + "learning_rate": 9.993657673669848e-06, + "loss": 0.4007, + "step": 712 + }, + { + "epoch": 0.09, + "learning_rate": 9.993605377197711e-06, + "loss": 0.3593, + "step": 713 + }, + { + "epoch": 0.09, + "learning_rate": 9.99355286613923e-06, + "loss": 0.3903, + "step": 714 + }, + { + "epoch": 0.09, + "learning_rate": 9.993500140496659e-06, + "loss": 0.3909, + "step": 715 + }, + { + "epoch": 0.09, + "learning_rate": 9.993447200272269e-06, + "loss": 0.4118, + "step": 716 + }, + { + "epoch": 0.09, + "learning_rate": 9.993394045468329e-06, + "loss": 0.3941, + "step": 717 + }, + { + "epoch": 0.09, + "learning_rate": 9.993340676087129e-06, + "loss": 0.3737, + "step": 718 + }, + { + "epoch": 0.09, + "learning_rate": 9.993287092130956e-06, + "loss": 0.3684, + "step": 719 + }, + { + "epoch": 0.09, + "learning_rate": 9.993233293602119e-06, + "loss": 0.3902, + "step": 720 + }, + { + "epoch": 0.09, + "learning_rate": 9.993179280502926e-06, + "loss": 0.3766, + "step": 721 + }, + { + "epoch": 0.09, + "learning_rate": 9.993125052835699e-06, + "loss": 0.3868, + "step": 722 + }, + { + "epoch": 0.09, + "learning_rate": 9.993070610602766e-06, + "loss": 0.3819, + "step": 723 + }, + { + "epoch": 0.09, + "learning_rate": 9.993015953806472e-06, + "loss": 0.377, + "step": 724 + }, + { + "epoch": 0.09, + "learning_rate": 9.992961082449161e-06, + "loss": 0.3743, + "step": 725 + }, + { + "epoch": 0.09, + "learning_rate": 9.992905996533193e-06, + "loss": 0.3782, + "step": 726 + }, + { + "epoch": 0.09, + "learning_rate": 9.992850696060933e-06, + "loss": 0.3712, + "step": 727 + }, + { + "epoch": 0.09, + "learning_rate": 9.99279518103476e-06, + "loss": 0.3869, + "step": 728 + }, + { + "epoch": 0.09, + "learning_rate": 9.992739451457058e-06, + "loss": 0.3926, + "step": 729 + }, + { + "epoch": 0.09, + "learning_rate": 9.992683507330223e-06, + "loss": 0.368, + "step": 730 + }, + { + "epoch": 0.09, + "learning_rate": 9.992627348656658e-06, + "loss": 0.3581, + "step": 731 + }, + { + "epoch": 0.09, + "learning_rate": 9.992570975438776e-06, + "loss": 0.3654, + "step": 732 + }, + { + "epoch": 0.09, + "learning_rate": 9.992514387679e-06, + "loss": 0.3759, + "step": 733 + }, + { + "epoch": 0.09, + "learning_rate": 9.992457585379764e-06, + "loss": 0.4004, + "step": 734 + }, + { + "epoch": 0.09, + "learning_rate": 9.992400568543506e-06, + "loss": 0.3853, + "step": 735 + }, + { + "epoch": 0.09, + "learning_rate": 9.992343337172674e-06, + "loss": 0.389, + "step": 736 + }, + { + "epoch": 0.09, + "learning_rate": 9.992285891269732e-06, + "loss": 0.3741, + "step": 737 + }, + { + "epoch": 0.09, + "learning_rate": 9.992228230837148e-06, + "loss": 0.4017, + "step": 738 + }, + { + "epoch": 0.09, + "learning_rate": 9.992170355877398e-06, + "loss": 0.3749, + "step": 739 + }, + { + "epoch": 0.09, + "learning_rate": 9.99211226639297e-06, + "loss": 0.4105, + "step": 740 + }, + { + "epoch": 0.09, + "learning_rate": 9.99205396238636e-06, + "loss": 0.3834, + "step": 741 + }, + { + "epoch": 0.09, + "learning_rate": 9.991995443860074e-06, + "loss": 0.3698, + "step": 742 + }, + { + "epoch": 0.1, + "learning_rate": 9.991936710816624e-06, + "loss": 0.3891, + "step": 743 + }, + { + "epoch": 0.1, + "learning_rate": 9.991877763258538e-06, + "loss": 0.3779, + "step": 744 + }, + { + "epoch": 0.1, + "learning_rate": 9.991818601188345e-06, + "loss": 0.3886, + "step": 745 + }, + { + "epoch": 0.1, + "learning_rate": 9.99175922460859e-06, + "loss": 0.3879, + "step": 746 + }, + { + "epoch": 0.1, + "learning_rate": 9.991699633521823e-06, + "loss": 0.3661, + "step": 747 + }, + { + "epoch": 0.1, + "learning_rate": 9.991639827930607e-06, + "loss": 0.3865, + "step": 748 + }, + { + "epoch": 0.1, + "learning_rate": 9.991579807837511e-06, + "loss": 0.3738, + "step": 749 + }, + { + "epoch": 0.1, + "learning_rate": 9.991519573245112e-06, + "loss": 0.3918, + "step": 750 + }, + { + "epoch": 0.1, + "learning_rate": 9.991459124156003e-06, + "loss": 0.3779, + "step": 751 + }, + { + "epoch": 0.1, + "learning_rate": 9.991398460572776e-06, + "loss": 0.4105, + "step": 752 + }, + { + "epoch": 0.1, + "learning_rate": 9.991337582498042e-06, + "loss": 0.3797, + "step": 753 + }, + { + "epoch": 0.1, + "learning_rate": 9.991276489934416e-06, + "loss": 0.3489, + "step": 754 + }, + { + "epoch": 0.1, + "learning_rate": 9.991215182884521e-06, + "loss": 0.389, + "step": 755 + }, + { + "epoch": 0.1, + "learning_rate": 9.991153661350996e-06, + "loss": 0.3689, + "step": 756 + }, + { + "epoch": 0.1, + "learning_rate": 9.991091925336481e-06, + "loss": 0.4078, + "step": 757 + }, + { + "epoch": 0.1, + "learning_rate": 9.991029974843632e-06, + "loss": 0.3842, + "step": 758 + }, + { + "epoch": 0.1, + "learning_rate": 9.990967809875107e-06, + "loss": 0.3863, + "step": 759 + }, + { + "epoch": 0.1, + "learning_rate": 9.990905430433582e-06, + "loss": 0.3546, + "step": 760 + }, + { + "epoch": 0.1, + "learning_rate": 9.990842836521732e-06, + "loss": 0.3851, + "step": 761 + }, + { + "epoch": 0.1, + "learning_rate": 9.990780028142253e-06, + "loss": 0.3756, + "step": 762 + }, + { + "epoch": 0.1, + "learning_rate": 9.990717005297841e-06, + "loss": 0.3641, + "step": 763 + }, + { + "epoch": 0.1, + "learning_rate": 9.990653767991203e-06, + "loss": 0.38, + "step": 764 + }, + { + "epoch": 0.1, + "learning_rate": 9.99059031622506e-06, + "loss": 0.3746, + "step": 765 + }, + { + "epoch": 0.1, + "learning_rate": 9.990526650002133e-06, + "loss": 0.396, + "step": 766 + }, + { + "epoch": 0.1, + "learning_rate": 9.990462769325163e-06, + "loss": 0.3917, + "step": 767 + }, + { + "epoch": 0.1, + "learning_rate": 9.990398674196896e-06, + "loss": 0.3645, + "step": 768 + }, + { + "epoch": 0.1, + "learning_rate": 9.99033436462008e-06, + "loss": 0.4238, + "step": 769 + }, + { + "epoch": 0.1, + "learning_rate": 9.990269840597484e-06, + "loss": 0.3882, + "step": 770 + }, + { + "epoch": 0.1, + "learning_rate": 9.990205102131879e-06, + "loss": 0.3492, + "step": 771 + }, + { + "epoch": 0.1, + "learning_rate": 9.990140149226047e-06, + "loss": 0.3775, + "step": 772 + }, + { + "epoch": 0.1, + "learning_rate": 9.99007498188278e-06, + "loss": 0.3696, + "step": 773 + }, + { + "epoch": 0.1, + "learning_rate": 9.990009600104875e-06, + "loss": 0.3883, + "step": 774 + }, + { + "epoch": 0.1, + "learning_rate": 9.989944003895146e-06, + "loss": 0.404, + "step": 775 + }, + { + "epoch": 0.1, + "learning_rate": 9.98987819325641e-06, + "loss": 0.379, + "step": 776 + }, + { + "epoch": 0.1, + "learning_rate": 9.989812168191495e-06, + "loss": 0.3407, + "step": 777 + }, + { + "epoch": 0.1, + "learning_rate": 9.989745928703237e-06, + "loss": 0.3641, + "step": 778 + }, + { + "epoch": 0.1, + "learning_rate": 9.989679474794484e-06, + "loss": 0.3693, + "step": 779 + }, + { + "epoch": 0.1, + "learning_rate": 9.989612806468092e-06, + "loss": 0.3569, + "step": 780 + }, + { + "epoch": 0.1, + "learning_rate": 9.989545923726925e-06, + "loss": 0.3771, + "step": 781 + }, + { + "epoch": 0.1, + "learning_rate": 9.989478826573857e-06, + "loss": 0.3476, + "step": 782 + }, + { + "epoch": 0.1, + "learning_rate": 9.989411515011773e-06, + "loss": 0.3539, + "step": 783 + }, + { + "epoch": 0.1, + "learning_rate": 9.989343989043563e-06, + "loss": 0.4058, + "step": 784 + }, + { + "epoch": 0.1, + "learning_rate": 9.989276248672131e-06, + "loss": 0.3893, + "step": 785 + }, + { + "epoch": 0.1, + "learning_rate": 9.989208293900386e-06, + "loss": 0.3796, + "step": 786 + }, + { + "epoch": 0.1, + "learning_rate": 9.98914012473125e-06, + "loss": 0.3602, + "step": 787 + }, + { + "epoch": 0.1, + "learning_rate": 9.989071741167649e-06, + "loss": 0.354, + "step": 788 + }, + { + "epoch": 0.1, + "learning_rate": 9.989003143212526e-06, + "loss": 0.3395, + "step": 789 + }, + { + "epoch": 0.1, + "learning_rate": 9.988934330868826e-06, + "loss": 0.3737, + "step": 790 + }, + { + "epoch": 0.1, + "learning_rate": 9.988865304139509e-06, + "loss": 0.3987, + "step": 791 + }, + { + "epoch": 0.1, + "learning_rate": 9.988796063027534e-06, + "loss": 0.3869, + "step": 792 + }, + { + "epoch": 0.1, + "learning_rate": 9.988726607535885e-06, + "loss": 0.3899, + "step": 793 + }, + { + "epoch": 0.1, + "learning_rate": 9.988656937667544e-06, + "loss": 0.3859, + "step": 794 + }, + { + "epoch": 0.1, + "learning_rate": 9.988587053425504e-06, + "loss": 0.3633, + "step": 795 + }, + { + "epoch": 0.1, + "learning_rate": 9.988516954812767e-06, + "loss": 0.3704, + "step": 796 + }, + { + "epoch": 0.1, + "learning_rate": 9.988446641832346e-06, + "loss": 0.3935, + "step": 797 + }, + { + "epoch": 0.1, + "learning_rate": 9.988376114487264e-06, + "loss": 0.3854, + "step": 798 + }, + { + "epoch": 0.1, + "learning_rate": 9.98830537278055e-06, + "loss": 0.4206, + "step": 799 + }, + { + "epoch": 0.1, + "learning_rate": 9.988234416715246e-06, + "loss": 0.3339, + "step": 800 + }, + { + "epoch": 0.1, + "learning_rate": 9.988163246294398e-06, + "loss": 0.3845, + "step": 801 + }, + { + "epoch": 0.1, + "learning_rate": 9.988091861521067e-06, + "loss": 0.363, + "step": 802 + }, + { + "epoch": 0.1, + "learning_rate": 9.98802026239832e-06, + "loss": 0.3672, + "step": 803 + }, + { + "epoch": 0.1, + "learning_rate": 9.987948448929232e-06, + "loss": 0.3759, + "step": 804 + }, + { + "epoch": 0.1, + "learning_rate": 9.98787642111689e-06, + "loss": 0.3926, + "step": 805 + }, + { + "epoch": 0.1, + "learning_rate": 9.987804178964391e-06, + "loss": 0.3887, + "step": 806 + }, + { + "epoch": 0.1, + "learning_rate": 9.987731722474839e-06, + "loss": 0.4127, + "step": 807 + }, + { + "epoch": 0.1, + "learning_rate": 9.987659051651345e-06, + "loss": 0.3795, + "step": 808 + }, + { + "epoch": 0.1, + "learning_rate": 9.987586166497032e-06, + "loss": 0.3876, + "step": 809 + }, + { + "epoch": 0.1, + "learning_rate": 9.987513067015035e-06, + "loss": 0.361, + "step": 810 + }, + { + "epoch": 0.1, + "learning_rate": 9.987439753208494e-06, + "loss": 0.3805, + "step": 811 + }, + { + "epoch": 0.1, + "learning_rate": 9.98736622508056e-06, + "loss": 0.3683, + "step": 812 + }, + { + "epoch": 0.1, + "learning_rate": 9.98729248263439e-06, + "loss": 0.3694, + "step": 813 + }, + { + "epoch": 0.1, + "learning_rate": 9.987218525873155e-06, + "loss": 0.3913, + "step": 814 + }, + { + "epoch": 0.1, + "learning_rate": 9.987144354800035e-06, + "loss": 0.3722, + "step": 815 + }, + { + "epoch": 0.1, + "learning_rate": 9.987069969418213e-06, + "loss": 0.3747, + "step": 816 + }, + { + "epoch": 0.1, + "learning_rate": 9.986995369730887e-06, + "loss": 0.3723, + "step": 817 + }, + { + "epoch": 0.1, + "learning_rate": 9.986920555741267e-06, + "loss": 0.3798, + "step": 818 + }, + { + "epoch": 0.1, + "learning_rate": 9.98684552745256e-06, + "loss": 0.3641, + "step": 819 + }, + { + "epoch": 0.1, + "learning_rate": 9.986770284867997e-06, + "loss": 0.3854, + "step": 820 + }, + { + "epoch": 0.11, + "learning_rate": 9.986694827990807e-06, + "loss": 0.3756, + "step": 821 + }, + { + "epoch": 0.11, + "learning_rate": 9.986619156824236e-06, + "loss": 0.3698, + "step": 822 + }, + { + "epoch": 0.11, + "learning_rate": 9.986543271371532e-06, + "loss": 0.3927, + "step": 823 + }, + { + "epoch": 0.11, + "learning_rate": 9.98646717163596e-06, + "loss": 0.3592, + "step": 824 + }, + { + "epoch": 0.11, + "learning_rate": 9.986390857620787e-06, + "loss": 0.3804, + "step": 825 + }, + { + "epoch": 0.11, + "learning_rate": 9.986314329329294e-06, + "loss": 0.3626, + "step": 826 + }, + { + "epoch": 0.11, + "learning_rate": 9.986237586764768e-06, + "loss": 0.3633, + "step": 827 + }, + { + "epoch": 0.11, + "learning_rate": 9.98616062993051e-06, + "loss": 0.3735, + "step": 828 + }, + { + "epoch": 0.11, + "learning_rate": 9.986083458829824e-06, + "loss": 0.3641, + "step": 829 + }, + { + "epoch": 0.11, + "learning_rate": 9.986006073466027e-06, + "loss": 0.3921, + "step": 830 + }, + { + "epoch": 0.11, + "learning_rate": 9.985928473842445e-06, + "loss": 0.3953, + "step": 831 + }, + { + "epoch": 0.11, + "learning_rate": 9.985850659962411e-06, + "loss": 0.3743, + "step": 832 + }, + { + "epoch": 0.11, + "learning_rate": 9.985772631829272e-06, + "loss": 0.3769, + "step": 833 + }, + { + "epoch": 0.11, + "learning_rate": 9.985694389446378e-06, + "loss": 0.3821, + "step": 834 + }, + { + "epoch": 0.11, + "learning_rate": 9.985615932817092e-06, + "loss": 0.3841, + "step": 835 + }, + { + "epoch": 0.11, + "learning_rate": 9.985537261944787e-06, + "loss": 0.3872, + "step": 836 + }, + { + "epoch": 0.11, + "learning_rate": 9.985458376832842e-06, + "loss": 0.3683, + "step": 837 + }, + { + "epoch": 0.11, + "learning_rate": 9.985379277484646e-06, + "loss": 0.3354, + "step": 838 + }, + { + "epoch": 0.11, + "learning_rate": 9.9852999639036e-06, + "loss": 0.3656, + "step": 839 + }, + { + "epoch": 0.11, + "learning_rate": 9.985220436093112e-06, + "loss": 0.3735, + "step": 840 + }, + { + "epoch": 0.11, + "learning_rate": 9.985140694056601e-06, + "loss": 0.3901, + "step": 841 + }, + { + "epoch": 0.11, + "learning_rate": 9.985060737797489e-06, + "loss": 0.3852, + "step": 842 + }, + { + "epoch": 0.11, + "learning_rate": 9.984980567319216e-06, + "loss": 0.3709, + "step": 843 + }, + { + "epoch": 0.11, + "learning_rate": 9.984900182625226e-06, + "loss": 0.3986, + "step": 844 + }, + { + "epoch": 0.11, + "learning_rate": 9.984819583718973e-06, + "loss": 0.3429, + "step": 845 + }, + { + "epoch": 0.11, + "learning_rate": 9.984738770603921e-06, + "loss": 0.3692, + "step": 846 + }, + { + "epoch": 0.11, + "learning_rate": 9.984657743283543e-06, + "loss": 0.3838, + "step": 847 + }, + { + "epoch": 0.11, + "learning_rate": 9.984576501761319e-06, + "loss": 0.4031, + "step": 848 + }, + { + "epoch": 0.11, + "learning_rate": 9.98449504604074e-06, + "loss": 0.3741, + "step": 849 + }, + { + "epoch": 0.11, + "learning_rate": 9.984413376125312e-06, + "loss": 0.3657, + "step": 850 + }, + { + "epoch": 0.11, + "learning_rate": 9.984331492018537e-06, + "loss": 0.3603, + "step": 851 + }, + { + "epoch": 0.11, + "learning_rate": 9.984249393723939e-06, + "loss": 0.4364, + "step": 852 + }, + { + "epoch": 0.11, + "learning_rate": 9.984167081245044e-06, + "loss": 0.3517, + "step": 853 + }, + { + "epoch": 0.11, + "learning_rate": 9.984084554585387e-06, + "loss": 0.3608, + "step": 854 + }, + { + "epoch": 0.11, + "learning_rate": 9.984001813748519e-06, + "loss": 0.3634, + "step": 855 + }, + { + "epoch": 0.11, + "learning_rate": 9.98391885873799e-06, + "loss": 0.3715, + "step": 856 + }, + { + "epoch": 0.11, + "learning_rate": 9.98383568955737e-06, + "loss": 0.3639, + "step": 857 + }, + { + "epoch": 0.11, + "learning_rate": 9.983752306210233e-06, + "loss": 0.3574, + "step": 858 + }, + { + "epoch": 0.11, + "learning_rate": 9.983668708700156e-06, + "loss": 0.339, + "step": 859 + }, + { + "epoch": 0.11, + "learning_rate": 9.983584897030737e-06, + "loss": 0.3586, + "step": 860 + }, + { + "epoch": 0.11, + "learning_rate": 9.983500871205577e-06, + "loss": 0.3484, + "step": 861 + }, + { + "epoch": 0.11, + "learning_rate": 9.983416631228284e-06, + "loss": 0.3532, + "step": 862 + }, + { + "epoch": 0.11, + "learning_rate": 9.98333217710248e-06, + "loss": 0.3572, + "step": 863 + }, + { + "epoch": 0.11, + "learning_rate": 9.983247508831795e-06, + "loss": 0.3696, + "step": 864 + }, + { + "epoch": 0.11, + "learning_rate": 9.983162626419866e-06, + "loss": 0.3692, + "step": 865 + }, + { + "epoch": 0.11, + "learning_rate": 9.98307752987034e-06, + "loss": 0.378, + "step": 866 + }, + { + "epoch": 0.11, + "learning_rate": 9.982992219186876e-06, + "loss": 0.3795, + "step": 867 + }, + { + "epoch": 0.11, + "learning_rate": 9.982906694373136e-06, + "loss": 0.3597, + "step": 868 + }, + { + "epoch": 0.11, + "learning_rate": 9.9828209554328e-06, + "loss": 0.3558, + "step": 869 + }, + { + "epoch": 0.11, + "learning_rate": 9.98273500236955e-06, + "loss": 0.3991, + "step": 870 + }, + { + "epoch": 0.11, + "learning_rate": 9.98264883518708e-06, + "loss": 0.3969, + "step": 871 + }, + { + "epoch": 0.11, + "learning_rate": 9.98256245388909e-06, + "loss": 0.3905, + "step": 872 + }, + { + "epoch": 0.11, + "learning_rate": 9.982475858479298e-06, + "loss": 0.3457, + "step": 873 + }, + { + "epoch": 0.11, + "learning_rate": 9.982389048961421e-06, + "loss": 0.3776, + "step": 874 + }, + { + "epoch": 0.11, + "learning_rate": 9.98230202533919e-06, + "loss": 0.3705, + "step": 875 + }, + { + "epoch": 0.11, + "learning_rate": 9.982214787616345e-06, + "loss": 0.3636, + "step": 876 + }, + { + "epoch": 0.11, + "learning_rate": 9.982127335796631e-06, + "loss": 0.3702, + "step": 877 + }, + { + "epoch": 0.11, + "learning_rate": 9.982039669883815e-06, + "loss": 0.3568, + "step": 878 + }, + { + "epoch": 0.11, + "learning_rate": 9.981951789881657e-06, + "loss": 0.373, + "step": 879 + }, + { + "epoch": 0.11, + "learning_rate": 9.981863695793934e-06, + "loss": 0.389, + "step": 880 + }, + { + "epoch": 0.11, + "learning_rate": 9.981775387624433e-06, + "loss": 0.3622, + "step": 881 + }, + { + "epoch": 0.11, + "learning_rate": 9.98168686537695e-06, + "loss": 0.3832, + "step": 882 + }, + { + "epoch": 0.11, + "learning_rate": 9.981598129055286e-06, + "loss": 0.388, + "step": 883 + }, + { + "epoch": 0.11, + "learning_rate": 9.981509178663256e-06, + "loss": 0.3562, + "step": 884 + }, + { + "epoch": 0.11, + "learning_rate": 9.981420014204682e-06, + "loss": 0.3836, + "step": 885 + }, + { + "epoch": 0.11, + "learning_rate": 9.981330635683396e-06, + "loss": 0.3746, + "step": 886 + }, + { + "epoch": 0.11, + "learning_rate": 9.981241043103239e-06, + "loss": 0.3528, + "step": 887 + }, + { + "epoch": 0.11, + "learning_rate": 9.981151236468061e-06, + "loss": 0.3634, + "step": 888 + }, + { + "epoch": 0.11, + "learning_rate": 9.98106121578172e-06, + "loss": 0.3724, + "step": 889 + }, + { + "epoch": 0.11, + "learning_rate": 9.980970981048086e-06, + "loss": 0.3969, + "step": 890 + }, + { + "epoch": 0.11, + "learning_rate": 9.980880532271033e-06, + "loss": 0.367, + "step": 891 + }, + { + "epoch": 0.11, + "learning_rate": 9.980789869454454e-06, + "loss": 0.4042, + "step": 892 + }, + { + "epoch": 0.11, + "learning_rate": 9.980698992602241e-06, + "loss": 0.3855, + "step": 893 + }, + { + "epoch": 0.11, + "learning_rate": 9.980607901718297e-06, + "loss": 0.3833, + "step": 894 + }, + { + "epoch": 0.11, + "learning_rate": 9.98051659680654e-06, + "loss": 0.3744, + "step": 895 + }, + { + "epoch": 0.11, + "learning_rate": 9.980425077870895e-06, + "loss": 0.3575, + "step": 896 + }, + { + "epoch": 0.11, + "learning_rate": 9.98033334491529e-06, + "loss": 0.3689, + "step": 897 + }, + { + "epoch": 0.11, + "learning_rate": 9.98024139794367e-06, + "loss": 0.3534, + "step": 898 + }, + { + "epoch": 0.12, + "learning_rate": 9.980149236959986e-06, + "loss": 0.3425, + "step": 899 + }, + { + "epoch": 0.12, + "learning_rate": 9.980056861968197e-06, + "loss": 0.3729, + "step": 900 + }, + { + "epoch": 0.12, + "learning_rate": 9.979964272972275e-06, + "loss": 0.3689, + "step": 901 + }, + { + "epoch": 0.12, + "learning_rate": 9.979871469976197e-06, + "loss": 0.388, + "step": 902 + }, + { + "epoch": 0.12, + "learning_rate": 9.979778452983949e-06, + "loss": 0.3909, + "step": 903 + }, + { + "epoch": 0.12, + "learning_rate": 9.979685221999532e-06, + "loss": 0.3477, + "step": 904 + }, + { + "epoch": 0.12, + "learning_rate": 9.979591777026952e-06, + "loss": 0.3954, + "step": 905 + }, + { + "epoch": 0.12, + "learning_rate": 9.97949811807022e-06, + "loss": 0.3691, + "step": 906 + }, + { + "epoch": 0.12, + "learning_rate": 9.979404245133367e-06, + "loss": 0.3725, + "step": 907 + }, + { + "epoch": 0.12, + "learning_rate": 9.979310158220422e-06, + "loss": 0.3705, + "step": 908 + }, + { + "epoch": 0.12, + "learning_rate": 9.97921585733543e-06, + "loss": 0.3539, + "step": 909 + }, + { + "epoch": 0.12, + "learning_rate": 9.979121342482442e-06, + "loss": 0.3733, + "step": 910 + }, + { + "epoch": 0.12, + "learning_rate": 9.979026613665523e-06, + "loss": 0.3611, + "step": 911 + }, + { + "epoch": 0.12, + "learning_rate": 9.978931670888741e-06, + "loss": 0.3807, + "step": 912 + }, + { + "epoch": 0.12, + "learning_rate": 9.978836514156177e-06, + "loss": 0.3791, + "step": 913 + }, + { + "epoch": 0.12, + "learning_rate": 9.97874114347192e-06, + "loss": 0.3629, + "step": 914 + }, + { + "epoch": 0.12, + "learning_rate": 9.978645558840066e-06, + "loss": 0.3704, + "step": 915 + }, + { + "epoch": 0.12, + "learning_rate": 9.978549760264724e-06, + "loss": 0.3426, + "step": 916 + }, + { + "epoch": 0.12, + "learning_rate": 9.978453747750012e-06, + "loss": 0.3705, + "step": 917 + }, + { + "epoch": 0.12, + "learning_rate": 9.978357521300054e-06, + "loss": 0.3737, + "step": 918 + }, + { + "epoch": 0.12, + "learning_rate": 9.978261080918988e-06, + "loss": 0.3869, + "step": 919 + }, + { + "epoch": 0.12, + "learning_rate": 9.978164426610956e-06, + "loss": 0.3566, + "step": 920 + }, + { + "epoch": 0.12, + "learning_rate": 9.97806755838011e-06, + "loss": 0.3718, + "step": 921 + }, + { + "epoch": 0.12, + "learning_rate": 9.977970476230615e-06, + "loss": 0.3746, + "step": 922 + }, + { + "epoch": 0.12, + "learning_rate": 9.977873180166641e-06, + "loss": 0.3967, + "step": 923 + }, + { + "epoch": 0.12, + "learning_rate": 9.977775670192373e-06, + "loss": 0.3447, + "step": 924 + }, + { + "epoch": 0.12, + "learning_rate": 9.977677946311995e-06, + "loss": 0.359, + "step": 925 + }, + { + "epoch": 0.12, + "learning_rate": 9.977580008529713e-06, + "loss": 0.3512, + "step": 926 + }, + { + "epoch": 0.12, + "learning_rate": 9.977481856849729e-06, + "loss": 0.348, + "step": 927 + }, + { + "epoch": 0.12, + "learning_rate": 9.977383491276267e-06, + "loss": 0.3606, + "step": 928 + }, + { + "epoch": 0.12, + "learning_rate": 9.977284911813549e-06, + "loss": 0.365, + "step": 929 + }, + { + "epoch": 0.12, + "learning_rate": 9.977186118465813e-06, + "loss": 0.3717, + "step": 930 + }, + { + "epoch": 0.12, + "learning_rate": 9.977087111237307e-06, + "loss": 0.3784, + "step": 931 + }, + { + "epoch": 0.12, + "learning_rate": 9.976987890132283e-06, + "loss": 0.3628, + "step": 932 + }, + { + "epoch": 0.12, + "learning_rate": 9.976888455155002e-06, + "loss": 0.4007, + "step": 933 + }, + { + "epoch": 0.12, + "learning_rate": 9.976788806309742e-06, + "loss": 0.3581, + "step": 934 + }, + { + "epoch": 0.12, + "learning_rate": 9.976688943600786e-06, + "loss": 0.3623, + "step": 935 + }, + { + "epoch": 0.12, + "learning_rate": 9.97658886703242e-06, + "loss": 0.3533, + "step": 936 + }, + { + "epoch": 0.12, + "learning_rate": 9.976488576608945e-06, + "loss": 0.3608, + "step": 937 + }, + { + "epoch": 0.12, + "learning_rate": 9.976388072334674e-06, + "loss": 0.3832, + "step": 938 + }, + { + "epoch": 0.12, + "learning_rate": 9.976287354213924e-06, + "loss": 0.3969, + "step": 939 + }, + { + "epoch": 0.12, + "learning_rate": 9.976186422251026e-06, + "loss": 0.3554, + "step": 940 + }, + { + "epoch": 0.12, + "learning_rate": 9.976085276450312e-06, + "loss": 0.3694, + "step": 941 + }, + { + "epoch": 0.12, + "learning_rate": 9.975983916816134e-06, + "loss": 0.3855, + "step": 942 + }, + { + "epoch": 0.12, + "learning_rate": 9.975882343352843e-06, + "loss": 0.3625, + "step": 943 + }, + { + "epoch": 0.12, + "learning_rate": 9.975780556064806e-06, + "loss": 0.363, + "step": 944 + }, + { + "epoch": 0.12, + "learning_rate": 9.975678554956397e-06, + "loss": 0.3765, + "step": 945 + }, + { + "epoch": 0.12, + "learning_rate": 9.975576340032e-06, + "loss": 0.3441, + "step": 946 + }, + { + "epoch": 0.12, + "learning_rate": 9.975473911296005e-06, + "loss": 0.3925, + "step": 947 + }, + { + "epoch": 0.12, + "learning_rate": 9.975371268752816e-06, + "loss": 0.3555, + "step": 948 + }, + { + "epoch": 0.12, + "learning_rate": 9.975268412406842e-06, + "loss": 0.3566, + "step": 949 + }, + { + "epoch": 0.12, + "learning_rate": 9.975165342262505e-06, + "loss": 0.395, + "step": 950 + }, + { + "epoch": 0.12, + "learning_rate": 9.975062058324232e-06, + "loss": 0.3566, + "step": 951 + }, + { + "epoch": 0.12, + "learning_rate": 9.974958560596464e-06, + "loss": 0.36, + "step": 952 + }, + { + "epoch": 0.12, + "learning_rate": 9.974854849083645e-06, + "loss": 0.3597, + "step": 953 + }, + { + "epoch": 0.12, + "learning_rate": 9.974750923790234e-06, + "loss": 0.3338, + "step": 954 + }, + { + "epoch": 0.12, + "learning_rate": 9.974646784720696e-06, + "loss": 0.3542, + "step": 955 + }, + { + "epoch": 0.12, + "learning_rate": 9.974542431879507e-06, + "loss": 0.3744, + "step": 956 + }, + { + "epoch": 0.12, + "learning_rate": 9.974437865271152e-06, + "loss": 0.3749, + "step": 957 + }, + { + "epoch": 0.12, + "learning_rate": 9.97433308490012e-06, + "loss": 0.3816, + "step": 958 + }, + { + "epoch": 0.12, + "learning_rate": 9.97422809077092e-06, + "loss": 0.3808, + "step": 959 + }, + { + "epoch": 0.12, + "learning_rate": 9.97412288288806e-06, + "loss": 0.3449, + "step": 960 + }, + { + "epoch": 0.12, + "learning_rate": 9.974017461256062e-06, + "loss": 0.3169, + "step": 961 + }, + { + "epoch": 0.12, + "learning_rate": 9.973911825879454e-06, + "loss": 0.3594, + "step": 962 + }, + { + "epoch": 0.12, + "learning_rate": 9.97380597676278e-06, + "loss": 0.3712, + "step": 963 + }, + { + "epoch": 0.12, + "learning_rate": 9.973699913910584e-06, + "loss": 0.392, + "step": 964 + }, + { + "epoch": 0.12, + "learning_rate": 9.973593637327427e-06, + "loss": 0.3508, + "step": 965 + }, + { + "epoch": 0.12, + "learning_rate": 9.973487147017874e-06, + "loss": 0.376, + "step": 966 + }, + { + "epoch": 0.12, + "learning_rate": 9.9733804429865e-06, + "loss": 0.3758, + "step": 967 + }, + { + "epoch": 0.12, + "learning_rate": 9.973273525237895e-06, + "loss": 0.3604, + "step": 968 + }, + { + "epoch": 0.12, + "learning_rate": 9.97316639377665e-06, + "loss": 0.3572, + "step": 969 + }, + { + "epoch": 0.12, + "learning_rate": 9.973059048607367e-06, + "loss": 0.3606, + "step": 970 + }, + { + "epoch": 0.12, + "learning_rate": 9.972951489734664e-06, + "loss": 0.3642, + "step": 971 + }, + { + "epoch": 0.12, + "learning_rate": 9.972843717163159e-06, + "loss": 0.356, + "step": 972 + }, + { + "epoch": 0.12, + "learning_rate": 9.972735730897484e-06, + "loss": 0.3611, + "step": 973 + }, + { + "epoch": 0.12, + "learning_rate": 9.97262753094228e-06, + "loss": 0.36, + "step": 974 + }, + { + "epoch": 0.12, + "learning_rate": 9.972519117302195e-06, + "loss": 0.3603, + "step": 975 + }, + { + "epoch": 0.12, + "learning_rate": 9.972410489981892e-06, + "loss": 0.3679, + "step": 976 + }, + { + "epoch": 0.13, + "learning_rate": 9.972301648986033e-06, + "loss": 0.3436, + "step": 977 + }, + { + "epoch": 0.13, + "learning_rate": 9.972192594319301e-06, + "loss": 0.386, + "step": 978 + }, + { + "epoch": 0.13, + "learning_rate": 9.972083325986377e-06, + "loss": 0.3871, + "step": 979 + }, + { + "epoch": 0.13, + "learning_rate": 9.97197384399196e-06, + "loss": 0.3504, + "step": 980 + }, + { + "epoch": 0.13, + "learning_rate": 9.971864148340755e-06, + "loss": 0.392, + "step": 981 + }, + { + "epoch": 0.13, + "learning_rate": 9.971754239037474e-06, + "loss": 0.3599, + "step": 982 + }, + { + "epoch": 0.13, + "learning_rate": 9.971644116086841e-06, + "loss": 0.3523, + "step": 983 + }, + { + "epoch": 0.13, + "learning_rate": 9.971533779493586e-06, + "loss": 0.3939, + "step": 984 + }, + { + "epoch": 0.13, + "learning_rate": 9.971423229262454e-06, + "loss": 0.3637, + "step": 985 + }, + { + "epoch": 0.13, + "learning_rate": 9.971312465398192e-06, + "loss": 0.3794, + "step": 986 + }, + { + "epoch": 0.13, + "learning_rate": 9.971201487905563e-06, + "loss": 0.3761, + "step": 987 + }, + { + "epoch": 0.13, + "learning_rate": 9.971090296789336e-06, + "loss": 0.3562, + "step": 988 + }, + { + "epoch": 0.13, + "learning_rate": 9.970978892054286e-06, + "loss": 0.3689, + "step": 989 + }, + { + "epoch": 0.13, + "learning_rate": 9.970867273705203e-06, + "loss": 0.3812, + "step": 990 + }, + { + "epoch": 0.13, + "learning_rate": 9.970755441746882e-06, + "loss": 0.3886, + "step": 991 + }, + { + "epoch": 0.13, + "learning_rate": 9.970643396184128e-06, + "loss": 0.3722, + "step": 992 + }, + { + "epoch": 0.13, + "learning_rate": 9.970531137021759e-06, + "loss": 0.3767, + "step": 993 + }, + { + "epoch": 0.13, + "learning_rate": 9.970418664264596e-06, + "loss": 0.3449, + "step": 994 + }, + { + "epoch": 0.13, + "learning_rate": 9.970305977917473e-06, + "loss": 0.373, + "step": 995 + }, + { + "epoch": 0.13, + "learning_rate": 9.970193077985235e-06, + "loss": 0.3913, + "step": 996 + }, + { + "epoch": 0.13, + "learning_rate": 9.97007996447273e-06, + "loss": 0.3716, + "step": 997 + }, + { + "epoch": 0.13, + "learning_rate": 9.969966637384818e-06, + "loss": 0.374, + "step": 998 + }, + { + "epoch": 0.13, + "learning_rate": 9.969853096726372e-06, + "loss": 0.3775, + "step": 999 + }, + { + "epoch": 0.13, + "learning_rate": 9.969739342502272e-06, + "loss": 0.3794, + "step": 1000 + }, + { + "epoch": 0.13, + "learning_rate": 9.969625374717401e-06, + "loss": 0.3407, + "step": 1001 + }, + { + "epoch": 0.13, + "learning_rate": 9.969511193376661e-06, + "loss": 0.383, + "step": 1002 + }, + { + "epoch": 0.13, + "learning_rate": 9.969396798484958e-06, + "loss": 0.3731, + "step": 1003 + }, + { + "epoch": 0.13, + "learning_rate": 9.969282190047207e-06, + "loss": 0.3171, + "step": 1004 + }, + { + "epoch": 0.13, + "learning_rate": 9.969167368068334e-06, + "loss": 0.364, + "step": 1005 + }, + { + "epoch": 0.13, + "learning_rate": 9.96905233255327e-06, + "loss": 0.355, + "step": 1006 + }, + { + "epoch": 0.13, + "learning_rate": 9.968937083506962e-06, + "loss": 0.3891, + "step": 1007 + }, + { + "epoch": 0.13, + "learning_rate": 9.96882162093436e-06, + "loss": 0.3776, + "step": 1008 + }, + { + "epoch": 0.13, + "learning_rate": 9.968705944840428e-06, + "loss": 0.3598, + "step": 1009 + }, + { + "epoch": 0.13, + "learning_rate": 9.968590055230135e-06, + "loss": 0.3768, + "step": 1010 + }, + { + "epoch": 0.13, + "learning_rate": 9.968473952108462e-06, + "loss": 0.3658, + "step": 1011 + }, + { + "epoch": 0.13, + "learning_rate": 9.968357635480397e-06, + "loss": 0.3369, + "step": 1012 + }, + { + "epoch": 0.13, + "learning_rate": 9.96824110535094e-06, + "loss": 0.3845, + "step": 1013 + }, + { + "epoch": 0.13, + "learning_rate": 9.968124361725098e-06, + "loss": 0.3692, + "step": 1014 + }, + { + "epoch": 0.13, + "learning_rate": 9.968007404607887e-06, + "loss": 0.3599, + "step": 1015 + }, + { + "epoch": 0.13, + "learning_rate": 9.967890234004335e-06, + "loss": 0.3935, + "step": 1016 + }, + { + "epoch": 0.13, + "learning_rate": 9.967772849919474e-06, + "loss": 0.3637, + "step": 1017 + }, + { + "epoch": 0.13, + "learning_rate": 9.96765525235835e-06, + "loss": 0.3717, + "step": 1018 + }, + { + "epoch": 0.13, + "learning_rate": 9.967537441326018e-06, + "loss": 0.3854, + "step": 1019 + }, + { + "epoch": 0.13, + "learning_rate": 9.967419416827537e-06, + "loss": 0.4018, + "step": 1020 + }, + { + "epoch": 0.13, + "learning_rate": 9.967301178867981e-06, + "loss": 0.3653, + "step": 1021 + }, + { + "epoch": 0.13, + "learning_rate": 9.96718272745243e-06, + "loss": 0.3722, + "step": 1022 + }, + { + "epoch": 0.13, + "learning_rate": 9.967064062585977e-06, + "loss": 0.3598, + "step": 1023 + }, + { + "epoch": 0.13, + "learning_rate": 9.966945184273716e-06, + "loss": 0.3698, + "step": 1024 + }, + { + "epoch": 0.13, + "learning_rate": 9.96682609252076e-06, + "loss": 0.3456, + "step": 1025 + }, + { + "epoch": 0.13, + "learning_rate": 9.966706787332224e-06, + "loss": 0.3297, + "step": 1026 + }, + { + "epoch": 0.13, + "learning_rate": 9.966587268713237e-06, + "loss": 0.3374, + "step": 1027 + }, + { + "epoch": 0.13, + "learning_rate": 9.966467536668933e-06, + "loss": 0.3862, + "step": 1028 + }, + { + "epoch": 0.13, + "learning_rate": 9.966347591204459e-06, + "loss": 0.3403, + "step": 1029 + }, + { + "epoch": 0.13, + "learning_rate": 9.96622743232497e-06, + "loss": 0.3843, + "step": 1030 + }, + { + "epoch": 0.13, + "learning_rate": 9.966107060035624e-06, + "loss": 0.3795, + "step": 1031 + }, + { + "epoch": 0.13, + "learning_rate": 9.9659864743416e-06, + "loss": 0.3878, + "step": 1032 + }, + { + "epoch": 0.13, + "learning_rate": 9.965865675248077e-06, + "loss": 0.3641, + "step": 1033 + }, + { + "epoch": 0.13, + "learning_rate": 9.965744662760246e-06, + "loss": 0.3566, + "step": 1034 + }, + { + "epoch": 0.13, + "learning_rate": 9.965623436883307e-06, + "loss": 0.3458, + "step": 1035 + }, + { + "epoch": 0.13, + "learning_rate": 9.96550199762247e-06, + "loss": 0.3932, + "step": 1036 + }, + { + "epoch": 0.13, + "learning_rate": 9.965380344982955e-06, + "loss": 0.3539, + "step": 1037 + }, + { + "epoch": 0.13, + "learning_rate": 9.965258478969985e-06, + "loss": 0.3518, + "step": 1038 + }, + { + "epoch": 0.13, + "learning_rate": 9.965136399588803e-06, + "loss": 0.3363, + "step": 1039 + }, + { + "epoch": 0.13, + "learning_rate": 9.96501410684465e-06, + "loss": 0.3754, + "step": 1040 + }, + { + "epoch": 0.13, + "learning_rate": 9.964891600742785e-06, + "loss": 0.3793, + "step": 1041 + }, + { + "epoch": 0.13, + "learning_rate": 9.96476888128847e-06, + "loss": 0.4054, + "step": 1042 + }, + { + "epoch": 0.13, + "learning_rate": 9.964645948486978e-06, + "loss": 0.365, + "step": 1043 + }, + { + "epoch": 0.13, + "learning_rate": 9.964522802343593e-06, + "loss": 0.3357, + "step": 1044 + }, + { + "epoch": 0.13, + "learning_rate": 9.964399442863609e-06, + "loss": 0.3634, + "step": 1045 + }, + { + "epoch": 0.13, + "learning_rate": 9.96427587005232e-06, + "loss": 0.3511, + "step": 1046 + }, + { + "epoch": 0.13, + "learning_rate": 9.964152083915045e-06, + "loss": 0.3807, + "step": 1047 + }, + { + "epoch": 0.13, + "learning_rate": 9.964028084457098e-06, + "loss": 0.3699, + "step": 1048 + }, + { + "epoch": 0.13, + "learning_rate": 9.963903871683806e-06, + "loss": 0.381, + "step": 1049 + }, + { + "epoch": 0.13, + "learning_rate": 9.963779445600512e-06, + "loss": 0.38, + "step": 1050 + }, + { + "epoch": 0.13, + "learning_rate": 9.963654806212561e-06, + "loss": 0.3888, + "step": 1051 + }, + { + "epoch": 0.13, + "learning_rate": 9.963529953525307e-06, + "loss": 0.3603, + "step": 1052 + }, + { + "epoch": 0.13, + "learning_rate": 9.963404887544117e-06, + "loss": 0.3689, + "step": 1053 + }, + { + "epoch": 0.13, + "learning_rate": 9.963279608274364e-06, + "loss": 0.3771, + "step": 1054 + }, + { + "epoch": 0.14, + "learning_rate": 9.963154115721433e-06, + "loss": 0.4064, + "step": 1055 + }, + { + "epoch": 0.14, + "learning_rate": 9.963028409890716e-06, + "loss": 0.3667, + "step": 1056 + }, + { + "epoch": 0.14, + "learning_rate": 9.962902490787616e-06, + "loss": 0.3739, + "step": 1057 + }, + { + "epoch": 0.14, + "learning_rate": 9.962776358417543e-06, + "loss": 0.4068, + "step": 1058 + }, + { + "epoch": 0.14, + "learning_rate": 9.962650012785917e-06, + "loss": 0.3711, + "step": 1059 + }, + { + "epoch": 0.14, + "learning_rate": 9.962523453898166e-06, + "loss": 0.3768, + "step": 1060 + }, + { + "epoch": 0.14, + "learning_rate": 9.96239668175973e-06, + "loss": 0.3988, + "step": 1061 + }, + { + "epoch": 0.14, + "learning_rate": 9.962269696376059e-06, + "loss": 0.361, + "step": 1062 + }, + { + "epoch": 0.14, + "learning_rate": 9.962142497752605e-06, + "loss": 0.3563, + "step": 1063 + }, + { + "epoch": 0.14, + "learning_rate": 9.962015085894838e-06, + "loss": 0.3971, + "step": 1064 + }, + { + "epoch": 0.14, + "learning_rate": 9.961887460808232e-06, + "loss": 0.3585, + "step": 1065 + }, + { + "epoch": 0.14, + "learning_rate": 9.96175962249827e-06, + "loss": 0.3863, + "step": 1066 + }, + { + "epoch": 0.14, + "learning_rate": 9.961631570970449e-06, + "loss": 0.3775, + "step": 1067 + }, + { + "epoch": 0.14, + "learning_rate": 9.961503306230267e-06, + "loss": 0.3963, + "step": 1068 + }, + { + "epoch": 0.14, + "learning_rate": 9.961374828283239e-06, + "loss": 0.3307, + "step": 1069 + }, + { + "epoch": 0.14, + "learning_rate": 9.961246137134883e-06, + "loss": 0.3734, + "step": 1070 + }, + { + "epoch": 0.14, + "learning_rate": 9.961117232790734e-06, + "loss": 0.3659, + "step": 1071 + }, + { + "epoch": 0.14, + "learning_rate": 9.960988115256328e-06, + "loss": 0.3704, + "step": 1072 + }, + { + "epoch": 0.14, + "learning_rate": 9.960858784537213e-06, + "loss": 0.379, + "step": 1073 + }, + { + "epoch": 0.14, + "learning_rate": 9.960729240638947e-06, + "loss": 0.3573, + "step": 1074 + }, + { + "epoch": 0.14, + "learning_rate": 9.9605994835671e-06, + "loss": 0.3732, + "step": 1075 + }, + { + "epoch": 0.14, + "learning_rate": 9.960469513327242e-06, + "loss": 0.3897, + "step": 1076 + }, + { + "epoch": 0.14, + "learning_rate": 9.960339329924964e-06, + "loss": 0.3844, + "step": 1077 + }, + { + "epoch": 0.14, + "learning_rate": 9.960208933365857e-06, + "loss": 0.3603, + "step": 1078 + }, + { + "epoch": 0.14, + "learning_rate": 9.960078323655524e-06, + "loss": 0.3696, + "step": 1079 + }, + { + "epoch": 0.14, + "learning_rate": 9.95994750079958e-06, + "loss": 0.3635, + "step": 1080 + }, + { + "epoch": 0.14, + "learning_rate": 9.959816464803647e-06, + "loss": 0.3581, + "step": 1081 + }, + { + "epoch": 0.14, + "learning_rate": 9.959685215673351e-06, + "loss": 0.3694, + "step": 1082 + }, + { + "epoch": 0.14, + "learning_rate": 9.959553753414338e-06, + "loss": 0.3624, + "step": 1083 + }, + { + "epoch": 0.14, + "learning_rate": 9.959422078032253e-06, + "loss": 0.3388, + "step": 1084 + }, + { + "epoch": 0.14, + "learning_rate": 9.959290189532757e-06, + "loss": 0.3543, + "step": 1085 + }, + { + "epoch": 0.14, + "learning_rate": 9.959158087921516e-06, + "loss": 0.3709, + "step": 1086 + }, + { + "epoch": 0.14, + "learning_rate": 9.95902577320421e-06, + "loss": 0.3581, + "step": 1087 + }, + { + "epoch": 0.14, + "learning_rate": 9.95889324538652e-06, + "loss": 0.3739, + "step": 1088 + }, + { + "epoch": 0.14, + "learning_rate": 9.958760504474144e-06, + "loss": 0.3668, + "step": 1089 + }, + { + "epoch": 0.14, + "learning_rate": 9.958627550472784e-06, + "loss": 0.3653, + "step": 1090 + }, + { + "epoch": 0.14, + "learning_rate": 9.958494383388155e-06, + "loss": 0.3637, + "step": 1091 + }, + { + "epoch": 0.14, + "learning_rate": 9.958361003225979e-06, + "loss": 0.3505, + "step": 1092 + }, + { + "epoch": 0.14, + "learning_rate": 9.958227409991988e-06, + "loss": 0.3364, + "step": 1093 + }, + { + "epoch": 0.14, + "learning_rate": 9.958093603691923e-06, + "loss": 0.3922, + "step": 1094 + }, + { + "epoch": 0.14, + "learning_rate": 9.957959584331533e-06, + "loss": 0.4, + "step": 1095 + }, + { + "epoch": 0.14, + "learning_rate": 9.957825351916579e-06, + "loss": 0.3485, + "step": 1096 + }, + { + "epoch": 0.14, + "learning_rate": 9.957690906452827e-06, + "loss": 0.3697, + "step": 1097 + }, + { + "epoch": 0.14, + "learning_rate": 9.957556247946057e-06, + "loss": 0.3253, + "step": 1098 + }, + { + "epoch": 0.14, + "learning_rate": 9.957421376402053e-06, + "loss": 0.3458, + "step": 1099 + }, + { + "epoch": 0.14, + "learning_rate": 9.95728629182661e-06, + "loss": 0.3645, + "step": 1100 + }, + { + "epoch": 0.14, + "learning_rate": 9.957150994225535e-06, + "loss": 0.4142, + "step": 1101 + }, + { + "epoch": 0.14, + "learning_rate": 9.957015483604643e-06, + "loss": 0.3591, + "step": 1102 + }, + { + "epoch": 0.14, + "learning_rate": 9.956879759969755e-06, + "loss": 0.3594, + "step": 1103 + }, + { + "epoch": 0.14, + "learning_rate": 9.956743823326704e-06, + "loss": 0.4016, + "step": 1104 + }, + { + "epoch": 0.14, + "learning_rate": 9.956607673681334e-06, + "loss": 0.3838, + "step": 1105 + }, + { + "epoch": 0.14, + "learning_rate": 9.956471311039491e-06, + "loss": 0.3694, + "step": 1106 + }, + { + "epoch": 0.14, + "learning_rate": 9.956334735407037e-06, + "loss": 0.3569, + "step": 1107 + }, + { + "epoch": 0.14, + "learning_rate": 9.95619794678984e-06, + "loss": 0.3701, + "step": 1108 + }, + { + "epoch": 0.14, + "learning_rate": 9.956060945193781e-06, + "loss": 0.3691, + "step": 1109 + }, + { + "epoch": 0.14, + "learning_rate": 9.955923730624745e-06, + "loss": 0.3527, + "step": 1110 + }, + { + "epoch": 0.14, + "learning_rate": 9.95578630308863e-06, + "loss": 0.3521, + "step": 1111 + }, + { + "epoch": 0.14, + "learning_rate": 9.95564866259134e-06, + "loss": 0.3655, + "step": 1112 + }, + { + "epoch": 0.14, + "learning_rate": 9.95551080913879e-06, + "loss": 0.3426, + "step": 1113 + }, + { + "epoch": 0.14, + "learning_rate": 9.955372742736903e-06, + "loss": 0.3622, + "step": 1114 + }, + { + "epoch": 0.14, + "learning_rate": 9.955234463391612e-06, + "loss": 0.3782, + "step": 1115 + }, + { + "epoch": 0.14, + "learning_rate": 9.955095971108863e-06, + "loss": 0.39, + "step": 1116 + }, + { + "epoch": 0.14, + "learning_rate": 9.954957265894602e-06, + "loss": 0.3601, + "step": 1117 + }, + { + "epoch": 0.14, + "learning_rate": 9.954818347754795e-06, + "loss": 0.3603, + "step": 1118 + }, + { + "epoch": 0.14, + "learning_rate": 9.954679216695406e-06, + "loss": 0.3617, + "step": 1119 + }, + { + "epoch": 0.14, + "learning_rate": 9.954539872722417e-06, + "loss": 0.3431, + "step": 1120 + }, + { + "epoch": 0.14, + "learning_rate": 9.954400315841817e-06, + "loss": 0.3709, + "step": 1121 + }, + { + "epoch": 0.14, + "learning_rate": 9.9542605460596e-06, + "loss": 0.3425, + "step": 1122 + }, + { + "epoch": 0.14, + "learning_rate": 9.954120563381772e-06, + "loss": 0.3668, + "step": 1123 + }, + { + "epoch": 0.14, + "learning_rate": 9.953980367814354e-06, + "loss": 0.3363, + "step": 1124 + }, + { + "epoch": 0.14, + "learning_rate": 9.953839959363363e-06, + "loss": 0.3753, + "step": 1125 + }, + { + "epoch": 0.14, + "learning_rate": 9.953699338034838e-06, + "loss": 0.3758, + "step": 1126 + }, + { + "epoch": 0.14, + "learning_rate": 9.953558503834819e-06, + "loss": 0.3535, + "step": 1127 + }, + { + "epoch": 0.14, + "learning_rate": 9.95341745676936e-06, + "loss": 0.3766, + "step": 1128 + }, + { + "epoch": 0.14, + "learning_rate": 9.953276196844519e-06, + "loss": 0.3699, + "step": 1129 + }, + { + "epoch": 0.14, + "learning_rate": 9.95313472406637e-06, + "loss": 0.3573, + "step": 1130 + }, + { + "epoch": 0.14, + "learning_rate": 9.95299303844099e-06, + "loss": 0.3644, + "step": 1131 + }, + { + "epoch": 0.14, + "learning_rate": 9.952851139974468e-06, + "loss": 0.3794, + "step": 1132 + }, + { + "epoch": 0.15, + "learning_rate": 9.952709028672902e-06, + "loss": 0.3605, + "step": 1133 + }, + { + "epoch": 0.15, + "learning_rate": 9.9525667045424e-06, + "loss": 0.3917, + "step": 1134 + }, + { + "epoch": 0.15, + "learning_rate": 9.952424167589076e-06, + "loss": 0.3771, + "step": 1135 + }, + { + "epoch": 0.15, + "learning_rate": 9.952281417819057e-06, + "loss": 0.3909, + "step": 1136 + }, + { + "epoch": 0.15, + "learning_rate": 9.952138455238474e-06, + "loss": 0.3558, + "step": 1137 + }, + { + "epoch": 0.15, + "learning_rate": 9.951995279853472e-06, + "loss": 0.3659, + "step": 1138 + }, + { + "epoch": 0.15, + "learning_rate": 9.951851891670206e-06, + "loss": 0.363, + "step": 1139 + }, + { + "epoch": 0.15, + "learning_rate": 9.951708290694837e-06, + "loss": 0.3572, + "step": 1140 + }, + { + "epoch": 0.15, + "learning_rate": 9.951564476933534e-06, + "loss": 0.3827, + "step": 1141 + }, + { + "epoch": 0.15, + "learning_rate": 9.951420450392476e-06, + "loss": 0.3788, + "step": 1142 + }, + { + "epoch": 0.15, + "learning_rate": 9.951276211077854e-06, + "loss": 0.3812, + "step": 1143 + }, + { + "epoch": 0.15, + "learning_rate": 9.951131758995866e-06, + "loss": 0.3919, + "step": 1144 + }, + { + "epoch": 0.15, + "learning_rate": 9.950987094152721e-06, + "loss": 0.3518, + "step": 1145 + }, + { + "epoch": 0.15, + "learning_rate": 9.950842216554633e-06, + "loss": 0.3822, + "step": 1146 + }, + { + "epoch": 0.15, + "learning_rate": 9.95069712620783e-06, + "loss": 0.373, + "step": 1147 + }, + { + "epoch": 0.15, + "learning_rate": 9.950551823118544e-06, + "loss": 0.3712, + "step": 1148 + }, + { + "epoch": 0.15, + "learning_rate": 9.950406307293023e-06, + "loss": 0.3694, + "step": 1149 + }, + { + "epoch": 0.15, + "learning_rate": 9.950260578737517e-06, + "loss": 0.3844, + "step": 1150 + }, + { + "epoch": 0.15, + "learning_rate": 9.950114637458288e-06, + "loss": 0.3824, + "step": 1151 + }, + { + "epoch": 0.15, + "learning_rate": 9.949968483461609e-06, + "loss": 0.3642, + "step": 1152 + }, + { + "epoch": 0.15, + "learning_rate": 9.94982211675376e-06, + "loss": 0.3691, + "step": 1153 + }, + { + "epoch": 0.15, + "learning_rate": 9.949675537341031e-06, + "loss": 0.3703, + "step": 1154 + }, + { + "epoch": 0.15, + "learning_rate": 9.949528745229721e-06, + "loss": 0.3475, + "step": 1155 + }, + { + "epoch": 0.15, + "learning_rate": 9.949381740426139e-06, + "loss": 0.3532, + "step": 1156 + }, + { + "epoch": 0.15, + "learning_rate": 9.949234522936597e-06, + "loss": 0.3792, + "step": 1157 + }, + { + "epoch": 0.15, + "learning_rate": 9.949087092767428e-06, + "loss": 0.3327, + "step": 1158 + }, + { + "epoch": 0.15, + "learning_rate": 9.948939449924964e-06, + "loss": 0.3492, + "step": 1159 + }, + { + "epoch": 0.15, + "learning_rate": 9.94879159441555e-06, + "loss": 0.3727, + "step": 1160 + }, + { + "epoch": 0.15, + "learning_rate": 9.948643526245538e-06, + "loss": 0.3586, + "step": 1161 + }, + { + "epoch": 0.15, + "learning_rate": 9.948495245421294e-06, + "loss": 0.369, + "step": 1162 + }, + { + "epoch": 0.15, + "learning_rate": 9.948346751949188e-06, + "loss": 0.354, + "step": 1163 + }, + { + "epoch": 0.15, + "learning_rate": 9.948198045835601e-06, + "loss": 0.3648, + "step": 1164 + }, + { + "epoch": 0.15, + "learning_rate": 9.948049127086925e-06, + "loss": 0.3693, + "step": 1165 + }, + { + "epoch": 0.15, + "learning_rate": 9.947899995709556e-06, + "loss": 0.3737, + "step": 1166 + }, + { + "epoch": 0.15, + "learning_rate": 9.947750651709907e-06, + "loss": 0.3702, + "step": 1167 + }, + { + "epoch": 0.15, + "learning_rate": 9.947601095094392e-06, + "loss": 0.3491, + "step": 1168 + }, + { + "epoch": 0.15, + "learning_rate": 9.94745132586944e-06, + "loss": 0.3528, + "step": 1169 + }, + { + "epoch": 0.15, + "learning_rate": 9.947301344041485e-06, + "loss": 0.3509, + "step": 1170 + }, + { + "epoch": 0.15, + "learning_rate": 9.947151149616972e-06, + "loss": 0.3688, + "step": 1171 + }, + { + "epoch": 0.15, + "learning_rate": 9.947000742602358e-06, + "loss": 0.3419, + "step": 1172 + }, + { + "epoch": 0.15, + "learning_rate": 9.946850123004103e-06, + "loss": 0.3616, + "step": 1173 + }, + { + "epoch": 0.15, + "learning_rate": 9.946699290828683e-06, + "loss": 0.3519, + "step": 1174 + }, + { + "epoch": 0.15, + "learning_rate": 9.946548246082577e-06, + "loss": 0.3343, + "step": 1175 + }, + { + "epoch": 0.15, + "learning_rate": 9.946396988772275e-06, + "loss": 0.384, + "step": 1176 + }, + { + "epoch": 0.15, + "learning_rate": 9.94624551890428e-06, + "loss": 0.3363, + "step": 1177 + }, + { + "epoch": 0.15, + "learning_rate": 9.946093836485097e-06, + "loss": 0.3531, + "step": 1178 + }, + { + "epoch": 0.15, + "learning_rate": 9.94594194152125e-06, + "loss": 0.3185, + "step": 1179 + }, + { + "epoch": 0.15, + "learning_rate": 9.945789834019259e-06, + "loss": 0.3691, + "step": 1180 + }, + { + "epoch": 0.15, + "learning_rate": 9.945637513985664e-06, + "loss": 0.3515, + "step": 1181 + }, + { + "epoch": 0.15, + "learning_rate": 9.945484981427011e-06, + "loss": 0.3569, + "step": 1182 + }, + { + "epoch": 0.15, + "learning_rate": 9.945332236349857e-06, + "loss": 0.3948, + "step": 1183 + }, + { + "epoch": 0.15, + "learning_rate": 9.945179278760759e-06, + "loss": 0.3664, + "step": 1184 + }, + { + "epoch": 0.15, + "learning_rate": 9.945026108666296e-06, + "loss": 0.3539, + "step": 1185 + }, + { + "epoch": 0.15, + "learning_rate": 9.944872726073048e-06, + "loss": 0.3939, + "step": 1186 + }, + { + "epoch": 0.15, + "learning_rate": 9.944719130987606e-06, + "loss": 0.4123, + "step": 1187 + }, + { + "epoch": 0.15, + "learning_rate": 9.94456532341657e-06, + "loss": 0.3637, + "step": 1188 + }, + { + "epoch": 0.15, + "learning_rate": 9.94441130336655e-06, + "loss": 0.375, + "step": 1189 + }, + { + "epoch": 0.15, + "learning_rate": 9.944257070844165e-06, + "loss": 0.394, + "step": 1190 + }, + { + "epoch": 0.15, + "learning_rate": 9.944102625856042e-06, + "loss": 0.4071, + "step": 1191 + }, + { + "epoch": 0.15, + "learning_rate": 9.943947968408816e-06, + "loss": 0.3842, + "step": 1192 + }, + { + "epoch": 0.15, + "learning_rate": 9.943793098509138e-06, + "loss": 0.3658, + "step": 1193 + }, + { + "epoch": 0.15, + "learning_rate": 9.943638016163658e-06, + "loss": 0.3345, + "step": 1194 + }, + { + "epoch": 0.15, + "learning_rate": 9.943482721379045e-06, + "loss": 0.3796, + "step": 1195 + }, + { + "epoch": 0.15, + "learning_rate": 9.943327214161968e-06, + "loss": 0.3813, + "step": 1196 + }, + { + "epoch": 0.15, + "learning_rate": 9.943171494519111e-06, + "loss": 0.3835, + "step": 1197 + }, + { + "epoch": 0.15, + "learning_rate": 9.943015562457166e-06, + "loss": 0.3585, + "step": 1198 + }, + { + "epoch": 0.15, + "learning_rate": 9.942859417982833e-06, + "loss": 0.3593, + "step": 1199 + }, + { + "epoch": 0.15, + "learning_rate": 9.942703061102823e-06, + "loss": 0.3632, + "step": 1200 + }, + { + "epoch": 0.15, + "learning_rate": 9.942546491823856e-06, + "loss": 0.3484, + "step": 1201 + }, + { + "epoch": 0.15, + "learning_rate": 9.942389710152657e-06, + "loss": 0.3676, + "step": 1202 + }, + { + "epoch": 0.15, + "learning_rate": 9.942232716095965e-06, + "loss": 0.3727, + "step": 1203 + }, + { + "epoch": 0.15, + "learning_rate": 9.942075509660527e-06, + "loss": 0.3721, + "step": 1204 + }, + { + "epoch": 0.15, + "learning_rate": 9.941918090853096e-06, + "loss": 0.3643, + "step": 1205 + }, + { + "epoch": 0.15, + "learning_rate": 9.941760459680441e-06, + "loss": 0.3354, + "step": 1206 + }, + { + "epoch": 0.15, + "learning_rate": 9.94160261614933e-06, + "loss": 0.3701, + "step": 1207 + }, + { + "epoch": 0.15, + "learning_rate": 9.941444560266551e-06, + "loss": 0.4013, + "step": 1208 + }, + { + "epoch": 0.15, + "learning_rate": 9.941286292038894e-06, + "loss": 0.3407, + "step": 1209 + }, + { + "epoch": 0.15, + "learning_rate": 9.941127811473162e-06, + "loss": 0.324, + "step": 1210 + }, + { + "epoch": 0.16, + "learning_rate": 9.94096911857616e-06, + "loss": 0.3853, + "step": 1211 + }, + { + "epoch": 0.16, + "learning_rate": 9.940810213354713e-06, + "loss": 0.3518, + "step": 1212 + }, + { + "epoch": 0.16, + "learning_rate": 9.940651095815646e-06, + "loss": 0.3505, + "step": 1213 + }, + { + "epoch": 0.16, + "learning_rate": 9.940491765965798e-06, + "loss": 0.3663, + "step": 1214 + }, + { + "epoch": 0.16, + "learning_rate": 9.940332223812017e-06, + "loss": 0.3613, + "step": 1215 + }, + { + "epoch": 0.16, + "learning_rate": 9.940172469361158e-06, + "loss": 0.3966, + "step": 1216 + }, + { + "epoch": 0.16, + "learning_rate": 9.940012502620085e-06, + "loss": 0.345, + "step": 1217 + }, + { + "epoch": 0.16, + "learning_rate": 9.939852323595671e-06, + "loss": 0.3586, + "step": 1218 + }, + { + "epoch": 0.16, + "learning_rate": 9.939691932294804e-06, + "loss": 0.3566, + "step": 1219 + }, + { + "epoch": 0.16, + "learning_rate": 9.939531328724371e-06, + "loss": 0.3828, + "step": 1220 + }, + { + "epoch": 0.16, + "learning_rate": 9.939370512891277e-06, + "loss": 0.3642, + "step": 1221 + }, + { + "epoch": 0.16, + "learning_rate": 9.93920948480243e-06, + "loss": 0.3452, + "step": 1222 + }, + { + "epoch": 0.16, + "learning_rate": 9.939048244464753e-06, + "loss": 0.3636, + "step": 1223 + }, + { + "epoch": 0.16, + "learning_rate": 9.938886791885172e-06, + "loss": 0.3503, + "step": 1224 + }, + { + "epoch": 0.16, + "learning_rate": 9.938725127070628e-06, + "loss": 0.3372, + "step": 1225 + }, + { + "epoch": 0.16, + "learning_rate": 9.938563250028063e-06, + "loss": 0.3979, + "step": 1226 + }, + { + "epoch": 0.16, + "learning_rate": 9.93840116076444e-06, + "loss": 0.4119, + "step": 1227 + }, + { + "epoch": 0.16, + "learning_rate": 9.938238859286719e-06, + "loss": 0.384, + "step": 1228 + }, + { + "epoch": 0.16, + "learning_rate": 9.938076345601875e-06, + "loss": 0.357, + "step": 1229 + }, + { + "epoch": 0.16, + "learning_rate": 9.937913619716895e-06, + "loss": 0.3747, + "step": 1230 + }, + { + "epoch": 0.16, + "learning_rate": 9.937750681638766e-06, + "loss": 0.372, + "step": 1231 + }, + { + "epoch": 0.16, + "learning_rate": 9.937587531374497e-06, + "loss": 0.3506, + "step": 1232 + }, + { + "epoch": 0.16, + "learning_rate": 9.937424168931094e-06, + "loss": 0.3485, + "step": 1233 + }, + { + "epoch": 0.16, + "learning_rate": 9.937260594315578e-06, + "loss": 0.3686, + "step": 1234 + }, + { + "epoch": 0.16, + "learning_rate": 9.937096807534978e-06, + "loss": 0.3664, + "step": 1235 + }, + { + "epoch": 0.16, + "learning_rate": 9.936932808596332e-06, + "loss": 0.3786, + "step": 1236 + }, + { + "epoch": 0.16, + "learning_rate": 9.936768597506689e-06, + "loss": 0.3529, + "step": 1237 + }, + { + "epoch": 0.16, + "learning_rate": 9.936604174273105e-06, + "loss": 0.3337, + "step": 1238 + }, + { + "epoch": 0.16, + "learning_rate": 9.936439538902644e-06, + "loss": 0.3423, + "step": 1239 + }, + { + "epoch": 0.16, + "learning_rate": 9.936274691402384e-06, + "loss": 0.3445, + "step": 1240 + }, + { + "epoch": 0.16, + "learning_rate": 9.936109631779404e-06, + "loss": 0.3557, + "step": 1241 + }, + { + "epoch": 0.16, + "learning_rate": 9.935944360040803e-06, + "loss": 0.3825, + "step": 1242 + }, + { + "epoch": 0.16, + "learning_rate": 9.935778876193678e-06, + "loss": 0.3715, + "step": 1243 + }, + { + "epoch": 0.16, + "learning_rate": 9.935613180245143e-06, + "loss": 0.3451, + "step": 1244 + }, + { + "epoch": 0.16, + "learning_rate": 9.935447272202317e-06, + "loss": 0.3587, + "step": 1245 + }, + { + "epoch": 0.16, + "learning_rate": 9.935281152072329e-06, + "loss": 0.3625, + "step": 1246 + }, + { + "epoch": 0.16, + "learning_rate": 9.93511481986232e-06, + "loss": 0.3565, + "step": 1247 + }, + { + "epoch": 0.16, + "learning_rate": 9.934948275579435e-06, + "loss": 0.3465, + "step": 1248 + }, + { + "epoch": 0.16, + "learning_rate": 9.934781519230832e-06, + "loss": 0.3949, + "step": 1249 + }, + { + "epoch": 0.16, + "learning_rate": 9.934614550823679e-06, + "loss": 0.3618, + "step": 1250 + }, + { + "epoch": 0.16, + "learning_rate": 9.934447370365146e-06, + "loss": 0.3637, + "step": 1251 + }, + { + "epoch": 0.16, + "learning_rate": 9.93427997786242e-06, + "loss": 0.3626, + "step": 1252 + }, + { + "epoch": 0.16, + "learning_rate": 9.934112373322695e-06, + "loss": 0.356, + "step": 1253 + }, + { + "epoch": 0.16, + "learning_rate": 9.933944556753173e-06, + "loss": 0.3499, + "step": 1254 + }, + { + "epoch": 0.16, + "learning_rate": 9.933776528161063e-06, + "loss": 0.3639, + "step": 1255 + }, + { + "epoch": 0.16, + "learning_rate": 9.933608287553589e-06, + "loss": 0.3761, + "step": 1256 + }, + { + "epoch": 0.16, + "learning_rate": 9.93343983493798e-06, + "loss": 0.3445, + "step": 1257 + }, + { + "epoch": 0.16, + "learning_rate": 9.93327117032147e-06, + "loss": 0.3955, + "step": 1258 + }, + { + "epoch": 0.16, + "learning_rate": 9.933102293711314e-06, + "loss": 0.3573, + "step": 1259 + }, + { + "epoch": 0.16, + "learning_rate": 9.932933205114766e-06, + "loss": 0.3507, + "step": 1260 + }, + { + "epoch": 0.16, + "learning_rate": 9.932763904539091e-06, + "loss": 0.363, + "step": 1261 + }, + { + "epoch": 0.16, + "learning_rate": 9.932594391991566e-06, + "loss": 0.3565, + "step": 1262 + }, + { + "epoch": 0.16, + "learning_rate": 9.932424667479475e-06, + "loss": 0.3688, + "step": 1263 + }, + { + "epoch": 0.16, + "learning_rate": 9.932254731010108e-06, + "loss": 0.3472, + "step": 1264 + }, + { + "epoch": 0.16, + "learning_rate": 9.932084582590773e-06, + "loss": 0.3658, + "step": 1265 + }, + { + "epoch": 0.16, + "learning_rate": 9.93191422222878e-06, + "loss": 0.3456, + "step": 1266 + }, + { + "epoch": 0.16, + "learning_rate": 9.931743649931446e-06, + "loss": 0.3704, + "step": 1267 + }, + { + "epoch": 0.16, + "learning_rate": 9.931572865706105e-06, + "loss": 0.3504, + "step": 1268 + }, + { + "epoch": 0.16, + "learning_rate": 9.931401869560096e-06, + "loss": 0.3502, + "step": 1269 + }, + { + "epoch": 0.16, + "learning_rate": 9.931230661500764e-06, + "loss": 0.3741, + "step": 1270 + }, + { + "epoch": 0.16, + "learning_rate": 9.93105924153547e-06, + "loss": 0.3278, + "step": 1271 + }, + { + "epoch": 0.16, + "learning_rate": 9.930887609671577e-06, + "loss": 0.3459, + "step": 1272 + }, + { + "epoch": 0.16, + "learning_rate": 9.930715765916462e-06, + "loss": 0.3831, + "step": 1273 + }, + { + "epoch": 0.16, + "learning_rate": 9.93054371027751e-06, + "loss": 0.3755, + "step": 1274 + }, + { + "epoch": 0.16, + "learning_rate": 9.930371442762112e-06, + "loss": 0.3474, + "step": 1275 + }, + { + "epoch": 0.16, + "learning_rate": 9.930198963377672e-06, + "loss": 0.3593, + "step": 1276 + }, + { + "epoch": 0.16, + "learning_rate": 9.930026272131605e-06, + "loss": 0.3275, + "step": 1277 + }, + { + "epoch": 0.16, + "learning_rate": 9.929853369031328e-06, + "loss": 0.3401, + "step": 1278 + }, + { + "epoch": 0.16, + "learning_rate": 9.929680254084273e-06, + "loss": 0.3735, + "step": 1279 + }, + { + "epoch": 0.16, + "learning_rate": 9.929506927297878e-06, + "loss": 0.3868, + "step": 1280 + }, + { + "epoch": 0.16, + "learning_rate": 9.929333388679593e-06, + "loss": 0.3672, + "step": 1281 + }, + { + "epoch": 0.16, + "learning_rate": 9.929159638236872e-06, + "loss": 0.3769, + "step": 1282 + }, + { + "epoch": 0.16, + "learning_rate": 9.928985675977185e-06, + "loss": 0.3563, + "step": 1283 + }, + { + "epoch": 0.16, + "learning_rate": 9.928811501908006e-06, + "loss": 0.3491, + "step": 1284 + }, + { + "epoch": 0.16, + "learning_rate": 9.928637116036818e-06, + "loss": 0.3511, + "step": 1285 + }, + { + "epoch": 0.16, + "learning_rate": 9.928462518371119e-06, + "loss": 0.33, + "step": 1286 + }, + { + "epoch": 0.16, + "learning_rate": 9.928287708918408e-06, + "loss": 0.3616, + "step": 1287 + }, + { + "epoch": 0.16, + "learning_rate": 9.928112687686197e-06, + "loss": 0.3957, + "step": 1288 + }, + { + "epoch": 0.16, + "learning_rate": 9.92793745468201e-06, + "loss": 0.394, + "step": 1289 + }, + { + "epoch": 0.17, + "learning_rate": 9.927762009913377e-06, + "loss": 0.3673, + "step": 1290 + }, + { + "epoch": 0.17, + "learning_rate": 9.927586353387832e-06, + "loss": 0.3669, + "step": 1291 + }, + { + "epoch": 0.17, + "learning_rate": 9.92741048511293e-06, + "loss": 0.3608, + "step": 1292 + }, + { + "epoch": 0.17, + "learning_rate": 9.927234405096224e-06, + "loss": 0.3092, + "step": 1293 + }, + { + "epoch": 0.17, + "learning_rate": 9.927058113345282e-06, + "loss": 0.3418, + "step": 1294 + }, + { + "epoch": 0.17, + "learning_rate": 9.92688160986768e-06, + "loss": 0.3575, + "step": 1295 + }, + { + "epoch": 0.17, + "learning_rate": 9.926704894671004e-06, + "loss": 0.3368, + "step": 1296 + }, + { + "epoch": 0.17, + "learning_rate": 9.926527967762845e-06, + "loss": 0.3299, + "step": 1297 + }, + { + "epoch": 0.17, + "learning_rate": 9.926350829150806e-06, + "loss": 0.3621, + "step": 1298 + }, + { + "epoch": 0.17, + "learning_rate": 9.926173478842502e-06, + "loss": 0.3451, + "step": 1299 + }, + { + "epoch": 0.17, + "learning_rate": 9.925995916845553e-06, + "loss": 0.3972, + "step": 1300 + }, + { + "epoch": 0.17, + "learning_rate": 9.925818143167587e-06, + "loss": 0.3599, + "step": 1301 + }, + { + "epoch": 0.17, + "learning_rate": 9.925640157816246e-06, + "loss": 0.3701, + "step": 1302 + }, + { + "epoch": 0.17, + "learning_rate": 9.925461960799177e-06, + "loss": 0.3848, + "step": 1303 + }, + { + "epoch": 0.17, + "learning_rate": 9.925283552124039e-06, + "loss": 0.3578, + "step": 1304 + }, + { + "epoch": 0.17, + "learning_rate": 9.925104931798496e-06, + "loss": 0.3756, + "step": 1305 + }, + { + "epoch": 0.17, + "learning_rate": 9.924926099830226e-06, + "loss": 0.3903, + "step": 1306 + }, + { + "epoch": 0.17, + "learning_rate": 9.924747056226913e-06, + "loss": 0.3703, + "step": 1307 + }, + { + "epoch": 0.17, + "learning_rate": 9.92456780099625e-06, + "loss": 0.3689, + "step": 1308 + }, + { + "epoch": 0.17, + "learning_rate": 9.924388334145943e-06, + "loss": 0.3477, + "step": 1309 + }, + { + "epoch": 0.17, + "learning_rate": 9.9242086556837e-06, + "loss": 0.3433, + "step": 1310 + }, + { + "epoch": 0.17, + "learning_rate": 9.924028765617247e-06, + "loss": 0.3545, + "step": 1311 + }, + { + "epoch": 0.17, + "learning_rate": 9.92384866395431e-06, + "loss": 0.353, + "step": 1312 + }, + { + "epoch": 0.17, + "learning_rate": 9.923668350702628e-06, + "loss": 0.3554, + "step": 1313 + }, + { + "epoch": 0.17, + "learning_rate": 9.923487825869955e-06, + "loss": 0.3598, + "step": 1314 + }, + { + "epoch": 0.17, + "learning_rate": 9.923307089464043e-06, + "loss": 0.3589, + "step": 1315 + }, + { + "epoch": 0.17, + "learning_rate": 9.92312614149266e-06, + "loss": 0.3633, + "step": 1316 + }, + { + "epoch": 0.17, + "learning_rate": 9.922944981963583e-06, + "loss": 0.378, + "step": 1317 + }, + { + "epoch": 0.17, + "learning_rate": 9.922763610884596e-06, + "loss": 0.3682, + "step": 1318 + }, + { + "epoch": 0.17, + "learning_rate": 9.922582028263495e-06, + "loss": 0.3403, + "step": 1319 + }, + { + "epoch": 0.17, + "learning_rate": 9.922400234108079e-06, + "loss": 0.3673, + "step": 1320 + }, + { + "epoch": 0.17, + "learning_rate": 9.922218228426162e-06, + "loss": 0.3762, + "step": 1321 + }, + { + "epoch": 0.17, + "learning_rate": 9.922036011225564e-06, + "loss": 0.3725, + "step": 1322 + }, + { + "epoch": 0.17, + "learning_rate": 9.92185358251412e-06, + "loss": 0.3781, + "step": 1323 + }, + { + "epoch": 0.17, + "learning_rate": 9.921670942299664e-06, + "loss": 0.3567, + "step": 1324 + }, + { + "epoch": 0.17, + "learning_rate": 9.921488090590047e-06, + "loss": 0.3619, + "step": 1325 + }, + { + "epoch": 0.17, + "learning_rate": 9.921305027393125e-06, + "loss": 0.3586, + "step": 1326 + }, + { + "epoch": 0.17, + "learning_rate": 9.921121752716767e-06, + "loss": 0.3724, + "step": 1327 + }, + { + "epoch": 0.17, + "learning_rate": 9.920938266568847e-06, + "loss": 0.3847, + "step": 1328 + }, + { + "epoch": 0.17, + "learning_rate": 9.92075456895725e-06, + "loss": 0.359, + "step": 1329 + }, + { + "epoch": 0.17, + "learning_rate": 9.92057065988987e-06, + "loss": 0.3295, + "step": 1330 + }, + { + "epoch": 0.17, + "learning_rate": 9.92038653937461e-06, + "loss": 0.3813, + "step": 1331 + }, + { + "epoch": 0.17, + "learning_rate": 9.920202207419382e-06, + "loss": 0.368, + "step": 1332 + }, + { + "epoch": 0.17, + "learning_rate": 9.920017664032109e-06, + "loss": 0.3759, + "step": 1333 + }, + { + "epoch": 0.17, + "learning_rate": 9.919832909220717e-06, + "loss": 0.3499, + "step": 1334 + }, + { + "epoch": 0.17, + "learning_rate": 9.91964794299315e-06, + "loss": 0.361, + "step": 1335 + }, + { + "epoch": 0.17, + "learning_rate": 9.919462765357353e-06, + "loss": 0.3656, + "step": 1336 + }, + { + "epoch": 0.17, + "learning_rate": 9.919277376321284e-06, + "loss": 0.3855, + "step": 1337 + }, + { + "epoch": 0.17, + "learning_rate": 9.91909177589291e-06, + "loss": 0.3844, + "step": 1338 + }, + { + "epoch": 0.17, + "learning_rate": 9.91890596408021e-06, + "loss": 0.3817, + "step": 1339 + }, + { + "epoch": 0.17, + "learning_rate": 9.918719940891165e-06, + "loss": 0.3564, + "step": 1340 + }, + { + "epoch": 0.17, + "learning_rate": 9.918533706333767e-06, + "loss": 0.3318, + "step": 1341 + }, + { + "epoch": 0.17, + "learning_rate": 9.918347260416024e-06, + "loss": 0.3691, + "step": 1342 + }, + { + "epoch": 0.17, + "learning_rate": 9.918160603145943e-06, + "loss": 0.3387, + "step": 1343 + }, + { + "epoch": 0.17, + "learning_rate": 9.917973734531549e-06, + "loss": 0.3672, + "step": 1344 + }, + { + "epoch": 0.17, + "learning_rate": 9.917786654580872e-06, + "loss": 0.3683, + "step": 1345 + }, + { + "epoch": 0.17, + "learning_rate": 9.917599363301947e-06, + "loss": 0.3484, + "step": 1346 + }, + { + "epoch": 0.17, + "learning_rate": 9.917411860702828e-06, + "loss": 0.3511, + "step": 1347 + }, + { + "epoch": 0.17, + "learning_rate": 9.917224146791568e-06, + "loss": 0.3385, + "step": 1348 + }, + { + "epoch": 0.17, + "learning_rate": 9.917036221576235e-06, + "loss": 0.3445, + "step": 1349 + }, + { + "epoch": 0.17, + "learning_rate": 9.916848085064906e-06, + "loss": 0.3605, + "step": 1350 + }, + { + "epoch": 0.17, + "learning_rate": 9.916659737265664e-06, + "loss": 0.3661, + "step": 1351 + }, + { + "epoch": 0.17, + "learning_rate": 9.916471178186602e-06, + "loss": 0.3795, + "step": 1352 + }, + { + "epoch": 0.17, + "learning_rate": 9.916282407835826e-06, + "loss": 0.3239, + "step": 1353 + }, + { + "epoch": 0.17, + "learning_rate": 9.916093426221445e-06, + "loss": 0.3756, + "step": 1354 + }, + { + "epoch": 0.17, + "learning_rate": 9.91590423335158e-06, + "loss": 0.3531, + "step": 1355 + }, + { + "epoch": 0.17, + "learning_rate": 9.915714829234361e-06, + "loss": 0.3687, + "step": 1356 + }, + { + "epoch": 0.17, + "learning_rate": 9.91552521387793e-06, + "loss": 0.3565, + "step": 1357 + }, + { + "epoch": 0.17, + "learning_rate": 9.915335387290432e-06, + "loss": 0.3715, + "step": 1358 + }, + { + "epoch": 0.17, + "learning_rate": 9.915145349480027e-06, + "loss": 0.3753, + "step": 1359 + }, + { + "epoch": 0.17, + "learning_rate": 9.914955100454878e-06, + "loss": 0.3677, + "step": 1360 + }, + { + "epoch": 0.17, + "learning_rate": 9.914764640223162e-06, + "loss": 0.377, + "step": 1361 + }, + { + "epoch": 0.17, + "learning_rate": 9.914573968793064e-06, + "loss": 0.336, + "step": 1362 + }, + { + "epoch": 0.17, + "learning_rate": 9.914383086172778e-06, + "loss": 0.3449, + "step": 1363 + }, + { + "epoch": 0.17, + "learning_rate": 9.914191992370504e-06, + "loss": 0.401, + "step": 1364 + }, + { + "epoch": 0.17, + "learning_rate": 9.914000687394457e-06, + "loss": 0.3504, + "step": 1365 + }, + { + "epoch": 0.17, + "learning_rate": 9.913809171252856e-06, + "loss": 0.3662, + "step": 1366 + }, + { + "epoch": 0.17, + "learning_rate": 9.913617443953931e-06, + "loss": 0.3733, + "step": 1367 + }, + { + "epoch": 0.18, + "learning_rate": 9.913425505505923e-06, + "loss": 0.3678, + "step": 1368 + }, + { + "epoch": 0.18, + "learning_rate": 9.913233355917075e-06, + "loss": 0.3169, + "step": 1369 + }, + { + "epoch": 0.18, + "learning_rate": 9.913040995195651e-06, + "loss": 0.3525, + "step": 1370 + }, + { + "epoch": 0.18, + "learning_rate": 9.91284842334991e-06, + "loss": 0.3377, + "step": 1371 + }, + { + "epoch": 0.18, + "learning_rate": 9.912655640388134e-06, + "loss": 0.3395, + "step": 1372 + }, + { + "epoch": 0.18, + "learning_rate": 9.912462646318602e-06, + "loss": 0.3687, + "step": 1373 + }, + { + "epoch": 0.18, + "learning_rate": 9.91226944114961e-06, + "loss": 0.3813, + "step": 1374 + }, + { + "epoch": 0.18, + "learning_rate": 9.91207602488946e-06, + "loss": 0.351, + "step": 1375 + }, + { + "epoch": 0.18, + "learning_rate": 9.911882397546464e-06, + "loss": 0.3423, + "step": 1376 + }, + { + "epoch": 0.18, + "learning_rate": 9.91168855912894e-06, + "loss": 0.3567, + "step": 1377 + }, + { + "epoch": 0.18, + "learning_rate": 9.911494509645222e-06, + "loss": 0.3515, + "step": 1378 + }, + { + "epoch": 0.18, + "learning_rate": 9.911300249103646e-06, + "loss": 0.3522, + "step": 1379 + }, + { + "epoch": 0.18, + "learning_rate": 9.91110577751256e-06, + "loss": 0.3223, + "step": 1380 + }, + { + "epoch": 0.18, + "learning_rate": 9.91091109488032e-06, + "loss": 0.3408, + "step": 1381 + }, + { + "epoch": 0.18, + "learning_rate": 9.910716201215294e-06, + "loss": 0.3571, + "step": 1382 + }, + { + "epoch": 0.18, + "learning_rate": 9.910521096525856e-06, + "loss": 0.3436, + "step": 1383 + }, + { + "epoch": 0.18, + "learning_rate": 9.910325780820391e-06, + "loss": 0.3871, + "step": 1384 + }, + { + "epoch": 0.18, + "learning_rate": 9.910130254107288e-06, + "loss": 0.3259, + "step": 1385 + }, + { + "epoch": 0.18, + "learning_rate": 9.909934516394957e-06, + "loss": 0.3848, + "step": 1386 + }, + { + "epoch": 0.18, + "learning_rate": 9.909738567691803e-06, + "loss": 0.3623, + "step": 1387 + }, + { + "epoch": 0.18, + "learning_rate": 9.909542408006247e-06, + "loss": 0.3588, + "step": 1388 + }, + { + "epoch": 0.18, + "learning_rate": 9.90934603734672e-06, + "loss": 0.3511, + "step": 1389 + }, + { + "epoch": 0.18, + "learning_rate": 9.909149455721661e-06, + "loss": 0.4004, + "step": 1390 + }, + { + "epoch": 0.18, + "learning_rate": 9.908952663139518e-06, + "loss": 0.3373, + "step": 1391 + }, + { + "epoch": 0.18, + "learning_rate": 9.908755659608743e-06, + "loss": 0.319, + "step": 1392 + }, + { + "epoch": 0.18, + "learning_rate": 9.908558445137807e-06, + "loss": 0.374, + "step": 1393 + }, + { + "epoch": 0.18, + "learning_rate": 9.908361019735181e-06, + "loss": 0.3919, + "step": 1394 + }, + { + "epoch": 0.18, + "learning_rate": 9.908163383409353e-06, + "loss": 0.3673, + "step": 1395 + }, + { + "epoch": 0.18, + "learning_rate": 9.907965536168811e-06, + "loss": 0.3838, + "step": 1396 + }, + { + "epoch": 0.18, + "learning_rate": 9.907767478022061e-06, + "loss": 0.3339, + "step": 1397 + }, + { + "epoch": 0.18, + "learning_rate": 9.90756920897761e-06, + "loss": 0.3618, + "step": 1398 + }, + { + "epoch": 0.18, + "learning_rate": 9.907370729043984e-06, + "loss": 0.3432, + "step": 1399 + }, + { + "epoch": 0.18, + "learning_rate": 9.907172038229706e-06, + "loss": 0.3641, + "step": 1400 + }, + { + "epoch": 0.18, + "learning_rate": 9.906973136543317e-06, + "loss": 0.331, + "step": 1401 + }, + { + "epoch": 0.18, + "learning_rate": 9.906774023993362e-06, + "loss": 0.333, + "step": 1402 + }, + { + "epoch": 0.18, + "learning_rate": 9.906574700588403e-06, + "loss": 0.3625, + "step": 1403 + }, + { + "epoch": 0.18, + "learning_rate": 9.906375166336998e-06, + "loss": 0.3705, + "step": 1404 + }, + { + "epoch": 0.18, + "learning_rate": 9.906175421247728e-06, + "loss": 0.3644, + "step": 1405 + }, + { + "epoch": 0.18, + "learning_rate": 9.905975465329172e-06, + "loss": 0.3897, + "step": 1406 + }, + { + "epoch": 0.18, + "learning_rate": 9.905775298589923e-06, + "loss": 0.3605, + "step": 1407 + }, + { + "epoch": 0.18, + "learning_rate": 9.905574921038586e-06, + "loss": 0.3443, + "step": 1408 + }, + { + "epoch": 0.18, + "learning_rate": 9.905374332683768e-06, + "loss": 0.3959, + "step": 1409 + }, + { + "epoch": 0.18, + "learning_rate": 9.90517353353409e-06, + "loss": 0.3606, + "step": 1410 + }, + { + "epoch": 0.18, + "learning_rate": 9.904972523598183e-06, + "loss": 0.3245, + "step": 1411 + }, + { + "epoch": 0.18, + "learning_rate": 9.90477130288468e-06, + "loss": 0.345, + "step": 1412 + }, + { + "epoch": 0.18, + "learning_rate": 9.904569871402233e-06, + "loss": 0.3779, + "step": 1413 + }, + { + "epoch": 0.18, + "learning_rate": 9.904368229159494e-06, + "loss": 0.3902, + "step": 1414 + }, + { + "epoch": 0.18, + "learning_rate": 9.904166376165129e-06, + "loss": 0.3425, + "step": 1415 + }, + { + "epoch": 0.18, + "learning_rate": 9.903964312427813e-06, + "loss": 0.3482, + "step": 1416 + }, + { + "epoch": 0.18, + "learning_rate": 9.903762037956228e-06, + "loss": 0.3803, + "step": 1417 + }, + { + "epoch": 0.18, + "learning_rate": 9.903559552759069e-06, + "loss": 0.3655, + "step": 1418 + }, + { + "epoch": 0.18, + "learning_rate": 9.903356856845035e-06, + "loss": 0.354, + "step": 1419 + }, + { + "epoch": 0.18, + "learning_rate": 9.903153950222834e-06, + "loss": 0.3536, + "step": 1420 + }, + { + "epoch": 0.18, + "learning_rate": 9.90295083290119e-06, + "loss": 0.3423, + "step": 1421 + }, + { + "epoch": 0.18, + "learning_rate": 9.90274750488883e-06, + "loss": 0.3663, + "step": 1422 + }, + { + "epoch": 0.18, + "learning_rate": 9.902543966194489e-06, + "loss": 0.3707, + "step": 1423 + }, + { + "epoch": 0.18, + "learning_rate": 9.902340216826915e-06, + "loss": 0.3423, + "step": 1424 + }, + { + "epoch": 0.18, + "learning_rate": 9.902136256794865e-06, + "loss": 0.3708, + "step": 1425 + }, + { + "epoch": 0.18, + "learning_rate": 9.901932086107103e-06, + "loss": 0.3843, + "step": 1426 + }, + { + "epoch": 0.18, + "learning_rate": 9.901727704772401e-06, + "loss": 0.3489, + "step": 1427 + }, + { + "epoch": 0.18, + "learning_rate": 9.901523112799543e-06, + "loss": 0.352, + "step": 1428 + }, + { + "epoch": 0.18, + "learning_rate": 9.90131831019732e-06, + "loss": 0.3745, + "step": 1429 + }, + { + "epoch": 0.18, + "learning_rate": 9.901113296974533e-06, + "loss": 0.3613, + "step": 1430 + }, + { + "epoch": 0.18, + "learning_rate": 9.900908073139995e-06, + "loss": 0.3749, + "step": 1431 + }, + { + "epoch": 0.18, + "learning_rate": 9.90070263870252e-06, + "loss": 0.3363, + "step": 1432 + }, + { + "epoch": 0.18, + "learning_rate": 9.900496993670937e-06, + "loss": 0.3517, + "step": 1433 + }, + { + "epoch": 0.18, + "learning_rate": 9.900291138054086e-06, + "loss": 0.3314, + "step": 1434 + }, + { + "epoch": 0.18, + "learning_rate": 9.90008507186081e-06, + "loss": 0.3524, + "step": 1435 + }, + { + "epoch": 0.18, + "learning_rate": 9.899878795099966e-06, + "loss": 0.3644, + "step": 1436 + }, + { + "epoch": 0.18, + "learning_rate": 9.899672307780419e-06, + "loss": 0.3595, + "step": 1437 + }, + { + "epoch": 0.18, + "learning_rate": 9.89946560991104e-06, + "loss": 0.3754, + "step": 1438 + }, + { + "epoch": 0.18, + "learning_rate": 9.899258701500712e-06, + "loss": 0.3877, + "step": 1439 + }, + { + "epoch": 0.18, + "learning_rate": 9.899051582558325e-06, + "loss": 0.3617, + "step": 1440 + }, + { + "epoch": 0.18, + "learning_rate": 9.898844253092782e-06, + "loss": 0.3964, + "step": 1441 + }, + { + "epoch": 0.18, + "learning_rate": 9.898636713112992e-06, + "loss": 0.3452, + "step": 1442 + }, + { + "epoch": 0.18, + "learning_rate": 9.89842896262787e-06, + "loss": 0.3581, + "step": 1443 + }, + { + "epoch": 0.18, + "learning_rate": 9.89822100164635e-06, + "loss": 0.3826, + "step": 1444 + }, + { + "epoch": 0.18, + "learning_rate": 9.898012830177361e-06, + "loss": 0.3612, + "step": 1445 + }, + { + "epoch": 0.19, + "learning_rate": 9.897804448229854e-06, + "loss": 0.3458, + "step": 1446 + }, + { + "epoch": 0.19, + "learning_rate": 9.89759585581278e-06, + "loss": 0.3754, + "step": 1447 + }, + { + "epoch": 0.19, + "learning_rate": 9.897387052935106e-06, + "loss": 0.3574, + "step": 1448 + }, + { + "epoch": 0.19, + "learning_rate": 9.897178039605803e-06, + "loss": 0.3575, + "step": 1449 + }, + { + "epoch": 0.19, + "learning_rate": 9.896968815833853e-06, + "loss": 0.3397, + "step": 1450 + }, + { + "epoch": 0.19, + "learning_rate": 9.896759381628247e-06, + "loss": 0.3567, + "step": 1451 + }, + { + "epoch": 0.19, + "learning_rate": 9.896549736997985e-06, + "loss": 0.3586, + "step": 1452 + }, + { + "epoch": 0.19, + "learning_rate": 9.896339881952076e-06, + "loss": 0.3617, + "step": 1453 + }, + { + "epoch": 0.19, + "learning_rate": 9.896129816499535e-06, + "loss": 0.3704, + "step": 1454 + }, + { + "epoch": 0.19, + "learning_rate": 9.895919540649395e-06, + "loss": 0.3741, + "step": 1455 + }, + { + "epoch": 0.19, + "learning_rate": 9.895709054410686e-06, + "loss": 0.3623, + "step": 1456 + }, + { + "epoch": 0.19, + "learning_rate": 9.895498357792456e-06, + "loss": 0.3797, + "step": 1457 + }, + { + "epoch": 0.19, + "learning_rate": 9.89528745080376e-06, + "loss": 0.3519, + "step": 1458 + }, + { + "epoch": 0.19, + "learning_rate": 9.89507633345366e-06, + "loss": 0.3339, + "step": 1459 + }, + { + "epoch": 0.19, + "learning_rate": 9.894865005751227e-06, + "loss": 0.3655, + "step": 1460 + }, + { + "epoch": 0.19, + "learning_rate": 9.894653467705542e-06, + "loss": 0.3658, + "step": 1461 + }, + { + "epoch": 0.19, + "learning_rate": 9.894441719325698e-06, + "loss": 0.3224, + "step": 1462 + }, + { + "epoch": 0.19, + "learning_rate": 9.894229760620793e-06, + "loss": 0.3455, + "step": 1463 + }, + { + "epoch": 0.19, + "learning_rate": 9.894017591599934e-06, + "loss": 0.362, + "step": 1464 + }, + { + "epoch": 0.19, + "learning_rate": 9.89380521227224e-06, + "loss": 0.3556, + "step": 1465 + }, + { + "epoch": 0.19, + "learning_rate": 9.893592622646838e-06, + "loss": 0.3723, + "step": 1466 + }, + { + "epoch": 0.19, + "learning_rate": 9.893379822732863e-06, + "loss": 0.3914, + "step": 1467 + }, + { + "epoch": 0.19, + "learning_rate": 9.893166812539456e-06, + "loss": 0.3601, + "step": 1468 + }, + { + "epoch": 0.19, + "learning_rate": 9.892953592075776e-06, + "loss": 0.3473, + "step": 1469 + }, + { + "epoch": 0.19, + "learning_rate": 9.892740161350981e-06, + "loss": 0.3573, + "step": 1470 + }, + { + "epoch": 0.19, + "learning_rate": 9.892526520374246e-06, + "loss": 0.3762, + "step": 1471 + }, + { + "epoch": 0.19, + "learning_rate": 9.892312669154749e-06, + "loss": 0.3561, + "step": 1472 + }, + { + "epoch": 0.19, + "learning_rate": 9.892098607701682e-06, + "loss": 0.3639, + "step": 1473 + }, + { + "epoch": 0.19, + "learning_rate": 9.891884336024242e-06, + "loss": 0.3605, + "step": 1474 + }, + { + "epoch": 0.19, + "learning_rate": 9.891669854131636e-06, + "loss": 0.3666, + "step": 1475 + }, + { + "epoch": 0.19, + "learning_rate": 9.891455162033085e-06, + "loss": 0.3766, + "step": 1476 + }, + { + "epoch": 0.19, + "learning_rate": 9.891240259737809e-06, + "loss": 0.3298, + "step": 1477 + }, + { + "epoch": 0.19, + "learning_rate": 9.891025147255047e-06, + "loss": 0.3725, + "step": 1478 + }, + { + "epoch": 0.19, + "learning_rate": 9.890809824594041e-06, + "loss": 0.3528, + "step": 1479 + }, + { + "epoch": 0.19, + "learning_rate": 9.890594291764044e-06, + "loss": 0.3563, + "step": 1480 + }, + { + "epoch": 0.19, + "learning_rate": 9.89037854877432e-06, + "loss": 0.3615, + "step": 1481 + }, + { + "epoch": 0.19, + "learning_rate": 9.890162595634138e-06, + "loss": 0.3513, + "step": 1482 + }, + { + "epoch": 0.19, + "learning_rate": 9.889946432352776e-06, + "loss": 0.3673, + "step": 1483 + }, + { + "epoch": 0.19, + "learning_rate": 9.889730058939529e-06, + "loss": 0.3656, + "step": 1484 + }, + { + "epoch": 0.19, + "learning_rate": 9.889513475403689e-06, + "loss": 0.3284, + "step": 1485 + }, + { + "epoch": 0.19, + "learning_rate": 9.889296681754565e-06, + "loss": 0.3474, + "step": 1486 + }, + { + "epoch": 0.19, + "learning_rate": 9.889079678001474e-06, + "loss": 0.3525, + "step": 1487 + }, + { + "epoch": 0.19, + "learning_rate": 9.88886246415374e-06, + "loss": 0.3558, + "step": 1488 + }, + { + "epoch": 0.19, + "learning_rate": 9.8886450402207e-06, + "loss": 0.386, + "step": 1489 + }, + { + "epoch": 0.19, + "learning_rate": 9.888427406211694e-06, + "loss": 0.3368, + "step": 1490 + }, + { + "epoch": 0.19, + "learning_rate": 9.888209562136074e-06, + "loss": 0.3741, + "step": 1491 + }, + { + "epoch": 0.19, + "learning_rate": 9.887991508003205e-06, + "loss": 0.3575, + "step": 1492 + }, + { + "epoch": 0.19, + "learning_rate": 9.887773243822454e-06, + "loss": 0.3832, + "step": 1493 + }, + { + "epoch": 0.19, + "learning_rate": 9.8875547696032e-06, + "loss": 0.3123, + "step": 1494 + }, + { + "epoch": 0.19, + "learning_rate": 9.887336085354834e-06, + "loss": 0.3672, + "step": 1495 + }, + { + "epoch": 0.19, + "learning_rate": 9.887117191086749e-06, + "loss": 0.347, + "step": 1496 + }, + { + "epoch": 0.19, + "learning_rate": 9.886898086808356e-06, + "loss": 0.3284, + "step": 1497 + }, + { + "epoch": 0.19, + "learning_rate": 9.886678772529069e-06, + "loss": 0.3755, + "step": 1498 + }, + { + "epoch": 0.19, + "learning_rate": 9.88645924825831e-06, + "loss": 0.3561, + "step": 1499 + }, + { + "epoch": 0.19, + "learning_rate": 9.886239514005515e-06, + "loss": 0.3708, + "step": 1500 + }, + { + "epoch": 0.19, + "learning_rate": 9.886019569780128e-06, + "loss": 0.379, + "step": 1501 + }, + { + "epoch": 0.19, + "learning_rate": 9.885799415591594e-06, + "loss": 0.3953, + "step": 1502 + }, + { + "epoch": 0.19, + "learning_rate": 9.88557905144938e-06, + "loss": 0.4002, + "step": 1503 + }, + { + "epoch": 0.19, + "learning_rate": 9.885358477362956e-06, + "loss": 0.3467, + "step": 1504 + }, + { + "epoch": 0.19, + "learning_rate": 9.885137693341795e-06, + "loss": 0.3537, + "step": 1505 + }, + { + "epoch": 0.19, + "learning_rate": 9.884916699395389e-06, + "loss": 0.354, + "step": 1506 + }, + { + "epoch": 0.19, + "learning_rate": 9.884695495533232e-06, + "loss": 0.3692, + "step": 1507 + }, + { + "epoch": 0.19, + "learning_rate": 9.884474081764833e-06, + "loss": 0.3697, + "step": 1508 + }, + { + "epoch": 0.19, + "learning_rate": 9.8842524580997e-06, + "loss": 0.324, + "step": 1509 + }, + { + "epoch": 0.19, + "learning_rate": 9.884030624547364e-06, + "loss": 0.3616, + "step": 1510 + }, + { + "epoch": 0.19, + "learning_rate": 9.883808581117355e-06, + "loss": 0.3482, + "step": 1511 + }, + { + "epoch": 0.19, + "learning_rate": 9.883586327819214e-06, + "loss": 0.3331, + "step": 1512 + }, + { + "epoch": 0.19, + "learning_rate": 9.883363864662491e-06, + "loss": 0.3552, + "step": 1513 + }, + { + "epoch": 0.19, + "learning_rate": 9.883141191656748e-06, + "loss": 0.3805, + "step": 1514 + }, + { + "epoch": 0.19, + "learning_rate": 9.882918308811554e-06, + "loss": 0.3391, + "step": 1515 + }, + { + "epoch": 0.19, + "learning_rate": 9.882695216136485e-06, + "loss": 0.3424, + "step": 1516 + }, + { + "epoch": 0.19, + "learning_rate": 9.882471913641126e-06, + "loss": 0.3814, + "step": 1517 + }, + { + "epoch": 0.19, + "learning_rate": 9.882248401335076e-06, + "loss": 0.3505, + "step": 1518 + }, + { + "epoch": 0.19, + "learning_rate": 9.88202467922794e-06, + "loss": 0.3717, + "step": 1519 + }, + { + "epoch": 0.19, + "learning_rate": 9.881800747329328e-06, + "loss": 0.3539, + "step": 1520 + }, + { + "epoch": 0.19, + "learning_rate": 9.881576605648869e-06, + "loss": 0.3688, + "step": 1521 + }, + { + "epoch": 0.19, + "learning_rate": 9.881352254196189e-06, + "loss": 0.335, + "step": 1522 + }, + { + "epoch": 0.19, + "learning_rate": 9.881127692980932e-06, + "loss": 0.357, + "step": 1523 + }, + { + "epoch": 0.2, + "learning_rate": 9.880902922012747e-06, + "loss": 0.3752, + "step": 1524 + }, + { + "epoch": 0.2, + "learning_rate": 9.880677941301293e-06, + "loss": 0.3578, + "step": 1525 + }, + { + "epoch": 0.2, + "learning_rate": 9.880452750856239e-06, + "loss": 0.3212, + "step": 1526 + }, + { + "epoch": 0.2, + "learning_rate": 9.880227350687259e-06, + "loss": 0.3325, + "step": 1527 + }, + { + "epoch": 0.2, + "learning_rate": 9.880001740804043e-06, + "loss": 0.3524, + "step": 1528 + }, + { + "epoch": 0.2, + "learning_rate": 9.879775921216284e-06, + "loss": 0.3674, + "step": 1529 + }, + { + "epoch": 0.2, + "learning_rate": 9.879549891933684e-06, + "loss": 0.3652, + "step": 1530 + }, + { + "epoch": 0.2, + "learning_rate": 9.879323652965957e-06, + "loss": 0.3222, + "step": 1531 + }, + { + "epoch": 0.2, + "learning_rate": 9.879097204322828e-06, + "loss": 0.3478, + "step": 1532 + }, + { + "epoch": 0.2, + "learning_rate": 9.878870546014025e-06, + "loss": 0.3609, + "step": 1533 + }, + { + "epoch": 0.2, + "learning_rate": 9.87864367804929e-06, + "loss": 0.3554, + "step": 1534 + }, + { + "epoch": 0.2, + "learning_rate": 9.87841660043837e-06, + "loss": 0.3639, + "step": 1535 + }, + { + "epoch": 0.2, + "learning_rate": 9.878189313191023e-06, + "loss": 0.3512, + "step": 1536 + }, + { + "epoch": 0.2, + "learning_rate": 9.877961816317018e-06, + "loss": 0.3538, + "step": 1537 + }, + { + "epoch": 0.2, + "learning_rate": 9.87773410982613e-06, + "loss": 0.3604, + "step": 1538 + }, + { + "epoch": 0.2, + "learning_rate": 9.877506193728144e-06, + "loss": 0.384, + "step": 1539 + }, + { + "epoch": 0.2, + "learning_rate": 9.877278068032852e-06, + "loss": 0.3518, + "step": 1540 + }, + { + "epoch": 0.2, + "learning_rate": 9.877049732750062e-06, + "loss": 0.3758, + "step": 1541 + }, + { + "epoch": 0.2, + "learning_rate": 9.876821187889581e-06, + "loss": 0.3667, + "step": 1542 + }, + { + "epoch": 0.2, + "learning_rate": 9.876592433461234e-06, + "loss": 0.3482, + "step": 1543 + }, + { + "epoch": 0.2, + "learning_rate": 9.876363469474848e-06, + "loss": 0.3758, + "step": 1544 + }, + { + "epoch": 0.2, + "learning_rate": 9.876134295940264e-06, + "loss": 0.3445, + "step": 1545 + }, + { + "epoch": 0.2, + "learning_rate": 9.875904912867328e-06, + "loss": 0.3372, + "step": 1546 + }, + { + "epoch": 0.2, + "learning_rate": 9.875675320265903e-06, + "loss": 0.3442, + "step": 1547 + }, + { + "epoch": 0.2, + "learning_rate": 9.875445518145848e-06, + "loss": 0.3538, + "step": 1548 + }, + { + "epoch": 0.2, + "learning_rate": 9.87521550651704e-06, + "loss": 0.3577, + "step": 1549 + }, + { + "epoch": 0.2, + "learning_rate": 9.874985285389364e-06, + "loss": 0.3547, + "step": 1550 + }, + { + "epoch": 0.2, + "learning_rate": 9.874754854772714e-06, + "loss": 0.3641, + "step": 1551 + }, + { + "epoch": 0.2, + "learning_rate": 9.874524214676993e-06, + "loss": 0.3669, + "step": 1552 + }, + { + "epoch": 0.2, + "learning_rate": 9.874293365112109e-06, + "loss": 0.341, + "step": 1553 + }, + { + "epoch": 0.2, + "learning_rate": 9.874062306087983e-06, + "loss": 0.3577, + "step": 1554 + }, + { + "epoch": 0.2, + "learning_rate": 9.873831037614544e-06, + "loss": 0.3672, + "step": 1555 + }, + { + "epoch": 0.2, + "learning_rate": 9.873599559701732e-06, + "loss": 0.3557, + "step": 1556 + }, + { + "epoch": 0.2, + "learning_rate": 9.873367872359492e-06, + "loss": 0.3518, + "step": 1557 + }, + { + "epoch": 0.2, + "learning_rate": 9.873135975597781e-06, + "loss": 0.3566, + "step": 1558 + }, + { + "epoch": 0.2, + "learning_rate": 9.872903869426564e-06, + "loss": 0.3718, + "step": 1559 + }, + { + "epoch": 0.2, + "learning_rate": 9.872671553855817e-06, + "loss": 0.3384, + "step": 1560 + }, + { + "epoch": 0.2, + "learning_rate": 9.872439028895518e-06, + "loss": 0.3674, + "step": 1561 + }, + { + "epoch": 0.2, + "learning_rate": 9.872206294555665e-06, + "loss": 0.3636, + "step": 1562 + }, + { + "epoch": 0.2, + "learning_rate": 9.871973350846255e-06, + "loss": 0.3364, + "step": 1563 + }, + { + "epoch": 0.2, + "learning_rate": 9.8717401977773e-06, + "loss": 0.3414, + "step": 1564 + }, + { + "epoch": 0.2, + "learning_rate": 9.87150683535882e-06, + "loss": 0.3274, + "step": 1565 + }, + { + "epoch": 0.2, + "learning_rate": 9.871273263600842e-06, + "loss": 0.3918, + "step": 1566 + }, + { + "epoch": 0.2, + "learning_rate": 9.871039482513402e-06, + "loss": 0.3826, + "step": 1567 + }, + { + "epoch": 0.2, + "learning_rate": 9.870805492106546e-06, + "loss": 0.3728, + "step": 1568 + }, + { + "epoch": 0.2, + "learning_rate": 9.870571292390331e-06, + "loss": 0.3552, + "step": 1569 + }, + { + "epoch": 0.2, + "learning_rate": 9.87033688337482e-06, + "loss": 0.3568, + "step": 1570 + }, + { + "epoch": 0.2, + "learning_rate": 9.870102265070087e-06, + "loss": 0.4138, + "step": 1571 + }, + { + "epoch": 0.2, + "learning_rate": 9.869867437486214e-06, + "loss": 0.3573, + "step": 1572 + }, + { + "epoch": 0.2, + "learning_rate": 9.86963240063329e-06, + "loss": 0.3344, + "step": 1573 + }, + { + "epoch": 0.2, + "learning_rate": 9.869397154521418e-06, + "loss": 0.3476, + "step": 1574 + }, + { + "epoch": 0.2, + "learning_rate": 9.869161699160704e-06, + "loss": 0.3564, + "step": 1575 + }, + { + "epoch": 0.2, + "learning_rate": 9.868926034561268e-06, + "loss": 0.3481, + "step": 1576 + }, + { + "epoch": 0.2, + "learning_rate": 9.868690160733237e-06, + "loss": 0.3666, + "step": 1577 + }, + { + "epoch": 0.2, + "learning_rate": 9.868454077686746e-06, + "loss": 0.3774, + "step": 1578 + }, + { + "epoch": 0.2, + "learning_rate": 9.868217785431942e-06, + "loss": 0.3565, + "step": 1579 + }, + { + "epoch": 0.2, + "learning_rate": 9.867981283978975e-06, + "loss": 0.3497, + "step": 1580 + }, + { + "epoch": 0.2, + "learning_rate": 9.867744573338012e-06, + "loss": 0.3482, + "step": 1581 + }, + { + "epoch": 0.2, + "learning_rate": 9.867507653519225e-06, + "loss": 0.3437, + "step": 1582 + }, + { + "epoch": 0.2, + "learning_rate": 9.867270524532792e-06, + "loss": 0.3479, + "step": 1583 + }, + { + "epoch": 0.2, + "learning_rate": 9.867033186388906e-06, + "loss": 0.3332, + "step": 1584 + }, + { + "epoch": 0.2, + "learning_rate": 9.866795639097763e-06, + "loss": 0.3054, + "step": 1585 + }, + { + "epoch": 0.2, + "learning_rate": 9.866557882669574e-06, + "loss": 0.3462, + "step": 1586 + }, + { + "epoch": 0.2, + "learning_rate": 9.866319917114554e-06, + "loss": 0.3719, + "step": 1587 + }, + { + "epoch": 0.2, + "learning_rate": 9.866081742442928e-06, + "loss": 0.3649, + "step": 1588 + }, + { + "epoch": 0.2, + "learning_rate": 9.865843358664933e-06, + "loss": 0.3474, + "step": 1589 + }, + { + "epoch": 0.2, + "learning_rate": 9.865604765790812e-06, + "loss": 0.3239, + "step": 1590 + }, + { + "epoch": 0.2, + "learning_rate": 9.865365963830818e-06, + "loss": 0.3486, + "step": 1591 + }, + { + "epoch": 0.2, + "learning_rate": 9.865126952795212e-06, + "loss": 0.3951, + "step": 1592 + }, + { + "epoch": 0.2, + "learning_rate": 9.864887732694266e-06, + "loss": 0.3548, + "step": 1593 + }, + { + "epoch": 0.2, + "learning_rate": 9.86464830353826e-06, + "loss": 0.3349, + "step": 1594 + }, + { + "epoch": 0.2, + "learning_rate": 9.864408665337482e-06, + "loss": 0.3594, + "step": 1595 + }, + { + "epoch": 0.2, + "learning_rate": 9.86416881810223e-06, + "loss": 0.3583, + "step": 1596 + }, + { + "epoch": 0.2, + "learning_rate": 9.86392876184281e-06, + "loss": 0.3467, + "step": 1597 + }, + { + "epoch": 0.2, + "learning_rate": 9.86368849656954e-06, + "loss": 0.36, + "step": 1598 + }, + { + "epoch": 0.2, + "learning_rate": 9.863448022292742e-06, + "loss": 0.3115, + "step": 1599 + }, + { + "epoch": 0.2, + "learning_rate": 9.863207339022753e-06, + "loss": 0.3872, + "step": 1600 + }, + { + "epoch": 0.2, + "learning_rate": 9.862966446769912e-06, + "loss": 0.3858, + "step": 1601 + }, + { + "epoch": 0.21, + "learning_rate": 9.862725345544573e-06, + "loss": 0.3518, + "step": 1602 + }, + { + "epoch": 0.21, + "learning_rate": 9.862484035357095e-06, + "loss": 0.3245, + "step": 1603 + }, + { + "epoch": 0.21, + "learning_rate": 9.86224251621785e-06, + "loss": 0.3365, + "step": 1604 + }, + { + "epoch": 0.21, + "learning_rate": 9.862000788137215e-06, + "loss": 0.3516, + "step": 1605 + }, + { + "epoch": 0.21, + "learning_rate": 9.861758851125578e-06, + "loss": 0.3826, + "step": 1606 + }, + { + "epoch": 0.21, + "learning_rate": 9.861516705193334e-06, + "loss": 0.3394, + "step": 1607 + }, + { + "epoch": 0.21, + "learning_rate": 9.861274350350891e-06, + "loss": 0.3598, + "step": 1608 + }, + { + "epoch": 0.21, + "learning_rate": 9.861031786608663e-06, + "loss": 0.3836, + "step": 1609 + }, + { + "epoch": 0.21, + "learning_rate": 9.860789013977074e-06, + "loss": 0.3447, + "step": 1610 + }, + { + "epoch": 0.21, + "learning_rate": 9.860546032466553e-06, + "loss": 0.3186, + "step": 1611 + }, + { + "epoch": 0.21, + "learning_rate": 9.860302842087545e-06, + "loss": 0.3748, + "step": 1612 + }, + { + "epoch": 0.21, + "learning_rate": 9.8600594428505e-06, + "loss": 0.365, + "step": 1613 + }, + { + "epoch": 0.21, + "learning_rate": 9.859815834765875e-06, + "loss": 0.3536, + "step": 1614 + }, + { + "epoch": 0.21, + "learning_rate": 9.859572017844143e-06, + "loss": 0.3415, + "step": 1615 + }, + { + "epoch": 0.21, + "learning_rate": 9.859327992095777e-06, + "loss": 0.344, + "step": 1616 + }, + { + "epoch": 0.21, + "learning_rate": 9.859083757531265e-06, + "loss": 0.3695, + "step": 1617 + }, + { + "epoch": 0.21, + "learning_rate": 9.858839314161101e-06, + "loss": 0.3506, + "step": 1618 + }, + { + "epoch": 0.21, + "learning_rate": 9.858594661995792e-06, + "loss": 0.3549, + "step": 1619 + }, + { + "epoch": 0.21, + "learning_rate": 9.85834980104585e-06, + "loss": 0.3393, + "step": 1620 + }, + { + "epoch": 0.21, + "learning_rate": 9.858104731321796e-06, + "loss": 0.3439, + "step": 1621 + }, + { + "epoch": 0.21, + "learning_rate": 9.857859452834161e-06, + "loss": 0.3616, + "step": 1622 + }, + { + "epoch": 0.21, + "learning_rate": 9.857613965593488e-06, + "loss": 0.3591, + "step": 1623 + }, + { + "epoch": 0.21, + "learning_rate": 9.857368269610325e-06, + "loss": 0.3801, + "step": 1624 + }, + { + "epoch": 0.21, + "learning_rate": 9.857122364895229e-06, + "loss": 0.4002, + "step": 1625 + }, + { + "epoch": 0.21, + "learning_rate": 9.856876251458767e-06, + "loss": 0.351, + "step": 1626 + }, + { + "epoch": 0.21, + "learning_rate": 9.856629929311516e-06, + "loss": 0.3412, + "step": 1627 + }, + { + "epoch": 0.21, + "learning_rate": 9.85638339846406e-06, + "loss": 0.3466, + "step": 1628 + }, + { + "epoch": 0.21, + "learning_rate": 9.856136658926993e-06, + "loss": 0.358, + "step": 1629 + }, + { + "epoch": 0.21, + "learning_rate": 9.855889710710919e-06, + "loss": 0.3396, + "step": 1630 + }, + { + "epoch": 0.21, + "learning_rate": 9.85564255382645e-06, + "loss": 0.377, + "step": 1631 + }, + { + "epoch": 0.21, + "learning_rate": 9.855395188284206e-06, + "loss": 0.375, + "step": 1632 + }, + { + "epoch": 0.21, + "learning_rate": 9.85514761409482e-06, + "loss": 0.313, + "step": 1633 + }, + { + "epoch": 0.21, + "learning_rate": 9.854899831268926e-06, + "loss": 0.3408, + "step": 1634 + }, + { + "epoch": 0.21, + "learning_rate": 9.854651839817174e-06, + "loss": 0.3326, + "step": 1635 + }, + { + "epoch": 0.21, + "learning_rate": 9.854403639750219e-06, + "loss": 0.3741, + "step": 1636 + }, + { + "epoch": 0.21, + "learning_rate": 9.854155231078728e-06, + "loss": 0.323, + "step": 1637 + }, + { + "epoch": 0.21, + "learning_rate": 9.853906613813378e-06, + "loss": 0.315, + "step": 1638 + }, + { + "epoch": 0.21, + "learning_rate": 9.85365778796485e-06, + "loss": 0.3719, + "step": 1639 + }, + { + "epoch": 0.21, + "learning_rate": 9.853408753543835e-06, + "loss": 0.4013, + "step": 1640 + }, + { + "epoch": 0.21, + "learning_rate": 9.85315951056104e-06, + "loss": 0.3549, + "step": 1641 + }, + { + "epoch": 0.21, + "learning_rate": 9.852910059027172e-06, + "loss": 0.3711, + "step": 1642 + }, + { + "epoch": 0.21, + "learning_rate": 9.852660398952949e-06, + "loss": 0.3723, + "step": 1643 + }, + { + "epoch": 0.21, + "learning_rate": 9.852410530349102e-06, + "loss": 0.3257, + "step": 1644 + }, + { + "epoch": 0.21, + "learning_rate": 9.852160453226367e-06, + "loss": 0.3708, + "step": 1645 + }, + { + "epoch": 0.21, + "learning_rate": 9.851910167595493e-06, + "loss": 0.4041, + "step": 1646 + }, + { + "epoch": 0.21, + "learning_rate": 9.851659673467232e-06, + "loss": 0.3853, + "step": 1647 + }, + { + "epoch": 0.21, + "learning_rate": 9.85140897085235e-06, + "loss": 0.3795, + "step": 1648 + }, + { + "epoch": 0.21, + "learning_rate": 9.851158059761617e-06, + "loss": 0.3501, + "step": 1649 + }, + { + "epoch": 0.21, + "learning_rate": 9.850906940205822e-06, + "loss": 0.3712, + "step": 1650 + }, + { + "epoch": 0.21, + "learning_rate": 9.85065561219575e-06, + "loss": 0.3612, + "step": 1651 + }, + { + "epoch": 0.21, + "learning_rate": 9.850404075742204e-06, + "loss": 0.3422, + "step": 1652 + }, + { + "epoch": 0.21, + "learning_rate": 9.850152330855992e-06, + "loss": 0.3881, + "step": 1653 + }, + { + "epoch": 0.21, + "learning_rate": 9.849900377547933e-06, + "loss": 0.3599, + "step": 1654 + }, + { + "epoch": 0.21, + "learning_rate": 9.849648215828853e-06, + "loss": 0.3514, + "step": 1655 + }, + { + "epoch": 0.21, + "learning_rate": 9.849395845709588e-06, + "loss": 0.3275, + "step": 1656 + }, + { + "epoch": 0.21, + "learning_rate": 9.849143267200985e-06, + "loss": 0.3649, + "step": 1657 + }, + { + "epoch": 0.21, + "learning_rate": 9.848890480313894e-06, + "loss": 0.3453, + "step": 1658 + }, + { + "epoch": 0.21, + "learning_rate": 9.848637485059183e-06, + "loss": 0.3641, + "step": 1659 + }, + { + "epoch": 0.21, + "learning_rate": 9.848384281447718e-06, + "loss": 0.3294, + "step": 1660 + }, + { + "epoch": 0.21, + "learning_rate": 9.848130869490384e-06, + "loss": 0.3551, + "step": 1661 + }, + { + "epoch": 0.21, + "learning_rate": 9.847877249198069e-06, + "loss": 0.344, + "step": 1662 + }, + { + "epoch": 0.21, + "learning_rate": 9.84762342058167e-06, + "loss": 0.3406, + "step": 1663 + }, + { + "epoch": 0.21, + "learning_rate": 9.8473693836521e-06, + "loss": 0.3334, + "step": 1664 + }, + { + "epoch": 0.21, + "learning_rate": 9.84711513842027e-06, + "loss": 0.3446, + "step": 1665 + }, + { + "epoch": 0.21, + "learning_rate": 9.846860684897107e-06, + "loss": 0.3321, + "step": 1666 + }, + { + "epoch": 0.21, + "learning_rate": 9.846606023093545e-06, + "loss": 0.3618, + "step": 1667 + }, + { + "epoch": 0.21, + "learning_rate": 9.84635115302053e-06, + "loss": 0.3743, + "step": 1668 + }, + { + "epoch": 0.21, + "learning_rate": 9.846096074689012e-06, + "loss": 0.3681, + "step": 1669 + }, + { + "epoch": 0.21, + "learning_rate": 9.845840788109953e-06, + "loss": 0.3394, + "step": 1670 + }, + { + "epoch": 0.21, + "learning_rate": 9.845585293294321e-06, + "loss": 0.3571, + "step": 1671 + }, + { + "epoch": 0.21, + "learning_rate": 9.845329590253098e-06, + "loss": 0.3734, + "step": 1672 + }, + { + "epoch": 0.21, + "learning_rate": 9.845073678997275e-06, + "loss": 0.3364, + "step": 1673 + }, + { + "epoch": 0.21, + "learning_rate": 9.844817559537841e-06, + "loss": 0.3296, + "step": 1674 + }, + { + "epoch": 0.21, + "learning_rate": 9.84456123188581e-06, + "loss": 0.3487, + "step": 1675 + }, + { + "epoch": 0.21, + "learning_rate": 9.84430469605219e-06, + "loss": 0.3576, + "step": 1676 + }, + { + "epoch": 0.21, + "learning_rate": 9.84404795204801e-06, + "loss": 0.3465, + "step": 1677 + }, + { + "epoch": 0.21, + "learning_rate": 9.843790999884301e-06, + "loss": 0.3317, + "step": 1678 + }, + { + "epoch": 0.21, + "learning_rate": 9.843533839572105e-06, + "loss": 0.3518, + "step": 1679 + }, + { + "epoch": 0.22, + "learning_rate": 9.843276471122473e-06, + "loss": 0.3811, + "step": 1680 + }, + { + "epoch": 0.22, + "learning_rate": 9.843018894546466e-06, + "loss": 0.3747, + "step": 1681 + }, + { + "epoch": 0.22, + "learning_rate": 9.84276110985515e-06, + "loss": 0.3731, + "step": 1682 + }, + { + "epoch": 0.22, + "learning_rate": 9.842503117059604e-06, + "loss": 0.3264, + "step": 1683 + }, + { + "epoch": 0.22, + "learning_rate": 9.842244916170913e-06, + "loss": 0.3588, + "step": 1684 + }, + { + "epoch": 0.22, + "learning_rate": 9.841986507200174e-06, + "loss": 0.3672, + "step": 1685 + }, + { + "epoch": 0.22, + "learning_rate": 9.841727890158493e-06, + "loss": 0.3257, + "step": 1686 + }, + { + "epoch": 0.22, + "learning_rate": 9.84146906505698e-06, + "loss": 0.3333, + "step": 1687 + }, + { + "epoch": 0.22, + "learning_rate": 9.841210031906758e-06, + "loss": 0.3827, + "step": 1688 + }, + { + "epoch": 0.22, + "learning_rate": 9.840950790718959e-06, + "loss": 0.3704, + "step": 1689 + }, + { + "epoch": 0.22, + "learning_rate": 9.840691341504725e-06, + "loss": 0.3466, + "step": 1690 + }, + { + "epoch": 0.22, + "learning_rate": 9.8404316842752e-06, + "loss": 0.3393, + "step": 1691 + }, + { + "epoch": 0.22, + "learning_rate": 9.84017181904155e-06, + "loss": 0.3454, + "step": 1692 + }, + { + "epoch": 0.22, + "learning_rate": 9.839911745814933e-06, + "loss": 0.3601, + "step": 1693 + }, + { + "epoch": 0.22, + "learning_rate": 9.83965146460653e-06, + "loss": 0.3653, + "step": 1694 + }, + { + "epoch": 0.22, + "learning_rate": 9.839390975427526e-06, + "loss": 0.3513, + "step": 1695 + }, + { + "epoch": 0.22, + "learning_rate": 9.839130278289115e-06, + "loss": 0.3515, + "step": 1696 + }, + { + "epoch": 0.22, + "learning_rate": 9.838869373202498e-06, + "loss": 0.3578, + "step": 1697 + }, + { + "epoch": 0.22, + "learning_rate": 9.838608260178885e-06, + "loss": 0.3431, + "step": 1698 + }, + { + "epoch": 0.22, + "learning_rate": 9.838346939229501e-06, + "loss": 0.3624, + "step": 1699 + }, + { + "epoch": 0.22, + "learning_rate": 9.838085410365573e-06, + "loss": 0.3543, + "step": 1700 + }, + { + "epoch": 0.22, + "learning_rate": 9.83782367359834e-06, + "loss": 0.3383, + "step": 1701 + }, + { + "epoch": 0.22, + "learning_rate": 9.837561728939048e-06, + "loss": 0.3458, + "step": 1702 + }, + { + "epoch": 0.22, + "learning_rate": 9.837299576398958e-06, + "loss": 0.3504, + "step": 1703 + }, + { + "epoch": 0.22, + "learning_rate": 9.83703721598933e-06, + "loss": 0.3499, + "step": 1704 + }, + { + "epoch": 0.22, + "learning_rate": 9.83677464772144e-06, + "loss": 0.3447, + "step": 1705 + }, + { + "epoch": 0.22, + "learning_rate": 9.83651187160657e-06, + "loss": 0.3706, + "step": 1706 + }, + { + "epoch": 0.22, + "learning_rate": 9.836248887656016e-06, + "loss": 0.3529, + "step": 1707 + }, + { + "epoch": 0.22, + "learning_rate": 9.835985695881076e-06, + "loss": 0.362, + "step": 1708 + }, + { + "epoch": 0.22, + "learning_rate": 9.835722296293058e-06, + "loss": 0.369, + "step": 1709 + }, + { + "epoch": 0.22, + "learning_rate": 9.835458688903286e-06, + "loss": 0.3806, + "step": 1710 + }, + { + "epoch": 0.22, + "learning_rate": 9.835194873723085e-06, + "loss": 0.3361, + "step": 1711 + }, + { + "epoch": 0.22, + "learning_rate": 9.834930850763789e-06, + "loss": 0.3476, + "step": 1712 + }, + { + "epoch": 0.22, + "learning_rate": 9.834666620036748e-06, + "loss": 0.347, + "step": 1713 + }, + { + "epoch": 0.22, + "learning_rate": 9.834402181553314e-06, + "loss": 0.3488, + "step": 1714 + }, + { + "epoch": 0.22, + "learning_rate": 9.834137535324852e-06, + "loss": 0.3709, + "step": 1715 + }, + { + "epoch": 0.22, + "learning_rate": 9.833872681362735e-06, + "loss": 0.3219, + "step": 1716 + }, + { + "epoch": 0.22, + "learning_rate": 9.833607619678343e-06, + "loss": 0.3559, + "step": 1717 + }, + { + "epoch": 0.22, + "learning_rate": 9.833342350283067e-06, + "loss": 0.3349, + "step": 1718 + }, + { + "epoch": 0.22, + "learning_rate": 9.833076873188303e-06, + "loss": 0.3774, + "step": 1719 + }, + { + "epoch": 0.22, + "learning_rate": 9.832811188405464e-06, + "loss": 0.3593, + "step": 1720 + }, + { + "epoch": 0.22, + "learning_rate": 9.832545295945964e-06, + "loss": 0.355, + "step": 1721 + }, + { + "epoch": 0.22, + "learning_rate": 9.83227919582123e-06, + "loss": 0.3624, + "step": 1722 + }, + { + "epoch": 0.22, + "learning_rate": 9.832012888042699e-06, + "loss": 0.3361, + "step": 1723 + }, + { + "epoch": 0.22, + "learning_rate": 9.831746372621811e-06, + "loss": 0.3471, + "step": 1724 + }, + { + "epoch": 0.22, + "learning_rate": 9.831479649570021e-06, + "loss": 0.3521, + "step": 1725 + }, + { + "epoch": 0.22, + "learning_rate": 9.83121271889879e-06, + "loss": 0.3549, + "step": 1726 + }, + { + "epoch": 0.22, + "learning_rate": 9.830945580619588e-06, + "loss": 0.3471, + "step": 1727 + }, + { + "epoch": 0.22, + "learning_rate": 9.830678234743896e-06, + "loss": 0.33, + "step": 1728 + }, + { + "epoch": 0.22, + "learning_rate": 9.830410681283203e-06, + "loss": 0.3445, + "step": 1729 + }, + { + "epoch": 0.22, + "learning_rate": 9.830142920249004e-06, + "loss": 0.3465, + "step": 1730 + }, + { + "epoch": 0.22, + "learning_rate": 9.829874951652807e-06, + "loss": 0.3301, + "step": 1731 + }, + { + "epoch": 0.22, + "learning_rate": 9.829606775506124e-06, + "loss": 0.3662, + "step": 1732 + }, + { + "epoch": 0.22, + "learning_rate": 9.829338391820484e-06, + "loss": 0.3755, + "step": 1733 + }, + { + "epoch": 0.22, + "learning_rate": 9.829069800607418e-06, + "loss": 0.3376, + "step": 1734 + }, + { + "epoch": 0.22, + "learning_rate": 9.828801001878468e-06, + "loss": 0.3592, + "step": 1735 + }, + { + "epoch": 0.22, + "learning_rate": 9.828531995645183e-06, + "loss": 0.358, + "step": 1736 + }, + { + "epoch": 0.22, + "learning_rate": 9.828262781919124e-06, + "loss": 0.3456, + "step": 1737 + }, + { + "epoch": 0.22, + "learning_rate": 9.827993360711863e-06, + "loss": 0.3341, + "step": 1738 + }, + { + "epoch": 0.22, + "learning_rate": 9.827723732034972e-06, + "loss": 0.3439, + "step": 1739 + }, + { + "epoch": 0.22, + "learning_rate": 9.827453895900043e-06, + "loss": 0.3595, + "step": 1740 + }, + { + "epoch": 0.22, + "learning_rate": 9.827183852318666e-06, + "loss": 0.3535, + "step": 1741 + }, + { + "epoch": 0.22, + "learning_rate": 9.82691360130245e-06, + "loss": 0.3751, + "step": 1742 + }, + { + "epoch": 0.22, + "learning_rate": 9.826643142863006e-06, + "loss": 0.3582, + "step": 1743 + }, + { + "epoch": 0.22, + "learning_rate": 9.826372477011956e-06, + "loss": 0.3749, + "step": 1744 + }, + { + "epoch": 0.22, + "learning_rate": 9.826101603760934e-06, + "loss": 0.3696, + "step": 1745 + }, + { + "epoch": 0.22, + "learning_rate": 9.825830523121575e-06, + "loss": 0.3436, + "step": 1746 + }, + { + "epoch": 0.22, + "learning_rate": 9.825559235105532e-06, + "loss": 0.3657, + "step": 1747 + }, + { + "epoch": 0.22, + "learning_rate": 9.82528773972446e-06, + "loss": 0.3534, + "step": 1748 + }, + { + "epoch": 0.22, + "learning_rate": 9.825016036990029e-06, + "loss": 0.3636, + "step": 1749 + }, + { + "epoch": 0.22, + "learning_rate": 9.824744126913914e-06, + "loss": 0.364, + "step": 1750 + }, + { + "epoch": 0.22, + "learning_rate": 9.824472009507796e-06, + "loss": 0.367, + "step": 1751 + }, + { + "epoch": 0.22, + "learning_rate": 9.824199684783373e-06, + "loss": 0.3395, + "step": 1752 + }, + { + "epoch": 0.22, + "learning_rate": 9.823927152752344e-06, + "loss": 0.3482, + "step": 1753 + }, + { + "epoch": 0.22, + "learning_rate": 9.823654413426424e-06, + "loss": 0.3625, + "step": 1754 + }, + { + "epoch": 0.22, + "learning_rate": 9.82338146681733e-06, + "loss": 0.356, + "step": 1755 + }, + { + "epoch": 0.22, + "learning_rate": 9.823108312936791e-06, + "loss": 0.3705, + "step": 1756 + }, + { + "epoch": 0.22, + "learning_rate": 9.822834951796547e-06, + "loss": 0.3698, + "step": 1757 + }, + { + "epoch": 0.23, + "learning_rate": 9.822561383408345e-06, + "loss": 0.3313, + "step": 1758 + }, + { + "epoch": 0.23, + "learning_rate": 9.822287607783938e-06, + "loss": 0.373, + "step": 1759 + }, + { + "epoch": 0.23, + "learning_rate": 9.822013624935093e-06, + "loss": 0.35, + "step": 1760 + }, + { + "epoch": 0.23, + "learning_rate": 9.821739434873586e-06, + "loss": 0.3367, + "step": 1761 + }, + { + "epoch": 0.23, + "learning_rate": 9.821465037611194e-06, + "loss": 0.3616, + "step": 1762 + }, + { + "epoch": 0.23, + "learning_rate": 9.821190433159711e-06, + "loss": 0.3537, + "step": 1763 + }, + { + "epoch": 0.23, + "learning_rate": 9.820915621530939e-06, + "loss": 0.3569, + "step": 1764 + }, + { + "epoch": 0.23, + "learning_rate": 9.820640602736687e-06, + "loss": 0.3493, + "step": 1765 + }, + { + "epoch": 0.23, + "learning_rate": 9.82036537678877e-06, + "loss": 0.3715, + "step": 1766 + }, + { + "epoch": 0.23, + "learning_rate": 9.820089943699018e-06, + "loss": 0.36, + "step": 1767 + }, + { + "epoch": 0.23, + "learning_rate": 9.819814303479268e-06, + "loss": 0.3659, + "step": 1768 + }, + { + "epoch": 0.23, + "learning_rate": 9.81953845614136e-06, + "loss": 0.3251, + "step": 1769 + }, + { + "epoch": 0.23, + "learning_rate": 9.819262401697154e-06, + "loss": 0.3273, + "step": 1770 + }, + { + "epoch": 0.23, + "learning_rate": 9.818986140158507e-06, + "loss": 0.3305, + "step": 1771 + }, + { + "epoch": 0.23, + "learning_rate": 9.818709671537295e-06, + "loss": 0.3697, + "step": 1772 + }, + { + "epoch": 0.23, + "learning_rate": 9.818432995845394e-06, + "loss": 0.3521, + "step": 1773 + }, + { + "epoch": 0.23, + "learning_rate": 9.818156113094699e-06, + "loss": 0.338, + "step": 1774 + }, + { + "epoch": 0.23, + "learning_rate": 9.817879023297103e-06, + "loss": 0.3626, + "step": 1775 + }, + { + "epoch": 0.23, + "learning_rate": 9.817601726464516e-06, + "loss": 0.335, + "step": 1776 + }, + { + "epoch": 0.23, + "learning_rate": 9.817324222608853e-06, + "loss": 0.3994, + "step": 1777 + }, + { + "epoch": 0.23, + "learning_rate": 9.817046511742042e-06, + "loss": 0.3337, + "step": 1778 + }, + { + "epoch": 0.23, + "learning_rate": 9.816768593876012e-06, + "loss": 0.3316, + "step": 1779 + }, + { + "epoch": 0.23, + "learning_rate": 9.816490469022708e-06, + "loss": 0.3573, + "step": 1780 + }, + { + "epoch": 0.23, + "learning_rate": 9.816212137194081e-06, + "loss": 0.3466, + "step": 1781 + }, + { + "epoch": 0.23, + "learning_rate": 9.815933598402095e-06, + "loss": 0.3569, + "step": 1782 + }, + { + "epoch": 0.23, + "learning_rate": 9.815654852658714e-06, + "loss": 0.3252, + "step": 1783 + }, + { + "epoch": 0.23, + "learning_rate": 9.81537589997592e-06, + "loss": 0.3671, + "step": 1784 + }, + { + "epoch": 0.23, + "learning_rate": 9.815096740365698e-06, + "loss": 0.4043, + "step": 1785 + }, + { + "epoch": 0.23, + "learning_rate": 9.814817373840046e-06, + "loss": 0.318, + "step": 1786 + }, + { + "epoch": 0.23, + "learning_rate": 9.814537800410968e-06, + "loss": 0.3597, + "step": 1787 + }, + { + "epoch": 0.23, + "learning_rate": 9.814258020090478e-06, + "loss": 0.3623, + "step": 1788 + }, + { + "epoch": 0.23, + "learning_rate": 9.8139780328906e-06, + "loss": 0.3434, + "step": 1789 + }, + { + "epoch": 0.23, + "learning_rate": 9.813697838823364e-06, + "loss": 0.3517, + "step": 1790 + }, + { + "epoch": 0.23, + "learning_rate": 9.813417437900812e-06, + "loss": 0.3655, + "step": 1791 + }, + { + "epoch": 0.23, + "learning_rate": 9.81313683013499e-06, + "loss": 0.3621, + "step": 1792 + }, + { + "epoch": 0.23, + "learning_rate": 9.81285601553796e-06, + "loss": 0.3476, + "step": 1793 + }, + { + "epoch": 0.23, + "learning_rate": 9.812574994121791e-06, + "loss": 0.3417, + "step": 1794 + }, + { + "epoch": 0.23, + "learning_rate": 9.812293765898555e-06, + "loss": 0.3598, + "step": 1795 + }, + { + "epoch": 0.23, + "learning_rate": 9.812012330880337e-06, + "loss": 0.3392, + "step": 1796 + }, + { + "epoch": 0.23, + "learning_rate": 9.811730689079233e-06, + "loss": 0.3625, + "step": 1797 + }, + { + "epoch": 0.23, + "learning_rate": 9.811448840507345e-06, + "loss": 0.3449, + "step": 1798 + }, + { + "epoch": 0.23, + "learning_rate": 9.811166785176785e-06, + "loss": 0.3364, + "step": 1799 + }, + { + "epoch": 0.23, + "learning_rate": 9.810884523099673e-06, + "loss": 0.3906, + "step": 1800 + }, + { + "epoch": 0.23, + "learning_rate": 9.810602054288138e-06, + "loss": 0.3657, + "step": 1801 + }, + { + "epoch": 0.23, + "learning_rate": 9.81031937875432e-06, + "loss": 0.3468, + "step": 1802 + }, + { + "epoch": 0.23, + "learning_rate": 9.810036496510364e-06, + "loss": 0.3486, + "step": 1803 + }, + { + "epoch": 0.23, + "learning_rate": 9.809753407568427e-06, + "loss": 0.3457, + "step": 1804 + }, + { + "epoch": 0.23, + "learning_rate": 9.809470111940675e-06, + "loss": 0.3484, + "step": 1805 + }, + { + "epoch": 0.23, + "learning_rate": 9.809186609639281e-06, + "loss": 0.3492, + "step": 1806 + }, + { + "epoch": 0.23, + "learning_rate": 9.808902900676429e-06, + "loss": 0.3476, + "step": 1807 + }, + { + "epoch": 0.23, + "learning_rate": 9.808618985064307e-06, + "loss": 0.346, + "step": 1808 + }, + { + "epoch": 0.23, + "learning_rate": 9.80833486281512e-06, + "loss": 0.348, + "step": 1809 + }, + { + "epoch": 0.23, + "learning_rate": 9.808050533941074e-06, + "loss": 0.3515, + "step": 1810 + }, + { + "epoch": 0.23, + "learning_rate": 9.807765998454388e-06, + "loss": 0.3667, + "step": 1811 + }, + { + "epoch": 0.23, + "learning_rate": 9.80748125636729e-06, + "loss": 0.3619, + "step": 1812 + }, + { + "epoch": 0.23, + "learning_rate": 9.807196307692015e-06, + "loss": 0.3732, + "step": 1813 + }, + { + "epoch": 0.23, + "learning_rate": 9.80691115244081e-06, + "loss": 0.3673, + "step": 1814 + }, + { + "epoch": 0.23, + "learning_rate": 9.806625790625925e-06, + "loss": 0.3681, + "step": 1815 + }, + { + "epoch": 0.23, + "learning_rate": 9.806340222259627e-06, + "loss": 0.3241, + "step": 1816 + }, + { + "epoch": 0.23, + "learning_rate": 9.806054447354185e-06, + "loss": 0.3468, + "step": 1817 + }, + { + "epoch": 0.23, + "learning_rate": 9.805768465921878e-06, + "loss": 0.3411, + "step": 1818 + }, + { + "epoch": 0.23, + "learning_rate": 9.805482277974999e-06, + "loss": 0.3608, + "step": 1819 + }, + { + "epoch": 0.23, + "learning_rate": 9.805195883525844e-06, + "loss": 0.3487, + "step": 1820 + }, + { + "epoch": 0.23, + "learning_rate": 9.804909282586718e-06, + "loss": 0.3303, + "step": 1821 + }, + { + "epoch": 0.23, + "learning_rate": 9.804622475169943e-06, + "loss": 0.3645, + "step": 1822 + }, + { + "epoch": 0.23, + "learning_rate": 9.804335461287835e-06, + "loss": 0.3387, + "step": 1823 + }, + { + "epoch": 0.23, + "learning_rate": 9.804048240952736e-06, + "loss": 0.3717, + "step": 1824 + }, + { + "epoch": 0.23, + "learning_rate": 9.803760814176983e-06, + "loss": 0.3629, + "step": 1825 + }, + { + "epoch": 0.23, + "learning_rate": 9.80347318097293e-06, + "loss": 0.3613, + "step": 1826 + }, + { + "epoch": 0.23, + "learning_rate": 9.803185341352936e-06, + "loss": 0.3403, + "step": 1827 + }, + { + "epoch": 0.23, + "learning_rate": 9.802897295329373e-06, + "loss": 0.347, + "step": 1828 + }, + { + "epoch": 0.23, + "learning_rate": 9.802609042914614e-06, + "loss": 0.358, + "step": 1829 + }, + { + "epoch": 0.23, + "learning_rate": 9.80232058412105e-06, + "loss": 0.3588, + "step": 1830 + }, + { + "epoch": 0.23, + "learning_rate": 9.802031918961073e-06, + "loss": 0.3601, + "step": 1831 + }, + { + "epoch": 0.23, + "learning_rate": 9.801743047447092e-06, + "loss": 0.3739, + "step": 1832 + }, + { + "epoch": 0.23, + "learning_rate": 9.801453969591517e-06, + "loss": 0.3609, + "step": 1833 + }, + { + "epoch": 0.23, + "learning_rate": 9.80116468540677e-06, + "loss": 0.3672, + "step": 1834 + }, + { + "epoch": 0.23, + "learning_rate": 9.800875194905286e-06, + "loss": 0.3419, + "step": 1835 + }, + { + "epoch": 0.24, + "learning_rate": 9.800585498099501e-06, + "loss": 0.3429, + "step": 1836 + }, + { + "epoch": 0.24, + "learning_rate": 9.800295595001868e-06, + "loss": 0.3738, + "step": 1837 + }, + { + "epoch": 0.24, + "learning_rate": 9.800005485624842e-06, + "loss": 0.3699, + "step": 1838 + }, + { + "epoch": 0.24, + "learning_rate": 9.79971516998089e-06, + "loss": 0.3713, + "step": 1839 + }, + { + "epoch": 0.24, + "learning_rate": 9.799424648082486e-06, + "loss": 0.3522, + "step": 1840 + }, + { + "epoch": 0.24, + "learning_rate": 9.799133919942117e-06, + "loss": 0.3353, + "step": 1841 + }, + { + "epoch": 0.24, + "learning_rate": 9.798842985572274e-06, + "loss": 0.3792, + "step": 1842 + }, + { + "epoch": 0.24, + "learning_rate": 9.798551844985463e-06, + "loss": 0.3366, + "step": 1843 + }, + { + "epoch": 0.24, + "learning_rate": 9.79826049819419e-06, + "loss": 0.355, + "step": 1844 + }, + { + "epoch": 0.24, + "learning_rate": 9.797968945210978e-06, + "loss": 0.3492, + "step": 1845 + }, + { + "epoch": 0.24, + "learning_rate": 9.797677186048356e-06, + "loss": 0.367, + "step": 1846 + }, + { + "epoch": 0.24, + "learning_rate": 9.797385220718859e-06, + "loss": 0.3542, + "step": 1847 + }, + { + "epoch": 0.24, + "learning_rate": 9.797093049235034e-06, + "loss": 0.3717, + "step": 1848 + }, + { + "epoch": 0.24, + "learning_rate": 9.796800671609436e-06, + "loss": 0.372, + "step": 1849 + }, + { + "epoch": 0.24, + "learning_rate": 9.796508087854632e-06, + "loss": 0.3273, + "step": 1850 + }, + { + "epoch": 0.24, + "learning_rate": 9.796215297983193e-06, + "loss": 0.386, + "step": 1851 + }, + { + "epoch": 0.24, + "learning_rate": 9.7959223020077e-06, + "loss": 0.3485, + "step": 1852 + }, + { + "epoch": 0.24, + "learning_rate": 9.795629099940746e-06, + "loss": 0.3635, + "step": 1853 + }, + { + "epoch": 0.24, + "learning_rate": 9.795335691794929e-06, + "loss": 0.3364, + "step": 1854 + }, + { + "epoch": 0.24, + "learning_rate": 9.795042077582856e-06, + "loss": 0.3503, + "step": 1855 + }, + { + "epoch": 0.24, + "learning_rate": 9.794748257317148e-06, + "loss": 0.3566, + "step": 1856 + }, + { + "epoch": 0.24, + "learning_rate": 9.794454231010427e-06, + "loss": 0.3653, + "step": 1857 + }, + { + "epoch": 0.24, + "learning_rate": 9.794159998675331e-06, + "loss": 0.3613, + "step": 1858 + }, + { + "epoch": 0.24, + "learning_rate": 9.793865560324503e-06, + "loss": 0.3516, + "step": 1859 + }, + { + "epoch": 0.24, + "learning_rate": 9.793570915970594e-06, + "loss": 0.3338, + "step": 1860 + }, + { + "epoch": 0.24, + "learning_rate": 9.793276065626267e-06, + "loss": 0.3688, + "step": 1861 + }, + { + "epoch": 0.24, + "learning_rate": 9.792981009304192e-06, + "loss": 0.3744, + "step": 1862 + }, + { + "epoch": 0.24, + "learning_rate": 9.79268574701705e-06, + "loss": 0.3449, + "step": 1863 + }, + { + "epoch": 0.24, + "learning_rate": 9.792390278777527e-06, + "loss": 0.3493, + "step": 1864 + }, + { + "epoch": 0.24, + "learning_rate": 9.79209460459832e-06, + "loss": 0.3654, + "step": 1865 + }, + { + "epoch": 0.24, + "learning_rate": 9.791798724492136e-06, + "loss": 0.3599, + "step": 1866 + }, + { + "epoch": 0.24, + "learning_rate": 9.791502638471689e-06, + "loss": 0.382, + "step": 1867 + }, + { + "epoch": 0.24, + "learning_rate": 9.7912063465497e-06, + "loss": 0.367, + "step": 1868 + }, + { + "epoch": 0.24, + "learning_rate": 9.790909848738907e-06, + "loss": 0.3299, + "step": 1869 + }, + { + "epoch": 0.24, + "learning_rate": 9.790613145052046e-06, + "loss": 0.3442, + "step": 1870 + }, + { + "epoch": 0.24, + "learning_rate": 9.790316235501869e-06, + "loss": 0.368, + "step": 1871 + }, + { + "epoch": 0.24, + "learning_rate": 9.790019120101135e-06, + "loss": 0.3496, + "step": 1872 + }, + { + "epoch": 0.24, + "learning_rate": 9.789721798862612e-06, + "loss": 0.3533, + "step": 1873 + }, + { + "epoch": 0.24, + "learning_rate": 9.789424271799075e-06, + "loss": 0.357, + "step": 1874 + }, + { + "epoch": 0.24, + "learning_rate": 9.789126538923312e-06, + "loss": 0.3613, + "step": 1875 + }, + { + "epoch": 0.24, + "learning_rate": 9.788828600248114e-06, + "loss": 0.3449, + "step": 1876 + }, + { + "epoch": 0.24, + "learning_rate": 9.788530455786288e-06, + "loss": 0.3548, + "step": 1877 + }, + { + "epoch": 0.24, + "learning_rate": 9.78823210555064e-06, + "loss": 0.3347, + "step": 1878 + }, + { + "epoch": 0.24, + "learning_rate": 9.787933549553996e-06, + "loss": 0.3667, + "step": 1879 + }, + { + "epoch": 0.24, + "learning_rate": 9.787634787809185e-06, + "loss": 0.3516, + "step": 1880 + }, + { + "epoch": 0.24, + "learning_rate": 9.787335820329045e-06, + "loss": 0.3721, + "step": 1881 + }, + { + "epoch": 0.24, + "learning_rate": 9.787036647126422e-06, + "loss": 0.347, + "step": 1882 + }, + { + "epoch": 0.24, + "learning_rate": 9.786737268214172e-06, + "loss": 0.3235, + "step": 1883 + }, + { + "epoch": 0.24, + "learning_rate": 9.786437683605161e-06, + "loss": 0.3691, + "step": 1884 + }, + { + "epoch": 0.24, + "learning_rate": 9.786137893312265e-06, + "loss": 0.346, + "step": 1885 + }, + { + "epoch": 0.24, + "learning_rate": 9.785837897348363e-06, + "loss": 0.3502, + "step": 1886 + }, + { + "epoch": 0.24, + "learning_rate": 9.785537695726348e-06, + "loss": 0.3597, + "step": 1887 + }, + { + "epoch": 0.24, + "learning_rate": 9.78523728845912e-06, + "loss": 0.3806, + "step": 1888 + }, + { + "epoch": 0.24, + "learning_rate": 9.78493667555959e-06, + "loss": 0.3715, + "step": 1889 + }, + { + "epoch": 0.24, + "learning_rate": 9.784635857040672e-06, + "loss": 0.3405, + "step": 1890 + }, + { + "epoch": 0.24, + "learning_rate": 9.784334832915297e-06, + "loss": 0.3305, + "step": 1891 + }, + { + "epoch": 0.24, + "learning_rate": 9.784033603196397e-06, + "loss": 0.3876, + "step": 1892 + }, + { + "epoch": 0.24, + "learning_rate": 9.78373216789692e-06, + "loss": 0.3612, + "step": 1893 + }, + { + "epoch": 0.24, + "learning_rate": 9.783430527029818e-06, + "loss": 0.3071, + "step": 1894 + }, + { + "epoch": 0.24, + "learning_rate": 9.783128680608052e-06, + "loss": 0.3257, + "step": 1895 + }, + { + "epoch": 0.24, + "learning_rate": 9.782826628644596e-06, + "loss": 0.3665, + "step": 1896 + }, + { + "epoch": 0.24, + "learning_rate": 9.782524371152425e-06, + "loss": 0.3617, + "step": 1897 + }, + { + "epoch": 0.24, + "learning_rate": 9.782221908144531e-06, + "loss": 0.3631, + "step": 1898 + }, + { + "epoch": 0.24, + "learning_rate": 9.781919239633912e-06, + "loss": 0.3474, + "step": 1899 + }, + { + "epoch": 0.24, + "learning_rate": 9.781616365633574e-06, + "loss": 0.3459, + "step": 1900 + }, + { + "epoch": 0.24, + "learning_rate": 9.78131328615653e-06, + "loss": 0.3358, + "step": 1901 + }, + { + "epoch": 0.24, + "learning_rate": 9.781010001215806e-06, + "loss": 0.3836, + "step": 1902 + }, + { + "epoch": 0.24, + "learning_rate": 9.780706510824436e-06, + "loss": 0.3506, + "step": 1903 + }, + { + "epoch": 0.24, + "learning_rate": 9.780402814995458e-06, + "loss": 0.3228, + "step": 1904 + }, + { + "epoch": 0.24, + "learning_rate": 9.780098913741926e-06, + "loss": 0.3381, + "step": 1905 + }, + { + "epoch": 0.24, + "learning_rate": 9.779794807076896e-06, + "loss": 0.3591, + "step": 1906 + }, + { + "epoch": 0.24, + "learning_rate": 9.77949049501344e-06, + "loss": 0.3455, + "step": 1907 + }, + { + "epoch": 0.24, + "learning_rate": 9.779185977564633e-06, + "loss": 0.3793, + "step": 1908 + }, + { + "epoch": 0.24, + "learning_rate": 9.77888125474356e-06, + "loss": 0.3625, + "step": 1909 + }, + { + "epoch": 0.24, + "learning_rate": 9.778576326563315e-06, + "loss": 0.3356, + "step": 1910 + }, + { + "epoch": 0.24, + "learning_rate": 9.778271193037003e-06, + "loss": 0.3334, + "step": 1911 + }, + { + "epoch": 0.24, + "learning_rate": 9.777965854177737e-06, + "loss": 0.3301, + "step": 1912 + }, + { + "epoch": 0.24, + "learning_rate": 9.777660309998638e-06, + "loss": 0.34, + "step": 1913 + }, + { + "epoch": 0.24, + "learning_rate": 9.777354560512835e-06, + "loss": 0.3649, + "step": 1914 + }, + { + "epoch": 0.25, + "learning_rate": 9.777048605733465e-06, + "loss": 0.3454, + "step": 1915 + }, + { + "epoch": 0.25, + "learning_rate": 9.776742445673679e-06, + "loss": 0.341, + "step": 1916 + }, + { + "epoch": 0.25, + "learning_rate": 9.77643608034663e-06, + "loss": 0.3461, + "step": 1917 + }, + { + "epoch": 0.25, + "learning_rate": 9.776129509765487e-06, + "loss": 0.3325, + "step": 1918 + }, + { + "epoch": 0.25, + "learning_rate": 9.77582273394342e-06, + "loss": 0.3698, + "step": 1919 + }, + { + "epoch": 0.25, + "learning_rate": 9.775515752893613e-06, + "loss": 0.3434, + "step": 1920 + }, + { + "epoch": 0.25, + "learning_rate": 9.775208566629262e-06, + "loss": 0.3454, + "step": 1921 + }, + { + "epoch": 0.25, + "learning_rate": 9.774901175163562e-06, + "loss": 0.3394, + "step": 1922 + }, + { + "epoch": 0.25, + "learning_rate": 9.774593578509724e-06, + "loss": 0.3335, + "step": 1923 + }, + { + "epoch": 0.25, + "learning_rate": 9.774285776680967e-06, + "loss": 0.3254, + "step": 1924 + }, + { + "epoch": 0.25, + "learning_rate": 9.773977769690517e-06, + "loss": 0.3554, + "step": 1925 + }, + { + "epoch": 0.25, + "learning_rate": 9.773669557551609e-06, + "loss": 0.3414, + "step": 1926 + }, + { + "epoch": 0.25, + "learning_rate": 9.77336114027749e-06, + "loss": 0.3458, + "step": 1927 + }, + { + "epoch": 0.25, + "learning_rate": 9.773052517881412e-06, + "loss": 0.3194, + "step": 1928 + }, + { + "epoch": 0.25, + "learning_rate": 9.772743690376636e-06, + "loss": 0.3328, + "step": 1929 + }, + { + "epoch": 0.25, + "learning_rate": 9.772434657776435e-06, + "loss": 0.3358, + "step": 1930 + }, + { + "epoch": 0.25, + "learning_rate": 9.772125420094087e-06, + "loss": 0.3408, + "step": 1931 + }, + { + "epoch": 0.25, + "learning_rate": 9.771815977342882e-06, + "loss": 0.3464, + "step": 1932 + }, + { + "epoch": 0.25, + "learning_rate": 9.771506329536118e-06, + "loss": 0.3672, + "step": 1933 + }, + { + "epoch": 0.25, + "learning_rate": 9.7711964766871e-06, + "loss": 0.3683, + "step": 1934 + }, + { + "epoch": 0.25, + "learning_rate": 9.770886418809142e-06, + "loss": 0.3327, + "step": 1935 + }, + { + "epoch": 0.25, + "learning_rate": 9.77057615591557e-06, + "loss": 0.3407, + "step": 1936 + }, + { + "epoch": 0.25, + "learning_rate": 9.770265688019718e-06, + "loss": 0.3538, + "step": 1937 + }, + { + "epoch": 0.25, + "learning_rate": 9.769955015134923e-06, + "loss": 0.3374, + "step": 1938 + }, + { + "epoch": 0.25, + "learning_rate": 9.76964413727454e-06, + "loss": 0.3444, + "step": 1939 + }, + { + "epoch": 0.25, + "learning_rate": 9.769333054451923e-06, + "loss": 0.3425, + "step": 1940 + }, + { + "epoch": 0.25, + "learning_rate": 9.769021766680444e-06, + "loss": 0.356, + "step": 1941 + }, + { + "epoch": 0.25, + "learning_rate": 9.768710273973479e-06, + "loss": 0.3639, + "step": 1942 + }, + { + "epoch": 0.25, + "learning_rate": 9.768398576344411e-06, + "loss": 0.3556, + "step": 1943 + }, + { + "epoch": 0.25, + "learning_rate": 9.768086673806638e-06, + "loss": 0.3514, + "step": 1944 + }, + { + "epoch": 0.25, + "learning_rate": 9.767774566373563e-06, + "loss": 0.3527, + "step": 1945 + }, + { + "epoch": 0.25, + "learning_rate": 9.767462254058593e-06, + "loss": 0.3803, + "step": 1946 + }, + { + "epoch": 0.25, + "learning_rate": 9.767149736875156e-06, + "loss": 0.3747, + "step": 1947 + }, + { + "epoch": 0.25, + "learning_rate": 9.766837014836675e-06, + "loss": 0.35, + "step": 1948 + }, + { + "epoch": 0.25, + "learning_rate": 9.766524087956592e-06, + "loss": 0.3435, + "step": 1949 + }, + { + "epoch": 0.25, + "learning_rate": 9.766210956248354e-06, + "loss": 0.3489, + "step": 1950 + }, + { + "epoch": 0.25, + "learning_rate": 9.765897619725416e-06, + "loss": 0.3355, + "step": 1951 + }, + { + "epoch": 0.25, + "learning_rate": 9.765584078401242e-06, + "loss": 0.3673, + "step": 1952 + }, + { + "epoch": 0.25, + "learning_rate": 9.765270332289307e-06, + "loss": 0.3816, + "step": 1953 + }, + { + "epoch": 0.25, + "learning_rate": 9.764956381403095e-06, + "loss": 0.3356, + "step": 1954 + }, + { + "epoch": 0.25, + "learning_rate": 9.764642225756093e-06, + "loss": 0.3655, + "step": 1955 + }, + { + "epoch": 0.25, + "learning_rate": 9.764327865361805e-06, + "loss": 0.3391, + "step": 1956 + }, + { + "epoch": 0.25, + "learning_rate": 9.764013300233736e-06, + "loss": 0.3382, + "step": 1957 + }, + { + "epoch": 0.25, + "learning_rate": 9.763698530385407e-06, + "loss": 0.3166, + "step": 1958 + }, + { + "epoch": 0.25, + "learning_rate": 9.76338355583034e-06, + "loss": 0.3383, + "step": 1959 + }, + { + "epoch": 0.25, + "learning_rate": 9.763068376582075e-06, + "loss": 0.3257, + "step": 1960 + }, + { + "epoch": 0.25, + "learning_rate": 9.762752992654155e-06, + "loss": 0.344, + "step": 1961 + }, + { + "epoch": 0.25, + "learning_rate": 9.76243740406013e-06, + "loss": 0.3516, + "step": 1962 + }, + { + "epoch": 0.25, + "learning_rate": 9.762121610813564e-06, + "loss": 0.359, + "step": 1963 + }, + { + "epoch": 0.25, + "learning_rate": 9.761805612928025e-06, + "loss": 0.3529, + "step": 1964 + }, + { + "epoch": 0.25, + "learning_rate": 9.761489410417095e-06, + "loss": 0.375, + "step": 1965 + }, + { + "epoch": 0.25, + "learning_rate": 9.761173003294362e-06, + "loss": 0.3377, + "step": 1966 + }, + { + "epoch": 0.25, + "learning_rate": 9.76085639157342e-06, + "loss": 0.3261, + "step": 1967 + }, + { + "epoch": 0.25, + "learning_rate": 9.760539575267875e-06, + "loss": 0.3174, + "step": 1968 + }, + { + "epoch": 0.25, + "learning_rate": 9.760222554391343e-06, + "loss": 0.3767, + "step": 1969 + }, + { + "epoch": 0.25, + "learning_rate": 9.759905328957446e-06, + "loss": 0.3657, + "step": 1970 + }, + { + "epoch": 0.25, + "learning_rate": 9.759587898979816e-06, + "loss": 0.3205, + "step": 1971 + }, + { + "epoch": 0.25, + "learning_rate": 9.759270264472097e-06, + "loss": 0.3183, + "step": 1972 + }, + { + "epoch": 0.25, + "learning_rate": 9.75895242544793e-06, + "loss": 0.3571, + "step": 1973 + }, + { + "epoch": 0.25, + "learning_rate": 9.758634381920982e-06, + "loss": 0.316, + "step": 1974 + }, + { + "epoch": 0.25, + "learning_rate": 9.758316133904914e-06, + "loss": 0.3405, + "step": 1975 + }, + { + "epoch": 0.25, + "learning_rate": 9.757997681413407e-06, + "loss": 0.3502, + "step": 1976 + }, + { + "epoch": 0.25, + "learning_rate": 9.757679024460142e-06, + "loss": 0.3515, + "step": 1977 + }, + { + "epoch": 0.25, + "learning_rate": 9.757360163058814e-06, + "loss": 0.3395, + "step": 1978 + }, + { + "epoch": 0.25, + "learning_rate": 9.757041097223123e-06, + "loss": 0.3593, + "step": 1979 + }, + { + "epoch": 0.25, + "learning_rate": 9.756721826966783e-06, + "loss": 0.3381, + "step": 1980 + }, + { + "epoch": 0.25, + "learning_rate": 9.756402352303513e-06, + "loss": 0.3348, + "step": 1981 + }, + { + "epoch": 0.25, + "learning_rate": 9.756082673247039e-06, + "loss": 0.3479, + "step": 1982 + }, + { + "epoch": 0.25, + "learning_rate": 9.755762789811101e-06, + "loss": 0.3575, + "step": 1983 + }, + { + "epoch": 0.25, + "learning_rate": 9.755442702009443e-06, + "loss": 0.3387, + "step": 1984 + }, + { + "epoch": 0.25, + "learning_rate": 9.755122409855822e-06, + "loss": 0.3505, + "step": 1985 + }, + { + "epoch": 0.25, + "learning_rate": 9.754801913364002e-06, + "loss": 0.3581, + "step": 1986 + }, + { + "epoch": 0.25, + "learning_rate": 9.754481212547752e-06, + "loss": 0.3202, + "step": 1987 + }, + { + "epoch": 0.25, + "learning_rate": 9.754160307420858e-06, + "loss": 0.3599, + "step": 1988 + }, + { + "epoch": 0.25, + "learning_rate": 9.753839197997105e-06, + "loss": 0.3066, + "step": 1989 + }, + { + "epoch": 0.25, + "learning_rate": 9.753517884290298e-06, + "loss": 0.335, + "step": 1990 + }, + { + "epoch": 0.25, + "learning_rate": 9.753196366314237e-06, + "loss": 0.3273, + "step": 1991 + }, + { + "epoch": 0.25, + "learning_rate": 9.752874644082743e-06, + "loss": 0.3511, + "step": 1992 + }, + { + "epoch": 0.26, + "learning_rate": 9.752552717609643e-06, + "loss": 0.3924, + "step": 1993 + }, + { + "epoch": 0.26, + "learning_rate": 9.752230586908767e-06, + "loss": 0.3053, + "step": 1994 + }, + { + "epoch": 0.26, + "learning_rate": 9.751908251993956e-06, + "loss": 0.3645, + "step": 1995 + }, + { + "epoch": 0.26, + "learning_rate": 9.751585712879067e-06, + "loss": 0.3588, + "step": 1996 + }, + { + "epoch": 0.26, + "learning_rate": 9.751262969577958e-06, + "loss": 0.382, + "step": 1997 + }, + { + "epoch": 0.26, + "learning_rate": 9.750940022104497e-06, + "loss": 0.3382, + "step": 1998 + }, + { + "epoch": 0.26, + "learning_rate": 9.75061687047256e-06, + "loss": 0.3503, + "step": 1999 + }, + { + "epoch": 0.26, + "learning_rate": 9.750293514696038e-06, + "loss": 0.3448, + "step": 2000 + }, + { + "epoch": 0.26, + "learning_rate": 9.749969954788825e-06, + "loss": 0.3298, + "step": 2001 + }, + { + "epoch": 0.26, + "learning_rate": 9.749646190764823e-06, + "loss": 0.3657, + "step": 2002 + }, + { + "epoch": 0.26, + "learning_rate": 9.749322222637947e-06, + "loss": 0.3852, + "step": 2003 + }, + { + "epoch": 0.26, + "learning_rate": 9.748998050422117e-06, + "loss": 0.3657, + "step": 2004 + }, + { + "epoch": 0.26, + "learning_rate": 9.748673674131264e-06, + "loss": 0.3473, + "step": 2005 + }, + { + "epoch": 0.26, + "learning_rate": 9.748349093779327e-06, + "loss": 0.363, + "step": 2006 + }, + { + "epoch": 0.26, + "learning_rate": 9.748024309380256e-06, + "loss": 0.3586, + "step": 2007 + }, + { + "epoch": 0.26, + "learning_rate": 9.747699320948006e-06, + "loss": 0.3344, + "step": 2008 + }, + { + "epoch": 0.26, + "learning_rate": 9.747374128496541e-06, + "loss": 0.3494, + "step": 2009 + }, + { + "epoch": 0.26, + "learning_rate": 9.747048732039837e-06, + "loss": 0.3498, + "step": 2010 + }, + { + "epoch": 0.26, + "learning_rate": 9.746723131591878e-06, + "loss": 0.3197, + "step": 2011 + }, + { + "epoch": 0.26, + "learning_rate": 9.746397327166653e-06, + "loss": 0.3666, + "step": 2012 + }, + { + "epoch": 0.26, + "learning_rate": 9.746071318778165e-06, + "loss": 0.3365, + "step": 2013 + }, + { + "epoch": 0.26, + "learning_rate": 9.745745106440422e-06, + "loss": 0.3246, + "step": 2014 + }, + { + "epoch": 0.26, + "learning_rate": 9.745418690167444e-06, + "loss": 0.3502, + "step": 2015 + }, + { + "epoch": 0.26, + "learning_rate": 9.745092069973254e-06, + "loss": 0.3459, + "step": 2016 + }, + { + "epoch": 0.26, + "learning_rate": 9.74476524587189e-06, + "loss": 0.3586, + "step": 2017 + }, + { + "epoch": 0.26, + "learning_rate": 9.744438217877396e-06, + "loss": 0.3719, + "step": 2018 + }, + { + "epoch": 0.26, + "learning_rate": 9.744110986003826e-06, + "loss": 0.3654, + "step": 2019 + }, + { + "epoch": 0.26, + "learning_rate": 9.743783550265242e-06, + "loss": 0.3473, + "step": 2020 + }, + { + "epoch": 0.26, + "learning_rate": 9.743455910675712e-06, + "loss": 0.3528, + "step": 2021 + }, + { + "epoch": 0.26, + "learning_rate": 9.74312806724932e-06, + "loss": 0.3511, + "step": 2022 + }, + { + "epoch": 0.26, + "learning_rate": 9.74280002000015e-06, + "loss": 0.3408, + "step": 2023 + }, + { + "epoch": 0.26, + "learning_rate": 9.742471768942299e-06, + "loss": 0.3574, + "step": 2024 + }, + { + "epoch": 0.26, + "learning_rate": 9.742143314089877e-06, + "loss": 0.3802, + "step": 2025 + }, + { + "epoch": 0.26, + "learning_rate": 9.741814655456994e-06, + "loss": 0.3373, + "step": 2026 + }, + { + "epoch": 0.26, + "learning_rate": 9.741485793057774e-06, + "loss": 0.3836, + "step": 2027 + }, + { + "epoch": 0.26, + "learning_rate": 9.74115672690635e-06, + "loss": 0.3268, + "step": 2028 + }, + { + "epoch": 0.26, + "learning_rate": 9.740827457016863e-06, + "loss": 0.3482, + "step": 2029 + }, + { + "epoch": 0.26, + "learning_rate": 9.74049798340346e-06, + "loss": 0.3679, + "step": 2030 + }, + { + "epoch": 0.26, + "learning_rate": 9.740168306080303e-06, + "loss": 0.374, + "step": 2031 + }, + { + "epoch": 0.26, + "learning_rate": 9.739838425061557e-06, + "loss": 0.3637, + "step": 2032 + }, + { + "epoch": 0.26, + "learning_rate": 9.739508340361397e-06, + "loss": 0.3403, + "step": 2033 + }, + { + "epoch": 0.26, + "learning_rate": 9.739178051994008e-06, + "loss": 0.3635, + "step": 2034 + }, + { + "epoch": 0.26, + "learning_rate": 9.738847559973584e-06, + "loss": 0.363, + "step": 2035 + }, + { + "epoch": 0.26, + "learning_rate": 9.738516864314324e-06, + "loss": 0.3443, + "step": 2036 + }, + { + "epoch": 0.26, + "learning_rate": 9.738185965030444e-06, + "loss": 0.3539, + "step": 2037 + }, + { + "epoch": 0.26, + "learning_rate": 9.73785486213616e-06, + "loss": 0.348, + "step": 2038 + }, + { + "epoch": 0.26, + "learning_rate": 9.7375235556457e-06, + "loss": 0.3437, + "step": 2039 + }, + { + "epoch": 0.26, + "learning_rate": 9.7371920455733e-06, + "loss": 0.3524, + "step": 2040 + }, + { + "epoch": 0.26, + "learning_rate": 9.736860331933212e-06, + "loss": 0.3499, + "step": 2041 + }, + { + "epoch": 0.26, + "learning_rate": 9.736528414739681e-06, + "loss": 0.3448, + "step": 2042 + }, + { + "epoch": 0.26, + "learning_rate": 9.736196294006978e-06, + "loss": 0.3546, + "step": 2043 + }, + { + "epoch": 0.26, + "learning_rate": 9.735863969749373e-06, + "loss": 0.346, + "step": 2044 + }, + { + "epoch": 0.26, + "learning_rate": 9.735531441981145e-06, + "loss": 0.3358, + "step": 2045 + }, + { + "epoch": 0.26, + "learning_rate": 9.735198710716585e-06, + "loss": 0.35, + "step": 2046 + }, + { + "epoch": 0.26, + "learning_rate": 9.734865775969988e-06, + "loss": 0.3379, + "step": 2047 + }, + { + "epoch": 0.26, + "learning_rate": 9.734532637755665e-06, + "loss": 0.355, + "step": 2048 + }, + { + "epoch": 0.26, + "learning_rate": 9.734199296087932e-06, + "loss": 0.3427, + "step": 2049 + }, + { + "epoch": 0.26, + "learning_rate": 9.73386575098111e-06, + "loss": 0.3328, + "step": 2050 + }, + { + "epoch": 0.26, + "learning_rate": 9.733532002449533e-06, + "loss": 0.3663, + "step": 2051 + }, + { + "epoch": 0.26, + "learning_rate": 9.733198050507544e-06, + "loss": 0.3771, + "step": 2052 + }, + { + "epoch": 0.26, + "learning_rate": 9.732863895169496e-06, + "loss": 0.3569, + "step": 2053 + }, + { + "epoch": 0.26, + "learning_rate": 9.732529536449741e-06, + "loss": 0.3911, + "step": 2054 + }, + { + "epoch": 0.26, + "learning_rate": 9.732194974362657e-06, + "loss": 0.3499, + "step": 2055 + }, + { + "epoch": 0.26, + "learning_rate": 9.731860208922612e-06, + "loss": 0.3466, + "step": 2056 + }, + { + "epoch": 0.26, + "learning_rate": 9.731525240143998e-06, + "loss": 0.3231, + "step": 2057 + }, + { + "epoch": 0.26, + "learning_rate": 9.731190068041205e-06, + "loss": 0.3449, + "step": 2058 + }, + { + "epoch": 0.26, + "learning_rate": 9.730854692628637e-06, + "loss": 0.3303, + "step": 2059 + }, + { + "epoch": 0.26, + "learning_rate": 9.730519113920708e-06, + "loss": 0.3628, + "step": 2060 + }, + { + "epoch": 0.26, + "learning_rate": 9.730183331931838e-06, + "loss": 0.3514, + "step": 2061 + }, + { + "epoch": 0.26, + "learning_rate": 9.729847346676455e-06, + "loss": 0.3498, + "step": 2062 + }, + { + "epoch": 0.26, + "learning_rate": 9.729511158168999e-06, + "loss": 0.3457, + "step": 2063 + }, + { + "epoch": 0.26, + "learning_rate": 9.729174766423912e-06, + "loss": 0.331, + "step": 2064 + }, + { + "epoch": 0.26, + "learning_rate": 9.728838171455655e-06, + "loss": 0.3595, + "step": 2065 + }, + { + "epoch": 0.26, + "learning_rate": 9.72850137327869e-06, + "loss": 0.3149, + "step": 2066 + }, + { + "epoch": 0.26, + "learning_rate": 9.728164371907489e-06, + "loss": 0.3411, + "step": 2067 + }, + { + "epoch": 0.26, + "learning_rate": 9.727827167356537e-06, + "loss": 0.3553, + "step": 2068 + }, + { + "epoch": 0.26, + "learning_rate": 9.72748975964032e-06, + "loss": 0.3533, + "step": 2069 + }, + { + "epoch": 0.26, + "learning_rate": 9.72715214877334e-06, + "loss": 0.3776, + "step": 2070 + }, + { + "epoch": 0.27, + "learning_rate": 9.726814334770106e-06, + "loss": 0.3762, + "step": 2071 + }, + { + "epoch": 0.27, + "learning_rate": 9.72647631764513e-06, + "loss": 0.3881, + "step": 2072 + }, + { + "epoch": 0.27, + "learning_rate": 9.72613809741294e-06, + "loss": 0.3794, + "step": 2073 + }, + { + "epoch": 0.27, + "learning_rate": 9.725799674088072e-06, + "loss": 0.3854, + "step": 2074 + }, + { + "epoch": 0.27, + "learning_rate": 9.725461047685067e-06, + "loss": 0.3384, + "step": 2075 + }, + { + "epoch": 0.27, + "learning_rate": 9.725122218218477e-06, + "loss": 0.3331, + "step": 2076 + }, + { + "epoch": 0.27, + "learning_rate": 9.72478318570286e-06, + "loss": 0.3179, + "step": 2077 + }, + { + "epoch": 0.27, + "learning_rate": 9.724443950152789e-06, + "loss": 0.3459, + "step": 2078 + }, + { + "epoch": 0.27, + "learning_rate": 9.724104511582838e-06, + "loss": 0.3082, + "step": 2079 + }, + { + "epoch": 0.27, + "learning_rate": 9.723764870007596e-06, + "loss": 0.3347, + "step": 2080 + }, + { + "epoch": 0.27, + "learning_rate": 9.723425025441657e-06, + "loss": 0.3522, + "step": 2081 + }, + { + "epoch": 0.27, + "learning_rate": 9.723084977899624e-06, + "loss": 0.3652, + "step": 2082 + }, + { + "epoch": 0.27, + "learning_rate": 9.722744727396111e-06, + "loss": 0.359, + "step": 2083 + }, + { + "epoch": 0.27, + "learning_rate": 9.72240427394574e-06, + "loss": 0.3419, + "step": 2084 + }, + { + "epoch": 0.27, + "learning_rate": 9.72206361756314e-06, + "loss": 0.3439, + "step": 2085 + }, + { + "epoch": 0.27, + "learning_rate": 9.721722758262948e-06, + "loss": 0.3267, + "step": 2086 + }, + { + "epoch": 0.27, + "learning_rate": 9.721381696059815e-06, + "loss": 0.365, + "step": 2087 + }, + { + "epoch": 0.27, + "learning_rate": 9.721040430968393e-06, + "loss": 0.3551, + "step": 2088 + }, + { + "epoch": 0.27, + "learning_rate": 9.720698963003351e-06, + "loss": 0.3395, + "step": 2089 + }, + { + "epoch": 0.27, + "learning_rate": 9.720357292179363e-06, + "loss": 0.3654, + "step": 2090 + }, + { + "epoch": 0.27, + "learning_rate": 9.720015418511108e-06, + "loss": 0.3535, + "step": 2091 + }, + { + "epoch": 0.27, + "learning_rate": 9.719673342013277e-06, + "loss": 0.3047, + "step": 2092 + }, + { + "epoch": 0.27, + "learning_rate": 9.719331062700572e-06, + "loss": 0.3617, + "step": 2093 + }, + { + "epoch": 0.27, + "learning_rate": 9.7189885805877e-06, + "loss": 0.3369, + "step": 2094 + }, + { + "epoch": 0.27, + "learning_rate": 9.71864589568938e-06, + "loss": 0.3744, + "step": 2095 + }, + { + "epoch": 0.27, + "learning_rate": 9.718303008020338e-06, + "loss": 0.3178, + "step": 2096 + }, + { + "epoch": 0.27, + "learning_rate": 9.717959917595305e-06, + "loss": 0.3285, + "step": 2097 + }, + { + "epoch": 0.27, + "learning_rate": 9.71761662442903e-06, + "loss": 0.3467, + "step": 2098 + }, + { + "epoch": 0.27, + "learning_rate": 9.717273128536259e-06, + "loss": 0.3391, + "step": 2099 + }, + { + "epoch": 0.27, + "learning_rate": 9.716929429931757e-06, + "loss": 0.3469, + "step": 2100 + }, + { + "epoch": 0.27, + "learning_rate": 9.716585528630291e-06, + "loss": 0.3727, + "step": 2101 + }, + { + "epoch": 0.27, + "learning_rate": 9.716241424646642e-06, + "loss": 0.3308, + "step": 2102 + }, + { + "epoch": 0.27, + "learning_rate": 9.715897117995594e-06, + "loss": 0.3538, + "step": 2103 + }, + { + "epoch": 0.27, + "learning_rate": 9.715552608691944e-06, + "loss": 0.3524, + "step": 2104 + }, + { + "epoch": 0.27, + "learning_rate": 9.715207896750499e-06, + "loss": 0.3326, + "step": 2105 + }, + { + "epoch": 0.27, + "learning_rate": 9.714862982186067e-06, + "loss": 0.3473, + "step": 2106 + }, + { + "epoch": 0.27, + "learning_rate": 9.714517865013473e-06, + "loss": 0.3647, + "step": 2107 + }, + { + "epoch": 0.27, + "learning_rate": 9.714172545247544e-06, + "loss": 0.352, + "step": 2108 + }, + { + "epoch": 0.27, + "learning_rate": 9.713827022903124e-06, + "loss": 0.3412, + "step": 2109 + }, + { + "epoch": 0.27, + "learning_rate": 9.71348129799506e-06, + "loss": 0.3368, + "step": 2110 + }, + { + "epoch": 0.27, + "learning_rate": 9.713135370538204e-06, + "loss": 0.355, + "step": 2111 + }, + { + "epoch": 0.27, + "learning_rate": 9.712789240547426e-06, + "loss": 0.3244, + "step": 2112 + }, + { + "epoch": 0.27, + "learning_rate": 9.712442908037599e-06, + "loss": 0.3286, + "step": 2113 + }, + { + "epoch": 0.27, + "learning_rate": 9.712096373023603e-06, + "loss": 0.3381, + "step": 2114 + }, + { + "epoch": 0.27, + "learning_rate": 9.711749635520333e-06, + "loss": 0.3781, + "step": 2115 + }, + { + "epoch": 0.27, + "learning_rate": 9.711402695542689e-06, + "loss": 0.3141, + "step": 2116 + }, + { + "epoch": 0.27, + "learning_rate": 9.711055553105575e-06, + "loss": 0.3294, + "step": 2117 + }, + { + "epoch": 0.27, + "learning_rate": 9.710708208223914e-06, + "loss": 0.3425, + "step": 2118 + }, + { + "epoch": 0.27, + "learning_rate": 9.710360660912629e-06, + "loss": 0.3459, + "step": 2119 + }, + { + "epoch": 0.27, + "learning_rate": 9.710012911186657e-06, + "loss": 0.3601, + "step": 2120 + }, + { + "epoch": 0.27, + "learning_rate": 9.70966495906094e-06, + "loss": 0.3446, + "step": 2121 + }, + { + "epoch": 0.27, + "learning_rate": 9.70931680455043e-06, + "loss": 0.3558, + "step": 2122 + }, + { + "epoch": 0.27, + "learning_rate": 9.708968447670088e-06, + "loss": 0.3504, + "step": 2123 + }, + { + "epoch": 0.27, + "learning_rate": 9.708619888434887e-06, + "loss": 0.321, + "step": 2124 + }, + { + "epoch": 0.27, + "learning_rate": 9.708271126859801e-06, + "loss": 0.3471, + "step": 2125 + }, + { + "epoch": 0.27, + "learning_rate": 9.70792216295982e-06, + "loss": 0.3453, + "step": 2126 + }, + { + "epoch": 0.27, + "learning_rate": 9.707572996749936e-06, + "loss": 0.3034, + "step": 2127 + }, + { + "epoch": 0.27, + "learning_rate": 9.707223628245157e-06, + "loss": 0.3266, + "step": 2128 + }, + { + "epoch": 0.27, + "learning_rate": 9.706874057460497e-06, + "loss": 0.3452, + "step": 2129 + }, + { + "epoch": 0.27, + "learning_rate": 9.706524284410973e-06, + "loss": 0.3614, + "step": 2130 + }, + { + "epoch": 0.27, + "learning_rate": 9.70617430911162e-06, + "loss": 0.3239, + "step": 2131 + }, + { + "epoch": 0.27, + "learning_rate": 9.705824131577476e-06, + "loss": 0.34, + "step": 2132 + }, + { + "epoch": 0.27, + "learning_rate": 9.70547375182359e-06, + "loss": 0.3658, + "step": 2133 + }, + { + "epoch": 0.27, + "learning_rate": 9.705123169865016e-06, + "loss": 0.322, + "step": 2134 + }, + { + "epoch": 0.27, + "learning_rate": 9.70477238571682e-06, + "loss": 0.3165, + "step": 2135 + }, + { + "epoch": 0.27, + "learning_rate": 9.704421399394077e-06, + "loss": 0.3601, + "step": 2136 + }, + { + "epoch": 0.27, + "learning_rate": 9.704070210911868e-06, + "loss": 0.3355, + "step": 2137 + }, + { + "epoch": 0.27, + "learning_rate": 9.703718820285288e-06, + "loss": 0.3417, + "step": 2138 + }, + { + "epoch": 0.27, + "learning_rate": 9.703367227529432e-06, + "loss": 0.3504, + "step": 2139 + }, + { + "epoch": 0.27, + "learning_rate": 9.703015432659413e-06, + "loss": 0.3408, + "step": 2140 + }, + { + "epoch": 0.27, + "learning_rate": 9.702663435690344e-06, + "loss": 0.3205, + "step": 2141 + }, + { + "epoch": 0.27, + "learning_rate": 9.702311236637357e-06, + "loss": 0.3393, + "step": 2142 + }, + { + "epoch": 0.27, + "learning_rate": 9.701958835515582e-06, + "loss": 0.3498, + "step": 2143 + }, + { + "epoch": 0.27, + "learning_rate": 9.701606232340165e-06, + "loss": 0.3573, + "step": 2144 + }, + { + "epoch": 0.27, + "learning_rate": 9.701253427126257e-06, + "loss": 0.3473, + "step": 2145 + }, + { + "epoch": 0.27, + "learning_rate": 9.700900419889018e-06, + "loss": 0.31, + "step": 2146 + }, + { + "epoch": 0.27, + "learning_rate": 9.700547210643618e-06, + "loss": 0.3347, + "step": 2147 + }, + { + "epoch": 0.27, + "learning_rate": 9.700193799405238e-06, + "loss": 0.3328, + "step": 2148 + }, + { + "epoch": 0.28, + "learning_rate": 9.699840186189061e-06, + "loss": 0.362, + "step": 2149 + }, + { + "epoch": 0.28, + "learning_rate": 9.699486371010285e-06, + "loss": 0.3456, + "step": 2150 + }, + { + "epoch": 0.28, + "learning_rate": 9.69913235388411e-06, + "loss": 0.3999, + "step": 2151 + }, + { + "epoch": 0.28, + "learning_rate": 9.698778134825755e-06, + "loss": 0.3258, + "step": 2152 + }, + { + "epoch": 0.28, + "learning_rate": 9.69842371385044e-06, + "loss": 0.3372, + "step": 2153 + }, + { + "epoch": 0.28, + "learning_rate": 9.698069090973391e-06, + "loss": 0.3584, + "step": 2154 + }, + { + "epoch": 0.28, + "learning_rate": 9.697714266209853e-06, + "loss": 0.3332, + "step": 2155 + }, + { + "epoch": 0.28, + "learning_rate": 9.697359239575069e-06, + "loss": 0.3577, + "step": 2156 + }, + { + "epoch": 0.28, + "learning_rate": 9.697004011084298e-06, + "loss": 0.3325, + "step": 2157 + }, + { + "epoch": 0.28, + "learning_rate": 9.696648580752803e-06, + "loss": 0.3579, + "step": 2158 + }, + { + "epoch": 0.28, + "learning_rate": 9.696292948595857e-06, + "loss": 0.3421, + "step": 2159 + }, + { + "epoch": 0.28, + "learning_rate": 9.695937114628746e-06, + "loss": 0.3781, + "step": 2160 + }, + { + "epoch": 0.28, + "learning_rate": 9.695581078866759e-06, + "loss": 0.3442, + "step": 2161 + }, + { + "epoch": 0.28, + "learning_rate": 9.695224841325194e-06, + "loss": 0.35, + "step": 2162 + }, + { + "epoch": 0.28, + "learning_rate": 9.694868402019362e-06, + "loss": 0.3303, + "step": 2163 + }, + { + "epoch": 0.28, + "learning_rate": 9.694511760964578e-06, + "loss": 0.3485, + "step": 2164 + }, + { + "epoch": 0.28, + "learning_rate": 9.694154918176168e-06, + "loss": 0.3627, + "step": 2165 + }, + { + "epoch": 0.28, + "learning_rate": 9.693797873669466e-06, + "loss": 0.3404, + "step": 2166 + }, + { + "epoch": 0.28, + "learning_rate": 9.693440627459817e-06, + "loss": 0.3292, + "step": 2167 + }, + { + "epoch": 0.28, + "learning_rate": 9.693083179562573e-06, + "loss": 0.3496, + "step": 2168 + }, + { + "epoch": 0.28, + "learning_rate": 9.69272552999309e-06, + "loss": 0.3469, + "step": 2169 + }, + { + "epoch": 0.28, + "learning_rate": 9.69236767876674e-06, + "loss": 0.3292, + "step": 2170 + }, + { + "epoch": 0.28, + "learning_rate": 9.692009625898902e-06, + "loss": 0.3549, + "step": 2171 + }, + { + "epoch": 0.28, + "learning_rate": 9.69165137140496e-06, + "loss": 0.3534, + "step": 2172 + }, + { + "epoch": 0.28, + "learning_rate": 9.69129291530031e-06, + "loss": 0.3272, + "step": 2173 + }, + { + "epoch": 0.28, + "learning_rate": 9.690934257600353e-06, + "loss": 0.3279, + "step": 2174 + }, + { + "epoch": 0.28, + "learning_rate": 9.690575398320504e-06, + "loss": 0.3483, + "step": 2175 + }, + { + "epoch": 0.28, + "learning_rate": 9.690216337476188e-06, + "loss": 0.3709, + "step": 2176 + }, + { + "epoch": 0.28, + "learning_rate": 9.689857075082828e-06, + "loss": 0.341, + "step": 2177 + }, + { + "epoch": 0.28, + "learning_rate": 9.689497611155862e-06, + "loss": 0.3706, + "step": 2178 + }, + { + "epoch": 0.28, + "learning_rate": 9.689137945710742e-06, + "loss": 0.3584, + "step": 2179 + }, + { + "epoch": 0.28, + "learning_rate": 9.688778078762922e-06, + "loss": 0.349, + "step": 2180 + }, + { + "epoch": 0.28, + "learning_rate": 9.688418010327862e-06, + "loss": 0.3496, + "step": 2181 + }, + { + "epoch": 0.28, + "learning_rate": 9.688057740421042e-06, + "loss": 0.352, + "step": 2182 + }, + { + "epoch": 0.28, + "learning_rate": 9.68769726905794e-06, + "loss": 0.3473, + "step": 2183 + }, + { + "epoch": 0.28, + "learning_rate": 9.687336596254045e-06, + "loss": 0.3422, + "step": 2184 + }, + { + "epoch": 0.28, + "learning_rate": 9.686975722024856e-06, + "loss": 0.3591, + "step": 2185 + }, + { + "epoch": 0.28, + "learning_rate": 9.686614646385883e-06, + "loss": 0.3618, + "step": 2186 + }, + { + "epoch": 0.28, + "learning_rate": 9.68625336935264e-06, + "loss": 0.3396, + "step": 2187 + }, + { + "epoch": 0.28, + "learning_rate": 9.685891890940655e-06, + "loss": 0.3387, + "step": 2188 + }, + { + "epoch": 0.28, + "learning_rate": 9.685530211165459e-06, + "loss": 0.3497, + "step": 2189 + }, + { + "epoch": 0.28, + "learning_rate": 9.685168330042594e-06, + "loss": 0.34, + "step": 2190 + }, + { + "epoch": 0.28, + "learning_rate": 9.68480624758761e-06, + "loss": 0.3729, + "step": 2191 + }, + { + "epoch": 0.28, + "learning_rate": 9.68444396381607e-06, + "loss": 0.3538, + "step": 2192 + }, + { + "epoch": 0.28, + "learning_rate": 9.68408147874354e-06, + "loss": 0.3758, + "step": 2193 + }, + { + "epoch": 0.28, + "learning_rate": 9.683718792385595e-06, + "loss": 0.3403, + "step": 2194 + }, + { + "epoch": 0.28, + "learning_rate": 9.683355904757822e-06, + "loss": 0.3668, + "step": 2195 + }, + { + "epoch": 0.28, + "learning_rate": 9.682992815875818e-06, + "loss": 0.3316, + "step": 2196 + }, + { + "epoch": 0.28, + "learning_rate": 9.682629525755182e-06, + "loss": 0.3469, + "step": 2197 + }, + { + "epoch": 0.28, + "learning_rate": 9.682266034411527e-06, + "loss": 0.3253, + "step": 2198 + }, + { + "epoch": 0.28, + "learning_rate": 9.681902341860471e-06, + "loss": 0.3315, + "step": 2199 + }, + { + "epoch": 0.28, + "learning_rate": 9.681538448117647e-06, + "loss": 0.3573, + "step": 2200 + }, + { + "epoch": 0.28, + "learning_rate": 9.681174353198687e-06, + "loss": 0.3311, + "step": 2201 + }, + { + "epoch": 0.28, + "learning_rate": 9.68081005711924e-06, + "loss": 0.3574, + "step": 2202 + }, + { + "epoch": 0.28, + "learning_rate": 9.68044555989496e-06, + "loss": 0.3345, + "step": 2203 + }, + { + "epoch": 0.28, + "learning_rate": 9.680080861541511e-06, + "loss": 0.3663, + "step": 2204 + }, + { + "epoch": 0.28, + "learning_rate": 9.679715962074566e-06, + "loss": 0.3293, + "step": 2205 + }, + { + "epoch": 0.28, + "learning_rate": 9.6793508615098e-06, + "loss": 0.3436, + "step": 2206 + }, + { + "epoch": 0.28, + "learning_rate": 9.678985559862909e-06, + "loss": 0.3691, + "step": 2207 + }, + { + "epoch": 0.28, + "learning_rate": 9.678620057149586e-06, + "loss": 0.3483, + "step": 2208 + }, + { + "epoch": 0.28, + "learning_rate": 9.678254353385538e-06, + "loss": 0.3286, + "step": 2209 + }, + { + "epoch": 0.28, + "learning_rate": 9.677888448586485e-06, + "loss": 0.353, + "step": 2210 + }, + { + "epoch": 0.28, + "learning_rate": 9.677522342768145e-06, + "loss": 0.3482, + "step": 2211 + }, + { + "epoch": 0.28, + "learning_rate": 9.677156035946253e-06, + "loss": 0.3658, + "step": 2212 + }, + { + "epoch": 0.28, + "learning_rate": 9.67678952813655e-06, + "loss": 0.3565, + "step": 2213 + }, + { + "epoch": 0.28, + "learning_rate": 9.676422819354785e-06, + "loss": 0.3442, + "step": 2214 + }, + { + "epoch": 0.28, + "learning_rate": 9.676055909616716e-06, + "loss": 0.3191, + "step": 2215 + }, + { + "epoch": 0.28, + "learning_rate": 9.675688798938112e-06, + "loss": 0.3156, + "step": 2216 + }, + { + "epoch": 0.28, + "learning_rate": 9.675321487334744e-06, + "loss": 0.3722, + "step": 2217 + }, + { + "epoch": 0.28, + "learning_rate": 9.674953974822402e-06, + "loss": 0.3219, + "step": 2218 + }, + { + "epoch": 0.28, + "learning_rate": 9.674586261416874e-06, + "loss": 0.3416, + "step": 2219 + }, + { + "epoch": 0.28, + "learning_rate": 9.674218347133965e-06, + "loss": 0.329, + "step": 2220 + }, + { + "epoch": 0.28, + "learning_rate": 9.673850231989484e-06, + "loss": 0.3698, + "step": 2221 + }, + { + "epoch": 0.28, + "learning_rate": 9.673481915999249e-06, + "loss": 0.3294, + "step": 2222 + }, + { + "epoch": 0.28, + "learning_rate": 9.673113399179085e-06, + "loss": 0.3363, + "step": 2223 + }, + { + "epoch": 0.28, + "learning_rate": 9.672744681544834e-06, + "loss": 0.3327, + "step": 2224 + }, + { + "epoch": 0.28, + "learning_rate": 9.672375763112335e-06, + "loss": 0.3532, + "step": 2225 + }, + { + "epoch": 0.28, + "learning_rate": 9.672006643897444e-06, + "loss": 0.3259, + "step": 2226 + }, + { + "epoch": 0.29, + "learning_rate": 9.671637323916023e-06, + "loss": 0.3322, + "step": 2227 + }, + { + "epoch": 0.29, + "learning_rate": 9.671267803183942e-06, + "loss": 0.3797, + "step": 2228 + }, + { + "epoch": 0.29, + "learning_rate": 9.670898081717079e-06, + "loss": 0.3443, + "step": 2229 + }, + { + "epoch": 0.29, + "learning_rate": 9.670528159531325e-06, + "loss": 0.3818, + "step": 2230 + }, + { + "epoch": 0.29, + "learning_rate": 9.670158036642572e-06, + "loss": 0.357, + "step": 2231 + }, + { + "epoch": 0.29, + "learning_rate": 9.669787713066728e-06, + "loss": 0.3653, + "step": 2232 + }, + { + "epoch": 0.29, + "learning_rate": 9.669417188819704e-06, + "loss": 0.3354, + "step": 2233 + }, + { + "epoch": 0.29, + "learning_rate": 9.669046463917427e-06, + "loss": 0.3499, + "step": 2234 + }, + { + "epoch": 0.29, + "learning_rate": 9.668675538375823e-06, + "loss": 0.3343, + "step": 2235 + }, + { + "epoch": 0.29, + "learning_rate": 9.668304412210835e-06, + "loss": 0.3672, + "step": 2236 + }, + { + "epoch": 0.29, + "learning_rate": 9.667933085438407e-06, + "loss": 0.3385, + "step": 2237 + }, + { + "epoch": 0.29, + "learning_rate": 9.6675615580745e-06, + "loss": 0.3523, + "step": 2238 + }, + { + "epoch": 0.29, + "learning_rate": 9.667189830135078e-06, + "loss": 0.3361, + "step": 2239 + }, + { + "epoch": 0.29, + "learning_rate": 9.666817901636115e-06, + "loss": 0.3573, + "step": 2240 + }, + { + "epoch": 0.29, + "learning_rate": 9.666445772593592e-06, + "loss": 0.3466, + "step": 2241 + }, + { + "epoch": 0.29, + "learning_rate": 9.666073443023502e-06, + "loss": 0.3227, + "step": 2242 + }, + { + "epoch": 0.29, + "learning_rate": 9.665700912941844e-06, + "loss": 0.3671, + "step": 2243 + }, + { + "epoch": 0.29, + "learning_rate": 9.665328182364627e-06, + "loss": 0.3184, + "step": 2244 + }, + { + "epoch": 0.29, + "learning_rate": 9.664955251307867e-06, + "loss": 0.3462, + "step": 2245 + }, + { + "epoch": 0.29, + "learning_rate": 9.66458211978759e-06, + "loss": 0.3117, + "step": 2246 + }, + { + "epoch": 0.29, + "learning_rate": 9.664208787819833e-06, + "loss": 0.3313, + "step": 2247 + }, + { + "epoch": 0.29, + "learning_rate": 9.663835255420635e-06, + "loss": 0.37, + "step": 2248 + }, + { + "epoch": 0.29, + "learning_rate": 9.663461522606049e-06, + "loss": 0.3478, + "step": 2249 + }, + { + "epoch": 0.29, + "learning_rate": 9.663087589392135e-06, + "loss": 0.3426, + "step": 2250 + }, + { + "epoch": 0.29, + "learning_rate": 9.662713455794963e-06, + "loss": 0.3559, + "step": 2251 + }, + { + "epoch": 0.29, + "learning_rate": 9.66233912183061e-06, + "loss": 0.3401, + "step": 2252 + }, + { + "epoch": 0.29, + "learning_rate": 9.66196458751516e-06, + "loss": 0.3444, + "step": 2253 + }, + { + "epoch": 0.29, + "learning_rate": 9.66158985286471e-06, + "loss": 0.3451, + "step": 2254 + }, + { + "epoch": 0.29, + "learning_rate": 9.661214917895361e-06, + "loss": 0.3522, + "step": 2255 + }, + { + "epoch": 0.29, + "learning_rate": 9.660839782623226e-06, + "loss": 0.3288, + "step": 2256 + }, + { + "epoch": 0.29, + "learning_rate": 9.660464447064427e-06, + "loss": 0.3529, + "step": 2257 + }, + { + "epoch": 0.29, + "learning_rate": 9.660088911235088e-06, + "loss": 0.3362, + "step": 2258 + }, + { + "epoch": 0.29, + "learning_rate": 9.659713175151352e-06, + "loss": 0.3547, + "step": 2259 + }, + { + "epoch": 0.29, + "learning_rate": 9.659337238829364e-06, + "loss": 0.3475, + "step": 2260 + }, + { + "epoch": 0.29, + "learning_rate": 9.658961102285276e-06, + "loss": 0.3875, + "step": 2261 + }, + { + "epoch": 0.29, + "learning_rate": 9.658584765535254e-06, + "loss": 0.3568, + "step": 2262 + }, + { + "epoch": 0.29, + "learning_rate": 9.65820822859547e-06, + "loss": 0.3168, + "step": 2263 + }, + { + "epoch": 0.29, + "learning_rate": 9.657831491482103e-06, + "loss": 0.3318, + "step": 2264 + }, + { + "epoch": 0.29, + "learning_rate": 9.657454554211344e-06, + "loss": 0.3346, + "step": 2265 + }, + { + "epoch": 0.29, + "learning_rate": 9.657077416799392e-06, + "loss": 0.3621, + "step": 2266 + }, + { + "epoch": 0.29, + "learning_rate": 9.656700079262448e-06, + "loss": 0.3656, + "step": 2267 + }, + { + "epoch": 0.29, + "learning_rate": 9.656322541616734e-06, + "loss": 0.3555, + "step": 2268 + }, + { + "epoch": 0.29, + "learning_rate": 9.655944803878467e-06, + "loss": 0.3239, + "step": 2269 + }, + { + "epoch": 0.29, + "learning_rate": 9.655566866063885e-06, + "loss": 0.3303, + "step": 2270 + }, + { + "epoch": 0.29, + "learning_rate": 9.655188728189225e-06, + "loss": 0.3577, + "step": 2271 + }, + { + "epoch": 0.29, + "learning_rate": 9.654810390270737e-06, + "loss": 0.354, + "step": 2272 + }, + { + "epoch": 0.29, + "learning_rate": 9.654431852324682e-06, + "loss": 0.3562, + "step": 2273 + }, + { + "epoch": 0.29, + "learning_rate": 9.654053114367321e-06, + "loss": 0.3652, + "step": 2274 + }, + { + "epoch": 0.29, + "learning_rate": 9.653674176414936e-06, + "loss": 0.3781, + "step": 2275 + }, + { + "epoch": 0.29, + "learning_rate": 9.653295038483806e-06, + "loss": 0.3421, + "step": 2276 + }, + { + "epoch": 0.29, + "learning_rate": 9.652915700590224e-06, + "loss": 0.3498, + "step": 2277 + }, + { + "epoch": 0.29, + "learning_rate": 9.652536162750492e-06, + "loss": 0.3451, + "step": 2278 + }, + { + "epoch": 0.29, + "learning_rate": 9.65215642498092e-06, + "loss": 0.3672, + "step": 2279 + }, + { + "epoch": 0.29, + "learning_rate": 9.651776487297823e-06, + "loss": 0.3575, + "step": 2280 + }, + { + "epoch": 0.29, + "learning_rate": 9.651396349717533e-06, + "loss": 0.3192, + "step": 2281 + }, + { + "epoch": 0.29, + "learning_rate": 9.651016012256382e-06, + "loss": 0.3641, + "step": 2282 + }, + { + "epoch": 0.29, + "learning_rate": 9.650635474930716e-06, + "loss": 0.3484, + "step": 2283 + }, + { + "epoch": 0.29, + "learning_rate": 9.650254737756883e-06, + "loss": 0.3627, + "step": 2284 + }, + { + "epoch": 0.29, + "learning_rate": 9.64987380075125e-06, + "loss": 0.3521, + "step": 2285 + }, + { + "epoch": 0.29, + "learning_rate": 9.649492663930182e-06, + "loss": 0.3673, + "step": 2286 + }, + { + "epoch": 0.29, + "learning_rate": 9.64911132731006e-06, + "loss": 0.3805, + "step": 2287 + }, + { + "epoch": 0.29, + "learning_rate": 9.648729790907271e-06, + "loss": 0.3526, + "step": 2288 + }, + { + "epoch": 0.29, + "learning_rate": 9.648348054738208e-06, + "loss": 0.3393, + "step": 2289 + }, + { + "epoch": 0.29, + "learning_rate": 9.647966118819278e-06, + "loss": 0.3293, + "step": 2290 + }, + { + "epoch": 0.29, + "learning_rate": 9.647583983166892e-06, + "loss": 0.3471, + "step": 2291 + }, + { + "epoch": 0.29, + "learning_rate": 9.647201647797472e-06, + "loss": 0.3589, + "step": 2292 + }, + { + "epoch": 0.29, + "learning_rate": 9.646819112727445e-06, + "loss": 0.3457, + "step": 2293 + }, + { + "epoch": 0.29, + "learning_rate": 9.646436377973253e-06, + "loss": 0.3404, + "step": 2294 + }, + { + "epoch": 0.29, + "learning_rate": 9.646053443551344e-06, + "loss": 0.3259, + "step": 2295 + }, + { + "epoch": 0.29, + "learning_rate": 9.64567030947817e-06, + "loss": 0.34, + "step": 2296 + }, + { + "epoch": 0.29, + "learning_rate": 9.645286975770194e-06, + "loss": 0.3318, + "step": 2297 + }, + { + "epoch": 0.29, + "learning_rate": 9.644903442443894e-06, + "loss": 0.3417, + "step": 2298 + }, + { + "epoch": 0.29, + "learning_rate": 9.644519709515746e-06, + "loss": 0.3456, + "step": 2299 + }, + { + "epoch": 0.29, + "learning_rate": 9.644135777002244e-06, + "loss": 0.32, + "step": 2300 + }, + { + "epoch": 0.29, + "learning_rate": 9.643751644919883e-06, + "loss": 0.3725, + "step": 2301 + }, + { + "epoch": 0.29, + "learning_rate": 9.643367313285172e-06, + "loss": 0.3371, + "step": 2302 + }, + { + "epoch": 0.29, + "learning_rate": 9.642982782114628e-06, + "loss": 0.346, + "step": 2303 + }, + { + "epoch": 0.29, + "learning_rate": 9.642598051424772e-06, + "loss": 0.3076, + "step": 2304 + }, + { + "epoch": 0.3, + "learning_rate": 9.642213121232137e-06, + "loss": 0.3658, + "step": 2305 + }, + { + "epoch": 0.3, + "learning_rate": 9.641827991553267e-06, + "loss": 0.3613, + "step": 2306 + }, + { + "epoch": 0.3, + "learning_rate": 9.64144266240471e-06, + "loss": 0.2997, + "step": 2307 + }, + { + "epoch": 0.3, + "learning_rate": 9.641057133803024e-06, + "loss": 0.3486, + "step": 2308 + }, + { + "epoch": 0.3, + "learning_rate": 9.640671405764777e-06, + "loss": 0.3146, + "step": 2309 + }, + { + "epoch": 0.3, + "learning_rate": 9.640285478306546e-06, + "loss": 0.3516, + "step": 2310 + }, + { + "epoch": 0.3, + "learning_rate": 9.639899351444911e-06, + "loss": 0.3556, + "step": 2311 + }, + { + "epoch": 0.3, + "learning_rate": 9.63951302519647e-06, + "loss": 0.3591, + "step": 2312 + }, + { + "epoch": 0.3, + "learning_rate": 9.639126499577818e-06, + "loss": 0.3208, + "step": 2313 + }, + { + "epoch": 0.3, + "learning_rate": 9.638739774605572e-06, + "loss": 0.3319, + "step": 2314 + }, + { + "epoch": 0.3, + "learning_rate": 9.638352850296344e-06, + "loss": 0.3208, + "step": 2315 + }, + { + "epoch": 0.3, + "learning_rate": 9.637965726666766e-06, + "loss": 0.3654, + "step": 2316 + }, + { + "epoch": 0.3, + "learning_rate": 9.63757840373347e-06, + "loss": 0.311, + "step": 2317 + }, + { + "epoch": 0.3, + "learning_rate": 9.637190881513103e-06, + "loss": 0.3248, + "step": 2318 + }, + { + "epoch": 0.3, + "learning_rate": 9.636803160022314e-06, + "loss": 0.3326, + "step": 2319 + }, + { + "epoch": 0.3, + "learning_rate": 9.63641523927777e-06, + "loss": 0.3354, + "step": 2320 + }, + { + "epoch": 0.3, + "learning_rate": 9.636027119296133e-06, + "loss": 0.3472, + "step": 2321 + }, + { + "epoch": 0.3, + "learning_rate": 9.63563880009409e-06, + "loss": 0.335, + "step": 2322 + }, + { + "epoch": 0.3, + "learning_rate": 9.63525028168832e-06, + "loss": 0.3498, + "step": 2323 + }, + { + "epoch": 0.3, + "learning_rate": 9.634861564095525e-06, + "loss": 0.3482, + "step": 2324 + }, + { + "epoch": 0.3, + "learning_rate": 9.634472647332405e-06, + "loss": 0.3591, + "step": 2325 + }, + { + "epoch": 0.3, + "learning_rate": 9.634083531415672e-06, + "loss": 0.3414, + "step": 2326 + }, + { + "epoch": 0.3, + "learning_rate": 9.633694216362051e-06, + "loss": 0.3484, + "step": 2327 + }, + { + "epoch": 0.3, + "learning_rate": 9.633304702188271e-06, + "loss": 0.3559, + "step": 2328 + }, + { + "epoch": 0.3, + "learning_rate": 9.632914988911066e-06, + "loss": 0.3381, + "step": 2329 + }, + { + "epoch": 0.3, + "learning_rate": 9.632525076547187e-06, + "loss": 0.3493, + "step": 2330 + }, + { + "epoch": 0.3, + "learning_rate": 9.632134965113389e-06, + "loss": 0.3236, + "step": 2331 + }, + { + "epoch": 0.3, + "learning_rate": 9.631744654626435e-06, + "loss": 0.3439, + "step": 2332 + }, + { + "epoch": 0.3, + "learning_rate": 9.631354145103098e-06, + "loss": 0.3479, + "step": 2333 + }, + { + "epoch": 0.3, + "learning_rate": 9.63096343656016e-06, + "loss": 0.3474, + "step": 2334 + }, + { + "epoch": 0.3, + "learning_rate": 9.630572529014406e-06, + "loss": 0.3189, + "step": 2335 + }, + { + "epoch": 0.3, + "learning_rate": 9.630181422482639e-06, + "loss": 0.3317, + "step": 2336 + }, + { + "epoch": 0.3, + "learning_rate": 9.629790116981665e-06, + "loss": 0.3587, + "step": 2337 + }, + { + "epoch": 0.3, + "learning_rate": 9.629398612528299e-06, + "loss": 0.335, + "step": 2338 + }, + { + "epoch": 0.3, + "learning_rate": 9.629006909139363e-06, + "loss": 0.3547, + "step": 2339 + }, + { + "epoch": 0.3, + "learning_rate": 9.628615006831692e-06, + "loss": 0.3252, + "step": 2340 + }, + { + "epoch": 0.3, + "learning_rate": 9.628222905622124e-06, + "loss": 0.3337, + "step": 2341 + }, + { + "epoch": 0.3, + "learning_rate": 9.627830605527513e-06, + "loss": 0.3636, + "step": 2342 + }, + { + "epoch": 0.3, + "learning_rate": 9.627438106564711e-06, + "loss": 0.3706, + "step": 2343 + }, + { + "epoch": 0.3, + "learning_rate": 9.62704540875059e-06, + "loss": 0.37, + "step": 2344 + }, + { + "epoch": 0.3, + "learning_rate": 9.626652512102021e-06, + "loss": 0.3674, + "step": 2345 + }, + { + "epoch": 0.3, + "learning_rate": 9.62625941663589e-06, + "loss": 0.3305, + "step": 2346 + }, + { + "epoch": 0.3, + "learning_rate": 9.625866122369089e-06, + "loss": 0.3319, + "step": 2347 + }, + { + "epoch": 0.3, + "learning_rate": 9.62547262931852e-06, + "loss": 0.3153, + "step": 2348 + }, + { + "epoch": 0.3, + "learning_rate": 9.625078937501089e-06, + "loss": 0.3247, + "step": 2349 + }, + { + "epoch": 0.3, + "learning_rate": 9.624685046933715e-06, + "loss": 0.3484, + "step": 2350 + }, + { + "epoch": 0.3, + "learning_rate": 9.624290957633325e-06, + "loss": 0.3552, + "step": 2351 + }, + { + "epoch": 0.3, + "learning_rate": 9.623896669616855e-06, + "loss": 0.3236, + "step": 2352 + }, + { + "epoch": 0.3, + "learning_rate": 9.623502182901245e-06, + "loss": 0.3393, + "step": 2353 + }, + { + "epoch": 0.3, + "learning_rate": 9.62310749750345e-06, + "loss": 0.3371, + "step": 2354 + }, + { + "epoch": 0.3, + "learning_rate": 9.62271261344043e-06, + "loss": 0.3422, + "step": 2355 + }, + { + "epoch": 0.3, + "learning_rate": 9.622317530729153e-06, + "loss": 0.3405, + "step": 2356 + }, + { + "epoch": 0.3, + "learning_rate": 9.621922249386598e-06, + "loss": 0.3563, + "step": 2357 + }, + { + "epoch": 0.3, + "learning_rate": 9.621526769429749e-06, + "loss": 0.3569, + "step": 2358 + }, + { + "epoch": 0.3, + "learning_rate": 9.621131090875603e-06, + "loss": 0.3412, + "step": 2359 + }, + { + "epoch": 0.3, + "learning_rate": 9.620735213741163e-06, + "loss": 0.3703, + "step": 2360 + }, + { + "epoch": 0.3, + "learning_rate": 9.62033913804344e-06, + "loss": 0.3567, + "step": 2361 + }, + { + "epoch": 0.3, + "learning_rate": 9.619942863799454e-06, + "loss": 0.3569, + "step": 2362 + }, + { + "epoch": 0.3, + "learning_rate": 9.619546391026234e-06, + "loss": 0.3362, + "step": 2363 + }, + { + "epoch": 0.3, + "learning_rate": 9.619149719740817e-06, + "loss": 0.3219, + "step": 2364 + }, + { + "epoch": 0.3, + "learning_rate": 9.618752849960248e-06, + "loss": 0.3168, + "step": 2365 + }, + { + "epoch": 0.3, + "learning_rate": 9.618355781701584e-06, + "loss": 0.3136, + "step": 2366 + }, + { + "epoch": 0.3, + "learning_rate": 9.617958514981885e-06, + "loss": 0.383, + "step": 2367 + }, + { + "epoch": 0.3, + "learning_rate": 9.617561049818225e-06, + "loss": 0.3598, + "step": 2368 + }, + { + "epoch": 0.3, + "learning_rate": 9.617163386227683e-06, + "loss": 0.3539, + "step": 2369 + }, + { + "epoch": 0.3, + "learning_rate": 9.616765524227348e-06, + "loss": 0.3333, + "step": 2370 + }, + { + "epoch": 0.3, + "learning_rate": 9.616367463834313e-06, + "loss": 0.3323, + "step": 2371 + }, + { + "epoch": 0.3, + "learning_rate": 9.61596920506569e-06, + "loss": 0.3488, + "step": 2372 + }, + { + "epoch": 0.3, + "learning_rate": 9.61557074793859e-06, + "loss": 0.3541, + "step": 2373 + }, + { + "epoch": 0.3, + "learning_rate": 9.615172092470134e-06, + "loss": 0.3805, + "step": 2374 + }, + { + "epoch": 0.3, + "learning_rate": 9.614773238677455e-06, + "loss": 0.34, + "step": 2375 + }, + { + "epoch": 0.3, + "learning_rate": 9.614374186577693e-06, + "loss": 0.3688, + "step": 2376 + }, + { + "epoch": 0.3, + "learning_rate": 9.613974936187993e-06, + "loss": 0.3737, + "step": 2377 + }, + { + "epoch": 0.3, + "learning_rate": 9.613575487525517e-06, + "loss": 0.3148, + "step": 2378 + }, + { + "epoch": 0.3, + "learning_rate": 9.613175840607428e-06, + "loss": 0.3403, + "step": 2379 + }, + { + "epoch": 0.3, + "learning_rate": 9.612775995450896e-06, + "loss": 0.3328, + "step": 2380 + }, + { + "epoch": 0.3, + "learning_rate": 9.612375952073108e-06, + "loss": 0.3632, + "step": 2381 + }, + { + "epoch": 0.3, + "learning_rate": 9.611975710491252e-06, + "loss": 0.3414, + "step": 2382 + }, + { + "epoch": 0.31, + "learning_rate": 9.611575270722529e-06, + "loss": 0.332, + "step": 2383 + }, + { + "epoch": 0.31, + "learning_rate": 9.611174632784147e-06, + "loss": 0.3453, + "step": 2384 + }, + { + "epoch": 0.31, + "learning_rate": 9.61077379669332e-06, + "loss": 0.3436, + "step": 2385 + }, + { + "epoch": 0.31, + "learning_rate": 9.610372762467275e-06, + "loss": 0.3406, + "step": 2386 + }, + { + "epoch": 0.31, + "learning_rate": 9.609971530123243e-06, + "loss": 0.3576, + "step": 2387 + }, + { + "epoch": 0.31, + "learning_rate": 9.60957009967847e-06, + "loss": 0.3425, + "step": 2388 + }, + { + "epoch": 0.31, + "learning_rate": 9.609168471150202e-06, + "loss": 0.3643, + "step": 2389 + }, + { + "epoch": 0.31, + "learning_rate": 9.6087666445557e-06, + "loss": 0.3591, + "step": 2390 + }, + { + "epoch": 0.31, + "learning_rate": 9.60836461991223e-06, + "loss": 0.3685, + "step": 2391 + }, + { + "epoch": 0.31, + "learning_rate": 9.607962397237071e-06, + "loss": 0.3608, + "step": 2392 + }, + { + "epoch": 0.31, + "learning_rate": 9.607559976547504e-06, + "loss": 0.3353, + "step": 2393 + }, + { + "epoch": 0.31, + "learning_rate": 9.607157357860823e-06, + "loss": 0.3549, + "step": 2394 + }, + { + "epoch": 0.31, + "learning_rate": 9.606754541194329e-06, + "loss": 0.3628, + "step": 2395 + }, + { + "epoch": 0.31, + "learning_rate": 9.606351526565336e-06, + "loss": 0.3434, + "step": 2396 + }, + { + "epoch": 0.31, + "learning_rate": 9.605948313991156e-06, + "loss": 0.3255, + "step": 2397 + }, + { + "epoch": 0.31, + "learning_rate": 9.60554490348912e-06, + "loss": 0.3313, + "step": 2398 + }, + { + "epoch": 0.31, + "learning_rate": 9.605141295076561e-06, + "loss": 0.3435, + "step": 2399 + }, + { + "epoch": 0.31, + "learning_rate": 9.604737488770826e-06, + "loss": 0.3597, + "step": 2400 + }, + { + "epoch": 0.31, + "learning_rate": 9.604333484589266e-06, + "loss": 0.3083, + "step": 2401 + }, + { + "epoch": 0.31, + "learning_rate": 9.60392928254924e-06, + "loss": 0.3144, + "step": 2402 + }, + { + "epoch": 0.31, + "learning_rate": 9.60352488266812e-06, + "loss": 0.3558, + "step": 2403 + }, + { + "epoch": 0.31, + "learning_rate": 9.603120284963284e-06, + "loss": 0.3583, + "step": 2404 + }, + { + "epoch": 0.31, + "learning_rate": 9.602715489452117e-06, + "loss": 0.3446, + "step": 2405 + }, + { + "epoch": 0.31, + "learning_rate": 9.602310496152014e-06, + "loss": 0.3666, + "step": 2406 + }, + { + "epoch": 0.31, + "learning_rate": 9.60190530508038e-06, + "loss": 0.3629, + "step": 2407 + }, + { + "epoch": 0.31, + "learning_rate": 9.601499916254626e-06, + "loss": 0.3421, + "step": 2408 + }, + { + "epoch": 0.31, + "learning_rate": 9.601094329692173e-06, + "loss": 0.3471, + "step": 2409 + }, + { + "epoch": 0.31, + "learning_rate": 9.600688545410449e-06, + "loss": 0.3427, + "step": 2410 + }, + { + "epoch": 0.31, + "learning_rate": 9.60028256342689e-06, + "loss": 0.3558, + "step": 2411 + }, + { + "epoch": 0.31, + "learning_rate": 9.599876383758946e-06, + "loss": 0.371, + "step": 2412 + }, + { + "epoch": 0.31, + "learning_rate": 9.599470006424069e-06, + "loss": 0.3585, + "step": 2413 + }, + { + "epoch": 0.31, + "learning_rate": 9.599063431439721e-06, + "loss": 0.3328, + "step": 2414 + }, + { + "epoch": 0.31, + "learning_rate": 9.598656658823378e-06, + "loss": 0.3522, + "step": 2415 + }, + { + "epoch": 0.31, + "learning_rate": 9.598249688592514e-06, + "loss": 0.3485, + "step": 2416 + }, + { + "epoch": 0.31, + "learning_rate": 9.597842520764619e-06, + "loss": 0.3425, + "step": 2417 + }, + { + "epoch": 0.31, + "learning_rate": 9.597435155357192e-06, + "loss": 0.3225, + "step": 2418 + }, + { + "epoch": 0.31, + "learning_rate": 9.597027592387739e-06, + "loss": 0.3718, + "step": 2419 + }, + { + "epoch": 0.31, + "learning_rate": 9.59661983187377e-06, + "loss": 0.3286, + "step": 2420 + }, + { + "epoch": 0.31, + "learning_rate": 9.59621187383281e-06, + "loss": 0.366, + "step": 2421 + }, + { + "epoch": 0.31, + "learning_rate": 9.595803718282391e-06, + "loss": 0.338, + "step": 2422 + }, + { + "epoch": 0.31, + "learning_rate": 9.59539536524005e-06, + "loss": 0.347, + "step": 2423 + }, + { + "epoch": 0.31, + "learning_rate": 9.594986814723335e-06, + "loss": 0.3482, + "step": 2424 + }, + { + "epoch": 0.31, + "learning_rate": 9.594578066749804e-06, + "loss": 0.3158, + "step": 2425 + }, + { + "epoch": 0.31, + "learning_rate": 9.59416912133702e-06, + "loss": 0.3329, + "step": 2426 + }, + { + "epoch": 0.31, + "learning_rate": 9.593759978502556e-06, + "loss": 0.3125, + "step": 2427 + }, + { + "epoch": 0.31, + "learning_rate": 9.593350638263998e-06, + "loss": 0.3413, + "step": 2428 + }, + { + "epoch": 0.31, + "learning_rate": 9.59294110063893e-06, + "loss": 0.3638, + "step": 2429 + }, + { + "epoch": 0.31, + "learning_rate": 9.592531365644957e-06, + "loss": 0.3472, + "step": 2430 + }, + { + "epoch": 0.31, + "learning_rate": 9.592121433299682e-06, + "loss": 0.3615, + "step": 2431 + }, + { + "epoch": 0.31, + "learning_rate": 9.59171130362072e-06, + "loss": 0.3531, + "step": 2432 + }, + { + "epoch": 0.31, + "learning_rate": 9.591300976625697e-06, + "loss": 0.3456, + "step": 2433 + }, + { + "epoch": 0.31, + "learning_rate": 9.590890452332249e-06, + "loss": 0.3335, + "step": 2434 + }, + { + "epoch": 0.31, + "learning_rate": 9.59047973075801e-06, + "loss": 0.3612, + "step": 2435 + }, + { + "epoch": 0.31, + "learning_rate": 9.590068811920637e-06, + "loss": 0.3759, + "step": 2436 + }, + { + "epoch": 0.31, + "learning_rate": 9.589657695837781e-06, + "loss": 0.3692, + "step": 2437 + }, + { + "epoch": 0.31, + "learning_rate": 9.589246382527113e-06, + "loss": 0.3386, + "step": 2438 + }, + { + "epoch": 0.31, + "learning_rate": 9.588834872006308e-06, + "loss": 0.3275, + "step": 2439 + }, + { + "epoch": 0.31, + "learning_rate": 9.588423164293049e-06, + "loss": 0.3327, + "step": 2440 + }, + { + "epoch": 0.31, + "learning_rate": 9.588011259405028e-06, + "loss": 0.3383, + "step": 2441 + }, + { + "epoch": 0.31, + "learning_rate": 9.587599157359943e-06, + "loss": 0.3449, + "step": 2442 + }, + { + "epoch": 0.31, + "learning_rate": 9.587186858175507e-06, + "loss": 0.3432, + "step": 2443 + }, + { + "epoch": 0.31, + "learning_rate": 9.586774361869436e-06, + "loss": 0.3228, + "step": 2444 + }, + { + "epoch": 0.31, + "learning_rate": 9.586361668459452e-06, + "loss": 0.3626, + "step": 2445 + }, + { + "epoch": 0.31, + "learning_rate": 9.585948777963296e-06, + "loss": 0.325, + "step": 2446 + }, + { + "epoch": 0.31, + "learning_rate": 9.585535690398706e-06, + "loss": 0.356, + "step": 2447 + }, + { + "epoch": 0.31, + "learning_rate": 9.585122405783435e-06, + "loss": 0.3466, + "step": 2448 + }, + { + "epoch": 0.31, + "learning_rate": 9.584708924135245e-06, + "loss": 0.348, + "step": 2449 + }, + { + "epoch": 0.31, + "learning_rate": 9.584295245471898e-06, + "loss": 0.3493, + "step": 2450 + }, + { + "epoch": 0.31, + "learning_rate": 9.583881369811176e-06, + "loss": 0.3484, + "step": 2451 + }, + { + "epoch": 0.31, + "learning_rate": 9.583467297170863e-06, + "loss": 0.332, + "step": 2452 + }, + { + "epoch": 0.31, + "learning_rate": 9.583053027568754e-06, + "loss": 0.3824, + "step": 2453 + }, + { + "epoch": 0.31, + "learning_rate": 9.582638561022646e-06, + "loss": 0.3421, + "step": 2454 + }, + { + "epoch": 0.31, + "learning_rate": 9.582223897550356e-06, + "loss": 0.3269, + "step": 2455 + }, + { + "epoch": 0.31, + "learning_rate": 9.581809037169698e-06, + "loss": 0.3431, + "step": 2456 + }, + { + "epoch": 0.31, + "learning_rate": 9.581393979898502e-06, + "loss": 0.3244, + "step": 2457 + }, + { + "epoch": 0.31, + "learning_rate": 9.580978725754604e-06, + "loss": 0.3432, + "step": 2458 + }, + { + "epoch": 0.31, + "learning_rate": 9.580563274755848e-06, + "loss": 0.3374, + "step": 2459 + }, + { + "epoch": 0.31, + "learning_rate": 9.580147626920084e-06, + "loss": 0.3284, + "step": 2460 + }, + { + "epoch": 0.32, + "learning_rate": 9.579731782265178e-06, + "loss": 0.3561, + "step": 2461 + }, + { + "epoch": 0.32, + "learning_rate": 9.579315740808998e-06, + "loss": 0.3326, + "step": 2462 + }, + { + "epoch": 0.32, + "learning_rate": 9.578899502569421e-06, + "loss": 0.3475, + "step": 2463 + }, + { + "epoch": 0.32, + "learning_rate": 9.578483067564335e-06, + "loss": 0.3235, + "step": 2464 + }, + { + "epoch": 0.32, + "learning_rate": 9.578066435811636e-06, + "loss": 0.3482, + "step": 2465 + }, + { + "epoch": 0.32, + "learning_rate": 9.577649607329225e-06, + "loss": 0.3395, + "step": 2466 + }, + { + "epoch": 0.32, + "learning_rate": 9.577232582135014e-06, + "loss": 0.3813, + "step": 2467 + }, + { + "epoch": 0.32, + "learning_rate": 9.576815360246926e-06, + "loss": 0.3618, + "step": 2468 + }, + { + "epoch": 0.32, + "learning_rate": 9.576397941682891e-06, + "loss": 0.3405, + "step": 2469 + }, + { + "epoch": 0.32, + "learning_rate": 9.575980326460841e-06, + "loss": 0.3191, + "step": 2470 + }, + { + "epoch": 0.32, + "learning_rate": 9.575562514598727e-06, + "loss": 0.3473, + "step": 2471 + }, + { + "epoch": 0.32, + "learning_rate": 9.575144506114501e-06, + "loss": 0.3706, + "step": 2472 + }, + { + "epoch": 0.32, + "learning_rate": 9.574726301026127e-06, + "loss": 0.3649, + "step": 2473 + }, + { + "epoch": 0.32, + "learning_rate": 9.574307899351574e-06, + "loss": 0.3319, + "step": 2474 + }, + { + "epoch": 0.32, + "learning_rate": 9.573889301108823e-06, + "loss": 0.3542, + "step": 2475 + }, + { + "epoch": 0.32, + "learning_rate": 9.573470506315864e-06, + "loss": 0.3315, + "step": 2476 + }, + { + "epoch": 0.32, + "learning_rate": 9.57305151499069e-06, + "loss": 0.3473, + "step": 2477 + }, + { + "epoch": 0.32, + "learning_rate": 9.572632327151309e-06, + "loss": 0.3279, + "step": 2478 + }, + { + "epoch": 0.32, + "learning_rate": 9.572212942815734e-06, + "loss": 0.3349, + "step": 2479 + }, + { + "epoch": 0.32, + "learning_rate": 9.571793362001983e-06, + "loss": 0.3486, + "step": 2480 + }, + { + "epoch": 0.32, + "learning_rate": 9.57137358472809e-06, + "loss": 0.3531, + "step": 2481 + }, + { + "epoch": 0.32, + "learning_rate": 9.570953611012092e-06, + "loss": 0.3481, + "step": 2482 + }, + { + "epoch": 0.32, + "learning_rate": 9.570533440872041e-06, + "loss": 0.3359, + "step": 2483 + }, + { + "epoch": 0.32, + "learning_rate": 9.570113074325986e-06, + "loss": 0.3193, + "step": 2484 + }, + { + "epoch": 0.32, + "learning_rate": 9.569692511391995e-06, + "loss": 0.3489, + "step": 2485 + }, + { + "epoch": 0.32, + "learning_rate": 9.569271752088139e-06, + "loss": 0.318, + "step": 2486 + }, + { + "epoch": 0.32, + "learning_rate": 9.5688507964325e-06, + "loss": 0.3593, + "step": 2487 + }, + { + "epoch": 0.32, + "learning_rate": 9.568429644443167e-06, + "loss": 0.368, + "step": 2488 + }, + { + "epoch": 0.32, + "learning_rate": 9.568008296138238e-06, + "loss": 0.3037, + "step": 2489 + }, + { + "epoch": 0.32, + "learning_rate": 9.567586751535818e-06, + "loss": 0.3449, + "step": 2490 + }, + { + "epoch": 0.32, + "learning_rate": 9.567165010654022e-06, + "loss": 0.3278, + "step": 2491 + }, + { + "epoch": 0.32, + "learning_rate": 9.566743073510976e-06, + "loss": 0.3358, + "step": 2492 + }, + { + "epoch": 0.32, + "learning_rate": 9.566320940124809e-06, + "loss": 0.3408, + "step": 2493 + }, + { + "epoch": 0.32, + "learning_rate": 9.565898610513661e-06, + "loss": 0.3424, + "step": 2494 + }, + { + "epoch": 0.32, + "learning_rate": 9.565476084695681e-06, + "loss": 0.3369, + "step": 2495 + }, + { + "epoch": 0.32, + "learning_rate": 9.565053362689026e-06, + "loss": 0.3615, + "step": 2496 + }, + { + "epoch": 0.32, + "learning_rate": 9.56463044451186e-06, + "loss": 0.3644, + "step": 2497 + }, + { + "epoch": 0.32, + "learning_rate": 9.564207330182359e-06, + "loss": 0.3266, + "step": 2498 + }, + { + "epoch": 0.32, + "learning_rate": 9.563784019718704e-06, + "loss": 0.3246, + "step": 2499 + }, + { + "epoch": 0.32, + "learning_rate": 9.563360513139085e-06, + "loss": 0.3734, + "step": 2500 + }, + { + "epoch": 0.32, + "learning_rate": 9.562936810461701e-06, + "loss": 0.366, + "step": 2501 + }, + { + "epoch": 0.32, + "learning_rate": 9.562512911704761e-06, + "loss": 0.3376, + "step": 2502 + }, + { + "epoch": 0.32, + "learning_rate": 9.56208881688648e-06, + "loss": 0.3434, + "step": 2503 + }, + { + "epoch": 0.32, + "learning_rate": 9.561664526025082e-06, + "loss": 0.3233, + "step": 2504 + }, + { + "epoch": 0.32, + "learning_rate": 9.5612400391388e-06, + "loss": 0.3526, + "step": 2505 + }, + { + "epoch": 0.32, + "learning_rate": 9.560815356245875e-06, + "loss": 0.3417, + "step": 2506 + }, + { + "epoch": 0.32, + "learning_rate": 9.560390477364555e-06, + "loss": 0.3565, + "step": 2507 + }, + { + "epoch": 0.32, + "learning_rate": 9.559965402513103e-06, + "loss": 0.3921, + "step": 2508 + }, + { + "epoch": 0.32, + "learning_rate": 9.55954013170978e-06, + "loss": 0.3694, + "step": 2509 + }, + { + "epoch": 0.32, + "learning_rate": 9.559114664972864e-06, + "loss": 0.3219, + "step": 2510 + }, + { + "epoch": 0.32, + "learning_rate": 9.558689002320635e-06, + "loss": 0.3401, + "step": 2511 + }, + { + "epoch": 0.32, + "learning_rate": 9.55826314377139e-06, + "loss": 0.3347, + "step": 2512 + }, + { + "epoch": 0.32, + "learning_rate": 9.557837089343424e-06, + "loss": 0.3257, + "step": 2513 + }, + { + "epoch": 0.32, + "learning_rate": 9.557410839055047e-06, + "loss": 0.3302, + "step": 2514 + }, + { + "epoch": 0.32, + "learning_rate": 9.556984392924577e-06, + "loss": 0.3462, + "step": 2515 + }, + { + "epoch": 0.32, + "learning_rate": 9.55655775097034e-06, + "loss": 0.3365, + "step": 2516 + }, + { + "epoch": 0.32, + "learning_rate": 9.556130913210666e-06, + "loss": 0.3424, + "step": 2517 + }, + { + "epoch": 0.32, + "learning_rate": 9.5557038796639e-06, + "loss": 0.3491, + "step": 2518 + }, + { + "epoch": 0.32, + "learning_rate": 9.555276650348393e-06, + "loss": 0.3461, + "step": 2519 + }, + { + "epoch": 0.32, + "learning_rate": 9.554849225282503e-06, + "loss": 0.3205, + "step": 2520 + }, + { + "epoch": 0.32, + "learning_rate": 9.554421604484599e-06, + "loss": 0.3247, + "step": 2521 + }, + { + "epoch": 0.32, + "learning_rate": 9.553993787973053e-06, + "loss": 0.3382, + "step": 2522 + }, + { + "epoch": 0.32, + "learning_rate": 9.553565775766253e-06, + "loss": 0.3298, + "step": 2523 + }, + { + "epoch": 0.32, + "learning_rate": 9.55313756788259e-06, + "loss": 0.3397, + "step": 2524 + }, + { + "epoch": 0.32, + "learning_rate": 9.552709164340466e-06, + "loss": 0.3106, + "step": 2525 + }, + { + "epoch": 0.32, + "learning_rate": 9.552280565158289e-06, + "loss": 0.3575, + "step": 2526 + }, + { + "epoch": 0.32, + "learning_rate": 9.551851770354477e-06, + "loss": 0.334, + "step": 2527 + }, + { + "epoch": 0.32, + "learning_rate": 9.551422779947458e-06, + "loss": 0.3432, + "step": 2528 + }, + { + "epoch": 0.32, + "learning_rate": 9.550993593955665e-06, + "loss": 0.3361, + "step": 2529 + }, + { + "epoch": 0.32, + "learning_rate": 9.550564212397541e-06, + "loss": 0.365, + "step": 2530 + }, + { + "epoch": 0.32, + "learning_rate": 9.55013463529154e-06, + "loss": 0.3746, + "step": 2531 + }, + { + "epoch": 0.32, + "learning_rate": 9.54970486265612e-06, + "loss": 0.33, + "step": 2532 + }, + { + "epoch": 0.32, + "learning_rate": 9.549274894509748e-06, + "loss": 0.3443, + "step": 2533 + }, + { + "epoch": 0.32, + "learning_rate": 9.548844730870903e-06, + "loss": 0.3494, + "step": 2534 + }, + { + "epoch": 0.32, + "learning_rate": 9.548414371758068e-06, + "loss": 0.3437, + "step": 2535 + }, + { + "epoch": 0.32, + "learning_rate": 9.547983817189738e-06, + "loss": 0.3677, + "step": 2536 + }, + { + "epoch": 0.32, + "learning_rate": 9.547553067184413e-06, + "loss": 0.3645, + "step": 2537 + }, + { + "epoch": 0.32, + "learning_rate": 9.547122121760607e-06, + "loss": 0.3233, + "step": 2538 + }, + { + "epoch": 0.32, + "learning_rate": 9.546690980936836e-06, + "loss": 0.3203, + "step": 2539 + }, + { + "epoch": 0.33, + "learning_rate": 9.546259644731628e-06, + "loss": 0.3189, + "step": 2540 + }, + { + "epoch": 0.33, + "learning_rate": 9.545828113163516e-06, + "loss": 0.3501, + "step": 2541 + }, + { + "epoch": 0.33, + "learning_rate": 9.545396386251048e-06, + "loss": 0.3666, + "step": 2542 + }, + { + "epoch": 0.33, + "learning_rate": 9.544964464012774e-06, + "loss": 0.2982, + "step": 2543 + }, + { + "epoch": 0.33, + "learning_rate": 9.544532346467254e-06, + "loss": 0.3385, + "step": 2544 + }, + { + "epoch": 0.33, + "learning_rate": 9.544100033633057e-06, + "loss": 0.3319, + "step": 2545 + }, + { + "epoch": 0.33, + "learning_rate": 9.543667525528762e-06, + "loss": 0.3154, + "step": 2546 + }, + { + "epoch": 0.33, + "learning_rate": 9.543234822172956e-06, + "loss": 0.3296, + "step": 2547 + }, + { + "epoch": 0.33, + "learning_rate": 9.542801923584228e-06, + "loss": 0.3525, + "step": 2548 + }, + { + "epoch": 0.33, + "learning_rate": 9.542368829781186e-06, + "loss": 0.3438, + "step": 2549 + }, + { + "epoch": 0.33, + "learning_rate": 9.541935540782439e-06, + "loss": 0.3179, + "step": 2550 + }, + { + "epoch": 0.33, + "learning_rate": 9.541502056606606e-06, + "loss": 0.331, + "step": 2551 + }, + { + "epoch": 0.33, + "learning_rate": 9.541068377272315e-06, + "loss": 0.3609, + "step": 2552 + }, + { + "epoch": 0.33, + "learning_rate": 9.540634502798203e-06, + "loss": 0.3746, + "step": 2553 + }, + { + "epoch": 0.33, + "learning_rate": 9.540200433202913e-06, + "loss": 0.3114, + "step": 2554 + }, + { + "epoch": 0.33, + "learning_rate": 9.5397661685051e-06, + "loss": 0.3498, + "step": 2555 + }, + { + "epoch": 0.33, + "learning_rate": 9.539331708723423e-06, + "loss": 0.3409, + "step": 2556 + }, + { + "epoch": 0.33, + "learning_rate": 9.538897053876553e-06, + "loss": 0.3761, + "step": 2557 + }, + { + "epoch": 0.33, + "learning_rate": 9.538462203983169e-06, + "loss": 0.3285, + "step": 2558 + }, + { + "epoch": 0.33, + "learning_rate": 9.538027159061955e-06, + "loss": 0.3569, + "step": 2559 + }, + { + "epoch": 0.33, + "learning_rate": 9.537591919131608e-06, + "loss": 0.2969, + "step": 2560 + }, + { + "epoch": 0.33, + "learning_rate": 9.53715648421083e-06, + "loss": 0.3751, + "step": 2561 + }, + { + "epoch": 0.33, + "learning_rate": 9.536720854318333e-06, + "loss": 0.3708, + "step": 2562 + }, + { + "epoch": 0.33, + "learning_rate": 9.536285029472838e-06, + "loss": 0.3742, + "step": 2563 + }, + { + "epoch": 0.33, + "learning_rate": 9.535849009693072e-06, + "loss": 0.3453, + "step": 2564 + }, + { + "epoch": 0.33, + "learning_rate": 9.535412794997772e-06, + "loss": 0.3481, + "step": 2565 + }, + { + "epoch": 0.33, + "learning_rate": 9.534976385405683e-06, + "loss": 0.3273, + "step": 2566 + }, + { + "epoch": 0.33, + "learning_rate": 9.53453978093556e-06, + "loss": 0.3462, + "step": 2567 + }, + { + "epoch": 0.33, + "learning_rate": 9.534102981606162e-06, + "loss": 0.3657, + "step": 2568 + }, + { + "epoch": 0.33, + "learning_rate": 9.533665987436262e-06, + "loss": 0.3462, + "step": 2569 + }, + { + "epoch": 0.33, + "learning_rate": 9.533228798444637e-06, + "loss": 0.3494, + "step": 2570 + }, + { + "epoch": 0.33, + "learning_rate": 9.532791414650075e-06, + "loss": 0.3324, + "step": 2571 + }, + { + "epoch": 0.33, + "learning_rate": 9.53235383607137e-06, + "loss": 0.3227, + "step": 2572 + }, + { + "epoch": 0.33, + "learning_rate": 9.531916062727328e-06, + "loss": 0.358, + "step": 2573 + }, + { + "epoch": 0.33, + "learning_rate": 9.531478094636758e-06, + "loss": 0.3261, + "step": 2574 + }, + { + "epoch": 0.33, + "learning_rate": 9.531039931818485e-06, + "loss": 0.3453, + "step": 2575 + }, + { + "epoch": 0.33, + "learning_rate": 9.530601574291331e-06, + "loss": 0.3555, + "step": 2576 + }, + { + "epoch": 0.33, + "learning_rate": 9.530163022074139e-06, + "loss": 0.3451, + "step": 2577 + }, + { + "epoch": 0.33, + "learning_rate": 9.529724275185753e-06, + "loss": 0.3296, + "step": 2578 + }, + { + "epoch": 0.33, + "learning_rate": 9.529285333645027e-06, + "loss": 0.3696, + "step": 2579 + }, + { + "epoch": 0.33, + "learning_rate": 9.528846197470822e-06, + "loss": 0.3464, + "step": 2580 + }, + { + "epoch": 0.33, + "learning_rate": 9.528406866682009e-06, + "loss": 0.3244, + "step": 2581 + }, + { + "epoch": 0.33, + "learning_rate": 9.527967341297471e-06, + "loss": 0.3409, + "step": 2582 + }, + { + "epoch": 0.33, + "learning_rate": 9.527527621336087e-06, + "loss": 0.3323, + "step": 2583 + }, + { + "epoch": 0.33, + "learning_rate": 9.527087706816762e-06, + "loss": 0.3354, + "step": 2584 + }, + { + "epoch": 0.33, + "learning_rate": 9.526647597758394e-06, + "loss": 0.2977, + "step": 2585 + }, + { + "epoch": 0.33, + "learning_rate": 9.526207294179897e-06, + "loss": 0.3203, + "step": 2586 + }, + { + "epoch": 0.33, + "learning_rate": 9.525766796100194e-06, + "loss": 0.3655, + "step": 2587 + }, + { + "epoch": 0.33, + "learning_rate": 9.52532610353821e-06, + "loss": 0.3394, + "step": 2588 + }, + { + "epoch": 0.33, + "learning_rate": 9.524885216512887e-06, + "loss": 0.3247, + "step": 2589 + }, + { + "epoch": 0.33, + "learning_rate": 9.524444135043168e-06, + "loss": 0.3469, + "step": 2590 + }, + { + "epoch": 0.33, + "learning_rate": 9.524002859148006e-06, + "loss": 0.3667, + "step": 2591 + }, + { + "epoch": 0.33, + "learning_rate": 9.523561388846368e-06, + "loss": 0.3494, + "step": 2592 + }, + { + "epoch": 0.33, + "learning_rate": 9.523119724157222e-06, + "loss": 0.3518, + "step": 2593 + }, + { + "epoch": 0.33, + "learning_rate": 9.522677865099548e-06, + "loss": 0.3329, + "step": 2594 + }, + { + "epoch": 0.33, + "learning_rate": 9.522235811692335e-06, + "loss": 0.3359, + "step": 2595 + }, + { + "epoch": 0.33, + "learning_rate": 9.521793563954575e-06, + "loss": 0.3343, + "step": 2596 + }, + { + "epoch": 0.33, + "learning_rate": 9.521351121905278e-06, + "loss": 0.3358, + "step": 2597 + }, + { + "epoch": 0.33, + "learning_rate": 9.520908485563452e-06, + "loss": 0.3491, + "step": 2598 + }, + { + "epoch": 0.33, + "learning_rate": 9.520465654948119e-06, + "loss": 0.3565, + "step": 2599 + }, + { + "epoch": 0.33, + "learning_rate": 9.52002263007831e-06, + "loss": 0.3388, + "step": 2600 + }, + { + "epoch": 0.33, + "learning_rate": 9.519579410973061e-06, + "loss": 0.3275, + "step": 2601 + }, + { + "epoch": 0.33, + "learning_rate": 9.51913599765142e-06, + "loss": 0.3563, + "step": 2602 + }, + { + "epoch": 0.33, + "learning_rate": 9.518692390132441e-06, + "loss": 0.3504, + "step": 2603 + }, + { + "epoch": 0.33, + "learning_rate": 9.518248588435185e-06, + "loss": 0.354, + "step": 2604 + }, + { + "epoch": 0.33, + "learning_rate": 9.517804592578725e-06, + "loss": 0.3327, + "step": 2605 + }, + { + "epoch": 0.33, + "learning_rate": 9.517360402582141e-06, + "loss": 0.3195, + "step": 2606 + }, + { + "epoch": 0.33, + "learning_rate": 9.51691601846452e-06, + "loss": 0.3352, + "step": 2607 + }, + { + "epoch": 0.33, + "learning_rate": 9.516471440244956e-06, + "loss": 0.314, + "step": 2608 + }, + { + "epoch": 0.33, + "learning_rate": 9.516026667942557e-06, + "loss": 0.3455, + "step": 2609 + }, + { + "epoch": 0.33, + "learning_rate": 9.515581701576433e-06, + "loss": 0.3527, + "step": 2610 + }, + { + "epoch": 0.33, + "learning_rate": 9.515136541165708e-06, + "loss": 0.3196, + "step": 2611 + }, + { + "epoch": 0.33, + "learning_rate": 9.514691186729509e-06, + "loss": 0.3191, + "step": 2612 + }, + { + "epoch": 0.33, + "learning_rate": 9.514245638286976e-06, + "loss": 0.3372, + "step": 2613 + }, + { + "epoch": 0.33, + "learning_rate": 9.513799895857252e-06, + "loss": 0.3661, + "step": 2614 + }, + { + "epoch": 0.33, + "learning_rate": 9.513353959459496e-06, + "loss": 0.3171, + "step": 2615 + }, + { + "epoch": 0.33, + "learning_rate": 9.512907829112867e-06, + "loss": 0.348, + "step": 2616 + }, + { + "epoch": 0.33, + "learning_rate": 9.512461504836538e-06, + "loss": 0.3506, + "step": 2617 + }, + { + "epoch": 0.34, + "learning_rate": 9.512014986649691e-06, + "loss": 0.3548, + "step": 2618 + }, + { + "epoch": 0.34, + "learning_rate": 9.511568274571508e-06, + "loss": 0.3431, + "step": 2619 + }, + { + "epoch": 0.34, + "learning_rate": 9.51112136862119e-06, + "loss": 0.3398, + "step": 2620 + }, + { + "epoch": 0.34, + "learning_rate": 9.51067426881794e-06, + "loss": 0.3559, + "step": 2621 + }, + { + "epoch": 0.34, + "learning_rate": 9.510226975180969e-06, + "loss": 0.3315, + "step": 2622 + }, + { + "epoch": 0.34, + "learning_rate": 9.509779487729502e-06, + "loss": 0.3304, + "step": 2623 + }, + { + "epoch": 0.34, + "learning_rate": 9.509331806482767e-06, + "loss": 0.3166, + "step": 2624 + }, + { + "epoch": 0.34, + "learning_rate": 9.50888393146e-06, + "loss": 0.3621, + "step": 2625 + }, + { + "epoch": 0.34, + "learning_rate": 9.508435862680449e-06, + "loss": 0.3297, + "step": 2626 + }, + { + "epoch": 0.34, + "learning_rate": 9.507987600163369e-06, + "loss": 0.3283, + "step": 2627 + }, + { + "epoch": 0.34, + "learning_rate": 9.507539143928021e-06, + "loss": 0.3144, + "step": 2628 + }, + { + "epoch": 0.34, + "learning_rate": 9.507090493993677e-06, + "loss": 0.3595, + "step": 2629 + }, + { + "epoch": 0.34, + "learning_rate": 9.506641650379617e-06, + "loss": 0.313, + "step": 2630 + }, + { + "epoch": 0.34, + "learning_rate": 9.50619261310513e-06, + "loss": 0.3327, + "step": 2631 + }, + { + "epoch": 0.34, + "learning_rate": 9.50574338218951e-06, + "loss": 0.359, + "step": 2632 + }, + { + "epoch": 0.34, + "learning_rate": 9.50529395765206e-06, + "loss": 0.3226, + "step": 2633 + }, + { + "epoch": 0.34, + "learning_rate": 9.504844339512096e-06, + "loss": 0.3402, + "step": 2634 + }, + { + "epoch": 0.34, + "learning_rate": 9.504394527788939e-06, + "loss": 0.331, + "step": 2635 + }, + { + "epoch": 0.34, + "learning_rate": 9.503944522501915e-06, + "loss": 0.3321, + "step": 2636 + }, + { + "epoch": 0.34, + "learning_rate": 9.503494323670366e-06, + "loss": 0.3157, + "step": 2637 + }, + { + "epoch": 0.34, + "learning_rate": 9.503043931313637e-06, + "loss": 0.3286, + "step": 2638 + }, + { + "epoch": 0.34, + "learning_rate": 9.502593345451078e-06, + "loss": 0.3298, + "step": 2639 + }, + { + "epoch": 0.34, + "learning_rate": 9.502142566102058e-06, + "loss": 0.3447, + "step": 2640 + }, + { + "epoch": 0.34, + "learning_rate": 9.501691593285943e-06, + "loss": 0.3423, + "step": 2641 + }, + { + "epoch": 0.34, + "learning_rate": 9.501240427022115e-06, + "loss": 0.3481, + "step": 2642 + }, + { + "epoch": 0.34, + "learning_rate": 9.500789067329963e-06, + "loss": 0.3474, + "step": 2643 + }, + { + "epoch": 0.34, + "learning_rate": 9.500337514228878e-06, + "loss": 0.3441, + "step": 2644 + }, + { + "epoch": 0.34, + "learning_rate": 9.49988576773827e-06, + "loss": 0.3482, + "step": 2645 + }, + { + "epoch": 0.34, + "learning_rate": 9.499433827877547e-06, + "loss": 0.3301, + "step": 2646 + }, + { + "epoch": 0.34, + "learning_rate": 9.498981694666133e-06, + "loss": 0.3378, + "step": 2647 + }, + { + "epoch": 0.34, + "learning_rate": 9.498529368123455e-06, + "loss": 0.3318, + "step": 2648 + }, + { + "epoch": 0.34, + "learning_rate": 9.49807684826895e-06, + "loss": 0.3215, + "step": 2649 + }, + { + "epoch": 0.34, + "learning_rate": 9.497624135122068e-06, + "loss": 0.339, + "step": 2650 + }, + { + "epoch": 0.34, + "learning_rate": 9.497171228702257e-06, + "loss": 0.3298, + "step": 2651 + }, + { + "epoch": 0.34, + "learning_rate": 9.496718129028986e-06, + "loss": 0.3331, + "step": 2652 + }, + { + "epoch": 0.34, + "learning_rate": 9.49626483612172e-06, + "loss": 0.3566, + "step": 2653 + }, + { + "epoch": 0.34, + "learning_rate": 9.495811349999941e-06, + "loss": 0.3323, + "step": 2654 + }, + { + "epoch": 0.34, + "learning_rate": 9.495357670683135e-06, + "loss": 0.3245, + "step": 2655 + }, + { + "epoch": 0.34, + "learning_rate": 9.494903798190798e-06, + "loss": 0.3403, + "step": 2656 + }, + { + "epoch": 0.34, + "learning_rate": 9.494449732542435e-06, + "loss": 0.3303, + "step": 2657 + }, + { + "epoch": 0.34, + "learning_rate": 9.493995473757558e-06, + "loss": 0.3315, + "step": 2658 + }, + { + "epoch": 0.34, + "learning_rate": 9.493541021855685e-06, + "loss": 0.3459, + "step": 2659 + }, + { + "epoch": 0.34, + "learning_rate": 9.493086376856346e-06, + "loss": 0.3442, + "step": 2660 + }, + { + "epoch": 0.34, + "learning_rate": 9.492631538779082e-06, + "loss": 0.344, + "step": 2661 + }, + { + "epoch": 0.34, + "learning_rate": 9.492176507643433e-06, + "loss": 0.3284, + "step": 2662 + }, + { + "epoch": 0.34, + "learning_rate": 9.491721283468954e-06, + "loss": 0.3423, + "step": 2663 + }, + { + "epoch": 0.34, + "learning_rate": 9.49126586627521e-06, + "loss": 0.3445, + "step": 2664 + }, + { + "epoch": 0.34, + "learning_rate": 9.490810256081766e-06, + "loss": 0.3237, + "step": 2665 + }, + { + "epoch": 0.34, + "learning_rate": 9.490354452908208e-06, + "loss": 0.3281, + "step": 2666 + }, + { + "epoch": 0.34, + "learning_rate": 9.489898456774116e-06, + "loss": 0.3376, + "step": 2667 + }, + { + "epoch": 0.34, + "learning_rate": 9.489442267699087e-06, + "loss": 0.317, + "step": 2668 + }, + { + "epoch": 0.34, + "learning_rate": 9.488985885702728e-06, + "loss": 0.3461, + "step": 2669 + }, + { + "epoch": 0.34, + "learning_rate": 9.488529310804645e-06, + "loss": 0.3681, + "step": 2670 + }, + { + "epoch": 0.34, + "learning_rate": 9.488072543024462e-06, + "loss": 0.3567, + "step": 2671 + }, + { + "epoch": 0.34, + "learning_rate": 9.487615582381809e-06, + "loss": 0.3406, + "step": 2672 + }, + { + "epoch": 0.34, + "learning_rate": 9.487158428896317e-06, + "loss": 0.3473, + "step": 2673 + }, + { + "epoch": 0.34, + "learning_rate": 9.486701082587635e-06, + "loss": 0.3095, + "step": 2674 + }, + { + "epoch": 0.34, + "learning_rate": 9.486243543475414e-06, + "loss": 0.3497, + "step": 2675 + }, + { + "epoch": 0.34, + "learning_rate": 9.485785811579318e-06, + "loss": 0.3461, + "step": 2676 + }, + { + "epoch": 0.34, + "learning_rate": 9.485327886919013e-06, + "loss": 0.3223, + "step": 2677 + }, + { + "epoch": 0.34, + "learning_rate": 9.484869769514182e-06, + "loss": 0.313, + "step": 2678 + }, + { + "epoch": 0.34, + "learning_rate": 9.484411459384508e-06, + "loss": 0.3278, + "step": 2679 + }, + { + "epoch": 0.34, + "learning_rate": 9.483952956549684e-06, + "loss": 0.3496, + "step": 2680 + }, + { + "epoch": 0.34, + "learning_rate": 9.483494261029418e-06, + "loss": 0.3679, + "step": 2681 + }, + { + "epoch": 0.34, + "learning_rate": 9.483035372843417e-06, + "loss": 0.3528, + "step": 2682 + }, + { + "epoch": 0.34, + "learning_rate": 9.482576292011402e-06, + "loss": 0.3386, + "step": 2683 + }, + { + "epoch": 0.34, + "learning_rate": 9.482117018553101e-06, + "loss": 0.3775, + "step": 2684 + }, + { + "epoch": 0.34, + "learning_rate": 9.481657552488248e-06, + "loss": 0.3122, + "step": 2685 + }, + { + "epoch": 0.34, + "learning_rate": 9.481197893836591e-06, + "loss": 0.3562, + "step": 2686 + }, + { + "epoch": 0.34, + "learning_rate": 9.480738042617878e-06, + "loss": 0.3442, + "step": 2687 + }, + { + "epoch": 0.34, + "learning_rate": 9.480277998851875e-06, + "loss": 0.3077, + "step": 2688 + }, + { + "epoch": 0.34, + "learning_rate": 9.479817762558345e-06, + "loss": 0.3379, + "step": 2689 + }, + { + "epoch": 0.34, + "learning_rate": 9.479357333757072e-06, + "loss": 0.3451, + "step": 2690 + }, + { + "epoch": 0.34, + "learning_rate": 9.478896712467836e-06, + "loss": 0.3469, + "step": 2691 + }, + { + "epoch": 0.34, + "learning_rate": 9.478435898710434e-06, + "loss": 0.3165, + "step": 2692 + }, + { + "epoch": 0.34, + "learning_rate": 9.477974892504666e-06, + "loss": 0.3526, + "step": 2693 + }, + { + "epoch": 0.34, + "learning_rate": 9.477513693870347e-06, + "loss": 0.3192, + "step": 2694 + }, + { + "epoch": 0.34, + "learning_rate": 9.47705230282729e-06, + "loss": 0.3479, + "step": 2695 + }, + { + "epoch": 0.35, + "learning_rate": 9.476590719395324e-06, + "loss": 0.3258, + "step": 2696 + }, + { + "epoch": 0.35, + "learning_rate": 9.476128943594287e-06, + "loss": 0.3646, + "step": 2697 + }, + { + "epoch": 0.35, + "learning_rate": 9.47566697544402e-06, + "loss": 0.338, + "step": 2698 + }, + { + "epoch": 0.35, + "learning_rate": 9.475204814964374e-06, + "loss": 0.3082, + "step": 2699 + }, + { + "epoch": 0.35, + "learning_rate": 9.474742462175212e-06, + "loss": 0.3446, + "step": 2700 + }, + { + "epoch": 0.35, + "learning_rate": 9.4742799170964e-06, + "loss": 0.3342, + "step": 2701 + }, + { + "epoch": 0.35, + "learning_rate": 9.473817179747815e-06, + "loss": 0.3334, + "step": 2702 + }, + { + "epoch": 0.35, + "learning_rate": 9.473354250149342e-06, + "loss": 0.3605, + "step": 2703 + }, + { + "epoch": 0.35, + "learning_rate": 9.472891128320874e-06, + "loss": 0.3627, + "step": 2704 + }, + { + "epoch": 0.35, + "learning_rate": 9.472427814282311e-06, + "loss": 0.3647, + "step": 2705 + }, + { + "epoch": 0.35, + "learning_rate": 9.471964308053567e-06, + "loss": 0.3599, + "step": 2706 + }, + { + "epoch": 0.35, + "learning_rate": 9.471500609654556e-06, + "loss": 0.3318, + "step": 2707 + }, + { + "epoch": 0.35, + "learning_rate": 9.471036719105205e-06, + "loss": 0.35, + "step": 2708 + }, + { + "epoch": 0.35, + "learning_rate": 9.470572636425451e-06, + "loss": 0.352, + "step": 2709 + }, + { + "epoch": 0.35, + "learning_rate": 9.470108361635231e-06, + "loss": 0.3265, + "step": 2710 + }, + { + "epoch": 0.35, + "learning_rate": 9.469643894754502e-06, + "loss": 0.3079, + "step": 2711 + }, + { + "epoch": 0.35, + "learning_rate": 9.469179235803217e-06, + "loss": 0.3637, + "step": 2712 + }, + { + "epoch": 0.35, + "learning_rate": 9.46871438480135e-06, + "loss": 0.3565, + "step": 2713 + }, + { + "epoch": 0.35, + "learning_rate": 9.46824934176887e-06, + "loss": 0.3051, + "step": 2714 + }, + { + "epoch": 0.35, + "learning_rate": 9.467784106725767e-06, + "loss": 0.3487, + "step": 2715 + }, + { + "epoch": 0.35, + "learning_rate": 9.467318679692031e-06, + "loss": 0.317, + "step": 2716 + }, + { + "epoch": 0.35, + "learning_rate": 9.466853060687662e-06, + "loss": 0.3263, + "step": 2717 + }, + { + "epoch": 0.35, + "learning_rate": 9.466387249732668e-06, + "loss": 0.3755, + "step": 2718 + }, + { + "epoch": 0.35, + "learning_rate": 9.465921246847067e-06, + "loss": 0.3359, + "step": 2719 + }, + { + "epoch": 0.35, + "learning_rate": 9.465455052050884e-06, + "loss": 0.3493, + "step": 2720 + }, + { + "epoch": 0.35, + "learning_rate": 9.464988665364152e-06, + "loss": 0.3172, + "step": 2721 + }, + { + "epoch": 0.35, + "learning_rate": 9.464522086806914e-06, + "loss": 0.3179, + "step": 2722 + }, + { + "epoch": 0.35, + "learning_rate": 9.464055316399217e-06, + "loss": 0.3553, + "step": 2723 + }, + { + "epoch": 0.35, + "learning_rate": 9.463588354161122e-06, + "loss": 0.3347, + "step": 2724 + }, + { + "epoch": 0.35, + "learning_rate": 9.463121200112694e-06, + "loss": 0.3329, + "step": 2725 + }, + { + "epoch": 0.35, + "learning_rate": 9.462653854274008e-06, + "loss": 0.3555, + "step": 2726 + }, + { + "epoch": 0.35, + "learning_rate": 9.462186316665148e-06, + "loss": 0.3324, + "step": 2727 + }, + { + "epoch": 0.35, + "learning_rate": 9.461718587306205e-06, + "loss": 0.3446, + "step": 2728 + }, + { + "epoch": 0.35, + "learning_rate": 9.461250666217277e-06, + "loss": 0.3429, + "step": 2729 + }, + { + "epoch": 0.35, + "learning_rate": 9.46078255341847e-06, + "loss": 0.3351, + "step": 2730 + }, + { + "epoch": 0.35, + "learning_rate": 9.460314248929903e-06, + "loss": 0.3306, + "step": 2731 + }, + { + "epoch": 0.35, + "learning_rate": 9.4598457527717e-06, + "loss": 0.3457, + "step": 2732 + }, + { + "epoch": 0.35, + "learning_rate": 9.459377064963993e-06, + "loss": 0.3909, + "step": 2733 + }, + { + "epoch": 0.35, + "learning_rate": 9.458908185526921e-06, + "loss": 0.3393, + "step": 2734 + }, + { + "epoch": 0.35, + "learning_rate": 9.458439114480634e-06, + "loss": 0.3234, + "step": 2735 + }, + { + "epoch": 0.35, + "learning_rate": 9.457969851845287e-06, + "loss": 0.3538, + "step": 2736 + }, + { + "epoch": 0.35, + "learning_rate": 9.457500397641049e-06, + "loss": 0.324, + "step": 2737 + }, + { + "epoch": 0.35, + "learning_rate": 9.45703075188809e-06, + "loss": 0.3127, + "step": 2738 + }, + { + "epoch": 0.35, + "learning_rate": 9.456560914606594e-06, + "loss": 0.3252, + "step": 2739 + }, + { + "epoch": 0.35, + "learning_rate": 9.456090885816751e-06, + "loss": 0.3497, + "step": 2740 + }, + { + "epoch": 0.35, + "learning_rate": 9.455620665538758e-06, + "loss": 0.3306, + "step": 2741 + }, + { + "epoch": 0.35, + "learning_rate": 9.455150253792822e-06, + "loss": 0.3382, + "step": 2742 + }, + { + "epoch": 0.35, + "learning_rate": 9.454679650599156e-06, + "loss": 0.3458, + "step": 2743 + }, + { + "epoch": 0.35, + "learning_rate": 9.454208855977986e-06, + "loss": 0.3429, + "step": 2744 + }, + { + "epoch": 0.35, + "learning_rate": 9.45373786994954e-06, + "loss": 0.3446, + "step": 2745 + }, + { + "epoch": 0.35, + "learning_rate": 9.45326669253406e-06, + "loss": 0.3384, + "step": 2746 + }, + { + "epoch": 0.35, + "learning_rate": 9.452795323751793e-06, + "loss": 0.3589, + "step": 2747 + }, + { + "epoch": 0.35, + "learning_rate": 9.452323763622993e-06, + "loss": 0.3849, + "step": 2748 + }, + { + "epoch": 0.35, + "learning_rate": 9.451852012167924e-06, + "loss": 0.3415, + "step": 2749 + }, + { + "epoch": 0.35, + "learning_rate": 9.45138006940686e-06, + "loss": 0.3224, + "step": 2750 + }, + { + "epoch": 0.35, + "learning_rate": 9.450907935360081e-06, + "loss": 0.3403, + "step": 2751 + }, + { + "epoch": 0.35, + "learning_rate": 9.450435610047875e-06, + "loss": 0.3533, + "step": 2752 + }, + { + "epoch": 0.35, + "learning_rate": 9.44996309349054e-06, + "loss": 0.3427, + "step": 2753 + }, + { + "epoch": 0.35, + "learning_rate": 9.449490385708378e-06, + "loss": 0.3567, + "step": 2754 + }, + { + "epoch": 0.35, + "learning_rate": 9.449017486721705e-06, + "loss": 0.3265, + "step": 2755 + }, + { + "epoch": 0.35, + "learning_rate": 9.448544396550846e-06, + "loss": 0.3416, + "step": 2756 + }, + { + "epoch": 0.35, + "learning_rate": 9.448071115216123e-06, + "loss": 0.3356, + "step": 2757 + }, + { + "epoch": 0.35, + "learning_rate": 9.447597642737878e-06, + "loss": 0.3448, + "step": 2758 + }, + { + "epoch": 0.35, + "learning_rate": 9.447123979136457e-06, + "loss": 0.3206, + "step": 2759 + }, + { + "epoch": 0.35, + "learning_rate": 9.446650124432215e-06, + "loss": 0.3654, + "step": 2760 + }, + { + "epoch": 0.35, + "learning_rate": 9.446176078645515e-06, + "loss": 0.3404, + "step": 2761 + }, + { + "epoch": 0.35, + "learning_rate": 9.445701841796726e-06, + "loss": 0.3452, + "step": 2762 + }, + { + "epoch": 0.35, + "learning_rate": 9.445227413906227e-06, + "loss": 0.3416, + "step": 2763 + }, + { + "epoch": 0.35, + "learning_rate": 9.444752794994408e-06, + "loss": 0.3722, + "step": 2764 + }, + { + "epoch": 0.35, + "learning_rate": 9.44427798508166e-06, + "loss": 0.3554, + "step": 2765 + }, + { + "epoch": 0.35, + "learning_rate": 9.44380298418839e-06, + "loss": 0.3409, + "step": 2766 + }, + { + "epoch": 0.35, + "learning_rate": 9.443327792335009e-06, + "loss": 0.3566, + "step": 2767 + }, + { + "epoch": 0.35, + "learning_rate": 9.442852409541935e-06, + "loss": 0.356, + "step": 2768 + }, + { + "epoch": 0.35, + "learning_rate": 9.4423768358296e-06, + "loss": 0.3775, + "step": 2769 + }, + { + "epoch": 0.35, + "learning_rate": 9.44190107121844e-06, + "loss": 0.3169, + "step": 2770 + }, + { + "epoch": 0.35, + "learning_rate": 9.441425115728898e-06, + "loss": 0.3704, + "step": 2771 + }, + { + "epoch": 0.35, + "learning_rate": 9.440948969381425e-06, + "loss": 0.3574, + "step": 2772 + }, + { + "epoch": 0.35, + "learning_rate": 9.440472632196485e-06, + "loss": 0.3786, + "step": 2773 + }, + { + "epoch": 0.36, + "learning_rate": 9.439996104194546e-06, + "loss": 0.3566, + "step": 2774 + }, + { + "epoch": 0.36, + "learning_rate": 9.439519385396088e-06, + "loss": 0.3476, + "step": 2775 + }, + { + "epoch": 0.36, + "learning_rate": 9.439042475821594e-06, + "loss": 0.3346, + "step": 2776 + }, + { + "epoch": 0.36, + "learning_rate": 9.438565375491558e-06, + "loss": 0.3484, + "step": 2777 + }, + { + "epoch": 0.36, + "learning_rate": 9.438088084426482e-06, + "loss": 0.335, + "step": 2778 + }, + { + "epoch": 0.36, + "learning_rate": 9.437610602646878e-06, + "loss": 0.3187, + "step": 2779 + }, + { + "epoch": 0.36, + "learning_rate": 9.437132930173264e-06, + "loss": 0.3529, + "step": 2780 + }, + { + "epoch": 0.36, + "learning_rate": 9.436655067026164e-06, + "loss": 0.3246, + "step": 2781 + }, + { + "epoch": 0.36, + "learning_rate": 9.436177013226116e-06, + "loss": 0.3249, + "step": 2782 + }, + { + "epoch": 0.36, + "learning_rate": 9.43569876879366e-06, + "loss": 0.3581, + "step": 2783 + }, + { + "epoch": 0.36, + "learning_rate": 9.43522033374935e-06, + "loss": 0.3082, + "step": 2784 + }, + { + "epoch": 0.36, + "learning_rate": 9.434741708113745e-06, + "loss": 0.3088, + "step": 2785 + }, + { + "epoch": 0.36, + "learning_rate": 9.434262891907413e-06, + "loss": 0.3752, + "step": 2786 + }, + { + "epoch": 0.36, + "learning_rate": 9.433783885150929e-06, + "loss": 0.3188, + "step": 2787 + }, + { + "epoch": 0.36, + "learning_rate": 9.433304687864876e-06, + "loss": 0.3348, + "step": 2788 + }, + { + "epoch": 0.36, + "learning_rate": 9.432825300069848e-06, + "loss": 0.3177, + "step": 2789 + }, + { + "epoch": 0.36, + "learning_rate": 9.432345721786442e-06, + "loss": 0.3258, + "step": 2790 + }, + { + "epoch": 0.36, + "learning_rate": 9.431865953035271e-06, + "loss": 0.3413, + "step": 2791 + }, + { + "epoch": 0.36, + "learning_rate": 9.431385993836949e-06, + "loss": 0.3485, + "step": 2792 + }, + { + "epoch": 0.36, + "learning_rate": 9.430905844212102e-06, + "loss": 0.3198, + "step": 2793 + }, + { + "epoch": 0.36, + "learning_rate": 9.430425504181361e-06, + "loss": 0.3392, + "step": 2794 + }, + { + "epoch": 0.36, + "learning_rate": 9.429944973765373e-06, + "loss": 0.3653, + "step": 2795 + }, + { + "epoch": 0.36, + "learning_rate": 9.429464252984779e-06, + "loss": 0.3247, + "step": 2796 + }, + { + "epoch": 0.36, + "learning_rate": 9.428983341860244e-06, + "loss": 0.3631, + "step": 2797 + }, + { + "epoch": 0.36, + "learning_rate": 9.42850224041243e-06, + "loss": 0.3333, + "step": 2798 + }, + { + "epoch": 0.36, + "learning_rate": 9.428020948662012e-06, + "loss": 0.3711, + "step": 2799 + }, + { + "epoch": 0.36, + "learning_rate": 9.427539466629672e-06, + "loss": 0.3187, + "step": 2800 + }, + { + "epoch": 0.36, + "learning_rate": 9.427057794336101e-06, + "loss": 0.3315, + "step": 2801 + }, + { + "epoch": 0.36, + "learning_rate": 9.426575931801996e-06, + "loss": 0.3733, + "step": 2802 + }, + { + "epoch": 0.36, + "learning_rate": 9.426093879048065e-06, + "loss": 0.3649, + "step": 2803 + }, + { + "epoch": 0.36, + "learning_rate": 9.425611636095023e-06, + "loss": 0.3118, + "step": 2804 + }, + { + "epoch": 0.36, + "learning_rate": 9.425129202963592e-06, + "loss": 0.3116, + "step": 2805 + }, + { + "epoch": 0.36, + "learning_rate": 9.424646579674504e-06, + "loss": 0.339, + "step": 2806 + }, + { + "epoch": 0.36, + "learning_rate": 9.424163766248499e-06, + "loss": 0.3668, + "step": 2807 + }, + { + "epoch": 0.36, + "learning_rate": 9.423680762706323e-06, + "loss": 0.3398, + "step": 2808 + }, + { + "epoch": 0.36, + "learning_rate": 9.423197569068733e-06, + "loss": 0.3278, + "step": 2809 + }, + { + "epoch": 0.36, + "learning_rate": 9.422714185356491e-06, + "loss": 0.3347, + "step": 2810 + }, + { + "epoch": 0.36, + "learning_rate": 9.422230611590373e-06, + "loss": 0.3307, + "step": 2811 + }, + { + "epoch": 0.36, + "learning_rate": 9.421746847791156e-06, + "loss": 0.3816, + "step": 2812 + }, + { + "epoch": 0.36, + "learning_rate": 9.421262893979628e-06, + "loss": 0.3595, + "step": 2813 + }, + { + "epoch": 0.36, + "learning_rate": 9.420778750176588e-06, + "loss": 0.3736, + "step": 2814 + }, + { + "epoch": 0.36, + "learning_rate": 9.420294416402839e-06, + "loss": 0.3462, + "step": 2815 + }, + { + "epoch": 0.36, + "learning_rate": 9.419809892679194e-06, + "loss": 0.362, + "step": 2816 + }, + { + "epoch": 0.36, + "learning_rate": 9.419325179026475e-06, + "loss": 0.3633, + "step": 2817 + }, + { + "epoch": 0.36, + "learning_rate": 9.41884027546551e-06, + "loss": 0.3404, + "step": 2818 + }, + { + "epoch": 0.36, + "learning_rate": 9.418355182017138e-06, + "loss": 0.3307, + "step": 2819 + }, + { + "epoch": 0.36, + "learning_rate": 9.417869898702205e-06, + "loss": 0.3342, + "step": 2820 + }, + { + "epoch": 0.36, + "learning_rate": 9.41738442554156e-06, + "loss": 0.358, + "step": 2821 + }, + { + "epoch": 0.36, + "learning_rate": 9.41689876255607e-06, + "loss": 0.3759, + "step": 2822 + }, + { + "epoch": 0.36, + "learning_rate": 9.416412909766604e-06, + "loss": 0.3643, + "step": 2823 + }, + { + "epoch": 0.36, + "learning_rate": 9.41592686719404e-06, + "loss": 0.3142, + "step": 2824 + }, + { + "epoch": 0.36, + "learning_rate": 9.41544063485926e-06, + "loss": 0.3532, + "step": 2825 + }, + { + "epoch": 0.36, + "learning_rate": 9.414954212783165e-06, + "loss": 0.3875, + "step": 2826 + }, + { + "epoch": 0.36, + "learning_rate": 9.414467600986655e-06, + "loss": 0.3684, + "step": 2827 + }, + { + "epoch": 0.36, + "learning_rate": 9.41398079949064e-06, + "loss": 0.3416, + "step": 2828 + }, + { + "epoch": 0.36, + "learning_rate": 9.413493808316038e-06, + "loss": 0.3481, + "step": 2829 + }, + { + "epoch": 0.36, + "learning_rate": 9.41300662748378e-06, + "loss": 0.3538, + "step": 2830 + }, + { + "epoch": 0.36, + "learning_rate": 9.412519257014798e-06, + "loss": 0.3512, + "step": 2831 + }, + { + "epoch": 0.36, + "learning_rate": 9.412031696930036e-06, + "loss": 0.3367, + "step": 2832 + }, + { + "epoch": 0.36, + "learning_rate": 9.411543947250447e-06, + "loss": 0.3565, + "step": 2833 + }, + { + "epoch": 0.36, + "learning_rate": 9.411056007996989e-06, + "loss": 0.3044, + "step": 2834 + }, + { + "epoch": 0.36, + "learning_rate": 9.41056787919063e-06, + "loss": 0.3703, + "step": 2835 + }, + { + "epoch": 0.36, + "learning_rate": 9.410079560852347e-06, + "loss": 0.3759, + "step": 2836 + }, + { + "epoch": 0.36, + "learning_rate": 9.409591053003121e-06, + "loss": 0.3459, + "step": 2837 + }, + { + "epoch": 0.36, + "learning_rate": 9.40910235566395e-06, + "loss": 0.3214, + "step": 2838 + }, + { + "epoch": 0.36, + "learning_rate": 9.408613468855829e-06, + "loss": 0.3513, + "step": 2839 + }, + { + "epoch": 0.36, + "learning_rate": 9.40812439259977e-06, + "loss": 0.3569, + "step": 2840 + }, + { + "epoch": 0.36, + "learning_rate": 9.40763512691679e-06, + "loss": 0.3596, + "step": 2841 + }, + { + "epoch": 0.36, + "learning_rate": 9.407145671827909e-06, + "loss": 0.3238, + "step": 2842 + }, + { + "epoch": 0.36, + "learning_rate": 9.406656027354166e-06, + "loss": 0.3052, + "step": 2843 + }, + { + "epoch": 0.36, + "learning_rate": 9.406166193516596e-06, + "loss": 0.3324, + "step": 2844 + }, + { + "epoch": 0.36, + "learning_rate": 9.405676170336255e-06, + "loss": 0.3343, + "step": 2845 + }, + { + "epoch": 0.36, + "learning_rate": 9.405185957834196e-06, + "loss": 0.3397, + "step": 2846 + }, + { + "epoch": 0.36, + "learning_rate": 9.404695556031485e-06, + "loss": 0.3274, + "step": 2847 + }, + { + "epoch": 0.36, + "learning_rate": 9.404204964949196e-06, + "loss": 0.3206, + "step": 2848 + }, + { + "epoch": 0.36, + "learning_rate": 9.403714184608411e-06, + "loss": 0.3896, + "step": 2849 + }, + { + "epoch": 0.36, + "learning_rate": 9.403223215030221e-06, + "loss": 0.3237, + "step": 2850 + }, + { + "epoch": 0.36, + "learning_rate": 9.402732056235722e-06, + "loss": 0.3413, + "step": 2851 + }, + { + "epoch": 0.37, + "learning_rate": 9.402240708246022e-06, + "loss": 0.3442, + "step": 2852 + }, + { + "epoch": 0.37, + "learning_rate": 9.401749171082233e-06, + "loss": 0.3282, + "step": 2853 + }, + { + "epoch": 0.37, + "learning_rate": 9.40125744476548e-06, + "loss": 0.3351, + "step": 2854 + }, + { + "epoch": 0.37, + "learning_rate": 9.400765529316892e-06, + "loss": 0.3226, + "step": 2855 + }, + { + "epoch": 0.37, + "learning_rate": 9.400273424757607e-06, + "loss": 0.3138, + "step": 2856 + }, + { + "epoch": 0.37, + "learning_rate": 9.399781131108775e-06, + "loss": 0.3093, + "step": 2857 + }, + { + "epoch": 0.37, + "learning_rate": 9.399288648391548e-06, + "loss": 0.3493, + "step": 2858 + }, + { + "epoch": 0.37, + "learning_rate": 9.398795976627091e-06, + "loss": 0.3267, + "step": 2859 + }, + { + "epoch": 0.37, + "learning_rate": 9.398303115836573e-06, + "loss": 0.3537, + "step": 2860 + }, + { + "epoch": 0.37, + "learning_rate": 9.397810066041176e-06, + "loss": 0.3546, + "step": 2861 + }, + { + "epoch": 0.37, + "learning_rate": 9.397316827262085e-06, + "loss": 0.3238, + "step": 2862 + }, + { + "epoch": 0.37, + "learning_rate": 9.396823399520495e-06, + "loss": 0.3454, + "step": 2863 + }, + { + "epoch": 0.37, + "learning_rate": 9.396329782837614e-06, + "loss": 0.3439, + "step": 2864 + }, + { + "epoch": 0.37, + "learning_rate": 9.39583597723465e-06, + "loss": 0.3481, + "step": 2865 + }, + { + "epoch": 0.37, + "learning_rate": 9.395341982732825e-06, + "loss": 0.3321, + "step": 2866 + }, + { + "epoch": 0.37, + "learning_rate": 9.394847799353363e-06, + "loss": 0.3214, + "step": 2867 + }, + { + "epoch": 0.37, + "learning_rate": 9.394353427117506e-06, + "loss": 0.339, + "step": 2868 + }, + { + "epoch": 0.37, + "learning_rate": 9.393858866046494e-06, + "loss": 0.3226, + "step": 2869 + }, + { + "epoch": 0.37, + "learning_rate": 9.393364116161582e-06, + "loss": 0.3716, + "step": 2870 + }, + { + "epoch": 0.37, + "learning_rate": 9.392869177484029e-06, + "loss": 0.3247, + "step": 2871 + }, + { + "epoch": 0.37, + "learning_rate": 9.392374050035104e-06, + "loss": 0.3467, + "step": 2872 + }, + { + "epoch": 0.37, + "learning_rate": 9.391878733836085e-06, + "loss": 0.3283, + "step": 2873 + }, + { + "epoch": 0.37, + "learning_rate": 9.391383228908253e-06, + "loss": 0.3529, + "step": 2874 + }, + { + "epoch": 0.37, + "learning_rate": 9.390887535272906e-06, + "loss": 0.3243, + "step": 2875 + }, + { + "epoch": 0.37, + "learning_rate": 9.39039165295134e-06, + "loss": 0.3192, + "step": 2876 + }, + { + "epoch": 0.37, + "learning_rate": 9.38989558196487e-06, + "loss": 0.341, + "step": 2877 + }, + { + "epoch": 0.37, + "learning_rate": 9.389399322334806e-06, + "loss": 0.3499, + "step": 2878 + }, + { + "epoch": 0.37, + "learning_rate": 9.388902874082482e-06, + "loss": 0.3274, + "step": 2879 + }, + { + "epoch": 0.37, + "learning_rate": 9.388406237229223e-06, + "loss": 0.3594, + "step": 2880 + }, + { + "epoch": 0.37, + "learning_rate": 9.387909411796377e-06, + "loss": 0.3196, + "step": 2881 + }, + { + "epoch": 0.37, + "learning_rate": 9.387412397805289e-06, + "loss": 0.3795, + "step": 2882 + }, + { + "epoch": 0.37, + "learning_rate": 9.386915195277321e-06, + "loss": 0.3465, + "step": 2883 + }, + { + "epoch": 0.37, + "learning_rate": 9.386417804233836e-06, + "loss": 0.3286, + "step": 2884 + }, + { + "epoch": 0.37, + "learning_rate": 9.385920224696208e-06, + "loss": 0.3087, + "step": 2885 + }, + { + "epoch": 0.37, + "learning_rate": 9.385422456685822e-06, + "loss": 0.3949, + "step": 2886 + }, + { + "epoch": 0.37, + "learning_rate": 9.384924500224065e-06, + "loss": 0.3289, + "step": 2887 + }, + { + "epoch": 0.37, + "learning_rate": 9.384426355332336e-06, + "loss": 0.3517, + "step": 2888 + }, + { + "epoch": 0.37, + "learning_rate": 9.383928022032044e-06, + "loss": 0.3606, + "step": 2889 + }, + { + "epoch": 0.37, + "learning_rate": 9.383429500344598e-06, + "loss": 0.3258, + "step": 2890 + }, + { + "epoch": 0.37, + "learning_rate": 9.382930790291426e-06, + "loss": 0.3245, + "step": 2891 + }, + { + "epoch": 0.37, + "learning_rate": 9.382431891893957e-06, + "loss": 0.3026, + "step": 2892 + }, + { + "epoch": 0.37, + "learning_rate": 9.381932805173628e-06, + "loss": 0.3193, + "step": 2893 + }, + { + "epoch": 0.37, + "learning_rate": 9.381433530151887e-06, + "loss": 0.3398, + "step": 2894 + }, + { + "epoch": 0.37, + "learning_rate": 9.380934066850191e-06, + "loss": 0.329, + "step": 2895 + }, + { + "epoch": 0.37, + "learning_rate": 9.38043441529e-06, + "loss": 0.3457, + "step": 2896 + }, + { + "epoch": 0.37, + "learning_rate": 9.379934575492788e-06, + "loss": 0.3281, + "step": 2897 + }, + { + "epoch": 0.37, + "learning_rate": 9.37943454748003e-06, + "loss": 0.339, + "step": 2898 + }, + { + "epoch": 0.37, + "learning_rate": 9.37893433127322e-06, + "loss": 0.346, + "step": 2899 + }, + { + "epoch": 0.37, + "learning_rate": 9.378433926893845e-06, + "loss": 0.3537, + "step": 2900 + }, + { + "epoch": 0.37, + "learning_rate": 9.377933334363416e-06, + "loss": 0.3401, + "step": 2901 + }, + { + "epoch": 0.37, + "learning_rate": 9.377432553703439e-06, + "loss": 0.3411, + "step": 2902 + }, + { + "epoch": 0.37, + "learning_rate": 9.376931584935439e-06, + "loss": 0.3452, + "step": 2903 + }, + { + "epoch": 0.37, + "learning_rate": 9.376430428080939e-06, + "loss": 0.3252, + "step": 2904 + }, + { + "epoch": 0.37, + "learning_rate": 9.375929083161475e-06, + "loss": 0.34, + "step": 2905 + }, + { + "epoch": 0.37, + "learning_rate": 9.375427550198595e-06, + "loss": 0.3768, + "step": 2906 + }, + { + "epoch": 0.37, + "learning_rate": 9.374925829213848e-06, + "loss": 0.3351, + "step": 2907 + }, + { + "epoch": 0.37, + "learning_rate": 9.374423920228795e-06, + "loss": 0.3439, + "step": 2908 + }, + { + "epoch": 0.37, + "learning_rate": 9.373921823265004e-06, + "loss": 0.3413, + "step": 2909 + }, + { + "epoch": 0.37, + "learning_rate": 9.373419538344049e-06, + "loss": 0.3586, + "step": 2910 + }, + { + "epoch": 0.37, + "learning_rate": 9.372917065487518e-06, + "loss": 0.3438, + "step": 2911 + }, + { + "epoch": 0.37, + "learning_rate": 9.372414404717001e-06, + "loss": 0.3451, + "step": 2912 + }, + { + "epoch": 0.37, + "learning_rate": 9.3719115560541e-06, + "loss": 0.3439, + "step": 2913 + }, + { + "epoch": 0.37, + "learning_rate": 9.371408519520421e-06, + "loss": 0.3339, + "step": 2914 + }, + { + "epoch": 0.37, + "learning_rate": 9.370905295137584e-06, + "loss": 0.3412, + "step": 2915 + }, + { + "epoch": 0.37, + "learning_rate": 9.370401882927212e-06, + "loss": 0.3386, + "step": 2916 + }, + { + "epoch": 0.37, + "learning_rate": 9.369898282910937e-06, + "loss": 0.3474, + "step": 2917 + }, + { + "epoch": 0.37, + "learning_rate": 9.369394495110401e-06, + "loss": 0.3351, + "step": 2918 + }, + { + "epoch": 0.37, + "learning_rate": 9.36889051954725e-06, + "loss": 0.3668, + "step": 2919 + }, + { + "epoch": 0.37, + "learning_rate": 9.368386356243148e-06, + "loss": 0.3296, + "step": 2920 + }, + { + "epoch": 0.37, + "learning_rate": 9.367882005219752e-06, + "loss": 0.3472, + "step": 2921 + }, + { + "epoch": 0.37, + "learning_rate": 9.367377466498739e-06, + "loss": 0.3613, + "step": 2922 + }, + { + "epoch": 0.37, + "learning_rate": 9.36687274010179e-06, + "loss": 0.3421, + "step": 2923 + }, + { + "epoch": 0.37, + "learning_rate": 9.366367826050593e-06, + "loss": 0.3266, + "step": 2924 + }, + { + "epoch": 0.37, + "learning_rate": 9.365862724366848e-06, + "loss": 0.3182, + "step": 2925 + }, + { + "epoch": 0.37, + "learning_rate": 9.365357435072255e-06, + "loss": 0.3549, + "step": 2926 + }, + { + "epoch": 0.37, + "learning_rate": 9.364851958188534e-06, + "loss": 0.3523, + "step": 2927 + }, + { + "epoch": 0.37, + "learning_rate": 9.364346293737403e-06, + "loss": 0.3453, + "step": 2928 + }, + { + "epoch": 0.37, + "learning_rate": 9.36384044174059e-06, + "loss": 0.3468, + "step": 2929 + }, + { + "epoch": 0.38, + "learning_rate": 9.363334402219836e-06, + "loss": 0.3347, + "step": 2930 + }, + { + "epoch": 0.38, + "learning_rate": 9.362828175196884e-06, + "loss": 0.3246, + "step": 2931 + }, + { + "epoch": 0.38, + "learning_rate": 9.362321760693489e-06, + "loss": 0.3436, + "step": 2932 + }, + { + "epoch": 0.38, + "learning_rate": 9.361815158731413e-06, + "loss": 0.3281, + "step": 2933 + }, + { + "epoch": 0.38, + "learning_rate": 9.361308369332426e-06, + "loss": 0.3544, + "step": 2934 + }, + { + "epoch": 0.38, + "learning_rate": 9.360801392518303e-06, + "loss": 0.3193, + "step": 2935 + }, + { + "epoch": 0.38, + "learning_rate": 9.360294228310834e-06, + "loss": 0.3421, + "step": 2936 + }, + { + "epoch": 0.38, + "learning_rate": 9.359786876731811e-06, + "loss": 0.3441, + "step": 2937 + }, + { + "epoch": 0.38, + "learning_rate": 9.359279337803036e-06, + "loss": 0.3207, + "step": 2938 + }, + { + "epoch": 0.38, + "learning_rate": 9.358771611546319e-06, + "loss": 0.3167, + "step": 2939 + }, + { + "epoch": 0.38, + "learning_rate": 9.358263697983479e-06, + "loss": 0.3511, + "step": 2940 + }, + { + "epoch": 0.38, + "learning_rate": 9.35775559713634e-06, + "loss": 0.3393, + "step": 2941 + }, + { + "epoch": 0.38, + "learning_rate": 9.357247309026738e-06, + "loss": 0.3406, + "step": 2942 + }, + { + "epoch": 0.38, + "learning_rate": 9.356738833676517e-06, + "loss": 0.3445, + "step": 2943 + }, + { + "epoch": 0.38, + "learning_rate": 9.356230171107524e-06, + "loss": 0.356, + "step": 2944 + }, + { + "epoch": 0.38, + "learning_rate": 9.355721321341618e-06, + "loss": 0.3327, + "step": 2945 + }, + { + "epoch": 0.38, + "learning_rate": 9.355212284400668e-06, + "loss": 0.3395, + "step": 2946 + }, + { + "epoch": 0.38, + "learning_rate": 9.354703060306546e-06, + "loss": 0.2982, + "step": 2947 + }, + { + "epoch": 0.38, + "learning_rate": 9.354193649081134e-06, + "loss": 0.3574, + "step": 2948 + }, + { + "epoch": 0.38, + "learning_rate": 9.353684050746323e-06, + "loss": 0.317, + "step": 2949 + }, + { + "epoch": 0.38, + "learning_rate": 9.353174265324014e-06, + "loss": 0.3294, + "step": 2950 + }, + { + "epoch": 0.38, + "learning_rate": 9.35266429283611e-06, + "loss": 0.3228, + "step": 2951 + }, + { + "epoch": 0.38, + "learning_rate": 9.352154133304528e-06, + "loss": 0.3115, + "step": 2952 + }, + { + "epoch": 0.38, + "learning_rate": 9.351643786751191e-06, + "loss": 0.3567, + "step": 2953 + }, + { + "epoch": 0.38, + "learning_rate": 9.351133253198027e-06, + "loss": 0.3773, + "step": 2954 + }, + { + "epoch": 0.38, + "learning_rate": 9.350622532666979e-06, + "loss": 0.3406, + "step": 2955 + }, + { + "epoch": 0.38, + "learning_rate": 9.350111625179991e-06, + "loss": 0.3587, + "step": 2956 + }, + { + "epoch": 0.38, + "learning_rate": 9.349600530759018e-06, + "loss": 0.3525, + "step": 2957 + }, + { + "epoch": 0.38, + "learning_rate": 9.349089249426022e-06, + "loss": 0.3937, + "step": 2958 + }, + { + "epoch": 0.38, + "learning_rate": 9.348577781202976e-06, + "loss": 0.3447, + "step": 2959 + }, + { + "epoch": 0.38, + "learning_rate": 9.348066126111857e-06, + "loss": 0.3418, + "step": 2960 + }, + { + "epoch": 0.38, + "learning_rate": 9.347554284174654e-06, + "loss": 0.3334, + "step": 2961 + }, + { + "epoch": 0.38, + "learning_rate": 9.347042255413362e-06, + "loss": 0.31, + "step": 2962 + }, + { + "epoch": 0.38, + "learning_rate": 9.34653003984998e-06, + "loss": 0.3364, + "step": 2963 + }, + { + "epoch": 0.38, + "learning_rate": 9.346017637506523e-06, + "loss": 0.2946, + "step": 2964 + }, + { + "epoch": 0.38, + "learning_rate": 9.34550504840501e-06, + "loss": 0.3259, + "step": 2965 + }, + { + "epoch": 0.38, + "learning_rate": 9.344992272567467e-06, + "loss": 0.3278, + "step": 2966 + }, + { + "epoch": 0.38, + "learning_rate": 9.344479310015928e-06, + "loss": 0.3426, + "step": 2967 + }, + { + "epoch": 0.38, + "learning_rate": 9.343966160772438e-06, + "loss": 0.3309, + "step": 2968 + }, + { + "epoch": 0.38, + "learning_rate": 9.343452824859048e-06, + "loss": 0.3479, + "step": 2969 + }, + { + "epoch": 0.38, + "learning_rate": 9.342939302297816e-06, + "loss": 0.3038, + "step": 2970 + }, + { + "epoch": 0.38, + "learning_rate": 9.34242559311081e-06, + "loss": 0.3465, + "step": 2971 + }, + { + "epoch": 0.38, + "learning_rate": 9.341911697320105e-06, + "loss": 0.308, + "step": 2972 + }, + { + "epoch": 0.38, + "learning_rate": 9.341397614947785e-06, + "loss": 0.3252, + "step": 2973 + }, + { + "epoch": 0.38, + "learning_rate": 9.340883346015941e-06, + "loss": 0.3347, + "step": 2974 + }, + { + "epoch": 0.38, + "learning_rate": 9.340368890546672e-06, + "loss": 0.3517, + "step": 2975 + }, + { + "epoch": 0.38, + "learning_rate": 9.339854248562084e-06, + "loss": 0.3555, + "step": 2976 + }, + { + "epoch": 0.38, + "learning_rate": 9.339339420084295e-06, + "loss": 0.3407, + "step": 2977 + }, + { + "epoch": 0.38, + "learning_rate": 9.338824405135425e-06, + "loss": 0.3329, + "step": 2978 + }, + { + "epoch": 0.38, + "learning_rate": 9.338309203737609e-06, + "loss": 0.3714, + "step": 2979 + }, + { + "epoch": 0.38, + "learning_rate": 9.337793815912984e-06, + "loss": 0.3434, + "step": 2980 + }, + { + "epoch": 0.38, + "learning_rate": 9.337278241683698e-06, + "loss": 0.3459, + "step": 2981 + }, + { + "epoch": 0.38, + "learning_rate": 9.336762481071906e-06, + "loss": 0.3213, + "step": 2982 + }, + { + "epoch": 0.38, + "learning_rate": 9.336246534099772e-06, + "loss": 0.3536, + "step": 2983 + }, + { + "epoch": 0.38, + "learning_rate": 9.335730400789466e-06, + "loss": 0.3206, + "step": 2984 + }, + { + "epoch": 0.38, + "learning_rate": 9.335214081163171e-06, + "loss": 0.3491, + "step": 2985 + }, + { + "epoch": 0.38, + "learning_rate": 9.33469757524307e-06, + "loss": 0.3577, + "step": 2986 + }, + { + "epoch": 0.38, + "learning_rate": 9.33418088305136e-06, + "loss": 0.3329, + "step": 2987 + }, + { + "epoch": 0.38, + "learning_rate": 9.333664004610246e-06, + "loss": 0.3205, + "step": 2988 + }, + { + "epoch": 0.38, + "learning_rate": 9.333146939941938e-06, + "loss": 0.3517, + "step": 2989 + }, + { + "epoch": 0.38, + "learning_rate": 9.332629689068655e-06, + "loss": 0.3576, + "step": 2990 + }, + { + "epoch": 0.38, + "learning_rate": 9.332112252012625e-06, + "loss": 0.3508, + "step": 2991 + }, + { + "epoch": 0.38, + "learning_rate": 9.331594628796083e-06, + "loss": 0.3382, + "step": 2992 + }, + { + "epoch": 0.38, + "learning_rate": 9.331076819441273e-06, + "loss": 0.3415, + "step": 2993 + }, + { + "epoch": 0.38, + "learning_rate": 9.330558823970448e-06, + "loss": 0.3529, + "step": 2994 + }, + { + "epoch": 0.38, + "learning_rate": 9.330040642405864e-06, + "loss": 0.3323, + "step": 2995 + }, + { + "epoch": 0.38, + "learning_rate": 9.329522274769791e-06, + "loss": 0.3511, + "step": 2996 + }, + { + "epoch": 0.38, + "learning_rate": 9.329003721084501e-06, + "loss": 0.3452, + "step": 2997 + }, + { + "epoch": 0.38, + "learning_rate": 9.328484981372283e-06, + "loss": 0.3605, + "step": 2998 + }, + { + "epoch": 0.38, + "learning_rate": 9.327966055655424e-06, + "loss": 0.3275, + "step": 2999 + }, + { + "epoch": 0.38, + "learning_rate": 9.327446943956224e-06, + "loss": 0.3958, + "step": 3000 + }, + { + "epoch": 0.38, + "learning_rate": 9.326927646296992e-06, + "loss": 0.3312, + "step": 3001 + }, + { + "epoch": 0.38, + "learning_rate": 9.326408162700043e-06, + "loss": 0.3535, + "step": 3002 + }, + { + "epoch": 0.38, + "learning_rate": 9.325888493187699e-06, + "loss": 0.3503, + "step": 3003 + }, + { + "epoch": 0.38, + "learning_rate": 9.325368637782292e-06, + "loss": 0.3367, + "step": 3004 + }, + { + "epoch": 0.38, + "learning_rate": 9.324848596506162e-06, + "loss": 0.3482, + "step": 3005 + }, + { + "epoch": 0.38, + "learning_rate": 9.324328369381654e-06, + "loss": 0.343, + "step": 3006 + }, + { + "epoch": 0.38, + "learning_rate": 9.323807956431128e-06, + "loss": 0.3257, + "step": 3007 + }, + { + "epoch": 0.39, + "learning_rate": 9.323287357676944e-06, + "loss": 0.313, + "step": 3008 + }, + { + "epoch": 0.39, + "learning_rate": 9.322766573141473e-06, + "loss": 0.3543, + "step": 3009 + }, + { + "epoch": 0.39, + "learning_rate": 9.322245602847094e-06, + "loss": 0.3564, + "step": 3010 + }, + { + "epoch": 0.39, + "learning_rate": 9.321724446816197e-06, + "loss": 0.3428, + "step": 3011 + }, + { + "epoch": 0.39, + "learning_rate": 9.321203105071176e-06, + "loss": 0.3382, + "step": 3012 + }, + { + "epoch": 0.39, + "learning_rate": 9.320681577634432e-06, + "loss": 0.3187, + "step": 3013 + }, + { + "epoch": 0.39, + "learning_rate": 9.320159864528378e-06, + "loss": 0.2987, + "step": 3014 + }, + { + "epoch": 0.39, + "learning_rate": 9.319637965775432e-06, + "loss": 0.3221, + "step": 3015 + }, + { + "epoch": 0.39, + "learning_rate": 9.319115881398024e-06, + "loss": 0.3343, + "step": 3016 + }, + { + "epoch": 0.39, + "learning_rate": 9.31859361141859e-06, + "loss": 0.3535, + "step": 3017 + }, + { + "epoch": 0.39, + "learning_rate": 9.318071155859567e-06, + "loss": 0.2994, + "step": 3018 + }, + { + "epoch": 0.39, + "learning_rate": 9.31754851474341e-06, + "loss": 0.3465, + "step": 3019 + }, + { + "epoch": 0.39, + "learning_rate": 9.317025688092577e-06, + "loss": 0.3352, + "step": 3020 + }, + { + "epoch": 0.39, + "learning_rate": 9.316502675929537e-06, + "loss": 0.3268, + "step": 3021 + }, + { + "epoch": 0.39, + "learning_rate": 9.315979478276763e-06, + "loss": 0.355, + "step": 3022 + }, + { + "epoch": 0.39, + "learning_rate": 9.315456095156739e-06, + "loss": 0.3629, + "step": 3023 + }, + { + "epoch": 0.39, + "learning_rate": 9.314932526591956e-06, + "loss": 0.3232, + "step": 3024 + }, + { + "epoch": 0.39, + "learning_rate": 9.314408772604911e-06, + "loss": 0.3361, + "step": 3025 + }, + { + "epoch": 0.39, + "learning_rate": 9.313884833218115e-06, + "loss": 0.3502, + "step": 3026 + }, + { + "epoch": 0.39, + "learning_rate": 9.313360708454078e-06, + "loss": 0.3615, + "step": 3027 + }, + { + "epoch": 0.39, + "learning_rate": 9.312836398335326e-06, + "loss": 0.3174, + "step": 3028 + }, + { + "epoch": 0.39, + "learning_rate": 9.312311902884388e-06, + "loss": 0.3397, + "step": 3029 + }, + { + "epoch": 0.39, + "learning_rate": 9.311787222123803e-06, + "loss": 0.3292, + "step": 3030 + }, + { + "epoch": 0.39, + "learning_rate": 9.311262356076118e-06, + "loss": 0.3459, + "step": 3031 + }, + { + "epoch": 0.39, + "learning_rate": 9.31073730476389e-06, + "loss": 0.3319, + "step": 3032 + }, + { + "epoch": 0.39, + "learning_rate": 9.310212068209678e-06, + "loss": 0.3409, + "step": 3033 + }, + { + "epoch": 0.39, + "learning_rate": 9.309686646436053e-06, + "loss": 0.3196, + "step": 3034 + }, + { + "epoch": 0.39, + "learning_rate": 9.309161039465597e-06, + "loss": 0.3485, + "step": 3035 + }, + { + "epoch": 0.39, + "learning_rate": 9.308635247320893e-06, + "loss": 0.3338, + "step": 3036 + }, + { + "epoch": 0.39, + "learning_rate": 9.308109270024537e-06, + "loss": 0.3292, + "step": 3037 + }, + { + "epoch": 0.39, + "learning_rate": 9.30758310759913e-06, + "loss": 0.3411, + "step": 3038 + }, + { + "epoch": 0.39, + "learning_rate": 9.307056760067284e-06, + "loss": 0.3291, + "step": 3039 + }, + { + "epoch": 0.39, + "learning_rate": 9.306530227451616e-06, + "loss": 0.3372, + "step": 3040 + }, + { + "epoch": 0.39, + "learning_rate": 9.306003509774755e-06, + "loss": 0.3362, + "step": 3041 + }, + { + "epoch": 0.39, + "learning_rate": 9.305476607059332e-06, + "loss": 0.3329, + "step": 3042 + }, + { + "epoch": 0.39, + "learning_rate": 9.30494951932799e-06, + "loss": 0.3063, + "step": 3043 + }, + { + "epoch": 0.39, + "learning_rate": 9.30442224660338e-06, + "loss": 0.3414, + "step": 3044 + }, + { + "epoch": 0.39, + "learning_rate": 9.303894788908158e-06, + "loss": 0.3214, + "step": 3045 + }, + { + "epoch": 0.39, + "learning_rate": 9.303367146264995e-06, + "loss": 0.3235, + "step": 3046 + }, + { + "epoch": 0.39, + "learning_rate": 9.302839318696558e-06, + "loss": 0.3235, + "step": 3047 + }, + { + "epoch": 0.39, + "learning_rate": 9.302311306225534e-06, + "loss": 0.3195, + "step": 3048 + }, + { + "epoch": 0.39, + "learning_rate": 9.301783108874611e-06, + "loss": 0.3351, + "step": 3049 + }, + { + "epoch": 0.39, + "learning_rate": 9.301254726666488e-06, + "loss": 0.3618, + "step": 3050 + }, + { + "epoch": 0.39, + "learning_rate": 9.300726159623869e-06, + "loss": 0.3474, + "step": 3051 + }, + { + "epoch": 0.39, + "learning_rate": 9.300197407769472e-06, + "loss": 0.31, + "step": 3052 + }, + { + "epoch": 0.39, + "learning_rate": 9.299668471126011e-06, + "loss": 0.335, + "step": 3053 + }, + { + "epoch": 0.39, + "learning_rate": 9.299139349716221e-06, + "loss": 0.3297, + "step": 3054 + }, + { + "epoch": 0.39, + "learning_rate": 9.29861004356284e-06, + "loss": 0.3529, + "step": 3055 + }, + { + "epoch": 0.39, + "learning_rate": 9.29808055268861e-06, + "loss": 0.3507, + "step": 3056 + }, + { + "epoch": 0.39, + "learning_rate": 9.297550877116288e-06, + "loss": 0.3272, + "step": 3057 + }, + { + "epoch": 0.39, + "learning_rate": 9.297021016868634e-06, + "loss": 0.3516, + "step": 3058 + }, + { + "epoch": 0.39, + "learning_rate": 9.296490971968416e-06, + "loss": 0.3459, + "step": 3059 + }, + { + "epoch": 0.39, + "learning_rate": 9.295960742438413e-06, + "loss": 0.3282, + "step": 3060 + }, + { + "epoch": 0.39, + "learning_rate": 9.295430328301406e-06, + "loss": 0.3434, + "step": 3061 + }, + { + "epoch": 0.39, + "learning_rate": 9.294899729580196e-06, + "loss": 0.3229, + "step": 3062 + }, + { + "epoch": 0.39, + "learning_rate": 9.294368946297576e-06, + "loss": 0.2967, + "step": 3063 + }, + { + "epoch": 0.39, + "learning_rate": 9.293837978476359e-06, + "loss": 0.3387, + "step": 3064 + }, + { + "epoch": 0.39, + "learning_rate": 9.293306826139361e-06, + "loss": 0.3243, + "step": 3065 + }, + { + "epoch": 0.39, + "learning_rate": 9.292775489309409e-06, + "loss": 0.3225, + "step": 3066 + }, + { + "epoch": 0.39, + "learning_rate": 9.292243968009332e-06, + "loss": 0.3428, + "step": 3067 + }, + { + "epoch": 0.39, + "learning_rate": 9.291712262261972e-06, + "loss": 0.3406, + "step": 3068 + }, + { + "epoch": 0.39, + "learning_rate": 9.291180372090178e-06, + "loss": 0.3525, + "step": 3069 + }, + { + "epoch": 0.39, + "learning_rate": 9.290648297516806e-06, + "loss": 0.3272, + "step": 3070 + }, + { + "epoch": 0.39, + "learning_rate": 9.290116038564722e-06, + "loss": 0.3277, + "step": 3071 + }, + { + "epoch": 0.39, + "learning_rate": 9.2895835952568e-06, + "loss": 0.3278, + "step": 3072 + }, + { + "epoch": 0.39, + "learning_rate": 9.289050967615914e-06, + "loss": 0.313, + "step": 3073 + }, + { + "epoch": 0.39, + "learning_rate": 9.288518155664956e-06, + "loss": 0.3412, + "step": 3074 + }, + { + "epoch": 0.39, + "learning_rate": 9.28798515942682e-06, + "loss": 0.3416, + "step": 3075 + }, + { + "epoch": 0.39, + "learning_rate": 9.287451978924415e-06, + "loss": 0.3337, + "step": 3076 + }, + { + "epoch": 0.39, + "learning_rate": 9.28691861418065e-06, + "loss": 0.3134, + "step": 3077 + }, + { + "epoch": 0.39, + "learning_rate": 9.286385065218442e-06, + "loss": 0.3216, + "step": 3078 + }, + { + "epoch": 0.39, + "learning_rate": 9.285851332060722e-06, + "loss": 0.3325, + "step": 3079 + }, + { + "epoch": 0.39, + "learning_rate": 9.285317414730427e-06, + "loss": 0.354, + "step": 3080 + }, + { + "epoch": 0.39, + "learning_rate": 9.284783313250499e-06, + "loss": 0.3182, + "step": 3081 + }, + { + "epoch": 0.39, + "learning_rate": 9.284249027643887e-06, + "loss": 0.3141, + "step": 3082 + }, + { + "epoch": 0.39, + "learning_rate": 9.283714557933554e-06, + "loss": 0.3303, + "step": 3083 + }, + { + "epoch": 0.39, + "learning_rate": 9.283179904142465e-06, + "loss": 0.3273, + "step": 3084 + }, + { + "epoch": 0.39, + "learning_rate": 9.282645066293597e-06, + "loss": 0.339, + "step": 3085 + }, + { + "epoch": 0.4, + "learning_rate": 9.282110044409933e-06, + "loss": 0.3085, + "step": 3086 + }, + { + "epoch": 0.4, + "learning_rate": 9.281574838514464e-06, + "loss": 0.3181, + "step": 3087 + }, + { + "epoch": 0.4, + "learning_rate": 9.281039448630187e-06, + "loss": 0.3128, + "step": 3088 + }, + { + "epoch": 0.4, + "learning_rate": 9.280503874780112e-06, + "loss": 0.3511, + "step": 3089 + }, + { + "epoch": 0.4, + "learning_rate": 9.279968116987253e-06, + "loss": 0.3525, + "step": 3090 + }, + { + "epoch": 0.4, + "learning_rate": 9.27943217527463e-06, + "loss": 0.3451, + "step": 3091 + }, + { + "epoch": 0.4, + "learning_rate": 9.278896049665276e-06, + "loss": 0.3331, + "step": 3092 + }, + { + "epoch": 0.4, + "learning_rate": 9.27835974018223e-06, + "loss": 0.351, + "step": 3093 + }, + { + "epoch": 0.4, + "learning_rate": 9.277823246848537e-06, + "loss": 0.3344, + "step": 3094 + }, + { + "epoch": 0.4, + "learning_rate": 9.277286569687252e-06, + "loss": 0.3345, + "step": 3095 + }, + { + "epoch": 0.4, + "learning_rate": 9.276749708721438e-06, + "loss": 0.3114, + "step": 3096 + }, + { + "epoch": 0.4, + "learning_rate": 9.276212663974163e-06, + "loss": 0.3199, + "step": 3097 + }, + { + "epoch": 0.4, + "learning_rate": 9.275675435468505e-06, + "loss": 0.3463, + "step": 3098 + }, + { + "epoch": 0.4, + "learning_rate": 9.275138023227555e-06, + "loss": 0.3559, + "step": 3099 + }, + { + "epoch": 0.4, + "learning_rate": 9.274600427274399e-06, + "loss": 0.3556, + "step": 3100 + }, + { + "epoch": 0.4, + "learning_rate": 9.274062647632144e-06, + "loss": 0.3426, + "step": 3101 + }, + { + "epoch": 0.4, + "learning_rate": 9.273524684323897e-06, + "loss": 0.3341, + "step": 3102 + }, + { + "epoch": 0.4, + "learning_rate": 9.27298653737278e-06, + "loss": 0.3469, + "step": 3103 + }, + { + "epoch": 0.4, + "learning_rate": 9.272448206801912e-06, + "loss": 0.3555, + "step": 3104 + }, + { + "epoch": 0.4, + "learning_rate": 9.271909692634431e-06, + "loss": 0.3473, + "step": 3105 + }, + { + "epoch": 0.4, + "learning_rate": 9.271370994893475e-06, + "loss": 0.3332, + "step": 3106 + }, + { + "epoch": 0.4, + "learning_rate": 9.270832113602196e-06, + "loss": 0.3449, + "step": 3107 + }, + { + "epoch": 0.4, + "learning_rate": 9.270293048783747e-06, + "loss": 0.3109, + "step": 3108 + }, + { + "epoch": 0.4, + "learning_rate": 9.269753800461299e-06, + "loss": 0.3489, + "step": 3109 + }, + { + "epoch": 0.4, + "learning_rate": 9.269214368658016e-06, + "loss": 0.3292, + "step": 3110 + }, + { + "epoch": 0.4, + "learning_rate": 9.268674753397087e-06, + "loss": 0.3434, + "step": 3111 + }, + { + "epoch": 0.4, + "learning_rate": 9.268134954701697e-06, + "loss": 0.3, + "step": 3112 + }, + { + "epoch": 0.4, + "learning_rate": 9.267594972595042e-06, + "loss": 0.3523, + "step": 3113 + }, + { + "epoch": 0.4, + "learning_rate": 9.267054807100327e-06, + "loss": 0.349, + "step": 3114 + }, + { + "epoch": 0.4, + "learning_rate": 9.266514458240762e-06, + "loss": 0.3485, + "step": 3115 + }, + { + "epoch": 0.4, + "learning_rate": 9.26597392603957e-06, + "loss": 0.3187, + "step": 3116 + }, + { + "epoch": 0.4, + "learning_rate": 9.265433210519976e-06, + "loss": 0.3204, + "step": 3117 + }, + { + "epoch": 0.4, + "learning_rate": 9.26489231170522e-06, + "loss": 0.3323, + "step": 3118 + }, + { + "epoch": 0.4, + "learning_rate": 9.264351229618541e-06, + "loss": 0.3062, + "step": 3119 + }, + { + "epoch": 0.4, + "learning_rate": 9.263809964283192e-06, + "loss": 0.3413, + "step": 3120 + }, + { + "epoch": 0.4, + "learning_rate": 9.263268515722435e-06, + "loss": 0.3622, + "step": 3121 + }, + { + "epoch": 0.4, + "learning_rate": 9.262726883959535e-06, + "loss": 0.3326, + "step": 3122 + }, + { + "epoch": 0.4, + "learning_rate": 9.262185069017764e-06, + "loss": 0.3585, + "step": 3123 + }, + { + "epoch": 0.4, + "learning_rate": 9.261643070920409e-06, + "loss": 0.3355, + "step": 3124 + }, + { + "epoch": 0.4, + "learning_rate": 9.261100889690763e-06, + "loss": 0.3358, + "step": 3125 + }, + { + "epoch": 0.4, + "learning_rate": 9.26055852535212e-06, + "loss": 0.3372, + "step": 3126 + }, + { + "epoch": 0.4, + "learning_rate": 9.260015977927788e-06, + "loss": 0.3067, + "step": 3127 + }, + { + "epoch": 0.4, + "learning_rate": 9.259473247441081e-06, + "loss": 0.347, + "step": 3128 + }, + { + "epoch": 0.4, + "learning_rate": 9.258930333915325e-06, + "loss": 0.317, + "step": 3129 + }, + { + "epoch": 0.4, + "learning_rate": 9.258387237373845e-06, + "loss": 0.3386, + "step": 3130 + }, + { + "epoch": 0.4, + "learning_rate": 9.257843957839982e-06, + "loss": 0.3408, + "step": 3131 + }, + { + "epoch": 0.4, + "learning_rate": 9.257300495337082e-06, + "loss": 0.3333, + "step": 3132 + }, + { + "epoch": 0.4, + "learning_rate": 9.256756849888499e-06, + "loss": 0.3239, + "step": 3133 + }, + { + "epoch": 0.4, + "learning_rate": 9.256213021517593e-06, + "loss": 0.3698, + "step": 3134 + }, + { + "epoch": 0.4, + "learning_rate": 9.255669010247734e-06, + "loss": 0.3455, + "step": 3135 + }, + { + "epoch": 0.4, + "learning_rate": 9.2551248161023e-06, + "loss": 0.3275, + "step": 3136 + }, + { + "epoch": 0.4, + "learning_rate": 9.254580439104677e-06, + "loss": 0.3353, + "step": 3137 + }, + { + "epoch": 0.4, + "learning_rate": 9.254035879278255e-06, + "loss": 0.3642, + "step": 3138 + }, + { + "epoch": 0.4, + "learning_rate": 9.253491136646437e-06, + "loss": 0.3583, + "step": 3139 + }, + { + "epoch": 0.4, + "learning_rate": 9.252946211232634e-06, + "loss": 0.3566, + "step": 3140 + }, + { + "epoch": 0.4, + "learning_rate": 9.25240110306026e-06, + "loss": 0.3514, + "step": 3141 + }, + { + "epoch": 0.4, + "learning_rate": 9.25185581215274e-06, + "loss": 0.3431, + "step": 3142 + }, + { + "epoch": 0.4, + "learning_rate": 9.251310338533504e-06, + "loss": 0.3491, + "step": 3143 + }, + { + "epoch": 0.4, + "learning_rate": 9.250764682225997e-06, + "loss": 0.3085, + "step": 3144 + }, + { + "epoch": 0.4, + "learning_rate": 9.250218843253663e-06, + "loss": 0.3714, + "step": 3145 + }, + { + "epoch": 0.4, + "learning_rate": 9.24967282163996e-06, + "loss": 0.2971, + "step": 3146 + }, + { + "epoch": 0.4, + "learning_rate": 9.249126617408353e-06, + "loss": 0.3394, + "step": 3147 + }, + { + "epoch": 0.4, + "learning_rate": 9.248580230582311e-06, + "loss": 0.3206, + "step": 3148 + }, + { + "epoch": 0.4, + "learning_rate": 9.248033661185313e-06, + "loss": 0.3552, + "step": 3149 + }, + { + "epoch": 0.4, + "learning_rate": 9.247486909240849e-06, + "loss": 0.3324, + "step": 3150 + }, + { + "epoch": 0.4, + "learning_rate": 9.246939974772413e-06, + "loss": 0.3375, + "step": 3151 + }, + { + "epoch": 0.4, + "learning_rate": 9.246392857803508e-06, + "loss": 0.3677, + "step": 3152 + }, + { + "epoch": 0.4, + "learning_rate": 9.245845558357643e-06, + "loss": 0.3606, + "step": 3153 + }, + { + "epoch": 0.4, + "learning_rate": 9.24529807645834e-06, + "loss": 0.3374, + "step": 3154 + }, + { + "epoch": 0.4, + "learning_rate": 9.244750412129123e-06, + "loss": 0.3389, + "step": 3155 + }, + { + "epoch": 0.4, + "learning_rate": 9.244202565393528e-06, + "loss": 0.3228, + "step": 3156 + }, + { + "epoch": 0.4, + "learning_rate": 9.243654536275095e-06, + "loss": 0.3201, + "step": 3157 + }, + { + "epoch": 0.4, + "learning_rate": 9.243106324797377e-06, + "loss": 0.3242, + "step": 3158 + }, + { + "epoch": 0.4, + "learning_rate": 9.24255793098393e-06, + "loss": 0.3559, + "step": 3159 + }, + { + "epoch": 0.4, + "learning_rate": 9.24200935485832e-06, + "loss": 0.3301, + "step": 3160 + }, + { + "epoch": 0.4, + "learning_rate": 9.24146059644412e-06, + "loss": 0.3465, + "step": 3161 + }, + { + "epoch": 0.4, + "learning_rate": 9.240911655764912e-06, + "loss": 0.3491, + "step": 3162 + }, + { + "epoch": 0.4, + "learning_rate": 9.240362532844287e-06, + "loss": 0.3484, + "step": 3163 + }, + { + "epoch": 0.4, + "learning_rate": 9.23981322770584e-06, + "loss": 0.2803, + "step": 3164 + }, + { + "epoch": 0.41, + "learning_rate": 9.239263740373173e-06, + "loss": 0.3414, + "step": 3165 + }, + { + "epoch": 0.41, + "learning_rate": 9.238714070869903e-06, + "loss": 0.3255, + "step": 3166 + }, + { + "epoch": 0.41, + "learning_rate": 9.238164219219649e-06, + "loss": 0.3135, + "step": 3167 + }, + { + "epoch": 0.41, + "learning_rate": 9.23761418544604e-06, + "loss": 0.3149, + "step": 3168 + }, + { + "epoch": 0.41, + "learning_rate": 9.237063969572713e-06, + "loss": 0.3429, + "step": 3169 + }, + { + "epoch": 0.41, + "learning_rate": 9.23651357162331e-06, + "loss": 0.3275, + "step": 3170 + }, + { + "epoch": 0.41, + "learning_rate": 9.235962991621484e-06, + "loss": 0.3648, + "step": 3171 + }, + { + "epoch": 0.41, + "learning_rate": 9.235412229590893e-06, + "loss": 0.3244, + "step": 3172 + }, + { + "epoch": 0.41, + "learning_rate": 9.234861285555207e-06, + "loss": 0.3276, + "step": 3173 + }, + { + "epoch": 0.41, + "learning_rate": 9.2343101595381e-06, + "loss": 0.3449, + "step": 3174 + }, + { + "epoch": 0.41, + "learning_rate": 9.233758851563254e-06, + "loss": 0.3425, + "step": 3175 + }, + { + "epoch": 0.41, + "learning_rate": 9.233207361654362e-06, + "loss": 0.3157, + "step": 3176 + }, + { + "epoch": 0.41, + "learning_rate": 9.23265568983512e-06, + "loss": 0.3334, + "step": 3177 + }, + { + "epoch": 0.41, + "learning_rate": 9.232103836129239e-06, + "loss": 0.3354, + "step": 3178 + }, + { + "epoch": 0.41, + "learning_rate": 9.23155180056043e-06, + "loss": 0.3669, + "step": 3179 + }, + { + "epoch": 0.41, + "learning_rate": 9.230999583152413e-06, + "loss": 0.332, + "step": 3180 + }, + { + "epoch": 0.41, + "learning_rate": 9.230447183928926e-06, + "loss": 0.3114, + "step": 3181 + }, + { + "epoch": 0.41, + "learning_rate": 9.229894602913698e-06, + "loss": 0.3512, + "step": 3182 + }, + { + "epoch": 0.41, + "learning_rate": 9.22934184013048e-06, + "loss": 0.3532, + "step": 3183 + }, + { + "epoch": 0.41, + "learning_rate": 9.228788895603024e-06, + "loss": 0.3911, + "step": 3184 + }, + { + "epoch": 0.41, + "learning_rate": 9.22823576935509e-06, + "loss": 0.3509, + "step": 3185 + }, + { + "epoch": 0.41, + "learning_rate": 9.22768246141045e-06, + "loss": 0.363, + "step": 3186 + }, + { + "epoch": 0.41, + "learning_rate": 9.227128971792877e-06, + "loss": 0.3417, + "step": 3187 + }, + { + "epoch": 0.41, + "learning_rate": 9.226575300526159e-06, + "loss": 0.3344, + "step": 3188 + }, + { + "epoch": 0.41, + "learning_rate": 9.226021447634085e-06, + "loss": 0.3607, + "step": 3189 + }, + { + "epoch": 0.41, + "learning_rate": 9.22546741314046e-06, + "loss": 0.34, + "step": 3190 + }, + { + "epoch": 0.41, + "learning_rate": 9.22491319706909e-06, + "loss": 0.3484, + "step": 3191 + }, + { + "epoch": 0.41, + "learning_rate": 9.224358799443791e-06, + "loss": 0.3496, + "step": 3192 + }, + { + "epoch": 0.41, + "learning_rate": 9.223804220288384e-06, + "loss": 0.3431, + "step": 3193 + }, + { + "epoch": 0.41, + "learning_rate": 9.223249459626704e-06, + "loss": 0.3565, + "step": 3194 + }, + { + "epoch": 0.41, + "learning_rate": 9.22269451748259e-06, + "loss": 0.3276, + "step": 3195 + }, + { + "epoch": 0.41, + "learning_rate": 9.222139393879885e-06, + "loss": 0.3514, + "step": 3196 + }, + { + "epoch": 0.41, + "learning_rate": 9.22158408884245e-06, + "loss": 0.331, + "step": 3197 + }, + { + "epoch": 0.41, + "learning_rate": 9.221028602394144e-06, + "loss": 0.321, + "step": 3198 + }, + { + "epoch": 0.41, + "learning_rate": 9.220472934558838e-06, + "loss": 0.3248, + "step": 3199 + }, + { + "epoch": 0.41, + "learning_rate": 9.21991708536041e-06, + "loss": 0.3392, + "step": 3200 + }, + { + "epoch": 0.41, + "learning_rate": 9.219361054822746e-06, + "loss": 0.372, + "step": 3201 + }, + { + "epoch": 0.41, + "learning_rate": 9.218804842969742e-06, + "loss": 0.3507, + "step": 3202 + }, + { + "epoch": 0.41, + "learning_rate": 9.218248449825297e-06, + "loss": 0.344, + "step": 3203 + }, + { + "epoch": 0.41, + "learning_rate": 9.217691875413323e-06, + "loss": 0.3231, + "step": 3204 + }, + { + "epoch": 0.41, + "learning_rate": 9.217135119757734e-06, + "loss": 0.3582, + "step": 3205 + }, + { + "epoch": 0.41, + "learning_rate": 9.216578182882459e-06, + "loss": 0.3584, + "step": 3206 + }, + { + "epoch": 0.41, + "learning_rate": 9.216021064811428e-06, + "loss": 0.3319, + "step": 3207 + }, + { + "epoch": 0.41, + "learning_rate": 9.21546376556858e-06, + "loss": 0.3049, + "step": 3208 + }, + { + "epoch": 0.41, + "learning_rate": 9.214906285177867e-06, + "loss": 0.3559, + "step": 3209 + }, + { + "epoch": 0.41, + "learning_rate": 9.214348623663244e-06, + "loss": 0.324, + "step": 3210 + }, + { + "epoch": 0.41, + "learning_rate": 9.213790781048677e-06, + "loss": 0.3155, + "step": 3211 + }, + { + "epoch": 0.41, + "learning_rate": 9.213232757358133e-06, + "loss": 0.3306, + "step": 3212 + }, + { + "epoch": 0.41, + "learning_rate": 9.212674552615594e-06, + "loss": 0.3485, + "step": 3213 + }, + { + "epoch": 0.41, + "learning_rate": 9.212116166845048e-06, + "loss": 0.3126, + "step": 3214 + }, + { + "epoch": 0.41, + "learning_rate": 9.211557600070489e-06, + "loss": 0.3276, + "step": 3215 + }, + { + "epoch": 0.41, + "learning_rate": 9.21099885231592e-06, + "loss": 0.3476, + "step": 3216 + }, + { + "epoch": 0.41, + "learning_rate": 9.210439923605352e-06, + "loss": 0.3343, + "step": 3217 + }, + { + "epoch": 0.41, + "learning_rate": 9.209880813962806e-06, + "loss": 0.3041, + "step": 3218 + }, + { + "epoch": 0.41, + "learning_rate": 9.209321523412303e-06, + "loss": 0.3196, + "step": 3219 + }, + { + "epoch": 0.41, + "learning_rate": 9.208762051977879e-06, + "loss": 0.3177, + "step": 3220 + }, + { + "epoch": 0.41, + "learning_rate": 9.208202399683577e-06, + "loss": 0.3309, + "step": 3221 + }, + { + "epoch": 0.41, + "learning_rate": 9.207642566553445e-06, + "loss": 0.342, + "step": 3222 + }, + { + "epoch": 0.41, + "learning_rate": 9.207082552611541e-06, + "loss": 0.328, + "step": 3223 + }, + { + "epoch": 0.41, + "learning_rate": 9.206522357881931e-06, + "loss": 0.3381, + "step": 3224 + }, + { + "epoch": 0.41, + "learning_rate": 9.205961982388686e-06, + "loss": 0.3449, + "step": 3225 + }, + { + "epoch": 0.41, + "learning_rate": 9.205401426155889e-06, + "loss": 0.321, + "step": 3226 + }, + { + "epoch": 0.41, + "learning_rate": 9.204840689207626e-06, + "loss": 0.3394, + "step": 3227 + }, + { + "epoch": 0.41, + "learning_rate": 9.204279771567994e-06, + "loss": 0.3372, + "step": 3228 + }, + { + "epoch": 0.41, + "learning_rate": 9.203718673261098e-06, + "loss": 0.328, + "step": 3229 + }, + { + "epoch": 0.41, + "learning_rate": 9.203157394311045e-06, + "loss": 0.3377, + "step": 3230 + }, + { + "epoch": 0.41, + "learning_rate": 9.20259593474196e-06, + "loss": 0.3364, + "step": 3231 + }, + { + "epoch": 0.41, + "learning_rate": 9.202034294577968e-06, + "loss": 0.3622, + "step": 3232 + }, + { + "epoch": 0.41, + "learning_rate": 9.201472473843204e-06, + "loss": 0.3784, + "step": 3233 + }, + { + "epoch": 0.41, + "learning_rate": 9.20091047256181e-06, + "loss": 0.3557, + "step": 3234 + }, + { + "epoch": 0.41, + "learning_rate": 9.200348290757937e-06, + "loss": 0.3305, + "step": 3235 + }, + { + "epoch": 0.41, + "learning_rate": 9.199785928455745e-06, + "loss": 0.3014, + "step": 3236 + }, + { + "epoch": 0.41, + "learning_rate": 9.199223385679396e-06, + "loss": 0.3565, + "step": 3237 + }, + { + "epoch": 0.41, + "learning_rate": 9.198660662453066e-06, + "loss": 0.3256, + "step": 3238 + }, + { + "epoch": 0.41, + "learning_rate": 9.198097758800938e-06, + "loss": 0.3273, + "step": 3239 + }, + { + "epoch": 0.41, + "learning_rate": 9.197534674747199e-06, + "loss": 0.3, + "step": 3240 + }, + { + "epoch": 0.41, + "learning_rate": 9.196971410316047e-06, + "loss": 0.3322, + "step": 3241 + }, + { + "epoch": 0.41, + "learning_rate": 9.196407965531686e-06, + "loss": 0.3338, + "step": 3242 + }, + { + "epoch": 0.42, + "learning_rate": 9.195844340418328e-06, + "loss": 0.3271, + "step": 3243 + }, + { + "epoch": 0.42, + "learning_rate": 9.195280535000196e-06, + "loss": 0.3259, + "step": 3244 + }, + { + "epoch": 0.42, + "learning_rate": 9.194716549301514e-06, + "loss": 0.3386, + "step": 3245 + }, + { + "epoch": 0.42, + "learning_rate": 9.19415238334652e-06, + "loss": 0.326, + "step": 3246 + }, + { + "epoch": 0.42, + "learning_rate": 9.193588037159457e-06, + "loss": 0.3458, + "step": 3247 + }, + { + "epoch": 0.42, + "learning_rate": 9.193023510764578e-06, + "loss": 0.3032, + "step": 3248 + }, + { + "epoch": 0.42, + "learning_rate": 9.19245880418614e-06, + "loss": 0.3441, + "step": 3249 + }, + { + "epoch": 0.42, + "learning_rate": 9.191893917448409e-06, + "loss": 0.3503, + "step": 3250 + }, + { + "epoch": 0.42, + "learning_rate": 9.19132885057566e-06, + "loss": 0.3444, + "step": 3251 + }, + { + "epoch": 0.42, + "learning_rate": 9.190763603592177e-06, + "loss": 0.3149, + "step": 3252 + }, + { + "epoch": 0.42, + "learning_rate": 9.190198176522249e-06, + "loss": 0.3468, + "step": 3253 + }, + { + "epoch": 0.42, + "learning_rate": 9.189632569390172e-06, + "loss": 0.3626, + "step": 3254 + }, + { + "epoch": 0.42, + "learning_rate": 9.189066782220253e-06, + "loss": 0.3104, + "step": 3255 + }, + { + "epoch": 0.42, + "learning_rate": 9.188500815036806e-06, + "loss": 0.3408, + "step": 3256 + }, + { + "epoch": 0.42, + "learning_rate": 9.18793466786415e-06, + "loss": 0.3536, + "step": 3257 + }, + { + "epoch": 0.42, + "learning_rate": 9.187368340726615e-06, + "loss": 0.3147, + "step": 3258 + }, + { + "epoch": 0.42, + "learning_rate": 9.186801833648535e-06, + "loss": 0.3041, + "step": 3259 + }, + { + "epoch": 0.42, + "learning_rate": 9.186235146654257e-06, + "loss": 0.3599, + "step": 3260 + }, + { + "epoch": 0.42, + "learning_rate": 9.18566827976813e-06, + "loss": 0.3398, + "step": 3261 + }, + { + "epoch": 0.42, + "learning_rate": 9.185101233014516e-06, + "loss": 0.3345, + "step": 3262 + }, + { + "epoch": 0.42, + "learning_rate": 9.184534006417782e-06, + "loss": 0.3379, + "step": 3263 + }, + { + "epoch": 0.42, + "learning_rate": 9.183966600002301e-06, + "loss": 0.3157, + "step": 3264 + }, + { + "epoch": 0.42, + "learning_rate": 9.183399013792457e-06, + "loss": 0.3493, + "step": 3265 + }, + { + "epoch": 0.42, + "learning_rate": 9.18283124781264e-06, + "loss": 0.3294, + "step": 3266 + }, + { + "epoch": 0.42, + "learning_rate": 9.18226330208725e-06, + "loss": 0.3679, + "step": 3267 + }, + { + "epoch": 0.42, + "learning_rate": 9.181695176640693e-06, + "loss": 0.3263, + "step": 3268 + }, + { + "epoch": 0.42, + "learning_rate": 9.181126871497378e-06, + "loss": 0.3554, + "step": 3269 + }, + { + "epoch": 0.42, + "learning_rate": 9.180558386681731e-06, + "loss": 0.3456, + "step": 3270 + }, + { + "epoch": 0.42, + "learning_rate": 9.179989722218179e-06, + "loss": 0.3425, + "step": 3271 + }, + { + "epoch": 0.42, + "learning_rate": 9.17942087813116e-06, + "loss": 0.3258, + "step": 3272 + }, + { + "epoch": 0.42, + "learning_rate": 9.178851854445118e-06, + "loss": 0.3297, + "step": 3273 + }, + { + "epoch": 0.42, + "learning_rate": 9.178282651184506e-06, + "loss": 0.3269, + "step": 3274 + }, + { + "epoch": 0.42, + "learning_rate": 9.177713268373781e-06, + "loss": 0.344, + "step": 3275 + }, + { + "epoch": 0.42, + "learning_rate": 9.177143706037411e-06, + "loss": 0.3059, + "step": 3276 + }, + { + "epoch": 0.42, + "learning_rate": 9.176573964199875e-06, + "loss": 0.3125, + "step": 3277 + }, + { + "epoch": 0.42, + "learning_rate": 9.176004042885653e-06, + "loss": 0.3372, + "step": 3278 + }, + { + "epoch": 0.42, + "learning_rate": 9.175433942119238e-06, + "loss": 0.329, + "step": 3279 + }, + { + "epoch": 0.42, + "learning_rate": 9.174863661925128e-06, + "loss": 0.3492, + "step": 3280 + }, + { + "epoch": 0.42, + "learning_rate": 9.174293202327828e-06, + "loss": 0.3297, + "step": 3281 + }, + { + "epoch": 0.42, + "learning_rate": 9.173722563351852e-06, + "loss": 0.3278, + "step": 3282 + }, + { + "epoch": 0.42, + "learning_rate": 9.173151745021722e-06, + "loss": 0.31, + "step": 3283 + }, + { + "epoch": 0.42, + "learning_rate": 9.172580747361968e-06, + "loss": 0.3367, + "step": 3284 + }, + { + "epoch": 0.42, + "learning_rate": 9.172009570397124e-06, + "loss": 0.3342, + "step": 3285 + }, + { + "epoch": 0.42, + "learning_rate": 9.17143821415174e-06, + "loss": 0.3482, + "step": 3286 + }, + { + "epoch": 0.42, + "learning_rate": 9.170866678650366e-06, + "loss": 0.3473, + "step": 3287 + }, + { + "epoch": 0.42, + "learning_rate": 9.17029496391756e-06, + "loss": 0.361, + "step": 3288 + }, + { + "epoch": 0.42, + "learning_rate": 9.169723069977892e-06, + "loss": 0.3652, + "step": 3289 + }, + { + "epoch": 0.42, + "learning_rate": 9.169150996855939e-06, + "loss": 0.315, + "step": 3290 + }, + { + "epoch": 0.42, + "learning_rate": 9.16857874457628e-06, + "loss": 0.3124, + "step": 3291 + }, + { + "epoch": 0.42, + "learning_rate": 9.16800631316351e-06, + "loss": 0.3359, + "step": 3292 + }, + { + "epoch": 0.42, + "learning_rate": 9.167433702642224e-06, + "loss": 0.3473, + "step": 3293 + }, + { + "epoch": 0.42, + "learning_rate": 9.166860913037032e-06, + "loss": 0.3387, + "step": 3294 + }, + { + "epoch": 0.42, + "learning_rate": 9.166287944372546e-06, + "loss": 0.3291, + "step": 3295 + }, + { + "epoch": 0.42, + "learning_rate": 9.165714796673389e-06, + "loss": 0.3607, + "step": 3296 + }, + { + "epoch": 0.42, + "learning_rate": 9.16514146996419e-06, + "loss": 0.3402, + "step": 3297 + }, + { + "epoch": 0.42, + "learning_rate": 9.164567964269583e-06, + "loss": 0.3221, + "step": 3298 + }, + { + "epoch": 0.42, + "learning_rate": 9.163994279614218e-06, + "loss": 0.3305, + "step": 3299 + }, + { + "epoch": 0.42, + "learning_rate": 9.163420416022745e-06, + "loss": 0.3134, + "step": 3300 + }, + { + "epoch": 0.42, + "learning_rate": 9.162846373519824e-06, + "loss": 0.336, + "step": 3301 + }, + { + "epoch": 0.42, + "learning_rate": 9.162272152130123e-06, + "loss": 0.335, + "step": 3302 + }, + { + "epoch": 0.42, + "learning_rate": 9.161697751878317e-06, + "loss": 0.3194, + "step": 3303 + }, + { + "epoch": 0.42, + "learning_rate": 9.161123172789091e-06, + "loss": 0.3534, + "step": 3304 + }, + { + "epoch": 0.42, + "learning_rate": 9.160548414887135e-06, + "loss": 0.3331, + "step": 3305 + }, + { + "epoch": 0.42, + "learning_rate": 9.159973478197148e-06, + "loss": 0.3678, + "step": 3306 + }, + { + "epoch": 0.42, + "learning_rate": 9.159398362743834e-06, + "loss": 0.3199, + "step": 3307 + }, + { + "epoch": 0.42, + "learning_rate": 9.15882306855191e-06, + "loss": 0.3401, + "step": 3308 + }, + { + "epoch": 0.42, + "learning_rate": 9.158247595646098e-06, + "loss": 0.3456, + "step": 3309 + }, + { + "epoch": 0.42, + "learning_rate": 9.157671944051125e-06, + "loss": 0.3313, + "step": 3310 + }, + { + "epoch": 0.42, + "learning_rate": 9.157096113791727e-06, + "loss": 0.3403, + "step": 3311 + }, + { + "epoch": 0.42, + "learning_rate": 9.156520104892653e-06, + "loss": 0.3394, + "step": 3312 + }, + { + "epoch": 0.42, + "learning_rate": 9.155943917378652e-06, + "loss": 0.3193, + "step": 3313 + }, + { + "epoch": 0.42, + "learning_rate": 9.155367551274485e-06, + "loss": 0.3522, + "step": 3314 + }, + { + "epoch": 0.42, + "learning_rate": 9.15479100660492e-06, + "loss": 0.3514, + "step": 3315 + }, + { + "epoch": 0.42, + "learning_rate": 9.154214283394733e-06, + "loss": 0.3315, + "step": 3316 + }, + { + "epoch": 0.42, + "learning_rate": 9.153637381668705e-06, + "loss": 0.3369, + "step": 3317 + }, + { + "epoch": 0.42, + "learning_rate": 9.153060301451629e-06, + "loss": 0.3172, + "step": 3318 + }, + { + "epoch": 0.42, + "learning_rate": 9.152483042768302e-06, + "loss": 0.3319, + "step": 3319 + }, + { + "epoch": 0.42, + "learning_rate": 9.151905605643531e-06, + "loss": 0.3268, + "step": 3320 + }, + { + "epoch": 0.43, + "learning_rate": 9.151327990102129e-06, + "loss": 0.3409, + "step": 3321 + }, + { + "epoch": 0.43, + "learning_rate": 9.150750196168918e-06, + "loss": 0.323, + "step": 3322 + }, + { + "epoch": 0.43, + "learning_rate": 9.150172223868727e-06, + "loss": 0.3397, + "step": 3323 + }, + { + "epoch": 0.43, + "learning_rate": 9.149594073226391e-06, + "loss": 0.3286, + "step": 3324 + }, + { + "epoch": 0.43, + "learning_rate": 9.149015744266759e-06, + "loss": 0.3057, + "step": 3325 + }, + { + "epoch": 0.43, + "learning_rate": 9.148437237014677e-06, + "loss": 0.3458, + "step": 3326 + }, + { + "epoch": 0.43, + "learning_rate": 9.14785855149501e-06, + "loss": 0.3076, + "step": 3327 + }, + { + "epoch": 0.43, + "learning_rate": 9.147279687732622e-06, + "loss": 0.3233, + "step": 3328 + }, + { + "epoch": 0.43, + "learning_rate": 9.14670064575239e-06, + "loss": 0.3253, + "step": 3329 + }, + { + "epoch": 0.43, + "learning_rate": 9.146121425579197e-06, + "loss": 0.3581, + "step": 3330 + }, + { + "epoch": 0.43, + "learning_rate": 9.14554202723793e-06, + "loss": 0.3394, + "step": 3331 + }, + { + "epoch": 0.43, + "learning_rate": 9.144962450753491e-06, + "loss": 0.3492, + "step": 3332 + }, + { + "epoch": 0.43, + "learning_rate": 9.144382696150785e-06, + "loss": 0.393, + "step": 3333 + }, + { + "epoch": 0.43, + "learning_rate": 9.143802763454723e-06, + "loss": 0.3335, + "step": 3334 + }, + { + "epoch": 0.43, + "learning_rate": 9.143222652690227e-06, + "loss": 0.3342, + "step": 3335 + }, + { + "epoch": 0.43, + "learning_rate": 9.142642363882228e-06, + "loss": 0.3536, + "step": 3336 + }, + { + "epoch": 0.43, + "learning_rate": 9.14206189705566e-06, + "loss": 0.3326, + "step": 3337 + }, + { + "epoch": 0.43, + "learning_rate": 9.141481252235467e-06, + "loss": 0.3246, + "step": 3338 + }, + { + "epoch": 0.43, + "learning_rate": 9.140900429446601e-06, + "loss": 0.3379, + "step": 3339 + }, + { + "epoch": 0.43, + "learning_rate": 9.140319428714022e-06, + "loss": 0.3176, + "step": 3340 + }, + { + "epoch": 0.43, + "learning_rate": 9.139738250062695e-06, + "loss": 0.3374, + "step": 3341 + }, + { + "epoch": 0.43, + "learning_rate": 9.139156893517595e-06, + "loss": 0.3431, + "step": 3342 + }, + { + "epoch": 0.43, + "learning_rate": 9.138575359103707e-06, + "loss": 0.3386, + "step": 3343 + }, + { + "epoch": 0.43, + "learning_rate": 9.137993646846018e-06, + "loss": 0.3236, + "step": 3344 + }, + { + "epoch": 0.43, + "learning_rate": 9.137411756769525e-06, + "loss": 0.3306, + "step": 3345 + }, + { + "epoch": 0.43, + "learning_rate": 9.136829688899236e-06, + "loss": 0.3268, + "step": 3346 + }, + { + "epoch": 0.43, + "learning_rate": 9.136247443260162e-06, + "loss": 0.352, + "step": 3347 + }, + { + "epoch": 0.43, + "learning_rate": 9.135665019877323e-06, + "loss": 0.3322, + "step": 3348 + }, + { + "epoch": 0.43, + "learning_rate": 9.135082418775746e-06, + "loss": 0.3159, + "step": 3349 + }, + { + "epoch": 0.43, + "learning_rate": 9.134499639980469e-06, + "loss": 0.3239, + "step": 3350 + }, + { + "epoch": 0.43, + "learning_rate": 9.133916683516536e-06, + "loss": 0.3533, + "step": 3351 + }, + { + "epoch": 0.43, + "learning_rate": 9.133333549408997e-06, + "loss": 0.3386, + "step": 3352 + }, + { + "epoch": 0.43, + "learning_rate": 9.132750237682907e-06, + "loss": 0.3491, + "step": 3353 + }, + { + "epoch": 0.43, + "learning_rate": 9.132166748363335e-06, + "loss": 0.3632, + "step": 3354 + }, + { + "epoch": 0.43, + "learning_rate": 9.131583081475356e-06, + "loss": 0.3703, + "step": 3355 + }, + { + "epoch": 0.43, + "learning_rate": 9.130999237044052e-06, + "loss": 0.311, + "step": 3356 + }, + { + "epoch": 0.43, + "learning_rate": 9.13041521509451e-06, + "loss": 0.3479, + "step": 3357 + }, + { + "epoch": 0.43, + "learning_rate": 9.129831015651827e-06, + "loss": 0.3196, + "step": 3358 + }, + { + "epoch": 0.43, + "learning_rate": 9.129246638741108e-06, + "loss": 0.3936, + "step": 3359 + }, + { + "epoch": 0.43, + "learning_rate": 9.128662084387462e-06, + "loss": 0.3307, + "step": 3360 + }, + { + "epoch": 0.43, + "learning_rate": 9.128077352616013e-06, + "loss": 0.3493, + "step": 3361 + }, + { + "epoch": 0.43, + "learning_rate": 9.127492443451887e-06, + "loss": 0.3402, + "step": 3362 + }, + { + "epoch": 0.43, + "learning_rate": 9.126907356920219e-06, + "loss": 0.3588, + "step": 3363 + }, + { + "epoch": 0.43, + "learning_rate": 9.126322093046149e-06, + "loss": 0.3144, + "step": 3364 + }, + { + "epoch": 0.43, + "learning_rate": 9.12573665185483e-06, + "loss": 0.3224, + "step": 3365 + }, + { + "epoch": 0.43, + "learning_rate": 9.125151033371417e-06, + "loss": 0.3244, + "step": 3366 + }, + { + "epoch": 0.43, + "learning_rate": 9.12456523762108e-06, + "loss": 0.3322, + "step": 3367 + }, + { + "epoch": 0.43, + "learning_rate": 9.123979264628985e-06, + "loss": 0.3641, + "step": 3368 + }, + { + "epoch": 0.43, + "learning_rate": 9.123393114420318e-06, + "loss": 0.3577, + "step": 3369 + }, + { + "epoch": 0.43, + "learning_rate": 9.122806787020266e-06, + "loss": 0.348, + "step": 3370 + }, + { + "epoch": 0.43, + "learning_rate": 9.122220282454024e-06, + "loss": 0.3536, + "step": 3371 + }, + { + "epoch": 0.43, + "learning_rate": 9.121633600746796e-06, + "loss": 0.323, + "step": 3372 + }, + { + "epoch": 0.43, + "learning_rate": 9.121046741923792e-06, + "loss": 0.3262, + "step": 3373 + }, + { + "epoch": 0.43, + "learning_rate": 9.120459706010233e-06, + "loss": 0.3157, + "step": 3374 + }, + { + "epoch": 0.43, + "learning_rate": 9.119872493031343e-06, + "loss": 0.3539, + "step": 3375 + }, + { + "epoch": 0.43, + "learning_rate": 9.119285103012356e-06, + "loss": 0.3554, + "step": 3376 + }, + { + "epoch": 0.43, + "learning_rate": 9.118697535978513e-06, + "loss": 0.3597, + "step": 3377 + }, + { + "epoch": 0.43, + "learning_rate": 9.118109791955067e-06, + "loss": 0.324, + "step": 3378 + }, + { + "epoch": 0.43, + "learning_rate": 9.11752187096727e-06, + "loss": 0.3533, + "step": 3379 + }, + { + "epoch": 0.43, + "learning_rate": 9.116933773040389e-06, + "loss": 0.3055, + "step": 3380 + }, + { + "epoch": 0.43, + "learning_rate": 9.116345498199693e-06, + "loss": 0.3287, + "step": 3381 + }, + { + "epoch": 0.43, + "learning_rate": 9.115757046470464e-06, + "loss": 0.346, + "step": 3382 + }, + { + "epoch": 0.43, + "learning_rate": 9.115168417877988e-06, + "loss": 0.3455, + "step": 3383 + }, + { + "epoch": 0.43, + "learning_rate": 9.114579612447562e-06, + "loss": 0.3378, + "step": 3384 + }, + { + "epoch": 0.43, + "learning_rate": 9.113990630204485e-06, + "loss": 0.3278, + "step": 3385 + }, + { + "epoch": 0.43, + "learning_rate": 9.113401471174068e-06, + "loss": 0.3415, + "step": 3386 + }, + { + "epoch": 0.43, + "learning_rate": 9.11281213538163e-06, + "loss": 0.3309, + "step": 3387 + }, + { + "epoch": 0.43, + "learning_rate": 9.112222622852494e-06, + "loss": 0.349, + "step": 3388 + }, + { + "epoch": 0.43, + "learning_rate": 9.111632933611993e-06, + "loss": 0.3166, + "step": 3389 + }, + { + "epoch": 0.43, + "learning_rate": 9.111043067685468e-06, + "loss": 0.3812, + "step": 3390 + }, + { + "epoch": 0.43, + "learning_rate": 9.110453025098267e-06, + "loss": 0.3253, + "step": 3391 + }, + { + "epoch": 0.43, + "learning_rate": 9.109862805875745e-06, + "loss": 0.3399, + "step": 3392 + }, + { + "epoch": 0.43, + "learning_rate": 9.109272410043265e-06, + "loss": 0.3274, + "step": 3393 + }, + { + "epoch": 0.43, + "learning_rate": 9.108681837626199e-06, + "loss": 0.3158, + "step": 3394 + }, + { + "epoch": 0.43, + "learning_rate": 9.108091088649922e-06, + "loss": 0.3338, + "step": 3395 + }, + { + "epoch": 0.43, + "learning_rate": 9.107500163139822e-06, + "loss": 0.3256, + "step": 3396 + }, + { + "epoch": 0.43, + "learning_rate": 9.106909061121291e-06, + "loss": 0.3347, + "step": 3397 + }, + { + "epoch": 0.43, + "learning_rate": 9.106317782619733e-06, + "loss": 0.3247, + "step": 3398 + }, + { + "epoch": 0.44, + "learning_rate": 9.105726327660556e-06, + "loss": 0.3327, + "step": 3399 + }, + { + "epoch": 0.44, + "learning_rate": 9.105134696269172e-06, + "loss": 0.3212, + "step": 3400 + }, + { + "epoch": 0.44, + "learning_rate": 9.10454288847101e-06, + "loss": 0.3511, + "step": 3401 + }, + { + "epoch": 0.44, + "learning_rate": 9.103950904291496e-06, + "loss": 0.3481, + "step": 3402 + }, + { + "epoch": 0.44, + "learning_rate": 9.103358743756072e-06, + "loss": 0.3493, + "step": 3403 + }, + { + "epoch": 0.44, + "learning_rate": 9.102766406890185e-06, + "loss": 0.361, + "step": 3404 + }, + { + "epoch": 0.44, + "learning_rate": 9.102173893719288e-06, + "loss": 0.3164, + "step": 3405 + }, + { + "epoch": 0.44, + "learning_rate": 9.101581204268843e-06, + "loss": 0.3114, + "step": 3406 + }, + { + "epoch": 0.44, + "learning_rate": 9.100988338564318e-06, + "loss": 0.321, + "step": 3407 + }, + { + "epoch": 0.44, + "learning_rate": 9.100395296631192e-06, + "loss": 0.3544, + "step": 3408 + }, + { + "epoch": 0.44, + "learning_rate": 9.099802078494947e-06, + "loss": 0.3208, + "step": 3409 + }, + { + "epoch": 0.44, + "learning_rate": 9.099208684181078e-06, + "loss": 0.3204, + "step": 3410 + }, + { + "epoch": 0.44, + "learning_rate": 9.098615113715078e-06, + "loss": 0.3206, + "step": 3411 + }, + { + "epoch": 0.44, + "learning_rate": 9.098021367122462e-06, + "loss": 0.3197, + "step": 3412 + }, + { + "epoch": 0.44, + "learning_rate": 9.097427444428742e-06, + "loss": 0.3702, + "step": 3413 + }, + { + "epoch": 0.44, + "learning_rate": 9.096833345659437e-06, + "loss": 0.331, + "step": 3414 + }, + { + "epoch": 0.44, + "learning_rate": 9.096239070840079e-06, + "loss": 0.3379, + "step": 3415 + }, + { + "epoch": 0.44, + "learning_rate": 9.095644619996206e-06, + "loss": 0.35, + "step": 3416 + }, + { + "epoch": 0.44, + "learning_rate": 9.095049993153362e-06, + "loss": 0.33, + "step": 3417 + }, + { + "epoch": 0.44, + "learning_rate": 9.0944551903371e-06, + "loss": 0.3237, + "step": 3418 + }, + { + "epoch": 0.44, + "learning_rate": 9.09386021157298e-06, + "loss": 0.3348, + "step": 3419 + }, + { + "epoch": 0.44, + "learning_rate": 9.09326505688657e-06, + "loss": 0.3198, + "step": 3420 + }, + { + "epoch": 0.44, + "learning_rate": 9.092669726303441e-06, + "loss": 0.3289, + "step": 3421 + }, + { + "epoch": 0.44, + "learning_rate": 9.092074219849181e-06, + "loss": 0.301, + "step": 3422 + }, + { + "epoch": 0.44, + "learning_rate": 9.09147853754938e-06, + "loss": 0.3395, + "step": 3423 + }, + { + "epoch": 0.44, + "learning_rate": 9.09088267942963e-06, + "loss": 0.3331, + "step": 3424 + }, + { + "epoch": 0.44, + "learning_rate": 9.090286645515542e-06, + "loss": 0.33, + "step": 3425 + }, + { + "epoch": 0.44, + "learning_rate": 9.089690435832729e-06, + "loss": 0.3342, + "step": 3426 + }, + { + "epoch": 0.44, + "learning_rate": 9.089094050406808e-06, + "loss": 0.3444, + "step": 3427 + }, + { + "epoch": 0.44, + "learning_rate": 9.088497489263411e-06, + "loss": 0.3229, + "step": 3428 + }, + { + "epoch": 0.44, + "learning_rate": 9.087900752428168e-06, + "loss": 0.3015, + "step": 3429 + }, + { + "epoch": 0.44, + "learning_rate": 9.087303839926727e-06, + "loss": 0.3363, + "step": 3430 + }, + { + "epoch": 0.44, + "learning_rate": 9.086706751784738e-06, + "loss": 0.3344, + "step": 3431 + }, + { + "epoch": 0.44, + "learning_rate": 9.086109488027857e-06, + "loss": 0.3364, + "step": 3432 + }, + { + "epoch": 0.44, + "learning_rate": 9.08551204868175e-06, + "loss": 0.3595, + "step": 3433 + }, + { + "epoch": 0.44, + "learning_rate": 9.084914433772094e-06, + "loss": 0.3325, + "step": 3434 + }, + { + "epoch": 0.44, + "learning_rate": 9.084316643324567e-06, + "loss": 0.3288, + "step": 3435 + }, + { + "epoch": 0.44, + "learning_rate": 9.083718677364855e-06, + "loss": 0.3135, + "step": 3436 + }, + { + "epoch": 0.44, + "learning_rate": 9.08312053591866e-06, + "loss": 0.352, + "step": 3437 + }, + { + "epoch": 0.44, + "learning_rate": 9.082522219011678e-06, + "loss": 0.3431, + "step": 3438 + }, + { + "epoch": 0.44, + "learning_rate": 9.081923726669626e-06, + "loss": 0.299, + "step": 3439 + }, + { + "epoch": 0.44, + "learning_rate": 9.081325058918222e-06, + "loss": 0.3324, + "step": 3440 + }, + { + "epoch": 0.44, + "learning_rate": 9.080726215783189e-06, + "loss": 0.3332, + "step": 3441 + }, + { + "epoch": 0.44, + "learning_rate": 9.080127197290262e-06, + "loss": 0.3191, + "step": 3442 + }, + { + "epoch": 0.44, + "learning_rate": 9.079528003465183e-06, + "loss": 0.3681, + "step": 3443 + }, + { + "epoch": 0.44, + "learning_rate": 9.0789286343337e-06, + "loss": 0.3053, + "step": 3444 + }, + { + "epoch": 0.44, + "learning_rate": 9.07832908992157e-06, + "loss": 0.3473, + "step": 3445 + }, + { + "epoch": 0.44, + "learning_rate": 9.077729370254555e-06, + "loss": 0.3349, + "step": 3446 + }, + { + "epoch": 0.44, + "learning_rate": 9.077129475358426e-06, + "loss": 0.3128, + "step": 3447 + }, + { + "epoch": 0.44, + "learning_rate": 9.076529405258966e-06, + "loss": 0.3314, + "step": 3448 + }, + { + "epoch": 0.44, + "learning_rate": 9.075929159981957e-06, + "loss": 0.3143, + "step": 3449 + }, + { + "epoch": 0.44, + "learning_rate": 9.075328739553195e-06, + "loss": 0.3231, + "step": 3450 + }, + { + "epoch": 0.44, + "learning_rate": 9.07472814399848e-06, + "loss": 0.3321, + "step": 3451 + }, + { + "epoch": 0.44, + "learning_rate": 9.074127373343623e-06, + "loss": 0.3486, + "step": 3452 + }, + { + "epoch": 0.44, + "learning_rate": 9.07352642761444e-06, + "loss": 0.3421, + "step": 3453 + }, + { + "epoch": 0.44, + "learning_rate": 9.072925306836751e-06, + "loss": 0.339, + "step": 3454 + }, + { + "epoch": 0.44, + "learning_rate": 9.072324011036392e-06, + "loss": 0.3388, + "step": 3455 + }, + { + "epoch": 0.44, + "learning_rate": 9.071722540239203e-06, + "loss": 0.3308, + "step": 3456 + }, + { + "epoch": 0.44, + "learning_rate": 9.071120894471026e-06, + "loss": 0.3288, + "step": 3457 + }, + { + "epoch": 0.44, + "learning_rate": 9.070519073757717e-06, + "loss": 0.3323, + "step": 3458 + }, + { + "epoch": 0.44, + "learning_rate": 9.06991707812514e-06, + "loss": 0.3256, + "step": 3459 + }, + { + "epoch": 0.44, + "learning_rate": 9.069314907599159e-06, + "loss": 0.3448, + "step": 3460 + }, + { + "epoch": 0.44, + "learning_rate": 9.068712562205655e-06, + "loss": 0.372, + "step": 3461 + }, + { + "epoch": 0.44, + "learning_rate": 9.06811004197051e-06, + "loss": 0.3366, + "step": 3462 + }, + { + "epoch": 0.44, + "learning_rate": 9.067507346919618e-06, + "loss": 0.3504, + "step": 3463 + }, + { + "epoch": 0.44, + "learning_rate": 9.066904477078875e-06, + "loss": 0.3521, + "step": 3464 + }, + { + "epoch": 0.44, + "learning_rate": 9.06630143247419e-06, + "loss": 0.3253, + "step": 3465 + }, + { + "epoch": 0.44, + "learning_rate": 9.065698213131477e-06, + "loss": 0.3228, + "step": 3466 + }, + { + "epoch": 0.44, + "learning_rate": 9.065094819076655e-06, + "loss": 0.297, + "step": 3467 + }, + { + "epoch": 0.44, + "learning_rate": 9.064491250335656e-06, + "loss": 0.3616, + "step": 3468 + }, + { + "epoch": 0.44, + "learning_rate": 9.063887506934417e-06, + "loss": 0.3555, + "step": 3469 + }, + { + "epoch": 0.44, + "learning_rate": 9.06328358889888e-06, + "loss": 0.332, + "step": 3470 + }, + { + "epoch": 0.44, + "learning_rate": 9.062679496254997e-06, + "loss": 0.356, + "step": 3471 + }, + { + "epoch": 0.44, + "learning_rate": 9.062075229028728e-06, + "loss": 0.3152, + "step": 3472 + }, + { + "epoch": 0.44, + "learning_rate": 9.061470787246042e-06, + "loss": 0.3445, + "step": 3473 + }, + { + "epoch": 0.44, + "learning_rate": 9.06086617093291e-06, + "loss": 0.3552, + "step": 3474 + }, + { + "epoch": 0.44, + "learning_rate": 9.060261380115314e-06, + "loss": 0.3619, + "step": 3475 + }, + { + "epoch": 0.44, + "learning_rate": 9.059656414819243e-06, + "loss": 0.3345, + "step": 3476 + }, + { + "epoch": 0.45, + "learning_rate": 9.059051275070696e-06, + "loss": 0.3396, + "step": 3477 + }, + { + "epoch": 0.45, + "learning_rate": 9.058445960895674e-06, + "loss": 0.3561, + "step": 3478 + }, + { + "epoch": 0.45, + "learning_rate": 9.057840472320192e-06, + "loss": 0.3341, + "step": 3479 + }, + { + "epoch": 0.45, + "learning_rate": 9.057234809370266e-06, + "loss": 0.3082, + "step": 3480 + }, + { + "epoch": 0.45, + "learning_rate": 9.056628972071926e-06, + "loss": 0.3393, + "step": 3481 + }, + { + "epoch": 0.45, + "learning_rate": 9.056022960451204e-06, + "loss": 0.3395, + "step": 3482 + }, + { + "epoch": 0.45, + "learning_rate": 9.055416774534142e-06, + "loss": 0.324, + "step": 3483 + }, + { + "epoch": 0.45, + "learning_rate": 9.054810414346789e-06, + "loss": 0.3049, + "step": 3484 + }, + { + "epoch": 0.45, + "learning_rate": 9.054203879915202e-06, + "loss": 0.3589, + "step": 3485 + }, + { + "epoch": 0.45, + "learning_rate": 9.053597171265447e-06, + "loss": 0.343, + "step": 3486 + }, + { + "epoch": 0.45, + "learning_rate": 9.052990288423591e-06, + "loss": 0.327, + "step": 3487 + }, + { + "epoch": 0.45, + "learning_rate": 9.052383231415717e-06, + "loss": 0.321, + "step": 3488 + }, + { + "epoch": 0.45, + "learning_rate": 9.05177600026791e-06, + "loss": 0.3287, + "step": 3489 + }, + { + "epoch": 0.45, + "learning_rate": 9.051168595006264e-06, + "loss": 0.3523, + "step": 3490 + }, + { + "epoch": 0.45, + "learning_rate": 9.050561015656882e-06, + "loss": 0.3606, + "step": 3491 + }, + { + "epoch": 0.45, + "learning_rate": 9.049953262245872e-06, + "loss": 0.3495, + "step": 3492 + }, + { + "epoch": 0.45, + "learning_rate": 9.04934533479935e-06, + "loss": 0.2941, + "step": 3493 + }, + { + "epoch": 0.45, + "learning_rate": 9.048737233343442e-06, + "loss": 0.3416, + "step": 3494 + }, + { + "epoch": 0.45, + "learning_rate": 9.048128957904277e-06, + "loss": 0.3385, + "step": 3495 + }, + { + "epoch": 0.45, + "learning_rate": 9.047520508507994e-06, + "loss": 0.3281, + "step": 3496 + }, + { + "epoch": 0.45, + "learning_rate": 9.046911885180743e-06, + "loss": 0.3389, + "step": 3497 + }, + { + "epoch": 0.45, + "learning_rate": 9.046303087948674e-06, + "loss": 0.3413, + "step": 3498 + }, + { + "epoch": 0.45, + "learning_rate": 9.045694116837948e-06, + "loss": 0.3517, + "step": 3499 + }, + { + "epoch": 0.45, + "learning_rate": 9.045084971874738e-06, + "loss": 0.3472, + "step": 3500 + }, + { + "epoch": 0.45, + "learning_rate": 9.044475653085218e-06, + "loss": 0.3328, + "step": 3501 + }, + { + "epoch": 0.45, + "learning_rate": 9.04386616049557e-06, + "loss": 0.3395, + "step": 3502 + }, + { + "epoch": 0.45, + "learning_rate": 9.043256494131987e-06, + "loss": 0.3248, + "step": 3503 + }, + { + "epoch": 0.45, + "learning_rate": 9.042646654020667e-06, + "loss": 0.328, + "step": 3504 + }, + { + "epoch": 0.45, + "learning_rate": 9.04203664018782e-06, + "loss": 0.2868, + "step": 3505 + }, + { + "epoch": 0.45, + "learning_rate": 9.041426452659654e-06, + "loss": 0.3532, + "step": 3506 + }, + { + "epoch": 0.45, + "learning_rate": 9.040816091462393e-06, + "loss": 0.296, + "step": 3507 + }, + { + "epoch": 0.45, + "learning_rate": 9.040205556622266e-06, + "loss": 0.3617, + "step": 3508 + }, + { + "epoch": 0.45, + "learning_rate": 9.039594848165507e-06, + "loss": 0.3788, + "step": 3509 + }, + { + "epoch": 0.45, + "learning_rate": 9.038983966118359e-06, + "loss": 0.3063, + "step": 3510 + }, + { + "epoch": 0.45, + "learning_rate": 9.038372910507079e-06, + "loss": 0.3223, + "step": 3511 + }, + { + "epoch": 0.45, + "learning_rate": 9.03776168135792e-06, + "loss": 0.3282, + "step": 3512 + }, + { + "epoch": 0.45, + "learning_rate": 9.037150278697147e-06, + "loss": 0.3356, + "step": 3513 + }, + { + "epoch": 0.45, + "learning_rate": 9.036538702551037e-06, + "loss": 0.2995, + "step": 3514 + }, + { + "epoch": 0.45, + "learning_rate": 9.035926952945868e-06, + "loss": 0.296, + "step": 3515 + }, + { + "epoch": 0.45, + "learning_rate": 9.035315029907928e-06, + "loss": 0.3303, + "step": 3516 + }, + { + "epoch": 0.45, + "learning_rate": 9.034702933463516e-06, + "loss": 0.3233, + "step": 3517 + }, + { + "epoch": 0.45, + "learning_rate": 9.034090663638933e-06, + "loss": 0.3494, + "step": 3518 + }, + { + "epoch": 0.45, + "learning_rate": 9.03347822046049e-06, + "loss": 0.3188, + "step": 3519 + }, + { + "epoch": 0.45, + "learning_rate": 9.032865603954504e-06, + "loss": 0.3188, + "step": 3520 + }, + { + "epoch": 0.45, + "learning_rate": 9.032252814147302e-06, + "loss": 0.3343, + "step": 3521 + }, + { + "epoch": 0.45, + "learning_rate": 9.031639851065217e-06, + "loss": 0.3148, + "step": 3522 + }, + { + "epoch": 0.45, + "learning_rate": 9.031026714734588e-06, + "loss": 0.3557, + "step": 3523 + }, + { + "epoch": 0.45, + "learning_rate": 9.03041340518176e-06, + "loss": 0.3314, + "step": 3524 + }, + { + "epoch": 0.45, + "learning_rate": 9.029799922433098e-06, + "loss": 0.3457, + "step": 3525 + }, + { + "epoch": 0.45, + "learning_rate": 9.029186266514956e-06, + "loss": 0.3253, + "step": 3526 + }, + { + "epoch": 0.45, + "learning_rate": 9.028572437453705e-06, + "loss": 0.3451, + "step": 3527 + }, + { + "epoch": 0.45, + "learning_rate": 9.027958435275726e-06, + "loss": 0.3448, + "step": 3528 + }, + { + "epoch": 0.45, + "learning_rate": 9.027344260007401e-06, + "loss": 0.3274, + "step": 3529 + }, + { + "epoch": 0.45, + "learning_rate": 9.026729911675124e-06, + "loss": 0.309, + "step": 3530 + }, + { + "epoch": 0.45, + "learning_rate": 9.026115390305295e-06, + "loss": 0.3336, + "step": 3531 + }, + { + "epoch": 0.45, + "learning_rate": 9.025500695924321e-06, + "loss": 0.3283, + "step": 3532 + }, + { + "epoch": 0.45, + "learning_rate": 9.024885828558618e-06, + "loss": 0.3441, + "step": 3533 + }, + { + "epoch": 0.45, + "learning_rate": 9.024270788234606e-06, + "loss": 0.3098, + "step": 3534 + }, + { + "epoch": 0.45, + "learning_rate": 9.023655574978716e-06, + "loss": 0.331, + "step": 3535 + }, + { + "epoch": 0.45, + "learning_rate": 9.023040188817385e-06, + "loss": 0.3356, + "step": 3536 + }, + { + "epoch": 0.45, + "learning_rate": 9.022424629777056e-06, + "loss": 0.3246, + "step": 3537 + }, + { + "epoch": 0.45, + "learning_rate": 9.021808897884183e-06, + "loss": 0.3373, + "step": 3538 + }, + { + "epoch": 0.45, + "learning_rate": 9.021192993165224e-06, + "loss": 0.3129, + "step": 3539 + }, + { + "epoch": 0.45, + "learning_rate": 9.020576915646649e-06, + "loss": 0.35, + "step": 3540 + }, + { + "epoch": 0.45, + "learning_rate": 9.019960665354926e-06, + "loss": 0.3386, + "step": 3541 + }, + { + "epoch": 0.45, + "learning_rate": 9.019344242316542e-06, + "loss": 0.3566, + "step": 3542 + }, + { + "epoch": 0.45, + "learning_rate": 9.018727646557985e-06, + "loss": 0.3251, + "step": 3543 + }, + { + "epoch": 0.45, + "learning_rate": 9.01811087810575e-06, + "loss": 0.3109, + "step": 3544 + }, + { + "epoch": 0.45, + "learning_rate": 9.01749393698634e-06, + "loss": 0.3435, + "step": 3545 + }, + { + "epoch": 0.45, + "learning_rate": 9.01687682322627e-06, + "loss": 0.3424, + "step": 3546 + }, + { + "epoch": 0.45, + "learning_rate": 9.016259536852059e-06, + "loss": 0.3304, + "step": 3547 + }, + { + "epoch": 0.45, + "learning_rate": 9.015642077890228e-06, + "loss": 0.3378, + "step": 3548 + }, + { + "epoch": 0.45, + "learning_rate": 9.015024446367315e-06, + "loss": 0.3088, + "step": 3549 + }, + { + "epoch": 0.45, + "learning_rate": 9.014406642309859e-06, + "loss": 0.329, + "step": 3550 + }, + { + "epoch": 0.45, + "learning_rate": 9.013788665744409e-06, + "loss": 0.3045, + "step": 3551 + }, + { + "epoch": 0.45, + "learning_rate": 9.01317051669752e-06, + "loss": 0.3221, + "step": 3552 + }, + { + "epoch": 0.45, + "learning_rate": 9.012552195195759e-06, + "loss": 0.3384, + "step": 3553 + }, + { + "epoch": 0.45, + "learning_rate": 9.01193370126569e-06, + "loss": 0.3242, + "step": 3554 + }, + { + "epoch": 0.46, + "learning_rate": 9.011315034933896e-06, + "loss": 0.363, + "step": 3555 + }, + { + "epoch": 0.46, + "learning_rate": 9.010696196226963e-06, + "loss": 0.3597, + "step": 3556 + }, + { + "epoch": 0.46, + "learning_rate": 9.010077185171481e-06, + "loss": 0.342, + "step": 3557 + }, + { + "epoch": 0.46, + "learning_rate": 9.009458001794052e-06, + "loss": 0.2976, + "step": 3558 + }, + { + "epoch": 0.46, + "learning_rate": 9.008838646121282e-06, + "loss": 0.3353, + "step": 3559 + }, + { + "epoch": 0.46, + "learning_rate": 9.008219118179787e-06, + "loss": 0.3228, + "step": 3560 + }, + { + "epoch": 0.46, + "learning_rate": 9.007599417996191e-06, + "loss": 0.3443, + "step": 3561 + }, + { + "epoch": 0.46, + "learning_rate": 9.006979545597123e-06, + "loss": 0.313, + "step": 3562 + }, + { + "epoch": 0.46, + "learning_rate": 9.00635950100922e-06, + "loss": 0.3564, + "step": 3563 + }, + { + "epoch": 0.46, + "learning_rate": 9.005739284259123e-06, + "loss": 0.3469, + "step": 3564 + }, + { + "epoch": 0.46, + "learning_rate": 9.00511889537349e-06, + "loss": 0.3518, + "step": 3565 + }, + { + "epoch": 0.46, + "learning_rate": 9.00449833437898e-06, + "loss": 0.3232, + "step": 3566 + }, + { + "epoch": 0.46, + "learning_rate": 9.003877601302256e-06, + "loss": 0.3595, + "step": 3567 + }, + { + "epoch": 0.46, + "learning_rate": 9.003256696169995e-06, + "loss": 0.3584, + "step": 3568 + }, + { + "epoch": 0.46, + "learning_rate": 9.002635619008877e-06, + "loss": 0.364, + "step": 3569 + }, + { + "epoch": 0.46, + "learning_rate": 9.002014369845592e-06, + "loss": 0.3264, + "step": 3570 + }, + { + "epoch": 0.46, + "learning_rate": 9.00139294870684e-06, + "loss": 0.3493, + "step": 3571 + }, + { + "epoch": 0.46, + "learning_rate": 9.000771355619318e-06, + "loss": 0.3145, + "step": 3572 + }, + { + "epoch": 0.46, + "learning_rate": 9.000149590609741e-06, + "loss": 0.3342, + "step": 3573 + }, + { + "epoch": 0.46, + "learning_rate": 8.999527653704829e-06, + "loss": 0.3517, + "step": 3574 + }, + { + "epoch": 0.46, + "learning_rate": 8.998905544931304e-06, + "loss": 0.3381, + "step": 3575 + }, + { + "epoch": 0.46, + "learning_rate": 8.998283264315903e-06, + "loss": 0.3316, + "step": 3576 + }, + { + "epoch": 0.46, + "learning_rate": 8.997660811885367e-06, + "loss": 0.3395, + "step": 3577 + }, + { + "epoch": 0.46, + "learning_rate": 8.99703818766644e-06, + "loss": 0.3347, + "step": 3578 + }, + { + "epoch": 0.46, + "learning_rate": 8.996415391685882e-06, + "loss": 0.3376, + "step": 3579 + }, + { + "epoch": 0.46, + "learning_rate": 8.995792423970454e-06, + "loss": 0.3149, + "step": 3580 + }, + { + "epoch": 0.46, + "learning_rate": 8.995169284546926e-06, + "loss": 0.3227, + "step": 3581 + }, + { + "epoch": 0.46, + "learning_rate": 8.994545973442076e-06, + "loss": 0.3093, + "step": 3582 + }, + { + "epoch": 0.46, + "learning_rate": 8.993922490682687e-06, + "loss": 0.3381, + "step": 3583 + }, + { + "epoch": 0.46, + "learning_rate": 8.993298836295556e-06, + "loss": 0.3248, + "step": 3584 + }, + { + "epoch": 0.46, + "learning_rate": 8.99267501030748e-06, + "loss": 0.3372, + "step": 3585 + }, + { + "epoch": 0.46, + "learning_rate": 8.992051012745268e-06, + "loss": 0.3425, + "step": 3586 + }, + { + "epoch": 0.46, + "learning_rate": 8.991426843635731e-06, + "loss": 0.3412, + "step": 3587 + }, + { + "epoch": 0.46, + "learning_rate": 8.990802503005695e-06, + "loss": 0.3339, + "step": 3588 + }, + { + "epoch": 0.46, + "learning_rate": 8.990177990881986e-06, + "loss": 0.3301, + "step": 3589 + }, + { + "epoch": 0.46, + "learning_rate": 8.989553307291443e-06, + "loss": 0.3227, + "step": 3590 + }, + { + "epoch": 0.46, + "learning_rate": 8.988928452260909e-06, + "loss": 0.3043, + "step": 3591 + }, + { + "epoch": 0.46, + "learning_rate": 8.988303425817235e-06, + "loss": 0.3316, + "step": 3592 + }, + { + "epoch": 0.46, + "learning_rate": 8.987678227987282e-06, + "loss": 0.3463, + "step": 3593 + }, + { + "epoch": 0.46, + "learning_rate": 8.987052858797914e-06, + "loss": 0.3661, + "step": 3594 + }, + { + "epoch": 0.46, + "learning_rate": 8.986427318276003e-06, + "loss": 0.343, + "step": 3595 + }, + { + "epoch": 0.46, + "learning_rate": 8.985801606448435e-06, + "loss": 0.3438, + "step": 3596 + }, + { + "epoch": 0.46, + "learning_rate": 8.985175723342093e-06, + "loss": 0.3384, + "step": 3597 + }, + { + "epoch": 0.46, + "learning_rate": 8.984549668983875e-06, + "loss": 0.314, + "step": 3598 + }, + { + "epoch": 0.46, + "learning_rate": 8.983923443400682e-06, + "loss": 0.3229, + "step": 3599 + }, + { + "epoch": 0.46, + "learning_rate": 8.983297046619427e-06, + "loss": 0.356, + "step": 3600 + }, + { + "epoch": 0.46, + "learning_rate": 8.982670478667029e-06, + "loss": 0.3411, + "step": 3601 + }, + { + "epoch": 0.46, + "learning_rate": 8.98204373957041e-06, + "loss": 0.3272, + "step": 3602 + }, + { + "epoch": 0.46, + "learning_rate": 8.981416829356502e-06, + "loss": 0.3289, + "step": 3603 + }, + { + "epoch": 0.46, + "learning_rate": 8.980789748052245e-06, + "loss": 0.3111, + "step": 3604 + }, + { + "epoch": 0.46, + "learning_rate": 8.980162495684587e-06, + "loss": 0.3357, + "step": 3605 + }, + { + "epoch": 0.46, + "learning_rate": 8.979535072280483e-06, + "loss": 0.3042, + "step": 3606 + }, + { + "epoch": 0.46, + "learning_rate": 8.978907477866894e-06, + "loss": 0.3724, + "step": 3607 + }, + { + "epoch": 0.46, + "learning_rate": 8.978279712470789e-06, + "loss": 0.359, + "step": 3608 + }, + { + "epoch": 0.46, + "learning_rate": 8.977651776119145e-06, + "loss": 0.316, + "step": 3609 + }, + { + "epoch": 0.46, + "learning_rate": 8.977023668838945e-06, + "loss": 0.3245, + "step": 3610 + }, + { + "epoch": 0.46, + "learning_rate": 8.976395390657181e-06, + "loss": 0.3197, + "step": 3611 + }, + { + "epoch": 0.46, + "learning_rate": 8.975766941600852e-06, + "loss": 0.3251, + "step": 3612 + }, + { + "epoch": 0.46, + "learning_rate": 8.975138321696961e-06, + "loss": 0.3505, + "step": 3613 + }, + { + "epoch": 0.46, + "learning_rate": 8.974509530972523e-06, + "loss": 0.3241, + "step": 3614 + }, + { + "epoch": 0.46, + "learning_rate": 8.973880569454561e-06, + "loss": 0.3161, + "step": 3615 + }, + { + "epoch": 0.46, + "learning_rate": 8.9732514371701e-06, + "loss": 0.3311, + "step": 3616 + }, + { + "epoch": 0.46, + "learning_rate": 8.972622134146174e-06, + "loss": 0.3447, + "step": 3617 + }, + { + "epoch": 0.46, + "learning_rate": 8.97199266040983e-06, + "loss": 0.3226, + "step": 3618 + }, + { + "epoch": 0.46, + "learning_rate": 8.971363015988115e-06, + "loss": 0.3337, + "step": 3619 + }, + { + "epoch": 0.46, + "learning_rate": 8.970733200908084e-06, + "loss": 0.3074, + "step": 3620 + }, + { + "epoch": 0.46, + "learning_rate": 8.970103215196807e-06, + "loss": 0.334, + "step": 3621 + }, + { + "epoch": 0.46, + "learning_rate": 8.96947305888135e-06, + "loss": 0.3336, + "step": 3622 + }, + { + "epoch": 0.46, + "learning_rate": 8.968842731988798e-06, + "loss": 0.3356, + "step": 3623 + }, + { + "epoch": 0.46, + "learning_rate": 8.968212234546235e-06, + "loss": 0.3191, + "step": 3624 + }, + { + "epoch": 0.46, + "learning_rate": 8.967581566580752e-06, + "loss": 0.3252, + "step": 3625 + }, + { + "epoch": 0.46, + "learning_rate": 8.966950728119453e-06, + "loss": 0.3393, + "step": 3626 + }, + { + "epoch": 0.46, + "learning_rate": 8.966319719189447e-06, + "loss": 0.3385, + "step": 3627 + }, + { + "epoch": 0.46, + "learning_rate": 8.96568853981785e-06, + "loss": 0.3443, + "step": 3628 + }, + { + "epoch": 0.46, + "learning_rate": 8.965057190031785e-06, + "loss": 0.3049, + "step": 3629 + }, + { + "epoch": 0.46, + "learning_rate": 8.96442566985838e-06, + "loss": 0.3289, + "step": 3630 + }, + { + "epoch": 0.46, + "learning_rate": 8.963793979324775e-06, + "loss": 0.3412, + "step": 3631 + }, + { + "epoch": 0.46, + "learning_rate": 8.963162118458115e-06, + "loss": 0.3586, + "step": 3632 + }, + { + "epoch": 0.47, + "learning_rate": 8.962530087285552e-06, + "loss": 0.3616, + "step": 3633 + }, + { + "epoch": 0.47, + "learning_rate": 8.961897885834247e-06, + "loss": 0.3422, + "step": 3634 + }, + { + "epoch": 0.47, + "learning_rate": 8.961265514131368e-06, + "loss": 0.323, + "step": 3635 + }, + { + "epoch": 0.47, + "learning_rate": 8.960632972204084e-06, + "loss": 0.3385, + "step": 3636 + }, + { + "epoch": 0.47, + "learning_rate": 8.960000260079582e-06, + "loss": 0.3271, + "step": 3637 + }, + { + "epoch": 0.47, + "learning_rate": 8.95936737778505e-06, + "loss": 0.3593, + "step": 3638 + }, + { + "epoch": 0.47, + "learning_rate": 8.958734325347684e-06, + "loss": 0.3352, + "step": 3639 + }, + { + "epoch": 0.47, + "learning_rate": 8.958101102794686e-06, + "loss": 0.3643, + "step": 3640 + }, + { + "epoch": 0.47, + "learning_rate": 8.95746771015327e-06, + "loss": 0.3394, + "step": 3641 + }, + { + "epoch": 0.47, + "learning_rate": 8.95683414745065e-06, + "loss": 0.3128, + "step": 3642 + }, + { + "epoch": 0.47, + "learning_rate": 8.956200414714057e-06, + "loss": 0.3201, + "step": 3643 + }, + { + "epoch": 0.47, + "learning_rate": 8.955566511970721e-06, + "loss": 0.3375, + "step": 3644 + }, + { + "epoch": 0.47, + "learning_rate": 8.954932439247882e-06, + "loss": 0.3125, + "step": 3645 + }, + { + "epoch": 0.47, + "learning_rate": 8.954298196572789e-06, + "loss": 0.3504, + "step": 3646 + }, + { + "epoch": 0.47, + "learning_rate": 8.953663783972692e-06, + "loss": 0.3886, + "step": 3647 + }, + { + "epoch": 0.47, + "learning_rate": 8.95302920147486e-06, + "loss": 0.3166, + "step": 3648 + }, + { + "epoch": 0.47, + "learning_rate": 8.95239444910656e-06, + "loss": 0.3576, + "step": 3649 + }, + { + "epoch": 0.47, + "learning_rate": 8.951759526895067e-06, + "loss": 0.3424, + "step": 3650 + }, + { + "epoch": 0.47, + "learning_rate": 8.951124434867666e-06, + "loss": 0.3263, + "step": 3651 + }, + { + "epoch": 0.47, + "learning_rate": 8.950489173051648e-06, + "loss": 0.3462, + "step": 3652 + }, + { + "epoch": 0.47, + "learning_rate": 8.949853741474312e-06, + "loss": 0.3564, + "step": 3653 + }, + { + "epoch": 0.47, + "learning_rate": 8.949218140162965e-06, + "loss": 0.3288, + "step": 3654 + }, + { + "epoch": 0.47, + "learning_rate": 8.948582369144919e-06, + "loss": 0.3351, + "step": 3655 + }, + { + "epoch": 0.47, + "learning_rate": 8.947946428447495e-06, + "loss": 0.3118, + "step": 3656 + }, + { + "epoch": 0.47, + "learning_rate": 8.94731031809802e-06, + "loss": 0.3362, + "step": 3657 + }, + { + "epoch": 0.47, + "learning_rate": 8.946674038123829e-06, + "loss": 0.332, + "step": 3658 + }, + { + "epoch": 0.47, + "learning_rate": 8.946037588552266e-06, + "loss": 0.3238, + "step": 3659 + }, + { + "epoch": 0.47, + "learning_rate": 8.945400969410678e-06, + "loss": 0.3046, + "step": 3660 + }, + { + "epoch": 0.47, + "learning_rate": 8.944764180726423e-06, + "loss": 0.3233, + "step": 3661 + }, + { + "epoch": 0.47, + "learning_rate": 8.944127222526867e-06, + "loss": 0.327, + "step": 3662 + }, + { + "epoch": 0.47, + "learning_rate": 8.94349009483938e-06, + "loss": 0.313, + "step": 3663 + }, + { + "epoch": 0.47, + "learning_rate": 8.94285279769134e-06, + "loss": 0.3226, + "step": 3664 + }, + { + "epoch": 0.47, + "learning_rate": 8.942215331110136e-06, + "loss": 0.3204, + "step": 3665 + }, + { + "epoch": 0.47, + "learning_rate": 8.941577695123158e-06, + "loss": 0.3542, + "step": 3666 + }, + { + "epoch": 0.47, + "learning_rate": 8.940939889757809e-06, + "loss": 0.3291, + "step": 3667 + }, + { + "epoch": 0.47, + "learning_rate": 8.940301915041496e-06, + "loss": 0.3265, + "step": 3668 + }, + { + "epoch": 0.47, + "learning_rate": 8.939663771001632e-06, + "loss": 0.3568, + "step": 3669 + }, + { + "epoch": 0.47, + "learning_rate": 8.939025457665644e-06, + "loss": 0.3154, + "step": 3670 + }, + { + "epoch": 0.47, + "learning_rate": 8.93838697506096e-06, + "loss": 0.3213, + "step": 3671 + }, + { + "epoch": 0.47, + "learning_rate": 8.937748323215013e-06, + "loss": 0.3194, + "step": 3672 + }, + { + "epoch": 0.47, + "learning_rate": 8.937109502155254e-06, + "loss": 0.3131, + "step": 3673 + }, + { + "epoch": 0.47, + "learning_rate": 8.93647051190913e-06, + "loss": 0.3265, + "step": 3674 + }, + { + "epoch": 0.47, + "learning_rate": 8.935831352504103e-06, + "loss": 0.3267, + "step": 3675 + }, + { + "epoch": 0.47, + "learning_rate": 8.935192023967634e-06, + "loss": 0.3209, + "step": 3676 + }, + { + "epoch": 0.47, + "learning_rate": 8.934552526327201e-06, + "loss": 0.3424, + "step": 3677 + }, + { + "epoch": 0.47, + "learning_rate": 8.933912859610284e-06, + "loss": 0.3448, + "step": 3678 + }, + { + "epoch": 0.47, + "learning_rate": 8.93327302384437e-06, + "loss": 0.3277, + "step": 3679 + }, + { + "epoch": 0.47, + "learning_rate": 8.932633019056954e-06, + "loss": 0.3519, + "step": 3680 + }, + { + "epoch": 0.47, + "learning_rate": 8.931992845275539e-06, + "loss": 0.3344, + "step": 3681 + }, + { + "epoch": 0.47, + "learning_rate": 8.931352502527633e-06, + "loss": 0.3566, + "step": 3682 + }, + { + "epoch": 0.47, + "learning_rate": 8.930711990840755e-06, + "loss": 0.3153, + "step": 3683 + }, + { + "epoch": 0.47, + "learning_rate": 8.930071310242429e-06, + "loss": 0.3103, + "step": 3684 + }, + { + "epoch": 0.47, + "learning_rate": 8.929430460760187e-06, + "loss": 0.3187, + "step": 3685 + }, + { + "epoch": 0.47, + "learning_rate": 8.928789442421564e-06, + "loss": 0.3484, + "step": 3686 + }, + { + "epoch": 0.47, + "learning_rate": 8.928148255254112e-06, + "loss": 0.3604, + "step": 3687 + }, + { + "epoch": 0.47, + "learning_rate": 8.927506899285378e-06, + "loss": 0.3024, + "step": 3688 + }, + { + "epoch": 0.47, + "learning_rate": 8.926865374542928e-06, + "loss": 0.3274, + "step": 3689 + }, + { + "epoch": 0.47, + "learning_rate": 8.926223681054326e-06, + "loss": 0.3291, + "step": 3690 + }, + { + "epoch": 0.47, + "learning_rate": 8.92558181884715e-06, + "loss": 0.3285, + "step": 3691 + }, + { + "epoch": 0.47, + "learning_rate": 8.924939787948977e-06, + "loss": 0.328, + "step": 3692 + }, + { + "epoch": 0.47, + "learning_rate": 8.924297588387404e-06, + "loss": 0.3535, + "step": 3693 + }, + { + "epoch": 0.47, + "learning_rate": 8.92365522019002e-06, + "loss": 0.3422, + "step": 3694 + }, + { + "epoch": 0.47, + "learning_rate": 8.923012683384436e-06, + "loss": 0.3138, + "step": 3695 + }, + { + "epoch": 0.47, + "learning_rate": 8.922369977998257e-06, + "loss": 0.3188, + "step": 3696 + }, + { + "epoch": 0.47, + "learning_rate": 8.921727104059107e-06, + "loss": 0.3446, + "step": 3697 + }, + { + "epoch": 0.47, + "learning_rate": 8.921084061594608e-06, + "loss": 0.3671, + "step": 3698 + }, + { + "epoch": 0.47, + "learning_rate": 8.920440850632395e-06, + "loss": 0.3352, + "step": 3699 + }, + { + "epoch": 0.47, + "learning_rate": 8.919797471200106e-06, + "loss": 0.3027, + "step": 3700 + }, + { + "epoch": 0.47, + "learning_rate": 8.91915392332539e-06, + "loss": 0.2995, + "step": 3701 + }, + { + "epoch": 0.47, + "learning_rate": 8.918510207035901e-06, + "loss": 0.3395, + "step": 3702 + }, + { + "epoch": 0.47, + "learning_rate": 8.917866322359303e-06, + "loss": 0.3197, + "step": 3703 + }, + { + "epoch": 0.47, + "learning_rate": 8.917222269323263e-06, + "loss": 0.3401, + "step": 3704 + }, + { + "epoch": 0.47, + "learning_rate": 8.916578047955458e-06, + "loss": 0.306, + "step": 3705 + }, + { + "epoch": 0.47, + "learning_rate": 8.915933658283572e-06, + "loss": 0.3451, + "step": 3706 + }, + { + "epoch": 0.47, + "learning_rate": 8.915289100335295e-06, + "loss": 0.346, + "step": 3707 + }, + { + "epoch": 0.47, + "learning_rate": 8.914644374138325e-06, + "loss": 0.3045, + "step": 3708 + }, + { + "epoch": 0.47, + "learning_rate": 8.91399947972037e-06, + "loss": 0.3176, + "step": 3709 + }, + { + "epoch": 0.47, + "learning_rate": 8.913354417109136e-06, + "loss": 0.3349, + "step": 3710 + }, + { + "epoch": 0.48, + "learning_rate": 8.91270918633235e-06, + "loss": 0.3402, + "step": 3711 + }, + { + "epoch": 0.48, + "learning_rate": 8.912063787417738e-06, + "loss": 0.3369, + "step": 3712 + }, + { + "epoch": 0.48, + "learning_rate": 8.911418220393031e-06, + "loss": 0.3222, + "step": 3713 + }, + { + "epoch": 0.48, + "learning_rate": 8.91077248528597e-06, + "loss": 0.3593, + "step": 3714 + }, + { + "epoch": 0.48, + "learning_rate": 8.910126582124307e-06, + "loss": 0.3443, + "step": 3715 + }, + { + "epoch": 0.48, + "learning_rate": 8.909480510935797e-06, + "loss": 0.3605, + "step": 3716 + }, + { + "epoch": 0.48, + "learning_rate": 8.908834271748202e-06, + "loss": 0.3277, + "step": 3717 + }, + { + "epoch": 0.48, + "learning_rate": 8.908187864589292e-06, + "loss": 0.3658, + "step": 3718 + }, + { + "epoch": 0.48, + "learning_rate": 8.907541289486847e-06, + "loss": 0.3328, + "step": 3719 + }, + { + "epoch": 0.48, + "learning_rate": 8.90689454646865e-06, + "loss": 0.3384, + "step": 3720 + }, + { + "epoch": 0.48, + "learning_rate": 8.906247635562493e-06, + "loss": 0.3195, + "step": 3721 + }, + { + "epoch": 0.48, + "learning_rate": 8.905600556796176e-06, + "loss": 0.2915, + "step": 3722 + }, + { + "epoch": 0.48, + "learning_rate": 8.904953310197504e-06, + "loss": 0.3626, + "step": 3723 + }, + { + "epoch": 0.48, + "learning_rate": 8.904305895794292e-06, + "loss": 0.3352, + "step": 3724 + }, + { + "epoch": 0.48, + "learning_rate": 8.903658313614358e-06, + "loss": 0.3227, + "step": 3725 + }, + { + "epoch": 0.48, + "learning_rate": 8.903010563685534e-06, + "loss": 0.3127, + "step": 3726 + }, + { + "epoch": 0.48, + "learning_rate": 8.902362646035655e-06, + "loss": 0.3342, + "step": 3727 + }, + { + "epoch": 0.48, + "learning_rate": 8.90171456069256e-06, + "loss": 0.304, + "step": 3728 + }, + { + "epoch": 0.48, + "learning_rate": 8.901066307684102e-06, + "loss": 0.3111, + "step": 3729 + }, + { + "epoch": 0.48, + "learning_rate": 8.900417887038136e-06, + "loss": 0.3493, + "step": 3730 + }, + { + "epoch": 0.48, + "learning_rate": 8.899769298782528e-06, + "loss": 0.3354, + "step": 3731 + }, + { + "epoch": 0.48, + "learning_rate": 8.899120542945147e-06, + "loss": 0.3356, + "step": 3732 + }, + { + "epoch": 0.48, + "learning_rate": 8.898471619553872e-06, + "loss": 0.3486, + "step": 3733 + }, + { + "epoch": 0.48, + "learning_rate": 8.89782252863659e-06, + "loss": 0.3177, + "step": 3734 + }, + { + "epoch": 0.48, + "learning_rate": 8.89717327022119e-06, + "loss": 0.3395, + "step": 3735 + }, + { + "epoch": 0.48, + "learning_rate": 8.89652384433558e-06, + "loss": 0.3404, + "step": 3736 + }, + { + "epoch": 0.48, + "learning_rate": 8.89587425100766e-06, + "loss": 0.3241, + "step": 3737 + }, + { + "epoch": 0.48, + "learning_rate": 8.895224490265346e-06, + "loss": 0.3222, + "step": 3738 + }, + { + "epoch": 0.48, + "learning_rate": 8.894574562136561e-06, + "loss": 0.3466, + "step": 3739 + }, + { + "epoch": 0.48, + "learning_rate": 8.893924466649235e-06, + "loss": 0.329, + "step": 3740 + }, + { + "epoch": 0.48, + "learning_rate": 8.893274203831302e-06, + "loss": 0.3245, + "step": 3741 + }, + { + "epoch": 0.48, + "learning_rate": 8.892623773710704e-06, + "loss": 0.3285, + "step": 3742 + }, + { + "epoch": 0.48, + "learning_rate": 8.891973176315393e-06, + "loss": 0.3191, + "step": 3743 + }, + { + "epoch": 0.48, + "learning_rate": 8.89132241167333e-06, + "loss": 0.3196, + "step": 3744 + }, + { + "epoch": 0.48, + "learning_rate": 8.890671479812472e-06, + "loss": 0.3148, + "step": 3745 + }, + { + "epoch": 0.48, + "learning_rate": 8.890020380760798e-06, + "loss": 0.3497, + "step": 3746 + }, + { + "epoch": 0.48, + "learning_rate": 8.889369114546285e-06, + "loss": 0.3288, + "step": 3747 + }, + { + "epoch": 0.48, + "learning_rate": 8.888717681196918e-06, + "loss": 0.3314, + "step": 3748 + }, + { + "epoch": 0.48, + "learning_rate": 8.888066080740692e-06, + "loss": 0.3145, + "step": 3749 + }, + { + "epoch": 0.48, + "learning_rate": 8.887414313205608e-06, + "loss": 0.3304, + "step": 3750 + }, + { + "epoch": 0.48, + "learning_rate": 8.886762378619674e-06, + "loss": 0.3527, + "step": 3751 + }, + { + "epoch": 0.48, + "learning_rate": 8.886110277010902e-06, + "loss": 0.326, + "step": 3752 + }, + { + "epoch": 0.48, + "learning_rate": 8.885458008407317e-06, + "loss": 0.3423, + "step": 3753 + }, + { + "epoch": 0.48, + "learning_rate": 8.88480557283695e-06, + "loss": 0.371, + "step": 3754 + }, + { + "epoch": 0.48, + "learning_rate": 8.884152970327833e-06, + "loss": 0.2907, + "step": 3755 + }, + { + "epoch": 0.48, + "learning_rate": 8.883500200908013e-06, + "loss": 0.3116, + "step": 3756 + }, + { + "epoch": 0.48, + "learning_rate": 8.882847264605542e-06, + "loss": 0.3188, + "step": 3757 + }, + { + "epoch": 0.48, + "learning_rate": 8.882194161448476e-06, + "loss": 0.303, + "step": 3758 + }, + { + "epoch": 0.48, + "learning_rate": 8.88154089146488e-06, + "loss": 0.3347, + "step": 3759 + }, + { + "epoch": 0.48, + "learning_rate": 8.880887454682827e-06, + "loss": 0.3603, + "step": 3760 + }, + { + "epoch": 0.48, + "learning_rate": 8.880233851130397e-06, + "loss": 0.3458, + "step": 3761 + }, + { + "epoch": 0.48, + "learning_rate": 8.879580080835677e-06, + "loss": 0.3414, + "step": 3762 + }, + { + "epoch": 0.48, + "learning_rate": 8.87892614382676e-06, + "loss": 0.3132, + "step": 3763 + }, + { + "epoch": 0.48, + "learning_rate": 8.878272040131748e-06, + "loss": 0.3381, + "step": 3764 + }, + { + "epoch": 0.48, + "learning_rate": 8.877617769778751e-06, + "loss": 0.313, + "step": 3765 + }, + { + "epoch": 0.48, + "learning_rate": 8.876963332795881e-06, + "loss": 0.3262, + "step": 3766 + }, + { + "epoch": 0.48, + "learning_rate": 8.876308729211261e-06, + "loss": 0.3452, + "step": 3767 + }, + { + "epoch": 0.48, + "learning_rate": 8.875653959053023e-06, + "loss": 0.3466, + "step": 3768 + }, + { + "epoch": 0.48, + "learning_rate": 8.874999022349303e-06, + "loss": 0.3487, + "step": 3769 + }, + { + "epoch": 0.48, + "learning_rate": 8.874343919128245e-06, + "loss": 0.3224, + "step": 3770 + }, + { + "epoch": 0.48, + "learning_rate": 8.873688649417999e-06, + "loss": 0.3257, + "step": 3771 + }, + { + "epoch": 0.48, + "learning_rate": 8.873033213246726e-06, + "loss": 0.3307, + "step": 3772 + }, + { + "epoch": 0.48, + "learning_rate": 8.87237761064259e-06, + "loss": 0.3172, + "step": 3773 + }, + { + "epoch": 0.48, + "learning_rate": 8.871721841633762e-06, + "loss": 0.3514, + "step": 3774 + }, + { + "epoch": 0.48, + "learning_rate": 8.871065906248426e-06, + "loss": 0.3475, + "step": 3775 + }, + { + "epoch": 0.48, + "learning_rate": 8.870409804514765e-06, + "loss": 0.3367, + "step": 3776 + }, + { + "epoch": 0.48, + "learning_rate": 8.869753536460976e-06, + "loss": 0.3221, + "step": 3777 + }, + { + "epoch": 0.48, + "learning_rate": 8.86909710211526e-06, + "loss": 0.307, + "step": 3778 + }, + { + "epoch": 0.48, + "learning_rate": 8.868440501505822e-06, + "loss": 0.3578, + "step": 3779 + }, + { + "epoch": 0.48, + "learning_rate": 8.867783734660883e-06, + "loss": 0.3035, + "step": 3780 + }, + { + "epoch": 0.48, + "learning_rate": 8.86712680160866e-06, + "loss": 0.3234, + "step": 3781 + }, + { + "epoch": 0.48, + "learning_rate": 8.866469702377386e-06, + "loss": 0.3342, + "step": 3782 + }, + { + "epoch": 0.48, + "learning_rate": 8.8658124369953e-06, + "loss": 0.3085, + "step": 3783 + }, + { + "epoch": 0.48, + "learning_rate": 8.865155005490643e-06, + "loss": 0.3453, + "step": 3784 + }, + { + "epoch": 0.48, + "learning_rate": 8.864497407891668e-06, + "loss": 0.3317, + "step": 3785 + }, + { + "epoch": 0.48, + "learning_rate": 8.86383964422663e-06, + "loss": 0.3388, + "step": 3786 + }, + { + "epoch": 0.48, + "learning_rate": 8.8631817145238e-06, + "loss": 0.3081, + "step": 3787 + }, + { + "epoch": 0.48, + "learning_rate": 8.862523618811448e-06, + "loss": 0.3464, + "step": 3788 + }, + { + "epoch": 0.48, + "learning_rate": 8.861865357117852e-06, + "loss": 0.3401, + "step": 3789 + }, + { + "epoch": 0.49, + "learning_rate": 8.861206929471302e-06, + "loss": 0.3319, + "step": 3790 + }, + { + "epoch": 0.49, + "learning_rate": 8.86054833590009e-06, + "loss": 0.3307, + "step": 3791 + }, + { + "epoch": 0.49, + "learning_rate": 8.859889576432519e-06, + "loss": 0.3266, + "step": 3792 + }, + { + "epoch": 0.49, + "learning_rate": 8.859230651096896e-06, + "loss": 0.3372, + "step": 3793 + }, + { + "epoch": 0.49, + "learning_rate": 8.858571559921539e-06, + "loss": 0.3432, + "step": 3794 + }, + { + "epoch": 0.49, + "learning_rate": 8.857912302934766e-06, + "loss": 0.3375, + "step": 3795 + }, + { + "epoch": 0.49, + "learning_rate": 8.857252880164908e-06, + "loss": 0.3587, + "step": 3796 + }, + { + "epoch": 0.49, + "learning_rate": 8.856593291640305e-06, + "loss": 0.3465, + "step": 3797 + }, + { + "epoch": 0.49, + "learning_rate": 8.8559335373893e-06, + "loss": 0.3206, + "step": 3798 + }, + { + "epoch": 0.49, + "learning_rate": 8.855273617440243e-06, + "loss": 0.3519, + "step": 3799 + }, + { + "epoch": 0.49, + "learning_rate": 8.854613531821491e-06, + "loss": 0.321, + "step": 3800 + }, + { + "epoch": 0.49, + "learning_rate": 8.853953280561412e-06, + "loss": 0.3797, + "step": 3801 + }, + { + "epoch": 0.49, + "learning_rate": 8.853292863688378e-06, + "loss": 0.3368, + "step": 3802 + }, + { + "epoch": 0.49, + "learning_rate": 8.852632281230766e-06, + "loss": 0.3429, + "step": 3803 + }, + { + "epoch": 0.49, + "learning_rate": 8.851971533216968e-06, + "loss": 0.3125, + "step": 3804 + }, + { + "epoch": 0.49, + "learning_rate": 8.85131061967537e-06, + "loss": 0.3211, + "step": 3805 + }, + { + "epoch": 0.49, + "learning_rate": 8.85064954063438e-06, + "loss": 0.3477, + "step": 3806 + }, + { + "epoch": 0.49, + "learning_rate": 8.849988296122402e-06, + "loss": 0.2995, + "step": 3807 + }, + { + "epoch": 0.49, + "learning_rate": 8.849326886167854e-06, + "loss": 0.3042, + "step": 3808 + }, + { + "epoch": 0.49, + "learning_rate": 8.848665310799156e-06, + "loss": 0.3319, + "step": 3809 + }, + { + "epoch": 0.49, + "learning_rate": 8.84800357004474e-06, + "loss": 0.3552, + "step": 3810 + }, + { + "epoch": 0.49, + "learning_rate": 8.847341663933038e-06, + "loss": 0.3029, + "step": 3811 + }, + { + "epoch": 0.49, + "learning_rate": 8.846679592492498e-06, + "loss": 0.3297, + "step": 3812 + }, + { + "epoch": 0.49, + "learning_rate": 8.846017355751567e-06, + "loss": 0.3343, + "step": 3813 + }, + { + "epoch": 0.49, + "learning_rate": 8.845354953738706e-06, + "loss": 0.3422, + "step": 3814 + }, + { + "epoch": 0.49, + "learning_rate": 8.844692386482379e-06, + "loss": 0.3394, + "step": 3815 + }, + { + "epoch": 0.49, + "learning_rate": 8.844029654011055e-06, + "loss": 0.3189, + "step": 3816 + }, + { + "epoch": 0.49, + "learning_rate": 8.84336675635322e-06, + "loss": 0.3565, + "step": 3817 + }, + { + "epoch": 0.49, + "learning_rate": 8.842703693537352e-06, + "loss": 0.352, + "step": 3818 + }, + { + "epoch": 0.49, + "learning_rate": 8.84204046559195e-06, + "loss": 0.3473, + "step": 3819 + }, + { + "epoch": 0.49, + "learning_rate": 8.841377072545513e-06, + "loss": 0.3248, + "step": 3820 + }, + { + "epoch": 0.49, + "learning_rate": 8.840713514426545e-06, + "loss": 0.3356, + "step": 3821 + }, + { + "epoch": 0.49, + "learning_rate": 8.840049791263567e-06, + "loss": 0.3269, + "step": 3822 + }, + { + "epoch": 0.49, + "learning_rate": 8.839385903085096e-06, + "loss": 0.301, + "step": 3823 + }, + { + "epoch": 0.49, + "learning_rate": 8.83872184991966e-06, + "loss": 0.3484, + "step": 3824 + }, + { + "epoch": 0.49, + "learning_rate": 8.8380576317958e-06, + "loss": 0.3472, + "step": 3825 + }, + { + "epoch": 0.49, + "learning_rate": 8.837393248742054e-06, + "loss": 0.2993, + "step": 3826 + }, + { + "epoch": 0.49, + "learning_rate": 8.836728700786974e-06, + "loss": 0.3001, + "step": 3827 + }, + { + "epoch": 0.49, + "learning_rate": 8.836063987959116e-06, + "loss": 0.3549, + "step": 3828 + }, + { + "epoch": 0.49, + "learning_rate": 8.835399110287046e-06, + "loss": 0.3575, + "step": 3829 + }, + { + "epoch": 0.49, + "learning_rate": 8.834734067799336e-06, + "loss": 0.3379, + "step": 3830 + }, + { + "epoch": 0.49, + "learning_rate": 8.83406886052456e-06, + "loss": 0.3241, + "step": 3831 + }, + { + "epoch": 0.49, + "learning_rate": 8.833403488491308e-06, + "loss": 0.3235, + "step": 3832 + }, + { + "epoch": 0.49, + "learning_rate": 8.83273795172817e-06, + "loss": 0.3453, + "step": 3833 + }, + { + "epoch": 0.49, + "learning_rate": 8.832072250263746e-06, + "loss": 0.3468, + "step": 3834 + }, + { + "epoch": 0.49, + "learning_rate": 8.831406384126643e-06, + "loss": 0.3264, + "step": 3835 + }, + { + "epoch": 0.49, + "learning_rate": 8.830740353345475e-06, + "loss": 0.3261, + "step": 3836 + }, + { + "epoch": 0.49, + "learning_rate": 8.830074157948862e-06, + "loss": 0.32, + "step": 3837 + }, + { + "epoch": 0.49, + "learning_rate": 8.829407797965433e-06, + "loss": 0.3066, + "step": 3838 + }, + { + "epoch": 0.49, + "learning_rate": 8.82874127342382e-06, + "loss": 0.3341, + "step": 3839 + }, + { + "epoch": 0.49, + "learning_rate": 8.82807458435267e-06, + "loss": 0.3314, + "step": 3840 + }, + { + "epoch": 0.49, + "learning_rate": 8.82740773078063e-06, + "loss": 0.3199, + "step": 3841 + }, + { + "epoch": 0.49, + "learning_rate": 8.826740712736355e-06, + "loss": 0.3423, + "step": 3842 + }, + { + "epoch": 0.49, + "learning_rate": 8.826073530248508e-06, + "loss": 0.3329, + "step": 3843 + }, + { + "epoch": 0.49, + "learning_rate": 8.82540618334576e-06, + "loss": 0.3, + "step": 3844 + }, + { + "epoch": 0.49, + "learning_rate": 8.82473867205679e-06, + "loss": 0.3281, + "step": 3845 + }, + { + "epoch": 0.49, + "learning_rate": 8.824070996410281e-06, + "loss": 0.2963, + "step": 3846 + }, + { + "epoch": 0.49, + "learning_rate": 8.823403156434924e-06, + "loss": 0.3314, + "step": 3847 + }, + { + "epoch": 0.49, + "learning_rate": 8.822735152159418e-06, + "loss": 0.2957, + "step": 3848 + }, + { + "epoch": 0.49, + "learning_rate": 8.82206698361247e-06, + "loss": 0.3272, + "step": 3849 + }, + { + "epoch": 0.49, + "learning_rate": 8.82139865082279e-06, + "loss": 0.3281, + "step": 3850 + }, + { + "epoch": 0.49, + "learning_rate": 8.8207301538191e-06, + "loss": 0.3316, + "step": 3851 + }, + { + "epoch": 0.49, + "learning_rate": 8.820061492630127e-06, + "loss": 0.346, + "step": 3852 + }, + { + "epoch": 0.49, + "learning_rate": 8.819392667284603e-06, + "loss": 0.343, + "step": 3853 + }, + { + "epoch": 0.49, + "learning_rate": 8.818723677811269e-06, + "loss": 0.3242, + "step": 3854 + }, + { + "epoch": 0.49, + "learning_rate": 8.818054524238874e-06, + "loss": 0.3425, + "step": 3855 + }, + { + "epoch": 0.49, + "learning_rate": 8.817385206596174e-06, + "loss": 0.3369, + "step": 3856 + }, + { + "epoch": 0.49, + "learning_rate": 8.81671572491193e-06, + "loss": 0.3202, + "step": 3857 + }, + { + "epoch": 0.49, + "learning_rate": 8.81604607921491e-06, + "loss": 0.338, + "step": 3858 + }, + { + "epoch": 0.49, + "learning_rate": 8.815376269533893e-06, + "loss": 0.3267, + "step": 3859 + }, + { + "epoch": 0.49, + "learning_rate": 8.814706295897659e-06, + "loss": 0.3293, + "step": 3860 + }, + { + "epoch": 0.49, + "learning_rate": 8.814036158335e-06, + "loss": 0.3087, + "step": 3861 + }, + { + "epoch": 0.49, + "learning_rate": 8.813365856874711e-06, + "loss": 0.3678, + "step": 3862 + }, + { + "epoch": 0.49, + "learning_rate": 8.8126953915456e-06, + "loss": 0.3385, + "step": 3863 + }, + { + "epoch": 0.49, + "learning_rate": 8.812024762376477e-06, + "loss": 0.3362, + "step": 3864 + }, + { + "epoch": 0.49, + "learning_rate": 8.81135396939616e-06, + "loss": 0.3057, + "step": 3865 + }, + { + "epoch": 0.49, + "learning_rate": 8.810683012633475e-06, + "loss": 0.3532, + "step": 3866 + }, + { + "epoch": 0.49, + "learning_rate": 8.810011892117254e-06, + "loss": 0.327, + "step": 3867 + }, + { + "epoch": 0.5, + "learning_rate": 8.809340607876335e-06, + "loss": 0.3181, + "step": 3868 + }, + { + "epoch": 0.5, + "learning_rate": 8.808669159939568e-06, + "loss": 0.3426, + "step": 3869 + }, + { + "epoch": 0.5, + "learning_rate": 8.807997548335806e-06, + "loss": 0.3656, + "step": 3870 + }, + { + "epoch": 0.5, + "learning_rate": 8.807325773093904e-06, + "loss": 0.2993, + "step": 3871 + }, + { + "epoch": 0.5, + "learning_rate": 8.806653834242738e-06, + "loss": 0.3192, + "step": 3872 + }, + { + "epoch": 0.5, + "learning_rate": 8.805981731811177e-06, + "loss": 0.3146, + "step": 3873 + }, + { + "epoch": 0.5, + "learning_rate": 8.805309465828105e-06, + "loss": 0.3015, + "step": 3874 + }, + { + "epoch": 0.5, + "learning_rate": 8.804637036322411e-06, + "loss": 0.3225, + "step": 3875 + }, + { + "epoch": 0.5, + "learning_rate": 8.80396444332299e-06, + "loss": 0.3382, + "step": 3876 + }, + { + "epoch": 0.5, + "learning_rate": 8.803291686858745e-06, + "loss": 0.3105, + "step": 3877 + }, + { + "epoch": 0.5, + "learning_rate": 8.802618766958586e-06, + "loss": 0.3132, + "step": 3878 + }, + { + "epoch": 0.5, + "learning_rate": 8.80194568365143e-06, + "loss": 0.3316, + "step": 3879 + }, + { + "epoch": 0.5, + "learning_rate": 8.8012724369662e-06, + "loss": 0.329, + "step": 3880 + }, + { + "epoch": 0.5, + "learning_rate": 8.800599026931827e-06, + "loss": 0.35, + "step": 3881 + }, + { + "epoch": 0.5, + "learning_rate": 8.79992545357725e-06, + "loss": 0.3361, + "step": 3882 + }, + { + "epoch": 0.5, + "learning_rate": 8.799251716931412e-06, + "loss": 0.3318, + "step": 3883 + }, + { + "epoch": 0.5, + "learning_rate": 8.798577817023269e-06, + "loss": 0.3313, + "step": 3884 + }, + { + "epoch": 0.5, + "learning_rate": 8.797903753881775e-06, + "loss": 0.3301, + "step": 3885 + }, + { + "epoch": 0.5, + "learning_rate": 8.7972295275359e-06, + "loss": 0.3615, + "step": 3886 + }, + { + "epoch": 0.5, + "learning_rate": 8.796555138014613e-06, + "loss": 0.3266, + "step": 3887 + }, + { + "epoch": 0.5, + "learning_rate": 8.795880585346899e-06, + "loss": 0.3353, + "step": 3888 + }, + { + "epoch": 0.5, + "learning_rate": 8.795205869561742e-06, + "loss": 0.3825, + "step": 3889 + }, + { + "epoch": 0.5, + "learning_rate": 8.794530990688135e-06, + "loss": 0.3576, + "step": 3890 + }, + { + "epoch": 0.5, + "learning_rate": 8.793855948755081e-06, + "loss": 0.3295, + "step": 3891 + }, + { + "epoch": 0.5, + "learning_rate": 8.793180743791587e-06, + "loss": 0.3308, + "step": 3892 + }, + { + "epoch": 0.5, + "learning_rate": 8.79250537582667e-06, + "loss": 0.336, + "step": 3893 + }, + { + "epoch": 0.5, + "learning_rate": 8.79182984488935e-06, + "loss": 0.3073, + "step": 3894 + }, + { + "epoch": 0.5, + "learning_rate": 8.791154151008657e-06, + "loss": 0.3298, + "step": 3895 + }, + { + "epoch": 0.5, + "learning_rate": 8.790478294213626e-06, + "loss": 0.346, + "step": 3896 + }, + { + "epoch": 0.5, + "learning_rate": 8.789802274533301e-06, + "loss": 0.33, + "step": 3897 + }, + { + "epoch": 0.5, + "learning_rate": 8.789126091996731e-06, + "loss": 0.3135, + "step": 3898 + }, + { + "epoch": 0.5, + "learning_rate": 8.788449746632976e-06, + "loss": 0.3695, + "step": 3899 + }, + { + "epoch": 0.5, + "learning_rate": 8.787773238471098e-06, + "loss": 0.33, + "step": 3900 + }, + { + "epoch": 0.5, + "learning_rate": 8.787096567540166e-06, + "loss": 0.3226, + "step": 3901 + }, + { + "epoch": 0.5, + "learning_rate": 8.786419733869262e-06, + "loss": 0.3595, + "step": 3902 + }, + { + "epoch": 0.5, + "learning_rate": 8.785742737487468e-06, + "loss": 0.3147, + "step": 3903 + }, + { + "epoch": 0.5, + "learning_rate": 8.78506557842388e-06, + "loss": 0.3143, + "step": 3904 + }, + { + "epoch": 0.5, + "learning_rate": 8.78438825670759e-06, + "loss": 0.2934, + "step": 3905 + }, + { + "epoch": 0.5, + "learning_rate": 8.78371077236771e-06, + "loss": 0.3151, + "step": 3906 + }, + { + "epoch": 0.5, + "learning_rate": 8.783033125433354e-06, + "loss": 0.3453, + "step": 3907 + }, + { + "epoch": 0.5, + "learning_rate": 8.782355315933638e-06, + "loss": 0.3352, + "step": 3908 + }, + { + "epoch": 0.5, + "learning_rate": 8.781677343897687e-06, + "loss": 0.3177, + "step": 3909 + }, + { + "epoch": 0.5, + "learning_rate": 8.780999209354642e-06, + "loss": 0.3193, + "step": 3910 + }, + { + "epoch": 0.5, + "learning_rate": 8.780320912333639e-06, + "loss": 0.3136, + "step": 3911 + }, + { + "epoch": 0.5, + "learning_rate": 8.779642452863827e-06, + "loss": 0.3518, + "step": 3912 + }, + { + "epoch": 0.5, + "learning_rate": 8.778963830974362e-06, + "loss": 0.3161, + "step": 3913 + }, + { + "epoch": 0.5, + "learning_rate": 8.778285046694403e-06, + "loss": 0.3589, + "step": 3914 + }, + { + "epoch": 0.5, + "learning_rate": 8.777606100053123e-06, + "loss": 0.3464, + "step": 3915 + }, + { + "epoch": 0.5, + "learning_rate": 8.776926991079696e-06, + "loss": 0.3317, + "step": 3916 + }, + { + "epoch": 0.5, + "learning_rate": 8.7762477198033e-06, + "loss": 0.3562, + "step": 3917 + }, + { + "epoch": 0.5, + "learning_rate": 8.775568286253135e-06, + "loss": 0.3267, + "step": 3918 + }, + { + "epoch": 0.5, + "learning_rate": 8.77488869045839e-06, + "loss": 0.3314, + "step": 3919 + }, + { + "epoch": 0.5, + "learning_rate": 8.77420893244827e-06, + "loss": 0.3264, + "step": 3920 + }, + { + "epoch": 0.5, + "learning_rate": 8.773529012251987e-06, + "loss": 0.3124, + "step": 3921 + }, + { + "epoch": 0.5, + "learning_rate": 8.772848929898758e-06, + "loss": 0.3305, + "step": 3922 + }, + { + "epoch": 0.5, + "learning_rate": 8.77216868541781e-06, + "loss": 0.3154, + "step": 3923 + }, + { + "epoch": 0.5, + "learning_rate": 8.771488278838368e-06, + "loss": 0.3193, + "step": 3924 + }, + { + "epoch": 0.5, + "learning_rate": 8.770807710189679e-06, + "loss": 0.3098, + "step": 3925 + }, + { + "epoch": 0.5, + "learning_rate": 8.770126979500984e-06, + "loss": 0.3147, + "step": 3926 + }, + { + "epoch": 0.5, + "learning_rate": 8.769446086801536e-06, + "loss": 0.3324, + "step": 3927 + }, + { + "epoch": 0.5, + "learning_rate": 8.768765032120595e-06, + "loss": 0.3623, + "step": 3928 + }, + { + "epoch": 0.5, + "learning_rate": 8.768083815487428e-06, + "loss": 0.34, + "step": 3929 + }, + { + "epoch": 0.5, + "learning_rate": 8.767402436931304e-06, + "loss": 0.3131, + "step": 3930 + }, + { + "epoch": 0.5, + "learning_rate": 8.76672089648151e-06, + "loss": 0.3226, + "step": 3931 + }, + { + "epoch": 0.5, + "learning_rate": 8.766039194167328e-06, + "loss": 0.3573, + "step": 3932 + }, + { + "epoch": 0.5, + "learning_rate": 8.765357330018056e-06, + "loss": 0.3065, + "step": 3933 + }, + { + "epoch": 0.5, + "learning_rate": 8.764675304062992e-06, + "loss": 0.3209, + "step": 3934 + }, + { + "epoch": 0.5, + "learning_rate": 8.763993116331448e-06, + "loss": 0.3579, + "step": 3935 + }, + { + "epoch": 0.5, + "learning_rate": 8.763310766852736e-06, + "loss": 0.3403, + "step": 3936 + }, + { + "epoch": 0.5, + "learning_rate": 8.762628255656178e-06, + "loss": 0.3282, + "step": 3937 + }, + { + "epoch": 0.5, + "learning_rate": 8.761945582771104e-06, + "loss": 0.3105, + "step": 3938 + }, + { + "epoch": 0.5, + "learning_rate": 8.76126274822685e-06, + "loss": 0.3079, + "step": 3939 + }, + { + "epoch": 0.5, + "learning_rate": 8.76057975205276e-06, + "loss": 0.3353, + "step": 3940 + }, + { + "epoch": 0.5, + "learning_rate": 8.759896594278183e-06, + "loss": 0.3324, + "step": 3941 + }, + { + "epoch": 0.5, + "learning_rate": 8.759213274932476e-06, + "loss": 0.3388, + "step": 3942 + }, + { + "epoch": 0.5, + "learning_rate": 8.758529794045e-06, + "loss": 0.3173, + "step": 3943 + }, + { + "epoch": 0.5, + "learning_rate": 8.75784615164513e-06, + "loss": 0.3332, + "step": 3944 + }, + { + "epoch": 0.5, + "learning_rate": 8.757162347762242e-06, + "loss": 0.3453, + "step": 3945 + }, + { + "epoch": 0.51, + "learning_rate": 8.75647838242572e-06, + "loss": 0.3115, + "step": 3946 + }, + { + "epoch": 0.51, + "learning_rate": 8.755794255664954e-06, + "loss": 0.3256, + "step": 3947 + }, + { + "epoch": 0.51, + "learning_rate": 8.755109967509345e-06, + "loss": 0.3425, + "step": 3948 + }, + { + "epoch": 0.51, + "learning_rate": 8.754425517988298e-06, + "loss": 0.3529, + "step": 3949 + }, + { + "epoch": 0.51, + "learning_rate": 8.753740907131226e-06, + "loss": 0.3442, + "step": 3950 + }, + { + "epoch": 0.51, + "learning_rate": 8.753056134967545e-06, + "loss": 0.3352, + "step": 3951 + }, + { + "epoch": 0.51, + "learning_rate": 8.752371201526685e-06, + "loss": 0.3194, + "step": 3952 + }, + { + "epoch": 0.51, + "learning_rate": 8.751686106838078e-06, + "loss": 0.3343, + "step": 3953 + }, + { + "epoch": 0.51, + "learning_rate": 8.751000850931162e-06, + "loss": 0.3333, + "step": 3954 + }, + { + "epoch": 0.51, + "learning_rate": 8.750315433835387e-06, + "loss": 0.3445, + "step": 3955 + }, + { + "epoch": 0.51, + "learning_rate": 8.749629855580204e-06, + "loss": 0.3319, + "step": 3956 + }, + { + "epoch": 0.51, + "learning_rate": 8.748944116195076e-06, + "loss": 0.3209, + "step": 3957 + }, + { + "epoch": 0.51, + "learning_rate": 8.74825821570947e-06, + "loss": 0.3239, + "step": 3958 + }, + { + "epoch": 0.51, + "learning_rate": 8.74757215415286e-06, + "loss": 0.3329, + "step": 3959 + }, + { + "epoch": 0.51, + "learning_rate": 8.74688593155473e-06, + "loss": 0.3075, + "step": 3960 + }, + { + "epoch": 0.51, + "learning_rate": 8.746199547944565e-06, + "loss": 0.3147, + "step": 3961 + }, + { + "epoch": 0.51, + "learning_rate": 8.745513003351862e-06, + "loss": 0.3441, + "step": 3962 + }, + { + "epoch": 0.51, + "learning_rate": 8.744826297806124e-06, + "loss": 0.3268, + "step": 3963 + }, + { + "epoch": 0.51, + "learning_rate": 8.74413943133686e-06, + "loss": 0.3031, + "step": 3964 + }, + { + "epoch": 0.51, + "learning_rate": 8.743452403973586e-06, + "loss": 0.3062, + "step": 3965 + }, + { + "epoch": 0.51, + "learning_rate": 8.742765215745825e-06, + "loss": 0.3389, + "step": 3966 + }, + { + "epoch": 0.51, + "learning_rate": 8.742077866683108e-06, + "loss": 0.3371, + "step": 3967 + }, + { + "epoch": 0.51, + "learning_rate": 8.74139035681497e-06, + "loss": 0.3019, + "step": 3968 + }, + { + "epoch": 0.51, + "learning_rate": 8.740702686170955e-06, + "loss": 0.3501, + "step": 3969 + }, + { + "epoch": 0.51, + "learning_rate": 8.740014854780616e-06, + "loss": 0.3283, + "step": 3970 + }, + { + "epoch": 0.51, + "learning_rate": 8.739326862673508e-06, + "loss": 0.3641, + "step": 3971 + }, + { + "epoch": 0.51, + "learning_rate": 8.738638709879198e-06, + "loss": 0.3414, + "step": 3972 + }, + { + "epoch": 0.51, + "learning_rate": 8.737950396427255e-06, + "loss": 0.3344, + "step": 3973 + }, + { + "epoch": 0.51, + "learning_rate": 8.73726192234726e-06, + "loss": 0.3003, + "step": 3974 + }, + { + "epoch": 0.51, + "learning_rate": 8.736573287668797e-06, + "loss": 0.3137, + "step": 3975 + }, + { + "epoch": 0.51, + "learning_rate": 8.735884492421457e-06, + "loss": 0.3545, + "step": 3976 + }, + { + "epoch": 0.51, + "learning_rate": 8.73519553663484e-06, + "loss": 0.3035, + "step": 3977 + }, + { + "epoch": 0.51, + "learning_rate": 8.734506420338554e-06, + "loss": 0.3437, + "step": 3978 + }, + { + "epoch": 0.51, + "learning_rate": 8.733817143562207e-06, + "loss": 0.3541, + "step": 3979 + }, + { + "epoch": 0.51, + "learning_rate": 8.733127706335423e-06, + "loss": 0.324, + "step": 3980 + }, + { + "epoch": 0.51, + "learning_rate": 8.732438108687829e-06, + "loss": 0.3139, + "step": 3981 + }, + { + "epoch": 0.51, + "learning_rate": 8.731748350649054e-06, + "loss": 0.3212, + "step": 3982 + }, + { + "epoch": 0.51, + "learning_rate": 8.731058432248743e-06, + "loss": 0.3416, + "step": 3983 + }, + { + "epoch": 0.51, + "learning_rate": 8.73036835351654e-06, + "loss": 0.337, + "step": 3984 + }, + { + "epoch": 0.51, + "learning_rate": 8.729678114482104e-06, + "loss": 0.3798, + "step": 3985 + }, + { + "epoch": 0.51, + "learning_rate": 8.72898771517509e-06, + "loss": 0.3406, + "step": 3986 + }, + { + "epoch": 0.51, + "learning_rate": 8.728297155625171e-06, + "loss": 0.3272, + "step": 3987 + }, + { + "epoch": 0.51, + "learning_rate": 8.727606435862018e-06, + "loss": 0.3127, + "step": 3988 + }, + { + "epoch": 0.51, + "learning_rate": 8.726915555915317e-06, + "loss": 0.3229, + "step": 3989 + }, + { + "epoch": 0.51, + "learning_rate": 8.726224515814752e-06, + "loss": 0.3526, + "step": 3990 + }, + { + "epoch": 0.51, + "learning_rate": 8.72553331559002e-06, + "loss": 0.3335, + "step": 3991 + }, + { + "epoch": 0.51, + "learning_rate": 8.724841955270827e-06, + "loss": 0.3184, + "step": 3992 + }, + { + "epoch": 0.51, + "learning_rate": 8.724150434886878e-06, + "loss": 0.3274, + "step": 3993 + }, + { + "epoch": 0.51, + "learning_rate": 8.723458754467893e-06, + "loss": 0.3438, + "step": 3994 + }, + { + "epoch": 0.51, + "learning_rate": 8.72276691404359e-06, + "loss": 0.3105, + "step": 3995 + }, + { + "epoch": 0.51, + "learning_rate": 8.722074913643703e-06, + "loss": 0.3435, + "step": 3996 + }, + { + "epoch": 0.51, + "learning_rate": 8.721382753297967e-06, + "loss": 0.3252, + "step": 3997 + }, + { + "epoch": 0.51, + "learning_rate": 8.720690433036125e-06, + "loss": 0.3316, + "step": 3998 + }, + { + "epoch": 0.51, + "learning_rate": 8.719997952887932e-06, + "loss": 0.3295, + "step": 3999 + }, + { + "epoch": 0.51, + "learning_rate": 8.719305312883137e-06, + "loss": 0.3281, + "step": 4000 + }, + { + "epoch": 0.51, + "learning_rate": 8.718612513051513e-06, + "loss": 0.2981, + "step": 4001 + }, + { + "epoch": 0.51, + "learning_rate": 8.717919553422827e-06, + "loss": 0.3223, + "step": 4002 + }, + { + "epoch": 0.51, + "learning_rate": 8.717226434026858e-06, + "loss": 0.3295, + "step": 4003 + }, + { + "epoch": 0.51, + "learning_rate": 8.71653315489339e-06, + "loss": 0.33, + "step": 4004 + }, + { + "epoch": 0.51, + "learning_rate": 8.715839716052215e-06, + "loss": 0.3013, + "step": 4005 + }, + { + "epoch": 0.51, + "learning_rate": 8.715146117533131e-06, + "loss": 0.3404, + "step": 4006 + }, + { + "epoch": 0.51, + "learning_rate": 8.714452359365943e-06, + "loss": 0.3188, + "step": 4007 + }, + { + "epoch": 0.51, + "learning_rate": 8.713758441580467e-06, + "loss": 0.3317, + "step": 4008 + }, + { + "epoch": 0.51, + "learning_rate": 8.71306436420652e-06, + "loss": 0.3365, + "step": 4009 + }, + { + "epoch": 0.51, + "learning_rate": 8.712370127273927e-06, + "loss": 0.3014, + "step": 4010 + }, + { + "epoch": 0.51, + "learning_rate": 8.711675730812522e-06, + "loss": 0.3109, + "step": 4011 + }, + { + "epoch": 0.51, + "learning_rate": 8.710981174852144e-06, + "loss": 0.3435, + "step": 4012 + }, + { + "epoch": 0.51, + "learning_rate": 8.710286459422641e-06, + "loss": 0.3273, + "step": 4013 + }, + { + "epoch": 0.51, + "learning_rate": 8.709591584553865e-06, + "loss": 0.3201, + "step": 4014 + }, + { + "epoch": 0.51, + "learning_rate": 8.708896550275675e-06, + "loss": 0.343, + "step": 4015 + }, + { + "epoch": 0.51, + "learning_rate": 8.708201356617945e-06, + "loss": 0.3128, + "step": 4016 + }, + { + "epoch": 0.51, + "learning_rate": 8.70750600361054e-06, + "loss": 0.3169, + "step": 4017 + }, + { + "epoch": 0.51, + "learning_rate": 8.706810491283346e-06, + "loss": 0.3076, + "step": 4018 + }, + { + "epoch": 0.51, + "learning_rate": 8.706114819666249e-06, + "loss": 0.3485, + "step": 4019 + }, + { + "epoch": 0.51, + "learning_rate": 8.705418988789146e-06, + "loss": 0.3288, + "step": 4020 + }, + { + "epoch": 0.51, + "learning_rate": 8.704722998681937e-06, + "loss": 0.3234, + "step": 4021 + }, + { + "epoch": 0.51, + "learning_rate": 8.704026849374527e-06, + "loss": 0.3473, + "step": 4022 + }, + { + "epoch": 0.51, + "learning_rate": 8.703330540896836e-06, + "loss": 0.3335, + "step": 4023 + }, + { + "epoch": 0.52, + "learning_rate": 8.702634073278784e-06, + "loss": 0.34, + "step": 4024 + }, + { + "epoch": 0.52, + "learning_rate": 8.701937446550298e-06, + "loss": 0.3483, + "step": 4025 + }, + { + "epoch": 0.52, + "learning_rate": 8.701240660741317e-06, + "loss": 0.3202, + "step": 4026 + }, + { + "epoch": 0.52, + "learning_rate": 8.700543715881781e-06, + "loss": 0.3347, + "step": 4027 + }, + { + "epoch": 0.52, + "learning_rate": 8.699846612001638e-06, + "loss": 0.3315, + "step": 4028 + }, + { + "epoch": 0.52, + "learning_rate": 8.699149349130848e-06, + "loss": 0.3216, + "step": 4029 + }, + { + "epoch": 0.52, + "learning_rate": 8.698451927299374e-06, + "loss": 0.3397, + "step": 4030 + }, + { + "epoch": 0.52, + "learning_rate": 8.697754346537182e-06, + "loss": 0.3394, + "step": 4031 + }, + { + "epoch": 0.52, + "learning_rate": 8.69705660687425e-06, + "loss": 0.3327, + "step": 4032 + }, + { + "epoch": 0.52, + "learning_rate": 8.696358708340562e-06, + "loss": 0.3309, + "step": 4033 + }, + { + "epoch": 0.52, + "learning_rate": 8.695660650966109e-06, + "loss": 0.3393, + "step": 4034 + }, + { + "epoch": 0.52, + "learning_rate": 8.694962434780885e-06, + "loss": 0.3465, + "step": 4035 + }, + { + "epoch": 0.52, + "learning_rate": 8.694264059814897e-06, + "loss": 0.3004, + "step": 4036 + }, + { + "epoch": 0.52, + "learning_rate": 8.693565526098156e-06, + "loss": 0.3307, + "step": 4037 + }, + { + "epoch": 0.52, + "learning_rate": 8.692866833660679e-06, + "loss": 0.3299, + "step": 4038 + }, + { + "epoch": 0.52, + "learning_rate": 8.692167982532487e-06, + "loss": 0.3237, + "step": 4039 + }, + { + "epoch": 0.52, + "learning_rate": 8.691468972743615e-06, + "loss": 0.32, + "step": 4040 + }, + { + "epoch": 0.52, + "learning_rate": 8.6907698043241e-06, + "loss": 0.3228, + "step": 4041 + }, + { + "epoch": 0.52, + "learning_rate": 8.690070477303987e-06, + "loss": 0.3167, + "step": 4042 + }, + { + "epoch": 0.52, + "learning_rate": 8.689370991713327e-06, + "loss": 0.3529, + "step": 4043 + }, + { + "epoch": 0.52, + "learning_rate": 8.688671347582178e-06, + "loss": 0.3165, + "step": 4044 + }, + { + "epoch": 0.52, + "learning_rate": 8.687971544940608e-06, + "loss": 0.3342, + "step": 4045 + }, + { + "epoch": 0.52, + "learning_rate": 8.687271583818687e-06, + "loss": 0.3459, + "step": 4046 + }, + { + "epoch": 0.52, + "learning_rate": 8.686571464246491e-06, + "loss": 0.3554, + "step": 4047 + }, + { + "epoch": 0.52, + "learning_rate": 8.685871186254112e-06, + "loss": 0.379, + "step": 4048 + }, + { + "epoch": 0.52, + "learning_rate": 8.685170749871638e-06, + "loss": 0.3299, + "step": 4049 + }, + { + "epoch": 0.52, + "learning_rate": 8.68447015512917e-06, + "loss": 0.3357, + "step": 4050 + }, + { + "epoch": 0.52, + "learning_rate": 8.683769402056814e-06, + "loss": 0.3235, + "step": 4051 + }, + { + "epoch": 0.52, + "learning_rate": 8.683068490684681e-06, + "loss": 0.3234, + "step": 4052 + }, + { + "epoch": 0.52, + "learning_rate": 8.682367421042895e-06, + "loss": 0.3262, + "step": 4053 + }, + { + "epoch": 0.52, + "learning_rate": 8.681666193161578e-06, + "loss": 0.2965, + "step": 4054 + }, + { + "epoch": 0.52, + "learning_rate": 8.680964807070865e-06, + "loss": 0.3586, + "step": 4055 + }, + { + "epoch": 0.52, + "learning_rate": 8.680263262800897e-06, + "loss": 0.3249, + "step": 4056 + }, + { + "epoch": 0.52, + "learning_rate": 8.679561560381818e-06, + "loss": 0.309, + "step": 4057 + }, + { + "epoch": 0.52, + "learning_rate": 8.678859699843787e-06, + "loss": 0.3428, + "step": 4058 + }, + { + "epoch": 0.52, + "learning_rate": 8.67815768121696e-06, + "loss": 0.3506, + "step": 4059 + }, + { + "epoch": 0.52, + "learning_rate": 8.677455504531507e-06, + "loss": 0.3108, + "step": 4060 + }, + { + "epoch": 0.52, + "learning_rate": 8.676753169817598e-06, + "loss": 0.3141, + "step": 4061 + }, + { + "epoch": 0.52, + "learning_rate": 8.676050677105419e-06, + "loss": 0.3346, + "step": 4062 + }, + { + "epoch": 0.52, + "learning_rate": 8.675348026425154e-06, + "loss": 0.3273, + "step": 4063 + }, + { + "epoch": 0.52, + "learning_rate": 8.674645217807e-06, + "loss": 0.3228, + "step": 4064 + }, + { + "epoch": 0.52, + "learning_rate": 8.673942251281158e-06, + "loss": 0.3089, + "step": 4065 + }, + { + "epoch": 0.52, + "learning_rate": 8.673239126877835e-06, + "loss": 0.3281, + "step": 4066 + }, + { + "epoch": 0.52, + "learning_rate": 8.672535844627243e-06, + "loss": 0.3322, + "step": 4067 + }, + { + "epoch": 0.52, + "learning_rate": 8.67183240455961e-06, + "loss": 0.3607, + "step": 4068 + }, + { + "epoch": 0.52, + "learning_rate": 8.671128806705159e-06, + "loss": 0.3535, + "step": 4069 + }, + { + "epoch": 0.52, + "learning_rate": 8.670425051094128e-06, + "loss": 0.3121, + "step": 4070 + }, + { + "epoch": 0.52, + "learning_rate": 8.669721137756756e-06, + "loss": 0.3578, + "step": 4071 + }, + { + "epoch": 0.52, + "learning_rate": 8.669017066723297e-06, + "loss": 0.3173, + "step": 4072 + }, + { + "epoch": 0.52, + "learning_rate": 8.668312838024002e-06, + "loss": 0.3281, + "step": 4073 + }, + { + "epoch": 0.52, + "learning_rate": 8.667608451689135e-06, + "loss": 0.3332, + "step": 4074 + }, + { + "epoch": 0.52, + "learning_rate": 8.666903907748963e-06, + "loss": 0.3233, + "step": 4075 + }, + { + "epoch": 0.52, + "learning_rate": 8.666199206233765e-06, + "loss": 0.3257, + "step": 4076 + }, + { + "epoch": 0.52, + "learning_rate": 8.665494347173822e-06, + "loss": 0.3373, + "step": 4077 + }, + { + "epoch": 0.52, + "learning_rate": 8.664789330599423e-06, + "loss": 0.3339, + "step": 4078 + }, + { + "epoch": 0.52, + "learning_rate": 8.664084156540864e-06, + "loss": 0.3297, + "step": 4079 + }, + { + "epoch": 0.52, + "learning_rate": 8.66337882502845e-06, + "loss": 0.3467, + "step": 4080 + }, + { + "epoch": 0.52, + "learning_rate": 8.662673336092487e-06, + "loss": 0.331, + "step": 4081 + }, + { + "epoch": 0.52, + "learning_rate": 8.661967689763296e-06, + "loss": 0.3178, + "step": 4082 + }, + { + "epoch": 0.52, + "learning_rate": 8.661261886071194e-06, + "loss": 0.3311, + "step": 4083 + }, + { + "epoch": 0.52, + "learning_rate": 8.660555925046518e-06, + "loss": 0.3479, + "step": 4084 + }, + { + "epoch": 0.52, + "learning_rate": 8.659849806719602e-06, + "loss": 0.3167, + "step": 4085 + }, + { + "epoch": 0.52, + "learning_rate": 8.659143531120785e-06, + "loss": 0.3251, + "step": 4086 + }, + { + "epoch": 0.52, + "learning_rate": 8.658437098280426e-06, + "loss": 0.34, + "step": 4087 + }, + { + "epoch": 0.52, + "learning_rate": 8.657730508228874e-06, + "loss": 0.3128, + "step": 4088 + }, + { + "epoch": 0.52, + "learning_rate": 8.657023760996497e-06, + "loss": 0.3336, + "step": 4089 + }, + { + "epoch": 0.52, + "learning_rate": 8.656316856613662e-06, + "loss": 0.3253, + "step": 4090 + }, + { + "epoch": 0.52, + "learning_rate": 8.655609795110751e-06, + "loss": 0.3361, + "step": 4091 + }, + { + "epoch": 0.52, + "learning_rate": 8.654902576518145e-06, + "loss": 0.3409, + "step": 4092 + }, + { + "epoch": 0.52, + "learning_rate": 8.654195200866236e-06, + "loss": 0.3121, + "step": 4093 + }, + { + "epoch": 0.52, + "learning_rate": 8.653487668185419e-06, + "loss": 0.3518, + "step": 4094 + }, + { + "epoch": 0.52, + "learning_rate": 8.652779978506103e-06, + "loss": 0.3305, + "step": 4095 + }, + { + "epoch": 0.52, + "learning_rate": 8.652072131858694e-06, + "loss": 0.3292, + "step": 4096 + }, + { + "epoch": 0.52, + "learning_rate": 8.651364128273612e-06, + "loss": 0.3422, + "step": 4097 + }, + { + "epoch": 0.52, + "learning_rate": 8.650655967781282e-06, + "loss": 0.2749, + "step": 4098 + }, + { + "epoch": 0.52, + "learning_rate": 8.649947650412135e-06, + "loss": 0.3505, + "step": 4099 + }, + { + "epoch": 0.52, + "learning_rate": 8.649239176196609e-06, + "loss": 0.3219, + "step": 4100 + }, + { + "epoch": 0.52, + "learning_rate": 8.648530545165146e-06, + "loss": 0.3462, + "step": 4101 + }, + { + "epoch": 0.53, + "learning_rate": 8.647821757348202e-06, + "loss": 0.3407, + "step": 4102 + }, + { + "epoch": 0.53, + "learning_rate": 8.647112812776231e-06, + "loss": 0.3462, + "step": 4103 + }, + { + "epoch": 0.53, + "learning_rate": 8.646403711479702e-06, + "loss": 0.2941, + "step": 4104 + }, + { + "epoch": 0.53, + "learning_rate": 8.645694453489085e-06, + "loss": 0.3296, + "step": 4105 + }, + { + "epoch": 0.53, + "learning_rate": 8.644985038834855e-06, + "loss": 0.3284, + "step": 4106 + }, + { + "epoch": 0.53, + "learning_rate": 8.644275467547502e-06, + "loss": 0.3269, + "step": 4107 + }, + { + "epoch": 0.53, + "learning_rate": 8.643565739657515e-06, + "loss": 0.3302, + "step": 4108 + }, + { + "epoch": 0.53, + "learning_rate": 8.642855855195394e-06, + "loss": 0.3132, + "step": 4109 + }, + { + "epoch": 0.53, + "learning_rate": 8.642145814191643e-06, + "loss": 0.3409, + "step": 4110 + }, + { + "epoch": 0.53, + "learning_rate": 8.641435616676776e-06, + "loss": 0.3433, + "step": 4111 + }, + { + "epoch": 0.53, + "learning_rate": 8.64072526268131e-06, + "loss": 0.3538, + "step": 4112 + }, + { + "epoch": 0.53, + "learning_rate": 8.640014752235773e-06, + "loss": 0.3129, + "step": 4113 + }, + { + "epoch": 0.53, + "learning_rate": 8.639304085370692e-06, + "loss": 0.3251, + "step": 4114 + }, + { + "epoch": 0.53, + "learning_rate": 8.638593262116612e-06, + "loss": 0.2857, + "step": 4115 + }, + { + "epoch": 0.53, + "learning_rate": 8.637882282504075e-06, + "loss": 0.3215, + "step": 4116 + }, + { + "epoch": 0.53, + "learning_rate": 8.637171146563634e-06, + "loss": 0.3299, + "step": 4117 + }, + { + "epoch": 0.53, + "learning_rate": 8.636459854325849e-06, + "loss": 0.3562, + "step": 4118 + }, + { + "epoch": 0.53, + "learning_rate": 8.635748405821285e-06, + "loss": 0.328, + "step": 4119 + }, + { + "epoch": 0.53, + "learning_rate": 8.635036801080513e-06, + "loss": 0.3557, + "step": 4120 + }, + { + "epoch": 0.53, + "learning_rate": 8.634325040134117e-06, + "loss": 0.3383, + "step": 4121 + }, + { + "epoch": 0.53, + "learning_rate": 8.63361312301268e-06, + "loss": 0.3117, + "step": 4122 + }, + { + "epoch": 0.53, + "learning_rate": 8.632901049746793e-06, + "loss": 0.3429, + "step": 4123 + }, + { + "epoch": 0.53, + "learning_rate": 8.632188820367056e-06, + "loss": 0.3365, + "step": 4124 + }, + { + "epoch": 0.53, + "learning_rate": 8.631476434904077e-06, + "loss": 0.3195, + "step": 4125 + }, + { + "epoch": 0.53, + "learning_rate": 8.63076389338847e-06, + "loss": 0.3146, + "step": 4126 + }, + { + "epoch": 0.53, + "learning_rate": 8.630051195850851e-06, + "loss": 0.3231, + "step": 4127 + }, + { + "epoch": 0.53, + "learning_rate": 8.629338342321846e-06, + "loss": 0.3461, + "step": 4128 + }, + { + "epoch": 0.53, + "learning_rate": 8.62862533283209e-06, + "loss": 0.3215, + "step": 4129 + }, + { + "epoch": 0.53, + "learning_rate": 8.627912167412222e-06, + "loss": 0.3269, + "step": 4130 + }, + { + "epoch": 0.53, + "learning_rate": 8.62719884609289e-06, + "loss": 0.3245, + "step": 4131 + }, + { + "epoch": 0.53, + "learning_rate": 8.626485368904744e-06, + "loss": 0.3334, + "step": 4132 + }, + { + "epoch": 0.53, + "learning_rate": 8.625771735878445e-06, + "loss": 0.3428, + "step": 4133 + }, + { + "epoch": 0.53, + "learning_rate": 8.625057947044662e-06, + "loss": 0.3546, + "step": 4134 + }, + { + "epoch": 0.53, + "learning_rate": 8.624344002434061e-06, + "loss": 0.3064, + "step": 4135 + }, + { + "epoch": 0.53, + "learning_rate": 8.62362990207733e-06, + "loss": 0.3176, + "step": 4136 + }, + { + "epoch": 0.53, + "learning_rate": 8.622915646005152e-06, + "loss": 0.333, + "step": 4137 + }, + { + "epoch": 0.53, + "learning_rate": 8.622201234248218e-06, + "loss": 0.3114, + "step": 4138 + }, + { + "epoch": 0.53, + "learning_rate": 8.62148666683723e-06, + "loss": 0.3142, + "step": 4139 + }, + { + "epoch": 0.53, + "learning_rate": 8.620771943802895e-06, + "loss": 0.3215, + "step": 4140 + }, + { + "epoch": 0.53, + "learning_rate": 8.620057065175926e-06, + "loss": 0.3069, + "step": 4141 + }, + { + "epoch": 0.53, + "learning_rate": 8.619342030987044e-06, + "loss": 0.3382, + "step": 4142 + }, + { + "epoch": 0.53, + "learning_rate": 8.618626841266972e-06, + "loss": 0.3113, + "step": 4143 + }, + { + "epoch": 0.53, + "learning_rate": 8.617911496046446e-06, + "loss": 0.3468, + "step": 4144 + }, + { + "epoch": 0.53, + "learning_rate": 8.617195995356206e-06, + "loss": 0.3237, + "step": 4145 + }, + { + "epoch": 0.53, + "learning_rate": 8.616480339226998e-06, + "loss": 0.3326, + "step": 4146 + }, + { + "epoch": 0.53, + "learning_rate": 8.615764527689574e-06, + "loss": 0.3314, + "step": 4147 + }, + { + "epoch": 0.53, + "learning_rate": 8.615048560774698e-06, + "loss": 0.3511, + "step": 4148 + }, + { + "epoch": 0.53, + "learning_rate": 8.614332438513132e-06, + "loss": 0.3428, + "step": 4149 + }, + { + "epoch": 0.53, + "learning_rate": 8.613616160935652e-06, + "loss": 0.3209, + "step": 4150 + }, + { + "epoch": 0.53, + "learning_rate": 8.612899728073039e-06, + "loss": 0.3321, + "step": 4151 + }, + { + "epoch": 0.53, + "learning_rate": 8.612183139956078e-06, + "loss": 0.3202, + "step": 4152 + }, + { + "epoch": 0.53, + "learning_rate": 8.611466396615562e-06, + "loss": 0.3352, + "step": 4153 + }, + { + "epoch": 0.53, + "learning_rate": 8.610749498082291e-06, + "loss": 0.3492, + "step": 4154 + }, + { + "epoch": 0.53, + "learning_rate": 8.610032444387074e-06, + "loss": 0.298, + "step": 4155 + }, + { + "epoch": 0.53, + "learning_rate": 8.609315235560722e-06, + "loss": 0.306, + "step": 4156 + }, + { + "epoch": 0.53, + "learning_rate": 8.608597871634056e-06, + "loss": 0.3449, + "step": 4157 + }, + { + "epoch": 0.53, + "learning_rate": 8.607880352637905e-06, + "loss": 0.3319, + "step": 4158 + }, + { + "epoch": 0.53, + "learning_rate": 8.607162678603097e-06, + "loss": 0.3187, + "step": 4159 + }, + { + "epoch": 0.53, + "learning_rate": 8.606444849560476e-06, + "loss": 0.3277, + "step": 4160 + }, + { + "epoch": 0.53, + "learning_rate": 8.605726865540889e-06, + "loss": 0.3425, + "step": 4161 + }, + { + "epoch": 0.53, + "learning_rate": 8.605008726575186e-06, + "loss": 0.3223, + "step": 4162 + }, + { + "epoch": 0.53, + "learning_rate": 8.60429043269423e-06, + "loss": 0.3369, + "step": 4163 + }, + { + "epoch": 0.53, + "learning_rate": 8.603571983928888e-06, + "loss": 0.3033, + "step": 4164 + }, + { + "epoch": 0.53, + "learning_rate": 8.602853380310033e-06, + "loss": 0.3243, + "step": 4165 + }, + { + "epoch": 0.53, + "learning_rate": 8.602134621868542e-06, + "loss": 0.3434, + "step": 4166 + }, + { + "epoch": 0.53, + "learning_rate": 8.601415708635304e-06, + "loss": 0.3528, + "step": 4167 + }, + { + "epoch": 0.53, + "learning_rate": 8.600696640641213e-06, + "loss": 0.3323, + "step": 4168 + }, + { + "epoch": 0.53, + "learning_rate": 8.599977417917169e-06, + "loss": 0.3344, + "step": 4169 + }, + { + "epoch": 0.53, + "learning_rate": 8.599258040494078e-06, + "loss": 0.3055, + "step": 4170 + }, + { + "epoch": 0.53, + "learning_rate": 8.59853850840285e-06, + "loss": 0.3416, + "step": 4171 + }, + { + "epoch": 0.53, + "learning_rate": 8.59781882167441e-06, + "loss": 0.3277, + "step": 4172 + }, + { + "epoch": 0.53, + "learning_rate": 8.597098980339683e-06, + "loss": 0.2994, + "step": 4173 + }, + { + "epoch": 0.53, + "learning_rate": 8.5963789844296e-06, + "loss": 0.3202, + "step": 4174 + }, + { + "epoch": 0.53, + "learning_rate": 8.595658833975104e-06, + "loss": 0.3243, + "step": 4175 + }, + { + "epoch": 0.53, + "learning_rate": 8.59493852900714e-06, + "loss": 0.3351, + "step": 4176 + }, + { + "epoch": 0.53, + "learning_rate": 8.59421806955666e-06, + "loss": 0.312, + "step": 4177 + }, + { + "epoch": 0.53, + "learning_rate": 8.593497455654627e-06, + "loss": 0.3428, + "step": 4178 + }, + { + "epoch": 0.53, + "learning_rate": 8.592776687332003e-06, + "loss": 0.3383, + "step": 4179 + }, + { + "epoch": 0.54, + "learning_rate": 8.592055764619762e-06, + "loss": 0.3352, + "step": 4180 + }, + { + "epoch": 0.54, + "learning_rate": 8.591334687548888e-06, + "loss": 0.3348, + "step": 4181 + }, + { + "epoch": 0.54, + "learning_rate": 8.590613456150364e-06, + "loss": 0.3182, + "step": 4182 + }, + { + "epoch": 0.54, + "learning_rate": 8.58989207045518e-06, + "loss": 0.3428, + "step": 4183 + }, + { + "epoch": 0.54, + "learning_rate": 8.58917053049434e-06, + "loss": 0.3245, + "step": 4184 + }, + { + "epoch": 0.54, + "learning_rate": 8.58844883629885e-06, + "loss": 0.3467, + "step": 4185 + }, + { + "epoch": 0.54, + "learning_rate": 8.58772698789972e-06, + "loss": 0.3484, + "step": 4186 + }, + { + "epoch": 0.54, + "learning_rate": 8.587004985327971e-06, + "loss": 0.3155, + "step": 4187 + }, + { + "epoch": 0.54, + "learning_rate": 8.586282828614631e-06, + "loss": 0.3175, + "step": 4188 + }, + { + "epoch": 0.54, + "learning_rate": 8.58556051779073e-06, + "loss": 0.3471, + "step": 4189 + }, + { + "epoch": 0.54, + "learning_rate": 8.584838052887308e-06, + "loss": 0.3446, + "step": 4190 + }, + { + "epoch": 0.54, + "learning_rate": 8.58411543393541e-06, + "loss": 0.3431, + "step": 4191 + }, + { + "epoch": 0.54, + "learning_rate": 8.58339266096609e-06, + "loss": 0.3191, + "step": 4192 + }, + { + "epoch": 0.54, + "learning_rate": 8.582669734010407e-06, + "loss": 0.3449, + "step": 4193 + }, + { + "epoch": 0.54, + "learning_rate": 8.581946653099427e-06, + "loss": 0.3206, + "step": 4194 + }, + { + "epoch": 0.54, + "learning_rate": 8.581223418264222e-06, + "loss": 0.3449, + "step": 4195 + }, + { + "epoch": 0.54, + "learning_rate": 8.58050002953587e-06, + "loss": 0.3348, + "step": 4196 + }, + { + "epoch": 0.54, + "learning_rate": 8.579776486945457e-06, + "loss": 0.3442, + "step": 4197 + }, + { + "epoch": 0.54, + "learning_rate": 8.579052790524077e-06, + "loss": 0.3288, + "step": 4198 + }, + { + "epoch": 0.54, + "learning_rate": 8.578328940302827e-06, + "loss": 0.3121, + "step": 4199 + }, + { + "epoch": 0.54, + "learning_rate": 8.577604936312813e-06, + "loss": 0.3204, + "step": 4200 + }, + { + "epoch": 0.54, + "learning_rate": 8.576880778585148e-06, + "loss": 0.3408, + "step": 4201 + }, + { + "epoch": 0.54, + "learning_rate": 8.57615646715095e-06, + "loss": 0.306, + "step": 4202 + }, + { + "epoch": 0.54, + "learning_rate": 8.575432002041341e-06, + "loss": 0.3216, + "step": 4203 + }, + { + "epoch": 0.54, + "learning_rate": 8.574707383287459e-06, + "loss": 0.3295, + "step": 4204 + }, + { + "epoch": 0.54, + "learning_rate": 8.57398261092044e-06, + "loss": 0.3491, + "step": 4205 + }, + { + "epoch": 0.54, + "learning_rate": 8.573257684971425e-06, + "loss": 0.3194, + "step": 4206 + }, + { + "epoch": 0.54, + "learning_rate": 8.572532605471572e-06, + "loss": 0.3278, + "step": 4207 + }, + { + "epoch": 0.54, + "learning_rate": 8.571807372452036e-06, + "loss": 0.3092, + "step": 4208 + }, + { + "epoch": 0.54, + "learning_rate": 8.571081985943984e-06, + "loss": 0.3366, + "step": 4209 + }, + { + "epoch": 0.54, + "learning_rate": 8.570356445978583e-06, + "loss": 0.3017, + "step": 4210 + }, + { + "epoch": 0.54, + "learning_rate": 8.569630752587014e-06, + "loss": 0.2927, + "step": 4211 + }, + { + "epoch": 0.54, + "learning_rate": 8.568904905800464e-06, + "loss": 0.3488, + "step": 4212 + }, + { + "epoch": 0.54, + "learning_rate": 8.56817890565012e-06, + "loss": 0.3335, + "step": 4213 + }, + { + "epoch": 0.54, + "learning_rate": 8.567452752167183e-06, + "loss": 0.3619, + "step": 4214 + }, + { + "epoch": 0.54, + "learning_rate": 8.566726445382854e-06, + "loss": 0.3282, + "step": 4215 + }, + { + "epoch": 0.54, + "learning_rate": 8.565999985328348e-06, + "loss": 0.3227, + "step": 4216 + }, + { + "epoch": 0.54, + "learning_rate": 8.565273372034879e-06, + "loss": 0.3104, + "step": 4217 + }, + { + "epoch": 0.54, + "learning_rate": 8.564546605533674e-06, + "loss": 0.33, + "step": 4218 + }, + { + "epoch": 0.54, + "learning_rate": 8.563819685855963e-06, + "loss": 0.3299, + "step": 4219 + }, + { + "epoch": 0.54, + "learning_rate": 8.563092613032981e-06, + "loss": 0.3175, + "step": 4220 + }, + { + "epoch": 0.54, + "learning_rate": 8.562365387095977e-06, + "loss": 0.3425, + "step": 4221 + }, + { + "epoch": 0.54, + "learning_rate": 8.561638008076197e-06, + "loss": 0.3532, + "step": 4222 + }, + { + "epoch": 0.54, + "learning_rate": 8.5609104760049e-06, + "loss": 0.318, + "step": 4223 + }, + { + "epoch": 0.54, + "learning_rate": 8.560182790913349e-06, + "loss": 0.3252, + "step": 4224 + }, + { + "epoch": 0.54, + "learning_rate": 8.559454952832815e-06, + "loss": 0.3149, + "step": 4225 + }, + { + "epoch": 0.54, + "learning_rate": 8.558726961794573e-06, + "loss": 0.3362, + "step": 4226 + }, + { + "epoch": 0.54, + "learning_rate": 8.557998817829909e-06, + "loss": 0.3423, + "step": 4227 + }, + { + "epoch": 0.54, + "learning_rate": 8.557270520970111e-06, + "loss": 0.3079, + "step": 4228 + }, + { + "epoch": 0.54, + "learning_rate": 8.556542071246476e-06, + "loss": 0.3008, + "step": 4229 + }, + { + "epoch": 0.54, + "learning_rate": 8.555813468690309e-06, + "loss": 0.3425, + "step": 4230 + }, + { + "epoch": 0.54, + "learning_rate": 8.555084713332917e-06, + "loss": 0.3289, + "step": 4231 + }, + { + "epoch": 0.54, + "learning_rate": 8.554355805205616e-06, + "loss": 0.3441, + "step": 4232 + }, + { + "epoch": 0.54, + "learning_rate": 8.553626744339732e-06, + "loss": 0.3074, + "step": 4233 + }, + { + "epoch": 0.54, + "learning_rate": 8.552897530766592e-06, + "loss": 0.3341, + "step": 4234 + }, + { + "epoch": 0.54, + "learning_rate": 8.552168164517532e-06, + "loss": 0.3195, + "step": 4235 + }, + { + "epoch": 0.54, + "learning_rate": 8.551438645623896e-06, + "loss": 0.3615, + "step": 4236 + }, + { + "epoch": 0.54, + "learning_rate": 8.55070897411703e-06, + "loss": 0.3126, + "step": 4237 + }, + { + "epoch": 0.54, + "learning_rate": 8.549979150028292e-06, + "loss": 0.326, + "step": 4238 + }, + { + "epoch": 0.54, + "learning_rate": 8.549249173389045e-06, + "loss": 0.3451, + "step": 4239 + }, + { + "epoch": 0.54, + "learning_rate": 8.548519044230654e-06, + "loss": 0.3028, + "step": 4240 + }, + { + "epoch": 0.54, + "learning_rate": 8.5477887625845e-06, + "loss": 0.3563, + "step": 4241 + }, + { + "epoch": 0.54, + "learning_rate": 8.547058328481959e-06, + "loss": 0.3465, + "step": 4242 + }, + { + "epoch": 0.54, + "learning_rate": 8.546327741954423e-06, + "loss": 0.3277, + "step": 4243 + }, + { + "epoch": 0.54, + "learning_rate": 8.545597003033286e-06, + "loss": 0.3241, + "step": 4244 + }, + { + "epoch": 0.54, + "learning_rate": 8.544866111749948e-06, + "loss": 0.307, + "step": 4245 + }, + { + "epoch": 0.54, + "learning_rate": 8.544135068135819e-06, + "loss": 0.3379, + "step": 4246 + }, + { + "epoch": 0.54, + "learning_rate": 8.543403872222313e-06, + "loss": 0.3423, + "step": 4247 + }, + { + "epoch": 0.54, + "learning_rate": 8.54267252404085e-06, + "loss": 0.3283, + "step": 4248 + }, + { + "epoch": 0.54, + "learning_rate": 8.54194102362286e-06, + "loss": 0.3684, + "step": 4249 + }, + { + "epoch": 0.54, + "learning_rate": 8.541209370999777e-06, + "loss": 0.3192, + "step": 4250 + }, + { + "epoch": 0.54, + "learning_rate": 8.540477566203039e-06, + "loss": 0.3309, + "step": 4251 + }, + { + "epoch": 0.54, + "learning_rate": 8.539745609264094e-06, + "loss": 0.3118, + "step": 4252 + }, + { + "epoch": 0.54, + "learning_rate": 8.539013500214399e-06, + "loss": 0.3355, + "step": 4253 + }, + { + "epoch": 0.54, + "learning_rate": 8.538281239085411e-06, + "loss": 0.3426, + "step": 4254 + }, + { + "epoch": 0.54, + "learning_rate": 8.537548825908597e-06, + "loss": 0.3457, + "step": 4255 + }, + { + "epoch": 0.54, + "learning_rate": 8.536816260715433e-06, + "loss": 0.3298, + "step": 4256 + }, + { + "epoch": 0.54, + "learning_rate": 8.536083543537396e-06, + "loss": 0.32, + "step": 4257 + }, + { + "epoch": 0.55, + "learning_rate": 8.535350674405975e-06, + "loss": 0.3394, + "step": 4258 + }, + { + "epoch": 0.55, + "learning_rate": 8.534617653352661e-06, + "loss": 0.3489, + "step": 4259 + }, + { + "epoch": 0.55, + "learning_rate": 8.533884480408955e-06, + "loss": 0.3573, + "step": 4260 + }, + { + "epoch": 0.55, + "learning_rate": 8.533151155606364e-06, + "loss": 0.3331, + "step": 4261 + }, + { + "epoch": 0.55, + "learning_rate": 8.532417678976398e-06, + "loss": 0.3076, + "step": 4262 + }, + { + "epoch": 0.55, + "learning_rate": 8.531684050550575e-06, + "loss": 0.3311, + "step": 4263 + }, + { + "epoch": 0.55, + "learning_rate": 8.530950270360425e-06, + "loss": 0.3055, + "step": 4264 + }, + { + "epoch": 0.55, + "learning_rate": 8.530216338437478e-06, + "loss": 0.3429, + "step": 4265 + }, + { + "epoch": 0.55, + "learning_rate": 8.529482254813272e-06, + "loss": 0.3337, + "step": 4266 + }, + { + "epoch": 0.55, + "learning_rate": 8.528748019519352e-06, + "loss": 0.3323, + "step": 4267 + }, + { + "epoch": 0.55, + "learning_rate": 8.528013632587272e-06, + "loss": 0.3361, + "step": 4268 + }, + { + "epoch": 0.55, + "learning_rate": 8.52727909404859e-06, + "loss": 0.326, + "step": 4269 + }, + { + "epoch": 0.55, + "learning_rate": 8.526544403934868e-06, + "loss": 0.3328, + "step": 4270 + }, + { + "epoch": 0.55, + "learning_rate": 8.52580956227768e-06, + "loss": 0.3241, + "step": 4271 + }, + { + "epoch": 0.55, + "learning_rate": 8.525074569108603e-06, + "loss": 0.3133, + "step": 4272 + }, + { + "epoch": 0.55, + "learning_rate": 8.524339424459219e-06, + "loss": 0.3302, + "step": 4273 + }, + { + "epoch": 0.55, + "learning_rate": 8.523604128361123e-06, + "loss": 0.3411, + "step": 4274 + }, + { + "epoch": 0.55, + "learning_rate": 8.522868680845908e-06, + "loss": 0.3433, + "step": 4275 + }, + { + "epoch": 0.55, + "learning_rate": 8.52213308194518e-06, + "loss": 0.3625, + "step": 4276 + }, + { + "epoch": 0.55, + "learning_rate": 8.521397331690551e-06, + "loss": 0.3566, + "step": 4277 + }, + { + "epoch": 0.55, + "learning_rate": 8.520661430113637e-06, + "loss": 0.3267, + "step": 4278 + }, + { + "epoch": 0.55, + "learning_rate": 8.519925377246057e-06, + "loss": 0.3366, + "step": 4279 + }, + { + "epoch": 0.55, + "learning_rate": 8.519189173119446e-06, + "loss": 0.2967, + "step": 4280 + }, + { + "epoch": 0.55, + "learning_rate": 8.518452817765438e-06, + "loss": 0.3264, + "step": 4281 + }, + { + "epoch": 0.55, + "learning_rate": 8.517716311215678e-06, + "loss": 0.3015, + "step": 4282 + }, + { + "epoch": 0.55, + "learning_rate": 8.516979653501813e-06, + "loss": 0.35, + "step": 4283 + }, + { + "epoch": 0.55, + "learning_rate": 8.516242844655498e-06, + "loss": 0.3246, + "step": 4284 + }, + { + "epoch": 0.55, + "learning_rate": 8.515505884708399e-06, + "loss": 0.3418, + "step": 4285 + }, + { + "epoch": 0.55, + "learning_rate": 8.514768773692182e-06, + "loss": 0.3673, + "step": 4286 + }, + { + "epoch": 0.55, + "learning_rate": 8.514031511638524e-06, + "loss": 0.2969, + "step": 4287 + }, + { + "epoch": 0.55, + "learning_rate": 8.513294098579103e-06, + "loss": 0.3394, + "step": 4288 + }, + { + "epoch": 0.55, + "learning_rate": 8.512556534545612e-06, + "loss": 0.3445, + "step": 4289 + }, + { + "epoch": 0.55, + "learning_rate": 8.511818819569743e-06, + "loss": 0.3249, + "step": 4290 + }, + { + "epoch": 0.55, + "learning_rate": 8.5110809536832e-06, + "loss": 0.3163, + "step": 4291 + }, + { + "epoch": 0.55, + "learning_rate": 8.510342936917685e-06, + "loss": 0.2976, + "step": 4292 + }, + { + "epoch": 0.55, + "learning_rate": 8.50960476930492e-06, + "loss": 0.3222, + "step": 4293 + }, + { + "epoch": 0.55, + "learning_rate": 8.50886645087662e-06, + "loss": 0.3186, + "step": 4294 + }, + { + "epoch": 0.55, + "learning_rate": 8.508127981664514e-06, + "loss": 0.3193, + "step": 4295 + }, + { + "epoch": 0.55, + "learning_rate": 8.507389361700335e-06, + "loss": 0.3015, + "step": 4296 + }, + { + "epoch": 0.55, + "learning_rate": 8.506650591015825e-06, + "loss": 0.3358, + "step": 4297 + }, + { + "epoch": 0.55, + "learning_rate": 8.50591166964273e-06, + "loss": 0.3447, + "step": 4298 + }, + { + "epoch": 0.55, + "learning_rate": 8.5051725976128e-06, + "loss": 0.3216, + "step": 4299 + }, + { + "epoch": 0.55, + "learning_rate": 8.504433374957799e-06, + "loss": 0.3279, + "step": 4300 + }, + { + "epoch": 0.55, + "learning_rate": 8.50369400170949e-06, + "loss": 0.3117, + "step": 4301 + }, + { + "epoch": 0.55, + "learning_rate": 8.502954477899647e-06, + "loss": 0.3061, + "step": 4302 + }, + { + "epoch": 0.55, + "learning_rate": 8.50221480356005e-06, + "loss": 0.3302, + "step": 4303 + }, + { + "epoch": 0.55, + "learning_rate": 8.50147497872248e-06, + "loss": 0.322, + "step": 4304 + }, + { + "epoch": 0.55, + "learning_rate": 8.500735003418734e-06, + "loss": 0.3244, + "step": 4305 + }, + { + "epoch": 0.55, + "learning_rate": 8.499994877680609e-06, + "loss": 0.305, + "step": 4306 + }, + { + "epoch": 0.55, + "learning_rate": 8.499254601539908e-06, + "loss": 0.3142, + "step": 4307 + }, + { + "epoch": 0.55, + "learning_rate": 8.498514175028442e-06, + "loss": 0.3357, + "step": 4308 + }, + { + "epoch": 0.55, + "learning_rate": 8.497773598178033e-06, + "loss": 0.3078, + "step": 4309 + }, + { + "epoch": 0.55, + "learning_rate": 8.497032871020501e-06, + "loss": 0.3418, + "step": 4310 + }, + { + "epoch": 0.55, + "learning_rate": 8.49629199358768e-06, + "loss": 0.3406, + "step": 4311 + }, + { + "epoch": 0.55, + "learning_rate": 8.495550965911403e-06, + "loss": 0.3639, + "step": 4312 + }, + { + "epoch": 0.55, + "learning_rate": 8.494809788023518e-06, + "loss": 0.312, + "step": 4313 + }, + { + "epoch": 0.55, + "learning_rate": 8.494068459955871e-06, + "loss": 0.3241, + "step": 4314 + }, + { + "epoch": 0.55, + "learning_rate": 8.493326981740322e-06, + "loss": 0.3124, + "step": 4315 + }, + { + "epoch": 0.55, + "learning_rate": 8.492585353408732e-06, + "loss": 0.3122, + "step": 4316 + }, + { + "epoch": 0.55, + "learning_rate": 8.491843574992971e-06, + "loss": 0.326, + "step": 4317 + }, + { + "epoch": 0.55, + "learning_rate": 8.491101646524916e-06, + "loss": 0.3139, + "step": 4318 + }, + { + "epoch": 0.55, + "learning_rate": 8.490359568036446e-06, + "loss": 0.3407, + "step": 4319 + }, + { + "epoch": 0.55, + "learning_rate": 8.489617339559455e-06, + "loss": 0.3216, + "step": 4320 + }, + { + "epoch": 0.55, + "learning_rate": 8.488874961125832e-06, + "loss": 0.3066, + "step": 4321 + }, + { + "epoch": 0.55, + "learning_rate": 8.488132432767483e-06, + "loss": 0.3476, + "step": 4322 + }, + { + "epoch": 0.55, + "learning_rate": 8.487389754516315e-06, + "loss": 0.3451, + "step": 4323 + }, + { + "epoch": 0.55, + "learning_rate": 8.486646926404243e-06, + "loss": 0.2944, + "step": 4324 + }, + { + "epoch": 0.55, + "learning_rate": 8.485903948463185e-06, + "loss": 0.3105, + "step": 4325 + }, + { + "epoch": 0.55, + "learning_rate": 8.485160820725073e-06, + "loss": 0.2934, + "step": 4326 + }, + { + "epoch": 0.55, + "learning_rate": 8.484417543221839e-06, + "loss": 0.3391, + "step": 4327 + }, + { + "epoch": 0.55, + "learning_rate": 8.483674115985421e-06, + "loss": 0.312, + "step": 4328 + }, + { + "epoch": 0.55, + "learning_rate": 8.48293053904777e-06, + "loss": 0.3107, + "step": 4329 + }, + { + "epoch": 0.55, + "learning_rate": 8.482186812440836e-06, + "loss": 0.3156, + "step": 4330 + }, + { + "epoch": 0.55, + "learning_rate": 8.481442936196578e-06, + "loss": 0.3256, + "step": 4331 + }, + { + "epoch": 0.55, + "learning_rate": 8.480698910346965e-06, + "loss": 0.3464, + "step": 4332 + }, + { + "epoch": 0.55, + "learning_rate": 8.479954734923967e-06, + "loss": 0.3248, + "step": 4333 + }, + { + "epoch": 0.55, + "learning_rate": 8.479210409959565e-06, + "loss": 0.3154, + "step": 4334 + }, + { + "epoch": 0.55, + "learning_rate": 8.478465935485741e-06, + "loss": 0.302, + "step": 4335 + }, + { + "epoch": 0.56, + "learning_rate": 8.47772131153449e-06, + "loss": 0.3181, + "step": 4336 + }, + { + "epoch": 0.56, + "learning_rate": 8.476976538137809e-06, + "loss": 0.363, + "step": 4337 + }, + { + "epoch": 0.56, + "learning_rate": 8.476231615327703e-06, + "loss": 0.3138, + "step": 4338 + }, + { + "epoch": 0.56, + "learning_rate": 8.475486543136181e-06, + "loss": 0.3176, + "step": 4339 + }, + { + "epoch": 0.56, + "learning_rate": 8.474741321595263e-06, + "loss": 0.3648, + "step": 4340 + }, + { + "epoch": 0.56, + "learning_rate": 8.473995950736973e-06, + "loss": 0.3219, + "step": 4341 + }, + { + "epoch": 0.56, + "learning_rate": 8.473250430593338e-06, + "loss": 0.3198, + "step": 4342 + }, + { + "epoch": 0.56, + "learning_rate": 8.472504761196397e-06, + "loss": 0.3128, + "step": 4343 + }, + { + "epoch": 0.56, + "learning_rate": 8.471758942578193e-06, + "loss": 0.3406, + "step": 4344 + }, + { + "epoch": 0.56, + "learning_rate": 8.471012974770776e-06, + "loss": 0.3145, + "step": 4345 + }, + { + "epoch": 0.56, + "learning_rate": 8.4702668578062e-06, + "loss": 0.3076, + "step": 4346 + }, + { + "epoch": 0.56, + "learning_rate": 8.46952059171653e-06, + "loss": 0.325, + "step": 4347 + }, + { + "epoch": 0.56, + "learning_rate": 8.468774176533831e-06, + "loss": 0.3458, + "step": 4348 + }, + { + "epoch": 0.56, + "learning_rate": 8.46802761229018e-06, + "loss": 0.3446, + "step": 4349 + }, + { + "epoch": 0.56, + "learning_rate": 8.46728089901766e-06, + "loss": 0.3233, + "step": 4350 + }, + { + "epoch": 0.56, + "learning_rate": 8.466534036748359e-06, + "loss": 0.3214, + "step": 4351 + }, + { + "epoch": 0.56, + "learning_rate": 8.465787025514368e-06, + "loss": 0.3363, + "step": 4352 + }, + { + "epoch": 0.56, + "learning_rate": 8.465039865347791e-06, + "loss": 0.3265, + "step": 4353 + }, + { + "epoch": 0.56, + "learning_rate": 8.464292556280734e-06, + "loss": 0.343, + "step": 4354 + }, + { + "epoch": 0.56, + "learning_rate": 8.463545098345308e-06, + "loss": 0.3347, + "step": 4355 + }, + { + "epoch": 0.56, + "learning_rate": 8.462797491573638e-06, + "loss": 0.3465, + "step": 4356 + }, + { + "epoch": 0.56, + "learning_rate": 8.462049735997848e-06, + "loss": 0.3103, + "step": 4357 + }, + { + "epoch": 0.56, + "learning_rate": 8.46130183165007e-06, + "loss": 0.346, + "step": 4358 + }, + { + "epoch": 0.56, + "learning_rate": 8.46055377856244e-06, + "loss": 0.3032, + "step": 4359 + }, + { + "epoch": 0.56, + "learning_rate": 8.459805576767111e-06, + "loss": 0.3612, + "step": 4360 + }, + { + "epoch": 0.56, + "learning_rate": 8.459057226296232e-06, + "loss": 0.3175, + "step": 4361 + }, + { + "epoch": 0.56, + "learning_rate": 8.458308727181956e-06, + "loss": 0.2946, + "step": 4362 + }, + { + "epoch": 0.56, + "learning_rate": 8.457560079456455e-06, + "loss": 0.306, + "step": 4363 + }, + { + "epoch": 0.56, + "learning_rate": 8.456811283151896e-06, + "loss": 0.3304, + "step": 4364 + }, + { + "epoch": 0.56, + "learning_rate": 8.456062338300458e-06, + "loss": 0.3516, + "step": 4365 + }, + { + "epoch": 0.56, + "learning_rate": 8.455313244934324e-06, + "loss": 0.3254, + "step": 4366 + }, + { + "epoch": 0.56, + "learning_rate": 8.454564003085685e-06, + "loss": 0.314, + "step": 4367 + }, + { + "epoch": 0.56, + "learning_rate": 8.453814612786736e-06, + "loss": 0.2919, + "step": 4368 + }, + { + "epoch": 0.56, + "learning_rate": 8.453065074069682e-06, + "loss": 0.3171, + "step": 4369 + }, + { + "epoch": 0.56, + "learning_rate": 8.45231538696673e-06, + "loss": 0.3255, + "step": 4370 + }, + { + "epoch": 0.56, + "learning_rate": 8.451565551510097e-06, + "loss": 0.331, + "step": 4371 + }, + { + "epoch": 0.56, + "learning_rate": 8.450815567732007e-06, + "loss": 0.3321, + "step": 4372 + }, + { + "epoch": 0.56, + "learning_rate": 8.450065435664686e-06, + "loss": 0.3452, + "step": 4373 + }, + { + "epoch": 0.56, + "learning_rate": 8.449315155340369e-06, + "loss": 0.3233, + "step": 4374 + }, + { + "epoch": 0.56, + "learning_rate": 8.4485647267913e-06, + "loss": 0.344, + "step": 4375 + }, + { + "epoch": 0.56, + "learning_rate": 8.44781415004972e-06, + "loss": 0.3469, + "step": 4376 + }, + { + "epoch": 0.56, + "learning_rate": 8.447063425147891e-06, + "loss": 0.3462, + "step": 4377 + }, + { + "epoch": 0.56, + "learning_rate": 8.446312552118068e-06, + "loss": 0.299, + "step": 4378 + }, + { + "epoch": 0.56, + "learning_rate": 8.44556153099252e-06, + "loss": 0.3154, + "step": 4379 + }, + { + "epoch": 0.56, + "learning_rate": 8.44481036180352e-06, + "loss": 0.3255, + "step": 4380 + }, + { + "epoch": 0.56, + "learning_rate": 8.444059044583344e-06, + "loss": 0.3334, + "step": 4381 + }, + { + "epoch": 0.56, + "learning_rate": 8.443307579364282e-06, + "loss": 0.3325, + "step": 4382 + }, + { + "epoch": 0.56, + "learning_rate": 8.442555966178626e-06, + "loss": 0.3163, + "step": 4383 + }, + { + "epoch": 0.56, + "learning_rate": 8.441804205058672e-06, + "loss": 0.3226, + "step": 4384 + }, + { + "epoch": 0.56, + "learning_rate": 8.441052296036724e-06, + "loss": 0.3005, + "step": 4385 + }, + { + "epoch": 0.56, + "learning_rate": 8.440300239145098e-06, + "loss": 0.3004, + "step": 4386 + }, + { + "epoch": 0.56, + "learning_rate": 8.439548034416108e-06, + "loss": 0.3465, + "step": 4387 + }, + { + "epoch": 0.56, + "learning_rate": 8.43879568188208e-06, + "loss": 0.3396, + "step": 4388 + }, + { + "epoch": 0.56, + "learning_rate": 8.43804318157534e-06, + "loss": 0.3167, + "step": 4389 + }, + { + "epoch": 0.56, + "learning_rate": 8.437290533528231e-06, + "loss": 0.3347, + "step": 4390 + }, + { + "epoch": 0.56, + "learning_rate": 8.436537737773089e-06, + "loss": 0.3347, + "step": 4391 + }, + { + "epoch": 0.56, + "learning_rate": 8.43578479434227e-06, + "loss": 0.3164, + "step": 4392 + }, + { + "epoch": 0.56, + "learning_rate": 8.435031703268123e-06, + "loss": 0.3556, + "step": 4393 + }, + { + "epoch": 0.56, + "learning_rate": 8.434278464583018e-06, + "loss": 0.3496, + "step": 4394 + }, + { + "epoch": 0.56, + "learning_rate": 8.433525078319316e-06, + "loss": 0.3109, + "step": 4395 + }, + { + "epoch": 0.56, + "learning_rate": 8.432771544509395e-06, + "loss": 0.3084, + "step": 4396 + }, + { + "epoch": 0.56, + "learning_rate": 8.432017863185635e-06, + "loss": 0.3391, + "step": 4397 + }, + { + "epoch": 0.56, + "learning_rate": 8.431264034380424e-06, + "loss": 0.3212, + "step": 4398 + }, + { + "epoch": 0.56, + "learning_rate": 8.430510058126156e-06, + "loss": 0.3385, + "step": 4399 + }, + { + "epoch": 0.56, + "learning_rate": 8.42975593445523e-06, + "loss": 0.3339, + "step": 4400 + }, + { + "epoch": 0.56, + "learning_rate": 8.429001663400054e-06, + "loss": 0.3118, + "step": 4401 + }, + { + "epoch": 0.56, + "learning_rate": 8.428247244993038e-06, + "loss": 0.348, + "step": 4402 + }, + { + "epoch": 0.56, + "learning_rate": 8.427492679266605e-06, + "loss": 0.3357, + "step": 4403 + }, + { + "epoch": 0.56, + "learning_rate": 8.426737966253176e-06, + "loss": 0.3165, + "step": 4404 + }, + { + "epoch": 0.56, + "learning_rate": 8.425983105985188e-06, + "loss": 0.3087, + "step": 4405 + }, + { + "epoch": 0.56, + "learning_rate": 8.425228098495073e-06, + "loss": 0.347, + "step": 4406 + }, + { + "epoch": 0.56, + "learning_rate": 8.424472943815278e-06, + "loss": 0.3219, + "step": 4407 + }, + { + "epoch": 0.56, + "learning_rate": 8.423717641978255e-06, + "loss": 0.3499, + "step": 4408 + }, + { + "epoch": 0.56, + "learning_rate": 8.422962193016459e-06, + "loss": 0.3022, + "step": 4409 + }, + { + "epoch": 0.56, + "learning_rate": 8.422206596962357e-06, + "loss": 0.3377, + "step": 4410 + }, + { + "epoch": 0.56, + "learning_rate": 8.421450853848414e-06, + "loss": 0.3183, + "step": 4411 + }, + { + "epoch": 0.56, + "learning_rate": 8.420694963707108e-06, + "loss": 0.3258, + "step": 4412 + }, + { + "epoch": 0.56, + "learning_rate": 8.419938926570921e-06, + "loss": 0.3124, + "step": 4413 + }, + { + "epoch": 0.56, + "learning_rate": 8.41918274247234e-06, + "loss": 0.3076, + "step": 4414 + }, + { + "epoch": 0.57, + "learning_rate": 8.418426411443864e-06, + "loss": 0.3281, + "step": 4415 + }, + { + "epoch": 0.57, + "learning_rate": 8.41766993351799e-06, + "loss": 0.3232, + "step": 4416 + }, + { + "epoch": 0.57, + "learning_rate": 8.416913308727229e-06, + "loss": 0.3168, + "step": 4417 + }, + { + "epoch": 0.57, + "learning_rate": 8.416156537104092e-06, + "loss": 0.3231, + "step": 4418 + }, + { + "epoch": 0.57, + "learning_rate": 8.415399618681101e-06, + "loss": 0.3325, + "step": 4419 + }, + { + "epoch": 0.57, + "learning_rate": 8.414642553490783e-06, + "loss": 0.3126, + "step": 4420 + }, + { + "epoch": 0.57, + "learning_rate": 8.413885341565668e-06, + "loss": 0.3385, + "step": 4421 + }, + { + "epoch": 0.57, + "learning_rate": 8.413127982938299e-06, + "loss": 0.3233, + "step": 4422 + }, + { + "epoch": 0.57, + "learning_rate": 8.412370477641215e-06, + "loss": 0.3197, + "step": 4423 + }, + { + "epoch": 0.57, + "learning_rate": 8.411612825706976e-06, + "loss": 0.3305, + "step": 4424 + }, + { + "epoch": 0.57, + "learning_rate": 8.410855027168134e-06, + "loss": 0.3159, + "step": 4425 + }, + { + "epoch": 0.57, + "learning_rate": 8.410097082057256e-06, + "loss": 0.3433, + "step": 4426 + }, + { + "epoch": 0.57, + "learning_rate": 8.40933899040691e-06, + "loss": 0.3447, + "step": 4427 + }, + { + "epoch": 0.57, + "learning_rate": 8.408580752249676e-06, + "loss": 0.334, + "step": 4428 + }, + { + "epoch": 0.57, + "learning_rate": 8.407822367618135e-06, + "loss": 0.2984, + "step": 4429 + }, + { + "epoch": 0.57, + "learning_rate": 8.407063836544877e-06, + "loss": 0.3104, + "step": 4430 + }, + { + "epoch": 0.57, + "learning_rate": 8.4063051590625e-06, + "loss": 0.3312, + "step": 4431 + }, + { + "epoch": 0.57, + "learning_rate": 8.405546335203602e-06, + "loss": 0.2948, + "step": 4432 + }, + { + "epoch": 0.57, + "learning_rate": 8.404787365000796e-06, + "loss": 0.3392, + "step": 4433 + }, + { + "epoch": 0.57, + "learning_rate": 8.40402824848669e-06, + "loss": 0.3213, + "step": 4434 + }, + { + "epoch": 0.57, + "learning_rate": 8.403268985693912e-06, + "loss": 0.3069, + "step": 4435 + }, + { + "epoch": 0.57, + "learning_rate": 8.402509576655085e-06, + "loss": 0.3351, + "step": 4436 + }, + { + "epoch": 0.57, + "learning_rate": 8.401750021402843e-06, + "loss": 0.3514, + "step": 4437 + }, + { + "epoch": 0.57, + "learning_rate": 8.400990319969829e-06, + "loss": 0.3331, + "step": 4438 + }, + { + "epoch": 0.57, + "learning_rate": 8.400230472388684e-06, + "loss": 0.3148, + "step": 4439 + }, + { + "epoch": 0.57, + "learning_rate": 8.399470478692064e-06, + "loss": 0.3439, + "step": 4440 + }, + { + "epoch": 0.57, + "learning_rate": 8.398710338912626e-06, + "loss": 0.3045, + "step": 4441 + }, + { + "epoch": 0.57, + "learning_rate": 8.397950053083036e-06, + "loss": 0.3323, + "step": 4442 + }, + { + "epoch": 0.57, + "learning_rate": 8.397189621235964e-06, + "loss": 0.3364, + "step": 4443 + }, + { + "epoch": 0.57, + "learning_rate": 8.396429043404088e-06, + "loss": 0.3302, + "step": 4444 + }, + { + "epoch": 0.57, + "learning_rate": 8.395668319620092e-06, + "loss": 0.3227, + "step": 4445 + }, + { + "epoch": 0.57, + "learning_rate": 8.394907449916667e-06, + "loss": 0.3355, + "step": 4446 + }, + { + "epoch": 0.57, + "learning_rate": 8.394146434326507e-06, + "loss": 0.3308, + "step": 4447 + }, + { + "epoch": 0.57, + "learning_rate": 8.393385272882315e-06, + "loss": 0.3398, + "step": 4448 + }, + { + "epoch": 0.57, + "learning_rate": 8.3926239656168e-06, + "loss": 0.3324, + "step": 4449 + }, + { + "epoch": 0.57, + "learning_rate": 8.391862512562679e-06, + "loss": 0.343, + "step": 4450 + }, + { + "epoch": 0.57, + "learning_rate": 8.39110091375267e-06, + "loss": 0.305, + "step": 4451 + }, + { + "epoch": 0.57, + "learning_rate": 8.390339169219504e-06, + "loss": 0.3562, + "step": 4452 + }, + { + "epoch": 0.57, + "learning_rate": 8.389577278995913e-06, + "loss": 0.3218, + "step": 4453 + }, + { + "epoch": 0.57, + "learning_rate": 8.388815243114637e-06, + "loss": 0.3429, + "step": 4454 + }, + { + "epoch": 0.57, + "learning_rate": 8.388053061608421e-06, + "loss": 0.3493, + "step": 4455 + }, + { + "epoch": 0.57, + "learning_rate": 8.387290734510022e-06, + "loss": 0.3322, + "step": 4456 + }, + { + "epoch": 0.57, + "learning_rate": 8.386528261852196e-06, + "loss": 0.3553, + "step": 4457 + }, + { + "epoch": 0.57, + "learning_rate": 8.385765643667707e-06, + "loss": 0.363, + "step": 4458 + }, + { + "epoch": 0.57, + "learning_rate": 8.385002879989328e-06, + "loss": 0.321, + "step": 4459 + }, + { + "epoch": 0.57, + "learning_rate": 8.384239970849837e-06, + "loss": 0.31, + "step": 4460 + }, + { + "epoch": 0.57, + "learning_rate": 8.383476916282015e-06, + "loss": 0.3099, + "step": 4461 + }, + { + "epoch": 0.57, + "learning_rate": 8.382713716318658e-06, + "loss": 0.3448, + "step": 4462 + }, + { + "epoch": 0.57, + "learning_rate": 8.381950370992557e-06, + "loss": 0.3253, + "step": 4463 + }, + { + "epoch": 0.57, + "learning_rate": 8.381186880336518e-06, + "loss": 0.3687, + "step": 4464 + }, + { + "epoch": 0.57, + "learning_rate": 8.380423244383347e-06, + "loss": 0.3509, + "step": 4465 + }, + { + "epoch": 0.57, + "learning_rate": 8.37965946316586e-06, + "loss": 0.308, + "step": 4466 + }, + { + "epoch": 0.57, + "learning_rate": 8.378895536716882e-06, + "loss": 0.3343, + "step": 4467 + }, + { + "epoch": 0.57, + "learning_rate": 8.378131465069235e-06, + "loss": 0.3374, + "step": 4468 + }, + { + "epoch": 0.57, + "learning_rate": 8.377367248255757e-06, + "loss": 0.3502, + "step": 4469 + }, + { + "epoch": 0.57, + "learning_rate": 8.376602886309285e-06, + "loss": 0.3297, + "step": 4470 + }, + { + "epoch": 0.57, + "learning_rate": 8.375838379262667e-06, + "loss": 0.3651, + "step": 4471 + }, + { + "epoch": 0.57, + "learning_rate": 8.375073727148756e-06, + "loss": 0.3527, + "step": 4472 + }, + { + "epoch": 0.57, + "learning_rate": 8.37430893000041e-06, + "loss": 0.3651, + "step": 4473 + }, + { + "epoch": 0.57, + "learning_rate": 8.373543987850494e-06, + "loss": 0.3432, + "step": 4474 + }, + { + "epoch": 0.57, + "learning_rate": 8.372778900731882e-06, + "loss": 0.3265, + "step": 4475 + }, + { + "epoch": 0.57, + "learning_rate": 8.372013668677446e-06, + "loss": 0.3234, + "step": 4476 + }, + { + "epoch": 0.57, + "learning_rate": 8.371248291720073e-06, + "loss": 0.3379, + "step": 4477 + }, + { + "epoch": 0.57, + "learning_rate": 8.370482769892654e-06, + "loss": 0.3258, + "step": 4478 + }, + { + "epoch": 0.57, + "learning_rate": 8.369717103228084e-06, + "loss": 0.3072, + "step": 4479 + }, + { + "epoch": 0.57, + "learning_rate": 8.368951291759264e-06, + "loss": 0.3357, + "step": 4480 + }, + { + "epoch": 0.57, + "learning_rate": 8.368185335519106e-06, + "loss": 0.3187, + "step": 4481 + }, + { + "epoch": 0.57, + "learning_rate": 8.367419234540522e-06, + "loss": 0.2953, + "step": 4482 + }, + { + "epoch": 0.57, + "learning_rate": 8.366652988856432e-06, + "loss": 0.2876, + "step": 4483 + }, + { + "epoch": 0.57, + "learning_rate": 8.365886598499766e-06, + "loss": 0.3199, + "step": 4484 + }, + { + "epoch": 0.57, + "learning_rate": 8.365120063503458e-06, + "loss": 0.3287, + "step": 4485 + }, + { + "epoch": 0.57, + "learning_rate": 8.364353383900445e-06, + "loss": 0.3034, + "step": 4486 + }, + { + "epoch": 0.57, + "learning_rate": 8.363586559723675e-06, + "loss": 0.3548, + "step": 4487 + }, + { + "epoch": 0.57, + "learning_rate": 8.3628195910061e-06, + "loss": 0.3325, + "step": 4488 + }, + { + "epoch": 0.57, + "learning_rate": 8.362052477780677e-06, + "loss": 0.3313, + "step": 4489 + }, + { + "epoch": 0.57, + "learning_rate": 8.36128522008037e-06, + "loss": 0.3074, + "step": 4490 + }, + { + "epoch": 0.57, + "learning_rate": 8.360517817938154e-06, + "loss": 0.3443, + "step": 4491 + }, + { + "epoch": 0.57, + "learning_rate": 8.359750271386999e-06, + "loss": 0.3305, + "step": 4492 + }, + { + "epoch": 0.58, + "learning_rate": 8.358982580459896e-06, + "loss": 0.3212, + "step": 4493 + }, + { + "epoch": 0.58, + "learning_rate": 8.35821474518983e-06, + "loss": 0.3422, + "step": 4494 + }, + { + "epoch": 0.58, + "learning_rate": 8.357446765609796e-06, + "loss": 0.3256, + "step": 4495 + }, + { + "epoch": 0.58, + "learning_rate": 8.356678641752797e-06, + "loss": 0.3187, + "step": 4496 + }, + { + "epoch": 0.58, + "learning_rate": 8.355910373651844e-06, + "loss": 0.3103, + "step": 4497 + }, + { + "epoch": 0.58, + "learning_rate": 8.355141961339945e-06, + "loss": 0.3322, + "step": 4498 + }, + { + "epoch": 0.58, + "learning_rate": 8.354373404850124e-06, + "loss": 0.3371, + "step": 4499 + }, + { + "epoch": 0.58, + "learning_rate": 8.353604704215408e-06, + "loss": 0.3297, + "step": 4500 + }, + { + "epoch": 0.58, + "learning_rate": 8.352835859468829e-06, + "loss": 0.3096, + "step": 4501 + }, + { + "epoch": 0.58, + "learning_rate": 8.352066870643424e-06, + "loss": 0.3175, + "step": 4502 + }, + { + "epoch": 0.58, + "learning_rate": 8.351297737772244e-06, + "loss": 0.3357, + "step": 4503 + }, + { + "epoch": 0.58, + "learning_rate": 8.350528460888334e-06, + "loss": 0.3239, + "step": 4504 + }, + { + "epoch": 0.58, + "learning_rate": 8.349759040024753e-06, + "loss": 0.3465, + "step": 4505 + }, + { + "epoch": 0.58, + "learning_rate": 8.348989475214568e-06, + "loss": 0.3294, + "step": 4506 + }, + { + "epoch": 0.58, + "learning_rate": 8.348219766490845e-06, + "loss": 0.3766, + "step": 4507 + }, + { + "epoch": 0.58, + "learning_rate": 8.347449913886662e-06, + "loss": 0.3247, + "step": 4508 + }, + { + "epoch": 0.58, + "learning_rate": 8.346679917435104e-06, + "loss": 0.3345, + "step": 4509 + }, + { + "epoch": 0.58, + "learning_rate": 8.345909777169252e-06, + "loss": 0.3081, + "step": 4510 + }, + { + "epoch": 0.58, + "learning_rate": 8.345139493122208e-06, + "loss": 0.3238, + "step": 4511 + }, + { + "epoch": 0.58, + "learning_rate": 8.34436906532707e-06, + "loss": 0.3132, + "step": 4512 + }, + { + "epoch": 0.58, + "learning_rate": 8.343598493816944e-06, + "loss": 0.3178, + "step": 4513 + }, + { + "epoch": 0.58, + "learning_rate": 8.342827778624943e-06, + "loss": 0.3118, + "step": 4514 + }, + { + "epoch": 0.58, + "learning_rate": 8.34205691978419e-06, + "loss": 0.3296, + "step": 4515 + }, + { + "epoch": 0.58, + "learning_rate": 8.341285917327807e-06, + "loss": 0.3001, + "step": 4516 + }, + { + "epoch": 0.58, + "learning_rate": 8.340514771288926e-06, + "loss": 0.3423, + "step": 4517 + }, + { + "epoch": 0.58, + "learning_rate": 8.339743481700685e-06, + "loss": 0.3221, + "step": 4518 + }, + { + "epoch": 0.58, + "learning_rate": 8.33897204859623e-06, + "loss": 0.3294, + "step": 4519 + }, + { + "epoch": 0.58, + "learning_rate": 8.338200472008708e-06, + "loss": 0.3203, + "step": 4520 + }, + { + "epoch": 0.58, + "learning_rate": 8.337428751971279e-06, + "loss": 0.338, + "step": 4521 + }, + { + "epoch": 0.58, + "learning_rate": 8.336656888517103e-06, + "loss": 0.3392, + "step": 4522 + }, + { + "epoch": 0.58, + "learning_rate": 8.33588488167935e-06, + "loss": 0.3224, + "step": 4523 + }, + { + "epoch": 0.58, + "learning_rate": 8.335112731491192e-06, + "loss": 0.3351, + "step": 4524 + }, + { + "epoch": 0.58, + "learning_rate": 8.334340437985814e-06, + "loss": 0.3235, + "step": 4525 + }, + { + "epoch": 0.58, + "learning_rate": 8.333568001196402e-06, + "loss": 0.3131, + "step": 4526 + }, + { + "epoch": 0.58, + "learning_rate": 8.332795421156147e-06, + "loss": 0.3061, + "step": 4527 + }, + { + "epoch": 0.58, + "learning_rate": 8.332022697898253e-06, + "loss": 0.308, + "step": 4528 + }, + { + "epoch": 0.58, + "learning_rate": 8.331249831455921e-06, + "loss": 0.2935, + "step": 4529 + }, + { + "epoch": 0.58, + "learning_rate": 8.330476821862366e-06, + "loss": 0.2951, + "step": 4530 + }, + { + "epoch": 0.58, + "learning_rate": 8.329703669150801e-06, + "loss": 0.3237, + "step": 4531 + }, + { + "epoch": 0.58, + "learning_rate": 8.328930373354457e-06, + "loss": 0.2997, + "step": 4532 + }, + { + "epoch": 0.58, + "learning_rate": 8.328156934506559e-06, + "loss": 0.3063, + "step": 4533 + }, + { + "epoch": 0.58, + "learning_rate": 8.327383352640347e-06, + "loss": 0.3396, + "step": 4534 + }, + { + "epoch": 0.58, + "learning_rate": 8.32660962778906e-06, + "loss": 0.3297, + "step": 4535 + }, + { + "epoch": 0.58, + "learning_rate": 8.325835759985951e-06, + "loss": 0.3456, + "step": 4536 + }, + { + "epoch": 0.58, + "learning_rate": 8.32506174926427e-06, + "loss": 0.3194, + "step": 4537 + }, + { + "epoch": 0.58, + "learning_rate": 8.324287595657284e-06, + "loss": 0.3209, + "step": 4538 + }, + { + "epoch": 0.58, + "learning_rate": 8.323513299198252e-06, + "loss": 0.3316, + "step": 4539 + }, + { + "epoch": 0.58, + "learning_rate": 8.322738859920453e-06, + "loss": 0.3356, + "step": 4540 + }, + { + "epoch": 0.58, + "learning_rate": 8.321964277857167e-06, + "loss": 0.312, + "step": 4541 + }, + { + "epoch": 0.58, + "learning_rate": 8.321189553041675e-06, + "loss": 0.3135, + "step": 4542 + }, + { + "epoch": 0.58, + "learning_rate": 8.320414685507272e-06, + "loss": 0.341, + "step": 4543 + }, + { + "epoch": 0.58, + "learning_rate": 8.319639675287255e-06, + "loss": 0.3083, + "step": 4544 + }, + { + "epoch": 0.58, + "learning_rate": 8.318864522414928e-06, + "loss": 0.3139, + "step": 4545 + }, + { + "epoch": 0.58, + "learning_rate": 8.318089226923602e-06, + "loss": 0.329, + "step": 4546 + }, + { + "epoch": 0.58, + "learning_rate": 8.317313788846591e-06, + "loss": 0.3192, + "step": 4547 + }, + { + "epoch": 0.58, + "learning_rate": 8.31653820821722e-06, + "loss": 0.3153, + "step": 4548 + }, + { + "epoch": 0.58, + "learning_rate": 8.315762485068815e-06, + "loss": 0.3419, + "step": 4549 + }, + { + "epoch": 0.58, + "learning_rate": 8.31498661943471e-06, + "loss": 0.3379, + "step": 4550 + }, + { + "epoch": 0.58, + "learning_rate": 8.314210611348249e-06, + "loss": 0.3356, + "step": 4551 + }, + { + "epoch": 0.58, + "learning_rate": 8.313434460842775e-06, + "loss": 0.3053, + "step": 4552 + }, + { + "epoch": 0.58, + "learning_rate": 8.312658167951644e-06, + "loss": 0.3232, + "step": 4553 + }, + { + "epoch": 0.58, + "learning_rate": 8.311881732708213e-06, + "loss": 0.3703, + "step": 4554 + }, + { + "epoch": 0.58, + "learning_rate": 8.311105155145849e-06, + "loss": 0.3286, + "step": 4555 + }, + { + "epoch": 0.58, + "learning_rate": 8.310328435297923e-06, + "loss": 0.3454, + "step": 4556 + }, + { + "epoch": 0.58, + "learning_rate": 8.309551573197809e-06, + "loss": 0.2943, + "step": 4557 + }, + { + "epoch": 0.58, + "learning_rate": 8.308774568878896e-06, + "loss": 0.3343, + "step": 4558 + }, + { + "epoch": 0.58, + "learning_rate": 8.307997422374569e-06, + "loss": 0.3437, + "step": 4559 + }, + { + "epoch": 0.58, + "learning_rate": 8.307220133718225e-06, + "loss": 0.3118, + "step": 4560 + }, + { + "epoch": 0.58, + "learning_rate": 8.306442702943268e-06, + "loss": 0.2919, + "step": 4561 + }, + { + "epoch": 0.58, + "learning_rate": 8.305665130083102e-06, + "loss": 0.3243, + "step": 4562 + }, + { + "epoch": 0.58, + "learning_rate": 8.304887415171146e-06, + "loss": 0.335, + "step": 4563 + }, + { + "epoch": 0.58, + "learning_rate": 8.304109558240817e-06, + "loss": 0.3595, + "step": 4564 + }, + { + "epoch": 0.58, + "learning_rate": 8.30333155932554e-06, + "loss": 0.3269, + "step": 4565 + }, + { + "epoch": 0.58, + "learning_rate": 8.302553418458749e-06, + "loss": 0.3131, + "step": 4566 + }, + { + "epoch": 0.58, + "learning_rate": 8.301775135673884e-06, + "loss": 0.2996, + "step": 4567 + }, + { + "epoch": 0.58, + "learning_rate": 8.300996711004387e-06, + "loss": 0.3294, + "step": 4568 + }, + { + "epoch": 0.58, + "learning_rate": 8.300218144483709e-06, + "loss": 0.304, + "step": 4569 + }, + { + "epoch": 0.58, + "learning_rate": 8.299439436145309e-06, + "loss": 0.3023, + "step": 4570 + }, + { + "epoch": 0.59, + "learning_rate": 8.298660586022646e-06, + "loss": 0.3242, + "step": 4571 + }, + { + "epoch": 0.59, + "learning_rate": 8.297881594149193e-06, + "loss": 0.3381, + "step": 4572 + }, + { + "epoch": 0.59, + "learning_rate": 8.297102460558421e-06, + "loss": 0.3573, + "step": 4573 + }, + { + "epoch": 0.59, + "learning_rate": 8.296323185283816e-06, + "loss": 0.2988, + "step": 4574 + }, + { + "epoch": 0.59, + "learning_rate": 8.29554376835886e-06, + "loss": 0.3275, + "step": 4575 + }, + { + "epoch": 0.59, + "learning_rate": 8.29476420981705e-06, + "loss": 0.3462, + "step": 4576 + }, + { + "epoch": 0.59, + "learning_rate": 8.293984509691885e-06, + "loss": 0.3402, + "step": 4577 + }, + { + "epoch": 0.59, + "learning_rate": 8.293204668016867e-06, + "loss": 0.3365, + "step": 4578 + }, + { + "epoch": 0.59, + "learning_rate": 8.292424684825514e-06, + "loss": 0.342, + "step": 4579 + }, + { + "epoch": 0.59, + "learning_rate": 8.291644560151335e-06, + "loss": 0.3234, + "step": 4580 + }, + { + "epoch": 0.59, + "learning_rate": 8.29086429402786e-06, + "loss": 0.3371, + "step": 4581 + }, + { + "epoch": 0.59, + "learning_rate": 8.290083886488618e-06, + "loss": 0.3203, + "step": 4582 + }, + { + "epoch": 0.59, + "learning_rate": 8.289303337567145e-06, + "loss": 0.3359, + "step": 4583 + }, + { + "epoch": 0.59, + "learning_rate": 8.28852264729698e-06, + "loss": 0.3395, + "step": 4584 + }, + { + "epoch": 0.59, + "learning_rate": 8.287741815711674e-06, + "loss": 0.3015, + "step": 4585 + }, + { + "epoch": 0.59, + "learning_rate": 8.286960842844779e-06, + "loss": 0.31, + "step": 4586 + }, + { + "epoch": 0.59, + "learning_rate": 8.286179728729856e-06, + "loss": 0.3311, + "step": 4587 + }, + { + "epoch": 0.59, + "learning_rate": 8.285398473400471e-06, + "loss": 0.3344, + "step": 4588 + }, + { + "epoch": 0.59, + "learning_rate": 8.284617076890199e-06, + "loss": 0.3378, + "step": 4589 + }, + { + "epoch": 0.59, + "learning_rate": 8.283835539232614e-06, + "loss": 0.35, + "step": 4590 + }, + { + "epoch": 0.59, + "learning_rate": 8.283053860461303e-06, + "loss": 0.3282, + "step": 4591 + }, + { + "epoch": 0.59, + "learning_rate": 8.282272040609855e-06, + "loss": 0.3414, + "step": 4592 + }, + { + "epoch": 0.59, + "learning_rate": 8.281490079711866e-06, + "loss": 0.2941, + "step": 4593 + }, + { + "epoch": 0.59, + "learning_rate": 8.280707977800944e-06, + "loss": 0.3483, + "step": 4594 + }, + { + "epoch": 0.59, + "learning_rate": 8.279925734910691e-06, + "loss": 0.3055, + "step": 4595 + }, + { + "epoch": 0.59, + "learning_rate": 8.279143351074726e-06, + "loss": 0.3062, + "step": 4596 + }, + { + "epoch": 0.59, + "learning_rate": 8.278360826326669e-06, + "loss": 0.3281, + "step": 4597 + }, + { + "epoch": 0.59, + "learning_rate": 8.277578160700143e-06, + "loss": 0.3443, + "step": 4598 + }, + { + "epoch": 0.59, + "learning_rate": 8.276795354228785e-06, + "loss": 0.341, + "step": 4599 + }, + { + "epoch": 0.59, + "learning_rate": 8.276012406946232e-06, + "loss": 0.3226, + "step": 4600 + }, + { + "epoch": 0.59, + "learning_rate": 8.275229318886132e-06, + "loss": 0.3309, + "step": 4601 + }, + { + "epoch": 0.59, + "learning_rate": 8.274446090082133e-06, + "loss": 0.3332, + "step": 4602 + }, + { + "epoch": 0.59, + "learning_rate": 8.273662720567892e-06, + "loss": 0.3321, + "step": 4603 + }, + { + "epoch": 0.59, + "learning_rate": 8.272879210377074e-06, + "loss": 0.326, + "step": 4604 + }, + { + "epoch": 0.59, + "learning_rate": 8.272095559543346e-06, + "loss": 0.309, + "step": 4605 + }, + { + "epoch": 0.59, + "learning_rate": 8.271311768100386e-06, + "loss": 0.3213, + "step": 4606 + }, + { + "epoch": 0.59, + "learning_rate": 8.270527836081872e-06, + "loss": 0.3235, + "step": 4607 + }, + { + "epoch": 0.59, + "learning_rate": 8.269743763521495e-06, + "loss": 0.3259, + "step": 4608 + }, + { + "epoch": 0.59, + "learning_rate": 8.268959550452946e-06, + "loss": 0.3106, + "step": 4609 + }, + { + "epoch": 0.59, + "learning_rate": 8.268175196909924e-06, + "loss": 0.3279, + "step": 4610 + }, + { + "epoch": 0.59, + "learning_rate": 8.267390702926135e-06, + "loss": 0.2943, + "step": 4611 + }, + { + "epoch": 0.59, + "learning_rate": 8.26660606853529e-06, + "loss": 0.2923, + "step": 4612 + }, + { + "epoch": 0.59, + "learning_rate": 8.26582129377111e-06, + "loss": 0.3219, + "step": 4613 + }, + { + "epoch": 0.59, + "learning_rate": 8.265036378667312e-06, + "loss": 0.3223, + "step": 4614 + }, + { + "epoch": 0.59, + "learning_rate": 8.264251323257633e-06, + "loss": 0.3076, + "step": 4615 + }, + { + "epoch": 0.59, + "learning_rate": 8.263466127575801e-06, + "loss": 0.3431, + "step": 4616 + }, + { + "epoch": 0.59, + "learning_rate": 8.262680791655565e-06, + "loss": 0.3277, + "step": 4617 + }, + { + "epoch": 0.59, + "learning_rate": 8.261895315530667e-06, + "loss": 0.3204, + "step": 4618 + }, + { + "epoch": 0.59, + "learning_rate": 8.261109699234862e-06, + "loss": 0.3326, + "step": 4619 + }, + { + "epoch": 0.59, + "learning_rate": 8.26032394280191e-06, + "loss": 0.3117, + "step": 4620 + }, + { + "epoch": 0.59, + "learning_rate": 8.259538046265578e-06, + "loss": 0.3373, + "step": 4621 + }, + { + "epoch": 0.59, + "learning_rate": 8.258752009659638e-06, + "loss": 0.3141, + "step": 4622 + }, + { + "epoch": 0.59, + "learning_rate": 8.257965833017864e-06, + "loss": 0.2888, + "step": 4623 + }, + { + "epoch": 0.59, + "learning_rate": 8.257179516374045e-06, + "loss": 0.3103, + "step": 4624 + }, + { + "epoch": 0.59, + "learning_rate": 8.256393059761966e-06, + "loss": 0.3528, + "step": 4625 + }, + { + "epoch": 0.59, + "learning_rate": 8.255606463215426e-06, + "loss": 0.2973, + "step": 4626 + }, + { + "epoch": 0.59, + "learning_rate": 8.254819726768224e-06, + "loss": 0.3566, + "step": 4627 + }, + { + "epoch": 0.59, + "learning_rate": 8.254032850454173e-06, + "loss": 0.3137, + "step": 4628 + }, + { + "epoch": 0.59, + "learning_rate": 8.253245834307079e-06, + "loss": 0.3508, + "step": 4629 + }, + { + "epoch": 0.59, + "learning_rate": 8.252458678360769e-06, + "loss": 0.3338, + "step": 4630 + }, + { + "epoch": 0.59, + "learning_rate": 8.251671382649065e-06, + "loss": 0.3182, + "step": 4631 + }, + { + "epoch": 0.59, + "learning_rate": 8.250883947205799e-06, + "loss": 0.3661, + "step": 4632 + }, + { + "epoch": 0.59, + "learning_rate": 8.25009637206481e-06, + "loss": 0.3199, + "step": 4633 + }, + { + "epoch": 0.59, + "learning_rate": 8.249308657259943e-06, + "loss": 0.3176, + "step": 4634 + }, + { + "epoch": 0.59, + "learning_rate": 8.248520802825046e-06, + "loss": 0.3287, + "step": 4635 + }, + { + "epoch": 0.59, + "learning_rate": 8.247732808793975e-06, + "loss": 0.3294, + "step": 4636 + }, + { + "epoch": 0.59, + "learning_rate": 8.246944675200592e-06, + "loss": 0.3356, + "step": 4637 + }, + { + "epoch": 0.59, + "learning_rate": 8.246156402078765e-06, + "loss": 0.3253, + "step": 4638 + }, + { + "epoch": 0.59, + "learning_rate": 8.245367989462368e-06, + "loss": 0.3114, + "step": 4639 + }, + { + "epoch": 0.59, + "learning_rate": 8.244579437385281e-06, + "loss": 0.3307, + "step": 4640 + }, + { + "epoch": 0.59, + "learning_rate": 8.243790745881389e-06, + "loss": 0.3294, + "step": 4641 + }, + { + "epoch": 0.59, + "learning_rate": 8.243001914984583e-06, + "loss": 0.3157, + "step": 4642 + }, + { + "epoch": 0.59, + "learning_rate": 8.242212944728762e-06, + "loss": 0.3575, + "step": 4643 + }, + { + "epoch": 0.59, + "learning_rate": 8.241423835147833e-06, + "loss": 0.3073, + "step": 4644 + }, + { + "epoch": 0.59, + "learning_rate": 8.240634586275701e-06, + "loss": 0.3419, + "step": 4645 + }, + { + "epoch": 0.59, + "learning_rate": 8.239845198146284e-06, + "loss": 0.3051, + "step": 4646 + }, + { + "epoch": 0.59, + "learning_rate": 8.239055670793503e-06, + "loss": 0.3089, + "step": 4647 + }, + { + "epoch": 0.59, + "learning_rate": 8.238266004251284e-06, + "loss": 0.3007, + "step": 4648 + }, + { + "epoch": 0.6, + "learning_rate": 8.237476198553567e-06, + "loss": 0.3366, + "step": 4649 + }, + { + "epoch": 0.6, + "learning_rate": 8.236686253734285e-06, + "loss": 0.319, + "step": 4650 + }, + { + "epoch": 0.6, + "learning_rate": 8.235896169827386e-06, + "loss": 0.32, + "step": 4651 + }, + { + "epoch": 0.6, + "learning_rate": 8.235105946866823e-06, + "loss": 0.328, + "step": 4652 + }, + { + "epoch": 0.6, + "learning_rate": 8.234315584886551e-06, + "loss": 0.3336, + "step": 4653 + }, + { + "epoch": 0.6, + "learning_rate": 8.233525083920536e-06, + "loss": 0.3135, + "step": 4654 + }, + { + "epoch": 0.6, + "learning_rate": 8.232734444002748e-06, + "loss": 0.2927, + "step": 4655 + }, + { + "epoch": 0.6, + "learning_rate": 8.23194366516716e-06, + "loss": 0.3374, + "step": 4656 + }, + { + "epoch": 0.6, + "learning_rate": 8.231152747447753e-06, + "loss": 0.3476, + "step": 4657 + }, + { + "epoch": 0.6, + "learning_rate": 8.230361690878519e-06, + "loss": 0.3098, + "step": 4658 + }, + { + "epoch": 0.6, + "learning_rate": 8.229570495493447e-06, + "loss": 0.327, + "step": 4659 + }, + { + "epoch": 0.6, + "learning_rate": 8.22877916132654e-06, + "loss": 0.3191, + "step": 4660 + }, + { + "epoch": 0.6, + "learning_rate": 8.2279876884118e-06, + "loss": 0.3111, + "step": 4661 + }, + { + "epoch": 0.6, + "learning_rate": 8.22719607678324e-06, + "loss": 0.3276, + "step": 4662 + }, + { + "epoch": 0.6, + "learning_rate": 8.226404326474878e-06, + "loss": 0.3166, + "step": 4663 + }, + { + "epoch": 0.6, + "learning_rate": 8.225612437520736e-06, + "loss": 0.3155, + "step": 4664 + }, + { + "epoch": 0.6, + "learning_rate": 8.224820409954844e-06, + "loss": 0.3345, + "step": 4665 + }, + { + "epoch": 0.6, + "learning_rate": 8.224028243811237e-06, + "loss": 0.3369, + "step": 4666 + }, + { + "epoch": 0.6, + "learning_rate": 8.223235939123955e-06, + "loss": 0.3007, + "step": 4667 + }, + { + "epoch": 0.6, + "learning_rate": 8.222443495927049e-06, + "loss": 0.3381, + "step": 4668 + }, + { + "epoch": 0.6, + "learning_rate": 8.221650914254566e-06, + "loss": 0.3055, + "step": 4669 + }, + { + "epoch": 0.6, + "learning_rate": 8.220858194140568e-06, + "loss": 0.3131, + "step": 4670 + }, + { + "epoch": 0.6, + "learning_rate": 8.220065335619123e-06, + "loss": 0.3035, + "step": 4671 + }, + { + "epoch": 0.6, + "learning_rate": 8.219272338724297e-06, + "loss": 0.3629, + "step": 4672 + }, + { + "epoch": 0.6, + "learning_rate": 8.21847920349017e-06, + "loss": 0.3142, + "step": 4673 + }, + { + "epoch": 0.6, + "learning_rate": 8.217685929950823e-06, + "loss": 0.3242, + "step": 4674 + }, + { + "epoch": 0.6, + "learning_rate": 8.216892518140346e-06, + "loss": 0.3403, + "step": 4675 + }, + { + "epoch": 0.6, + "learning_rate": 8.216098968092833e-06, + "loss": 0.357, + "step": 4676 + }, + { + "epoch": 0.6, + "learning_rate": 8.215305279842385e-06, + "loss": 0.3217, + "step": 4677 + }, + { + "epoch": 0.6, + "learning_rate": 8.214511453423107e-06, + "loss": 0.3286, + "step": 4678 + }, + { + "epoch": 0.6, + "learning_rate": 8.213717488869113e-06, + "loss": 0.2984, + "step": 4679 + }, + { + "epoch": 0.6, + "learning_rate": 8.212923386214522e-06, + "loss": 0.3478, + "step": 4680 + }, + { + "epoch": 0.6, + "learning_rate": 8.212129145493457e-06, + "loss": 0.3544, + "step": 4681 + }, + { + "epoch": 0.6, + "learning_rate": 8.211334766740048e-06, + "loss": 0.3503, + "step": 4682 + }, + { + "epoch": 0.6, + "learning_rate": 8.210540249988435e-06, + "loss": 0.2925, + "step": 4683 + }, + { + "epoch": 0.6, + "learning_rate": 8.209745595272755e-06, + "loss": 0.333, + "step": 4684 + }, + { + "epoch": 0.6, + "learning_rate": 8.208950802627157e-06, + "loss": 0.331, + "step": 4685 + }, + { + "epoch": 0.6, + "learning_rate": 8.208155872085799e-06, + "loss": 0.3101, + "step": 4686 + }, + { + "epoch": 0.6, + "learning_rate": 8.207360803682837e-06, + "loss": 0.3282, + "step": 4687 + }, + { + "epoch": 0.6, + "learning_rate": 8.206565597452438e-06, + "loss": 0.3169, + "step": 4688 + }, + { + "epoch": 0.6, + "learning_rate": 8.205770253428775e-06, + "loss": 0.346, + "step": 4689 + }, + { + "epoch": 0.6, + "learning_rate": 8.204974771646023e-06, + "loss": 0.3018, + "step": 4690 + }, + { + "epoch": 0.6, + "learning_rate": 8.204179152138367e-06, + "loss": 0.3474, + "step": 4691 + }, + { + "epoch": 0.6, + "learning_rate": 8.203383394939998e-06, + "loss": 0.3195, + "step": 4692 + }, + { + "epoch": 0.6, + "learning_rate": 8.20258750008511e-06, + "loss": 0.3455, + "step": 4693 + }, + { + "epoch": 0.6, + "learning_rate": 8.201791467607905e-06, + "loss": 0.342, + "step": 4694 + }, + { + "epoch": 0.6, + "learning_rate": 8.200995297542589e-06, + "loss": 0.3561, + "step": 4695 + }, + { + "epoch": 0.6, + "learning_rate": 8.200198989923376e-06, + "loss": 0.3583, + "step": 4696 + }, + { + "epoch": 0.6, + "learning_rate": 8.199402544784485e-06, + "loss": 0.307, + "step": 4697 + }, + { + "epoch": 0.6, + "learning_rate": 8.198605962160143e-06, + "loss": 0.3348, + "step": 4698 + }, + { + "epoch": 0.6, + "learning_rate": 8.197809242084575e-06, + "loss": 0.3485, + "step": 4699 + }, + { + "epoch": 0.6, + "learning_rate": 8.197012384592027e-06, + "loss": 0.346, + "step": 4700 + }, + { + "epoch": 0.6, + "learning_rate": 8.196215389716732e-06, + "loss": 0.3158, + "step": 4701 + }, + { + "epoch": 0.6, + "learning_rate": 8.195418257492948e-06, + "loss": 0.302, + "step": 4702 + }, + { + "epoch": 0.6, + "learning_rate": 8.194620987954922e-06, + "loss": 0.3075, + "step": 4703 + }, + { + "epoch": 0.6, + "learning_rate": 8.193823581136919e-06, + "loss": 0.2949, + "step": 4704 + }, + { + "epoch": 0.6, + "learning_rate": 8.193026037073201e-06, + "loss": 0.3301, + "step": 4705 + }, + { + "epoch": 0.6, + "learning_rate": 8.192228355798045e-06, + "loss": 0.3313, + "step": 4706 + }, + { + "epoch": 0.6, + "learning_rate": 8.191430537345728e-06, + "loss": 0.2968, + "step": 4707 + }, + { + "epoch": 0.6, + "learning_rate": 8.19063258175053e-06, + "loss": 0.3299, + "step": 4708 + }, + { + "epoch": 0.6, + "learning_rate": 8.189834489046746e-06, + "loss": 0.325, + "step": 4709 + }, + { + "epoch": 0.6, + "learning_rate": 8.18903625926867e-06, + "loss": 0.3193, + "step": 4710 + }, + { + "epoch": 0.6, + "learning_rate": 8.188237892450603e-06, + "loss": 0.3141, + "step": 4711 + }, + { + "epoch": 0.6, + "learning_rate": 8.187439388626855e-06, + "loss": 0.3223, + "step": 4712 + }, + { + "epoch": 0.6, + "learning_rate": 8.186640747831735e-06, + "loss": 0.3184, + "step": 4713 + }, + { + "epoch": 0.6, + "learning_rate": 8.185841970099566e-06, + "loss": 0.3264, + "step": 4714 + }, + { + "epoch": 0.6, + "learning_rate": 8.185043055464673e-06, + "loss": 0.3285, + "step": 4715 + }, + { + "epoch": 0.6, + "learning_rate": 8.184244003961386e-06, + "loss": 0.3244, + "step": 4716 + }, + { + "epoch": 0.6, + "learning_rate": 8.183444815624041e-06, + "loss": 0.3642, + "step": 4717 + }, + { + "epoch": 0.6, + "learning_rate": 8.182645490486986e-06, + "loss": 0.3443, + "step": 4718 + }, + { + "epoch": 0.6, + "learning_rate": 8.181846028584563e-06, + "loss": 0.3297, + "step": 4719 + }, + { + "epoch": 0.6, + "learning_rate": 8.181046429951131e-06, + "loss": 0.3427, + "step": 4720 + }, + { + "epoch": 0.6, + "learning_rate": 8.180246694621048e-06, + "loss": 0.3195, + "step": 4721 + }, + { + "epoch": 0.6, + "learning_rate": 8.179446822628684e-06, + "loss": 0.2976, + "step": 4722 + }, + { + "epoch": 0.6, + "learning_rate": 8.178646814008407e-06, + "loss": 0.31, + "step": 4723 + }, + { + "epoch": 0.6, + "learning_rate": 8.177846668794598e-06, + "loss": 0.3358, + "step": 4724 + }, + { + "epoch": 0.6, + "learning_rate": 8.177046387021641e-06, + "loss": 0.3253, + "step": 4725 + }, + { + "epoch": 0.6, + "learning_rate": 8.176245968723924e-06, + "loss": 0.3586, + "step": 4726 + }, + { + "epoch": 0.61, + "learning_rate": 8.175445413935844e-06, + "loss": 0.2871, + "step": 4727 + }, + { + "epoch": 0.61, + "learning_rate": 8.174644722691802e-06, + "loss": 0.2896, + "step": 4728 + }, + { + "epoch": 0.61, + "learning_rate": 8.173843895026207e-06, + "loss": 0.3296, + "step": 4729 + }, + { + "epoch": 0.61, + "learning_rate": 8.17304293097347e-06, + "loss": 0.3337, + "step": 4730 + }, + { + "epoch": 0.61, + "learning_rate": 8.172241830568012e-06, + "loss": 0.3193, + "step": 4731 + }, + { + "epoch": 0.61, + "learning_rate": 8.17144059384426e-06, + "loss": 0.3476, + "step": 4732 + }, + { + "epoch": 0.61, + "learning_rate": 8.170639220836639e-06, + "loss": 0.35, + "step": 4733 + }, + { + "epoch": 0.61, + "learning_rate": 8.169837711579591e-06, + "loss": 0.3198, + "step": 4734 + }, + { + "epoch": 0.61, + "learning_rate": 8.169036066107556e-06, + "loss": 0.3283, + "step": 4735 + }, + { + "epoch": 0.61, + "learning_rate": 8.168234284454984e-06, + "loss": 0.3117, + "step": 4736 + }, + { + "epoch": 0.61, + "learning_rate": 8.16743236665633e-06, + "loss": 0.3306, + "step": 4737 + }, + { + "epoch": 0.61, + "learning_rate": 8.166630312746051e-06, + "loss": 0.3632, + "step": 4738 + }, + { + "epoch": 0.61, + "learning_rate": 8.165828122758615e-06, + "loss": 0.3011, + "step": 4739 + }, + { + "epoch": 0.61, + "learning_rate": 8.165025796728495e-06, + "loss": 0.3342, + "step": 4740 + }, + { + "epoch": 0.61, + "learning_rate": 8.164223334690168e-06, + "loss": 0.3182, + "step": 4741 + }, + { + "epoch": 0.61, + "learning_rate": 8.163420736678115e-06, + "loss": 0.2905, + "step": 4742 + }, + { + "epoch": 0.61, + "learning_rate": 8.162618002726829e-06, + "loss": 0.307, + "step": 4743 + }, + { + "epoch": 0.61, + "learning_rate": 8.161815132870806e-06, + "loss": 0.3124, + "step": 4744 + }, + { + "epoch": 0.61, + "learning_rate": 8.161012127144543e-06, + "loss": 0.3272, + "step": 4745 + }, + { + "epoch": 0.61, + "learning_rate": 8.160208985582547e-06, + "loss": 0.3252, + "step": 4746 + }, + { + "epoch": 0.61, + "learning_rate": 8.159405708219335e-06, + "loss": 0.307, + "step": 4747 + }, + { + "epoch": 0.61, + "learning_rate": 8.158602295089423e-06, + "loss": 0.3105, + "step": 4748 + }, + { + "epoch": 0.61, + "learning_rate": 8.157798746227337e-06, + "loss": 0.3138, + "step": 4749 + }, + { + "epoch": 0.61, + "learning_rate": 8.156995061667605e-06, + "loss": 0.3154, + "step": 4750 + }, + { + "epoch": 0.61, + "learning_rate": 8.156191241444763e-06, + "loss": 0.3442, + "step": 4751 + }, + { + "epoch": 0.61, + "learning_rate": 8.155387285593356e-06, + "loss": 0.3024, + "step": 4752 + }, + { + "epoch": 0.61, + "learning_rate": 8.154583194147929e-06, + "loss": 0.3039, + "step": 4753 + }, + { + "epoch": 0.61, + "learning_rate": 8.153778967143035e-06, + "loss": 0.3463, + "step": 4754 + }, + { + "epoch": 0.61, + "learning_rate": 8.152974604613238e-06, + "loss": 0.3369, + "step": 4755 + }, + { + "epoch": 0.61, + "learning_rate": 8.152170106593099e-06, + "loss": 0.324, + "step": 4756 + }, + { + "epoch": 0.61, + "learning_rate": 8.15136547311719e-06, + "loss": 0.332, + "step": 4757 + }, + { + "epoch": 0.61, + "learning_rate": 8.150560704220087e-06, + "loss": 0.2982, + "step": 4758 + }, + { + "epoch": 0.61, + "learning_rate": 8.149755799936377e-06, + "loss": 0.3125, + "step": 4759 + }, + { + "epoch": 0.61, + "learning_rate": 8.148950760300642e-06, + "loss": 0.3092, + "step": 4760 + }, + { + "epoch": 0.61, + "learning_rate": 8.148145585347482e-06, + "loss": 0.3273, + "step": 4761 + }, + { + "epoch": 0.61, + "learning_rate": 8.147340275111492e-06, + "loss": 0.3207, + "step": 4762 + }, + { + "epoch": 0.61, + "learning_rate": 8.146534829627285e-06, + "loss": 0.3247, + "step": 4763 + }, + { + "epoch": 0.61, + "learning_rate": 8.145729248929466e-06, + "loss": 0.3299, + "step": 4764 + }, + { + "epoch": 0.61, + "learning_rate": 8.144923533052655e-06, + "loss": 0.3284, + "step": 4765 + }, + { + "epoch": 0.61, + "learning_rate": 8.144117682031478e-06, + "loss": 0.2989, + "step": 4766 + }, + { + "epoch": 0.61, + "learning_rate": 8.14331169590056e-06, + "loss": 0.3068, + "step": 4767 + }, + { + "epoch": 0.61, + "learning_rate": 8.142505574694539e-06, + "loss": 0.3389, + "step": 4768 + }, + { + "epoch": 0.61, + "learning_rate": 8.141699318448053e-06, + "loss": 0.321, + "step": 4769 + }, + { + "epoch": 0.61, + "learning_rate": 8.14089292719575e-06, + "loss": 0.3062, + "step": 4770 + }, + { + "epoch": 0.61, + "learning_rate": 8.140086400972285e-06, + "loss": 0.3333, + "step": 4771 + }, + { + "epoch": 0.61, + "learning_rate": 8.139279739812314e-06, + "loss": 0.3156, + "step": 4772 + }, + { + "epoch": 0.61, + "learning_rate": 8.1384729437505e-06, + "loss": 0.3015, + "step": 4773 + }, + { + "epoch": 0.61, + "learning_rate": 8.137666012821514e-06, + "loss": 0.3288, + "step": 4774 + }, + { + "epoch": 0.61, + "learning_rate": 8.136858947060032e-06, + "loss": 0.334, + "step": 4775 + }, + { + "epoch": 0.61, + "learning_rate": 8.136051746500735e-06, + "loss": 0.3101, + "step": 4776 + }, + { + "epoch": 0.61, + "learning_rate": 8.135244411178309e-06, + "loss": 0.3261, + "step": 4777 + }, + { + "epoch": 0.61, + "learning_rate": 8.134436941127448e-06, + "loss": 0.3247, + "step": 4778 + }, + { + "epoch": 0.61, + "learning_rate": 8.13362933638285e-06, + "loss": 0.3528, + "step": 4779 + }, + { + "epoch": 0.61, + "learning_rate": 8.132821596979223e-06, + "loss": 0.326, + "step": 4780 + }, + { + "epoch": 0.61, + "learning_rate": 8.132013722951275e-06, + "loss": 0.3238, + "step": 4781 + }, + { + "epoch": 0.61, + "learning_rate": 8.13120571433372e-06, + "loss": 0.326, + "step": 4782 + }, + { + "epoch": 0.61, + "learning_rate": 8.130397571161283e-06, + "loss": 0.3356, + "step": 4783 + }, + { + "epoch": 0.61, + "learning_rate": 8.129589293468689e-06, + "loss": 0.3167, + "step": 4784 + }, + { + "epoch": 0.61, + "learning_rate": 8.128780881290674e-06, + "loss": 0.321, + "step": 4785 + }, + { + "epoch": 0.61, + "learning_rate": 8.127972334661978e-06, + "loss": 0.3044, + "step": 4786 + }, + { + "epoch": 0.61, + "learning_rate": 8.127163653617342e-06, + "loss": 0.3163, + "step": 4787 + }, + { + "epoch": 0.61, + "learning_rate": 8.12635483819152e-06, + "loss": 0.3502, + "step": 4788 + }, + { + "epoch": 0.61, + "learning_rate": 8.125545888419269e-06, + "loss": 0.3376, + "step": 4789 + }, + { + "epoch": 0.61, + "learning_rate": 8.124736804335348e-06, + "loss": 0.3174, + "step": 4790 + }, + { + "epoch": 0.61, + "learning_rate": 8.123927585974529e-06, + "loss": 0.3376, + "step": 4791 + }, + { + "epoch": 0.61, + "learning_rate": 8.123118233371585e-06, + "loss": 0.2962, + "step": 4792 + }, + { + "epoch": 0.61, + "learning_rate": 8.122308746561294e-06, + "loss": 0.3055, + "step": 4793 + }, + { + "epoch": 0.61, + "learning_rate": 8.12149912557844e-06, + "loss": 0.3329, + "step": 4794 + }, + { + "epoch": 0.61, + "learning_rate": 8.12068937045782e-06, + "loss": 0.3155, + "step": 4795 + }, + { + "epoch": 0.61, + "learning_rate": 8.119879481234228e-06, + "loss": 0.3317, + "step": 4796 + }, + { + "epoch": 0.61, + "learning_rate": 8.119069457942464e-06, + "loss": 0.3241, + "step": 4797 + }, + { + "epoch": 0.61, + "learning_rate": 8.118259300617339e-06, + "loss": 0.3067, + "step": 4798 + }, + { + "epoch": 0.61, + "learning_rate": 8.117449009293668e-06, + "loss": 0.2931, + "step": 4799 + }, + { + "epoch": 0.61, + "learning_rate": 8.11663858400627e-06, + "loss": 0.3045, + "step": 4800 + }, + { + "epoch": 0.61, + "learning_rate": 8.115828024789972e-06, + "loss": 0.3303, + "step": 4801 + }, + { + "epoch": 0.61, + "learning_rate": 8.115017331679602e-06, + "loss": 0.3243, + "step": 4802 + }, + { + "epoch": 0.61, + "learning_rate": 8.114206504710002e-06, + "loss": 0.3315, + "step": 4803 + }, + { + "epoch": 0.61, + "learning_rate": 8.113395543916012e-06, + "loss": 0.3261, + "step": 4804 + }, + { + "epoch": 0.62, + "learning_rate": 8.112584449332481e-06, + "loss": 0.3172, + "step": 4805 + }, + { + "epoch": 0.62, + "learning_rate": 8.111773220994264e-06, + "loss": 0.3148, + "step": 4806 + }, + { + "epoch": 0.62, + "learning_rate": 8.110961858936222e-06, + "loss": 0.3422, + "step": 4807 + }, + { + "epoch": 0.62, + "learning_rate": 8.11015036319322e-06, + "loss": 0.328, + "step": 4808 + }, + { + "epoch": 0.62, + "learning_rate": 8.109338733800132e-06, + "loss": 0.3303, + "step": 4809 + }, + { + "epoch": 0.62, + "learning_rate": 8.108526970791832e-06, + "loss": 0.3134, + "step": 4810 + }, + { + "epoch": 0.62, + "learning_rate": 8.107715074203205e-06, + "loss": 0.3121, + "step": 4811 + }, + { + "epoch": 0.62, + "learning_rate": 8.10690304406914e-06, + "loss": 0.3369, + "step": 4812 + }, + { + "epoch": 0.62, + "learning_rate": 8.106090880424534e-06, + "loss": 0.3194, + "step": 4813 + }, + { + "epoch": 0.62, + "learning_rate": 8.10527858330428e-06, + "loss": 0.3183, + "step": 4814 + }, + { + "epoch": 0.62, + "learning_rate": 8.104466152743295e-06, + "loss": 0.3183, + "step": 4815 + }, + { + "epoch": 0.62, + "learning_rate": 8.103653588776483e-06, + "loss": 0.3489, + "step": 4816 + }, + { + "epoch": 0.62, + "learning_rate": 8.102840891438764e-06, + "loss": 0.3255, + "step": 4817 + }, + { + "epoch": 0.62, + "learning_rate": 8.10202806076506e-06, + "loss": 0.3347, + "step": 4818 + }, + { + "epoch": 0.62, + "learning_rate": 8.101215096790305e-06, + "loss": 0.3335, + "step": 4819 + }, + { + "epoch": 0.62, + "learning_rate": 8.10040199954943e-06, + "loss": 0.3211, + "step": 4820 + }, + { + "epoch": 0.62, + "learning_rate": 8.099588769077374e-06, + "loss": 0.3211, + "step": 4821 + }, + { + "epoch": 0.62, + "learning_rate": 8.098775405409087e-06, + "loss": 0.3094, + "step": 4822 + }, + { + "epoch": 0.62, + "learning_rate": 8.09796190857952e-06, + "loss": 0.3181, + "step": 4823 + }, + { + "epoch": 0.62, + "learning_rate": 8.097148278623628e-06, + "loss": 0.2869, + "step": 4824 + }, + { + "epoch": 0.62, + "learning_rate": 8.096334515576379e-06, + "loss": 0.3257, + "step": 4825 + }, + { + "epoch": 0.62, + "learning_rate": 8.095520619472739e-06, + "loss": 0.3033, + "step": 4826 + }, + { + "epoch": 0.62, + "learning_rate": 8.094706590347683e-06, + "loss": 0.3397, + "step": 4827 + }, + { + "epoch": 0.62, + "learning_rate": 8.093892428236192e-06, + "loss": 0.3231, + "step": 4828 + }, + { + "epoch": 0.62, + "learning_rate": 8.093078133173256e-06, + "loss": 0.3357, + "step": 4829 + }, + { + "epoch": 0.62, + "learning_rate": 8.09226370519386e-06, + "loss": 0.3178, + "step": 4830 + }, + { + "epoch": 0.62, + "learning_rate": 8.091449144333009e-06, + "loss": 0.331, + "step": 4831 + }, + { + "epoch": 0.62, + "learning_rate": 8.090634450625704e-06, + "loss": 0.2872, + "step": 4832 + }, + { + "epoch": 0.62, + "learning_rate": 8.08981962410695e-06, + "loss": 0.3071, + "step": 4833 + }, + { + "epoch": 0.62, + "learning_rate": 8.089004664811767e-06, + "loss": 0.3294, + "step": 4834 + }, + { + "epoch": 0.62, + "learning_rate": 8.088189572775173e-06, + "loss": 0.3429, + "step": 4835 + }, + { + "epoch": 0.62, + "learning_rate": 8.087374348032198e-06, + "loss": 0.3299, + "step": 4836 + }, + { + "epoch": 0.62, + "learning_rate": 8.08655899061787e-06, + "loss": 0.3073, + "step": 4837 + }, + { + "epoch": 0.62, + "learning_rate": 8.085743500567228e-06, + "loss": 0.301, + "step": 4838 + }, + { + "epoch": 0.62, + "learning_rate": 8.084927877915314e-06, + "loss": 0.3337, + "step": 4839 + }, + { + "epoch": 0.62, + "learning_rate": 8.084112122697178e-06, + "loss": 0.3324, + "step": 4840 + }, + { + "epoch": 0.62, + "learning_rate": 8.083296234947878e-06, + "loss": 0.3103, + "step": 4841 + }, + { + "epoch": 0.62, + "learning_rate": 8.082480214702472e-06, + "loss": 0.3395, + "step": 4842 + }, + { + "epoch": 0.62, + "learning_rate": 8.081664061996024e-06, + "loss": 0.3347, + "step": 4843 + }, + { + "epoch": 0.62, + "learning_rate": 8.080847776863609e-06, + "loss": 0.2889, + "step": 4844 + }, + { + "epoch": 0.62, + "learning_rate": 8.080031359340303e-06, + "loss": 0.3032, + "step": 4845 + }, + { + "epoch": 0.62, + "learning_rate": 8.079214809461192e-06, + "loss": 0.344, + "step": 4846 + }, + { + "epoch": 0.62, + "learning_rate": 8.07839812726136e-06, + "loss": 0.3393, + "step": 4847 + }, + { + "epoch": 0.62, + "learning_rate": 8.077581312775908e-06, + "loss": 0.3261, + "step": 4848 + }, + { + "epoch": 0.62, + "learning_rate": 8.07676436603993e-06, + "loss": 0.3, + "step": 4849 + }, + { + "epoch": 0.62, + "learning_rate": 8.075947287088535e-06, + "loss": 0.3124, + "step": 4850 + }, + { + "epoch": 0.62, + "learning_rate": 8.075130075956836e-06, + "loss": 0.3318, + "step": 4851 + }, + { + "epoch": 0.62, + "learning_rate": 8.074312732679948e-06, + "loss": 0.3264, + "step": 4852 + }, + { + "epoch": 0.62, + "learning_rate": 8.073495257292996e-06, + "loss": 0.317, + "step": 4853 + }, + { + "epoch": 0.62, + "learning_rate": 8.072677649831107e-06, + "loss": 0.3274, + "step": 4854 + }, + { + "epoch": 0.62, + "learning_rate": 8.071859910329416e-06, + "loss": 0.3384, + "step": 4855 + }, + { + "epoch": 0.62, + "learning_rate": 8.071042038823063e-06, + "loss": 0.3165, + "step": 4856 + }, + { + "epoch": 0.62, + "learning_rate": 8.070224035347193e-06, + "loss": 0.3066, + "step": 4857 + }, + { + "epoch": 0.62, + "learning_rate": 8.069405899936961e-06, + "loss": 0.3365, + "step": 4858 + }, + { + "epoch": 0.62, + "learning_rate": 8.068587632627521e-06, + "loss": 0.3356, + "step": 4859 + }, + { + "epoch": 0.62, + "learning_rate": 8.067769233454037e-06, + "loss": 0.3248, + "step": 4860 + }, + { + "epoch": 0.62, + "learning_rate": 8.066950702451673e-06, + "loss": 0.2858, + "step": 4861 + }, + { + "epoch": 0.62, + "learning_rate": 8.066132039655609e-06, + "loss": 0.3421, + "step": 4862 + }, + { + "epoch": 0.62, + "learning_rate": 8.065313245101024e-06, + "loss": 0.3155, + "step": 4863 + }, + { + "epoch": 0.62, + "learning_rate": 8.064494318823102e-06, + "loss": 0.3326, + "step": 4864 + }, + { + "epoch": 0.62, + "learning_rate": 8.06367526085703e-06, + "loss": 0.3186, + "step": 4865 + }, + { + "epoch": 0.62, + "learning_rate": 8.062856071238014e-06, + "loss": 0.3176, + "step": 4866 + }, + { + "epoch": 0.62, + "learning_rate": 8.062036750001249e-06, + "loss": 0.3034, + "step": 4867 + }, + { + "epoch": 0.62, + "learning_rate": 8.061217297181946e-06, + "loss": 0.3487, + "step": 4868 + }, + { + "epoch": 0.62, + "learning_rate": 8.060397712815318e-06, + "loss": 0.3104, + "step": 4869 + }, + { + "epoch": 0.62, + "learning_rate": 8.059577996936583e-06, + "loss": 0.3311, + "step": 4870 + }, + { + "epoch": 0.62, + "learning_rate": 8.05875814958097e-06, + "loss": 0.3331, + "step": 4871 + }, + { + "epoch": 0.62, + "learning_rate": 8.057938170783704e-06, + "loss": 0.3084, + "step": 4872 + }, + { + "epoch": 0.62, + "learning_rate": 8.057118060580027e-06, + "loss": 0.3046, + "step": 4873 + }, + { + "epoch": 0.62, + "learning_rate": 8.056297819005177e-06, + "loss": 0.3394, + "step": 4874 + }, + { + "epoch": 0.62, + "learning_rate": 8.055477446094404e-06, + "loss": 0.3153, + "step": 4875 + }, + { + "epoch": 0.62, + "learning_rate": 8.054656941882959e-06, + "loss": 0.3351, + "step": 4876 + }, + { + "epoch": 0.62, + "learning_rate": 8.053836306406102e-06, + "loss": 0.327, + "step": 4877 + }, + { + "epoch": 0.62, + "learning_rate": 8.053015539699099e-06, + "loss": 0.3119, + "step": 4878 + }, + { + "epoch": 0.62, + "learning_rate": 8.052194641797217e-06, + "loss": 0.3416, + "step": 4879 + }, + { + "epoch": 0.62, + "learning_rate": 8.051373612735736e-06, + "loss": 0.3255, + "step": 4880 + }, + { + "epoch": 0.62, + "learning_rate": 8.050552452549933e-06, + "loss": 0.3368, + "step": 4881 + }, + { + "epoch": 0.62, + "learning_rate": 8.049731161275099e-06, + "loss": 0.317, + "step": 4882 + }, + { + "epoch": 0.63, + "learning_rate": 8.048909738946523e-06, + "loss": 0.3047, + "step": 4883 + }, + { + "epoch": 0.63, + "learning_rate": 8.048088185599507e-06, + "loss": 0.3086, + "step": 4884 + }, + { + "epoch": 0.63, + "learning_rate": 8.047266501269352e-06, + "loss": 0.3283, + "step": 4885 + }, + { + "epoch": 0.63, + "learning_rate": 8.046444685991369e-06, + "loss": 0.3124, + "step": 4886 + }, + { + "epoch": 0.63, + "learning_rate": 8.045622739800873e-06, + "loss": 0.3248, + "step": 4887 + }, + { + "epoch": 0.63, + "learning_rate": 8.044800662733185e-06, + "loss": 0.3344, + "step": 4888 + }, + { + "epoch": 0.63, + "learning_rate": 8.043978454823632e-06, + "loss": 0.3369, + "step": 4889 + }, + { + "epoch": 0.63, + "learning_rate": 8.043156116107545e-06, + "loss": 0.3206, + "step": 4890 + }, + { + "epoch": 0.63, + "learning_rate": 8.042333646620262e-06, + "loss": 0.3095, + "step": 4891 + }, + { + "epoch": 0.63, + "learning_rate": 8.041511046397127e-06, + "loss": 0.3202, + "step": 4892 + }, + { + "epoch": 0.63, + "learning_rate": 8.040688315473489e-06, + "loss": 0.3143, + "step": 4893 + }, + { + "epoch": 0.63, + "learning_rate": 8.0398654538847e-06, + "loss": 0.3403, + "step": 4894 + }, + { + "epoch": 0.63, + "learning_rate": 8.039042461666125e-06, + "loss": 0.332, + "step": 4895 + }, + { + "epoch": 0.63, + "learning_rate": 8.038219338853126e-06, + "loss": 0.33, + "step": 4896 + }, + { + "epoch": 0.63, + "learning_rate": 8.037396085481075e-06, + "loss": 0.3421, + "step": 4897 + }, + { + "epoch": 0.63, + "learning_rate": 8.03657270158535e-06, + "loss": 0.3416, + "step": 4898 + }, + { + "epoch": 0.63, + "learning_rate": 8.035749187201333e-06, + "loss": 0.3008, + "step": 4899 + }, + { + "epoch": 0.63, + "learning_rate": 8.034925542364412e-06, + "loss": 0.3302, + "step": 4900 + }, + { + "epoch": 0.63, + "learning_rate": 8.034101767109982e-06, + "loss": 0.343, + "step": 4901 + }, + { + "epoch": 0.63, + "learning_rate": 8.033277861473441e-06, + "loss": 0.3053, + "step": 4902 + }, + { + "epoch": 0.63, + "learning_rate": 8.032453825490197e-06, + "loss": 0.3339, + "step": 4903 + }, + { + "epoch": 0.63, + "learning_rate": 8.031629659195657e-06, + "loss": 0.3357, + "step": 4904 + }, + { + "epoch": 0.63, + "learning_rate": 8.030805362625238e-06, + "loss": 0.3196, + "step": 4905 + }, + { + "epoch": 0.63, + "learning_rate": 8.029980935814363e-06, + "loss": 0.3196, + "step": 4906 + }, + { + "epoch": 0.63, + "learning_rate": 8.029156378798459e-06, + "loss": 0.3041, + "step": 4907 + }, + { + "epoch": 0.63, + "learning_rate": 8.028331691612961e-06, + "loss": 0.3202, + "step": 4908 + }, + { + "epoch": 0.63, + "learning_rate": 8.027506874293304e-06, + "loss": 0.296, + "step": 4909 + }, + { + "epoch": 0.63, + "learning_rate": 8.026681926874932e-06, + "loss": 0.3324, + "step": 4910 + }, + { + "epoch": 0.63, + "learning_rate": 8.025856849393301e-06, + "loss": 0.2833, + "step": 4911 + }, + { + "epoch": 0.63, + "learning_rate": 8.02503164188386e-06, + "loss": 0.3433, + "step": 4912 + }, + { + "epoch": 0.63, + "learning_rate": 8.024206304382072e-06, + "loss": 0.3371, + "step": 4913 + }, + { + "epoch": 0.63, + "learning_rate": 8.023380836923404e-06, + "loss": 0.3032, + "step": 4914 + }, + { + "epoch": 0.63, + "learning_rate": 8.022555239543328e-06, + "loss": 0.3189, + "step": 4915 + }, + { + "epoch": 0.63, + "learning_rate": 8.021729512277323e-06, + "loss": 0.3081, + "step": 4916 + }, + { + "epoch": 0.63, + "learning_rate": 8.02090365516087e-06, + "loss": 0.3132, + "step": 4917 + }, + { + "epoch": 0.63, + "learning_rate": 8.02007766822946e-06, + "loss": 0.2913, + "step": 4918 + }, + { + "epoch": 0.63, + "learning_rate": 8.019251551518585e-06, + "loss": 0.2935, + "step": 4919 + }, + { + "epoch": 0.63, + "learning_rate": 8.018425305063749e-06, + "loss": 0.3364, + "step": 4920 + }, + { + "epoch": 0.63, + "learning_rate": 8.017598928900452e-06, + "loss": 0.2967, + "step": 4921 + }, + { + "epoch": 0.63, + "learning_rate": 8.01677242306421e-06, + "loss": 0.3456, + "step": 4922 + }, + { + "epoch": 0.63, + "learning_rate": 8.015945787590537e-06, + "loss": 0.3175, + "step": 4923 + }, + { + "epoch": 0.63, + "learning_rate": 8.015119022514958e-06, + "loss": 0.3549, + "step": 4924 + }, + { + "epoch": 0.63, + "learning_rate": 8.014292127873002e-06, + "loss": 0.3405, + "step": 4925 + }, + { + "epoch": 0.63, + "learning_rate": 8.013465103700197e-06, + "loss": 0.3442, + "step": 4926 + }, + { + "epoch": 0.63, + "learning_rate": 8.012637950032086e-06, + "loss": 0.294, + "step": 4927 + }, + { + "epoch": 0.63, + "learning_rate": 8.011810666904212e-06, + "loss": 0.3199, + "step": 4928 + }, + { + "epoch": 0.63, + "learning_rate": 8.010983254352127e-06, + "loss": 0.3238, + "step": 4929 + }, + { + "epoch": 0.63, + "learning_rate": 8.010155712411386e-06, + "loss": 0.3433, + "step": 4930 + }, + { + "epoch": 0.63, + "learning_rate": 8.009328041117547e-06, + "loss": 0.3146, + "step": 4931 + }, + { + "epoch": 0.63, + "learning_rate": 8.008500240506182e-06, + "loss": 0.3099, + "step": 4932 + }, + { + "epoch": 0.63, + "learning_rate": 8.007672310612863e-06, + "loss": 0.3223, + "step": 4933 + }, + { + "epoch": 0.63, + "learning_rate": 8.006844251473165e-06, + "loss": 0.3358, + "step": 4934 + }, + { + "epoch": 0.63, + "learning_rate": 8.006016063122672e-06, + "loss": 0.3221, + "step": 4935 + }, + { + "epoch": 0.63, + "learning_rate": 8.005187745596976e-06, + "loss": 0.2926, + "step": 4936 + }, + { + "epoch": 0.63, + "learning_rate": 8.004359298931668e-06, + "loss": 0.3518, + "step": 4937 + }, + { + "epoch": 0.63, + "learning_rate": 8.003530723162352e-06, + "loss": 0.3561, + "step": 4938 + }, + { + "epoch": 0.63, + "learning_rate": 8.002702018324629e-06, + "loss": 0.3054, + "step": 4939 + }, + { + "epoch": 0.63, + "learning_rate": 8.001873184454114e-06, + "loss": 0.3239, + "step": 4940 + }, + { + "epoch": 0.63, + "learning_rate": 8.001044221586423e-06, + "loss": 0.3271, + "step": 4941 + }, + { + "epoch": 0.63, + "learning_rate": 8.000215129757178e-06, + "loss": 0.2818, + "step": 4942 + }, + { + "epoch": 0.63, + "learning_rate": 7.999385909002007e-06, + "loss": 0.3379, + "step": 4943 + }, + { + "epoch": 0.63, + "learning_rate": 7.998556559356543e-06, + "loss": 0.3413, + "step": 4944 + }, + { + "epoch": 0.63, + "learning_rate": 7.997727080856425e-06, + "loss": 0.2743, + "step": 4945 + }, + { + "epoch": 0.63, + "learning_rate": 7.9968974735373e-06, + "loss": 0.312, + "step": 4946 + }, + { + "epoch": 0.63, + "learning_rate": 7.996067737434815e-06, + "loss": 0.3095, + "step": 4947 + }, + { + "epoch": 0.63, + "learning_rate": 7.995237872584627e-06, + "loss": 0.3134, + "step": 4948 + }, + { + "epoch": 0.63, + "learning_rate": 7.994407879022397e-06, + "loss": 0.3043, + "step": 4949 + }, + { + "epoch": 0.63, + "learning_rate": 7.99357775678379e-06, + "loss": 0.329, + "step": 4950 + }, + { + "epoch": 0.63, + "learning_rate": 7.99274750590448e-06, + "loss": 0.3352, + "step": 4951 + }, + { + "epoch": 0.63, + "learning_rate": 7.991917126420147e-06, + "loss": 0.3077, + "step": 4952 + }, + { + "epoch": 0.63, + "learning_rate": 7.99108661836647e-06, + "loss": 0.3224, + "step": 4953 + }, + { + "epoch": 0.63, + "learning_rate": 7.990255981779139e-06, + "loss": 0.2919, + "step": 4954 + }, + { + "epoch": 0.63, + "learning_rate": 7.989425216693849e-06, + "loss": 0.3525, + "step": 4955 + }, + { + "epoch": 0.63, + "learning_rate": 7.9885943231463e-06, + "loss": 0.2895, + "step": 4956 + }, + { + "epoch": 0.63, + "learning_rate": 7.987763301172197e-06, + "loss": 0.2968, + "step": 4957 + }, + { + "epoch": 0.63, + "learning_rate": 7.986932150807253e-06, + "loss": 0.3072, + "step": 4958 + }, + { + "epoch": 0.63, + "learning_rate": 7.986100872087177e-06, + "loss": 0.2893, + "step": 4959 + }, + { + "epoch": 0.63, + "learning_rate": 7.9852694650477e-06, + "loss": 0.3253, + "step": 4960 + }, + { + "epoch": 0.64, + "learning_rate": 7.984437929724546e-06, + "loss": 0.36, + "step": 4961 + }, + { + "epoch": 0.64, + "learning_rate": 7.983606266153445e-06, + "loss": 0.3327, + "step": 4962 + }, + { + "epoch": 0.64, + "learning_rate": 7.98277447437014e-06, + "loss": 0.2974, + "step": 4963 + }, + { + "epoch": 0.64, + "learning_rate": 7.981942554410371e-06, + "loss": 0.3099, + "step": 4964 + }, + { + "epoch": 0.64, + "learning_rate": 7.98111050630989e-06, + "loss": 0.3263, + "step": 4965 + }, + { + "epoch": 0.64, + "learning_rate": 7.980278330104452e-06, + "loss": 0.3154, + "step": 4966 + }, + { + "epoch": 0.64, + "learning_rate": 7.979446025829815e-06, + "loss": 0.3189, + "step": 4967 + }, + { + "epoch": 0.64, + "learning_rate": 7.978613593521748e-06, + "loss": 0.3398, + "step": 4968 + }, + { + "epoch": 0.64, + "learning_rate": 7.97778103321602e-06, + "loss": 0.3157, + "step": 4969 + }, + { + "epoch": 0.64, + "learning_rate": 7.976948344948412e-06, + "loss": 0.3208, + "step": 4970 + }, + { + "epoch": 0.64, + "learning_rate": 7.976115528754702e-06, + "loss": 0.3025, + "step": 4971 + }, + { + "epoch": 0.64, + "learning_rate": 7.975282584670679e-06, + "loss": 0.3409, + "step": 4972 + }, + { + "epoch": 0.64, + "learning_rate": 7.974449512732137e-06, + "loss": 0.3019, + "step": 4973 + }, + { + "epoch": 0.64, + "learning_rate": 7.973616312974876e-06, + "loss": 0.3459, + "step": 4974 + }, + { + "epoch": 0.64, + "learning_rate": 7.972782985434697e-06, + "loss": 0.3164, + "step": 4975 + }, + { + "epoch": 0.64, + "learning_rate": 7.971949530147417e-06, + "loss": 0.321, + "step": 4976 + }, + { + "epoch": 0.64, + "learning_rate": 7.971115947148842e-06, + "loss": 0.3451, + "step": 4977 + }, + { + "epoch": 0.64, + "learning_rate": 7.9702822364748e-06, + "loss": 0.2972, + "step": 4978 + }, + { + "epoch": 0.64, + "learning_rate": 7.969448398161115e-06, + "loss": 0.2997, + "step": 4979 + }, + { + "epoch": 0.64, + "learning_rate": 7.968614432243617e-06, + "loss": 0.2862, + "step": 4980 + }, + { + "epoch": 0.64, + "learning_rate": 7.96778033875815e-06, + "loss": 0.3319, + "step": 4981 + }, + { + "epoch": 0.64, + "learning_rate": 7.966946117740548e-06, + "loss": 0.3429, + "step": 4982 + }, + { + "epoch": 0.64, + "learning_rate": 7.966111769226666e-06, + "loss": 0.2941, + "step": 4983 + }, + { + "epoch": 0.64, + "learning_rate": 7.965277293252354e-06, + "loss": 0.3317, + "step": 4984 + }, + { + "epoch": 0.64, + "learning_rate": 7.964442689853473e-06, + "loss": 0.3214, + "step": 4985 + }, + { + "epoch": 0.64, + "learning_rate": 7.963607959065887e-06, + "loss": 0.3046, + "step": 4986 + }, + { + "epoch": 0.64, + "learning_rate": 7.962773100925467e-06, + "loss": 0.3299, + "step": 4987 + }, + { + "epoch": 0.64, + "learning_rate": 7.961938115468088e-06, + "loss": 0.3178, + "step": 4988 + }, + { + "epoch": 0.64, + "learning_rate": 7.961103002729634e-06, + "loss": 0.3116, + "step": 4989 + }, + { + "epoch": 0.64, + "learning_rate": 7.960267762745985e-06, + "loss": 0.3226, + "step": 4990 + }, + { + "epoch": 0.64, + "learning_rate": 7.95943239555304e-06, + "loss": 0.3348, + "step": 4991 + }, + { + "epoch": 0.64, + "learning_rate": 7.958596901186695e-06, + "loss": 0.3088, + "step": 4992 + }, + { + "epoch": 0.64, + "learning_rate": 7.95776127968285e-06, + "loss": 0.3172, + "step": 4993 + }, + { + "epoch": 0.64, + "learning_rate": 7.956925531077417e-06, + "loss": 0.335, + "step": 4994 + }, + { + "epoch": 0.64, + "learning_rate": 7.956089655406307e-06, + "loss": 0.3253, + "step": 4995 + }, + { + "epoch": 0.64, + "learning_rate": 7.955253652705442e-06, + "loss": 0.3437, + "step": 4996 + }, + { + "epoch": 0.64, + "learning_rate": 7.954417523010747e-06, + "loss": 0.3167, + "step": 4997 + }, + { + "epoch": 0.64, + "learning_rate": 7.953581266358148e-06, + "loss": 0.3045, + "step": 4998 + }, + { + "epoch": 0.64, + "learning_rate": 7.952744882783587e-06, + "loss": 0.3116, + "step": 4999 + }, + { + "epoch": 0.64, + "learning_rate": 7.951908372323001e-06, + "loss": 0.318, + "step": 5000 + }, + { + "epoch": 0.64, + "learning_rate": 7.951071735012337e-06, + "loss": 0.3445, + "step": 5001 + }, + { + "epoch": 0.64, + "learning_rate": 7.95023497088755e-06, + "loss": 0.3112, + "step": 5002 + }, + { + "epoch": 0.64, + "learning_rate": 7.949398079984594e-06, + "loss": 0.3207, + "step": 5003 + }, + { + "epoch": 0.64, + "learning_rate": 7.948561062339435e-06, + "loss": 0.3187, + "step": 5004 + }, + { + "epoch": 0.64, + "learning_rate": 7.94772391798804e-06, + "loss": 0.3062, + "step": 5005 + }, + { + "epoch": 0.64, + "learning_rate": 7.946886646966384e-06, + "loss": 0.3177, + "step": 5006 + }, + { + "epoch": 0.64, + "learning_rate": 7.946049249310445e-06, + "loss": 0.3295, + "step": 5007 + }, + { + "epoch": 0.64, + "learning_rate": 7.945211725056208e-06, + "loss": 0.311, + "step": 5008 + }, + { + "epoch": 0.64, + "learning_rate": 7.944374074239665e-06, + "loss": 0.3311, + "step": 5009 + }, + { + "epoch": 0.64, + "learning_rate": 7.94353629689681e-06, + "loss": 0.3147, + "step": 5010 + }, + { + "epoch": 0.64, + "learning_rate": 7.942698393063646e-06, + "loss": 0.3202, + "step": 5011 + }, + { + "epoch": 0.64, + "learning_rate": 7.941860362776176e-06, + "loss": 0.3252, + "step": 5012 + }, + { + "epoch": 0.64, + "learning_rate": 7.941022206070415e-06, + "loss": 0.3163, + "step": 5013 + }, + { + "epoch": 0.64, + "learning_rate": 7.940183922982381e-06, + "loss": 0.3254, + "step": 5014 + }, + { + "epoch": 0.64, + "learning_rate": 7.939345513548095e-06, + "loss": 0.3357, + "step": 5015 + }, + { + "epoch": 0.64, + "learning_rate": 7.938506977803586e-06, + "loss": 0.3119, + "step": 5016 + }, + { + "epoch": 0.64, + "learning_rate": 7.937668315784888e-06, + "loss": 0.3198, + "step": 5017 + }, + { + "epoch": 0.64, + "learning_rate": 7.93682952752804e-06, + "loss": 0.3095, + "step": 5018 + }, + { + "epoch": 0.64, + "learning_rate": 7.935990613069087e-06, + "loss": 0.2907, + "step": 5019 + }, + { + "epoch": 0.64, + "learning_rate": 7.935151572444076e-06, + "loss": 0.31, + "step": 5020 + }, + { + "epoch": 0.64, + "learning_rate": 7.934312405689067e-06, + "loss": 0.2965, + "step": 5021 + }, + { + "epoch": 0.64, + "learning_rate": 7.933473112840117e-06, + "loss": 0.3282, + "step": 5022 + }, + { + "epoch": 0.64, + "learning_rate": 7.932633693933298e-06, + "loss": 0.3412, + "step": 5023 + }, + { + "epoch": 0.64, + "learning_rate": 7.931794149004675e-06, + "loss": 0.3099, + "step": 5024 + }, + { + "epoch": 0.64, + "learning_rate": 7.930954478090329e-06, + "loss": 0.322, + "step": 5025 + }, + { + "epoch": 0.64, + "learning_rate": 7.930114681226341e-06, + "loss": 0.3343, + "step": 5026 + }, + { + "epoch": 0.64, + "learning_rate": 7.9292747584488e-06, + "loss": 0.3063, + "step": 5027 + }, + { + "epoch": 0.64, + "learning_rate": 7.928434709793798e-06, + "loss": 0.3072, + "step": 5028 + }, + { + "epoch": 0.64, + "learning_rate": 7.927594535297433e-06, + "loss": 0.3057, + "step": 5029 + }, + { + "epoch": 0.64, + "learning_rate": 7.926754234995814e-06, + "loss": 0.2918, + "step": 5030 + }, + { + "epoch": 0.64, + "learning_rate": 7.925913808925045e-06, + "loss": 0.3308, + "step": 5031 + }, + { + "epoch": 0.64, + "learning_rate": 7.925073257121245e-06, + "loss": 0.3101, + "step": 5032 + }, + { + "epoch": 0.64, + "learning_rate": 7.924232579620533e-06, + "loss": 0.3146, + "step": 5033 + }, + { + "epoch": 0.64, + "learning_rate": 7.923391776459031e-06, + "loss": 0.3214, + "step": 5034 + }, + { + "epoch": 0.64, + "learning_rate": 7.922550847672876e-06, + "loss": 0.351, + "step": 5035 + }, + { + "epoch": 0.64, + "learning_rate": 7.921709793298202e-06, + "loss": 0.3133, + "step": 5036 + }, + { + "epoch": 0.64, + "learning_rate": 7.920868613371151e-06, + "loss": 0.3166, + "step": 5037 + }, + { + "epoch": 0.64, + "learning_rate": 7.920027307927872e-06, + "loss": 0.3037, + "step": 5038 + }, + { + "epoch": 0.64, + "learning_rate": 7.919185877004515e-06, + "loss": 0.324, + "step": 5039 + }, + { + "epoch": 0.65, + "learning_rate": 7.91834432063724e-06, + "loss": 0.3088, + "step": 5040 + }, + { + "epoch": 0.65, + "learning_rate": 7.917502638862209e-06, + "loss": 0.3054, + "step": 5041 + }, + { + "epoch": 0.65, + "learning_rate": 7.916660831715592e-06, + "loss": 0.3144, + "step": 5042 + }, + { + "epoch": 0.65, + "learning_rate": 7.915818899233564e-06, + "loss": 0.3508, + "step": 5043 + }, + { + "epoch": 0.65, + "learning_rate": 7.914976841452304e-06, + "loss": 0.3468, + "step": 5044 + }, + { + "epoch": 0.65, + "learning_rate": 7.914134658407997e-06, + "loss": 0.3219, + "step": 5045 + }, + { + "epoch": 0.65, + "learning_rate": 7.913292350136834e-06, + "loss": 0.3415, + "step": 5046 + }, + { + "epoch": 0.65, + "learning_rate": 7.912449916675008e-06, + "loss": 0.3368, + "step": 5047 + }, + { + "epoch": 0.65, + "learning_rate": 7.911607358058726e-06, + "loss": 0.347, + "step": 5048 + }, + { + "epoch": 0.65, + "learning_rate": 7.91076467432419e-06, + "loss": 0.3286, + "step": 5049 + }, + { + "epoch": 0.65, + "learning_rate": 7.909921865507614e-06, + "loss": 0.3084, + "step": 5050 + }, + { + "epoch": 0.65, + "learning_rate": 7.909078931645215e-06, + "loss": 0.2945, + "step": 5051 + }, + { + "epoch": 0.65, + "learning_rate": 7.908235872773214e-06, + "loss": 0.3193, + "step": 5052 + }, + { + "epoch": 0.65, + "learning_rate": 7.907392688927842e-06, + "loss": 0.2795, + "step": 5053 + }, + { + "epoch": 0.65, + "learning_rate": 7.90654938014533e-06, + "loss": 0.3058, + "step": 5054 + }, + { + "epoch": 0.65, + "learning_rate": 7.905705946461918e-06, + "loss": 0.2903, + "step": 5055 + }, + { + "epoch": 0.65, + "learning_rate": 7.90486238791385e-06, + "loss": 0.3191, + "step": 5056 + }, + { + "epoch": 0.65, + "learning_rate": 7.904018704537376e-06, + "loss": 0.3425, + "step": 5057 + }, + { + "epoch": 0.65, + "learning_rate": 7.90317489636875e-06, + "loss": 0.3191, + "step": 5058 + }, + { + "epoch": 0.65, + "learning_rate": 7.902330963444234e-06, + "loss": 0.3314, + "step": 5059 + }, + { + "epoch": 0.65, + "learning_rate": 7.901486905800092e-06, + "loss": 0.3118, + "step": 5060 + }, + { + "epoch": 0.65, + "learning_rate": 7.900642723472596e-06, + "loss": 0.3472, + "step": 5061 + }, + { + "epoch": 0.65, + "learning_rate": 7.899798416498023e-06, + "loss": 0.3403, + "step": 5062 + }, + { + "epoch": 0.65, + "learning_rate": 7.898953984912652e-06, + "loss": 0.3221, + "step": 5063 + }, + { + "epoch": 0.65, + "learning_rate": 7.898109428752773e-06, + "loss": 0.3093, + "step": 5064 + }, + { + "epoch": 0.65, + "learning_rate": 7.897264748054679e-06, + "loss": 0.3233, + "step": 5065 + }, + { + "epoch": 0.65, + "learning_rate": 7.896419942854662e-06, + "loss": 0.3677, + "step": 5066 + }, + { + "epoch": 0.65, + "learning_rate": 7.895575013189032e-06, + "loss": 0.3327, + "step": 5067 + }, + { + "epoch": 0.65, + "learning_rate": 7.894729959094097e-06, + "loss": 0.3282, + "step": 5068 + }, + { + "epoch": 0.65, + "learning_rate": 7.893884780606164e-06, + "loss": 0.3394, + "step": 5069 + }, + { + "epoch": 0.65, + "learning_rate": 7.893039477761562e-06, + "loss": 0.3429, + "step": 5070 + }, + { + "epoch": 0.65, + "learning_rate": 7.892194050596606e-06, + "loss": 0.341, + "step": 5071 + }, + { + "epoch": 0.65, + "learning_rate": 7.891348499147634e-06, + "loss": 0.3019, + "step": 5072 + }, + { + "epoch": 0.65, + "learning_rate": 7.890502823450975e-06, + "loss": 0.3105, + "step": 5073 + }, + { + "epoch": 0.65, + "learning_rate": 7.889657023542973e-06, + "loss": 0.3187, + "step": 5074 + }, + { + "epoch": 0.65, + "learning_rate": 7.888811099459974e-06, + "loss": 0.3455, + "step": 5075 + }, + { + "epoch": 0.65, + "learning_rate": 7.887965051238326e-06, + "loss": 0.3337, + "step": 5076 + }, + { + "epoch": 0.65, + "learning_rate": 7.88711887891439e-06, + "loss": 0.289, + "step": 5077 + }, + { + "epoch": 0.65, + "learning_rate": 7.886272582524525e-06, + "loss": 0.2865, + "step": 5078 + }, + { + "epoch": 0.65, + "learning_rate": 7.885426162105101e-06, + "loss": 0.2896, + "step": 5079 + }, + { + "epoch": 0.65, + "learning_rate": 7.884579617692487e-06, + "loss": 0.2877, + "step": 5080 + }, + { + "epoch": 0.65, + "learning_rate": 7.883732949323061e-06, + "loss": 0.3104, + "step": 5081 + }, + { + "epoch": 0.65, + "learning_rate": 7.882886157033209e-06, + "loss": 0.294, + "step": 5082 + }, + { + "epoch": 0.65, + "learning_rate": 7.882039240859318e-06, + "loss": 0.3406, + "step": 5083 + }, + { + "epoch": 0.65, + "learning_rate": 7.881192200837785e-06, + "loss": 0.3367, + "step": 5084 + }, + { + "epoch": 0.65, + "learning_rate": 7.880345037005002e-06, + "loss": 0.3498, + "step": 5085 + }, + { + "epoch": 0.65, + "learning_rate": 7.879497749397382e-06, + "loss": 0.3201, + "step": 5086 + }, + { + "epoch": 0.65, + "learning_rate": 7.878650338051328e-06, + "loss": 0.3147, + "step": 5087 + }, + { + "epoch": 0.65, + "learning_rate": 7.877802803003258e-06, + "loss": 0.3089, + "step": 5088 + }, + { + "epoch": 0.65, + "learning_rate": 7.876955144289594e-06, + "loss": 0.3099, + "step": 5089 + }, + { + "epoch": 0.65, + "learning_rate": 7.876107361946758e-06, + "loss": 0.3115, + "step": 5090 + }, + { + "epoch": 0.65, + "learning_rate": 7.875259456011185e-06, + "loss": 0.3176, + "step": 5091 + }, + { + "epoch": 0.65, + "learning_rate": 7.874411426519308e-06, + "loss": 0.3247, + "step": 5092 + }, + { + "epoch": 0.65, + "learning_rate": 7.873563273507571e-06, + "loss": 0.3181, + "step": 5093 + }, + { + "epoch": 0.65, + "learning_rate": 7.872714997012421e-06, + "loss": 0.29, + "step": 5094 + }, + { + "epoch": 0.65, + "learning_rate": 7.87186659707031e-06, + "loss": 0.3288, + "step": 5095 + }, + { + "epoch": 0.65, + "learning_rate": 7.871018073717693e-06, + "loss": 0.2857, + "step": 5096 + }, + { + "epoch": 0.65, + "learning_rate": 7.870169426991038e-06, + "loss": 0.3189, + "step": 5097 + }, + { + "epoch": 0.65, + "learning_rate": 7.86932065692681e-06, + "loss": 0.3045, + "step": 5098 + }, + { + "epoch": 0.65, + "learning_rate": 7.868471763561482e-06, + "loss": 0.3136, + "step": 5099 + }, + { + "epoch": 0.65, + "learning_rate": 7.867622746931533e-06, + "loss": 0.3136, + "step": 5100 + }, + { + "epoch": 0.65, + "learning_rate": 7.86677360707345e-06, + "loss": 0.3049, + "step": 5101 + }, + { + "epoch": 0.65, + "learning_rate": 7.865924344023722e-06, + "loss": 0.3489, + "step": 5102 + }, + { + "epoch": 0.65, + "learning_rate": 7.865074957818839e-06, + "loss": 0.3291, + "step": 5103 + }, + { + "epoch": 0.65, + "learning_rate": 7.864225448495304e-06, + "loss": 0.3411, + "step": 5104 + }, + { + "epoch": 0.65, + "learning_rate": 7.863375816089624e-06, + "loss": 0.3277, + "step": 5105 + }, + { + "epoch": 0.65, + "learning_rate": 7.862526060638309e-06, + "loss": 0.3485, + "step": 5106 + }, + { + "epoch": 0.65, + "learning_rate": 7.861676182177873e-06, + "loss": 0.3184, + "step": 5107 + }, + { + "epoch": 0.65, + "learning_rate": 7.860826180744837e-06, + "loss": 0.3233, + "step": 5108 + }, + { + "epoch": 0.65, + "learning_rate": 7.85997605637573e-06, + "loss": 0.3085, + "step": 5109 + }, + { + "epoch": 0.65, + "learning_rate": 7.859125809107082e-06, + "loss": 0.304, + "step": 5110 + }, + { + "epoch": 0.65, + "learning_rate": 7.85827543897543e-06, + "loss": 0.3067, + "step": 5111 + }, + { + "epoch": 0.65, + "learning_rate": 7.857424946017317e-06, + "loss": 0.3377, + "step": 5112 + }, + { + "epoch": 0.65, + "learning_rate": 7.85657433026929e-06, + "loss": 0.2815, + "step": 5113 + }, + { + "epoch": 0.65, + "learning_rate": 7.855723591767903e-06, + "loss": 0.29, + "step": 5114 + }, + { + "epoch": 0.65, + "learning_rate": 7.854872730549712e-06, + "loss": 0.3107, + "step": 5115 + }, + { + "epoch": 0.65, + "learning_rate": 7.854021746651283e-06, + "loss": 0.36, + "step": 5116 + }, + { + "epoch": 0.65, + "learning_rate": 7.853170640109182e-06, + "loss": 0.3129, + "step": 5117 + }, + { + "epoch": 0.66, + "learning_rate": 7.852319410959984e-06, + "loss": 0.3149, + "step": 5118 + }, + { + "epoch": 0.66, + "learning_rate": 7.85146805924027e-06, + "loss": 0.3452, + "step": 5119 + }, + { + "epoch": 0.66, + "learning_rate": 7.850616584986621e-06, + "loss": 0.3043, + "step": 5120 + }, + { + "epoch": 0.66, + "learning_rate": 7.84976498823563e-06, + "loss": 0.3036, + "step": 5121 + }, + { + "epoch": 0.66, + "learning_rate": 7.84891326902389e-06, + "loss": 0.3715, + "step": 5122 + }, + { + "epoch": 0.66, + "learning_rate": 7.848061427388002e-06, + "loss": 0.3351, + "step": 5123 + }, + { + "epoch": 0.66, + "learning_rate": 7.847209463364574e-06, + "loss": 0.3287, + "step": 5124 + }, + { + "epoch": 0.66, + "learning_rate": 7.846357376990213e-06, + "loss": 0.3264, + "step": 5125 + }, + { + "epoch": 0.66, + "learning_rate": 7.845505168301533e-06, + "loss": 0.3129, + "step": 5126 + }, + { + "epoch": 0.66, + "learning_rate": 7.844652837335162e-06, + "loss": 0.3129, + "step": 5127 + }, + { + "epoch": 0.66, + "learning_rate": 7.843800384127721e-06, + "loss": 0.3316, + "step": 5128 + }, + { + "epoch": 0.66, + "learning_rate": 7.842947808715848e-06, + "loss": 0.3265, + "step": 5129 + }, + { + "epoch": 0.66, + "learning_rate": 7.842095111136173e-06, + "loss": 0.3238, + "step": 5130 + }, + { + "epoch": 0.66, + "learning_rate": 7.841242291425342e-06, + "loss": 0.316, + "step": 5131 + }, + { + "epoch": 0.66, + "learning_rate": 7.840389349620002e-06, + "loss": 0.3111, + "step": 5132 + }, + { + "epoch": 0.66, + "learning_rate": 7.839536285756804e-06, + "loss": 0.3141, + "step": 5133 + }, + { + "epoch": 0.66, + "learning_rate": 7.83868309987241e-06, + "loss": 0.3225, + "step": 5134 + }, + { + "epoch": 0.66, + "learning_rate": 7.837829792003479e-06, + "loss": 0.3529, + "step": 5135 + }, + { + "epoch": 0.66, + "learning_rate": 7.836976362186684e-06, + "loss": 0.3205, + "step": 5136 + }, + { + "epoch": 0.66, + "learning_rate": 7.836122810458696e-06, + "loss": 0.3196, + "step": 5137 + }, + { + "epoch": 0.66, + "learning_rate": 7.835269136856194e-06, + "loss": 0.3284, + "step": 5138 + }, + { + "epoch": 0.66, + "learning_rate": 7.834415341415862e-06, + "loss": 0.3407, + "step": 5139 + }, + { + "epoch": 0.66, + "learning_rate": 7.833561424174392e-06, + "loss": 0.3508, + "step": 5140 + }, + { + "epoch": 0.66, + "learning_rate": 7.832707385168474e-06, + "loss": 0.3335, + "step": 5141 + }, + { + "epoch": 0.66, + "learning_rate": 7.831853224434815e-06, + "loss": 0.2993, + "step": 5142 + }, + { + "epoch": 0.66, + "learning_rate": 7.830998942010113e-06, + "loss": 0.3343, + "step": 5143 + }, + { + "epoch": 0.66, + "learning_rate": 7.830144537931082e-06, + "loss": 0.3435, + "step": 5144 + }, + { + "epoch": 0.66, + "learning_rate": 7.829290012234438e-06, + "loss": 0.3098, + "step": 5145 + }, + { + "epoch": 0.66, + "learning_rate": 7.8284353649569e-06, + "loss": 0.3044, + "step": 5146 + }, + { + "epoch": 0.66, + "learning_rate": 7.827580596135196e-06, + "loss": 0.2914, + "step": 5147 + }, + { + "epoch": 0.66, + "learning_rate": 7.826725705806056e-06, + "loss": 0.3234, + "step": 5148 + }, + { + "epoch": 0.66, + "learning_rate": 7.825870694006217e-06, + "loss": 0.2874, + "step": 5149 + }, + { + "epoch": 0.66, + "learning_rate": 7.82501556077242e-06, + "loss": 0.3515, + "step": 5150 + }, + { + "epoch": 0.66, + "learning_rate": 7.824160306141413e-06, + "loss": 0.3093, + "step": 5151 + }, + { + "epoch": 0.66, + "learning_rate": 7.823304930149949e-06, + "loss": 0.3201, + "step": 5152 + }, + { + "epoch": 0.66, + "learning_rate": 7.822449432834784e-06, + "loss": 0.3202, + "step": 5153 + }, + { + "epoch": 0.66, + "learning_rate": 7.82159381423268e-06, + "loss": 0.3025, + "step": 5154 + }, + { + "epoch": 0.66, + "learning_rate": 7.820738074380404e-06, + "loss": 0.3323, + "step": 5155 + }, + { + "epoch": 0.66, + "learning_rate": 7.819882213314736e-06, + "loss": 0.2952, + "step": 5156 + }, + { + "epoch": 0.66, + "learning_rate": 7.819026231072445e-06, + "loss": 0.3279, + "step": 5157 + }, + { + "epoch": 0.66, + "learning_rate": 7.81817012769032e-06, + "loss": 0.3179, + "step": 5158 + }, + { + "epoch": 0.66, + "learning_rate": 7.817313903205148e-06, + "loss": 0.3181, + "step": 5159 + }, + { + "epoch": 0.66, + "learning_rate": 7.816457557653722e-06, + "loss": 0.3269, + "step": 5160 + }, + { + "epoch": 0.66, + "learning_rate": 7.815601091072845e-06, + "loss": 0.3033, + "step": 5161 + }, + { + "epoch": 0.66, + "learning_rate": 7.814744503499317e-06, + "loss": 0.3224, + "step": 5162 + }, + { + "epoch": 0.66, + "learning_rate": 7.813887794969948e-06, + "loss": 0.3051, + "step": 5163 + }, + { + "epoch": 0.66, + "learning_rate": 7.813030965521554e-06, + "loss": 0.3064, + "step": 5164 + }, + { + "epoch": 0.66, + "learning_rate": 7.812174015190955e-06, + "loss": 0.304, + "step": 5165 + }, + { + "epoch": 0.66, + "learning_rate": 7.811316944014974e-06, + "loss": 0.306, + "step": 5166 + }, + { + "epoch": 0.66, + "learning_rate": 7.810459752030444e-06, + "loss": 0.3102, + "step": 5167 + }, + { + "epoch": 0.66, + "learning_rate": 7.809602439274198e-06, + "loss": 0.3112, + "step": 5168 + }, + { + "epoch": 0.66, + "learning_rate": 7.80874500578308e-06, + "loss": 0.3383, + "step": 5169 + }, + { + "epoch": 0.66, + "learning_rate": 7.807887451593932e-06, + "loss": 0.3065, + "step": 5170 + }, + { + "epoch": 0.66, + "learning_rate": 7.807029776743608e-06, + "loss": 0.3181, + "step": 5171 + }, + { + "epoch": 0.66, + "learning_rate": 7.806171981268962e-06, + "loss": 0.363, + "step": 5172 + }, + { + "epoch": 0.66, + "learning_rate": 7.805314065206857e-06, + "loss": 0.3162, + "step": 5173 + }, + { + "epoch": 0.66, + "learning_rate": 7.804456028594158e-06, + "loss": 0.3244, + "step": 5174 + }, + { + "epoch": 0.66, + "learning_rate": 7.803597871467738e-06, + "loss": 0.3233, + "step": 5175 + }, + { + "epoch": 0.66, + "learning_rate": 7.802739593864475e-06, + "loss": 0.346, + "step": 5176 + }, + { + "epoch": 0.66, + "learning_rate": 7.801881195821246e-06, + "loss": 0.3106, + "step": 5177 + }, + { + "epoch": 0.66, + "learning_rate": 7.801022677374945e-06, + "loss": 0.3195, + "step": 5178 + }, + { + "epoch": 0.66, + "learning_rate": 7.80016403856246e-06, + "loss": 0.3348, + "step": 5179 + }, + { + "epoch": 0.66, + "learning_rate": 7.799305279420691e-06, + "loss": 0.3251, + "step": 5180 + }, + { + "epoch": 0.66, + "learning_rate": 7.79844639998654e-06, + "loss": 0.341, + "step": 5181 + }, + { + "epoch": 0.66, + "learning_rate": 7.797587400296913e-06, + "loss": 0.2931, + "step": 5182 + }, + { + "epoch": 0.66, + "learning_rate": 7.796728280388725e-06, + "loss": 0.3076, + "step": 5183 + }, + { + "epoch": 0.66, + "learning_rate": 7.795869040298895e-06, + "loss": 0.3047, + "step": 5184 + }, + { + "epoch": 0.66, + "learning_rate": 7.795009680064344e-06, + "loss": 0.3049, + "step": 5185 + }, + { + "epoch": 0.66, + "learning_rate": 7.794150199722004e-06, + "loss": 0.3357, + "step": 5186 + }, + { + "epoch": 0.66, + "learning_rate": 7.793290599308807e-06, + "loss": 0.3557, + "step": 5187 + }, + { + "epoch": 0.66, + "learning_rate": 7.792430878861691e-06, + "loss": 0.3498, + "step": 5188 + }, + { + "epoch": 0.66, + "learning_rate": 7.791571038417602e-06, + "loss": 0.3484, + "step": 5189 + }, + { + "epoch": 0.66, + "learning_rate": 7.79071107801349e-06, + "loss": 0.306, + "step": 5190 + }, + { + "epoch": 0.66, + "learning_rate": 7.789850997686303e-06, + "loss": 0.3117, + "step": 5191 + }, + { + "epoch": 0.66, + "learning_rate": 7.78899079747301e-06, + "loss": 0.3195, + "step": 5192 + }, + { + "epoch": 0.66, + "learning_rate": 7.788130477410567e-06, + "loss": 0.3119, + "step": 5193 + }, + { + "epoch": 0.66, + "learning_rate": 7.78727003753595e-06, + "loss": 0.304, + "step": 5194 + }, + { + "epoch": 0.66, + "learning_rate": 7.786409477886133e-06, + "loss": 0.3124, + "step": 5195 + }, + { + "epoch": 0.67, + "learning_rate": 7.785548798498093e-06, + "loss": 0.3335, + "step": 5196 + }, + { + "epoch": 0.67, + "learning_rate": 7.784687999408817e-06, + "loss": 0.2948, + "step": 5197 + }, + { + "epoch": 0.67, + "learning_rate": 7.7838270806553e-06, + "loss": 0.3172, + "step": 5198 + }, + { + "epoch": 0.67, + "learning_rate": 7.782966042274529e-06, + "loss": 0.3248, + "step": 5199 + }, + { + "epoch": 0.67, + "learning_rate": 7.782104884303512e-06, + "loss": 0.3296, + "step": 5200 + }, + { + "epoch": 0.67, + "learning_rate": 7.78124360677925e-06, + "loss": 0.2913, + "step": 5201 + }, + { + "epoch": 0.67, + "learning_rate": 7.780382209738756e-06, + "loss": 0.3198, + "step": 5202 + }, + { + "epoch": 0.67, + "learning_rate": 7.779520693219047e-06, + "loss": 0.3194, + "step": 5203 + }, + { + "epoch": 0.67, + "learning_rate": 7.778659057257144e-06, + "loss": 0.3045, + "step": 5204 + }, + { + "epoch": 0.67, + "learning_rate": 7.777797301890073e-06, + "loss": 0.3102, + "step": 5205 + }, + { + "epoch": 0.67, + "learning_rate": 7.776935427154864e-06, + "loss": 0.3333, + "step": 5206 + }, + { + "epoch": 0.67, + "learning_rate": 7.776073433088555e-06, + "loss": 0.3068, + "step": 5207 + }, + { + "epoch": 0.67, + "learning_rate": 7.775211319728191e-06, + "loss": 0.2866, + "step": 5208 + }, + { + "epoch": 0.67, + "learning_rate": 7.774349087110813e-06, + "loss": 0.316, + "step": 5209 + }, + { + "epoch": 0.67, + "learning_rate": 7.773486735273476e-06, + "loss": 0.3189, + "step": 5210 + }, + { + "epoch": 0.67, + "learning_rate": 7.772624264253237e-06, + "loss": 0.3214, + "step": 5211 + }, + { + "epoch": 0.67, + "learning_rate": 7.77176167408716e-06, + "loss": 0.3332, + "step": 5212 + }, + { + "epoch": 0.67, + "learning_rate": 7.77089896481231e-06, + "loss": 0.3127, + "step": 5213 + }, + { + "epoch": 0.67, + "learning_rate": 7.77003613646576e-06, + "loss": 0.3065, + "step": 5214 + }, + { + "epoch": 0.67, + "learning_rate": 7.769173189084589e-06, + "loss": 0.3224, + "step": 5215 + }, + { + "epoch": 0.67, + "learning_rate": 7.768310122705877e-06, + "loss": 0.3362, + "step": 5216 + }, + { + "epoch": 0.67, + "learning_rate": 7.767446937366716e-06, + "loss": 0.2823, + "step": 5217 + }, + { + "epoch": 0.67, + "learning_rate": 7.766583633104195e-06, + "loss": 0.307, + "step": 5218 + }, + { + "epoch": 0.67, + "learning_rate": 7.765720209955414e-06, + "loss": 0.2967, + "step": 5219 + }, + { + "epoch": 0.67, + "learning_rate": 7.764856667957477e-06, + "loss": 0.3117, + "step": 5220 + }, + { + "epoch": 0.67, + "learning_rate": 7.76399300714749e-06, + "loss": 0.2827, + "step": 5221 + }, + { + "epoch": 0.67, + "learning_rate": 7.763129227562568e-06, + "loss": 0.3299, + "step": 5222 + }, + { + "epoch": 0.67, + "learning_rate": 7.762265329239829e-06, + "loss": 0.2952, + "step": 5223 + }, + { + "epoch": 0.67, + "learning_rate": 7.761401312216398e-06, + "loss": 0.3067, + "step": 5224 + }, + { + "epoch": 0.67, + "learning_rate": 7.760537176529402e-06, + "loss": 0.3167, + "step": 5225 + }, + { + "epoch": 0.67, + "learning_rate": 7.759672922215976e-06, + "loss": 0.3312, + "step": 5226 + }, + { + "epoch": 0.67, + "learning_rate": 7.758808549313258e-06, + "loss": 0.3265, + "step": 5227 + }, + { + "epoch": 0.67, + "learning_rate": 7.757944057858392e-06, + "loss": 0.3447, + "step": 5228 + }, + { + "epoch": 0.67, + "learning_rate": 7.757079447888529e-06, + "loss": 0.323, + "step": 5229 + }, + { + "epoch": 0.67, + "learning_rate": 7.75621471944082e-06, + "loss": 0.307, + "step": 5230 + }, + { + "epoch": 0.67, + "learning_rate": 7.755349872552426e-06, + "loss": 0.3234, + "step": 5231 + }, + { + "epoch": 0.67, + "learning_rate": 7.754484907260513e-06, + "loss": 0.3289, + "step": 5232 + }, + { + "epoch": 0.67, + "learning_rate": 7.753619823602249e-06, + "loss": 0.3101, + "step": 5233 + }, + { + "epoch": 0.67, + "learning_rate": 7.752754621614807e-06, + "loss": 0.3079, + "step": 5234 + }, + { + "epoch": 0.67, + "learning_rate": 7.751889301335369e-06, + "loss": 0.3437, + "step": 5235 + }, + { + "epoch": 0.67, + "learning_rate": 7.75102386280112e-06, + "loss": 0.3374, + "step": 5236 + }, + { + "epoch": 0.67, + "learning_rate": 7.750158306049247e-06, + "loss": 0.3448, + "step": 5237 + }, + { + "epoch": 0.67, + "learning_rate": 7.749292631116946e-06, + "loss": 0.3231, + "step": 5238 + }, + { + "epoch": 0.67, + "learning_rate": 7.748426838041421e-06, + "loss": 0.3426, + "step": 5239 + }, + { + "epoch": 0.67, + "learning_rate": 7.747560926859872e-06, + "loss": 0.3142, + "step": 5240 + }, + { + "epoch": 0.67, + "learning_rate": 7.74669489760951e-06, + "loss": 0.3293, + "step": 5241 + }, + { + "epoch": 0.67, + "learning_rate": 7.745828750327551e-06, + "loss": 0.3115, + "step": 5242 + }, + { + "epoch": 0.67, + "learning_rate": 7.744962485051217e-06, + "loss": 0.3092, + "step": 5243 + }, + { + "epoch": 0.67, + "learning_rate": 7.744096101817731e-06, + "loss": 0.3311, + "step": 5244 + }, + { + "epoch": 0.67, + "learning_rate": 7.743229600664322e-06, + "loss": 0.3233, + "step": 5245 + }, + { + "epoch": 0.67, + "learning_rate": 7.742362981628229e-06, + "loss": 0.321, + "step": 5246 + }, + { + "epoch": 0.67, + "learning_rate": 7.741496244746692e-06, + "loss": 0.3226, + "step": 5247 + }, + { + "epoch": 0.67, + "learning_rate": 7.740629390056955e-06, + "loss": 0.3244, + "step": 5248 + }, + { + "epoch": 0.67, + "learning_rate": 7.73976241759627e-06, + "loss": 0.3385, + "step": 5249 + }, + { + "epoch": 0.67, + "learning_rate": 7.738895327401891e-06, + "loss": 0.3474, + "step": 5250 + }, + { + "epoch": 0.67, + "learning_rate": 7.738028119511081e-06, + "loss": 0.3182, + "step": 5251 + }, + { + "epoch": 0.67, + "learning_rate": 7.737160793961103e-06, + "loss": 0.3456, + "step": 5252 + }, + { + "epoch": 0.67, + "learning_rate": 7.736293350789232e-06, + "loss": 0.3111, + "step": 5253 + }, + { + "epoch": 0.67, + "learning_rate": 7.73542579003274e-06, + "loss": 0.3339, + "step": 5254 + }, + { + "epoch": 0.67, + "learning_rate": 7.734558111728911e-06, + "loss": 0.3131, + "step": 5255 + }, + { + "epoch": 0.67, + "learning_rate": 7.733690315915028e-06, + "loss": 0.2936, + "step": 5256 + }, + { + "epoch": 0.67, + "learning_rate": 7.732822402628385e-06, + "loss": 0.3321, + "step": 5257 + }, + { + "epoch": 0.67, + "learning_rate": 7.731954371906279e-06, + "loss": 0.3213, + "step": 5258 + }, + { + "epoch": 0.67, + "learning_rate": 7.731086223786006e-06, + "loss": 0.2992, + "step": 5259 + }, + { + "epoch": 0.67, + "learning_rate": 7.730217958304876e-06, + "loss": 0.3133, + "step": 5260 + }, + { + "epoch": 0.67, + "learning_rate": 7.729349575500202e-06, + "loss": 0.33, + "step": 5261 + }, + { + "epoch": 0.67, + "learning_rate": 7.728481075409297e-06, + "loss": 0.3268, + "step": 5262 + }, + { + "epoch": 0.67, + "learning_rate": 7.727612458069482e-06, + "loss": 0.3116, + "step": 5263 + }, + { + "epoch": 0.67, + "learning_rate": 7.726743723518087e-06, + "loss": 0.3066, + "step": 5264 + }, + { + "epoch": 0.67, + "learning_rate": 7.72587487179244e-06, + "loss": 0.3116, + "step": 5265 + }, + { + "epoch": 0.67, + "learning_rate": 7.72500590292988e-06, + "loss": 0.362, + "step": 5266 + }, + { + "epoch": 0.67, + "learning_rate": 7.724136816967746e-06, + "loss": 0.3284, + "step": 5267 + }, + { + "epoch": 0.67, + "learning_rate": 7.723267613943388e-06, + "loss": 0.3086, + "step": 5268 + }, + { + "epoch": 0.67, + "learning_rate": 7.722398293894153e-06, + "loss": 0.3059, + "step": 5269 + }, + { + "epoch": 0.67, + "learning_rate": 7.721528856857403e-06, + "loss": 0.3148, + "step": 5270 + }, + { + "epoch": 0.67, + "learning_rate": 7.720659302870496e-06, + "loss": 0.3333, + "step": 5271 + }, + { + "epoch": 0.67, + "learning_rate": 7.719789631970798e-06, + "loss": 0.327, + "step": 5272 + }, + { + "epoch": 0.67, + "learning_rate": 7.718919844195685e-06, + "loss": 0.3353, + "step": 5273 + }, + { + "epoch": 0.68, + "learning_rate": 7.718049939582529e-06, + "loss": 0.3289, + "step": 5274 + }, + { + "epoch": 0.68, + "learning_rate": 7.717179918168713e-06, + "loss": 0.3373, + "step": 5275 + }, + { + "epoch": 0.68, + "learning_rate": 7.716309779991625e-06, + "loss": 0.3306, + "step": 5276 + }, + { + "epoch": 0.68, + "learning_rate": 7.715439525088657e-06, + "loss": 0.3168, + "step": 5277 + }, + { + "epoch": 0.68, + "learning_rate": 7.714569153497204e-06, + "loss": 0.3204, + "step": 5278 + }, + { + "epoch": 0.68, + "learning_rate": 7.713698665254669e-06, + "loss": 0.3179, + "step": 5279 + }, + { + "epoch": 0.68, + "learning_rate": 7.71282806039846e-06, + "loss": 0.2888, + "step": 5280 + }, + { + "epoch": 0.68, + "learning_rate": 7.711957338965986e-06, + "loss": 0.3298, + "step": 5281 + }, + { + "epoch": 0.68, + "learning_rate": 7.711086500994667e-06, + "loss": 0.3267, + "step": 5282 + }, + { + "epoch": 0.68, + "learning_rate": 7.710215546521921e-06, + "loss": 0.324, + "step": 5283 + }, + { + "epoch": 0.68, + "learning_rate": 7.70934447558518e-06, + "loss": 0.301, + "step": 5284 + }, + { + "epoch": 0.68, + "learning_rate": 7.708473288221868e-06, + "loss": 0.303, + "step": 5285 + }, + { + "epoch": 0.68, + "learning_rate": 7.70760198446943e-06, + "loss": 0.3517, + "step": 5286 + }, + { + "epoch": 0.68, + "learning_rate": 7.706730564365304e-06, + "loss": 0.3327, + "step": 5287 + }, + { + "epoch": 0.68, + "learning_rate": 7.705859027946939e-06, + "loss": 0.309, + "step": 5288 + }, + { + "epoch": 0.68, + "learning_rate": 7.704987375251782e-06, + "loss": 0.331, + "step": 5289 + }, + { + "epoch": 0.68, + "learning_rate": 7.704115606317296e-06, + "loss": 0.3061, + "step": 5290 + }, + { + "epoch": 0.68, + "learning_rate": 7.703243721180938e-06, + "loss": 0.3118, + "step": 5291 + }, + { + "epoch": 0.68, + "learning_rate": 7.702371719880178e-06, + "loss": 0.322, + "step": 5292 + }, + { + "epoch": 0.68, + "learning_rate": 7.701499602452487e-06, + "loss": 0.3168, + "step": 5293 + }, + { + "epoch": 0.68, + "learning_rate": 7.70062736893534e-06, + "loss": 0.3048, + "step": 5294 + }, + { + "epoch": 0.68, + "learning_rate": 7.699755019366221e-06, + "loss": 0.3055, + "step": 5295 + }, + { + "epoch": 0.68, + "learning_rate": 7.698882553782617e-06, + "loss": 0.3477, + "step": 5296 + }, + { + "epoch": 0.68, + "learning_rate": 7.698009972222017e-06, + "loss": 0.2825, + "step": 5297 + }, + { + "epoch": 0.68, + "learning_rate": 7.697137274721922e-06, + "loss": 0.3238, + "step": 5298 + }, + { + "epoch": 0.68, + "learning_rate": 7.696264461319831e-06, + "loss": 0.2891, + "step": 5299 + }, + { + "epoch": 0.68, + "learning_rate": 7.69539153205325e-06, + "loss": 0.3329, + "step": 5300 + }, + { + "epoch": 0.68, + "learning_rate": 7.694518486959695e-06, + "loss": 0.3308, + "step": 5301 + }, + { + "epoch": 0.68, + "learning_rate": 7.693645326076677e-06, + "loss": 0.31, + "step": 5302 + }, + { + "epoch": 0.68, + "learning_rate": 7.692772049441718e-06, + "loss": 0.3044, + "step": 5303 + }, + { + "epoch": 0.68, + "learning_rate": 7.69189865709235e-06, + "loss": 0.3164, + "step": 5304 + }, + { + "epoch": 0.68, + "learning_rate": 7.691025149066103e-06, + "loss": 0.3193, + "step": 5305 + }, + { + "epoch": 0.68, + "learning_rate": 7.69015152540051e-06, + "loss": 0.3329, + "step": 5306 + }, + { + "epoch": 0.68, + "learning_rate": 7.689277786133113e-06, + "loss": 0.3249, + "step": 5307 + }, + { + "epoch": 0.68, + "learning_rate": 7.688403931301462e-06, + "loss": 0.3099, + "step": 5308 + }, + { + "epoch": 0.68, + "learning_rate": 7.687529960943107e-06, + "loss": 0.33, + "step": 5309 + }, + { + "epoch": 0.68, + "learning_rate": 7.686655875095603e-06, + "loss": 0.308, + "step": 5310 + }, + { + "epoch": 0.68, + "learning_rate": 7.685781673796515e-06, + "loss": 0.2907, + "step": 5311 + }, + { + "epoch": 0.68, + "learning_rate": 7.684907357083404e-06, + "loss": 0.2881, + "step": 5312 + }, + { + "epoch": 0.68, + "learning_rate": 7.684032924993845e-06, + "loss": 0.3078, + "step": 5313 + }, + { + "epoch": 0.68, + "learning_rate": 7.683158377565415e-06, + "loss": 0.3294, + "step": 5314 + }, + { + "epoch": 0.68, + "learning_rate": 7.682283714835691e-06, + "loss": 0.3215, + "step": 5315 + }, + { + "epoch": 0.68, + "learning_rate": 7.681408936842266e-06, + "loss": 0.3248, + "step": 5316 + }, + { + "epoch": 0.68, + "learning_rate": 7.680534043622725e-06, + "loss": 0.3265, + "step": 5317 + }, + { + "epoch": 0.68, + "learning_rate": 7.679659035214666e-06, + "loss": 0.3156, + "step": 5318 + }, + { + "epoch": 0.68, + "learning_rate": 7.678783911655691e-06, + "loss": 0.3401, + "step": 5319 + }, + { + "epoch": 0.68, + "learning_rate": 7.677908672983404e-06, + "loss": 0.3383, + "step": 5320 + }, + { + "epoch": 0.68, + "learning_rate": 7.677033319235418e-06, + "loss": 0.32, + "step": 5321 + }, + { + "epoch": 0.68, + "learning_rate": 7.676157850449348e-06, + "loss": 0.3215, + "step": 5322 + }, + { + "epoch": 0.68, + "learning_rate": 7.675282266662816e-06, + "loss": 0.3178, + "step": 5323 + }, + { + "epoch": 0.68, + "learning_rate": 7.674406567913447e-06, + "loss": 0.3409, + "step": 5324 + }, + { + "epoch": 0.68, + "learning_rate": 7.67353075423887e-06, + "loss": 0.3056, + "step": 5325 + }, + { + "epoch": 0.68, + "learning_rate": 7.672654825676724e-06, + "loss": 0.3253, + "step": 5326 + }, + { + "epoch": 0.68, + "learning_rate": 7.671778782264647e-06, + "loss": 0.3001, + "step": 5327 + }, + { + "epoch": 0.68, + "learning_rate": 7.670902624040286e-06, + "loss": 0.2914, + "step": 5328 + }, + { + "epoch": 0.68, + "learning_rate": 7.67002635104129e-06, + "loss": 0.3407, + "step": 5329 + }, + { + "epoch": 0.68, + "learning_rate": 7.669149963305314e-06, + "loss": 0.3108, + "step": 5330 + }, + { + "epoch": 0.68, + "learning_rate": 7.668273460870022e-06, + "loss": 0.2807, + "step": 5331 + }, + { + "epoch": 0.68, + "learning_rate": 7.667396843773074e-06, + "loss": 0.3187, + "step": 5332 + }, + { + "epoch": 0.68, + "learning_rate": 7.666520112052145e-06, + "loss": 0.3135, + "step": 5333 + }, + { + "epoch": 0.68, + "learning_rate": 7.66564326574491e-06, + "loss": 0.3124, + "step": 5334 + }, + { + "epoch": 0.68, + "learning_rate": 7.664766304889044e-06, + "loss": 0.3238, + "step": 5335 + }, + { + "epoch": 0.68, + "learning_rate": 7.663889229522235e-06, + "loss": 0.296, + "step": 5336 + }, + { + "epoch": 0.68, + "learning_rate": 7.663012039682174e-06, + "loss": 0.323, + "step": 5337 + }, + { + "epoch": 0.68, + "learning_rate": 7.662134735406555e-06, + "loss": 0.3359, + "step": 5338 + }, + { + "epoch": 0.68, + "learning_rate": 7.661257316733078e-06, + "loss": 0.3224, + "step": 5339 + }, + { + "epoch": 0.68, + "learning_rate": 7.660379783699446e-06, + "loss": 0.2791, + "step": 5340 + }, + { + "epoch": 0.68, + "learning_rate": 7.65950213634337e-06, + "loss": 0.3204, + "step": 5341 + }, + { + "epoch": 0.68, + "learning_rate": 7.658624374702565e-06, + "loss": 0.3356, + "step": 5342 + }, + { + "epoch": 0.68, + "learning_rate": 7.657746498814749e-06, + "loss": 0.3327, + "step": 5343 + }, + { + "epoch": 0.68, + "learning_rate": 7.656868508717648e-06, + "loss": 0.3041, + "step": 5344 + }, + { + "epoch": 0.68, + "learning_rate": 7.655990404448988e-06, + "loss": 0.3324, + "step": 5345 + }, + { + "epoch": 0.68, + "learning_rate": 7.655112186046508e-06, + "loss": 0.3322, + "step": 5346 + }, + { + "epoch": 0.68, + "learning_rate": 7.65423385354794e-06, + "loss": 0.3066, + "step": 5347 + }, + { + "epoch": 0.68, + "learning_rate": 7.653355406991034e-06, + "loss": 0.3064, + "step": 5348 + }, + { + "epoch": 0.68, + "learning_rate": 7.652476846413537e-06, + "loss": 0.3349, + "step": 5349 + }, + { + "epoch": 0.68, + "learning_rate": 7.651598171853203e-06, + "loss": 0.3413, + "step": 5350 + }, + { + "epoch": 0.68, + "learning_rate": 7.65071938334779e-06, + "loss": 0.3236, + "step": 5351 + }, + { + "epoch": 0.69, + "learning_rate": 7.64984048093506e-06, + "loss": 0.3033, + "step": 5352 + }, + { + "epoch": 0.69, + "learning_rate": 7.648961464652784e-06, + "loss": 0.3446, + "step": 5353 + }, + { + "epoch": 0.69, + "learning_rate": 7.648082334538735e-06, + "loss": 0.3201, + "step": 5354 + }, + { + "epoch": 0.69, + "learning_rate": 7.64720309063069e-06, + "loss": 0.3125, + "step": 5355 + }, + { + "epoch": 0.69, + "learning_rate": 7.646323732966433e-06, + "loss": 0.2959, + "step": 5356 + }, + { + "epoch": 0.69, + "learning_rate": 7.645444261583752e-06, + "loss": 0.302, + "step": 5357 + }, + { + "epoch": 0.69, + "learning_rate": 7.644564676520439e-06, + "loss": 0.324, + "step": 5358 + }, + { + "epoch": 0.69, + "learning_rate": 7.64368497781429e-06, + "loss": 0.328, + "step": 5359 + }, + { + "epoch": 0.69, + "learning_rate": 7.642805165503112e-06, + "loss": 0.3071, + "step": 5360 + }, + { + "epoch": 0.69, + "learning_rate": 7.641925239624708e-06, + "loss": 0.3098, + "step": 5361 + }, + { + "epoch": 0.69, + "learning_rate": 7.641045200216896e-06, + "loss": 0.3359, + "step": 5362 + }, + { + "epoch": 0.69, + "learning_rate": 7.640165047317488e-06, + "loss": 0.336, + "step": 5363 + }, + { + "epoch": 0.69, + "learning_rate": 7.639284780964307e-06, + "loss": 0.3235, + "step": 5364 + }, + { + "epoch": 0.69, + "learning_rate": 7.638404401195182e-06, + "loss": 0.3321, + "step": 5365 + }, + { + "epoch": 0.69, + "learning_rate": 7.637523908047943e-06, + "loss": 0.2943, + "step": 5366 + }, + { + "epoch": 0.69, + "learning_rate": 7.63664330156043e-06, + "loss": 0.3028, + "step": 5367 + }, + { + "epoch": 0.69, + "learning_rate": 7.635762581770478e-06, + "loss": 0.3299, + "step": 5368 + }, + { + "epoch": 0.69, + "learning_rate": 7.634881748715941e-06, + "loss": 0.3308, + "step": 5369 + }, + { + "epoch": 0.69, + "learning_rate": 7.634000802434667e-06, + "loss": 0.3326, + "step": 5370 + }, + { + "epoch": 0.69, + "learning_rate": 7.633119742964511e-06, + "loss": 0.3476, + "step": 5371 + }, + { + "epoch": 0.69, + "learning_rate": 7.632238570343335e-06, + "loss": 0.3122, + "step": 5372 + }, + { + "epoch": 0.69, + "learning_rate": 7.631357284609006e-06, + "loss": 0.328, + "step": 5373 + }, + { + "epoch": 0.69, + "learning_rate": 7.630475885799395e-06, + "loss": 0.2883, + "step": 5374 + }, + { + "epoch": 0.69, + "learning_rate": 7.629594373952375e-06, + "loss": 0.3112, + "step": 5375 + }, + { + "epoch": 0.69, + "learning_rate": 7.628712749105831e-06, + "loss": 0.3317, + "step": 5376 + }, + { + "epoch": 0.69, + "learning_rate": 7.627831011297644e-06, + "loss": 0.3365, + "step": 5377 + }, + { + "epoch": 0.69, + "learning_rate": 7.626949160565706e-06, + "loss": 0.3093, + "step": 5378 + }, + { + "epoch": 0.69, + "learning_rate": 7.626067196947913e-06, + "loss": 0.3303, + "step": 5379 + }, + { + "epoch": 0.69, + "learning_rate": 7.625185120482162e-06, + "loss": 0.3408, + "step": 5380 + }, + { + "epoch": 0.69, + "learning_rate": 7.624302931206362e-06, + "loss": 0.3092, + "step": 5381 + }, + { + "epoch": 0.69, + "learning_rate": 7.623420629158418e-06, + "loss": 0.2858, + "step": 5382 + }, + { + "epoch": 0.69, + "learning_rate": 7.622538214376248e-06, + "loss": 0.3085, + "step": 5383 + }, + { + "epoch": 0.69, + "learning_rate": 7.621655686897771e-06, + "loss": 0.3286, + "step": 5384 + }, + { + "epoch": 0.69, + "learning_rate": 7.62077304676091e-06, + "loss": 0.3286, + "step": 5385 + }, + { + "epoch": 0.69, + "learning_rate": 7.619890294003593e-06, + "loss": 0.3296, + "step": 5386 + }, + { + "epoch": 0.69, + "learning_rate": 7.6190074286637575e-06, + "loss": 0.3211, + "step": 5387 + }, + { + "epoch": 0.69, + "learning_rate": 7.618124450779338e-06, + "loss": 0.3092, + "step": 5388 + }, + { + "epoch": 0.69, + "learning_rate": 7.617241360388282e-06, + "loss": 0.3195, + "step": 5389 + }, + { + "epoch": 0.69, + "learning_rate": 7.616358157528535e-06, + "loss": 0.3281, + "step": 5390 + }, + { + "epoch": 0.69, + "learning_rate": 7.615474842238051e-06, + "loss": 0.3161, + "step": 5391 + }, + { + "epoch": 0.69, + "learning_rate": 7.614591414554787e-06, + "loss": 0.3076, + "step": 5392 + }, + { + "epoch": 0.69, + "learning_rate": 7.613707874516708e-06, + "loss": 0.3327, + "step": 5393 + }, + { + "epoch": 0.69, + "learning_rate": 7.612824222161781e-06, + "loss": 0.3441, + "step": 5394 + }, + { + "epoch": 0.69, + "learning_rate": 7.611940457527976e-06, + "loss": 0.3307, + "step": 5395 + }, + { + "epoch": 0.69, + "learning_rate": 7.6110565806532745e-06, + "loss": 0.3274, + "step": 5396 + }, + { + "epoch": 0.69, + "learning_rate": 7.610172591575656e-06, + "loss": 0.3484, + "step": 5397 + }, + { + "epoch": 0.69, + "learning_rate": 7.609288490333109e-06, + "loss": 0.2988, + "step": 5398 + }, + { + "epoch": 0.69, + "learning_rate": 7.608404276963623e-06, + "loss": 0.3107, + "step": 5399 + }, + { + "epoch": 0.69, + "learning_rate": 7.6075199515051955e-06, + "loss": 0.337, + "step": 5400 + }, + { + "epoch": 0.69, + "learning_rate": 7.60663551399583e-06, + "loss": 0.3219, + "step": 5401 + }, + { + "epoch": 0.69, + "learning_rate": 7.605750964473531e-06, + "loss": 0.3161, + "step": 5402 + }, + { + "epoch": 0.69, + "learning_rate": 7.604866302976309e-06, + "loss": 0.2863, + "step": 5403 + }, + { + "epoch": 0.69, + "learning_rate": 7.60398152954218e-06, + "loss": 0.3032, + "step": 5404 + }, + { + "epoch": 0.69, + "learning_rate": 7.6030966442091665e-06, + "loss": 0.3061, + "step": 5405 + }, + { + "epoch": 0.69, + "learning_rate": 7.602211647015292e-06, + "loss": 0.2932, + "step": 5406 + }, + { + "epoch": 0.69, + "learning_rate": 7.601326537998589e-06, + "loss": 0.3292, + "step": 5407 + }, + { + "epoch": 0.69, + "learning_rate": 7.60044131719709e-06, + "loss": 0.3296, + "step": 5408 + }, + { + "epoch": 0.69, + "learning_rate": 7.599555984648836e-06, + "loss": 0.3113, + "step": 5409 + }, + { + "epoch": 0.69, + "learning_rate": 7.598670540391872e-06, + "loss": 0.3407, + "step": 5410 + }, + { + "epoch": 0.69, + "learning_rate": 7.597784984464248e-06, + "loss": 0.2948, + "step": 5411 + }, + { + "epoch": 0.69, + "learning_rate": 7.596899316904018e-06, + "loss": 0.3152, + "step": 5412 + }, + { + "epoch": 0.69, + "learning_rate": 7.596013537749238e-06, + "loss": 0.3008, + "step": 5413 + }, + { + "epoch": 0.69, + "learning_rate": 7.595127647037976e-06, + "loss": 0.3509, + "step": 5414 + }, + { + "epoch": 0.69, + "learning_rate": 7.5942416448083e-06, + "loss": 0.3005, + "step": 5415 + }, + { + "epoch": 0.69, + "learning_rate": 7.593355531098284e-06, + "loss": 0.2983, + "step": 5416 + }, + { + "epoch": 0.69, + "learning_rate": 7.592469305946003e-06, + "loss": 0.3184, + "step": 5417 + }, + { + "epoch": 0.69, + "learning_rate": 7.5915829693895435e-06, + "loss": 0.3386, + "step": 5418 + }, + { + "epoch": 0.69, + "learning_rate": 7.590696521466992e-06, + "loss": 0.2876, + "step": 5419 + }, + { + "epoch": 0.69, + "learning_rate": 7.589809962216439e-06, + "loss": 0.3244, + "step": 5420 + }, + { + "epoch": 0.69, + "learning_rate": 7.588923291675987e-06, + "loss": 0.3281, + "step": 5421 + }, + { + "epoch": 0.69, + "learning_rate": 7.588036509883734e-06, + "loss": 0.336, + "step": 5422 + }, + { + "epoch": 0.69, + "learning_rate": 7.587149616877789e-06, + "loss": 0.3278, + "step": 5423 + }, + { + "epoch": 0.69, + "learning_rate": 7.586262612696263e-06, + "loss": 0.3094, + "step": 5424 + }, + { + "epoch": 0.69, + "learning_rate": 7.585375497377271e-06, + "loss": 0.3265, + "step": 5425 + }, + { + "epoch": 0.69, + "learning_rate": 7.584488270958937e-06, + "loss": 0.2986, + "step": 5426 + }, + { + "epoch": 0.69, + "learning_rate": 7.583600933479387e-06, + "loss": 0.3077, + "step": 5427 + }, + { + "epoch": 0.69, + "learning_rate": 7.582713484976749e-06, + "loss": 0.3307, + "step": 5428 + }, + { + "epoch": 0.69, + "learning_rate": 7.5818259254891614e-06, + "loss": 0.2977, + "step": 5429 + }, + { + "epoch": 0.7, + "learning_rate": 7.580938255054765e-06, + "loss": 0.3322, + "step": 5430 + }, + { + "epoch": 0.7, + "learning_rate": 7.580050473711702e-06, + "loss": 0.3223, + "step": 5431 + }, + { + "epoch": 0.7, + "learning_rate": 7.579162581498125e-06, + "loss": 0.3067, + "step": 5432 + }, + { + "epoch": 0.7, + "learning_rate": 7.5782745784521875e-06, + "loss": 0.3341, + "step": 5433 + }, + { + "epoch": 0.7, + "learning_rate": 7.577386464612049e-06, + "loss": 0.3431, + "step": 5434 + }, + { + "epoch": 0.7, + "learning_rate": 7.576498240015875e-06, + "loss": 0.3171, + "step": 5435 + }, + { + "epoch": 0.7, + "learning_rate": 7.5756099047018315e-06, + "loss": 0.3172, + "step": 5436 + }, + { + "epoch": 0.7, + "learning_rate": 7.574721458708096e-06, + "loss": 0.3177, + "step": 5437 + }, + { + "epoch": 0.7, + "learning_rate": 7.573832902072844e-06, + "loss": 0.286, + "step": 5438 + }, + { + "epoch": 0.7, + "learning_rate": 7.572944234834261e-06, + "loss": 0.3283, + "step": 5439 + }, + { + "epoch": 0.7, + "learning_rate": 7.572055457030533e-06, + "loss": 0.3393, + "step": 5440 + }, + { + "epoch": 0.7, + "learning_rate": 7.5711665686998545e-06, + "loss": 0.3018, + "step": 5441 + }, + { + "epoch": 0.7, + "learning_rate": 7.570277569880422e-06, + "loss": 0.2996, + "step": 5442 + }, + { + "epoch": 0.7, + "learning_rate": 7.569388460610437e-06, + "loss": 0.3323, + "step": 5443 + }, + { + "epoch": 0.7, + "learning_rate": 7.568499240928109e-06, + "loss": 0.3233, + "step": 5444 + }, + { + "epoch": 0.7, + "learning_rate": 7.5676099108716485e-06, + "loss": 0.3297, + "step": 5445 + }, + { + "epoch": 0.7, + "learning_rate": 7.5667204704792706e-06, + "loss": 0.3353, + "step": 5446 + }, + { + "epoch": 0.7, + "learning_rate": 7.565830919789198e-06, + "loss": 0.3163, + "step": 5447 + }, + { + "epoch": 0.7, + "learning_rate": 7.564941258839655e-06, + "loss": 0.3261, + "step": 5448 + }, + { + "epoch": 0.7, + "learning_rate": 7.5640514876688765e-06, + "loss": 0.3288, + "step": 5449 + }, + { + "epoch": 0.7, + "learning_rate": 7.563161606315095e-06, + "loss": 0.3533, + "step": 5450 + }, + { + "epoch": 0.7, + "learning_rate": 7.5622716148165475e-06, + "loss": 0.3044, + "step": 5451 + }, + { + "epoch": 0.7, + "learning_rate": 7.561381513211486e-06, + "loss": 0.3064, + "step": 5452 + }, + { + "epoch": 0.7, + "learning_rate": 7.5604913015381535e-06, + "loss": 0.3043, + "step": 5453 + }, + { + "epoch": 0.7, + "learning_rate": 7.559600979834809e-06, + "loss": 0.3379, + "step": 5454 + }, + { + "epoch": 0.7, + "learning_rate": 7.5587105481397095e-06, + "loss": 0.3111, + "step": 5455 + }, + { + "epoch": 0.7, + "learning_rate": 7.557820006491118e-06, + "loss": 0.3281, + "step": 5456 + }, + { + "epoch": 0.7, + "learning_rate": 7.5569293549273046e-06, + "loss": 0.3267, + "step": 5457 + }, + { + "epoch": 0.7, + "learning_rate": 7.556038593486543e-06, + "loss": 0.3213, + "step": 5458 + }, + { + "epoch": 0.7, + "learning_rate": 7.555147722207111e-06, + "loss": 0.3138, + "step": 5459 + }, + { + "epoch": 0.7, + "learning_rate": 7.554256741127291e-06, + "loss": 0.3059, + "step": 5460 + }, + { + "epoch": 0.7, + "learning_rate": 7.553365650285368e-06, + "loss": 0.2915, + "step": 5461 + }, + { + "epoch": 0.7, + "learning_rate": 7.5524744497196376e-06, + "loss": 0.3467, + "step": 5462 + }, + { + "epoch": 0.7, + "learning_rate": 7.5515831394683954e-06, + "loss": 0.3316, + "step": 5463 + }, + { + "epoch": 0.7, + "learning_rate": 7.550691719569944e-06, + "loss": 0.3156, + "step": 5464 + }, + { + "epoch": 0.7, + "learning_rate": 7.549800190062586e-06, + "loss": 0.3093, + "step": 5465 + }, + { + "epoch": 0.7, + "learning_rate": 7.548908550984637e-06, + "loss": 0.3321, + "step": 5466 + }, + { + "epoch": 0.7, + "learning_rate": 7.548016802374412e-06, + "loss": 0.3249, + "step": 5467 + }, + { + "epoch": 0.7, + "learning_rate": 7.547124944270229e-06, + "loss": 0.3364, + "step": 5468 + }, + { + "epoch": 0.7, + "learning_rate": 7.546232976710413e-06, + "loss": 0.3124, + "step": 5469 + }, + { + "epoch": 0.7, + "learning_rate": 7.545340899733297e-06, + "loss": 0.3195, + "step": 5470 + }, + { + "epoch": 0.7, + "learning_rate": 7.544448713377213e-06, + "loss": 0.2992, + "step": 5471 + }, + { + "epoch": 0.7, + "learning_rate": 7.543556417680502e-06, + "loss": 0.3517, + "step": 5472 + }, + { + "epoch": 0.7, + "learning_rate": 7.542664012681507e-06, + "loss": 0.2958, + "step": 5473 + }, + { + "epoch": 0.7, + "learning_rate": 7.541771498418575e-06, + "loss": 0.35, + "step": 5474 + }, + { + "epoch": 0.7, + "learning_rate": 7.540878874930062e-06, + "loss": 0.3001, + "step": 5475 + }, + { + "epoch": 0.7, + "learning_rate": 7.539986142254324e-06, + "loss": 0.3112, + "step": 5476 + }, + { + "epoch": 0.7, + "learning_rate": 7.539093300429727e-06, + "loss": 0.3186, + "step": 5477 + }, + { + "epoch": 0.7, + "learning_rate": 7.538200349494633e-06, + "loss": 0.3385, + "step": 5478 + }, + { + "epoch": 0.7, + "learning_rate": 7.537307289487419e-06, + "loss": 0.306, + "step": 5479 + }, + { + "epoch": 0.7, + "learning_rate": 7.536414120446458e-06, + "loss": 0.3126, + "step": 5480 + }, + { + "epoch": 0.7, + "learning_rate": 7.535520842410136e-06, + "loss": 0.3588, + "step": 5481 + }, + { + "epoch": 0.7, + "learning_rate": 7.534627455416835e-06, + "loss": 0.3149, + "step": 5482 + }, + { + "epoch": 0.7, + "learning_rate": 7.533733959504947e-06, + "loss": 0.3326, + "step": 5483 + }, + { + "epoch": 0.7, + "learning_rate": 7.532840354712868e-06, + "loss": 0.3136, + "step": 5484 + }, + { + "epoch": 0.7, + "learning_rate": 7.531946641078998e-06, + "loss": 0.3209, + "step": 5485 + }, + { + "epoch": 0.7, + "learning_rate": 7.531052818641743e-06, + "loss": 0.327, + "step": 5486 + }, + { + "epoch": 0.7, + "learning_rate": 7.530158887439509e-06, + "loss": 0.3115, + "step": 5487 + }, + { + "epoch": 0.7, + "learning_rate": 7.529264847510715e-06, + "loss": 0.3351, + "step": 5488 + }, + { + "epoch": 0.7, + "learning_rate": 7.5283706988937765e-06, + "loss": 0.3066, + "step": 5489 + }, + { + "epoch": 0.7, + "learning_rate": 7.5274764416271185e-06, + "loss": 0.3183, + "step": 5490 + }, + { + "epoch": 0.7, + "learning_rate": 7.526582075749169e-06, + "loss": 0.3367, + "step": 5491 + }, + { + "epoch": 0.7, + "learning_rate": 7.525687601298361e-06, + "loss": 0.3061, + "step": 5492 + }, + { + "epoch": 0.7, + "learning_rate": 7.5247930183131305e-06, + "loss": 0.323, + "step": 5493 + }, + { + "epoch": 0.7, + "learning_rate": 7.523898326831921e-06, + "loss": 0.3134, + "step": 5494 + }, + { + "epoch": 0.7, + "learning_rate": 7.52300352689318e-06, + "loss": 0.2911, + "step": 5495 + }, + { + "epoch": 0.7, + "learning_rate": 7.522108618535359e-06, + "loss": 0.3029, + "step": 5496 + }, + { + "epoch": 0.7, + "learning_rate": 7.521213601796913e-06, + "loss": 0.297, + "step": 5497 + }, + { + "epoch": 0.7, + "learning_rate": 7.520318476716303e-06, + "loss": 0.3289, + "step": 5498 + }, + { + "epoch": 0.7, + "learning_rate": 7.5194232433319955e-06, + "loss": 0.3001, + "step": 5499 + }, + { + "epoch": 0.7, + "learning_rate": 7.51852790168246e-06, + "loss": 0.2988, + "step": 5500 + }, + { + "epoch": 0.7, + "learning_rate": 7.517632451806172e-06, + "loss": 0.3489, + "step": 5501 + }, + { + "epoch": 0.7, + "learning_rate": 7.516736893741611e-06, + "loss": 0.3441, + "step": 5502 + }, + { + "epoch": 0.7, + "learning_rate": 7.515841227527258e-06, + "loss": 0.2973, + "step": 5503 + }, + { + "epoch": 0.7, + "learning_rate": 7.514945453201608e-06, + "loss": 0.3193, + "step": 5504 + }, + { + "epoch": 0.7, + "learning_rate": 7.514049570803148e-06, + "loss": 0.3293, + "step": 5505 + }, + { + "epoch": 0.7, + "learning_rate": 7.5131535803703805e-06, + "loss": 0.3166, + "step": 5506 + }, + { + "epoch": 0.7, + "learning_rate": 7.512257481941805e-06, + "loss": 0.3099, + "step": 5507 + }, + { + "epoch": 0.71, + "learning_rate": 7.511361275555931e-06, + "loss": 0.319, + "step": 5508 + }, + { + "epoch": 0.71, + "learning_rate": 7.510464961251271e-06, + "loss": 0.3036, + "step": 5509 + }, + { + "epoch": 0.71, + "learning_rate": 7.50956853906634e-06, + "loss": 0.3535, + "step": 5510 + }, + { + "epoch": 0.71, + "learning_rate": 7.508672009039659e-06, + "loss": 0.3265, + "step": 5511 + }, + { + "epoch": 0.71, + "learning_rate": 7.507775371209754e-06, + "loss": 0.3202, + "step": 5512 + }, + { + "epoch": 0.71, + "learning_rate": 7.5068786256151585e-06, + "loss": 0.294, + "step": 5513 + }, + { + "epoch": 0.71, + "learning_rate": 7.505981772294404e-06, + "loss": 0.3142, + "step": 5514 + }, + { + "epoch": 0.71, + "learning_rate": 7.505084811286032e-06, + "loss": 0.3364, + "step": 5515 + }, + { + "epoch": 0.71, + "learning_rate": 7.5041877426285856e-06, + "loss": 0.3098, + "step": 5516 + }, + { + "epoch": 0.71, + "learning_rate": 7.503290566360615e-06, + "loss": 0.3194, + "step": 5517 + }, + { + "epoch": 0.71, + "learning_rate": 7.502393282520675e-06, + "loss": 0.3122, + "step": 5518 + }, + { + "epoch": 0.71, + "learning_rate": 7.501495891147322e-06, + "loss": 0.3069, + "step": 5519 + }, + { + "epoch": 0.71, + "learning_rate": 7.500598392279119e-06, + "loss": 0.3387, + "step": 5520 + }, + { + "epoch": 0.71, + "learning_rate": 7.499700785954633e-06, + "loss": 0.3036, + "step": 5521 + }, + { + "epoch": 0.71, + "learning_rate": 7.498803072212439e-06, + "loss": 0.3186, + "step": 5522 + }, + { + "epoch": 0.71, + "learning_rate": 7.49790525109111e-06, + "loss": 0.3126, + "step": 5523 + }, + { + "epoch": 0.71, + "learning_rate": 7.497007322629231e-06, + "loss": 0.3082, + "step": 5524 + }, + { + "epoch": 0.71, + "learning_rate": 7.496109286865384e-06, + "loss": 0.2823, + "step": 5525 + }, + { + "epoch": 0.71, + "learning_rate": 7.495211143838164e-06, + "loss": 0.3305, + "step": 5526 + }, + { + "epoch": 0.71, + "learning_rate": 7.494312893586163e-06, + "loss": 0.3407, + "step": 5527 + }, + { + "epoch": 0.71, + "learning_rate": 7.493414536147983e-06, + "loss": 0.3085, + "step": 5528 + }, + { + "epoch": 0.71, + "learning_rate": 7.492516071562226e-06, + "loss": 0.3046, + "step": 5529 + }, + { + "epoch": 0.71, + "learning_rate": 7.491617499867502e-06, + "loss": 0.3066, + "step": 5530 + }, + { + "epoch": 0.71, + "learning_rate": 7.4907188211024254e-06, + "loss": 0.3387, + "step": 5531 + }, + { + "epoch": 0.71, + "learning_rate": 7.489820035305613e-06, + "loss": 0.3315, + "step": 5532 + }, + { + "epoch": 0.71, + "learning_rate": 7.488921142515691e-06, + "loss": 0.3177, + "step": 5533 + }, + { + "epoch": 0.71, + "learning_rate": 7.488022142771282e-06, + "loss": 0.3237, + "step": 5534 + }, + { + "epoch": 0.71, + "learning_rate": 7.4871230361110214e-06, + "loss": 0.2901, + "step": 5535 + }, + { + "epoch": 0.71, + "learning_rate": 7.486223822573545e-06, + "loss": 0.318, + "step": 5536 + }, + { + "epoch": 0.71, + "learning_rate": 7.485324502197494e-06, + "loss": 0.3378, + "step": 5537 + }, + { + "epoch": 0.71, + "learning_rate": 7.484425075021513e-06, + "loss": 0.3115, + "step": 5538 + }, + { + "epoch": 0.71, + "learning_rate": 7.483525541084253e-06, + "loss": 0.3547, + "step": 5539 + }, + { + "epoch": 0.71, + "learning_rate": 7.482625900424372e-06, + "loss": 0.3249, + "step": 5540 + }, + { + "epoch": 0.71, + "learning_rate": 7.481726153080524e-06, + "loss": 0.3456, + "step": 5541 + }, + { + "epoch": 0.71, + "learning_rate": 7.480826299091378e-06, + "loss": 0.3305, + "step": 5542 + }, + { + "epoch": 0.71, + "learning_rate": 7.4799263384956e-06, + "loss": 0.3174, + "step": 5543 + }, + { + "epoch": 0.71, + "learning_rate": 7.479026271331864e-06, + "loss": 0.3128, + "step": 5544 + }, + { + "epoch": 0.71, + "learning_rate": 7.478126097638848e-06, + "loss": 0.3125, + "step": 5545 + }, + { + "epoch": 0.71, + "learning_rate": 7.477225817455236e-06, + "loss": 0.3303, + "step": 5546 + }, + { + "epoch": 0.71, + "learning_rate": 7.476325430819713e-06, + "loss": 0.2911, + "step": 5547 + }, + { + "epoch": 0.71, + "learning_rate": 7.47542493777097e-06, + "loss": 0.3269, + "step": 5548 + }, + { + "epoch": 0.71, + "learning_rate": 7.4745243383477055e-06, + "loss": 0.2957, + "step": 5549 + }, + { + "epoch": 0.71, + "learning_rate": 7.473623632588618e-06, + "loss": 0.3507, + "step": 5550 + }, + { + "epoch": 0.71, + "learning_rate": 7.472722820532414e-06, + "loss": 0.3201, + "step": 5551 + }, + { + "epoch": 0.71, + "learning_rate": 7.471821902217804e-06, + "loss": 0.3115, + "step": 5552 + }, + { + "epoch": 0.71, + "learning_rate": 7.470920877683503e-06, + "loss": 0.324, + "step": 5553 + }, + { + "epoch": 0.71, + "learning_rate": 7.470019746968226e-06, + "loss": 0.2947, + "step": 5554 + }, + { + "epoch": 0.71, + "learning_rate": 7.469118510110702e-06, + "loss": 0.3112, + "step": 5555 + }, + { + "epoch": 0.71, + "learning_rate": 7.468217167149656e-06, + "loss": 0.3514, + "step": 5556 + }, + { + "epoch": 0.71, + "learning_rate": 7.467315718123821e-06, + "loss": 0.3201, + "step": 5557 + }, + { + "epoch": 0.71, + "learning_rate": 7.466414163071934e-06, + "loss": 0.321, + "step": 5558 + }, + { + "epoch": 0.71, + "learning_rate": 7.4655125020327376e-06, + "loss": 0.2678, + "step": 5559 + }, + { + "epoch": 0.71, + "learning_rate": 7.464610735044979e-06, + "loss": 0.3481, + "step": 5560 + }, + { + "epoch": 0.71, + "learning_rate": 7.463708862147408e-06, + "loss": 0.3096, + "step": 5561 + }, + { + "epoch": 0.71, + "learning_rate": 7.462806883378779e-06, + "loss": 0.2955, + "step": 5562 + }, + { + "epoch": 0.71, + "learning_rate": 7.4619047987778536e-06, + "loss": 0.3399, + "step": 5563 + }, + { + "epoch": 0.71, + "learning_rate": 7.461002608383396e-06, + "loss": 0.3373, + "step": 5564 + }, + { + "epoch": 0.71, + "learning_rate": 7.460100312234176e-06, + "loss": 0.3068, + "step": 5565 + }, + { + "epoch": 0.71, + "learning_rate": 7.4591979103689675e-06, + "loss": 0.313, + "step": 5566 + }, + { + "epoch": 0.71, + "learning_rate": 7.458295402826546e-06, + "loss": 0.3062, + "step": 5567 + }, + { + "epoch": 0.71, + "learning_rate": 7.4573927896456966e-06, + "loss": 0.3302, + "step": 5568 + }, + { + "epoch": 0.71, + "learning_rate": 7.456490070865206e-06, + "loss": 0.3216, + "step": 5569 + }, + { + "epoch": 0.71, + "learning_rate": 7.455587246523868e-06, + "loss": 0.3225, + "step": 5570 + }, + { + "epoch": 0.71, + "learning_rate": 7.454684316660475e-06, + "loss": 0.3004, + "step": 5571 + }, + { + "epoch": 0.71, + "learning_rate": 7.453781281313831e-06, + "loss": 0.3109, + "step": 5572 + }, + { + "epoch": 0.71, + "learning_rate": 7.45287814052274e-06, + "loss": 0.3172, + "step": 5573 + }, + { + "epoch": 0.71, + "learning_rate": 7.4519748943260126e-06, + "loss": 0.3245, + "step": 5574 + }, + { + "epoch": 0.71, + "learning_rate": 7.4510715427624635e-06, + "loss": 0.3088, + "step": 5575 + }, + { + "epoch": 0.71, + "learning_rate": 7.450168085870911e-06, + "loss": 0.3393, + "step": 5576 + }, + { + "epoch": 0.71, + "learning_rate": 7.4492645236901795e-06, + "loss": 0.3265, + "step": 5577 + }, + { + "epoch": 0.71, + "learning_rate": 7.4483608562590955e-06, + "loss": 0.332, + "step": 5578 + }, + { + "epoch": 0.71, + "learning_rate": 7.447457083616494e-06, + "loss": 0.3275, + "step": 5579 + }, + { + "epoch": 0.71, + "learning_rate": 7.4465532058012105e-06, + "loss": 0.3114, + "step": 5580 + }, + { + "epoch": 0.71, + "learning_rate": 7.445649222852086e-06, + "loss": 0.2988, + "step": 5581 + }, + { + "epoch": 0.71, + "learning_rate": 7.444745134807969e-06, + "loss": 0.3015, + "step": 5582 + }, + { + "epoch": 0.71, + "learning_rate": 7.443840941707709e-06, + "loss": 0.3118, + "step": 5583 + }, + { + "epoch": 0.71, + "learning_rate": 7.44293664359016e-06, + "loss": 0.3019, + "step": 5584 + }, + { + "epoch": 0.71, + "learning_rate": 7.442032240494184e-06, + "loss": 0.3362, + "step": 5585 + }, + { + "epoch": 0.72, + "learning_rate": 7.441127732458642e-06, + "loss": 0.2839, + "step": 5586 + }, + { + "epoch": 0.72, + "learning_rate": 7.440223119522405e-06, + "loss": 0.3018, + "step": 5587 + }, + { + "epoch": 0.72, + "learning_rate": 7.439318401724347e-06, + "loss": 0.3167, + "step": 5588 + }, + { + "epoch": 0.72, + "learning_rate": 7.438413579103344e-06, + "loss": 0.3081, + "step": 5589 + }, + { + "epoch": 0.72, + "learning_rate": 7.4375086516982775e-06, + "loss": 0.3497, + "step": 5590 + }, + { + "epoch": 0.72, + "learning_rate": 7.436603619548038e-06, + "loss": 0.2965, + "step": 5591 + }, + { + "epoch": 0.72, + "learning_rate": 7.4356984826915135e-06, + "loss": 0.3379, + "step": 5592 + }, + { + "epoch": 0.72, + "learning_rate": 7.434793241167601e-06, + "loss": 0.3244, + "step": 5593 + }, + { + "epoch": 0.72, + "learning_rate": 7.433887895015199e-06, + "loss": 0.3586, + "step": 5594 + }, + { + "epoch": 0.72, + "learning_rate": 7.432982444273215e-06, + "loss": 0.334, + "step": 5595 + }, + { + "epoch": 0.72, + "learning_rate": 7.432076888980556e-06, + "loss": 0.3215, + "step": 5596 + }, + { + "epoch": 0.72, + "learning_rate": 7.431171229176136e-06, + "loss": 0.3029, + "step": 5597 + }, + { + "epoch": 0.72, + "learning_rate": 7.4302654648988755e-06, + "loss": 0.3039, + "step": 5598 + }, + { + "epoch": 0.72, + "learning_rate": 7.429359596187694e-06, + "loss": 0.33, + "step": 5599 + }, + { + "epoch": 0.72, + "learning_rate": 7.428453623081522e-06, + "loss": 0.3292, + "step": 5600 + }, + { + "epoch": 0.72, + "learning_rate": 7.427547545619288e-06, + "loss": 0.3333, + "step": 5601 + }, + { + "epoch": 0.72, + "learning_rate": 7.4266413638399284e-06, + "loss": 0.305, + "step": 5602 + }, + { + "epoch": 0.72, + "learning_rate": 7.425735077782387e-06, + "loss": 0.3146, + "step": 5603 + }, + { + "epoch": 0.72, + "learning_rate": 7.424828687485606e-06, + "loss": 0.3414, + "step": 5604 + }, + { + "epoch": 0.72, + "learning_rate": 7.423922192988536e-06, + "loss": 0.3162, + "step": 5605 + }, + { + "epoch": 0.72, + "learning_rate": 7.423015594330131e-06, + "loss": 0.3158, + "step": 5606 + }, + { + "epoch": 0.72, + "learning_rate": 7.422108891549349e-06, + "loss": 0.3154, + "step": 5607 + }, + { + "epoch": 0.72, + "learning_rate": 7.421202084685155e-06, + "loss": 0.2947, + "step": 5608 + }, + { + "epoch": 0.72, + "learning_rate": 7.420295173776515e-06, + "loss": 0.3054, + "step": 5609 + }, + { + "epoch": 0.72, + "learning_rate": 7.4193881588624e-06, + "loss": 0.3243, + "step": 5610 + }, + { + "epoch": 0.72, + "learning_rate": 7.418481039981787e-06, + "loss": 0.2904, + "step": 5611 + }, + { + "epoch": 0.72, + "learning_rate": 7.41757381717366e-06, + "loss": 0.3008, + "step": 5612 + }, + { + "epoch": 0.72, + "learning_rate": 7.416666490476999e-06, + "loss": 0.3236, + "step": 5613 + }, + { + "epoch": 0.72, + "learning_rate": 7.415759059930799e-06, + "loss": 0.3362, + "step": 5614 + }, + { + "epoch": 0.72, + "learning_rate": 7.41485152557405e-06, + "loss": 0.3185, + "step": 5615 + }, + { + "epoch": 0.72, + "learning_rate": 7.4139438874457536e-06, + "loss": 0.3319, + "step": 5616 + }, + { + "epoch": 0.72, + "learning_rate": 7.413036145584913e-06, + "loss": 0.3128, + "step": 5617 + }, + { + "epoch": 0.72, + "learning_rate": 7.412128300030534e-06, + "loss": 0.3117, + "step": 5618 + }, + { + "epoch": 0.72, + "learning_rate": 7.411220350821631e-06, + "loss": 0.312, + "step": 5619 + }, + { + "epoch": 0.72, + "learning_rate": 7.410312297997219e-06, + "loss": 0.3196, + "step": 5620 + }, + { + "epoch": 0.72, + "learning_rate": 7.409404141596319e-06, + "loss": 0.3274, + "step": 5621 + }, + { + "epoch": 0.72, + "learning_rate": 7.4084958816579575e-06, + "loss": 0.2981, + "step": 5622 + }, + { + "epoch": 0.72, + "learning_rate": 7.407587518221164e-06, + "loss": 0.3205, + "step": 5623 + }, + { + "epoch": 0.72, + "learning_rate": 7.406679051324972e-06, + "loss": 0.324, + "step": 5624 + }, + { + "epoch": 0.72, + "learning_rate": 7.4057704810084215e-06, + "loss": 0.3023, + "step": 5625 + }, + { + "epoch": 0.72, + "learning_rate": 7.404861807310556e-06, + "loss": 0.339, + "step": 5626 + }, + { + "epoch": 0.72, + "learning_rate": 7.4039530302704236e-06, + "loss": 0.2961, + "step": 5627 + }, + { + "epoch": 0.72, + "learning_rate": 7.403044149927074e-06, + "loss": 0.3145, + "step": 5628 + }, + { + "epoch": 0.72, + "learning_rate": 7.402135166319567e-06, + "loss": 0.3048, + "step": 5629 + }, + { + "epoch": 0.72, + "learning_rate": 7.40122607948696e-06, + "loss": 0.3341, + "step": 5630 + }, + { + "epoch": 0.72, + "learning_rate": 7.400316889468322e-06, + "loss": 0.3534, + "step": 5631 + }, + { + "epoch": 0.72, + "learning_rate": 7.399407596302721e-06, + "loss": 0.2976, + "step": 5632 + }, + { + "epoch": 0.72, + "learning_rate": 7.398498200029232e-06, + "loss": 0.3239, + "step": 5633 + }, + { + "epoch": 0.72, + "learning_rate": 7.397588700686933e-06, + "loss": 0.3047, + "step": 5634 + }, + { + "epoch": 0.72, + "learning_rate": 7.396679098314908e-06, + "loss": 0.3179, + "step": 5635 + }, + { + "epoch": 0.72, + "learning_rate": 7.395769392952246e-06, + "loss": 0.3075, + "step": 5636 + }, + { + "epoch": 0.72, + "learning_rate": 7.394859584638035e-06, + "loss": 0.321, + "step": 5637 + }, + { + "epoch": 0.72, + "learning_rate": 7.393949673411375e-06, + "loss": 0.3231, + "step": 5638 + }, + { + "epoch": 0.72, + "learning_rate": 7.393039659311366e-06, + "loss": 0.3156, + "step": 5639 + }, + { + "epoch": 0.72, + "learning_rate": 7.392129542377114e-06, + "loss": 0.3171, + "step": 5640 + }, + { + "epoch": 0.72, + "learning_rate": 7.391219322647728e-06, + "loss": 0.3038, + "step": 5641 + }, + { + "epoch": 0.72, + "learning_rate": 7.390309000162321e-06, + "loss": 0.3206, + "step": 5642 + }, + { + "epoch": 0.72, + "learning_rate": 7.389398574960014e-06, + "loss": 0.3001, + "step": 5643 + }, + { + "epoch": 0.72, + "learning_rate": 7.388488047079927e-06, + "loss": 0.3226, + "step": 5644 + }, + { + "epoch": 0.72, + "learning_rate": 7.387577416561191e-06, + "loss": 0.3241, + "step": 5645 + }, + { + "epoch": 0.72, + "learning_rate": 7.386666683442936e-06, + "loss": 0.3053, + "step": 5646 + }, + { + "epoch": 0.72, + "learning_rate": 7.3857558477642966e-06, + "loss": 0.318, + "step": 5647 + }, + { + "epoch": 0.72, + "learning_rate": 7.3848449095644155e-06, + "loss": 0.3124, + "step": 5648 + }, + { + "epoch": 0.72, + "learning_rate": 7.383933868882438e-06, + "loss": 0.2943, + "step": 5649 + }, + { + "epoch": 0.72, + "learning_rate": 7.383022725757514e-06, + "loss": 0.3595, + "step": 5650 + }, + { + "epoch": 0.72, + "learning_rate": 7.382111480228793e-06, + "loss": 0.3169, + "step": 5651 + }, + { + "epoch": 0.72, + "learning_rate": 7.381200132335438e-06, + "loss": 0.3369, + "step": 5652 + }, + { + "epoch": 0.72, + "learning_rate": 7.38028868211661e-06, + "loss": 0.2927, + "step": 5653 + }, + { + "epoch": 0.72, + "learning_rate": 7.379377129611478e-06, + "loss": 0.3128, + "step": 5654 + }, + { + "epoch": 0.72, + "learning_rate": 7.378465474859211e-06, + "loss": 0.3713, + "step": 5655 + }, + { + "epoch": 0.72, + "learning_rate": 7.377553717898983e-06, + "loss": 0.3073, + "step": 5656 + }, + { + "epoch": 0.72, + "learning_rate": 7.376641858769978e-06, + "loss": 0.3149, + "step": 5657 + }, + { + "epoch": 0.72, + "learning_rate": 7.375729897511379e-06, + "loss": 0.3149, + "step": 5658 + }, + { + "epoch": 0.72, + "learning_rate": 7.374817834162378e-06, + "loss": 0.2957, + "step": 5659 + }, + { + "epoch": 0.72, + "learning_rate": 7.3739056687621616e-06, + "loss": 0.3401, + "step": 5660 + }, + { + "epoch": 0.72, + "learning_rate": 7.3729934013499335e-06, + "loss": 0.3217, + "step": 5661 + }, + { + "epoch": 0.72, + "learning_rate": 7.372081031964893e-06, + "loss": 0.3164, + "step": 5662 + }, + { + "epoch": 0.72, + "learning_rate": 7.37116856064625e-06, + "loss": 0.3247, + "step": 5663 + }, + { + "epoch": 0.72, + "learning_rate": 7.3702559874332125e-06, + "loss": 0.2888, + "step": 5664 + }, + { + "epoch": 0.73, + "learning_rate": 7.369343312364994e-06, + "loss": 0.3116, + "step": 5665 + }, + { + "epoch": 0.73, + "learning_rate": 7.368430535480818e-06, + "loss": 0.3298, + "step": 5666 + }, + { + "epoch": 0.73, + "learning_rate": 7.367517656819907e-06, + "loss": 0.3229, + "step": 5667 + }, + { + "epoch": 0.73, + "learning_rate": 7.366604676421491e-06, + "loss": 0.3428, + "step": 5668 + }, + { + "epoch": 0.73, + "learning_rate": 7.3656915943247984e-06, + "loss": 0.3252, + "step": 5669 + }, + { + "epoch": 0.73, + "learning_rate": 7.364778410569071e-06, + "loss": 0.3299, + "step": 5670 + }, + { + "epoch": 0.73, + "learning_rate": 7.363865125193549e-06, + "loss": 0.3081, + "step": 5671 + }, + { + "epoch": 0.73, + "learning_rate": 7.362951738237477e-06, + "loss": 0.3107, + "step": 5672 + }, + { + "epoch": 0.73, + "learning_rate": 7.362038249740108e-06, + "loss": 0.2972, + "step": 5673 + }, + { + "epoch": 0.73, + "learning_rate": 7.3611246597406925e-06, + "loss": 0.316, + "step": 5674 + }, + { + "epoch": 0.73, + "learning_rate": 7.360210968278494e-06, + "loss": 0.3125, + "step": 5675 + }, + { + "epoch": 0.73, + "learning_rate": 7.359297175392772e-06, + "loss": 0.3263, + "step": 5676 + }, + { + "epoch": 0.73, + "learning_rate": 7.358383281122797e-06, + "loss": 0.3398, + "step": 5677 + }, + { + "epoch": 0.73, + "learning_rate": 7.35746928550784e-06, + "loss": 0.3408, + "step": 5678 + }, + { + "epoch": 0.73, + "learning_rate": 7.356555188587178e-06, + "loss": 0.3183, + "step": 5679 + }, + { + "epoch": 0.73, + "learning_rate": 7.355640990400089e-06, + "loss": 0.3108, + "step": 5680 + }, + { + "epoch": 0.73, + "learning_rate": 7.354726690985862e-06, + "loss": 0.3397, + "step": 5681 + }, + { + "epoch": 0.73, + "learning_rate": 7.353812290383785e-06, + "loss": 0.3329, + "step": 5682 + }, + { + "epoch": 0.73, + "learning_rate": 7.352897788633151e-06, + "loss": 0.3333, + "step": 5683 + }, + { + "epoch": 0.73, + "learning_rate": 7.351983185773259e-06, + "loss": 0.3083, + "step": 5684 + }, + { + "epoch": 0.73, + "learning_rate": 7.351068481843411e-06, + "loss": 0.3355, + "step": 5685 + }, + { + "epoch": 0.73, + "learning_rate": 7.3501536768829154e-06, + "loss": 0.3122, + "step": 5686 + }, + { + "epoch": 0.73, + "learning_rate": 7.349238770931081e-06, + "loss": 0.3023, + "step": 5687 + }, + { + "epoch": 0.73, + "learning_rate": 7.348323764027225e-06, + "loss": 0.3087, + "step": 5688 + }, + { + "epoch": 0.73, + "learning_rate": 7.347408656210666e-06, + "loss": 0.3013, + "step": 5689 + }, + { + "epoch": 0.73, + "learning_rate": 7.346493447520731e-06, + "loss": 0.3114, + "step": 5690 + }, + { + "epoch": 0.73, + "learning_rate": 7.345578137996745e-06, + "loss": 0.3152, + "step": 5691 + }, + { + "epoch": 0.73, + "learning_rate": 7.344662727678043e-06, + "loss": 0.2881, + "step": 5692 + }, + { + "epoch": 0.73, + "learning_rate": 7.343747216603962e-06, + "loss": 0.3236, + "step": 5693 + }, + { + "epoch": 0.73, + "learning_rate": 7.342831604813844e-06, + "loss": 0.3208, + "step": 5694 + }, + { + "epoch": 0.73, + "learning_rate": 7.341915892347033e-06, + "loss": 0.3364, + "step": 5695 + }, + { + "epoch": 0.73, + "learning_rate": 7.341000079242881e-06, + "loss": 0.3123, + "step": 5696 + }, + { + "epoch": 0.73, + "learning_rate": 7.340084165540742e-06, + "loss": 0.3228, + "step": 5697 + }, + { + "epoch": 0.73, + "learning_rate": 7.339168151279974e-06, + "loss": 0.296, + "step": 5698 + }, + { + "epoch": 0.73, + "learning_rate": 7.338252036499941e-06, + "loss": 0.3368, + "step": 5699 + }, + { + "epoch": 0.73, + "learning_rate": 7.3373358212400104e-06, + "loss": 0.3399, + "step": 5700 + }, + { + "epoch": 0.73, + "learning_rate": 7.336419505539555e-06, + "loss": 0.3143, + "step": 5701 + }, + { + "epoch": 0.73, + "learning_rate": 7.33550308943795e-06, + "loss": 0.3364, + "step": 5702 + }, + { + "epoch": 0.73, + "learning_rate": 7.334586572974573e-06, + "loss": 0.3166, + "step": 5703 + }, + { + "epoch": 0.73, + "learning_rate": 7.333669956188815e-06, + "loss": 0.3086, + "step": 5704 + }, + { + "epoch": 0.73, + "learning_rate": 7.332753239120061e-06, + "loss": 0.3107, + "step": 5705 + }, + { + "epoch": 0.73, + "learning_rate": 7.331836421807704e-06, + "loss": 0.3159, + "step": 5706 + }, + { + "epoch": 0.73, + "learning_rate": 7.330919504291143e-06, + "loss": 0.3244, + "step": 5707 + }, + { + "epoch": 0.73, + "learning_rate": 7.33000248660978e-06, + "loss": 0.3177, + "step": 5708 + }, + { + "epoch": 0.73, + "learning_rate": 7.3290853688030196e-06, + "loss": 0.3157, + "step": 5709 + }, + { + "epoch": 0.73, + "learning_rate": 7.328168150910275e-06, + "loss": 0.2969, + "step": 5710 + }, + { + "epoch": 0.73, + "learning_rate": 7.32725083297096e-06, + "loss": 0.3138, + "step": 5711 + }, + { + "epoch": 0.73, + "learning_rate": 7.326333415024494e-06, + "loss": 0.3274, + "step": 5712 + }, + { + "epoch": 0.73, + "learning_rate": 7.325415897110299e-06, + "loss": 0.3315, + "step": 5713 + }, + { + "epoch": 0.73, + "learning_rate": 7.324498279267803e-06, + "loss": 0.3409, + "step": 5714 + }, + { + "epoch": 0.73, + "learning_rate": 7.323580561536442e-06, + "loss": 0.3222, + "step": 5715 + }, + { + "epoch": 0.73, + "learning_rate": 7.3226627439556466e-06, + "loss": 0.3456, + "step": 5716 + }, + { + "epoch": 0.73, + "learning_rate": 7.321744826564862e-06, + "loss": 0.3457, + "step": 5717 + }, + { + "epoch": 0.73, + "learning_rate": 7.3208268094035295e-06, + "loss": 0.2791, + "step": 5718 + }, + { + "epoch": 0.73, + "learning_rate": 7.319908692511103e-06, + "loss": 0.3293, + "step": 5719 + }, + { + "epoch": 0.73, + "learning_rate": 7.318990475927033e-06, + "loss": 0.3027, + "step": 5720 + }, + { + "epoch": 0.73, + "learning_rate": 7.318072159690775e-06, + "loss": 0.3086, + "step": 5721 + }, + { + "epoch": 0.73, + "learning_rate": 7.317153743841795e-06, + "loss": 0.3353, + "step": 5722 + }, + { + "epoch": 0.73, + "learning_rate": 7.316235228419557e-06, + "loss": 0.3133, + "step": 5723 + }, + { + "epoch": 0.73, + "learning_rate": 7.315316613463535e-06, + "loss": 0.2967, + "step": 5724 + }, + { + "epoch": 0.73, + "learning_rate": 7.314397899013199e-06, + "loss": 0.321, + "step": 5725 + }, + { + "epoch": 0.73, + "learning_rate": 7.313479085108033e-06, + "loss": 0.3149, + "step": 5726 + }, + { + "epoch": 0.73, + "learning_rate": 7.312560171787518e-06, + "loss": 0.3325, + "step": 5727 + }, + { + "epoch": 0.73, + "learning_rate": 7.311641159091141e-06, + "loss": 0.306, + "step": 5728 + }, + { + "epoch": 0.73, + "learning_rate": 7.310722047058396e-06, + "loss": 0.3267, + "step": 5729 + }, + { + "epoch": 0.73, + "learning_rate": 7.309802835728779e-06, + "loss": 0.3108, + "step": 5730 + }, + { + "epoch": 0.73, + "learning_rate": 7.308883525141788e-06, + "loss": 0.3327, + "step": 5731 + }, + { + "epoch": 0.73, + "learning_rate": 7.307964115336931e-06, + "loss": 0.2816, + "step": 5732 + }, + { + "epoch": 0.73, + "learning_rate": 7.307044606353715e-06, + "loss": 0.3025, + "step": 5733 + }, + { + "epoch": 0.73, + "learning_rate": 7.306124998231655e-06, + "loss": 0.314, + "step": 5734 + }, + { + "epoch": 0.73, + "learning_rate": 7.305205291010269e-06, + "loss": 0.3179, + "step": 5735 + }, + { + "epoch": 0.73, + "learning_rate": 7.304285484729074e-06, + "loss": 0.3331, + "step": 5736 + }, + { + "epoch": 0.73, + "learning_rate": 7.303365579427603e-06, + "loss": 0.2845, + "step": 5737 + }, + { + "epoch": 0.73, + "learning_rate": 7.302445575145383e-06, + "loss": 0.3388, + "step": 5738 + }, + { + "epoch": 0.73, + "learning_rate": 7.301525471921949e-06, + "loss": 0.3506, + "step": 5739 + }, + { + "epoch": 0.73, + "learning_rate": 7.300605269796839e-06, + "loss": 0.323, + "step": 5740 + }, + { + "epoch": 0.73, + "learning_rate": 7.299684968809595e-06, + "loss": 0.3298, + "step": 5741 + }, + { + "epoch": 0.73, + "learning_rate": 7.298764568999768e-06, + "loss": 0.3121, + "step": 5742 + }, + { + "epoch": 0.74, + "learning_rate": 7.297844070406908e-06, + "loss": 0.2824, + "step": 5743 + }, + { + "epoch": 0.74, + "learning_rate": 7.296923473070571e-06, + "loss": 0.3114, + "step": 5744 + }, + { + "epoch": 0.74, + "learning_rate": 7.296002777030316e-06, + "loss": 0.3226, + "step": 5745 + }, + { + "epoch": 0.74, + "learning_rate": 7.295081982325708e-06, + "loss": 0.331, + "step": 5746 + }, + { + "epoch": 0.74, + "learning_rate": 7.2941610889963164e-06, + "loss": 0.3159, + "step": 5747 + }, + { + "epoch": 0.74, + "learning_rate": 7.293240097081714e-06, + "loss": 0.2894, + "step": 5748 + }, + { + "epoch": 0.74, + "learning_rate": 7.292319006621477e-06, + "loss": 0.2919, + "step": 5749 + }, + { + "epoch": 0.74, + "learning_rate": 7.291397817655186e-06, + "loss": 0.2972, + "step": 5750 + }, + { + "epoch": 0.74, + "learning_rate": 7.2904765302224276e-06, + "loss": 0.306, + "step": 5751 + }, + { + "epoch": 0.74, + "learning_rate": 7.289555144362793e-06, + "loss": 0.3448, + "step": 5752 + }, + { + "epoch": 0.74, + "learning_rate": 7.288633660115874e-06, + "loss": 0.3308, + "step": 5753 + }, + { + "epoch": 0.74, + "learning_rate": 7.2877120775212685e-06, + "loss": 0.3091, + "step": 5754 + }, + { + "epoch": 0.74, + "learning_rate": 7.286790396618582e-06, + "loss": 0.3176, + "step": 5755 + }, + { + "epoch": 0.74, + "learning_rate": 7.285868617447418e-06, + "loss": 0.3184, + "step": 5756 + }, + { + "epoch": 0.74, + "learning_rate": 7.28494674004739e-06, + "loss": 0.3107, + "step": 5757 + }, + { + "epoch": 0.74, + "learning_rate": 7.28402476445811e-06, + "loss": 0.3361, + "step": 5758 + }, + { + "epoch": 0.74, + "learning_rate": 7.283102690719198e-06, + "loss": 0.3129, + "step": 5759 + }, + { + "epoch": 0.74, + "learning_rate": 7.282180518870281e-06, + "loss": 0.323, + "step": 5760 + }, + { + "epoch": 0.74, + "learning_rate": 7.2812582489509844e-06, + "loss": 0.2953, + "step": 5761 + }, + { + "epoch": 0.74, + "learning_rate": 7.28033588100094e-06, + "loss": 0.3206, + "step": 5762 + }, + { + "epoch": 0.74, + "learning_rate": 7.279413415059782e-06, + "loss": 0.322, + "step": 5763 + }, + { + "epoch": 0.74, + "learning_rate": 7.278490851167155e-06, + "loss": 0.3257, + "step": 5764 + }, + { + "epoch": 0.74, + "learning_rate": 7.277568189362701e-06, + "loss": 0.303, + "step": 5765 + }, + { + "epoch": 0.74, + "learning_rate": 7.276645429686071e-06, + "loss": 0.3337, + "step": 5766 + }, + { + "epoch": 0.74, + "learning_rate": 7.275722572176915e-06, + "loss": 0.3316, + "step": 5767 + }, + { + "epoch": 0.74, + "learning_rate": 7.2747996168748915e-06, + "loss": 0.3043, + "step": 5768 + }, + { + "epoch": 0.74, + "learning_rate": 7.2738765638196625e-06, + "loss": 0.3127, + "step": 5769 + }, + { + "epoch": 0.74, + "learning_rate": 7.272953413050894e-06, + "loss": 0.3287, + "step": 5770 + }, + { + "epoch": 0.74, + "learning_rate": 7.272030164608256e-06, + "loss": 0.3465, + "step": 5771 + }, + { + "epoch": 0.74, + "learning_rate": 7.27110681853142e-06, + "loss": 0.313, + "step": 5772 + }, + { + "epoch": 0.74, + "learning_rate": 7.270183374860066e-06, + "loss": 0.3445, + "step": 5773 + }, + { + "epoch": 0.74, + "learning_rate": 7.269259833633877e-06, + "loss": 0.3268, + "step": 5774 + }, + { + "epoch": 0.74, + "learning_rate": 7.26833619489254e-06, + "loss": 0.3276, + "step": 5775 + }, + { + "epoch": 0.74, + "learning_rate": 7.267412458675744e-06, + "loss": 0.3, + "step": 5776 + }, + { + "epoch": 0.74, + "learning_rate": 7.266488625023184e-06, + "loss": 0.3083, + "step": 5777 + }, + { + "epoch": 0.74, + "learning_rate": 7.265564693974561e-06, + "loss": 0.3262, + "step": 5778 + }, + { + "epoch": 0.74, + "learning_rate": 7.264640665569577e-06, + "loss": 0.3071, + "step": 5779 + }, + { + "epoch": 0.74, + "learning_rate": 7.2637165398479405e-06, + "loss": 0.3004, + "step": 5780 + }, + { + "epoch": 0.74, + "learning_rate": 7.262792316849362e-06, + "loss": 0.2984, + "step": 5781 + }, + { + "epoch": 0.74, + "learning_rate": 7.261867996613559e-06, + "loss": 0.348, + "step": 5782 + }, + { + "epoch": 0.74, + "learning_rate": 7.26094357918025e-06, + "loss": 0.3241, + "step": 5783 + }, + { + "epoch": 0.74, + "learning_rate": 7.26001906458916e-06, + "loss": 0.3337, + "step": 5784 + }, + { + "epoch": 0.74, + "learning_rate": 7.259094452880019e-06, + "loss": 0.3317, + "step": 5785 + }, + { + "epoch": 0.74, + "learning_rate": 7.258169744092556e-06, + "loss": 0.3058, + "step": 5786 + }, + { + "epoch": 0.74, + "learning_rate": 7.257244938266511e-06, + "loss": 0.2932, + "step": 5787 + }, + { + "epoch": 0.74, + "learning_rate": 7.256320035441623e-06, + "loss": 0.2948, + "step": 5788 + }, + { + "epoch": 0.74, + "learning_rate": 7.255395035657639e-06, + "loss": 0.3148, + "step": 5789 + }, + { + "epoch": 0.74, + "learning_rate": 7.254469938954307e-06, + "loss": 0.3181, + "step": 5790 + }, + { + "epoch": 0.74, + "learning_rate": 7.25354474537138e-06, + "loss": 0.355, + "step": 5791 + }, + { + "epoch": 0.74, + "learning_rate": 7.252619454948617e-06, + "loss": 0.3094, + "step": 5792 + }, + { + "epoch": 0.74, + "learning_rate": 7.251694067725779e-06, + "loss": 0.3099, + "step": 5793 + }, + { + "epoch": 0.74, + "learning_rate": 7.250768583742634e-06, + "loss": 0.2933, + "step": 5794 + }, + { + "epoch": 0.74, + "learning_rate": 7.249843003038948e-06, + "loss": 0.2775, + "step": 5795 + }, + { + "epoch": 0.74, + "learning_rate": 7.2489173256544975e-06, + "loss": 0.3381, + "step": 5796 + }, + { + "epoch": 0.74, + "learning_rate": 7.247991551629061e-06, + "loss": 0.3311, + "step": 5797 + }, + { + "epoch": 0.74, + "learning_rate": 7.247065681002421e-06, + "loss": 0.3099, + "step": 5798 + }, + { + "epoch": 0.74, + "learning_rate": 7.246139713814365e-06, + "loss": 0.3022, + "step": 5799 + }, + { + "epoch": 0.74, + "learning_rate": 7.245213650104683e-06, + "loss": 0.3099, + "step": 5800 + }, + { + "epoch": 0.74, + "learning_rate": 7.2442874899131685e-06, + "loss": 0.2905, + "step": 5801 + }, + { + "epoch": 0.74, + "learning_rate": 7.2433612332796245e-06, + "loss": 0.3243, + "step": 5802 + }, + { + "epoch": 0.74, + "learning_rate": 7.242434880243851e-06, + "loss": 0.2951, + "step": 5803 + }, + { + "epoch": 0.74, + "learning_rate": 7.241508430845656e-06, + "loss": 0.3144, + "step": 5804 + }, + { + "epoch": 0.74, + "learning_rate": 7.2405818851248535e-06, + "loss": 0.3441, + "step": 5805 + }, + { + "epoch": 0.74, + "learning_rate": 7.239655243121255e-06, + "loss": 0.3364, + "step": 5806 + }, + { + "epoch": 0.74, + "learning_rate": 7.238728504874683e-06, + "loss": 0.3151, + "step": 5807 + }, + { + "epoch": 0.74, + "learning_rate": 7.237801670424963e-06, + "loss": 0.3443, + "step": 5808 + }, + { + "epoch": 0.74, + "learning_rate": 7.236874739811921e-06, + "loss": 0.3161, + "step": 5809 + }, + { + "epoch": 0.74, + "learning_rate": 7.235947713075389e-06, + "loss": 0.304, + "step": 5810 + }, + { + "epoch": 0.74, + "learning_rate": 7.235020590255204e-06, + "loss": 0.3146, + "step": 5811 + }, + { + "epoch": 0.74, + "learning_rate": 7.234093371391206e-06, + "loss": 0.3164, + "step": 5812 + }, + { + "epoch": 0.74, + "learning_rate": 7.233166056523242e-06, + "loss": 0.288, + "step": 5813 + }, + { + "epoch": 0.74, + "learning_rate": 7.232238645691157e-06, + "loss": 0.3217, + "step": 5814 + }, + { + "epoch": 0.74, + "learning_rate": 7.231311138934807e-06, + "loss": 0.3413, + "step": 5815 + }, + { + "epoch": 0.74, + "learning_rate": 7.230383536294048e-06, + "loss": 0.318, + "step": 5816 + }, + { + "epoch": 0.74, + "learning_rate": 7.229455837808741e-06, + "loss": 0.3022, + "step": 5817 + }, + { + "epoch": 0.74, + "learning_rate": 7.228528043518752e-06, + "loss": 0.3407, + "step": 5818 + }, + { + "epoch": 0.74, + "learning_rate": 7.227600153463947e-06, + "loss": 0.3277, + "step": 5819 + }, + { + "epoch": 0.74, + "learning_rate": 7.226672167684205e-06, + "loss": 0.3091, + "step": 5820 + }, + { + "epoch": 0.75, + "learning_rate": 7.225744086219402e-06, + "loss": 0.3083, + "step": 5821 + }, + { + "epoch": 0.75, + "learning_rate": 7.224815909109416e-06, + "loss": 0.3257, + "step": 5822 + }, + { + "epoch": 0.75, + "learning_rate": 7.223887636394137e-06, + "loss": 0.3199, + "step": 5823 + }, + { + "epoch": 0.75, + "learning_rate": 7.222959268113452e-06, + "loss": 0.3179, + "step": 5824 + }, + { + "epoch": 0.75, + "learning_rate": 7.222030804307257e-06, + "loss": 0.3168, + "step": 5825 + }, + { + "epoch": 0.75, + "learning_rate": 7.22110224501545e-06, + "loss": 0.3113, + "step": 5826 + }, + { + "epoch": 0.75, + "learning_rate": 7.220173590277933e-06, + "loss": 0.3079, + "step": 5827 + }, + { + "epoch": 0.75, + "learning_rate": 7.219244840134612e-06, + "loss": 0.3144, + "step": 5828 + }, + { + "epoch": 0.75, + "learning_rate": 7.218315994625397e-06, + "loss": 0.3068, + "step": 5829 + }, + { + "epoch": 0.75, + "learning_rate": 7.217387053790204e-06, + "loss": 0.3307, + "step": 5830 + }, + { + "epoch": 0.75, + "learning_rate": 7.216458017668951e-06, + "loss": 0.3346, + "step": 5831 + }, + { + "epoch": 0.75, + "learning_rate": 7.21552888630156e-06, + "loss": 0.3226, + "step": 5832 + }, + { + "epoch": 0.75, + "learning_rate": 7.214599659727959e-06, + "loss": 0.3158, + "step": 5833 + }, + { + "epoch": 0.75, + "learning_rate": 7.213670337988079e-06, + "loss": 0.3299, + "step": 5834 + }, + { + "epoch": 0.75, + "learning_rate": 7.2127409211218526e-06, + "loss": 0.2956, + "step": 5835 + }, + { + "epoch": 0.75, + "learning_rate": 7.211811409169222e-06, + "loss": 0.2969, + "step": 5836 + }, + { + "epoch": 0.75, + "learning_rate": 7.21088180217013e-06, + "loss": 0.3453, + "step": 5837 + }, + { + "epoch": 0.75, + "learning_rate": 7.2099521001645225e-06, + "loss": 0.2975, + "step": 5838 + }, + { + "epoch": 0.75, + "learning_rate": 7.209022303192351e-06, + "loss": 0.3224, + "step": 5839 + }, + { + "epoch": 0.75, + "learning_rate": 7.208092411293572e-06, + "loss": 0.2985, + "step": 5840 + }, + { + "epoch": 0.75, + "learning_rate": 7.207162424508144e-06, + "loss": 0.3136, + "step": 5841 + }, + { + "epoch": 0.75, + "learning_rate": 7.206232342876031e-06, + "loss": 0.3321, + "step": 5842 + }, + { + "epoch": 0.75, + "learning_rate": 7.2053021664372e-06, + "loss": 0.2949, + "step": 5843 + }, + { + "epoch": 0.75, + "learning_rate": 7.204371895231623e-06, + "loss": 0.3026, + "step": 5844 + }, + { + "epoch": 0.75, + "learning_rate": 7.20344152929928e-06, + "loss": 0.3129, + "step": 5845 + }, + { + "epoch": 0.75, + "learning_rate": 7.202511068680143e-06, + "loss": 0.3207, + "step": 5846 + }, + { + "epoch": 0.75, + "learning_rate": 7.201580513414201e-06, + "loss": 0.3024, + "step": 5847 + }, + { + "epoch": 0.75, + "learning_rate": 7.200649863541442e-06, + "loss": 0.2947, + "step": 5848 + }, + { + "epoch": 0.75, + "learning_rate": 7.199719119101858e-06, + "loss": 0.3209, + "step": 5849 + }, + { + "epoch": 0.75, + "learning_rate": 7.198788280135443e-06, + "loss": 0.2864, + "step": 5850 + }, + { + "epoch": 0.75, + "learning_rate": 7.197857346682199e-06, + "loss": 0.3213, + "step": 5851 + }, + { + "epoch": 0.75, + "learning_rate": 7.19692631878213e-06, + "loss": 0.3206, + "step": 5852 + }, + { + "epoch": 0.75, + "learning_rate": 7.195995196475244e-06, + "loss": 0.3073, + "step": 5853 + }, + { + "epoch": 0.75, + "learning_rate": 7.195063979801554e-06, + "loss": 0.329, + "step": 5854 + }, + { + "epoch": 0.75, + "learning_rate": 7.194132668801077e-06, + "loss": 0.3093, + "step": 5855 + }, + { + "epoch": 0.75, + "learning_rate": 7.193201263513831e-06, + "loss": 0.3165, + "step": 5856 + }, + { + "epoch": 0.75, + "learning_rate": 7.192269763979844e-06, + "loss": 0.3051, + "step": 5857 + }, + { + "epoch": 0.75, + "learning_rate": 7.1913381702391405e-06, + "loss": 0.3128, + "step": 5858 + }, + { + "epoch": 0.75, + "learning_rate": 7.190406482331757e-06, + "loss": 0.2971, + "step": 5859 + }, + { + "epoch": 0.75, + "learning_rate": 7.189474700297728e-06, + "loss": 0.301, + "step": 5860 + }, + { + "epoch": 0.75, + "learning_rate": 7.188542824177096e-06, + "loss": 0.3428, + "step": 5861 + }, + { + "epoch": 0.75, + "learning_rate": 7.187610854009903e-06, + "loss": 0.3217, + "step": 5862 + }, + { + "epoch": 0.75, + "learning_rate": 7.186678789836201e-06, + "loss": 0.328, + "step": 5863 + }, + { + "epoch": 0.75, + "learning_rate": 7.18574663169604e-06, + "loss": 0.3394, + "step": 5864 + }, + { + "epoch": 0.75, + "learning_rate": 7.18481437962948e-06, + "loss": 0.3089, + "step": 5865 + }, + { + "epoch": 0.75, + "learning_rate": 7.183882033676579e-06, + "loss": 0.309, + "step": 5866 + }, + { + "epoch": 0.75, + "learning_rate": 7.182949593877404e-06, + "loss": 0.3074, + "step": 5867 + }, + { + "epoch": 0.75, + "learning_rate": 7.182017060272023e-06, + "loss": 0.3014, + "step": 5868 + }, + { + "epoch": 0.75, + "learning_rate": 7.1810844329005095e-06, + "loss": 0.3261, + "step": 5869 + }, + { + "epoch": 0.75, + "learning_rate": 7.180151711802941e-06, + "loss": 0.3197, + "step": 5870 + }, + { + "epoch": 0.75, + "learning_rate": 7.179218897019395e-06, + "loss": 0.3385, + "step": 5871 + }, + { + "epoch": 0.75, + "learning_rate": 7.178285988589963e-06, + "loss": 0.297, + "step": 5872 + }, + { + "epoch": 0.75, + "learning_rate": 7.177352986554729e-06, + "loss": 0.2967, + "step": 5873 + }, + { + "epoch": 0.75, + "learning_rate": 7.176419890953788e-06, + "loss": 0.3147, + "step": 5874 + }, + { + "epoch": 0.75, + "learning_rate": 7.175486701827239e-06, + "loss": 0.294, + "step": 5875 + }, + { + "epoch": 0.75, + "learning_rate": 7.174553419215179e-06, + "loss": 0.3079, + "step": 5876 + }, + { + "epoch": 0.75, + "learning_rate": 7.173620043157716e-06, + "loss": 0.3175, + "step": 5877 + }, + { + "epoch": 0.75, + "learning_rate": 7.17268657369496e-06, + "loss": 0.3058, + "step": 5878 + }, + { + "epoch": 0.75, + "learning_rate": 7.171753010867023e-06, + "loss": 0.3068, + "step": 5879 + }, + { + "epoch": 0.75, + "learning_rate": 7.1708193547140205e-06, + "loss": 0.3306, + "step": 5880 + }, + { + "epoch": 0.75, + "learning_rate": 7.169885605276077e-06, + "loss": 0.2919, + "step": 5881 + }, + { + "epoch": 0.75, + "learning_rate": 7.1689517625933165e-06, + "loss": 0.2856, + "step": 5882 + }, + { + "epoch": 0.75, + "learning_rate": 7.168017826705869e-06, + "loss": 0.2943, + "step": 5883 + }, + { + "epoch": 0.75, + "learning_rate": 7.167083797653866e-06, + "loss": 0.2827, + "step": 5884 + }, + { + "epoch": 0.75, + "learning_rate": 7.166149675477445e-06, + "loss": 0.3115, + "step": 5885 + }, + { + "epoch": 0.75, + "learning_rate": 7.16521546021675e-06, + "loss": 0.3168, + "step": 5886 + }, + { + "epoch": 0.75, + "learning_rate": 7.164281151911923e-06, + "loss": 0.2764, + "step": 5887 + }, + { + "epoch": 0.75, + "learning_rate": 7.163346750603117e-06, + "loss": 0.3584, + "step": 5888 + }, + { + "epoch": 0.75, + "learning_rate": 7.162412256330481e-06, + "loss": 0.3427, + "step": 5889 + }, + { + "epoch": 0.75, + "learning_rate": 7.161477669134174e-06, + "loss": 0.3209, + "step": 5890 + }, + { + "epoch": 0.75, + "learning_rate": 7.160542989054359e-06, + "loss": 0.2832, + "step": 5891 + }, + { + "epoch": 0.75, + "learning_rate": 7.1596082161312005e-06, + "loss": 0.323, + "step": 5892 + }, + { + "epoch": 0.75, + "learning_rate": 7.158673350404866e-06, + "loss": 0.3128, + "step": 5893 + }, + { + "epoch": 0.75, + "learning_rate": 7.157738391915531e-06, + "loss": 0.3177, + "step": 5894 + }, + { + "epoch": 0.75, + "learning_rate": 7.156803340703371e-06, + "loss": 0.3147, + "step": 5895 + }, + { + "epoch": 0.75, + "learning_rate": 7.155868196808569e-06, + "loss": 0.3149, + "step": 5896 + }, + { + "epoch": 0.75, + "learning_rate": 7.154932960271308e-06, + "loss": 0.3341, + "step": 5897 + }, + { + "epoch": 0.75, + "learning_rate": 7.153997631131778e-06, + "loss": 0.3253, + "step": 5898 + }, + { + "epoch": 0.76, + "learning_rate": 7.153062209430174e-06, + "loss": 0.314, + "step": 5899 + }, + { + "epoch": 0.76, + "learning_rate": 7.152126695206689e-06, + "loss": 0.3183, + "step": 5900 + }, + { + "epoch": 0.76, + "learning_rate": 7.151191088501531e-06, + "loss": 0.303, + "step": 5901 + }, + { + "epoch": 0.76, + "learning_rate": 7.150255389354899e-06, + "loss": 0.3467, + "step": 5902 + }, + { + "epoch": 0.76, + "learning_rate": 7.149319597807003e-06, + "loss": 0.3133, + "step": 5903 + }, + { + "epoch": 0.76, + "learning_rate": 7.148383713898058e-06, + "loss": 0.3152, + "step": 5904 + }, + { + "epoch": 0.76, + "learning_rate": 7.14744773766828e-06, + "loss": 0.3375, + "step": 5905 + }, + { + "epoch": 0.76, + "learning_rate": 7.146511669157892e-06, + "loss": 0.3357, + "step": 5906 + }, + { + "epoch": 0.76, + "learning_rate": 7.145575508407114e-06, + "loss": 0.3257, + "step": 5907 + }, + { + "epoch": 0.76, + "learning_rate": 7.14463925545618e-06, + "loss": 0.2951, + "step": 5908 + }, + { + "epoch": 0.76, + "learning_rate": 7.143702910345318e-06, + "loss": 0.3083, + "step": 5909 + }, + { + "epoch": 0.76, + "learning_rate": 7.142766473114771e-06, + "loss": 0.3228, + "step": 5910 + }, + { + "epoch": 0.76, + "learning_rate": 7.141829943804777e-06, + "loss": 0.3234, + "step": 5911 + }, + { + "epoch": 0.76, + "learning_rate": 7.1408933224555765e-06, + "loss": 0.334, + "step": 5912 + }, + { + "epoch": 0.76, + "learning_rate": 7.139956609107425e-06, + "loss": 0.3218, + "step": 5913 + }, + { + "epoch": 0.76, + "learning_rate": 7.139019803800569e-06, + "loss": 0.3092, + "step": 5914 + }, + { + "epoch": 0.76, + "learning_rate": 7.138082906575271e-06, + "loss": 0.31, + "step": 5915 + }, + { + "epoch": 0.76, + "learning_rate": 7.137145917471788e-06, + "loss": 0.3276, + "step": 5916 + }, + { + "epoch": 0.76, + "learning_rate": 7.136208836530385e-06, + "loss": 0.2963, + "step": 5917 + }, + { + "epoch": 0.76, + "learning_rate": 7.13527166379133e-06, + "loss": 0.2951, + "step": 5918 + }, + { + "epoch": 0.76, + "learning_rate": 7.134334399294897e-06, + "loss": 0.304, + "step": 5919 + }, + { + "epoch": 0.76, + "learning_rate": 7.1333970430813615e-06, + "loss": 0.3133, + "step": 5920 + }, + { + "epoch": 0.76, + "learning_rate": 7.132459595191003e-06, + "loss": 0.3212, + "step": 5921 + }, + { + "epoch": 0.76, + "learning_rate": 7.131522055664109e-06, + "loss": 0.2925, + "step": 5922 + }, + { + "epoch": 0.76, + "learning_rate": 7.13058442454096e-06, + "loss": 0.298, + "step": 5923 + }, + { + "epoch": 0.76, + "learning_rate": 7.129646701861858e-06, + "loss": 0.3132, + "step": 5924 + }, + { + "epoch": 0.76, + "learning_rate": 7.128708887667093e-06, + "loss": 0.3021, + "step": 5925 + }, + { + "epoch": 0.76, + "learning_rate": 7.127770981996966e-06, + "loss": 0.3254, + "step": 5926 + }, + { + "epoch": 0.76, + "learning_rate": 7.1268329848917795e-06, + "loss": 0.3149, + "step": 5927 + }, + { + "epoch": 0.76, + "learning_rate": 7.125894896391845e-06, + "loss": 0.3187, + "step": 5928 + }, + { + "epoch": 0.76, + "learning_rate": 7.124956716537471e-06, + "loss": 0.3238, + "step": 5929 + }, + { + "epoch": 0.76, + "learning_rate": 7.124018445368975e-06, + "loss": 0.3365, + "step": 5930 + }, + { + "epoch": 0.76, + "learning_rate": 7.123080082926677e-06, + "loss": 0.3182, + "step": 5931 + }, + { + "epoch": 0.76, + "learning_rate": 7.122141629250896e-06, + "loss": 0.3134, + "step": 5932 + }, + { + "epoch": 0.76, + "learning_rate": 7.1212030843819656e-06, + "loss": 0.3306, + "step": 5933 + }, + { + "epoch": 0.76, + "learning_rate": 7.120264448360214e-06, + "loss": 0.3025, + "step": 5934 + }, + { + "epoch": 0.76, + "learning_rate": 7.1193257212259784e-06, + "loss": 0.3174, + "step": 5935 + }, + { + "epoch": 0.76, + "learning_rate": 7.118386903019594e-06, + "loss": 0.3317, + "step": 5936 + }, + { + "epoch": 0.76, + "learning_rate": 7.117447993781408e-06, + "loss": 0.3255, + "step": 5937 + }, + { + "epoch": 0.76, + "learning_rate": 7.116508993551765e-06, + "loss": 0.2787, + "step": 5938 + }, + { + "epoch": 0.76, + "learning_rate": 7.115569902371018e-06, + "loss": 0.3135, + "step": 5939 + }, + { + "epoch": 0.76, + "learning_rate": 7.114630720279521e-06, + "loss": 0.3275, + "step": 5940 + }, + { + "epoch": 0.76, + "learning_rate": 7.11369144731763e-06, + "loss": 0.3135, + "step": 5941 + }, + { + "epoch": 0.76, + "learning_rate": 7.1127520835257125e-06, + "loss": 0.3145, + "step": 5942 + }, + { + "epoch": 0.76, + "learning_rate": 7.111812628944132e-06, + "loss": 0.3081, + "step": 5943 + }, + { + "epoch": 0.76, + "learning_rate": 7.110873083613259e-06, + "loss": 0.331, + "step": 5944 + }, + { + "epoch": 0.76, + "learning_rate": 7.109933447573469e-06, + "loss": 0.35, + "step": 5945 + }, + { + "epoch": 0.76, + "learning_rate": 7.108993720865138e-06, + "loss": 0.2974, + "step": 5946 + }, + { + "epoch": 0.76, + "learning_rate": 7.108053903528652e-06, + "loss": 0.2926, + "step": 5947 + }, + { + "epoch": 0.76, + "learning_rate": 7.107113995604395e-06, + "loss": 0.2904, + "step": 5948 + }, + { + "epoch": 0.76, + "learning_rate": 7.106173997132755e-06, + "loss": 0.3235, + "step": 5949 + }, + { + "epoch": 0.76, + "learning_rate": 7.105233908154128e-06, + "loss": 0.3615, + "step": 5950 + }, + { + "epoch": 0.76, + "learning_rate": 7.104293728708912e-06, + "loss": 0.3061, + "step": 5951 + }, + { + "epoch": 0.76, + "learning_rate": 7.103353458837509e-06, + "loss": 0.3445, + "step": 5952 + }, + { + "epoch": 0.76, + "learning_rate": 7.102413098580322e-06, + "loss": 0.3168, + "step": 5953 + }, + { + "epoch": 0.76, + "learning_rate": 7.101472647977761e-06, + "loss": 0.3437, + "step": 5954 + }, + { + "epoch": 0.76, + "learning_rate": 7.100532107070242e-06, + "loss": 0.3297, + "step": 5955 + }, + { + "epoch": 0.76, + "learning_rate": 7.099591475898178e-06, + "loss": 0.2947, + "step": 5956 + }, + { + "epoch": 0.76, + "learning_rate": 7.098650754501994e-06, + "loss": 0.3004, + "step": 5957 + }, + { + "epoch": 0.76, + "learning_rate": 7.0977099429221145e-06, + "loss": 0.3068, + "step": 5958 + }, + { + "epoch": 0.76, + "learning_rate": 7.096769041198964e-06, + "loss": 0.313, + "step": 5959 + }, + { + "epoch": 0.76, + "learning_rate": 7.095828049372979e-06, + "loss": 0.3587, + "step": 5960 + }, + { + "epoch": 0.76, + "learning_rate": 7.0948869674845955e-06, + "loss": 0.2904, + "step": 5961 + }, + { + "epoch": 0.76, + "learning_rate": 7.093945795574254e-06, + "loss": 0.303, + "step": 5962 + }, + { + "epoch": 0.76, + "learning_rate": 7.093004533682397e-06, + "loss": 0.2834, + "step": 5963 + }, + { + "epoch": 0.76, + "learning_rate": 7.0920631818494745e-06, + "loss": 0.3026, + "step": 5964 + }, + { + "epoch": 0.76, + "learning_rate": 7.091121740115936e-06, + "loss": 0.3406, + "step": 5965 + }, + { + "epoch": 0.76, + "learning_rate": 7.090180208522241e-06, + "loss": 0.3369, + "step": 5966 + }, + { + "epoch": 0.76, + "learning_rate": 7.089238587108849e-06, + "loss": 0.2781, + "step": 5967 + }, + { + "epoch": 0.76, + "learning_rate": 7.08829687591622e-06, + "loss": 0.3107, + "step": 5968 + }, + { + "epoch": 0.76, + "learning_rate": 7.087355074984823e-06, + "loss": 0.3394, + "step": 5969 + }, + { + "epoch": 0.76, + "learning_rate": 7.086413184355129e-06, + "loss": 0.3073, + "step": 5970 + }, + { + "epoch": 0.76, + "learning_rate": 7.085471204067616e-06, + "loss": 0.3096, + "step": 5971 + }, + { + "epoch": 0.76, + "learning_rate": 7.084529134162759e-06, + "loss": 0.3343, + "step": 5972 + }, + { + "epoch": 0.76, + "learning_rate": 7.083586974681042e-06, + "loss": 0.3145, + "step": 5973 + }, + { + "epoch": 0.76, + "learning_rate": 7.082644725662954e-06, + "loss": 0.3011, + "step": 5974 + }, + { + "epoch": 0.76, + "learning_rate": 7.0817023871489835e-06, + "loss": 0.32, + "step": 5975 + }, + { + "epoch": 0.76, + "learning_rate": 7.080759959179626e-06, + "loss": 0.3163, + "step": 5976 + }, + { + "epoch": 0.77, + "learning_rate": 7.079817441795378e-06, + "loss": 0.2963, + "step": 5977 + }, + { + "epoch": 0.77, + "learning_rate": 7.078874835036742e-06, + "loss": 0.3081, + "step": 5978 + }, + { + "epoch": 0.77, + "learning_rate": 7.077932138944225e-06, + "loss": 0.3186, + "step": 5979 + }, + { + "epoch": 0.77, + "learning_rate": 7.076989353558335e-06, + "loss": 0.3171, + "step": 5980 + }, + { + "epoch": 0.77, + "learning_rate": 7.076046478919589e-06, + "loss": 0.3065, + "step": 5981 + }, + { + "epoch": 0.77, + "learning_rate": 7.075103515068501e-06, + "loss": 0.3319, + "step": 5982 + }, + { + "epoch": 0.77, + "learning_rate": 7.074160462045593e-06, + "loss": 0.294, + "step": 5983 + }, + { + "epoch": 0.77, + "learning_rate": 7.073217319891391e-06, + "loss": 0.3366, + "step": 5984 + }, + { + "epoch": 0.77, + "learning_rate": 7.072274088646425e-06, + "loss": 0.3034, + "step": 5985 + }, + { + "epoch": 0.77, + "learning_rate": 7.071330768351223e-06, + "loss": 0.3342, + "step": 5986 + }, + { + "epoch": 0.77, + "learning_rate": 7.070387359046328e-06, + "loss": 0.3158, + "step": 5987 + }, + { + "epoch": 0.77, + "learning_rate": 7.0694438607722746e-06, + "loss": 0.3033, + "step": 5988 + }, + { + "epoch": 0.77, + "learning_rate": 7.068500273569612e-06, + "loss": 0.2964, + "step": 5989 + }, + { + "epoch": 0.77, + "learning_rate": 7.067556597478884e-06, + "loss": 0.301, + "step": 5990 + }, + { + "epoch": 0.77, + "learning_rate": 7.066612832540644e-06, + "loss": 0.288, + "step": 5991 + }, + { + "epoch": 0.77, + "learning_rate": 7.065668978795449e-06, + "loss": 0.3121, + "step": 5992 + }, + { + "epoch": 0.77, + "learning_rate": 7.064725036283857e-06, + "loss": 0.3187, + "step": 5993 + }, + { + "epoch": 0.77, + "learning_rate": 7.063781005046433e-06, + "loss": 0.3503, + "step": 5994 + }, + { + "epoch": 0.77, + "learning_rate": 7.0628368851237424e-06, + "loss": 0.3003, + "step": 5995 + }, + { + "epoch": 0.77, + "learning_rate": 7.061892676556357e-06, + "loss": 0.3134, + "step": 5996 + }, + { + "epoch": 0.77, + "learning_rate": 7.06094837938485e-06, + "loss": 0.3269, + "step": 5997 + }, + { + "epoch": 0.77, + "learning_rate": 7.060003993649802e-06, + "loss": 0.2878, + "step": 5998 + }, + { + "epoch": 0.77, + "learning_rate": 7.059059519391794e-06, + "loss": 0.3101, + "step": 5999 + }, + { + "epoch": 0.77, + "learning_rate": 7.058114956651413e-06, + "loss": 0.3222, + "step": 6000 + }, + { + "epoch": 0.77, + "learning_rate": 7.057170305469248e-06, + "loss": 0.3043, + "step": 6001 + }, + { + "epoch": 0.77, + "learning_rate": 7.056225565885895e-06, + "loss": 0.333, + "step": 6002 + }, + { + "epoch": 0.77, + "learning_rate": 7.055280737941949e-06, + "loss": 0.3253, + "step": 6003 + }, + { + "epoch": 0.77, + "learning_rate": 7.054335821678012e-06, + "loss": 0.338, + "step": 6004 + }, + { + "epoch": 0.77, + "learning_rate": 7.05339081713469e-06, + "loss": 0.3098, + "step": 6005 + }, + { + "epoch": 0.77, + "learning_rate": 7.05244572435259e-06, + "loss": 0.3228, + "step": 6006 + }, + { + "epoch": 0.77, + "learning_rate": 7.051500543372328e-06, + "loss": 0.3234, + "step": 6007 + }, + { + "epoch": 0.77, + "learning_rate": 7.050555274234518e-06, + "loss": 0.3291, + "step": 6008 + }, + { + "epoch": 0.77, + "learning_rate": 7.049609916979782e-06, + "loss": 0.3116, + "step": 6009 + }, + { + "epoch": 0.77, + "learning_rate": 7.04866447164874e-06, + "loss": 0.3222, + "step": 6010 + }, + { + "epoch": 0.77, + "learning_rate": 7.0477189382820266e-06, + "loss": 0.3092, + "step": 6011 + }, + { + "epoch": 0.77, + "learning_rate": 7.046773316920269e-06, + "loss": 0.3086, + "step": 6012 + }, + { + "epoch": 0.77, + "learning_rate": 7.045827607604103e-06, + "loss": 0.298, + "step": 6013 + }, + { + "epoch": 0.77, + "learning_rate": 7.044881810374169e-06, + "loss": 0.31, + "step": 6014 + }, + { + "epoch": 0.77, + "learning_rate": 7.043935925271108e-06, + "loss": 0.2945, + "step": 6015 + }, + { + "epoch": 0.77, + "learning_rate": 7.042989952335571e-06, + "loss": 0.3253, + "step": 6016 + }, + { + "epoch": 0.77, + "learning_rate": 7.0420438916082024e-06, + "loss": 0.3145, + "step": 6017 + }, + { + "epoch": 0.77, + "learning_rate": 7.041097743129662e-06, + "loss": 0.3081, + "step": 6018 + }, + { + "epoch": 0.77, + "learning_rate": 7.040151506940605e-06, + "loss": 0.338, + "step": 6019 + }, + { + "epoch": 0.77, + "learning_rate": 7.039205183081694e-06, + "loss": 0.3118, + "step": 6020 + }, + { + "epoch": 0.77, + "learning_rate": 7.038258771593596e-06, + "loss": 0.3156, + "step": 6021 + }, + { + "epoch": 0.77, + "learning_rate": 7.037312272516977e-06, + "loss": 0.3127, + "step": 6022 + }, + { + "epoch": 0.77, + "learning_rate": 7.036365685892515e-06, + "loss": 0.32, + "step": 6023 + }, + { + "epoch": 0.77, + "learning_rate": 7.035419011760882e-06, + "loss": 0.3109, + "step": 6024 + }, + { + "epoch": 0.77, + "learning_rate": 7.0344722501627625e-06, + "loss": 0.2937, + "step": 6025 + }, + { + "epoch": 0.77, + "learning_rate": 7.033525401138838e-06, + "loss": 0.3108, + "step": 6026 + }, + { + "epoch": 0.77, + "learning_rate": 7.0325784647298e-06, + "loss": 0.281, + "step": 6027 + }, + { + "epoch": 0.77, + "learning_rate": 7.031631440976336e-06, + "loss": 0.3077, + "step": 6028 + }, + { + "epoch": 0.77, + "learning_rate": 7.0306843299191465e-06, + "loss": 0.3289, + "step": 6029 + }, + { + "epoch": 0.77, + "learning_rate": 7.0297371315989284e-06, + "loss": 0.3022, + "step": 6030 + }, + { + "epoch": 0.77, + "learning_rate": 7.028789846056383e-06, + "loss": 0.2861, + "step": 6031 + }, + { + "epoch": 0.77, + "learning_rate": 7.0278424733322225e-06, + "loss": 0.2986, + "step": 6032 + }, + { + "epoch": 0.77, + "learning_rate": 7.026895013467153e-06, + "loss": 0.3136, + "step": 6033 + }, + { + "epoch": 0.77, + "learning_rate": 7.0259474665018915e-06, + "loss": 0.3198, + "step": 6034 + }, + { + "epoch": 0.77, + "learning_rate": 7.024999832477154e-06, + "loss": 0.3196, + "step": 6035 + }, + { + "epoch": 0.77, + "learning_rate": 7.0240521114336655e-06, + "loss": 0.329, + "step": 6036 + }, + { + "epoch": 0.77, + "learning_rate": 7.023104303412149e-06, + "loss": 0.3158, + "step": 6037 + }, + { + "epoch": 0.77, + "learning_rate": 7.022156408453336e-06, + "loss": 0.3285, + "step": 6038 + }, + { + "epoch": 0.77, + "learning_rate": 7.0212084265979575e-06, + "loss": 0.3369, + "step": 6039 + }, + { + "epoch": 0.77, + "learning_rate": 7.02026035788675e-06, + "loss": 0.3146, + "step": 6040 + }, + { + "epoch": 0.77, + "learning_rate": 7.019312202360457e-06, + "loss": 0.3268, + "step": 6041 + }, + { + "epoch": 0.77, + "learning_rate": 7.018363960059823e-06, + "loss": 0.3543, + "step": 6042 + }, + { + "epoch": 0.77, + "learning_rate": 7.017415631025593e-06, + "loss": 0.3205, + "step": 6043 + }, + { + "epoch": 0.77, + "learning_rate": 7.016467215298519e-06, + "loss": 0.3141, + "step": 6044 + }, + { + "epoch": 0.77, + "learning_rate": 7.01551871291936e-06, + "loss": 0.3369, + "step": 6045 + }, + { + "epoch": 0.77, + "learning_rate": 7.014570123928872e-06, + "loss": 0.345, + "step": 6046 + }, + { + "epoch": 0.77, + "learning_rate": 7.01362144836782e-06, + "loss": 0.3192, + "step": 6047 + }, + { + "epoch": 0.77, + "learning_rate": 7.012672686276969e-06, + "loss": 0.3317, + "step": 6048 + }, + { + "epoch": 0.77, + "learning_rate": 7.011723837697091e-06, + "loss": 0.289, + "step": 6049 + }, + { + "epoch": 0.77, + "learning_rate": 7.010774902668958e-06, + "loss": 0.3498, + "step": 6050 + }, + { + "epoch": 0.77, + "learning_rate": 7.009825881233351e-06, + "loss": 0.3039, + "step": 6051 + }, + { + "epoch": 0.77, + "learning_rate": 7.008876773431048e-06, + "loss": 0.3088, + "step": 6052 + }, + { + "epoch": 0.77, + "learning_rate": 7.007927579302837e-06, + "loss": 0.3195, + "step": 6053 + }, + { + "epoch": 0.77, + "learning_rate": 7.0069782988895056e-06, + "loss": 0.3261, + "step": 6054 + }, + { + "epoch": 0.78, + "learning_rate": 7.006028932231847e-06, + "loss": 0.352, + "step": 6055 + }, + { + "epoch": 0.78, + "learning_rate": 7.005079479370658e-06, + "loss": 0.2986, + "step": 6056 + }, + { + "epoch": 0.78, + "learning_rate": 7.0041299403467365e-06, + "loss": 0.3234, + "step": 6057 + }, + { + "epoch": 0.78, + "learning_rate": 7.003180315200891e-06, + "loss": 0.2924, + "step": 6058 + }, + { + "epoch": 0.78, + "learning_rate": 7.002230603973924e-06, + "loss": 0.332, + "step": 6059 + }, + { + "epoch": 0.78, + "learning_rate": 7.001280806706649e-06, + "loss": 0.3337, + "step": 6060 + }, + { + "epoch": 0.78, + "learning_rate": 7.0003309234398805e-06, + "loss": 0.2972, + "step": 6061 + }, + { + "epoch": 0.78, + "learning_rate": 6.999380954214438e-06, + "loss": 0.3063, + "step": 6062 + }, + { + "epoch": 0.78, + "learning_rate": 6.9984308990711425e-06, + "loss": 0.3309, + "step": 6063 + }, + { + "epoch": 0.78, + "learning_rate": 6.9974807580508205e-06, + "loss": 0.3326, + "step": 6064 + }, + { + "epoch": 0.78, + "learning_rate": 6.996530531194302e-06, + "loss": 0.2909, + "step": 6065 + }, + { + "epoch": 0.78, + "learning_rate": 6.995580218542419e-06, + "loss": 0.3054, + "step": 6066 + }, + { + "epoch": 0.78, + "learning_rate": 6.994629820136011e-06, + "loss": 0.308, + "step": 6067 + }, + { + "epoch": 0.78, + "learning_rate": 6.9936793360159175e-06, + "loss": 0.3073, + "step": 6068 + }, + { + "epoch": 0.78, + "learning_rate": 6.992728766222982e-06, + "loss": 0.3352, + "step": 6069 + }, + { + "epoch": 0.78, + "learning_rate": 6.991778110798053e-06, + "loss": 0.2972, + "step": 6070 + }, + { + "epoch": 0.78, + "learning_rate": 6.990827369781983e-06, + "loss": 0.3161, + "step": 6071 + }, + { + "epoch": 0.78, + "learning_rate": 6.9898765432156266e-06, + "loss": 0.3177, + "step": 6072 + }, + { + "epoch": 0.78, + "learning_rate": 6.988925631139843e-06, + "loss": 0.3151, + "step": 6073 + }, + { + "epoch": 0.78, + "learning_rate": 6.987974633595498e-06, + "loss": 0.3263, + "step": 6074 + }, + { + "epoch": 0.78, + "learning_rate": 6.987023550623453e-06, + "loss": 0.3238, + "step": 6075 + }, + { + "epoch": 0.78, + "learning_rate": 6.9860723822645825e-06, + "loss": 0.3219, + "step": 6076 + }, + { + "epoch": 0.78, + "learning_rate": 6.985121128559757e-06, + "loss": 0.3276, + "step": 6077 + }, + { + "epoch": 0.78, + "learning_rate": 6.984169789549857e-06, + "loss": 0.3198, + "step": 6078 + }, + { + "epoch": 0.78, + "learning_rate": 6.9832183652757625e-06, + "loss": 0.3343, + "step": 6079 + }, + { + "epoch": 0.78, + "learning_rate": 6.982266855778356e-06, + "loss": 0.3084, + "step": 6080 + }, + { + "epoch": 0.78, + "learning_rate": 6.981315261098529e-06, + "loss": 0.3043, + "step": 6081 + }, + { + "epoch": 0.78, + "learning_rate": 6.980363581277172e-06, + "loss": 0.3179, + "step": 6082 + }, + { + "epoch": 0.78, + "learning_rate": 6.979411816355183e-06, + "loss": 0.3147, + "step": 6083 + }, + { + "epoch": 0.78, + "learning_rate": 6.978459966373458e-06, + "loss": 0.281, + "step": 6084 + }, + { + "epoch": 0.78, + "learning_rate": 6.9775080313729026e-06, + "loss": 0.3371, + "step": 6085 + }, + { + "epoch": 0.78, + "learning_rate": 6.9765560113944235e-06, + "loss": 0.3531, + "step": 6086 + }, + { + "epoch": 0.78, + "learning_rate": 6.9756039064789295e-06, + "loss": 0.2888, + "step": 6087 + }, + { + "epoch": 0.78, + "learning_rate": 6.9746517166673375e-06, + "loss": 0.2918, + "step": 6088 + }, + { + "epoch": 0.78, + "learning_rate": 6.973699442000561e-06, + "loss": 0.3378, + "step": 6089 + }, + { + "epoch": 0.78, + "learning_rate": 6.972747082519526e-06, + "loss": 0.3247, + "step": 6090 + }, + { + "epoch": 0.78, + "learning_rate": 6.971794638265153e-06, + "loss": 0.305, + "step": 6091 + }, + { + "epoch": 0.78, + "learning_rate": 6.970842109278375e-06, + "loss": 0.3169, + "step": 6092 + }, + { + "epoch": 0.78, + "learning_rate": 6.969889495600122e-06, + "loss": 0.3024, + "step": 6093 + }, + { + "epoch": 0.78, + "learning_rate": 6.96893679727133e-06, + "loss": 0.3212, + "step": 6094 + }, + { + "epoch": 0.78, + "learning_rate": 6.967984014332938e-06, + "loss": 0.3149, + "step": 6095 + }, + { + "epoch": 0.78, + "learning_rate": 6.96703114682589e-06, + "loss": 0.3143, + "step": 6096 + }, + { + "epoch": 0.78, + "learning_rate": 6.966078194791133e-06, + "loss": 0.3213, + "step": 6097 + }, + { + "epoch": 0.78, + "learning_rate": 6.965125158269619e-06, + "loss": 0.3026, + "step": 6098 + }, + { + "epoch": 0.78, + "learning_rate": 6.9641720373022996e-06, + "loss": 0.3373, + "step": 6099 + }, + { + "epoch": 0.78, + "learning_rate": 6.963218831930132e-06, + "loss": 0.3278, + "step": 6100 + }, + { + "epoch": 0.78, + "learning_rate": 6.96226554219408e-06, + "loss": 0.304, + "step": 6101 + }, + { + "epoch": 0.78, + "learning_rate": 6.961312168135107e-06, + "loss": 0.3247, + "step": 6102 + }, + { + "epoch": 0.78, + "learning_rate": 6.960358709794182e-06, + "loss": 0.323, + "step": 6103 + }, + { + "epoch": 0.78, + "learning_rate": 6.959405167212278e-06, + "loss": 0.3257, + "step": 6104 + }, + { + "epoch": 0.78, + "learning_rate": 6.9584515404303685e-06, + "loss": 0.2819, + "step": 6105 + }, + { + "epoch": 0.78, + "learning_rate": 6.9574978294894355e-06, + "loss": 0.3002, + "step": 6106 + }, + { + "epoch": 0.78, + "learning_rate": 6.956544034430463e-06, + "loss": 0.3321, + "step": 6107 + }, + { + "epoch": 0.78, + "learning_rate": 6.955590155294434e-06, + "loss": 0.3126, + "step": 6108 + }, + { + "epoch": 0.78, + "learning_rate": 6.954636192122339e-06, + "loss": 0.3166, + "step": 6109 + }, + { + "epoch": 0.78, + "learning_rate": 6.953682144955176e-06, + "loss": 0.32, + "step": 6110 + }, + { + "epoch": 0.78, + "learning_rate": 6.952728013833941e-06, + "loss": 0.322, + "step": 6111 + }, + { + "epoch": 0.78, + "learning_rate": 6.951773798799632e-06, + "loss": 0.2965, + "step": 6112 + }, + { + "epoch": 0.78, + "learning_rate": 6.950819499893257e-06, + "loss": 0.3349, + "step": 6113 + }, + { + "epoch": 0.78, + "learning_rate": 6.949865117155823e-06, + "loss": 0.3279, + "step": 6114 + }, + { + "epoch": 0.78, + "learning_rate": 6.948910650628343e-06, + "loss": 0.3259, + "step": 6115 + }, + { + "epoch": 0.78, + "learning_rate": 6.947956100351833e-06, + "loss": 0.315, + "step": 6116 + }, + { + "epoch": 0.78, + "learning_rate": 6.947001466367309e-06, + "loss": 0.317, + "step": 6117 + }, + { + "epoch": 0.78, + "learning_rate": 6.946046748715796e-06, + "loss": 0.3132, + "step": 6118 + }, + { + "epoch": 0.78, + "learning_rate": 6.94509194743832e-06, + "loss": 0.2975, + "step": 6119 + }, + { + "epoch": 0.78, + "learning_rate": 6.944137062575913e-06, + "loss": 0.3057, + "step": 6120 + }, + { + "epoch": 0.78, + "learning_rate": 6.943182094169605e-06, + "loss": 0.3217, + "step": 6121 + }, + { + "epoch": 0.78, + "learning_rate": 6.942227042260435e-06, + "loss": 0.309, + "step": 6122 + }, + { + "epoch": 0.78, + "learning_rate": 6.941271906889443e-06, + "loss": 0.2977, + "step": 6123 + }, + { + "epoch": 0.78, + "learning_rate": 6.940316688097675e-06, + "loss": 0.3034, + "step": 6124 + }, + { + "epoch": 0.78, + "learning_rate": 6.9393613859261755e-06, + "loss": 0.325, + "step": 6125 + }, + { + "epoch": 0.78, + "learning_rate": 6.938406000416e-06, + "loss": 0.3042, + "step": 6126 + }, + { + "epoch": 0.78, + "learning_rate": 6.9374505316082e-06, + "loss": 0.3003, + "step": 6127 + }, + { + "epoch": 0.78, + "learning_rate": 6.936494979543836e-06, + "loss": 0.3082, + "step": 6128 + }, + { + "epoch": 0.78, + "learning_rate": 6.935539344263971e-06, + "loss": 0.3416, + "step": 6129 + }, + { + "epoch": 0.78, + "learning_rate": 6.93458362580967e-06, + "loss": 0.3194, + "step": 6130 + }, + { + "epoch": 0.78, + "learning_rate": 6.9336278242220015e-06, + "loss": 0.3032, + "step": 6131 + }, + { + "epoch": 0.78, + "learning_rate": 6.932671939542037e-06, + "loss": 0.3326, + "step": 6132 + }, + { + "epoch": 0.79, + "learning_rate": 6.9317159718108575e-06, + "loss": 0.2967, + "step": 6133 + }, + { + "epoch": 0.79, + "learning_rate": 6.93075992106954e-06, + "loss": 0.3514, + "step": 6134 + }, + { + "epoch": 0.79, + "learning_rate": 6.929803787359169e-06, + "loss": 0.3071, + "step": 6135 + }, + { + "epoch": 0.79, + "learning_rate": 6.928847570720829e-06, + "loss": 0.3082, + "step": 6136 + }, + { + "epoch": 0.79, + "learning_rate": 6.927891271195616e-06, + "loss": 0.3309, + "step": 6137 + }, + { + "epoch": 0.79, + "learning_rate": 6.926934888824619e-06, + "loss": 0.3226, + "step": 6138 + }, + { + "epoch": 0.79, + "learning_rate": 6.925978423648941e-06, + "loss": 0.3178, + "step": 6139 + }, + { + "epoch": 0.79, + "learning_rate": 6.92502187570968e-06, + "loss": 0.3219, + "step": 6140 + }, + { + "epoch": 0.79, + "learning_rate": 6.92406524504794e-06, + "loss": 0.3223, + "step": 6141 + }, + { + "epoch": 0.79, + "learning_rate": 6.923108531704832e-06, + "loss": 0.3188, + "step": 6142 + }, + { + "epoch": 0.79, + "learning_rate": 6.9221517357214674e-06, + "loss": 0.3154, + "step": 6143 + }, + { + "epoch": 0.79, + "learning_rate": 6.921194857138963e-06, + "loss": 0.3316, + "step": 6144 + }, + { + "epoch": 0.79, + "learning_rate": 6.920237895998436e-06, + "loss": 0.319, + "step": 6145 + }, + { + "epoch": 0.79, + "learning_rate": 6.919280852341011e-06, + "loss": 0.3096, + "step": 6146 + }, + { + "epoch": 0.79, + "learning_rate": 6.91832372620781e-06, + "loss": 0.3116, + "step": 6147 + }, + { + "epoch": 0.79, + "learning_rate": 6.917366517639969e-06, + "loss": 0.3343, + "step": 6148 + }, + { + "epoch": 0.79, + "learning_rate": 6.91640922667862e-06, + "loss": 0.2926, + "step": 6149 + }, + { + "epoch": 0.79, + "learning_rate": 6.9154518533648966e-06, + "loss": 0.3204, + "step": 6150 + }, + { + "epoch": 0.79, + "learning_rate": 6.91449439773994e-06, + "loss": 0.3187, + "step": 6151 + }, + { + "epoch": 0.79, + "learning_rate": 6.913536859844896e-06, + "loss": 0.3135, + "step": 6152 + }, + { + "epoch": 0.79, + "learning_rate": 6.912579239720913e-06, + "loss": 0.2976, + "step": 6153 + }, + { + "epoch": 0.79, + "learning_rate": 6.911621537409139e-06, + "loss": 0.3021, + "step": 6154 + }, + { + "epoch": 0.79, + "learning_rate": 6.9106637529507305e-06, + "loss": 0.3066, + "step": 6155 + }, + { + "epoch": 0.79, + "learning_rate": 6.909705886386844e-06, + "loss": 0.3154, + "step": 6156 + }, + { + "epoch": 0.79, + "learning_rate": 6.908747937758644e-06, + "loss": 0.2834, + "step": 6157 + }, + { + "epoch": 0.79, + "learning_rate": 6.9077899071072954e-06, + "loss": 0.3041, + "step": 6158 + }, + { + "epoch": 0.79, + "learning_rate": 6.906831794473963e-06, + "loss": 0.312, + "step": 6159 + }, + { + "epoch": 0.79, + "learning_rate": 6.9058735998998224e-06, + "loss": 0.2997, + "step": 6160 + }, + { + "epoch": 0.79, + "learning_rate": 6.9049153234260495e-06, + "loss": 0.3338, + "step": 6161 + }, + { + "epoch": 0.79, + "learning_rate": 6.903956965093821e-06, + "loss": 0.3232, + "step": 6162 + }, + { + "epoch": 0.79, + "learning_rate": 6.902998524944322e-06, + "loss": 0.3139, + "step": 6163 + }, + { + "epoch": 0.79, + "learning_rate": 6.9020400030187394e-06, + "loss": 0.3139, + "step": 6164 + }, + { + "epoch": 0.79, + "learning_rate": 6.90108139935826e-06, + "loss": 0.3163, + "step": 6165 + }, + { + "epoch": 0.79, + "learning_rate": 6.90012271400408e-06, + "loss": 0.2959, + "step": 6166 + }, + { + "epoch": 0.79, + "learning_rate": 6.899163946997396e-06, + "loss": 0.3319, + "step": 6167 + }, + { + "epoch": 0.79, + "learning_rate": 6.898205098379407e-06, + "loss": 0.32, + "step": 6168 + }, + { + "epoch": 0.79, + "learning_rate": 6.897246168191317e-06, + "loss": 0.3377, + "step": 6169 + }, + { + "epoch": 0.79, + "learning_rate": 6.8962871564743325e-06, + "loss": 0.3372, + "step": 6170 + }, + { + "epoch": 0.79, + "learning_rate": 6.895328063269667e-06, + "loss": 0.3155, + "step": 6171 + }, + { + "epoch": 0.79, + "learning_rate": 6.894368888618534e-06, + "loss": 0.3082, + "step": 6172 + }, + { + "epoch": 0.79, + "learning_rate": 6.8934096325621505e-06, + "loss": 0.3088, + "step": 6173 + }, + { + "epoch": 0.79, + "learning_rate": 6.892450295141737e-06, + "loss": 0.3255, + "step": 6174 + }, + { + "epoch": 0.79, + "learning_rate": 6.891490876398521e-06, + "loss": 0.3319, + "step": 6175 + }, + { + "epoch": 0.79, + "learning_rate": 6.890531376373729e-06, + "loss": 0.3261, + "step": 6176 + }, + { + "epoch": 0.79, + "learning_rate": 6.889571795108594e-06, + "loss": 0.3109, + "step": 6177 + }, + { + "epoch": 0.79, + "learning_rate": 6.88861213264435e-06, + "loss": 0.3028, + "step": 6178 + }, + { + "epoch": 0.79, + "learning_rate": 6.887652389022236e-06, + "loss": 0.3302, + "step": 6179 + }, + { + "epoch": 0.79, + "learning_rate": 6.886692564283496e-06, + "loss": 0.3041, + "step": 6180 + }, + { + "epoch": 0.79, + "learning_rate": 6.885732658469374e-06, + "loss": 0.3354, + "step": 6181 + }, + { + "epoch": 0.79, + "learning_rate": 6.88477267162112e-06, + "loss": 0.3, + "step": 6182 + }, + { + "epoch": 0.79, + "learning_rate": 6.883812603779985e-06, + "loss": 0.3191, + "step": 6183 + }, + { + "epoch": 0.79, + "learning_rate": 6.88285245498723e-06, + "loss": 0.3317, + "step": 6184 + }, + { + "epoch": 0.79, + "learning_rate": 6.88189222528411e-06, + "loss": 0.286, + "step": 6185 + }, + { + "epoch": 0.79, + "learning_rate": 6.8809319147118905e-06, + "loss": 0.3201, + "step": 6186 + }, + { + "epoch": 0.79, + "learning_rate": 6.879971523311837e-06, + "loss": 0.3192, + "step": 6187 + }, + { + "epoch": 0.79, + "learning_rate": 6.8790110511252195e-06, + "loss": 0.3004, + "step": 6188 + }, + { + "epoch": 0.79, + "learning_rate": 6.878050498193314e-06, + "loss": 0.2982, + "step": 6189 + }, + { + "epoch": 0.79, + "learning_rate": 6.877089864557395e-06, + "loss": 0.309, + "step": 6190 + }, + { + "epoch": 0.79, + "learning_rate": 6.876129150258744e-06, + "loss": 0.297, + "step": 6191 + }, + { + "epoch": 0.79, + "learning_rate": 6.875168355338645e-06, + "loss": 0.326, + "step": 6192 + }, + { + "epoch": 0.79, + "learning_rate": 6.874207479838386e-06, + "loss": 0.3014, + "step": 6193 + }, + { + "epoch": 0.79, + "learning_rate": 6.873246523799256e-06, + "loss": 0.3207, + "step": 6194 + }, + { + "epoch": 0.79, + "learning_rate": 6.872285487262555e-06, + "loss": 0.3232, + "step": 6195 + }, + { + "epoch": 0.79, + "learning_rate": 6.871324370269573e-06, + "loss": 0.3001, + "step": 6196 + }, + { + "epoch": 0.79, + "learning_rate": 6.870363172861616e-06, + "loss": 0.3248, + "step": 6197 + }, + { + "epoch": 0.79, + "learning_rate": 6.869401895079988e-06, + "loss": 0.3082, + "step": 6198 + }, + { + "epoch": 0.79, + "learning_rate": 6.868440536965997e-06, + "loss": 0.3129, + "step": 6199 + }, + { + "epoch": 0.79, + "learning_rate": 6.867479098560956e-06, + "loss": 0.2854, + "step": 6200 + }, + { + "epoch": 0.79, + "learning_rate": 6.866517579906178e-06, + "loss": 0.3299, + "step": 6201 + }, + { + "epoch": 0.79, + "learning_rate": 6.865555981042983e-06, + "loss": 0.3031, + "step": 6202 + }, + { + "epoch": 0.79, + "learning_rate": 6.864594302012691e-06, + "loss": 0.3382, + "step": 6203 + }, + { + "epoch": 0.79, + "learning_rate": 6.863632542856632e-06, + "loss": 0.2879, + "step": 6204 + }, + { + "epoch": 0.79, + "learning_rate": 6.8626707036161314e-06, + "loss": 0.2621, + "step": 6205 + }, + { + "epoch": 0.79, + "learning_rate": 6.86170878433252e-06, + "loss": 0.3181, + "step": 6206 + }, + { + "epoch": 0.79, + "learning_rate": 6.860746785047139e-06, + "loss": 0.3139, + "step": 6207 + }, + { + "epoch": 0.79, + "learning_rate": 6.859784705801323e-06, + "loss": 0.3076, + "step": 6208 + }, + { + "epoch": 0.79, + "learning_rate": 6.858822546636417e-06, + "loss": 0.2953, + "step": 6209 + }, + { + "epoch": 0.79, + "learning_rate": 6.857860307593764e-06, + "loss": 0.3045, + "step": 6210 + }, + { + "epoch": 0.8, + "learning_rate": 6.856897988714718e-06, + "loss": 0.3188, + "step": 6211 + }, + { + "epoch": 0.8, + "learning_rate": 6.855935590040629e-06, + "loss": 0.2764, + "step": 6212 + }, + { + "epoch": 0.8, + "learning_rate": 6.854973111612855e-06, + "loss": 0.3025, + "step": 6213 + }, + { + "epoch": 0.8, + "learning_rate": 6.854010553472757e-06, + "loss": 0.326, + "step": 6214 + }, + { + "epoch": 0.8, + "learning_rate": 6.8530479156616925e-06, + "loss": 0.3064, + "step": 6215 + }, + { + "epoch": 0.8, + "learning_rate": 6.852085198221035e-06, + "loss": 0.3128, + "step": 6216 + }, + { + "epoch": 0.8, + "learning_rate": 6.851122401192149e-06, + "loss": 0.3328, + "step": 6217 + }, + { + "epoch": 0.8, + "learning_rate": 6.850159524616413e-06, + "loss": 0.3192, + "step": 6218 + }, + { + "epoch": 0.8, + "learning_rate": 6.849196568535201e-06, + "loss": 0.286, + "step": 6219 + }, + { + "epoch": 0.8, + "learning_rate": 6.848233532989894e-06, + "loss": 0.2986, + "step": 6220 + }, + { + "epoch": 0.8, + "learning_rate": 6.847270418021876e-06, + "loss": 0.3289, + "step": 6221 + }, + { + "epoch": 0.8, + "learning_rate": 6.8463072236725345e-06, + "loss": 0.3322, + "step": 6222 + }, + { + "epoch": 0.8, + "learning_rate": 6.845343949983258e-06, + "loss": 0.316, + "step": 6223 + }, + { + "epoch": 0.8, + "learning_rate": 6.8443805969954445e-06, + "loss": 0.3228, + "step": 6224 + }, + { + "epoch": 0.8, + "learning_rate": 6.8434171647504885e-06, + "loss": 0.3175, + "step": 6225 + }, + { + "epoch": 0.8, + "learning_rate": 6.84245365328979e-06, + "loss": 0.2763, + "step": 6226 + }, + { + "epoch": 0.8, + "learning_rate": 6.841490062654757e-06, + "loss": 0.3117, + "step": 6227 + }, + { + "epoch": 0.8, + "learning_rate": 6.840526392886793e-06, + "loss": 0.2931, + "step": 6228 + }, + { + "epoch": 0.8, + "learning_rate": 6.839562644027311e-06, + "loss": 0.3006, + "step": 6229 + }, + { + "epoch": 0.8, + "learning_rate": 6.838598816117725e-06, + "loss": 0.3386, + "step": 6230 + }, + { + "epoch": 0.8, + "learning_rate": 6.837634909199453e-06, + "loss": 0.3303, + "step": 6231 + }, + { + "epoch": 0.8, + "learning_rate": 6.836670923313917e-06, + "loss": 0.3311, + "step": 6232 + }, + { + "epoch": 0.8, + "learning_rate": 6.835706858502542e-06, + "loss": 0.3044, + "step": 6233 + }, + { + "epoch": 0.8, + "learning_rate": 6.834742714806754e-06, + "loss": 0.3257, + "step": 6234 + }, + { + "epoch": 0.8, + "learning_rate": 6.833778492267984e-06, + "loss": 0.2969, + "step": 6235 + }, + { + "epoch": 0.8, + "learning_rate": 6.832814190927669e-06, + "loss": 0.2851, + "step": 6236 + }, + { + "epoch": 0.8, + "learning_rate": 6.831849810827247e-06, + "loss": 0.3098, + "step": 6237 + }, + { + "epoch": 0.8, + "learning_rate": 6.830885352008159e-06, + "loss": 0.3357, + "step": 6238 + }, + { + "epoch": 0.8, + "learning_rate": 6.8299208145118475e-06, + "loss": 0.2951, + "step": 6239 + }, + { + "epoch": 0.8, + "learning_rate": 6.828956198379766e-06, + "loss": 0.3042, + "step": 6240 + }, + { + "epoch": 0.8, + "learning_rate": 6.827991503653363e-06, + "loss": 0.2946, + "step": 6241 + }, + { + "epoch": 0.8, + "learning_rate": 6.827026730374093e-06, + "loss": 0.3271, + "step": 6242 + }, + { + "epoch": 0.8, + "learning_rate": 6.826061878583416e-06, + "loss": 0.3187, + "step": 6243 + }, + { + "epoch": 0.8, + "learning_rate": 6.825096948322791e-06, + "loss": 0.2929, + "step": 6244 + }, + { + "epoch": 0.8, + "learning_rate": 6.824131939633688e-06, + "loss": 0.3076, + "step": 6245 + }, + { + "epoch": 0.8, + "learning_rate": 6.823166852557572e-06, + "loss": 0.345, + "step": 6246 + }, + { + "epoch": 0.8, + "learning_rate": 6.822201687135916e-06, + "loss": 0.2884, + "step": 6247 + }, + { + "epoch": 0.8, + "learning_rate": 6.821236443410195e-06, + "loss": 0.3106, + "step": 6248 + }, + { + "epoch": 0.8, + "learning_rate": 6.820271121421889e-06, + "loss": 0.2986, + "step": 6249 + }, + { + "epoch": 0.8, + "learning_rate": 6.819305721212479e-06, + "loss": 0.298, + "step": 6250 + }, + { + "epoch": 0.8, + "learning_rate": 6.818340242823449e-06, + "loss": 0.2984, + "step": 6251 + }, + { + "epoch": 0.8, + "learning_rate": 6.8173746862962904e-06, + "loss": 0.3653, + "step": 6252 + }, + { + "epoch": 0.8, + "learning_rate": 6.816409051672492e-06, + "loss": 0.3208, + "step": 6253 + }, + { + "epoch": 0.8, + "learning_rate": 6.815443338993554e-06, + "loss": 0.3291, + "step": 6254 + }, + { + "epoch": 0.8, + "learning_rate": 6.81447754830097e-06, + "loss": 0.2776, + "step": 6255 + }, + { + "epoch": 0.8, + "learning_rate": 6.813511679636247e-06, + "loss": 0.3049, + "step": 6256 + }, + { + "epoch": 0.8, + "learning_rate": 6.8125457330408865e-06, + "loss": 0.316, + "step": 6257 + }, + { + "epoch": 0.8, + "learning_rate": 6.8115797085564e-06, + "loss": 0.3033, + "step": 6258 + }, + { + "epoch": 0.8, + "learning_rate": 6.810613606224299e-06, + "loss": 0.3212, + "step": 6259 + }, + { + "epoch": 0.8, + "learning_rate": 6.809647426086098e-06, + "loss": 0.3162, + "step": 6260 + }, + { + "epoch": 0.8, + "learning_rate": 6.808681168183317e-06, + "loss": 0.3382, + "step": 6261 + }, + { + "epoch": 0.8, + "learning_rate": 6.807714832557479e-06, + "loss": 0.3016, + "step": 6262 + }, + { + "epoch": 0.8, + "learning_rate": 6.806748419250107e-06, + "loss": 0.3262, + "step": 6263 + }, + { + "epoch": 0.8, + "learning_rate": 6.805781928302732e-06, + "loss": 0.3368, + "step": 6264 + }, + { + "epoch": 0.8, + "learning_rate": 6.804815359756887e-06, + "loss": 0.2847, + "step": 6265 + }, + { + "epoch": 0.8, + "learning_rate": 6.803848713654105e-06, + "loss": 0.3234, + "step": 6266 + }, + { + "epoch": 0.8, + "learning_rate": 6.8028819900359276e-06, + "loss": 0.2949, + "step": 6267 + }, + { + "epoch": 0.8, + "learning_rate": 6.801915188943895e-06, + "loss": 0.3306, + "step": 6268 + }, + { + "epoch": 0.8, + "learning_rate": 6.800948310419554e-06, + "loss": 0.2948, + "step": 6269 + }, + { + "epoch": 0.8, + "learning_rate": 6.799981354504455e-06, + "loss": 0.3189, + "step": 6270 + }, + { + "epoch": 0.8, + "learning_rate": 6.799014321240145e-06, + "loss": 0.3373, + "step": 6271 + }, + { + "epoch": 0.8, + "learning_rate": 6.798047210668185e-06, + "loss": 0.3263, + "step": 6272 + }, + { + "epoch": 0.8, + "learning_rate": 6.797080022830131e-06, + "loss": 0.3285, + "step": 6273 + }, + { + "epoch": 0.8, + "learning_rate": 6.796112757767547e-06, + "loss": 0.3002, + "step": 6274 + }, + { + "epoch": 0.8, + "learning_rate": 6.795145415521997e-06, + "loss": 0.2993, + "step": 6275 + }, + { + "epoch": 0.8, + "learning_rate": 6.79417799613505e-06, + "loss": 0.313, + "step": 6276 + }, + { + "epoch": 0.8, + "learning_rate": 6.793210499648281e-06, + "loss": 0.3224, + "step": 6277 + }, + { + "epoch": 0.8, + "learning_rate": 6.792242926103261e-06, + "loss": 0.3429, + "step": 6278 + }, + { + "epoch": 0.8, + "learning_rate": 6.7912752755415716e-06, + "loss": 0.2989, + "step": 6279 + }, + { + "epoch": 0.8, + "learning_rate": 6.790307548004794e-06, + "loss": 0.3021, + "step": 6280 + }, + { + "epoch": 0.8, + "learning_rate": 6.7893397435345144e-06, + "loss": 0.3017, + "step": 6281 + }, + { + "epoch": 0.8, + "learning_rate": 6.788371862172319e-06, + "loss": 0.2983, + "step": 6282 + }, + { + "epoch": 0.8, + "learning_rate": 6.787403903959804e-06, + "loss": 0.2805, + "step": 6283 + }, + { + "epoch": 0.8, + "learning_rate": 6.786435868938561e-06, + "loss": 0.3179, + "step": 6284 + }, + { + "epoch": 0.8, + "learning_rate": 6.785467757150193e-06, + "loss": 0.3343, + "step": 6285 + }, + { + "epoch": 0.8, + "learning_rate": 6.7844995686362955e-06, + "loss": 0.321, + "step": 6286 + }, + { + "epoch": 0.8, + "learning_rate": 6.7835313034384786e-06, + "loss": 0.3517, + "step": 6287 + }, + { + "epoch": 0.8, + "learning_rate": 6.782562961598349e-06, + "loss": 0.2918, + "step": 6288 + }, + { + "epoch": 0.8, + "learning_rate": 6.78159454315752e-06, + "loss": 0.305, + "step": 6289 + }, + { + "epoch": 0.81, + "learning_rate": 6.780626048157606e-06, + "loss": 0.2901, + "step": 6290 + }, + { + "epoch": 0.81, + "learning_rate": 6.779657476640222e-06, + "loss": 0.3077, + "step": 6291 + }, + { + "epoch": 0.81, + "learning_rate": 6.778688828646996e-06, + "loss": 0.3071, + "step": 6292 + }, + { + "epoch": 0.81, + "learning_rate": 6.777720104219548e-06, + "loss": 0.3258, + "step": 6293 + }, + { + "epoch": 0.81, + "learning_rate": 6.776751303399509e-06, + "loss": 0.2939, + "step": 6294 + }, + { + "epoch": 0.81, + "learning_rate": 6.775782426228509e-06, + "loss": 0.2999, + "step": 6295 + }, + { + "epoch": 0.81, + "learning_rate": 6.774813472748183e-06, + "loss": 0.3284, + "step": 6296 + }, + { + "epoch": 0.81, + "learning_rate": 6.773844443000169e-06, + "loss": 0.3253, + "step": 6297 + }, + { + "epoch": 0.81, + "learning_rate": 6.77287533702611e-06, + "loss": 0.3202, + "step": 6298 + }, + { + "epoch": 0.81, + "learning_rate": 6.771906154867649e-06, + "loss": 0.3229, + "step": 6299 + }, + { + "epoch": 0.81, + "learning_rate": 6.770936896566434e-06, + "loss": 0.3259, + "step": 6300 + }, + { + "epoch": 0.81, + "learning_rate": 6.769967562164116e-06, + "loss": 0.29, + "step": 6301 + }, + { + "epoch": 0.81, + "learning_rate": 6.768998151702351e-06, + "loss": 0.267, + "step": 6302 + }, + { + "epoch": 0.81, + "learning_rate": 6.768028665222795e-06, + "loss": 0.2968, + "step": 6303 + }, + { + "epoch": 0.81, + "learning_rate": 6.767059102767109e-06, + "loss": 0.3103, + "step": 6304 + }, + { + "epoch": 0.81, + "learning_rate": 6.766089464376958e-06, + "loss": 0.3245, + "step": 6305 + }, + { + "epoch": 0.81, + "learning_rate": 6.76511975009401e-06, + "loss": 0.3095, + "step": 6306 + }, + { + "epoch": 0.81, + "learning_rate": 6.7641499599599355e-06, + "loss": 0.288, + "step": 6307 + }, + { + "epoch": 0.81, + "learning_rate": 6.763180094016409e-06, + "loss": 0.2578, + "step": 6308 + }, + { + "epoch": 0.81, + "learning_rate": 6.7622101523051045e-06, + "loss": 0.3041, + "step": 6309 + }, + { + "epoch": 0.81, + "learning_rate": 6.761240134867706e-06, + "loss": 0.3143, + "step": 6310 + }, + { + "epoch": 0.81, + "learning_rate": 6.760270041745898e-06, + "loss": 0.2723, + "step": 6311 + }, + { + "epoch": 0.81, + "learning_rate": 6.759299872981364e-06, + "loss": 0.3079, + "step": 6312 + }, + { + "epoch": 0.81, + "learning_rate": 6.758329628615796e-06, + "loss": 0.3443, + "step": 6313 + }, + { + "epoch": 0.81, + "learning_rate": 6.757359308690889e-06, + "loss": 0.3223, + "step": 6314 + }, + { + "epoch": 0.81, + "learning_rate": 6.756388913248339e-06, + "loss": 0.3253, + "step": 6315 + }, + { + "epoch": 0.81, + "learning_rate": 6.755418442329846e-06, + "loss": 0.3272, + "step": 6316 + }, + { + "epoch": 0.81, + "learning_rate": 6.754447895977113e-06, + "loss": 0.2734, + "step": 6317 + }, + { + "epoch": 0.81, + "learning_rate": 6.753477274231846e-06, + "loss": 0.2917, + "step": 6318 + }, + { + "epoch": 0.81, + "learning_rate": 6.7525065771357546e-06, + "loss": 0.321, + "step": 6319 + }, + { + "epoch": 0.81, + "learning_rate": 6.751535804730553e-06, + "loss": 0.3184, + "step": 6320 + }, + { + "epoch": 0.81, + "learning_rate": 6.750564957057958e-06, + "loss": 0.2978, + "step": 6321 + }, + { + "epoch": 0.81, + "learning_rate": 6.749594034159687e-06, + "loss": 0.2996, + "step": 6322 + }, + { + "epoch": 0.81, + "learning_rate": 6.748623036077464e-06, + "loss": 0.2944, + "step": 6323 + }, + { + "epoch": 0.81, + "learning_rate": 6.7476519628530145e-06, + "loss": 0.3276, + "step": 6324 + }, + { + "epoch": 0.81, + "learning_rate": 6.7466808145280685e-06, + "loss": 0.3458, + "step": 6325 + }, + { + "epoch": 0.81, + "learning_rate": 6.745709591144358e-06, + "loss": 0.301, + "step": 6326 + }, + { + "epoch": 0.81, + "learning_rate": 6.744738292743617e-06, + "loss": 0.312, + "step": 6327 + }, + { + "epoch": 0.81, + "learning_rate": 6.743766919367588e-06, + "loss": 0.329, + "step": 6328 + }, + { + "epoch": 0.81, + "learning_rate": 6.742795471058009e-06, + "loss": 0.3111, + "step": 6329 + }, + { + "epoch": 0.81, + "learning_rate": 6.741823947856627e-06, + "loss": 0.3026, + "step": 6330 + }, + { + "epoch": 0.81, + "learning_rate": 6.740852349805193e-06, + "loss": 0.3185, + "step": 6331 + }, + { + "epoch": 0.81, + "learning_rate": 6.739880676945455e-06, + "loss": 0.2977, + "step": 6332 + }, + { + "epoch": 0.81, + "learning_rate": 6.73890892931917e-06, + "loss": 0.2851, + "step": 6333 + }, + { + "epoch": 0.81, + "learning_rate": 6.737937106968094e-06, + "loss": 0.3126, + "step": 6334 + }, + { + "epoch": 0.81, + "learning_rate": 6.736965209933992e-06, + "loss": 0.3224, + "step": 6335 + }, + { + "epoch": 0.81, + "learning_rate": 6.735993238258624e-06, + "loss": 0.298, + "step": 6336 + }, + { + "epoch": 0.81, + "learning_rate": 6.735021191983763e-06, + "loss": 0.3176, + "step": 6337 + }, + { + "epoch": 0.81, + "learning_rate": 6.734049071151175e-06, + "loss": 0.3359, + "step": 6338 + }, + { + "epoch": 0.81, + "learning_rate": 6.7330768758026374e-06, + "loss": 0.3072, + "step": 6339 + }, + { + "epoch": 0.81, + "learning_rate": 6.732104605979928e-06, + "loss": 0.3436, + "step": 6340 + }, + { + "epoch": 0.81, + "learning_rate": 6.7311322617248246e-06, + "loss": 0.2822, + "step": 6341 + }, + { + "epoch": 0.81, + "learning_rate": 6.730159843079113e-06, + "loss": 0.3129, + "step": 6342 + }, + { + "epoch": 0.81, + "learning_rate": 6.729187350084579e-06, + "loss": 0.3205, + "step": 6343 + }, + { + "epoch": 0.81, + "learning_rate": 6.728214782783013e-06, + "loss": 0.3123, + "step": 6344 + }, + { + "epoch": 0.81, + "learning_rate": 6.72724214121621e-06, + "loss": 0.3077, + "step": 6345 + }, + { + "epoch": 0.81, + "learning_rate": 6.726269425425967e-06, + "loss": 0.2801, + "step": 6346 + }, + { + "epoch": 0.81, + "learning_rate": 6.725296635454079e-06, + "loss": 0.3016, + "step": 6347 + }, + { + "epoch": 0.81, + "learning_rate": 6.724323771342354e-06, + "loss": 0.2818, + "step": 6348 + }, + { + "epoch": 0.81, + "learning_rate": 6.723350833132596e-06, + "loss": 0.3032, + "step": 6349 + }, + { + "epoch": 0.81, + "learning_rate": 6.722377820866614e-06, + "loss": 0.3009, + "step": 6350 + }, + { + "epoch": 0.81, + "learning_rate": 6.721404734586221e-06, + "loss": 0.315, + "step": 6351 + }, + { + "epoch": 0.81, + "learning_rate": 6.7204315743332325e-06, + "loss": 0.3279, + "step": 6352 + }, + { + "epoch": 0.81, + "learning_rate": 6.71945834014947e-06, + "loss": 0.2972, + "step": 6353 + }, + { + "epoch": 0.81, + "learning_rate": 6.7184850320767505e-06, + "loss": 0.3052, + "step": 6354 + }, + { + "epoch": 0.81, + "learning_rate": 6.717511650156903e-06, + "loss": 0.3341, + "step": 6355 + }, + { + "epoch": 0.81, + "learning_rate": 6.716538194431754e-06, + "loss": 0.3218, + "step": 6356 + }, + { + "epoch": 0.81, + "learning_rate": 6.715564664943138e-06, + "loss": 0.3172, + "step": 6357 + }, + { + "epoch": 0.81, + "learning_rate": 6.714591061732886e-06, + "loss": 0.333, + "step": 6358 + }, + { + "epoch": 0.81, + "learning_rate": 6.7136173848428375e-06, + "loss": 0.3046, + "step": 6359 + }, + { + "epoch": 0.81, + "learning_rate": 6.712643634314834e-06, + "loss": 0.3079, + "step": 6360 + }, + { + "epoch": 0.81, + "learning_rate": 6.711669810190717e-06, + "loss": 0.3079, + "step": 6361 + }, + { + "epoch": 0.81, + "learning_rate": 6.710695912512339e-06, + "loss": 0.32, + "step": 6362 + }, + { + "epoch": 0.81, + "learning_rate": 6.7097219413215474e-06, + "loss": 0.3152, + "step": 6363 + }, + { + "epoch": 0.81, + "learning_rate": 6.708747896660196e-06, + "loss": 0.3402, + "step": 6364 + }, + { + "epoch": 0.81, + "learning_rate": 6.70777377857014e-06, + "loss": 0.3225, + "step": 6365 + }, + { + "epoch": 0.81, + "learning_rate": 6.706799587093243e-06, + "loss": 0.3289, + "step": 6366 + }, + { + "epoch": 0.81, + "learning_rate": 6.705825322271367e-06, + "loss": 0.3025, + "step": 6367 + }, + { + "epoch": 0.82, + "learning_rate": 6.7048509841463775e-06, + "loss": 0.3464, + "step": 6368 + }, + { + "epoch": 0.82, + "learning_rate": 6.703876572760144e-06, + "loss": 0.3348, + "step": 6369 + }, + { + "epoch": 0.82, + "learning_rate": 6.702902088154539e-06, + "loss": 0.3345, + "step": 6370 + }, + { + "epoch": 0.82, + "learning_rate": 6.701927530371439e-06, + "loss": 0.304, + "step": 6371 + }, + { + "epoch": 0.82, + "learning_rate": 6.700952899452723e-06, + "loss": 0.3239, + "step": 6372 + }, + { + "epoch": 0.82, + "learning_rate": 6.699978195440273e-06, + "loss": 0.311, + "step": 6373 + }, + { + "epoch": 0.82, + "learning_rate": 6.6990034183759726e-06, + "loss": 0.3132, + "step": 6374 + }, + { + "epoch": 0.82, + "learning_rate": 6.698028568301712e-06, + "loss": 0.3124, + "step": 6375 + }, + { + "epoch": 0.82, + "learning_rate": 6.697053645259382e-06, + "loss": 0.3336, + "step": 6376 + }, + { + "epoch": 0.82, + "learning_rate": 6.696078649290878e-06, + "loss": 0.2875, + "step": 6377 + }, + { + "epoch": 0.82, + "learning_rate": 6.695103580438097e-06, + "loss": 0.3161, + "step": 6378 + }, + { + "epoch": 0.82, + "learning_rate": 6.694128438742939e-06, + "loss": 0.2975, + "step": 6379 + }, + { + "epoch": 0.82, + "learning_rate": 6.693153224247309e-06, + "loss": 0.2943, + "step": 6380 + }, + { + "epoch": 0.82, + "learning_rate": 6.692177936993114e-06, + "loss": 0.3189, + "step": 6381 + }, + { + "epoch": 0.82, + "learning_rate": 6.691202577022267e-06, + "loss": 0.3017, + "step": 6382 + }, + { + "epoch": 0.82, + "learning_rate": 6.690227144376676e-06, + "loss": 0.295, + "step": 6383 + }, + { + "epoch": 0.82, + "learning_rate": 6.689251639098261e-06, + "loss": 0.3087, + "step": 6384 + }, + { + "epoch": 0.82, + "learning_rate": 6.68827606122894e-06, + "loss": 0.3169, + "step": 6385 + }, + { + "epoch": 0.82, + "learning_rate": 6.687300410810638e-06, + "loss": 0.2884, + "step": 6386 + }, + { + "epoch": 0.82, + "learning_rate": 6.686324687885281e-06, + "loss": 0.3255, + "step": 6387 + }, + { + "epoch": 0.82, + "learning_rate": 6.685348892494793e-06, + "loss": 0.3461, + "step": 6388 + }, + { + "epoch": 0.82, + "learning_rate": 6.684373024681112e-06, + "loss": 0.3308, + "step": 6389 + }, + { + "epoch": 0.82, + "learning_rate": 6.683397084486169e-06, + "loss": 0.3159, + "step": 6390 + }, + { + "epoch": 0.82, + "learning_rate": 6.682421071951907e-06, + "loss": 0.2935, + "step": 6391 + }, + { + "epoch": 0.82, + "learning_rate": 6.681444987120262e-06, + "loss": 0.3228, + "step": 6392 + }, + { + "epoch": 0.82, + "learning_rate": 6.680468830033182e-06, + "loss": 0.3268, + "step": 6393 + }, + { + "epoch": 0.82, + "learning_rate": 6.679492600732614e-06, + "loss": 0.3393, + "step": 6394 + }, + { + "epoch": 0.82, + "learning_rate": 6.678516299260507e-06, + "loss": 0.3435, + "step": 6395 + }, + { + "epoch": 0.82, + "learning_rate": 6.677539925658819e-06, + "loss": 0.3206, + "step": 6396 + }, + { + "epoch": 0.82, + "learning_rate": 6.676563479969502e-06, + "loss": 0.3346, + "step": 6397 + }, + { + "epoch": 0.82, + "learning_rate": 6.67558696223452e-06, + "loss": 0.3165, + "step": 6398 + }, + { + "epoch": 0.82, + "learning_rate": 6.674610372495832e-06, + "loss": 0.3038, + "step": 6399 + }, + { + "epoch": 0.82, + "learning_rate": 6.673633710795409e-06, + "loss": 0.2882, + "step": 6400 + }, + { + "epoch": 0.82, + "learning_rate": 6.672656977175218e-06, + "loss": 0.3187, + "step": 6401 + }, + { + "epoch": 0.82, + "learning_rate": 6.671680171677232e-06, + "loss": 0.3231, + "step": 6402 + }, + { + "epoch": 0.82, + "learning_rate": 6.670703294343423e-06, + "loss": 0.2757, + "step": 6403 + }, + { + "epoch": 0.82, + "learning_rate": 6.669726345215776e-06, + "loss": 0.3445, + "step": 6404 + }, + { + "epoch": 0.82, + "learning_rate": 6.668749324336268e-06, + "loss": 0.3005, + "step": 6405 + }, + { + "epoch": 0.82, + "learning_rate": 6.667772231746885e-06, + "loss": 0.3306, + "step": 6406 + }, + { + "epoch": 0.82, + "learning_rate": 6.666795067489615e-06, + "loss": 0.318, + "step": 6407 + }, + { + "epoch": 0.82, + "learning_rate": 6.665817831606447e-06, + "loss": 0.2821, + "step": 6408 + }, + { + "epoch": 0.82, + "learning_rate": 6.66484052413938e-06, + "loss": 0.3002, + "step": 6409 + }, + { + "epoch": 0.82, + "learning_rate": 6.663863145130406e-06, + "loss": 0.303, + "step": 6410 + }, + { + "epoch": 0.82, + "learning_rate": 6.662885694621527e-06, + "loss": 0.3079, + "step": 6411 + }, + { + "epoch": 0.82, + "learning_rate": 6.661908172654746e-06, + "loss": 0.2993, + "step": 6412 + }, + { + "epoch": 0.82, + "learning_rate": 6.6609305792720705e-06, + "loss": 0.3229, + "step": 6413 + }, + { + "epoch": 0.82, + "learning_rate": 6.659952914515508e-06, + "loss": 0.3259, + "step": 6414 + }, + { + "epoch": 0.82, + "learning_rate": 6.658975178427073e-06, + "loss": 0.3123, + "step": 6415 + }, + { + "epoch": 0.82, + "learning_rate": 6.65799737104878e-06, + "loss": 0.3237, + "step": 6416 + }, + { + "epoch": 0.82, + "learning_rate": 6.657019492422645e-06, + "loss": 0.2864, + "step": 6417 + }, + { + "epoch": 0.82, + "learning_rate": 6.656041542590694e-06, + "loss": 0.3118, + "step": 6418 + }, + { + "epoch": 0.82, + "learning_rate": 6.65506352159495e-06, + "loss": 0.2965, + "step": 6419 + }, + { + "epoch": 0.82, + "learning_rate": 6.65408542947744e-06, + "loss": 0.3466, + "step": 6420 + }, + { + "epoch": 0.82, + "learning_rate": 6.653107266280194e-06, + "loss": 0.3144, + "step": 6421 + }, + { + "epoch": 0.82, + "learning_rate": 6.652129032045249e-06, + "loss": 0.3132, + "step": 6422 + }, + { + "epoch": 0.82, + "learning_rate": 6.651150726814639e-06, + "loss": 0.3087, + "step": 6423 + }, + { + "epoch": 0.82, + "learning_rate": 6.650172350630406e-06, + "loss": 0.2985, + "step": 6424 + }, + { + "epoch": 0.82, + "learning_rate": 6.649193903534591e-06, + "loss": 0.312, + "step": 6425 + }, + { + "epoch": 0.82, + "learning_rate": 6.6482153855692395e-06, + "loss": 0.3201, + "step": 6426 + }, + { + "epoch": 0.82, + "learning_rate": 6.647236796776405e-06, + "loss": 0.3175, + "step": 6427 + }, + { + "epoch": 0.82, + "learning_rate": 6.646258137198136e-06, + "loss": 0.2935, + "step": 6428 + }, + { + "epoch": 0.82, + "learning_rate": 6.645279406876488e-06, + "loss": 0.3142, + "step": 6429 + }, + { + "epoch": 0.82, + "learning_rate": 6.644300605853518e-06, + "loss": 0.333, + "step": 6430 + }, + { + "epoch": 0.82, + "learning_rate": 6.643321734171291e-06, + "loss": 0.3073, + "step": 6431 + }, + { + "epoch": 0.82, + "learning_rate": 6.642342791871868e-06, + "loss": 0.3205, + "step": 6432 + }, + { + "epoch": 0.82, + "learning_rate": 6.64136377899732e-06, + "loss": 0.2952, + "step": 6433 + }, + { + "epoch": 0.82, + "learning_rate": 6.640384695589714e-06, + "loss": 0.3142, + "step": 6434 + }, + { + "epoch": 0.82, + "learning_rate": 6.639405541691122e-06, + "loss": 0.2805, + "step": 6435 + }, + { + "epoch": 0.82, + "learning_rate": 6.638426317343624e-06, + "loss": 0.325, + "step": 6436 + }, + { + "epoch": 0.82, + "learning_rate": 6.6374470225892985e-06, + "loss": 0.3058, + "step": 6437 + }, + { + "epoch": 0.82, + "learning_rate": 6.6364676574702284e-06, + "loss": 0.2974, + "step": 6438 + }, + { + "epoch": 0.82, + "learning_rate": 6.635488222028497e-06, + "loss": 0.305, + "step": 6439 + }, + { + "epoch": 0.82, + "learning_rate": 6.6345087163061935e-06, + "loss": 0.321, + "step": 6440 + }, + { + "epoch": 0.82, + "learning_rate": 6.633529140345412e-06, + "loss": 0.3168, + "step": 6441 + }, + { + "epoch": 0.82, + "learning_rate": 6.632549494188245e-06, + "loss": 0.2841, + "step": 6442 + }, + { + "epoch": 0.82, + "learning_rate": 6.631569777876791e-06, + "loss": 0.2962, + "step": 6443 + }, + { + "epoch": 0.82, + "learning_rate": 6.630589991453148e-06, + "loss": 0.2968, + "step": 6444 + }, + { + "epoch": 0.82, + "learning_rate": 6.629610134959423e-06, + "loss": 0.271, + "step": 6445 + }, + { + "epoch": 0.83, + "learning_rate": 6.628630208437719e-06, + "loss": 0.3329, + "step": 6446 + }, + { + "epoch": 0.83, + "learning_rate": 6.627650211930152e-06, + "loss": 0.3047, + "step": 6447 + }, + { + "epoch": 0.83, + "learning_rate": 6.626670145478826e-06, + "loss": 0.2983, + "step": 6448 + }, + { + "epoch": 0.83, + "learning_rate": 6.6256900091258644e-06, + "loss": 0.3228, + "step": 6449 + }, + { + "epoch": 0.83, + "learning_rate": 6.62470980291338e-06, + "loss": 0.3223, + "step": 6450 + }, + { + "epoch": 0.83, + "learning_rate": 6.623729526883498e-06, + "loss": 0.2945, + "step": 6451 + }, + { + "epoch": 0.83, + "learning_rate": 6.622749181078344e-06, + "loss": 0.3259, + "step": 6452 + }, + { + "epoch": 0.83, + "learning_rate": 6.621768765540041e-06, + "loss": 0.296, + "step": 6453 + }, + { + "epoch": 0.83, + "learning_rate": 6.620788280310722e-06, + "loss": 0.2971, + "step": 6454 + }, + { + "epoch": 0.83, + "learning_rate": 6.619807725432522e-06, + "loss": 0.3336, + "step": 6455 + }, + { + "epoch": 0.83, + "learning_rate": 6.618827100947577e-06, + "loss": 0.318, + "step": 6456 + }, + { + "epoch": 0.83, + "learning_rate": 6.6178464068980256e-06, + "loss": 0.2869, + "step": 6457 + }, + { + "epoch": 0.83, + "learning_rate": 6.616865643326011e-06, + "loss": 0.3091, + "step": 6458 + }, + { + "epoch": 0.83, + "learning_rate": 6.615884810273678e-06, + "loss": 0.3109, + "step": 6459 + }, + { + "epoch": 0.83, + "learning_rate": 6.614903907783177e-06, + "loss": 0.3099, + "step": 6460 + }, + { + "epoch": 0.83, + "learning_rate": 6.613922935896659e-06, + "loss": 0.2792, + "step": 6461 + }, + { + "epoch": 0.83, + "learning_rate": 6.612941894656277e-06, + "loss": 0.3291, + "step": 6462 + }, + { + "epoch": 0.83, + "learning_rate": 6.61196078410419e-06, + "loss": 0.2954, + "step": 6463 + }, + { + "epoch": 0.83, + "learning_rate": 6.610979604282557e-06, + "loss": 0.3123, + "step": 6464 + }, + { + "epoch": 0.83, + "learning_rate": 6.609998355233543e-06, + "loss": 0.32, + "step": 6465 + }, + { + "epoch": 0.83, + "learning_rate": 6.609017036999314e-06, + "loss": 0.305, + "step": 6466 + }, + { + "epoch": 0.83, + "learning_rate": 6.608035649622041e-06, + "loss": 0.3228, + "step": 6467 + }, + { + "epoch": 0.83, + "learning_rate": 6.607054193143894e-06, + "loss": 0.323, + "step": 6468 + }, + { + "epoch": 0.83, + "learning_rate": 6.606072667607048e-06, + "loss": 0.2901, + "step": 6469 + }, + { + "epoch": 0.83, + "learning_rate": 6.605091073053685e-06, + "loss": 0.3383, + "step": 6470 + }, + { + "epoch": 0.83, + "learning_rate": 6.604109409525982e-06, + "loss": 0.292, + "step": 6471 + }, + { + "epoch": 0.83, + "learning_rate": 6.603127677066126e-06, + "loss": 0.3071, + "step": 6472 + }, + { + "epoch": 0.83, + "learning_rate": 6.602145875716301e-06, + "loss": 0.3075, + "step": 6473 + }, + { + "epoch": 0.83, + "learning_rate": 6.601164005518702e-06, + "loss": 0.3127, + "step": 6474 + }, + { + "epoch": 0.83, + "learning_rate": 6.600182066515519e-06, + "loss": 0.2914, + "step": 6475 + }, + { + "epoch": 0.83, + "learning_rate": 6.599200058748949e-06, + "loss": 0.3335, + "step": 6476 + }, + { + "epoch": 0.83, + "learning_rate": 6.59821798226119e-06, + "loss": 0.3093, + "step": 6477 + }, + { + "epoch": 0.83, + "learning_rate": 6.597235837094446e-06, + "loss": 0.2972, + "step": 6478 + }, + { + "epoch": 0.83, + "learning_rate": 6.59625362329092e-06, + "loss": 0.334, + "step": 6479 + }, + { + "epoch": 0.83, + "learning_rate": 6.595271340892823e-06, + "loss": 0.3378, + "step": 6480 + }, + { + "epoch": 0.83, + "learning_rate": 6.594288989942361e-06, + "loss": 0.3104, + "step": 6481 + }, + { + "epoch": 0.83, + "learning_rate": 6.593306570481751e-06, + "loss": 0.2892, + "step": 6482 + }, + { + "epoch": 0.83, + "learning_rate": 6.592324082553209e-06, + "loss": 0.2924, + "step": 6483 + }, + { + "epoch": 0.83, + "learning_rate": 6.591341526198955e-06, + "loss": 0.2987, + "step": 6484 + }, + { + "epoch": 0.83, + "learning_rate": 6.590358901461213e-06, + "loss": 0.3224, + "step": 6485 + }, + { + "epoch": 0.83, + "learning_rate": 6.589376208382206e-06, + "loss": 0.313, + "step": 6486 + }, + { + "epoch": 0.83, + "learning_rate": 6.588393447004163e-06, + "loss": 0.3125, + "step": 6487 + }, + { + "epoch": 0.83, + "learning_rate": 6.587410617369316e-06, + "loss": 0.2881, + "step": 6488 + }, + { + "epoch": 0.83, + "learning_rate": 6.586427719519901e-06, + "loss": 0.3192, + "step": 6489 + }, + { + "epoch": 0.83, + "learning_rate": 6.585444753498153e-06, + "loss": 0.2962, + "step": 6490 + }, + { + "epoch": 0.83, + "learning_rate": 6.584461719346312e-06, + "loss": 0.2962, + "step": 6491 + }, + { + "epoch": 0.83, + "learning_rate": 6.583478617106623e-06, + "loss": 0.3246, + "step": 6492 + }, + { + "epoch": 0.83, + "learning_rate": 6.582495446821331e-06, + "loss": 0.2717, + "step": 6493 + }, + { + "epoch": 0.83, + "learning_rate": 6.581512208532685e-06, + "loss": 0.3311, + "step": 6494 + }, + { + "epoch": 0.83, + "learning_rate": 6.580528902282938e-06, + "loss": 0.3101, + "step": 6495 + }, + { + "epoch": 0.83, + "learning_rate": 6.579545528114344e-06, + "loss": 0.3151, + "step": 6496 + }, + { + "epoch": 0.83, + "learning_rate": 6.57856208606916e-06, + "loss": 0.2903, + "step": 6497 + }, + { + "epoch": 0.83, + "learning_rate": 6.577578576189648e-06, + "loss": 0.3368, + "step": 6498 + }, + { + "epoch": 0.83, + "learning_rate": 6.576594998518071e-06, + "loss": 0.3535, + "step": 6499 + }, + { + "epoch": 0.83, + "learning_rate": 6.575611353096695e-06, + "loss": 0.3242, + "step": 6500 + }, + { + "epoch": 0.83, + "learning_rate": 6.574627639967791e-06, + "loss": 0.2858, + "step": 6501 + }, + { + "epoch": 0.83, + "learning_rate": 6.57364385917363e-06, + "loss": 0.3116, + "step": 6502 + }, + { + "epoch": 0.83, + "learning_rate": 6.572660010756489e-06, + "loss": 0.295, + "step": 6503 + }, + { + "epoch": 0.83, + "learning_rate": 6.5716760947586425e-06, + "loss": 0.3019, + "step": 6504 + }, + { + "epoch": 0.83, + "learning_rate": 6.570692111222375e-06, + "loss": 0.3064, + "step": 6505 + }, + { + "epoch": 0.83, + "learning_rate": 6.56970806018997e-06, + "loss": 0.3051, + "step": 6506 + }, + { + "epoch": 0.83, + "learning_rate": 6.568723941703712e-06, + "loss": 0.3354, + "step": 6507 + }, + { + "epoch": 0.83, + "learning_rate": 6.567739755805895e-06, + "loss": 0.2945, + "step": 6508 + }, + { + "epoch": 0.83, + "learning_rate": 6.566755502538806e-06, + "loss": 0.2858, + "step": 6509 + }, + { + "epoch": 0.83, + "learning_rate": 6.565771181944747e-06, + "loss": 0.3139, + "step": 6510 + }, + { + "epoch": 0.83, + "learning_rate": 6.5647867940660105e-06, + "loss": 0.3268, + "step": 6511 + }, + { + "epoch": 0.83, + "learning_rate": 6.563802338944902e-06, + "loss": 0.3173, + "step": 6512 + }, + { + "epoch": 0.83, + "learning_rate": 6.562817816623724e-06, + "loss": 0.2918, + "step": 6513 + }, + { + "epoch": 0.83, + "learning_rate": 6.561833227144784e-06, + "loss": 0.3448, + "step": 6514 + }, + { + "epoch": 0.83, + "learning_rate": 6.560848570550391e-06, + "loss": 0.3245, + "step": 6515 + }, + { + "epoch": 0.83, + "learning_rate": 6.559863846882859e-06, + "loss": 0.3254, + "step": 6516 + }, + { + "epoch": 0.83, + "learning_rate": 6.558879056184505e-06, + "loss": 0.304, + "step": 6517 + }, + { + "epoch": 0.83, + "learning_rate": 6.557894198497644e-06, + "loss": 0.2941, + "step": 6518 + }, + { + "epoch": 0.83, + "learning_rate": 6.556909273864601e-06, + "loss": 0.2876, + "step": 6519 + }, + { + "epoch": 0.83, + "learning_rate": 6.555924282327698e-06, + "loss": 0.2818, + "step": 6520 + }, + { + "epoch": 0.83, + "learning_rate": 6.554939223929264e-06, + "loss": 0.2816, + "step": 6521 + }, + { + "epoch": 0.83, + "learning_rate": 6.553954098711629e-06, + "loss": 0.3109, + "step": 6522 + }, + { + "epoch": 0.83, + "learning_rate": 6.5529689067171255e-06, + "loss": 0.3056, + "step": 6523 + }, + { + "epoch": 0.84, + "learning_rate": 6.551983647988089e-06, + "loss": 0.3173, + "step": 6524 + }, + { + "epoch": 0.84, + "learning_rate": 6.550998322566857e-06, + "loss": 0.2911, + "step": 6525 + }, + { + "epoch": 0.84, + "learning_rate": 6.550012930495775e-06, + "loss": 0.3184, + "step": 6526 + }, + { + "epoch": 0.84, + "learning_rate": 6.549027471817186e-06, + "loss": 0.3235, + "step": 6527 + }, + { + "epoch": 0.84, + "learning_rate": 6.5480419465734355e-06, + "loss": 0.3123, + "step": 6528 + }, + { + "epoch": 0.84, + "learning_rate": 6.547056354806874e-06, + "loss": 0.301, + "step": 6529 + }, + { + "epoch": 0.84, + "learning_rate": 6.546070696559856e-06, + "loss": 0.3034, + "step": 6530 + }, + { + "epoch": 0.84, + "learning_rate": 6.545084971874738e-06, + "loss": 0.2942, + "step": 6531 + }, + { + "epoch": 0.84, + "learning_rate": 6.544099180793877e-06, + "loss": 0.3308, + "step": 6532 + }, + { + "epoch": 0.84, + "learning_rate": 6.543113323359635e-06, + "loss": 0.3136, + "step": 6533 + }, + { + "epoch": 0.84, + "learning_rate": 6.542127399614376e-06, + "loss": 0.3265, + "step": 6534 + }, + { + "epoch": 0.84, + "learning_rate": 6.54114140960047e-06, + "loss": 0.303, + "step": 6535 + }, + { + "epoch": 0.84, + "learning_rate": 6.540155353360284e-06, + "loss": 0.3073, + "step": 6536 + }, + { + "epoch": 0.84, + "learning_rate": 6.539169230936193e-06, + "loss": 0.318, + "step": 6537 + }, + { + "epoch": 0.84, + "learning_rate": 6.5381830423705714e-06, + "loss": 0.3208, + "step": 6538 + }, + { + "epoch": 0.84, + "learning_rate": 6.5371967877058e-06, + "loss": 0.2864, + "step": 6539 + }, + { + "epoch": 0.84, + "learning_rate": 6.536210466984259e-06, + "loss": 0.3242, + "step": 6540 + }, + { + "epoch": 0.84, + "learning_rate": 6.535224080248332e-06, + "loss": 0.3092, + "step": 6541 + }, + { + "epoch": 0.84, + "learning_rate": 6.534237627540408e-06, + "loss": 0.3157, + "step": 6542 + }, + { + "epoch": 0.84, + "learning_rate": 6.533251108902875e-06, + "loss": 0.3142, + "step": 6543 + }, + { + "epoch": 0.84, + "learning_rate": 6.532264524378128e-06, + "loss": 0.3148, + "step": 6544 + }, + { + "epoch": 0.84, + "learning_rate": 6.531277874008562e-06, + "loss": 0.3193, + "step": 6545 + }, + { + "epoch": 0.84, + "learning_rate": 6.5302911578365755e-06, + "loss": 0.3104, + "step": 6546 + }, + { + "epoch": 0.84, + "learning_rate": 6.529304375904568e-06, + "loss": 0.3136, + "step": 6547 + }, + { + "epoch": 0.84, + "learning_rate": 6.528317528254948e-06, + "loss": 0.3144, + "step": 6548 + }, + { + "epoch": 0.84, + "learning_rate": 6.52733061493012e-06, + "loss": 0.3073, + "step": 6549 + }, + { + "epoch": 0.84, + "learning_rate": 6.526343635972492e-06, + "loss": 0.2853, + "step": 6550 + }, + { + "epoch": 0.84, + "learning_rate": 6.525356591424479e-06, + "loss": 0.3385, + "step": 6551 + }, + { + "epoch": 0.84, + "learning_rate": 6.5243694813284975e-06, + "loss": 0.2944, + "step": 6552 + }, + { + "epoch": 0.84, + "learning_rate": 6.523382305726964e-06, + "loss": 0.3106, + "step": 6553 + }, + { + "epoch": 0.84, + "learning_rate": 6.522395064662299e-06, + "loss": 0.3556, + "step": 6554 + }, + { + "epoch": 0.84, + "learning_rate": 6.521407758176929e-06, + "loss": 0.3116, + "step": 6555 + }, + { + "epoch": 0.84, + "learning_rate": 6.520420386313277e-06, + "loss": 0.3037, + "step": 6556 + }, + { + "epoch": 0.84, + "learning_rate": 6.5194329491137775e-06, + "loss": 0.3209, + "step": 6557 + }, + { + "epoch": 0.84, + "learning_rate": 6.518445446620858e-06, + "loss": 0.3232, + "step": 6558 + }, + { + "epoch": 0.84, + "learning_rate": 6.517457878876958e-06, + "loss": 0.3221, + "step": 6559 + }, + { + "epoch": 0.84, + "learning_rate": 6.516470245924511e-06, + "loss": 0.2823, + "step": 6560 + }, + { + "epoch": 0.84, + "learning_rate": 6.515482547805962e-06, + "loss": 0.3231, + "step": 6561 + }, + { + "epoch": 0.84, + "learning_rate": 6.514494784563753e-06, + "loss": 0.2919, + "step": 6562 + }, + { + "epoch": 0.84, + "learning_rate": 6.5135069562403285e-06, + "loss": 0.2967, + "step": 6563 + }, + { + "epoch": 0.84, + "learning_rate": 6.512519062878142e-06, + "loss": 0.3021, + "step": 6564 + }, + { + "epoch": 0.84, + "learning_rate": 6.511531104519639e-06, + "loss": 0.3062, + "step": 6565 + }, + { + "epoch": 0.84, + "learning_rate": 6.510543081207281e-06, + "loss": 0.3303, + "step": 6566 + }, + { + "epoch": 0.84, + "learning_rate": 6.509554992983521e-06, + "loss": 0.3169, + "step": 6567 + }, + { + "epoch": 0.84, + "learning_rate": 6.508566839890823e-06, + "loss": 0.2885, + "step": 6568 + }, + { + "epoch": 0.84, + "learning_rate": 6.507578621971646e-06, + "loss": 0.3338, + "step": 6569 + }, + { + "epoch": 0.84, + "learning_rate": 6.506590339268459e-06, + "loss": 0.3218, + "step": 6570 + }, + { + "epoch": 0.84, + "learning_rate": 6.50560199182373e-06, + "loss": 0.3084, + "step": 6571 + }, + { + "epoch": 0.84, + "learning_rate": 6.504613579679929e-06, + "loss": 0.334, + "step": 6572 + }, + { + "epoch": 0.84, + "learning_rate": 6.503625102879534e-06, + "loss": 0.2757, + "step": 6573 + }, + { + "epoch": 0.84, + "learning_rate": 6.502636561465018e-06, + "loss": 0.3292, + "step": 6574 + }, + { + "epoch": 0.84, + "learning_rate": 6.501647955478863e-06, + "loss": 0.3363, + "step": 6575 + }, + { + "epoch": 0.84, + "learning_rate": 6.500659284963549e-06, + "loss": 0.2936, + "step": 6576 + }, + { + "epoch": 0.84, + "learning_rate": 6.499670549961565e-06, + "loss": 0.311, + "step": 6577 + }, + { + "epoch": 0.84, + "learning_rate": 6.498681750515398e-06, + "loss": 0.3108, + "step": 6578 + }, + { + "epoch": 0.84, + "learning_rate": 6.497692886667537e-06, + "loss": 0.3163, + "step": 6579 + }, + { + "epoch": 0.84, + "learning_rate": 6.496703958460479e-06, + "loss": 0.3192, + "step": 6580 + }, + { + "epoch": 0.84, + "learning_rate": 6.495714965936717e-06, + "loss": 0.3267, + "step": 6581 + }, + { + "epoch": 0.84, + "learning_rate": 6.494725909138751e-06, + "loss": 0.307, + "step": 6582 + }, + { + "epoch": 0.84, + "learning_rate": 6.493736788109086e-06, + "loss": 0.2995, + "step": 6583 + }, + { + "epoch": 0.84, + "learning_rate": 6.492747602890223e-06, + "loss": 0.3457, + "step": 6584 + }, + { + "epoch": 0.84, + "learning_rate": 6.491758353524672e-06, + "loss": 0.2915, + "step": 6585 + }, + { + "epoch": 0.84, + "learning_rate": 6.490769040054942e-06, + "loss": 0.3178, + "step": 6586 + }, + { + "epoch": 0.84, + "learning_rate": 6.489779662523545e-06, + "loss": 0.3102, + "step": 6587 + }, + { + "epoch": 0.84, + "learning_rate": 6.4887902209730004e-06, + "loss": 0.3198, + "step": 6588 + }, + { + "epoch": 0.84, + "learning_rate": 6.487800715445822e-06, + "loss": 0.3153, + "step": 6589 + }, + { + "epoch": 0.84, + "learning_rate": 6.486811145984534e-06, + "loss": 0.3027, + "step": 6590 + }, + { + "epoch": 0.84, + "learning_rate": 6.48582151263166e-06, + "loss": 0.2995, + "step": 6591 + }, + { + "epoch": 0.84, + "learning_rate": 6.484831815429726e-06, + "loss": 0.3069, + "step": 6592 + }, + { + "epoch": 0.84, + "learning_rate": 6.483842054421263e-06, + "loss": 0.3329, + "step": 6593 + }, + { + "epoch": 0.84, + "learning_rate": 6.4828522296488014e-06, + "loss": 0.3067, + "step": 6594 + }, + { + "epoch": 0.84, + "learning_rate": 6.481862341154878e-06, + "loss": 0.3065, + "step": 6595 + }, + { + "epoch": 0.84, + "learning_rate": 6.480872388982028e-06, + "loss": 0.3094, + "step": 6596 + }, + { + "epoch": 0.84, + "learning_rate": 6.479882373172795e-06, + "loss": 0.34, + "step": 6597 + }, + { + "epoch": 0.84, + "learning_rate": 6.47889229376972e-06, + "loss": 0.3056, + "step": 6598 + }, + { + "epoch": 0.84, + "learning_rate": 6.477902150815347e-06, + "loss": 0.3255, + "step": 6599 + }, + { + "epoch": 0.84, + "learning_rate": 6.476911944352231e-06, + "loss": 0.3051, + "step": 6600 + }, + { + "epoch": 0.84, + "learning_rate": 6.475921674422917e-06, + "loss": 0.299, + "step": 6601 + }, + { + "epoch": 0.85, + "learning_rate": 6.474931341069963e-06, + "loss": 0.3219, + "step": 6602 + }, + { + "epoch": 0.85, + "learning_rate": 6.473940944335923e-06, + "loss": 0.3019, + "step": 6603 + }, + { + "epoch": 0.85, + "learning_rate": 6.472950484263359e-06, + "loss": 0.2904, + "step": 6604 + }, + { + "epoch": 0.85, + "learning_rate": 6.471959960894832e-06, + "loss": 0.3277, + "step": 6605 + }, + { + "epoch": 0.85, + "learning_rate": 6.470969374272908e-06, + "loss": 0.3351, + "step": 6606 + }, + { + "epoch": 0.85, + "learning_rate": 6.469978724440153e-06, + "loss": 0.3068, + "step": 6607 + }, + { + "epoch": 0.85, + "learning_rate": 6.4689880114391375e-06, + "loss": 0.304, + "step": 6608 + }, + { + "epoch": 0.85, + "learning_rate": 6.467997235312437e-06, + "loss": 0.3106, + "step": 6609 + }, + { + "epoch": 0.85, + "learning_rate": 6.4670063961026265e-06, + "loss": 0.3251, + "step": 6610 + }, + { + "epoch": 0.85, + "learning_rate": 6.466015493852283e-06, + "loss": 0.2967, + "step": 6611 + }, + { + "epoch": 0.85, + "learning_rate": 6.465024528603987e-06, + "loss": 0.3066, + "step": 6612 + }, + { + "epoch": 0.85, + "learning_rate": 6.464033500400327e-06, + "loss": 0.3188, + "step": 6613 + }, + { + "epoch": 0.85, + "learning_rate": 6.463042409283885e-06, + "loss": 0.2716, + "step": 6614 + }, + { + "epoch": 0.85, + "learning_rate": 6.462051255297255e-06, + "loss": 0.2816, + "step": 6615 + }, + { + "epoch": 0.85, + "learning_rate": 6.461060038483025e-06, + "loss": 0.297, + "step": 6616 + }, + { + "epoch": 0.85, + "learning_rate": 6.460068758883789e-06, + "loss": 0.3475, + "step": 6617 + }, + { + "epoch": 0.85, + "learning_rate": 6.4590774165421485e-06, + "loss": 0.2871, + "step": 6618 + }, + { + "epoch": 0.85, + "learning_rate": 6.458086011500703e-06, + "loss": 0.3197, + "step": 6619 + }, + { + "epoch": 0.85, + "learning_rate": 6.457094543802053e-06, + "loss": 0.3203, + "step": 6620 + }, + { + "epoch": 0.85, + "learning_rate": 6.456103013488804e-06, + "loss": 0.2806, + "step": 6621 + }, + { + "epoch": 0.85, + "learning_rate": 6.455111420603568e-06, + "loss": 0.3061, + "step": 6622 + }, + { + "epoch": 0.85, + "learning_rate": 6.454119765188951e-06, + "loss": 0.302, + "step": 6623 + }, + { + "epoch": 0.85, + "learning_rate": 6.453128047287573e-06, + "loss": 0.2924, + "step": 6624 + }, + { + "epoch": 0.85, + "learning_rate": 6.452136266942044e-06, + "loss": 0.3271, + "step": 6625 + }, + { + "epoch": 0.85, + "learning_rate": 6.451144424194985e-06, + "loss": 0.3022, + "step": 6626 + }, + { + "epoch": 0.85, + "learning_rate": 6.450152519089019e-06, + "loss": 0.3147, + "step": 6627 + }, + { + "epoch": 0.85, + "learning_rate": 6.449160551666769e-06, + "loss": 0.2785, + "step": 6628 + }, + { + "epoch": 0.85, + "learning_rate": 6.448168521970865e-06, + "loss": 0.3225, + "step": 6629 + }, + { + "epoch": 0.85, + "learning_rate": 6.447176430043931e-06, + "loss": 0.3176, + "step": 6630 + }, + { + "epoch": 0.85, + "learning_rate": 6.446184275928604e-06, + "loss": 0.3306, + "step": 6631 + }, + { + "epoch": 0.85, + "learning_rate": 6.445192059667518e-06, + "loss": 0.2907, + "step": 6632 + }, + { + "epoch": 0.85, + "learning_rate": 6.444199781303311e-06, + "loss": 0.2833, + "step": 6633 + }, + { + "epoch": 0.85, + "learning_rate": 6.443207440878624e-06, + "loss": 0.305, + "step": 6634 + }, + { + "epoch": 0.85, + "learning_rate": 6.442215038436097e-06, + "loss": 0.306, + "step": 6635 + }, + { + "epoch": 0.85, + "learning_rate": 6.441222574018378e-06, + "loss": 0.3056, + "step": 6636 + }, + { + "epoch": 0.85, + "learning_rate": 6.440230047668116e-06, + "loss": 0.3144, + "step": 6637 + }, + { + "epoch": 0.85, + "learning_rate": 6.4392374594279614e-06, + "loss": 0.3161, + "step": 6638 + }, + { + "epoch": 0.85, + "learning_rate": 6.438244809340568e-06, + "loss": 0.3021, + "step": 6639 + }, + { + "epoch": 0.85, + "learning_rate": 6.4372520974485916e-06, + "loss": 0.3165, + "step": 6640 + }, + { + "epoch": 0.85, + "learning_rate": 6.436259323794691e-06, + "loss": 0.2677, + "step": 6641 + }, + { + "epoch": 0.85, + "learning_rate": 6.43526648842153e-06, + "loss": 0.3004, + "step": 6642 + }, + { + "epoch": 0.85, + "learning_rate": 6.434273591371771e-06, + "loss": 0.2979, + "step": 6643 + }, + { + "epoch": 0.85, + "learning_rate": 6.43328063268808e-06, + "loss": 0.315, + "step": 6644 + }, + { + "epoch": 0.85, + "learning_rate": 6.432287612413131e-06, + "loss": 0.3596, + "step": 6645 + }, + { + "epoch": 0.85, + "learning_rate": 6.431294530589589e-06, + "loss": 0.3232, + "step": 6646 + }, + { + "epoch": 0.85, + "learning_rate": 6.4303013872601375e-06, + "loss": 0.3016, + "step": 6647 + }, + { + "epoch": 0.85, + "learning_rate": 6.4293081824674485e-06, + "loss": 0.306, + "step": 6648 + }, + { + "epoch": 0.85, + "learning_rate": 6.428314916254203e-06, + "loss": 0.3091, + "step": 6649 + }, + { + "epoch": 0.85, + "learning_rate": 6.427321588663085e-06, + "loss": 0.3218, + "step": 6650 + }, + { + "epoch": 0.85, + "learning_rate": 6.42632819973678e-06, + "loss": 0.3088, + "step": 6651 + }, + { + "epoch": 0.85, + "learning_rate": 6.425334749517975e-06, + "loss": 0.2988, + "step": 6652 + }, + { + "epoch": 0.85, + "learning_rate": 6.424341238049362e-06, + "loss": 0.3005, + "step": 6653 + }, + { + "epoch": 0.85, + "learning_rate": 6.423347665373633e-06, + "loss": 0.3199, + "step": 6654 + }, + { + "epoch": 0.85, + "learning_rate": 6.422354031533485e-06, + "loss": 0.3169, + "step": 6655 + }, + { + "epoch": 0.85, + "learning_rate": 6.421360336571618e-06, + "loss": 0.327, + "step": 6656 + }, + { + "epoch": 0.85, + "learning_rate": 6.42036658053073e-06, + "loss": 0.306, + "step": 6657 + }, + { + "epoch": 0.85, + "learning_rate": 6.419372763453529e-06, + "loss": 0.3024, + "step": 6658 + }, + { + "epoch": 0.85, + "learning_rate": 6.418378885382716e-06, + "loss": 0.3058, + "step": 6659 + }, + { + "epoch": 0.85, + "learning_rate": 6.417384946361005e-06, + "loss": 0.3258, + "step": 6660 + }, + { + "epoch": 0.85, + "learning_rate": 6.416390946431107e-06, + "loss": 0.3235, + "step": 6661 + }, + { + "epoch": 0.85, + "learning_rate": 6.4153968856357355e-06, + "loss": 0.2865, + "step": 6662 + }, + { + "epoch": 0.85, + "learning_rate": 6.414402764017607e-06, + "loss": 0.2859, + "step": 6663 + }, + { + "epoch": 0.85, + "learning_rate": 6.41340858161944e-06, + "loss": 0.3108, + "step": 6664 + }, + { + "epoch": 0.85, + "learning_rate": 6.412414338483961e-06, + "loss": 0.2579, + "step": 6665 + }, + { + "epoch": 0.85, + "learning_rate": 6.411420034653891e-06, + "loss": 0.323, + "step": 6666 + }, + { + "epoch": 0.85, + "learning_rate": 6.410425670171959e-06, + "loss": 0.3046, + "step": 6667 + }, + { + "epoch": 0.85, + "learning_rate": 6.409431245080894e-06, + "loss": 0.3111, + "step": 6668 + }, + { + "epoch": 0.85, + "learning_rate": 6.408436759423431e-06, + "loss": 0.3234, + "step": 6669 + }, + { + "epoch": 0.85, + "learning_rate": 6.4074422132423035e-06, + "loss": 0.3072, + "step": 6670 + }, + { + "epoch": 0.85, + "learning_rate": 6.406447606580248e-06, + "loss": 0.3149, + "step": 6671 + }, + { + "epoch": 0.85, + "learning_rate": 6.405452939480008e-06, + "loss": 0.3257, + "step": 6672 + }, + { + "epoch": 0.85, + "learning_rate": 6.404458211984324e-06, + "loss": 0.3052, + "step": 6673 + }, + { + "epoch": 0.85, + "learning_rate": 6.403463424135943e-06, + "loss": 0.2897, + "step": 6674 + }, + { + "epoch": 0.85, + "learning_rate": 6.402468575977614e-06, + "loss": 0.2986, + "step": 6675 + }, + { + "epoch": 0.85, + "learning_rate": 6.401473667552085e-06, + "loss": 0.3059, + "step": 6676 + }, + { + "epoch": 0.85, + "learning_rate": 6.400478698902112e-06, + "loss": 0.2986, + "step": 6677 + }, + { + "epoch": 0.85, + "learning_rate": 6.399483670070451e-06, + "loss": 0.302, + "step": 6678 + }, + { + "epoch": 0.85, + "learning_rate": 6.398488581099859e-06, + "loss": 0.3105, + "step": 6679 + }, + { + "epoch": 0.86, + "learning_rate": 6.3974934320330996e-06, + "loss": 0.2959, + "step": 6680 + }, + { + "epoch": 0.86, + "learning_rate": 6.396498222912933e-06, + "loss": 0.2882, + "step": 6681 + }, + { + "epoch": 0.86, + "learning_rate": 6.395502953782129e-06, + "loss": 0.3106, + "step": 6682 + }, + { + "epoch": 0.86, + "learning_rate": 6.394507624683455e-06, + "loss": 0.295, + "step": 6683 + }, + { + "epoch": 0.86, + "learning_rate": 6.393512235659681e-06, + "loss": 0.3506, + "step": 6684 + }, + { + "epoch": 0.86, + "learning_rate": 6.392516786753586e-06, + "loss": 0.3268, + "step": 6685 + }, + { + "epoch": 0.86, + "learning_rate": 6.391521278007939e-06, + "loss": 0.3098, + "step": 6686 + }, + { + "epoch": 0.86, + "learning_rate": 6.390525709465527e-06, + "loss": 0.3063, + "step": 6687 + }, + { + "epoch": 0.86, + "learning_rate": 6.389530081169126e-06, + "loss": 0.2963, + "step": 6688 + }, + { + "epoch": 0.86, + "learning_rate": 6.388534393161525e-06, + "loss": 0.2881, + "step": 6689 + }, + { + "epoch": 0.86, + "learning_rate": 6.38753864548551e-06, + "loss": 0.3168, + "step": 6690 + }, + { + "epoch": 0.86, + "learning_rate": 6.386542838183865e-06, + "loss": 0.3306, + "step": 6691 + }, + { + "epoch": 0.86, + "learning_rate": 6.385546971299389e-06, + "loss": 0.3155, + "step": 6692 + }, + { + "epoch": 0.86, + "learning_rate": 6.384551044874871e-06, + "loss": 0.2962, + "step": 6693 + }, + { + "epoch": 0.86, + "learning_rate": 6.383555058953115e-06, + "loss": 0.318, + "step": 6694 + }, + { + "epoch": 0.86, + "learning_rate": 6.382559013576914e-06, + "loss": 0.3251, + "step": 6695 + }, + { + "epoch": 0.86, + "learning_rate": 6.381562908789075e-06, + "loss": 0.2626, + "step": 6696 + }, + { + "epoch": 0.86, + "learning_rate": 6.380566744632399e-06, + "loss": 0.3083, + "step": 6697 + }, + { + "epoch": 0.86, + "learning_rate": 6.379570521149696e-06, + "loss": 0.3141, + "step": 6698 + }, + { + "epoch": 0.86, + "learning_rate": 6.378574238383776e-06, + "loss": 0.3242, + "step": 6699 + }, + { + "epoch": 0.86, + "learning_rate": 6.377577896377451e-06, + "loss": 0.3152, + "step": 6700 + }, + { + "epoch": 0.86, + "learning_rate": 6.3765814951735346e-06, + "loss": 0.312, + "step": 6701 + }, + { + "epoch": 0.86, + "learning_rate": 6.375585034814845e-06, + "loss": 0.3204, + "step": 6702 + }, + { + "epoch": 0.86, + "learning_rate": 6.374588515344204e-06, + "loss": 0.3127, + "step": 6703 + }, + { + "epoch": 0.86, + "learning_rate": 6.373591936804433e-06, + "loss": 0.3033, + "step": 6704 + }, + { + "epoch": 0.86, + "learning_rate": 6.372595299238357e-06, + "loss": 0.284, + "step": 6705 + }, + { + "epoch": 0.86, + "learning_rate": 6.3715986026888046e-06, + "loss": 0.2888, + "step": 6706 + }, + { + "epoch": 0.86, + "learning_rate": 6.370601847198606e-06, + "loss": 0.2847, + "step": 6707 + }, + { + "epoch": 0.86, + "learning_rate": 6.3696050328105915e-06, + "loss": 0.2985, + "step": 6708 + }, + { + "epoch": 0.86, + "learning_rate": 6.3686081595676e-06, + "loss": 0.2944, + "step": 6709 + }, + { + "epoch": 0.86, + "learning_rate": 6.367611227512468e-06, + "loss": 0.308, + "step": 6710 + }, + { + "epoch": 0.86, + "learning_rate": 6.366614236688034e-06, + "loss": 0.3184, + "step": 6711 + }, + { + "epoch": 0.86, + "learning_rate": 6.365617187137144e-06, + "loss": 0.2896, + "step": 6712 + }, + { + "epoch": 0.86, + "learning_rate": 6.3646200789026426e-06, + "loss": 0.3037, + "step": 6713 + }, + { + "epoch": 0.86, + "learning_rate": 6.3636229120273766e-06, + "loss": 0.3152, + "step": 6714 + }, + { + "epoch": 0.86, + "learning_rate": 6.362625686554196e-06, + "loss": 0.3051, + "step": 6715 + }, + { + "epoch": 0.86, + "learning_rate": 6.361628402525956e-06, + "loss": 0.3194, + "step": 6716 + }, + { + "epoch": 0.86, + "learning_rate": 6.360631059985512e-06, + "loss": 0.3672, + "step": 6717 + }, + { + "epoch": 0.86, + "learning_rate": 6.35963365897572e-06, + "loss": 0.3163, + "step": 6718 + }, + { + "epoch": 0.86, + "learning_rate": 6.3586361995394415e-06, + "loss": 0.3172, + "step": 6719 + }, + { + "epoch": 0.86, + "learning_rate": 6.35763868171954e-06, + "loss": 0.304, + "step": 6720 + }, + { + "epoch": 0.86, + "learning_rate": 6.3566411055588806e-06, + "loss": 0.2918, + "step": 6721 + }, + { + "epoch": 0.86, + "learning_rate": 6.355643471100332e-06, + "loss": 0.3111, + "step": 6722 + }, + { + "epoch": 0.86, + "learning_rate": 6.354645778386763e-06, + "loss": 0.3241, + "step": 6723 + }, + { + "epoch": 0.86, + "learning_rate": 6.353648027461048e-06, + "loss": 0.3255, + "step": 6724 + }, + { + "epoch": 0.86, + "learning_rate": 6.3526502183660646e-06, + "loss": 0.3122, + "step": 6725 + }, + { + "epoch": 0.86, + "learning_rate": 6.351652351144687e-06, + "loss": 0.3075, + "step": 6726 + }, + { + "epoch": 0.86, + "learning_rate": 6.350654425839799e-06, + "loss": 0.3165, + "step": 6727 + }, + { + "epoch": 0.86, + "learning_rate": 6.349656442494281e-06, + "loss": 0.3118, + "step": 6728 + }, + { + "epoch": 0.86, + "learning_rate": 6.348658401151018e-06, + "loss": 0.325, + "step": 6729 + }, + { + "epoch": 0.86, + "learning_rate": 6.347660301852903e-06, + "loss": 0.3051, + "step": 6730 + }, + { + "epoch": 0.86, + "learning_rate": 6.346662144642823e-06, + "loss": 0.3157, + "step": 6731 + }, + { + "epoch": 0.86, + "learning_rate": 6.345663929563672e-06, + "loss": 0.2992, + "step": 6732 + }, + { + "epoch": 0.86, + "learning_rate": 6.344665656658342e-06, + "loss": 0.302, + "step": 6733 + }, + { + "epoch": 0.86, + "learning_rate": 6.343667325969736e-06, + "loss": 0.3114, + "step": 6734 + }, + { + "epoch": 0.86, + "learning_rate": 6.342668937540752e-06, + "loss": 0.3114, + "step": 6735 + }, + { + "epoch": 0.86, + "learning_rate": 6.341670491414294e-06, + "loss": 0.3159, + "step": 6736 + }, + { + "epoch": 0.86, + "learning_rate": 6.3406719876332675e-06, + "loss": 0.3302, + "step": 6737 + }, + { + "epoch": 0.86, + "learning_rate": 6.339673426240578e-06, + "loss": 0.3123, + "step": 6738 + }, + { + "epoch": 0.86, + "learning_rate": 6.3386748072791395e-06, + "loss": 0.3054, + "step": 6739 + }, + { + "epoch": 0.86, + "learning_rate": 6.337676130791861e-06, + "loss": 0.3049, + "step": 6740 + }, + { + "epoch": 0.86, + "learning_rate": 6.336677396821663e-06, + "loss": 0.3098, + "step": 6741 + }, + { + "epoch": 0.86, + "learning_rate": 6.3356786054114585e-06, + "loss": 0.3173, + "step": 6742 + }, + { + "epoch": 0.86, + "learning_rate": 6.3346797566041695e-06, + "loss": 0.2977, + "step": 6743 + }, + { + "epoch": 0.86, + "learning_rate": 6.33368085044272e-06, + "loss": 0.3062, + "step": 6744 + }, + { + "epoch": 0.86, + "learning_rate": 6.332681886970032e-06, + "loss": 0.3048, + "step": 6745 + }, + { + "epoch": 0.86, + "learning_rate": 6.331682866229039e-06, + "loss": 0.32, + "step": 6746 + }, + { + "epoch": 0.86, + "learning_rate": 6.3306837882626635e-06, + "loss": 0.3305, + "step": 6747 + }, + { + "epoch": 0.86, + "learning_rate": 6.3296846531138445e-06, + "loss": 0.3044, + "step": 6748 + }, + { + "epoch": 0.86, + "learning_rate": 6.328685460825512e-06, + "loss": 0.2933, + "step": 6749 + }, + { + "epoch": 0.86, + "learning_rate": 6.327686211440609e-06, + "loss": 0.3235, + "step": 6750 + }, + { + "epoch": 0.86, + "learning_rate": 6.32668690500207e-06, + "loss": 0.3313, + "step": 6751 + }, + { + "epoch": 0.86, + "learning_rate": 6.325687541552843e-06, + "loss": 0.3045, + "step": 6752 + }, + { + "epoch": 0.86, + "learning_rate": 6.324688121135868e-06, + "loss": 0.3039, + "step": 6753 + }, + { + "epoch": 0.86, + "learning_rate": 6.323688643794094e-06, + "loss": 0.3175, + "step": 6754 + }, + { + "epoch": 0.86, + "learning_rate": 6.322689109570472e-06, + "loss": 0.3088, + "step": 6755 + }, + { + "epoch": 0.86, + "learning_rate": 6.3216895185079515e-06, + "loss": 0.3122, + "step": 6756 + }, + { + "epoch": 0.86, + "learning_rate": 6.3206898706494915e-06, + "loss": 0.3141, + "step": 6757 + }, + { + "epoch": 0.87, + "learning_rate": 6.3196901660380436e-06, + "loss": 0.3044, + "step": 6758 + }, + { + "epoch": 0.87, + "learning_rate": 6.318690404716572e-06, + "loss": 0.3035, + "step": 6759 + }, + { + "epoch": 0.87, + "learning_rate": 6.317690586728036e-06, + "loss": 0.2923, + "step": 6760 + }, + { + "epoch": 0.87, + "learning_rate": 6.316690712115401e-06, + "loss": 0.3141, + "step": 6761 + }, + { + "epoch": 0.87, + "learning_rate": 6.315690780921634e-06, + "loss": 0.3012, + "step": 6762 + }, + { + "epoch": 0.87, + "learning_rate": 6.314690793189703e-06, + "loss": 0.2719, + "step": 6763 + }, + { + "epoch": 0.87, + "learning_rate": 6.313690748962582e-06, + "loss": 0.3288, + "step": 6764 + }, + { + "epoch": 0.87, + "learning_rate": 6.312690648283243e-06, + "loss": 0.3103, + "step": 6765 + }, + { + "epoch": 0.87, + "learning_rate": 6.311690491194664e-06, + "loss": 0.3063, + "step": 6766 + }, + { + "epoch": 0.87, + "learning_rate": 6.310690277739821e-06, + "loss": 0.339, + "step": 6767 + }, + { + "epoch": 0.87, + "learning_rate": 6.3096900079617e-06, + "loss": 0.2934, + "step": 6768 + }, + { + "epoch": 0.87, + "learning_rate": 6.3086896819032814e-06, + "loss": 0.2938, + "step": 6769 + }, + { + "epoch": 0.87, + "learning_rate": 6.307689299607555e-06, + "loss": 0.3284, + "step": 6770 + }, + { + "epoch": 0.87, + "learning_rate": 6.306688861117505e-06, + "loss": 0.2986, + "step": 6771 + }, + { + "epoch": 0.87, + "learning_rate": 6.305688366476124e-06, + "loss": 0.3006, + "step": 6772 + }, + { + "epoch": 0.87, + "learning_rate": 6.304687815726406e-06, + "loss": 0.2906, + "step": 6773 + }, + { + "epoch": 0.87, + "learning_rate": 6.303687208911348e-06, + "loss": 0.3032, + "step": 6774 + }, + { + "epoch": 0.87, + "learning_rate": 6.302686546073946e-06, + "loss": 0.346, + "step": 6775 + }, + { + "epoch": 0.87, + "learning_rate": 6.301685827257202e-06, + "loss": 0.325, + "step": 6776 + }, + { + "epoch": 0.87, + "learning_rate": 6.300685052504119e-06, + "loss": 0.3227, + "step": 6777 + }, + { + "epoch": 0.87, + "learning_rate": 6.299684221857705e-06, + "loss": 0.3119, + "step": 6778 + }, + { + "epoch": 0.87, + "learning_rate": 6.298683335360962e-06, + "loss": 0.3191, + "step": 6779 + }, + { + "epoch": 0.87, + "learning_rate": 6.297682393056906e-06, + "loss": 0.2911, + "step": 6780 + }, + { + "epoch": 0.87, + "learning_rate": 6.296681394988546e-06, + "loss": 0.3099, + "step": 6781 + }, + { + "epoch": 0.87, + "learning_rate": 6.2956803411989e-06, + "loss": 0.2807, + "step": 6782 + }, + { + "epoch": 0.87, + "learning_rate": 6.294679231730983e-06, + "loss": 0.3041, + "step": 6783 + }, + { + "epoch": 0.87, + "learning_rate": 6.293678066627816e-06, + "loss": 0.3281, + "step": 6784 + }, + { + "epoch": 0.87, + "learning_rate": 6.292676845932422e-06, + "loss": 0.3231, + "step": 6785 + }, + { + "epoch": 0.87, + "learning_rate": 6.291675569687824e-06, + "loss": 0.331, + "step": 6786 + }, + { + "epoch": 0.87, + "learning_rate": 6.290674237937051e-06, + "loss": 0.3087, + "step": 6787 + }, + { + "epoch": 0.87, + "learning_rate": 6.289672850723132e-06, + "loss": 0.3014, + "step": 6788 + }, + { + "epoch": 0.87, + "learning_rate": 6.288671408089098e-06, + "loss": 0.2836, + "step": 6789 + }, + { + "epoch": 0.87, + "learning_rate": 6.2876699100779815e-06, + "loss": 0.3168, + "step": 6790 + }, + { + "epoch": 0.87, + "learning_rate": 6.2866683567328235e-06, + "loss": 0.3201, + "step": 6791 + }, + { + "epoch": 0.87, + "learning_rate": 6.285666748096659e-06, + "loss": 0.3222, + "step": 6792 + }, + { + "epoch": 0.87, + "learning_rate": 6.284665084212533e-06, + "loss": 0.3028, + "step": 6793 + }, + { + "epoch": 0.87, + "learning_rate": 6.283663365123486e-06, + "loss": 0.2984, + "step": 6794 + }, + { + "epoch": 0.87, + "learning_rate": 6.282661590872565e-06, + "loss": 0.3054, + "step": 6795 + }, + { + "epoch": 0.87, + "learning_rate": 6.281659761502819e-06, + "loss": 0.2956, + "step": 6796 + }, + { + "epoch": 0.87, + "learning_rate": 6.2806578770573e-06, + "loss": 0.3192, + "step": 6797 + }, + { + "epoch": 0.87, + "learning_rate": 6.279655937579058e-06, + "loss": 0.2866, + "step": 6798 + }, + { + "epoch": 0.87, + "learning_rate": 6.278653943111152e-06, + "loss": 0.3004, + "step": 6799 + }, + { + "epoch": 0.87, + "learning_rate": 6.277651893696637e-06, + "loss": 0.3148, + "step": 6800 + }, + { + "epoch": 0.87, + "learning_rate": 6.276649789378575e-06, + "loss": 0.2993, + "step": 6801 + }, + { + "epoch": 0.87, + "learning_rate": 6.275647630200029e-06, + "loss": 0.3055, + "step": 6802 + }, + { + "epoch": 0.87, + "learning_rate": 6.274645416204062e-06, + "loss": 0.2939, + "step": 6803 + }, + { + "epoch": 0.87, + "learning_rate": 6.273643147433743e-06, + "loss": 0.303, + "step": 6804 + }, + { + "epoch": 0.87, + "learning_rate": 6.272640823932141e-06, + "loss": 0.3361, + "step": 6805 + }, + { + "epoch": 0.87, + "learning_rate": 6.271638445742332e-06, + "loss": 0.2984, + "step": 6806 + }, + { + "epoch": 0.87, + "learning_rate": 6.270636012907383e-06, + "loss": 0.3234, + "step": 6807 + }, + { + "epoch": 0.87, + "learning_rate": 6.269633525470376e-06, + "loss": 0.3033, + "step": 6808 + }, + { + "epoch": 0.87, + "learning_rate": 6.268630983474388e-06, + "loss": 0.3031, + "step": 6809 + }, + { + "epoch": 0.87, + "learning_rate": 6.267628386962502e-06, + "loss": 0.3391, + "step": 6810 + }, + { + "epoch": 0.87, + "learning_rate": 6.266625735977802e-06, + "loss": 0.2785, + "step": 6811 + }, + { + "epoch": 0.87, + "learning_rate": 6.265623030563372e-06, + "loss": 0.2979, + "step": 6812 + }, + { + "epoch": 0.87, + "learning_rate": 6.264620270762302e-06, + "loss": 0.2948, + "step": 6813 + }, + { + "epoch": 0.87, + "learning_rate": 6.263617456617681e-06, + "loss": 0.314, + "step": 6814 + }, + { + "epoch": 0.87, + "learning_rate": 6.262614588172607e-06, + "loss": 0.3308, + "step": 6815 + }, + { + "epoch": 0.87, + "learning_rate": 6.261611665470168e-06, + "loss": 0.3201, + "step": 6816 + }, + { + "epoch": 0.87, + "learning_rate": 6.260608688553469e-06, + "loss": 0.2826, + "step": 6817 + }, + { + "epoch": 0.87, + "learning_rate": 6.259605657465607e-06, + "loss": 0.3132, + "step": 6818 + }, + { + "epoch": 0.87, + "learning_rate": 6.258602572249683e-06, + "loss": 0.3289, + "step": 6819 + }, + { + "epoch": 0.87, + "learning_rate": 6.2575994329488045e-06, + "loss": 0.2996, + "step": 6820 + }, + { + "epoch": 0.87, + "learning_rate": 6.2565962396060774e-06, + "loss": 0.3213, + "step": 6821 + }, + { + "epoch": 0.87, + "learning_rate": 6.255592992264612e-06, + "loss": 0.2927, + "step": 6822 + }, + { + "epoch": 0.87, + "learning_rate": 6.254589690967517e-06, + "loss": 0.3064, + "step": 6823 + }, + { + "epoch": 0.87, + "learning_rate": 6.2535863357579105e-06, + "loss": 0.2955, + "step": 6824 + }, + { + "epoch": 0.87, + "learning_rate": 6.252582926678908e-06, + "loss": 0.3267, + "step": 6825 + }, + { + "epoch": 0.87, + "learning_rate": 6.2515794637736275e-06, + "loss": 0.2961, + "step": 6826 + }, + { + "epoch": 0.87, + "learning_rate": 6.250575947085189e-06, + "loss": 0.3297, + "step": 6827 + }, + { + "epoch": 0.87, + "learning_rate": 6.2495723766567165e-06, + "loss": 0.3154, + "step": 6828 + }, + { + "epoch": 0.87, + "learning_rate": 6.248568752531337e-06, + "loss": 0.3093, + "step": 6829 + }, + { + "epoch": 0.87, + "learning_rate": 6.247565074752177e-06, + "loss": 0.3116, + "step": 6830 + }, + { + "epoch": 0.87, + "learning_rate": 6.246561343362368e-06, + "loss": 0.292, + "step": 6831 + }, + { + "epoch": 0.87, + "learning_rate": 6.24555755840504e-06, + "loss": 0.2895, + "step": 6832 + }, + { + "epoch": 0.87, + "learning_rate": 6.244553719923332e-06, + "loss": 0.3369, + "step": 6833 + }, + { + "epoch": 0.87, + "learning_rate": 6.243549827960378e-06, + "loss": 0.3147, + "step": 6834 + }, + { + "epoch": 0.87, + "learning_rate": 6.242545882559318e-06, + "loss": 0.3105, + "step": 6835 + }, + { + "epoch": 0.88, + "learning_rate": 6.241541883763294e-06, + "loss": 0.3045, + "step": 6836 + }, + { + "epoch": 0.88, + "learning_rate": 6.240537831615451e-06, + "loss": 0.3073, + "step": 6837 + }, + { + "epoch": 0.88, + "learning_rate": 6.239533726158934e-06, + "loss": 0.3019, + "step": 6838 + }, + { + "epoch": 0.88, + "learning_rate": 6.238529567436892e-06, + "loss": 0.3096, + "step": 6839 + }, + { + "epoch": 0.88, + "learning_rate": 6.2375253554924766e-06, + "loss": 0.3448, + "step": 6840 + }, + { + "epoch": 0.88, + "learning_rate": 6.23652109036884e-06, + "loss": 0.314, + "step": 6841 + }, + { + "epoch": 0.88, + "learning_rate": 6.235516772109138e-06, + "loss": 0.3155, + "step": 6842 + }, + { + "epoch": 0.88, + "learning_rate": 6.23451240075653e-06, + "loss": 0.3354, + "step": 6843 + }, + { + "epoch": 0.88, + "learning_rate": 6.233507976354174e-06, + "loss": 0.3104, + "step": 6844 + }, + { + "epoch": 0.88, + "learning_rate": 6.2325034989452335e-06, + "loss": 0.3309, + "step": 6845 + }, + { + "epoch": 0.88, + "learning_rate": 6.231498968572872e-06, + "loss": 0.297, + "step": 6846 + }, + { + "epoch": 0.88, + "learning_rate": 6.230494385280257e-06, + "loss": 0.3044, + "step": 6847 + }, + { + "epoch": 0.88, + "learning_rate": 6.229489749110559e-06, + "loss": 0.3016, + "step": 6848 + }, + { + "epoch": 0.88, + "learning_rate": 6.228485060106948e-06, + "loss": 0.294, + "step": 6849 + }, + { + "epoch": 0.88, + "learning_rate": 6.227480318312597e-06, + "loss": 0.3374, + "step": 6850 + }, + { + "epoch": 0.88, + "learning_rate": 6.226475523770683e-06, + "loss": 0.3191, + "step": 6851 + }, + { + "epoch": 0.88, + "learning_rate": 6.225470676524385e-06, + "loss": 0.3143, + "step": 6852 + }, + { + "epoch": 0.88, + "learning_rate": 6.224465776616883e-06, + "loss": 0.3108, + "step": 6853 + }, + { + "epoch": 0.88, + "learning_rate": 6.223460824091358e-06, + "loss": 0.275, + "step": 6854 + }, + { + "epoch": 0.88, + "learning_rate": 6.222455818990998e-06, + "loss": 0.297, + "step": 6855 + }, + { + "epoch": 0.88, + "learning_rate": 6.221450761358988e-06, + "loss": 0.3114, + "step": 6856 + }, + { + "epoch": 0.88, + "learning_rate": 6.220445651238519e-06, + "loss": 0.2919, + "step": 6857 + }, + { + "epoch": 0.88, + "learning_rate": 6.2194404886727835e-06, + "loss": 0.3182, + "step": 6858 + }, + { + "epoch": 0.88, + "learning_rate": 6.218435273704973e-06, + "loss": 0.3091, + "step": 6859 + }, + { + "epoch": 0.88, + "learning_rate": 6.217430006378285e-06, + "loss": 0.3146, + "step": 6860 + }, + { + "epoch": 0.88, + "learning_rate": 6.216424686735917e-06, + "loss": 0.3385, + "step": 6861 + }, + { + "epoch": 0.88, + "learning_rate": 6.215419314821074e-06, + "loss": 0.2871, + "step": 6862 + }, + { + "epoch": 0.88, + "learning_rate": 6.214413890676956e-06, + "loss": 0.3268, + "step": 6863 + }, + { + "epoch": 0.88, + "learning_rate": 6.213408414346765e-06, + "loss": 0.3084, + "step": 6864 + }, + { + "epoch": 0.88, + "learning_rate": 6.212402885873715e-06, + "loss": 0.2987, + "step": 6865 + }, + { + "epoch": 0.88, + "learning_rate": 6.211397305301011e-06, + "loss": 0.2665, + "step": 6866 + }, + { + "epoch": 0.88, + "learning_rate": 6.210391672671869e-06, + "loss": 0.2925, + "step": 6867 + }, + { + "epoch": 0.88, + "learning_rate": 6.2093859880295e-06, + "loss": 0.3005, + "step": 6868 + }, + { + "epoch": 0.88, + "learning_rate": 6.208380251417122e-06, + "loss": 0.327, + "step": 6869 + }, + { + "epoch": 0.88, + "learning_rate": 6.207374462877953e-06, + "loss": 0.3465, + "step": 6870 + }, + { + "epoch": 0.88, + "learning_rate": 6.2063686224552144e-06, + "loss": 0.3208, + "step": 6871 + }, + { + "epoch": 0.88, + "learning_rate": 6.205362730192131e-06, + "loss": 0.2905, + "step": 6872 + }, + { + "epoch": 0.88, + "learning_rate": 6.2043567861319245e-06, + "loss": 0.2976, + "step": 6873 + }, + { + "epoch": 0.88, + "learning_rate": 6.203350790317825e-06, + "loss": 0.3168, + "step": 6874 + }, + { + "epoch": 0.88, + "learning_rate": 6.2023447427930615e-06, + "loss": 0.3198, + "step": 6875 + }, + { + "epoch": 0.88, + "learning_rate": 6.201338643600869e-06, + "loss": 0.2982, + "step": 6876 + }, + { + "epoch": 0.88, + "learning_rate": 6.2003324927844765e-06, + "loss": 0.2876, + "step": 6877 + }, + { + "epoch": 0.88, + "learning_rate": 6.199326290387126e-06, + "loss": 0.3109, + "step": 6878 + }, + { + "epoch": 0.88, + "learning_rate": 6.198320036452051e-06, + "loss": 0.3036, + "step": 6879 + }, + { + "epoch": 0.88, + "learning_rate": 6.197313731022497e-06, + "loss": 0.3083, + "step": 6880 + }, + { + "epoch": 0.88, + "learning_rate": 6.196307374141707e-06, + "loss": 0.2924, + "step": 6881 + }, + { + "epoch": 0.88, + "learning_rate": 6.195300965852923e-06, + "loss": 0.3239, + "step": 6882 + }, + { + "epoch": 0.88, + "learning_rate": 6.194294506199394e-06, + "loss": 0.3074, + "step": 6883 + }, + { + "epoch": 0.88, + "learning_rate": 6.193287995224371e-06, + "loss": 0.3133, + "step": 6884 + }, + { + "epoch": 0.88, + "learning_rate": 6.192281432971104e-06, + "loss": 0.2613, + "step": 6885 + }, + { + "epoch": 0.88, + "learning_rate": 6.19127481948285e-06, + "loss": 0.3022, + "step": 6886 + }, + { + "epoch": 0.88, + "learning_rate": 6.1902681548028646e-06, + "loss": 0.3035, + "step": 6887 + }, + { + "epoch": 0.88, + "learning_rate": 6.189261438974403e-06, + "loss": 0.3095, + "step": 6888 + }, + { + "epoch": 0.88, + "learning_rate": 6.18825467204073e-06, + "loss": 0.3013, + "step": 6889 + }, + { + "epoch": 0.88, + "learning_rate": 6.187247854045109e-06, + "loss": 0.3215, + "step": 6890 + }, + { + "epoch": 0.88, + "learning_rate": 6.186240985030802e-06, + "loss": 0.2813, + "step": 6891 + }, + { + "epoch": 0.88, + "learning_rate": 6.1852340650410784e-06, + "loss": 0.3245, + "step": 6892 + }, + { + "epoch": 0.88, + "learning_rate": 6.184227094119207e-06, + "loss": 0.2939, + "step": 6893 + }, + { + "epoch": 0.88, + "learning_rate": 6.183220072308459e-06, + "loss": 0.3, + "step": 6894 + }, + { + "epoch": 0.88, + "learning_rate": 6.1822129996521105e-06, + "loss": 0.2788, + "step": 6895 + }, + { + "epoch": 0.88, + "learning_rate": 6.181205876193437e-06, + "loss": 0.3308, + "step": 6896 + }, + { + "epoch": 0.88, + "learning_rate": 6.180198701975715e-06, + "loss": 0.3004, + "step": 6897 + }, + { + "epoch": 0.88, + "learning_rate": 6.179191477042227e-06, + "loss": 0.3219, + "step": 6898 + }, + { + "epoch": 0.88, + "learning_rate": 6.178184201436256e-06, + "loss": 0.3188, + "step": 6899 + }, + { + "epoch": 0.88, + "learning_rate": 6.177176875201086e-06, + "loss": 0.3114, + "step": 6900 + }, + { + "epoch": 0.88, + "learning_rate": 6.176169498380001e-06, + "loss": 0.2768, + "step": 6901 + }, + { + "epoch": 0.88, + "learning_rate": 6.175162071016295e-06, + "loss": 0.3112, + "step": 6902 + }, + { + "epoch": 0.88, + "learning_rate": 6.174154593153258e-06, + "loss": 0.3216, + "step": 6903 + }, + { + "epoch": 0.88, + "learning_rate": 6.173147064834183e-06, + "loss": 0.3153, + "step": 6904 + }, + { + "epoch": 0.88, + "learning_rate": 6.1721394861023665e-06, + "loss": 0.3032, + "step": 6905 + }, + { + "epoch": 0.88, + "learning_rate": 6.171131857001104e-06, + "loss": 0.2941, + "step": 6906 + }, + { + "epoch": 0.88, + "learning_rate": 6.170124177573698e-06, + "loss": 0.3148, + "step": 6907 + }, + { + "epoch": 0.88, + "learning_rate": 6.169116447863451e-06, + "loss": 0.302, + "step": 6908 + }, + { + "epoch": 0.88, + "learning_rate": 6.168108667913666e-06, + "loss": 0.3309, + "step": 6909 + }, + { + "epoch": 0.88, + "learning_rate": 6.16710083776765e-06, + "loss": 0.2989, + "step": 6910 + }, + { + "epoch": 0.88, + "learning_rate": 6.1660929574687115e-06, + "loss": 0.296, + "step": 6911 + }, + { + "epoch": 0.88, + "learning_rate": 6.165085027060162e-06, + "loss": 0.3224, + "step": 6912 + }, + { + "epoch": 0.88, + "learning_rate": 6.164077046585314e-06, + "loss": 0.2672, + "step": 6913 + }, + { + "epoch": 0.88, + "learning_rate": 6.163069016087483e-06, + "loss": 0.3211, + "step": 6914 + }, + { + "epoch": 0.89, + "learning_rate": 6.162060935609985e-06, + "loss": 0.2899, + "step": 6915 + }, + { + "epoch": 0.89, + "learning_rate": 6.161052805196141e-06, + "loss": 0.3082, + "step": 6916 + }, + { + "epoch": 0.89, + "learning_rate": 6.160044624889272e-06, + "loss": 0.3038, + "step": 6917 + }, + { + "epoch": 0.89, + "learning_rate": 6.1590363947327025e-06, + "loss": 0.3178, + "step": 6918 + }, + { + "epoch": 0.89, + "learning_rate": 6.158028114769758e-06, + "loss": 0.292, + "step": 6919 + }, + { + "epoch": 0.89, + "learning_rate": 6.157019785043765e-06, + "loss": 0.3093, + "step": 6920 + }, + { + "epoch": 0.89, + "learning_rate": 6.156011405598057e-06, + "loss": 0.317, + "step": 6921 + }, + { + "epoch": 0.89, + "learning_rate": 6.155002976475962e-06, + "loss": 0.2886, + "step": 6922 + }, + { + "epoch": 0.89, + "learning_rate": 6.15399449772082e-06, + "loss": 0.3151, + "step": 6923 + }, + { + "epoch": 0.89, + "learning_rate": 6.152985969375962e-06, + "loss": 0.3136, + "step": 6924 + }, + { + "epoch": 0.89, + "learning_rate": 6.151977391484729e-06, + "loss": 0.2975, + "step": 6925 + }, + { + "epoch": 0.89, + "learning_rate": 6.150968764090461e-06, + "loss": 0.2959, + "step": 6926 + }, + { + "epoch": 0.89, + "learning_rate": 6.149960087236505e-06, + "loss": 0.3071, + "step": 6927 + }, + { + "epoch": 0.89, + "learning_rate": 6.1489513609662025e-06, + "loss": 0.3327, + "step": 6928 + }, + { + "epoch": 0.89, + "learning_rate": 6.147942585322898e-06, + "loss": 0.3346, + "step": 6929 + }, + { + "epoch": 0.89, + "learning_rate": 6.146933760349947e-06, + "loss": 0.3229, + "step": 6930 + }, + { + "epoch": 0.89, + "learning_rate": 6.145924886090695e-06, + "loss": 0.2985, + "step": 6931 + }, + { + "epoch": 0.89, + "learning_rate": 6.144915962588503e-06, + "loss": 0.3154, + "step": 6932 + }, + { + "epoch": 0.89, + "learning_rate": 6.143906989886718e-06, + "loss": 0.3073, + "step": 6933 + }, + { + "epoch": 0.89, + "learning_rate": 6.142897968028704e-06, + "loss": 0.309, + "step": 6934 + }, + { + "epoch": 0.89, + "learning_rate": 6.141888897057817e-06, + "loss": 0.2912, + "step": 6935 + }, + { + "epoch": 0.89, + "learning_rate": 6.140879777017423e-06, + "loss": 0.2827, + "step": 6936 + }, + { + "epoch": 0.89, + "learning_rate": 6.139870607950885e-06, + "loss": 0.2917, + "step": 6937 + }, + { + "epoch": 0.89, + "learning_rate": 6.138861389901566e-06, + "loss": 0.3412, + "step": 6938 + }, + { + "epoch": 0.89, + "learning_rate": 6.137852122912839e-06, + "loss": 0.3328, + "step": 6939 + }, + { + "epoch": 0.89, + "learning_rate": 6.136842807028069e-06, + "loss": 0.3269, + "step": 6940 + }, + { + "epoch": 0.89, + "learning_rate": 6.135833442290634e-06, + "loss": 0.2917, + "step": 6941 + }, + { + "epoch": 0.89, + "learning_rate": 6.134824028743906e-06, + "loss": 0.3088, + "step": 6942 + }, + { + "epoch": 0.89, + "learning_rate": 6.133814566431262e-06, + "loss": 0.3032, + "step": 6943 + }, + { + "epoch": 0.89, + "learning_rate": 6.1328050553960804e-06, + "loss": 0.3021, + "step": 6944 + }, + { + "epoch": 0.89, + "learning_rate": 6.131795495681743e-06, + "loss": 0.3122, + "step": 6945 + }, + { + "epoch": 0.89, + "learning_rate": 6.130785887331633e-06, + "loss": 0.3106, + "step": 6946 + }, + { + "epoch": 0.89, + "learning_rate": 6.129776230389135e-06, + "loss": 0.2952, + "step": 6947 + }, + { + "epoch": 0.89, + "learning_rate": 6.128766524897636e-06, + "loss": 0.2843, + "step": 6948 + }, + { + "epoch": 0.89, + "learning_rate": 6.1277567709005245e-06, + "loss": 0.3021, + "step": 6949 + }, + { + "epoch": 0.89, + "learning_rate": 6.126746968441195e-06, + "loss": 0.3054, + "step": 6950 + }, + { + "epoch": 0.89, + "learning_rate": 6.1257371175630375e-06, + "loss": 0.2772, + "step": 6951 + }, + { + "epoch": 0.89, + "learning_rate": 6.124727218309449e-06, + "loss": 0.2918, + "step": 6952 + }, + { + "epoch": 0.89, + "learning_rate": 6.123717270723827e-06, + "loss": 0.3032, + "step": 6953 + }, + { + "epoch": 0.89, + "learning_rate": 6.122707274849572e-06, + "loss": 0.3075, + "step": 6954 + }, + { + "epoch": 0.89, + "learning_rate": 6.121697230730084e-06, + "loss": 0.312, + "step": 6955 + }, + { + "epoch": 0.89, + "learning_rate": 6.120687138408768e-06, + "loss": 0.2968, + "step": 6956 + }, + { + "epoch": 0.89, + "learning_rate": 6.11967699792903e-06, + "loss": 0.29, + "step": 6957 + }, + { + "epoch": 0.89, + "learning_rate": 6.118666809334277e-06, + "loss": 0.349, + "step": 6958 + }, + { + "epoch": 0.89, + "learning_rate": 6.117656572667921e-06, + "loss": 0.304, + "step": 6959 + }, + { + "epoch": 0.89, + "learning_rate": 6.116646287973374e-06, + "loss": 0.3409, + "step": 6960 + }, + { + "epoch": 0.89, + "learning_rate": 6.115635955294047e-06, + "loss": 0.2913, + "step": 6961 + }, + { + "epoch": 0.89, + "learning_rate": 6.114625574673359e-06, + "loss": 0.3221, + "step": 6962 + }, + { + "epoch": 0.89, + "learning_rate": 6.1136151461547266e-06, + "loss": 0.2956, + "step": 6963 + }, + { + "epoch": 0.89, + "learning_rate": 6.112604669781572e-06, + "loss": 0.33, + "step": 6964 + }, + { + "epoch": 0.89, + "learning_rate": 6.111594145597319e-06, + "loss": 0.2919, + "step": 6965 + }, + { + "epoch": 0.89, + "learning_rate": 6.1105835736453874e-06, + "loss": 0.2937, + "step": 6966 + }, + { + "epoch": 0.89, + "learning_rate": 6.109572953969206e-06, + "loss": 0.3034, + "step": 6967 + }, + { + "epoch": 0.89, + "learning_rate": 6.108562286612204e-06, + "loss": 0.2946, + "step": 6968 + }, + { + "epoch": 0.89, + "learning_rate": 6.107551571617813e-06, + "loss": 0.2643, + "step": 6969 + }, + { + "epoch": 0.89, + "learning_rate": 6.106540809029463e-06, + "loss": 0.3062, + "step": 6970 + }, + { + "epoch": 0.89, + "learning_rate": 6.105529998890589e-06, + "loss": 0.2956, + "step": 6971 + }, + { + "epoch": 0.89, + "learning_rate": 6.104519141244631e-06, + "loss": 0.3045, + "step": 6972 + }, + { + "epoch": 0.89, + "learning_rate": 6.103508236135025e-06, + "loss": 0.3088, + "step": 6973 + }, + { + "epoch": 0.89, + "learning_rate": 6.1024972836052135e-06, + "loss": 0.3054, + "step": 6974 + }, + { + "epoch": 0.89, + "learning_rate": 6.1014862836986364e-06, + "loss": 0.3311, + "step": 6975 + }, + { + "epoch": 0.89, + "learning_rate": 6.10047523645874e-06, + "loss": 0.3194, + "step": 6976 + }, + { + "epoch": 0.89, + "learning_rate": 6.099464141928973e-06, + "loss": 0.3147, + "step": 6977 + }, + { + "epoch": 0.89, + "learning_rate": 6.098453000152784e-06, + "loss": 0.3077, + "step": 6978 + }, + { + "epoch": 0.89, + "learning_rate": 6.0974418111736235e-06, + "loss": 0.2931, + "step": 6979 + }, + { + "epoch": 0.89, + "learning_rate": 6.096430575034942e-06, + "loss": 0.312, + "step": 6980 + }, + { + "epoch": 0.89, + "learning_rate": 6.095419291780198e-06, + "loss": 0.3258, + "step": 6981 + }, + { + "epoch": 0.89, + "learning_rate": 6.0944079614528475e-06, + "loss": 0.3021, + "step": 6982 + }, + { + "epoch": 0.89, + "learning_rate": 6.0933965840963494e-06, + "loss": 0.2876, + "step": 6983 + }, + { + "epoch": 0.89, + "learning_rate": 6.092385159754165e-06, + "loss": 0.308, + "step": 6984 + }, + { + "epoch": 0.89, + "learning_rate": 6.091373688469757e-06, + "loss": 0.2881, + "step": 6985 + }, + { + "epoch": 0.89, + "learning_rate": 6.090362170286591e-06, + "loss": 0.3097, + "step": 6986 + }, + { + "epoch": 0.89, + "learning_rate": 6.089350605248134e-06, + "loss": 0.305, + "step": 6987 + }, + { + "epoch": 0.89, + "learning_rate": 6.088338993397857e-06, + "loss": 0.2922, + "step": 6988 + }, + { + "epoch": 0.89, + "learning_rate": 6.0873273347792275e-06, + "loss": 0.2986, + "step": 6989 + }, + { + "epoch": 0.89, + "learning_rate": 6.086315629435722e-06, + "loss": 0.3179, + "step": 6990 + }, + { + "epoch": 0.89, + "learning_rate": 6.085303877410816e-06, + "loss": 0.3353, + "step": 6991 + }, + { + "epoch": 0.89, + "learning_rate": 6.084292078747982e-06, + "loss": 0.3185, + "step": 6992 + }, + { + "epoch": 0.9, + "learning_rate": 6.0832802334907044e-06, + "loss": 0.3206, + "step": 6993 + }, + { + "epoch": 0.9, + "learning_rate": 6.0822683416824625e-06, + "loss": 0.3153, + "step": 6994 + }, + { + "epoch": 0.9, + "learning_rate": 6.08125640336674e-06, + "loss": 0.3323, + "step": 6995 + }, + { + "epoch": 0.9, + "learning_rate": 6.08024441858702e-06, + "loss": 0.284, + "step": 6996 + }, + { + "epoch": 0.9, + "learning_rate": 6.079232387386793e-06, + "loss": 0.3029, + "step": 6997 + }, + { + "epoch": 0.9, + "learning_rate": 6.078220309809546e-06, + "loss": 0.3164, + "step": 6998 + }, + { + "epoch": 0.9, + "learning_rate": 6.077208185898772e-06, + "loss": 0.3065, + "step": 6999 + }, + { + "epoch": 0.9, + "learning_rate": 6.076196015697963e-06, + "loss": 0.2988, + "step": 7000 + }, + { + "epoch": 0.9, + "learning_rate": 6.0751837992506126e-06, + "loss": 0.2984, + "step": 7001 + }, + { + "epoch": 0.9, + "learning_rate": 6.074171536600222e-06, + "loss": 0.3223, + "step": 7002 + }, + { + "epoch": 0.9, + "learning_rate": 6.073159227790287e-06, + "loss": 0.319, + "step": 7003 + }, + { + "epoch": 0.9, + "learning_rate": 6.07214687286431e-06, + "loss": 0.295, + "step": 7004 + }, + { + "epoch": 0.9, + "learning_rate": 6.0711344718657934e-06, + "loss": 0.2972, + "step": 7005 + }, + { + "epoch": 0.9, + "learning_rate": 6.070122024838245e-06, + "loss": 0.3107, + "step": 7006 + }, + { + "epoch": 0.9, + "learning_rate": 6.069109531825169e-06, + "loss": 0.3076, + "step": 7007 + }, + { + "epoch": 0.9, + "learning_rate": 6.068096992870075e-06, + "loss": 0.3115, + "step": 7008 + }, + { + "epoch": 0.9, + "learning_rate": 6.067084408016475e-06, + "loss": 0.3141, + "step": 7009 + }, + { + "epoch": 0.9, + "learning_rate": 6.06607177730788e-06, + "loss": 0.2956, + "step": 7010 + }, + { + "epoch": 0.9, + "learning_rate": 6.065059100787808e-06, + "loss": 0.2897, + "step": 7011 + }, + { + "epoch": 0.9, + "learning_rate": 6.064046378499775e-06, + "loss": 0.2924, + "step": 7012 + }, + { + "epoch": 0.9, + "learning_rate": 6.063033610487298e-06, + "loss": 0.2881, + "step": 7013 + }, + { + "epoch": 0.9, + "learning_rate": 6.0620207967939e-06, + "loss": 0.3104, + "step": 7014 + }, + { + "epoch": 0.9, + "learning_rate": 6.061007937463101e-06, + "loss": 0.3134, + "step": 7015 + }, + { + "epoch": 0.9, + "learning_rate": 6.05999503253843e-06, + "loss": 0.3142, + "step": 7016 + }, + { + "epoch": 0.9, + "learning_rate": 6.058982082063413e-06, + "loss": 0.2927, + "step": 7017 + }, + { + "epoch": 0.9, + "learning_rate": 6.057969086081575e-06, + "loss": 0.3008, + "step": 7018 + }, + { + "epoch": 0.9, + "learning_rate": 6.0569560446364495e-06, + "loss": 0.3191, + "step": 7019 + }, + { + "epoch": 0.9, + "learning_rate": 6.05594295777157e-06, + "loss": 0.2937, + "step": 7020 + }, + { + "epoch": 0.9, + "learning_rate": 6.054929825530469e-06, + "loss": 0.2618, + "step": 7021 + }, + { + "epoch": 0.9, + "learning_rate": 6.0539166479566844e-06, + "loss": 0.2986, + "step": 7022 + }, + { + "epoch": 0.9, + "learning_rate": 6.052903425093752e-06, + "loss": 0.3193, + "step": 7023 + }, + { + "epoch": 0.9, + "learning_rate": 6.051890156985217e-06, + "loss": 0.3135, + "step": 7024 + }, + { + "epoch": 0.9, + "learning_rate": 6.050876843674619e-06, + "loss": 0.3119, + "step": 7025 + }, + { + "epoch": 0.9, + "learning_rate": 6.049863485205503e-06, + "loss": 0.2792, + "step": 7026 + }, + { + "epoch": 0.9, + "learning_rate": 6.048850081621415e-06, + "loss": 0.3155, + "step": 7027 + }, + { + "epoch": 0.9, + "learning_rate": 6.047836632965901e-06, + "loss": 0.2854, + "step": 7028 + }, + { + "epoch": 0.9, + "learning_rate": 6.046823139282515e-06, + "loss": 0.3246, + "step": 7029 + }, + { + "epoch": 0.9, + "learning_rate": 6.045809600614807e-06, + "loss": 0.3283, + "step": 7030 + }, + { + "epoch": 0.9, + "learning_rate": 6.044796017006331e-06, + "loss": 0.2804, + "step": 7031 + }, + { + "epoch": 0.9, + "learning_rate": 6.043782388500642e-06, + "loss": 0.3066, + "step": 7032 + }, + { + "epoch": 0.9, + "learning_rate": 6.0427687151413004e-06, + "loss": 0.3116, + "step": 7033 + }, + { + "epoch": 0.9, + "learning_rate": 6.041754996971866e-06, + "loss": 0.3371, + "step": 7034 + }, + { + "epoch": 0.9, + "learning_rate": 6.040741234035898e-06, + "loss": 0.2935, + "step": 7035 + }, + { + "epoch": 0.9, + "learning_rate": 6.039727426376961e-06, + "loss": 0.3332, + "step": 7036 + }, + { + "epoch": 0.9, + "learning_rate": 6.038713574038622e-06, + "loss": 0.2997, + "step": 7037 + }, + { + "epoch": 0.9, + "learning_rate": 6.037699677064446e-06, + "loss": 0.3101, + "step": 7038 + }, + { + "epoch": 0.9, + "learning_rate": 6.036685735498004e-06, + "loss": 0.319, + "step": 7039 + }, + { + "epoch": 0.9, + "learning_rate": 6.035671749382869e-06, + "loss": 0.3241, + "step": 7040 + }, + { + "epoch": 0.9, + "learning_rate": 6.03465771876261e-06, + "loss": 0.3024, + "step": 7041 + }, + { + "epoch": 0.9, + "learning_rate": 6.0336436436808054e-06, + "loss": 0.3092, + "step": 7042 + }, + { + "epoch": 0.9, + "learning_rate": 6.032629524181031e-06, + "loss": 0.307, + "step": 7043 + }, + { + "epoch": 0.9, + "learning_rate": 6.031615360306867e-06, + "loss": 0.2927, + "step": 7044 + }, + { + "epoch": 0.9, + "learning_rate": 6.030601152101892e-06, + "loss": 0.2962, + "step": 7045 + }, + { + "epoch": 0.9, + "learning_rate": 6.029586899609692e-06, + "loss": 0.3015, + "step": 7046 + }, + { + "epoch": 0.9, + "learning_rate": 6.02857260287385e-06, + "loss": 0.3332, + "step": 7047 + }, + { + "epoch": 0.9, + "learning_rate": 6.02755826193795e-06, + "loss": 0.2987, + "step": 7048 + }, + { + "epoch": 0.9, + "learning_rate": 6.026543876845586e-06, + "loss": 0.2921, + "step": 7049 + }, + { + "epoch": 0.9, + "learning_rate": 6.025529447640343e-06, + "loss": 0.3277, + "step": 7050 + }, + { + "epoch": 0.9, + "learning_rate": 6.024514974365818e-06, + "loss": 0.303, + "step": 7051 + }, + { + "epoch": 0.9, + "learning_rate": 6.0235004570656005e-06, + "loss": 0.3135, + "step": 7052 + }, + { + "epoch": 0.9, + "learning_rate": 6.02248589578329e-06, + "loss": 0.3557, + "step": 7053 + }, + { + "epoch": 0.9, + "learning_rate": 6.021471290562484e-06, + "loss": 0.3421, + "step": 7054 + }, + { + "epoch": 0.9, + "learning_rate": 6.020456641446781e-06, + "loss": 0.3158, + "step": 7055 + }, + { + "epoch": 0.9, + "learning_rate": 6.019441948479784e-06, + "loss": 0.3228, + "step": 7056 + }, + { + "epoch": 0.9, + "learning_rate": 6.018427211705094e-06, + "loss": 0.2689, + "step": 7057 + }, + { + "epoch": 0.9, + "learning_rate": 6.017412431166322e-06, + "loss": 0.2899, + "step": 7058 + }, + { + "epoch": 0.9, + "learning_rate": 6.016397606907069e-06, + "loss": 0.3146, + "step": 7059 + }, + { + "epoch": 0.9, + "learning_rate": 6.015382738970949e-06, + "loss": 0.3204, + "step": 7060 + }, + { + "epoch": 0.9, + "learning_rate": 6.01436782740157e-06, + "loss": 0.2869, + "step": 7061 + }, + { + "epoch": 0.9, + "learning_rate": 6.013352872242546e-06, + "loss": 0.3144, + "step": 7062 + }, + { + "epoch": 0.9, + "learning_rate": 6.012337873537494e-06, + "loss": 0.3117, + "step": 7063 + }, + { + "epoch": 0.9, + "learning_rate": 6.011322831330028e-06, + "loss": 0.2917, + "step": 7064 + }, + { + "epoch": 0.9, + "learning_rate": 6.010307745663768e-06, + "loss": 0.2715, + "step": 7065 + }, + { + "epoch": 0.9, + "learning_rate": 6.009292616582333e-06, + "loss": 0.2844, + "step": 7066 + }, + { + "epoch": 0.9, + "learning_rate": 6.008277444129347e-06, + "loss": 0.3262, + "step": 7067 + }, + { + "epoch": 0.9, + "learning_rate": 6.007262228348434e-06, + "loss": 0.3091, + "step": 7068 + }, + { + "epoch": 0.9, + "learning_rate": 6.0062469692832205e-06, + "loss": 0.2971, + "step": 7069 + }, + { + "epoch": 0.9, + "learning_rate": 6.005231666977331e-06, + "loss": 0.2903, + "step": 7070 + }, + { + "epoch": 0.91, + "learning_rate": 6.0042163214744006e-06, + "loss": 0.3042, + "step": 7071 + }, + { + "epoch": 0.91, + "learning_rate": 6.003200932818058e-06, + "loss": 0.3214, + "step": 7072 + }, + { + "epoch": 0.91, + "learning_rate": 6.002185501051937e-06, + "loss": 0.3223, + "step": 7073 + }, + { + "epoch": 0.91, + "learning_rate": 6.001170026219673e-06, + "loss": 0.2936, + "step": 7074 + }, + { + "epoch": 0.91, + "learning_rate": 6.000154508364901e-06, + "loss": 0.3071, + "step": 7075 + }, + { + "epoch": 0.91, + "learning_rate": 5.999138947531265e-06, + "loss": 0.2899, + "step": 7076 + }, + { + "epoch": 0.91, + "learning_rate": 5.998123343762403e-06, + "loss": 0.3078, + "step": 7077 + }, + { + "epoch": 0.91, + "learning_rate": 5.997107697101957e-06, + "loss": 0.3025, + "step": 7078 + }, + { + "epoch": 0.91, + "learning_rate": 5.996092007593572e-06, + "loss": 0.2861, + "step": 7079 + }, + { + "epoch": 0.91, + "learning_rate": 5.9950762752808965e-06, + "loss": 0.2937, + "step": 7080 + }, + { + "epoch": 0.91, + "learning_rate": 5.994060500207577e-06, + "loss": 0.2945, + "step": 7081 + }, + { + "epoch": 0.91, + "learning_rate": 5.993044682417264e-06, + "loss": 0.3168, + "step": 7082 + }, + { + "epoch": 0.91, + "learning_rate": 5.992028821953609e-06, + "loss": 0.2917, + "step": 7083 + }, + { + "epoch": 0.91, + "learning_rate": 5.9910129188602665e-06, + "loss": 0.2893, + "step": 7084 + }, + { + "epoch": 0.91, + "learning_rate": 5.989996973180892e-06, + "loss": 0.2942, + "step": 7085 + }, + { + "epoch": 0.91, + "learning_rate": 5.988980984959142e-06, + "loss": 0.2967, + "step": 7086 + }, + { + "epoch": 0.91, + "learning_rate": 5.987964954238677e-06, + "loss": 0.2988, + "step": 7087 + }, + { + "epoch": 0.91, + "learning_rate": 5.986948881063157e-06, + "loss": 0.3144, + "step": 7088 + }, + { + "epoch": 0.91, + "learning_rate": 5.985932765476246e-06, + "loss": 0.3475, + "step": 7089 + }, + { + "epoch": 0.91, + "learning_rate": 5.984916607521608e-06, + "loss": 0.3284, + "step": 7090 + }, + { + "epoch": 0.91, + "learning_rate": 5.983900407242911e-06, + "loss": 0.3076, + "step": 7091 + }, + { + "epoch": 0.91, + "learning_rate": 5.982884164683821e-06, + "loss": 0.3785, + "step": 7092 + }, + { + "epoch": 0.91, + "learning_rate": 5.9818678798880085e-06, + "loss": 0.293, + "step": 7093 + }, + { + "epoch": 0.91, + "learning_rate": 5.9808515528991486e-06, + "loss": 0.3156, + "step": 7094 + }, + { + "epoch": 0.91, + "learning_rate": 5.979835183760911e-06, + "loss": 0.2941, + "step": 7095 + }, + { + "epoch": 0.91, + "learning_rate": 5.978818772516976e-06, + "loss": 0.3223, + "step": 7096 + }, + { + "epoch": 0.91, + "learning_rate": 5.977802319211016e-06, + "loss": 0.2971, + "step": 7097 + }, + { + "epoch": 0.91, + "learning_rate": 5.976785823886713e-06, + "loss": 0.302, + "step": 7098 + }, + { + "epoch": 0.91, + "learning_rate": 5.975769286587747e-06, + "loss": 0.3257, + "step": 7099 + }, + { + "epoch": 0.91, + "learning_rate": 5.974752707357805e-06, + "loss": 0.3129, + "step": 7100 + }, + { + "epoch": 0.91, + "learning_rate": 5.973736086240566e-06, + "loss": 0.3187, + "step": 7101 + }, + { + "epoch": 0.91, + "learning_rate": 5.9727194232797185e-06, + "loss": 0.2998, + "step": 7102 + }, + { + "epoch": 0.91, + "learning_rate": 5.97170271851895e-06, + "loss": 0.3032, + "step": 7103 + }, + { + "epoch": 0.91, + "learning_rate": 5.970685972001953e-06, + "loss": 0.3256, + "step": 7104 + }, + { + "epoch": 0.91, + "learning_rate": 5.96966918377242e-06, + "loss": 0.302, + "step": 7105 + }, + { + "epoch": 0.91, + "learning_rate": 5.9686523538740385e-06, + "loss": 0.3045, + "step": 7106 + }, + { + "epoch": 0.91, + "learning_rate": 5.96763548235051e-06, + "loss": 0.3425, + "step": 7107 + }, + { + "epoch": 0.91, + "learning_rate": 5.966618569245529e-06, + "loss": 0.294, + "step": 7108 + }, + { + "epoch": 0.91, + "learning_rate": 5.965601614602798e-06, + "loss": 0.3218, + "step": 7109 + }, + { + "epoch": 0.91, + "learning_rate": 5.964584618466014e-06, + "loss": 0.3154, + "step": 7110 + }, + { + "epoch": 0.91, + "learning_rate": 5.9635675808788785e-06, + "loss": 0.3163, + "step": 7111 + }, + { + "epoch": 0.91, + "learning_rate": 5.9625505018851e-06, + "loss": 0.3018, + "step": 7112 + }, + { + "epoch": 0.91, + "learning_rate": 5.961533381528382e-06, + "loss": 0.3071, + "step": 7113 + }, + { + "epoch": 0.91, + "learning_rate": 5.960516219852433e-06, + "loss": 0.3038, + "step": 7114 + }, + { + "epoch": 0.91, + "learning_rate": 5.959499016900963e-06, + "loss": 0.3158, + "step": 7115 + }, + { + "epoch": 0.91, + "learning_rate": 5.9584817727176836e-06, + "loss": 0.2969, + "step": 7116 + }, + { + "epoch": 0.91, + "learning_rate": 5.9574644873463075e-06, + "loss": 0.2994, + "step": 7117 + }, + { + "epoch": 0.91, + "learning_rate": 5.95644716083055e-06, + "loss": 0.3313, + "step": 7118 + }, + { + "epoch": 0.91, + "learning_rate": 5.955429793214129e-06, + "loss": 0.3051, + "step": 7119 + }, + { + "epoch": 0.91, + "learning_rate": 5.954412384540761e-06, + "loss": 0.2986, + "step": 7120 + }, + { + "epoch": 0.91, + "learning_rate": 5.953394934854167e-06, + "loss": 0.2872, + "step": 7121 + }, + { + "epoch": 0.91, + "learning_rate": 5.952377444198068e-06, + "loss": 0.3133, + "step": 7122 + }, + { + "epoch": 0.91, + "learning_rate": 5.951359912616192e-06, + "loss": 0.3065, + "step": 7123 + }, + { + "epoch": 0.91, + "learning_rate": 5.950342340152261e-06, + "loss": 0.3008, + "step": 7124 + }, + { + "epoch": 0.91, + "learning_rate": 5.949324726850002e-06, + "loss": 0.3101, + "step": 7125 + }, + { + "epoch": 0.91, + "learning_rate": 5.948307072753146e-06, + "loss": 0.3079, + "step": 7126 + }, + { + "epoch": 0.91, + "learning_rate": 5.947289377905422e-06, + "loss": 0.3241, + "step": 7127 + }, + { + "epoch": 0.91, + "learning_rate": 5.946271642350565e-06, + "loss": 0.2871, + "step": 7128 + }, + { + "epoch": 0.91, + "learning_rate": 5.945253866132308e-06, + "loss": 0.288, + "step": 7129 + }, + { + "epoch": 0.91, + "learning_rate": 5.9442360492943876e-06, + "loss": 0.3123, + "step": 7130 + }, + { + "epoch": 0.91, + "learning_rate": 5.94321819188054e-06, + "loss": 0.308, + "step": 7131 + }, + { + "epoch": 0.91, + "learning_rate": 5.942200293934506e-06, + "loss": 0.3045, + "step": 7132 + }, + { + "epoch": 0.91, + "learning_rate": 5.941182355500028e-06, + "loss": 0.2643, + "step": 7133 + }, + { + "epoch": 0.91, + "learning_rate": 5.940164376620847e-06, + "loss": 0.3104, + "step": 7134 + }, + { + "epoch": 0.91, + "learning_rate": 5.93914635734071e-06, + "loss": 0.3018, + "step": 7135 + }, + { + "epoch": 0.91, + "learning_rate": 5.938128297703361e-06, + "loss": 0.3096, + "step": 7136 + }, + { + "epoch": 0.91, + "learning_rate": 5.937110197752551e-06, + "loss": 0.3072, + "step": 7137 + }, + { + "epoch": 0.91, + "learning_rate": 5.936092057532029e-06, + "loss": 0.2968, + "step": 7138 + }, + { + "epoch": 0.91, + "learning_rate": 5.935073877085546e-06, + "loss": 0.3069, + "step": 7139 + }, + { + "epoch": 0.91, + "learning_rate": 5.934055656456855e-06, + "loss": 0.315, + "step": 7140 + }, + { + "epoch": 0.91, + "learning_rate": 5.9330373956897135e-06, + "loss": 0.3053, + "step": 7141 + }, + { + "epoch": 0.91, + "learning_rate": 5.932019094827877e-06, + "loss": 0.3142, + "step": 7142 + }, + { + "epoch": 0.91, + "learning_rate": 5.931000753915104e-06, + "loss": 0.3008, + "step": 7143 + }, + { + "epoch": 0.91, + "learning_rate": 5.9299823729951544e-06, + "loss": 0.2791, + "step": 7144 + }, + { + "epoch": 0.91, + "learning_rate": 5.928963952111791e-06, + "loss": 0.2981, + "step": 7145 + }, + { + "epoch": 0.91, + "learning_rate": 5.9279454913087795e-06, + "loss": 0.305, + "step": 7146 + }, + { + "epoch": 0.91, + "learning_rate": 5.926926990629883e-06, + "loss": 0.2875, + "step": 7147 + }, + { + "epoch": 0.91, + "learning_rate": 5.9259084501188695e-06, + "loss": 0.289, + "step": 7148 + }, + { + "epoch": 0.92, + "learning_rate": 5.9248898698195054e-06, + "loss": 0.2995, + "step": 7149 + }, + { + "epoch": 0.92, + "learning_rate": 5.923871249775566e-06, + "loss": 0.3026, + "step": 7150 + }, + { + "epoch": 0.92, + "learning_rate": 5.922852590030821e-06, + "loss": 0.2908, + "step": 7151 + }, + { + "epoch": 0.92, + "learning_rate": 5.921833890629045e-06, + "loss": 0.3257, + "step": 7152 + }, + { + "epoch": 0.92, + "learning_rate": 5.920815151614012e-06, + "loss": 0.301, + "step": 7153 + }, + { + "epoch": 0.92, + "learning_rate": 5.919796373029504e-06, + "loss": 0.2923, + "step": 7154 + }, + { + "epoch": 0.92, + "learning_rate": 5.918777554919296e-06, + "loss": 0.3136, + "step": 7155 + }, + { + "epoch": 0.92, + "learning_rate": 5.917758697327171e-06, + "loss": 0.3203, + "step": 7156 + }, + { + "epoch": 0.92, + "learning_rate": 5.9167398002969104e-06, + "loss": 0.3024, + "step": 7157 + }, + { + "epoch": 0.92, + "learning_rate": 5.915720863872297e-06, + "loss": 0.2896, + "step": 7158 + }, + { + "epoch": 0.92, + "learning_rate": 5.914701888097121e-06, + "loss": 0.284, + "step": 7159 + }, + { + "epoch": 0.92, + "learning_rate": 5.913682873015166e-06, + "loss": 0.307, + "step": 7160 + }, + { + "epoch": 0.92, + "learning_rate": 5.912663818670224e-06, + "loss": 0.3038, + "step": 7161 + }, + { + "epoch": 0.92, + "learning_rate": 5.911644725106085e-06, + "loss": 0.3167, + "step": 7162 + }, + { + "epoch": 0.92, + "learning_rate": 5.910625592366542e-06, + "loss": 0.3064, + "step": 7163 + }, + { + "epoch": 0.92, + "learning_rate": 5.90960642049539e-06, + "loss": 0.3116, + "step": 7164 + }, + { + "epoch": 0.92, + "learning_rate": 5.9085872095364236e-06, + "loss": 0.297, + "step": 7165 + }, + { + "epoch": 0.92, + "learning_rate": 5.907567959533441e-06, + "loss": 0.292, + "step": 7166 + }, + { + "epoch": 0.92, + "learning_rate": 5.906548670530241e-06, + "loss": 0.2838, + "step": 7167 + }, + { + "epoch": 0.92, + "learning_rate": 5.905529342570627e-06, + "loss": 0.2965, + "step": 7168 + }, + { + "epoch": 0.92, + "learning_rate": 5.904509975698399e-06, + "loss": 0.3195, + "step": 7169 + }, + { + "epoch": 0.92, + "learning_rate": 5.903490569957366e-06, + "loss": 0.2836, + "step": 7170 + }, + { + "epoch": 0.92, + "learning_rate": 5.902471125391328e-06, + "loss": 0.3154, + "step": 7171 + }, + { + "epoch": 0.92, + "learning_rate": 5.901451642044097e-06, + "loss": 0.3031, + "step": 7172 + }, + { + "epoch": 0.92, + "learning_rate": 5.90043211995948e-06, + "loss": 0.3253, + "step": 7173 + }, + { + "epoch": 0.92, + "learning_rate": 5.8994125591812914e-06, + "loss": 0.2871, + "step": 7174 + }, + { + "epoch": 0.92, + "learning_rate": 5.898392959753343e-06, + "loss": 0.2864, + "step": 7175 + }, + { + "epoch": 0.92, + "learning_rate": 5.897373321719445e-06, + "loss": 0.2976, + "step": 7176 + }, + { + "epoch": 0.92, + "learning_rate": 5.896353645123418e-06, + "loss": 0.3219, + "step": 7177 + }, + { + "epoch": 0.92, + "learning_rate": 5.895333930009079e-06, + "loss": 0.3062, + "step": 7178 + }, + { + "epoch": 0.92, + "learning_rate": 5.894314176420247e-06, + "loss": 0.2748, + "step": 7179 + }, + { + "epoch": 0.92, + "learning_rate": 5.893294384400743e-06, + "loss": 0.3145, + "step": 7180 + }, + { + "epoch": 0.92, + "learning_rate": 5.89227455399439e-06, + "loss": 0.2941, + "step": 7181 + }, + { + "epoch": 0.92, + "learning_rate": 5.8912546852450116e-06, + "loss": 0.3228, + "step": 7182 + }, + { + "epoch": 0.92, + "learning_rate": 5.890234778196435e-06, + "loss": 0.3279, + "step": 7183 + }, + { + "epoch": 0.92, + "learning_rate": 5.889214832892489e-06, + "loss": 0.3058, + "step": 7184 + }, + { + "epoch": 0.92, + "learning_rate": 5.888194849376998e-06, + "loss": 0.3317, + "step": 7185 + }, + { + "epoch": 0.92, + "learning_rate": 5.8871748276937975e-06, + "loss": 0.3361, + "step": 7186 + }, + { + "epoch": 0.92, + "learning_rate": 5.886154767886719e-06, + "loss": 0.3044, + "step": 7187 + }, + { + "epoch": 0.92, + "learning_rate": 5.885134669999597e-06, + "loss": 0.3027, + "step": 7188 + }, + { + "epoch": 0.92, + "learning_rate": 5.8841145340762665e-06, + "loss": 0.3063, + "step": 7189 + }, + { + "epoch": 0.92, + "learning_rate": 5.8830943601605665e-06, + "loss": 0.272, + "step": 7190 + }, + { + "epoch": 0.92, + "learning_rate": 5.882074148296332e-06, + "loss": 0.305, + "step": 7191 + }, + { + "epoch": 0.92, + "learning_rate": 5.881053898527409e-06, + "loss": 0.3075, + "step": 7192 + }, + { + "epoch": 0.92, + "learning_rate": 5.880033610897638e-06, + "loss": 0.283, + "step": 7193 + }, + { + "epoch": 0.92, + "learning_rate": 5.879013285450863e-06, + "loss": 0.2731, + "step": 7194 + }, + { + "epoch": 0.92, + "learning_rate": 5.877992922230928e-06, + "loss": 0.2933, + "step": 7195 + }, + { + "epoch": 0.92, + "learning_rate": 5.876972521281683e-06, + "loss": 0.289, + "step": 7196 + }, + { + "epoch": 0.92, + "learning_rate": 5.875952082646975e-06, + "loss": 0.309, + "step": 7197 + }, + { + "epoch": 0.92, + "learning_rate": 5.8749316063706565e-06, + "loss": 0.3244, + "step": 7198 + }, + { + "epoch": 0.92, + "learning_rate": 5.873911092496577e-06, + "loss": 0.3213, + "step": 7199 + }, + { + "epoch": 0.92, + "learning_rate": 5.872890541068591e-06, + "loss": 0.2969, + "step": 7200 + }, + { + "epoch": 0.92, + "learning_rate": 5.871869952130556e-06, + "loss": 0.334, + "step": 7201 + }, + { + "epoch": 0.92, + "learning_rate": 5.870849325726326e-06, + "loss": 0.3154, + "step": 7202 + }, + { + "epoch": 0.92, + "learning_rate": 5.869828661899761e-06, + "loss": 0.3341, + "step": 7203 + }, + { + "epoch": 0.92, + "learning_rate": 5.8688079606947226e-06, + "loss": 0.3092, + "step": 7204 + }, + { + "epoch": 0.92, + "learning_rate": 5.86778722215507e-06, + "loss": 0.285, + "step": 7205 + }, + { + "epoch": 0.92, + "learning_rate": 5.866766446324668e-06, + "loss": 0.3257, + "step": 7206 + }, + { + "epoch": 0.92, + "learning_rate": 5.865745633247381e-06, + "loss": 0.2958, + "step": 7207 + }, + { + "epoch": 0.92, + "learning_rate": 5.864724782967077e-06, + "loss": 0.3166, + "step": 7208 + }, + { + "epoch": 0.92, + "learning_rate": 5.8637038955276225e-06, + "loss": 0.3, + "step": 7209 + }, + { + "epoch": 0.92, + "learning_rate": 5.862682970972888e-06, + "loss": 0.3161, + "step": 7210 + }, + { + "epoch": 0.92, + "learning_rate": 5.861662009346747e-06, + "loss": 0.309, + "step": 7211 + }, + { + "epoch": 0.92, + "learning_rate": 5.8606410106930675e-06, + "loss": 0.3221, + "step": 7212 + }, + { + "epoch": 0.92, + "learning_rate": 5.85961997505573e-06, + "loss": 0.3068, + "step": 7213 + }, + { + "epoch": 0.92, + "learning_rate": 5.858598902478604e-06, + "loss": 0.2897, + "step": 7214 + }, + { + "epoch": 0.92, + "learning_rate": 5.857577793005573e-06, + "loss": 0.2956, + "step": 7215 + }, + { + "epoch": 0.92, + "learning_rate": 5.856556646680514e-06, + "loss": 0.2893, + "step": 7216 + }, + { + "epoch": 0.92, + "learning_rate": 5.855535463547309e-06, + "loss": 0.3343, + "step": 7217 + }, + { + "epoch": 0.92, + "learning_rate": 5.854514243649839e-06, + "loss": 0.2987, + "step": 7218 + }, + { + "epoch": 0.92, + "learning_rate": 5.853492987031989e-06, + "loss": 0.299, + "step": 7219 + }, + { + "epoch": 0.92, + "learning_rate": 5.8524716937376446e-06, + "loss": 0.3357, + "step": 7220 + }, + { + "epoch": 0.92, + "learning_rate": 5.851450363810694e-06, + "loss": 0.3025, + "step": 7221 + }, + { + "epoch": 0.92, + "learning_rate": 5.850428997295023e-06, + "loss": 0.3002, + "step": 7222 + }, + { + "epoch": 0.92, + "learning_rate": 5.8494075942345244e-06, + "loss": 0.3047, + "step": 7223 + }, + { + "epoch": 0.92, + "learning_rate": 5.8483861546730915e-06, + "loss": 0.287, + "step": 7224 + }, + { + "epoch": 0.92, + "learning_rate": 5.8473646786546134e-06, + "loss": 0.3089, + "step": 7225 + }, + { + "epoch": 0.92, + "learning_rate": 5.846343166222991e-06, + "loss": 0.3081, + "step": 7226 + }, + { + "epoch": 0.93, + "learning_rate": 5.845321617422115e-06, + "loss": 0.2902, + "step": 7227 + }, + { + "epoch": 0.93, + "learning_rate": 5.8443000322958875e-06, + "loss": 0.2956, + "step": 7228 + }, + { + "epoch": 0.93, + "learning_rate": 5.843278410888208e-06, + "loss": 0.3002, + "step": 7229 + }, + { + "epoch": 0.93, + "learning_rate": 5.842256753242975e-06, + "loss": 0.3059, + "step": 7230 + }, + { + "epoch": 0.93, + "learning_rate": 5.841235059404097e-06, + "loss": 0.2955, + "step": 7231 + }, + { + "epoch": 0.93, + "learning_rate": 5.840213329415471e-06, + "loss": 0.2822, + "step": 7232 + }, + { + "epoch": 0.93, + "learning_rate": 5.839191563321009e-06, + "loss": 0.3142, + "step": 7233 + }, + { + "epoch": 0.93, + "learning_rate": 5.838169761164616e-06, + "loss": 0.2985, + "step": 7234 + }, + { + "epoch": 0.93, + "learning_rate": 5.837147922990204e-06, + "loss": 0.3176, + "step": 7235 + }, + { + "epoch": 0.93, + "learning_rate": 5.836126048841678e-06, + "loss": 0.311, + "step": 7236 + }, + { + "epoch": 0.93, + "learning_rate": 5.8351041387629546e-06, + "loss": 0.3353, + "step": 7237 + }, + { + "epoch": 0.93, + "learning_rate": 5.834082192797948e-06, + "loss": 0.3178, + "step": 7238 + }, + { + "epoch": 0.93, + "learning_rate": 5.83306021099057e-06, + "loss": 0.2887, + "step": 7239 + }, + { + "epoch": 0.93, + "learning_rate": 5.832038193384741e-06, + "loss": 0.2815, + "step": 7240 + }, + { + "epoch": 0.93, + "learning_rate": 5.831016140024377e-06, + "loss": 0.2967, + "step": 7241 + }, + { + "epoch": 0.93, + "learning_rate": 5.829994050953398e-06, + "loss": 0.3, + "step": 7242 + }, + { + "epoch": 0.93, + "learning_rate": 5.828971926215726e-06, + "loss": 0.2753, + "step": 7243 + }, + { + "epoch": 0.93, + "learning_rate": 5.827949765855285e-06, + "loss": 0.2931, + "step": 7244 + }, + { + "epoch": 0.93, + "learning_rate": 5.826927569915999e-06, + "loss": 0.3313, + "step": 7245 + }, + { + "epoch": 0.93, + "learning_rate": 5.825905338441794e-06, + "loss": 0.2984, + "step": 7246 + }, + { + "epoch": 0.93, + "learning_rate": 5.824883071476597e-06, + "loss": 0.3271, + "step": 7247 + }, + { + "epoch": 0.93, + "learning_rate": 5.823860769064335e-06, + "loss": 0.328, + "step": 7248 + }, + { + "epoch": 0.93, + "learning_rate": 5.822838431248943e-06, + "loss": 0.2934, + "step": 7249 + }, + { + "epoch": 0.93, + "learning_rate": 5.821816058074351e-06, + "loss": 0.2841, + "step": 7250 + }, + { + "epoch": 0.93, + "learning_rate": 5.820793649584493e-06, + "loss": 0.3314, + "step": 7251 + }, + { + "epoch": 0.93, + "learning_rate": 5.819771205823303e-06, + "loss": 0.3021, + "step": 7252 + }, + { + "epoch": 0.93, + "learning_rate": 5.818748726834718e-06, + "loss": 0.3048, + "step": 7253 + }, + { + "epoch": 0.93, + "learning_rate": 5.817726212662678e-06, + "loss": 0.3167, + "step": 7254 + }, + { + "epoch": 0.93, + "learning_rate": 5.8167036633511206e-06, + "loss": 0.2971, + "step": 7255 + }, + { + "epoch": 0.93, + "learning_rate": 5.815681078943989e-06, + "loss": 0.318, + "step": 7256 + }, + { + "epoch": 0.93, + "learning_rate": 5.814658459485223e-06, + "loss": 0.3209, + "step": 7257 + }, + { + "epoch": 0.93, + "learning_rate": 5.81363580501877e-06, + "loss": 0.2998, + "step": 7258 + }, + { + "epoch": 0.93, + "learning_rate": 5.812613115588575e-06, + "loss": 0.3264, + "step": 7259 + }, + { + "epoch": 0.93, + "learning_rate": 5.811590391238584e-06, + "loss": 0.314, + "step": 7260 + }, + { + "epoch": 0.93, + "learning_rate": 5.8105676320127455e-06, + "loss": 0.2894, + "step": 7261 + }, + { + "epoch": 0.93, + "learning_rate": 5.809544837955011e-06, + "loss": 0.2963, + "step": 7262 + }, + { + "epoch": 0.93, + "learning_rate": 5.808522009109333e-06, + "loss": 0.3007, + "step": 7263 + }, + { + "epoch": 0.93, + "learning_rate": 5.807499145519663e-06, + "loss": 0.3083, + "step": 7264 + }, + { + "epoch": 0.93, + "learning_rate": 5.806476247229956e-06, + "loss": 0.3377, + "step": 7265 + }, + { + "epoch": 0.93, + "learning_rate": 5.805453314284168e-06, + "loss": 0.2743, + "step": 7266 + }, + { + "epoch": 0.93, + "learning_rate": 5.804430346726258e-06, + "loss": 0.2973, + "step": 7267 + }, + { + "epoch": 0.93, + "learning_rate": 5.803407344600185e-06, + "loss": 0.3069, + "step": 7268 + }, + { + "epoch": 0.93, + "learning_rate": 5.802384307949909e-06, + "loss": 0.3042, + "step": 7269 + }, + { + "epoch": 0.93, + "learning_rate": 5.8013612368193905e-06, + "loss": 0.3152, + "step": 7270 + }, + { + "epoch": 0.93, + "learning_rate": 5.800338131252597e-06, + "loss": 0.3243, + "step": 7271 + }, + { + "epoch": 0.93, + "learning_rate": 5.79931499129349e-06, + "loss": 0.3015, + "step": 7272 + }, + { + "epoch": 0.93, + "learning_rate": 5.7982918169860395e-06, + "loss": 0.2822, + "step": 7273 + }, + { + "epoch": 0.93, + "learning_rate": 5.79726860837421e-06, + "loss": 0.2942, + "step": 7274 + }, + { + "epoch": 0.93, + "learning_rate": 5.796245365501973e-06, + "loss": 0.2863, + "step": 7275 + }, + { + "epoch": 0.93, + "learning_rate": 5.795222088413299e-06, + "loss": 0.3104, + "step": 7276 + }, + { + "epoch": 0.93, + "learning_rate": 5.794198777152162e-06, + "loss": 0.3107, + "step": 7277 + }, + { + "epoch": 0.93, + "learning_rate": 5.793175431762534e-06, + "loss": 0.3016, + "step": 7278 + }, + { + "epoch": 0.93, + "learning_rate": 5.792152052288391e-06, + "loss": 0.3241, + "step": 7279 + }, + { + "epoch": 0.93, + "learning_rate": 5.791128638773711e-06, + "loss": 0.3323, + "step": 7280 + }, + { + "epoch": 0.93, + "learning_rate": 5.790105191262471e-06, + "loss": 0.3067, + "step": 7281 + }, + { + "epoch": 0.93, + "learning_rate": 5.789081709798652e-06, + "loss": 0.2953, + "step": 7282 + }, + { + "epoch": 0.93, + "learning_rate": 5.788058194426234e-06, + "loss": 0.2854, + "step": 7283 + }, + { + "epoch": 0.93, + "learning_rate": 5.787034645189199e-06, + "loss": 0.2773, + "step": 7284 + }, + { + "epoch": 0.93, + "learning_rate": 5.786011062131535e-06, + "loss": 0.3126, + "step": 7285 + }, + { + "epoch": 0.93, + "learning_rate": 5.784987445297222e-06, + "loss": 0.3228, + "step": 7286 + }, + { + "epoch": 0.93, + "learning_rate": 5.783963794730254e-06, + "loss": 0.3258, + "step": 7287 + }, + { + "epoch": 0.93, + "learning_rate": 5.782940110474612e-06, + "loss": 0.3029, + "step": 7288 + }, + { + "epoch": 0.93, + "learning_rate": 5.7819163925742915e-06, + "loss": 0.3013, + "step": 7289 + }, + { + "epoch": 0.93, + "learning_rate": 5.780892641073281e-06, + "loss": 0.3284, + "step": 7290 + }, + { + "epoch": 0.93, + "learning_rate": 5.779868856015578e-06, + "loss": 0.2969, + "step": 7291 + }, + { + "epoch": 0.93, + "learning_rate": 5.778845037445171e-06, + "loss": 0.2754, + "step": 7292 + }, + { + "epoch": 0.93, + "learning_rate": 5.7778211854060575e-06, + "loss": 0.2798, + "step": 7293 + }, + { + "epoch": 0.93, + "learning_rate": 5.776797299942236e-06, + "loss": 0.3214, + "step": 7294 + }, + { + "epoch": 0.93, + "learning_rate": 5.775773381097705e-06, + "loss": 0.2986, + "step": 7295 + }, + { + "epoch": 0.93, + "learning_rate": 5.774749428916464e-06, + "loss": 0.323, + "step": 7296 + }, + { + "epoch": 0.93, + "learning_rate": 5.773725443442514e-06, + "loss": 0.292, + "step": 7297 + }, + { + "epoch": 0.93, + "learning_rate": 5.7727014247198585e-06, + "loss": 0.3223, + "step": 7298 + }, + { + "epoch": 0.93, + "learning_rate": 5.771677372792502e-06, + "loss": 0.2894, + "step": 7299 + }, + { + "epoch": 0.93, + "learning_rate": 5.770653287704451e-06, + "loss": 0.2982, + "step": 7300 + }, + { + "epoch": 0.93, + "learning_rate": 5.7696291694997105e-06, + "loss": 0.3223, + "step": 7301 + }, + { + "epoch": 0.93, + "learning_rate": 5.768605018222292e-06, + "loss": 0.2983, + "step": 7302 + }, + { + "epoch": 0.93, + "learning_rate": 5.767580833916203e-06, + "loss": 0.2953, + "step": 7303 + }, + { + "epoch": 0.93, + "learning_rate": 5.766556616625456e-06, + "loss": 0.3034, + "step": 7304 + }, + { + "epoch": 0.94, + "learning_rate": 5.765532366394064e-06, + "loss": 0.2819, + "step": 7305 + }, + { + "epoch": 0.94, + "learning_rate": 5.764508083266043e-06, + "loss": 0.301, + "step": 7306 + }, + { + "epoch": 0.94, + "learning_rate": 5.763483767285405e-06, + "loss": 0.2802, + "step": 7307 + }, + { + "epoch": 0.94, + "learning_rate": 5.762459418496169e-06, + "loss": 0.3119, + "step": 7308 + }, + { + "epoch": 0.94, + "learning_rate": 5.7614350369423555e-06, + "loss": 0.3309, + "step": 7309 + }, + { + "epoch": 0.94, + "learning_rate": 5.760410622667981e-06, + "loss": 0.2723, + "step": 7310 + }, + { + "epoch": 0.94, + "learning_rate": 5.75938617571707e-06, + "loss": 0.3151, + "step": 7311 + }, + { + "epoch": 0.94, + "learning_rate": 5.758361696133643e-06, + "loss": 0.3082, + "step": 7312 + }, + { + "epoch": 0.94, + "learning_rate": 5.757337183961724e-06, + "loss": 0.3055, + "step": 7313 + }, + { + "epoch": 0.94, + "learning_rate": 5.7563126392453415e-06, + "loss": 0.2847, + "step": 7314 + }, + { + "epoch": 0.94, + "learning_rate": 5.755288062028519e-06, + "loss": 0.2958, + "step": 7315 + }, + { + "epoch": 0.94, + "learning_rate": 5.754263452355287e-06, + "loss": 0.332, + "step": 7316 + }, + { + "epoch": 0.94, + "learning_rate": 5.753238810269674e-06, + "loss": 0.2949, + "step": 7317 + }, + { + "epoch": 0.94, + "learning_rate": 5.752214135815712e-06, + "loss": 0.3032, + "step": 7318 + }, + { + "epoch": 0.94, + "learning_rate": 5.751189429037435e-06, + "loss": 0.3071, + "step": 7319 + }, + { + "epoch": 0.94, + "learning_rate": 5.750164689978873e-06, + "loss": 0.2773, + "step": 7320 + }, + { + "epoch": 0.94, + "learning_rate": 5.7491399186840646e-06, + "loss": 0.3006, + "step": 7321 + }, + { + "epoch": 0.94, + "learning_rate": 5.748115115197045e-06, + "loss": 0.2956, + "step": 7322 + }, + { + "epoch": 0.94, + "learning_rate": 5.7470902795618535e-06, + "loss": 0.2858, + "step": 7323 + }, + { + "epoch": 0.94, + "learning_rate": 5.746065411822528e-06, + "loss": 0.3125, + "step": 7324 + }, + { + "epoch": 0.94, + "learning_rate": 5.745040512023111e-06, + "loss": 0.3149, + "step": 7325 + }, + { + "epoch": 0.94, + "learning_rate": 5.744015580207642e-06, + "loss": 0.2863, + "step": 7326 + }, + { + "epoch": 0.94, + "learning_rate": 5.742990616420169e-06, + "loss": 0.3168, + "step": 7327 + }, + { + "epoch": 0.94, + "learning_rate": 5.741965620704734e-06, + "loss": 0.2819, + "step": 7328 + }, + { + "epoch": 0.94, + "learning_rate": 5.740940593105383e-06, + "loss": 0.3008, + "step": 7329 + }, + { + "epoch": 0.94, + "learning_rate": 5.7399155336661645e-06, + "loss": 0.3032, + "step": 7330 + }, + { + "epoch": 0.94, + "learning_rate": 5.738890442431128e-06, + "loss": 0.2868, + "step": 7331 + }, + { + "epoch": 0.94, + "learning_rate": 5.737865319444324e-06, + "loss": 0.3082, + "step": 7332 + }, + { + "epoch": 0.94, + "learning_rate": 5.736840164749803e-06, + "loss": 0.2846, + "step": 7333 + }, + { + "epoch": 0.94, + "learning_rate": 5.73581497839162e-06, + "loss": 0.303, + "step": 7334 + }, + { + "epoch": 0.94, + "learning_rate": 5.734789760413827e-06, + "loss": 0.321, + "step": 7335 + }, + { + "epoch": 0.94, + "learning_rate": 5.733764510860482e-06, + "loss": 0.3143, + "step": 7336 + }, + { + "epoch": 0.94, + "learning_rate": 5.7327392297756426e-06, + "loss": 0.3034, + "step": 7337 + }, + { + "epoch": 0.94, + "learning_rate": 5.731713917203368e-06, + "loss": 0.33, + "step": 7338 + }, + { + "epoch": 0.94, + "learning_rate": 5.730688573187715e-06, + "loss": 0.3198, + "step": 7339 + }, + { + "epoch": 0.94, + "learning_rate": 5.729663197772745e-06, + "loss": 0.3137, + "step": 7340 + }, + { + "epoch": 0.94, + "learning_rate": 5.728637791002525e-06, + "loss": 0.2905, + "step": 7341 + }, + { + "epoch": 0.94, + "learning_rate": 5.727612352921116e-06, + "loss": 0.343, + "step": 7342 + }, + { + "epoch": 0.94, + "learning_rate": 5.726586883572584e-06, + "loss": 0.2787, + "step": 7343 + }, + { + "epoch": 0.94, + "learning_rate": 5.725561383000994e-06, + "loss": 0.3122, + "step": 7344 + }, + { + "epoch": 0.94, + "learning_rate": 5.724535851250416e-06, + "loss": 0.3226, + "step": 7345 + }, + { + "epoch": 0.94, + "learning_rate": 5.723510288364918e-06, + "loss": 0.2985, + "step": 7346 + }, + { + "epoch": 0.94, + "learning_rate": 5.722484694388573e-06, + "loss": 0.282, + "step": 7347 + }, + { + "epoch": 0.94, + "learning_rate": 5.721459069365452e-06, + "loss": 0.2877, + "step": 7348 + }, + { + "epoch": 0.94, + "learning_rate": 5.720433413339627e-06, + "loss": 0.3072, + "step": 7349 + }, + { + "epoch": 0.94, + "learning_rate": 5.719407726355174e-06, + "loss": 0.3248, + "step": 7350 + }, + { + "epoch": 0.94, + "learning_rate": 5.718382008456168e-06, + "loss": 0.3057, + "step": 7351 + }, + { + "epoch": 0.94, + "learning_rate": 5.717356259686689e-06, + "loss": 0.3224, + "step": 7352 + }, + { + "epoch": 0.94, + "learning_rate": 5.716330480090812e-06, + "loss": 0.284, + "step": 7353 + }, + { + "epoch": 0.94, + "learning_rate": 5.71530466971262e-06, + "loss": 0.317, + "step": 7354 + }, + { + "epoch": 0.94, + "learning_rate": 5.714278828596192e-06, + "loss": 0.3212, + "step": 7355 + }, + { + "epoch": 0.94, + "learning_rate": 5.713252956785613e-06, + "loss": 0.303, + "step": 7356 + }, + { + "epoch": 0.94, + "learning_rate": 5.712227054324968e-06, + "loss": 0.3023, + "step": 7357 + }, + { + "epoch": 0.94, + "learning_rate": 5.711201121258337e-06, + "loss": 0.2992, + "step": 7358 + }, + { + "epoch": 0.94, + "learning_rate": 5.710175157629812e-06, + "loss": 0.3022, + "step": 7359 + }, + { + "epoch": 0.94, + "learning_rate": 5.709149163483476e-06, + "loss": 0.3204, + "step": 7360 + }, + { + "epoch": 0.94, + "learning_rate": 5.708123138863424e-06, + "loss": 0.3167, + "step": 7361 + }, + { + "epoch": 0.94, + "learning_rate": 5.707097083813743e-06, + "loss": 0.3202, + "step": 7362 + }, + { + "epoch": 0.94, + "learning_rate": 5.706070998378524e-06, + "loss": 0.2813, + "step": 7363 + }, + { + "epoch": 0.94, + "learning_rate": 5.705044882601862e-06, + "loss": 0.3154, + "step": 7364 + }, + { + "epoch": 0.94, + "learning_rate": 5.704018736527853e-06, + "loss": 0.2994, + "step": 7365 + }, + { + "epoch": 0.94, + "learning_rate": 5.7029925602005905e-06, + "loss": 0.3335, + "step": 7366 + }, + { + "epoch": 0.94, + "learning_rate": 5.701966353664171e-06, + "loss": 0.299, + "step": 7367 + }, + { + "epoch": 0.94, + "learning_rate": 5.7009401169626955e-06, + "loss": 0.2873, + "step": 7368 + }, + { + "epoch": 0.94, + "learning_rate": 5.69991385014026e-06, + "loss": 0.3212, + "step": 7369 + }, + { + "epoch": 0.94, + "learning_rate": 5.698887553240968e-06, + "loss": 0.2779, + "step": 7370 + }, + { + "epoch": 0.94, + "learning_rate": 5.697861226308923e-06, + "loss": 0.3344, + "step": 7371 + }, + { + "epoch": 0.94, + "learning_rate": 5.696834869388226e-06, + "loss": 0.2881, + "step": 7372 + }, + { + "epoch": 0.94, + "learning_rate": 5.695808482522982e-06, + "loss": 0.3148, + "step": 7373 + }, + { + "epoch": 0.94, + "learning_rate": 5.694782065757298e-06, + "loss": 0.3083, + "step": 7374 + }, + { + "epoch": 0.94, + "learning_rate": 5.693755619135282e-06, + "loss": 0.3007, + "step": 7375 + }, + { + "epoch": 0.94, + "learning_rate": 5.692729142701042e-06, + "loss": 0.277, + "step": 7376 + }, + { + "epoch": 0.94, + "learning_rate": 5.691702636498688e-06, + "loss": 0.3151, + "step": 7377 + }, + { + "epoch": 0.94, + "learning_rate": 5.69067610057233e-06, + "loss": 0.319, + "step": 7378 + }, + { + "epoch": 0.94, + "learning_rate": 5.689649534966083e-06, + "loss": 0.2952, + "step": 7379 + }, + { + "epoch": 0.94, + "learning_rate": 5.6886229397240585e-06, + "loss": 0.3102, + "step": 7380 + }, + { + "epoch": 0.94, + "learning_rate": 5.6875963148903735e-06, + "loss": 0.3011, + "step": 7381 + }, + { + "epoch": 0.94, + "learning_rate": 5.6865696605091426e-06, + "loss": 0.3203, + "step": 7382 + }, + { + "epoch": 0.95, + "learning_rate": 5.685542976624485e-06, + "loss": 0.3279, + "step": 7383 + }, + { + "epoch": 0.95, + "learning_rate": 5.684516263280519e-06, + "loss": 0.293, + "step": 7384 + }, + { + "epoch": 0.95, + "learning_rate": 5.683489520521365e-06, + "loss": 0.3099, + "step": 7385 + }, + { + "epoch": 0.95, + "learning_rate": 5.682462748391144e-06, + "loss": 0.2915, + "step": 7386 + }, + { + "epoch": 0.95, + "learning_rate": 5.681435946933978e-06, + "loss": 0.308, + "step": 7387 + }, + { + "epoch": 0.95, + "learning_rate": 5.680409116193991e-06, + "loss": 0.3232, + "step": 7388 + }, + { + "epoch": 0.95, + "learning_rate": 5.679382256215311e-06, + "loss": 0.2855, + "step": 7389 + }, + { + "epoch": 0.95, + "learning_rate": 5.678355367042061e-06, + "loss": 0.2912, + "step": 7390 + }, + { + "epoch": 0.95, + "learning_rate": 5.67732844871837e-06, + "loss": 0.3035, + "step": 7391 + }, + { + "epoch": 0.95, + "learning_rate": 5.6763015012883686e-06, + "loss": 0.3359, + "step": 7392 + }, + { + "epoch": 0.95, + "learning_rate": 5.675274524796184e-06, + "loss": 0.2984, + "step": 7393 + }, + { + "epoch": 0.95, + "learning_rate": 5.674247519285951e-06, + "loss": 0.2943, + "step": 7394 + }, + { + "epoch": 0.95, + "learning_rate": 5.673220484801798e-06, + "loss": 0.3112, + "step": 7395 + }, + { + "epoch": 0.95, + "learning_rate": 5.672193421387862e-06, + "loss": 0.29, + "step": 7396 + }, + { + "epoch": 0.95, + "learning_rate": 5.671166329088278e-06, + "loss": 0.3136, + "step": 7397 + }, + { + "epoch": 0.95, + "learning_rate": 5.6701392079471825e-06, + "loss": 0.324, + "step": 7398 + }, + { + "epoch": 0.95, + "learning_rate": 5.6691120580087126e-06, + "loss": 0.3186, + "step": 7399 + }, + { + "epoch": 0.95, + "learning_rate": 5.668084879317006e-06, + "loss": 0.3186, + "step": 7400 + }, + { + "epoch": 0.95, + "learning_rate": 5.6670576719162065e-06, + "loss": 0.2977, + "step": 7401 + }, + { + "epoch": 0.95, + "learning_rate": 5.6660304358504524e-06, + "loss": 0.2803, + "step": 7402 + }, + { + "epoch": 0.95, + "learning_rate": 5.665003171163886e-06, + "loss": 0.3109, + "step": 7403 + }, + { + "epoch": 0.95, + "learning_rate": 5.6639758779006535e-06, + "loss": 0.3091, + "step": 7404 + }, + { + "epoch": 0.95, + "learning_rate": 5.662948556104898e-06, + "loss": 0.299, + "step": 7405 + }, + { + "epoch": 0.95, + "learning_rate": 5.661921205820767e-06, + "loss": 0.2964, + "step": 7406 + }, + { + "epoch": 0.95, + "learning_rate": 5.660893827092407e-06, + "loss": 0.2873, + "step": 7407 + }, + { + "epoch": 0.95, + "learning_rate": 5.659866419963969e-06, + "loss": 0.2782, + "step": 7408 + }, + { + "epoch": 0.95, + "learning_rate": 5.6588389844796e-06, + "loss": 0.3166, + "step": 7409 + }, + { + "epoch": 0.95, + "learning_rate": 5.657811520683454e-06, + "loss": 0.3097, + "step": 7410 + }, + { + "epoch": 0.95, + "learning_rate": 5.656784028619681e-06, + "loss": 0.3074, + "step": 7411 + }, + { + "epoch": 0.95, + "learning_rate": 5.655756508332434e-06, + "loss": 0.2887, + "step": 7412 + }, + { + "epoch": 0.95, + "learning_rate": 5.654728959865872e-06, + "loss": 0.3291, + "step": 7413 + }, + { + "epoch": 0.95, + "learning_rate": 5.653701383264147e-06, + "loss": 0.2883, + "step": 7414 + }, + { + "epoch": 0.95, + "learning_rate": 5.652673778571418e-06, + "loss": 0.31, + "step": 7415 + }, + { + "epoch": 0.95, + "learning_rate": 5.651646145831842e-06, + "loss": 0.3177, + "step": 7416 + }, + { + "epoch": 0.95, + "learning_rate": 5.650618485089582e-06, + "loss": 0.2741, + "step": 7417 + }, + { + "epoch": 0.95, + "learning_rate": 5.649590796388794e-06, + "loss": 0.3181, + "step": 7418 + }, + { + "epoch": 0.95, + "learning_rate": 5.648563079773646e-06, + "loss": 0.3116, + "step": 7419 + }, + { + "epoch": 0.95, + "learning_rate": 5.647535335288296e-06, + "loss": 0.3051, + "step": 7420 + }, + { + "epoch": 0.95, + "learning_rate": 5.6465075629769095e-06, + "loss": 0.3169, + "step": 7421 + }, + { + "epoch": 0.95, + "learning_rate": 5.645479762883657e-06, + "loss": 0.2686, + "step": 7422 + }, + { + "epoch": 0.95, + "learning_rate": 5.644451935052697e-06, + "loss": 0.2533, + "step": 7423 + }, + { + "epoch": 0.95, + "learning_rate": 5.6434240795282045e-06, + "loss": 0.3195, + "step": 7424 + }, + { + "epoch": 0.95, + "learning_rate": 5.642396196354345e-06, + "loss": 0.2724, + "step": 7425 + }, + { + "epoch": 0.95, + "learning_rate": 5.641368285575292e-06, + "loss": 0.3114, + "step": 7426 + }, + { + "epoch": 0.95, + "learning_rate": 5.640340347235215e-06, + "loss": 0.3312, + "step": 7427 + }, + { + "epoch": 0.95, + "learning_rate": 5.639312381378286e-06, + "loss": 0.2842, + "step": 7428 + }, + { + "epoch": 0.95, + "learning_rate": 5.63828438804868e-06, + "loss": 0.2993, + "step": 7429 + }, + { + "epoch": 0.95, + "learning_rate": 5.637256367290573e-06, + "loss": 0.2956, + "step": 7430 + }, + { + "epoch": 0.95, + "learning_rate": 5.636228319148141e-06, + "loss": 0.321, + "step": 7431 + }, + { + "epoch": 0.95, + "learning_rate": 5.635200243665562e-06, + "loss": 0.3018, + "step": 7432 + }, + { + "epoch": 0.95, + "learning_rate": 5.634172140887013e-06, + "loss": 0.3215, + "step": 7433 + }, + { + "epoch": 0.95, + "learning_rate": 5.6331440108566735e-06, + "loss": 0.3095, + "step": 7434 + }, + { + "epoch": 0.95, + "learning_rate": 5.632115853618727e-06, + "loss": 0.2971, + "step": 7435 + }, + { + "epoch": 0.95, + "learning_rate": 5.631087669217356e-06, + "loss": 0.2943, + "step": 7436 + }, + { + "epoch": 0.95, + "learning_rate": 5.630059457696741e-06, + "loss": 0.3047, + "step": 7437 + }, + { + "epoch": 0.95, + "learning_rate": 5.629031219101065e-06, + "loss": 0.3185, + "step": 7438 + }, + { + "epoch": 0.95, + "learning_rate": 5.628002953474521e-06, + "loss": 0.2946, + "step": 7439 + }, + { + "epoch": 0.95, + "learning_rate": 5.626974660861288e-06, + "loss": 0.3233, + "step": 7440 + }, + { + "epoch": 0.95, + "learning_rate": 5.6259463413055604e-06, + "loss": 0.3046, + "step": 7441 + }, + { + "epoch": 0.95, + "learning_rate": 5.624917994851523e-06, + "loss": 0.2912, + "step": 7442 + }, + { + "epoch": 0.95, + "learning_rate": 5.6238896215433666e-06, + "loss": 0.3205, + "step": 7443 + }, + { + "epoch": 0.95, + "learning_rate": 5.622861221425286e-06, + "loss": 0.2811, + "step": 7444 + }, + { + "epoch": 0.95, + "learning_rate": 5.6218327945414695e-06, + "loss": 0.306, + "step": 7445 + }, + { + "epoch": 0.95, + "learning_rate": 5.620804340936114e-06, + "loss": 0.3413, + "step": 7446 + }, + { + "epoch": 0.95, + "learning_rate": 5.619775860653412e-06, + "loss": 0.3249, + "step": 7447 + }, + { + "epoch": 0.95, + "learning_rate": 5.6187473537375635e-06, + "loss": 0.299, + "step": 7448 + }, + { + "epoch": 0.95, + "learning_rate": 5.617718820232762e-06, + "loss": 0.3119, + "step": 7449 + }, + { + "epoch": 0.95, + "learning_rate": 5.616690260183206e-06, + "loss": 0.3127, + "step": 7450 + }, + { + "epoch": 0.95, + "learning_rate": 5.615661673633098e-06, + "loss": 0.2926, + "step": 7451 + }, + { + "epoch": 0.95, + "learning_rate": 5.614633060626634e-06, + "loss": 0.2883, + "step": 7452 + }, + { + "epoch": 0.95, + "learning_rate": 5.613604421208021e-06, + "loss": 0.2814, + "step": 7453 + }, + { + "epoch": 0.95, + "learning_rate": 5.612575755421459e-06, + "loss": 0.3307, + "step": 7454 + }, + { + "epoch": 0.95, + "learning_rate": 5.611547063311152e-06, + "loss": 0.3254, + "step": 7455 + }, + { + "epoch": 0.95, + "learning_rate": 5.610518344921305e-06, + "loss": 0.2902, + "step": 7456 + }, + { + "epoch": 0.95, + "learning_rate": 5.609489600296127e-06, + "loss": 0.3056, + "step": 7457 + }, + { + "epoch": 0.95, + "learning_rate": 5.608460829479821e-06, + "loss": 0.288, + "step": 7458 + }, + { + "epoch": 0.95, + "learning_rate": 5.607432032516601e-06, + "loss": 0.2858, + "step": 7459 + }, + { + "epoch": 0.95, + "learning_rate": 5.606403209450672e-06, + "loss": 0.2724, + "step": 7460 + }, + { + "epoch": 0.96, + "learning_rate": 5.605374360326246e-06, + "loss": 0.2976, + "step": 7461 + }, + { + "epoch": 0.96, + "learning_rate": 5.604345485187535e-06, + "loss": 0.2802, + "step": 7462 + }, + { + "epoch": 0.96, + "learning_rate": 5.603316584078754e-06, + "loss": 0.2888, + "step": 7463 + }, + { + "epoch": 0.96, + "learning_rate": 5.602287657044116e-06, + "loss": 0.315, + "step": 7464 + }, + { + "epoch": 0.96, + "learning_rate": 5.601258704127835e-06, + "loss": 0.3012, + "step": 7465 + }, + { + "epoch": 0.96, + "learning_rate": 5.600229725374129e-06, + "loss": 0.3093, + "step": 7466 + }, + { + "epoch": 0.96, + "learning_rate": 5.599200720827215e-06, + "loss": 0.2708, + "step": 7467 + }, + { + "epoch": 0.96, + "learning_rate": 5.598171690531312e-06, + "loss": 0.2894, + "step": 7468 + }, + { + "epoch": 0.96, + "learning_rate": 5.597142634530639e-06, + "loss": 0.295, + "step": 7469 + }, + { + "epoch": 0.96, + "learning_rate": 5.5961135528694155e-06, + "loss": 0.3396, + "step": 7470 + }, + { + "epoch": 0.96, + "learning_rate": 5.595084445591866e-06, + "loss": 0.3007, + "step": 7471 + }, + { + "epoch": 0.96, + "learning_rate": 5.594055312742213e-06, + "loss": 0.3026, + "step": 7472 + }, + { + "epoch": 0.96, + "learning_rate": 5.59302615436468e-06, + "loss": 0.3306, + "step": 7473 + }, + { + "epoch": 0.96, + "learning_rate": 5.5919969705034914e-06, + "loss": 0.3164, + "step": 7474 + }, + { + "epoch": 0.96, + "learning_rate": 5.590967761202876e-06, + "loss": 0.3158, + "step": 7475 + }, + { + "epoch": 0.96, + "learning_rate": 5.589938526507059e-06, + "loss": 0.296, + "step": 7476 + }, + { + "epoch": 0.96, + "learning_rate": 5.5889092664602696e-06, + "loss": 0.2778, + "step": 7477 + }, + { + "epoch": 0.96, + "learning_rate": 5.5878799811067384e-06, + "loss": 0.2985, + "step": 7478 + }, + { + "epoch": 0.96, + "learning_rate": 5.586850670490694e-06, + "loss": 0.3078, + "step": 7479 + }, + { + "epoch": 0.96, + "learning_rate": 5.58582133465637e-06, + "loss": 0.3168, + "step": 7480 + }, + { + "epoch": 0.96, + "learning_rate": 5.584791973647997e-06, + "loss": 0.3085, + "step": 7481 + }, + { + "epoch": 0.96, + "learning_rate": 5.583762587509812e-06, + "loss": 0.3304, + "step": 7482 + }, + { + "epoch": 0.96, + "learning_rate": 5.582733176286048e-06, + "loss": 0.2847, + "step": 7483 + }, + { + "epoch": 0.96, + "learning_rate": 5.581703740020943e-06, + "loss": 0.3407, + "step": 7484 + }, + { + "epoch": 0.96, + "learning_rate": 5.580674278758732e-06, + "loss": 0.2871, + "step": 7485 + }, + { + "epoch": 0.96, + "learning_rate": 5.579644792543653e-06, + "loss": 0.2974, + "step": 7486 + }, + { + "epoch": 0.96, + "learning_rate": 5.578615281419947e-06, + "loss": 0.2944, + "step": 7487 + }, + { + "epoch": 0.96, + "learning_rate": 5.577585745431854e-06, + "loss": 0.3117, + "step": 7488 + }, + { + "epoch": 0.96, + "learning_rate": 5.576556184623615e-06, + "loss": 0.2948, + "step": 7489 + }, + { + "epoch": 0.96, + "learning_rate": 5.575526599039472e-06, + "loss": 0.3198, + "step": 7490 + }, + { + "epoch": 0.96, + "learning_rate": 5.574496988723669e-06, + "loss": 0.3141, + "step": 7491 + }, + { + "epoch": 0.96, + "learning_rate": 5.573467353720452e-06, + "loss": 0.2831, + "step": 7492 + }, + { + "epoch": 0.96, + "learning_rate": 5.572437694074065e-06, + "loss": 0.314, + "step": 7493 + }, + { + "epoch": 0.96, + "learning_rate": 5.571408009828757e-06, + "loss": 0.2971, + "step": 7494 + }, + { + "epoch": 0.96, + "learning_rate": 5.570378301028771e-06, + "loss": 0.3348, + "step": 7495 + }, + { + "epoch": 0.96, + "learning_rate": 5.569348567718363e-06, + "loss": 0.2893, + "step": 7496 + }, + { + "epoch": 0.96, + "learning_rate": 5.568318809941777e-06, + "loss": 0.3162, + "step": 7497 + }, + { + "epoch": 0.96, + "learning_rate": 5.567289027743266e-06, + "loss": 0.3519, + "step": 7498 + }, + { + "epoch": 0.96, + "learning_rate": 5.56625922116708e-06, + "loss": 0.3255, + "step": 7499 + }, + { + "epoch": 0.96, + "learning_rate": 5.565229390257478e-06, + "loss": 0.3387, + "step": 7500 + }, + { + "epoch": 0.96, + "learning_rate": 5.564199535058708e-06, + "loss": 0.3053, + "step": 7501 + }, + { + "epoch": 0.96, + "learning_rate": 5.563169655615029e-06, + "loss": 0.3048, + "step": 7502 + }, + { + "epoch": 0.96, + "learning_rate": 5.562139751970694e-06, + "loss": 0.2912, + "step": 7503 + }, + { + "epoch": 0.96, + "learning_rate": 5.561109824169962e-06, + "loss": 0.2988, + "step": 7504 + }, + { + "epoch": 0.96, + "learning_rate": 5.5600798722570925e-06, + "loss": 0.3321, + "step": 7505 + }, + { + "epoch": 0.96, + "learning_rate": 5.559049896276343e-06, + "loss": 0.2999, + "step": 7506 + }, + { + "epoch": 0.96, + "learning_rate": 5.558019896271975e-06, + "loss": 0.3135, + "step": 7507 + }, + { + "epoch": 0.96, + "learning_rate": 5.556989872288248e-06, + "loss": 0.2839, + "step": 7508 + }, + { + "epoch": 0.96, + "learning_rate": 5.555959824369426e-06, + "loss": 0.2988, + "step": 7509 + }, + { + "epoch": 0.96, + "learning_rate": 5.554929752559772e-06, + "loss": 0.294, + "step": 7510 + }, + { + "epoch": 0.96, + "learning_rate": 5.553899656903552e-06, + "loss": 0.2645, + "step": 7511 + }, + { + "epoch": 0.96, + "learning_rate": 5.552869537445029e-06, + "loss": 0.3311, + "step": 7512 + }, + { + "epoch": 0.96, + "learning_rate": 5.55183939422847e-06, + "loss": 0.2808, + "step": 7513 + }, + { + "epoch": 0.96, + "learning_rate": 5.550809227298144e-06, + "loss": 0.3055, + "step": 7514 + }, + { + "epoch": 0.96, + "learning_rate": 5.54977903669832e-06, + "loss": 0.2816, + "step": 7515 + }, + { + "epoch": 0.96, + "learning_rate": 5.548748822473265e-06, + "loss": 0.2995, + "step": 7516 + }, + { + "epoch": 0.96, + "learning_rate": 5.54771858466725e-06, + "loss": 0.2969, + "step": 7517 + }, + { + "epoch": 0.96, + "learning_rate": 5.546688323324548e-06, + "loss": 0.3089, + "step": 7518 + }, + { + "epoch": 0.96, + "learning_rate": 5.545658038489433e-06, + "loss": 0.3102, + "step": 7519 + }, + { + "epoch": 0.96, + "learning_rate": 5.544627730206176e-06, + "loss": 0.2997, + "step": 7520 + }, + { + "epoch": 0.96, + "learning_rate": 5.543597398519053e-06, + "loss": 0.3124, + "step": 7521 + }, + { + "epoch": 0.96, + "learning_rate": 5.542567043472337e-06, + "loss": 0.3103, + "step": 7522 + }, + { + "epoch": 0.96, + "learning_rate": 5.541536665110309e-06, + "loss": 0.3135, + "step": 7523 + }, + { + "epoch": 0.96, + "learning_rate": 5.540506263477243e-06, + "loss": 0.3145, + "step": 7524 + }, + { + "epoch": 0.96, + "learning_rate": 5.53947583861742e-06, + "loss": 0.3152, + "step": 7525 + }, + { + "epoch": 0.96, + "learning_rate": 5.5384453905751175e-06, + "loss": 0.3143, + "step": 7526 + }, + { + "epoch": 0.96, + "learning_rate": 5.537414919394618e-06, + "loss": 0.2943, + "step": 7527 + }, + { + "epoch": 0.96, + "learning_rate": 5.536384425120202e-06, + "loss": 0.2875, + "step": 7528 + }, + { + "epoch": 0.96, + "learning_rate": 5.535353907796155e-06, + "loss": 0.307, + "step": 7529 + }, + { + "epoch": 0.96, + "learning_rate": 5.534323367466758e-06, + "loss": 0.3213, + "step": 7530 + }, + { + "epoch": 0.96, + "learning_rate": 5.5332928041762936e-06, + "loss": 0.3098, + "step": 7531 + }, + { + "epoch": 0.96, + "learning_rate": 5.5322622179690514e-06, + "loss": 0.3159, + "step": 7532 + }, + { + "epoch": 0.96, + "learning_rate": 5.531231608889313e-06, + "loss": 0.329, + "step": 7533 + }, + { + "epoch": 0.96, + "learning_rate": 5.530200976981375e-06, + "loss": 0.2854, + "step": 7534 + }, + { + "epoch": 0.96, + "learning_rate": 5.529170322289515e-06, + "loss": 0.2875, + "step": 7535 + }, + { + "epoch": 0.96, + "learning_rate": 5.528139644858031e-06, + "loss": 0.3109, + "step": 7536 + }, + { + "epoch": 0.96, + "learning_rate": 5.527108944731207e-06, + "loss": 0.2931, + "step": 7537 + }, + { + "epoch": 0.96, + "learning_rate": 5.526078221953341e-06, + "loss": 0.2856, + "step": 7538 + }, + { + "epoch": 0.96, + "learning_rate": 5.525047476568722e-06, + "loss": 0.29, + "step": 7539 + }, + { + "epoch": 0.97, + "learning_rate": 5.524016708621641e-06, + "loss": 0.3033, + "step": 7540 + }, + { + "epoch": 0.97, + "learning_rate": 5.522985918156397e-06, + "loss": 0.3068, + "step": 7541 + }, + { + "epoch": 0.97, + "learning_rate": 5.5219551052172825e-06, + "loss": 0.3337, + "step": 7542 + }, + { + "epoch": 0.97, + "learning_rate": 5.5209242698485955e-06, + "loss": 0.3074, + "step": 7543 + }, + { + "epoch": 0.97, + "learning_rate": 5.519893412094631e-06, + "loss": 0.2862, + "step": 7544 + }, + { + "epoch": 0.97, + "learning_rate": 5.518862531999691e-06, + "loss": 0.3159, + "step": 7545 + }, + { + "epoch": 0.97, + "learning_rate": 5.51783162960807e-06, + "loss": 0.3045, + "step": 7546 + }, + { + "epoch": 0.97, + "learning_rate": 5.516800704964071e-06, + "loss": 0.2825, + "step": 7547 + }, + { + "epoch": 0.97, + "learning_rate": 5.515769758111996e-06, + "loss": 0.2751, + "step": 7548 + }, + { + "epoch": 0.97, + "learning_rate": 5.514738789096146e-06, + "loss": 0.296, + "step": 7549 + }, + { + "epoch": 0.97, + "learning_rate": 5.513707797960823e-06, + "loss": 0.2998, + "step": 7550 + }, + { + "epoch": 0.97, + "learning_rate": 5.512676784750332e-06, + "loss": 0.2987, + "step": 7551 + }, + { + "epoch": 0.97, + "learning_rate": 5.511645749508977e-06, + "loss": 0.3178, + "step": 7552 + }, + { + "epoch": 0.97, + "learning_rate": 5.5106146922810664e-06, + "loss": 0.2956, + "step": 7553 + }, + { + "epoch": 0.97, + "learning_rate": 5.509583613110904e-06, + "loss": 0.2803, + "step": 7554 + }, + { + "epoch": 0.97, + "learning_rate": 5.508552512042799e-06, + "loss": 0.3317, + "step": 7555 + }, + { + "epoch": 0.97, + "learning_rate": 5.50752138912106e-06, + "loss": 0.2933, + "step": 7556 + }, + { + "epoch": 0.97, + "learning_rate": 5.506490244389997e-06, + "loss": 0.2957, + "step": 7557 + }, + { + "epoch": 0.97, + "learning_rate": 5.50545907789392e-06, + "loss": 0.3192, + "step": 7558 + }, + { + "epoch": 0.97, + "learning_rate": 5.504427889677141e-06, + "loss": 0.3028, + "step": 7559 + }, + { + "epoch": 0.97, + "learning_rate": 5.50339667978397e-06, + "loss": 0.2865, + "step": 7560 + }, + { + "epoch": 0.97, + "learning_rate": 5.502365448258724e-06, + "loss": 0.2903, + "step": 7561 + }, + { + "epoch": 0.97, + "learning_rate": 5.5013341951457166e-06, + "loss": 0.3325, + "step": 7562 + }, + { + "epoch": 0.97, + "learning_rate": 5.500302920489262e-06, + "loss": 0.3276, + "step": 7563 + }, + { + "epoch": 0.97, + "learning_rate": 5.499271624333676e-06, + "loss": 0.2913, + "step": 7564 + }, + { + "epoch": 0.97, + "learning_rate": 5.498240306723277e-06, + "loss": 0.3199, + "step": 7565 + }, + { + "epoch": 0.97, + "learning_rate": 5.497208967702382e-06, + "loss": 0.3175, + "step": 7566 + }, + { + "epoch": 0.97, + "learning_rate": 5.496177607315312e-06, + "loss": 0.3031, + "step": 7567 + }, + { + "epoch": 0.97, + "learning_rate": 5.495146225606383e-06, + "loss": 0.2909, + "step": 7568 + }, + { + "epoch": 0.97, + "learning_rate": 5.494114822619918e-06, + "loss": 0.2898, + "step": 7569 + }, + { + "epoch": 0.97, + "learning_rate": 5.493083398400239e-06, + "loss": 0.2944, + "step": 7570 + }, + { + "epoch": 0.97, + "learning_rate": 5.492051952991669e-06, + "loss": 0.3172, + "step": 7571 + }, + { + "epoch": 0.97, + "learning_rate": 5.4910204864385306e-06, + "loss": 0.2838, + "step": 7572 + }, + { + "epoch": 0.97, + "learning_rate": 5.489988998785147e-06, + "loss": 0.323, + "step": 7573 + }, + { + "epoch": 0.97, + "learning_rate": 5.488957490075846e-06, + "loss": 0.3097, + "step": 7574 + }, + { + "epoch": 0.97, + "learning_rate": 5.487925960354953e-06, + "loss": 0.3103, + "step": 7575 + }, + { + "epoch": 0.97, + "learning_rate": 5.486894409666794e-06, + "loss": 0.3129, + "step": 7576 + }, + { + "epoch": 0.97, + "learning_rate": 5.485862838055699e-06, + "loss": 0.3201, + "step": 7577 + }, + { + "epoch": 0.97, + "learning_rate": 5.4848312455659935e-06, + "loss": 0.2935, + "step": 7578 + }, + { + "epoch": 0.97, + "learning_rate": 5.483799632242012e-06, + "loss": 0.308, + "step": 7579 + }, + { + "epoch": 0.97, + "learning_rate": 5.482767998128081e-06, + "loss": 0.2979, + "step": 7580 + }, + { + "epoch": 0.97, + "learning_rate": 5.4817363432685355e-06, + "loss": 0.314, + "step": 7581 + }, + { + "epoch": 0.97, + "learning_rate": 5.4807046677077045e-06, + "loss": 0.3046, + "step": 7582 + }, + { + "epoch": 0.97, + "learning_rate": 5.479672971489924e-06, + "loss": 0.3255, + "step": 7583 + }, + { + "epoch": 0.97, + "learning_rate": 5.478641254659528e-06, + "loss": 0.3184, + "step": 7584 + }, + { + "epoch": 0.97, + "learning_rate": 5.4776095172608535e-06, + "loss": 0.3211, + "step": 7585 + }, + { + "epoch": 0.97, + "learning_rate": 5.476577759338232e-06, + "loss": 0.2969, + "step": 7586 + }, + { + "epoch": 0.97, + "learning_rate": 5.475545980936003e-06, + "loss": 0.3038, + "step": 7587 + }, + { + "epoch": 0.97, + "learning_rate": 5.474514182098504e-06, + "loss": 0.3219, + "step": 7588 + }, + { + "epoch": 0.97, + "learning_rate": 5.473482362870073e-06, + "loss": 0.289, + "step": 7589 + }, + { + "epoch": 0.97, + "learning_rate": 5.472450523295052e-06, + "loss": 0.2995, + "step": 7590 + }, + { + "epoch": 0.97, + "learning_rate": 5.471418663417779e-06, + "loss": 0.3003, + "step": 7591 + }, + { + "epoch": 0.97, + "learning_rate": 5.470386783282597e-06, + "loss": 0.3079, + "step": 7592 + }, + { + "epoch": 0.97, + "learning_rate": 5.469354882933845e-06, + "loss": 0.2862, + "step": 7593 + }, + { + "epoch": 0.97, + "learning_rate": 5.468322962415871e-06, + "loss": 0.3133, + "step": 7594 + }, + { + "epoch": 0.97, + "learning_rate": 5.4672910217730155e-06, + "loss": 0.3087, + "step": 7595 + }, + { + "epoch": 0.97, + "learning_rate": 5.4662590610496235e-06, + "loss": 0.305, + "step": 7596 + }, + { + "epoch": 0.97, + "learning_rate": 5.465227080290042e-06, + "loss": 0.3148, + "step": 7597 + }, + { + "epoch": 0.97, + "learning_rate": 5.464195079538615e-06, + "loss": 0.2828, + "step": 7598 + }, + { + "epoch": 0.97, + "learning_rate": 5.463163058839694e-06, + "loss": 0.2913, + "step": 7599 + }, + { + "epoch": 0.97, + "learning_rate": 5.462131018237623e-06, + "loss": 0.3146, + "step": 7600 + }, + { + "epoch": 0.97, + "learning_rate": 5.461098957776755e-06, + "loss": 0.3268, + "step": 7601 + }, + { + "epoch": 0.97, + "learning_rate": 5.4600668775014355e-06, + "loss": 0.3024, + "step": 7602 + }, + { + "epoch": 0.97, + "learning_rate": 5.459034777456018e-06, + "loss": 0.3272, + "step": 7603 + }, + { + "epoch": 0.97, + "learning_rate": 5.4580026576848565e-06, + "loss": 0.3098, + "step": 7604 + }, + { + "epoch": 0.97, + "learning_rate": 5.4569705182322975e-06, + "loss": 0.3018, + "step": 7605 + }, + { + "epoch": 0.97, + "learning_rate": 5.455938359142699e-06, + "loss": 0.312, + "step": 7606 + }, + { + "epoch": 0.97, + "learning_rate": 5.454906180460413e-06, + "loss": 0.2827, + "step": 7607 + }, + { + "epoch": 0.97, + "learning_rate": 5.453873982229797e-06, + "loss": 0.2754, + "step": 7608 + }, + { + "epoch": 0.97, + "learning_rate": 5.452841764495203e-06, + "loss": 0.2823, + "step": 7609 + }, + { + "epoch": 0.97, + "learning_rate": 5.451809527300992e-06, + "loss": 0.2843, + "step": 7610 + }, + { + "epoch": 0.97, + "learning_rate": 5.450777270691517e-06, + "loss": 0.2953, + "step": 7611 + }, + { + "epoch": 0.97, + "learning_rate": 5.449744994711141e-06, + "loss": 0.2761, + "step": 7612 + }, + { + "epoch": 0.97, + "learning_rate": 5.448712699404221e-06, + "loss": 0.3126, + "step": 7613 + }, + { + "epoch": 0.97, + "learning_rate": 5.4476803848151146e-06, + "loss": 0.2756, + "step": 7614 + }, + { + "epoch": 0.97, + "learning_rate": 5.446648050988187e-06, + "loss": 0.2866, + "step": 7615 + }, + { + "epoch": 0.97, + "learning_rate": 5.445615697967797e-06, + "loss": 0.297, + "step": 7616 + }, + { + "epoch": 0.97, + "learning_rate": 5.444583325798308e-06, + "loss": 0.278, + "step": 7617 + }, + { + "epoch": 0.98, + "learning_rate": 5.443550934524085e-06, + "loss": 0.3147, + "step": 7618 + }, + { + "epoch": 0.98, + "learning_rate": 5.442518524189489e-06, + "loss": 0.2934, + "step": 7619 + }, + { + "epoch": 0.98, + "learning_rate": 5.441486094838886e-06, + "loss": 0.288, + "step": 7620 + }, + { + "epoch": 0.98, + "learning_rate": 5.440453646516642e-06, + "loss": 0.2948, + "step": 7621 + }, + { + "epoch": 0.98, + "learning_rate": 5.439421179267126e-06, + "loss": 0.2941, + "step": 7622 + }, + { + "epoch": 0.98, + "learning_rate": 5.438388693134702e-06, + "loss": 0.299, + "step": 7623 + }, + { + "epoch": 0.98, + "learning_rate": 5.4373561881637405e-06, + "loss": 0.3141, + "step": 7624 + }, + { + "epoch": 0.98, + "learning_rate": 5.436323664398607e-06, + "loss": 0.2976, + "step": 7625 + }, + { + "epoch": 0.98, + "learning_rate": 5.435291121883675e-06, + "loss": 0.3081, + "step": 7626 + }, + { + "epoch": 0.98, + "learning_rate": 5.434258560663316e-06, + "loss": 0.304, + "step": 7627 + }, + { + "epoch": 0.98, + "learning_rate": 5.433225980781898e-06, + "loss": 0.3021, + "step": 7628 + }, + { + "epoch": 0.98, + "learning_rate": 5.432193382283794e-06, + "loss": 0.314, + "step": 7629 + }, + { + "epoch": 0.98, + "learning_rate": 5.431160765213379e-06, + "loss": 0.3249, + "step": 7630 + }, + { + "epoch": 0.98, + "learning_rate": 5.430128129615025e-06, + "loss": 0.2987, + "step": 7631 + }, + { + "epoch": 0.98, + "learning_rate": 5.429095475533108e-06, + "loss": 0.3034, + "step": 7632 + }, + { + "epoch": 0.98, + "learning_rate": 5.428062803012003e-06, + "loss": 0.3013, + "step": 7633 + }, + { + "epoch": 0.98, + "learning_rate": 5.4270301120960856e-06, + "loss": 0.285, + "step": 7634 + }, + { + "epoch": 0.98, + "learning_rate": 5.425997402829732e-06, + "loss": 0.2863, + "step": 7635 + }, + { + "epoch": 0.98, + "learning_rate": 5.424964675257324e-06, + "loss": 0.3183, + "step": 7636 + }, + { + "epoch": 0.98, + "learning_rate": 5.423931929423235e-06, + "loss": 0.2999, + "step": 7637 + }, + { + "epoch": 0.98, + "learning_rate": 5.422899165371846e-06, + "loss": 0.2938, + "step": 7638 + }, + { + "epoch": 0.98, + "learning_rate": 5.421866383147541e-06, + "loss": 0.2868, + "step": 7639 + }, + { + "epoch": 0.98, + "learning_rate": 5.420833582794696e-06, + "loss": 0.3049, + "step": 7640 + }, + { + "epoch": 0.98, + "learning_rate": 5.419800764357697e-06, + "loss": 0.3115, + "step": 7641 + }, + { + "epoch": 0.98, + "learning_rate": 5.418767927880923e-06, + "loss": 0.2817, + "step": 7642 + }, + { + "epoch": 0.98, + "learning_rate": 5.417735073408756e-06, + "loss": 0.2924, + "step": 7643 + }, + { + "epoch": 0.98, + "learning_rate": 5.416702200985585e-06, + "loss": 0.2766, + "step": 7644 + }, + { + "epoch": 0.98, + "learning_rate": 5.415669310655791e-06, + "loss": 0.2969, + "step": 7645 + }, + { + "epoch": 0.98, + "learning_rate": 5.414636402463764e-06, + "loss": 0.2968, + "step": 7646 + }, + { + "epoch": 0.98, + "learning_rate": 5.413603476453884e-06, + "loss": 0.3218, + "step": 7647 + }, + { + "epoch": 0.98, + "learning_rate": 5.4125705326705425e-06, + "loss": 0.2861, + "step": 7648 + }, + { + "epoch": 0.98, + "learning_rate": 5.411537571158127e-06, + "loss": 0.2931, + "step": 7649 + }, + { + "epoch": 0.98, + "learning_rate": 5.410504591961025e-06, + "loss": 0.2583, + "step": 7650 + }, + { + "epoch": 0.98, + "learning_rate": 5.409471595123628e-06, + "loss": 0.3064, + "step": 7651 + }, + { + "epoch": 0.98, + "learning_rate": 5.408438580690322e-06, + "loss": 0.2772, + "step": 7652 + }, + { + "epoch": 0.98, + "learning_rate": 5.4074055487055025e-06, + "loss": 0.341, + "step": 7653 + }, + { + "epoch": 0.98, + "learning_rate": 5.406372499213557e-06, + "loss": 0.3057, + "step": 7654 + }, + { + "epoch": 0.98, + "learning_rate": 5.4053394322588825e-06, + "loss": 0.3048, + "step": 7655 + }, + { + "epoch": 0.98, + "learning_rate": 5.404306347885868e-06, + "loss": 0.304, + "step": 7656 + }, + { + "epoch": 0.98, + "learning_rate": 5.403273246138912e-06, + "loss": 0.31, + "step": 7657 + }, + { + "epoch": 0.98, + "learning_rate": 5.4022401270624036e-06, + "loss": 0.3229, + "step": 7658 + }, + { + "epoch": 0.98, + "learning_rate": 5.401206990700741e-06, + "loss": 0.3031, + "step": 7659 + }, + { + "epoch": 0.98, + "learning_rate": 5.400173837098324e-06, + "loss": 0.2971, + "step": 7660 + }, + { + "epoch": 0.98, + "learning_rate": 5.399140666299543e-06, + "loss": 0.2946, + "step": 7661 + }, + { + "epoch": 0.98, + "learning_rate": 5.3981074783488e-06, + "loss": 0.3076, + "step": 7662 + }, + { + "epoch": 0.98, + "learning_rate": 5.3970742732904905e-06, + "loss": 0.2963, + "step": 7663 + }, + { + "epoch": 0.98, + "learning_rate": 5.396041051169016e-06, + "loss": 0.3016, + "step": 7664 + }, + { + "epoch": 0.98, + "learning_rate": 5.395007812028775e-06, + "loss": 0.2646, + "step": 7665 + }, + { + "epoch": 0.98, + "learning_rate": 5.39397455591417e-06, + "loss": 0.2973, + "step": 7666 + }, + { + "epoch": 0.98, + "learning_rate": 5.3929412828696006e-06, + "loss": 0.3171, + "step": 7667 + }, + { + "epoch": 0.98, + "learning_rate": 5.3919079929394665e-06, + "loss": 0.3108, + "step": 7668 + }, + { + "epoch": 0.98, + "learning_rate": 5.390874686168176e-06, + "loss": 0.299, + "step": 7669 + }, + { + "epoch": 0.98, + "learning_rate": 5.389841362600129e-06, + "loss": 0.2891, + "step": 7670 + }, + { + "epoch": 0.98, + "learning_rate": 5.388808022279731e-06, + "loss": 0.321, + "step": 7671 + }, + { + "epoch": 0.98, + "learning_rate": 5.387774665251385e-06, + "loss": 0.2873, + "step": 7672 + }, + { + "epoch": 0.98, + "learning_rate": 5.386741291559499e-06, + "loss": 0.3091, + "step": 7673 + }, + { + "epoch": 0.98, + "learning_rate": 5.385707901248478e-06, + "loss": 0.301, + "step": 7674 + }, + { + "epoch": 0.98, + "learning_rate": 5.3846744943627295e-06, + "loss": 0.2996, + "step": 7675 + }, + { + "epoch": 0.98, + "learning_rate": 5.38364107094666e-06, + "loss": 0.3, + "step": 7676 + }, + { + "epoch": 0.98, + "learning_rate": 5.382607631044682e-06, + "loss": 0.3028, + "step": 7677 + }, + { + "epoch": 0.98, + "learning_rate": 5.381574174701201e-06, + "loss": 0.321, + "step": 7678 + }, + { + "epoch": 0.98, + "learning_rate": 5.380540701960627e-06, + "loss": 0.2983, + "step": 7679 + }, + { + "epoch": 0.98, + "learning_rate": 5.379507212867372e-06, + "loss": 0.292, + "step": 7680 + }, + { + "epoch": 0.98, + "learning_rate": 5.378473707465847e-06, + "loss": 0.3417, + "step": 7681 + }, + { + "epoch": 0.98, + "learning_rate": 5.377440185800463e-06, + "loss": 0.3257, + "step": 7682 + }, + { + "epoch": 0.98, + "learning_rate": 5.376406647915635e-06, + "loss": 0.3424, + "step": 7683 + }, + { + "epoch": 0.98, + "learning_rate": 5.375373093855774e-06, + "loss": 0.3325, + "step": 7684 + }, + { + "epoch": 0.98, + "learning_rate": 5.374339523665295e-06, + "loss": 0.3042, + "step": 7685 + }, + { + "epoch": 0.98, + "learning_rate": 5.373305937388613e-06, + "loss": 0.3026, + "step": 7686 + }, + { + "epoch": 0.98, + "learning_rate": 5.372272335070145e-06, + "loss": 0.3115, + "step": 7687 + }, + { + "epoch": 0.98, + "learning_rate": 5.371238716754305e-06, + "loss": 0.2923, + "step": 7688 + }, + { + "epoch": 0.98, + "learning_rate": 5.37020508248551e-06, + "loss": 0.322, + "step": 7689 + }, + { + "epoch": 0.98, + "learning_rate": 5.369171432308178e-06, + "loss": 0.3389, + "step": 7690 + }, + { + "epoch": 0.98, + "learning_rate": 5.368137766266728e-06, + "loss": 0.3087, + "step": 7691 + }, + { + "epoch": 0.98, + "learning_rate": 5.367104084405578e-06, + "loss": 0.2808, + "step": 7692 + }, + { + "epoch": 0.98, + "learning_rate": 5.3660703867691475e-06, + "loss": 0.2745, + "step": 7693 + }, + { + "epoch": 0.98, + "learning_rate": 5.365036673401857e-06, + "loss": 0.3148, + "step": 7694 + }, + { + "epoch": 0.98, + "learning_rate": 5.364002944348129e-06, + "loss": 0.2854, + "step": 7695 + }, + { + "epoch": 0.99, + "learning_rate": 5.362969199652382e-06, + "loss": 0.3023, + "step": 7696 + }, + { + "epoch": 0.99, + "learning_rate": 5.361935439359042e-06, + "loss": 0.3398, + "step": 7697 + }, + { + "epoch": 0.99, + "learning_rate": 5.36090166351253e-06, + "loss": 0.2965, + "step": 7698 + }, + { + "epoch": 0.99, + "learning_rate": 5.359867872157267e-06, + "loss": 0.2874, + "step": 7699 + }, + { + "epoch": 0.99, + "learning_rate": 5.358834065337684e-06, + "loss": 0.3393, + "step": 7700 + }, + { + "epoch": 0.99, + "learning_rate": 5.357800243098199e-06, + "loss": 0.3039, + "step": 7701 + }, + { + "epoch": 0.99, + "learning_rate": 5.3567664054832426e-06, + "loss": 0.334, + "step": 7702 + }, + { + "epoch": 0.99, + "learning_rate": 5.355732552537237e-06, + "loss": 0.3041, + "step": 7703 + }, + { + "epoch": 0.99, + "learning_rate": 5.354698684304613e-06, + "loss": 0.2819, + "step": 7704 + }, + { + "epoch": 0.99, + "learning_rate": 5.353664800829796e-06, + "loss": 0.3031, + "step": 7705 + }, + { + "epoch": 0.99, + "learning_rate": 5.352630902157217e-06, + "loss": 0.2822, + "step": 7706 + }, + { + "epoch": 0.99, + "learning_rate": 5.3515969883313e-06, + "loss": 0.2874, + "step": 7707 + }, + { + "epoch": 0.99, + "learning_rate": 5.350563059396478e-06, + "loss": 0.3425, + "step": 7708 + }, + { + "epoch": 0.99, + "learning_rate": 5.3495291153971806e-06, + "loss": 0.2912, + "step": 7709 + }, + { + "epoch": 0.99, + "learning_rate": 5.348495156377839e-06, + "loss": 0.2944, + "step": 7710 + }, + { + "epoch": 0.99, + "learning_rate": 5.347461182382886e-06, + "loss": 0.3028, + "step": 7711 + }, + { + "epoch": 0.99, + "learning_rate": 5.346427193456749e-06, + "loss": 0.3012, + "step": 7712 + }, + { + "epoch": 0.99, + "learning_rate": 5.345393189643866e-06, + "loss": 0.2849, + "step": 7713 + }, + { + "epoch": 0.99, + "learning_rate": 5.344359170988668e-06, + "loss": 0.3147, + "step": 7714 + }, + { + "epoch": 0.99, + "learning_rate": 5.3433251375355884e-06, + "loss": 0.3091, + "step": 7715 + }, + { + "epoch": 0.99, + "learning_rate": 5.342291089329066e-06, + "loss": 0.3202, + "step": 7716 + }, + { + "epoch": 0.99, + "learning_rate": 5.34125702641353e-06, + "loss": 0.2913, + "step": 7717 + }, + { + "epoch": 0.99, + "learning_rate": 5.340222948833421e-06, + "loss": 0.303, + "step": 7718 + }, + { + "epoch": 0.99, + "learning_rate": 5.339188856633173e-06, + "loss": 0.2939, + "step": 7719 + }, + { + "epoch": 0.99, + "learning_rate": 5.338154749857225e-06, + "loss": 0.3127, + "step": 7720 + }, + { + "epoch": 0.99, + "learning_rate": 5.337120628550016e-06, + "loss": 0.2983, + "step": 7721 + }, + { + "epoch": 0.99, + "learning_rate": 5.3360864927559805e-06, + "loss": 0.3034, + "step": 7722 + }, + { + "epoch": 0.99, + "learning_rate": 5.335052342519561e-06, + "loss": 0.3234, + "step": 7723 + }, + { + "epoch": 0.99, + "learning_rate": 5.3340181778851954e-06, + "loss": 0.3118, + "step": 7724 + }, + { + "epoch": 0.99, + "learning_rate": 5.332983998897327e-06, + "loss": 0.2984, + "step": 7725 + }, + { + "epoch": 0.99, + "learning_rate": 5.331949805600391e-06, + "loss": 0.3054, + "step": 7726 + }, + { + "epoch": 0.99, + "learning_rate": 5.330915598038835e-06, + "loss": 0.296, + "step": 7727 + }, + { + "epoch": 0.99, + "learning_rate": 5.329881376257098e-06, + "loss": 0.3136, + "step": 7728 + }, + { + "epoch": 0.99, + "learning_rate": 5.328847140299624e-06, + "loss": 0.2964, + "step": 7729 + }, + { + "epoch": 0.99, + "learning_rate": 5.327812890210856e-06, + "loss": 0.3136, + "step": 7730 + }, + { + "epoch": 0.99, + "learning_rate": 5.326778626035238e-06, + "loss": 0.3128, + "step": 7731 + }, + { + "epoch": 0.99, + "learning_rate": 5.3257443478172146e-06, + "loss": 0.3287, + "step": 7732 + }, + { + "epoch": 0.99, + "learning_rate": 5.32471005560123e-06, + "loss": 0.3255, + "step": 7733 + }, + { + "epoch": 0.99, + "learning_rate": 5.323675749431732e-06, + "loss": 0.2995, + "step": 7734 + }, + { + "epoch": 0.99, + "learning_rate": 5.322641429353167e-06, + "loss": 0.312, + "step": 7735 + }, + { + "epoch": 0.99, + "learning_rate": 5.321607095409981e-06, + "loss": 0.3211, + "step": 7736 + }, + { + "epoch": 0.99, + "learning_rate": 5.3205727476466206e-06, + "loss": 0.3204, + "step": 7737 + }, + { + "epoch": 0.99, + "learning_rate": 5.3195383861075365e-06, + "loss": 0.2977, + "step": 7738 + }, + { + "epoch": 0.99, + "learning_rate": 5.318504010837175e-06, + "loss": 0.2934, + "step": 7739 + }, + { + "epoch": 0.99, + "learning_rate": 5.3174696218799894e-06, + "loss": 0.324, + "step": 7740 + }, + { + "epoch": 0.99, + "learning_rate": 5.316435219280425e-06, + "loss": 0.2972, + "step": 7741 + }, + { + "epoch": 0.99, + "learning_rate": 5.315400803082934e-06, + "loss": 0.2956, + "step": 7742 + }, + { + "epoch": 0.99, + "learning_rate": 5.314366373331969e-06, + "loss": 0.3102, + "step": 7743 + }, + { + "epoch": 0.99, + "learning_rate": 5.313331930071981e-06, + "loss": 0.2832, + "step": 7744 + }, + { + "epoch": 0.99, + "learning_rate": 5.312297473347422e-06, + "loss": 0.307, + "step": 7745 + }, + { + "epoch": 0.99, + "learning_rate": 5.311263003202745e-06, + "loss": 0.3031, + "step": 7746 + }, + { + "epoch": 0.99, + "learning_rate": 5.310228519682403e-06, + "loss": 0.2928, + "step": 7747 + }, + { + "epoch": 0.99, + "learning_rate": 5.309194022830852e-06, + "loss": 0.2996, + "step": 7748 + }, + { + "epoch": 0.99, + "learning_rate": 5.308159512692544e-06, + "loss": 0.3338, + "step": 7749 + }, + { + "epoch": 0.99, + "learning_rate": 5.307124989311936e-06, + "loss": 0.2726, + "step": 7750 + }, + { + "epoch": 0.99, + "learning_rate": 5.306090452733482e-06, + "loss": 0.3061, + "step": 7751 + }, + { + "epoch": 0.99, + "learning_rate": 5.305055903001642e-06, + "loss": 0.3187, + "step": 7752 + }, + { + "epoch": 0.99, + "learning_rate": 5.304021340160868e-06, + "loss": 0.2967, + "step": 7753 + }, + { + "epoch": 0.99, + "learning_rate": 5.302986764255621e-06, + "loss": 0.3261, + "step": 7754 + }, + { + "epoch": 0.99, + "learning_rate": 5.301952175330357e-06, + "loss": 0.305, + "step": 7755 + }, + { + "epoch": 0.99, + "learning_rate": 5.300917573429536e-06, + "loss": 0.335, + "step": 7756 + }, + { + "epoch": 0.99, + "learning_rate": 5.299882958597617e-06, + "loss": 0.2856, + "step": 7757 + }, + { + "epoch": 0.99, + "learning_rate": 5.298848330879061e-06, + "loss": 0.3026, + "step": 7758 + }, + { + "epoch": 0.99, + "learning_rate": 5.297813690318325e-06, + "loss": 0.3066, + "step": 7759 + }, + { + "epoch": 0.99, + "learning_rate": 5.29677903695987e-06, + "loss": 0.3381, + "step": 7760 + }, + { + "epoch": 0.99, + "learning_rate": 5.295744370848162e-06, + "loss": 0.2964, + "step": 7761 + }, + { + "epoch": 0.99, + "learning_rate": 5.294709692027658e-06, + "loss": 0.2888, + "step": 7762 + }, + { + "epoch": 0.99, + "learning_rate": 5.293675000542822e-06, + "loss": 0.3157, + "step": 7763 + }, + { + "epoch": 0.99, + "learning_rate": 5.292640296438116e-06, + "loss": 0.2843, + "step": 7764 + }, + { + "epoch": 0.99, + "learning_rate": 5.291605579758007e-06, + "loss": 0.3209, + "step": 7765 + }, + { + "epoch": 0.99, + "learning_rate": 5.290570850546954e-06, + "loss": 0.2912, + "step": 7766 + }, + { + "epoch": 0.99, + "learning_rate": 5.289536108849429e-06, + "loss": 0.3324, + "step": 7767 + }, + { + "epoch": 0.99, + "learning_rate": 5.28850135470989e-06, + "loss": 0.306, + "step": 7768 + }, + { + "epoch": 0.99, + "learning_rate": 5.287466588172804e-06, + "loss": 0.285, + "step": 7769 + }, + { + "epoch": 0.99, + "learning_rate": 5.286431809282639e-06, + "loss": 0.2939, + "step": 7770 + }, + { + "epoch": 0.99, + "learning_rate": 5.2853970180838624e-06, + "loss": 0.3051, + "step": 7771 + }, + { + "epoch": 0.99, + "learning_rate": 5.2843622146209405e-06, + "loss": 0.325, + "step": 7772 + }, + { + "epoch": 0.99, + "learning_rate": 5.283327398938339e-06, + "loss": 0.2952, + "step": 7773 + }, + { + "epoch": 1.0, + "learning_rate": 5.2822925710805305e-06, + "loss": 0.3332, + "step": 7774 + }, + { + "epoch": 1.0, + "learning_rate": 5.28125773109198e-06, + "loss": 0.2823, + "step": 7775 + }, + { + "epoch": 1.0, + "learning_rate": 5.2802228790171596e-06, + "loss": 0.2934, + "step": 7776 + }, + { + "epoch": 1.0, + "learning_rate": 5.279188014900537e-06, + "loss": 0.2721, + "step": 7777 + }, + { + "epoch": 1.0, + "learning_rate": 5.278153138786583e-06, + "loss": 0.2947, + "step": 7778 + }, + { + "epoch": 1.0, + "learning_rate": 5.27711825071977e-06, + "loss": 0.3207, + "step": 7779 + }, + { + "epoch": 1.0, + "learning_rate": 5.276083350744568e-06, + "loss": 0.3221, + "step": 7780 + }, + { + "epoch": 1.0, + "learning_rate": 5.275048438905452e-06, + "loss": 0.2973, + "step": 7781 + }, + { + "epoch": 1.0, + "learning_rate": 5.27401351524689e-06, + "loss": 0.2901, + "step": 7782 + }, + { + "epoch": 1.0, + "learning_rate": 5.272978579813357e-06, + "loss": 0.3116, + "step": 7783 + }, + { + "epoch": 1.0, + "learning_rate": 5.2719436326493255e-06, + "loss": 0.2888, + "step": 7784 + }, + { + "epoch": 1.0, + "learning_rate": 5.270908673799272e-06, + "loss": 0.3108, + "step": 7785 + }, + { + "epoch": 1.0, + "learning_rate": 5.26987370330767e-06, + "loss": 0.3005, + "step": 7786 + }, + { + "epoch": 1.0, + "learning_rate": 5.2688387212189915e-06, + "loss": 0.2999, + "step": 7787 + }, + { + "epoch": 1.0, + "learning_rate": 5.267803727577717e-06, + "loss": 0.342, + "step": 7788 + }, + { + "epoch": 1.0, + "learning_rate": 5.266768722428318e-06, + "loss": 0.2986, + "step": 7789 + }, + { + "epoch": 1.0, + "learning_rate": 5.2657337058152735e-06, + "loss": 0.316, + "step": 7790 + }, + { + "epoch": 1.0, + "learning_rate": 5.26469867778306e-06, + "loss": 0.3185, + "step": 7791 + }, + { + "epoch": 1.0, + "learning_rate": 5.263663638376155e-06, + "loss": 0.2901, + "step": 7792 + }, + { + "epoch": 1.0, + "learning_rate": 5.262628587639036e-06, + "loss": 0.2875, + "step": 7793 + }, + { + "epoch": 1.0, + "learning_rate": 5.261593525616181e-06, + "loss": 0.3148, + "step": 7794 + }, + { + "epoch": 1.0, + "learning_rate": 5.2605584523520715e-06, + "loss": 0.2875, + "step": 7795 + }, + { + "epoch": 1.0, + "learning_rate": 5.259523367891184e-06, + "loss": 0.2682, + "step": 7796 + }, + { + "epoch": 1.0, + "learning_rate": 5.258488272277998e-06, + "loss": 0.3142, + "step": 7797 + }, + { + "epoch": 1.0, + "learning_rate": 5.257453165556996e-06, + "loss": 0.3179, + "step": 7798 + }, + { + "epoch": 1.0, + "learning_rate": 5.256418047772659e-06, + "loss": 0.2976, + "step": 7799 + }, + { + "epoch": 1.0, + "learning_rate": 5.255382918969467e-06, + "loss": 0.2873, + "step": 7800 + }, + { + "epoch": 1.0, + "learning_rate": 5.2543477791919025e-06, + "loss": 0.3051, + "step": 7801 + }, + { + "epoch": 1.0, + "learning_rate": 5.253312628484447e-06, + "loss": 0.3001, + "step": 7802 + }, + { + "epoch": 1.0, + "learning_rate": 5.252277466891583e-06, + "loss": 0.322, + "step": 7803 + }, + { + "epoch": 1.0, + "learning_rate": 5.251242294457796e-06, + "loss": 0.3069, + "step": 7804 + }, + { + "epoch": 1.0, + "learning_rate": 5.2502071112275675e-06, + "loss": 0.3038, + "step": 7805 + }, + { + "epoch": 1.0, + "learning_rate": 5.249171917245382e-06, + "loss": 0.2625, + "step": 7806 + }, + { + "epoch": 1.0, + "learning_rate": 5.248136712555724e-06, + "loss": 0.2967, + "step": 7807 + }, + { + "epoch": 1.0, + "learning_rate": 5.247101497203079e-06, + "loss": 0.2804, + "step": 7808 + }, + { + "epoch": 1.0, + "learning_rate": 5.2460662712319335e-06, + "loss": 0.307, + "step": 7809 + }, + { + "epoch": 1.0, + "learning_rate": 5.24503103468677e-06, + "loss": 0.2839, + "step": 7810 + }, + { + "epoch": 1.0, + "learning_rate": 5.243995787612078e-06, + "loss": 0.2853, + "step": 7811 + }, + { + "epoch": 1.0, + "learning_rate": 5.242960530052344e-06, + "loss": 0.3051, + "step": 7812 + }, + { + "epoch": 1.0, + "learning_rate": 5.241925262052055e-06, + "loss": 0.2494, + "step": 7813 + }, + { + "epoch": 1.0, + "learning_rate": 5.240889983655701e-06, + "loss": 0.1732, + "step": 7814 + }, + { + "epoch": 1.0, + "learning_rate": 5.239854694907764e-06, + "loss": 0.1959, + "step": 7815 + }, + { + "epoch": 1.0, + "learning_rate": 5.238819395852738e-06, + "loss": 0.1676, + "step": 7816 + }, + { + "epoch": 1.0, + "learning_rate": 5.2377840865351115e-06, + "loss": 0.1712, + "step": 7817 + }, + { + "epoch": 1.0, + "learning_rate": 5.236748766999372e-06, + "loss": 0.175, + "step": 7818 + }, + { + "epoch": 1.0, + "learning_rate": 5.235713437290012e-06, + "loss": 0.1667, + "step": 7819 + }, + { + "epoch": 1.0, + "learning_rate": 5.234678097451519e-06, + "loss": 0.1779, + "step": 7820 + }, + { + "epoch": 1.0, + "learning_rate": 5.233642747528387e-06, + "loss": 0.1724, + "step": 7821 + }, + { + "epoch": 1.0, + "learning_rate": 5.232607387565104e-06, + "loss": 0.1776, + "step": 7822 + }, + { + "epoch": 1.0, + "learning_rate": 5.231572017606166e-06, + "loss": 0.1625, + "step": 7823 + }, + { + "epoch": 1.0, + "learning_rate": 5.230536637696062e-06, + "loss": 0.1519, + "step": 7824 + }, + { + "epoch": 1.0, + "learning_rate": 5.229501247879284e-06, + "loss": 0.1573, + "step": 7825 + }, + { + "epoch": 1.0, + "learning_rate": 5.228465848200327e-06, + "loss": 0.1706, + "step": 7826 + }, + { + "epoch": 1.0, + "learning_rate": 5.227430438703683e-06, + "loss": 0.159, + "step": 7827 + }, + { + "epoch": 1.0, + "learning_rate": 5.226395019433847e-06, + "loss": 0.1648, + "step": 7828 + }, + { + "epoch": 1.0, + "learning_rate": 5.225359590435312e-06, + "loss": 0.1683, + "step": 7829 + }, + { + "epoch": 1.0, + "learning_rate": 5.224324151752575e-06, + "loss": 0.1549, + "step": 7830 + }, + { + "epoch": 1.0, + "learning_rate": 5.223288703430128e-06, + "loss": 0.1742, + "step": 7831 + }, + { + "epoch": 1.0, + "learning_rate": 5.222253245512471e-06, + "loss": 0.1776, + "step": 7832 + }, + { + "epoch": 1.0, + "learning_rate": 5.221217778044096e-06, + "loss": 0.1695, + "step": 7833 + }, + { + "epoch": 1.0, + "learning_rate": 5.220182301069499e-06, + "loss": 0.1593, + "step": 7834 + }, + { + "epoch": 1.0, + "learning_rate": 5.219146814633178e-06, + "loss": 0.1691, + "step": 7835 + }, + { + "epoch": 1.0, + "learning_rate": 5.218111318779631e-06, + "loss": 0.1822, + "step": 7836 + }, + { + "epoch": 1.0, + "learning_rate": 5.2170758135533554e-06, + "loss": 0.1391, + "step": 7837 + }, + { + "epoch": 1.0, + "learning_rate": 5.2160402989988475e-06, + "loss": 0.1659, + "step": 7838 + }, + { + "epoch": 1.0, + "learning_rate": 5.215004775160608e-06, + "loss": 0.1521, + "step": 7839 + }, + { + "epoch": 1.0, + "learning_rate": 5.2139692420831325e-06, + "loss": 0.1622, + "step": 7840 + }, + { + "epoch": 1.0, + "learning_rate": 5.212933699810924e-06, + "loss": 0.1678, + "step": 7841 + }, + { + "epoch": 1.0, + "learning_rate": 5.211898148388481e-06, + "loss": 0.1476, + "step": 7842 + }, + { + "epoch": 1.0, + "learning_rate": 5.2108625878603e-06, + "loss": 0.1611, + "step": 7843 + }, + { + "epoch": 1.0, + "learning_rate": 5.209827018270886e-06, + "loss": 0.1563, + "step": 7844 + }, + { + "epoch": 1.0, + "learning_rate": 5.208791439664736e-06, + "loss": 0.1578, + "step": 7845 + }, + { + "epoch": 1.0, + "learning_rate": 5.207755852086355e-06, + "loss": 0.1657, + "step": 7846 + }, + { + "epoch": 1.0, + "learning_rate": 5.206720255580241e-06, + "loss": 0.1402, + "step": 7847 + }, + { + "epoch": 1.0, + "learning_rate": 5.2056846501908975e-06, + "loss": 0.1611, + "step": 7848 + }, + { + "epoch": 1.0, + "learning_rate": 5.204649035962825e-06, + "loss": 0.1534, + "step": 7849 + }, + { + "epoch": 1.0, + "learning_rate": 5.2036134129405305e-06, + "loss": 0.1582, + "step": 7850 + }, + { + "epoch": 1.0, + "learning_rate": 5.202577781168513e-06, + "loss": 0.1753, + "step": 7851 + }, + { + "epoch": 1.01, + "learning_rate": 5.201542140691277e-06, + "loss": 0.1493, + "step": 7852 + }, + { + "epoch": 1.01, + "learning_rate": 5.200506491553326e-06, + "loss": 0.1623, + "step": 7853 + }, + { + "epoch": 1.01, + "learning_rate": 5.199470833799164e-06, + "loss": 0.1662, + "step": 7854 + }, + { + "epoch": 1.01, + "learning_rate": 5.198435167473297e-06, + "loss": 0.151, + "step": 7855 + }, + { + "epoch": 1.01, + "learning_rate": 5.1973994926202296e-06, + "loss": 0.1674, + "step": 7856 + }, + { + "epoch": 1.01, + "learning_rate": 5.196363809284466e-06, + "loss": 0.1647, + "step": 7857 + }, + { + "epoch": 1.01, + "learning_rate": 5.19532811751051e-06, + "loss": 0.16, + "step": 7858 + }, + { + "epoch": 1.01, + "learning_rate": 5.1942924173428725e-06, + "loss": 0.1699, + "step": 7859 + }, + { + "epoch": 1.01, + "learning_rate": 5.193256708826055e-06, + "loss": 0.1745, + "step": 7860 + }, + { + "epoch": 1.01, + "learning_rate": 5.192220992004569e-06, + "loss": 0.1487, + "step": 7861 + }, + { + "epoch": 1.01, + "learning_rate": 5.191185266922917e-06, + "loss": 0.1531, + "step": 7862 + }, + { + "epoch": 1.01, + "learning_rate": 5.190149533625607e-06, + "loss": 0.1526, + "step": 7863 + }, + { + "epoch": 1.01, + "learning_rate": 5.18911379215715e-06, + "loss": 0.1465, + "step": 7864 + }, + { + "epoch": 1.01, + "learning_rate": 5.188078042562052e-06, + "loss": 0.1542, + "step": 7865 + }, + { + "epoch": 1.01, + "learning_rate": 5.187042284884821e-06, + "loss": 0.1456, + "step": 7866 + }, + { + "epoch": 1.01, + "learning_rate": 5.186006519169967e-06, + "loss": 0.1508, + "step": 7867 + }, + { + "epoch": 1.01, + "learning_rate": 5.184970745461998e-06, + "loss": 0.148, + "step": 7868 + }, + { + "epoch": 1.01, + "learning_rate": 5.1839349638054245e-06, + "loss": 0.1704, + "step": 7869 + }, + { + "epoch": 1.01, + "learning_rate": 5.182899174244757e-06, + "loss": 0.1499, + "step": 7870 + }, + { + "epoch": 1.01, + "learning_rate": 5.181863376824504e-06, + "loss": 0.1666, + "step": 7871 + }, + { + "epoch": 1.01, + "learning_rate": 5.1808275715891756e-06, + "loss": 0.1509, + "step": 7872 + }, + { + "epoch": 1.01, + "learning_rate": 5.1797917585832846e-06, + "loss": 0.1642, + "step": 7873 + }, + { + "epoch": 1.01, + "learning_rate": 5.178755937851341e-06, + "loss": 0.1499, + "step": 7874 + }, + { + "epoch": 1.01, + "learning_rate": 5.177720109437857e-06, + "loss": 0.1753, + "step": 7875 + }, + { + "epoch": 1.01, + "learning_rate": 5.176684273387344e-06, + "loss": 0.1484, + "step": 7876 + }, + { + "epoch": 1.01, + "learning_rate": 5.1756484297443135e-06, + "loss": 0.1421, + "step": 7877 + }, + { + "epoch": 1.01, + "learning_rate": 5.1746125785532795e-06, + "loss": 0.1678, + "step": 7878 + }, + { + "epoch": 1.01, + "learning_rate": 5.173576719858755e-06, + "loss": 0.1629, + "step": 7879 + }, + { + "epoch": 1.01, + "learning_rate": 5.172540853705251e-06, + "loss": 0.1355, + "step": 7880 + }, + { + "epoch": 1.01, + "learning_rate": 5.171504980137282e-06, + "loss": 0.1409, + "step": 7881 + }, + { + "epoch": 1.01, + "learning_rate": 5.170469099199363e-06, + "loss": 0.1737, + "step": 7882 + }, + { + "epoch": 1.01, + "learning_rate": 5.169433210936007e-06, + "loss": 0.1779, + "step": 7883 + }, + { + "epoch": 1.01, + "learning_rate": 5.168397315391729e-06, + "loss": 0.1642, + "step": 7884 + }, + { + "epoch": 1.01, + "learning_rate": 5.167361412611042e-06, + "loss": 0.1719, + "step": 7885 + }, + { + "epoch": 1.01, + "learning_rate": 5.1663255026384625e-06, + "loss": 0.1766, + "step": 7886 + }, + { + "epoch": 1.01, + "learning_rate": 5.165289585518507e-06, + "loss": 0.1775, + "step": 7887 + }, + { + "epoch": 1.01, + "learning_rate": 5.164253661295689e-06, + "loss": 0.1559, + "step": 7888 + }, + { + "epoch": 1.01, + "learning_rate": 5.1632177300145255e-06, + "loss": 0.151, + "step": 7889 + }, + { + "epoch": 1.01, + "learning_rate": 5.162181791719532e-06, + "loss": 0.166, + "step": 7890 + }, + { + "epoch": 1.01, + "learning_rate": 5.161145846455227e-06, + "loss": 0.1618, + "step": 7891 + }, + { + "epoch": 1.01, + "learning_rate": 5.160109894266125e-06, + "loss": 0.162, + "step": 7892 + }, + { + "epoch": 1.01, + "learning_rate": 5.159073935196746e-06, + "loss": 0.1741, + "step": 7893 + }, + { + "epoch": 1.01, + "learning_rate": 5.1580379692916025e-06, + "loss": 0.1454, + "step": 7894 + }, + { + "epoch": 1.01, + "learning_rate": 5.157001996595218e-06, + "loss": 0.1513, + "step": 7895 + }, + { + "epoch": 1.01, + "learning_rate": 5.155966017152108e-06, + "loss": 0.1421, + "step": 7896 + }, + { + "epoch": 1.01, + "learning_rate": 5.1549300310067896e-06, + "loss": 0.1627, + "step": 7897 + }, + { + "epoch": 1.01, + "learning_rate": 5.153894038203785e-06, + "loss": 0.1536, + "step": 7898 + }, + { + "epoch": 1.01, + "learning_rate": 5.152858038787608e-06, + "loss": 0.1482, + "step": 7899 + }, + { + "epoch": 1.01, + "learning_rate": 5.151822032802782e-06, + "loss": 0.171, + "step": 7900 + }, + { + "epoch": 1.01, + "learning_rate": 5.150786020293824e-06, + "loss": 0.1479, + "step": 7901 + }, + { + "epoch": 1.01, + "learning_rate": 5.149750001305257e-06, + "loss": 0.1693, + "step": 7902 + }, + { + "epoch": 1.01, + "learning_rate": 5.148713975881598e-06, + "loss": 0.1749, + "step": 7903 + }, + { + "epoch": 1.01, + "learning_rate": 5.147677944067368e-06, + "loss": 0.1456, + "step": 7904 + }, + { + "epoch": 1.01, + "learning_rate": 5.146641905907088e-06, + "loss": 0.1474, + "step": 7905 + }, + { + "epoch": 1.01, + "learning_rate": 5.145605861445279e-06, + "loss": 0.1662, + "step": 7906 + }, + { + "epoch": 1.01, + "learning_rate": 5.144569810726462e-06, + "loss": 0.1573, + "step": 7907 + }, + { + "epoch": 1.01, + "learning_rate": 5.143533753795157e-06, + "loss": 0.1602, + "step": 7908 + }, + { + "epoch": 1.01, + "learning_rate": 5.142497690695888e-06, + "loss": 0.1331, + "step": 7909 + }, + { + "epoch": 1.01, + "learning_rate": 5.141461621473175e-06, + "loss": 0.1507, + "step": 7910 + }, + { + "epoch": 1.01, + "learning_rate": 5.140425546171542e-06, + "loss": 0.1471, + "step": 7911 + }, + { + "epoch": 1.01, + "learning_rate": 5.13938946483551e-06, + "loss": 0.16, + "step": 7912 + }, + { + "epoch": 1.01, + "learning_rate": 5.1383533775096025e-06, + "loss": 0.1521, + "step": 7913 + }, + { + "epoch": 1.01, + "learning_rate": 5.137317284238344e-06, + "loss": 0.1568, + "step": 7914 + }, + { + "epoch": 1.01, + "learning_rate": 5.136281185066253e-06, + "loss": 0.1428, + "step": 7915 + }, + { + "epoch": 1.01, + "learning_rate": 5.135245080037857e-06, + "loss": 0.149, + "step": 7916 + }, + { + "epoch": 1.01, + "learning_rate": 5.1342089691976794e-06, + "loss": 0.1389, + "step": 7917 + }, + { + "epoch": 1.01, + "learning_rate": 5.1331728525902435e-06, + "loss": 0.1727, + "step": 7918 + }, + { + "epoch": 1.01, + "learning_rate": 5.1321367302600726e-06, + "loss": 0.1528, + "step": 7919 + }, + { + "epoch": 1.01, + "learning_rate": 5.131100602251692e-06, + "loss": 0.1416, + "step": 7920 + }, + { + "epoch": 1.01, + "learning_rate": 5.130064468609627e-06, + "loss": 0.1537, + "step": 7921 + }, + { + "epoch": 1.01, + "learning_rate": 5.129028329378403e-06, + "loss": 0.1629, + "step": 7922 + }, + { + "epoch": 1.01, + "learning_rate": 5.127992184602542e-06, + "loss": 0.1666, + "step": 7923 + }, + { + "epoch": 1.01, + "learning_rate": 5.126956034326573e-06, + "loss": 0.1759, + "step": 7924 + }, + { + "epoch": 1.01, + "learning_rate": 5.125919878595022e-06, + "loss": 0.1655, + "step": 7925 + }, + { + "epoch": 1.01, + "learning_rate": 5.124883717452412e-06, + "loss": 0.1551, + "step": 7926 + }, + { + "epoch": 1.01, + "learning_rate": 5.123847550943272e-06, + "loss": 0.1572, + "step": 7927 + }, + { + "epoch": 1.01, + "learning_rate": 5.122811379112124e-06, + "loss": 0.1489, + "step": 7928 + }, + { + "epoch": 1.01, + "learning_rate": 5.121775202003499e-06, + "loss": 0.1584, + "step": 7929 + }, + { + "epoch": 1.02, + "learning_rate": 5.120739019661923e-06, + "loss": 0.16, + "step": 7930 + }, + { + "epoch": 1.02, + "learning_rate": 5.119702832131922e-06, + "loss": 0.1569, + "step": 7931 + }, + { + "epoch": 1.02, + "learning_rate": 5.118666639458023e-06, + "loss": 0.1605, + "step": 7932 + }, + { + "epoch": 1.02, + "learning_rate": 5.117630441684755e-06, + "loss": 0.1576, + "step": 7933 + }, + { + "epoch": 1.02, + "learning_rate": 5.116594238856645e-06, + "loss": 0.1522, + "step": 7934 + }, + { + "epoch": 1.02, + "learning_rate": 5.115558031018221e-06, + "loss": 0.1723, + "step": 7935 + }, + { + "epoch": 1.02, + "learning_rate": 5.114521818214011e-06, + "loss": 0.1603, + "step": 7936 + }, + { + "epoch": 1.02, + "learning_rate": 5.113485600488541e-06, + "loss": 0.1506, + "step": 7937 + }, + { + "epoch": 1.02, + "learning_rate": 5.112449377886345e-06, + "loss": 0.1786, + "step": 7938 + }, + { + "epoch": 1.02, + "learning_rate": 5.111413150451948e-06, + "loss": 0.1603, + "step": 7939 + }, + { + "epoch": 1.02, + "learning_rate": 5.11037691822988e-06, + "loss": 0.1734, + "step": 7940 + }, + { + "epoch": 1.02, + "learning_rate": 5.10934068126467e-06, + "loss": 0.1712, + "step": 7941 + }, + { + "epoch": 1.02, + "learning_rate": 5.108304439600847e-06, + "loss": 0.1577, + "step": 7942 + }, + { + "epoch": 1.02, + "learning_rate": 5.107268193282941e-06, + "loss": 0.1547, + "step": 7943 + }, + { + "epoch": 1.02, + "learning_rate": 5.1062319423554815e-06, + "loss": 0.1625, + "step": 7944 + }, + { + "epoch": 1.02, + "learning_rate": 5.105195686863e-06, + "loss": 0.1524, + "step": 7945 + }, + { + "epoch": 1.02, + "learning_rate": 5.104159426850024e-06, + "loss": 0.1371, + "step": 7946 + }, + { + "epoch": 1.02, + "learning_rate": 5.103123162361087e-06, + "loss": 0.1648, + "step": 7947 + }, + { + "epoch": 1.02, + "learning_rate": 5.102086893440717e-06, + "loss": 0.1539, + "step": 7948 + }, + { + "epoch": 1.02, + "learning_rate": 5.101050620133447e-06, + "loss": 0.1433, + "step": 7949 + }, + { + "epoch": 1.02, + "learning_rate": 5.100014342483804e-06, + "loss": 0.1597, + "step": 7950 + }, + { + "epoch": 1.02, + "learning_rate": 5.098978060536325e-06, + "loss": 0.1597, + "step": 7951 + }, + { + "epoch": 1.02, + "learning_rate": 5.097941774335538e-06, + "loss": 0.1536, + "step": 7952 + }, + { + "epoch": 1.02, + "learning_rate": 5.096905483925972e-06, + "loss": 0.1596, + "step": 7953 + }, + { + "epoch": 1.02, + "learning_rate": 5.095869189352166e-06, + "loss": 0.1536, + "step": 7954 + }, + { + "epoch": 1.02, + "learning_rate": 5.094832890658644e-06, + "loss": 0.1406, + "step": 7955 + }, + { + "epoch": 1.02, + "learning_rate": 5.0937965878899435e-06, + "loss": 0.15, + "step": 7956 + }, + { + "epoch": 1.02, + "learning_rate": 5.092760281090592e-06, + "loss": 0.1454, + "step": 7957 + }, + { + "epoch": 1.02, + "learning_rate": 5.091723970305128e-06, + "loss": 0.1639, + "step": 7958 + }, + { + "epoch": 1.02, + "learning_rate": 5.090687655578078e-06, + "loss": 0.16, + "step": 7959 + }, + { + "epoch": 1.02, + "learning_rate": 5.089651336953979e-06, + "loss": 0.1611, + "step": 7960 + }, + { + "epoch": 1.02, + "learning_rate": 5.088615014477362e-06, + "loss": 0.1635, + "step": 7961 + }, + { + "epoch": 1.02, + "learning_rate": 5.087578688192759e-06, + "loss": 0.1637, + "step": 7962 + }, + { + "epoch": 1.02, + "learning_rate": 5.086542358144708e-06, + "loss": 0.1566, + "step": 7963 + }, + { + "epoch": 1.02, + "learning_rate": 5.0855060243777366e-06, + "loss": 0.1631, + "step": 7964 + }, + { + "epoch": 1.02, + "learning_rate": 5.084469686936382e-06, + "loss": 0.1559, + "step": 7965 + }, + { + "epoch": 1.02, + "learning_rate": 5.083433345865175e-06, + "loss": 0.1577, + "step": 7966 + }, + { + "epoch": 1.02, + "learning_rate": 5.082397001208653e-06, + "loss": 0.151, + "step": 7967 + }, + { + "epoch": 1.02, + "learning_rate": 5.081360653011349e-06, + "loss": 0.15, + "step": 7968 + }, + { + "epoch": 1.02, + "learning_rate": 5.080324301317795e-06, + "loss": 0.1519, + "step": 7969 + }, + { + "epoch": 1.02, + "learning_rate": 5.079287946172529e-06, + "loss": 0.1423, + "step": 7970 + }, + { + "epoch": 1.02, + "learning_rate": 5.07825158762008e-06, + "loss": 0.1417, + "step": 7971 + }, + { + "epoch": 1.02, + "learning_rate": 5.077215225704988e-06, + "loss": 0.1606, + "step": 7972 + }, + { + "epoch": 1.02, + "learning_rate": 5.076178860471787e-06, + "loss": 0.1484, + "step": 7973 + }, + { + "epoch": 1.02, + "learning_rate": 5.0751424919650085e-06, + "loss": 0.1551, + "step": 7974 + }, + { + "epoch": 1.02, + "learning_rate": 5.07410612022919e-06, + "loss": 0.1416, + "step": 7975 + }, + { + "epoch": 1.02, + "learning_rate": 5.073069745308868e-06, + "loss": 0.1564, + "step": 7976 + }, + { + "epoch": 1.02, + "learning_rate": 5.072033367248574e-06, + "loss": 0.153, + "step": 7977 + }, + { + "epoch": 1.02, + "learning_rate": 5.0709969860928485e-06, + "loss": 0.1591, + "step": 7978 + }, + { + "epoch": 1.02, + "learning_rate": 5.069960601886224e-06, + "loss": 0.1719, + "step": 7979 + }, + { + "epoch": 1.02, + "learning_rate": 5.068924214673234e-06, + "loss": 0.1375, + "step": 7980 + }, + { + "epoch": 1.02, + "learning_rate": 5.067887824498419e-06, + "loss": 0.1612, + "step": 7981 + }, + { + "epoch": 1.02, + "learning_rate": 5.0668514314063135e-06, + "loss": 0.1529, + "step": 7982 + }, + { + "epoch": 1.02, + "learning_rate": 5.065815035441452e-06, + "loss": 0.147, + "step": 7983 + }, + { + "epoch": 1.02, + "learning_rate": 5.064778636648371e-06, + "loss": 0.1558, + "step": 7984 + }, + { + "epoch": 1.02, + "learning_rate": 5.063742235071609e-06, + "loss": 0.1589, + "step": 7985 + }, + { + "epoch": 1.02, + "learning_rate": 5.062705830755702e-06, + "loss": 0.1526, + "step": 7986 + }, + { + "epoch": 1.02, + "learning_rate": 5.061669423745185e-06, + "loss": 0.1713, + "step": 7987 + }, + { + "epoch": 1.02, + "learning_rate": 5.060633014084595e-06, + "loss": 0.1834, + "step": 7988 + }, + { + "epoch": 1.02, + "learning_rate": 5.05959660181847e-06, + "loss": 0.1401, + "step": 7989 + }, + { + "epoch": 1.02, + "learning_rate": 5.058560186991346e-06, + "loss": 0.1565, + "step": 7990 + }, + { + "epoch": 1.02, + "learning_rate": 5.0575237696477596e-06, + "loss": 0.1568, + "step": 7991 + }, + { + "epoch": 1.02, + "learning_rate": 5.05648734983225e-06, + "loss": 0.1529, + "step": 7992 + }, + { + "epoch": 1.02, + "learning_rate": 5.055450927589352e-06, + "loss": 0.1512, + "step": 7993 + }, + { + "epoch": 1.02, + "learning_rate": 5.054414502963605e-06, + "loss": 0.1652, + "step": 7994 + }, + { + "epoch": 1.02, + "learning_rate": 5.053378075999545e-06, + "loss": 0.1476, + "step": 7995 + }, + { + "epoch": 1.02, + "learning_rate": 5.052341646741711e-06, + "loss": 0.1697, + "step": 7996 + }, + { + "epoch": 1.02, + "learning_rate": 5.05130521523464e-06, + "loss": 0.1598, + "step": 7997 + }, + { + "epoch": 1.02, + "learning_rate": 5.050268781522868e-06, + "loss": 0.1719, + "step": 7998 + }, + { + "epoch": 1.02, + "learning_rate": 5.049232345650936e-06, + "loss": 0.153, + "step": 7999 + }, + { + "epoch": 1.02, + "learning_rate": 5.04819590766338e-06, + "loss": 0.1558, + "step": 8000 + }, + { + "epoch": 1.02, + "learning_rate": 5.0471594676047385e-06, + "loss": 0.1374, + "step": 8001 + }, + { + "epoch": 1.02, + "learning_rate": 5.0461230255195495e-06, + "loss": 0.1621, + "step": 8002 + }, + { + "epoch": 1.02, + "learning_rate": 5.045086581452352e-06, + "loss": 0.1538, + "step": 8003 + }, + { + "epoch": 1.02, + "learning_rate": 5.044050135447682e-06, + "loss": 0.16, + "step": 8004 + }, + { + "epoch": 1.02, + "learning_rate": 5.043013687550083e-06, + "loss": 0.1358, + "step": 8005 + }, + { + "epoch": 1.02, + "learning_rate": 5.041977237804088e-06, + "loss": 0.1415, + "step": 8006 + }, + { + "epoch": 1.02, + "learning_rate": 5.040940786254236e-06, + "loss": 0.1525, + "step": 8007 + }, + { + "epoch": 1.03, + "learning_rate": 5.039904332945069e-06, + "loss": 0.165, + "step": 8008 + }, + { + "epoch": 1.03, + "learning_rate": 5.038867877921124e-06, + "loss": 0.1659, + "step": 8009 + }, + { + "epoch": 1.03, + "learning_rate": 5.037831421226939e-06, + "loss": 0.1637, + "step": 8010 + }, + { + "epoch": 1.03, + "learning_rate": 5.036794962907054e-06, + "loss": 0.1428, + "step": 8011 + }, + { + "epoch": 1.03, + "learning_rate": 5.035758503006007e-06, + "loss": 0.1565, + "step": 8012 + }, + { + "epoch": 1.03, + "learning_rate": 5.034722041568337e-06, + "loss": 0.154, + "step": 8013 + }, + { + "epoch": 1.03, + "learning_rate": 5.033685578638586e-06, + "loss": 0.1561, + "step": 8014 + }, + { + "epoch": 1.03, + "learning_rate": 5.03264911426129e-06, + "loss": 0.16, + "step": 8015 + }, + { + "epoch": 1.03, + "learning_rate": 5.031612648480987e-06, + "loss": 0.1821, + "step": 8016 + }, + { + "epoch": 1.03, + "learning_rate": 5.03057618134222e-06, + "loss": 0.1675, + "step": 8017 + }, + { + "epoch": 1.03, + "learning_rate": 5.029539712889524e-06, + "loss": 0.1651, + "step": 8018 + }, + { + "epoch": 1.03, + "learning_rate": 5.028503243167443e-06, + "loss": 0.166, + "step": 8019 + }, + { + "epoch": 1.03, + "learning_rate": 5.027466772220513e-06, + "loss": 0.1704, + "step": 8020 + }, + { + "epoch": 1.03, + "learning_rate": 5.026430300093275e-06, + "loss": 0.167, + "step": 8021 + }, + { + "epoch": 1.03, + "learning_rate": 5.025393826830267e-06, + "loss": 0.1597, + "step": 8022 + }, + { + "epoch": 1.03, + "learning_rate": 5.024357352476032e-06, + "loss": 0.1502, + "step": 8023 + }, + { + "epoch": 1.03, + "learning_rate": 5.023320877075107e-06, + "loss": 0.1692, + "step": 8024 + }, + { + "epoch": 1.03, + "learning_rate": 5.02228440067203e-06, + "loss": 0.1582, + "step": 8025 + }, + { + "epoch": 1.03, + "learning_rate": 5.0212479233113445e-06, + "loss": 0.1586, + "step": 8026 + }, + { + "epoch": 1.03, + "learning_rate": 5.020211445037587e-06, + "loss": 0.1536, + "step": 8027 + }, + { + "epoch": 1.03, + "learning_rate": 5.019174965895299e-06, + "loss": 0.1502, + "step": 8028 + }, + { + "epoch": 1.03, + "learning_rate": 5.0181384859290215e-06, + "loss": 0.153, + "step": 8029 + }, + { + "epoch": 1.03, + "learning_rate": 5.017102005183292e-06, + "loss": 0.153, + "step": 8030 + }, + { + "epoch": 1.03, + "learning_rate": 5.01606552370265e-06, + "loss": 0.1437, + "step": 8031 + }, + { + "epoch": 1.03, + "learning_rate": 5.015029041531639e-06, + "loss": 0.1569, + "step": 8032 + }, + { + "epoch": 1.03, + "learning_rate": 5.013992558714795e-06, + "loss": 0.1555, + "step": 8033 + }, + { + "epoch": 1.03, + "learning_rate": 5.01295607529666e-06, + "loss": 0.1472, + "step": 8034 + }, + { + "epoch": 1.03, + "learning_rate": 5.011919591321773e-06, + "loss": 0.1553, + "step": 8035 + }, + { + "epoch": 1.03, + "learning_rate": 5.010883106834676e-06, + "loss": 0.1565, + "step": 8036 + }, + { + "epoch": 1.03, + "learning_rate": 5.009846621879906e-06, + "loss": 0.1546, + "step": 8037 + }, + { + "epoch": 1.03, + "learning_rate": 5.008810136502006e-06, + "loss": 0.1356, + "step": 8038 + }, + { + "epoch": 1.03, + "learning_rate": 5.007773650745514e-06, + "loss": 0.1575, + "step": 8039 + }, + { + "epoch": 1.03, + "learning_rate": 5.00673716465497e-06, + "loss": 0.1768, + "step": 8040 + }, + { + "epoch": 1.03, + "learning_rate": 5.005700678274918e-06, + "loss": 0.1387, + "step": 8041 + }, + { + "epoch": 1.03, + "learning_rate": 5.004664191649893e-06, + "loss": 0.1481, + "step": 8042 + }, + { + "epoch": 1.03, + "learning_rate": 5.003627704824438e-06, + "loss": 0.1651, + "step": 8043 + }, + { + "epoch": 1.03, + "learning_rate": 5.0025912178430925e-06, + "loss": 0.1763, + "step": 8044 + }, + { + "epoch": 1.03, + "learning_rate": 5.001554730750395e-06, + "loss": 0.1522, + "step": 8045 + }, + { + "epoch": 1.03, + "learning_rate": 5.0005182435908885e-06, + "loss": 0.1672, + "step": 8046 + }, + { + "epoch": 1.03, + "learning_rate": 4.999481756409112e-06, + "loss": 0.1502, + "step": 8047 + }, + { + "epoch": 1.03, + "learning_rate": 4.998445269249606e-06, + "loss": 0.1401, + "step": 8048 + }, + { + "epoch": 1.03, + "learning_rate": 4.997408782156909e-06, + "loss": 0.1582, + "step": 8049 + }, + { + "epoch": 1.03, + "learning_rate": 4.996372295175563e-06, + "loss": 0.1481, + "step": 8050 + }, + { + "epoch": 1.03, + "learning_rate": 4.995335808350109e-06, + "loss": 0.1601, + "step": 8051 + }, + { + "epoch": 1.03, + "learning_rate": 4.994299321725085e-06, + "loss": 0.1657, + "step": 8052 + }, + { + "epoch": 1.03, + "learning_rate": 4.99326283534503e-06, + "loss": 0.1407, + "step": 8053 + }, + { + "epoch": 1.03, + "learning_rate": 4.9922263492544885e-06, + "loss": 0.154, + "step": 8054 + }, + { + "epoch": 1.03, + "learning_rate": 4.991189863497996e-06, + "loss": 0.161, + "step": 8055 + }, + { + "epoch": 1.03, + "learning_rate": 4.990153378120096e-06, + "loss": 0.1408, + "step": 8056 + }, + { + "epoch": 1.03, + "learning_rate": 4.989116893165325e-06, + "loss": 0.1557, + "step": 8057 + }, + { + "epoch": 1.03, + "learning_rate": 4.988080408678229e-06, + "loss": 0.167, + "step": 8058 + }, + { + "epoch": 1.03, + "learning_rate": 4.987043924703342e-06, + "loss": 0.1427, + "step": 8059 + }, + { + "epoch": 1.03, + "learning_rate": 4.986007441285206e-06, + "loss": 0.1587, + "step": 8060 + }, + { + "epoch": 1.03, + "learning_rate": 4.984970958468364e-06, + "loss": 0.146, + "step": 8061 + }, + { + "epoch": 1.03, + "learning_rate": 4.983934476297351e-06, + "loss": 0.1696, + "step": 8062 + }, + { + "epoch": 1.03, + "learning_rate": 4.9828979948167095e-06, + "loss": 0.1383, + "step": 8063 + }, + { + "epoch": 1.03, + "learning_rate": 4.981861514070979e-06, + "loss": 0.1592, + "step": 8064 + }, + { + "epoch": 1.03, + "learning_rate": 4.980825034104702e-06, + "loss": 0.1451, + "step": 8065 + }, + { + "epoch": 1.03, + "learning_rate": 4.979788554962415e-06, + "loss": 0.1468, + "step": 8066 + }, + { + "epoch": 1.03, + "learning_rate": 4.978752076688657e-06, + "loss": 0.1483, + "step": 8067 + }, + { + "epoch": 1.03, + "learning_rate": 4.97771559932797e-06, + "loss": 0.1436, + "step": 8068 + }, + { + "epoch": 1.03, + "learning_rate": 4.976679122924896e-06, + "loss": 0.1621, + "step": 8069 + }, + { + "epoch": 1.03, + "learning_rate": 4.97564264752397e-06, + "loss": 0.1605, + "step": 8070 + }, + { + "epoch": 1.03, + "learning_rate": 4.974606173169733e-06, + "loss": 0.1301, + "step": 8071 + }, + { + "epoch": 1.03, + "learning_rate": 4.973569699906727e-06, + "loss": 0.1798, + "step": 8072 + }, + { + "epoch": 1.03, + "learning_rate": 4.972533227779489e-06, + "loss": 0.1393, + "step": 8073 + }, + { + "epoch": 1.03, + "learning_rate": 4.971496756832557e-06, + "loss": 0.1363, + "step": 8074 + }, + { + "epoch": 1.03, + "learning_rate": 4.9704602871104765e-06, + "loss": 0.1599, + "step": 8075 + }, + { + "epoch": 1.03, + "learning_rate": 4.969423818657783e-06, + "loss": 0.1545, + "step": 8076 + }, + { + "epoch": 1.03, + "learning_rate": 4.9683873515190145e-06, + "loss": 0.1545, + "step": 8077 + }, + { + "epoch": 1.03, + "learning_rate": 4.9673508857387115e-06, + "loss": 0.1499, + "step": 8078 + }, + { + "epoch": 1.03, + "learning_rate": 4.966314421361416e-06, + "loss": 0.1628, + "step": 8079 + }, + { + "epoch": 1.03, + "learning_rate": 4.965277958431664e-06, + "loss": 0.1518, + "step": 8080 + }, + { + "epoch": 1.03, + "learning_rate": 4.964241496993994e-06, + "loss": 0.1704, + "step": 8081 + }, + { + "epoch": 1.03, + "learning_rate": 4.963205037092947e-06, + "loss": 0.1568, + "step": 8082 + }, + { + "epoch": 1.03, + "learning_rate": 4.962168578773063e-06, + "loss": 0.1533, + "step": 8083 + }, + { + "epoch": 1.03, + "learning_rate": 4.9611321220788775e-06, + "loss": 0.1511, + "step": 8084 + }, + { + "epoch": 1.03, + "learning_rate": 4.9600956670549324e-06, + "loss": 0.1443, + "step": 8085 + }, + { + "epoch": 1.04, + "learning_rate": 4.959059213745764e-06, + "loss": 0.1503, + "step": 8086 + }, + { + "epoch": 1.04, + "learning_rate": 4.9580227621959145e-06, + "loss": 0.1531, + "step": 8087 + }, + { + "epoch": 1.04, + "learning_rate": 4.956986312449919e-06, + "loss": 0.1646, + "step": 8088 + }, + { + "epoch": 1.04, + "learning_rate": 4.955949864552318e-06, + "loss": 0.1746, + "step": 8089 + }, + { + "epoch": 1.04, + "learning_rate": 4.954913418547651e-06, + "loss": 0.1566, + "step": 8090 + }, + { + "epoch": 1.04, + "learning_rate": 4.953876974480452e-06, + "loss": 0.1547, + "step": 8091 + }, + { + "epoch": 1.04, + "learning_rate": 4.952840532395262e-06, + "loss": 0.1542, + "step": 8092 + }, + { + "epoch": 1.04, + "learning_rate": 4.951804092336621e-06, + "loss": 0.1346, + "step": 8093 + }, + { + "epoch": 1.04, + "learning_rate": 4.950767654349067e-06, + "loss": 0.1685, + "step": 8094 + }, + { + "epoch": 1.04, + "learning_rate": 4.949731218477133e-06, + "loss": 0.1618, + "step": 8095 + }, + { + "epoch": 1.04, + "learning_rate": 4.9486947847653615e-06, + "loss": 0.1703, + "step": 8096 + }, + { + "epoch": 1.04, + "learning_rate": 4.947658353258291e-06, + "loss": 0.1518, + "step": 8097 + }, + { + "epoch": 1.04, + "learning_rate": 4.946621924000456e-06, + "loss": 0.171, + "step": 8098 + }, + { + "epoch": 1.04, + "learning_rate": 4.945585497036396e-06, + "loss": 0.1538, + "step": 8099 + }, + { + "epoch": 1.04, + "learning_rate": 4.944549072410648e-06, + "loss": 0.1695, + "step": 8100 + }, + { + "epoch": 1.04, + "learning_rate": 4.9435126501677525e-06, + "loss": 0.1637, + "step": 8101 + }, + { + "epoch": 1.04, + "learning_rate": 4.942476230352241e-06, + "loss": 0.146, + "step": 8102 + }, + { + "epoch": 1.04, + "learning_rate": 4.941439813008656e-06, + "loss": 0.1545, + "step": 8103 + }, + { + "epoch": 1.04, + "learning_rate": 4.940403398181531e-06, + "loss": 0.1545, + "step": 8104 + }, + { + "epoch": 1.04, + "learning_rate": 4.939366985915408e-06, + "loss": 0.1565, + "step": 8105 + }, + { + "epoch": 1.04, + "learning_rate": 4.938330576254817e-06, + "loss": 0.1484, + "step": 8106 + }, + { + "epoch": 1.04, + "learning_rate": 4.9372941692443e-06, + "loss": 0.1635, + "step": 8107 + }, + { + "epoch": 1.04, + "learning_rate": 4.936257764928392e-06, + "loss": 0.1471, + "step": 8108 + }, + { + "epoch": 1.04, + "learning_rate": 4.935221363351631e-06, + "loss": 0.1514, + "step": 8109 + }, + { + "epoch": 1.04, + "learning_rate": 4.934184964558549e-06, + "loss": 0.1633, + "step": 8110 + }, + { + "epoch": 1.04, + "learning_rate": 4.933148568593687e-06, + "loss": 0.1492, + "step": 8111 + }, + { + "epoch": 1.04, + "learning_rate": 4.932112175501583e-06, + "loss": 0.1592, + "step": 8112 + }, + { + "epoch": 1.04, + "learning_rate": 4.931075785326767e-06, + "loss": 0.1579, + "step": 8113 + }, + { + "epoch": 1.04, + "learning_rate": 4.930039398113779e-06, + "loss": 0.1436, + "step": 8114 + }, + { + "epoch": 1.04, + "learning_rate": 4.929003013907152e-06, + "loss": 0.1486, + "step": 8115 + }, + { + "epoch": 1.04, + "learning_rate": 4.927966632751427e-06, + "loss": 0.1471, + "step": 8116 + }, + { + "epoch": 1.04, + "learning_rate": 4.926930254691134e-06, + "loss": 0.1553, + "step": 8117 + }, + { + "epoch": 1.04, + "learning_rate": 4.92589387977081e-06, + "loss": 0.1705, + "step": 8118 + }, + { + "epoch": 1.04, + "learning_rate": 4.924857508034994e-06, + "loss": 0.1727, + "step": 8119 + }, + { + "epoch": 1.04, + "learning_rate": 4.9238211395282156e-06, + "loss": 0.143, + "step": 8120 + }, + { + "epoch": 1.04, + "learning_rate": 4.922784774295013e-06, + "loss": 0.1388, + "step": 8121 + }, + { + "epoch": 1.04, + "learning_rate": 4.92174841237992e-06, + "loss": 0.153, + "step": 8122 + }, + { + "epoch": 1.04, + "learning_rate": 4.920712053827475e-06, + "loss": 0.1546, + "step": 8123 + }, + { + "epoch": 1.04, + "learning_rate": 4.919675698682206e-06, + "loss": 0.1549, + "step": 8124 + }, + { + "epoch": 1.04, + "learning_rate": 4.918639346988652e-06, + "loss": 0.1462, + "step": 8125 + }, + { + "epoch": 1.04, + "learning_rate": 4.917602998791348e-06, + "loss": 0.1395, + "step": 8126 + }, + { + "epoch": 1.04, + "learning_rate": 4.9165666541348265e-06, + "loss": 0.153, + "step": 8127 + }, + { + "epoch": 1.04, + "learning_rate": 4.91553031306362e-06, + "loss": 0.1746, + "step": 8128 + }, + { + "epoch": 1.04, + "learning_rate": 4.914493975622263e-06, + "loss": 0.1593, + "step": 8129 + }, + { + "epoch": 1.04, + "learning_rate": 4.9134576418552945e-06, + "loss": 0.1508, + "step": 8130 + }, + { + "epoch": 1.04, + "learning_rate": 4.9124213118072415e-06, + "loss": 0.1782, + "step": 8131 + }, + { + "epoch": 1.04, + "learning_rate": 4.911384985522639e-06, + "loss": 0.1417, + "step": 8132 + }, + { + "epoch": 1.04, + "learning_rate": 4.910348663046021e-06, + "loss": 0.1599, + "step": 8133 + }, + { + "epoch": 1.04, + "learning_rate": 4.909312344421923e-06, + "loss": 0.1426, + "step": 8134 + }, + { + "epoch": 1.04, + "learning_rate": 4.908276029694873e-06, + "loss": 0.1729, + "step": 8135 + }, + { + "epoch": 1.04, + "learning_rate": 4.907239718909408e-06, + "loss": 0.1461, + "step": 8136 + }, + { + "epoch": 1.04, + "learning_rate": 4.90620341211006e-06, + "loss": 0.1428, + "step": 8137 + }, + { + "epoch": 1.04, + "learning_rate": 4.905167109341357e-06, + "loss": 0.1382, + "step": 8138 + }, + { + "epoch": 1.04, + "learning_rate": 4.904130810647836e-06, + "loss": 0.1628, + "step": 8139 + }, + { + "epoch": 1.04, + "learning_rate": 4.903094516074027e-06, + "loss": 0.1589, + "step": 8140 + }, + { + "epoch": 1.04, + "learning_rate": 4.902058225664465e-06, + "loss": 0.1667, + "step": 8141 + }, + { + "epoch": 1.04, + "learning_rate": 4.901021939463676e-06, + "loss": 0.1525, + "step": 8142 + }, + { + "epoch": 1.04, + "learning_rate": 4.899985657516195e-06, + "loss": 0.1597, + "step": 8143 + }, + { + "epoch": 1.04, + "learning_rate": 4.898949379866556e-06, + "loss": 0.1687, + "step": 8144 + }, + { + "epoch": 1.04, + "learning_rate": 4.897913106559285e-06, + "loss": 0.1388, + "step": 8145 + }, + { + "epoch": 1.04, + "learning_rate": 4.896876837638915e-06, + "loss": 0.1438, + "step": 8146 + }, + { + "epoch": 1.04, + "learning_rate": 4.895840573149977e-06, + "loss": 0.1719, + "step": 8147 + }, + { + "epoch": 1.04, + "learning_rate": 4.8948043131370025e-06, + "loss": 0.1599, + "step": 8148 + }, + { + "epoch": 1.04, + "learning_rate": 4.893768057644519e-06, + "loss": 0.1525, + "step": 8149 + }, + { + "epoch": 1.04, + "learning_rate": 4.89273180671706e-06, + "loss": 0.1421, + "step": 8150 + }, + { + "epoch": 1.04, + "learning_rate": 4.891695560399154e-06, + "loss": 0.1574, + "step": 8151 + }, + { + "epoch": 1.04, + "learning_rate": 4.890659318735333e-06, + "loss": 0.1481, + "step": 8152 + }, + { + "epoch": 1.04, + "learning_rate": 4.8896230817701214e-06, + "loss": 0.1641, + "step": 8153 + }, + { + "epoch": 1.04, + "learning_rate": 4.888586849548053e-06, + "loss": 0.1478, + "step": 8154 + }, + { + "epoch": 1.04, + "learning_rate": 4.887550622113657e-06, + "loss": 0.1501, + "step": 8155 + }, + { + "epoch": 1.04, + "learning_rate": 4.88651439951146e-06, + "loss": 0.1615, + "step": 8156 + }, + { + "epoch": 1.04, + "learning_rate": 4.885478181785991e-06, + "loss": 0.1562, + "step": 8157 + }, + { + "epoch": 1.04, + "learning_rate": 4.884441968981781e-06, + "loss": 0.1569, + "step": 8158 + }, + { + "epoch": 1.04, + "learning_rate": 4.883405761143357e-06, + "loss": 0.1419, + "step": 8159 + }, + { + "epoch": 1.04, + "learning_rate": 4.882369558315246e-06, + "loss": 0.1373, + "step": 8160 + }, + { + "epoch": 1.04, + "learning_rate": 4.8813333605419775e-06, + "loss": 0.1302, + "step": 8161 + }, + { + "epoch": 1.04, + "learning_rate": 4.88029716786808e-06, + "loss": 0.1505, + "step": 8162 + }, + { + "epoch": 1.04, + "learning_rate": 4.879260980338078e-06, + "loss": 0.1515, + "step": 8163 + }, + { + "epoch": 1.04, + "learning_rate": 4.878224797996502e-06, + "loss": 0.1561, + "step": 8164 + }, + { + "epoch": 1.05, + "learning_rate": 4.877188620887876e-06, + "loss": 0.161, + "step": 8165 + }, + { + "epoch": 1.05, + "learning_rate": 4.8761524490567315e-06, + "loss": 0.1586, + "step": 8166 + }, + { + "epoch": 1.05, + "learning_rate": 4.875116282547589e-06, + "loss": 0.1572, + "step": 8167 + }, + { + "epoch": 1.05, + "learning_rate": 4.874080121404979e-06, + "loss": 0.1562, + "step": 8168 + }, + { + "epoch": 1.05, + "learning_rate": 4.873043965673427e-06, + "loss": 0.1375, + "step": 8169 + }, + { + "epoch": 1.05, + "learning_rate": 4.872007815397459e-06, + "loss": 0.1638, + "step": 8170 + }, + { + "epoch": 1.05, + "learning_rate": 4.870971670621599e-06, + "loss": 0.1452, + "step": 8171 + }, + { + "epoch": 1.05, + "learning_rate": 4.869935531390374e-06, + "loss": 0.1559, + "step": 8172 + }, + { + "epoch": 1.05, + "learning_rate": 4.86889939774831e-06, + "loss": 0.1483, + "step": 8173 + }, + { + "epoch": 1.05, + "learning_rate": 4.86786326973993e-06, + "loss": 0.1543, + "step": 8174 + }, + { + "epoch": 1.05, + "learning_rate": 4.866827147409758e-06, + "loss": 0.1545, + "step": 8175 + }, + { + "epoch": 1.05, + "learning_rate": 4.8657910308023205e-06, + "loss": 0.1596, + "step": 8176 + }, + { + "epoch": 1.05, + "learning_rate": 4.864754919962144e-06, + "loss": 0.1465, + "step": 8177 + }, + { + "epoch": 1.05, + "learning_rate": 4.863718814933749e-06, + "loss": 0.1604, + "step": 8178 + }, + { + "epoch": 1.05, + "learning_rate": 4.862682715761658e-06, + "loss": 0.1541, + "step": 8179 + }, + { + "epoch": 1.05, + "learning_rate": 4.861646622490399e-06, + "loss": 0.1427, + "step": 8180 + }, + { + "epoch": 1.05, + "learning_rate": 4.860610535164491e-06, + "loss": 0.1451, + "step": 8181 + }, + { + "epoch": 1.05, + "learning_rate": 4.85957445382846e-06, + "loss": 0.1466, + "step": 8182 + }, + { + "epoch": 1.05, + "learning_rate": 4.858538378526825e-06, + "loss": 0.1642, + "step": 8183 + }, + { + "epoch": 1.05, + "learning_rate": 4.857502309304114e-06, + "loss": 0.1515, + "step": 8184 + }, + { + "epoch": 1.05, + "learning_rate": 4.856466246204844e-06, + "loss": 0.1576, + "step": 8185 + }, + { + "epoch": 1.05, + "learning_rate": 4.8554301892735385e-06, + "loss": 0.1506, + "step": 8186 + }, + { + "epoch": 1.05, + "learning_rate": 4.854394138554722e-06, + "loss": 0.1593, + "step": 8187 + }, + { + "epoch": 1.05, + "learning_rate": 4.853358094092913e-06, + "loss": 0.1371, + "step": 8188 + }, + { + "epoch": 1.05, + "learning_rate": 4.852322055932633e-06, + "loss": 0.169, + "step": 8189 + }, + { + "epoch": 1.05, + "learning_rate": 4.851286024118402e-06, + "loss": 0.1506, + "step": 8190 + }, + { + "epoch": 1.05, + "learning_rate": 4.850249998694745e-06, + "loss": 0.1416, + "step": 8191 + }, + { + "epoch": 1.05, + "learning_rate": 4.849213979706177e-06, + "loss": 0.1543, + "step": 8192 + }, + { + "epoch": 1.05, + "learning_rate": 4.848177967197219e-06, + "loss": 0.1627, + "step": 8193 + }, + { + "epoch": 1.05, + "learning_rate": 4.8471419612123925e-06, + "loss": 0.1535, + "step": 8194 + }, + { + "epoch": 1.05, + "learning_rate": 4.846105961796218e-06, + "loss": 0.1602, + "step": 8195 + }, + { + "epoch": 1.05, + "learning_rate": 4.845069968993212e-06, + "loss": 0.1391, + "step": 8196 + }, + { + "epoch": 1.05, + "learning_rate": 4.844033982847893e-06, + "loss": 0.1452, + "step": 8197 + }, + { + "epoch": 1.05, + "learning_rate": 4.842998003404784e-06, + "loss": 0.1624, + "step": 8198 + }, + { + "epoch": 1.05, + "learning_rate": 4.841962030708398e-06, + "loss": 0.136, + "step": 8199 + }, + { + "epoch": 1.05, + "learning_rate": 4.840926064803256e-06, + "loss": 0.1575, + "step": 8200 + }, + { + "epoch": 1.05, + "learning_rate": 4.839890105733876e-06, + "loss": 0.1542, + "step": 8201 + }, + { + "epoch": 1.05, + "learning_rate": 4.8388541535447756e-06, + "loss": 0.165, + "step": 8202 + }, + { + "epoch": 1.05, + "learning_rate": 4.837818208280469e-06, + "loss": 0.1425, + "step": 8203 + }, + { + "epoch": 1.05, + "learning_rate": 4.836782269985475e-06, + "loss": 0.1448, + "step": 8204 + }, + { + "epoch": 1.05, + "learning_rate": 4.8357463387043124e-06, + "loss": 0.1455, + "step": 8205 + }, + { + "epoch": 1.05, + "learning_rate": 4.834710414481496e-06, + "loss": 0.148, + "step": 8206 + }, + { + "epoch": 1.05, + "learning_rate": 4.833674497361539e-06, + "loss": 0.1563, + "step": 8207 + }, + { + "epoch": 1.05, + "learning_rate": 4.832638587388959e-06, + "loss": 0.1578, + "step": 8208 + }, + { + "epoch": 1.05, + "learning_rate": 4.831602684608274e-06, + "loss": 0.1666, + "step": 8209 + }, + { + "epoch": 1.05, + "learning_rate": 4.830566789063995e-06, + "loss": 0.1584, + "step": 8210 + }, + { + "epoch": 1.05, + "learning_rate": 4.829530900800638e-06, + "loss": 0.1461, + "step": 8211 + }, + { + "epoch": 1.05, + "learning_rate": 4.8284950198627186e-06, + "loss": 0.147, + "step": 8212 + }, + { + "epoch": 1.05, + "learning_rate": 4.827459146294751e-06, + "loss": 0.1483, + "step": 8213 + }, + { + "epoch": 1.05, + "learning_rate": 4.826423280141247e-06, + "loss": 0.132, + "step": 8214 + }, + { + "epoch": 1.05, + "learning_rate": 4.825387421446721e-06, + "loss": 0.1522, + "step": 8215 + }, + { + "epoch": 1.05, + "learning_rate": 4.824351570255689e-06, + "loss": 0.1495, + "step": 8216 + }, + { + "epoch": 1.05, + "learning_rate": 4.823315726612659e-06, + "loss": 0.1522, + "step": 8217 + }, + { + "epoch": 1.05, + "learning_rate": 4.8222798905621445e-06, + "loss": 0.1684, + "step": 8218 + }, + { + "epoch": 1.05, + "learning_rate": 4.82124406214866e-06, + "loss": 0.1514, + "step": 8219 + }, + { + "epoch": 1.05, + "learning_rate": 4.820208241416719e-06, + "loss": 0.1612, + "step": 8220 + }, + { + "epoch": 1.05, + "learning_rate": 4.819172428410826e-06, + "loss": 0.159, + "step": 8221 + }, + { + "epoch": 1.05, + "learning_rate": 4.818136623175498e-06, + "loss": 0.1492, + "step": 8222 + }, + { + "epoch": 1.05, + "learning_rate": 4.817100825755244e-06, + "loss": 0.158, + "step": 8223 + }, + { + "epoch": 1.05, + "learning_rate": 4.816065036194576e-06, + "loss": 0.1692, + "step": 8224 + }, + { + "epoch": 1.05, + "learning_rate": 4.815029254538003e-06, + "loss": 0.1427, + "step": 8225 + }, + { + "epoch": 1.05, + "learning_rate": 4.813993480830034e-06, + "loss": 0.1581, + "step": 8226 + }, + { + "epoch": 1.05, + "learning_rate": 4.812957715115181e-06, + "loss": 0.1511, + "step": 8227 + }, + { + "epoch": 1.05, + "learning_rate": 4.8119219574379495e-06, + "loss": 0.1623, + "step": 8228 + }, + { + "epoch": 1.05, + "learning_rate": 4.810886207842852e-06, + "loss": 0.1462, + "step": 8229 + }, + { + "epoch": 1.05, + "learning_rate": 4.809850466374393e-06, + "loss": 0.1585, + "step": 8230 + }, + { + "epoch": 1.05, + "learning_rate": 4.8088147330770855e-06, + "loss": 0.1587, + "step": 8231 + }, + { + "epoch": 1.05, + "learning_rate": 4.807779007995434e-06, + "loss": 0.1434, + "step": 8232 + }, + { + "epoch": 1.05, + "learning_rate": 4.8067432911739455e-06, + "loss": 0.153, + "step": 8233 + }, + { + "epoch": 1.05, + "learning_rate": 4.80570758265713e-06, + "loss": 0.157, + "step": 8234 + }, + { + "epoch": 1.05, + "learning_rate": 4.804671882489491e-06, + "loss": 0.1688, + "step": 8235 + }, + { + "epoch": 1.05, + "learning_rate": 4.803636190715536e-06, + "loss": 0.1609, + "step": 8236 + }, + { + "epoch": 1.05, + "learning_rate": 4.802600507379771e-06, + "loss": 0.1474, + "step": 8237 + }, + { + "epoch": 1.05, + "learning_rate": 4.801564832526704e-06, + "loss": 0.1692, + "step": 8238 + }, + { + "epoch": 1.05, + "learning_rate": 4.800529166200837e-06, + "loss": 0.1542, + "step": 8239 + }, + { + "epoch": 1.05, + "learning_rate": 4.7994935084466745e-06, + "loss": 0.15, + "step": 8240 + }, + { + "epoch": 1.05, + "learning_rate": 4.798457859308724e-06, + "loss": 0.1584, + "step": 8241 + }, + { + "epoch": 1.05, + "learning_rate": 4.797422218831488e-06, + "loss": 0.1663, + "step": 8242 + }, + { + "epoch": 1.06, + "learning_rate": 4.796386587059471e-06, + "loss": 0.1475, + "step": 8243 + }, + { + "epoch": 1.06, + "learning_rate": 4.795350964037174e-06, + "loss": 0.1484, + "step": 8244 + }, + { + "epoch": 1.06, + "learning_rate": 4.794315349809105e-06, + "loss": 0.1491, + "step": 8245 + }, + { + "epoch": 1.06, + "learning_rate": 4.7932797444197604e-06, + "loss": 0.1721, + "step": 8246 + }, + { + "epoch": 1.06, + "learning_rate": 4.792244147913647e-06, + "loss": 0.1467, + "step": 8247 + }, + { + "epoch": 1.06, + "learning_rate": 4.791208560335264e-06, + "loss": 0.1506, + "step": 8248 + }, + { + "epoch": 1.06, + "learning_rate": 4.790172981729116e-06, + "loss": 0.1697, + "step": 8249 + }, + { + "epoch": 1.06, + "learning_rate": 4.789137412139701e-06, + "loss": 0.1574, + "step": 8250 + }, + { + "epoch": 1.06, + "learning_rate": 4.7881018516115205e-06, + "loss": 0.1597, + "step": 8251 + }, + { + "epoch": 1.06, + "learning_rate": 4.787066300189077e-06, + "loss": 0.1446, + "step": 8252 + }, + { + "epoch": 1.06, + "learning_rate": 4.786030757916868e-06, + "loss": 0.1552, + "step": 8253 + }, + { + "epoch": 1.06, + "learning_rate": 4.784995224839394e-06, + "loss": 0.1515, + "step": 8254 + }, + { + "epoch": 1.06, + "learning_rate": 4.783959701001153e-06, + "loss": 0.1501, + "step": 8255 + }, + { + "epoch": 1.06, + "learning_rate": 4.782924186446647e-06, + "loss": 0.1576, + "step": 8256 + }, + { + "epoch": 1.06, + "learning_rate": 4.7818886812203715e-06, + "loss": 0.1439, + "step": 8257 + }, + { + "epoch": 1.06, + "learning_rate": 4.780853185366823e-06, + "loss": 0.1502, + "step": 8258 + }, + { + "epoch": 1.06, + "learning_rate": 4.779817698930502e-06, + "loss": 0.1479, + "step": 8259 + }, + { + "epoch": 1.06, + "learning_rate": 4.778782221955907e-06, + "loss": 0.1559, + "step": 8260 + }, + { + "epoch": 1.06, + "learning_rate": 4.77774675448753e-06, + "loss": 0.1463, + "step": 8261 + }, + { + "epoch": 1.06, + "learning_rate": 4.776711296569872e-06, + "loss": 0.1597, + "step": 8262 + }, + { + "epoch": 1.06, + "learning_rate": 4.775675848247427e-06, + "loss": 0.1555, + "step": 8263 + }, + { + "epoch": 1.06, + "learning_rate": 4.774640409564688e-06, + "loss": 0.155, + "step": 8264 + }, + { + "epoch": 1.06, + "learning_rate": 4.773604980566154e-06, + "loss": 0.15, + "step": 8265 + }, + { + "epoch": 1.06, + "learning_rate": 4.772569561296318e-06, + "loss": 0.137, + "step": 8266 + }, + { + "epoch": 1.06, + "learning_rate": 4.771534151799676e-06, + "loss": 0.1533, + "step": 8267 + }, + { + "epoch": 1.06, + "learning_rate": 4.770498752120718e-06, + "loss": 0.162, + "step": 8268 + }, + { + "epoch": 1.06, + "learning_rate": 4.76946336230394e-06, + "loss": 0.1537, + "step": 8269 + }, + { + "epoch": 1.06, + "learning_rate": 4.768427982393836e-06, + "loss": 0.1483, + "step": 8270 + }, + { + "epoch": 1.06, + "learning_rate": 4.767392612434897e-06, + "loss": 0.1525, + "step": 8271 + }, + { + "epoch": 1.06, + "learning_rate": 4.766357252471615e-06, + "loss": 0.163, + "step": 8272 + }, + { + "epoch": 1.06, + "learning_rate": 4.765321902548482e-06, + "loss": 0.1532, + "step": 8273 + }, + { + "epoch": 1.06, + "learning_rate": 4.76428656270999e-06, + "loss": 0.1639, + "step": 8274 + }, + { + "epoch": 1.06, + "learning_rate": 4.7632512330006296e-06, + "loss": 0.1595, + "step": 8275 + }, + { + "epoch": 1.06, + "learning_rate": 4.76221591346489e-06, + "loss": 0.15, + "step": 8276 + }, + { + "epoch": 1.06, + "learning_rate": 4.761180604147262e-06, + "loss": 0.1624, + "step": 8277 + }, + { + "epoch": 1.06, + "learning_rate": 4.760145305092238e-06, + "loss": 0.1434, + "step": 8278 + }, + { + "epoch": 1.06, + "learning_rate": 4.759110016344302e-06, + "loss": 0.1371, + "step": 8279 + }, + { + "epoch": 1.06, + "learning_rate": 4.7580747379479455e-06, + "loss": 0.1568, + "step": 8280 + }, + { + "epoch": 1.06, + "learning_rate": 4.757039469947658e-06, + "loss": 0.1691, + "step": 8281 + }, + { + "epoch": 1.06, + "learning_rate": 4.756004212387923e-06, + "loss": 0.1579, + "step": 8282 + }, + { + "epoch": 1.06, + "learning_rate": 4.7549689653132304e-06, + "loss": 0.1623, + "step": 8283 + }, + { + "epoch": 1.06, + "learning_rate": 4.753933728768069e-06, + "loss": 0.1574, + "step": 8284 + }, + { + "epoch": 1.06, + "learning_rate": 4.752898502796922e-06, + "loss": 0.1431, + "step": 8285 + }, + { + "epoch": 1.06, + "learning_rate": 4.751863287444278e-06, + "loss": 0.1648, + "step": 8286 + }, + { + "epoch": 1.06, + "learning_rate": 4.750828082754619e-06, + "loss": 0.1518, + "step": 8287 + }, + { + "epoch": 1.06, + "learning_rate": 4.7497928887724325e-06, + "loss": 0.148, + "step": 8288 + }, + { + "epoch": 1.06, + "learning_rate": 4.748757705542205e-06, + "loss": 0.1623, + "step": 8289 + }, + { + "epoch": 1.06, + "learning_rate": 4.7477225331084174e-06, + "loss": 0.1451, + "step": 8290 + }, + { + "epoch": 1.06, + "learning_rate": 4.746687371515554e-06, + "loss": 0.1536, + "step": 8291 + }, + { + "epoch": 1.06, + "learning_rate": 4.7456522208081e-06, + "loss": 0.1697, + "step": 8292 + }, + { + "epoch": 1.06, + "learning_rate": 4.7446170810305346e-06, + "loss": 0.1565, + "step": 8293 + }, + { + "epoch": 1.06, + "learning_rate": 4.743581952227342e-06, + "loss": 0.1598, + "step": 8294 + }, + { + "epoch": 1.06, + "learning_rate": 4.7425468344430035e-06, + "loss": 0.1444, + "step": 8295 + }, + { + "epoch": 1.06, + "learning_rate": 4.741511727722003e-06, + "loss": 0.1478, + "step": 8296 + }, + { + "epoch": 1.06, + "learning_rate": 4.740476632108818e-06, + "loss": 0.1477, + "step": 8297 + }, + { + "epoch": 1.06, + "learning_rate": 4.73944154764793e-06, + "loss": 0.1324, + "step": 8298 + }, + { + "epoch": 1.06, + "learning_rate": 4.73840647438382e-06, + "loss": 0.1715, + "step": 8299 + }, + { + "epoch": 1.06, + "learning_rate": 4.737371412360966e-06, + "loss": 0.1607, + "step": 8300 + }, + { + "epoch": 1.06, + "learning_rate": 4.7363363616238465e-06, + "loss": 0.1666, + "step": 8301 + }, + { + "epoch": 1.06, + "learning_rate": 4.73530132221694e-06, + "loss": 0.1592, + "step": 8302 + }, + { + "epoch": 1.06, + "learning_rate": 4.734266294184728e-06, + "loss": 0.1694, + "step": 8303 + }, + { + "epoch": 1.06, + "learning_rate": 4.733231277571683e-06, + "loss": 0.1576, + "step": 8304 + }, + { + "epoch": 1.06, + "learning_rate": 4.732196272422285e-06, + "loss": 0.1552, + "step": 8305 + }, + { + "epoch": 1.06, + "learning_rate": 4.731161278781008e-06, + "loss": 0.1528, + "step": 8306 + }, + { + "epoch": 1.06, + "learning_rate": 4.730126296692332e-06, + "loss": 0.1402, + "step": 8307 + }, + { + "epoch": 1.06, + "learning_rate": 4.72909132620073e-06, + "loss": 0.1261, + "step": 8308 + }, + { + "epoch": 1.06, + "learning_rate": 4.7280563673506745e-06, + "loss": 0.1454, + "step": 8309 + }, + { + "epoch": 1.06, + "learning_rate": 4.727021420186646e-06, + "loss": 0.1419, + "step": 8310 + }, + { + "epoch": 1.06, + "learning_rate": 4.725986484753112e-06, + "loss": 0.1596, + "step": 8311 + }, + { + "epoch": 1.06, + "learning_rate": 4.72495156109455e-06, + "loss": 0.1425, + "step": 8312 + }, + { + "epoch": 1.06, + "learning_rate": 4.723916649255432e-06, + "loss": 0.1406, + "step": 8313 + }, + { + "epoch": 1.06, + "learning_rate": 4.722881749280232e-06, + "loss": 0.161, + "step": 8314 + }, + { + "epoch": 1.06, + "learning_rate": 4.7218468612134175e-06, + "loss": 0.1529, + "step": 8315 + }, + { + "epoch": 1.06, + "learning_rate": 4.720811985099464e-06, + "loss": 0.1602, + "step": 8316 + }, + { + "epoch": 1.06, + "learning_rate": 4.719777120982843e-06, + "loss": 0.1389, + "step": 8317 + }, + { + "epoch": 1.06, + "learning_rate": 4.718742268908022e-06, + "loss": 0.1521, + "step": 8318 + }, + { + "epoch": 1.06, + "learning_rate": 4.717707428919471e-06, + "loss": 0.1509, + "step": 8319 + }, + { + "epoch": 1.06, + "learning_rate": 4.716672601061661e-06, + "loss": 0.1421, + "step": 8320 + }, + { + "epoch": 1.07, + "learning_rate": 4.715637785379062e-06, + "loss": 0.1599, + "step": 8321 + }, + { + "epoch": 1.07, + "learning_rate": 4.714602981916139e-06, + "loss": 0.1488, + "step": 8322 + }, + { + "epoch": 1.07, + "learning_rate": 4.713568190717362e-06, + "loss": 0.1512, + "step": 8323 + }, + { + "epoch": 1.07, + "learning_rate": 4.712533411827197e-06, + "loss": 0.1557, + "step": 8324 + }, + { + "epoch": 1.07, + "learning_rate": 4.711498645290113e-06, + "loss": 0.1681, + "step": 8325 + }, + { + "epoch": 1.07, + "learning_rate": 4.710463891150573e-06, + "loss": 0.1652, + "step": 8326 + }, + { + "epoch": 1.07, + "learning_rate": 4.709429149453046e-06, + "loss": 0.1656, + "step": 8327 + }, + { + "epoch": 1.07, + "learning_rate": 4.708394420241996e-06, + "loss": 0.1646, + "step": 8328 + }, + { + "epoch": 1.07, + "learning_rate": 4.707359703561885e-06, + "loss": 0.1739, + "step": 8329 + }, + { + "epoch": 1.07, + "learning_rate": 4.70632499945718e-06, + "loss": 0.17, + "step": 8330 + }, + { + "epoch": 1.07, + "learning_rate": 4.705290307972344e-06, + "loss": 0.1535, + "step": 8331 + }, + { + "epoch": 1.07, + "learning_rate": 4.7042556291518415e-06, + "loss": 0.155, + "step": 8332 + }, + { + "epoch": 1.07, + "learning_rate": 4.703220963040131e-06, + "loss": 0.1464, + "step": 8333 + }, + { + "epoch": 1.07, + "learning_rate": 4.702186309681677e-06, + "loss": 0.1423, + "step": 8334 + }, + { + "epoch": 1.07, + "learning_rate": 4.701151669120942e-06, + "loss": 0.1542, + "step": 8335 + }, + { + "epoch": 1.07, + "learning_rate": 4.700117041402384e-06, + "loss": 0.1482, + "step": 8336 + }, + { + "epoch": 1.07, + "learning_rate": 4.699082426570465e-06, + "loss": 0.1505, + "step": 8337 + }, + { + "epoch": 1.07, + "learning_rate": 4.6980478246696435e-06, + "loss": 0.16, + "step": 8338 + }, + { + "epoch": 1.07, + "learning_rate": 4.697013235744382e-06, + "loss": 0.1634, + "step": 8339 + }, + { + "epoch": 1.07, + "learning_rate": 4.695978659839133e-06, + "loss": 0.156, + "step": 8340 + }, + { + "epoch": 1.07, + "learning_rate": 4.694944096998361e-06, + "loss": 0.1476, + "step": 8341 + }, + { + "epoch": 1.07, + "learning_rate": 4.693909547266518e-06, + "loss": 0.1408, + "step": 8342 + }, + { + "epoch": 1.07, + "learning_rate": 4.692875010688066e-06, + "loss": 0.1467, + "step": 8343 + }, + { + "epoch": 1.07, + "learning_rate": 4.6918404873074574e-06, + "loss": 0.1507, + "step": 8344 + }, + { + "epoch": 1.07, + "learning_rate": 4.69080597716915e-06, + "loss": 0.1545, + "step": 8345 + }, + { + "epoch": 1.07, + "learning_rate": 4.6897714803175995e-06, + "loss": 0.1588, + "step": 8346 + }, + { + "epoch": 1.07, + "learning_rate": 4.688736996797257e-06, + "loss": 0.1506, + "step": 8347 + }, + { + "epoch": 1.07, + "learning_rate": 4.687702526652579e-06, + "loss": 0.1542, + "step": 8348 + }, + { + "epoch": 1.07, + "learning_rate": 4.68666806992802e-06, + "loss": 0.1636, + "step": 8349 + }, + { + "epoch": 1.07, + "learning_rate": 4.685633626668032e-06, + "loss": 0.1537, + "step": 8350 + }, + { + "epoch": 1.07, + "learning_rate": 4.684599196917067e-06, + "loss": 0.1772, + "step": 8351 + }, + { + "epoch": 1.07, + "learning_rate": 4.683564780719576e-06, + "loss": 0.16, + "step": 8352 + }, + { + "epoch": 1.07, + "learning_rate": 4.682530378120014e-06, + "loss": 0.1639, + "step": 8353 + }, + { + "epoch": 1.07, + "learning_rate": 4.681495989162826e-06, + "loss": 0.159, + "step": 8354 + }, + { + "epoch": 1.07, + "learning_rate": 4.680461613892465e-06, + "loss": 0.1735, + "step": 8355 + }, + { + "epoch": 1.07, + "learning_rate": 4.679427252353379e-06, + "loss": 0.1489, + "step": 8356 + }, + { + "epoch": 1.07, + "learning_rate": 4.678392904590021e-06, + "loss": 0.1423, + "step": 8357 + }, + { + "epoch": 1.07, + "learning_rate": 4.677358570646834e-06, + "loss": 0.1564, + "step": 8358 + }, + { + "epoch": 1.07, + "learning_rate": 4.676324250568269e-06, + "loss": 0.1509, + "step": 8359 + }, + { + "epoch": 1.07, + "learning_rate": 4.6752899443987694e-06, + "loss": 0.1812, + "step": 8360 + }, + { + "epoch": 1.07, + "learning_rate": 4.674255652182788e-06, + "loss": 0.1427, + "step": 8361 + }, + { + "epoch": 1.07, + "learning_rate": 4.673221373964764e-06, + "loss": 0.1484, + "step": 8362 + }, + { + "epoch": 1.07, + "learning_rate": 4.672187109789144e-06, + "loss": 0.1559, + "step": 8363 + }, + { + "epoch": 1.07, + "learning_rate": 4.671152859700377e-06, + "loss": 0.1452, + "step": 8364 + }, + { + "epoch": 1.07, + "learning_rate": 4.670118623742904e-06, + "loss": 0.1384, + "step": 8365 + }, + { + "epoch": 1.07, + "learning_rate": 4.669084401961166e-06, + "loss": 0.153, + "step": 8366 + }, + { + "epoch": 1.07, + "learning_rate": 4.668050194399609e-06, + "loss": 0.1479, + "step": 8367 + }, + { + "epoch": 1.07, + "learning_rate": 4.667016001102675e-06, + "loss": 0.1547, + "step": 8368 + }, + { + "epoch": 1.07, + "learning_rate": 4.665981822114805e-06, + "loss": 0.1573, + "step": 8369 + }, + { + "epoch": 1.07, + "learning_rate": 4.66494765748044e-06, + "loss": 0.1393, + "step": 8370 + }, + { + "epoch": 1.07, + "learning_rate": 4.6639135072440195e-06, + "loss": 0.1472, + "step": 8371 + }, + { + "epoch": 1.07, + "learning_rate": 4.662879371449987e-06, + "loss": 0.1536, + "step": 8372 + }, + { + "epoch": 1.07, + "learning_rate": 4.6618452501427755e-06, + "loss": 0.1633, + "step": 8373 + }, + { + "epoch": 1.07, + "learning_rate": 4.660811143366828e-06, + "loss": 0.1524, + "step": 8374 + }, + { + "epoch": 1.07, + "learning_rate": 4.6597770511665814e-06, + "loss": 0.1472, + "step": 8375 + }, + { + "epoch": 1.07, + "learning_rate": 4.658742973586471e-06, + "loss": 0.14, + "step": 8376 + }, + { + "epoch": 1.07, + "learning_rate": 4.657708910670936e-06, + "loss": 0.1574, + "step": 8377 + }, + { + "epoch": 1.07, + "learning_rate": 4.656674862464412e-06, + "loss": 0.1506, + "step": 8378 + }, + { + "epoch": 1.07, + "learning_rate": 4.655640829011335e-06, + "loss": 0.1414, + "step": 8379 + }, + { + "epoch": 1.07, + "learning_rate": 4.654606810356135e-06, + "loss": 0.1454, + "step": 8380 + }, + { + "epoch": 1.07, + "learning_rate": 4.653572806543251e-06, + "loss": 0.1586, + "step": 8381 + }, + { + "epoch": 1.07, + "learning_rate": 4.652538817617117e-06, + "loss": 0.1455, + "step": 8382 + }, + { + "epoch": 1.07, + "learning_rate": 4.651504843622163e-06, + "loss": 0.1614, + "step": 8383 + }, + { + "epoch": 1.07, + "learning_rate": 4.65047088460282e-06, + "loss": 0.1488, + "step": 8384 + }, + { + "epoch": 1.07, + "learning_rate": 4.6494369406035225e-06, + "loss": 0.1515, + "step": 8385 + }, + { + "epoch": 1.07, + "learning_rate": 4.6484030116687014e-06, + "loss": 0.1593, + "step": 8386 + }, + { + "epoch": 1.07, + "learning_rate": 4.647369097842785e-06, + "loss": 0.1544, + "step": 8387 + }, + { + "epoch": 1.07, + "learning_rate": 4.646335199170205e-06, + "loss": 0.1745, + "step": 8388 + }, + { + "epoch": 1.07, + "learning_rate": 4.645301315695387e-06, + "loss": 0.1388, + "step": 8389 + }, + { + "epoch": 1.07, + "learning_rate": 4.6442674474627645e-06, + "loss": 0.1281, + "step": 8390 + }, + { + "epoch": 1.07, + "learning_rate": 4.643233594516759e-06, + "loss": 0.1433, + "step": 8391 + }, + { + "epoch": 1.07, + "learning_rate": 4.642199756901802e-06, + "loss": 0.1552, + "step": 8392 + }, + { + "epoch": 1.07, + "learning_rate": 4.64116593466232e-06, + "loss": 0.1507, + "step": 8393 + }, + { + "epoch": 1.07, + "learning_rate": 4.6401321278427334e-06, + "loss": 0.1642, + "step": 8394 + }, + { + "epoch": 1.07, + "learning_rate": 4.639098336487472e-06, + "loss": 0.1687, + "step": 8395 + }, + { + "epoch": 1.07, + "learning_rate": 4.638064560640959e-06, + "loss": 0.1544, + "step": 8396 + }, + { + "epoch": 1.07, + "learning_rate": 4.63703080034762e-06, + "loss": 0.1501, + "step": 8397 + }, + { + "epoch": 1.07, + "learning_rate": 4.635997055651873e-06, + "loss": 0.1559, + "step": 8398 + }, + { + "epoch": 1.08, + "learning_rate": 4.634963326598143e-06, + "loss": 0.1544, + "step": 8399 + }, + { + "epoch": 1.08, + "learning_rate": 4.633929613230855e-06, + "loss": 0.1437, + "step": 8400 + }, + { + "epoch": 1.08, + "learning_rate": 4.632895915594424e-06, + "loss": 0.1538, + "step": 8401 + }, + { + "epoch": 1.08, + "learning_rate": 4.631862233733274e-06, + "loss": 0.1436, + "step": 8402 + }, + { + "epoch": 1.08, + "learning_rate": 4.630828567691823e-06, + "loss": 0.1506, + "step": 8403 + }, + { + "epoch": 1.08, + "learning_rate": 4.629794917514492e-06, + "loss": 0.1544, + "step": 8404 + }, + { + "epoch": 1.08, + "learning_rate": 4.628761283245697e-06, + "loss": 0.1563, + "step": 8405 + }, + { + "epoch": 1.08, + "learning_rate": 4.627727664929856e-06, + "loss": 0.137, + "step": 8406 + }, + { + "epoch": 1.08, + "learning_rate": 4.626694062611387e-06, + "loss": 0.1445, + "step": 8407 + }, + { + "epoch": 1.08, + "learning_rate": 4.6256604763347066e-06, + "loss": 0.1412, + "step": 8408 + }, + { + "epoch": 1.08, + "learning_rate": 4.624626906144227e-06, + "loss": 0.1522, + "step": 8409 + }, + { + "epoch": 1.08, + "learning_rate": 4.623593352084367e-06, + "loss": 0.1463, + "step": 8410 + }, + { + "epoch": 1.08, + "learning_rate": 4.622559814199538e-06, + "loss": 0.1432, + "step": 8411 + }, + { + "epoch": 1.08, + "learning_rate": 4.621526292534156e-06, + "loss": 0.1605, + "step": 8412 + }, + { + "epoch": 1.08, + "learning_rate": 4.6204927871326295e-06, + "loss": 0.1711, + "step": 8413 + }, + { + "epoch": 1.08, + "learning_rate": 4.619459298039373e-06, + "loss": 0.1426, + "step": 8414 + }, + { + "epoch": 1.08, + "learning_rate": 4.6184258252988016e-06, + "loss": 0.153, + "step": 8415 + }, + { + "epoch": 1.08, + "learning_rate": 4.6173923689553205e-06, + "loss": 0.1434, + "step": 8416 + }, + { + "epoch": 1.08, + "learning_rate": 4.616358929053339e-06, + "loss": 0.1719, + "step": 8417 + }, + { + "epoch": 1.08, + "learning_rate": 4.615325505637272e-06, + "loss": 0.1517, + "step": 8418 + }, + { + "epoch": 1.08, + "learning_rate": 4.614292098751524e-06, + "loss": 0.1664, + "step": 8419 + }, + { + "epoch": 1.08, + "learning_rate": 4.613258708440503e-06, + "loss": 0.1519, + "step": 8420 + }, + { + "epoch": 1.08, + "learning_rate": 4.612225334748616e-06, + "loss": 0.1415, + "step": 8421 + }, + { + "epoch": 1.08, + "learning_rate": 4.611191977720272e-06, + "loss": 0.1376, + "step": 8422 + }, + { + "epoch": 1.08, + "learning_rate": 4.610158637399872e-06, + "loss": 0.1383, + "step": 8423 + }, + { + "epoch": 1.08, + "learning_rate": 4.609125313831826e-06, + "loss": 0.1371, + "step": 8424 + }, + { + "epoch": 1.08, + "learning_rate": 4.608092007060533e-06, + "loss": 0.1489, + "step": 8425 + }, + { + "epoch": 1.08, + "learning_rate": 4.607058717130403e-06, + "loss": 0.1589, + "step": 8426 + }, + { + "epoch": 1.08, + "learning_rate": 4.6060254440858315e-06, + "loss": 0.148, + "step": 8427 + }, + { + "epoch": 1.08, + "learning_rate": 4.6049921879712254e-06, + "loss": 0.158, + "step": 8428 + }, + { + "epoch": 1.08, + "learning_rate": 4.603958948830985e-06, + "loss": 0.1435, + "step": 8429 + }, + { + "epoch": 1.08, + "learning_rate": 4.602925726709512e-06, + "loss": 0.1382, + "step": 8430 + }, + { + "epoch": 1.08, + "learning_rate": 4.6018925216512025e-06, + "loss": 0.1469, + "step": 8431 + }, + { + "epoch": 1.08, + "learning_rate": 4.600859333700457e-06, + "loss": 0.1436, + "step": 8432 + }, + { + "epoch": 1.08, + "learning_rate": 4.599826162901679e-06, + "loss": 0.15, + "step": 8433 + }, + { + "epoch": 1.08, + "learning_rate": 4.5987930092992596e-06, + "loss": 0.1587, + "step": 8434 + }, + { + "epoch": 1.08, + "learning_rate": 4.597759872937597e-06, + "loss": 0.1536, + "step": 8435 + }, + { + "epoch": 1.08, + "learning_rate": 4.5967267538610915e-06, + "loss": 0.1513, + "step": 8436 + }, + { + "epoch": 1.08, + "learning_rate": 4.595693652114133e-06, + "loss": 0.1473, + "step": 8437 + }, + { + "epoch": 1.08, + "learning_rate": 4.594660567741118e-06, + "loss": 0.1593, + "step": 8438 + }, + { + "epoch": 1.08, + "learning_rate": 4.593627500786444e-06, + "loss": 0.1404, + "step": 8439 + }, + { + "epoch": 1.08, + "learning_rate": 4.592594451294501e-06, + "loss": 0.1553, + "step": 8440 + }, + { + "epoch": 1.08, + "learning_rate": 4.59156141930968e-06, + "loss": 0.1559, + "step": 8441 + }, + { + "epoch": 1.08, + "learning_rate": 4.590528404876374e-06, + "loss": 0.1419, + "step": 8442 + }, + { + "epoch": 1.08, + "learning_rate": 4.5894954080389755e-06, + "loss": 0.1511, + "step": 8443 + }, + { + "epoch": 1.08, + "learning_rate": 4.588462428841875e-06, + "loss": 0.1461, + "step": 8444 + }, + { + "epoch": 1.08, + "learning_rate": 4.587429467329458e-06, + "loss": 0.157, + "step": 8445 + }, + { + "epoch": 1.08, + "learning_rate": 4.586396523546116e-06, + "loss": 0.1497, + "step": 8446 + }, + { + "epoch": 1.08, + "learning_rate": 4.585363597536239e-06, + "loss": 0.1442, + "step": 8447 + }, + { + "epoch": 1.08, + "learning_rate": 4.584330689344211e-06, + "loss": 0.1602, + "step": 8448 + }, + { + "epoch": 1.08, + "learning_rate": 4.5832977990144165e-06, + "loss": 0.1502, + "step": 8449 + }, + { + "epoch": 1.08, + "learning_rate": 4.582264926591244e-06, + "loss": 0.1576, + "step": 8450 + }, + { + "epoch": 1.08, + "learning_rate": 4.581232072119081e-06, + "loss": 0.1396, + "step": 8451 + }, + { + "epoch": 1.08, + "learning_rate": 4.580199235642306e-06, + "loss": 0.1375, + "step": 8452 + }, + { + "epoch": 1.08, + "learning_rate": 4.5791664172053044e-06, + "loss": 0.1441, + "step": 8453 + }, + { + "epoch": 1.08, + "learning_rate": 4.578133616852462e-06, + "loss": 0.1427, + "step": 8454 + }, + { + "epoch": 1.08, + "learning_rate": 4.577100834628155e-06, + "loss": 0.1525, + "step": 8455 + }, + { + "epoch": 1.08, + "learning_rate": 4.5760680705767665e-06, + "loss": 0.1494, + "step": 8456 + }, + { + "epoch": 1.08, + "learning_rate": 4.5750353247426785e-06, + "loss": 0.1581, + "step": 8457 + }, + { + "epoch": 1.08, + "learning_rate": 4.5740025971702695e-06, + "loss": 0.1425, + "step": 8458 + }, + { + "epoch": 1.08, + "learning_rate": 4.572969887903916e-06, + "loss": 0.1434, + "step": 8459 + }, + { + "epoch": 1.08, + "learning_rate": 4.571937196987998e-06, + "loss": 0.1544, + "step": 8460 + }, + { + "epoch": 1.08, + "learning_rate": 4.570904524466893e-06, + "loss": 0.1457, + "step": 8461 + }, + { + "epoch": 1.08, + "learning_rate": 4.5698718703849755e-06, + "loss": 0.1612, + "step": 8462 + }, + { + "epoch": 1.08, + "learning_rate": 4.5688392347866226e-06, + "loss": 0.1494, + "step": 8463 + }, + { + "epoch": 1.08, + "learning_rate": 4.5678066177162065e-06, + "loss": 0.17, + "step": 8464 + }, + { + "epoch": 1.08, + "learning_rate": 4.566774019218104e-06, + "loss": 0.1603, + "step": 8465 + }, + { + "epoch": 1.08, + "learning_rate": 4.565741439336686e-06, + "loss": 0.1537, + "step": 8466 + }, + { + "epoch": 1.08, + "learning_rate": 4.5647088781163255e-06, + "loss": 0.1532, + "step": 8467 + }, + { + "epoch": 1.08, + "learning_rate": 4.563676335601393e-06, + "loss": 0.1434, + "step": 8468 + }, + { + "epoch": 1.08, + "learning_rate": 4.562643811836263e-06, + "loss": 0.1436, + "step": 8469 + }, + { + "epoch": 1.08, + "learning_rate": 4.561611306865299e-06, + "loss": 0.137, + "step": 8470 + }, + { + "epoch": 1.08, + "learning_rate": 4.560578820732876e-06, + "loss": 0.147, + "step": 8471 + }, + { + "epoch": 1.08, + "learning_rate": 4.559546353483359e-06, + "loss": 0.1406, + "step": 8472 + }, + { + "epoch": 1.08, + "learning_rate": 4.558513905161116e-06, + "loss": 0.1534, + "step": 8473 + }, + { + "epoch": 1.08, + "learning_rate": 4.557481475810512e-06, + "loss": 0.1384, + "step": 8474 + }, + { + "epoch": 1.08, + "learning_rate": 4.556449065475917e-06, + "loss": 0.1455, + "step": 8475 + }, + { + "epoch": 1.08, + "learning_rate": 4.555416674201693e-06, + "loss": 0.1573, + "step": 8476 + }, + { + "epoch": 1.09, + "learning_rate": 4.554384302032204e-06, + "loss": 0.1532, + "step": 8477 + }, + { + "epoch": 1.09, + "learning_rate": 4.553351949011814e-06, + "loss": 0.1569, + "step": 8478 + }, + { + "epoch": 1.09, + "learning_rate": 4.5523196151848846e-06, + "loss": 0.1565, + "step": 8479 + }, + { + "epoch": 1.09, + "learning_rate": 4.551287300595781e-06, + "loss": 0.1531, + "step": 8480 + }, + { + "epoch": 1.09, + "learning_rate": 4.550255005288861e-06, + "loss": 0.1495, + "step": 8481 + }, + { + "epoch": 1.09, + "learning_rate": 4.549222729308483e-06, + "loss": 0.1665, + "step": 8482 + }, + { + "epoch": 1.09, + "learning_rate": 4.548190472699011e-06, + "loss": 0.1515, + "step": 8483 + }, + { + "epoch": 1.09, + "learning_rate": 4.547158235504797e-06, + "loss": 0.1515, + "step": 8484 + }, + { + "epoch": 1.09, + "learning_rate": 4.546126017770205e-06, + "loss": 0.1595, + "step": 8485 + }, + { + "epoch": 1.09, + "learning_rate": 4.5450938195395875e-06, + "loss": 0.1513, + "step": 8486 + }, + { + "epoch": 1.09, + "learning_rate": 4.544061640857303e-06, + "loss": 0.1664, + "step": 8487 + }, + { + "epoch": 1.09, + "learning_rate": 4.543029481767703e-06, + "loss": 0.1726, + "step": 8488 + }, + { + "epoch": 1.09, + "learning_rate": 4.541997342315145e-06, + "loss": 0.1488, + "step": 8489 + }, + { + "epoch": 1.09, + "learning_rate": 4.540965222543981e-06, + "loss": 0.1394, + "step": 8490 + }, + { + "epoch": 1.09, + "learning_rate": 4.539933122498566e-06, + "loss": 0.1393, + "step": 8491 + }, + { + "epoch": 1.09, + "learning_rate": 4.5389010422232474e-06, + "loss": 0.1543, + "step": 8492 + }, + { + "epoch": 1.09, + "learning_rate": 4.5378689817623765e-06, + "loss": 0.1349, + "step": 8493 + }, + { + "epoch": 1.09, + "learning_rate": 4.536836941160308e-06, + "loss": 0.1445, + "step": 8494 + }, + { + "epoch": 1.09, + "learning_rate": 4.535804920461386e-06, + "loss": 0.1488, + "step": 8495 + }, + { + "epoch": 1.09, + "learning_rate": 4.53477291970996e-06, + "loss": 0.1546, + "step": 8496 + }, + { + "epoch": 1.09, + "learning_rate": 4.5337409389503764e-06, + "loss": 0.1606, + "step": 8497 + }, + { + "epoch": 1.09, + "learning_rate": 4.532708978226987e-06, + "loss": 0.1455, + "step": 8498 + }, + { + "epoch": 1.09, + "learning_rate": 4.5316770375841315e-06, + "loss": 0.1518, + "step": 8499 + }, + { + "epoch": 1.09, + "learning_rate": 4.530645117066155e-06, + "loss": 0.1535, + "step": 8500 + }, + { + "epoch": 1.09, + "learning_rate": 4.529613216717406e-06, + "loss": 0.1318, + "step": 8501 + }, + { + "epoch": 1.09, + "learning_rate": 4.528581336582223e-06, + "loss": 0.1632, + "step": 8502 + }, + { + "epoch": 1.09, + "learning_rate": 4.527549476704949e-06, + "loss": 0.1515, + "step": 8503 + }, + { + "epoch": 1.09, + "learning_rate": 4.526517637129927e-06, + "loss": 0.1458, + "step": 8504 + }, + { + "epoch": 1.09, + "learning_rate": 4.525485817901499e-06, + "loss": 0.1441, + "step": 8505 + }, + { + "epoch": 1.09, + "learning_rate": 4.524454019063999e-06, + "loss": 0.1503, + "step": 8506 + }, + { + "epoch": 1.09, + "learning_rate": 4.52342224066177e-06, + "loss": 0.1404, + "step": 8507 + }, + { + "epoch": 1.09, + "learning_rate": 4.522390482739148e-06, + "loss": 0.1416, + "step": 8508 + }, + { + "epoch": 1.09, + "learning_rate": 4.5213587453404736e-06, + "loss": 0.1426, + "step": 8509 + }, + { + "epoch": 1.09, + "learning_rate": 4.520327028510076e-06, + "loss": 0.1726, + "step": 8510 + }, + { + "epoch": 1.09, + "learning_rate": 4.5192953322922955e-06, + "loss": 0.1526, + "step": 8511 + }, + { + "epoch": 1.09, + "learning_rate": 4.518263656731468e-06, + "loss": 0.1486, + "step": 8512 + }, + { + "epoch": 1.09, + "learning_rate": 4.5172320018719205e-06, + "loss": 0.1495, + "step": 8513 + }, + { + "epoch": 1.09, + "learning_rate": 4.5162003677579905e-06, + "loss": 0.1451, + "step": 8514 + }, + { + "epoch": 1.09, + "learning_rate": 4.5151687544340065e-06, + "loss": 0.1468, + "step": 8515 + }, + { + "epoch": 1.09, + "learning_rate": 4.514137161944304e-06, + "loss": 0.15, + "step": 8516 + }, + { + "epoch": 1.09, + "learning_rate": 4.513105590333207e-06, + "loss": 0.1443, + "step": 8517 + }, + { + "epoch": 1.09, + "learning_rate": 4.512074039645049e-06, + "loss": 0.1794, + "step": 8518 + }, + { + "epoch": 1.09, + "learning_rate": 4.511042509924157e-06, + "loss": 0.17, + "step": 8519 + }, + { + "epoch": 1.09, + "learning_rate": 4.5100110012148546e-06, + "loss": 0.1404, + "step": 8520 + }, + { + "epoch": 1.09, + "learning_rate": 4.508979513561471e-06, + "loss": 0.1522, + "step": 8521 + }, + { + "epoch": 1.09, + "learning_rate": 4.507948047008332e-06, + "loss": 0.15, + "step": 8522 + }, + { + "epoch": 1.09, + "learning_rate": 4.506916601599763e-06, + "loss": 0.1418, + "step": 8523 + }, + { + "epoch": 1.09, + "learning_rate": 4.505885177380083e-06, + "loss": 0.1431, + "step": 8524 + }, + { + "epoch": 1.09, + "learning_rate": 4.504853774393618e-06, + "loss": 0.1678, + "step": 8525 + }, + { + "epoch": 1.09, + "learning_rate": 4.5038223926846905e-06, + "loss": 0.143, + "step": 8526 + }, + { + "epoch": 1.09, + "learning_rate": 4.5027910322976186e-06, + "loss": 0.1546, + "step": 8527 + }, + { + "epoch": 1.09, + "learning_rate": 4.501759693276724e-06, + "loss": 0.1505, + "step": 8528 + }, + { + "epoch": 1.09, + "learning_rate": 4.5007283756663245e-06, + "loss": 0.1502, + "step": 8529 + }, + { + "epoch": 1.09, + "learning_rate": 4.49969707951074e-06, + "loss": 0.1534, + "step": 8530 + }, + { + "epoch": 1.09, + "learning_rate": 4.498665804854285e-06, + "loss": 0.1422, + "step": 8531 + }, + { + "epoch": 1.09, + "learning_rate": 4.497634551741277e-06, + "loss": 0.1656, + "step": 8532 + }, + { + "epoch": 1.09, + "learning_rate": 4.49660332021603e-06, + "loss": 0.1455, + "step": 8533 + }, + { + "epoch": 1.09, + "learning_rate": 4.495572110322862e-06, + "loss": 0.1459, + "step": 8534 + }, + { + "epoch": 1.09, + "learning_rate": 4.494540922106082e-06, + "loss": 0.1497, + "step": 8535 + }, + { + "epoch": 1.09, + "learning_rate": 4.4935097556100045e-06, + "loss": 0.1575, + "step": 8536 + }, + { + "epoch": 1.09, + "learning_rate": 4.492478610878942e-06, + "loss": 0.1616, + "step": 8537 + }, + { + "epoch": 1.09, + "learning_rate": 4.491447487957203e-06, + "loss": 0.1536, + "step": 8538 + }, + { + "epoch": 1.09, + "learning_rate": 4.490416386889097e-06, + "loss": 0.1636, + "step": 8539 + }, + { + "epoch": 1.09, + "learning_rate": 4.489385307718934e-06, + "loss": 0.1608, + "step": 8540 + }, + { + "epoch": 1.09, + "learning_rate": 4.488354250491024e-06, + "loss": 0.1359, + "step": 8541 + }, + { + "epoch": 1.09, + "learning_rate": 4.48732321524967e-06, + "loss": 0.1581, + "step": 8542 + }, + { + "epoch": 1.09, + "learning_rate": 4.486292202039178e-06, + "loss": 0.1593, + "step": 8543 + }, + { + "epoch": 1.09, + "learning_rate": 4.485261210903854e-06, + "loss": 0.1828, + "step": 8544 + }, + { + "epoch": 1.09, + "learning_rate": 4.484230241888005e-06, + "loss": 0.1578, + "step": 8545 + }, + { + "epoch": 1.09, + "learning_rate": 4.48319929503593e-06, + "loss": 0.1611, + "step": 8546 + }, + { + "epoch": 1.09, + "learning_rate": 4.482168370391931e-06, + "loss": 0.1548, + "step": 8547 + }, + { + "epoch": 1.09, + "learning_rate": 4.481137468000312e-06, + "loss": 0.1488, + "step": 8548 + }, + { + "epoch": 1.09, + "learning_rate": 4.48010658790537e-06, + "loss": 0.1676, + "step": 8549 + }, + { + "epoch": 1.09, + "learning_rate": 4.479075730151406e-06, + "loss": 0.1544, + "step": 8550 + }, + { + "epoch": 1.09, + "learning_rate": 4.478044894782718e-06, + "loss": 0.166, + "step": 8551 + }, + { + "epoch": 1.09, + "learning_rate": 4.477014081843605e-06, + "loss": 0.1443, + "step": 8552 + }, + { + "epoch": 1.09, + "learning_rate": 4.47598329137836e-06, + "loss": 0.1428, + "step": 8553 + }, + { + "epoch": 1.09, + "learning_rate": 4.47495252343128e-06, + "loss": 0.1612, + "step": 8554 + }, + { + "epoch": 1.1, + "learning_rate": 4.473921778046661e-06, + "loss": 0.1449, + "step": 8555 + }, + { + "epoch": 1.1, + "learning_rate": 4.4728910552687935e-06, + "loss": 0.1347, + "step": 8556 + }, + { + "epoch": 1.1, + "learning_rate": 4.471860355141971e-06, + "loss": 0.1407, + "step": 8557 + }, + { + "epoch": 1.1, + "learning_rate": 4.470829677710485e-06, + "loss": 0.1417, + "step": 8558 + }, + { + "epoch": 1.1, + "learning_rate": 4.469799023018628e-06, + "loss": 0.157, + "step": 8559 + }, + { + "epoch": 1.1, + "learning_rate": 4.468768391110687e-06, + "loss": 0.1534, + "step": 8560 + }, + { + "epoch": 1.1, + "learning_rate": 4.467737782030951e-06, + "loss": 0.16, + "step": 8561 + }, + { + "epoch": 1.1, + "learning_rate": 4.466707195823707e-06, + "loss": 0.1593, + "step": 8562 + }, + { + "epoch": 1.1, + "learning_rate": 4.465676632533245e-06, + "loss": 0.159, + "step": 8563 + }, + { + "epoch": 1.1, + "learning_rate": 4.464646092203846e-06, + "loss": 0.1458, + "step": 8564 + }, + { + "epoch": 1.1, + "learning_rate": 4.463615574879798e-06, + "loss": 0.1587, + "step": 8565 + }, + { + "epoch": 1.1, + "learning_rate": 4.462585080605384e-06, + "loss": 0.1387, + "step": 8566 + }, + { + "epoch": 1.1, + "learning_rate": 4.461554609424884e-06, + "loss": 0.1631, + "step": 8567 + }, + { + "epoch": 1.1, + "learning_rate": 4.460524161382582e-06, + "loss": 0.1394, + "step": 8568 + }, + { + "epoch": 1.1, + "learning_rate": 4.459493736522759e-06, + "loss": 0.1468, + "step": 8569 + }, + { + "epoch": 1.1, + "learning_rate": 4.4584633348896945e-06, + "loss": 0.1603, + "step": 8570 + }, + { + "epoch": 1.1, + "learning_rate": 4.457432956527665e-06, + "loss": 0.1381, + "step": 8571 + }, + { + "epoch": 1.1, + "learning_rate": 4.456402601480949e-06, + "loss": 0.1472, + "step": 8572 + }, + { + "epoch": 1.1, + "learning_rate": 4.455372269793826e-06, + "loss": 0.1689, + "step": 8573 + }, + { + "epoch": 1.1, + "learning_rate": 4.4543419615105685e-06, + "loss": 0.1595, + "step": 8574 + }, + { + "epoch": 1.1, + "learning_rate": 4.453311676675453e-06, + "loss": 0.1609, + "step": 8575 + }, + { + "epoch": 1.1, + "learning_rate": 4.452281415332751e-06, + "loss": 0.1416, + "step": 8576 + }, + { + "epoch": 1.1, + "learning_rate": 4.451251177526738e-06, + "loss": 0.1544, + "step": 8577 + }, + { + "epoch": 1.1, + "learning_rate": 4.450220963301683e-06, + "loss": 0.154, + "step": 8578 + }, + { + "epoch": 1.1, + "learning_rate": 4.449190772701857e-06, + "loss": 0.1577, + "step": 8579 + }, + { + "epoch": 1.1, + "learning_rate": 4.44816060577153e-06, + "loss": 0.1595, + "step": 8580 + }, + { + "epoch": 1.1, + "learning_rate": 4.447130462554974e-06, + "loss": 0.1437, + "step": 8581 + }, + { + "epoch": 1.1, + "learning_rate": 4.44610034309645e-06, + "loss": 0.1416, + "step": 8582 + }, + { + "epoch": 1.1, + "learning_rate": 4.4450702474402295e-06, + "loss": 0.144, + "step": 8583 + }, + { + "epoch": 1.1, + "learning_rate": 4.444040175630577e-06, + "loss": 0.1556, + "step": 8584 + }, + { + "epoch": 1.1, + "learning_rate": 4.443010127711755e-06, + "loss": 0.1492, + "step": 8585 + }, + { + "epoch": 1.1, + "learning_rate": 4.441980103728027e-06, + "loss": 0.1475, + "step": 8586 + }, + { + "epoch": 1.1, + "learning_rate": 4.440950103723658e-06, + "loss": 0.1545, + "step": 8587 + }, + { + "epoch": 1.1, + "learning_rate": 4.439920127742909e-06, + "loss": 0.1679, + "step": 8588 + }, + { + "epoch": 1.1, + "learning_rate": 4.438890175830039e-06, + "loss": 0.1748, + "step": 8589 + }, + { + "epoch": 1.1, + "learning_rate": 4.437860248029307e-06, + "loss": 0.1543, + "step": 8590 + }, + { + "epoch": 1.1, + "learning_rate": 4.4368303443849735e-06, + "loss": 0.1407, + "step": 8591 + }, + { + "epoch": 1.1, + "learning_rate": 4.435800464941292e-06, + "loss": 0.1353, + "step": 8592 + }, + { + "epoch": 1.1, + "learning_rate": 4.434770609742523e-06, + "loss": 0.1522, + "step": 8593 + }, + { + "epoch": 1.1, + "learning_rate": 4.433740778832919e-06, + "loss": 0.1569, + "step": 8594 + }, + { + "epoch": 1.1, + "learning_rate": 4.432710972256737e-06, + "loss": 0.1405, + "step": 8595 + }, + { + "epoch": 1.1, + "learning_rate": 4.431681190058224e-06, + "loss": 0.158, + "step": 8596 + }, + { + "epoch": 1.1, + "learning_rate": 4.430651432281639e-06, + "loss": 0.1384, + "step": 8597 + }, + { + "epoch": 1.1, + "learning_rate": 4.429621698971228e-06, + "loss": 0.1566, + "step": 8598 + }, + { + "epoch": 1.1, + "learning_rate": 4.428591990171246e-06, + "loss": 0.1525, + "step": 8599 + }, + { + "epoch": 1.1, + "learning_rate": 4.4275623059259355e-06, + "loss": 0.1569, + "step": 8600 + }, + { + "epoch": 1.1, + "learning_rate": 4.426532646279548e-06, + "loss": 0.1544, + "step": 8601 + }, + { + "epoch": 1.1, + "learning_rate": 4.425503011276332e-06, + "loss": 0.1648, + "step": 8602 + }, + { + "epoch": 1.1, + "learning_rate": 4.42447340096053e-06, + "loss": 0.1419, + "step": 8603 + }, + { + "epoch": 1.1, + "learning_rate": 4.423443815376387e-06, + "loss": 0.1418, + "step": 8604 + }, + { + "epoch": 1.1, + "learning_rate": 4.422414254568147e-06, + "loss": 0.1438, + "step": 8605 + }, + { + "epoch": 1.1, + "learning_rate": 4.421384718580055e-06, + "loss": 0.1447, + "step": 8606 + }, + { + "epoch": 1.1, + "learning_rate": 4.420355207456349e-06, + "loss": 0.1361, + "step": 8607 + }, + { + "epoch": 1.1, + "learning_rate": 4.4193257212412695e-06, + "loss": 0.149, + "step": 8608 + }, + { + "epoch": 1.1, + "learning_rate": 4.41829625997906e-06, + "loss": 0.1439, + "step": 8609 + }, + { + "epoch": 1.1, + "learning_rate": 4.417266823713953e-06, + "loss": 0.1543, + "step": 8610 + }, + { + "epoch": 1.1, + "learning_rate": 4.416237412490189e-06, + "loss": 0.1524, + "step": 8611 + }, + { + "epoch": 1.1, + "learning_rate": 4.415208026352003e-06, + "loss": 0.1442, + "step": 8612 + }, + { + "epoch": 1.1, + "learning_rate": 4.414178665343633e-06, + "loss": 0.1567, + "step": 8613 + }, + { + "epoch": 1.1, + "learning_rate": 4.413149329509307e-06, + "loss": 0.1362, + "step": 8614 + }, + { + "epoch": 1.1, + "learning_rate": 4.412120018893263e-06, + "loss": 0.164, + "step": 8615 + }, + { + "epoch": 1.1, + "learning_rate": 4.411090733539731e-06, + "loss": 0.1431, + "step": 8616 + }, + { + "epoch": 1.1, + "learning_rate": 4.410061473492943e-06, + "loss": 0.1464, + "step": 8617 + }, + { + "epoch": 1.1, + "learning_rate": 4.409032238797125e-06, + "loss": 0.1464, + "step": 8618 + }, + { + "epoch": 1.1, + "learning_rate": 4.4080030294965085e-06, + "loss": 0.1337, + "step": 8619 + }, + { + "epoch": 1.1, + "learning_rate": 4.406973845635322e-06, + "loss": 0.1481, + "step": 8620 + }, + { + "epoch": 1.1, + "learning_rate": 4.405944687257789e-06, + "loss": 0.1547, + "step": 8621 + }, + { + "epoch": 1.1, + "learning_rate": 4.4049155544081355e-06, + "loss": 0.1485, + "step": 8622 + }, + { + "epoch": 1.1, + "learning_rate": 4.4038864471305845e-06, + "loss": 0.1354, + "step": 8623 + }, + { + "epoch": 1.1, + "learning_rate": 4.402857365469364e-06, + "loss": 0.1579, + "step": 8624 + }, + { + "epoch": 1.1, + "learning_rate": 4.40182830946869e-06, + "loss": 0.1557, + "step": 8625 + }, + { + "epoch": 1.1, + "learning_rate": 4.400799279172786e-06, + "loss": 0.1502, + "step": 8626 + }, + { + "epoch": 1.1, + "learning_rate": 4.399770274625871e-06, + "loss": 0.1604, + "step": 8627 + }, + { + "epoch": 1.1, + "learning_rate": 4.3987412958721664e-06, + "loss": 0.1531, + "step": 8628 + }, + { + "epoch": 1.1, + "learning_rate": 4.397712342955885e-06, + "loss": 0.1614, + "step": 8629 + }, + { + "epoch": 1.1, + "learning_rate": 4.396683415921247e-06, + "loss": 0.1322, + "step": 8630 + }, + { + "epoch": 1.1, + "learning_rate": 4.3956545148124665e-06, + "loss": 0.145, + "step": 8631 + }, + { + "epoch": 1.1, + "learning_rate": 4.394625639673756e-06, + "loss": 0.1501, + "step": 8632 + }, + { + "epoch": 1.11, + "learning_rate": 4.39359679054933e-06, + "loss": 0.1543, + "step": 8633 + }, + { + "epoch": 1.11, + "learning_rate": 4.392567967483401e-06, + "loss": 0.1568, + "step": 8634 + }, + { + "epoch": 1.11, + "learning_rate": 4.3915391705201805e-06, + "loss": 0.1596, + "step": 8635 + }, + { + "epoch": 1.11, + "learning_rate": 4.390510399703875e-06, + "loss": 0.1508, + "step": 8636 + }, + { + "epoch": 1.11, + "learning_rate": 4.389481655078695e-06, + "loss": 0.1409, + "step": 8637 + }, + { + "epoch": 1.11, + "learning_rate": 4.38845293668885e-06, + "loss": 0.1632, + "step": 8638 + }, + { + "epoch": 1.11, + "learning_rate": 4.387424244578543e-06, + "loss": 0.1538, + "step": 8639 + }, + { + "epoch": 1.11, + "learning_rate": 4.386395578791981e-06, + "loss": 0.1406, + "step": 8640 + }, + { + "epoch": 1.11, + "learning_rate": 4.385366939373365e-06, + "loss": 0.1705, + "step": 8641 + }, + { + "epoch": 1.11, + "learning_rate": 4.384338326366905e-06, + "loss": 0.1446, + "step": 8642 + }, + { + "epoch": 1.11, + "learning_rate": 4.383309739816795e-06, + "loss": 0.1431, + "step": 8643 + }, + { + "epoch": 1.11, + "learning_rate": 4.38228117976724e-06, + "loss": 0.1602, + "step": 8644 + }, + { + "epoch": 1.11, + "learning_rate": 4.381252646262437e-06, + "loss": 0.1333, + "step": 8645 + }, + { + "epoch": 1.11, + "learning_rate": 4.3802241393465885e-06, + "loss": 0.1289, + "step": 8646 + }, + { + "epoch": 1.11, + "learning_rate": 4.3791956590638866e-06, + "loss": 0.1591, + "step": 8647 + }, + { + "epoch": 1.11, + "learning_rate": 4.378167205458531e-06, + "loss": 0.1635, + "step": 8648 + }, + { + "epoch": 1.11, + "learning_rate": 4.377138778574716e-06, + "loss": 0.1222, + "step": 8649 + }, + { + "epoch": 1.11, + "learning_rate": 4.376110378456634e-06, + "loss": 0.1698, + "step": 8650 + }, + { + "epoch": 1.11, + "learning_rate": 4.375082005148479e-06, + "loss": 0.1408, + "step": 8651 + }, + { + "epoch": 1.11, + "learning_rate": 4.37405365869444e-06, + "loss": 0.1466, + "step": 8652 + }, + { + "epoch": 1.11, + "learning_rate": 4.373025339138713e-06, + "loss": 0.1687, + "step": 8653 + }, + { + "epoch": 1.11, + "learning_rate": 4.371997046525481e-06, + "loss": 0.1524, + "step": 8654 + }, + { + "epoch": 1.11, + "learning_rate": 4.370968780898935e-06, + "loss": 0.146, + "step": 8655 + }, + { + "epoch": 1.11, + "learning_rate": 4.3699405423032625e-06, + "loss": 0.1506, + "step": 8656 + }, + { + "epoch": 1.11, + "learning_rate": 4.368912330782647e-06, + "loss": 0.1441, + "step": 8657 + }, + { + "epoch": 1.11, + "learning_rate": 4.367884146381274e-06, + "loss": 0.1413, + "step": 8658 + }, + { + "epoch": 1.11, + "learning_rate": 4.366855989143326e-06, + "loss": 0.1602, + "step": 8659 + }, + { + "epoch": 1.11, + "learning_rate": 4.365827859112989e-06, + "loss": 0.1612, + "step": 8660 + }, + { + "epoch": 1.11, + "learning_rate": 4.364799756334439e-06, + "loss": 0.1452, + "step": 8661 + }, + { + "epoch": 1.11, + "learning_rate": 4.3637716808518596e-06, + "loss": 0.1567, + "step": 8662 + }, + { + "epoch": 1.11, + "learning_rate": 4.362743632709426e-06, + "loss": 0.151, + "step": 8663 + }, + { + "epoch": 1.11, + "learning_rate": 4.3617156119513206e-06, + "loss": 0.1484, + "step": 8664 + }, + { + "epoch": 1.11, + "learning_rate": 4.360687618621715e-06, + "loss": 0.1523, + "step": 8665 + }, + { + "epoch": 1.11, + "learning_rate": 4.359659652764786e-06, + "loss": 0.1423, + "step": 8666 + }, + { + "epoch": 1.11, + "learning_rate": 4.35863171442471e-06, + "loss": 0.1473, + "step": 8667 + }, + { + "epoch": 1.11, + "learning_rate": 4.357603803645657e-06, + "loss": 0.1612, + "step": 8668 + }, + { + "epoch": 1.11, + "learning_rate": 4.356575920471796e-06, + "loss": 0.1402, + "step": 8669 + }, + { + "epoch": 1.11, + "learning_rate": 4.355548064947303e-06, + "loss": 0.14, + "step": 8670 + }, + { + "epoch": 1.11, + "learning_rate": 4.354520237116347e-06, + "loss": 0.1571, + "step": 8671 + }, + { + "epoch": 1.11, + "learning_rate": 4.353492437023092e-06, + "loss": 0.143, + "step": 8672 + }, + { + "epoch": 1.11, + "learning_rate": 4.352464664711706e-06, + "loss": 0.141, + "step": 8673 + }, + { + "epoch": 1.11, + "learning_rate": 4.351436920226357e-06, + "loss": 0.157, + "step": 8674 + }, + { + "epoch": 1.11, + "learning_rate": 4.350409203611207e-06, + "loss": 0.1396, + "step": 8675 + }, + { + "epoch": 1.11, + "learning_rate": 4.34938151491042e-06, + "loss": 0.1581, + "step": 8676 + }, + { + "epoch": 1.11, + "learning_rate": 4.348353854168158e-06, + "loss": 0.1649, + "step": 8677 + }, + { + "epoch": 1.11, + "learning_rate": 4.347326221428585e-06, + "loss": 0.1593, + "step": 8678 + }, + { + "epoch": 1.11, + "learning_rate": 4.346298616735855e-06, + "loss": 0.1472, + "step": 8679 + }, + { + "epoch": 1.11, + "learning_rate": 4.345271040134129e-06, + "loss": 0.1432, + "step": 8680 + }, + { + "epoch": 1.11, + "learning_rate": 4.344243491667566e-06, + "loss": 0.1503, + "step": 8681 + }, + { + "epoch": 1.11, + "learning_rate": 4.343215971380323e-06, + "loss": 0.1489, + "step": 8682 + }, + { + "epoch": 1.11, + "learning_rate": 4.342188479316548e-06, + "loss": 0.1443, + "step": 8683 + }, + { + "epoch": 1.11, + "learning_rate": 4.3411610155204e-06, + "loss": 0.1379, + "step": 8684 + }, + { + "epoch": 1.11, + "learning_rate": 4.340133580036033e-06, + "loss": 0.1448, + "step": 8685 + }, + { + "epoch": 1.11, + "learning_rate": 4.339106172907594e-06, + "loss": 0.1494, + "step": 8686 + }, + { + "epoch": 1.11, + "learning_rate": 4.338078794179234e-06, + "loss": 0.1373, + "step": 8687 + }, + { + "epoch": 1.11, + "learning_rate": 4.337051443895102e-06, + "loss": 0.1486, + "step": 8688 + }, + { + "epoch": 1.11, + "learning_rate": 4.336024122099348e-06, + "loss": 0.143, + "step": 8689 + }, + { + "epoch": 1.11, + "learning_rate": 4.334996828836115e-06, + "loss": 0.1478, + "step": 8690 + }, + { + "epoch": 1.11, + "learning_rate": 4.333969564149549e-06, + "loss": 0.1556, + "step": 8691 + }, + { + "epoch": 1.11, + "learning_rate": 4.332942328083796e-06, + "loss": 0.1639, + "step": 8692 + }, + { + "epoch": 1.11, + "learning_rate": 4.3319151206829955e-06, + "loss": 0.1487, + "step": 8693 + }, + { + "epoch": 1.11, + "learning_rate": 4.330887941991288e-06, + "loss": 0.1598, + "step": 8694 + }, + { + "epoch": 1.11, + "learning_rate": 4.329860792052819e-06, + "loss": 0.1488, + "step": 8695 + }, + { + "epoch": 1.11, + "learning_rate": 4.3288336709117246e-06, + "loss": 0.1491, + "step": 8696 + }, + { + "epoch": 1.11, + "learning_rate": 4.32780657861214e-06, + "loss": 0.1561, + "step": 8697 + }, + { + "epoch": 1.11, + "learning_rate": 4.326779515198203e-06, + "loss": 0.1378, + "step": 8698 + }, + { + "epoch": 1.11, + "learning_rate": 4.325752480714052e-06, + "loss": 0.1439, + "step": 8699 + }, + { + "epoch": 1.11, + "learning_rate": 4.324725475203818e-06, + "loss": 0.1509, + "step": 8700 + }, + { + "epoch": 1.11, + "learning_rate": 4.323698498711634e-06, + "loss": 0.1471, + "step": 8701 + }, + { + "epoch": 1.11, + "learning_rate": 4.32267155128163e-06, + "loss": 0.1486, + "step": 8702 + }, + { + "epoch": 1.11, + "learning_rate": 4.321644632957941e-06, + "loss": 0.1392, + "step": 8703 + }, + { + "epoch": 1.11, + "learning_rate": 4.320617743784691e-06, + "loss": 0.1571, + "step": 8704 + }, + { + "epoch": 1.11, + "learning_rate": 4.31959088380601e-06, + "loss": 0.1319, + "step": 8705 + }, + { + "epoch": 1.11, + "learning_rate": 4.318564053066023e-06, + "loss": 0.1311, + "step": 8706 + }, + { + "epoch": 1.11, + "learning_rate": 4.317537251608859e-06, + "loss": 0.1558, + "step": 8707 + }, + { + "epoch": 1.11, + "learning_rate": 4.316510479478636e-06, + "loss": 0.1577, + "step": 8708 + }, + { + "epoch": 1.11, + "learning_rate": 4.315483736719482e-06, + "loss": 0.1633, + "step": 8709 + }, + { + "epoch": 1.11, + "learning_rate": 4.314457023375517e-06, + "loss": 0.1556, + "step": 8710 + }, + { + "epoch": 1.12, + "learning_rate": 4.313430339490859e-06, + "loss": 0.1669, + "step": 8711 + }, + { + "epoch": 1.12, + "learning_rate": 4.312403685109627e-06, + "loss": 0.1416, + "step": 8712 + }, + { + "epoch": 1.12, + "learning_rate": 4.311377060275942e-06, + "loss": 0.1706, + "step": 8713 + }, + { + "epoch": 1.12, + "learning_rate": 4.310350465033919e-06, + "loss": 0.1505, + "step": 8714 + }, + { + "epoch": 1.12, + "learning_rate": 4.309323899427671e-06, + "loss": 0.1504, + "step": 8715 + }, + { + "epoch": 1.12, + "learning_rate": 4.308297363501314e-06, + "loss": 0.1556, + "step": 8716 + }, + { + "epoch": 1.12, + "learning_rate": 4.3072708572989585e-06, + "loss": 0.1488, + "step": 8717 + }, + { + "epoch": 1.12, + "learning_rate": 4.306244380864719e-06, + "loss": 0.147, + "step": 8718 + }, + { + "epoch": 1.12, + "learning_rate": 4.305217934242703e-06, + "loss": 0.1541, + "step": 8719 + }, + { + "epoch": 1.12, + "learning_rate": 4.304191517477019e-06, + "loss": 0.1577, + "step": 8720 + }, + { + "epoch": 1.12, + "learning_rate": 4.303165130611776e-06, + "loss": 0.1475, + "step": 8721 + }, + { + "epoch": 1.12, + "learning_rate": 4.302138773691079e-06, + "loss": 0.1377, + "step": 8722 + }, + { + "epoch": 1.12, + "learning_rate": 4.301112446759033e-06, + "loss": 0.1656, + "step": 8723 + }, + { + "epoch": 1.12, + "learning_rate": 4.30008614985974e-06, + "loss": 0.149, + "step": 8724 + }, + { + "epoch": 1.12, + "learning_rate": 4.299059883037308e-06, + "loss": 0.15, + "step": 8725 + }, + { + "epoch": 1.12, + "learning_rate": 4.2980336463358296e-06, + "loss": 0.1475, + "step": 8726 + }, + { + "epoch": 1.12, + "learning_rate": 4.29700743979941e-06, + "loss": 0.152, + "step": 8727 + }, + { + "epoch": 1.12, + "learning_rate": 4.295981263472148e-06, + "loss": 0.1537, + "step": 8728 + }, + { + "epoch": 1.12, + "learning_rate": 4.294955117398139e-06, + "loss": 0.1411, + "step": 8729 + }, + { + "epoch": 1.12, + "learning_rate": 4.293929001621477e-06, + "loss": 0.174, + "step": 8730 + }, + { + "epoch": 1.12, + "learning_rate": 4.2929029161862575e-06, + "loss": 0.1383, + "step": 8731 + }, + { + "epoch": 1.12, + "learning_rate": 4.291876861136578e-06, + "loss": 0.148, + "step": 8732 + }, + { + "epoch": 1.12, + "learning_rate": 4.290850836516526e-06, + "loss": 0.1557, + "step": 8733 + }, + { + "epoch": 1.12, + "learning_rate": 4.28982484237019e-06, + "loss": 0.1423, + "step": 8734 + }, + { + "epoch": 1.12, + "learning_rate": 4.288798878741664e-06, + "loss": 0.1386, + "step": 8735 + }, + { + "epoch": 1.12, + "learning_rate": 4.287772945675035e-06, + "loss": 0.1563, + "step": 8736 + }, + { + "epoch": 1.12, + "learning_rate": 4.286747043214388e-06, + "loss": 0.1518, + "step": 8737 + }, + { + "epoch": 1.12, + "learning_rate": 4.285721171403809e-06, + "loss": 0.145, + "step": 8738 + }, + { + "epoch": 1.12, + "learning_rate": 4.284695330287383e-06, + "loss": 0.1643, + "step": 8739 + }, + { + "epoch": 1.12, + "learning_rate": 4.283669519909189e-06, + "loss": 0.1572, + "step": 8740 + }, + { + "epoch": 1.12, + "learning_rate": 4.282643740313312e-06, + "loss": 0.143, + "step": 8741 + }, + { + "epoch": 1.12, + "learning_rate": 4.281617991543832e-06, + "loss": 0.174, + "step": 8742 + }, + { + "epoch": 1.12, + "learning_rate": 4.280592273644829e-06, + "loss": 0.1563, + "step": 8743 + }, + { + "epoch": 1.12, + "learning_rate": 4.279566586660375e-06, + "loss": 0.1416, + "step": 8744 + }, + { + "epoch": 1.12, + "learning_rate": 4.278540930634549e-06, + "loss": 0.1329, + "step": 8745 + }, + { + "epoch": 1.12, + "learning_rate": 4.277515305611427e-06, + "loss": 0.1545, + "step": 8746 + }, + { + "epoch": 1.12, + "learning_rate": 4.276489711635083e-06, + "loss": 0.1554, + "step": 8747 + }, + { + "epoch": 1.12, + "learning_rate": 4.275464148749585e-06, + "loss": 0.1374, + "step": 8748 + }, + { + "epoch": 1.12, + "learning_rate": 4.274438616999007e-06, + "loss": 0.1525, + "step": 8749 + }, + { + "epoch": 1.12, + "learning_rate": 4.273413116427419e-06, + "loss": 0.1497, + "step": 8750 + }, + { + "epoch": 1.12, + "learning_rate": 4.272387647078885e-06, + "loss": 0.1468, + "step": 8751 + }, + { + "epoch": 1.12, + "learning_rate": 4.271362208997476e-06, + "loss": 0.1638, + "step": 8752 + }, + { + "epoch": 1.12, + "learning_rate": 4.270336802227255e-06, + "loss": 0.1469, + "step": 8753 + }, + { + "epoch": 1.12, + "learning_rate": 4.269311426812287e-06, + "loss": 0.1438, + "step": 8754 + }, + { + "epoch": 1.12, + "learning_rate": 4.268286082796634e-06, + "loss": 0.139, + "step": 8755 + }, + { + "epoch": 1.12, + "learning_rate": 4.267260770224358e-06, + "loss": 0.128, + "step": 8756 + }, + { + "epoch": 1.12, + "learning_rate": 4.26623548913952e-06, + "loss": 0.153, + "step": 8757 + }, + { + "epoch": 1.12, + "learning_rate": 4.2652102395861746e-06, + "loss": 0.1417, + "step": 8758 + }, + { + "epoch": 1.12, + "learning_rate": 4.264185021608382e-06, + "loss": 0.1524, + "step": 8759 + }, + { + "epoch": 1.12, + "learning_rate": 4.263159835250199e-06, + "loss": 0.1486, + "step": 8760 + }, + { + "epoch": 1.12, + "learning_rate": 4.26213468055568e-06, + "loss": 0.1526, + "step": 8761 + }, + { + "epoch": 1.12, + "learning_rate": 4.2611095575688745e-06, + "loss": 0.1447, + "step": 8762 + }, + { + "epoch": 1.12, + "learning_rate": 4.260084466333837e-06, + "loss": 0.1498, + "step": 8763 + }, + { + "epoch": 1.12, + "learning_rate": 4.259059406894619e-06, + "loss": 0.1603, + "step": 8764 + }, + { + "epoch": 1.12, + "learning_rate": 4.258034379295268e-06, + "loss": 0.1543, + "step": 8765 + }, + { + "epoch": 1.12, + "learning_rate": 4.257009383579833e-06, + "loss": 0.154, + "step": 8766 + }, + { + "epoch": 1.12, + "learning_rate": 4.255984419792358e-06, + "loss": 0.1468, + "step": 8767 + }, + { + "epoch": 1.12, + "learning_rate": 4.254959487976892e-06, + "loss": 0.1504, + "step": 8768 + }, + { + "epoch": 1.12, + "learning_rate": 4.253934588177473e-06, + "loss": 0.1632, + "step": 8769 + }, + { + "epoch": 1.12, + "learning_rate": 4.252909720438149e-06, + "loss": 0.146, + "step": 8770 + }, + { + "epoch": 1.12, + "learning_rate": 4.251884884802956e-06, + "loss": 0.162, + "step": 8771 + }, + { + "epoch": 1.12, + "learning_rate": 4.250860081315937e-06, + "loss": 0.142, + "step": 8772 + }, + { + "epoch": 1.12, + "learning_rate": 4.2498353100211275e-06, + "loss": 0.1418, + "step": 8773 + }, + { + "epoch": 1.12, + "learning_rate": 4.248810570962567e-06, + "loss": 0.1577, + "step": 8774 + }, + { + "epoch": 1.12, + "learning_rate": 4.247785864184289e-06, + "loss": 0.1282, + "step": 8775 + }, + { + "epoch": 1.12, + "learning_rate": 4.246761189730327e-06, + "loss": 0.1321, + "step": 8776 + }, + { + "epoch": 1.12, + "learning_rate": 4.245736547644714e-06, + "loss": 0.1441, + "step": 8777 + }, + { + "epoch": 1.12, + "learning_rate": 4.2447119379714805e-06, + "loss": 0.1478, + "step": 8778 + }, + { + "epoch": 1.12, + "learning_rate": 4.24368736075466e-06, + "loss": 0.1452, + "step": 8779 + }, + { + "epoch": 1.12, + "learning_rate": 4.242662816038276e-06, + "loss": 0.1251, + "step": 8780 + }, + { + "epoch": 1.12, + "learning_rate": 4.241638303866358e-06, + "loss": 0.1551, + "step": 8781 + }, + { + "epoch": 1.12, + "learning_rate": 4.24061382428293e-06, + "loss": 0.1526, + "step": 8782 + }, + { + "epoch": 1.12, + "learning_rate": 4.23958937733202e-06, + "loss": 0.1527, + "step": 8783 + }, + { + "epoch": 1.12, + "learning_rate": 4.238564963057646e-06, + "loss": 0.1582, + "step": 8784 + }, + { + "epoch": 1.12, + "learning_rate": 4.237540581503831e-06, + "loss": 0.161, + "step": 8785 + }, + { + "epoch": 1.12, + "learning_rate": 4.236516232714597e-06, + "loss": 0.1453, + "step": 8786 + }, + { + "epoch": 1.12, + "learning_rate": 4.235491916733959e-06, + "loss": 0.1449, + "step": 8787 + }, + { + "epoch": 1.12, + "learning_rate": 4.234467633605937e-06, + "loss": 0.1376, + "step": 8788 + }, + { + "epoch": 1.12, + "learning_rate": 4.233443383374545e-06, + "loss": 0.143, + "step": 8789 + }, + { + "epoch": 1.13, + "learning_rate": 4.232419166083799e-06, + "loss": 0.1309, + "step": 8790 + }, + { + "epoch": 1.13, + "learning_rate": 4.23139498177771e-06, + "loss": 0.1432, + "step": 8791 + }, + { + "epoch": 1.13, + "learning_rate": 4.23037083050029e-06, + "loss": 0.1633, + "step": 8792 + }, + { + "epoch": 1.13, + "learning_rate": 4.229346712295551e-06, + "loss": 0.1535, + "step": 8793 + }, + { + "epoch": 1.13, + "learning_rate": 4.228322627207499e-06, + "loss": 0.1492, + "step": 8794 + }, + { + "epoch": 1.13, + "learning_rate": 4.227298575280142e-06, + "loss": 0.1557, + "step": 8795 + }, + { + "epoch": 1.13, + "learning_rate": 4.226274556557487e-06, + "loss": 0.1533, + "step": 8796 + }, + { + "epoch": 1.13, + "learning_rate": 4.225250571083538e-06, + "loss": 0.1684, + "step": 8797 + }, + { + "epoch": 1.13, + "learning_rate": 4.2242266189022975e-06, + "loss": 0.1336, + "step": 8798 + }, + { + "epoch": 1.13, + "learning_rate": 4.223202700057765e-06, + "loss": 0.1443, + "step": 8799 + }, + { + "epoch": 1.13, + "learning_rate": 4.2221788145939425e-06, + "loss": 0.1535, + "step": 8800 + }, + { + "epoch": 1.13, + "learning_rate": 4.221154962554831e-06, + "loss": 0.1382, + "step": 8801 + }, + { + "epoch": 1.13, + "learning_rate": 4.220131143984424e-06, + "loss": 0.1593, + "step": 8802 + }, + { + "epoch": 1.13, + "learning_rate": 4.219107358926718e-06, + "loss": 0.1675, + "step": 8803 + }, + { + "epoch": 1.13, + "learning_rate": 4.21808360742571e-06, + "loss": 0.1509, + "step": 8804 + }, + { + "epoch": 1.13, + "learning_rate": 4.217059889525389e-06, + "loss": 0.1406, + "step": 8805 + }, + { + "epoch": 1.13, + "learning_rate": 4.216036205269748e-06, + "loss": 0.1575, + "step": 8806 + }, + { + "epoch": 1.13, + "learning_rate": 4.215012554702778e-06, + "loss": 0.1384, + "step": 8807 + }, + { + "epoch": 1.13, + "learning_rate": 4.213988937868469e-06, + "loss": 0.1586, + "step": 8808 + }, + { + "epoch": 1.13, + "learning_rate": 4.212965354810802e-06, + "loss": 0.1608, + "step": 8809 + }, + { + "epoch": 1.13, + "learning_rate": 4.211941805573767e-06, + "loss": 0.1534, + "step": 8810 + }, + { + "epoch": 1.13, + "learning_rate": 4.21091829020135e-06, + "loss": 0.1563, + "step": 8811 + }, + { + "epoch": 1.13, + "learning_rate": 4.209894808737531e-06, + "loss": 0.1559, + "step": 8812 + }, + { + "epoch": 1.13, + "learning_rate": 4.20887136122629e-06, + "loss": 0.1435, + "step": 8813 + }, + { + "epoch": 1.13, + "learning_rate": 4.207847947711609e-06, + "loss": 0.1633, + "step": 8814 + }, + { + "epoch": 1.13, + "learning_rate": 4.206824568237468e-06, + "loss": 0.1476, + "step": 8815 + }, + { + "epoch": 1.13, + "learning_rate": 4.205801222847839e-06, + "loss": 0.1616, + "step": 8816 + }, + { + "epoch": 1.13, + "learning_rate": 4.204777911586702e-06, + "loss": 0.1445, + "step": 8817 + }, + { + "epoch": 1.13, + "learning_rate": 4.203754634498027e-06, + "loss": 0.1481, + "step": 8818 + }, + { + "epoch": 1.13, + "learning_rate": 4.202731391625793e-06, + "loss": 0.1809, + "step": 8819 + }, + { + "epoch": 1.13, + "learning_rate": 4.201708183013963e-06, + "loss": 0.1332, + "step": 8820 + }, + { + "epoch": 1.13, + "learning_rate": 4.200685008706511e-06, + "loss": 0.128, + "step": 8821 + }, + { + "epoch": 1.13, + "learning_rate": 4.199661868747406e-06, + "loss": 0.1522, + "step": 8822 + }, + { + "epoch": 1.13, + "learning_rate": 4.198638763180611e-06, + "loss": 0.1552, + "step": 8823 + }, + { + "epoch": 1.13, + "learning_rate": 4.1976156920500935e-06, + "loss": 0.1509, + "step": 8824 + }, + { + "epoch": 1.13, + "learning_rate": 4.196592655399816e-06, + "loss": 0.138, + "step": 8825 + }, + { + "epoch": 1.13, + "learning_rate": 4.195569653273743e-06, + "loss": 0.149, + "step": 8826 + }, + { + "epoch": 1.13, + "learning_rate": 4.1945466857158336e-06, + "loss": 0.1534, + "step": 8827 + }, + { + "epoch": 1.13, + "learning_rate": 4.193523752770045e-06, + "loss": 0.1354, + "step": 8828 + }, + { + "epoch": 1.13, + "learning_rate": 4.19250085448034e-06, + "loss": 0.1354, + "step": 8829 + }, + { + "epoch": 1.13, + "learning_rate": 4.191477990890668e-06, + "loss": 0.1666, + "step": 8830 + }, + { + "epoch": 1.13, + "learning_rate": 4.19045516204499e-06, + "loss": 0.1474, + "step": 8831 + }, + { + "epoch": 1.13, + "learning_rate": 4.189432367987255e-06, + "loss": 0.1531, + "step": 8832 + }, + { + "epoch": 1.13, + "learning_rate": 4.188409608761419e-06, + "loss": 0.1374, + "step": 8833 + }, + { + "epoch": 1.13, + "learning_rate": 4.187386884411426e-06, + "loss": 0.1533, + "step": 8834 + }, + { + "epoch": 1.13, + "learning_rate": 4.186364194981231e-06, + "loss": 0.1532, + "step": 8835 + }, + { + "epoch": 1.13, + "learning_rate": 4.1853415405147765e-06, + "loss": 0.1387, + "step": 8836 + }, + { + "epoch": 1.13, + "learning_rate": 4.184318921056013e-06, + "loss": 0.162, + "step": 8837 + }, + { + "epoch": 1.13, + "learning_rate": 4.18329633664888e-06, + "loss": 0.1475, + "step": 8838 + }, + { + "epoch": 1.13, + "learning_rate": 4.182273787337323e-06, + "loss": 0.1623, + "step": 8839 + }, + { + "epoch": 1.13, + "learning_rate": 4.181251273165283e-06, + "loss": 0.1491, + "step": 8840 + }, + { + "epoch": 1.13, + "learning_rate": 4.1802287941767e-06, + "loss": 0.168, + "step": 8841 + }, + { + "epoch": 1.13, + "learning_rate": 4.179206350415509e-06, + "loss": 0.149, + "step": 8842 + }, + { + "epoch": 1.13, + "learning_rate": 4.17818394192565e-06, + "loss": 0.1287, + "step": 8843 + }, + { + "epoch": 1.13, + "learning_rate": 4.177161568751058e-06, + "loss": 0.1396, + "step": 8844 + }, + { + "epoch": 1.13, + "learning_rate": 4.176139230935666e-06, + "loss": 0.1613, + "step": 8845 + }, + { + "epoch": 1.13, + "learning_rate": 4.175116928523405e-06, + "loss": 0.1609, + "step": 8846 + }, + { + "epoch": 1.13, + "learning_rate": 4.174094661558209e-06, + "loss": 0.1456, + "step": 8847 + }, + { + "epoch": 1.13, + "learning_rate": 4.173072430084002e-06, + "loss": 0.1595, + "step": 8848 + }, + { + "epoch": 1.13, + "learning_rate": 4.172050234144716e-06, + "loss": 0.1522, + "step": 8849 + }, + { + "epoch": 1.13, + "learning_rate": 4.171028073784274e-06, + "loss": 0.1484, + "step": 8850 + }, + { + "epoch": 1.13, + "learning_rate": 4.170005949046604e-06, + "loss": 0.1547, + "step": 8851 + }, + { + "epoch": 1.13, + "learning_rate": 4.168983859975625e-06, + "loss": 0.1543, + "step": 8852 + }, + { + "epoch": 1.13, + "learning_rate": 4.16796180661526e-06, + "loss": 0.1416, + "step": 8853 + }, + { + "epoch": 1.13, + "learning_rate": 4.16693978900943e-06, + "loss": 0.1721, + "step": 8854 + }, + { + "epoch": 1.13, + "learning_rate": 4.165917807202055e-06, + "loss": 0.1532, + "step": 8855 + }, + { + "epoch": 1.13, + "learning_rate": 4.164895861237046e-06, + "loss": 0.1331, + "step": 8856 + }, + { + "epoch": 1.13, + "learning_rate": 4.1638739511583224e-06, + "loss": 0.1376, + "step": 8857 + }, + { + "epoch": 1.13, + "learning_rate": 4.1628520770097994e-06, + "loss": 0.1362, + "step": 8858 + }, + { + "epoch": 1.13, + "learning_rate": 4.161830238835386e-06, + "loss": 0.1439, + "step": 8859 + }, + { + "epoch": 1.13, + "learning_rate": 4.160808436678992e-06, + "loss": 0.1599, + "step": 8860 + }, + { + "epoch": 1.13, + "learning_rate": 4.1597866705845295e-06, + "loss": 0.1573, + "step": 8861 + }, + { + "epoch": 1.13, + "learning_rate": 4.1587649405959065e-06, + "loss": 0.1587, + "step": 8862 + }, + { + "epoch": 1.13, + "learning_rate": 4.157743246757026e-06, + "loss": 0.1447, + "step": 8863 + }, + { + "epoch": 1.13, + "learning_rate": 4.156721589111794e-06, + "loss": 0.1504, + "step": 8864 + }, + { + "epoch": 1.13, + "learning_rate": 4.155699967704113e-06, + "loss": 0.1489, + "step": 8865 + }, + { + "epoch": 1.13, + "learning_rate": 4.154678382577887e-06, + "loss": 0.1428, + "step": 8866 + }, + { + "epoch": 1.13, + "learning_rate": 4.1536568337770114e-06, + "loss": 0.1384, + "step": 8867 + }, + { + "epoch": 1.14, + "learning_rate": 4.152635321345387e-06, + "loss": 0.1494, + "step": 8868 + }, + { + "epoch": 1.14, + "learning_rate": 4.151613845326912e-06, + "loss": 0.1371, + "step": 8869 + }, + { + "epoch": 1.14, + "learning_rate": 4.150592405765476e-06, + "loss": 0.156, + "step": 8870 + }, + { + "epoch": 1.14, + "learning_rate": 4.1495710027049776e-06, + "loss": 0.1443, + "step": 8871 + }, + { + "epoch": 1.14, + "learning_rate": 4.148549636189308e-06, + "loss": 0.1523, + "step": 8872 + }, + { + "epoch": 1.14, + "learning_rate": 4.147528306262357e-06, + "loss": 0.1424, + "step": 8873 + }, + { + "epoch": 1.14, + "learning_rate": 4.146507012968013e-06, + "loss": 0.133, + "step": 8874 + }, + { + "epoch": 1.14, + "learning_rate": 4.145485756350162e-06, + "loss": 0.1413, + "step": 8875 + }, + { + "epoch": 1.14, + "learning_rate": 4.144464536452693e-06, + "loss": 0.1564, + "step": 8876 + }, + { + "epoch": 1.14, + "learning_rate": 4.1434433533194865e-06, + "loss": 0.1514, + "step": 8877 + }, + { + "epoch": 1.14, + "learning_rate": 4.142422206994428e-06, + "loss": 0.1568, + "step": 8878 + }, + { + "epoch": 1.14, + "learning_rate": 4.141401097521396e-06, + "loss": 0.1386, + "step": 8879 + }, + { + "epoch": 1.14, + "learning_rate": 4.140380024944273e-06, + "loss": 0.1481, + "step": 8880 + }, + { + "epoch": 1.14, + "learning_rate": 4.139358989306933e-06, + "loss": 0.1285, + "step": 8881 + }, + { + "epoch": 1.14, + "learning_rate": 4.138337990653255e-06, + "loss": 0.1617, + "step": 8882 + }, + { + "epoch": 1.14, + "learning_rate": 4.137317029027111e-06, + "loss": 0.1487, + "step": 8883 + }, + { + "epoch": 1.14, + "learning_rate": 4.136296104472378e-06, + "loss": 0.143, + "step": 8884 + }, + { + "epoch": 1.14, + "learning_rate": 4.1352752170329236e-06, + "loss": 0.1428, + "step": 8885 + }, + { + "epoch": 1.14, + "learning_rate": 4.1342543667526195e-06, + "loss": 0.1543, + "step": 8886 + }, + { + "epoch": 1.14, + "learning_rate": 4.133233553675334e-06, + "loss": 0.1665, + "step": 8887 + }, + { + "epoch": 1.14, + "learning_rate": 4.1322127778449315e-06, + "loss": 0.1422, + "step": 8888 + }, + { + "epoch": 1.14, + "learning_rate": 4.131192039305278e-06, + "loss": 0.1432, + "step": 8889 + }, + { + "epoch": 1.14, + "learning_rate": 4.1301713381002394e-06, + "loss": 0.1665, + "step": 8890 + }, + { + "epoch": 1.14, + "learning_rate": 4.129150674273675e-06, + "loss": 0.1388, + "step": 8891 + }, + { + "epoch": 1.14, + "learning_rate": 4.128130047869446e-06, + "loss": 0.1309, + "step": 8892 + }, + { + "epoch": 1.14, + "learning_rate": 4.12710945893141e-06, + "loss": 0.177, + "step": 8893 + }, + { + "epoch": 1.14, + "learning_rate": 4.1260889075034254e-06, + "loss": 0.1457, + "step": 8894 + }, + { + "epoch": 1.14, + "learning_rate": 4.125068393629346e-06, + "loss": 0.144, + "step": 8895 + }, + { + "epoch": 1.14, + "learning_rate": 4.124047917353026e-06, + "loss": 0.1537, + "step": 8896 + }, + { + "epoch": 1.14, + "learning_rate": 4.123027478718318e-06, + "loss": 0.1459, + "step": 8897 + }, + { + "epoch": 1.14, + "learning_rate": 4.1220070777690736e-06, + "loss": 0.1274, + "step": 8898 + }, + { + "epoch": 1.14, + "learning_rate": 4.120986714549139e-06, + "loss": 0.152, + "step": 8899 + }, + { + "epoch": 1.14, + "learning_rate": 4.119966389102363e-06, + "loss": 0.1518, + "step": 8900 + }, + { + "epoch": 1.14, + "learning_rate": 4.118946101472591e-06, + "loss": 0.1402, + "step": 8901 + }, + { + "epoch": 1.14, + "learning_rate": 4.117925851703669e-06, + "loss": 0.1647, + "step": 8902 + }, + { + "epoch": 1.14, + "learning_rate": 4.116905639839436e-06, + "loss": 0.1505, + "step": 8903 + }, + { + "epoch": 1.14, + "learning_rate": 4.115885465923734e-06, + "loss": 0.1437, + "step": 8904 + }, + { + "epoch": 1.14, + "learning_rate": 4.114865330000405e-06, + "loss": 0.1667, + "step": 8905 + }, + { + "epoch": 1.14, + "learning_rate": 4.113845232113282e-06, + "loss": 0.1631, + "step": 8906 + }, + { + "epoch": 1.14, + "learning_rate": 4.112825172306203e-06, + "loss": 0.1554, + "step": 8907 + }, + { + "epoch": 1.14, + "learning_rate": 4.111805150623002e-06, + "loss": 0.1501, + "step": 8908 + }, + { + "epoch": 1.14, + "learning_rate": 4.110785167107514e-06, + "loss": 0.1453, + "step": 8909 + }, + { + "epoch": 1.14, + "learning_rate": 4.1097652218035666e-06, + "loss": 0.1494, + "step": 8910 + }, + { + "epoch": 1.14, + "learning_rate": 4.108745314754989e-06, + "loss": 0.1656, + "step": 8911 + }, + { + "epoch": 1.14, + "learning_rate": 4.107725446005612e-06, + "loss": 0.1422, + "step": 8912 + }, + { + "epoch": 1.14, + "learning_rate": 4.106705615599258e-06, + "loss": 0.155, + "step": 8913 + }, + { + "epoch": 1.14, + "learning_rate": 4.1056858235797545e-06, + "loss": 0.1638, + "step": 8914 + }, + { + "epoch": 1.14, + "learning_rate": 4.104666069990921e-06, + "loss": 0.1415, + "step": 8915 + }, + { + "epoch": 1.14, + "learning_rate": 4.103646354876584e-06, + "loss": 0.1383, + "step": 8916 + }, + { + "epoch": 1.14, + "learning_rate": 4.102626678280556e-06, + "loss": 0.1462, + "step": 8917 + }, + { + "epoch": 1.14, + "learning_rate": 4.101607040246659e-06, + "loss": 0.1691, + "step": 8918 + }, + { + "epoch": 1.14, + "learning_rate": 4.100587440818709e-06, + "loss": 0.1473, + "step": 8919 + }, + { + "epoch": 1.14, + "learning_rate": 4.099567880040521e-06, + "loss": 0.1414, + "step": 8920 + }, + { + "epoch": 1.14, + "learning_rate": 4.098548357955904e-06, + "loss": 0.1295, + "step": 8921 + }, + { + "epoch": 1.14, + "learning_rate": 4.0975288746086724e-06, + "loss": 0.148, + "step": 8922 + }, + { + "epoch": 1.14, + "learning_rate": 4.0965094300426364e-06, + "loss": 0.1483, + "step": 8923 + }, + { + "epoch": 1.14, + "learning_rate": 4.0954900243016016e-06, + "loss": 0.1372, + "step": 8924 + }, + { + "epoch": 1.14, + "learning_rate": 4.094470657429374e-06, + "loss": 0.15, + "step": 8925 + }, + { + "epoch": 1.14, + "learning_rate": 4.093451329469758e-06, + "loss": 0.1397, + "step": 8926 + }, + { + "epoch": 1.14, + "learning_rate": 4.092432040466561e-06, + "loss": 0.1446, + "step": 8927 + }, + { + "epoch": 1.14, + "learning_rate": 4.091412790463578e-06, + "loss": 0.1421, + "step": 8928 + }, + { + "epoch": 1.14, + "learning_rate": 4.090393579504612e-06, + "loss": 0.1426, + "step": 8929 + }, + { + "epoch": 1.14, + "learning_rate": 4.0893744076334606e-06, + "loss": 0.1509, + "step": 8930 + }, + { + "epoch": 1.14, + "learning_rate": 4.088355274893916e-06, + "loss": 0.1603, + "step": 8931 + }, + { + "epoch": 1.14, + "learning_rate": 4.087336181329777e-06, + "loss": 0.1439, + "step": 8932 + }, + { + "epoch": 1.14, + "learning_rate": 4.086317126984835e-06, + "loss": 0.1627, + "step": 8933 + }, + { + "epoch": 1.14, + "learning_rate": 4.085298111902882e-06, + "loss": 0.1527, + "step": 8934 + }, + { + "epoch": 1.14, + "learning_rate": 4.084279136127704e-06, + "loss": 0.1771, + "step": 8935 + }, + { + "epoch": 1.14, + "learning_rate": 4.083260199703092e-06, + "loss": 0.147, + "step": 8936 + }, + { + "epoch": 1.14, + "learning_rate": 4.082241302672831e-06, + "loss": 0.1562, + "step": 8937 + }, + { + "epoch": 1.14, + "learning_rate": 4.081222445080707e-06, + "loss": 0.1677, + "step": 8938 + }, + { + "epoch": 1.14, + "learning_rate": 4.080203626970498e-06, + "loss": 0.1593, + "step": 8939 + }, + { + "epoch": 1.14, + "learning_rate": 4.079184848385988e-06, + "loss": 0.1541, + "step": 8940 + }, + { + "epoch": 1.14, + "learning_rate": 4.078166109370957e-06, + "loss": 0.1394, + "step": 8941 + }, + { + "epoch": 1.14, + "learning_rate": 4.077147409969181e-06, + "loss": 0.1484, + "step": 8942 + }, + { + "epoch": 1.14, + "learning_rate": 4.076128750224436e-06, + "loss": 0.1537, + "step": 8943 + }, + { + "epoch": 1.14, + "learning_rate": 4.0751101301804945e-06, + "loss": 0.1444, + "step": 8944 + }, + { + "epoch": 1.14, + "learning_rate": 4.074091549881134e-06, + "loss": 0.1403, + "step": 8945 + }, + { + "epoch": 1.15, + "learning_rate": 4.0730730093701185e-06, + "loss": 0.1516, + "step": 8946 + }, + { + "epoch": 1.15, + "learning_rate": 4.072054508691222e-06, + "loss": 0.1353, + "step": 8947 + }, + { + "epoch": 1.15, + "learning_rate": 4.07103604788821e-06, + "loss": 0.1553, + "step": 8948 + }, + { + "epoch": 1.15, + "learning_rate": 4.070017627004847e-06, + "loss": 0.1571, + "step": 8949 + }, + { + "epoch": 1.15, + "learning_rate": 4.068999246084898e-06, + "loss": 0.1725, + "step": 8950 + }, + { + "epoch": 1.15, + "learning_rate": 4.067980905172125e-06, + "loss": 0.1373, + "step": 8951 + }, + { + "epoch": 1.15, + "learning_rate": 4.066962604310288e-06, + "loss": 0.1548, + "step": 8952 + }, + { + "epoch": 1.15, + "learning_rate": 4.065944343543146e-06, + "loss": 0.1562, + "step": 8953 + }, + { + "epoch": 1.15, + "learning_rate": 4.0649261229144554e-06, + "loss": 0.1501, + "step": 8954 + }, + { + "epoch": 1.15, + "learning_rate": 4.063907942467971e-06, + "loss": 0.1465, + "step": 8955 + }, + { + "epoch": 1.15, + "learning_rate": 4.06288980224745e-06, + "loss": 0.1662, + "step": 8956 + }, + { + "epoch": 1.15, + "learning_rate": 4.0618717022966395e-06, + "loss": 0.1531, + "step": 8957 + }, + { + "epoch": 1.15, + "learning_rate": 4.060853642659291e-06, + "loss": 0.1547, + "step": 8958 + }, + { + "epoch": 1.15, + "learning_rate": 4.059835623379155e-06, + "loss": 0.156, + "step": 8959 + }, + { + "epoch": 1.15, + "learning_rate": 4.058817644499973e-06, + "loss": 0.1511, + "step": 8960 + }, + { + "epoch": 1.15, + "learning_rate": 4.057799706065495e-06, + "loss": 0.152, + "step": 8961 + }, + { + "epoch": 1.15, + "learning_rate": 4.056781808119461e-06, + "loss": 0.1551, + "step": 8962 + }, + { + "epoch": 1.15, + "learning_rate": 4.055763950705615e-06, + "loss": 0.1587, + "step": 8963 + }, + { + "epoch": 1.15, + "learning_rate": 4.054746133867693e-06, + "loss": 0.1608, + "step": 8964 + }, + { + "epoch": 1.15, + "learning_rate": 4.053728357649436e-06, + "loss": 0.1415, + "step": 8965 + }, + { + "epoch": 1.15, + "learning_rate": 4.052710622094579e-06, + "loss": 0.139, + "step": 8966 + }, + { + "epoch": 1.15, + "learning_rate": 4.051692927246857e-06, + "loss": 0.1532, + "step": 8967 + }, + { + "epoch": 1.15, + "learning_rate": 4.050675273149999e-06, + "loss": 0.1369, + "step": 8968 + }, + { + "epoch": 1.15, + "learning_rate": 4.0496576598477396e-06, + "loss": 0.1459, + "step": 8969 + }, + { + "epoch": 1.15, + "learning_rate": 4.048640087383809e-06, + "loss": 0.1547, + "step": 8970 + }, + { + "epoch": 1.15, + "learning_rate": 4.0476225558019324e-06, + "loss": 0.1363, + "step": 8971 + }, + { + "epoch": 1.15, + "learning_rate": 4.046605065145834e-06, + "loss": 0.1478, + "step": 8972 + }, + { + "epoch": 1.15, + "learning_rate": 4.04558761545924e-06, + "loss": 0.1689, + "step": 8973 + }, + { + "epoch": 1.15, + "learning_rate": 4.044570206785874e-06, + "loss": 0.1413, + "step": 8974 + }, + { + "epoch": 1.15, + "learning_rate": 4.043552839169451e-06, + "loss": 0.154, + "step": 8975 + }, + { + "epoch": 1.15, + "learning_rate": 4.042535512653693e-06, + "loss": 0.1344, + "step": 8976 + }, + { + "epoch": 1.15, + "learning_rate": 4.041518227282319e-06, + "loss": 0.1336, + "step": 8977 + }, + { + "epoch": 1.15, + "learning_rate": 4.040500983099038e-06, + "loss": 0.148, + "step": 8978 + }, + { + "epoch": 1.15, + "learning_rate": 4.039483780147568e-06, + "loss": 0.1421, + "step": 8979 + }, + { + "epoch": 1.15, + "learning_rate": 4.038466618471619e-06, + "loss": 0.1485, + "step": 8980 + }, + { + "epoch": 1.15, + "learning_rate": 4.037449498114903e-06, + "loss": 0.1323, + "step": 8981 + }, + { + "epoch": 1.15, + "learning_rate": 4.036432419121123e-06, + "loss": 0.1508, + "step": 8982 + }, + { + "epoch": 1.15, + "learning_rate": 4.035415381533988e-06, + "loss": 0.1468, + "step": 8983 + }, + { + "epoch": 1.15, + "learning_rate": 4.0343983853972045e-06, + "loss": 0.149, + "step": 8984 + }, + { + "epoch": 1.15, + "learning_rate": 4.0333814307544726e-06, + "loss": 0.1518, + "step": 8985 + }, + { + "epoch": 1.15, + "learning_rate": 4.032364517649491e-06, + "loss": 0.1335, + "step": 8986 + }, + { + "epoch": 1.15, + "learning_rate": 4.0313476461259615e-06, + "loss": 0.1553, + "step": 8987 + }, + { + "epoch": 1.15, + "learning_rate": 4.0303308162275835e-06, + "loss": 0.149, + "step": 8988 + }, + { + "epoch": 1.15, + "learning_rate": 4.029314027998049e-06, + "loss": 0.1615, + "step": 8989 + }, + { + "epoch": 1.15, + "learning_rate": 4.028297281481051e-06, + "loss": 0.1537, + "step": 8990 + }, + { + "epoch": 1.15, + "learning_rate": 4.027280576720282e-06, + "loss": 0.1598, + "step": 8991 + }, + { + "epoch": 1.15, + "learning_rate": 4.026263913759437e-06, + "loss": 0.1411, + "step": 8992 + }, + { + "epoch": 1.15, + "learning_rate": 4.025247292642197e-06, + "loss": 0.1429, + "step": 8993 + }, + { + "epoch": 1.15, + "learning_rate": 4.024230713412253e-06, + "loss": 0.1477, + "step": 8994 + }, + { + "epoch": 1.15, + "learning_rate": 4.0232141761132894e-06, + "loss": 0.1374, + "step": 8995 + }, + { + "epoch": 1.15, + "learning_rate": 4.022197680788986e-06, + "loss": 0.1403, + "step": 8996 + }, + { + "epoch": 1.15, + "learning_rate": 4.021181227483026e-06, + "loss": 0.1566, + "step": 8997 + }, + { + "epoch": 1.15, + "learning_rate": 4.02016481623909e-06, + "loss": 0.1616, + "step": 8998 + }, + { + "epoch": 1.15, + "learning_rate": 4.019148447100855e-06, + "loss": 0.142, + "step": 8999 + }, + { + "epoch": 1.15, + "learning_rate": 4.018132120111992e-06, + "loss": 0.1491, + "step": 9000 + }, + { + "epoch": 1.15, + "learning_rate": 4.0171158353161805e-06, + "loss": 0.1412, + "step": 9001 + }, + { + "epoch": 1.15, + "learning_rate": 4.016099592757091e-06, + "loss": 0.1489, + "step": 9002 + }, + { + "epoch": 1.15, + "learning_rate": 4.015083392478393e-06, + "loss": 0.1306, + "step": 9003 + }, + { + "epoch": 1.15, + "learning_rate": 4.014067234523756e-06, + "loss": 0.1484, + "step": 9004 + }, + { + "epoch": 1.15, + "learning_rate": 4.0130511189368435e-06, + "loss": 0.1461, + "step": 9005 + }, + { + "epoch": 1.15, + "learning_rate": 4.012035045761326e-06, + "loss": 0.1428, + "step": 9006 + }, + { + "epoch": 1.15, + "learning_rate": 4.0110190150408594e-06, + "loss": 0.1431, + "step": 9007 + }, + { + "epoch": 1.15, + "learning_rate": 4.01000302681911e-06, + "loss": 0.1386, + "step": 9008 + }, + { + "epoch": 1.15, + "learning_rate": 4.008987081139734e-06, + "loss": 0.1485, + "step": 9009 + }, + { + "epoch": 1.15, + "learning_rate": 4.007971178046393e-06, + "loss": 0.1502, + "step": 9010 + }, + { + "epoch": 1.15, + "learning_rate": 4.006955317582737e-06, + "loss": 0.1358, + "step": 9011 + }, + { + "epoch": 1.15, + "learning_rate": 4.005939499792424e-06, + "loss": 0.1429, + "step": 9012 + }, + { + "epoch": 1.15, + "learning_rate": 4.004923724719106e-06, + "loss": 0.1542, + "step": 9013 + }, + { + "epoch": 1.15, + "learning_rate": 4.0039079924064285e-06, + "loss": 0.149, + "step": 9014 + }, + { + "epoch": 1.15, + "learning_rate": 4.0028923028980435e-06, + "loss": 0.1508, + "step": 9015 + }, + { + "epoch": 1.15, + "learning_rate": 4.0018766562375984e-06, + "loss": 0.1443, + "step": 9016 + }, + { + "epoch": 1.15, + "learning_rate": 4.000861052468736e-06, + "loss": 0.1533, + "step": 9017 + }, + { + "epoch": 1.15, + "learning_rate": 3.9998454916350996e-06, + "loss": 0.124, + "step": 9018 + }, + { + "epoch": 1.15, + "learning_rate": 3.998829973780329e-06, + "loss": 0.1373, + "step": 9019 + }, + { + "epoch": 1.15, + "learning_rate": 3.997814498948064e-06, + "loss": 0.1424, + "step": 9020 + }, + { + "epoch": 1.15, + "learning_rate": 3.996799067181943e-06, + "loss": 0.1595, + "step": 9021 + }, + { + "epoch": 1.15, + "learning_rate": 3.995783678525601e-06, + "loss": 0.1489, + "step": 9022 + }, + { + "epoch": 1.15, + "learning_rate": 3.994768333022669e-06, + "loss": 0.1415, + "step": 9023 + }, + { + "epoch": 1.16, + "learning_rate": 3.993753030716783e-06, + "loss": 0.1495, + "step": 9024 + }, + { + "epoch": 1.16, + "learning_rate": 3.992737771651567e-06, + "loss": 0.1569, + "step": 9025 + }, + { + "epoch": 1.16, + "learning_rate": 3.991722555870655e-06, + "loss": 0.1372, + "step": 9026 + }, + { + "epoch": 1.16, + "learning_rate": 3.990707383417668e-06, + "loss": 0.137, + "step": 9027 + }, + { + "epoch": 1.16, + "learning_rate": 3.989692254336235e-06, + "loss": 0.1513, + "step": 9028 + }, + { + "epoch": 1.16, + "learning_rate": 3.988677168669974e-06, + "loss": 0.1474, + "step": 9029 + }, + { + "epoch": 1.16, + "learning_rate": 3.987662126462507e-06, + "loss": 0.1423, + "step": 9030 + }, + { + "epoch": 1.16, + "learning_rate": 3.9866471277574554e-06, + "loss": 0.1516, + "step": 9031 + }, + { + "epoch": 1.16, + "learning_rate": 3.985632172598433e-06, + "loss": 0.148, + "step": 9032 + }, + { + "epoch": 1.16, + "learning_rate": 3.984617261029054e-06, + "loss": 0.1499, + "step": 9033 + }, + { + "epoch": 1.16, + "learning_rate": 3.983602393092931e-06, + "loss": 0.1533, + "step": 9034 + }, + { + "epoch": 1.16, + "learning_rate": 3.982587568833681e-06, + "loss": 0.1391, + "step": 9035 + }, + { + "epoch": 1.16, + "learning_rate": 3.981572788294907e-06, + "loss": 0.1686, + "step": 9036 + }, + { + "epoch": 1.16, + "learning_rate": 3.980558051520218e-06, + "loss": 0.1518, + "step": 9037 + }, + { + "epoch": 1.16, + "learning_rate": 3.97954335855322e-06, + "loss": 0.1446, + "step": 9038 + }, + { + "epoch": 1.16, + "learning_rate": 3.978528709437518e-06, + "loss": 0.1364, + "step": 9039 + }, + { + "epoch": 1.16, + "learning_rate": 3.977514104216711e-06, + "loss": 0.1394, + "step": 9040 + }, + { + "epoch": 1.16, + "learning_rate": 3.9764995429344e-06, + "loss": 0.1402, + "step": 9041 + }, + { + "epoch": 1.16, + "learning_rate": 3.975485025634185e-06, + "loss": 0.1731, + "step": 9042 + }, + { + "epoch": 1.16, + "learning_rate": 3.9744705523596575e-06, + "loss": 0.1677, + "step": 9043 + }, + { + "epoch": 1.16, + "learning_rate": 3.973456123154415e-06, + "loss": 0.1499, + "step": 9044 + }, + { + "epoch": 1.16, + "learning_rate": 3.972441738062049e-06, + "loss": 0.1598, + "step": 9045 + }, + { + "epoch": 1.16, + "learning_rate": 3.971427397126153e-06, + "loss": 0.1382, + "step": 9046 + }, + { + "epoch": 1.16, + "learning_rate": 3.970413100390309e-06, + "loss": 0.157, + "step": 9047 + }, + { + "epoch": 1.16, + "learning_rate": 3.9693988478981076e-06, + "loss": 0.1518, + "step": 9048 + }, + { + "epoch": 1.16, + "learning_rate": 3.9683846396931345e-06, + "loss": 0.139, + "step": 9049 + }, + { + "epoch": 1.16, + "learning_rate": 3.967370475818971e-06, + "loss": 0.1315, + "step": 9050 + }, + { + "epoch": 1.16, + "learning_rate": 3.966356356319196e-06, + "loss": 0.1467, + "step": 9051 + }, + { + "epoch": 1.16, + "learning_rate": 3.965342281237391e-06, + "loss": 0.1529, + "step": 9052 + }, + { + "epoch": 1.16, + "learning_rate": 3.964328250617134e-06, + "loss": 0.1462, + "step": 9053 + }, + { + "epoch": 1.16, + "learning_rate": 3.9633142645019965e-06, + "loss": 0.1657, + "step": 9054 + }, + { + "epoch": 1.16, + "learning_rate": 3.962300322935556e-06, + "loss": 0.1523, + "step": 9055 + }, + { + "epoch": 1.16, + "learning_rate": 3.961286425961379e-06, + "loss": 0.157, + "step": 9056 + }, + { + "epoch": 1.16, + "learning_rate": 3.9602725736230405e-06, + "loss": 0.1582, + "step": 9057 + }, + { + "epoch": 1.16, + "learning_rate": 3.959258765964104e-06, + "loss": 0.1603, + "step": 9058 + }, + { + "epoch": 1.16, + "learning_rate": 3.958245003028136e-06, + "loss": 0.1585, + "step": 9059 + }, + { + "epoch": 1.16, + "learning_rate": 3.957231284858701e-06, + "loss": 0.1416, + "step": 9060 + }, + { + "epoch": 1.16, + "learning_rate": 3.956217611499359e-06, + "loss": 0.1659, + "step": 9061 + }, + { + "epoch": 1.16, + "learning_rate": 3.9552039829936705e-06, + "loss": 0.1459, + "step": 9062 + }, + { + "epoch": 1.16, + "learning_rate": 3.954190399385195e-06, + "loss": 0.1522, + "step": 9063 + }, + { + "epoch": 1.16, + "learning_rate": 3.953176860717488e-06, + "loss": 0.1598, + "step": 9064 + }, + { + "epoch": 1.16, + "learning_rate": 3.9521633670341005e-06, + "loss": 0.1481, + "step": 9065 + }, + { + "epoch": 1.16, + "learning_rate": 3.9511499183785875e-06, + "loss": 0.1528, + "step": 9066 + }, + { + "epoch": 1.16, + "learning_rate": 3.950136514794499e-06, + "loss": 0.1485, + "step": 9067 + }, + { + "epoch": 1.16, + "learning_rate": 3.9491231563253815e-06, + "loss": 0.1592, + "step": 9068 + }, + { + "epoch": 1.16, + "learning_rate": 3.948109843014784e-06, + "loss": 0.1377, + "step": 9069 + }, + { + "epoch": 1.16, + "learning_rate": 3.947096574906248e-06, + "loss": 0.1597, + "step": 9070 + }, + { + "epoch": 1.16, + "learning_rate": 3.946083352043318e-06, + "loss": 0.1432, + "step": 9071 + }, + { + "epoch": 1.16, + "learning_rate": 3.9450701744695325e-06, + "loss": 0.1368, + "step": 9072 + }, + { + "epoch": 1.16, + "learning_rate": 3.944057042228432e-06, + "loss": 0.1538, + "step": 9073 + }, + { + "epoch": 1.16, + "learning_rate": 3.9430439553635504e-06, + "loss": 0.1511, + "step": 9074 + }, + { + "epoch": 1.16, + "learning_rate": 3.942030913918427e-06, + "loss": 0.1558, + "step": 9075 + }, + { + "epoch": 1.16, + "learning_rate": 3.9410179179365895e-06, + "loss": 0.1522, + "step": 9076 + }, + { + "epoch": 1.16, + "learning_rate": 3.940004967461571e-06, + "loss": 0.1628, + "step": 9077 + }, + { + "epoch": 1.16, + "learning_rate": 3.9389920625368996e-06, + "loss": 0.1317, + "step": 9078 + }, + { + "epoch": 1.16, + "learning_rate": 3.937979203206103e-06, + "loss": 0.1504, + "step": 9079 + }, + { + "epoch": 1.16, + "learning_rate": 3.936966389512703e-06, + "loss": 0.144, + "step": 9080 + }, + { + "epoch": 1.16, + "learning_rate": 3.935953621500226e-06, + "loss": 0.139, + "step": 9081 + }, + { + "epoch": 1.16, + "learning_rate": 3.934940899212193e-06, + "loss": 0.1498, + "step": 9082 + }, + { + "epoch": 1.16, + "learning_rate": 3.9339282226921215e-06, + "loss": 0.1544, + "step": 9083 + }, + { + "epoch": 1.16, + "learning_rate": 3.932915591983526e-06, + "loss": 0.1425, + "step": 9084 + }, + { + "epoch": 1.16, + "learning_rate": 3.931903007129927e-06, + "loss": 0.1403, + "step": 9085 + }, + { + "epoch": 1.16, + "learning_rate": 3.930890468174833e-06, + "loss": 0.1441, + "step": 9086 + }, + { + "epoch": 1.16, + "learning_rate": 3.929877975161757e-06, + "loss": 0.1493, + "step": 9087 + }, + { + "epoch": 1.16, + "learning_rate": 3.928865528134206e-06, + "loss": 0.1581, + "step": 9088 + }, + { + "epoch": 1.16, + "learning_rate": 3.927853127135692e-06, + "loss": 0.1541, + "step": 9089 + }, + { + "epoch": 1.16, + "learning_rate": 3.926840772209714e-06, + "loss": 0.1416, + "step": 9090 + }, + { + "epoch": 1.16, + "learning_rate": 3.92582846339978e-06, + "loss": 0.157, + "step": 9091 + }, + { + "epoch": 1.16, + "learning_rate": 3.924816200749387e-06, + "loss": 0.146, + "step": 9092 + }, + { + "epoch": 1.16, + "learning_rate": 3.92380398430204e-06, + "loss": 0.1552, + "step": 9093 + }, + { + "epoch": 1.16, + "learning_rate": 3.92279181410123e-06, + "loss": 0.1477, + "step": 9094 + }, + { + "epoch": 1.16, + "learning_rate": 3.921779690190454e-06, + "loss": 0.1444, + "step": 9095 + }, + { + "epoch": 1.16, + "learning_rate": 3.920767612613209e-06, + "loss": 0.1383, + "step": 9096 + }, + { + "epoch": 1.16, + "learning_rate": 3.919755581412982e-06, + "loss": 0.1498, + "step": 9097 + }, + { + "epoch": 1.16, + "learning_rate": 3.918743596633262e-06, + "loss": 0.1418, + "step": 9098 + }, + { + "epoch": 1.16, + "learning_rate": 3.917731658317538e-06, + "loss": 0.1403, + "step": 9099 + }, + { + "epoch": 1.16, + "learning_rate": 3.916719766509297e-06, + "loss": 0.1646, + "step": 9100 + }, + { + "epoch": 1.16, + "learning_rate": 3.91570792125202e-06, + "loss": 0.1483, + "step": 9101 + }, + { + "epoch": 1.17, + "learning_rate": 3.914696122589187e-06, + "loss": 0.1464, + "step": 9102 + }, + { + "epoch": 1.17, + "learning_rate": 3.91368437056428e-06, + "loss": 0.139, + "step": 9103 + }, + { + "epoch": 1.17, + "learning_rate": 3.912672665220773e-06, + "loss": 0.1572, + "step": 9104 + }, + { + "epoch": 1.17, + "learning_rate": 3.911661006602144e-06, + "loss": 0.1288, + "step": 9105 + }, + { + "epoch": 1.17, + "learning_rate": 3.910649394751867e-06, + "loss": 0.1401, + "step": 9106 + }, + { + "epoch": 1.17, + "learning_rate": 3.9096378297134115e-06, + "loss": 0.156, + "step": 9107 + }, + { + "epoch": 1.17, + "learning_rate": 3.908626311530245e-06, + "loss": 0.1536, + "step": 9108 + }, + { + "epoch": 1.17, + "learning_rate": 3.907614840245836e-06, + "loss": 0.1584, + "step": 9109 + }, + { + "epoch": 1.17, + "learning_rate": 3.906603415903652e-06, + "loss": 0.1385, + "step": 9110 + }, + { + "epoch": 1.17, + "learning_rate": 3.905592038547155e-06, + "loss": 0.1539, + "step": 9111 + }, + { + "epoch": 1.17, + "learning_rate": 3.904580708219804e-06, + "loss": 0.1517, + "step": 9112 + }, + { + "epoch": 1.17, + "learning_rate": 3.903569424965059e-06, + "loss": 0.1361, + "step": 9113 + }, + { + "epoch": 1.17, + "learning_rate": 3.90255818882638e-06, + "loss": 0.1661, + "step": 9114 + }, + { + "epoch": 1.17, + "learning_rate": 3.901546999847217e-06, + "loss": 0.1498, + "step": 9115 + }, + { + "epoch": 1.17, + "learning_rate": 3.9005358580710275e-06, + "loss": 0.1538, + "step": 9116 + }, + { + "epoch": 1.17, + "learning_rate": 3.89952476354126e-06, + "loss": 0.1332, + "step": 9117 + }, + { + "epoch": 1.17, + "learning_rate": 3.898513716301366e-06, + "loss": 0.1411, + "step": 9118 + }, + { + "epoch": 1.17, + "learning_rate": 3.897502716394789e-06, + "loss": 0.1444, + "step": 9119 + }, + { + "epoch": 1.17, + "learning_rate": 3.896491763864976e-06, + "loss": 0.1702, + "step": 9120 + }, + { + "epoch": 1.17, + "learning_rate": 3.89548085875537e-06, + "loss": 0.1531, + "step": 9121 + }, + { + "epoch": 1.17, + "learning_rate": 3.894470001109412e-06, + "loss": 0.152, + "step": 9122 + }, + { + "epoch": 1.17, + "learning_rate": 3.8934591909705385e-06, + "loss": 0.1516, + "step": 9123 + }, + { + "epoch": 1.17, + "learning_rate": 3.892448428382189e-06, + "loss": 0.132, + "step": 9124 + }, + { + "epoch": 1.17, + "learning_rate": 3.8914377133877976e-06, + "loss": 0.146, + "step": 9125 + }, + { + "epoch": 1.17, + "learning_rate": 3.890427046030796e-06, + "loss": 0.1469, + "step": 9126 + }, + { + "epoch": 1.17, + "learning_rate": 3.889416426354614e-06, + "loss": 0.1457, + "step": 9127 + }, + { + "epoch": 1.17, + "learning_rate": 3.888405854402684e-06, + "loss": 0.148, + "step": 9128 + }, + { + "epoch": 1.17, + "learning_rate": 3.887395330218429e-06, + "loss": 0.1557, + "step": 9129 + }, + { + "epoch": 1.17, + "learning_rate": 3.886384853845274e-06, + "loss": 0.162, + "step": 9130 + }, + { + "epoch": 1.17, + "learning_rate": 3.885374425326642e-06, + "loss": 0.1487, + "step": 9131 + }, + { + "epoch": 1.17, + "learning_rate": 3.884364044705955e-06, + "loss": 0.1587, + "step": 9132 + }, + { + "epoch": 1.17, + "learning_rate": 3.883353712026629e-06, + "loss": 0.1421, + "step": 9133 + }, + { + "epoch": 1.17, + "learning_rate": 3.8823434273320794e-06, + "loss": 0.1429, + "step": 9134 + }, + { + "epoch": 1.17, + "learning_rate": 3.881333190665723e-06, + "loss": 0.1343, + "step": 9135 + }, + { + "epoch": 1.17, + "learning_rate": 3.880323002070971e-06, + "loss": 0.156, + "step": 9136 + }, + { + "epoch": 1.17, + "learning_rate": 3.879312861591233e-06, + "loss": 0.166, + "step": 9137 + }, + { + "epoch": 1.17, + "learning_rate": 3.878302769269917e-06, + "loss": 0.141, + "step": 9138 + }, + { + "epoch": 1.17, + "learning_rate": 3.877292725150429e-06, + "loss": 0.1431, + "step": 9139 + }, + { + "epoch": 1.17, + "learning_rate": 3.876282729276174e-06, + "loss": 0.1392, + "step": 9140 + }, + { + "epoch": 1.17, + "learning_rate": 3.875272781690552e-06, + "loss": 0.1469, + "step": 9141 + }, + { + "epoch": 1.17, + "learning_rate": 3.8742628824369624e-06, + "loss": 0.1563, + "step": 9142 + }, + { + "epoch": 1.17, + "learning_rate": 3.8732530315588065e-06, + "loss": 0.1488, + "step": 9143 + }, + { + "epoch": 1.17, + "learning_rate": 3.872243229099476e-06, + "loss": 0.161, + "step": 9144 + }, + { + "epoch": 1.17, + "learning_rate": 3.871233475102365e-06, + "loss": 0.1685, + "step": 9145 + }, + { + "epoch": 1.17, + "learning_rate": 3.870223769610865e-06, + "loss": 0.1612, + "step": 9146 + }, + { + "epoch": 1.17, + "learning_rate": 3.869214112668368e-06, + "loss": 0.1449, + "step": 9147 + }, + { + "epoch": 1.17, + "learning_rate": 3.868204504318258e-06, + "loss": 0.1417, + "step": 9148 + }, + { + "epoch": 1.17, + "learning_rate": 3.86719494460392e-06, + "loss": 0.1668, + "step": 9149 + }, + { + "epoch": 1.17, + "learning_rate": 3.866185433568741e-06, + "loss": 0.1522, + "step": 9150 + }, + { + "epoch": 1.17, + "learning_rate": 3.865175971256095e-06, + "loss": 0.1345, + "step": 9151 + }, + { + "epoch": 1.17, + "learning_rate": 3.864166557709368e-06, + "loss": 0.1387, + "step": 9152 + }, + { + "epoch": 1.17, + "learning_rate": 3.863157192971932e-06, + "loss": 0.1395, + "step": 9153 + }, + { + "epoch": 1.17, + "learning_rate": 3.8621478770871645e-06, + "loss": 0.1321, + "step": 9154 + }, + { + "epoch": 1.17, + "learning_rate": 3.861138610098435e-06, + "loss": 0.1631, + "step": 9155 + }, + { + "epoch": 1.17, + "learning_rate": 3.8601293920491165e-06, + "loss": 0.1441, + "step": 9156 + }, + { + "epoch": 1.17, + "learning_rate": 3.859120222982578e-06, + "loss": 0.1609, + "step": 9157 + }, + { + "epoch": 1.17, + "learning_rate": 3.858111102942184e-06, + "loss": 0.16, + "step": 9158 + }, + { + "epoch": 1.17, + "learning_rate": 3.857102031971298e-06, + "loss": 0.1443, + "step": 9159 + }, + { + "epoch": 1.17, + "learning_rate": 3.856093010113282e-06, + "loss": 0.1385, + "step": 9160 + }, + { + "epoch": 1.17, + "learning_rate": 3.855084037411501e-06, + "loss": 0.1528, + "step": 9161 + }, + { + "epoch": 1.17, + "learning_rate": 3.854075113909307e-06, + "loss": 0.1318, + "step": 9162 + }, + { + "epoch": 1.17, + "learning_rate": 3.853066239650055e-06, + "loss": 0.1362, + "step": 9163 + }, + { + "epoch": 1.17, + "learning_rate": 3.852057414677102e-06, + "loss": 0.1438, + "step": 9164 + }, + { + "epoch": 1.17, + "learning_rate": 3.851048639033801e-06, + "loss": 0.1425, + "step": 9165 + }, + { + "epoch": 1.17, + "learning_rate": 3.850039912763496e-06, + "loss": 0.145, + "step": 9166 + }, + { + "epoch": 1.17, + "learning_rate": 3.849031235909539e-06, + "loss": 0.1634, + "step": 9167 + }, + { + "epoch": 1.17, + "learning_rate": 3.848022608515273e-06, + "loss": 0.1586, + "step": 9168 + }, + { + "epoch": 1.17, + "learning_rate": 3.84701403062404e-06, + "loss": 0.1375, + "step": 9169 + }, + { + "epoch": 1.17, + "learning_rate": 3.846005502279182e-06, + "loss": 0.1532, + "step": 9170 + }, + { + "epoch": 1.17, + "learning_rate": 3.844997023524038e-06, + "loss": 0.1668, + "step": 9171 + }, + { + "epoch": 1.17, + "learning_rate": 3.843988594401946e-06, + "loss": 0.1523, + "step": 9172 + }, + { + "epoch": 1.17, + "learning_rate": 3.842980214956236e-06, + "loss": 0.1531, + "step": 9173 + }, + { + "epoch": 1.17, + "learning_rate": 3.841971885230243e-06, + "loss": 0.1365, + "step": 9174 + }, + { + "epoch": 1.17, + "learning_rate": 3.840963605267298e-06, + "loss": 0.1359, + "step": 9175 + }, + { + "epoch": 1.17, + "learning_rate": 3.83995537511073e-06, + "loss": 0.1556, + "step": 9176 + }, + { + "epoch": 1.17, + "learning_rate": 3.83894719480386e-06, + "loss": 0.1514, + "step": 9177 + }, + { + "epoch": 1.17, + "learning_rate": 3.837939064390016e-06, + "loss": 0.1506, + "step": 9178 + }, + { + "epoch": 1.17, + "learning_rate": 3.83693098391252e-06, + "loss": 0.136, + "step": 9179 + }, + { + "epoch": 1.18, + "learning_rate": 3.835922953414688e-06, + "loss": 0.1421, + "step": 9180 + }, + { + "epoch": 1.18, + "learning_rate": 3.83491497293984e-06, + "loss": 0.1388, + "step": 9181 + }, + { + "epoch": 1.18, + "learning_rate": 3.833907042531289e-06, + "loss": 0.1518, + "step": 9182 + }, + { + "epoch": 1.18, + "learning_rate": 3.832899162232352e-06, + "loss": 0.1431, + "step": 9183 + }, + { + "epoch": 1.18, + "learning_rate": 3.8318913320863355e-06, + "loss": 0.1422, + "step": 9184 + }, + { + "epoch": 1.18, + "learning_rate": 3.830883552136551e-06, + "loss": 0.1531, + "step": 9185 + }, + { + "epoch": 1.18, + "learning_rate": 3.829875822426304e-06, + "loss": 0.1431, + "step": 9186 + }, + { + "epoch": 1.18, + "learning_rate": 3.828868142998898e-06, + "loss": 0.147, + "step": 9187 + }, + { + "epoch": 1.18, + "learning_rate": 3.827860513897635e-06, + "loss": 0.1404, + "step": 9188 + }, + { + "epoch": 1.18, + "learning_rate": 3.826852935165818e-06, + "loss": 0.1653, + "step": 9189 + }, + { + "epoch": 1.18, + "learning_rate": 3.825845406846743e-06, + "loss": 0.1701, + "step": 9190 + }, + { + "epoch": 1.18, + "learning_rate": 3.8248379289837065e-06, + "loss": 0.1519, + "step": 9191 + }, + { + "epoch": 1.18, + "learning_rate": 3.8238305016199995e-06, + "loss": 0.1348, + "step": 9192 + }, + { + "epoch": 1.18, + "learning_rate": 3.822823124798915e-06, + "loss": 0.141, + "step": 9193 + }, + { + "epoch": 1.18, + "learning_rate": 3.8218157985637465e-06, + "loss": 0.1479, + "step": 9194 + }, + { + "epoch": 1.18, + "learning_rate": 3.820808522957774e-06, + "loss": 0.1459, + "step": 9195 + }, + { + "epoch": 1.18, + "learning_rate": 3.819801298024286e-06, + "loss": 0.1626, + "step": 9196 + }, + { + "epoch": 1.18, + "learning_rate": 3.818794123806565e-06, + "loss": 0.1612, + "step": 9197 + }, + { + "epoch": 1.18, + "learning_rate": 3.81778700034789e-06, + "loss": 0.1325, + "step": 9198 + }, + { + "epoch": 1.18, + "learning_rate": 3.816779927691542e-06, + "loss": 0.1478, + "step": 9199 + }, + { + "epoch": 1.18, + "learning_rate": 3.815772905880794e-06, + "loss": 0.1355, + "step": 9200 + }, + { + "epoch": 1.18, + "learning_rate": 3.814765934958924e-06, + "loss": 0.1611, + "step": 9201 + }, + { + "epoch": 1.18, + "learning_rate": 3.8137590149691992e-06, + "loss": 0.1472, + "step": 9202 + }, + { + "epoch": 1.18, + "learning_rate": 3.8127521459548934e-06, + "loss": 0.1559, + "step": 9203 + }, + { + "epoch": 1.18, + "learning_rate": 3.811745327959271e-06, + "loss": 0.1324, + "step": 9204 + }, + { + "epoch": 1.18, + "learning_rate": 3.810738561025599e-06, + "loss": 0.152, + "step": 9205 + }, + { + "epoch": 1.18, + "learning_rate": 3.8097318451971375e-06, + "loss": 0.1654, + "step": 9206 + }, + { + "epoch": 1.18, + "learning_rate": 3.80872518051715e-06, + "loss": 0.1559, + "step": 9207 + }, + { + "epoch": 1.18, + "learning_rate": 3.807718567028897e-06, + "loss": 0.1451, + "step": 9208 + }, + { + "epoch": 1.18, + "learning_rate": 3.8067120047756313e-06, + "loss": 0.1597, + "step": 9209 + }, + { + "epoch": 1.18, + "learning_rate": 3.8057054938006072e-06, + "loss": 0.1431, + "step": 9210 + }, + { + "epoch": 1.18, + "learning_rate": 3.804699034147078e-06, + "loss": 0.1598, + "step": 9211 + }, + { + "epoch": 1.18, + "learning_rate": 3.803692625858295e-06, + "loss": 0.1352, + "step": 9212 + }, + { + "epoch": 1.18, + "learning_rate": 3.8026862689775033e-06, + "loss": 0.154, + "step": 9213 + }, + { + "epoch": 1.18, + "learning_rate": 3.801679963547949e-06, + "loss": 0.1378, + "step": 9214 + }, + { + "epoch": 1.18, + "learning_rate": 3.8006737096128763e-06, + "loss": 0.1592, + "step": 9215 + }, + { + "epoch": 1.18, + "learning_rate": 3.7996675072155243e-06, + "loss": 0.1453, + "step": 9216 + }, + { + "epoch": 1.18, + "learning_rate": 3.7986613563991327e-06, + "loss": 0.146, + "step": 9217 + }, + { + "epoch": 1.18, + "learning_rate": 3.7976552572069385e-06, + "loss": 0.1275, + "step": 9218 + }, + { + "epoch": 1.18, + "learning_rate": 3.7966492096821773e-06, + "loss": 0.1557, + "step": 9219 + }, + { + "epoch": 1.18, + "learning_rate": 3.795643213868077e-06, + "loss": 0.1418, + "step": 9220 + }, + { + "epoch": 1.18, + "learning_rate": 3.7946372698078704e-06, + "loss": 0.1559, + "step": 9221 + }, + { + "epoch": 1.18, + "learning_rate": 3.793631377544787e-06, + "loss": 0.1515, + "step": 9222 + }, + { + "epoch": 1.18, + "learning_rate": 3.7926255371220487e-06, + "loss": 0.145, + "step": 9223 + }, + { + "epoch": 1.18, + "learning_rate": 3.7916197485828793e-06, + "loss": 0.146, + "step": 9224 + }, + { + "epoch": 1.18, + "learning_rate": 3.7906140119705006e-06, + "loss": 0.1443, + "step": 9225 + }, + { + "epoch": 1.18, + "learning_rate": 3.7896083273281324e-06, + "loss": 0.1516, + "step": 9226 + }, + { + "epoch": 1.18, + "learning_rate": 3.7886026946989896e-06, + "loss": 0.1506, + "step": 9227 + }, + { + "epoch": 1.18, + "learning_rate": 3.787597114126286e-06, + "loss": 0.1613, + "step": 9228 + }, + { + "epoch": 1.18, + "learning_rate": 3.786591585653235e-06, + "loss": 0.1355, + "step": 9229 + }, + { + "epoch": 1.18, + "learning_rate": 3.785586109323047e-06, + "loss": 0.143, + "step": 9230 + }, + { + "epoch": 1.18, + "learning_rate": 3.7845806851789275e-06, + "loss": 0.1441, + "step": 9231 + }, + { + "epoch": 1.18, + "learning_rate": 3.783575313264083e-06, + "loss": 0.1588, + "step": 9232 + }, + { + "epoch": 1.18, + "learning_rate": 3.7825699936217183e-06, + "loss": 0.1593, + "step": 9233 + }, + { + "epoch": 1.18, + "learning_rate": 3.7815647262950293e-06, + "loss": 0.1622, + "step": 9234 + }, + { + "epoch": 1.18, + "learning_rate": 3.7805595113272186e-06, + "loss": 0.1681, + "step": 9235 + }, + { + "epoch": 1.18, + "learning_rate": 3.7795543487614815e-06, + "loss": 0.1499, + "step": 9236 + }, + { + "epoch": 1.18, + "learning_rate": 3.7785492386410138e-06, + "loss": 0.1445, + "step": 9237 + }, + { + "epoch": 1.18, + "learning_rate": 3.7775441810090043e-06, + "loss": 0.1416, + "step": 9238 + }, + { + "epoch": 1.18, + "learning_rate": 3.7765391759086424e-06, + "loss": 0.1477, + "step": 9239 + }, + { + "epoch": 1.18, + "learning_rate": 3.7755342233831188e-06, + "loss": 0.132, + "step": 9240 + }, + { + "epoch": 1.18, + "learning_rate": 3.7745293234756164e-06, + "loss": 0.1529, + "step": 9241 + }, + { + "epoch": 1.18, + "learning_rate": 3.7735244762293183e-06, + "loss": 0.1531, + "step": 9242 + }, + { + "epoch": 1.18, + "learning_rate": 3.7725196816874045e-06, + "loss": 0.1583, + "step": 9243 + }, + { + "epoch": 1.18, + "learning_rate": 3.771514939893055e-06, + "loss": 0.136, + "step": 9244 + }, + { + "epoch": 1.18, + "learning_rate": 3.7705102508894425e-06, + "loss": 0.1386, + "step": 9245 + }, + { + "epoch": 1.18, + "learning_rate": 3.769505614719744e-06, + "loss": 0.1426, + "step": 9246 + }, + { + "epoch": 1.18, + "learning_rate": 3.7685010314271287e-06, + "loss": 0.148, + "step": 9247 + }, + { + "epoch": 1.18, + "learning_rate": 3.7674965010547686e-06, + "loss": 0.1423, + "step": 9248 + }, + { + "epoch": 1.18, + "learning_rate": 3.766492023645827e-06, + "loss": 0.1328, + "step": 9249 + }, + { + "epoch": 1.18, + "learning_rate": 3.7654875992434714e-06, + "loss": 0.1567, + "step": 9250 + }, + { + "epoch": 1.18, + "learning_rate": 3.764483227890864e-06, + "loss": 0.1724, + "step": 9251 + }, + { + "epoch": 1.18, + "learning_rate": 3.763478909631162e-06, + "loss": 0.1581, + "step": 9252 + }, + { + "epoch": 1.18, + "learning_rate": 3.7624746445075243e-06, + "loss": 0.1398, + "step": 9253 + }, + { + "epoch": 1.18, + "learning_rate": 3.761470432563109e-06, + "loss": 0.1597, + "step": 9254 + }, + { + "epoch": 1.18, + "learning_rate": 3.760466273841068e-06, + "loss": 0.1394, + "step": 9255 + }, + { + "epoch": 1.18, + "learning_rate": 3.759462168384551e-06, + "loss": 0.1648, + "step": 9256 + }, + { + "epoch": 1.18, + "learning_rate": 3.758458116236707e-06, + "loss": 0.1489, + "step": 9257 + }, + { + "epoch": 1.19, + "learning_rate": 3.757454117440682e-06, + "loss": 0.1401, + "step": 9258 + }, + { + "epoch": 1.19, + "learning_rate": 3.7564501720396242e-06, + "loss": 0.1285, + "step": 9259 + }, + { + "epoch": 1.19, + "learning_rate": 3.75544628007667e-06, + "loss": 0.1383, + "step": 9260 + }, + { + "epoch": 1.19, + "learning_rate": 3.75444244159496e-06, + "loss": 0.1351, + "step": 9261 + }, + { + "epoch": 1.19, + "learning_rate": 3.7534386566376345e-06, + "loss": 0.1494, + "step": 9262 + }, + { + "epoch": 1.19, + "learning_rate": 3.7524349252478243e-06, + "loss": 0.152, + "step": 9263 + }, + { + "epoch": 1.19, + "learning_rate": 3.7514312474686643e-06, + "loss": 0.1618, + "step": 9264 + }, + { + "epoch": 1.19, + "learning_rate": 3.7504276233432835e-06, + "loss": 0.1653, + "step": 9265 + }, + { + "epoch": 1.19, + "learning_rate": 3.749424052914813e-06, + "loss": 0.1334, + "step": 9266 + }, + { + "epoch": 1.19, + "learning_rate": 3.7484205362263737e-06, + "loss": 0.1401, + "step": 9267 + }, + { + "epoch": 1.19, + "learning_rate": 3.747417073321092e-06, + "loss": 0.1452, + "step": 9268 + }, + { + "epoch": 1.19, + "learning_rate": 3.74641366424209e-06, + "loss": 0.1466, + "step": 9269 + }, + { + "epoch": 1.19, + "learning_rate": 3.7454103090324835e-06, + "loss": 0.1484, + "step": 9270 + }, + { + "epoch": 1.19, + "learning_rate": 3.7444070077353896e-06, + "loss": 0.1289, + "step": 9271 + }, + { + "epoch": 1.19, + "learning_rate": 3.743403760393922e-06, + "loss": 0.1525, + "step": 9272 + }, + { + "epoch": 1.19, + "learning_rate": 3.7424005670511964e-06, + "loss": 0.1414, + "step": 9273 + }, + { + "epoch": 1.19, + "learning_rate": 3.7413974277503183e-06, + "loss": 0.152, + "step": 9274 + }, + { + "epoch": 1.19, + "learning_rate": 3.740394342534394e-06, + "loss": 0.1555, + "step": 9275 + }, + { + "epoch": 1.19, + "learning_rate": 3.739391311446531e-06, + "loss": 0.1475, + "step": 9276 + }, + { + "epoch": 1.19, + "learning_rate": 3.738388334529832e-06, + "loss": 0.148, + "step": 9277 + }, + { + "epoch": 1.19, + "learning_rate": 3.7373854118273955e-06, + "loss": 0.154, + "step": 9278 + }, + { + "epoch": 1.19, + "learning_rate": 3.7363825433823187e-06, + "loss": 0.1367, + "step": 9279 + }, + { + "epoch": 1.19, + "learning_rate": 3.7353797292377002e-06, + "loss": 0.1543, + "step": 9280 + }, + { + "epoch": 1.19, + "learning_rate": 3.7343769694366294e-06, + "loss": 0.1324, + "step": 9281 + }, + { + "epoch": 1.19, + "learning_rate": 3.7333742640221994e-06, + "loss": 0.1464, + "step": 9282 + }, + { + "epoch": 1.19, + "learning_rate": 3.732371613037498e-06, + "loss": 0.1344, + "step": 9283 + }, + { + "epoch": 1.19, + "learning_rate": 3.7313690165256134e-06, + "loss": 0.1447, + "step": 9284 + }, + { + "epoch": 1.19, + "learning_rate": 3.730366474529625e-06, + "loss": 0.1491, + "step": 9285 + }, + { + "epoch": 1.19, + "learning_rate": 3.7293639870926173e-06, + "loss": 0.1522, + "step": 9286 + }, + { + "epoch": 1.19, + "learning_rate": 3.728361554257671e-06, + "loss": 0.1347, + "step": 9287 + }, + { + "epoch": 1.19, + "learning_rate": 3.7273591760678594e-06, + "loss": 0.1424, + "step": 9288 + }, + { + "epoch": 1.19, + "learning_rate": 3.7263568525662574e-06, + "loss": 0.1391, + "step": 9289 + }, + { + "epoch": 1.19, + "learning_rate": 3.7253545837959383e-06, + "loss": 0.1407, + "step": 9290 + }, + { + "epoch": 1.19, + "learning_rate": 3.7243523697999733e-06, + "loss": 0.1695, + "step": 9291 + }, + { + "epoch": 1.19, + "learning_rate": 3.723350210621426e-06, + "loss": 0.1517, + "step": 9292 + }, + { + "epoch": 1.19, + "learning_rate": 3.722348106303364e-06, + "loss": 0.1428, + "step": 9293 + }, + { + "epoch": 1.19, + "learning_rate": 3.7213460568888493e-06, + "loss": 0.1397, + "step": 9294 + }, + { + "epoch": 1.19, + "learning_rate": 3.7203440624209438e-06, + "loss": 0.1469, + "step": 9295 + }, + { + "epoch": 1.19, + "learning_rate": 3.7193421229427017e-06, + "loss": 0.1585, + "step": 9296 + }, + { + "epoch": 1.19, + "learning_rate": 3.7183402384971818e-06, + "loss": 0.1604, + "step": 9297 + }, + { + "epoch": 1.19, + "learning_rate": 3.7173384091274372e-06, + "loss": 0.1414, + "step": 9298 + }, + { + "epoch": 1.19, + "learning_rate": 3.716336634876516e-06, + "loss": 0.1497, + "step": 9299 + }, + { + "epoch": 1.19, + "learning_rate": 3.7153349157874687e-06, + "loss": 0.143, + "step": 9300 + }, + { + "epoch": 1.19, + "learning_rate": 3.7143332519033413e-06, + "loss": 0.1468, + "step": 9301 + }, + { + "epoch": 1.19, + "learning_rate": 3.7133316432671794e-06, + "loss": 0.1451, + "step": 9302 + }, + { + "epoch": 1.19, + "learning_rate": 3.7123300899220193e-06, + "loss": 0.1397, + "step": 9303 + }, + { + "epoch": 1.19, + "learning_rate": 3.711328591910904e-06, + "loss": 0.1396, + "step": 9304 + }, + { + "epoch": 1.19, + "learning_rate": 3.710327149276871e-06, + "loss": 0.1644, + "step": 9305 + }, + { + "epoch": 1.19, + "learning_rate": 3.70932576206295e-06, + "loss": 0.1613, + "step": 9306 + }, + { + "epoch": 1.19, + "learning_rate": 3.708324430312177e-06, + "loss": 0.1354, + "step": 9307 + }, + { + "epoch": 1.19, + "learning_rate": 3.7073231540675792e-06, + "loss": 0.1411, + "step": 9308 + }, + { + "epoch": 1.19, + "learning_rate": 3.7063219333721857e-06, + "loss": 0.1605, + "step": 9309 + }, + { + "epoch": 1.19, + "learning_rate": 3.7053207682690184e-06, + "loss": 0.1358, + "step": 9310 + }, + { + "epoch": 1.19, + "learning_rate": 3.704319658801102e-06, + "loss": 0.1446, + "step": 9311 + }, + { + "epoch": 1.19, + "learning_rate": 3.7033186050114547e-06, + "loss": 0.1363, + "step": 9312 + }, + { + "epoch": 1.19, + "learning_rate": 3.7023176069430965e-06, + "loss": 0.1575, + "step": 9313 + }, + { + "epoch": 1.19, + "learning_rate": 3.7013166646390384e-06, + "loss": 0.1386, + "step": 9314 + }, + { + "epoch": 1.19, + "learning_rate": 3.700315778142297e-06, + "loss": 0.1475, + "step": 9315 + }, + { + "epoch": 1.19, + "learning_rate": 3.699314947495881e-06, + "loss": 0.1475, + "step": 9316 + }, + { + "epoch": 1.19, + "learning_rate": 3.698314172742799e-06, + "loss": 0.1354, + "step": 9317 + }, + { + "epoch": 1.19, + "learning_rate": 3.6973134539260545e-06, + "loss": 0.1312, + "step": 9318 + }, + { + "epoch": 1.19, + "learning_rate": 3.6963127910886526e-06, + "loss": 0.1517, + "step": 9319 + }, + { + "epoch": 1.19, + "learning_rate": 3.695312184273595e-06, + "loss": 0.1497, + "step": 9320 + }, + { + "epoch": 1.19, + "learning_rate": 3.694311633523878e-06, + "loss": 0.1653, + "step": 9321 + }, + { + "epoch": 1.19, + "learning_rate": 3.693311138882497e-06, + "loss": 0.1504, + "step": 9322 + }, + { + "epoch": 1.19, + "learning_rate": 3.6923107003924486e-06, + "loss": 0.1445, + "step": 9323 + }, + { + "epoch": 1.19, + "learning_rate": 3.691310318096719e-06, + "loss": 0.1474, + "step": 9324 + }, + { + "epoch": 1.19, + "learning_rate": 3.690309992038301e-06, + "loss": 0.1285, + "step": 9325 + }, + { + "epoch": 1.19, + "learning_rate": 3.689309722260179e-06, + "loss": 0.1385, + "step": 9326 + }, + { + "epoch": 1.19, + "learning_rate": 3.6883095088053387e-06, + "loss": 0.1335, + "step": 9327 + }, + { + "epoch": 1.19, + "learning_rate": 3.6873093517167584e-06, + "loss": 0.1588, + "step": 9328 + }, + { + "epoch": 1.19, + "learning_rate": 3.6863092510374198e-06, + "loss": 0.1361, + "step": 9329 + }, + { + "epoch": 1.19, + "learning_rate": 3.685309206810297e-06, + "loss": 0.1576, + "step": 9330 + }, + { + "epoch": 1.19, + "learning_rate": 3.684309219078368e-06, + "loss": 0.1333, + "step": 9331 + }, + { + "epoch": 1.19, + "learning_rate": 3.6833092878846e-06, + "loss": 0.1638, + "step": 9332 + }, + { + "epoch": 1.19, + "learning_rate": 3.6823094132719645e-06, + "loss": 0.1447, + "step": 9333 + }, + { + "epoch": 1.19, + "learning_rate": 3.68130959528343e-06, + "loss": 0.1241, + "step": 9334 + }, + { + "epoch": 1.19, + "learning_rate": 3.680309833961958e-06, + "loss": 0.1547, + "step": 9335 + }, + { + "epoch": 1.2, + "learning_rate": 3.6793101293505106e-06, + "loss": 0.1589, + "step": 9336 + }, + { + "epoch": 1.2, + "learning_rate": 3.678310481492048e-06, + "loss": 0.1473, + "step": 9337 + }, + { + "epoch": 1.2, + "learning_rate": 3.6773108904295294e-06, + "loss": 0.1469, + "step": 9338 + }, + { + "epoch": 1.2, + "learning_rate": 3.6763113562059077e-06, + "loss": 0.1504, + "step": 9339 + }, + { + "epoch": 1.2, + "learning_rate": 3.6753118788641327e-06, + "loss": 0.1464, + "step": 9340 + }, + { + "epoch": 1.2, + "learning_rate": 3.67431245844716e-06, + "loss": 0.1481, + "step": 9341 + }, + { + "epoch": 1.2, + "learning_rate": 3.67331309499793e-06, + "loss": 0.1525, + "step": 9342 + }, + { + "epoch": 1.2, + "learning_rate": 3.672313788559392e-06, + "loss": 0.1527, + "step": 9343 + }, + { + "epoch": 1.2, + "learning_rate": 3.6713145391744877e-06, + "loss": 0.1588, + "step": 9344 + }, + { + "epoch": 1.2, + "learning_rate": 3.6703153468861585e-06, + "loss": 0.1463, + "step": 9345 + }, + { + "epoch": 1.2, + "learning_rate": 3.6693162117373377e-06, + "loss": 0.1454, + "step": 9346 + }, + { + "epoch": 1.2, + "learning_rate": 3.668317133770963e-06, + "loss": 0.1412, + "step": 9347 + }, + { + "epoch": 1.2, + "learning_rate": 3.667318113029968e-06, + "loss": 0.1611, + "step": 9348 + }, + { + "epoch": 1.2, + "learning_rate": 3.6663191495572827e-06, + "loss": 0.1408, + "step": 9349 + }, + { + "epoch": 1.2, + "learning_rate": 3.6653202433958313e-06, + "loss": 0.16, + "step": 9350 + }, + { + "epoch": 1.2, + "learning_rate": 3.664321394588542e-06, + "loss": 0.1411, + "step": 9351 + }, + { + "epoch": 1.2, + "learning_rate": 3.663322603178339e-06, + "loss": 0.1425, + "step": 9352 + }, + { + "epoch": 1.2, + "learning_rate": 3.66232386920814e-06, + "loss": 0.1495, + "step": 9353 + }, + { + "epoch": 1.2, + "learning_rate": 3.661325192720862e-06, + "loss": 0.144, + "step": 9354 + }, + { + "epoch": 1.2, + "learning_rate": 3.660326573759422e-06, + "loss": 0.1247, + "step": 9355 + }, + { + "epoch": 1.2, + "learning_rate": 3.659328012366735e-06, + "loss": 0.1413, + "step": 9356 + }, + { + "epoch": 1.2, + "learning_rate": 3.658329508585707e-06, + "loss": 0.1436, + "step": 9357 + }, + { + "epoch": 1.2, + "learning_rate": 3.657331062459249e-06, + "loss": 0.1442, + "step": 9358 + }, + { + "epoch": 1.2, + "learning_rate": 3.6563326740302664e-06, + "loss": 0.1264, + "step": 9359 + }, + { + "epoch": 1.2, + "learning_rate": 3.6553343433416598e-06, + "loss": 0.14, + "step": 9360 + }, + { + "epoch": 1.2, + "learning_rate": 3.6543360704363305e-06, + "loss": 0.1402, + "step": 9361 + }, + { + "epoch": 1.2, + "learning_rate": 3.6533378553571786e-06, + "loss": 0.1524, + "step": 9362 + }, + { + "epoch": 1.2, + "learning_rate": 3.6523396981470995e-06, + "loss": 0.1454, + "step": 9363 + }, + { + "epoch": 1.2, + "learning_rate": 3.6513415988489824e-06, + "loss": 0.1376, + "step": 9364 + }, + { + "epoch": 1.2, + "learning_rate": 3.6503435575057205e-06, + "loss": 0.1495, + "step": 9365 + }, + { + "epoch": 1.2, + "learning_rate": 3.6493455741602035e-06, + "loss": 0.1466, + "step": 9366 + }, + { + "epoch": 1.2, + "learning_rate": 3.6483476488553143e-06, + "loss": 0.1523, + "step": 9367 + }, + { + "epoch": 1.2, + "learning_rate": 3.6473497816339375e-06, + "loss": 0.1556, + "step": 9368 + }, + { + "epoch": 1.2, + "learning_rate": 3.6463519725389516e-06, + "loss": 0.1518, + "step": 9369 + }, + { + "epoch": 1.2, + "learning_rate": 3.645354221613239e-06, + "loss": 0.146, + "step": 9370 + }, + { + "epoch": 1.2, + "learning_rate": 3.6443565288996698e-06, + "loss": 0.1464, + "step": 9371 + }, + { + "epoch": 1.2, + "learning_rate": 3.6433588944411207e-06, + "loss": 0.1405, + "step": 9372 + }, + { + "epoch": 1.2, + "learning_rate": 3.642361318280461e-06, + "loss": 0.1527, + "step": 9373 + }, + { + "epoch": 1.2, + "learning_rate": 3.64136380046056e-06, + "loss": 0.1484, + "step": 9374 + }, + { + "epoch": 1.2, + "learning_rate": 3.640366341024281e-06, + "loss": 0.1429, + "step": 9375 + }, + { + "epoch": 1.2, + "learning_rate": 3.639368940014489e-06, + "loss": 0.1534, + "step": 9376 + }, + { + "epoch": 1.2, + "learning_rate": 3.638371597474044e-06, + "loss": 0.1458, + "step": 9377 + }, + { + "epoch": 1.2, + "learning_rate": 3.637374313445805e-06, + "loss": 0.1533, + "step": 9378 + }, + { + "epoch": 1.2, + "learning_rate": 3.6363770879726247e-06, + "loss": 0.178, + "step": 9379 + }, + { + "epoch": 1.2, + "learning_rate": 3.635379921097359e-06, + "loss": 0.1317, + "step": 9380 + }, + { + "epoch": 1.2, + "learning_rate": 3.634382812862857e-06, + "loss": 0.1732, + "step": 9381 + }, + { + "epoch": 1.2, + "learning_rate": 3.6333857633119673e-06, + "loss": 0.1498, + "step": 9382 + }, + { + "epoch": 1.2, + "learning_rate": 3.632388772487534e-06, + "loss": 0.1485, + "step": 9383 + }, + { + "epoch": 1.2, + "learning_rate": 3.6313918404324e-06, + "loss": 0.1583, + "step": 9384 + }, + { + "epoch": 1.2, + "learning_rate": 3.63039496718941e-06, + "loss": 0.1225, + "step": 9385 + }, + { + "epoch": 1.2, + "learning_rate": 3.6293981528013965e-06, + "loss": 0.1663, + "step": 9386 + }, + { + "epoch": 1.2, + "learning_rate": 3.6284013973111962e-06, + "loss": 0.1535, + "step": 9387 + }, + { + "epoch": 1.2, + "learning_rate": 3.627404700761645e-06, + "loss": 0.143, + "step": 9388 + }, + { + "epoch": 1.2, + "learning_rate": 3.6264080631955683e-06, + "loss": 0.1325, + "step": 9389 + }, + { + "epoch": 1.2, + "learning_rate": 3.6254114846557977e-06, + "loss": 0.1471, + "step": 9390 + }, + { + "epoch": 1.2, + "learning_rate": 3.624414965185156e-06, + "loss": 0.1562, + "step": 9391 + }, + { + "epoch": 1.2, + "learning_rate": 3.623418504826468e-06, + "loss": 0.1523, + "step": 9392 + }, + { + "epoch": 1.2, + "learning_rate": 3.622422103622551e-06, + "loss": 0.1421, + "step": 9393 + }, + { + "epoch": 1.2, + "learning_rate": 3.621425761616224e-06, + "loss": 0.1412, + "step": 9394 + }, + { + "epoch": 1.2, + "learning_rate": 3.6204294788503034e-06, + "loss": 0.147, + "step": 9395 + }, + { + "epoch": 1.2, + "learning_rate": 3.6194332553676026e-06, + "loss": 0.1601, + "step": 9396 + }, + { + "epoch": 1.2, + "learning_rate": 3.618437091210927e-06, + "loss": 0.1552, + "step": 9397 + }, + { + "epoch": 1.2, + "learning_rate": 3.617440986423086e-06, + "loss": 0.1468, + "step": 9398 + }, + { + "epoch": 1.2, + "learning_rate": 3.616444941046887e-06, + "loss": 0.1476, + "step": 9399 + }, + { + "epoch": 1.2, + "learning_rate": 3.615448955125129e-06, + "loss": 0.1527, + "step": 9400 + }, + { + "epoch": 1.2, + "learning_rate": 3.614453028700613e-06, + "loss": 0.1469, + "step": 9401 + }, + { + "epoch": 1.2, + "learning_rate": 3.613457161816135e-06, + "loss": 0.1757, + "step": 9402 + }, + { + "epoch": 1.2, + "learning_rate": 3.6124613545144937e-06, + "loss": 0.1427, + "step": 9403 + }, + { + "epoch": 1.2, + "learning_rate": 3.6114656068384767e-06, + "loss": 0.1526, + "step": 9404 + }, + { + "epoch": 1.2, + "learning_rate": 3.610469918830874e-06, + "loss": 0.1481, + "step": 9405 + }, + { + "epoch": 1.2, + "learning_rate": 3.6094742905344753e-06, + "loss": 0.1411, + "step": 9406 + }, + { + "epoch": 1.2, + "learning_rate": 3.6084787219920616e-06, + "loss": 0.1542, + "step": 9407 + }, + { + "epoch": 1.2, + "learning_rate": 3.6074832132464165e-06, + "loss": 0.1309, + "step": 9408 + }, + { + "epoch": 1.2, + "learning_rate": 3.6064877643403194e-06, + "loss": 0.135, + "step": 9409 + }, + { + "epoch": 1.2, + "learning_rate": 3.605492375316548e-06, + "loss": 0.1412, + "step": 9410 + }, + { + "epoch": 1.2, + "learning_rate": 3.604497046217873e-06, + "loss": 0.1367, + "step": 9411 + }, + { + "epoch": 1.2, + "learning_rate": 3.6035017770870672e-06, + "loss": 0.1352, + "step": 9412 + }, + { + "epoch": 1.2, + "learning_rate": 3.6025065679669025e-06, + "loss": 0.1655, + "step": 9413 + }, + { + "epoch": 1.2, + "learning_rate": 3.601511418900143e-06, + "loss": 0.1284, + "step": 9414 + }, + { + "epoch": 1.21, + "learning_rate": 3.600516329929551e-06, + "loss": 0.1431, + "step": 9415 + }, + { + "epoch": 1.21, + "learning_rate": 3.599521301097888e-06, + "loss": 0.1422, + "step": 9416 + }, + { + "epoch": 1.21, + "learning_rate": 3.598526332447917e-06, + "loss": 0.1328, + "step": 9417 + }, + { + "epoch": 1.21, + "learning_rate": 3.597531424022388e-06, + "loss": 0.1602, + "step": 9418 + }, + { + "epoch": 1.21, + "learning_rate": 3.5965365758640587e-06, + "loss": 0.1605, + "step": 9419 + }, + { + "epoch": 1.21, + "learning_rate": 3.5955417880156766e-06, + "loss": 0.1507, + "step": 9420 + }, + { + "epoch": 1.21, + "learning_rate": 3.594547060519995e-06, + "loss": 0.1484, + "step": 9421 + }, + { + "epoch": 1.21, + "learning_rate": 3.5935523934197537e-06, + "loss": 0.1453, + "step": 9422 + }, + { + "epoch": 1.21, + "learning_rate": 3.592557786757699e-06, + "loss": 0.1377, + "step": 9423 + }, + { + "epoch": 1.21, + "learning_rate": 3.591563240576572e-06, + "loss": 0.164, + "step": 9424 + }, + { + "epoch": 1.21, + "learning_rate": 3.590568754919107e-06, + "loss": 0.1525, + "step": 9425 + }, + { + "epoch": 1.21, + "learning_rate": 3.5895743298280423e-06, + "loss": 0.1442, + "step": 9426 + }, + { + "epoch": 1.21, + "learning_rate": 3.5885799653461107e-06, + "loss": 0.1381, + "step": 9427 + }, + { + "epoch": 1.21, + "learning_rate": 3.587585661516042e-06, + "loss": 0.1391, + "step": 9428 + }, + { + "epoch": 1.21, + "learning_rate": 3.5865914183805606e-06, + "loss": 0.1479, + "step": 9429 + }, + { + "epoch": 1.21, + "learning_rate": 3.585597235982394e-06, + "loss": 0.1575, + "step": 9430 + }, + { + "epoch": 1.21, + "learning_rate": 3.584603114364266e-06, + "loss": 0.1506, + "step": 9431 + }, + { + "epoch": 1.21, + "learning_rate": 3.5836090535688944e-06, + "loss": 0.1395, + "step": 9432 + }, + { + "epoch": 1.21, + "learning_rate": 3.582615053638996e-06, + "loss": 0.1382, + "step": 9433 + }, + { + "epoch": 1.21, + "learning_rate": 3.581621114617284e-06, + "loss": 0.1349, + "step": 9434 + }, + { + "epoch": 1.21, + "learning_rate": 3.580627236546474e-06, + "loss": 0.1456, + "step": 9435 + }, + { + "epoch": 1.21, + "learning_rate": 3.5796334194692704e-06, + "loss": 0.1364, + "step": 9436 + }, + { + "epoch": 1.21, + "learning_rate": 3.578639663428384e-06, + "loss": 0.152, + "step": 9437 + }, + { + "epoch": 1.21, + "learning_rate": 3.5776459684665146e-06, + "loss": 0.1498, + "step": 9438 + }, + { + "epoch": 1.21, + "learning_rate": 3.5766523346263682e-06, + "loss": 0.148, + "step": 9439 + }, + { + "epoch": 1.21, + "learning_rate": 3.5756587619506388e-06, + "loss": 0.1434, + "step": 9440 + }, + { + "epoch": 1.21, + "learning_rate": 3.5746652504820263e-06, + "loss": 0.1527, + "step": 9441 + }, + { + "epoch": 1.21, + "learning_rate": 3.5736718002632222e-06, + "loss": 0.1493, + "step": 9442 + }, + { + "epoch": 1.21, + "learning_rate": 3.572678411336916e-06, + "loss": 0.1444, + "step": 9443 + }, + { + "epoch": 1.21, + "learning_rate": 3.571685083745798e-06, + "loss": 0.1495, + "step": 9444 + }, + { + "epoch": 1.21, + "learning_rate": 3.5706918175325523e-06, + "loss": 0.1471, + "step": 9445 + }, + { + "epoch": 1.21, + "learning_rate": 3.5696986127398646e-06, + "loss": 0.1489, + "step": 9446 + }, + { + "epoch": 1.21, + "learning_rate": 3.5687054694104117e-06, + "loss": 0.1396, + "step": 9447 + }, + { + "epoch": 1.21, + "learning_rate": 3.5677123875868713e-06, + "loss": 0.1647, + "step": 9448 + }, + { + "epoch": 1.21, + "learning_rate": 3.56671936731192e-06, + "loss": 0.1328, + "step": 9449 + }, + { + "epoch": 1.21, + "learning_rate": 3.5657264086282317e-06, + "loss": 0.1327, + "step": 9450 + }, + { + "epoch": 1.21, + "learning_rate": 3.564733511578472e-06, + "loss": 0.145, + "step": 9451 + }, + { + "epoch": 1.21, + "learning_rate": 3.5637406762053094e-06, + "loss": 0.1282, + "step": 9452 + }, + { + "epoch": 1.21, + "learning_rate": 3.562747902551411e-06, + "loss": 0.1421, + "step": 9453 + }, + { + "epoch": 1.21, + "learning_rate": 3.561755190659434e-06, + "loss": 0.1686, + "step": 9454 + }, + { + "epoch": 1.21, + "learning_rate": 3.5607625405720402e-06, + "loss": 0.1433, + "step": 9455 + }, + { + "epoch": 1.21, + "learning_rate": 3.559769952331884e-06, + "loss": 0.1616, + "step": 9456 + }, + { + "epoch": 1.21, + "learning_rate": 3.5587774259816234e-06, + "loss": 0.1585, + "step": 9457 + }, + { + "epoch": 1.21, + "learning_rate": 3.557784961563904e-06, + "loss": 0.1379, + "step": 9458 + }, + { + "epoch": 1.21, + "learning_rate": 3.556792559121377e-06, + "loss": 0.1438, + "step": 9459 + }, + { + "epoch": 1.21, + "learning_rate": 3.5558002186966906e-06, + "loss": 0.1422, + "step": 9460 + }, + { + "epoch": 1.21, + "learning_rate": 3.554807940332483e-06, + "loss": 0.1297, + "step": 9461 + }, + { + "epoch": 1.21, + "learning_rate": 3.5538157240713964e-06, + "loss": 0.1463, + "step": 9462 + }, + { + "epoch": 1.21, + "learning_rate": 3.5528235699560697e-06, + "loss": 0.1554, + "step": 9463 + }, + { + "epoch": 1.21, + "learning_rate": 3.5518314780291384e-06, + "loss": 0.1463, + "step": 9464 + }, + { + "epoch": 1.21, + "learning_rate": 3.5508394483332333e-06, + "loss": 0.1507, + "step": 9465 + }, + { + "epoch": 1.21, + "learning_rate": 3.549847480910983e-06, + "loss": 0.155, + "step": 9466 + }, + { + "epoch": 1.21, + "learning_rate": 3.548855575805016e-06, + "loss": 0.1319, + "step": 9467 + }, + { + "epoch": 1.21, + "learning_rate": 3.547863733057959e-06, + "loss": 0.1429, + "step": 9468 + }, + { + "epoch": 1.21, + "learning_rate": 3.5468719527124294e-06, + "loss": 0.1445, + "step": 9469 + }, + { + "epoch": 1.21, + "learning_rate": 3.5458802348110488e-06, + "loss": 0.1567, + "step": 9470 + }, + { + "epoch": 1.21, + "learning_rate": 3.544888579396435e-06, + "loss": 0.1397, + "step": 9471 + }, + { + "epoch": 1.21, + "learning_rate": 3.543896986511197e-06, + "loss": 0.1478, + "step": 9472 + }, + { + "epoch": 1.21, + "learning_rate": 3.5429054561979485e-06, + "loss": 0.1538, + "step": 9473 + }, + { + "epoch": 1.21, + "learning_rate": 3.541913988499299e-06, + "loss": 0.1489, + "step": 9474 + }, + { + "epoch": 1.21, + "learning_rate": 3.5409225834578536e-06, + "loss": 0.1475, + "step": 9475 + }, + { + "epoch": 1.21, + "learning_rate": 3.5399312411162124e-06, + "loss": 0.1434, + "step": 9476 + }, + { + "epoch": 1.21, + "learning_rate": 3.5389399615169774e-06, + "loss": 0.1461, + "step": 9477 + }, + { + "epoch": 1.21, + "learning_rate": 3.5379487447027483e-06, + "loss": 0.1436, + "step": 9478 + }, + { + "epoch": 1.21, + "learning_rate": 3.5369575907161167e-06, + "loss": 0.1488, + "step": 9479 + }, + { + "epoch": 1.21, + "learning_rate": 3.5359664995996746e-06, + "loss": 0.1405, + "step": 9480 + }, + { + "epoch": 1.21, + "learning_rate": 3.5349754713960126e-06, + "loss": 0.1336, + "step": 9481 + }, + { + "epoch": 1.21, + "learning_rate": 3.5339845061477195e-06, + "loss": 0.1421, + "step": 9482 + }, + { + "epoch": 1.21, + "learning_rate": 3.5329936038973756e-06, + "loss": 0.1281, + "step": 9483 + }, + { + "epoch": 1.21, + "learning_rate": 3.5320027646875643e-06, + "loss": 0.1504, + "step": 9484 + }, + { + "epoch": 1.21, + "learning_rate": 3.5310119885608625e-06, + "loss": 0.1382, + "step": 9485 + }, + { + "epoch": 1.21, + "learning_rate": 3.5300212755598497e-06, + "loss": 0.1519, + "step": 9486 + }, + { + "epoch": 1.21, + "learning_rate": 3.5290306257270935e-06, + "loss": 0.14, + "step": 9487 + }, + { + "epoch": 1.21, + "learning_rate": 3.5280400391051693e-06, + "loss": 0.143, + "step": 9488 + }, + { + "epoch": 1.21, + "learning_rate": 3.5270495157366434e-06, + "loss": 0.1484, + "step": 9489 + }, + { + "epoch": 1.21, + "learning_rate": 3.5260590556640783e-06, + "loss": 0.1443, + "step": 9490 + }, + { + "epoch": 1.21, + "learning_rate": 3.5250686589300387e-06, + "loss": 0.1431, + "step": 9491 + }, + { + "epoch": 1.21, + "learning_rate": 3.524078325577084e-06, + "loss": 0.152, + "step": 9492 + }, + { + "epoch": 1.22, + "learning_rate": 3.5230880556477707e-06, + "loss": 0.1415, + "step": 9493 + }, + { + "epoch": 1.22, + "learning_rate": 3.5220978491846534e-06, + "loss": 0.1419, + "step": 9494 + }, + { + "epoch": 1.22, + "learning_rate": 3.521107706230282e-06, + "loss": 0.1406, + "step": 9495 + }, + { + "epoch": 1.22, + "learning_rate": 3.5201176268272058e-06, + "loss": 0.1435, + "step": 9496 + }, + { + "epoch": 1.22, + "learning_rate": 3.519127611017973e-06, + "loss": 0.1342, + "step": 9497 + }, + { + "epoch": 1.22, + "learning_rate": 3.5181376588451244e-06, + "loss": 0.1452, + "step": 9498 + }, + { + "epoch": 1.22, + "learning_rate": 3.517147770351199e-06, + "loss": 0.1319, + "step": 9499 + }, + { + "epoch": 1.22, + "learning_rate": 3.5161579455787388e-06, + "loss": 0.1425, + "step": 9500 + }, + { + "epoch": 1.22, + "learning_rate": 3.5151681845702747e-06, + "loss": 0.1554, + "step": 9501 + }, + { + "epoch": 1.22, + "learning_rate": 3.5141784873683418e-06, + "loss": 0.1338, + "step": 9502 + }, + { + "epoch": 1.22, + "learning_rate": 3.513188854015466e-06, + "loss": 0.1421, + "step": 9503 + }, + { + "epoch": 1.22, + "learning_rate": 3.5121992845541797e-06, + "loss": 0.1515, + "step": 9504 + }, + { + "epoch": 1.22, + "learning_rate": 3.5112097790270017e-06, + "loss": 0.1417, + "step": 9505 + }, + { + "epoch": 1.22, + "learning_rate": 3.5102203374764555e-06, + "loss": 0.1294, + "step": 9506 + }, + { + "epoch": 1.22, + "learning_rate": 3.5092309599450596e-06, + "loss": 0.1563, + "step": 9507 + }, + { + "epoch": 1.22, + "learning_rate": 3.50824164647533e-06, + "loss": 0.1576, + "step": 9508 + }, + { + "epoch": 1.22, + "learning_rate": 3.507252397109777e-06, + "loss": 0.1369, + "step": 9509 + }, + { + "epoch": 1.22, + "learning_rate": 3.506263211890914e-06, + "loss": 0.1437, + "step": 9510 + }, + { + "epoch": 1.22, + "learning_rate": 3.505274090861249e-06, + "loss": 0.1281, + "step": 9511 + }, + { + "epoch": 1.22, + "learning_rate": 3.504285034063285e-06, + "loss": 0.1351, + "step": 9512 + }, + { + "epoch": 1.22, + "learning_rate": 3.503296041539522e-06, + "loss": 0.1648, + "step": 9513 + }, + { + "epoch": 1.22, + "learning_rate": 3.5023071133324627e-06, + "loss": 0.1481, + "step": 9514 + }, + { + "epoch": 1.22, + "learning_rate": 3.501318249484604e-06, + "loss": 0.1403, + "step": 9515 + }, + { + "epoch": 1.22, + "learning_rate": 3.5003294500384367e-06, + "loss": 0.1516, + "step": 9516 + }, + { + "epoch": 1.22, + "learning_rate": 3.4993407150364513e-06, + "loss": 0.1599, + "step": 9517 + }, + { + "epoch": 1.22, + "learning_rate": 3.4983520445211403e-06, + "loss": 0.1625, + "step": 9518 + }, + { + "epoch": 1.22, + "learning_rate": 3.497363438534984e-06, + "loss": 0.1477, + "step": 9519 + }, + { + "epoch": 1.22, + "learning_rate": 3.496374897120467e-06, + "loss": 0.1454, + "step": 9520 + }, + { + "epoch": 1.22, + "learning_rate": 3.495386420320071e-06, + "loss": 0.1404, + "step": 9521 + }, + { + "epoch": 1.22, + "learning_rate": 3.4943980081762717e-06, + "loss": 0.1508, + "step": 9522 + }, + { + "epoch": 1.22, + "learning_rate": 3.493409660731542e-06, + "loss": 0.1381, + "step": 9523 + }, + { + "epoch": 1.22, + "learning_rate": 3.4924213780283545e-06, + "loss": 0.1444, + "step": 9524 + }, + { + "epoch": 1.22, + "learning_rate": 3.4914331601091793e-06, + "loss": 0.1414, + "step": 9525 + }, + { + "epoch": 1.22, + "learning_rate": 3.4904450070164803e-06, + "loss": 0.1247, + "step": 9526 + }, + { + "epoch": 1.22, + "learning_rate": 3.4894569187927204e-06, + "loss": 0.1528, + "step": 9527 + }, + { + "epoch": 1.22, + "learning_rate": 3.48846889548036e-06, + "loss": 0.1567, + "step": 9528 + }, + { + "epoch": 1.22, + "learning_rate": 3.4874809371218608e-06, + "loss": 0.1525, + "step": 9529 + }, + { + "epoch": 1.22, + "learning_rate": 3.486493043759673e-06, + "loss": 0.152, + "step": 9530 + }, + { + "epoch": 1.22, + "learning_rate": 3.4855052154362485e-06, + "loss": 0.148, + "step": 9531 + }, + { + "epoch": 1.22, + "learning_rate": 3.4845174521940384e-06, + "loss": 0.1459, + "step": 9532 + }, + { + "epoch": 1.22, + "learning_rate": 3.4835297540754896e-06, + "loss": 0.1427, + "step": 9533 + }, + { + "epoch": 1.22, + "learning_rate": 3.4825421211230437e-06, + "loss": 0.1438, + "step": 9534 + }, + { + "epoch": 1.22, + "learning_rate": 3.481554553379143e-06, + "loss": 0.1571, + "step": 9535 + }, + { + "epoch": 1.22, + "learning_rate": 3.4805670508862255e-06, + "loss": 0.1428, + "step": 9536 + }, + { + "epoch": 1.22, + "learning_rate": 3.4795796136867237e-06, + "loss": 0.1384, + "step": 9537 + }, + { + "epoch": 1.22, + "learning_rate": 3.4785922418230722e-06, + "loss": 0.1531, + "step": 9538 + }, + { + "epoch": 1.22, + "learning_rate": 3.4776049353377016e-06, + "loss": 0.1354, + "step": 9539 + }, + { + "epoch": 1.22, + "learning_rate": 3.476617694273039e-06, + "loss": 0.1401, + "step": 9540 + }, + { + "epoch": 1.22, + "learning_rate": 3.4756305186715046e-06, + "loss": 0.1482, + "step": 9541 + }, + { + "epoch": 1.22, + "learning_rate": 3.474643408575521e-06, + "loss": 0.1425, + "step": 9542 + }, + { + "epoch": 1.22, + "learning_rate": 3.47365636402751e-06, + "loss": 0.1468, + "step": 9543 + }, + { + "epoch": 1.22, + "learning_rate": 3.4726693850698824e-06, + "loss": 0.1536, + "step": 9544 + }, + { + "epoch": 1.22, + "learning_rate": 3.4716824717450538e-06, + "loss": 0.1327, + "step": 9545 + }, + { + "epoch": 1.22, + "learning_rate": 3.4706956240954317e-06, + "loss": 0.1427, + "step": 9546 + }, + { + "epoch": 1.22, + "learning_rate": 3.4697088421634266e-06, + "loss": 0.1555, + "step": 9547 + }, + { + "epoch": 1.22, + "learning_rate": 3.4687221259914394e-06, + "loss": 0.1488, + "step": 9548 + }, + { + "epoch": 1.22, + "learning_rate": 3.467735475621873e-06, + "loss": 0.1479, + "step": 9549 + }, + { + "epoch": 1.22, + "learning_rate": 3.4667488910971252e-06, + "loss": 0.1339, + "step": 9550 + }, + { + "epoch": 1.22, + "learning_rate": 3.4657623724595944e-06, + "loss": 0.1268, + "step": 9551 + }, + { + "epoch": 1.22, + "learning_rate": 3.4647759197516687e-06, + "loss": 0.1636, + "step": 9552 + }, + { + "epoch": 1.22, + "learning_rate": 3.4637895330157423e-06, + "loss": 0.1535, + "step": 9553 + }, + { + "epoch": 1.22, + "learning_rate": 3.4628032122942024e-06, + "loss": 0.1422, + "step": 9554 + }, + { + "epoch": 1.22, + "learning_rate": 3.461816957629429e-06, + "loss": 0.1462, + "step": 9555 + }, + { + "epoch": 1.22, + "learning_rate": 3.4608307690638075e-06, + "loss": 0.1386, + "step": 9556 + }, + { + "epoch": 1.22, + "learning_rate": 3.459844646639717e-06, + "loss": 0.1591, + "step": 9557 + }, + { + "epoch": 1.22, + "learning_rate": 3.4588585903995314e-06, + "loss": 0.138, + "step": 9558 + }, + { + "epoch": 1.22, + "learning_rate": 3.4578726003856245e-06, + "loss": 0.1454, + "step": 9559 + }, + { + "epoch": 1.22, + "learning_rate": 3.4568866766403665e-06, + "loss": 0.1383, + "step": 9560 + }, + { + "epoch": 1.22, + "learning_rate": 3.4559008192061254e-06, + "loss": 0.1402, + "step": 9561 + }, + { + "epoch": 1.22, + "learning_rate": 3.4549150281252635e-06, + "loss": 0.1522, + "step": 9562 + }, + { + "epoch": 1.22, + "learning_rate": 3.453929303440145e-06, + "loss": 0.1519, + "step": 9563 + }, + { + "epoch": 1.22, + "learning_rate": 3.4529436451931263e-06, + "loss": 0.1361, + "step": 9564 + }, + { + "epoch": 1.22, + "learning_rate": 3.4519580534265674e-06, + "loss": 0.1433, + "step": 9565 + }, + { + "epoch": 1.22, + "learning_rate": 3.4509725281828155e-06, + "loss": 0.1449, + "step": 9566 + }, + { + "epoch": 1.22, + "learning_rate": 3.449987069504226e-06, + "loss": 0.153, + "step": 9567 + }, + { + "epoch": 1.22, + "learning_rate": 3.4490016774331426e-06, + "loss": 0.1461, + "step": 9568 + }, + { + "epoch": 1.22, + "learning_rate": 3.448016352011914e-06, + "loss": 0.1365, + "step": 9569 + }, + { + "epoch": 1.22, + "learning_rate": 3.4470310932828766e-06, + "loss": 0.1629, + "step": 9570 + }, + { + "epoch": 1.23, + "learning_rate": 3.4460459012883716e-06, + "loss": 0.1442, + "step": 9571 + }, + { + "epoch": 1.23, + "learning_rate": 3.4450607760707373e-06, + "loss": 0.1622, + "step": 9572 + }, + { + "epoch": 1.23, + "learning_rate": 3.4440757176723037e-06, + "loss": 0.1529, + "step": 9573 + }, + { + "epoch": 1.23, + "learning_rate": 3.4430907261354e-06, + "loss": 0.1412, + "step": 9574 + }, + { + "epoch": 1.23, + "learning_rate": 3.442105801502356e-06, + "loss": 0.1603, + "step": 9575 + }, + { + "epoch": 1.23, + "learning_rate": 3.441120943815497e-06, + "loss": 0.1822, + "step": 9576 + }, + { + "epoch": 1.23, + "learning_rate": 3.440136153117142e-06, + "loss": 0.1375, + "step": 9577 + }, + { + "epoch": 1.23, + "learning_rate": 3.4391514294496097e-06, + "loss": 0.142, + "step": 9578 + }, + { + "epoch": 1.23, + "learning_rate": 3.438166772855218e-06, + "loss": 0.1415, + "step": 9579 + }, + { + "epoch": 1.23, + "learning_rate": 3.4371821833762776e-06, + "loss": 0.1414, + "step": 9580 + }, + { + "epoch": 1.23, + "learning_rate": 3.4361976610550996e-06, + "loss": 0.1598, + "step": 9581 + }, + { + "epoch": 1.23, + "learning_rate": 3.43521320593399e-06, + "loss": 0.1462, + "step": 9582 + }, + { + "epoch": 1.23, + "learning_rate": 3.4342288180552556e-06, + "loss": 0.1433, + "step": 9583 + }, + { + "epoch": 1.23, + "learning_rate": 3.4332444974611946e-06, + "loss": 0.1444, + "step": 9584 + }, + { + "epoch": 1.23, + "learning_rate": 3.4322602441941064e-06, + "loss": 0.1423, + "step": 9585 + }, + { + "epoch": 1.23, + "learning_rate": 3.4312760582962877e-06, + "loss": 0.1384, + "step": 9586 + }, + { + "epoch": 1.23, + "learning_rate": 3.4302919398100325e-06, + "loss": 0.1514, + "step": 9587 + }, + { + "epoch": 1.23, + "learning_rate": 3.4293078887776264e-06, + "loss": 0.1418, + "step": 9588 + }, + { + "epoch": 1.23, + "learning_rate": 3.428323905241358e-06, + "loss": 0.1303, + "step": 9589 + }, + { + "epoch": 1.23, + "learning_rate": 3.427339989243514e-06, + "loss": 0.1547, + "step": 9590 + }, + { + "epoch": 1.23, + "learning_rate": 3.426356140826372e-06, + "loss": 0.1498, + "step": 9591 + }, + { + "epoch": 1.23, + "learning_rate": 3.4253723600322105e-06, + "loss": 0.131, + "step": 9592 + }, + { + "epoch": 1.23, + "learning_rate": 3.424388646903305e-06, + "loss": 0.1358, + "step": 9593 + }, + { + "epoch": 1.23, + "learning_rate": 3.4234050014819308e-06, + "loss": 0.1587, + "step": 9594 + }, + { + "epoch": 1.23, + "learning_rate": 3.422421423810354e-06, + "loss": 0.1336, + "step": 9595 + }, + { + "epoch": 1.23, + "learning_rate": 3.421437913930842e-06, + "loss": 0.145, + "step": 9596 + }, + { + "epoch": 1.23, + "learning_rate": 3.420454471885659e-06, + "loss": 0.15, + "step": 9597 + }, + { + "epoch": 1.23, + "learning_rate": 3.4194710977170635e-06, + "loss": 0.1531, + "step": 9598 + }, + { + "epoch": 1.23, + "learning_rate": 3.4184877914673155e-06, + "loss": 0.1532, + "step": 9599 + }, + { + "epoch": 1.23, + "learning_rate": 3.41750455317867e-06, + "loss": 0.1251, + "step": 9600 + }, + { + "epoch": 1.23, + "learning_rate": 3.4165213828933797e-06, + "loss": 0.1467, + "step": 9601 + }, + { + "epoch": 1.23, + "learning_rate": 3.4155382806536897e-06, + "loss": 0.1571, + "step": 9602 + }, + { + "epoch": 1.23, + "learning_rate": 3.4145552465018483e-06, + "loss": 0.1337, + "step": 9603 + }, + { + "epoch": 1.23, + "learning_rate": 3.4135722804801004e-06, + "loss": 0.1653, + "step": 9604 + }, + { + "epoch": 1.23, + "learning_rate": 3.4125893826306855e-06, + "loss": 0.1468, + "step": 9605 + }, + { + "epoch": 1.23, + "learning_rate": 3.411606552995838e-06, + "loss": 0.1442, + "step": 9606 + }, + { + "epoch": 1.23, + "learning_rate": 3.4106237916177954e-06, + "loss": 0.1514, + "step": 9607 + }, + { + "epoch": 1.23, + "learning_rate": 3.4096410985387898e-06, + "loss": 0.1618, + "step": 9608 + }, + { + "epoch": 1.23, + "learning_rate": 3.4086584738010455e-06, + "loss": 0.1425, + "step": 9609 + }, + { + "epoch": 1.23, + "learning_rate": 3.4076759174467923e-06, + "loss": 0.1394, + "step": 9610 + }, + { + "epoch": 1.23, + "learning_rate": 3.4066934295182496e-06, + "loss": 0.1342, + "step": 9611 + }, + { + "epoch": 1.23, + "learning_rate": 3.4057110100576408e-06, + "loss": 0.1529, + "step": 9612 + }, + { + "epoch": 1.23, + "learning_rate": 3.4047286591071794e-06, + "loss": 0.1492, + "step": 9613 + }, + { + "epoch": 1.23, + "learning_rate": 3.4037463767090807e-06, + "loss": 0.1374, + "step": 9614 + }, + { + "epoch": 1.23, + "learning_rate": 3.402764162905554e-06, + "loss": 0.1331, + "step": 9615 + }, + { + "epoch": 1.23, + "learning_rate": 3.401782017738811e-06, + "loss": 0.1474, + "step": 9616 + }, + { + "epoch": 1.23, + "learning_rate": 3.400799941251052e-06, + "loss": 0.1355, + "step": 9617 + }, + { + "epoch": 1.23, + "learning_rate": 3.3998179334844823e-06, + "loss": 0.15, + "step": 9618 + }, + { + "epoch": 1.23, + "learning_rate": 3.3988359944812997e-06, + "loss": 0.1414, + "step": 9619 + }, + { + "epoch": 1.23, + "learning_rate": 3.3978541242837003e-06, + "loss": 0.1347, + "step": 9620 + }, + { + "epoch": 1.23, + "learning_rate": 3.396872322933876e-06, + "loss": 0.1415, + "step": 9621 + }, + { + "epoch": 1.23, + "learning_rate": 3.395890590474019e-06, + "loss": 0.1346, + "step": 9622 + }, + { + "epoch": 1.23, + "learning_rate": 3.3949089269463178e-06, + "loss": 0.1478, + "step": 9623 + }, + { + "epoch": 1.23, + "learning_rate": 3.3939273323929533e-06, + "loss": 0.1279, + "step": 9624 + }, + { + "epoch": 1.23, + "learning_rate": 3.3929458068561073e-06, + "loss": 0.1488, + "step": 9625 + }, + { + "epoch": 1.23, + "learning_rate": 3.391964350377961e-06, + "loss": 0.1395, + "step": 9626 + }, + { + "epoch": 1.23, + "learning_rate": 3.3909829630006865e-06, + "loss": 0.1334, + "step": 9627 + }, + { + "epoch": 1.23, + "learning_rate": 3.390001644766458e-06, + "loss": 0.1278, + "step": 9628 + }, + { + "epoch": 1.23, + "learning_rate": 3.3890203957174437e-06, + "loss": 0.1499, + "step": 9629 + }, + { + "epoch": 1.23, + "learning_rate": 3.388039215895813e-06, + "loss": 0.1528, + "step": 9630 + }, + { + "epoch": 1.23, + "learning_rate": 3.3870581053437244e-06, + "loss": 0.1553, + "step": 9631 + }, + { + "epoch": 1.23, + "learning_rate": 3.3860770641033417e-06, + "loss": 0.1509, + "step": 9632 + }, + { + "epoch": 1.23, + "learning_rate": 3.385096092216823e-06, + "loss": 0.1523, + "step": 9633 + }, + { + "epoch": 1.23, + "learning_rate": 3.3841151897263234e-06, + "loss": 0.148, + "step": 9634 + }, + { + "epoch": 1.23, + "learning_rate": 3.3831343566739904e-06, + "loss": 0.1582, + "step": 9635 + }, + { + "epoch": 1.23, + "learning_rate": 3.3821535931019744e-06, + "loss": 0.1573, + "step": 9636 + }, + { + "epoch": 1.23, + "learning_rate": 3.3811728990524245e-06, + "loss": 0.1434, + "step": 9637 + }, + { + "epoch": 1.23, + "learning_rate": 3.380192274567479e-06, + "loss": 0.1392, + "step": 9638 + }, + { + "epoch": 1.23, + "learning_rate": 3.379211719689278e-06, + "loss": 0.1252, + "step": 9639 + }, + { + "epoch": 1.23, + "learning_rate": 3.3782312344599598e-06, + "loss": 0.1335, + "step": 9640 + }, + { + "epoch": 1.23, + "learning_rate": 3.3772508189216586e-06, + "loss": 0.1441, + "step": 9641 + }, + { + "epoch": 1.23, + "learning_rate": 3.376270473116503e-06, + "loss": 0.1434, + "step": 9642 + }, + { + "epoch": 1.23, + "learning_rate": 3.37529019708662e-06, + "loss": 0.1428, + "step": 9643 + }, + { + "epoch": 1.23, + "learning_rate": 3.3743099908741385e-06, + "loss": 0.1505, + "step": 9644 + }, + { + "epoch": 1.23, + "learning_rate": 3.3733298545211748e-06, + "loss": 0.1712, + "step": 9645 + }, + { + "epoch": 1.23, + "learning_rate": 3.37234978806985e-06, + "loss": 0.1486, + "step": 9646 + }, + { + "epoch": 1.23, + "learning_rate": 3.3713697915622806e-06, + "loss": 0.1417, + "step": 9647 + }, + { + "epoch": 1.23, + "learning_rate": 3.3703898650405796e-06, + "loss": 0.1462, + "step": 9648 + }, + { + "epoch": 1.24, + "learning_rate": 3.3694100085468535e-06, + "loss": 0.1465, + "step": 9649 + }, + { + "epoch": 1.24, + "learning_rate": 3.3684302221232106e-06, + "loss": 0.1451, + "step": 9650 + }, + { + "epoch": 1.24, + "learning_rate": 3.3674505058117556e-06, + "loss": 0.1475, + "step": 9651 + }, + { + "epoch": 1.24, + "learning_rate": 3.36647085965459e-06, + "loss": 0.1464, + "step": 9652 + }, + { + "epoch": 1.24, + "learning_rate": 3.365491283693807e-06, + "loss": 0.141, + "step": 9653 + }, + { + "epoch": 1.24, + "learning_rate": 3.364511777971504e-06, + "loss": 0.1465, + "step": 9654 + }, + { + "epoch": 1.24, + "learning_rate": 3.363532342529775e-06, + "loss": 0.1455, + "step": 9655 + }, + { + "epoch": 1.24, + "learning_rate": 3.3625529774107028e-06, + "loss": 0.1411, + "step": 9656 + }, + { + "epoch": 1.24, + "learning_rate": 3.361573682656377e-06, + "loss": 0.1449, + "step": 9657 + }, + { + "epoch": 1.24, + "learning_rate": 3.360594458308879e-06, + "loss": 0.1425, + "step": 9658 + }, + { + "epoch": 1.24, + "learning_rate": 3.3596153044102897e-06, + "loss": 0.1543, + "step": 9659 + }, + { + "epoch": 1.24, + "learning_rate": 3.358636221002682e-06, + "loss": 0.1466, + "step": 9660 + }, + { + "epoch": 1.24, + "learning_rate": 3.357657208128132e-06, + "loss": 0.1423, + "step": 9661 + }, + { + "epoch": 1.24, + "learning_rate": 3.356678265828711e-06, + "loss": 0.1451, + "step": 9662 + }, + { + "epoch": 1.24, + "learning_rate": 3.3556993941464834e-06, + "loss": 0.1451, + "step": 9663 + }, + { + "epoch": 1.24, + "learning_rate": 3.354720593123514e-06, + "loss": 0.1395, + "step": 9664 + }, + { + "epoch": 1.24, + "learning_rate": 3.353741862801866e-06, + "loss": 0.1285, + "step": 9665 + }, + { + "epoch": 1.24, + "learning_rate": 3.352763203223598e-06, + "loss": 0.1575, + "step": 9666 + }, + { + "epoch": 1.24, + "learning_rate": 3.351784614430761e-06, + "loss": 0.139, + "step": 9667 + }, + { + "epoch": 1.24, + "learning_rate": 3.3508060964654106e-06, + "loss": 0.1517, + "step": 9668 + }, + { + "epoch": 1.24, + "learning_rate": 3.349827649369596e-06, + "loss": 0.1388, + "step": 9669 + }, + { + "epoch": 1.24, + "learning_rate": 3.348849273185362e-06, + "loss": 0.147, + "step": 9670 + }, + { + "epoch": 1.24, + "learning_rate": 3.3478709679547527e-06, + "loss": 0.1458, + "step": 9671 + }, + { + "epoch": 1.24, + "learning_rate": 3.346892733719806e-06, + "loss": 0.134, + "step": 9672 + }, + { + "epoch": 1.24, + "learning_rate": 3.3459145705225627e-06, + "loss": 0.1394, + "step": 9673 + }, + { + "epoch": 1.24, + "learning_rate": 3.3449364784050515e-06, + "loss": 0.1359, + "step": 9674 + }, + { + "epoch": 1.24, + "learning_rate": 3.343958457409307e-06, + "loss": 0.158, + "step": 9675 + }, + { + "epoch": 1.24, + "learning_rate": 3.3429805075773547e-06, + "loss": 0.1468, + "step": 9676 + }, + { + "epoch": 1.24, + "learning_rate": 3.3420026289512232e-06, + "loss": 0.1421, + "step": 9677 + }, + { + "epoch": 1.24, + "learning_rate": 3.341024821572928e-06, + "loss": 0.136, + "step": 9678 + }, + { + "epoch": 1.24, + "learning_rate": 3.3400470854844925e-06, + "loss": 0.1495, + "step": 9679 + }, + { + "epoch": 1.24, + "learning_rate": 3.3390694207279308e-06, + "loss": 0.1554, + "step": 9680 + }, + { + "epoch": 1.24, + "learning_rate": 3.3380918273452557e-06, + "loss": 0.1466, + "step": 9681 + }, + { + "epoch": 1.24, + "learning_rate": 3.3371143053784737e-06, + "loss": 0.1486, + "step": 9682 + }, + { + "epoch": 1.24, + "learning_rate": 3.336136854869595e-06, + "loss": 0.1307, + "step": 9683 + }, + { + "epoch": 1.24, + "learning_rate": 3.3351594758606222e-06, + "loss": 0.1347, + "step": 9684 + }, + { + "epoch": 1.24, + "learning_rate": 3.334182168393554e-06, + "loss": 0.1371, + "step": 9685 + }, + { + "epoch": 1.24, + "learning_rate": 3.3332049325103867e-06, + "loss": 0.1436, + "step": 9686 + }, + { + "epoch": 1.24, + "learning_rate": 3.332227768253116e-06, + "loss": 0.1516, + "step": 9687 + }, + { + "epoch": 1.24, + "learning_rate": 3.3312506756637343e-06, + "loss": 0.1596, + "step": 9688 + }, + { + "epoch": 1.24, + "learning_rate": 3.3302736547842263e-06, + "loss": 0.1458, + "step": 9689 + }, + { + "epoch": 1.24, + "learning_rate": 3.3292967056565766e-06, + "loss": 0.1378, + "step": 9690 + }, + { + "epoch": 1.24, + "learning_rate": 3.3283198283227715e-06, + "loss": 0.1562, + "step": 9691 + }, + { + "epoch": 1.24, + "learning_rate": 3.3273430228247834e-06, + "loss": 0.1282, + "step": 9692 + }, + { + "epoch": 1.24, + "learning_rate": 3.3263662892045924e-06, + "loss": 0.1369, + "step": 9693 + }, + { + "epoch": 1.24, + "learning_rate": 3.3253896275041677e-06, + "loss": 0.1283, + "step": 9694 + }, + { + "epoch": 1.24, + "learning_rate": 3.324413037765483e-06, + "loss": 0.1454, + "step": 9695 + }, + { + "epoch": 1.24, + "learning_rate": 3.3234365200304997e-06, + "loss": 0.1439, + "step": 9696 + }, + { + "epoch": 1.24, + "learning_rate": 3.322460074341183e-06, + "loss": 0.1451, + "step": 9697 + }, + { + "epoch": 1.24, + "learning_rate": 3.321483700739494e-06, + "loss": 0.142, + "step": 9698 + }, + { + "epoch": 1.24, + "learning_rate": 3.3205073992673885e-06, + "loss": 0.1498, + "step": 9699 + }, + { + "epoch": 1.24, + "learning_rate": 3.31953116996682e-06, + "loss": 0.1381, + "step": 9700 + }, + { + "epoch": 1.24, + "learning_rate": 3.3185550128797387e-06, + "loss": 0.1465, + "step": 9701 + }, + { + "epoch": 1.24, + "learning_rate": 3.317578928048096e-06, + "loss": 0.1317, + "step": 9702 + }, + { + "epoch": 1.24, + "learning_rate": 3.3166029155138324e-06, + "loss": 0.1424, + "step": 9703 + }, + { + "epoch": 1.24, + "learning_rate": 3.3156269753188895e-06, + "loss": 0.1537, + "step": 9704 + }, + { + "epoch": 1.24, + "learning_rate": 3.314651107505207e-06, + "loss": 0.1336, + "step": 9705 + }, + { + "epoch": 1.24, + "learning_rate": 3.313675312114722e-06, + "loss": 0.1523, + "step": 9706 + }, + { + "epoch": 1.24, + "learning_rate": 3.312699589189362e-06, + "loss": 0.1515, + "step": 9707 + }, + { + "epoch": 1.24, + "learning_rate": 3.31172393877106e-06, + "loss": 0.1509, + "step": 9708 + }, + { + "epoch": 1.24, + "learning_rate": 3.310748360901741e-06, + "loss": 0.129, + "step": 9709 + }, + { + "epoch": 1.24, + "learning_rate": 3.3097728556233256e-06, + "loss": 0.1496, + "step": 9710 + }, + { + "epoch": 1.24, + "learning_rate": 3.308797422977734e-06, + "loss": 0.142, + "step": 9711 + }, + { + "epoch": 1.24, + "learning_rate": 3.307822063006886e-06, + "loss": 0.1289, + "step": 9712 + }, + { + "epoch": 1.24, + "learning_rate": 3.3068467757526927e-06, + "loss": 0.1303, + "step": 9713 + }, + { + "epoch": 1.24, + "learning_rate": 3.3058715612570623e-06, + "loss": 0.1212, + "step": 9714 + }, + { + "epoch": 1.24, + "learning_rate": 3.3048964195619044e-06, + "loss": 0.1607, + "step": 9715 + }, + { + "epoch": 1.24, + "learning_rate": 3.303921350709124e-06, + "loss": 0.1348, + "step": 9716 + }, + { + "epoch": 1.24, + "learning_rate": 3.3029463547406198e-06, + "loss": 0.1288, + "step": 9717 + }, + { + "epoch": 1.24, + "learning_rate": 3.30197143169829e-06, + "loss": 0.1598, + "step": 9718 + }, + { + "epoch": 1.24, + "learning_rate": 3.300996581624028e-06, + "loss": 0.1399, + "step": 9719 + }, + { + "epoch": 1.24, + "learning_rate": 3.30002180455973e-06, + "loss": 0.147, + "step": 9720 + }, + { + "epoch": 1.24, + "learning_rate": 3.299047100547278e-06, + "loss": 0.1448, + "step": 9721 + }, + { + "epoch": 1.24, + "learning_rate": 3.2980724696285626e-06, + "loss": 0.138, + "step": 9722 + }, + { + "epoch": 1.24, + "learning_rate": 3.2970979118454616e-06, + "loss": 0.1581, + "step": 9723 + }, + { + "epoch": 1.24, + "learning_rate": 3.2961234272398578e-06, + "loss": 0.1447, + "step": 9724 + }, + { + "epoch": 1.24, + "learning_rate": 3.2951490158536238e-06, + "loss": 0.1441, + "step": 9725 + }, + { + "epoch": 1.24, + "learning_rate": 3.2941746777286344e-06, + "loss": 0.1354, + "step": 9726 + }, + { + "epoch": 1.25, + "learning_rate": 3.2932004129067592e-06, + "loss": 0.1395, + "step": 9727 + }, + { + "epoch": 1.25, + "learning_rate": 3.2922262214298613e-06, + "loss": 0.1535, + "step": 9728 + }, + { + "epoch": 1.25, + "learning_rate": 3.291252103339806e-06, + "loss": 0.1396, + "step": 9729 + }, + { + "epoch": 1.25, + "learning_rate": 3.2902780586784542e-06, + "loss": 0.1461, + "step": 9730 + }, + { + "epoch": 1.25, + "learning_rate": 3.2893040874876624e-06, + "loss": 0.1395, + "step": 9731 + }, + { + "epoch": 1.25, + "learning_rate": 3.2883301898092833e-06, + "loss": 0.1507, + "step": 9732 + }, + { + "epoch": 1.25, + "learning_rate": 3.287356365685168e-06, + "loss": 0.1362, + "step": 9733 + }, + { + "epoch": 1.25, + "learning_rate": 3.2863826151571654e-06, + "loss": 0.1645, + "step": 9734 + }, + { + "epoch": 1.25, + "learning_rate": 3.285408938267116e-06, + "loss": 0.1338, + "step": 9735 + }, + { + "epoch": 1.25, + "learning_rate": 3.284435335056865e-06, + "loss": 0.1305, + "step": 9736 + }, + { + "epoch": 1.25, + "learning_rate": 3.283461805568246e-06, + "loss": 0.136, + "step": 9737 + }, + { + "epoch": 1.25, + "learning_rate": 3.2824883498430992e-06, + "loss": 0.1437, + "step": 9738 + }, + { + "epoch": 1.25, + "learning_rate": 3.2815149679232507e-06, + "loss": 0.1409, + "step": 9739 + }, + { + "epoch": 1.25, + "learning_rate": 3.2805416598505323e-06, + "loss": 0.1418, + "step": 9740 + }, + { + "epoch": 1.25, + "learning_rate": 3.2795684256667674e-06, + "loss": 0.135, + "step": 9741 + }, + { + "epoch": 1.25, + "learning_rate": 3.278595265413781e-06, + "loss": 0.1438, + "step": 9742 + }, + { + "epoch": 1.25, + "learning_rate": 3.277622179133387e-06, + "loss": 0.1446, + "step": 9743 + }, + { + "epoch": 1.25, + "learning_rate": 3.276649166867406e-06, + "loss": 0.1502, + "step": 9744 + }, + { + "epoch": 1.25, + "learning_rate": 3.2756762286576482e-06, + "loss": 0.1505, + "step": 9745 + }, + { + "epoch": 1.25, + "learning_rate": 3.2747033645459226e-06, + "loss": 0.1546, + "step": 9746 + }, + { + "epoch": 1.25, + "learning_rate": 3.2737305745740353e-06, + "loss": 0.1436, + "step": 9747 + }, + { + "epoch": 1.25, + "learning_rate": 3.2727578587837893e-06, + "loss": 0.1364, + "step": 9748 + }, + { + "epoch": 1.25, + "learning_rate": 3.271785217216987e-06, + "loss": 0.143, + "step": 9749 + }, + { + "epoch": 1.25, + "learning_rate": 3.2708126499154225e-06, + "loss": 0.1382, + "step": 9750 + }, + { + "epoch": 1.25, + "learning_rate": 3.2698401569208883e-06, + "loss": 0.1389, + "step": 9751 + }, + { + "epoch": 1.25, + "learning_rate": 3.2688677382751754e-06, + "loss": 0.1485, + "step": 9752 + }, + { + "epoch": 1.25, + "learning_rate": 3.2678953940200744e-06, + "loss": 0.1524, + "step": 9753 + }, + { + "epoch": 1.25, + "learning_rate": 3.266923124197363e-06, + "loss": 0.159, + "step": 9754 + }, + { + "epoch": 1.25, + "learning_rate": 3.265950928848825e-06, + "loss": 0.1365, + "step": 9755 + }, + { + "epoch": 1.25, + "learning_rate": 3.264978808016239e-06, + "loss": 0.152, + "step": 9756 + }, + { + "epoch": 1.25, + "learning_rate": 3.264006761741376e-06, + "loss": 0.1518, + "step": 9757 + }, + { + "epoch": 1.25, + "learning_rate": 3.2630347900660094e-06, + "loss": 0.151, + "step": 9758 + }, + { + "epoch": 1.25, + "learning_rate": 3.2620628930319065e-06, + "loss": 0.1509, + "step": 9759 + }, + { + "epoch": 1.25, + "learning_rate": 3.261091070680833e-06, + "loss": 0.1429, + "step": 9760 + }, + { + "epoch": 1.25, + "learning_rate": 3.260119323054546e-06, + "loss": 0.1556, + "step": 9761 + }, + { + "epoch": 1.25, + "learning_rate": 3.2591476501948075e-06, + "loss": 0.1495, + "step": 9762 + }, + { + "epoch": 1.25, + "learning_rate": 3.258176052143374e-06, + "loss": 0.15, + "step": 9763 + }, + { + "epoch": 1.25, + "learning_rate": 3.257204528941993e-06, + "loss": 0.1605, + "step": 9764 + }, + { + "epoch": 1.25, + "learning_rate": 3.256233080632414e-06, + "loss": 0.1523, + "step": 9765 + }, + { + "epoch": 1.25, + "learning_rate": 3.255261707256383e-06, + "loss": 0.1543, + "step": 9766 + }, + { + "epoch": 1.25, + "learning_rate": 3.2542904088556437e-06, + "loss": 0.1312, + "step": 9767 + }, + { + "epoch": 1.25, + "learning_rate": 3.2533191854719336e-06, + "loss": 0.1517, + "step": 9768 + }, + { + "epoch": 1.25, + "learning_rate": 3.2523480371469863e-06, + "loss": 0.1423, + "step": 9769 + }, + { + "epoch": 1.25, + "learning_rate": 3.251376963922537e-06, + "loss": 0.1455, + "step": 9770 + }, + { + "epoch": 1.25, + "learning_rate": 3.250405965840315e-06, + "loss": 0.1456, + "step": 9771 + }, + { + "epoch": 1.25, + "learning_rate": 3.249435042942043e-06, + "loss": 0.1491, + "step": 9772 + }, + { + "epoch": 1.25, + "learning_rate": 3.2484641952694473e-06, + "loss": 0.1435, + "step": 9773 + }, + { + "epoch": 1.25, + "learning_rate": 3.2474934228642475e-06, + "loss": 0.1524, + "step": 9774 + }, + { + "epoch": 1.25, + "learning_rate": 3.246522725768156e-06, + "loss": 0.1383, + "step": 9775 + }, + { + "epoch": 1.25, + "learning_rate": 3.2455521040228883e-06, + "loss": 0.1645, + "step": 9776 + }, + { + "epoch": 1.25, + "learning_rate": 3.2445815576701544e-06, + "loss": 0.1465, + "step": 9777 + }, + { + "epoch": 1.25, + "learning_rate": 3.2436110867516625e-06, + "loss": 0.149, + "step": 9778 + }, + { + "epoch": 1.25, + "learning_rate": 3.242640691309111e-06, + "loss": 0.126, + "step": 9779 + }, + { + "epoch": 1.25, + "learning_rate": 3.2416703713842036e-06, + "loss": 0.1466, + "step": 9780 + }, + { + "epoch": 1.25, + "learning_rate": 3.240700127018638e-06, + "loss": 0.1565, + "step": 9781 + }, + { + "epoch": 1.25, + "learning_rate": 3.239729958254104e-06, + "loss": 0.1428, + "step": 9782 + }, + { + "epoch": 1.25, + "learning_rate": 3.238759865132295e-06, + "loss": 0.1553, + "step": 9783 + }, + { + "epoch": 1.25, + "learning_rate": 3.2377898476948964e-06, + "loss": 0.1575, + "step": 9784 + }, + { + "epoch": 1.25, + "learning_rate": 3.2368199059835947e-06, + "loss": 0.1313, + "step": 9785 + }, + { + "epoch": 1.25, + "learning_rate": 3.235850040040066e-06, + "loss": 0.1344, + "step": 9786 + }, + { + "epoch": 1.25, + "learning_rate": 3.2348802499059915e-06, + "loss": 0.152, + "step": 9787 + }, + { + "epoch": 1.25, + "learning_rate": 3.2339105356230426e-06, + "loss": 0.1401, + "step": 9788 + }, + { + "epoch": 1.25, + "learning_rate": 3.2329408972328934e-06, + "loss": 0.1425, + "step": 9789 + }, + { + "epoch": 1.25, + "learning_rate": 3.2319713347772075e-06, + "loss": 0.1526, + "step": 9790 + }, + { + "epoch": 1.25, + "learning_rate": 3.231001848297651e-06, + "loss": 0.1358, + "step": 9791 + }, + { + "epoch": 1.25, + "learning_rate": 3.230032437835887e-06, + "loss": 0.1442, + "step": 9792 + }, + { + "epoch": 1.25, + "learning_rate": 3.2290631034335684e-06, + "loss": 0.1418, + "step": 9793 + }, + { + "epoch": 1.25, + "learning_rate": 3.2280938451323524e-06, + "loss": 0.1419, + "step": 9794 + }, + { + "epoch": 1.25, + "learning_rate": 3.2271246629738917e-06, + "loss": 0.1428, + "step": 9795 + }, + { + "epoch": 1.25, + "learning_rate": 3.2261555569998316e-06, + "loss": 0.1415, + "step": 9796 + }, + { + "epoch": 1.25, + "learning_rate": 3.2251865272518187e-06, + "loss": 0.1383, + "step": 9797 + }, + { + "epoch": 1.25, + "learning_rate": 3.224217573771492e-06, + "loss": 0.1447, + "step": 9798 + }, + { + "epoch": 1.25, + "learning_rate": 3.223248696600493e-06, + "loss": 0.1451, + "step": 9799 + }, + { + "epoch": 1.25, + "learning_rate": 3.2222798957804524e-06, + "loss": 0.1543, + "step": 9800 + }, + { + "epoch": 1.25, + "learning_rate": 3.2213111713530056e-06, + "loss": 0.161, + "step": 9801 + }, + { + "epoch": 1.25, + "learning_rate": 3.2203425233597773e-06, + "loss": 0.1514, + "step": 9802 + }, + { + "epoch": 1.25, + "learning_rate": 3.2193739518423972e-06, + "loss": 0.1376, + "step": 9803 + }, + { + "epoch": 1.25, + "learning_rate": 3.2184054568424817e-06, + "loss": 0.1455, + "step": 9804 + }, + { + "epoch": 1.26, + "learning_rate": 3.217437038401652e-06, + "loss": 0.144, + "step": 9805 + }, + { + "epoch": 1.26, + "learning_rate": 3.2164686965615223e-06, + "loss": 0.1383, + "step": 9806 + }, + { + "epoch": 1.26, + "learning_rate": 3.215500431363706e-06, + "loss": 0.1453, + "step": 9807 + }, + { + "epoch": 1.26, + "learning_rate": 3.2145322428498093e-06, + "loss": 0.1487, + "step": 9808 + }, + { + "epoch": 1.26, + "learning_rate": 3.2135641310614383e-06, + "loss": 0.1379, + "step": 9809 + }, + { + "epoch": 1.26, + "learning_rate": 3.2125960960401974e-06, + "loss": 0.1493, + "step": 9810 + }, + { + "epoch": 1.26, + "learning_rate": 3.211628137827682e-06, + "loss": 0.149, + "step": 9811 + }, + { + "epoch": 1.26, + "learning_rate": 3.2106602564654877e-06, + "loss": 0.1379, + "step": 9812 + }, + { + "epoch": 1.26, + "learning_rate": 3.2096924519952067e-06, + "loss": 0.1464, + "step": 9813 + }, + { + "epoch": 1.26, + "learning_rate": 3.20872472445843e-06, + "loss": 0.1354, + "step": 9814 + }, + { + "epoch": 1.26, + "learning_rate": 3.207757073896741e-06, + "loss": 0.15, + "step": 9815 + }, + { + "epoch": 1.26, + "learning_rate": 3.2067895003517207e-06, + "loss": 0.1586, + "step": 9816 + }, + { + "epoch": 1.26, + "learning_rate": 3.2058220038649513e-06, + "loss": 0.1359, + "step": 9817 + }, + { + "epoch": 1.26, + "learning_rate": 3.2048545844780044e-06, + "loss": 0.1392, + "step": 9818 + }, + { + "epoch": 1.26, + "learning_rate": 3.203887242232455e-06, + "loss": 0.1255, + "step": 9819 + }, + { + "epoch": 1.26, + "learning_rate": 3.2029199771698693e-06, + "loss": 0.1431, + "step": 9820 + }, + { + "epoch": 1.26, + "learning_rate": 3.2019527893318177e-06, + "loss": 0.1487, + "step": 9821 + }, + { + "epoch": 1.26, + "learning_rate": 3.2009856787598558e-06, + "loss": 0.1472, + "step": 9822 + }, + { + "epoch": 1.26, + "learning_rate": 3.2000186454955474e-06, + "loss": 0.1638, + "step": 9823 + }, + { + "epoch": 1.26, + "learning_rate": 3.1990516895804467e-06, + "loss": 0.1588, + "step": 9824 + }, + { + "epoch": 1.26, + "learning_rate": 3.198084811056107e-06, + "loss": 0.1215, + "step": 9825 + }, + { + "epoch": 1.26, + "learning_rate": 3.197118009964074e-06, + "loss": 0.1485, + "step": 9826 + }, + { + "epoch": 1.26, + "learning_rate": 3.1961512863458953e-06, + "loss": 0.1562, + "step": 9827 + }, + { + "epoch": 1.26, + "learning_rate": 3.195184640243115e-06, + "loss": 0.1382, + "step": 9828 + }, + { + "epoch": 1.26, + "learning_rate": 3.1942180716972698e-06, + "loss": 0.1498, + "step": 9829 + }, + { + "epoch": 1.26, + "learning_rate": 3.1932515807498945e-06, + "loss": 0.1408, + "step": 9830 + }, + { + "epoch": 1.26, + "learning_rate": 3.1922851674425226e-06, + "loss": 0.1281, + "step": 9831 + }, + { + "epoch": 1.26, + "learning_rate": 3.191318831816685e-06, + "loss": 0.1365, + "step": 9832 + }, + { + "epoch": 1.26, + "learning_rate": 3.190352573913903e-06, + "loss": 0.1458, + "step": 9833 + }, + { + "epoch": 1.26, + "learning_rate": 3.189386393775703e-06, + "loss": 0.141, + "step": 9834 + }, + { + "epoch": 1.26, + "learning_rate": 3.1884202914436024e-06, + "loss": 0.1426, + "step": 9835 + }, + { + "epoch": 1.26, + "learning_rate": 3.1874542669591148e-06, + "loss": 0.1289, + "step": 9836 + }, + { + "epoch": 1.26, + "learning_rate": 3.1864883203637544e-06, + "loss": 0.144, + "step": 9837 + }, + { + "epoch": 1.26, + "learning_rate": 3.18552245169903e-06, + "loss": 0.1486, + "step": 9838 + }, + { + "epoch": 1.26, + "learning_rate": 3.1845566610064487e-06, + "loss": 0.1539, + "step": 9839 + }, + { + "epoch": 1.26, + "learning_rate": 3.1835909483275083e-06, + "loss": 0.1376, + "step": 9840 + }, + { + "epoch": 1.26, + "learning_rate": 3.1826253137037112e-06, + "loss": 0.1454, + "step": 9841 + }, + { + "epoch": 1.26, + "learning_rate": 3.1816597571765517e-06, + "loss": 0.1521, + "step": 9842 + }, + { + "epoch": 1.26, + "learning_rate": 3.180694278787524e-06, + "loss": 0.1568, + "step": 9843 + }, + { + "epoch": 1.26, + "learning_rate": 3.179728878578112e-06, + "loss": 0.1302, + "step": 9844 + }, + { + "epoch": 1.26, + "learning_rate": 3.1787635565898046e-06, + "loss": 0.1489, + "step": 9845 + }, + { + "epoch": 1.26, + "learning_rate": 3.1777983128640855e-06, + "loss": 0.1428, + "step": 9846 + }, + { + "epoch": 1.26, + "learning_rate": 3.1768331474424285e-06, + "loss": 0.1392, + "step": 9847 + }, + { + "epoch": 1.26, + "learning_rate": 3.1758680603663127e-06, + "loss": 0.1275, + "step": 9848 + }, + { + "epoch": 1.26, + "learning_rate": 3.1749030516772084e-06, + "loss": 0.1644, + "step": 9849 + }, + { + "epoch": 1.26, + "learning_rate": 3.1739381214165864e-06, + "loss": 0.1504, + "step": 9850 + }, + { + "epoch": 1.26, + "learning_rate": 3.1729732696259085e-06, + "loss": 0.1318, + "step": 9851 + }, + { + "epoch": 1.26, + "learning_rate": 3.172008496346639e-06, + "loss": 0.1584, + "step": 9852 + }, + { + "epoch": 1.26, + "learning_rate": 3.1710438016202362e-06, + "loss": 0.1476, + "step": 9853 + }, + { + "epoch": 1.26, + "learning_rate": 3.170079185488153e-06, + "loss": 0.1334, + "step": 9854 + }, + { + "epoch": 1.26, + "learning_rate": 3.1691146479918423e-06, + "loss": 0.1433, + "step": 9855 + }, + { + "epoch": 1.26, + "learning_rate": 3.168150189172754e-06, + "loss": 0.1406, + "step": 9856 + }, + { + "epoch": 1.26, + "learning_rate": 3.1671858090723315e-06, + "loss": 0.1465, + "step": 9857 + }, + { + "epoch": 1.26, + "learning_rate": 3.1662215077320174e-06, + "loss": 0.1413, + "step": 9858 + }, + { + "epoch": 1.26, + "learning_rate": 3.165257285193248e-06, + "loss": 0.1455, + "step": 9859 + }, + { + "epoch": 1.26, + "learning_rate": 3.1642931414974586e-06, + "loss": 0.1367, + "step": 9860 + }, + { + "epoch": 1.26, + "learning_rate": 3.1633290766860834e-06, + "loss": 0.1464, + "step": 9861 + }, + { + "epoch": 1.26, + "learning_rate": 3.1623650908005476e-06, + "loss": 0.1346, + "step": 9862 + }, + { + "epoch": 1.26, + "learning_rate": 3.1614011838822755e-06, + "loss": 0.1315, + "step": 9863 + }, + { + "epoch": 1.26, + "learning_rate": 3.1604373559726915e-06, + "loss": 0.1614, + "step": 9864 + }, + { + "epoch": 1.26, + "learning_rate": 3.1594736071132086e-06, + "loss": 0.1329, + "step": 9865 + }, + { + "epoch": 1.26, + "learning_rate": 3.1585099373452454e-06, + "loss": 0.1479, + "step": 9866 + }, + { + "epoch": 1.26, + "learning_rate": 3.15754634671021e-06, + "loss": 0.1428, + "step": 9867 + }, + { + "epoch": 1.26, + "learning_rate": 3.1565828352495144e-06, + "loss": 0.138, + "step": 9868 + }, + { + "epoch": 1.26, + "learning_rate": 3.1556194030045563e-06, + "loss": 0.1385, + "step": 9869 + }, + { + "epoch": 1.26, + "learning_rate": 3.154656050016742e-06, + "loss": 0.1424, + "step": 9870 + }, + { + "epoch": 1.26, + "learning_rate": 3.153692776327466e-06, + "loss": 0.1561, + "step": 9871 + }, + { + "epoch": 1.26, + "learning_rate": 3.1527295819781256e-06, + "loss": 0.141, + "step": 9872 + }, + { + "epoch": 1.26, + "learning_rate": 3.151766467010107e-06, + "loss": 0.1392, + "step": 9873 + }, + { + "epoch": 1.26, + "learning_rate": 3.1508034314647994e-06, + "loss": 0.139, + "step": 9874 + }, + { + "epoch": 1.26, + "learning_rate": 3.149840475383589e-06, + "loss": 0.1491, + "step": 9875 + }, + { + "epoch": 1.26, + "learning_rate": 3.1488775988078525e-06, + "loss": 0.1382, + "step": 9876 + }, + { + "epoch": 1.26, + "learning_rate": 3.1479148017789673e-06, + "loss": 0.1508, + "step": 9877 + }, + { + "epoch": 1.26, + "learning_rate": 3.146952084338308e-06, + "loss": 0.1412, + "step": 9878 + }, + { + "epoch": 1.26, + "learning_rate": 3.1459894465272467e-06, + "loss": 0.1344, + "step": 9879 + }, + { + "epoch": 1.26, + "learning_rate": 3.1450268883871467e-06, + "loss": 0.1449, + "step": 9880 + }, + { + "epoch": 1.26, + "learning_rate": 3.1440644099593716e-06, + "loss": 0.1544, + "step": 9881 + }, + { + "epoch": 1.26, + "learning_rate": 3.143102011285284e-06, + "loss": 0.1387, + "step": 9882 + }, + { + "epoch": 1.27, + "learning_rate": 3.142139692406237e-06, + "loss": 0.1506, + "step": 9883 + }, + { + "epoch": 1.27, + "learning_rate": 3.1411774533635854e-06, + "loss": 0.1277, + "step": 9884 + }, + { + "epoch": 1.27, + "learning_rate": 3.1402152941986786e-06, + "loss": 0.1369, + "step": 9885 + }, + { + "epoch": 1.27, + "learning_rate": 3.1392532149528643e-06, + "loss": 0.1581, + "step": 9886 + }, + { + "epoch": 1.27, + "learning_rate": 3.1382912156674807e-06, + "loss": 0.1449, + "step": 9887 + }, + { + "epoch": 1.27, + "learning_rate": 3.13732929638387e-06, + "loss": 0.138, + "step": 9888 + }, + { + "epoch": 1.27, + "learning_rate": 3.136367457143369e-06, + "loss": 0.1548, + "step": 9889 + }, + { + "epoch": 1.27, + "learning_rate": 3.1354056979873104e-06, + "loss": 0.1339, + "step": 9890 + }, + { + "epoch": 1.27, + "learning_rate": 3.134444018957019e-06, + "loss": 0.1266, + "step": 9891 + }, + { + "epoch": 1.27, + "learning_rate": 3.1334824200938228e-06, + "loss": 0.1475, + "step": 9892 + }, + { + "epoch": 1.27, + "learning_rate": 3.132520901439047e-06, + "loss": 0.1474, + "step": 9893 + }, + { + "epoch": 1.27, + "learning_rate": 3.1315594630340052e-06, + "loss": 0.1399, + "step": 9894 + }, + { + "epoch": 1.27, + "learning_rate": 3.1305981049200134e-06, + "loss": 0.1515, + "step": 9895 + }, + { + "epoch": 1.27, + "learning_rate": 3.129636827138385e-06, + "loss": 0.1518, + "step": 9896 + }, + { + "epoch": 1.27, + "learning_rate": 3.128675629730429e-06, + "loss": 0.1369, + "step": 9897 + }, + { + "epoch": 1.27, + "learning_rate": 3.1277145127374475e-06, + "loss": 0.1501, + "step": 9898 + }, + { + "epoch": 1.27, + "learning_rate": 3.1267534762007435e-06, + "loss": 0.1519, + "step": 9899 + }, + { + "epoch": 1.27, + "learning_rate": 3.125792520161616e-06, + "loss": 0.1355, + "step": 9900 + }, + { + "epoch": 1.27, + "learning_rate": 3.1248316446613563e-06, + "loss": 0.1561, + "step": 9901 + }, + { + "epoch": 1.27, + "learning_rate": 3.1238708497412566e-06, + "loss": 0.1348, + "step": 9902 + }, + { + "epoch": 1.27, + "learning_rate": 3.1229101354426063e-06, + "loss": 0.1403, + "step": 9903 + }, + { + "epoch": 1.27, + "learning_rate": 3.1219495018066888e-06, + "loss": 0.1462, + "step": 9904 + }, + { + "epoch": 1.27, + "learning_rate": 3.1209889488747813e-06, + "loss": 0.1473, + "step": 9905 + }, + { + "epoch": 1.27, + "learning_rate": 3.120028476688164e-06, + "loss": 0.1395, + "step": 9906 + }, + { + "epoch": 1.27, + "learning_rate": 3.119068085288111e-06, + "loss": 0.1431, + "step": 9907 + }, + { + "epoch": 1.27, + "learning_rate": 3.118107774715892e-06, + "loss": 0.1632, + "step": 9908 + }, + { + "epoch": 1.27, + "learning_rate": 3.1171475450127717e-06, + "loss": 0.1523, + "step": 9909 + }, + { + "epoch": 1.27, + "learning_rate": 3.1161873962200146e-06, + "loss": 0.1447, + "step": 9910 + }, + { + "epoch": 1.27, + "learning_rate": 3.1152273283788824e-06, + "loss": 0.1406, + "step": 9911 + }, + { + "epoch": 1.27, + "learning_rate": 3.114267341530627e-06, + "loss": 0.1338, + "step": 9912 + }, + { + "epoch": 1.27, + "learning_rate": 3.1133074357165055e-06, + "loss": 0.1393, + "step": 9913 + }, + { + "epoch": 1.27, + "learning_rate": 3.112347610977764e-06, + "loss": 0.1482, + "step": 9914 + }, + { + "epoch": 1.27, + "learning_rate": 3.111387867355652e-06, + "loss": 0.1445, + "step": 9915 + }, + { + "epoch": 1.27, + "learning_rate": 3.110428204891407e-06, + "loss": 0.1325, + "step": 9916 + }, + { + "epoch": 1.27, + "learning_rate": 3.109468623626272e-06, + "loss": 0.1428, + "step": 9917 + }, + { + "epoch": 1.27, + "learning_rate": 3.1085091236014808e-06, + "loss": 0.1467, + "step": 9918 + }, + { + "epoch": 1.27, + "learning_rate": 3.1075497048582635e-06, + "loss": 0.1461, + "step": 9919 + }, + { + "epoch": 1.27, + "learning_rate": 3.1065903674378507e-06, + "loss": 0.1315, + "step": 9920 + }, + { + "epoch": 1.27, + "learning_rate": 3.1056311113814675e-06, + "loss": 0.1245, + "step": 9921 + }, + { + "epoch": 1.27, + "learning_rate": 3.1046719367303334e-06, + "loss": 0.1445, + "step": 9922 + }, + { + "epoch": 1.27, + "learning_rate": 3.1037128435256688e-06, + "loss": 0.1513, + "step": 9923 + }, + { + "epoch": 1.27, + "learning_rate": 3.102753831808685e-06, + "loss": 0.1427, + "step": 9924 + }, + { + "epoch": 1.27, + "learning_rate": 3.101794901620594e-06, + "loss": 0.1446, + "step": 9925 + }, + { + "epoch": 1.27, + "learning_rate": 3.1008360530026053e-06, + "loss": 0.1333, + "step": 9926 + }, + { + "epoch": 1.27, + "learning_rate": 3.099877285995921e-06, + "loss": 0.1456, + "step": 9927 + }, + { + "epoch": 1.27, + "learning_rate": 3.09891860064174e-06, + "loss": 0.1535, + "step": 9928 + }, + { + "epoch": 1.27, + "learning_rate": 3.097959996981263e-06, + "loss": 0.142, + "step": 9929 + }, + { + "epoch": 1.27, + "learning_rate": 3.0970014750556786e-06, + "loss": 0.1569, + "step": 9930 + }, + { + "epoch": 1.27, + "learning_rate": 3.0960430349061797e-06, + "loss": 0.1579, + "step": 9931 + }, + { + "epoch": 1.27, + "learning_rate": 3.0950846765739518e-06, + "loss": 0.1561, + "step": 9932 + }, + { + "epoch": 1.27, + "learning_rate": 3.0941264001001796e-06, + "loss": 0.1453, + "step": 9933 + }, + { + "epoch": 1.27, + "learning_rate": 3.093168205526038e-06, + "loss": 0.14, + "step": 9934 + }, + { + "epoch": 1.27, + "learning_rate": 3.0922100928927062e-06, + "loss": 0.1487, + "step": 9935 + }, + { + "epoch": 1.27, + "learning_rate": 3.0912520622413573e-06, + "loss": 0.1477, + "step": 9936 + }, + { + "epoch": 1.27, + "learning_rate": 3.090294113613157e-06, + "loss": 0.1423, + "step": 9937 + }, + { + "epoch": 1.27, + "learning_rate": 3.0893362470492716e-06, + "loss": 0.1274, + "step": 9938 + }, + { + "epoch": 1.27, + "learning_rate": 3.0883784625908618e-06, + "loss": 0.1532, + "step": 9939 + }, + { + "epoch": 1.27, + "learning_rate": 3.0874207602790895e-06, + "loss": 0.153, + "step": 9940 + }, + { + "epoch": 1.27, + "learning_rate": 3.086463140155106e-06, + "loss": 0.1344, + "step": 9941 + }, + { + "epoch": 1.27, + "learning_rate": 3.085505602260061e-06, + "loss": 0.1405, + "step": 9942 + }, + { + "epoch": 1.27, + "learning_rate": 3.0845481466351047e-06, + "loss": 0.1348, + "step": 9943 + }, + { + "epoch": 1.27, + "learning_rate": 3.083590773321383e-06, + "loss": 0.1656, + "step": 9944 + }, + { + "epoch": 1.27, + "learning_rate": 3.082633482360032e-06, + "loss": 0.1416, + "step": 9945 + }, + { + "epoch": 1.27, + "learning_rate": 3.0816762737921896e-06, + "loss": 0.1397, + "step": 9946 + }, + { + "epoch": 1.27, + "learning_rate": 3.0807191476589926e-06, + "loss": 0.1324, + "step": 9947 + }, + { + "epoch": 1.27, + "learning_rate": 3.0797621040015656e-06, + "loss": 0.1664, + "step": 9948 + }, + { + "epoch": 1.27, + "learning_rate": 3.0788051428610377e-06, + "loss": 0.153, + "step": 9949 + }, + { + "epoch": 1.27, + "learning_rate": 3.077848264278533e-06, + "loss": 0.1496, + "step": 9950 + }, + { + "epoch": 1.27, + "learning_rate": 3.07689146829517e-06, + "loss": 0.1515, + "step": 9951 + }, + { + "epoch": 1.27, + "learning_rate": 3.0759347549520614e-06, + "loss": 0.1518, + "step": 9952 + }, + { + "epoch": 1.27, + "learning_rate": 3.074978124290322e-06, + "loss": 0.1313, + "step": 9953 + }, + { + "epoch": 1.27, + "learning_rate": 3.0740215763510617e-06, + "loss": 0.1501, + "step": 9954 + }, + { + "epoch": 1.27, + "learning_rate": 3.0730651111753824e-06, + "loss": 0.1511, + "step": 9955 + }, + { + "epoch": 1.27, + "learning_rate": 3.072108728804386e-06, + "loss": 0.1435, + "step": 9956 + }, + { + "epoch": 1.27, + "learning_rate": 3.0711524292791707e-06, + "loss": 0.1386, + "step": 9957 + }, + { + "epoch": 1.27, + "learning_rate": 3.0701962126408334e-06, + "loss": 0.1521, + "step": 9958 + }, + { + "epoch": 1.27, + "learning_rate": 3.069240078930461e-06, + "loss": 0.1467, + "step": 9959 + }, + { + "epoch": 1.27, + "learning_rate": 3.0682840281891433e-06, + "loss": 0.1439, + "step": 9960 + }, + { + "epoch": 1.28, + "learning_rate": 3.0673280604579623e-06, + "loss": 0.1582, + "step": 9961 + }, + { + "epoch": 1.28, + "learning_rate": 3.0663721757780006e-06, + "loss": 0.1502, + "step": 9962 + }, + { + "epoch": 1.28, + "learning_rate": 3.0654163741903315e-06, + "loss": 0.148, + "step": 9963 + }, + { + "epoch": 1.28, + "learning_rate": 3.0644606557360303e-06, + "loss": 0.1358, + "step": 9964 + }, + { + "epoch": 1.28, + "learning_rate": 3.0635050204561658e-06, + "loss": 0.1374, + "step": 9965 + }, + { + "epoch": 1.28, + "learning_rate": 3.0625494683918012e-06, + "loss": 0.1525, + "step": 9966 + }, + { + "epoch": 1.28, + "learning_rate": 3.0615939995840017e-06, + "loss": 0.1375, + "step": 9967 + }, + { + "epoch": 1.28, + "learning_rate": 3.0606386140738253e-06, + "loss": 0.1583, + "step": 9968 + }, + { + "epoch": 1.28, + "learning_rate": 3.0596833119023283e-06, + "loss": 0.1252, + "step": 9969 + }, + { + "epoch": 1.28, + "learning_rate": 3.058728093110559e-06, + "loss": 0.1652, + "step": 9970 + }, + { + "epoch": 1.28, + "learning_rate": 3.0577729577395663e-06, + "loss": 0.1406, + "step": 9971 + }, + { + "epoch": 1.28, + "learning_rate": 3.056817905830397e-06, + "loss": 0.1448, + "step": 9972 + }, + { + "epoch": 1.28, + "learning_rate": 3.055862937424089e-06, + "loss": 0.1397, + "step": 9973 + }, + { + "epoch": 1.28, + "learning_rate": 3.054908052561681e-06, + "loss": 0.1429, + "step": 9974 + }, + { + "epoch": 1.28, + "learning_rate": 3.053953251284205e-06, + "loss": 0.1446, + "step": 9975 + }, + { + "epoch": 1.28, + "learning_rate": 3.0529985336326933e-06, + "loss": 0.1396, + "step": 9976 + }, + { + "epoch": 1.28, + "learning_rate": 3.0520438996481694e-06, + "loss": 0.1556, + "step": 9977 + }, + { + "epoch": 1.28, + "learning_rate": 3.0510893493716574e-06, + "loss": 0.1366, + "step": 9978 + }, + { + "epoch": 1.28, + "learning_rate": 3.0501348828441767e-06, + "loss": 0.1356, + "step": 9979 + }, + { + "epoch": 1.28, + "learning_rate": 3.0491805001067443e-06, + "loss": 0.1324, + "step": 9980 + }, + { + "epoch": 1.28, + "learning_rate": 3.048226201200369e-06, + "loss": 0.1604, + "step": 9981 + }, + { + "epoch": 1.28, + "learning_rate": 3.047271986166061e-06, + "loss": 0.143, + "step": 9982 + }, + { + "epoch": 1.28, + "learning_rate": 3.0463178550448246e-06, + "loss": 0.1343, + "step": 9983 + }, + { + "epoch": 1.28, + "learning_rate": 3.0453638078776614e-06, + "loss": 0.1357, + "step": 9984 + }, + { + "epoch": 1.28, + "learning_rate": 3.044409844705568e-06, + "loss": 0.137, + "step": 9985 + }, + { + "epoch": 1.28, + "learning_rate": 3.043455965569538e-06, + "loss": 0.1443, + "step": 9986 + }, + { + "epoch": 1.28, + "learning_rate": 3.042502170510565e-06, + "loss": 0.1554, + "step": 9987 + }, + { + "epoch": 1.28, + "learning_rate": 3.041548459569633e-06, + "loss": 0.1514, + "step": 9988 + }, + { + "epoch": 1.28, + "learning_rate": 3.0405948327877233e-06, + "loss": 0.1444, + "step": 9989 + }, + { + "epoch": 1.28, + "learning_rate": 3.039641290205818e-06, + "loss": 0.1506, + "step": 9990 + }, + { + "epoch": 1.28, + "learning_rate": 3.038687831864895e-06, + "loss": 0.1595, + "step": 9991 + }, + { + "epoch": 1.28, + "learning_rate": 3.037734457805922e-06, + "loss": 0.1563, + "step": 9992 + }, + { + "epoch": 1.28, + "learning_rate": 3.036781168069869e-06, + "loss": 0.1472, + "step": 9993 + }, + { + "epoch": 1.28, + "learning_rate": 3.0358279626977034e-06, + "loss": 0.1485, + "step": 9994 + }, + { + "epoch": 1.28, + "learning_rate": 3.0348748417303826e-06, + "loss": 0.1392, + "step": 9995 + }, + { + "epoch": 1.28, + "learning_rate": 3.033921805208867e-06, + "loss": 0.1422, + "step": 9996 + }, + { + "epoch": 1.28, + "learning_rate": 3.0329688531741097e-06, + "loss": 0.1421, + "step": 9997 + }, + { + "epoch": 1.28, + "learning_rate": 3.032015985667064e-06, + "loss": 0.1491, + "step": 9998 + }, + { + "epoch": 1.28, + "learning_rate": 3.0310632027286717e-06, + "loss": 0.1272, + "step": 9999 + }, + { + "epoch": 1.28, + "learning_rate": 3.030110504399879e-06, + "loss": 0.1588, + "step": 10000 + }, + { + "epoch": 1.28, + "learning_rate": 3.029157890721627e-06, + "loss": 0.1523, + "step": 10001 + }, + { + "epoch": 1.28, + "learning_rate": 3.0282053617348485e-06, + "loss": 0.143, + "step": 10002 + }, + { + "epoch": 1.28, + "learning_rate": 3.027252917480476e-06, + "loss": 0.1456, + "step": 10003 + }, + { + "epoch": 1.28, + "learning_rate": 3.026300557999439e-06, + "loss": 0.1476, + "step": 10004 + }, + { + "epoch": 1.28, + "learning_rate": 3.0253482833326654e-06, + "loss": 0.1296, + "step": 10005 + }, + { + "epoch": 1.28, + "learning_rate": 3.0243960935210726e-06, + "loss": 0.1366, + "step": 10006 + }, + { + "epoch": 1.28, + "learning_rate": 3.023443988605578e-06, + "loss": 0.1435, + "step": 10007 + }, + { + "epoch": 1.28, + "learning_rate": 3.0224919686270982e-06, + "loss": 0.1571, + "step": 10008 + }, + { + "epoch": 1.28, + "learning_rate": 3.021540033626544e-06, + "loss": 0.1395, + "step": 10009 + }, + { + "epoch": 1.28, + "learning_rate": 3.0205881836448186e-06, + "loss": 0.1498, + "step": 10010 + }, + { + "epoch": 1.28, + "learning_rate": 3.0196364187228287e-06, + "loss": 0.1315, + "step": 10011 + }, + { + "epoch": 1.28, + "learning_rate": 3.0186847389014738e-06, + "loss": 0.1261, + "step": 10012 + }, + { + "epoch": 1.28, + "learning_rate": 3.0177331442216455e-06, + "loss": 0.1485, + "step": 10013 + }, + { + "epoch": 1.28, + "learning_rate": 3.0167816347242396e-06, + "loss": 0.1393, + "step": 10014 + }, + { + "epoch": 1.28, + "learning_rate": 3.0158302104501435e-06, + "loss": 0.1377, + "step": 10015 + }, + { + "epoch": 1.28, + "learning_rate": 3.0148788714402444e-06, + "loss": 0.1405, + "step": 10016 + }, + { + "epoch": 1.28, + "learning_rate": 3.0139276177354188e-06, + "loss": 0.1438, + "step": 10017 + }, + { + "epoch": 1.28, + "learning_rate": 3.0129764493765466e-06, + "loss": 0.1488, + "step": 10018 + }, + { + "epoch": 1.28, + "learning_rate": 3.012025366404504e-06, + "loss": 0.1386, + "step": 10019 + }, + { + "epoch": 1.28, + "learning_rate": 3.0110743688601578e-06, + "loss": 0.1552, + "step": 10020 + }, + { + "epoch": 1.28, + "learning_rate": 3.0101234567843747e-06, + "loss": 0.1466, + "step": 10021 + }, + { + "epoch": 1.28, + "learning_rate": 3.009172630218018e-06, + "loss": 0.1371, + "step": 10022 + }, + { + "epoch": 1.28, + "learning_rate": 3.0082218892019487e-06, + "loss": 0.1488, + "step": 10023 + }, + { + "epoch": 1.28, + "learning_rate": 3.00727123377702e-06, + "loss": 0.1539, + "step": 10024 + }, + { + "epoch": 1.28, + "learning_rate": 3.0063206639840846e-06, + "loss": 0.1412, + "step": 10025 + }, + { + "epoch": 1.28, + "learning_rate": 3.00537017986399e-06, + "loss": 0.1472, + "step": 10026 + }, + { + "epoch": 1.28, + "learning_rate": 3.0044197814575825e-06, + "loss": 0.1628, + "step": 10027 + }, + { + "epoch": 1.28, + "learning_rate": 3.0034694688056998e-06, + "loss": 0.1503, + "step": 10028 + }, + { + "epoch": 1.28, + "learning_rate": 3.002519241949181e-06, + "loss": 0.1559, + "step": 10029 + }, + { + "epoch": 1.28, + "learning_rate": 3.0015691009288605e-06, + "loss": 0.1435, + "step": 10030 + }, + { + "epoch": 1.28, + "learning_rate": 3.0006190457855643e-06, + "loss": 0.1613, + "step": 10031 + }, + { + "epoch": 1.28, + "learning_rate": 2.99966907656012e-06, + "loss": 0.1532, + "step": 10032 + }, + { + "epoch": 1.28, + "learning_rate": 2.9987191932933523e-06, + "loss": 0.1437, + "step": 10033 + }, + { + "epoch": 1.28, + "learning_rate": 2.997769396026078e-06, + "loss": 0.1427, + "step": 10034 + }, + { + "epoch": 1.28, + "learning_rate": 2.9968196847991117e-06, + "loss": 0.1283, + "step": 10035 + }, + { + "epoch": 1.28, + "learning_rate": 2.995870059653263e-06, + "loss": 0.1409, + "step": 10036 + }, + { + "epoch": 1.28, + "learning_rate": 2.994920520629344e-06, + "loss": 0.1505, + "step": 10037 + }, + { + "epoch": 1.28, + "learning_rate": 2.9939710677681545e-06, + "loss": 0.1445, + "step": 10038 + }, + { + "epoch": 1.28, + "learning_rate": 2.9930217011104957e-06, + "loss": 0.1412, + "step": 10039 + }, + { + "epoch": 1.29, + "learning_rate": 2.992072420697164e-06, + "loss": 0.144, + "step": 10040 + }, + { + "epoch": 1.29, + "learning_rate": 2.991123226568954e-06, + "loss": 0.1391, + "step": 10041 + }, + { + "epoch": 1.29, + "learning_rate": 2.990174118766651e-06, + "loss": 0.158, + "step": 10042 + }, + { + "epoch": 1.29, + "learning_rate": 2.9892250973310433e-06, + "loss": 0.1439, + "step": 10043 + }, + { + "epoch": 1.29, + "learning_rate": 2.98827616230291e-06, + "loss": 0.1474, + "step": 10044 + }, + { + "epoch": 1.29, + "learning_rate": 2.987327313723033e-06, + "loss": 0.1452, + "step": 10045 + }, + { + "epoch": 1.29, + "learning_rate": 2.9863785516321806e-06, + "loss": 0.1566, + "step": 10046 + }, + { + "epoch": 1.29, + "learning_rate": 2.9854298760711285e-06, + "loss": 0.1429, + "step": 10047 + }, + { + "epoch": 1.29, + "learning_rate": 2.9844812870806417e-06, + "loss": 0.1352, + "step": 10048 + }, + { + "epoch": 1.29, + "learning_rate": 2.9835327847014816e-06, + "loss": 0.1488, + "step": 10049 + }, + { + "epoch": 1.29, + "learning_rate": 2.982584368974408e-06, + "loss": 0.1524, + "step": 10050 + }, + { + "epoch": 1.29, + "learning_rate": 2.9816360399401777e-06, + "loss": 0.1534, + "step": 10051 + }, + { + "epoch": 1.29, + "learning_rate": 2.980687797639543e-06, + "loss": 0.1654, + "step": 10052 + }, + { + "epoch": 1.29, + "learning_rate": 2.979739642113251e-06, + "loss": 0.149, + "step": 10053 + }, + { + "epoch": 1.29, + "learning_rate": 2.9787915734020446e-06, + "loss": 0.1445, + "step": 10054 + }, + { + "epoch": 1.29, + "learning_rate": 2.9778435915466674e-06, + "loss": 0.1388, + "step": 10055 + }, + { + "epoch": 1.29, + "learning_rate": 2.9768956965878526e-06, + "loss": 0.1405, + "step": 10056 + }, + { + "epoch": 1.29, + "learning_rate": 2.9759478885663362e-06, + "loss": 0.1351, + "step": 10057 + }, + { + "epoch": 1.29, + "learning_rate": 2.975000167522846e-06, + "loss": 0.1454, + "step": 10058 + }, + { + "epoch": 1.29, + "learning_rate": 2.9740525334981105e-06, + "loss": 0.131, + "step": 10059 + }, + { + "epoch": 1.29, + "learning_rate": 2.9731049865328486e-06, + "loss": 0.1419, + "step": 10060 + }, + { + "epoch": 1.29, + "learning_rate": 2.9721575266677783e-06, + "loss": 0.1485, + "step": 10061 + }, + { + "epoch": 1.29, + "learning_rate": 2.971210153943617e-06, + "loss": 0.1283, + "step": 10062 + }, + { + "epoch": 1.29, + "learning_rate": 2.970262868401075e-06, + "loss": 0.1533, + "step": 10063 + }, + { + "epoch": 1.29, + "learning_rate": 2.9693156700808556e-06, + "loss": 0.1476, + "step": 10064 + }, + { + "epoch": 1.29, + "learning_rate": 2.968368559023664e-06, + "loss": 0.1446, + "step": 10065 + }, + { + "epoch": 1.29, + "learning_rate": 2.967421535270203e-06, + "loss": 0.1505, + "step": 10066 + }, + { + "epoch": 1.29, + "learning_rate": 2.966474598861164e-06, + "loss": 0.127, + "step": 10067 + }, + { + "epoch": 1.29, + "learning_rate": 2.965527749837239e-06, + "loss": 0.1323, + "step": 10068 + }, + { + "epoch": 1.29, + "learning_rate": 2.9645809882391187e-06, + "loss": 0.1525, + "step": 10069 + }, + { + "epoch": 1.29, + "learning_rate": 2.9636343141074873e-06, + "loss": 0.1568, + "step": 10070 + }, + { + "epoch": 1.29, + "learning_rate": 2.962687727483024e-06, + "loss": 0.1437, + "step": 10071 + }, + { + "epoch": 1.29, + "learning_rate": 2.961741228406405e-06, + "loss": 0.1655, + "step": 10072 + }, + { + "epoch": 1.29, + "learning_rate": 2.9607948169183077e-06, + "loss": 0.1469, + "step": 10073 + }, + { + "epoch": 1.29, + "learning_rate": 2.959848493059396e-06, + "loss": 0.1693, + "step": 10074 + }, + { + "epoch": 1.29, + "learning_rate": 2.958902256870339e-06, + "loss": 0.1526, + "step": 10075 + }, + { + "epoch": 1.29, + "learning_rate": 2.9579561083917984e-06, + "loss": 0.156, + "step": 10076 + }, + { + "epoch": 1.29, + "learning_rate": 2.9570100476644325e-06, + "loss": 0.1608, + "step": 10077 + }, + { + "epoch": 1.29, + "learning_rate": 2.9560640747288925e-06, + "loss": 0.1427, + "step": 10078 + }, + { + "epoch": 1.29, + "learning_rate": 2.9551181896258317e-06, + "loss": 0.1442, + "step": 10079 + }, + { + "epoch": 1.29, + "learning_rate": 2.9541723923958975e-06, + "loss": 0.1574, + "step": 10080 + }, + { + "epoch": 1.29, + "learning_rate": 2.9532266830797336e-06, + "loss": 0.1449, + "step": 10081 + }, + { + "epoch": 1.29, + "learning_rate": 2.9522810617179742e-06, + "loss": 0.1297, + "step": 10082 + }, + { + "epoch": 1.29, + "learning_rate": 2.951335528351259e-06, + "loss": 0.1318, + "step": 10083 + }, + { + "epoch": 1.29, + "learning_rate": 2.9503900830202202e-06, + "loss": 0.1682, + "step": 10084 + }, + { + "epoch": 1.29, + "learning_rate": 2.9494447257654836e-06, + "loss": 0.1347, + "step": 10085 + }, + { + "epoch": 1.29, + "learning_rate": 2.948499456627674e-06, + "loss": 0.1284, + "step": 10086 + }, + { + "epoch": 1.29, + "learning_rate": 2.94755427564741e-06, + "loss": 0.1488, + "step": 10087 + }, + { + "epoch": 1.29, + "learning_rate": 2.9466091828653127e-06, + "loss": 0.1459, + "step": 10088 + }, + { + "epoch": 1.29, + "learning_rate": 2.9456641783219897e-06, + "loss": 0.1398, + "step": 10089 + }, + { + "epoch": 1.29, + "learning_rate": 2.9447192620580532e-06, + "loss": 0.1482, + "step": 10090 + }, + { + "epoch": 1.29, + "learning_rate": 2.9437744341141084e-06, + "loss": 0.126, + "step": 10091 + }, + { + "epoch": 1.29, + "learning_rate": 2.9428296945307533e-06, + "loss": 0.1438, + "step": 10092 + }, + { + "epoch": 1.29, + "learning_rate": 2.9418850433485877e-06, + "loss": 0.1696, + "step": 10093 + }, + { + "epoch": 1.29, + "learning_rate": 2.9409404806082077e-06, + "loss": 0.1441, + "step": 10094 + }, + { + "epoch": 1.29, + "learning_rate": 2.939996006350201e-06, + "loss": 0.1396, + "step": 10095 + }, + { + "epoch": 1.29, + "learning_rate": 2.939051620615152e-06, + "loss": 0.1384, + "step": 10096 + }, + { + "epoch": 1.29, + "learning_rate": 2.938107323443645e-06, + "loss": 0.1535, + "step": 10097 + }, + { + "epoch": 1.29, + "learning_rate": 2.9371631148762592e-06, + "loss": 0.1487, + "step": 10098 + }, + { + "epoch": 1.29, + "learning_rate": 2.936218994953568e-06, + "loss": 0.1572, + "step": 10099 + }, + { + "epoch": 1.29, + "learning_rate": 2.935274963716144e-06, + "loss": 0.1307, + "step": 10100 + }, + { + "epoch": 1.29, + "learning_rate": 2.934331021204551e-06, + "loss": 0.1396, + "step": 10101 + }, + { + "epoch": 1.29, + "learning_rate": 2.9333871674593573e-06, + "loss": 0.1268, + "step": 10102 + }, + { + "epoch": 1.29, + "learning_rate": 2.9324434025211173e-06, + "loss": 0.1558, + "step": 10103 + }, + { + "epoch": 1.29, + "learning_rate": 2.93149972643039e-06, + "loss": 0.1405, + "step": 10104 + }, + { + "epoch": 1.29, + "learning_rate": 2.930556139227726e-06, + "loss": 0.1488, + "step": 10105 + }, + { + "epoch": 1.29, + "learning_rate": 2.929612640953675e-06, + "loss": 0.1447, + "step": 10106 + }, + { + "epoch": 1.29, + "learning_rate": 2.9286692316487776e-06, + "loss": 0.144, + "step": 10107 + }, + { + "epoch": 1.29, + "learning_rate": 2.9277259113535774e-06, + "loss": 0.1367, + "step": 10108 + }, + { + "epoch": 1.29, + "learning_rate": 2.9267826801086103e-06, + "loss": 0.1414, + "step": 10109 + }, + { + "epoch": 1.29, + "learning_rate": 2.9258395379544085e-06, + "loss": 0.1503, + "step": 10110 + }, + { + "epoch": 1.29, + "learning_rate": 2.9248964849315004e-06, + "loss": 0.1593, + "step": 10111 + }, + { + "epoch": 1.29, + "learning_rate": 2.9239535210804115e-06, + "loss": 0.1428, + "step": 10112 + }, + { + "epoch": 1.29, + "learning_rate": 2.923010646441666e-06, + "loss": 0.1308, + "step": 10113 + }, + { + "epoch": 1.29, + "learning_rate": 2.9220678610557773e-06, + "loss": 0.1539, + "step": 10114 + }, + { + "epoch": 1.29, + "learning_rate": 2.9211251649632587e-06, + "loss": 0.1581, + "step": 10115 + }, + { + "epoch": 1.29, + "learning_rate": 2.920182558204623e-06, + "loss": 0.1231, + "step": 10116 + }, + { + "epoch": 1.29, + "learning_rate": 2.919240040820376e-06, + "loss": 0.141, + "step": 10117 + }, + { + "epoch": 1.3, + "learning_rate": 2.9182976128510177e-06, + "loss": 0.1325, + "step": 10118 + }, + { + "epoch": 1.3, + "learning_rate": 2.9173552743370454e-06, + "loss": 0.1478, + "step": 10119 + }, + { + "epoch": 1.3, + "learning_rate": 2.9164130253189594e-06, + "loss": 0.1535, + "step": 10120 + }, + { + "epoch": 1.3, + "learning_rate": 2.9154708658372433e-06, + "loss": 0.1388, + "step": 10121 + }, + { + "epoch": 1.3, + "learning_rate": 2.9145287959323852e-06, + "loss": 0.1562, + "step": 10122 + }, + { + "epoch": 1.3, + "learning_rate": 2.913586815644871e-06, + "loss": 0.14, + "step": 10123 + }, + { + "epoch": 1.3, + "learning_rate": 2.912644925015179e-06, + "loss": 0.1224, + "step": 10124 + }, + { + "epoch": 1.3, + "learning_rate": 2.9117031240837825e-06, + "loss": 0.1439, + "step": 10125 + }, + { + "epoch": 1.3, + "learning_rate": 2.910761412891153e-06, + "loss": 0.1548, + "step": 10126 + }, + { + "epoch": 1.3, + "learning_rate": 2.9098197914777575e-06, + "loss": 0.1339, + "step": 10127 + }, + { + "epoch": 1.3, + "learning_rate": 2.9088782598840646e-06, + "loss": 0.1636, + "step": 10128 + }, + { + "epoch": 1.3, + "learning_rate": 2.9079368181505263e-06, + "loss": 0.1273, + "step": 10129 + }, + { + "epoch": 1.3, + "learning_rate": 2.9069954663176036e-06, + "loss": 0.1287, + "step": 10130 + }, + { + "epoch": 1.3, + "learning_rate": 2.9060542044257487e-06, + "loss": 0.1482, + "step": 10131 + }, + { + "epoch": 1.3, + "learning_rate": 2.9051130325154053e-06, + "loss": 0.1381, + "step": 10132 + }, + { + "epoch": 1.3, + "learning_rate": 2.904171950627022e-06, + "loss": 0.1289, + "step": 10133 + }, + { + "epoch": 1.3, + "learning_rate": 2.9032309588010372e-06, + "loss": 0.1354, + "step": 10134 + }, + { + "epoch": 1.3, + "learning_rate": 2.9022900570778876e-06, + "loss": 0.1498, + "step": 10135 + }, + { + "epoch": 1.3, + "learning_rate": 2.9013492454980074e-06, + "loss": 0.1345, + "step": 10136 + }, + { + "epoch": 1.3, + "learning_rate": 2.9004085241018208e-06, + "loss": 0.1376, + "step": 10137 + }, + { + "epoch": 1.3, + "learning_rate": 2.899467892929761e-06, + "loss": 0.1418, + "step": 10138 + }, + { + "epoch": 1.3, + "learning_rate": 2.8985273520222414e-06, + "loss": 0.1463, + "step": 10139 + }, + { + "epoch": 1.3, + "learning_rate": 2.8975869014196797e-06, + "loss": 0.149, + "step": 10140 + }, + { + "epoch": 1.3, + "learning_rate": 2.896646541162493e-06, + "loss": 0.1711, + "step": 10141 + }, + { + "epoch": 1.3, + "learning_rate": 2.895706271291089e-06, + "loss": 0.1438, + "step": 10142 + }, + { + "epoch": 1.3, + "learning_rate": 2.894766091845873e-06, + "loss": 0.1522, + "step": 10143 + }, + { + "epoch": 1.3, + "learning_rate": 2.893826002867247e-06, + "loss": 0.1305, + "step": 10144 + }, + { + "epoch": 1.3, + "learning_rate": 2.8928860043956062e-06, + "loss": 0.1502, + "step": 10145 + }, + { + "epoch": 1.3, + "learning_rate": 2.8919460964713507e-06, + "loss": 0.1611, + "step": 10146 + }, + { + "epoch": 1.3, + "learning_rate": 2.891006279134862e-06, + "loss": 0.1399, + "step": 10147 + }, + { + "epoch": 1.3, + "learning_rate": 2.8900665524265326e-06, + "loss": 0.1371, + "step": 10148 + }, + { + "epoch": 1.3, + "learning_rate": 2.889126916386744e-06, + "loss": 0.1378, + "step": 10149 + }, + { + "epoch": 1.3, + "learning_rate": 2.88818737105587e-06, + "loss": 0.1371, + "step": 10150 + }, + { + "epoch": 1.3, + "learning_rate": 2.8872479164742896e-06, + "loss": 0.1345, + "step": 10151 + }, + { + "epoch": 1.3, + "learning_rate": 2.886308552682371e-06, + "loss": 0.123, + "step": 10152 + }, + { + "epoch": 1.3, + "learning_rate": 2.885369279720482e-06, + "loss": 0.1382, + "step": 10153 + }, + { + "epoch": 1.3, + "learning_rate": 2.884430097628984e-06, + "loss": 0.1362, + "step": 10154 + }, + { + "epoch": 1.3, + "learning_rate": 2.883491006448235e-06, + "loss": 0.1327, + "step": 10155 + }, + { + "epoch": 1.3, + "learning_rate": 2.8825520062185945e-06, + "loss": 0.1375, + "step": 10156 + }, + { + "epoch": 1.3, + "learning_rate": 2.881613096980407e-06, + "loss": 0.1443, + "step": 10157 + }, + { + "epoch": 1.3, + "learning_rate": 2.8806742787740237e-06, + "loss": 0.1474, + "step": 10158 + }, + { + "epoch": 1.3, + "learning_rate": 2.879735551639787e-06, + "loss": 0.1402, + "step": 10159 + }, + { + "epoch": 1.3, + "learning_rate": 2.8787969156180353e-06, + "loss": 0.1362, + "step": 10160 + }, + { + "epoch": 1.3, + "learning_rate": 2.877858370749105e-06, + "loss": 0.1547, + "step": 10161 + }, + { + "epoch": 1.3, + "learning_rate": 2.8769199170733265e-06, + "loss": 0.1273, + "step": 10162 + }, + { + "epoch": 1.3, + "learning_rate": 2.8759815546310254e-06, + "loss": 0.1507, + "step": 10163 + }, + { + "epoch": 1.3, + "learning_rate": 2.8750432834625312e-06, + "loss": 0.1348, + "step": 10164 + }, + { + "epoch": 1.3, + "learning_rate": 2.874105103608156e-06, + "loss": 0.1401, + "step": 10165 + }, + { + "epoch": 1.3, + "learning_rate": 2.8731670151082213e-06, + "loss": 0.1508, + "step": 10166 + }, + { + "epoch": 1.3, + "learning_rate": 2.872229018003036e-06, + "loss": 0.1385, + "step": 10167 + }, + { + "epoch": 1.3, + "learning_rate": 2.871291112332909e-06, + "loss": 0.1353, + "step": 10168 + }, + { + "epoch": 1.3, + "learning_rate": 2.8703532981381437e-06, + "loss": 0.1409, + "step": 10169 + }, + { + "epoch": 1.3, + "learning_rate": 2.869415575459038e-06, + "loss": 0.1419, + "step": 10170 + }, + { + "epoch": 1.3, + "learning_rate": 2.8684779443358945e-06, + "loss": 0.1567, + "step": 10171 + }, + { + "epoch": 1.3, + "learning_rate": 2.8675404048089987e-06, + "loss": 0.1378, + "step": 10172 + }, + { + "epoch": 1.3, + "learning_rate": 2.8666029569186393e-06, + "loss": 0.1492, + "step": 10173 + }, + { + "epoch": 1.3, + "learning_rate": 2.8656656007051055e-06, + "loss": 0.145, + "step": 10174 + }, + { + "epoch": 1.3, + "learning_rate": 2.864728336208671e-06, + "loss": 0.1456, + "step": 10175 + }, + { + "epoch": 1.3, + "learning_rate": 2.8637911634696165e-06, + "loss": 0.1357, + "step": 10176 + }, + { + "epoch": 1.3, + "learning_rate": 2.862854082528214e-06, + "loss": 0.1546, + "step": 10177 + }, + { + "epoch": 1.3, + "learning_rate": 2.861917093424731e-06, + "loss": 0.1442, + "step": 10178 + }, + { + "epoch": 1.3, + "learning_rate": 2.860980196199432e-06, + "loss": 0.1308, + "step": 10179 + }, + { + "epoch": 1.3, + "learning_rate": 2.8600433908925764e-06, + "loss": 0.1407, + "step": 10180 + }, + { + "epoch": 1.3, + "learning_rate": 2.859106677544424e-06, + "loss": 0.1348, + "step": 10181 + }, + { + "epoch": 1.3, + "learning_rate": 2.8581700561952274e-06, + "loss": 0.1472, + "step": 10182 + }, + { + "epoch": 1.3, + "learning_rate": 2.8572335268852297e-06, + "loss": 0.1526, + "step": 10183 + }, + { + "epoch": 1.3, + "learning_rate": 2.8562970896546815e-06, + "loss": 0.1445, + "step": 10184 + }, + { + "epoch": 1.3, + "learning_rate": 2.855360744543822e-06, + "loss": 0.1495, + "step": 10185 + }, + { + "epoch": 1.3, + "learning_rate": 2.8544244915928876e-06, + "loss": 0.1507, + "step": 10186 + }, + { + "epoch": 1.3, + "learning_rate": 2.8534883308421114e-06, + "loss": 0.1411, + "step": 10187 + }, + { + "epoch": 1.3, + "learning_rate": 2.852552262331719e-06, + "loss": 0.1376, + "step": 10188 + }, + { + "epoch": 1.3, + "learning_rate": 2.8516162861019437e-06, + "loss": 0.1479, + "step": 10189 + }, + { + "epoch": 1.3, + "learning_rate": 2.850680402192999e-06, + "loss": 0.1375, + "step": 10190 + }, + { + "epoch": 1.3, + "learning_rate": 2.8497446106451022e-06, + "loss": 0.1458, + "step": 10191 + }, + { + "epoch": 1.3, + "learning_rate": 2.8488089114984725e-06, + "loss": 0.1494, + "step": 10192 + }, + { + "epoch": 1.3, + "learning_rate": 2.8478733047933103e-06, + "loss": 0.1591, + "step": 10193 + }, + { + "epoch": 1.3, + "learning_rate": 2.846937790569828e-06, + "loss": 0.1374, + "step": 10194 + }, + { + "epoch": 1.3, + "learning_rate": 2.8460023688682237e-06, + "loss": 0.1396, + "step": 10195 + }, + { + "epoch": 1.31, + "learning_rate": 2.8450670397286945e-06, + "loss": 0.1312, + "step": 10196 + }, + { + "epoch": 1.31, + "learning_rate": 2.8441318031914344e-06, + "loss": 0.1483, + "step": 10197 + }, + { + "epoch": 1.31, + "learning_rate": 2.8431966592966297e-06, + "loss": 0.1532, + "step": 10198 + }, + { + "epoch": 1.31, + "learning_rate": 2.84226160808447e-06, + "loss": 0.1557, + "step": 10199 + }, + { + "epoch": 1.31, + "learning_rate": 2.8413266495951366e-06, + "loss": 0.131, + "step": 10200 + }, + { + "epoch": 1.31, + "learning_rate": 2.8403917838688007e-06, + "loss": 0.1497, + "step": 10201 + }, + { + "epoch": 1.31, + "learning_rate": 2.8394570109456413e-06, + "loss": 0.1307, + "step": 10202 + }, + { + "epoch": 1.31, + "learning_rate": 2.838522330865826e-06, + "loss": 0.1458, + "step": 10203 + }, + { + "epoch": 1.31, + "learning_rate": 2.837587743669521e-06, + "loss": 0.1446, + "step": 10204 + }, + { + "epoch": 1.31, + "learning_rate": 2.8366532493968858e-06, + "loss": 0.1413, + "step": 10205 + }, + { + "epoch": 1.31, + "learning_rate": 2.835718848088076e-06, + "loss": 0.1497, + "step": 10206 + }, + { + "epoch": 1.31, + "learning_rate": 2.8347845397832517e-06, + "loss": 0.1346, + "step": 10207 + }, + { + "epoch": 1.31, + "learning_rate": 2.8338503245225544e-06, + "loss": 0.1389, + "step": 10208 + }, + { + "epoch": 1.31, + "learning_rate": 2.8329162023461355e-06, + "loss": 0.1443, + "step": 10209 + }, + { + "epoch": 1.31, + "learning_rate": 2.8319821732941345e-06, + "loss": 0.145, + "step": 10210 + }, + { + "epoch": 1.31, + "learning_rate": 2.8310482374066843e-06, + "loss": 0.158, + "step": 10211 + }, + { + "epoch": 1.31, + "learning_rate": 2.830114394723924e-06, + "loss": 0.1443, + "step": 10212 + }, + { + "epoch": 1.31, + "learning_rate": 2.8291806452859803e-06, + "loss": 0.1325, + "step": 10213 + }, + { + "epoch": 1.31, + "learning_rate": 2.82824698913298e-06, + "loss": 0.1545, + "step": 10214 + }, + { + "epoch": 1.31, + "learning_rate": 2.827313426305042e-06, + "loss": 0.1322, + "step": 10215 + }, + { + "epoch": 1.31, + "learning_rate": 2.826379956842284e-06, + "loss": 0.1561, + "step": 10216 + }, + { + "epoch": 1.31, + "learning_rate": 2.825446580784822e-06, + "loss": 0.149, + "step": 10217 + }, + { + "epoch": 1.31, + "learning_rate": 2.824513298172763e-06, + "loss": 0.1418, + "step": 10218 + }, + { + "epoch": 1.31, + "learning_rate": 2.823580109046212e-06, + "loss": 0.1428, + "step": 10219 + }, + { + "epoch": 1.31, + "learning_rate": 2.822647013445272e-06, + "loss": 0.1478, + "step": 10220 + }, + { + "epoch": 1.31, + "learning_rate": 2.821714011410039e-06, + "loss": 0.1304, + "step": 10221 + }, + { + "epoch": 1.31, + "learning_rate": 2.820781102980606e-06, + "loss": 0.1384, + "step": 10222 + }, + { + "epoch": 1.31, + "learning_rate": 2.8198482881970626e-06, + "loss": 0.1305, + "step": 10223 + }, + { + "epoch": 1.31, + "learning_rate": 2.8189155670994913e-06, + "loss": 0.1254, + "step": 10224 + }, + { + "epoch": 1.31, + "learning_rate": 2.8179829397279795e-06, + "loss": 0.1395, + "step": 10225 + }, + { + "epoch": 1.31, + "learning_rate": 2.8170504061225966e-06, + "loss": 0.1584, + "step": 10226 + }, + { + "epoch": 1.31, + "learning_rate": 2.8161179663234215e-06, + "loss": 0.1347, + "step": 10227 + }, + { + "epoch": 1.31, + "learning_rate": 2.8151856203705215e-06, + "loss": 0.119, + "step": 10228 + }, + { + "epoch": 1.31, + "learning_rate": 2.814253368303961e-06, + "loss": 0.1513, + "step": 10229 + }, + { + "epoch": 1.31, + "learning_rate": 2.813321210163801e-06, + "loss": 0.1482, + "step": 10230 + }, + { + "epoch": 1.31, + "learning_rate": 2.8123891459900967e-06, + "loss": 0.1415, + "step": 10231 + }, + { + "epoch": 1.31, + "learning_rate": 2.8114571758229064e-06, + "loss": 0.1468, + "step": 10232 + }, + { + "epoch": 1.31, + "learning_rate": 2.8105252997022737e-06, + "loss": 0.1564, + "step": 10233 + }, + { + "epoch": 1.31, + "learning_rate": 2.809593517668243e-06, + "loss": 0.1256, + "step": 10234 + }, + { + "epoch": 1.31, + "learning_rate": 2.80866182976086e-06, + "loss": 0.1337, + "step": 10235 + }, + { + "epoch": 1.31, + "learning_rate": 2.8077302360201575e-06, + "loss": 0.1347, + "step": 10236 + }, + { + "epoch": 1.31, + "learning_rate": 2.80679873648617e-06, + "loss": 0.1491, + "step": 10237 + }, + { + "epoch": 1.31, + "learning_rate": 2.8058673311989247e-06, + "loss": 0.1386, + "step": 10238 + }, + { + "epoch": 1.31, + "learning_rate": 2.804936020198447e-06, + "loss": 0.1496, + "step": 10239 + }, + { + "epoch": 1.31, + "learning_rate": 2.8040048035247576e-06, + "loss": 0.1383, + "step": 10240 + }, + { + "epoch": 1.31, + "learning_rate": 2.8030736812178717e-06, + "loss": 0.1418, + "step": 10241 + }, + { + "epoch": 1.31, + "learning_rate": 2.8021426533178007e-06, + "loss": 0.1684, + "step": 10242 + }, + { + "epoch": 1.31, + "learning_rate": 2.8012117198645596e-06, + "loss": 0.1409, + "step": 10243 + }, + { + "epoch": 1.31, + "learning_rate": 2.800280880898143e-06, + "loss": 0.1395, + "step": 10244 + }, + { + "epoch": 1.31, + "learning_rate": 2.7993501364585584e-06, + "loss": 0.1499, + "step": 10245 + }, + { + "epoch": 1.31, + "learning_rate": 2.7984194865857994e-06, + "loss": 0.1439, + "step": 10246 + }, + { + "epoch": 1.31, + "learning_rate": 2.7974889313198584e-06, + "loss": 0.1506, + "step": 10247 + }, + { + "epoch": 1.31, + "learning_rate": 2.796558470700723e-06, + "loss": 0.1548, + "step": 10248 + }, + { + "epoch": 1.31, + "learning_rate": 2.795628104768376e-06, + "loss": 0.1405, + "step": 10249 + }, + { + "epoch": 1.31, + "learning_rate": 2.7946978335628023e-06, + "loss": 0.1439, + "step": 10250 + }, + { + "epoch": 1.31, + "learning_rate": 2.793767657123972e-06, + "loss": 0.1324, + "step": 10251 + }, + { + "epoch": 1.31, + "learning_rate": 2.792837575491857e-06, + "loss": 0.1523, + "step": 10252 + }, + { + "epoch": 1.31, + "learning_rate": 2.7919075887064296e-06, + "loss": 0.1437, + "step": 10253 + }, + { + "epoch": 1.31, + "learning_rate": 2.79097769680765e-06, + "loss": 0.1527, + "step": 10254 + }, + { + "epoch": 1.31, + "learning_rate": 2.790047899835479e-06, + "loss": 0.1536, + "step": 10255 + }, + { + "epoch": 1.31, + "learning_rate": 2.789118197829872e-06, + "loss": 0.1418, + "step": 10256 + }, + { + "epoch": 1.31, + "learning_rate": 2.7881885908307794e-06, + "loss": 0.1446, + "step": 10257 + }, + { + "epoch": 1.31, + "learning_rate": 2.7872590788781483e-06, + "loss": 0.1384, + "step": 10258 + }, + { + "epoch": 1.31, + "learning_rate": 2.7863296620119217e-06, + "loss": 0.1414, + "step": 10259 + }, + { + "epoch": 1.31, + "learning_rate": 2.7854003402720416e-06, + "loss": 0.1411, + "step": 10260 + }, + { + "epoch": 1.31, + "learning_rate": 2.7844711136984425e-06, + "loss": 0.1418, + "step": 10261 + }, + { + "epoch": 1.31, + "learning_rate": 2.7835419823310507e-06, + "loss": 0.136, + "step": 10262 + }, + { + "epoch": 1.31, + "learning_rate": 2.7826129462097974e-06, + "loss": 0.135, + "step": 10263 + }, + { + "epoch": 1.31, + "learning_rate": 2.781684005374604e-06, + "loss": 0.1384, + "step": 10264 + }, + { + "epoch": 1.31, + "learning_rate": 2.7807551598653905e-06, + "loss": 0.1437, + "step": 10265 + }, + { + "epoch": 1.31, + "learning_rate": 2.7798264097220694e-06, + "loss": 0.1428, + "step": 10266 + }, + { + "epoch": 1.31, + "learning_rate": 2.7788977549845503e-06, + "loss": 0.1411, + "step": 10267 + }, + { + "epoch": 1.31, + "learning_rate": 2.777969195692745e-06, + "loss": 0.1566, + "step": 10268 + }, + { + "epoch": 1.31, + "learning_rate": 2.777040731886549e-06, + "loss": 0.1349, + "step": 10269 + }, + { + "epoch": 1.31, + "learning_rate": 2.7761123636058645e-06, + "loss": 0.1614, + "step": 10270 + }, + { + "epoch": 1.31, + "learning_rate": 2.775184090890585e-06, + "loss": 0.1278, + "step": 10271 + }, + { + "epoch": 1.31, + "learning_rate": 2.7742559137806e-06, + "loss": 0.1479, + "step": 10272 + }, + { + "epoch": 1.31, + "learning_rate": 2.773327832315796e-06, + "loss": 0.1472, + "step": 10273 + }, + { + "epoch": 1.32, + "learning_rate": 2.7723998465360537e-06, + "loss": 0.154, + "step": 10274 + }, + { + "epoch": 1.32, + "learning_rate": 2.771471956481251e-06, + "loss": 0.1525, + "step": 10275 + }, + { + "epoch": 1.32, + "learning_rate": 2.770544162191261e-06, + "loss": 0.1338, + "step": 10276 + }, + { + "epoch": 1.32, + "learning_rate": 2.7696164637059527e-06, + "loss": 0.1553, + "step": 10277 + }, + { + "epoch": 1.32, + "learning_rate": 2.7686888610651936e-06, + "loss": 0.1671, + "step": 10278 + }, + { + "epoch": 1.32, + "learning_rate": 2.7677613543088432e-06, + "loss": 0.1388, + "step": 10279 + }, + { + "epoch": 1.32, + "learning_rate": 2.76683394347676e-06, + "loss": 0.1481, + "step": 10280 + }, + { + "epoch": 1.32, + "learning_rate": 2.7659066286087947e-06, + "loss": 0.1393, + "step": 10281 + }, + { + "epoch": 1.32, + "learning_rate": 2.7649794097447956e-06, + "loss": 0.152, + "step": 10282 + }, + { + "epoch": 1.32, + "learning_rate": 2.7640522869246134e-06, + "loss": 0.1412, + "step": 10283 + }, + { + "epoch": 1.32, + "learning_rate": 2.7631252601880816e-06, + "loss": 0.1371, + "step": 10284 + }, + { + "epoch": 1.32, + "learning_rate": 2.762198329575037e-06, + "loss": 0.1259, + "step": 10285 + }, + { + "epoch": 1.32, + "learning_rate": 2.7612714951253183e-06, + "loss": 0.1357, + "step": 10286 + }, + { + "epoch": 1.32, + "learning_rate": 2.7603447568787456e-06, + "loss": 0.1414, + "step": 10287 + }, + { + "epoch": 1.32, + "learning_rate": 2.759418114875148e-06, + "loss": 0.1258, + "step": 10288 + }, + { + "epoch": 1.32, + "learning_rate": 2.7584915691543444e-06, + "loss": 0.1328, + "step": 10289 + }, + { + "epoch": 1.32, + "learning_rate": 2.7575651197561504e-06, + "loss": 0.1563, + "step": 10290 + }, + { + "epoch": 1.32, + "learning_rate": 2.7566387667203776e-06, + "loss": 0.1476, + "step": 10291 + }, + { + "epoch": 1.32, + "learning_rate": 2.7557125100868327e-06, + "loss": 0.1387, + "step": 10292 + }, + { + "epoch": 1.32, + "learning_rate": 2.75478634989532e-06, + "loss": 0.1403, + "step": 10293 + }, + { + "epoch": 1.32, + "learning_rate": 2.753860286185637e-06, + "loss": 0.1313, + "step": 10294 + }, + { + "epoch": 1.32, + "learning_rate": 2.7529343189975788e-06, + "loss": 0.1327, + "step": 10295 + }, + { + "epoch": 1.32, + "learning_rate": 2.7520084483709397e-06, + "loss": 0.1445, + "step": 10296 + }, + { + "epoch": 1.32, + "learning_rate": 2.7510826743455037e-06, + "loss": 0.1413, + "step": 10297 + }, + { + "epoch": 1.32, + "learning_rate": 2.7501569969610544e-06, + "loss": 0.129, + "step": 10298 + }, + { + "epoch": 1.32, + "learning_rate": 2.7492314162573687e-06, + "loss": 0.1443, + "step": 10299 + }, + { + "epoch": 1.32, + "learning_rate": 2.74830593227422e-06, + "loss": 0.1475, + "step": 10300 + }, + { + "epoch": 1.32, + "learning_rate": 2.7473805450513846e-06, + "loss": 0.147, + "step": 10301 + }, + { + "epoch": 1.32, + "learning_rate": 2.7464552546286217e-06, + "loss": 0.1593, + "step": 10302 + }, + { + "epoch": 1.32, + "learning_rate": 2.7455300610456935e-06, + "loss": 0.1391, + "step": 10303 + }, + { + "epoch": 1.32, + "learning_rate": 2.744604964342364e-06, + "loss": 0.1378, + "step": 10304 + }, + { + "epoch": 1.32, + "learning_rate": 2.743679964558378e-06, + "loss": 0.1348, + "step": 10305 + }, + { + "epoch": 1.32, + "learning_rate": 2.7427550617334905e-06, + "loss": 0.1329, + "step": 10306 + }, + { + "epoch": 1.32, + "learning_rate": 2.741830255907445e-06, + "loss": 0.1418, + "step": 10307 + }, + { + "epoch": 1.32, + "learning_rate": 2.740905547119983e-06, + "loss": 0.1464, + "step": 10308 + }, + { + "epoch": 1.32, + "learning_rate": 2.7399809354108415e-06, + "loss": 0.1263, + "step": 10309 + }, + { + "epoch": 1.32, + "learning_rate": 2.73905642081975e-06, + "loss": 0.1421, + "step": 10310 + }, + { + "epoch": 1.32, + "learning_rate": 2.7381320033864434e-06, + "loss": 0.1485, + "step": 10311 + }, + { + "epoch": 1.32, + "learning_rate": 2.73720768315064e-06, + "loss": 0.139, + "step": 10312 + }, + { + "epoch": 1.32, + "learning_rate": 2.7362834601520603e-06, + "loss": 0.1348, + "step": 10313 + }, + { + "epoch": 1.32, + "learning_rate": 2.735359334430424e-06, + "loss": 0.1404, + "step": 10314 + }, + { + "epoch": 1.32, + "learning_rate": 2.73443530602544e-06, + "loss": 0.1489, + "step": 10315 + }, + { + "epoch": 1.32, + "learning_rate": 2.733511374976817e-06, + "loss": 0.1414, + "step": 10316 + }, + { + "epoch": 1.32, + "learning_rate": 2.7325875413242585e-06, + "loss": 0.1541, + "step": 10317 + }, + { + "epoch": 1.32, + "learning_rate": 2.7316638051074605e-06, + "loss": 0.13, + "step": 10318 + }, + { + "epoch": 1.32, + "learning_rate": 2.7307401663661247e-06, + "loss": 0.127, + "step": 10319 + }, + { + "epoch": 1.32, + "learning_rate": 2.729816625139934e-06, + "loss": 0.1388, + "step": 10320 + }, + { + "epoch": 1.32, + "learning_rate": 2.728893181468581e-06, + "loss": 0.1486, + "step": 10321 + }, + { + "epoch": 1.32, + "learning_rate": 2.7279698353917476e-06, + "loss": 0.1488, + "step": 10322 + }, + { + "epoch": 1.32, + "learning_rate": 2.727046586949107e-06, + "loss": 0.1441, + "step": 10323 + }, + { + "epoch": 1.32, + "learning_rate": 2.7261234361803383e-06, + "loss": 0.1563, + "step": 10324 + }, + { + "epoch": 1.32, + "learning_rate": 2.72520038312511e-06, + "loss": 0.1487, + "step": 10325 + }, + { + "epoch": 1.32, + "learning_rate": 2.7242774278230876e-06, + "loss": 0.1492, + "step": 10326 + }, + { + "epoch": 1.32, + "learning_rate": 2.723354570313932e-06, + "loss": 0.135, + "step": 10327 + }, + { + "epoch": 1.32, + "learning_rate": 2.7224318106372995e-06, + "loss": 0.1578, + "step": 10328 + }, + { + "epoch": 1.32, + "learning_rate": 2.721509148832847e-06, + "loss": 0.1329, + "step": 10329 + }, + { + "epoch": 1.32, + "learning_rate": 2.7205865849402187e-06, + "loss": 0.1456, + "step": 10330 + }, + { + "epoch": 1.32, + "learning_rate": 2.7196641189990623e-06, + "loss": 0.1464, + "step": 10331 + }, + { + "epoch": 1.32, + "learning_rate": 2.7187417510490176e-06, + "loss": 0.1443, + "step": 10332 + }, + { + "epoch": 1.32, + "learning_rate": 2.7178194811297204e-06, + "loss": 0.1509, + "step": 10333 + }, + { + "epoch": 1.32, + "learning_rate": 2.7168973092808025e-06, + "loss": 0.1493, + "step": 10334 + }, + { + "epoch": 1.32, + "learning_rate": 2.7159752355418927e-06, + "loss": 0.1487, + "step": 10335 + }, + { + "epoch": 1.32, + "learning_rate": 2.7150532599526114e-06, + "loss": 0.1434, + "step": 10336 + }, + { + "epoch": 1.32, + "learning_rate": 2.7141313825525845e-06, + "loss": 0.1507, + "step": 10337 + }, + { + "epoch": 1.32, + "learning_rate": 2.7132096033814193e-06, + "loss": 0.1519, + "step": 10338 + }, + { + "epoch": 1.32, + "learning_rate": 2.7122879224787315e-06, + "loss": 0.1391, + "step": 10339 + }, + { + "epoch": 1.32, + "learning_rate": 2.7113663398841296e-06, + "loss": 0.1346, + "step": 10340 + }, + { + "epoch": 1.32, + "learning_rate": 2.7104448556372086e-06, + "loss": 0.129, + "step": 10341 + }, + { + "epoch": 1.32, + "learning_rate": 2.709523469777573e-06, + "loss": 0.1423, + "step": 10342 + }, + { + "epoch": 1.32, + "learning_rate": 2.7086021823448155e-06, + "loss": 0.1544, + "step": 10343 + }, + { + "epoch": 1.32, + "learning_rate": 2.7076809933785254e-06, + "loss": 0.1301, + "step": 10344 + }, + { + "epoch": 1.32, + "learning_rate": 2.7067599029182884e-06, + "loss": 0.1315, + "step": 10345 + }, + { + "epoch": 1.32, + "learning_rate": 2.7058389110036835e-06, + "loss": 0.1412, + "step": 10346 + }, + { + "epoch": 1.32, + "learning_rate": 2.704918017674294e-06, + "loss": 0.139, + "step": 10347 + }, + { + "epoch": 1.32, + "learning_rate": 2.7039972229696847e-06, + "loss": 0.1571, + "step": 10348 + }, + { + "epoch": 1.32, + "learning_rate": 2.70307652692943e-06, + "loss": 0.1682, + "step": 10349 + }, + { + "epoch": 1.32, + "learning_rate": 2.702155929593093e-06, + "loss": 0.1432, + "step": 10350 + }, + { + "epoch": 1.32, + "learning_rate": 2.7012354310002333e-06, + "loss": 0.1533, + "step": 10351 + }, + { + "epoch": 1.33, + "learning_rate": 2.700315031190406e-06, + "loss": 0.1363, + "step": 10352 + }, + { + "epoch": 1.33, + "learning_rate": 2.6993947302031643e-06, + "loss": 0.1507, + "step": 10353 + }, + { + "epoch": 1.33, + "learning_rate": 2.6984745280780524e-06, + "loss": 0.143, + "step": 10354 + }, + { + "epoch": 1.33, + "learning_rate": 2.6975544248546195e-06, + "loss": 0.1415, + "step": 10355 + }, + { + "epoch": 1.33, + "learning_rate": 2.696634420572397e-06, + "loss": 0.1494, + "step": 10356 + }, + { + "epoch": 1.33, + "learning_rate": 2.6957145152709253e-06, + "loss": 0.1633, + "step": 10357 + }, + { + "epoch": 1.33, + "learning_rate": 2.694794708989733e-06, + "loss": 0.147, + "step": 10358 + }, + { + "epoch": 1.33, + "learning_rate": 2.6938750017683457e-06, + "loss": 0.1373, + "step": 10359 + }, + { + "epoch": 1.33, + "learning_rate": 2.692955393646286e-06, + "loss": 0.1444, + "step": 10360 + }, + { + "epoch": 1.33, + "learning_rate": 2.6920358846630688e-06, + "loss": 0.1478, + "step": 10361 + }, + { + "epoch": 1.33, + "learning_rate": 2.691116474858214e-06, + "loss": 0.1311, + "step": 10362 + }, + { + "epoch": 1.33, + "learning_rate": 2.690197164271224e-06, + "loss": 0.1334, + "step": 10363 + }, + { + "epoch": 1.33, + "learning_rate": 2.6892779529416045e-06, + "loss": 0.1513, + "step": 10364 + }, + { + "epoch": 1.33, + "learning_rate": 2.6883588409088597e-06, + "loss": 0.1304, + "step": 10365 + }, + { + "epoch": 1.33, + "learning_rate": 2.6874398282124837e-06, + "loss": 0.142, + "step": 10366 + }, + { + "epoch": 1.33, + "learning_rate": 2.686520914891968e-06, + "loss": 0.1434, + "step": 10367 + }, + { + "epoch": 1.33, + "learning_rate": 2.6856021009868016e-06, + "loss": 0.1457, + "step": 10368 + }, + { + "epoch": 1.33, + "learning_rate": 2.6846833865364674e-06, + "loss": 0.1257, + "step": 10369 + }, + { + "epoch": 1.33, + "learning_rate": 2.6837647715804444e-06, + "loss": 0.1466, + "step": 10370 + }, + { + "epoch": 1.33, + "learning_rate": 2.682846256158206e-06, + "loss": 0.1426, + "step": 10371 + }, + { + "epoch": 1.33, + "learning_rate": 2.6819278403092258e-06, + "loss": 0.1577, + "step": 10372 + }, + { + "epoch": 1.33, + "learning_rate": 2.6810095240729715e-06, + "loss": 0.1399, + "step": 10373 + }, + { + "epoch": 1.33, + "learning_rate": 2.6800913074888984e-06, + "loss": 0.1282, + "step": 10374 + }, + { + "epoch": 1.33, + "learning_rate": 2.679173190596471e-06, + "loss": 0.143, + "step": 10375 + }, + { + "epoch": 1.33, + "learning_rate": 2.6782551734351396e-06, + "loss": 0.1547, + "step": 10376 + }, + { + "epoch": 1.33, + "learning_rate": 2.6773372560443543e-06, + "loss": 0.1332, + "step": 10377 + }, + { + "epoch": 1.33, + "learning_rate": 2.6764194384635607e-06, + "loss": 0.1332, + "step": 10378 + }, + { + "epoch": 1.33, + "learning_rate": 2.6755017207321964e-06, + "loss": 0.1446, + "step": 10379 + }, + { + "epoch": 1.33, + "learning_rate": 2.6745841028897034e-06, + "loss": 0.1338, + "step": 10380 + }, + { + "epoch": 1.33, + "learning_rate": 2.6736665849755073e-06, + "loss": 0.1499, + "step": 10381 + }, + { + "epoch": 1.33, + "learning_rate": 2.6727491670290405e-06, + "loss": 0.1405, + "step": 10382 + }, + { + "epoch": 1.33, + "learning_rate": 2.6718318490897256e-06, + "loss": 0.1428, + "step": 10383 + }, + { + "epoch": 1.33, + "learning_rate": 2.6709146311969813e-06, + "loss": 0.1538, + "step": 10384 + }, + { + "epoch": 1.33, + "learning_rate": 2.669997513390222e-06, + "loss": 0.1427, + "step": 10385 + }, + { + "epoch": 1.33, + "learning_rate": 2.669080495708859e-06, + "loss": 0.1184, + "step": 10386 + }, + { + "epoch": 1.33, + "learning_rate": 2.668163578192298e-06, + "loss": 0.1505, + "step": 10387 + }, + { + "epoch": 1.33, + "learning_rate": 2.6672467608799413e-06, + "loss": 0.1398, + "step": 10388 + }, + { + "epoch": 1.33, + "learning_rate": 2.666330043811185e-06, + "loss": 0.1341, + "step": 10389 + }, + { + "epoch": 1.33, + "learning_rate": 2.6654134270254263e-06, + "loss": 0.1548, + "step": 10390 + }, + { + "epoch": 1.33, + "learning_rate": 2.6644969105620535e-06, + "loss": 0.1359, + "step": 10391 + }, + { + "epoch": 1.33, + "learning_rate": 2.663580494460446e-06, + "loss": 0.1234, + "step": 10392 + }, + { + "epoch": 1.33, + "learning_rate": 2.6626641787599904e-06, + "loss": 0.1251, + "step": 10393 + }, + { + "epoch": 1.33, + "learning_rate": 2.66174796350006e-06, + "loss": 0.1279, + "step": 10394 + }, + { + "epoch": 1.33, + "learning_rate": 2.660831848720028e-06, + "loss": 0.1445, + "step": 10395 + }, + { + "epoch": 1.33, + "learning_rate": 2.6599158344592606e-06, + "loss": 0.1432, + "step": 10396 + }, + { + "epoch": 1.33, + "learning_rate": 2.658999920757119e-06, + "loss": 0.1463, + "step": 10397 + }, + { + "epoch": 1.33, + "learning_rate": 2.6580841076529697e-06, + "loss": 0.1296, + "step": 10398 + }, + { + "epoch": 1.33, + "learning_rate": 2.657168395186157e-06, + "loss": 0.1523, + "step": 10399 + }, + { + "epoch": 1.33, + "learning_rate": 2.656252783396038e-06, + "loss": 0.1357, + "step": 10400 + }, + { + "epoch": 1.33, + "learning_rate": 2.655337272321957e-06, + "loss": 0.1428, + "step": 10401 + }, + { + "epoch": 1.33, + "learning_rate": 2.654421862003256e-06, + "loss": 0.1606, + "step": 10402 + }, + { + "epoch": 1.33, + "learning_rate": 2.653506552479271e-06, + "loss": 0.1486, + "step": 10403 + }, + { + "epoch": 1.33, + "learning_rate": 2.6525913437893346e-06, + "loss": 0.1352, + "step": 10404 + }, + { + "epoch": 1.33, + "learning_rate": 2.651676235972777e-06, + "loss": 0.1422, + "step": 10405 + }, + { + "epoch": 1.33, + "learning_rate": 2.650761229068921e-06, + "loss": 0.1489, + "step": 10406 + }, + { + "epoch": 1.33, + "learning_rate": 2.649846323117086e-06, + "loss": 0.1527, + "step": 10407 + }, + { + "epoch": 1.33, + "learning_rate": 2.6489315181565896e-06, + "loss": 0.1457, + "step": 10408 + }, + { + "epoch": 1.33, + "learning_rate": 2.648016814226742e-06, + "loss": 0.1414, + "step": 10409 + }, + { + "epoch": 1.33, + "learning_rate": 2.6471022113668505e-06, + "loss": 0.1539, + "step": 10410 + }, + { + "epoch": 1.33, + "learning_rate": 2.646187709616217e-06, + "loss": 0.1522, + "step": 10411 + }, + { + "epoch": 1.33, + "learning_rate": 2.645273309014139e-06, + "loss": 0.1552, + "step": 10412 + }, + { + "epoch": 1.33, + "learning_rate": 2.6443590095999127e-06, + "loss": 0.1364, + "step": 10413 + }, + { + "epoch": 1.33, + "learning_rate": 2.6434448114128252e-06, + "loss": 0.1311, + "step": 10414 + }, + { + "epoch": 1.33, + "learning_rate": 2.642530714492161e-06, + "loss": 0.1552, + "step": 10415 + }, + { + "epoch": 1.33, + "learning_rate": 2.6416167188772052e-06, + "loss": 0.1306, + "step": 10416 + }, + { + "epoch": 1.33, + "learning_rate": 2.6407028246072287e-06, + "loss": 0.1471, + "step": 10417 + }, + { + "epoch": 1.33, + "learning_rate": 2.6397890317215067e-06, + "loss": 0.1389, + "step": 10418 + }, + { + "epoch": 1.33, + "learning_rate": 2.6388753402593083e-06, + "loss": 0.1426, + "step": 10419 + }, + { + "epoch": 1.33, + "learning_rate": 2.637961750259894e-06, + "loss": 0.1468, + "step": 10420 + }, + { + "epoch": 1.33, + "learning_rate": 2.6370482617625236e-06, + "loss": 0.1417, + "step": 10421 + }, + { + "epoch": 1.33, + "learning_rate": 2.636134874806451e-06, + "loss": 0.1408, + "step": 10422 + }, + { + "epoch": 1.33, + "learning_rate": 2.6352215894309306e-06, + "loss": 0.1262, + "step": 10423 + }, + { + "epoch": 1.33, + "learning_rate": 2.6343084056752032e-06, + "loss": 0.1418, + "step": 10424 + }, + { + "epoch": 1.33, + "learning_rate": 2.6333953235785105e-06, + "loss": 0.137, + "step": 10425 + }, + { + "epoch": 1.33, + "learning_rate": 2.632482343180094e-06, + "loss": 0.1346, + "step": 10426 + }, + { + "epoch": 1.33, + "learning_rate": 2.631569464519183e-06, + "loss": 0.1395, + "step": 10427 + }, + { + "epoch": 1.33, + "learning_rate": 2.6306566876350072e-06, + "loss": 0.1482, + "step": 10428 + }, + { + "epoch": 1.33, + "learning_rate": 2.6297440125667904e-06, + "loss": 0.1543, + "step": 10429 + }, + { + "epoch": 1.34, + "learning_rate": 2.6288314393537522e-06, + "loss": 0.1379, + "step": 10430 + }, + { + "epoch": 1.34, + "learning_rate": 2.627918968035108e-06, + "loss": 0.1301, + "step": 10431 + }, + { + "epoch": 1.34, + "learning_rate": 2.627006598650067e-06, + "loss": 0.1476, + "step": 10432 + }, + { + "epoch": 1.34, + "learning_rate": 2.6260943312378384e-06, + "loss": 0.1403, + "step": 10433 + }, + { + "epoch": 1.34, + "learning_rate": 2.6251821658376265e-06, + "loss": 0.1252, + "step": 10434 + }, + { + "epoch": 1.34, + "learning_rate": 2.624270102488621e-06, + "loss": 0.1435, + "step": 10435 + }, + { + "epoch": 1.34, + "learning_rate": 2.6233581412300222e-06, + "loss": 0.1324, + "step": 10436 + }, + { + "epoch": 1.34, + "learning_rate": 2.6224462821010185e-06, + "loss": 0.1452, + "step": 10437 + }, + { + "epoch": 1.34, + "learning_rate": 2.621534525140792e-06, + "loss": 0.1436, + "step": 10438 + }, + { + "epoch": 1.34, + "learning_rate": 2.620622870388524e-06, + "loss": 0.1424, + "step": 10439 + }, + { + "epoch": 1.34, + "learning_rate": 2.619711317883389e-06, + "loss": 0.1568, + "step": 10440 + }, + { + "epoch": 1.34, + "learning_rate": 2.6187998676645633e-06, + "loss": 0.1235, + "step": 10441 + }, + { + "epoch": 1.34, + "learning_rate": 2.617888519771207e-06, + "loss": 0.1369, + "step": 10442 + }, + { + "epoch": 1.34, + "learning_rate": 2.616977274242488e-06, + "loss": 0.1498, + "step": 10443 + }, + { + "epoch": 1.34, + "learning_rate": 2.616066131117563e-06, + "loss": 0.1328, + "step": 10444 + }, + { + "epoch": 1.34, + "learning_rate": 2.6151550904355853e-06, + "loss": 0.1541, + "step": 10445 + }, + { + "epoch": 1.34, + "learning_rate": 2.6142441522357055e-06, + "loss": 0.1552, + "step": 10446 + }, + { + "epoch": 1.34, + "learning_rate": 2.6133333165570667e-06, + "loss": 0.1473, + "step": 10447 + }, + { + "epoch": 1.34, + "learning_rate": 2.612422583438811e-06, + "loss": 0.1468, + "step": 10448 + }, + { + "epoch": 1.34, + "learning_rate": 2.6115119529200748e-06, + "loss": 0.1482, + "step": 10449 + }, + { + "epoch": 1.34, + "learning_rate": 2.6106014250399868e-06, + "loss": 0.1296, + "step": 10450 + }, + { + "epoch": 1.34, + "learning_rate": 2.6096909998376794e-06, + "loss": 0.1492, + "step": 10451 + }, + { + "epoch": 1.34, + "learning_rate": 2.6087806773522755e-06, + "loss": 0.1557, + "step": 10452 + }, + { + "epoch": 1.34, + "learning_rate": 2.6078704576228876e-06, + "loss": 0.1465, + "step": 10453 + }, + { + "epoch": 1.34, + "learning_rate": 2.6069603406886347e-06, + "loss": 0.1432, + "step": 10454 + }, + { + "epoch": 1.34, + "learning_rate": 2.606050326588626e-06, + "loss": 0.145, + "step": 10455 + }, + { + "epoch": 1.34, + "learning_rate": 2.605140415361967e-06, + "loss": 0.1509, + "step": 10456 + }, + { + "epoch": 1.34, + "learning_rate": 2.6042306070477576e-06, + "loss": 0.1199, + "step": 10457 + }, + { + "epoch": 1.34, + "learning_rate": 2.6033209016850926e-06, + "loss": 0.1518, + "step": 10458 + }, + { + "epoch": 1.34, + "learning_rate": 2.60241129931307e-06, + "loss": 0.1497, + "step": 10459 + }, + { + "epoch": 1.34, + "learning_rate": 2.601501799970769e-06, + "loss": 0.1433, + "step": 10460 + }, + { + "epoch": 1.34, + "learning_rate": 2.6005924036972807e-06, + "loss": 0.1271, + "step": 10461 + }, + { + "epoch": 1.34, + "learning_rate": 2.59968311053168e-06, + "loss": 0.1495, + "step": 10462 + }, + { + "epoch": 1.34, + "learning_rate": 2.5987739205130413e-06, + "loss": 0.1537, + "step": 10463 + }, + { + "epoch": 1.34, + "learning_rate": 2.597864833680436e-06, + "loss": 0.1492, + "step": 10464 + }, + { + "epoch": 1.34, + "learning_rate": 2.596955850072928e-06, + "loss": 0.1387, + "step": 10465 + }, + { + "epoch": 1.34, + "learning_rate": 2.5960469697295794e-06, + "loss": 0.1373, + "step": 10466 + }, + { + "epoch": 1.34, + "learning_rate": 2.595138192689446e-06, + "loss": 0.1311, + "step": 10467 + }, + { + "epoch": 1.34, + "learning_rate": 2.594229518991579e-06, + "loss": 0.1515, + "step": 10468 + }, + { + "epoch": 1.34, + "learning_rate": 2.593320948675029e-06, + "loss": 0.1358, + "step": 10469 + }, + { + "epoch": 1.34, + "learning_rate": 2.5924124817788377e-06, + "loss": 0.1356, + "step": 10470 + }, + { + "epoch": 1.34, + "learning_rate": 2.591504118342044e-06, + "loss": 0.1315, + "step": 10471 + }, + { + "epoch": 1.34, + "learning_rate": 2.5905958584036826e-06, + "loss": 0.133, + "step": 10472 + }, + { + "epoch": 1.34, + "learning_rate": 2.5896877020027813e-06, + "loss": 0.1396, + "step": 10473 + }, + { + "epoch": 1.34, + "learning_rate": 2.588779649178371e-06, + "loss": 0.1303, + "step": 10474 + }, + { + "epoch": 1.34, + "learning_rate": 2.5878716999694675e-06, + "loss": 0.1429, + "step": 10475 + }, + { + "epoch": 1.34, + "learning_rate": 2.5869638544150876e-06, + "loss": 0.146, + "step": 10476 + }, + { + "epoch": 1.34, + "learning_rate": 2.586056112554248e-06, + "loss": 0.1487, + "step": 10477 + }, + { + "epoch": 1.34, + "learning_rate": 2.5851484744259503e-06, + "loss": 0.1513, + "step": 10478 + }, + { + "epoch": 1.34, + "learning_rate": 2.5842409400692026e-06, + "loss": 0.1421, + "step": 10479 + }, + { + "epoch": 1.34, + "learning_rate": 2.5833335095230016e-06, + "loss": 0.139, + "step": 10480 + }, + { + "epoch": 1.34, + "learning_rate": 2.5824261828263424e-06, + "loss": 0.1274, + "step": 10481 + }, + { + "epoch": 1.34, + "learning_rate": 2.5815189600182145e-06, + "loss": 0.1567, + "step": 10482 + }, + { + "epoch": 1.34, + "learning_rate": 2.5806118411376e-06, + "loss": 0.1292, + "step": 10483 + }, + { + "epoch": 1.34, + "learning_rate": 2.579704826223488e-06, + "loss": 0.1421, + "step": 10484 + }, + { + "epoch": 1.34, + "learning_rate": 2.578797915314848e-06, + "loss": 0.144, + "step": 10485 + }, + { + "epoch": 1.34, + "learning_rate": 2.577891108450651e-06, + "loss": 0.1282, + "step": 10486 + }, + { + "epoch": 1.34, + "learning_rate": 2.5769844056698702e-06, + "loss": 0.1365, + "step": 10487 + }, + { + "epoch": 1.34, + "learning_rate": 2.576077807011465e-06, + "loss": 0.1479, + "step": 10488 + }, + { + "epoch": 1.34, + "learning_rate": 2.575171312514395e-06, + "loss": 0.1585, + "step": 10489 + }, + { + "epoch": 1.34, + "learning_rate": 2.5742649222176147e-06, + "loss": 0.1497, + "step": 10490 + }, + { + "epoch": 1.34, + "learning_rate": 2.573358636160071e-06, + "loss": 0.1469, + "step": 10491 + }, + { + "epoch": 1.34, + "learning_rate": 2.572452454380715e-06, + "loss": 0.1428, + "step": 10492 + }, + { + "epoch": 1.34, + "learning_rate": 2.571546376918479e-06, + "loss": 0.1416, + "step": 10493 + }, + { + "epoch": 1.34, + "learning_rate": 2.570640403812306e-06, + "loss": 0.1378, + "step": 10494 + }, + { + "epoch": 1.34, + "learning_rate": 2.569734535101127e-06, + "loss": 0.1347, + "step": 10495 + }, + { + "epoch": 1.34, + "learning_rate": 2.5688287708238647e-06, + "loss": 0.1321, + "step": 10496 + }, + { + "epoch": 1.34, + "learning_rate": 2.5679231110194454e-06, + "loss": 0.1371, + "step": 10497 + }, + { + "epoch": 1.34, + "learning_rate": 2.567017555726787e-06, + "loss": 0.1397, + "step": 10498 + }, + { + "epoch": 1.34, + "learning_rate": 2.5661121049848026e-06, + "loss": 0.1494, + "step": 10499 + }, + { + "epoch": 1.34, + "learning_rate": 2.5652067588324015e-06, + "loss": 0.1459, + "step": 10500 + }, + { + "epoch": 1.34, + "learning_rate": 2.564301517308487e-06, + "loss": 0.1422, + "step": 10501 + }, + { + "epoch": 1.34, + "learning_rate": 2.5633963804519623e-06, + "loss": 0.1295, + "step": 10502 + }, + { + "epoch": 1.34, + "learning_rate": 2.5624913483017246e-06, + "loss": 0.1327, + "step": 10503 + }, + { + "epoch": 1.34, + "learning_rate": 2.5615864208966573e-06, + "loss": 0.1308, + "step": 10504 + }, + { + "epoch": 1.34, + "learning_rate": 2.560681598275655e-06, + "loss": 0.1667, + "step": 10505 + }, + { + "epoch": 1.34, + "learning_rate": 2.559776880477596e-06, + "loss": 0.1336, + "step": 10506 + }, + { + "epoch": 1.34, + "learning_rate": 2.55887226754136e-06, + "loss": 0.1392, + "step": 10507 + }, + { + "epoch": 1.35, + "learning_rate": 2.5579677595058196e-06, + "loss": 0.1312, + "step": 10508 + }, + { + "epoch": 1.35, + "learning_rate": 2.55706335640984e-06, + "loss": 0.1454, + "step": 10509 + }, + { + "epoch": 1.35, + "learning_rate": 2.5561590582922934e-06, + "loss": 0.1266, + "step": 10510 + }, + { + "epoch": 1.35, + "learning_rate": 2.5552548651920317e-06, + "loss": 0.1307, + "step": 10511 + }, + { + "epoch": 1.35, + "learning_rate": 2.5543507771479137e-06, + "loss": 0.1357, + "step": 10512 + }, + { + "epoch": 1.35, + "learning_rate": 2.553446794198793e-06, + "loss": 0.1316, + "step": 10513 + }, + { + "epoch": 1.35, + "learning_rate": 2.552542916383507e-06, + "loss": 0.1448, + "step": 10514 + }, + { + "epoch": 1.35, + "learning_rate": 2.551639143740905e-06, + "loss": 0.1424, + "step": 10515 + }, + { + "epoch": 1.35, + "learning_rate": 2.5507354763098226e-06, + "loss": 0.1333, + "step": 10516 + }, + { + "epoch": 1.35, + "learning_rate": 2.5498319141290904e-06, + "loss": 0.1513, + "step": 10517 + }, + { + "epoch": 1.35, + "learning_rate": 2.548928457237538e-06, + "loss": 0.131, + "step": 10518 + }, + { + "epoch": 1.35, + "learning_rate": 2.5480251056739874e-06, + "loss": 0.1316, + "step": 10519 + }, + { + "epoch": 1.35, + "learning_rate": 2.5471218594772602e-06, + "loss": 0.1232, + "step": 10520 + }, + { + "epoch": 1.35, + "learning_rate": 2.5462187186861697e-06, + "loss": 0.137, + "step": 10521 + }, + { + "epoch": 1.35, + "learning_rate": 2.5453156833395254e-06, + "loss": 0.1276, + "step": 10522 + }, + { + "epoch": 1.35, + "learning_rate": 2.544412753476134e-06, + "loss": 0.1521, + "step": 10523 + }, + { + "epoch": 1.35, + "learning_rate": 2.543509929134794e-06, + "loss": 0.1446, + "step": 10524 + }, + { + "epoch": 1.35, + "learning_rate": 2.5426072103543043e-06, + "loss": 0.1283, + "step": 10525 + }, + { + "epoch": 1.35, + "learning_rate": 2.5417045971734556e-06, + "loss": 0.1528, + "step": 10526 + }, + { + "epoch": 1.35, + "learning_rate": 2.5408020896310333e-06, + "loss": 0.1591, + "step": 10527 + }, + { + "epoch": 1.35, + "learning_rate": 2.5398996877658256e-06, + "loss": 0.1499, + "step": 10528 + }, + { + "epoch": 1.35, + "learning_rate": 2.5389973916166037e-06, + "loss": 0.1319, + "step": 10529 + }, + { + "epoch": 1.35, + "learning_rate": 2.5380952012221473e-06, + "loss": 0.1293, + "step": 10530 + }, + { + "epoch": 1.35, + "learning_rate": 2.5371931166212216e-06, + "loss": 0.1466, + "step": 10531 + }, + { + "epoch": 1.35, + "learning_rate": 2.536291137852594e-06, + "loss": 0.1454, + "step": 10532 + }, + { + "epoch": 1.35, + "learning_rate": 2.535389264955023e-06, + "loss": 0.1295, + "step": 10533 + }, + { + "epoch": 1.35, + "learning_rate": 2.534487497967262e-06, + "loss": 0.1301, + "step": 10534 + }, + { + "epoch": 1.35, + "learning_rate": 2.5335858369280674e-06, + "loss": 0.1432, + "step": 10535 + }, + { + "epoch": 1.35, + "learning_rate": 2.5326842818761814e-06, + "loss": 0.1556, + "step": 10536 + }, + { + "epoch": 1.35, + "learning_rate": 2.5317828328503445e-06, + "loss": 0.1583, + "step": 10537 + }, + { + "epoch": 1.35, + "learning_rate": 2.5308814898892985e-06, + "loss": 0.1462, + "step": 10538 + }, + { + "epoch": 1.35, + "learning_rate": 2.529980253031774e-06, + "loss": 0.1356, + "step": 10539 + }, + { + "epoch": 1.35, + "learning_rate": 2.529079122316499e-06, + "loss": 0.1476, + "step": 10540 + }, + { + "epoch": 1.35, + "learning_rate": 2.5281780977821967e-06, + "loss": 0.1245, + "step": 10541 + }, + { + "epoch": 1.35, + "learning_rate": 2.5272771794675866e-06, + "loss": 0.1501, + "step": 10542 + }, + { + "epoch": 1.35, + "learning_rate": 2.526376367411384e-06, + "loss": 0.1347, + "step": 10543 + }, + { + "epoch": 1.35, + "learning_rate": 2.5254756616522953e-06, + "loss": 0.1253, + "step": 10544 + }, + { + "epoch": 1.35, + "learning_rate": 2.52457506222903e-06, + "loss": 0.1522, + "step": 10545 + }, + { + "epoch": 1.35, + "learning_rate": 2.52367456918029e-06, + "loss": 0.1508, + "step": 10546 + }, + { + "epoch": 1.35, + "learning_rate": 2.522774182544765e-06, + "loss": 0.1615, + "step": 10547 + }, + { + "epoch": 1.35, + "learning_rate": 2.5218739023611523e-06, + "loss": 0.1388, + "step": 10548 + }, + { + "epoch": 1.35, + "learning_rate": 2.5209737286681367e-06, + "loss": 0.1389, + "step": 10549 + }, + { + "epoch": 1.35, + "learning_rate": 2.5200736615044012e-06, + "loss": 0.1467, + "step": 10550 + }, + { + "epoch": 1.35, + "learning_rate": 2.5191737009086235e-06, + "loss": 0.1366, + "step": 10551 + }, + { + "epoch": 1.35, + "learning_rate": 2.5182738469194757e-06, + "loss": 0.149, + "step": 10552 + }, + { + "epoch": 1.35, + "learning_rate": 2.5173740995756313e-06, + "loss": 0.1504, + "step": 10553 + }, + { + "epoch": 1.35, + "learning_rate": 2.5164744589157488e-06, + "loss": 0.1292, + "step": 10554 + }, + { + "epoch": 1.35, + "learning_rate": 2.5155749249784876e-06, + "loss": 0.1341, + "step": 10555 + }, + { + "epoch": 1.35, + "learning_rate": 2.514675497802508e-06, + "loss": 0.1759, + "step": 10556 + }, + { + "epoch": 1.35, + "learning_rate": 2.513776177426457e-06, + "loss": 0.1477, + "step": 10557 + }, + { + "epoch": 1.35, + "learning_rate": 2.51287696388898e-06, + "loss": 0.1303, + "step": 10558 + }, + { + "epoch": 1.35, + "learning_rate": 2.5119778572287195e-06, + "loss": 0.1366, + "step": 10559 + }, + { + "epoch": 1.35, + "learning_rate": 2.5110788574843113e-06, + "loss": 0.1428, + "step": 10560 + }, + { + "epoch": 1.35, + "learning_rate": 2.510179964694388e-06, + "loss": 0.1324, + "step": 10561 + }, + { + "epoch": 1.35, + "learning_rate": 2.5092811788975754e-06, + "loss": 0.1283, + "step": 10562 + }, + { + "epoch": 1.35, + "learning_rate": 2.508382500132499e-06, + "loss": 0.1406, + "step": 10563 + }, + { + "epoch": 1.35, + "learning_rate": 2.5074839284377774e-06, + "loss": 0.1273, + "step": 10564 + }, + { + "epoch": 1.35, + "learning_rate": 2.506585463852019e-06, + "loss": 0.1357, + "step": 10565 + }, + { + "epoch": 1.35, + "learning_rate": 2.5056871064138383e-06, + "loss": 0.1364, + "step": 10566 + }, + { + "epoch": 1.35, + "learning_rate": 2.504788856161838e-06, + "loss": 0.1318, + "step": 10567 + }, + { + "epoch": 1.35, + "learning_rate": 2.5038907131346168e-06, + "loss": 0.1592, + "step": 10568 + }, + { + "epoch": 1.35, + "learning_rate": 2.5029926773707713e-06, + "loss": 0.1522, + "step": 10569 + }, + { + "epoch": 1.35, + "learning_rate": 2.50209474890889e-06, + "loss": 0.1318, + "step": 10570 + }, + { + "epoch": 1.35, + "learning_rate": 2.5011969277875643e-06, + "loss": 0.1409, + "step": 10571 + }, + { + "epoch": 1.35, + "learning_rate": 2.5002992140453674e-06, + "loss": 0.1388, + "step": 10572 + }, + { + "epoch": 1.35, + "learning_rate": 2.499401607720883e-06, + "loss": 0.1544, + "step": 10573 + }, + { + "epoch": 1.35, + "learning_rate": 2.49850410885268e-06, + "loss": 0.1431, + "step": 10574 + }, + { + "epoch": 1.35, + "learning_rate": 2.4976067174793268e-06, + "loss": 0.151, + "step": 10575 + }, + { + "epoch": 1.35, + "learning_rate": 2.496709433639386e-06, + "loss": 0.1436, + "step": 10576 + }, + { + "epoch": 1.35, + "learning_rate": 2.495812257371416e-06, + "loss": 0.15, + "step": 10577 + }, + { + "epoch": 1.35, + "learning_rate": 2.4949151887139705e-06, + "loss": 0.1433, + "step": 10578 + }, + { + "epoch": 1.35, + "learning_rate": 2.4940182277055987e-06, + "loss": 0.1532, + "step": 10579 + }, + { + "epoch": 1.35, + "learning_rate": 2.4931213743848428e-06, + "loss": 0.1446, + "step": 10580 + }, + { + "epoch": 1.35, + "learning_rate": 2.4922246287902458e-06, + "loss": 0.1431, + "step": 10581 + }, + { + "epoch": 1.35, + "learning_rate": 2.491327990960342e-06, + "loss": 0.141, + "step": 10582 + }, + { + "epoch": 1.35, + "learning_rate": 2.4904314609336616e-06, + "loss": 0.1394, + "step": 10583 + }, + { + "epoch": 1.35, + "learning_rate": 2.4895350387487304e-06, + "loss": 0.127, + "step": 10584 + }, + { + "epoch": 1.35, + "learning_rate": 2.48863872444407e-06, + "loss": 0.1521, + "step": 10585 + }, + { + "epoch": 1.36, + "learning_rate": 2.4877425180581964e-06, + "loss": 0.1559, + "step": 10586 + }, + { + "epoch": 1.36, + "learning_rate": 2.486846419629622e-06, + "loss": 0.1204, + "step": 10587 + }, + { + "epoch": 1.36, + "learning_rate": 2.4859504291968522e-06, + "loss": 0.1291, + "step": 10588 + }, + { + "epoch": 1.36, + "learning_rate": 2.485054546798395e-06, + "loss": 0.1409, + "step": 10589 + }, + { + "epoch": 1.36, + "learning_rate": 2.4841587724727416e-06, + "loss": 0.1436, + "step": 10590 + }, + { + "epoch": 1.36, + "learning_rate": 2.4832631062583906e-06, + "loss": 0.1429, + "step": 10591 + }, + { + "epoch": 1.36, + "learning_rate": 2.4823675481938293e-06, + "loss": 0.1423, + "step": 10592 + }, + { + "epoch": 1.36, + "learning_rate": 2.4814720983175413e-06, + "loss": 0.1304, + "step": 10593 + }, + { + "epoch": 1.36, + "learning_rate": 2.4805767566680057e-06, + "loss": 0.142, + "step": 10594 + }, + { + "epoch": 1.36, + "learning_rate": 2.4796815232836965e-06, + "loss": 0.1492, + "step": 10595 + }, + { + "epoch": 1.36, + "learning_rate": 2.478786398203089e-06, + "loss": 0.1483, + "step": 10596 + }, + { + "epoch": 1.36, + "learning_rate": 2.4778913814646433e-06, + "loss": 0.1477, + "step": 10597 + }, + { + "epoch": 1.36, + "learning_rate": 2.47699647310682e-06, + "loss": 0.1565, + "step": 10598 + }, + { + "epoch": 1.36, + "learning_rate": 2.4761016731680792e-06, + "loss": 0.1247, + "step": 10599 + }, + { + "epoch": 1.36, + "learning_rate": 2.4752069816868707e-06, + "loss": 0.1367, + "step": 10600 + }, + { + "epoch": 1.36, + "learning_rate": 2.474312398701641e-06, + "loss": 0.134, + "step": 10601 + }, + { + "epoch": 1.36, + "learning_rate": 2.473417924250833e-06, + "loss": 0.1514, + "step": 10602 + }, + { + "epoch": 1.36, + "learning_rate": 2.472523558372883e-06, + "loss": 0.1514, + "step": 10603 + }, + { + "epoch": 1.36, + "learning_rate": 2.4716293011062248e-06, + "loss": 0.1354, + "step": 10604 + }, + { + "epoch": 1.36, + "learning_rate": 2.470735152489287e-06, + "loss": 0.114, + "step": 10605 + }, + { + "epoch": 1.36, + "learning_rate": 2.4698411125604903e-06, + "loss": 0.1437, + "step": 10606 + }, + { + "epoch": 1.36, + "learning_rate": 2.46894718135826e-06, + "loss": 0.1389, + "step": 10607 + }, + { + "epoch": 1.36, + "learning_rate": 2.4680533589210028e-06, + "loss": 0.1507, + "step": 10608 + }, + { + "epoch": 1.36, + "learning_rate": 2.467159645287133e-06, + "loss": 0.134, + "step": 10609 + }, + { + "epoch": 1.36, + "learning_rate": 2.4662660404950544e-06, + "loss": 0.1486, + "step": 10610 + }, + { + "epoch": 1.36, + "learning_rate": 2.465372544583167e-06, + "loss": 0.1511, + "step": 10611 + }, + { + "epoch": 1.36, + "learning_rate": 2.4644791575898665e-06, + "loss": 0.1255, + "step": 10612 + }, + { + "epoch": 1.36, + "learning_rate": 2.4635858795535413e-06, + "loss": 0.1266, + "step": 10613 + }, + { + "epoch": 1.36, + "learning_rate": 2.4626927105125834e-06, + "loss": 0.1169, + "step": 10614 + }, + { + "epoch": 1.36, + "learning_rate": 2.461799650505369e-06, + "loss": 0.1429, + "step": 10615 + }, + { + "epoch": 1.36, + "learning_rate": 2.4609066995702745e-06, + "loss": 0.1473, + "step": 10616 + }, + { + "epoch": 1.36, + "learning_rate": 2.460013857745676e-06, + "loss": 0.1557, + "step": 10617 + }, + { + "epoch": 1.36, + "learning_rate": 2.4591211250699393e-06, + "loss": 0.1457, + "step": 10618 + }, + { + "epoch": 1.36, + "learning_rate": 2.4582285015814263e-06, + "loss": 0.1515, + "step": 10619 + }, + { + "epoch": 1.36, + "learning_rate": 2.457335987318495e-06, + "loss": 0.1311, + "step": 10620 + }, + { + "epoch": 1.36, + "learning_rate": 2.4564435823194977e-06, + "loss": 0.1329, + "step": 10621 + }, + { + "epoch": 1.36, + "learning_rate": 2.455551286622788e-06, + "loss": 0.1431, + "step": 10622 + }, + { + "epoch": 1.36, + "learning_rate": 2.454659100266703e-06, + "loss": 0.1338, + "step": 10623 + }, + { + "epoch": 1.36, + "learning_rate": 2.4537670232895866e-06, + "loss": 0.1417, + "step": 10624 + }, + { + "epoch": 1.36, + "learning_rate": 2.4528750557297745e-06, + "loss": 0.1449, + "step": 10625 + }, + { + "epoch": 1.36, + "learning_rate": 2.4519831976255892e-06, + "loss": 0.1294, + "step": 10626 + }, + { + "epoch": 1.36, + "learning_rate": 2.451091449015364e-06, + "loss": 0.1489, + "step": 10627 + }, + { + "epoch": 1.36, + "learning_rate": 2.4501998099374147e-06, + "loss": 0.1241, + "step": 10628 + }, + { + "epoch": 1.36, + "learning_rate": 2.4493082804300585e-06, + "loss": 0.1477, + "step": 10629 + }, + { + "epoch": 1.36, + "learning_rate": 2.4484168605316062e-06, + "loss": 0.1379, + "step": 10630 + }, + { + "epoch": 1.36, + "learning_rate": 2.4475255502803624e-06, + "loss": 0.1421, + "step": 10631 + }, + { + "epoch": 1.36, + "learning_rate": 2.4466343497146345e-06, + "loss": 0.145, + "step": 10632 + }, + { + "epoch": 1.36, + "learning_rate": 2.445743258872711e-06, + "loss": 0.1285, + "step": 10633 + }, + { + "epoch": 1.36, + "learning_rate": 2.4448522777928903e-06, + "loss": 0.1643, + "step": 10634 + }, + { + "epoch": 1.36, + "learning_rate": 2.4439614065134576e-06, + "loss": 0.1572, + "step": 10635 + }, + { + "epoch": 1.36, + "learning_rate": 2.443070645072696e-06, + "loss": 0.146, + "step": 10636 + }, + { + "epoch": 1.36, + "learning_rate": 2.4421799935088837e-06, + "loss": 0.1293, + "step": 10637 + }, + { + "epoch": 1.36, + "learning_rate": 2.441289451860293e-06, + "loss": 0.1391, + "step": 10638 + }, + { + "epoch": 1.36, + "learning_rate": 2.4403990201651915e-06, + "loss": 0.1231, + "step": 10639 + }, + { + "epoch": 1.36, + "learning_rate": 2.4395086984618486e-06, + "loss": 0.1376, + "step": 10640 + }, + { + "epoch": 1.36, + "learning_rate": 2.4386184867885154e-06, + "loss": 0.1497, + "step": 10641 + }, + { + "epoch": 1.36, + "learning_rate": 2.437728385183453e-06, + "loss": 0.1395, + "step": 10642 + }, + { + "epoch": 1.36, + "learning_rate": 2.436838393684907e-06, + "loss": 0.1409, + "step": 10643 + }, + { + "epoch": 1.36, + "learning_rate": 2.435948512331125e-06, + "loss": 0.1361, + "step": 10644 + }, + { + "epoch": 1.36, + "learning_rate": 2.4350587411603454e-06, + "loss": 0.135, + "step": 10645 + }, + { + "epoch": 1.36, + "learning_rate": 2.434169080210802e-06, + "loss": 0.1323, + "step": 10646 + }, + { + "epoch": 1.36, + "learning_rate": 2.433279529520732e-06, + "loss": 0.1564, + "step": 10647 + }, + { + "epoch": 1.36, + "learning_rate": 2.432390089128354e-06, + "loss": 0.1427, + "step": 10648 + }, + { + "epoch": 1.36, + "learning_rate": 2.4315007590718913e-06, + "loss": 0.135, + "step": 10649 + }, + { + "epoch": 1.36, + "learning_rate": 2.4306115393895645e-06, + "loss": 0.1412, + "step": 10650 + }, + { + "epoch": 1.36, + "learning_rate": 2.4297224301195795e-06, + "loss": 0.1515, + "step": 10651 + }, + { + "epoch": 1.36, + "learning_rate": 2.4288334313001467e-06, + "loss": 0.1391, + "step": 10652 + }, + { + "epoch": 1.36, + "learning_rate": 2.4279445429694683e-06, + "loss": 0.1275, + "step": 10653 + }, + { + "epoch": 1.36, + "learning_rate": 2.427055765165741e-06, + "loss": 0.1439, + "step": 10654 + }, + { + "epoch": 1.36, + "learning_rate": 2.4261670979271577e-06, + "loss": 0.146, + "step": 10655 + }, + { + "epoch": 1.36, + "learning_rate": 2.4252785412919065e-06, + "loss": 0.1261, + "step": 10656 + }, + { + "epoch": 1.36, + "learning_rate": 2.4243900952981685e-06, + "loss": 0.1385, + "step": 10657 + }, + { + "epoch": 1.36, + "learning_rate": 2.423501759984128e-06, + "loss": 0.1302, + "step": 10658 + }, + { + "epoch": 1.36, + "learning_rate": 2.4226135353879516e-06, + "loss": 0.1456, + "step": 10659 + }, + { + "epoch": 1.36, + "learning_rate": 2.4217254215478137e-06, + "loss": 0.1316, + "step": 10660 + }, + { + "epoch": 1.36, + "learning_rate": 2.420837418501876e-06, + "loss": 0.1336, + "step": 10661 + }, + { + "epoch": 1.36, + "learning_rate": 2.4199495262882993e-06, + "loss": 0.1559, + "step": 10662 + }, + { + "epoch": 1.36, + "learning_rate": 2.419061744945237e-06, + "loss": 0.1336, + "step": 10663 + }, + { + "epoch": 1.36, + "learning_rate": 2.4181740745108377e-06, + "loss": 0.1189, + "step": 10664 + }, + { + "epoch": 1.37, + "learning_rate": 2.4172865150232528e-06, + "loss": 0.1308, + "step": 10665 + }, + { + "epoch": 1.37, + "learning_rate": 2.4163990665206153e-06, + "loss": 0.1368, + "step": 10666 + }, + { + "epoch": 1.37, + "learning_rate": 2.415511729041063e-06, + "loss": 0.1371, + "step": 10667 + }, + { + "epoch": 1.37, + "learning_rate": 2.414624502622731e-06, + "loss": 0.1285, + "step": 10668 + }, + { + "epoch": 1.37, + "learning_rate": 2.413737387303739e-06, + "loss": 0.1508, + "step": 10669 + }, + { + "epoch": 1.37, + "learning_rate": 2.412850383122213e-06, + "loss": 0.129, + "step": 10670 + }, + { + "epoch": 1.37, + "learning_rate": 2.411963490116267e-06, + "loss": 0.1388, + "step": 10671 + }, + { + "epoch": 1.37, + "learning_rate": 2.4110767083240145e-06, + "loss": 0.1391, + "step": 10672 + }, + { + "epoch": 1.37, + "learning_rate": 2.410190037783562e-06, + "loss": 0.1407, + "step": 10673 + }, + { + "epoch": 1.37, + "learning_rate": 2.4093034785330087e-06, + "loss": 0.1359, + "step": 10674 + }, + { + "epoch": 1.37, + "learning_rate": 2.408417030610457e-06, + "loss": 0.1441, + "step": 10675 + }, + { + "epoch": 1.37, + "learning_rate": 2.4075306940539988e-06, + "loss": 0.1534, + "step": 10676 + }, + { + "epoch": 1.37, + "learning_rate": 2.4066444689017173e-06, + "loss": 0.1468, + "step": 10677 + }, + { + "epoch": 1.37, + "learning_rate": 2.4057583551917e-06, + "loss": 0.1407, + "step": 10678 + }, + { + "epoch": 1.37, + "learning_rate": 2.4048723529620246e-06, + "loss": 0.1402, + "step": 10679 + }, + { + "epoch": 1.37, + "learning_rate": 2.403986462250763e-06, + "loss": 0.1389, + "step": 10680 + }, + { + "epoch": 1.37, + "learning_rate": 2.4031006830959853e-06, + "loss": 0.1265, + "step": 10681 + }, + { + "epoch": 1.37, + "learning_rate": 2.4022150155357526e-06, + "loss": 0.1389, + "step": 10682 + }, + { + "epoch": 1.37, + "learning_rate": 2.40132945960813e-06, + "loss": 0.1434, + "step": 10683 + }, + { + "epoch": 1.37, + "learning_rate": 2.4004440153511642e-06, + "loss": 0.1433, + "step": 10684 + }, + { + "epoch": 1.37, + "learning_rate": 2.399558682802911e-06, + "loss": 0.1633, + "step": 10685 + }, + { + "epoch": 1.37, + "learning_rate": 2.3986734620014146e-06, + "loss": 0.128, + "step": 10686 + }, + { + "epoch": 1.37, + "learning_rate": 2.3977883529847087e-06, + "loss": 0.1394, + "step": 10687 + }, + { + "epoch": 1.37, + "learning_rate": 2.396903355790835e-06, + "loss": 0.1516, + "step": 10688 + }, + { + "epoch": 1.37, + "learning_rate": 2.396018470457821e-06, + "loss": 0.1403, + "step": 10689 + }, + { + "epoch": 1.37, + "learning_rate": 2.395133697023693e-06, + "loss": 0.1324, + "step": 10690 + }, + { + "epoch": 1.37, + "learning_rate": 2.394249035526472e-06, + "loss": 0.1399, + "step": 10691 + }, + { + "epoch": 1.37, + "learning_rate": 2.3933644860041703e-06, + "loss": 0.1442, + "step": 10692 + }, + { + "epoch": 1.37, + "learning_rate": 2.3924800484948045e-06, + "loss": 0.1404, + "step": 10693 + }, + { + "epoch": 1.37, + "learning_rate": 2.3915957230363783e-06, + "loss": 0.1419, + "step": 10694 + }, + { + "epoch": 1.37, + "learning_rate": 2.390711509666893e-06, + "loss": 0.1329, + "step": 10695 + }, + { + "epoch": 1.37, + "learning_rate": 2.389827408424345e-06, + "loss": 0.1325, + "step": 10696 + }, + { + "epoch": 1.37, + "learning_rate": 2.388943419346727e-06, + "loss": 0.1281, + "step": 10697 + }, + { + "epoch": 1.37, + "learning_rate": 2.388059542472025e-06, + "loss": 0.1481, + "step": 10698 + }, + { + "epoch": 1.37, + "learning_rate": 2.3871757778382216e-06, + "loss": 0.1602, + "step": 10699 + }, + { + "epoch": 1.37, + "learning_rate": 2.386292125483292e-06, + "loss": 0.1508, + "step": 10700 + }, + { + "epoch": 1.37, + "learning_rate": 2.385408585445215e-06, + "loss": 0.1321, + "step": 10701 + }, + { + "epoch": 1.37, + "learning_rate": 2.38452515776195e-06, + "loss": 0.1399, + "step": 10702 + }, + { + "epoch": 1.37, + "learning_rate": 2.3836418424714665e-06, + "loss": 0.1401, + "step": 10703 + }, + { + "epoch": 1.37, + "learning_rate": 2.3827586396117207e-06, + "loss": 0.1527, + "step": 10704 + }, + { + "epoch": 1.37, + "learning_rate": 2.3818755492206624e-06, + "loss": 0.1364, + "step": 10705 + }, + { + "epoch": 1.37, + "learning_rate": 2.3809925713362437e-06, + "loss": 0.1573, + "step": 10706 + }, + { + "epoch": 1.37, + "learning_rate": 2.3801097059964075e-06, + "loss": 0.1411, + "step": 10707 + }, + { + "epoch": 1.37, + "learning_rate": 2.3792269532390923e-06, + "loss": 0.1342, + "step": 10708 + }, + { + "epoch": 1.37, + "learning_rate": 2.378344313102231e-06, + "loss": 0.143, + "step": 10709 + }, + { + "epoch": 1.37, + "learning_rate": 2.377461785623752e-06, + "loss": 0.1375, + "step": 10710 + }, + { + "epoch": 1.37, + "learning_rate": 2.3765793708415825e-06, + "loss": 0.1427, + "step": 10711 + }, + { + "epoch": 1.37, + "learning_rate": 2.3756970687936397e-06, + "loss": 0.1339, + "step": 10712 + }, + { + "epoch": 1.37, + "learning_rate": 2.3748148795178387e-06, + "loss": 0.1452, + "step": 10713 + }, + { + "epoch": 1.37, + "learning_rate": 2.373932803052089e-06, + "loss": 0.1449, + "step": 10714 + }, + { + "epoch": 1.37, + "learning_rate": 2.3730508394342957e-06, + "loss": 0.128, + "step": 10715 + }, + { + "epoch": 1.37, + "learning_rate": 2.372168988702358e-06, + "loss": 0.1406, + "step": 10716 + }, + { + "epoch": 1.37, + "learning_rate": 2.3712872508941714e-06, + "loss": 0.1413, + "step": 10717 + }, + { + "epoch": 1.37, + "learning_rate": 2.3704056260476237e-06, + "loss": 0.1403, + "step": 10718 + }, + { + "epoch": 1.37, + "learning_rate": 2.369524114200607e-06, + "loss": 0.15, + "step": 10719 + }, + { + "epoch": 1.37, + "learning_rate": 2.368642715390994e-06, + "loss": 0.1352, + "step": 10720 + }, + { + "epoch": 1.37, + "learning_rate": 2.3677614296566654e-06, + "loss": 0.1506, + "step": 10721 + }, + { + "epoch": 1.37, + "learning_rate": 2.3668802570354903e-06, + "loss": 0.1401, + "step": 10722 + }, + { + "epoch": 1.37, + "learning_rate": 2.365999197565335e-06, + "loss": 0.1428, + "step": 10723 + }, + { + "epoch": 1.37, + "learning_rate": 2.3651182512840604e-06, + "loss": 0.1405, + "step": 10724 + }, + { + "epoch": 1.37, + "learning_rate": 2.3642374182295207e-06, + "loss": 0.1385, + "step": 10725 + }, + { + "epoch": 1.37, + "learning_rate": 2.363356698439573e-06, + "loss": 0.1334, + "step": 10726 + }, + { + "epoch": 1.37, + "learning_rate": 2.362476091952059e-06, + "loss": 0.1404, + "step": 10727 + }, + { + "epoch": 1.37, + "learning_rate": 2.361595598804819e-06, + "loss": 0.1302, + "step": 10728 + }, + { + "epoch": 1.37, + "learning_rate": 2.360715219035694e-06, + "loss": 0.1445, + "step": 10729 + }, + { + "epoch": 1.37, + "learning_rate": 2.3598349526825137e-06, + "loss": 0.1489, + "step": 10730 + }, + { + "epoch": 1.37, + "learning_rate": 2.358954799783106e-06, + "loss": 0.1337, + "step": 10731 + }, + { + "epoch": 1.37, + "learning_rate": 2.358074760375292e-06, + "loss": 0.1258, + "step": 10732 + }, + { + "epoch": 1.37, + "learning_rate": 2.3571948344968896e-06, + "loss": 0.131, + "step": 10733 + }, + { + "epoch": 1.37, + "learning_rate": 2.356315022185712e-06, + "loss": 0.1335, + "step": 10734 + }, + { + "epoch": 1.37, + "learning_rate": 2.3554353234795624e-06, + "loss": 0.1332, + "step": 10735 + }, + { + "epoch": 1.37, + "learning_rate": 2.3545557384162494e-06, + "loss": 0.1341, + "step": 10736 + }, + { + "epoch": 1.37, + "learning_rate": 2.3536762670335696e-06, + "loss": 0.1374, + "step": 10737 + }, + { + "epoch": 1.37, + "learning_rate": 2.3527969093693105e-06, + "loss": 0.1432, + "step": 10738 + }, + { + "epoch": 1.37, + "learning_rate": 2.3519176654612657e-06, + "loss": 0.1438, + "step": 10739 + }, + { + "epoch": 1.37, + "learning_rate": 2.3510385353472163e-06, + "loss": 0.138, + "step": 10740 + }, + { + "epoch": 1.37, + "learning_rate": 2.3501595190649405e-06, + "loss": 0.1394, + "step": 10741 + }, + { + "epoch": 1.37, + "learning_rate": 2.3492806166522125e-06, + "loss": 0.1393, + "step": 10742 + }, + { + "epoch": 1.38, + "learning_rate": 2.3484018281467973e-06, + "loss": 0.1412, + "step": 10743 + }, + { + "epoch": 1.38, + "learning_rate": 2.3475231535864653e-06, + "loss": 0.1388, + "step": 10744 + }, + { + "epoch": 1.38, + "learning_rate": 2.346644593008966e-06, + "loss": 0.1358, + "step": 10745 + }, + { + "epoch": 1.38, + "learning_rate": 2.3457661464520605e-06, + "loss": 0.1425, + "step": 10746 + }, + { + "epoch": 1.38, + "learning_rate": 2.3448878139534948e-06, + "loss": 0.1365, + "step": 10747 + }, + { + "epoch": 1.38, + "learning_rate": 2.344009595551013e-06, + "loss": 0.1543, + "step": 10748 + }, + { + "epoch": 1.38, + "learning_rate": 2.3431314912823543e-06, + "loss": 0.1313, + "step": 10749 + }, + { + "epoch": 1.38, + "learning_rate": 2.3422535011852522e-06, + "loss": 0.129, + "step": 10750 + }, + { + "epoch": 1.38, + "learning_rate": 2.3413756252974366e-06, + "loss": 0.1525, + "step": 10751 + }, + { + "epoch": 1.38, + "learning_rate": 2.3404978636566312e-06, + "loss": 0.1369, + "step": 10752 + }, + { + "epoch": 1.38, + "learning_rate": 2.3396202163005536e-06, + "loss": 0.1623, + "step": 10753 + }, + { + "epoch": 1.38, + "learning_rate": 2.338742683266923e-06, + "loss": 0.1456, + "step": 10754 + }, + { + "epoch": 1.38, + "learning_rate": 2.3378652645934473e-06, + "loss": 0.1273, + "step": 10755 + }, + { + "epoch": 1.38, + "learning_rate": 2.3369879603178264e-06, + "loss": 0.1397, + "step": 10756 + }, + { + "epoch": 1.38, + "learning_rate": 2.336110770477766e-06, + "loss": 0.1532, + "step": 10757 + }, + { + "epoch": 1.38, + "learning_rate": 2.3352336951109584e-06, + "loss": 0.1432, + "step": 10758 + }, + { + "epoch": 1.38, + "learning_rate": 2.3343567342550933e-06, + "loss": 0.1408, + "step": 10759 + }, + { + "epoch": 1.38, + "learning_rate": 2.3334798879478563e-06, + "loss": 0.163, + "step": 10760 + }, + { + "epoch": 1.38, + "learning_rate": 2.332603156226926e-06, + "loss": 0.1354, + "step": 10761 + }, + { + "epoch": 1.38, + "learning_rate": 2.3317265391299813e-06, + "loss": 0.1451, + "step": 10762 + }, + { + "epoch": 1.38, + "learning_rate": 2.330850036694687e-06, + "loss": 0.1441, + "step": 10763 + }, + { + "epoch": 1.38, + "learning_rate": 2.329973648958712e-06, + "loss": 0.144, + "step": 10764 + }, + { + "epoch": 1.38, + "learning_rate": 2.3290973759597165e-06, + "loss": 0.1517, + "step": 10765 + }, + { + "epoch": 1.38, + "learning_rate": 2.328221217735355e-06, + "loss": 0.1489, + "step": 10766 + }, + { + "epoch": 1.38, + "learning_rate": 2.3273451743232777e-06, + "loss": 0.1356, + "step": 10767 + }, + { + "epoch": 1.38, + "learning_rate": 2.326469245761131e-06, + "loss": 0.1414, + "step": 10768 + }, + { + "epoch": 1.38, + "learning_rate": 2.3255934320865555e-06, + "loss": 0.1649, + "step": 10769 + }, + { + "epoch": 1.38, + "learning_rate": 2.324717733337186e-06, + "loss": 0.1304, + "step": 10770 + }, + { + "epoch": 1.38, + "learning_rate": 2.3238421495506515e-06, + "loss": 0.127, + "step": 10771 + }, + { + "epoch": 1.38, + "learning_rate": 2.322966680764582e-06, + "loss": 0.1243, + "step": 10772 + }, + { + "epoch": 1.38, + "learning_rate": 2.322091327016597e-06, + "loss": 0.1333, + "step": 10773 + }, + { + "epoch": 1.38, + "learning_rate": 2.3212160883443107e-06, + "loss": 0.1461, + "step": 10774 + }, + { + "epoch": 1.38, + "learning_rate": 2.320340964785336e-06, + "loss": 0.145, + "step": 10775 + }, + { + "epoch": 1.38, + "learning_rate": 2.3194659563772754e-06, + "loss": 0.1444, + "step": 10776 + }, + { + "epoch": 1.38, + "learning_rate": 2.318591063157736e-06, + "loss": 0.1409, + "step": 10777 + }, + { + "epoch": 1.38, + "learning_rate": 2.317716285164309e-06, + "loss": 0.1393, + "step": 10778 + }, + { + "epoch": 1.38, + "learning_rate": 2.316841622434586e-06, + "loss": 0.1413, + "step": 10779 + }, + { + "epoch": 1.38, + "learning_rate": 2.3159670750061563e-06, + "loss": 0.1236, + "step": 10780 + }, + { + "epoch": 1.38, + "learning_rate": 2.3150926429165967e-06, + "loss": 0.1495, + "step": 10781 + }, + { + "epoch": 1.38, + "learning_rate": 2.3142183262034865e-06, + "loss": 0.1455, + "step": 10782 + }, + { + "epoch": 1.38, + "learning_rate": 2.3133441249043973e-06, + "loss": 0.1413, + "step": 10783 + }, + { + "epoch": 1.38, + "learning_rate": 2.3124700390568945e-06, + "loss": 0.1496, + "step": 10784 + }, + { + "epoch": 1.38, + "learning_rate": 2.311596068698539e-06, + "loss": 0.131, + "step": 10785 + }, + { + "epoch": 1.38, + "learning_rate": 2.3107222138668863e-06, + "loss": 0.138, + "step": 10786 + }, + { + "epoch": 1.38, + "learning_rate": 2.3098484745994933e-06, + "loss": 0.1473, + "step": 10787 + }, + { + "epoch": 1.38, + "learning_rate": 2.3089748509339007e-06, + "loss": 0.1467, + "step": 10788 + }, + { + "epoch": 1.38, + "learning_rate": 2.30810134290765e-06, + "loss": 0.1502, + "step": 10789 + }, + { + "epoch": 1.38, + "learning_rate": 2.307227950558281e-06, + "loss": 0.1216, + "step": 10790 + }, + { + "epoch": 1.38, + "learning_rate": 2.306354673923325e-06, + "loss": 0.1476, + "step": 10791 + }, + { + "epoch": 1.38, + "learning_rate": 2.3054815130403073e-06, + "loss": 0.1367, + "step": 10792 + }, + { + "epoch": 1.38, + "learning_rate": 2.3046084679467506e-06, + "loss": 0.1441, + "step": 10793 + }, + { + "epoch": 1.38, + "learning_rate": 2.3037355386801683e-06, + "loss": 0.1319, + "step": 10794 + }, + { + "epoch": 1.38, + "learning_rate": 2.3028627252780794e-06, + "loss": 0.1459, + "step": 10795 + }, + { + "epoch": 1.38, + "learning_rate": 2.3019900277779816e-06, + "loss": 0.136, + "step": 10796 + }, + { + "epoch": 1.38, + "learning_rate": 2.3011174462173836e-06, + "loss": 0.1292, + "step": 10797 + }, + { + "epoch": 1.38, + "learning_rate": 2.3002449806337807e-06, + "loss": 0.1331, + "step": 10798 + }, + { + "epoch": 1.38, + "learning_rate": 2.2993726310646603e-06, + "loss": 0.1255, + "step": 10799 + }, + { + "epoch": 1.38, + "learning_rate": 2.2985003975475146e-06, + "loss": 0.1231, + "step": 10800 + }, + { + "epoch": 1.38, + "learning_rate": 2.2976282801198237e-06, + "loss": 0.1353, + "step": 10801 + }, + { + "epoch": 1.38, + "learning_rate": 2.2967562788190633e-06, + "loss": 0.1308, + "step": 10802 + }, + { + "epoch": 1.38, + "learning_rate": 2.2958843936827064e-06, + "loss": 0.1666, + "step": 10803 + }, + { + "epoch": 1.38, + "learning_rate": 2.2950126247482178e-06, + "loss": 0.1429, + "step": 10804 + }, + { + "epoch": 1.38, + "learning_rate": 2.2941409720530642e-06, + "loss": 0.1431, + "step": 10805 + }, + { + "epoch": 1.38, + "learning_rate": 2.2932694356346986e-06, + "loss": 0.1487, + "step": 10806 + }, + { + "epoch": 1.38, + "learning_rate": 2.292398015530571e-06, + "loss": 0.156, + "step": 10807 + }, + { + "epoch": 1.38, + "learning_rate": 2.2915267117781328e-06, + "loss": 0.1402, + "step": 10808 + }, + { + "epoch": 1.38, + "learning_rate": 2.2906555244148233e-06, + "loss": 0.1327, + "step": 10809 + }, + { + "epoch": 1.38, + "learning_rate": 2.2897844534780805e-06, + "loss": 0.1404, + "step": 10810 + }, + { + "epoch": 1.38, + "learning_rate": 2.2889134990053356e-06, + "loss": 0.1473, + "step": 10811 + }, + { + "epoch": 1.38, + "learning_rate": 2.2880426610340135e-06, + "loss": 0.1328, + "step": 10812 + }, + { + "epoch": 1.38, + "learning_rate": 2.2871719396015423e-06, + "loss": 0.1379, + "step": 10813 + }, + { + "epoch": 1.38, + "learning_rate": 2.2863013347453305e-06, + "loss": 0.1497, + "step": 10814 + }, + { + "epoch": 1.38, + "learning_rate": 2.2854308465027963e-06, + "loss": 0.1346, + "step": 10815 + }, + { + "epoch": 1.38, + "learning_rate": 2.2845604749113457e-06, + "loss": 0.141, + "step": 10816 + }, + { + "epoch": 1.38, + "learning_rate": 2.2836902200083762e-06, + "loss": 0.1478, + "step": 10817 + }, + { + "epoch": 1.38, + "learning_rate": 2.2828200818312886e-06, + "loss": 0.1351, + "step": 10818 + }, + { + "epoch": 1.38, + "learning_rate": 2.2819500604174733e-06, + "loss": 0.1392, + "step": 10819 + }, + { + "epoch": 1.38, + "learning_rate": 2.2810801558043177e-06, + "loss": 0.148, + "step": 10820 + }, + { + "epoch": 1.39, + "learning_rate": 2.2802103680292037e-06, + "loss": 0.1406, + "step": 10821 + }, + { + "epoch": 1.39, + "learning_rate": 2.279340697129505e-06, + "loss": 0.1469, + "step": 10822 + }, + { + "epoch": 1.39, + "learning_rate": 2.2784711431426e-06, + "loss": 0.1356, + "step": 10823 + }, + { + "epoch": 1.39, + "learning_rate": 2.277601706105847e-06, + "loss": 0.1433, + "step": 10824 + }, + { + "epoch": 1.39, + "learning_rate": 2.2767323860566137e-06, + "loss": 0.1465, + "step": 10825 + }, + { + "epoch": 1.39, + "learning_rate": 2.2758631830322546e-06, + "loss": 0.1484, + "step": 10826 + }, + { + "epoch": 1.39, + "learning_rate": 2.274994097070122e-06, + "loss": 0.1255, + "step": 10827 + }, + { + "epoch": 1.39, + "learning_rate": 2.2741251282075617e-06, + "loss": 0.1463, + "step": 10828 + }, + { + "epoch": 1.39, + "learning_rate": 2.2732562764819157e-06, + "loss": 0.1339, + "step": 10829 + }, + { + "epoch": 1.39, + "learning_rate": 2.272387541930518e-06, + "loss": 0.1366, + "step": 10830 + }, + { + "epoch": 1.39, + "learning_rate": 2.2715189245907066e-06, + "loss": 0.1312, + "step": 10831 + }, + { + "epoch": 1.39, + "learning_rate": 2.2706504244997997e-06, + "loss": 0.1419, + "step": 10832 + }, + { + "epoch": 1.39, + "learning_rate": 2.269782041695124e-06, + "loss": 0.1498, + "step": 10833 + }, + { + "epoch": 1.39, + "learning_rate": 2.2689137762139952e-06, + "loss": 0.1516, + "step": 10834 + }, + { + "epoch": 1.39, + "learning_rate": 2.2680456280937234e-06, + "loss": 0.1437, + "step": 10835 + }, + { + "epoch": 1.39, + "learning_rate": 2.267177597371616e-06, + "loss": 0.1411, + "step": 10836 + }, + { + "epoch": 1.39, + "learning_rate": 2.266309684084971e-06, + "loss": 0.1503, + "step": 10837 + }, + { + "epoch": 1.39, + "learning_rate": 2.265441888271091e-06, + "loss": 0.1339, + "step": 10838 + }, + { + "epoch": 1.39, + "learning_rate": 2.264574209967262e-06, + "loss": 0.137, + "step": 10839 + }, + { + "epoch": 1.39, + "learning_rate": 2.263706649210769e-06, + "loss": 0.1367, + "step": 10840 + }, + { + "epoch": 1.39, + "learning_rate": 2.2628392060388986e-06, + "loss": 0.1262, + "step": 10841 + }, + { + "epoch": 1.39, + "learning_rate": 2.2619718804889203e-06, + "loss": 0.135, + "step": 10842 + }, + { + "epoch": 1.39, + "learning_rate": 2.26110467259811e-06, + "loss": 0.1365, + "step": 10843 + }, + { + "epoch": 1.39, + "learning_rate": 2.260237582403732e-06, + "loss": 0.1377, + "step": 10844 + }, + { + "epoch": 1.39, + "learning_rate": 2.259370609943046e-06, + "loss": 0.1412, + "step": 10845 + }, + { + "epoch": 1.39, + "learning_rate": 2.2585037552533097e-06, + "loss": 0.1278, + "step": 10846 + }, + { + "epoch": 1.39, + "learning_rate": 2.2576370183717704e-06, + "loss": 0.1387, + "step": 10847 + }, + { + "epoch": 1.39, + "learning_rate": 2.2567703993356775e-06, + "loss": 0.1359, + "step": 10848 + }, + { + "epoch": 1.39, + "learning_rate": 2.2559038981822724e-06, + "loss": 0.138, + "step": 10849 + }, + { + "epoch": 1.39, + "learning_rate": 2.255037514948785e-06, + "loss": 0.1416, + "step": 10850 + }, + { + "epoch": 1.39, + "learning_rate": 2.2541712496724495e-06, + "loss": 0.1275, + "step": 10851 + }, + { + "epoch": 1.39, + "learning_rate": 2.2533051023904913e-06, + "loss": 0.1423, + "step": 10852 + }, + { + "epoch": 1.39, + "learning_rate": 2.25243907314013e-06, + "loss": 0.1362, + "step": 10853 + }, + { + "epoch": 1.39, + "learning_rate": 2.2515731619585814e-06, + "loss": 0.1527, + "step": 10854 + }, + { + "epoch": 1.39, + "learning_rate": 2.250707368883052e-06, + "loss": 0.1445, + "step": 10855 + }, + { + "epoch": 1.39, + "learning_rate": 2.249841693950755e-06, + "loss": 0.1165, + "step": 10856 + }, + { + "epoch": 1.39, + "learning_rate": 2.2489761371988826e-06, + "loss": 0.1397, + "step": 10857 + }, + { + "epoch": 1.39, + "learning_rate": 2.2481106986646314e-06, + "loss": 0.1417, + "step": 10858 + }, + { + "epoch": 1.39, + "learning_rate": 2.247245378385195e-06, + "loss": 0.1499, + "step": 10859 + }, + { + "epoch": 1.39, + "learning_rate": 2.246380176397752e-06, + "loss": 0.1344, + "step": 10860 + }, + { + "epoch": 1.39, + "learning_rate": 2.245515092739488e-06, + "loss": 0.1321, + "step": 10861 + }, + { + "epoch": 1.39, + "learning_rate": 2.2446501274475747e-06, + "loss": 0.1438, + "step": 10862 + }, + { + "epoch": 1.39, + "learning_rate": 2.2437852805591815e-06, + "loss": 0.1276, + "step": 10863 + }, + { + "epoch": 1.39, + "learning_rate": 2.242920552111473e-06, + "loss": 0.1344, + "step": 10864 + }, + { + "epoch": 1.39, + "learning_rate": 2.2420559421416075e-06, + "loss": 0.1469, + "step": 10865 + }, + { + "epoch": 1.39, + "learning_rate": 2.241191450686743e-06, + "loss": 0.1356, + "step": 10866 + }, + { + "epoch": 1.39, + "learning_rate": 2.2403270777840262e-06, + "loss": 0.1297, + "step": 10867 + }, + { + "epoch": 1.39, + "learning_rate": 2.239462823470598e-06, + "loss": 0.1426, + "step": 10868 + }, + { + "epoch": 1.39, + "learning_rate": 2.238598687783603e-06, + "loss": 0.1346, + "step": 10869 + }, + { + "epoch": 1.39, + "learning_rate": 2.237734670760172e-06, + "loss": 0.1511, + "step": 10870 + }, + { + "epoch": 1.39, + "learning_rate": 2.236870772437433e-06, + "loss": 0.1419, + "step": 10871 + }, + { + "epoch": 1.39, + "learning_rate": 2.2360069928525118e-06, + "loss": 0.1569, + "step": 10872 + }, + { + "epoch": 1.39, + "learning_rate": 2.2351433320425237e-06, + "loss": 0.1473, + "step": 10873 + }, + { + "epoch": 1.39, + "learning_rate": 2.234279790044588e-06, + "loss": 0.1453, + "step": 10874 + }, + { + "epoch": 1.39, + "learning_rate": 2.2334163668958055e-06, + "loss": 0.1291, + "step": 10875 + }, + { + "epoch": 1.39, + "learning_rate": 2.2325530626332852e-06, + "loss": 0.1409, + "step": 10876 + }, + { + "epoch": 1.39, + "learning_rate": 2.231689877294123e-06, + "loss": 0.146, + "step": 10877 + }, + { + "epoch": 1.39, + "learning_rate": 2.2308268109154126e-06, + "loss": 0.1277, + "step": 10878 + }, + { + "epoch": 1.39, + "learning_rate": 2.229963863534241e-06, + "loss": 0.1365, + "step": 10879 + }, + { + "epoch": 1.39, + "learning_rate": 2.229101035187692e-06, + "loss": 0.1404, + "step": 10880 + }, + { + "epoch": 1.39, + "learning_rate": 2.2282383259128416e-06, + "loss": 0.131, + "step": 10881 + }, + { + "epoch": 1.39, + "learning_rate": 2.227375735746764e-06, + "loss": 0.134, + "step": 10882 + }, + { + "epoch": 1.39, + "learning_rate": 2.2265132647265243e-06, + "loss": 0.1479, + "step": 10883 + }, + { + "epoch": 1.39, + "learning_rate": 2.225650912889188e-06, + "loss": 0.1362, + "step": 10884 + }, + { + "epoch": 1.39, + "learning_rate": 2.224788680271811e-06, + "loss": 0.1363, + "step": 10885 + }, + { + "epoch": 1.39, + "learning_rate": 2.223926566911445e-06, + "loss": 0.1315, + "step": 10886 + }, + { + "epoch": 1.39, + "learning_rate": 2.223064572845137e-06, + "loss": 0.1324, + "step": 10887 + }, + { + "epoch": 1.39, + "learning_rate": 2.222202698109929e-06, + "loss": 0.1405, + "step": 10888 + }, + { + "epoch": 1.39, + "learning_rate": 2.221340942742858e-06, + "loss": 0.1456, + "step": 10889 + }, + { + "epoch": 1.39, + "learning_rate": 2.2204793067809545e-06, + "loss": 0.1522, + "step": 10890 + }, + { + "epoch": 1.39, + "learning_rate": 2.219617790261244e-06, + "loss": 0.1247, + "step": 10891 + }, + { + "epoch": 1.39, + "learning_rate": 2.218756393220753e-06, + "loss": 0.1475, + "step": 10892 + }, + { + "epoch": 1.39, + "learning_rate": 2.2178951156964895e-06, + "loss": 0.1539, + "step": 10893 + }, + { + "epoch": 1.39, + "learning_rate": 2.2170339577254714e-06, + "loss": 0.1272, + "step": 10894 + }, + { + "epoch": 1.39, + "learning_rate": 2.2161729193447024e-06, + "loss": 0.1551, + "step": 10895 + }, + { + "epoch": 1.39, + "learning_rate": 2.2153120005911825e-06, + "loss": 0.1405, + "step": 10896 + }, + { + "epoch": 1.39, + "learning_rate": 2.214451201501908e-06, + "loss": 0.1655, + "step": 10897 + }, + { + "epoch": 1.39, + "learning_rate": 2.213590522113867e-06, + "loss": 0.1268, + "step": 10898 + }, + { + "epoch": 1.4, + "learning_rate": 2.212729962464051e-06, + "loss": 0.1435, + "step": 10899 + }, + { + "epoch": 1.4, + "learning_rate": 2.2118695225894343e-06, + "loss": 0.1336, + "step": 10900 + }, + { + "epoch": 1.4, + "learning_rate": 2.2110092025269915e-06, + "loss": 0.1365, + "step": 10901 + }, + { + "epoch": 1.4, + "learning_rate": 2.210149002313697e-06, + "loss": 0.1403, + "step": 10902 + }, + { + "epoch": 1.4, + "learning_rate": 2.2092889219865127e-06, + "loss": 0.1391, + "step": 10903 + }, + { + "epoch": 1.4, + "learning_rate": 2.208428961582399e-06, + "loss": 0.1428, + "step": 10904 + }, + { + "epoch": 1.4, + "learning_rate": 2.2075691211383094e-06, + "loss": 0.1302, + "step": 10905 + }, + { + "epoch": 1.4, + "learning_rate": 2.2067094006911943e-06, + "loss": 0.1193, + "step": 10906 + }, + { + "epoch": 1.4, + "learning_rate": 2.205849800277997e-06, + "loss": 0.142, + "step": 10907 + }, + { + "epoch": 1.4, + "learning_rate": 2.204990319935657e-06, + "loss": 0.1333, + "step": 10908 + }, + { + "epoch": 1.4, + "learning_rate": 2.2041309597011057e-06, + "loss": 0.1319, + "step": 10909 + }, + { + "epoch": 1.4, + "learning_rate": 2.2032717196112776e-06, + "loss": 0.1382, + "step": 10910 + }, + { + "epoch": 1.4, + "learning_rate": 2.2024125997030885e-06, + "loss": 0.1604, + "step": 10911 + }, + { + "epoch": 1.4, + "learning_rate": 2.2015536000134624e-06, + "loss": 0.1459, + "step": 10912 + }, + { + "epoch": 1.4, + "learning_rate": 2.2006947205793107e-06, + "loss": 0.1388, + "step": 10913 + }, + { + "epoch": 1.4, + "learning_rate": 2.1998359614375412e-06, + "loss": 0.1394, + "step": 10914 + }, + { + "epoch": 1.4, + "learning_rate": 2.198977322625057e-06, + "loss": 0.1391, + "step": 10915 + }, + { + "epoch": 1.4, + "learning_rate": 2.1981188041787534e-06, + "loss": 0.1505, + "step": 10916 + }, + { + "epoch": 1.4, + "learning_rate": 2.1972604061355285e-06, + "loss": 0.1363, + "step": 10917 + }, + { + "epoch": 1.4, + "learning_rate": 2.196402128532264e-06, + "loss": 0.1534, + "step": 10918 + }, + { + "epoch": 1.4, + "learning_rate": 2.1955439714058422e-06, + "loss": 0.1252, + "step": 10919 + }, + { + "epoch": 1.4, + "learning_rate": 2.1946859347931442e-06, + "loss": 0.1302, + "step": 10920 + }, + { + "epoch": 1.4, + "learning_rate": 2.193828018731039e-06, + "loss": 0.1355, + "step": 10921 + }, + { + "epoch": 1.4, + "learning_rate": 2.192970223256393e-06, + "loss": 0.1242, + "step": 10922 + }, + { + "epoch": 1.4, + "learning_rate": 2.1921125484060692e-06, + "loss": 0.1403, + "step": 10923 + }, + { + "epoch": 1.4, + "learning_rate": 2.191254994216922e-06, + "loss": 0.1461, + "step": 10924 + }, + { + "epoch": 1.4, + "learning_rate": 2.1903975607258025e-06, + "loss": 0.1437, + "step": 10925 + }, + { + "epoch": 1.4, + "learning_rate": 2.1895402479695566e-06, + "loss": 0.1309, + "step": 10926 + }, + { + "epoch": 1.4, + "learning_rate": 2.1886830559850264e-06, + "loss": 0.1415, + "step": 10927 + }, + { + "epoch": 1.4, + "learning_rate": 2.187825984809049e-06, + "loss": 0.1282, + "step": 10928 + }, + { + "epoch": 1.4, + "learning_rate": 2.186969034478448e-06, + "loss": 0.1183, + "step": 10929 + }, + { + "epoch": 1.4, + "learning_rate": 2.186112205030054e-06, + "loss": 0.1367, + "step": 10930 + }, + { + "epoch": 1.4, + "learning_rate": 2.1852554965006854e-06, + "loss": 0.1357, + "step": 10931 + }, + { + "epoch": 1.4, + "learning_rate": 2.1843989089271572e-06, + "loss": 0.1335, + "step": 10932 + }, + { + "epoch": 1.4, + "learning_rate": 2.183542442346279e-06, + "loss": 0.1485, + "step": 10933 + }, + { + "epoch": 1.4, + "learning_rate": 2.182686096794852e-06, + "loss": 0.1528, + "step": 10934 + }, + { + "epoch": 1.4, + "learning_rate": 2.181829872309682e-06, + "loss": 0.1471, + "step": 10935 + }, + { + "epoch": 1.4, + "learning_rate": 2.180973768927555e-06, + "loss": 0.1307, + "step": 10936 + }, + { + "epoch": 1.4, + "learning_rate": 2.1801177866852658e-06, + "loss": 0.143, + "step": 10937 + }, + { + "epoch": 1.4, + "learning_rate": 2.179261925619595e-06, + "loss": 0.1366, + "step": 10938 + }, + { + "epoch": 1.4, + "learning_rate": 2.1784061857673217e-06, + "loss": 0.126, + "step": 10939 + }, + { + "epoch": 1.4, + "learning_rate": 2.177550567165218e-06, + "loss": 0.1618, + "step": 10940 + }, + { + "epoch": 1.4, + "learning_rate": 2.176695069850053e-06, + "loss": 0.1446, + "step": 10941 + }, + { + "epoch": 1.4, + "learning_rate": 2.1758396938585885e-06, + "loss": 0.1408, + "step": 10942 + }, + { + "epoch": 1.4, + "learning_rate": 2.174984439227582e-06, + "loss": 0.1307, + "step": 10943 + }, + { + "epoch": 1.4, + "learning_rate": 2.174129305993784e-06, + "loss": 0.1414, + "step": 10944 + }, + { + "epoch": 1.4, + "learning_rate": 2.173274294193945e-06, + "loss": 0.1352, + "step": 10945 + }, + { + "epoch": 1.4, + "learning_rate": 2.1724194038648057e-06, + "loss": 0.1368, + "step": 10946 + }, + { + "epoch": 1.4, + "learning_rate": 2.1715646350431015e-06, + "loss": 0.1404, + "step": 10947 + }, + { + "epoch": 1.4, + "learning_rate": 2.1707099877655634e-06, + "loss": 0.1261, + "step": 10948 + }, + { + "epoch": 1.4, + "learning_rate": 2.1698554620689178e-06, + "loss": 0.1397, + "step": 10949 + }, + { + "epoch": 1.4, + "learning_rate": 2.169001057989889e-06, + "loss": 0.1325, + "step": 10950 + }, + { + "epoch": 1.4, + "learning_rate": 2.1681467755651882e-06, + "loss": 0.1261, + "step": 10951 + }, + { + "epoch": 1.4, + "learning_rate": 2.1672926148315247e-06, + "loss": 0.1419, + "step": 10952 + }, + { + "epoch": 1.4, + "learning_rate": 2.1664385758256106e-06, + "loss": 0.1193, + "step": 10953 + }, + { + "epoch": 1.4, + "learning_rate": 2.165584658584138e-06, + "loss": 0.1429, + "step": 10954 + }, + { + "epoch": 1.4, + "learning_rate": 2.1647308631438068e-06, + "loss": 0.1543, + "step": 10955 + }, + { + "epoch": 1.4, + "learning_rate": 2.163877189541305e-06, + "loss": 0.1523, + "step": 10956 + }, + { + "epoch": 1.4, + "learning_rate": 2.1630236378133168e-06, + "loss": 0.1303, + "step": 10957 + }, + { + "epoch": 1.4, + "learning_rate": 2.1621702079965214e-06, + "loss": 0.1398, + "step": 10958 + }, + { + "epoch": 1.4, + "learning_rate": 2.16131690012759e-06, + "loss": 0.137, + "step": 10959 + }, + { + "epoch": 1.4, + "learning_rate": 2.1604637142431978e-06, + "loss": 0.1406, + "step": 10960 + }, + { + "epoch": 1.4, + "learning_rate": 2.1596106503800013e-06, + "loss": 0.1385, + "step": 10961 + }, + { + "epoch": 1.4, + "learning_rate": 2.1587577085746596e-06, + "loss": 0.1483, + "step": 10962 + }, + { + "epoch": 1.4, + "learning_rate": 2.157904888863829e-06, + "loss": 0.1434, + "step": 10963 + }, + { + "epoch": 1.4, + "learning_rate": 2.157052191284154e-06, + "loss": 0.1416, + "step": 10964 + }, + { + "epoch": 1.4, + "learning_rate": 2.1561996158722785e-06, + "loss": 0.149, + "step": 10965 + }, + { + "epoch": 1.4, + "learning_rate": 2.1553471626648392e-06, + "loss": 0.1442, + "step": 10966 + }, + { + "epoch": 1.4, + "learning_rate": 2.1544948316984658e-06, + "loss": 0.1467, + "step": 10967 + }, + { + "epoch": 1.4, + "learning_rate": 2.1536426230097906e-06, + "loss": 0.1227, + "step": 10968 + }, + { + "epoch": 1.4, + "learning_rate": 2.1527905366354292e-06, + "loss": 0.1403, + "step": 10969 + }, + { + "epoch": 1.4, + "learning_rate": 2.1519385726119972e-06, + "loss": 0.1373, + "step": 10970 + }, + { + "epoch": 1.4, + "learning_rate": 2.151086730976112e-06, + "loss": 0.1453, + "step": 10971 + }, + { + "epoch": 1.4, + "learning_rate": 2.1502350117643704e-06, + "loss": 0.1368, + "step": 10972 + }, + { + "epoch": 1.4, + "learning_rate": 2.1493834150133795e-06, + "loss": 0.1429, + "step": 10973 + }, + { + "epoch": 1.4, + "learning_rate": 2.1485319407597315e-06, + "loss": 0.1534, + "step": 10974 + }, + { + "epoch": 1.4, + "learning_rate": 2.1476805890400172e-06, + "loss": 0.1499, + "step": 10975 + }, + { + "epoch": 1.4, + "learning_rate": 2.14682935989082e-06, + "loss": 0.1342, + "step": 10976 + }, + { + "epoch": 1.41, + "learning_rate": 2.1459782533487176e-06, + "loss": 0.1412, + "step": 10977 + }, + { + "epoch": 1.41, + "learning_rate": 2.14512726945029e-06, + "loss": 0.1575, + "step": 10978 + }, + { + "epoch": 1.41, + "learning_rate": 2.1442764082321e-06, + "loss": 0.1323, + "step": 10979 + }, + { + "epoch": 1.41, + "learning_rate": 2.1434256697307103e-06, + "loss": 0.1419, + "step": 10980 + }, + { + "epoch": 1.41, + "learning_rate": 2.142575053982684e-06, + "loss": 0.13, + "step": 10981 + }, + { + "epoch": 1.41, + "learning_rate": 2.1417245610245714e-06, + "loss": 0.1587, + "step": 10982 + }, + { + "epoch": 1.41, + "learning_rate": 2.14087419089292e-06, + "loss": 0.1431, + "step": 10983 + }, + { + "epoch": 1.41, + "learning_rate": 2.140023943624272e-06, + "loss": 0.1531, + "step": 10984 + }, + { + "epoch": 1.41, + "learning_rate": 2.139173819255163e-06, + "loss": 0.1387, + "step": 10985 + }, + { + "epoch": 1.41, + "learning_rate": 2.13832381782213e-06, + "loss": 0.1416, + "step": 10986 + }, + { + "epoch": 1.41, + "learning_rate": 2.1374739393616923e-06, + "loss": 0.1367, + "step": 10987 + }, + { + "epoch": 1.41, + "learning_rate": 2.1366241839103764e-06, + "loss": 0.1374, + "step": 10988 + }, + { + "epoch": 1.41, + "learning_rate": 2.135774551504698e-06, + "loss": 0.1448, + "step": 10989 + }, + { + "epoch": 1.41, + "learning_rate": 2.1349250421811622e-06, + "loss": 0.1519, + "step": 10990 + }, + { + "epoch": 1.41, + "learning_rate": 2.1340756559762808e-06, + "loss": 0.1493, + "step": 10991 + }, + { + "epoch": 1.41, + "learning_rate": 2.1332263929265505e-06, + "loss": 0.144, + "step": 10992 + }, + { + "epoch": 1.41, + "learning_rate": 2.132377253068467e-06, + "loss": 0.1383, + "step": 10993 + }, + { + "epoch": 1.41, + "learning_rate": 2.1315282364385197e-06, + "loss": 0.137, + "step": 10994 + }, + { + "epoch": 1.41, + "learning_rate": 2.1306793430731908e-06, + "loss": 0.154, + "step": 10995 + }, + { + "epoch": 1.41, + "learning_rate": 2.1298305730089626e-06, + "loss": 0.1448, + "step": 10996 + }, + { + "epoch": 1.41, + "learning_rate": 2.1289819262823065e-06, + "loss": 0.1335, + "step": 10997 + }, + { + "epoch": 1.41, + "learning_rate": 2.1281334029296913e-06, + "loss": 0.135, + "step": 10998 + }, + { + "epoch": 1.41, + "learning_rate": 2.1272850029875802e-06, + "loss": 0.147, + "step": 10999 + }, + { + "epoch": 1.41, + "learning_rate": 2.1264367264924295e-06, + "loss": 0.1377, + "step": 11000 + }, + { + "epoch": 1.41, + "learning_rate": 2.125588573480693e-06, + "loss": 0.1188, + "step": 11001 + }, + { + "epoch": 1.41, + "learning_rate": 2.1247405439888173e-06, + "loss": 0.1204, + "step": 11002 + }, + { + "epoch": 1.41, + "learning_rate": 2.1238926380532423e-06, + "loss": 0.1444, + "step": 11003 + }, + { + "epoch": 1.41, + "learning_rate": 2.1230448557104087e-06, + "loss": 0.1415, + "step": 11004 + }, + { + "epoch": 1.41, + "learning_rate": 2.1221971969967424e-06, + "loss": 0.1445, + "step": 11005 + }, + { + "epoch": 1.41, + "learning_rate": 2.121349661948673e-06, + "loss": 0.15, + "step": 11006 + }, + { + "epoch": 1.41, + "learning_rate": 2.12050225060262e-06, + "loss": 0.1265, + "step": 11007 + }, + { + "epoch": 1.41, + "learning_rate": 2.119654962994998e-06, + "loss": 0.1572, + "step": 11008 + }, + { + "epoch": 1.41, + "learning_rate": 2.1188077991622174e-06, + "loss": 0.1486, + "step": 11009 + }, + { + "epoch": 1.41, + "learning_rate": 2.1179607591406807e-06, + "loss": 0.1485, + "step": 11010 + }, + { + "epoch": 1.41, + "learning_rate": 2.117113842966792e-06, + "loss": 0.1252, + "step": 11011 + }, + { + "epoch": 1.41, + "learning_rate": 2.1162670506769408e-06, + "loss": 0.1282, + "step": 11012 + }, + { + "epoch": 1.41, + "learning_rate": 2.1154203823075146e-06, + "loss": 0.1254, + "step": 11013 + }, + { + "epoch": 1.41, + "learning_rate": 2.1145738378949004e-06, + "loss": 0.1478, + "step": 11014 + }, + { + "epoch": 1.41, + "learning_rate": 2.113727417475475e-06, + "loss": 0.1329, + "step": 11015 + }, + { + "epoch": 1.41, + "learning_rate": 2.112881121085611e-06, + "loss": 0.1353, + "step": 11016 + }, + { + "epoch": 1.41, + "learning_rate": 2.112034948761674e-06, + "loss": 0.1305, + "step": 11017 + }, + { + "epoch": 1.41, + "learning_rate": 2.111188900540028e-06, + "loss": 0.1365, + "step": 11018 + }, + { + "epoch": 1.41, + "learning_rate": 2.110342976457029e-06, + "loss": 0.1369, + "step": 11019 + }, + { + "epoch": 1.41, + "learning_rate": 2.1094971765490266e-06, + "loss": 0.1271, + "step": 11020 + }, + { + "epoch": 1.41, + "learning_rate": 2.108651500852367e-06, + "loss": 0.1218, + "step": 11021 + }, + { + "epoch": 1.41, + "learning_rate": 2.107805949403396e-06, + "loss": 0.139, + "step": 11022 + }, + { + "epoch": 1.41, + "learning_rate": 2.10696052223844e-06, + "loss": 0.1236, + "step": 11023 + }, + { + "epoch": 1.41, + "learning_rate": 2.1061152193938355e-06, + "loss": 0.1461, + "step": 11024 + }, + { + "epoch": 1.41, + "learning_rate": 2.1052700409059057e-06, + "loss": 0.1304, + "step": 11025 + }, + { + "epoch": 1.41, + "learning_rate": 2.1044249868109683e-06, + "loss": 0.1444, + "step": 11026 + }, + { + "epoch": 1.41, + "learning_rate": 2.1035800571453386e-06, + "loss": 0.1513, + "step": 11027 + }, + { + "epoch": 1.41, + "learning_rate": 2.1027352519453225e-06, + "loss": 0.1299, + "step": 11028 + }, + { + "epoch": 1.41, + "learning_rate": 2.1018905712472285e-06, + "loss": 0.1363, + "step": 11029 + }, + { + "epoch": 1.41, + "learning_rate": 2.1010460150873495e-06, + "loss": 0.1503, + "step": 11030 + }, + { + "epoch": 1.41, + "learning_rate": 2.1002015835019777e-06, + "loss": 0.1374, + "step": 11031 + }, + { + "epoch": 1.41, + "learning_rate": 2.0993572765274044e-06, + "loss": 0.1388, + "step": 11032 + }, + { + "epoch": 1.41, + "learning_rate": 2.098513094199909e-06, + "loss": 0.1423, + "step": 11033 + }, + { + "epoch": 1.41, + "learning_rate": 2.0976690365557673e-06, + "loss": 0.1495, + "step": 11034 + }, + { + "epoch": 1.41, + "learning_rate": 2.096825103631251e-06, + "loss": 0.1348, + "step": 11035 + }, + { + "epoch": 1.41, + "learning_rate": 2.0959812954626256e-06, + "loss": 0.1415, + "step": 11036 + }, + { + "epoch": 1.41, + "learning_rate": 2.0951376120861523e-06, + "loss": 0.136, + "step": 11037 + }, + { + "epoch": 1.41, + "learning_rate": 2.0942940535380823e-06, + "loss": 0.1454, + "step": 11038 + }, + { + "epoch": 1.41, + "learning_rate": 2.093450619854671e-06, + "loss": 0.1448, + "step": 11039 + }, + { + "epoch": 1.41, + "learning_rate": 2.0926073110721613e-06, + "loss": 0.1397, + "step": 11040 + }, + { + "epoch": 1.41, + "learning_rate": 2.0917641272267867e-06, + "loss": 0.1343, + "step": 11041 + }, + { + "epoch": 1.41, + "learning_rate": 2.0909210683547865e-06, + "loss": 0.1437, + "step": 11042 + }, + { + "epoch": 1.41, + "learning_rate": 2.0900781344923872e-06, + "loss": 0.1411, + "step": 11043 + }, + { + "epoch": 1.41, + "learning_rate": 2.0892353256758107e-06, + "loss": 0.1631, + "step": 11044 + }, + { + "epoch": 1.41, + "learning_rate": 2.0883926419412748e-06, + "loss": 0.1428, + "step": 11045 + }, + { + "epoch": 1.41, + "learning_rate": 2.08755008332499e-06, + "loss": 0.1494, + "step": 11046 + }, + { + "epoch": 1.41, + "learning_rate": 2.0867076498631685e-06, + "loss": 0.1245, + "step": 11047 + }, + { + "epoch": 1.41, + "learning_rate": 2.0858653415920034e-06, + "loss": 0.141, + "step": 11048 + }, + { + "epoch": 1.41, + "learning_rate": 2.0850231585476965e-06, + "loss": 0.1461, + "step": 11049 + }, + { + "epoch": 1.41, + "learning_rate": 2.084181100766437e-06, + "loss": 0.1426, + "step": 11050 + }, + { + "epoch": 1.41, + "learning_rate": 2.083339168284409e-06, + "loss": 0.1499, + "step": 11051 + }, + { + "epoch": 1.41, + "learning_rate": 2.0824973611377924e-06, + "loss": 0.1234, + "step": 11052 + }, + { + "epoch": 1.41, + "learning_rate": 2.0816556793627624e-06, + "loss": 0.1287, + "step": 11053 + }, + { + "epoch": 1.41, + "learning_rate": 2.0808141229954876e-06, + "loss": 0.1618, + "step": 11054 + }, + { + "epoch": 1.42, + "learning_rate": 2.079972692072131e-06, + "loss": 0.1404, + "step": 11055 + }, + { + "epoch": 1.42, + "learning_rate": 2.0791313866288485e-06, + "loss": 0.1383, + "step": 11056 + }, + { + "epoch": 1.42, + "learning_rate": 2.078290206701798e-06, + "loss": 0.1215, + "step": 11057 + }, + { + "epoch": 1.42, + "learning_rate": 2.0774491523271243e-06, + "loss": 0.1362, + "step": 11058 + }, + { + "epoch": 1.42, + "learning_rate": 2.0766082235409695e-06, + "loss": 0.1324, + "step": 11059 + }, + { + "epoch": 1.42, + "learning_rate": 2.0757674203794696e-06, + "loss": 0.128, + "step": 11060 + }, + { + "epoch": 1.42, + "learning_rate": 2.074926742878757e-06, + "loss": 0.1316, + "step": 11061 + }, + { + "epoch": 1.42, + "learning_rate": 2.074086191074956e-06, + "loss": 0.1541, + "step": 11062 + }, + { + "epoch": 1.42, + "learning_rate": 2.0732457650041884e-06, + "loss": 0.1536, + "step": 11063 + }, + { + "epoch": 1.42, + "learning_rate": 2.072405464702566e-06, + "loss": 0.1497, + "step": 11064 + }, + { + "epoch": 1.42, + "learning_rate": 2.071565290206205e-06, + "loss": 0.1396, + "step": 11065 + }, + { + "epoch": 1.42, + "learning_rate": 2.0707252415512015e-06, + "loss": 0.1289, + "step": 11066 + }, + { + "epoch": 1.42, + "learning_rate": 2.06988531877366e-06, + "loss": 0.1373, + "step": 11067 + }, + { + "epoch": 1.42, + "learning_rate": 2.069045521909672e-06, + "loss": 0.1288, + "step": 11068 + }, + { + "epoch": 1.42, + "learning_rate": 2.068205850995326e-06, + "loss": 0.1447, + "step": 11069 + }, + { + "epoch": 1.42, + "learning_rate": 2.067366306066704e-06, + "loss": 0.1283, + "step": 11070 + }, + { + "epoch": 1.42, + "learning_rate": 2.0665268871598832e-06, + "loss": 0.1343, + "step": 11071 + }, + { + "epoch": 1.42, + "learning_rate": 2.065687594310935e-06, + "loss": 0.1457, + "step": 11072 + }, + { + "epoch": 1.42, + "learning_rate": 2.064848427555926e-06, + "loss": 0.1311, + "step": 11073 + }, + { + "epoch": 1.42, + "learning_rate": 2.064009386930915e-06, + "loss": 0.1344, + "step": 11074 + }, + { + "epoch": 1.42, + "learning_rate": 2.0631704724719613e-06, + "loss": 0.1478, + "step": 11075 + }, + { + "epoch": 1.42, + "learning_rate": 2.0623316842151132e-06, + "loss": 0.1487, + "step": 11076 + }, + { + "epoch": 1.42, + "learning_rate": 2.061493022196415e-06, + "loss": 0.1435, + "step": 11077 + }, + { + "epoch": 1.42, + "learning_rate": 2.0606544864519064e-06, + "loss": 0.145, + "step": 11078 + }, + { + "epoch": 1.42, + "learning_rate": 2.0598160770176208e-06, + "loss": 0.1565, + "step": 11079 + }, + { + "epoch": 1.42, + "learning_rate": 2.0589777939295855e-06, + "loss": 0.1422, + "step": 11080 + }, + { + "epoch": 1.42, + "learning_rate": 2.0581396372238254e-06, + "loss": 0.13, + "step": 11081 + }, + { + "epoch": 1.42, + "learning_rate": 2.0573016069363554e-06, + "loss": 0.1455, + "step": 11082 + }, + { + "epoch": 1.42, + "learning_rate": 2.056463703103192e-06, + "loss": 0.1419, + "step": 11083 + }, + { + "epoch": 1.42, + "learning_rate": 2.0556259257603355e-06, + "loss": 0.1449, + "step": 11084 + }, + { + "epoch": 1.42, + "learning_rate": 2.0547882749437923e-06, + "loss": 0.1534, + "step": 11085 + }, + { + "epoch": 1.42, + "learning_rate": 2.053950750689556e-06, + "loss": 0.1479, + "step": 11086 + }, + { + "epoch": 1.42, + "learning_rate": 2.053113353033618e-06, + "loss": 0.1509, + "step": 11087 + }, + { + "epoch": 1.42, + "learning_rate": 2.0522760820119615e-06, + "loss": 0.1312, + "step": 11088 + }, + { + "epoch": 1.42, + "learning_rate": 2.0514389376605646e-06, + "loss": 0.14, + "step": 11089 + }, + { + "epoch": 1.42, + "learning_rate": 2.0506019200154076e-06, + "loss": 0.1171, + "step": 11090 + }, + { + "epoch": 1.42, + "learning_rate": 2.049765029112453e-06, + "loss": 0.1383, + "step": 11091 + }, + { + "epoch": 1.42, + "learning_rate": 2.0489282649876633e-06, + "loss": 0.1496, + "step": 11092 + }, + { + "epoch": 1.42, + "learning_rate": 2.0480916276770005e-06, + "loss": 0.149, + "step": 11093 + }, + { + "epoch": 1.42, + "learning_rate": 2.0472551172164152e-06, + "loss": 0.1417, + "step": 11094 + }, + { + "epoch": 1.42, + "learning_rate": 2.046418733641853e-06, + "loss": 0.1391, + "step": 11095 + }, + { + "epoch": 1.42, + "learning_rate": 2.0455824769892556e-06, + "loss": 0.1496, + "step": 11096 + }, + { + "epoch": 1.42, + "learning_rate": 2.0447463472945593e-06, + "loss": 0.143, + "step": 11097 + }, + { + "epoch": 1.42, + "learning_rate": 2.0439103445936946e-06, + "loss": 0.1323, + "step": 11098 + }, + { + "epoch": 1.42, + "learning_rate": 2.0430744689225833e-06, + "loss": 0.1354, + "step": 11099 + }, + { + "epoch": 1.42, + "learning_rate": 2.0422387203171503e-06, + "loss": 0.1323, + "step": 11100 + }, + { + "epoch": 1.42, + "learning_rate": 2.0414030988133076e-06, + "loss": 0.1345, + "step": 11101 + }, + { + "epoch": 1.42, + "learning_rate": 2.04056760444696e-06, + "loss": 0.1293, + "step": 11102 + }, + { + "epoch": 1.42, + "learning_rate": 2.039732237254015e-06, + "loss": 0.1244, + "step": 11103 + }, + { + "epoch": 1.42, + "learning_rate": 2.0388969972703688e-06, + "loss": 0.1324, + "step": 11104 + }, + { + "epoch": 1.42, + "learning_rate": 2.0380618845319132e-06, + "loss": 0.1301, + "step": 11105 + }, + { + "epoch": 1.42, + "learning_rate": 2.0372268990745347e-06, + "loss": 0.1345, + "step": 11106 + }, + { + "epoch": 1.42, + "learning_rate": 2.036392040934114e-06, + "loss": 0.1465, + "step": 11107 + }, + { + "epoch": 1.42, + "learning_rate": 2.03555731014653e-06, + "loss": 0.1348, + "step": 11108 + }, + { + "epoch": 1.42, + "learning_rate": 2.0347227067476478e-06, + "loss": 0.1441, + "step": 11109 + }, + { + "epoch": 1.42, + "learning_rate": 2.033888230773336e-06, + "loss": 0.1474, + "step": 11110 + }, + { + "epoch": 1.42, + "learning_rate": 2.0330538822594532e-06, + "loss": 0.1518, + "step": 11111 + }, + { + "epoch": 1.42, + "learning_rate": 2.0322196612418527e-06, + "loss": 0.1438, + "step": 11112 + }, + { + "epoch": 1.42, + "learning_rate": 2.031385567756383e-06, + "loss": 0.1369, + "step": 11113 + }, + { + "epoch": 1.42, + "learning_rate": 2.030551601838887e-06, + "loss": 0.1607, + "step": 11114 + }, + { + "epoch": 1.42, + "learning_rate": 2.029717763525202e-06, + "loss": 0.1405, + "step": 11115 + }, + { + "epoch": 1.42, + "learning_rate": 2.02888405285116e-06, + "loss": 0.1489, + "step": 11116 + }, + { + "epoch": 1.42, + "learning_rate": 2.0280504698525856e-06, + "loss": 0.1261, + "step": 11117 + }, + { + "epoch": 1.42, + "learning_rate": 2.0272170145653025e-06, + "loss": 0.1399, + "step": 11118 + }, + { + "epoch": 1.42, + "learning_rate": 2.0263836870251277e-06, + "loss": 0.1376, + "step": 11119 + }, + { + "epoch": 1.42, + "learning_rate": 2.025550487267864e-06, + "loss": 0.1447, + "step": 11120 + }, + { + "epoch": 1.42, + "learning_rate": 2.0247174153293226e-06, + "loss": 0.1282, + "step": 11121 + }, + { + "epoch": 1.42, + "learning_rate": 2.0238844712453e-06, + "loss": 0.128, + "step": 11122 + }, + { + "epoch": 1.42, + "learning_rate": 2.02305165505159e-06, + "loss": 0.1437, + "step": 11123 + }, + { + "epoch": 1.42, + "learning_rate": 2.0222189667839805e-06, + "loss": 0.1511, + "step": 11124 + }, + { + "epoch": 1.42, + "learning_rate": 2.0213864064782516e-06, + "loss": 0.1396, + "step": 11125 + }, + { + "epoch": 1.42, + "learning_rate": 2.020553974170186e-06, + "loss": 0.1528, + "step": 11126 + }, + { + "epoch": 1.42, + "learning_rate": 2.019721669895549e-06, + "loss": 0.1272, + "step": 11127 + }, + { + "epoch": 1.42, + "learning_rate": 2.018889493690111e-06, + "loss": 0.1289, + "step": 11128 + }, + { + "epoch": 1.42, + "learning_rate": 2.01805744558963e-06, + "loss": 0.1404, + "step": 11129 + }, + { + "epoch": 1.42, + "learning_rate": 2.0172255256298623e-06, + "loss": 0.1421, + "step": 11130 + }, + { + "epoch": 1.42, + "learning_rate": 2.016393733846557e-06, + "loss": 0.1422, + "step": 11131 + }, + { + "epoch": 1.42, + "learning_rate": 2.015562070275457e-06, + "loss": 0.1407, + "step": 11132 + }, + { + "epoch": 1.43, + "learning_rate": 2.0147305349523e-06, + "loss": 0.14, + "step": 11133 + }, + { + "epoch": 1.43, + "learning_rate": 2.013899127912824e-06, + "loss": 0.135, + "step": 11134 + }, + { + "epoch": 1.43, + "learning_rate": 2.0130678491927495e-06, + "loss": 0.1429, + "step": 11135 + }, + { + "epoch": 1.43, + "learning_rate": 2.0122366988278035e-06, + "loss": 0.1343, + "step": 11136 + }, + { + "epoch": 1.43, + "learning_rate": 2.0114056768537005e-06, + "loss": 0.1369, + "step": 11137 + }, + { + "epoch": 1.43, + "learning_rate": 2.0105747833061516e-06, + "loss": 0.1354, + "step": 11138 + }, + { + "epoch": 1.43, + "learning_rate": 2.009744018220863e-06, + "loss": 0.1416, + "step": 11139 + }, + { + "epoch": 1.43, + "learning_rate": 2.0089133816335303e-06, + "loss": 0.1282, + "step": 11140 + }, + { + "epoch": 1.43, + "learning_rate": 2.0080828735798554e-06, + "loss": 0.1647, + "step": 11141 + }, + { + "epoch": 1.43, + "learning_rate": 2.0072524940955213e-06, + "loss": 0.1153, + "step": 11142 + }, + { + "epoch": 1.43, + "learning_rate": 2.00642224321621e-06, + "loss": 0.1587, + "step": 11143 + }, + { + "epoch": 1.43, + "learning_rate": 2.005592120977606e-06, + "loss": 0.1432, + "step": 11144 + }, + { + "epoch": 1.43, + "learning_rate": 2.0047621274153746e-06, + "loss": 0.1281, + "step": 11145 + }, + { + "epoch": 1.43, + "learning_rate": 2.0039322625651865e-06, + "loss": 0.1342, + "step": 11146 + }, + { + "epoch": 1.43, + "learning_rate": 2.0031025264627015e-06, + "loss": 0.1306, + "step": 11147 + }, + { + "epoch": 1.43, + "learning_rate": 2.002272919143576e-06, + "loss": 0.1496, + "step": 11148 + }, + { + "epoch": 1.43, + "learning_rate": 2.0014434406434584e-06, + "loss": 0.1416, + "step": 11149 + }, + { + "epoch": 1.43, + "learning_rate": 2.0006140909979937e-06, + "loss": 0.1388, + "step": 11150 + }, + { + "epoch": 1.43, + "learning_rate": 1.9997848702428226e-06, + "loss": 0.128, + "step": 11151 + }, + { + "epoch": 1.43, + "learning_rate": 1.9989557784135792e-06, + "loss": 0.1412, + "step": 11152 + }, + { + "epoch": 1.43, + "learning_rate": 1.9981268155458864e-06, + "loss": 0.1424, + "step": 11153 + }, + { + "epoch": 1.43, + "learning_rate": 1.9972979816753717e-06, + "loss": 0.1433, + "step": 11154 + }, + { + "epoch": 1.43, + "learning_rate": 1.9964692768376497e-06, + "loss": 0.1437, + "step": 11155 + }, + { + "epoch": 1.43, + "learning_rate": 1.9956407010683324e-06, + "loss": 0.1452, + "step": 11156 + }, + { + "epoch": 1.43, + "learning_rate": 1.994812254403025e-06, + "loss": 0.1456, + "step": 11157 + }, + { + "epoch": 1.43, + "learning_rate": 1.9939839368773267e-06, + "loss": 0.1326, + "step": 11158 + }, + { + "epoch": 1.43, + "learning_rate": 1.9931557485268365e-06, + "loss": 0.1502, + "step": 11159 + }, + { + "epoch": 1.43, + "learning_rate": 1.992327689387137e-06, + "loss": 0.1281, + "step": 11160 + }, + { + "epoch": 1.43, + "learning_rate": 1.991499759493817e-06, + "loss": 0.1455, + "step": 11161 + }, + { + "epoch": 1.43, + "learning_rate": 1.990671958882454e-06, + "loss": 0.1411, + "step": 11162 + }, + { + "epoch": 1.43, + "learning_rate": 1.9898442875886157e-06, + "loss": 0.1417, + "step": 11163 + }, + { + "epoch": 1.43, + "learning_rate": 1.9890167456478748e-06, + "loss": 0.1179, + "step": 11164 + }, + { + "epoch": 1.43, + "learning_rate": 1.9881893330957893e-06, + "loss": 0.1394, + "step": 11165 + }, + { + "epoch": 1.43, + "learning_rate": 1.9873620499679157e-06, + "loss": 0.1495, + "step": 11166 + }, + { + "epoch": 1.43, + "learning_rate": 1.986534896299805e-06, + "loss": 0.1393, + "step": 11167 + }, + { + "epoch": 1.43, + "learning_rate": 1.985707872126999e-06, + "loss": 0.1478, + "step": 11168 + }, + { + "epoch": 1.43, + "learning_rate": 1.984880977485041e-06, + "loss": 0.1378, + "step": 11169 + }, + { + "epoch": 1.43, + "learning_rate": 1.9840542124094635e-06, + "loss": 0.1335, + "step": 11170 + }, + { + "epoch": 1.43, + "learning_rate": 1.9832275769357906e-06, + "loss": 0.1385, + "step": 11171 + }, + { + "epoch": 1.43, + "learning_rate": 1.982401071099549e-06, + "loss": 0.1337, + "step": 11172 + }, + { + "epoch": 1.43, + "learning_rate": 1.9815746949362536e-06, + "loss": 0.1609, + "step": 11173 + }, + { + "epoch": 1.43, + "learning_rate": 1.980748448481416e-06, + "loss": 0.1414, + "step": 11174 + }, + { + "epoch": 1.43, + "learning_rate": 1.9799223317705426e-06, + "loss": 0.1393, + "step": 11175 + }, + { + "epoch": 1.43, + "learning_rate": 1.97909634483913e-06, + "loss": 0.1325, + "step": 11176 + }, + { + "epoch": 1.43, + "learning_rate": 1.9782704877226796e-06, + "loss": 0.1393, + "step": 11177 + }, + { + "epoch": 1.43, + "learning_rate": 1.9774447604566715e-06, + "loss": 0.1309, + "step": 11178 + }, + { + "epoch": 1.43, + "learning_rate": 1.9766191630765964e-06, + "loss": 0.1478, + "step": 11179 + }, + { + "epoch": 1.43, + "learning_rate": 1.9757936956179308e-06, + "loss": 0.1295, + "step": 11180 + }, + { + "epoch": 1.43, + "learning_rate": 1.9749683581161417e-06, + "loss": 0.1377, + "step": 11181 + }, + { + "epoch": 1.43, + "learning_rate": 1.9741431506067012e-06, + "loss": 0.1263, + "step": 11182 + }, + { + "epoch": 1.43, + "learning_rate": 1.9733180731250683e-06, + "loss": 0.1473, + "step": 11183 + }, + { + "epoch": 1.43, + "learning_rate": 1.9724931257066988e-06, + "loss": 0.1416, + "step": 11184 + }, + { + "epoch": 1.43, + "learning_rate": 1.971668308387042e-06, + "loss": 0.1255, + "step": 11185 + }, + { + "epoch": 1.43, + "learning_rate": 1.970843621201541e-06, + "loss": 0.1415, + "step": 11186 + }, + { + "epoch": 1.43, + "learning_rate": 1.9700190641856378e-06, + "loss": 0.1406, + "step": 11187 + }, + { + "epoch": 1.43, + "learning_rate": 1.9691946373747626e-06, + "loss": 0.158, + "step": 11188 + }, + { + "epoch": 1.43, + "learning_rate": 1.9683703408043447e-06, + "loss": 0.1459, + "step": 11189 + }, + { + "epoch": 1.43, + "learning_rate": 1.967546174509805e-06, + "loss": 0.1192, + "step": 11190 + }, + { + "epoch": 1.43, + "learning_rate": 1.9667221385265595e-06, + "loss": 0.1376, + "step": 11191 + }, + { + "epoch": 1.43, + "learning_rate": 1.9658982328900195e-06, + "loss": 0.1405, + "step": 11192 + }, + { + "epoch": 1.43, + "learning_rate": 1.9650744576355894e-06, + "loss": 0.1363, + "step": 11193 + }, + { + "epoch": 1.43, + "learning_rate": 1.9642508127986676e-06, + "loss": 0.131, + "step": 11194 + }, + { + "epoch": 1.43, + "learning_rate": 1.963427298414653e-06, + "loss": 0.1458, + "step": 11195 + }, + { + "epoch": 1.43, + "learning_rate": 1.9626039145189263e-06, + "loss": 0.143, + "step": 11196 + }, + { + "epoch": 1.43, + "learning_rate": 1.9617806611468756e-06, + "loss": 0.1441, + "step": 11197 + }, + { + "epoch": 1.43, + "learning_rate": 1.960957538333877e-06, + "loss": 0.1585, + "step": 11198 + }, + { + "epoch": 1.43, + "learning_rate": 1.9601345461153005e-06, + "loss": 0.1468, + "step": 11199 + }, + { + "epoch": 1.43, + "learning_rate": 1.959311684526513e-06, + "loss": 0.1275, + "step": 11200 + }, + { + "epoch": 1.43, + "learning_rate": 1.9584889536028728e-06, + "loss": 0.1394, + "step": 11201 + }, + { + "epoch": 1.43, + "learning_rate": 1.95766635337974e-06, + "loss": 0.1403, + "step": 11202 + }, + { + "epoch": 1.43, + "learning_rate": 1.956843883892457e-06, + "loss": 0.1335, + "step": 11203 + }, + { + "epoch": 1.43, + "learning_rate": 1.9560215451763685e-06, + "loss": 0.1355, + "step": 11204 + }, + { + "epoch": 1.43, + "learning_rate": 1.9551993372668153e-06, + "loss": 0.134, + "step": 11205 + }, + { + "epoch": 1.43, + "learning_rate": 1.9543772601991277e-06, + "loss": 0.1526, + "step": 11206 + }, + { + "epoch": 1.43, + "learning_rate": 1.9535553140086322e-06, + "loss": 0.1435, + "step": 11207 + }, + { + "epoch": 1.43, + "learning_rate": 1.9527334987306495e-06, + "loss": 0.156, + "step": 11208 + }, + { + "epoch": 1.43, + "learning_rate": 1.951911814400495e-06, + "loss": 0.1422, + "step": 11209 + }, + { + "epoch": 1.43, + "learning_rate": 1.9510902610534782e-06, + "loss": 0.1409, + "step": 11210 + }, + { + "epoch": 1.44, + "learning_rate": 1.950268838724902e-06, + "loss": 0.1375, + "step": 11211 + }, + { + "epoch": 1.44, + "learning_rate": 1.949447547450067e-06, + "loss": 0.1586, + "step": 11212 + }, + { + "epoch": 1.44, + "learning_rate": 1.948626387264267e-06, + "loss": 0.1357, + "step": 11213 + }, + { + "epoch": 1.44, + "learning_rate": 1.9478053582027826e-06, + "loss": 0.1374, + "step": 11214 + }, + { + "epoch": 1.44, + "learning_rate": 1.9469844603009026e-06, + "loss": 0.1325, + "step": 11215 + }, + { + "epoch": 1.44, + "learning_rate": 1.946163693593899e-06, + "loss": 0.1225, + "step": 11216 + }, + { + "epoch": 1.44, + "learning_rate": 1.945343058117043e-06, + "loss": 0.1415, + "step": 11217 + }, + { + "epoch": 1.44, + "learning_rate": 1.9445225539055982e-06, + "loss": 0.133, + "step": 11218 + }, + { + "epoch": 1.44, + "learning_rate": 1.9437021809948232e-06, + "loss": 0.1399, + "step": 11219 + }, + { + "epoch": 1.44, + "learning_rate": 1.9428819394199753e-06, + "loss": 0.1284, + "step": 11220 + }, + { + "epoch": 1.44, + "learning_rate": 1.9420618292162974e-06, + "loss": 0.142, + "step": 11221 + }, + { + "epoch": 1.44, + "learning_rate": 1.9412418504190316e-06, + "loss": 0.1344, + "step": 11222 + }, + { + "epoch": 1.44, + "learning_rate": 1.9404220030634173e-06, + "loss": 0.1426, + "step": 11223 + }, + { + "epoch": 1.44, + "learning_rate": 1.9396022871846836e-06, + "loss": 0.1587, + "step": 11224 + }, + { + "epoch": 1.44, + "learning_rate": 1.9387827028180556e-06, + "loss": 0.1488, + "step": 11225 + }, + { + "epoch": 1.44, + "learning_rate": 1.937963249998752e-06, + "loss": 0.1257, + "step": 11226 + }, + { + "epoch": 1.44, + "learning_rate": 1.9371439287619876e-06, + "loss": 0.1454, + "step": 11227 + }, + { + "epoch": 1.44, + "learning_rate": 1.9363247391429695e-06, + "loss": 0.1392, + "step": 11228 + }, + { + "epoch": 1.44, + "learning_rate": 1.935505681176899e-06, + "loss": 0.1357, + "step": 11229 + }, + { + "epoch": 1.44, + "learning_rate": 1.9346867548989767e-06, + "loss": 0.1254, + "step": 11230 + }, + { + "epoch": 1.44, + "learning_rate": 1.9338679603443922e-06, + "loss": 0.1538, + "step": 11231 + }, + { + "epoch": 1.44, + "learning_rate": 1.933049297548327e-06, + "loss": 0.1283, + "step": 11232 + }, + { + "epoch": 1.44, + "learning_rate": 1.932230766545966e-06, + "loss": 0.1533, + "step": 11233 + }, + { + "epoch": 1.44, + "learning_rate": 1.9314123673724805e-06, + "loss": 0.1425, + "step": 11234 + }, + { + "epoch": 1.44, + "learning_rate": 1.93059410006304e-06, + "loss": 0.1331, + "step": 11235 + }, + { + "epoch": 1.44, + "learning_rate": 1.9297759646528076e-06, + "loss": 0.1346, + "step": 11236 + }, + { + "epoch": 1.44, + "learning_rate": 1.928957961176937e-06, + "loss": 0.1393, + "step": 11237 + }, + { + "epoch": 1.44, + "learning_rate": 1.9281400896705865e-06, + "loss": 0.1469, + "step": 11238 + }, + { + "epoch": 1.44, + "learning_rate": 1.9273223501688943e-06, + "loss": 0.1328, + "step": 11239 + }, + { + "epoch": 1.44, + "learning_rate": 1.9265047427070054e-06, + "loss": 0.1295, + "step": 11240 + }, + { + "epoch": 1.44, + "learning_rate": 1.925687267320053e-06, + "loss": 0.1336, + "step": 11241 + }, + { + "epoch": 1.44, + "learning_rate": 1.924869924043165e-06, + "loss": 0.1341, + "step": 11242 + }, + { + "epoch": 1.44, + "learning_rate": 1.9240527129114654e-06, + "loss": 0.1078, + "step": 11243 + }, + { + "epoch": 1.44, + "learning_rate": 1.9232356339600717e-06, + "loss": 0.1469, + "step": 11244 + }, + { + "epoch": 1.44, + "learning_rate": 1.9224186872240946e-06, + "loss": 0.1325, + "step": 11245 + }, + { + "epoch": 1.44, + "learning_rate": 1.921601872738641e-06, + "loss": 0.1196, + "step": 11246 + }, + { + "epoch": 1.44, + "learning_rate": 1.920785190538809e-06, + "loss": 0.133, + "step": 11247 + }, + { + "epoch": 1.44, + "learning_rate": 1.9199686406596968e-06, + "loss": 0.1539, + "step": 11248 + }, + { + "epoch": 1.44, + "learning_rate": 1.919152223136391e-06, + "loss": 0.138, + "step": 11249 + }, + { + "epoch": 1.44, + "learning_rate": 1.918335938003977e-06, + "loss": 0.1541, + "step": 11250 + }, + { + "epoch": 1.44, + "learning_rate": 1.9175197852975304e-06, + "loss": 0.1344, + "step": 11251 + }, + { + "epoch": 1.44, + "learning_rate": 1.9167037650521215e-06, + "loss": 0.1409, + "step": 11252 + }, + { + "epoch": 1.44, + "learning_rate": 1.915887877302823e-06, + "loss": 0.1657, + "step": 11253 + }, + { + "epoch": 1.44, + "learning_rate": 1.9150721220846884e-06, + "loss": 0.1504, + "step": 11254 + }, + { + "epoch": 1.44, + "learning_rate": 1.914256499432774e-06, + "loss": 0.1348, + "step": 11255 + }, + { + "epoch": 1.44, + "learning_rate": 1.913441009382133e-06, + "loss": 0.1442, + "step": 11256 + }, + { + "epoch": 1.44, + "learning_rate": 1.9126256519678034e-06, + "loss": 0.1532, + "step": 11257 + }, + { + "epoch": 1.44, + "learning_rate": 1.9118104272248266e-06, + "loss": 0.134, + "step": 11258 + }, + { + "epoch": 1.44, + "learning_rate": 1.910995335188234e-06, + "loss": 0.1313, + "step": 11259 + }, + { + "epoch": 1.44, + "learning_rate": 1.9101803758930514e-06, + "loss": 0.1475, + "step": 11260 + }, + { + "epoch": 1.44, + "learning_rate": 1.909365549374299e-06, + "loss": 0.1546, + "step": 11261 + }, + { + "epoch": 1.44, + "learning_rate": 1.9085508556669905e-06, + "loss": 0.1346, + "step": 11262 + }, + { + "epoch": 1.44, + "learning_rate": 1.9077362948061404e-06, + "loss": 0.1469, + "step": 11263 + }, + { + "epoch": 1.44, + "learning_rate": 1.906921866826747e-06, + "loss": 0.1287, + "step": 11264 + }, + { + "epoch": 1.44, + "learning_rate": 1.9061075717638078e-06, + "loss": 0.1417, + "step": 11265 + }, + { + "epoch": 1.44, + "learning_rate": 1.9052934096523184e-06, + "loss": 0.1288, + "step": 11266 + }, + { + "epoch": 1.44, + "learning_rate": 1.9044793805272633e-06, + "loss": 0.1406, + "step": 11267 + }, + { + "epoch": 1.44, + "learning_rate": 1.9036654844236234e-06, + "loss": 0.1432, + "step": 11268 + }, + { + "epoch": 1.44, + "learning_rate": 1.9028517213763737e-06, + "loss": 0.1507, + "step": 11269 + }, + { + "epoch": 1.44, + "learning_rate": 1.902038091420481e-06, + "loss": 0.1503, + "step": 11270 + }, + { + "epoch": 1.44, + "learning_rate": 1.9012245945909153e-06, + "loss": 0.1406, + "step": 11271 + }, + { + "epoch": 1.44, + "learning_rate": 1.900411230922628e-06, + "loss": 0.1478, + "step": 11272 + }, + { + "epoch": 1.44, + "learning_rate": 1.8995980004505715e-06, + "loss": 0.1433, + "step": 11273 + }, + { + "epoch": 1.44, + "learning_rate": 1.8987849032096973e-06, + "loss": 0.1389, + "step": 11274 + }, + { + "epoch": 1.44, + "learning_rate": 1.8979719392349388e-06, + "loss": 0.1261, + "step": 11275 + }, + { + "epoch": 1.44, + "learning_rate": 1.8971591085612367e-06, + "loss": 0.1418, + "step": 11276 + }, + { + "epoch": 1.44, + "learning_rate": 1.8963464112235185e-06, + "loss": 0.1382, + "step": 11277 + }, + { + "epoch": 1.44, + "learning_rate": 1.895533847256707e-06, + "loss": 0.1415, + "step": 11278 + }, + { + "epoch": 1.44, + "learning_rate": 1.89472141669572e-06, + "loss": 0.1453, + "step": 11279 + }, + { + "epoch": 1.44, + "learning_rate": 1.8939091195754678e-06, + "loss": 0.1314, + "step": 11280 + }, + { + "epoch": 1.44, + "learning_rate": 1.8930969559308615e-06, + "loss": 0.1418, + "step": 11281 + }, + { + "epoch": 1.44, + "learning_rate": 1.8922849257967972e-06, + "loss": 0.1325, + "step": 11282 + }, + { + "epoch": 1.44, + "learning_rate": 1.891473029208169e-06, + "loss": 0.1458, + "step": 11283 + }, + { + "epoch": 1.44, + "learning_rate": 1.8906612661998698e-06, + "loss": 0.1428, + "step": 11284 + }, + { + "epoch": 1.44, + "learning_rate": 1.8898496368067804e-06, + "loss": 0.151, + "step": 11285 + }, + { + "epoch": 1.44, + "learning_rate": 1.8890381410637786e-06, + "loss": 0.1292, + "step": 11286 + }, + { + "epoch": 1.44, + "learning_rate": 1.8882267790057374e-06, + "loss": 0.1346, + "step": 11287 + }, + { + "epoch": 1.44, + "learning_rate": 1.887415550667519e-06, + "loss": 0.1479, + "step": 11288 + }, + { + "epoch": 1.44, + "learning_rate": 1.8866044560839902e-06, + "loss": 0.1423, + "step": 11289 + }, + { + "epoch": 1.45, + "learning_rate": 1.8857934952899987e-06, + "loss": 0.1492, + "step": 11290 + }, + { + "epoch": 1.45, + "learning_rate": 1.884982668320398e-06, + "loss": 0.1371, + "step": 11291 + }, + { + "epoch": 1.45, + "learning_rate": 1.8841719752100313e-06, + "loss": 0.1549, + "step": 11292 + }, + { + "epoch": 1.45, + "learning_rate": 1.8833614159937307e-06, + "loss": 0.1452, + "step": 11293 + }, + { + "epoch": 1.45, + "learning_rate": 1.8825509907063328e-06, + "loss": 0.1361, + "step": 11294 + }, + { + "epoch": 1.45, + "learning_rate": 1.881740699382662e-06, + "loss": 0.1433, + "step": 11295 + }, + { + "epoch": 1.45, + "learning_rate": 1.880930542057538e-06, + "loss": 0.1424, + "step": 11296 + }, + { + "epoch": 1.45, + "learning_rate": 1.880120518765775e-06, + "loss": 0.1383, + "step": 11297 + }, + { + "epoch": 1.45, + "learning_rate": 1.8793106295421797e-06, + "loss": 0.1277, + "step": 11298 + }, + { + "epoch": 1.45, + "learning_rate": 1.8785008744215606e-06, + "loss": 0.1479, + "step": 11299 + }, + { + "epoch": 1.45, + "learning_rate": 1.8776912534387076e-06, + "loss": 0.1232, + "step": 11300 + }, + { + "epoch": 1.45, + "learning_rate": 1.8768817666284166e-06, + "loss": 0.1578, + "step": 11301 + }, + { + "epoch": 1.45, + "learning_rate": 1.8760724140254716e-06, + "loss": 0.1469, + "step": 11302 + }, + { + "epoch": 1.45, + "learning_rate": 1.8752631956646522e-06, + "loss": 0.148, + "step": 11303 + }, + { + "epoch": 1.45, + "learning_rate": 1.874454111580733e-06, + "loss": 0.1339, + "step": 11304 + }, + { + "epoch": 1.45, + "learning_rate": 1.873645161808481e-06, + "loss": 0.1385, + "step": 11305 + }, + { + "epoch": 1.45, + "learning_rate": 1.8728363463826577e-06, + "loss": 0.1327, + "step": 11306 + }, + { + "epoch": 1.45, + "learning_rate": 1.872027665338025e-06, + "loss": 0.126, + "step": 11307 + }, + { + "epoch": 1.45, + "learning_rate": 1.871219118709326e-06, + "loss": 0.1463, + "step": 11308 + }, + { + "epoch": 1.45, + "learning_rate": 1.8704107065313116e-06, + "loss": 0.1299, + "step": 11309 + }, + { + "epoch": 1.45, + "learning_rate": 1.8696024288387189e-06, + "loss": 0.126, + "step": 11310 + }, + { + "epoch": 1.45, + "learning_rate": 1.8687942856662815e-06, + "loss": 0.1304, + "step": 11311 + }, + { + "epoch": 1.45, + "learning_rate": 1.8679862770487273e-06, + "loss": 0.1385, + "step": 11312 + }, + { + "epoch": 1.45, + "learning_rate": 1.8671784030207762e-06, + "loss": 0.1405, + "step": 11313 + }, + { + "epoch": 1.45, + "learning_rate": 1.8663706636171503e-06, + "loss": 0.1287, + "step": 11314 + }, + { + "epoch": 1.45, + "learning_rate": 1.8655630588725536e-06, + "loss": 0.1272, + "step": 11315 + }, + { + "epoch": 1.45, + "learning_rate": 1.8647555888216918e-06, + "loss": 0.1269, + "step": 11316 + }, + { + "epoch": 1.45, + "learning_rate": 1.8639482534992682e-06, + "loss": 0.1403, + "step": 11317 + }, + { + "epoch": 1.45, + "learning_rate": 1.863141052939969e-06, + "loss": 0.1473, + "step": 11318 + }, + { + "epoch": 1.45, + "learning_rate": 1.8623339871784869e-06, + "loss": 0.1242, + "step": 11319 + }, + { + "epoch": 1.45, + "learning_rate": 1.8615270562495014e-06, + "loss": 0.1257, + "step": 11320 + }, + { + "epoch": 1.45, + "learning_rate": 1.8607202601876873e-06, + "loss": 0.1271, + "step": 11321 + }, + { + "epoch": 1.45, + "learning_rate": 1.8599135990277156e-06, + "loss": 0.1312, + "step": 11322 + }, + { + "epoch": 1.45, + "learning_rate": 1.8591070728042503e-06, + "loss": 0.1287, + "step": 11323 + }, + { + "epoch": 1.45, + "learning_rate": 1.8583006815519473e-06, + "loss": 0.1565, + "step": 11324 + }, + { + "epoch": 1.45, + "learning_rate": 1.8574944253054638e-06, + "loss": 0.1486, + "step": 11325 + }, + { + "epoch": 1.45, + "learning_rate": 1.8566883040994411e-06, + "loss": 0.1357, + "step": 11326 + }, + { + "epoch": 1.45, + "learning_rate": 1.855882317968523e-06, + "loss": 0.1433, + "step": 11327 + }, + { + "epoch": 1.45, + "learning_rate": 1.8550764669473454e-06, + "loss": 0.1304, + "step": 11328 + }, + { + "epoch": 1.45, + "learning_rate": 1.8542707510705355e-06, + "loss": 0.1304, + "step": 11329 + }, + { + "epoch": 1.45, + "learning_rate": 1.853465170372717e-06, + "loss": 0.1356, + "step": 11330 + }, + { + "epoch": 1.45, + "learning_rate": 1.8526597248885065e-06, + "loss": 0.1464, + "step": 11331 + }, + { + "epoch": 1.45, + "learning_rate": 1.8518544146525203e-06, + "loss": 0.1348, + "step": 11332 + }, + { + "epoch": 1.45, + "learning_rate": 1.8510492396993595e-06, + "loss": 0.1284, + "step": 11333 + }, + { + "epoch": 1.45, + "learning_rate": 1.8502442000636246e-06, + "loss": 0.1489, + "step": 11334 + }, + { + "epoch": 1.45, + "learning_rate": 1.8494392957799146e-06, + "loss": 0.1242, + "step": 11335 + }, + { + "epoch": 1.45, + "learning_rate": 1.8486345268828115e-06, + "loss": 0.1463, + "step": 11336 + }, + { + "epoch": 1.45, + "learning_rate": 1.8478298934069028e-06, + "loss": 0.1277, + "step": 11337 + }, + { + "epoch": 1.45, + "learning_rate": 1.8470253953867635e-06, + "loss": 0.1406, + "step": 11338 + }, + { + "epoch": 1.45, + "learning_rate": 1.846221032856965e-06, + "loss": 0.1304, + "step": 11339 + }, + { + "epoch": 1.45, + "learning_rate": 1.8454168058520732e-06, + "loss": 0.1272, + "step": 11340 + }, + { + "epoch": 1.45, + "learning_rate": 1.8446127144066445e-06, + "loss": 0.142, + "step": 11341 + }, + { + "epoch": 1.45, + "learning_rate": 1.8438087585552371e-06, + "loss": 0.1317, + "step": 11342 + }, + { + "epoch": 1.45, + "learning_rate": 1.8430049383323983e-06, + "loss": 0.1243, + "step": 11343 + }, + { + "epoch": 1.45, + "learning_rate": 1.8422012537726646e-06, + "loss": 0.1319, + "step": 11344 + }, + { + "epoch": 1.45, + "learning_rate": 1.8413977049105774e-06, + "loss": 0.1549, + "step": 11345 + }, + { + "epoch": 1.45, + "learning_rate": 1.8405942917806657e-06, + "loss": 0.152, + "step": 11346 + }, + { + "epoch": 1.45, + "learning_rate": 1.8397910144174536e-06, + "loss": 0.1377, + "step": 11347 + }, + { + "epoch": 1.45, + "learning_rate": 1.8389878728554594e-06, + "loss": 0.1372, + "step": 11348 + }, + { + "epoch": 1.45, + "learning_rate": 1.8381848671291953e-06, + "loss": 0.1361, + "step": 11349 + }, + { + "epoch": 1.45, + "learning_rate": 1.8373819972731721e-06, + "loss": 0.13, + "step": 11350 + }, + { + "epoch": 1.45, + "learning_rate": 1.8365792633218844e-06, + "loss": 0.1318, + "step": 11351 + }, + { + "epoch": 1.45, + "learning_rate": 1.835776665309833e-06, + "loss": 0.1221, + "step": 11352 + }, + { + "epoch": 1.45, + "learning_rate": 1.8349742032715072e-06, + "loss": 0.1527, + "step": 11353 + }, + { + "epoch": 1.45, + "learning_rate": 1.8341718772413852e-06, + "loss": 0.1614, + "step": 11354 + }, + { + "epoch": 1.45, + "learning_rate": 1.8333696872539502e-06, + "loss": 0.1342, + "step": 11355 + }, + { + "epoch": 1.45, + "learning_rate": 1.8325676333436727e-06, + "loss": 0.142, + "step": 11356 + }, + { + "epoch": 1.45, + "learning_rate": 1.8317657155450174e-06, + "loss": 0.1421, + "step": 11357 + }, + { + "epoch": 1.45, + "learning_rate": 1.8309639338924456e-06, + "loss": 0.1393, + "step": 11358 + }, + { + "epoch": 1.45, + "learning_rate": 1.8301622884204096e-06, + "loss": 0.1427, + "step": 11359 + }, + { + "epoch": 1.45, + "learning_rate": 1.8293607791633617e-06, + "loss": 0.1384, + "step": 11360 + }, + { + "epoch": 1.45, + "learning_rate": 1.8285594061557421e-06, + "loss": 0.1412, + "step": 11361 + }, + { + "epoch": 1.45, + "learning_rate": 1.8277581694319884e-06, + "loss": 0.1357, + "step": 11362 + }, + { + "epoch": 1.45, + "learning_rate": 1.8269570690265308e-06, + "loss": 0.1273, + "step": 11363 + }, + { + "epoch": 1.45, + "learning_rate": 1.8261561049737946e-06, + "loss": 0.1325, + "step": 11364 + }, + { + "epoch": 1.45, + "learning_rate": 1.8253552773081995e-06, + "loss": 0.1462, + "step": 11365 + }, + { + "epoch": 1.45, + "learning_rate": 1.8245545860641584e-06, + "loss": 0.1322, + "step": 11366 + }, + { + "epoch": 1.45, + "learning_rate": 1.8237540312760764e-06, + "loss": 0.1285, + "step": 11367 + }, + { + "epoch": 1.46, + "learning_rate": 1.822953612978362e-06, + "loss": 0.15, + "step": 11368 + }, + { + "epoch": 1.46, + "learning_rate": 1.8221533312054024e-06, + "loss": 0.154, + "step": 11369 + }, + { + "epoch": 1.46, + "learning_rate": 1.8213531859915939e-06, + "loss": 0.1391, + "step": 11370 + }, + { + "epoch": 1.46, + "learning_rate": 1.8205531773713175e-06, + "loss": 0.1463, + "step": 11371 + }, + { + "epoch": 1.46, + "learning_rate": 1.8197533053789524e-06, + "loss": 0.129, + "step": 11372 + }, + { + "epoch": 1.46, + "learning_rate": 1.8189535700488708e-06, + "loss": 0.148, + "step": 11373 + }, + { + "epoch": 1.46, + "learning_rate": 1.818153971415439e-06, + "loss": 0.139, + "step": 11374 + }, + { + "epoch": 1.46, + "learning_rate": 1.817354509513017e-06, + "loss": 0.1435, + "step": 11375 + }, + { + "epoch": 1.46, + "learning_rate": 1.81655518437596e-06, + "loss": 0.1248, + "step": 11376 + }, + { + "epoch": 1.46, + "learning_rate": 1.8157559960386146e-06, + "loss": 0.1376, + "step": 11377 + }, + { + "epoch": 1.46, + "learning_rate": 1.8149569445353277e-06, + "loss": 0.1394, + "step": 11378 + }, + { + "epoch": 1.46, + "learning_rate": 1.8141580299004342e-06, + "loss": 0.1347, + "step": 11379 + }, + { + "epoch": 1.46, + "learning_rate": 1.8133592521682657e-06, + "loss": 0.1464, + "step": 11380 + }, + { + "epoch": 1.46, + "learning_rate": 1.812560611373147e-06, + "loss": 0.1348, + "step": 11381 + }, + { + "epoch": 1.46, + "learning_rate": 1.8117621075493979e-06, + "loss": 0.1345, + "step": 11382 + }, + { + "epoch": 1.46, + "learning_rate": 1.8109637407313313e-06, + "loss": 0.1466, + "step": 11383 + }, + { + "epoch": 1.46, + "learning_rate": 1.8101655109532552e-06, + "loss": 0.1513, + "step": 11384 + }, + { + "epoch": 1.46, + "learning_rate": 1.8093674182494698e-06, + "loss": 0.1342, + "step": 11385 + }, + { + "epoch": 1.46, + "learning_rate": 1.8085694626542755e-06, + "loss": 0.1325, + "step": 11386 + }, + { + "epoch": 1.46, + "learning_rate": 1.8077716442019554e-06, + "loss": 0.1256, + "step": 11387 + }, + { + "epoch": 1.46, + "learning_rate": 1.8069739629267991e-06, + "loss": 0.1166, + "step": 11388 + }, + { + "epoch": 1.46, + "learning_rate": 1.8061764188630831e-06, + "loss": 0.138, + "step": 11389 + }, + { + "epoch": 1.46, + "learning_rate": 1.8053790120450793e-06, + "loss": 0.1454, + "step": 11390 + }, + { + "epoch": 1.46, + "learning_rate": 1.8045817425070544e-06, + "loss": 0.1308, + "step": 11391 + }, + { + "epoch": 1.46, + "learning_rate": 1.8037846102832667e-06, + "loss": 0.1437, + "step": 11392 + }, + { + "epoch": 1.46, + "learning_rate": 1.8029876154079755e-06, + "loss": 0.1476, + "step": 11393 + }, + { + "epoch": 1.46, + "learning_rate": 1.8021907579154257e-06, + "loss": 0.1322, + "step": 11394 + }, + { + "epoch": 1.46, + "learning_rate": 1.8013940378398593e-06, + "loss": 0.1378, + "step": 11395 + }, + { + "epoch": 1.46, + "learning_rate": 1.8005974552155158e-06, + "loss": 0.1423, + "step": 11396 + }, + { + "epoch": 1.46, + "learning_rate": 1.7998010100766255e-06, + "loss": 0.1471, + "step": 11397 + }, + { + "epoch": 1.46, + "learning_rate": 1.799004702457413e-06, + "loss": 0.14, + "step": 11398 + }, + { + "epoch": 1.46, + "learning_rate": 1.7982085323920973e-06, + "loss": 0.1432, + "step": 11399 + }, + { + "epoch": 1.46, + "learning_rate": 1.7974124999148918e-06, + "loss": 0.1309, + "step": 11400 + }, + { + "epoch": 1.46, + "learning_rate": 1.7966166050600037e-06, + "loss": 0.1504, + "step": 11401 + }, + { + "epoch": 1.46, + "learning_rate": 1.795820847861633e-06, + "loss": 0.1243, + "step": 11402 + }, + { + "epoch": 1.46, + "learning_rate": 1.7950252283539776e-06, + "loss": 0.1335, + "step": 11403 + }, + { + "epoch": 1.46, + "learning_rate": 1.7942297465712282e-06, + "loss": 0.1275, + "step": 11404 + }, + { + "epoch": 1.46, + "learning_rate": 1.7934344025475625e-06, + "loss": 0.1413, + "step": 11405 + }, + { + "epoch": 1.46, + "learning_rate": 1.7926391963171642e-06, + "loss": 0.1392, + "step": 11406 + }, + { + "epoch": 1.46, + "learning_rate": 1.7918441279142025e-06, + "loss": 0.1454, + "step": 11407 + }, + { + "epoch": 1.46, + "learning_rate": 1.7910491973728433e-06, + "loss": 0.1203, + "step": 11408 + }, + { + "epoch": 1.46, + "learning_rate": 1.7902544047272468e-06, + "loss": 0.1503, + "step": 11409 + }, + { + "epoch": 1.46, + "learning_rate": 1.7894597500115657e-06, + "loss": 0.1426, + "step": 11410 + }, + { + "epoch": 1.46, + "learning_rate": 1.788665233259953e-06, + "loss": 0.1378, + "step": 11411 + }, + { + "epoch": 1.46, + "learning_rate": 1.7878708545065433e-06, + "loss": 0.1288, + "step": 11412 + }, + { + "epoch": 1.46, + "learning_rate": 1.7870766137854784e-06, + "loss": 0.1371, + "step": 11413 + }, + { + "epoch": 1.46, + "learning_rate": 1.7862825111308873e-06, + "loss": 0.1275, + "step": 11414 + }, + { + "epoch": 1.46, + "learning_rate": 1.7854885465768939e-06, + "loss": 0.1332, + "step": 11415 + }, + { + "epoch": 1.46, + "learning_rate": 1.7846947201576171e-06, + "loss": 0.1349, + "step": 11416 + }, + { + "epoch": 1.46, + "learning_rate": 1.7839010319071687e-06, + "loss": 0.1308, + "step": 11417 + }, + { + "epoch": 1.46, + "learning_rate": 1.7831074818596555e-06, + "loss": 0.1277, + "step": 11418 + }, + { + "epoch": 1.46, + "learning_rate": 1.7823140700491786e-06, + "loss": 0.141, + "step": 11419 + }, + { + "epoch": 1.46, + "learning_rate": 1.7815207965098303e-06, + "loss": 0.1366, + "step": 11420 + }, + { + "epoch": 1.46, + "learning_rate": 1.780727661275703e-06, + "loss": 0.1398, + "step": 11421 + }, + { + "epoch": 1.46, + "learning_rate": 1.7799346643808796e-06, + "loss": 0.1333, + "step": 11422 + }, + { + "epoch": 1.46, + "learning_rate": 1.7791418058594318e-06, + "loss": 0.1491, + "step": 11423 + }, + { + "epoch": 1.46, + "learning_rate": 1.7783490857454354e-06, + "loss": 0.1337, + "step": 11424 + }, + { + "epoch": 1.46, + "learning_rate": 1.7775565040729536e-06, + "loss": 0.1392, + "step": 11425 + }, + { + "epoch": 1.46, + "learning_rate": 1.776764060876046e-06, + "loss": 0.1429, + "step": 11426 + }, + { + "epoch": 1.46, + "learning_rate": 1.7759717561887652e-06, + "loss": 0.1399, + "step": 11427 + }, + { + "epoch": 1.46, + "learning_rate": 1.7751795900451562e-06, + "loss": 0.1348, + "step": 11428 + }, + { + "epoch": 1.46, + "learning_rate": 1.7743875624792662e-06, + "loss": 0.1431, + "step": 11429 + }, + { + "epoch": 1.46, + "learning_rate": 1.7735956735251224e-06, + "loss": 0.1526, + "step": 11430 + }, + { + "epoch": 1.46, + "learning_rate": 1.7728039232167603e-06, + "loss": 0.1452, + "step": 11431 + }, + { + "epoch": 1.46, + "learning_rate": 1.7720123115882009e-06, + "loss": 0.1511, + "step": 11432 + }, + { + "epoch": 1.46, + "learning_rate": 1.771220838673462e-06, + "loss": 0.1414, + "step": 11433 + }, + { + "epoch": 1.46, + "learning_rate": 1.770429504506554e-06, + "loss": 0.1283, + "step": 11434 + }, + { + "epoch": 1.46, + "learning_rate": 1.769638309121483e-06, + "loss": 0.15, + "step": 11435 + }, + { + "epoch": 1.46, + "learning_rate": 1.7688472525522481e-06, + "loss": 0.1363, + "step": 11436 + }, + { + "epoch": 1.46, + "learning_rate": 1.7680563348328433e-06, + "loss": 0.1386, + "step": 11437 + }, + { + "epoch": 1.46, + "learning_rate": 1.7672655559972535e-06, + "loss": 0.1342, + "step": 11438 + }, + { + "epoch": 1.46, + "learning_rate": 1.7664749160794642e-06, + "loss": 0.1451, + "step": 11439 + }, + { + "epoch": 1.46, + "learning_rate": 1.7656844151134495e-06, + "loss": 0.1358, + "step": 11440 + }, + { + "epoch": 1.46, + "learning_rate": 1.7648940531331787e-06, + "loss": 0.138, + "step": 11441 + }, + { + "epoch": 1.46, + "learning_rate": 1.7641038301726155e-06, + "loss": 0.1369, + "step": 11442 + }, + { + "epoch": 1.46, + "learning_rate": 1.763313746265715e-06, + "loss": 0.1256, + "step": 11443 + }, + { + "epoch": 1.46, + "learning_rate": 1.7625238014464358e-06, + "loss": 0.1279, + "step": 11444 + }, + { + "epoch": 1.46, + "learning_rate": 1.7617339957487167e-06, + "loss": 0.1617, + "step": 11445 + }, + { + "epoch": 1.47, + "learning_rate": 1.760944329206498e-06, + "loss": 0.1428, + "step": 11446 + }, + { + "epoch": 1.47, + "learning_rate": 1.760154801853719e-06, + "loss": 0.1165, + "step": 11447 + }, + { + "epoch": 1.47, + "learning_rate": 1.7593654137243005e-06, + "loss": 0.1256, + "step": 11448 + }, + { + "epoch": 1.47, + "learning_rate": 1.7585761648521688e-06, + "loss": 0.1635, + "step": 11449 + }, + { + "epoch": 1.47, + "learning_rate": 1.7577870552712378e-06, + "loss": 0.1315, + "step": 11450 + }, + { + "epoch": 1.47, + "learning_rate": 1.756998085015419e-06, + "loss": 0.1364, + "step": 11451 + }, + { + "epoch": 1.47, + "learning_rate": 1.7562092541186144e-06, + "loss": 0.1454, + "step": 11452 + }, + { + "epoch": 1.47, + "learning_rate": 1.7554205626147202e-06, + "loss": 0.1412, + "step": 11453 + }, + { + "epoch": 1.47, + "learning_rate": 1.7546320105376346e-06, + "loss": 0.1426, + "step": 11454 + }, + { + "epoch": 1.47, + "learning_rate": 1.7538435979212376e-06, + "loss": 0.1414, + "step": 11455 + }, + { + "epoch": 1.47, + "learning_rate": 1.7530553247994093e-06, + "loss": 0.1319, + "step": 11456 + }, + { + "epoch": 1.47, + "learning_rate": 1.7522671912060262e-06, + "loss": 0.1513, + "step": 11457 + }, + { + "epoch": 1.47, + "learning_rate": 1.751479197174955e-06, + "loss": 0.1423, + "step": 11458 + }, + { + "epoch": 1.47, + "learning_rate": 1.750691342740058e-06, + "loss": 0.1307, + "step": 11459 + }, + { + "epoch": 1.47, + "learning_rate": 1.7499036279351905e-06, + "loss": 0.1383, + "step": 11460 + }, + { + "epoch": 1.47, + "learning_rate": 1.7491160527942002e-06, + "loss": 0.134, + "step": 11461 + }, + { + "epoch": 1.47, + "learning_rate": 1.7483286173509372e-06, + "loss": 0.1318, + "step": 11462 + }, + { + "epoch": 1.47, + "learning_rate": 1.7475413216392317e-06, + "loss": 0.1377, + "step": 11463 + }, + { + "epoch": 1.47, + "learning_rate": 1.746754165692921e-06, + "loss": 0.1431, + "step": 11464 + }, + { + "epoch": 1.47, + "learning_rate": 1.7459671495458308e-06, + "loss": 0.1455, + "step": 11465 + }, + { + "epoch": 1.47, + "learning_rate": 1.7451802732317763e-06, + "loss": 0.1394, + "step": 11466 + }, + { + "epoch": 1.47, + "learning_rate": 1.7443935367845755e-06, + "loss": 0.1579, + "step": 11467 + }, + { + "epoch": 1.47, + "learning_rate": 1.7436069402380352e-06, + "loss": 0.1305, + "step": 11468 + }, + { + "epoch": 1.47, + "learning_rate": 1.742820483625957e-06, + "loss": 0.13, + "step": 11469 + }, + { + "epoch": 1.47, + "learning_rate": 1.7420341669821373e-06, + "loss": 0.1379, + "step": 11470 + }, + { + "epoch": 1.47, + "learning_rate": 1.7412479903403628e-06, + "loss": 0.1451, + "step": 11471 + }, + { + "epoch": 1.47, + "learning_rate": 1.7404619537344236e-06, + "loss": 0.1367, + "step": 11472 + }, + { + "epoch": 1.47, + "learning_rate": 1.7396760571980902e-06, + "loss": 0.1304, + "step": 11473 + }, + { + "epoch": 1.47, + "learning_rate": 1.7388903007651398e-06, + "loss": 0.1406, + "step": 11474 + }, + { + "epoch": 1.47, + "learning_rate": 1.7381046844693356e-06, + "loss": 0.1421, + "step": 11475 + }, + { + "epoch": 1.47, + "learning_rate": 1.737319208344438e-06, + "loss": 0.1394, + "step": 11476 + }, + { + "epoch": 1.47, + "learning_rate": 1.7365338724242003e-06, + "loss": 0.145, + "step": 11477 + }, + { + "epoch": 1.47, + "learning_rate": 1.7357486767423699e-06, + "loss": 0.1249, + "step": 11478 + }, + { + "epoch": 1.47, + "learning_rate": 1.7349636213326876e-06, + "loss": 0.1326, + "step": 11479 + }, + { + "epoch": 1.47, + "learning_rate": 1.7341787062288928e-06, + "loss": 0.1399, + "step": 11480 + }, + { + "epoch": 1.47, + "learning_rate": 1.7333939314647097e-06, + "loss": 0.1615, + "step": 11481 + }, + { + "epoch": 1.47, + "learning_rate": 1.7326092970738656e-06, + "loss": 0.1261, + "step": 11482 + }, + { + "epoch": 1.47, + "learning_rate": 1.7318248030900792e-06, + "loss": 0.1491, + "step": 11483 + }, + { + "epoch": 1.47, + "learning_rate": 1.7310404495470557e-06, + "loss": 0.1084, + "step": 11484 + }, + { + "epoch": 1.47, + "learning_rate": 1.7302562364785063e-06, + "loss": 0.1502, + "step": 11485 + }, + { + "epoch": 1.47, + "learning_rate": 1.729472163918129e-06, + "loss": 0.1351, + "step": 11486 + }, + { + "epoch": 1.47, + "learning_rate": 1.7286882318996162e-06, + "loss": 0.1498, + "step": 11487 + }, + { + "epoch": 1.47, + "learning_rate": 1.7279044404566554e-06, + "loss": 0.1334, + "step": 11488 + }, + { + "epoch": 1.47, + "learning_rate": 1.727120789622927e-06, + "loss": 0.1291, + "step": 11489 + }, + { + "epoch": 1.47, + "learning_rate": 1.7263372794321104e-06, + "loss": 0.1314, + "step": 11490 + }, + { + "epoch": 1.47, + "learning_rate": 1.7255539099178687e-06, + "loss": 0.1522, + "step": 11491 + }, + { + "epoch": 1.47, + "learning_rate": 1.7247706811138692e-06, + "loss": 0.1411, + "step": 11492 + }, + { + "epoch": 1.47, + "learning_rate": 1.723987593053768e-06, + "loss": 0.1482, + "step": 11493 + }, + { + "epoch": 1.47, + "learning_rate": 1.7232046457712164e-06, + "loss": 0.1396, + "step": 11494 + }, + { + "epoch": 1.47, + "learning_rate": 1.7224218392998587e-06, + "loss": 0.1297, + "step": 11495 + }, + { + "epoch": 1.47, + "learning_rate": 1.7216391736733345e-06, + "loss": 0.1504, + "step": 11496 + }, + { + "epoch": 1.47, + "learning_rate": 1.7208566489252742e-06, + "loss": 0.138, + "step": 11497 + }, + { + "epoch": 1.47, + "learning_rate": 1.7200742650893105e-06, + "loss": 0.1335, + "step": 11498 + }, + { + "epoch": 1.47, + "learning_rate": 1.7192920221990566e-06, + "loss": 0.1372, + "step": 11499 + }, + { + "epoch": 1.47, + "learning_rate": 1.7185099202881328e-06, + "loss": 0.1392, + "step": 11500 + }, + { + "epoch": 1.47, + "learning_rate": 1.7177279593901463e-06, + "loss": 0.1306, + "step": 11501 + }, + { + "epoch": 1.47, + "learning_rate": 1.7169461395386988e-06, + "loss": 0.1292, + "step": 11502 + }, + { + "epoch": 1.47, + "learning_rate": 1.7161644607673884e-06, + "loss": 0.1423, + "step": 11503 + }, + { + "epoch": 1.47, + "learning_rate": 1.7153829231098018e-06, + "loss": 0.1285, + "step": 11504 + }, + { + "epoch": 1.47, + "learning_rate": 1.7146015265995302e-06, + "loss": 0.1512, + "step": 11505 + }, + { + "epoch": 1.47, + "learning_rate": 1.7138202712701463e-06, + "loss": 0.1467, + "step": 11506 + }, + { + "epoch": 1.47, + "learning_rate": 1.7130391571552224e-06, + "loss": 0.1199, + "step": 11507 + }, + { + "epoch": 1.47, + "learning_rate": 1.712258184288328e-06, + "loss": 0.1408, + "step": 11508 + }, + { + "epoch": 1.47, + "learning_rate": 1.7114773527030215e-06, + "loss": 0.1352, + "step": 11509 + }, + { + "epoch": 1.47, + "learning_rate": 1.7106966624328575e-06, + "loss": 0.14, + "step": 11510 + }, + { + "epoch": 1.47, + "learning_rate": 1.7099161135113828e-06, + "loss": 0.1392, + "step": 11511 + }, + { + "epoch": 1.47, + "learning_rate": 1.7091357059721409e-06, + "loss": 0.132, + "step": 11512 + }, + { + "epoch": 1.47, + "learning_rate": 1.7083554398486663e-06, + "loss": 0.1458, + "step": 11513 + }, + { + "epoch": 1.47, + "learning_rate": 1.7075753151744885e-06, + "loss": 0.1352, + "step": 11514 + }, + { + "epoch": 1.47, + "learning_rate": 1.7067953319831327e-06, + "loss": 0.164, + "step": 11515 + }, + { + "epoch": 1.47, + "learning_rate": 1.7060154903081177e-06, + "loss": 0.1228, + "step": 11516 + }, + { + "epoch": 1.47, + "learning_rate": 1.7052357901829502e-06, + "loss": 0.1421, + "step": 11517 + }, + { + "epoch": 1.47, + "learning_rate": 1.70445623164114e-06, + "loss": 0.1229, + "step": 11518 + }, + { + "epoch": 1.47, + "learning_rate": 1.7036768147161853e-06, + "loss": 0.1549, + "step": 11519 + }, + { + "epoch": 1.47, + "learning_rate": 1.7028975394415791e-06, + "loss": 0.1274, + "step": 11520 + }, + { + "epoch": 1.47, + "learning_rate": 1.702118405850809e-06, + "loss": 0.1244, + "step": 11521 + }, + { + "epoch": 1.47, + "learning_rate": 1.7013394139773537e-06, + "loss": 0.1335, + "step": 11522 + }, + { + "epoch": 1.47, + "learning_rate": 1.700560563854694e-06, + "loss": 0.1368, + "step": 11523 + }, + { + "epoch": 1.48, + "learning_rate": 1.6997818555162915e-06, + "loss": 0.1379, + "step": 11524 + }, + { + "epoch": 1.48, + "learning_rate": 1.6990032889956142e-06, + "loss": 0.1394, + "step": 11525 + }, + { + "epoch": 1.48, + "learning_rate": 1.6982248643261173e-06, + "loss": 0.1447, + "step": 11526 + }, + { + "epoch": 1.48, + "learning_rate": 1.6974465815412517e-06, + "loss": 0.141, + "step": 11527 + }, + { + "epoch": 1.48, + "learning_rate": 1.6966684406744615e-06, + "loss": 0.1475, + "step": 11528 + }, + { + "epoch": 1.48, + "learning_rate": 1.6958904417591853e-06, + "loss": 0.138, + "step": 11529 + }, + { + "epoch": 1.48, + "learning_rate": 1.6951125848288558e-06, + "loss": 0.1305, + "step": 11530 + }, + { + "epoch": 1.48, + "learning_rate": 1.6943348699168981e-06, + "loss": 0.1384, + "step": 11531 + }, + { + "epoch": 1.48, + "learning_rate": 1.6935572970567321e-06, + "loss": 0.1457, + "step": 11532 + }, + { + "epoch": 1.48, + "learning_rate": 1.6927798662817745e-06, + "loss": 0.1532, + "step": 11533 + }, + { + "epoch": 1.48, + "learning_rate": 1.6920025776254334e-06, + "loss": 0.1228, + "step": 11534 + }, + { + "epoch": 1.48, + "learning_rate": 1.6912254311211052e-06, + "loss": 0.1405, + "step": 11535 + }, + { + "epoch": 1.48, + "learning_rate": 1.6904484268021915e-06, + "loss": 0.1486, + "step": 11536 + }, + { + "epoch": 1.48, + "learning_rate": 1.689671564702079e-06, + "loss": 0.1335, + "step": 11537 + }, + { + "epoch": 1.48, + "learning_rate": 1.688894844854152e-06, + "loss": 0.1444, + "step": 11538 + }, + { + "epoch": 1.48, + "learning_rate": 1.6881182672917879e-06, + "loss": 0.1433, + "step": 11539 + }, + { + "epoch": 1.48, + "learning_rate": 1.6873418320483565e-06, + "loss": 0.1327, + "step": 11540 + }, + { + "epoch": 1.48, + "learning_rate": 1.6865655391572266e-06, + "loss": 0.1435, + "step": 11541 + }, + { + "epoch": 1.48, + "learning_rate": 1.6857893886517523e-06, + "loss": 0.1331, + "step": 11542 + }, + { + "epoch": 1.48, + "learning_rate": 1.6850133805652907e-06, + "loss": 0.1291, + "step": 11543 + }, + { + "epoch": 1.48, + "learning_rate": 1.6842375149311868e-06, + "loss": 0.138, + "step": 11544 + }, + { + "epoch": 1.48, + "learning_rate": 1.6834617917827817e-06, + "loss": 0.1413, + "step": 11545 + }, + { + "epoch": 1.48, + "learning_rate": 1.6826862111534098e-06, + "loss": 0.1334, + "step": 11546 + }, + { + "epoch": 1.48, + "learning_rate": 1.6819107730763996e-06, + "loss": 0.151, + "step": 11547 + }, + { + "epoch": 1.48, + "learning_rate": 1.681135477585073e-06, + "loss": 0.1357, + "step": 11548 + }, + { + "epoch": 1.48, + "learning_rate": 1.680360324712746e-06, + "loss": 0.1579, + "step": 11549 + }, + { + "epoch": 1.48, + "learning_rate": 1.6795853144927282e-06, + "loss": 0.1314, + "step": 11550 + }, + { + "epoch": 1.48, + "learning_rate": 1.6788104469583256e-06, + "loss": 0.1498, + "step": 11551 + }, + { + "epoch": 1.48, + "learning_rate": 1.678035722142835e-06, + "loss": 0.1363, + "step": 11552 + }, + { + "epoch": 1.48, + "learning_rate": 1.6772611400795475e-06, + "loss": 0.1265, + "step": 11553 + }, + { + "epoch": 1.48, + "learning_rate": 1.6764867008017493e-06, + "loss": 0.1368, + "step": 11554 + }, + { + "epoch": 1.48, + "learning_rate": 1.6757124043427193e-06, + "loss": 0.1393, + "step": 11555 + }, + { + "epoch": 1.48, + "learning_rate": 1.674938250735731e-06, + "loss": 0.1431, + "step": 11556 + }, + { + "epoch": 1.48, + "learning_rate": 1.6741642400140513e-06, + "loss": 0.1496, + "step": 11557 + }, + { + "epoch": 1.48, + "learning_rate": 1.6733903722109391e-06, + "loss": 0.1177, + "step": 11558 + }, + { + "epoch": 1.48, + "learning_rate": 1.672616647359655e-06, + "loss": 0.1374, + "step": 11559 + }, + { + "epoch": 1.48, + "learning_rate": 1.6718430654934408e-06, + "loss": 0.1349, + "step": 11560 + }, + { + "epoch": 1.48, + "learning_rate": 1.671069626645544e-06, + "loss": 0.1304, + "step": 11561 + }, + { + "epoch": 1.48, + "learning_rate": 1.6702963308491994e-06, + "loss": 0.1442, + "step": 11562 + }, + { + "epoch": 1.48, + "learning_rate": 1.669523178137637e-06, + "loss": 0.1353, + "step": 11563 + }, + { + "epoch": 1.48, + "learning_rate": 1.668750168544081e-06, + "loss": 0.1311, + "step": 11564 + }, + { + "epoch": 1.48, + "learning_rate": 1.6679773021017475e-06, + "loss": 0.129, + "step": 11565 + }, + { + "epoch": 1.48, + "learning_rate": 1.6672045788438534e-06, + "loss": 0.1365, + "step": 11566 + }, + { + "epoch": 1.48, + "learning_rate": 1.6664319988036e-06, + "loss": 0.149, + "step": 11567 + }, + { + "epoch": 1.48, + "learning_rate": 1.6656595620141857e-06, + "loss": 0.1475, + "step": 11568 + }, + { + "epoch": 1.48, + "learning_rate": 1.664887268508808e-06, + "loss": 0.1344, + "step": 11569 + }, + { + "epoch": 1.48, + "learning_rate": 1.6641151183206516e-06, + "loss": 0.131, + "step": 11570 + }, + { + "epoch": 1.48, + "learning_rate": 1.663343111482898e-06, + "loss": 0.1421, + "step": 11571 + }, + { + "epoch": 1.48, + "learning_rate": 1.6625712480287225e-06, + "loss": 0.148, + "step": 11572 + }, + { + "epoch": 1.48, + "learning_rate": 1.661799527991293e-06, + "loss": 0.1403, + "step": 11573 + }, + { + "epoch": 1.48, + "learning_rate": 1.6610279514037725e-06, + "loss": 0.1435, + "step": 11574 + }, + { + "epoch": 1.48, + "learning_rate": 1.6602565182993152e-06, + "loss": 0.1384, + "step": 11575 + }, + { + "epoch": 1.48, + "learning_rate": 1.6594852287110758e-06, + "loss": 0.1305, + "step": 11576 + }, + { + "epoch": 1.48, + "learning_rate": 1.6587140826721964e-06, + "loss": 0.1401, + "step": 11577 + }, + { + "epoch": 1.48, + "learning_rate": 1.657943080215812e-06, + "loss": 0.1343, + "step": 11578 + }, + { + "epoch": 1.48, + "learning_rate": 1.657172221375058e-06, + "loss": 0.1428, + "step": 11579 + }, + { + "epoch": 1.48, + "learning_rate": 1.656401506183058e-06, + "loss": 0.1445, + "step": 11580 + }, + { + "epoch": 1.48, + "learning_rate": 1.6556309346729322e-06, + "loss": 0.1542, + "step": 11581 + }, + { + "epoch": 1.48, + "learning_rate": 1.6548605068777935e-06, + "loss": 0.116, + "step": 11582 + }, + { + "epoch": 1.48, + "learning_rate": 1.6540902228307471e-06, + "loss": 0.1523, + "step": 11583 + }, + { + "epoch": 1.48, + "learning_rate": 1.6533200825648993e-06, + "loss": 0.1491, + "step": 11584 + }, + { + "epoch": 1.48, + "learning_rate": 1.6525500861133386e-06, + "loss": 0.1232, + "step": 11585 + }, + { + "epoch": 1.48, + "learning_rate": 1.6517802335091549e-06, + "loss": 0.1149, + "step": 11586 + }, + { + "epoch": 1.48, + "learning_rate": 1.6510105247854325e-06, + "loss": 0.1349, + "step": 11587 + }, + { + "epoch": 1.48, + "learning_rate": 1.6502409599752468e-06, + "loss": 0.1439, + "step": 11588 + }, + { + "epoch": 1.48, + "learning_rate": 1.6494715391116671e-06, + "loss": 0.1287, + "step": 11589 + }, + { + "epoch": 1.48, + "learning_rate": 1.6487022622277582e-06, + "loss": 0.1394, + "step": 11590 + }, + { + "epoch": 1.48, + "learning_rate": 1.6479331293565758e-06, + "loss": 0.1318, + "step": 11591 + }, + { + "epoch": 1.48, + "learning_rate": 1.6471641405311727e-06, + "loss": 0.1397, + "step": 11592 + }, + { + "epoch": 1.48, + "learning_rate": 1.6463952957845924e-06, + "loss": 0.1567, + "step": 11593 + }, + { + "epoch": 1.48, + "learning_rate": 1.6456265951498763e-06, + "loss": 0.1453, + "step": 11594 + }, + { + "epoch": 1.48, + "learning_rate": 1.6448580386600576e-06, + "loss": 0.1541, + "step": 11595 + }, + { + "epoch": 1.48, + "learning_rate": 1.6440896263481582e-06, + "loss": 0.1313, + "step": 11596 + }, + { + "epoch": 1.48, + "learning_rate": 1.6433213582472036e-06, + "loss": 0.1437, + "step": 11597 + }, + { + "epoch": 1.48, + "learning_rate": 1.6425532343902051e-06, + "loss": 0.1437, + "step": 11598 + }, + { + "epoch": 1.48, + "learning_rate": 1.641785254810172e-06, + "loss": 0.1269, + "step": 11599 + }, + { + "epoch": 1.48, + "learning_rate": 1.6410174195401057e-06, + "loss": 0.1338, + "step": 11600 + }, + { + "epoch": 1.48, + "learning_rate": 1.6402497286129998e-06, + "loss": 0.1416, + "step": 11601 + }, + { + "epoch": 1.49, + "learning_rate": 1.6394821820618496e-06, + "loss": 0.1582, + "step": 11602 + }, + { + "epoch": 1.49, + "learning_rate": 1.63871477991963e-06, + "loss": 0.1271, + "step": 11603 + }, + { + "epoch": 1.49, + "learning_rate": 1.6379475222193248e-06, + "loss": 0.1383, + "step": 11604 + }, + { + "epoch": 1.49, + "learning_rate": 1.637180408993902e-06, + "loss": 0.1474, + "step": 11605 + }, + { + "epoch": 1.49, + "learning_rate": 1.636413440276326e-06, + "loss": 0.1266, + "step": 11606 + }, + { + "epoch": 1.49, + "learning_rate": 1.635646616099556e-06, + "loss": 0.1418, + "step": 11607 + }, + { + "epoch": 1.49, + "learning_rate": 1.634879936496544e-06, + "loss": 0.131, + "step": 11608 + }, + { + "epoch": 1.49, + "learning_rate": 1.6341134015002352e-06, + "loss": 0.1498, + "step": 11609 + }, + { + "epoch": 1.49, + "learning_rate": 1.63334701114357e-06, + "loss": 0.1365, + "step": 11610 + }, + { + "epoch": 1.49, + "learning_rate": 1.63258076545948e-06, + "loss": 0.1348, + "step": 11611 + }, + { + "epoch": 1.49, + "learning_rate": 1.6318146644808952e-06, + "loss": 0.1238, + "step": 11612 + }, + { + "epoch": 1.49, + "learning_rate": 1.631048708240736e-06, + "loss": 0.1384, + "step": 11613 + }, + { + "epoch": 1.49, + "learning_rate": 1.6302828967719175e-06, + "loss": 0.128, + "step": 11614 + }, + { + "epoch": 1.49, + "learning_rate": 1.6295172301073469e-06, + "loss": 0.1392, + "step": 11615 + }, + { + "epoch": 1.49, + "learning_rate": 1.6287517082799265e-06, + "loss": 0.1438, + "step": 11616 + }, + { + "epoch": 1.49, + "learning_rate": 1.6279863313225559e-06, + "loss": 0.1219, + "step": 11617 + }, + { + "epoch": 1.49, + "learning_rate": 1.6272210992681213e-06, + "loss": 0.1325, + "step": 11618 + }, + { + "epoch": 1.49, + "learning_rate": 1.626456012149506e-06, + "loss": 0.1558, + "step": 11619 + }, + { + "epoch": 1.49, + "learning_rate": 1.6256910699995921e-06, + "loss": 0.1321, + "step": 11620 + }, + { + "epoch": 1.49, + "learning_rate": 1.624926272851245e-06, + "loss": 0.13, + "step": 11621 + }, + { + "epoch": 1.49, + "learning_rate": 1.6241616207373339e-06, + "loss": 0.1326, + "step": 11622 + }, + { + "epoch": 1.49, + "learning_rate": 1.6233971136907168e-06, + "loss": 0.1432, + "step": 11623 + }, + { + "epoch": 1.49, + "learning_rate": 1.6226327517442453e-06, + "loss": 0.1427, + "step": 11624 + }, + { + "epoch": 1.49, + "learning_rate": 1.6218685349307667e-06, + "loss": 0.1474, + "step": 11625 + }, + { + "epoch": 1.49, + "learning_rate": 1.6211044632831185e-06, + "loss": 0.1268, + "step": 11626 + }, + { + "epoch": 1.49, + "learning_rate": 1.620340536834139e-06, + "loss": 0.1641, + "step": 11627 + }, + { + "epoch": 1.49, + "learning_rate": 1.6195767556166548e-06, + "loss": 0.128, + "step": 11628 + }, + { + "epoch": 1.49, + "learning_rate": 1.6188131196634827e-06, + "loss": 0.1442, + "step": 11629 + }, + { + "epoch": 1.49, + "learning_rate": 1.6180496290074432e-06, + "loss": 0.135, + "step": 11630 + }, + { + "epoch": 1.49, + "learning_rate": 1.617286283681343e-06, + "loss": 0.1273, + "step": 11631 + }, + { + "epoch": 1.49, + "learning_rate": 1.6165230837179846e-06, + "loss": 0.1544, + "step": 11632 + }, + { + "epoch": 1.49, + "learning_rate": 1.6157600291501646e-06, + "loss": 0.1441, + "step": 11633 + }, + { + "epoch": 1.49, + "learning_rate": 1.6149971200106723e-06, + "loss": 0.135, + "step": 11634 + }, + { + "epoch": 1.49, + "learning_rate": 1.6142343563322955e-06, + "loss": 0.1257, + "step": 11635 + }, + { + "epoch": 1.49, + "learning_rate": 1.613471738147807e-06, + "loss": 0.1175, + "step": 11636 + }, + { + "epoch": 1.49, + "learning_rate": 1.6127092654899784e-06, + "loss": 0.1434, + "step": 11637 + }, + { + "epoch": 1.49, + "learning_rate": 1.6119469383915804e-06, + "loss": 0.1379, + "step": 11638 + }, + { + "epoch": 1.49, + "learning_rate": 1.6111847568853645e-06, + "loss": 0.1343, + "step": 11639 + }, + { + "epoch": 1.49, + "learning_rate": 1.6104227210040884e-06, + "loss": 0.132, + "step": 11640 + }, + { + "epoch": 1.49, + "learning_rate": 1.6096608307804973e-06, + "loss": 0.1356, + "step": 11641 + }, + { + "epoch": 1.49, + "learning_rate": 1.608899086247331e-06, + "loss": 0.1246, + "step": 11642 + }, + { + "epoch": 1.49, + "learning_rate": 1.608137487437323e-06, + "loss": 0.1199, + "step": 11643 + }, + { + "epoch": 1.49, + "learning_rate": 1.6073760343831996e-06, + "loss": 0.1394, + "step": 11644 + }, + { + "epoch": 1.49, + "learning_rate": 1.6066147271176857e-06, + "loss": 0.1489, + "step": 11645 + }, + { + "epoch": 1.49, + "learning_rate": 1.6058535656734958e-06, + "loss": 0.1405, + "step": 11646 + }, + { + "epoch": 1.49, + "learning_rate": 1.6050925500833342e-06, + "loss": 0.1373, + "step": 11647 + }, + { + "epoch": 1.49, + "learning_rate": 1.604331680379908e-06, + "loss": 0.1426, + "step": 11648 + }, + { + "epoch": 1.49, + "learning_rate": 1.603570956595913e-06, + "loss": 0.118, + "step": 11649 + }, + { + "epoch": 1.49, + "learning_rate": 1.602810378764037e-06, + "loss": 0.138, + "step": 11650 + }, + { + "epoch": 1.49, + "learning_rate": 1.6020499469169659e-06, + "loss": 0.1535, + "step": 11651 + }, + { + "epoch": 1.49, + "learning_rate": 1.601289661087374e-06, + "loss": 0.1585, + "step": 11652 + }, + { + "epoch": 1.49, + "learning_rate": 1.600529521307938e-06, + "loss": 0.1255, + "step": 11653 + }, + { + "epoch": 1.49, + "learning_rate": 1.5997695276113168e-06, + "loss": 0.1447, + "step": 11654 + }, + { + "epoch": 1.49, + "learning_rate": 1.599009680030173e-06, + "loss": 0.1438, + "step": 11655 + }, + { + "epoch": 1.49, + "learning_rate": 1.598249978597159e-06, + "loss": 0.1381, + "step": 11656 + }, + { + "epoch": 1.49, + "learning_rate": 1.5974904233449167e-06, + "loss": 0.1353, + "step": 11657 + }, + { + "epoch": 1.49, + "learning_rate": 1.59673101430609e-06, + "loss": 0.135, + "step": 11658 + }, + { + "epoch": 1.49, + "learning_rate": 1.595971751513311e-06, + "loss": 0.1296, + "step": 11659 + }, + { + "epoch": 1.49, + "learning_rate": 1.5952126349992076e-06, + "loss": 0.1336, + "step": 11660 + }, + { + "epoch": 1.49, + "learning_rate": 1.5944536647963998e-06, + "loss": 0.1302, + "step": 11661 + }, + { + "epoch": 1.49, + "learning_rate": 1.5936948409375007e-06, + "loss": 0.1419, + "step": 11662 + }, + { + "epoch": 1.49, + "learning_rate": 1.5929361634551227e-06, + "loss": 0.1468, + "step": 11663 + }, + { + "epoch": 1.49, + "learning_rate": 1.5921776323818655e-06, + "loss": 0.1227, + "step": 11664 + }, + { + "epoch": 1.49, + "learning_rate": 1.5914192477503248e-06, + "loss": 0.1415, + "step": 11665 + }, + { + "epoch": 1.49, + "learning_rate": 1.5906610095930908e-06, + "loss": 0.1498, + "step": 11666 + }, + { + "epoch": 1.49, + "learning_rate": 1.589902917942746e-06, + "loss": 0.1513, + "step": 11667 + }, + { + "epoch": 1.49, + "learning_rate": 1.5891449728318675e-06, + "loss": 0.1497, + "step": 11668 + }, + { + "epoch": 1.49, + "learning_rate": 1.5883871742930257e-06, + "loss": 0.1472, + "step": 11669 + }, + { + "epoch": 1.49, + "learning_rate": 1.5876295223587835e-06, + "loss": 0.1359, + "step": 11670 + }, + { + "epoch": 1.49, + "learning_rate": 1.586872017061704e-06, + "loss": 0.1445, + "step": 11671 + }, + { + "epoch": 1.49, + "learning_rate": 1.5861146584343318e-06, + "loss": 0.1554, + "step": 11672 + }, + { + "epoch": 1.49, + "learning_rate": 1.585357446509218e-06, + "loss": 0.1416, + "step": 11673 + }, + { + "epoch": 1.49, + "learning_rate": 1.5846003813188993e-06, + "loss": 0.1351, + "step": 11674 + }, + { + "epoch": 1.49, + "learning_rate": 1.5838434628959081e-06, + "loss": 0.1387, + "step": 11675 + }, + { + "epoch": 1.49, + "learning_rate": 1.5830866912727722e-06, + "loss": 0.1268, + "step": 11676 + }, + { + "epoch": 1.49, + "learning_rate": 1.582330066482009e-06, + "loss": 0.1482, + "step": 11677 + }, + { + "epoch": 1.49, + "learning_rate": 1.5815735885561385e-06, + "loss": 0.1388, + "step": 11678 + }, + { + "epoch": 1.49, + "learning_rate": 1.5808172575276615e-06, + "loss": 0.1359, + "step": 11679 + }, + { + "epoch": 1.5, + "learning_rate": 1.5800610734290805e-06, + "loss": 0.144, + "step": 11680 + }, + { + "epoch": 1.5, + "learning_rate": 1.5793050362928935e-06, + "loss": 0.1562, + "step": 11681 + }, + { + "epoch": 1.5, + "learning_rate": 1.5785491461515878e-06, + "loss": 0.123, + "step": 11682 + }, + { + "epoch": 1.5, + "learning_rate": 1.5777934030376445e-06, + "loss": 0.1456, + "step": 11683 + }, + { + "epoch": 1.5, + "learning_rate": 1.5770378069835412e-06, + "loss": 0.1379, + "step": 11684 + }, + { + "epoch": 1.5, + "learning_rate": 1.5762823580217463e-06, + "loss": 0.1621, + "step": 11685 + }, + { + "epoch": 1.5, + "learning_rate": 1.5755270561847236e-06, + "loss": 0.1335, + "step": 11686 + }, + { + "epoch": 1.5, + "learning_rate": 1.5747719015049294e-06, + "loss": 0.1535, + "step": 11687 + }, + { + "epoch": 1.5, + "learning_rate": 1.5740168940148137e-06, + "loss": 0.1175, + "step": 11688 + }, + { + "epoch": 1.5, + "learning_rate": 1.5732620337468258e-06, + "loss": 0.1441, + "step": 11689 + }, + { + "epoch": 1.5, + "learning_rate": 1.5725073207333963e-06, + "loss": 0.1294, + "step": 11690 + }, + { + "epoch": 1.5, + "learning_rate": 1.5717527550069628e-06, + "loss": 0.134, + "step": 11691 + }, + { + "epoch": 1.5, + "learning_rate": 1.5709983365999481e-06, + "loss": 0.1294, + "step": 11692 + }, + { + "epoch": 1.5, + "learning_rate": 1.570244065544772e-06, + "loss": 0.141, + "step": 11693 + }, + { + "epoch": 1.5, + "learning_rate": 1.5694899418738462e-06, + "loss": 0.1277, + "step": 11694 + }, + { + "epoch": 1.5, + "learning_rate": 1.568735965619577e-06, + "loss": 0.135, + "step": 11695 + }, + { + "epoch": 1.5, + "learning_rate": 1.5679821368143678e-06, + "loss": 0.13, + "step": 11696 + }, + { + "epoch": 1.5, + "learning_rate": 1.5672284554906087e-06, + "loss": 0.1303, + "step": 11697 + }, + { + "epoch": 1.5, + "learning_rate": 1.5664749216806858e-06, + "loss": 0.1184, + "step": 11698 + }, + { + "epoch": 1.5, + "learning_rate": 1.5657215354169841e-06, + "loss": 0.1326, + "step": 11699 + }, + { + "epoch": 1.5, + "learning_rate": 1.564968296731877e-06, + "loss": 0.1205, + "step": 11700 + }, + { + "epoch": 1.5, + "learning_rate": 1.564215205657732e-06, + "loss": 0.1371, + "step": 11701 + }, + { + "epoch": 1.5, + "learning_rate": 1.563462262226912e-06, + "loss": 0.1242, + "step": 11702 + }, + { + "epoch": 1.5, + "learning_rate": 1.5627094664717719e-06, + "loss": 0.1334, + "step": 11703 + }, + { + "epoch": 1.5, + "learning_rate": 1.561956818424661e-06, + "loss": 0.1402, + "step": 11704 + }, + { + "epoch": 1.5, + "learning_rate": 1.561204318117921e-06, + "loss": 0.1473, + "step": 11705 + }, + { + "epoch": 1.5, + "learning_rate": 1.5604519655838918e-06, + "loss": 0.137, + "step": 11706 + }, + { + "epoch": 1.5, + "learning_rate": 1.5596997608549036e-06, + "loss": 0.13, + "step": 11707 + }, + { + "epoch": 1.5, + "learning_rate": 1.5589477039632755e-06, + "loss": 0.1402, + "step": 11708 + }, + { + "epoch": 1.5, + "learning_rate": 1.5581957949413295e-06, + "loss": 0.1531, + "step": 11709 + }, + { + "epoch": 1.5, + "learning_rate": 1.557444033821376e-06, + "loss": 0.1369, + "step": 11710 + }, + { + "epoch": 1.5, + "learning_rate": 1.5566924206357187e-06, + "loss": 0.1281, + "step": 11711 + }, + { + "epoch": 1.5, + "learning_rate": 1.5559409554166572e-06, + "loss": 0.135, + "step": 11712 + }, + { + "epoch": 1.5, + "learning_rate": 1.5551896381964814e-06, + "loss": 0.1323, + "step": 11713 + }, + { + "epoch": 1.5, + "learning_rate": 1.554438469007482e-06, + "loss": 0.1377, + "step": 11714 + }, + { + "epoch": 1.5, + "learning_rate": 1.5536874478819325e-06, + "loss": 0.1499, + "step": 11715 + }, + { + "epoch": 1.5, + "learning_rate": 1.5529365748521097e-06, + "loss": 0.1214, + "step": 11716 + }, + { + "epoch": 1.5, + "learning_rate": 1.5521858499502794e-06, + "loss": 0.1274, + "step": 11717 + }, + { + "epoch": 1.5, + "learning_rate": 1.5514352732087024e-06, + "loss": 0.1306, + "step": 11718 + }, + { + "epoch": 1.5, + "learning_rate": 1.5506848446596317e-06, + "loss": 0.1416, + "step": 11719 + }, + { + "epoch": 1.5, + "learning_rate": 1.5499345643353154e-06, + "loss": 0.1534, + "step": 11720 + }, + { + "epoch": 1.5, + "learning_rate": 1.5491844322679944e-06, + "loss": 0.1387, + "step": 11721 + }, + { + "epoch": 1.5, + "learning_rate": 1.5484344484899038e-06, + "loss": 0.1298, + "step": 11722 + }, + { + "epoch": 1.5, + "learning_rate": 1.5476846130332702e-06, + "loss": 0.1411, + "step": 11723 + }, + { + "epoch": 1.5, + "learning_rate": 1.546934925930319e-06, + "loss": 0.1373, + "step": 11724 + }, + { + "epoch": 1.5, + "learning_rate": 1.5461853872132648e-06, + "loss": 0.1259, + "step": 11725 + }, + { + "epoch": 1.5, + "learning_rate": 1.5454359969143161e-06, + "loss": 0.1509, + "step": 11726 + }, + { + "epoch": 1.5, + "learning_rate": 1.544686755065677e-06, + "loss": 0.1318, + "step": 11727 + }, + { + "epoch": 1.5, + "learning_rate": 1.5439376616995432e-06, + "loss": 0.1392, + "step": 11728 + }, + { + "epoch": 1.5, + "learning_rate": 1.5431887168481051e-06, + "loss": 0.1224, + "step": 11729 + }, + { + "epoch": 1.5, + "learning_rate": 1.5424399205435464e-06, + "loss": 0.143, + "step": 11730 + }, + { + "epoch": 1.5, + "learning_rate": 1.5416912728180433e-06, + "loss": 0.1482, + "step": 11731 + }, + { + "epoch": 1.5, + "learning_rate": 1.5409427737037713e-06, + "loss": 0.1232, + "step": 11732 + }, + { + "epoch": 1.5, + "learning_rate": 1.540194423232889e-06, + "loss": 0.1494, + "step": 11733 + }, + { + "epoch": 1.5, + "learning_rate": 1.5394462214375593e-06, + "loss": 0.1366, + "step": 11734 + }, + { + "epoch": 1.5, + "learning_rate": 1.5386981683499325e-06, + "loss": 0.1332, + "step": 11735 + }, + { + "epoch": 1.5, + "learning_rate": 1.5379502640021544e-06, + "loss": 0.1462, + "step": 11736 + }, + { + "epoch": 1.5, + "learning_rate": 1.537202508426363e-06, + "loss": 0.13, + "step": 11737 + }, + { + "epoch": 1.5, + "learning_rate": 1.5364549016546925e-06, + "loss": 0.1235, + "step": 11738 + }, + { + "epoch": 1.5, + "learning_rate": 1.5357074437192688e-06, + "loss": 0.133, + "step": 11739 + }, + { + "epoch": 1.5, + "learning_rate": 1.5349601346522115e-06, + "loss": 0.1408, + "step": 11740 + }, + { + "epoch": 1.5, + "learning_rate": 1.5342129744856327e-06, + "loss": 0.1609, + "step": 11741 + }, + { + "epoch": 1.5, + "learning_rate": 1.5334659632516424e-06, + "loss": 0.1363, + "step": 11742 + }, + { + "epoch": 1.5, + "learning_rate": 1.5327191009823405e-06, + "loss": 0.1404, + "step": 11743 + }, + { + "epoch": 1.5, + "learning_rate": 1.5319723877098202e-06, + "loss": 0.1348, + "step": 11744 + }, + { + "epoch": 1.5, + "learning_rate": 1.531225823466171e-06, + "loss": 0.145, + "step": 11745 + }, + { + "epoch": 1.5, + "learning_rate": 1.5304794082834713e-06, + "loss": 0.1398, + "step": 11746 + }, + { + "epoch": 1.5, + "learning_rate": 1.5297331421938017e-06, + "loss": 0.1376, + "step": 11747 + }, + { + "epoch": 1.5, + "learning_rate": 1.5289870252292265e-06, + "loss": 0.1399, + "step": 11748 + }, + { + "epoch": 1.5, + "learning_rate": 1.5282410574218072e-06, + "loss": 0.119, + "step": 11749 + }, + { + "epoch": 1.5, + "learning_rate": 1.5274952388036052e-06, + "loss": 0.1377, + "step": 11750 + }, + { + "epoch": 1.5, + "learning_rate": 1.5267495694066631e-06, + "loss": 0.1427, + "step": 11751 + }, + { + "epoch": 1.5, + "learning_rate": 1.5260040492630286e-06, + "loss": 0.1447, + "step": 11752 + }, + { + "epoch": 1.5, + "learning_rate": 1.5252586784047374e-06, + "loss": 0.1299, + "step": 11753 + }, + { + "epoch": 1.5, + "learning_rate": 1.5245134568638197e-06, + "loss": 0.1379, + "step": 11754 + }, + { + "epoch": 1.5, + "learning_rate": 1.523768384672299e-06, + "loss": 0.1428, + "step": 11755 + }, + { + "epoch": 1.5, + "learning_rate": 1.5230234618621908e-06, + "loss": 0.1295, + "step": 11756 + }, + { + "epoch": 1.5, + "learning_rate": 1.5222786884655117e-06, + "loss": 0.1345, + "step": 11757 + }, + { + "epoch": 1.51, + "learning_rate": 1.5215340645142607e-06, + "loss": 0.1238, + "step": 11758 + }, + { + "epoch": 1.51, + "learning_rate": 1.5207895900404363e-06, + "loss": 0.1317, + "step": 11759 + }, + { + "epoch": 1.51, + "learning_rate": 1.520045265076034e-06, + "loss": 0.1509, + "step": 11760 + }, + { + "epoch": 1.51, + "learning_rate": 1.5193010896530364e-06, + "loss": 0.1272, + "step": 11761 + }, + { + "epoch": 1.51, + "learning_rate": 1.518557063803423e-06, + "loss": 0.1549, + "step": 11762 + }, + { + "epoch": 1.51, + "learning_rate": 1.5178131875591662e-06, + "loss": 0.1329, + "step": 11763 + }, + { + "epoch": 1.51, + "learning_rate": 1.5170694609522306e-06, + "loss": 0.1315, + "step": 11764 + }, + { + "epoch": 1.51, + "learning_rate": 1.51632588401458e-06, + "loss": 0.1366, + "step": 11765 + }, + { + "epoch": 1.51, + "learning_rate": 1.5155824567781618e-06, + "loss": 0.1489, + "step": 11766 + }, + { + "epoch": 1.51, + "learning_rate": 1.5148391792749272e-06, + "loss": 0.138, + "step": 11767 + }, + { + "epoch": 1.51, + "learning_rate": 1.5140960515368165e-06, + "loss": 0.1537, + "step": 11768 + }, + { + "epoch": 1.51, + "learning_rate": 1.5133530735957586e-06, + "loss": 0.1309, + "step": 11769 + }, + { + "epoch": 1.51, + "learning_rate": 1.512610245483686e-06, + "loss": 0.1331, + "step": 11770 + }, + { + "epoch": 1.51, + "learning_rate": 1.5118675672325184e-06, + "loss": 0.1388, + "step": 11771 + }, + { + "epoch": 1.51, + "learning_rate": 1.5111250388741693e-06, + "loss": 0.128, + "step": 11772 + }, + { + "epoch": 1.51, + "learning_rate": 1.510382660440548e-06, + "loss": 0.129, + "step": 11773 + }, + { + "epoch": 1.51, + "learning_rate": 1.5096404319635533e-06, + "loss": 0.1491, + "step": 11774 + }, + { + "epoch": 1.51, + "learning_rate": 1.5088983534750867e-06, + "loss": 0.1342, + "step": 11775 + }, + { + "epoch": 1.51, + "learning_rate": 1.5081564250070291e-06, + "loss": 0.1258, + "step": 11776 + }, + { + "epoch": 1.51, + "learning_rate": 1.5074146465912687e-06, + "loss": 0.1379, + "step": 11777 + }, + { + "epoch": 1.51, + "learning_rate": 1.506673018259679e-06, + "loss": 0.1368, + "step": 11778 + }, + { + "epoch": 1.51, + "learning_rate": 1.50593154004413e-06, + "loss": 0.1349, + "step": 11779 + }, + { + "epoch": 1.51, + "learning_rate": 1.505190211976484e-06, + "loss": 0.1435, + "step": 11780 + }, + { + "epoch": 1.51, + "learning_rate": 1.5044490340885987e-06, + "loss": 0.1404, + "step": 11781 + }, + { + "epoch": 1.51, + "learning_rate": 1.5037080064123212e-06, + "loss": 0.1265, + "step": 11782 + }, + { + "epoch": 1.51, + "learning_rate": 1.5029671289795007e-06, + "loss": 0.1385, + "step": 11783 + }, + { + "epoch": 1.51, + "learning_rate": 1.502226401821968e-06, + "loss": 0.1435, + "step": 11784 + }, + { + "epoch": 1.51, + "learning_rate": 1.501485824971558e-06, + "loss": 0.1387, + "step": 11785 + }, + { + "epoch": 1.51, + "learning_rate": 1.5007453984600956e-06, + "loss": 0.1295, + "step": 11786 + }, + { + "epoch": 1.51, + "learning_rate": 1.5000051223193928e-06, + "loss": 0.1443, + "step": 11787 + }, + { + "epoch": 1.51, + "learning_rate": 1.4992649965812673e-06, + "loss": 0.144, + "step": 11788 + }, + { + "epoch": 1.51, + "learning_rate": 1.498525021277521e-06, + "loss": 0.1389, + "step": 11789 + }, + { + "epoch": 1.51, + "learning_rate": 1.497785196439953e-06, + "loss": 0.1374, + "step": 11790 + }, + { + "epoch": 1.51, + "learning_rate": 1.497045522100355e-06, + "loss": 0.1288, + "step": 11791 + }, + { + "epoch": 1.51, + "learning_rate": 1.4963059982905104e-06, + "loss": 0.1341, + "step": 11792 + }, + { + "epoch": 1.51, + "learning_rate": 1.4955666250422035e-06, + "loss": 0.1356, + "step": 11793 + }, + { + "epoch": 1.51, + "learning_rate": 1.4948274023872005e-06, + "loss": 0.1269, + "step": 11794 + }, + { + "epoch": 1.51, + "learning_rate": 1.4940883303572724e-06, + "loss": 0.1173, + "step": 11795 + }, + { + "epoch": 1.51, + "learning_rate": 1.493349408984176e-06, + "loss": 0.1417, + "step": 11796 + }, + { + "epoch": 1.51, + "learning_rate": 1.4926106382996658e-06, + "loss": 0.1255, + "step": 11797 + }, + { + "epoch": 1.51, + "learning_rate": 1.491872018335488e-06, + "loss": 0.1192, + "step": 11798 + }, + { + "epoch": 1.51, + "learning_rate": 1.4911335491233818e-06, + "loss": 0.1413, + "step": 11799 + }, + { + "epoch": 1.51, + "learning_rate": 1.4903952306950808e-06, + "loss": 0.1392, + "step": 11800 + }, + { + "epoch": 1.51, + "learning_rate": 1.489657063082316e-06, + "loss": 0.1305, + "step": 11801 + }, + { + "epoch": 1.51, + "learning_rate": 1.4889190463168019e-06, + "loss": 0.1359, + "step": 11802 + }, + { + "epoch": 1.51, + "learning_rate": 1.4881811804302577e-06, + "loss": 0.1166, + "step": 11803 + }, + { + "epoch": 1.51, + "learning_rate": 1.487443465454389e-06, + "loss": 0.1452, + "step": 11804 + }, + { + "epoch": 1.51, + "learning_rate": 1.4867059014208979e-06, + "loss": 0.1316, + "step": 11805 + }, + { + "epoch": 1.51, + "learning_rate": 1.4859684883614788e-06, + "loss": 0.1332, + "step": 11806 + }, + { + "epoch": 1.51, + "learning_rate": 1.4852312263078183e-06, + "loss": 0.1475, + "step": 11807 + }, + { + "epoch": 1.51, + "learning_rate": 1.4844941152916026e-06, + "loss": 0.1292, + "step": 11808 + }, + { + "epoch": 1.51, + "learning_rate": 1.483757155344503e-06, + "loss": 0.1292, + "step": 11809 + }, + { + "epoch": 1.51, + "learning_rate": 1.4830203464981879e-06, + "loss": 0.1274, + "step": 11810 + }, + { + "epoch": 1.51, + "learning_rate": 1.4822836887843244e-06, + "loss": 0.1229, + "step": 11811 + }, + { + "epoch": 1.51, + "learning_rate": 1.4815471822345618e-06, + "loss": 0.134, + "step": 11812 + }, + { + "epoch": 1.51, + "learning_rate": 1.4808108268805549e-06, + "loss": 0.1419, + "step": 11813 + }, + { + "epoch": 1.51, + "learning_rate": 1.4800746227539437e-06, + "loss": 0.1344, + "step": 11814 + }, + { + "epoch": 1.51, + "learning_rate": 1.479338569886366e-06, + "loss": 0.1462, + "step": 11815 + }, + { + "epoch": 1.51, + "learning_rate": 1.47860266830945e-06, + "loss": 0.1428, + "step": 11816 + }, + { + "epoch": 1.51, + "learning_rate": 1.4778669180548195e-06, + "loss": 0.1301, + "step": 11817 + }, + { + "epoch": 1.51, + "learning_rate": 1.4771313191540927e-06, + "loss": 0.1528, + "step": 11818 + }, + { + "epoch": 1.51, + "learning_rate": 1.4763958716388798e-06, + "loss": 0.1322, + "step": 11819 + }, + { + "epoch": 1.51, + "learning_rate": 1.4756605755407816e-06, + "loss": 0.1343, + "step": 11820 + }, + { + "epoch": 1.51, + "learning_rate": 1.474925430891399e-06, + "loss": 0.1314, + "step": 11821 + }, + { + "epoch": 1.51, + "learning_rate": 1.4741904377223215e-06, + "loss": 0.1252, + "step": 11822 + }, + { + "epoch": 1.51, + "learning_rate": 1.473455596065133e-06, + "loss": 0.1507, + "step": 11823 + }, + { + "epoch": 1.51, + "learning_rate": 1.4727209059514114e-06, + "loss": 0.1371, + "step": 11824 + }, + { + "epoch": 1.51, + "learning_rate": 1.4719863674127272e-06, + "loss": 0.1377, + "step": 11825 + }, + { + "epoch": 1.51, + "learning_rate": 1.4712519804806485e-06, + "loss": 0.1267, + "step": 11826 + }, + { + "epoch": 1.51, + "learning_rate": 1.4705177451867287e-06, + "loss": 0.1464, + "step": 11827 + }, + { + "epoch": 1.51, + "learning_rate": 1.4697836615625233e-06, + "loss": 0.1406, + "step": 11828 + }, + { + "epoch": 1.51, + "learning_rate": 1.4690497296395773e-06, + "loss": 0.1332, + "step": 11829 + }, + { + "epoch": 1.51, + "learning_rate": 1.4683159494494259e-06, + "loss": 0.1365, + "step": 11830 + }, + { + "epoch": 1.51, + "learning_rate": 1.4675823210236046e-06, + "loss": 0.115, + "step": 11831 + }, + { + "epoch": 1.51, + "learning_rate": 1.4668488443936385e-06, + "loss": 0.1431, + "step": 11832 + }, + { + "epoch": 1.51, + "learning_rate": 1.466115519591046e-06, + "loss": 0.1392, + "step": 11833 + }, + { + "epoch": 1.51, + "learning_rate": 1.46538234664734e-06, + "loss": 0.1424, + "step": 11834 + }, + { + "epoch": 1.51, + "learning_rate": 1.4646493255940253e-06, + "loss": 0.1464, + "step": 11835 + }, + { + "epoch": 1.52, + "learning_rate": 1.4639164564626041e-06, + "loss": 0.1314, + "step": 11836 + }, + { + "epoch": 1.52, + "learning_rate": 1.4631837392845694e-06, + "loss": 0.1324, + "step": 11837 + }, + { + "epoch": 1.52, + "learning_rate": 1.4624511740914032e-06, + "loss": 0.1383, + "step": 11838 + }, + { + "epoch": 1.52, + "learning_rate": 1.4617187609145906e-06, + "loss": 0.1394, + "step": 11839 + }, + { + "epoch": 1.52, + "learning_rate": 1.4609864997856026e-06, + "loss": 0.1424, + "step": 11840 + }, + { + "epoch": 1.52, + "learning_rate": 1.4602543907359068e-06, + "loss": 0.1311, + "step": 11841 + }, + { + "epoch": 1.52, + "learning_rate": 1.4595224337969633e-06, + "loss": 0.1303, + "step": 11842 + }, + { + "epoch": 1.52, + "learning_rate": 1.4587906290002242e-06, + "loss": 0.1345, + "step": 11843 + }, + { + "epoch": 1.52, + "learning_rate": 1.4580589763771413e-06, + "loss": 0.1468, + "step": 11844 + }, + { + "epoch": 1.52, + "learning_rate": 1.4573274759591499e-06, + "loss": 0.1541, + "step": 11845 + }, + { + "epoch": 1.52, + "learning_rate": 1.456596127777688e-06, + "loss": 0.1451, + "step": 11846 + }, + { + "epoch": 1.52, + "learning_rate": 1.4558649318641837e-06, + "loss": 0.1395, + "step": 11847 + }, + { + "epoch": 1.52, + "learning_rate": 1.4551338882500538e-06, + "loss": 0.1379, + "step": 11848 + }, + { + "epoch": 1.52, + "learning_rate": 1.4544029969667167e-06, + "loss": 0.1146, + "step": 11849 + }, + { + "epoch": 1.52, + "learning_rate": 1.4536722580455792e-06, + "loss": 0.13, + "step": 11850 + }, + { + "epoch": 1.52, + "learning_rate": 1.4529416715180434e-06, + "loss": 0.1355, + "step": 11851 + }, + { + "epoch": 1.52, + "learning_rate": 1.452211237415503e-06, + "loss": 0.1264, + "step": 11852 + }, + { + "epoch": 1.52, + "learning_rate": 1.451480955769346e-06, + "loss": 0.1392, + "step": 11853 + }, + { + "epoch": 1.52, + "learning_rate": 1.4507508266109565e-06, + "loss": 0.1343, + "step": 11854 + }, + { + "epoch": 1.52, + "learning_rate": 1.4500208499717088e-06, + "loss": 0.1371, + "step": 11855 + }, + { + "epoch": 1.52, + "learning_rate": 1.4492910258829717e-06, + "loss": 0.1331, + "step": 11856 + }, + { + "epoch": 1.52, + "learning_rate": 1.4485613543761068e-06, + "loss": 0.1431, + "step": 11857 + }, + { + "epoch": 1.52, + "learning_rate": 1.44783183548247e-06, + "loss": 0.1421, + "step": 11858 + }, + { + "epoch": 1.52, + "learning_rate": 1.4471024692334101e-06, + "loss": 0.1135, + "step": 11859 + }, + { + "epoch": 1.52, + "learning_rate": 1.44637325566027e-06, + "loss": 0.1412, + "step": 11860 + }, + { + "epoch": 1.52, + "learning_rate": 1.445644194794384e-06, + "loss": 0.1374, + "step": 11861 + }, + { + "epoch": 1.52, + "learning_rate": 1.4449152866670858e-06, + "loss": 0.1377, + "step": 11862 + }, + { + "epoch": 1.52, + "learning_rate": 1.4441865313096926e-06, + "loss": 0.1303, + "step": 11863 + }, + { + "epoch": 1.52, + "learning_rate": 1.4434579287535244e-06, + "loss": 0.1434, + "step": 11864 + }, + { + "epoch": 1.52, + "learning_rate": 1.4427294790298902e-06, + "loss": 0.1289, + "step": 11865 + }, + { + "epoch": 1.52, + "learning_rate": 1.4420011821700924e-06, + "loss": 0.1284, + "step": 11866 + }, + { + "epoch": 1.52, + "learning_rate": 1.4412730382054285e-06, + "loss": 0.1343, + "step": 11867 + }, + { + "epoch": 1.52, + "learning_rate": 1.4405450471671861e-06, + "loss": 0.1256, + "step": 11868 + }, + { + "epoch": 1.52, + "learning_rate": 1.439817209086653e-06, + "loss": 0.1336, + "step": 11869 + }, + { + "epoch": 1.52, + "learning_rate": 1.4390895239951025e-06, + "loss": 0.1258, + "step": 11870 + }, + { + "epoch": 1.52, + "learning_rate": 1.4383619919238035e-06, + "loss": 0.1499, + "step": 11871 + }, + { + "epoch": 1.52, + "learning_rate": 1.4376346129040243e-06, + "loss": 0.1151, + "step": 11872 + }, + { + "epoch": 1.52, + "learning_rate": 1.4369073869670186e-06, + "loss": 0.1364, + "step": 11873 + }, + { + "epoch": 1.52, + "learning_rate": 1.4361803141440384e-06, + "loss": 0.1388, + "step": 11874 + }, + { + "epoch": 1.52, + "learning_rate": 1.4354533944663274e-06, + "loss": 0.1305, + "step": 11875 + }, + { + "epoch": 1.52, + "learning_rate": 1.4347266279651224e-06, + "loss": 0.1383, + "step": 11876 + }, + { + "epoch": 1.52, + "learning_rate": 1.4340000146716544e-06, + "loss": 0.1471, + "step": 11877 + }, + { + "epoch": 1.52, + "learning_rate": 1.4332735546171466e-06, + "loss": 0.1293, + "step": 11878 + }, + { + "epoch": 1.52, + "learning_rate": 1.432547247832819e-06, + "loss": 0.1514, + "step": 11879 + }, + { + "epoch": 1.52, + "learning_rate": 1.431821094349883e-06, + "loss": 0.1512, + "step": 11880 + }, + { + "epoch": 1.52, + "learning_rate": 1.4310950941995378e-06, + "loss": 0.1463, + "step": 11881 + }, + { + "epoch": 1.52, + "learning_rate": 1.4303692474129866e-06, + "loss": 0.1389, + "step": 11882 + }, + { + "epoch": 1.52, + "learning_rate": 1.4296435540214181e-06, + "loss": 0.1413, + "step": 11883 + }, + { + "epoch": 1.52, + "learning_rate": 1.4289180140560189e-06, + "loss": 0.1469, + "step": 11884 + }, + { + "epoch": 1.52, + "learning_rate": 1.428192627547965e-06, + "loss": 0.1338, + "step": 11885 + }, + { + "epoch": 1.52, + "learning_rate": 1.4274673945284278e-06, + "loss": 0.1332, + "step": 11886 + }, + { + "epoch": 1.52, + "learning_rate": 1.4267423150285758e-06, + "loss": 0.1409, + "step": 11887 + }, + { + "epoch": 1.52, + "learning_rate": 1.4260173890795631e-06, + "loss": 0.1534, + "step": 11888 + }, + { + "epoch": 1.52, + "learning_rate": 1.4252926167125413e-06, + "loss": 0.136, + "step": 11889 + }, + { + "epoch": 1.52, + "learning_rate": 1.4245679979586591e-06, + "loss": 0.1305, + "step": 11890 + }, + { + "epoch": 1.52, + "learning_rate": 1.4238435328490525e-06, + "loss": 0.1305, + "step": 11891 + }, + { + "epoch": 1.52, + "learning_rate": 1.4231192214148538e-06, + "loss": 0.1447, + "step": 11892 + }, + { + "epoch": 1.52, + "learning_rate": 1.422395063687188e-06, + "loss": 0.1325, + "step": 11893 + }, + { + "epoch": 1.52, + "learning_rate": 1.421671059697175e-06, + "loss": 0.1417, + "step": 11894 + }, + { + "epoch": 1.52, + "learning_rate": 1.4209472094759252e-06, + "loss": 0.1415, + "step": 11895 + }, + { + "epoch": 1.52, + "learning_rate": 1.4202235130545432e-06, + "loss": 0.1449, + "step": 11896 + }, + { + "epoch": 1.52, + "learning_rate": 1.4194999704641315e-06, + "loss": 0.1382, + "step": 11897 + }, + { + "epoch": 1.52, + "learning_rate": 1.4187765817357812e-06, + "loss": 0.135, + "step": 11898 + }, + { + "epoch": 1.52, + "learning_rate": 1.418053346900574e-06, + "loss": 0.1352, + "step": 11899 + }, + { + "epoch": 1.52, + "learning_rate": 1.4173302659895938e-06, + "loss": 0.1252, + "step": 11900 + }, + { + "epoch": 1.52, + "learning_rate": 1.4166073390339113e-06, + "loss": 0.1356, + "step": 11901 + }, + { + "epoch": 1.52, + "learning_rate": 1.4158845660645915e-06, + "loss": 0.1317, + "step": 11902 + }, + { + "epoch": 1.52, + "learning_rate": 1.4151619471126943e-06, + "loss": 0.1484, + "step": 11903 + }, + { + "epoch": 1.52, + "learning_rate": 1.4144394822092712e-06, + "loss": 0.1394, + "step": 11904 + }, + { + "epoch": 1.52, + "learning_rate": 1.4137171713853714e-06, + "loss": 0.1368, + "step": 11905 + }, + { + "epoch": 1.52, + "learning_rate": 1.412995014672029e-06, + "loss": 0.13, + "step": 11906 + }, + { + "epoch": 1.52, + "learning_rate": 1.4122730121002808e-06, + "loss": 0.127, + "step": 11907 + }, + { + "epoch": 1.52, + "learning_rate": 1.4115511637011514e-06, + "loss": 0.1427, + "step": 11908 + }, + { + "epoch": 1.52, + "learning_rate": 1.4108294695056606e-06, + "loss": 0.1338, + "step": 11909 + }, + { + "epoch": 1.52, + "learning_rate": 1.4101079295448217e-06, + "loss": 0.1519, + "step": 11910 + }, + { + "epoch": 1.52, + "learning_rate": 1.4093865438496395e-06, + "loss": 0.1274, + "step": 11911 + }, + { + "epoch": 1.52, + "learning_rate": 1.408665312451114e-06, + "loss": 0.1272, + "step": 11912 + }, + { + "epoch": 1.52, + "learning_rate": 1.4079442353802392e-06, + "loss": 0.1336, + "step": 11913 + }, + { + "epoch": 1.52, + "learning_rate": 1.4072233126679985e-06, + "loss": 0.1493, + "step": 11914 + }, + { + "epoch": 1.53, + "learning_rate": 1.406502544345375e-06, + "loss": 0.1429, + "step": 11915 + }, + { + "epoch": 1.53, + "learning_rate": 1.40578193044334e-06, + "loss": 0.1193, + "step": 11916 + }, + { + "epoch": 1.53, + "learning_rate": 1.4050614709928612e-06, + "loss": 0.1332, + "step": 11917 + }, + { + "epoch": 1.53, + "learning_rate": 1.4043411660248967e-06, + "loss": 0.1388, + "step": 11918 + }, + { + "epoch": 1.53, + "learning_rate": 1.4036210155703989e-06, + "loss": 0.1334, + "step": 11919 + }, + { + "epoch": 1.53, + "learning_rate": 1.4029010196603182e-06, + "loss": 0.13, + "step": 11920 + }, + { + "epoch": 1.53, + "learning_rate": 1.4021811783255912e-06, + "loss": 0.1127, + "step": 11921 + }, + { + "epoch": 1.53, + "learning_rate": 1.4014614915971498e-06, + "loss": 0.1362, + "step": 11922 + }, + { + "epoch": 1.53, + "learning_rate": 1.4007419595059252e-06, + "loss": 0.1487, + "step": 11923 + }, + { + "epoch": 1.53, + "learning_rate": 1.4000225820828317e-06, + "loss": 0.1418, + "step": 11924 + }, + { + "epoch": 1.53, + "learning_rate": 1.3993033593587874e-06, + "loss": 0.1321, + "step": 11925 + }, + { + "epoch": 1.53, + "learning_rate": 1.3985842913646963e-06, + "loss": 0.1455, + "step": 11926 + }, + { + "epoch": 1.53, + "learning_rate": 1.3978653781314595e-06, + "loss": 0.1473, + "step": 11927 + }, + { + "epoch": 1.53, + "learning_rate": 1.3971466196899697e-06, + "loss": 0.1383, + "step": 11928 + }, + { + "epoch": 1.53, + "learning_rate": 1.3964280160711119e-06, + "loss": 0.133, + "step": 11929 + }, + { + "epoch": 1.53, + "learning_rate": 1.3957095673057708e-06, + "loss": 0.1392, + "step": 11930 + }, + { + "epoch": 1.53, + "learning_rate": 1.3949912734248156e-06, + "loss": 0.1239, + "step": 11931 + }, + { + "epoch": 1.53, + "learning_rate": 1.3942731344591127e-06, + "loss": 0.1329, + "step": 11932 + }, + { + "epoch": 1.53, + "learning_rate": 1.3935551504395246e-06, + "loss": 0.1423, + "step": 11933 + }, + { + "epoch": 1.53, + "learning_rate": 1.3928373213969038e-06, + "loss": 0.1395, + "step": 11934 + }, + { + "epoch": 1.53, + "learning_rate": 1.3921196473620975e-06, + "loss": 0.1377, + "step": 11935 + }, + { + "epoch": 1.53, + "learning_rate": 1.3914021283659445e-06, + "loss": 0.14, + "step": 11936 + }, + { + "epoch": 1.53, + "learning_rate": 1.3906847644392773e-06, + "loss": 0.1251, + "step": 11937 + }, + { + "epoch": 1.53, + "learning_rate": 1.3899675556129272e-06, + "loss": 0.1284, + "step": 11938 + }, + { + "epoch": 1.53, + "learning_rate": 1.38925050191771e-06, + "loss": 0.141, + "step": 11939 + }, + { + "epoch": 1.53, + "learning_rate": 1.3885336033844388e-06, + "loss": 0.1335, + "step": 11940 + }, + { + "epoch": 1.53, + "learning_rate": 1.3878168600439246e-06, + "loss": 0.1363, + "step": 11941 + }, + { + "epoch": 1.53, + "learning_rate": 1.3871002719269616e-06, + "loss": 0.1343, + "step": 11942 + }, + { + "epoch": 1.53, + "learning_rate": 1.386383839064348e-06, + "loss": 0.1441, + "step": 11943 + }, + { + "epoch": 1.53, + "learning_rate": 1.3856675614868687e-06, + "loss": 0.1282, + "step": 11944 + }, + { + "epoch": 1.53, + "learning_rate": 1.3849514392253038e-06, + "loss": 0.1495, + "step": 11945 + }, + { + "epoch": 1.53, + "learning_rate": 1.3842354723104267e-06, + "loss": 0.1421, + "step": 11946 + }, + { + "epoch": 1.53, + "learning_rate": 1.3835196607730028e-06, + "loss": 0.1315, + "step": 11947 + }, + { + "epoch": 1.53, + "learning_rate": 1.3828040046437963e-06, + "loss": 0.1398, + "step": 11948 + }, + { + "epoch": 1.53, + "learning_rate": 1.3820885039535564e-06, + "loss": 0.1442, + "step": 11949 + }, + { + "epoch": 1.53, + "learning_rate": 1.3813731587330291e-06, + "loss": 0.1284, + "step": 11950 + }, + { + "epoch": 1.53, + "learning_rate": 1.380657969012958e-06, + "loss": 0.1414, + "step": 11951 + }, + { + "epoch": 1.53, + "learning_rate": 1.3799429348240746e-06, + "loss": 0.1199, + "step": 11952 + }, + { + "epoch": 1.53, + "learning_rate": 1.3792280561971056e-06, + "loss": 0.149, + "step": 11953 + }, + { + "epoch": 1.53, + "learning_rate": 1.378513333162771e-06, + "loss": 0.1347, + "step": 11954 + }, + { + "epoch": 1.53, + "learning_rate": 1.3777987657517822e-06, + "loss": 0.1255, + "step": 11955 + }, + { + "epoch": 1.53, + "learning_rate": 1.3770843539948508e-06, + "loss": 0.1251, + "step": 11956 + }, + { + "epoch": 1.53, + "learning_rate": 1.3763700979226701e-06, + "loss": 0.1312, + "step": 11957 + }, + { + "epoch": 1.53, + "learning_rate": 1.3756559975659385e-06, + "loss": 0.1338, + "step": 11958 + }, + { + "epoch": 1.53, + "learning_rate": 1.3749420529553414e-06, + "loss": 0.1419, + "step": 11959 + }, + { + "epoch": 1.53, + "learning_rate": 1.3742282641215549e-06, + "loss": 0.1323, + "step": 11960 + }, + { + "epoch": 1.53, + "learning_rate": 1.3735146310952568e-06, + "loss": 0.1297, + "step": 11961 + }, + { + "epoch": 1.53, + "learning_rate": 1.3728011539071112e-06, + "loss": 0.1291, + "step": 11962 + }, + { + "epoch": 1.53, + "learning_rate": 1.3720878325877785e-06, + "loss": 0.1192, + "step": 11963 + }, + { + "epoch": 1.53, + "learning_rate": 1.3713746671679112e-06, + "loss": 0.111, + "step": 11964 + }, + { + "epoch": 1.53, + "learning_rate": 1.3706616576781545e-06, + "loss": 0.1441, + "step": 11965 + }, + { + "epoch": 1.53, + "learning_rate": 1.3699488041491526e-06, + "loss": 0.1315, + "step": 11966 + }, + { + "epoch": 1.53, + "learning_rate": 1.3692361066115318e-06, + "loss": 0.1398, + "step": 11967 + }, + { + "epoch": 1.53, + "learning_rate": 1.3685235650959228e-06, + "loss": 0.1369, + "step": 11968 + }, + { + "epoch": 1.53, + "learning_rate": 1.3678111796329446e-06, + "loss": 0.162, + "step": 11969 + }, + { + "epoch": 1.53, + "learning_rate": 1.3670989502532089e-06, + "loss": 0.1384, + "step": 11970 + }, + { + "epoch": 1.53, + "learning_rate": 1.3663868769873223e-06, + "loss": 0.1393, + "step": 11971 + }, + { + "epoch": 1.53, + "learning_rate": 1.365674959865884e-06, + "loss": 0.141, + "step": 11972 + }, + { + "epoch": 1.53, + "learning_rate": 1.3649631989194856e-06, + "loss": 0.1326, + "step": 11973 + }, + { + "epoch": 1.53, + "learning_rate": 1.3642515941787171e-06, + "loss": 0.1399, + "step": 11974 + }, + { + "epoch": 1.53, + "learning_rate": 1.363540145674152e-06, + "loss": 0.1322, + "step": 11975 + }, + { + "epoch": 1.53, + "learning_rate": 1.3628288534363664e-06, + "loss": 0.1293, + "step": 11976 + }, + { + "epoch": 1.53, + "learning_rate": 1.362117717495926e-06, + "loss": 0.1463, + "step": 11977 + }, + { + "epoch": 1.53, + "learning_rate": 1.3614067378833895e-06, + "loss": 0.1293, + "step": 11978 + }, + { + "epoch": 1.53, + "learning_rate": 1.3606959146293086e-06, + "loss": 0.1326, + "step": 11979 + }, + { + "epoch": 1.53, + "learning_rate": 1.3599852477642283e-06, + "loss": 0.1302, + "step": 11980 + }, + { + "epoch": 1.53, + "learning_rate": 1.3592747373186915e-06, + "loss": 0.1373, + "step": 11981 + }, + { + "epoch": 1.53, + "learning_rate": 1.358564383323226e-06, + "loss": 0.1543, + "step": 11982 + }, + { + "epoch": 1.53, + "learning_rate": 1.357854185808357e-06, + "loss": 0.1538, + "step": 11983 + }, + { + "epoch": 1.53, + "learning_rate": 1.3571441448046086e-06, + "loss": 0.13, + "step": 11984 + }, + { + "epoch": 1.53, + "learning_rate": 1.3564342603424864e-06, + "loss": 0.1461, + "step": 11985 + }, + { + "epoch": 1.53, + "learning_rate": 1.3557245324524999e-06, + "loss": 0.1265, + "step": 11986 + }, + { + "epoch": 1.53, + "learning_rate": 1.3550149611651463e-06, + "loss": 0.1304, + "step": 11987 + }, + { + "epoch": 1.53, + "learning_rate": 1.3543055465109183e-06, + "loss": 0.1464, + "step": 11988 + }, + { + "epoch": 1.53, + "learning_rate": 1.3535962885202997e-06, + "loss": 0.1425, + "step": 11989 + }, + { + "epoch": 1.53, + "learning_rate": 1.3528871872237687e-06, + "loss": 0.1339, + "step": 11990 + }, + { + "epoch": 1.53, + "learning_rate": 1.3521782426517988e-06, + "loss": 0.1274, + "step": 11991 + }, + { + "epoch": 1.53, + "learning_rate": 1.3514694548348556e-06, + "loss": 0.1367, + "step": 11992 + }, + { + "epoch": 1.54, + "learning_rate": 1.3507608238033927e-06, + "loss": 0.1308, + "step": 11993 + }, + { + "epoch": 1.54, + "learning_rate": 1.350052349587866e-06, + "loss": 0.1317, + "step": 11994 + }, + { + "epoch": 1.54, + "learning_rate": 1.3493440322187185e-06, + "loss": 0.1297, + "step": 11995 + }, + { + "epoch": 1.54, + "learning_rate": 1.3486358717263887e-06, + "loss": 0.1261, + "step": 11996 + }, + { + "epoch": 1.54, + "learning_rate": 1.3479278681413072e-06, + "loss": 0.139, + "step": 11997 + }, + { + "epoch": 1.54, + "learning_rate": 1.3472200214938974e-06, + "loss": 0.1263, + "step": 11998 + }, + { + "epoch": 1.54, + "learning_rate": 1.3465123318145817e-06, + "loss": 0.1504, + "step": 11999 + }, + { + "epoch": 1.54, + "learning_rate": 1.3458047991337664e-06, + "loss": 0.1552, + "step": 12000 + }, + { + "epoch": 1.54, + "learning_rate": 1.3450974234818554e-06, + "loss": 0.1339, + "step": 12001 + }, + { + "epoch": 1.54, + "learning_rate": 1.34439020488925e-06, + "loss": 0.1236, + "step": 12002 + }, + { + "epoch": 1.54, + "learning_rate": 1.3436831433863384e-06, + "loss": 0.135, + "step": 12003 + }, + { + "epoch": 1.54, + "learning_rate": 1.342976239003505e-06, + "loss": 0.1411, + "step": 12004 + }, + { + "epoch": 1.54, + "learning_rate": 1.3422694917711276e-06, + "loss": 0.1368, + "step": 12005 + }, + { + "epoch": 1.54, + "learning_rate": 1.3415629017195763e-06, + "loss": 0.1192, + "step": 12006 + }, + { + "epoch": 1.54, + "learning_rate": 1.3408564688792153e-06, + "loss": 0.1308, + "step": 12007 + }, + { + "epoch": 1.54, + "learning_rate": 1.340150193280399e-06, + "loss": 0.1249, + "step": 12008 + }, + { + "epoch": 1.54, + "learning_rate": 1.339444074953482e-06, + "loss": 0.1313, + "step": 12009 + }, + { + "epoch": 1.54, + "learning_rate": 1.3387381139288064e-06, + "loss": 0.1302, + "step": 12010 + }, + { + "epoch": 1.54, + "learning_rate": 1.3380323102367055e-06, + "loss": 0.1377, + "step": 12011 + }, + { + "epoch": 1.54, + "learning_rate": 1.3373266639075134e-06, + "loss": 0.1376, + "step": 12012 + }, + { + "epoch": 1.54, + "learning_rate": 1.3366211749715519e-06, + "loss": 0.1434, + "step": 12013 + }, + { + "epoch": 1.54, + "learning_rate": 1.335915843459137e-06, + "loss": 0.1275, + "step": 12014 + }, + { + "epoch": 1.54, + "learning_rate": 1.335210669400579e-06, + "loss": 0.1348, + "step": 12015 + }, + { + "epoch": 1.54, + "learning_rate": 1.3345056528261784e-06, + "loss": 0.1417, + "step": 12016 + }, + { + "epoch": 1.54, + "learning_rate": 1.3338007937662367e-06, + "loss": 0.1457, + "step": 12017 + }, + { + "epoch": 1.54, + "learning_rate": 1.3330960922510373e-06, + "loss": 0.153, + "step": 12018 + }, + { + "epoch": 1.54, + "learning_rate": 1.3323915483108662e-06, + "loss": 0.1434, + "step": 12019 + }, + { + "epoch": 1.54, + "learning_rate": 1.3316871619759992e-06, + "loss": 0.1186, + "step": 12020 + }, + { + "epoch": 1.54, + "learning_rate": 1.3309829332767037e-06, + "loss": 0.1249, + "step": 12021 + }, + { + "epoch": 1.54, + "learning_rate": 1.330278862243244e-06, + "loss": 0.1314, + "step": 12022 + }, + { + "epoch": 1.54, + "learning_rate": 1.3295749489058741e-06, + "loss": 0.1394, + "step": 12023 + }, + { + "epoch": 1.54, + "learning_rate": 1.3288711932948427e-06, + "loss": 0.1476, + "step": 12024 + }, + { + "epoch": 1.54, + "learning_rate": 1.3281675954403923e-06, + "loss": 0.14, + "step": 12025 + }, + { + "epoch": 1.54, + "learning_rate": 1.3274641553727568e-06, + "loss": 0.141, + "step": 12026 + }, + { + "epoch": 1.54, + "learning_rate": 1.3267608731221671e-06, + "loss": 0.1411, + "step": 12027 + }, + { + "epoch": 1.54, + "learning_rate": 1.3260577487188431e-06, + "loss": 0.1443, + "step": 12028 + }, + { + "epoch": 1.54, + "learning_rate": 1.3253547821930002e-06, + "loss": 0.1362, + "step": 12029 + }, + { + "epoch": 1.54, + "learning_rate": 1.3246519735748465e-06, + "loss": 0.1409, + "step": 12030 + }, + { + "epoch": 1.54, + "learning_rate": 1.3239493228945821e-06, + "loss": 0.1491, + "step": 12031 + }, + { + "epoch": 1.54, + "learning_rate": 1.323246830182403e-06, + "loss": 0.1451, + "step": 12032 + }, + { + "epoch": 1.54, + "learning_rate": 1.3225444954684962e-06, + "loss": 0.118, + "step": 12033 + }, + { + "epoch": 1.54, + "learning_rate": 1.3218423187830409e-06, + "loss": 0.1355, + "step": 12034 + }, + { + "epoch": 1.54, + "learning_rate": 1.3211403001562155e-06, + "loss": 0.1524, + "step": 12035 + }, + { + "epoch": 1.54, + "learning_rate": 1.3204384396181819e-06, + "loss": 0.129, + "step": 12036 + }, + { + "epoch": 1.54, + "learning_rate": 1.3197367371991048e-06, + "loss": 0.1213, + "step": 12037 + }, + { + "epoch": 1.54, + "learning_rate": 1.3190351929291367e-06, + "loss": 0.1503, + "step": 12038 + }, + { + "epoch": 1.54, + "learning_rate": 1.3183338068384243e-06, + "loss": 0.1502, + "step": 12039 + }, + { + "epoch": 1.54, + "learning_rate": 1.3176325789571075e-06, + "loss": 0.1334, + "step": 12040 + }, + { + "epoch": 1.54, + "learning_rate": 1.316931509315319e-06, + "loss": 0.1294, + "step": 12041 + }, + { + "epoch": 1.54, + "learning_rate": 1.3162305979431883e-06, + "loss": 0.1394, + "step": 12042 + }, + { + "epoch": 1.54, + "learning_rate": 1.315529844870832e-06, + "loss": 0.1232, + "step": 12043 + }, + { + "epoch": 1.54, + "learning_rate": 1.3148292501283627e-06, + "loss": 0.1376, + "step": 12044 + }, + { + "epoch": 1.54, + "learning_rate": 1.314128813745889e-06, + "loss": 0.1277, + "step": 12045 + }, + { + "epoch": 1.54, + "learning_rate": 1.3134285357535093e-06, + "loss": 0.1241, + "step": 12046 + }, + { + "epoch": 1.54, + "learning_rate": 1.3127284161813153e-06, + "loss": 0.1215, + "step": 12047 + }, + { + "epoch": 1.54, + "learning_rate": 1.3120284550593936e-06, + "loss": 0.1268, + "step": 12048 + }, + { + "epoch": 1.54, + "learning_rate": 1.3113286524178232e-06, + "loss": 0.1238, + "step": 12049 + }, + { + "epoch": 1.54, + "learning_rate": 1.310629008286675e-06, + "loss": 0.1331, + "step": 12050 + }, + { + "epoch": 1.54, + "learning_rate": 1.3099295226960151e-06, + "loss": 0.1178, + "step": 12051 + }, + { + "epoch": 1.54, + "learning_rate": 1.3092301956759008e-06, + "loss": 0.1321, + "step": 12052 + }, + { + "epoch": 1.54, + "learning_rate": 1.3085310272563872e-06, + "loss": 0.1599, + "step": 12053 + }, + { + "epoch": 1.54, + "learning_rate": 1.3078320174675141e-06, + "loss": 0.1337, + "step": 12054 + }, + { + "epoch": 1.54, + "learning_rate": 1.3071331663393233e-06, + "loss": 0.123, + "step": 12055 + }, + { + "epoch": 1.54, + "learning_rate": 1.3064344739018452e-06, + "loss": 0.1501, + "step": 12056 + }, + { + "epoch": 1.54, + "learning_rate": 1.3057359401851034e-06, + "loss": 0.1536, + "step": 12057 + }, + { + "epoch": 1.54, + "learning_rate": 1.305037565219116e-06, + "loss": 0.1423, + "step": 12058 + }, + { + "epoch": 1.54, + "learning_rate": 1.3043393490338918e-06, + "loss": 0.138, + "step": 12059 + }, + { + "epoch": 1.54, + "learning_rate": 1.3036412916594398e-06, + "loss": 0.1342, + "step": 12060 + }, + { + "epoch": 1.54, + "learning_rate": 1.3029433931257524e-06, + "loss": 0.1263, + "step": 12061 + }, + { + "epoch": 1.54, + "learning_rate": 1.3022456534628191e-06, + "loss": 0.1546, + "step": 12062 + }, + { + "epoch": 1.54, + "learning_rate": 1.3015480727006274e-06, + "loss": 0.1289, + "step": 12063 + }, + { + "epoch": 1.54, + "learning_rate": 1.3008506508691516e-06, + "loss": 0.1427, + "step": 12064 + }, + { + "epoch": 1.54, + "learning_rate": 1.3001533879983618e-06, + "loss": 0.148, + "step": 12065 + }, + { + "epoch": 1.54, + "learning_rate": 1.2994562841182213e-06, + "loss": 0.127, + "step": 12066 + }, + { + "epoch": 1.54, + "learning_rate": 1.298759339258685e-06, + "loss": 0.1273, + "step": 12067 + }, + { + "epoch": 1.54, + "learning_rate": 1.2980625534497037e-06, + "loss": 0.1304, + "step": 12068 + }, + { + "epoch": 1.54, + "learning_rate": 1.2973659267212173e-06, + "loss": 0.1251, + "step": 12069 + }, + { + "epoch": 1.54, + "learning_rate": 1.2966694591031653e-06, + "loss": 0.1474, + "step": 12070 + }, + { + "epoch": 1.55, + "learning_rate": 1.2959731506254751e-06, + "loss": 0.1466, + "step": 12071 + }, + { + "epoch": 1.55, + "learning_rate": 1.2952770013180655e-06, + "loss": 0.129, + "step": 12072 + }, + { + "epoch": 1.55, + "learning_rate": 1.2945810112108554e-06, + "loss": 0.1497, + "step": 12073 + }, + { + "epoch": 1.55, + "learning_rate": 1.2938851803337516e-06, + "loss": 0.141, + "step": 12074 + }, + { + "epoch": 1.55, + "learning_rate": 1.2931895087166551e-06, + "loss": 0.1365, + "step": 12075 + }, + { + "epoch": 1.55, + "learning_rate": 1.2924939963894617e-06, + "loss": 0.1217, + "step": 12076 + }, + { + "epoch": 1.55, + "learning_rate": 1.2917986433820567e-06, + "loss": 0.1192, + "step": 12077 + }, + { + "epoch": 1.55, + "learning_rate": 1.2911034497243251e-06, + "loss": 0.1389, + "step": 12078 + }, + { + "epoch": 1.55, + "learning_rate": 1.290408415446136e-06, + "loss": 0.1529, + "step": 12079 + }, + { + "epoch": 1.55, + "learning_rate": 1.2897135405773602e-06, + "loss": 0.1356, + "step": 12080 + }, + { + "epoch": 1.55, + "learning_rate": 1.2890188251478569e-06, + "loss": 0.1272, + "step": 12081 + }, + { + "epoch": 1.55, + "learning_rate": 1.2883242691874792e-06, + "loss": 0.1422, + "step": 12082 + }, + { + "epoch": 1.55, + "learning_rate": 1.2876298727260744e-06, + "loss": 0.1469, + "step": 12083 + }, + { + "epoch": 1.55, + "learning_rate": 1.2869356357934815e-06, + "loss": 0.1315, + "step": 12084 + }, + { + "epoch": 1.55, + "learning_rate": 1.2862415584195338e-06, + "loss": 0.1396, + "step": 12085 + }, + { + "epoch": 1.55, + "learning_rate": 1.2855476406340578e-06, + "loss": 0.138, + "step": 12086 + }, + { + "epoch": 1.55, + "learning_rate": 1.28485388246687e-06, + "loss": 0.1168, + "step": 12087 + }, + { + "epoch": 1.55, + "learning_rate": 1.2841602839477868e-06, + "loss": 0.1422, + "step": 12088 + }, + { + "epoch": 1.55, + "learning_rate": 1.2834668451066118e-06, + "loss": 0.1228, + "step": 12089 + }, + { + "epoch": 1.55, + "learning_rate": 1.2827735659731438e-06, + "loss": 0.1298, + "step": 12090 + }, + { + "epoch": 1.55, + "learning_rate": 1.2820804465771742e-06, + "loss": 0.1303, + "step": 12091 + }, + { + "epoch": 1.55, + "learning_rate": 1.2813874869484866e-06, + "loss": 0.144, + "step": 12092 + }, + { + "epoch": 1.55, + "learning_rate": 1.2806946871168634e-06, + "loss": 0.1354, + "step": 12093 + }, + { + "epoch": 1.55, + "learning_rate": 1.2800020471120717e-06, + "loss": 0.1245, + "step": 12094 + }, + { + "epoch": 1.55, + "learning_rate": 1.279309566963875e-06, + "loss": 0.1415, + "step": 12095 + }, + { + "epoch": 1.55, + "learning_rate": 1.2786172467020357e-06, + "loss": 0.1343, + "step": 12096 + }, + { + "epoch": 1.55, + "learning_rate": 1.2779250863562987e-06, + "loss": 0.1325, + "step": 12097 + }, + { + "epoch": 1.55, + "learning_rate": 1.2772330859564115e-06, + "loss": 0.1339, + "step": 12098 + }, + { + "epoch": 1.55, + "learning_rate": 1.276541245532109e-06, + "loss": 0.1373, + "step": 12099 + }, + { + "epoch": 1.55, + "learning_rate": 1.2758495651131226e-06, + "loss": 0.1539, + "step": 12100 + }, + { + "epoch": 1.55, + "learning_rate": 1.275158044729174e-06, + "loss": 0.1267, + "step": 12101 + }, + { + "epoch": 1.55, + "learning_rate": 1.2744666844099801e-06, + "loss": 0.1406, + "step": 12102 + }, + { + "epoch": 1.55, + "learning_rate": 1.2737754841852501e-06, + "loss": 0.1575, + "step": 12103 + }, + { + "epoch": 1.55, + "learning_rate": 1.2730844440846862e-06, + "loss": 0.1419, + "step": 12104 + }, + { + "epoch": 1.55, + "learning_rate": 1.2723935641379826e-06, + "loss": 0.1318, + "step": 12105 + }, + { + "epoch": 1.55, + "learning_rate": 1.2717028443748303e-06, + "loss": 0.146, + "step": 12106 + }, + { + "epoch": 1.55, + "learning_rate": 1.2710122848249106e-06, + "loss": 0.1281, + "step": 12107 + }, + { + "epoch": 1.55, + "learning_rate": 1.2703218855178984e-06, + "loss": 0.1324, + "step": 12108 + }, + { + "epoch": 1.55, + "learning_rate": 1.2696316464834607e-06, + "loss": 0.1419, + "step": 12109 + }, + { + "epoch": 1.55, + "learning_rate": 1.2689415677512574e-06, + "loss": 0.1248, + "step": 12110 + }, + { + "epoch": 1.55, + "learning_rate": 1.2682516493509478e-06, + "loss": 0.1358, + "step": 12111 + }, + { + "epoch": 1.55, + "learning_rate": 1.267561891312174e-06, + "loss": 0.1405, + "step": 12112 + }, + { + "epoch": 1.55, + "learning_rate": 1.2668722936645773e-06, + "loss": 0.1319, + "step": 12113 + }, + { + "epoch": 1.55, + "learning_rate": 1.2661828564377948e-06, + "loss": 0.132, + "step": 12114 + }, + { + "epoch": 1.55, + "learning_rate": 1.2654935796614481e-06, + "loss": 0.1274, + "step": 12115 + }, + { + "epoch": 1.55, + "learning_rate": 1.2648044633651607e-06, + "loss": 0.1281, + "step": 12116 + }, + { + "epoch": 1.55, + "learning_rate": 1.2641155075785444e-06, + "loss": 0.137, + "step": 12117 + }, + { + "epoch": 1.55, + "learning_rate": 1.2634267123312049e-06, + "loss": 0.1363, + "step": 12118 + }, + { + "epoch": 1.55, + "learning_rate": 1.2627380776527415e-06, + "loss": 0.1359, + "step": 12119 + }, + { + "epoch": 1.55, + "learning_rate": 1.2620496035727448e-06, + "loss": 0.1318, + "step": 12120 + }, + { + "epoch": 1.55, + "learning_rate": 1.2613612901208022e-06, + "loss": 0.1331, + "step": 12121 + }, + { + "epoch": 1.55, + "learning_rate": 1.2606731373264936e-06, + "loss": 0.1474, + "step": 12122 + }, + { + "epoch": 1.55, + "learning_rate": 1.2599851452193851e-06, + "loss": 0.1352, + "step": 12123 + }, + { + "epoch": 1.55, + "learning_rate": 1.259297313829046e-06, + "loss": 0.135, + "step": 12124 + }, + { + "epoch": 1.55, + "learning_rate": 1.258609643185032e-06, + "loss": 0.1314, + "step": 12125 + }, + { + "epoch": 1.55, + "learning_rate": 1.2579221333168945e-06, + "loss": 0.1347, + "step": 12126 + }, + { + "epoch": 1.55, + "learning_rate": 1.2572347842541766e-06, + "loss": 0.1351, + "step": 12127 + }, + { + "epoch": 1.55, + "learning_rate": 1.2565475960264145e-06, + "loss": 0.1361, + "step": 12128 + }, + { + "epoch": 1.55, + "learning_rate": 1.255860568663142e-06, + "loss": 0.1387, + "step": 12129 + }, + { + "epoch": 1.55, + "learning_rate": 1.2551737021938765e-06, + "loss": 0.1229, + "step": 12130 + }, + { + "epoch": 1.55, + "learning_rate": 1.2544869966481389e-06, + "loss": 0.138, + "step": 12131 + }, + { + "epoch": 1.55, + "learning_rate": 1.253800452055438e-06, + "loss": 0.1314, + "step": 12132 + }, + { + "epoch": 1.55, + "learning_rate": 1.2531140684452724e-06, + "loss": 0.1409, + "step": 12133 + }, + { + "epoch": 1.55, + "learning_rate": 1.2524278458471411e-06, + "loss": 0.1345, + "step": 12134 + }, + { + "epoch": 1.55, + "learning_rate": 1.2517417842905316e-06, + "loss": 0.1319, + "step": 12135 + }, + { + "epoch": 1.55, + "learning_rate": 1.2510558838049258e-06, + "loss": 0.1318, + "step": 12136 + }, + { + "epoch": 1.55, + "learning_rate": 1.2503701444197974e-06, + "loss": 0.1357, + "step": 12137 + }, + { + "epoch": 1.55, + "learning_rate": 1.249684566164614e-06, + "loss": 0.1337, + "step": 12138 + }, + { + "epoch": 1.55, + "learning_rate": 1.248999149068838e-06, + "loss": 0.1485, + "step": 12139 + }, + { + "epoch": 1.55, + "learning_rate": 1.2483138931619227e-06, + "loss": 0.1263, + "step": 12140 + }, + { + "epoch": 1.55, + "learning_rate": 1.2476287984733154e-06, + "loss": 0.1434, + "step": 12141 + }, + { + "epoch": 1.55, + "learning_rate": 1.246943865032455e-06, + "loss": 0.144, + "step": 12142 + }, + { + "epoch": 1.55, + "learning_rate": 1.246259092868775e-06, + "loss": 0.1209, + "step": 12143 + }, + { + "epoch": 1.55, + "learning_rate": 1.2455744820117028e-06, + "loss": 0.1385, + "step": 12144 + }, + { + "epoch": 1.55, + "learning_rate": 1.2448900324906559e-06, + "loss": 0.1363, + "step": 12145 + }, + { + "epoch": 1.55, + "learning_rate": 1.2442057443350458e-06, + "loss": 0.141, + "step": 12146 + }, + { + "epoch": 1.55, + "learning_rate": 1.2435216175742826e-06, + "loss": 0.1406, + "step": 12147 + }, + { + "epoch": 1.55, + "learning_rate": 1.242837652237759e-06, + "loss": 0.1405, + "step": 12148 + }, + { + "epoch": 1.56, + "learning_rate": 1.2421538483548706e-06, + "loss": 0.1284, + "step": 12149 + }, + { + "epoch": 1.56, + "learning_rate": 1.2414702059550016e-06, + "loss": 0.1251, + "step": 12150 + }, + { + "epoch": 1.56, + "learning_rate": 1.2407867250675253e-06, + "loss": 0.1367, + "step": 12151 + }, + { + "epoch": 1.56, + "learning_rate": 1.2401034057218181e-06, + "loss": 0.1469, + "step": 12152 + }, + { + "epoch": 1.56, + "learning_rate": 1.2394202479472406e-06, + "loss": 0.1367, + "step": 12153 + }, + { + "epoch": 1.56, + "learning_rate": 1.2387372517731505e-06, + "loss": 0.142, + "step": 12154 + }, + { + "epoch": 1.56, + "learning_rate": 1.238054417228897e-06, + "loss": 0.1351, + "step": 12155 + }, + { + "epoch": 1.56, + "learning_rate": 1.2373717443438227e-06, + "loss": 0.1152, + "step": 12156 + }, + { + "epoch": 1.56, + "learning_rate": 1.2366892331472657e-06, + "loss": 0.1249, + "step": 12157 + }, + { + "epoch": 1.56, + "learning_rate": 1.2360068836685536e-06, + "loss": 0.1268, + "step": 12158 + }, + { + "epoch": 1.56, + "learning_rate": 1.2353246959370086e-06, + "loss": 0.119, + "step": 12159 + }, + { + "epoch": 1.56, + "learning_rate": 1.234642669981946e-06, + "loss": 0.1427, + "step": 12160 + }, + { + "epoch": 1.56, + "learning_rate": 1.2339608058326736e-06, + "loss": 0.1472, + "step": 12161 + }, + { + "epoch": 1.56, + "learning_rate": 1.2332791035184926e-06, + "loss": 0.1384, + "step": 12162 + }, + { + "epoch": 1.56, + "learning_rate": 1.2325975630686976e-06, + "loss": 0.1446, + "step": 12163 + }, + { + "epoch": 1.56, + "learning_rate": 1.2319161845125744e-06, + "loss": 0.1334, + "step": 12164 + }, + { + "epoch": 1.56, + "learning_rate": 1.2312349678794072e-06, + "loss": 0.1436, + "step": 12165 + }, + { + "epoch": 1.56, + "learning_rate": 1.2305539131984646e-06, + "loss": 0.1424, + "step": 12166 + }, + { + "epoch": 1.56, + "learning_rate": 1.2298730204990162e-06, + "loss": 0.1358, + "step": 12167 + }, + { + "epoch": 1.56, + "learning_rate": 1.229192289810321e-06, + "loss": 0.1343, + "step": 12168 + }, + { + "epoch": 1.56, + "learning_rate": 1.228511721161631e-06, + "loss": 0.1222, + "step": 12169 + }, + { + "epoch": 1.56, + "learning_rate": 1.2278313145821924e-06, + "loss": 0.1416, + "step": 12170 + }, + { + "epoch": 1.56, + "learning_rate": 1.2271510701012412e-06, + "loss": 0.1327, + "step": 12171 + }, + { + "epoch": 1.56, + "learning_rate": 1.2264709877480147e-06, + "loss": 0.1345, + "step": 12172 + }, + { + "epoch": 1.56, + "learning_rate": 1.2257910675517315e-06, + "loss": 0.1356, + "step": 12173 + }, + { + "epoch": 1.56, + "learning_rate": 1.2251113095416113e-06, + "loss": 0.1343, + "step": 12174 + }, + { + "epoch": 1.56, + "learning_rate": 1.2244317137468658e-06, + "loss": 0.1405, + "step": 12175 + }, + { + "epoch": 1.56, + "learning_rate": 1.223752280196699e-06, + "loss": 0.1383, + "step": 12176 + }, + { + "epoch": 1.56, + "learning_rate": 1.2230730089203063e-06, + "loss": 0.1436, + "step": 12177 + }, + { + "epoch": 1.56, + "learning_rate": 1.2223938999468788e-06, + "loss": 0.1312, + "step": 12178 + }, + { + "epoch": 1.56, + "learning_rate": 1.2217149533055976e-06, + "loss": 0.1198, + "step": 12179 + }, + { + "epoch": 1.56, + "learning_rate": 1.22103616902564e-06, + "loss": 0.1441, + "step": 12180 + }, + { + "epoch": 1.56, + "learning_rate": 1.2203575471361733e-06, + "loss": 0.1447, + "step": 12181 + }, + { + "epoch": 1.56, + "learning_rate": 1.2196790876663617e-06, + "loss": 0.1347, + "step": 12182 + }, + { + "epoch": 1.56, + "learning_rate": 1.2190007906453605e-06, + "loss": 0.1434, + "step": 12183 + }, + { + "epoch": 1.56, + "learning_rate": 1.2183226561023132e-06, + "loss": 0.1233, + "step": 12184 + }, + { + "epoch": 1.56, + "learning_rate": 1.2176446840663647e-06, + "loss": 0.1412, + "step": 12185 + }, + { + "epoch": 1.56, + "learning_rate": 1.216966874566648e-06, + "loss": 0.1317, + "step": 12186 + }, + { + "epoch": 1.56, + "learning_rate": 1.21628922763229e-06, + "loss": 0.1422, + "step": 12187 + }, + { + "epoch": 1.56, + "learning_rate": 1.2156117432924108e-06, + "loss": 0.1466, + "step": 12188 + }, + { + "epoch": 1.56, + "learning_rate": 1.2149344215761216e-06, + "loss": 0.12, + "step": 12189 + }, + { + "epoch": 1.56, + "learning_rate": 1.2142572625125332e-06, + "loss": 0.1195, + "step": 12190 + }, + { + "epoch": 1.56, + "learning_rate": 1.2135802661307388e-06, + "loss": 0.1389, + "step": 12191 + }, + { + "epoch": 1.56, + "learning_rate": 1.2129034324598343e-06, + "loss": 0.1337, + "step": 12192 + }, + { + "epoch": 1.56, + "learning_rate": 1.212226761528904e-06, + "loss": 0.1327, + "step": 12193 + }, + { + "epoch": 1.56, + "learning_rate": 1.2115502533670253e-06, + "loss": 0.143, + "step": 12194 + }, + { + "epoch": 1.56, + "learning_rate": 1.2108739080032695e-06, + "loss": 0.1214, + "step": 12195 + }, + { + "epoch": 1.56, + "learning_rate": 1.2101977254667007e-06, + "loss": 0.1393, + "step": 12196 + }, + { + "epoch": 1.56, + "learning_rate": 1.2095217057863762e-06, + "loss": 0.1449, + "step": 12197 + }, + { + "epoch": 1.56, + "learning_rate": 1.2088458489913458e-06, + "loss": 0.1268, + "step": 12198 + }, + { + "epoch": 1.56, + "learning_rate": 1.2081701551106506e-06, + "loss": 0.1199, + "step": 12199 + }, + { + "epoch": 1.56, + "learning_rate": 1.207494624173331e-06, + "loss": 0.1371, + "step": 12200 + }, + { + "epoch": 1.56, + "learning_rate": 1.2068192562084146e-06, + "loss": 0.1262, + "step": 12201 + }, + { + "epoch": 1.56, + "learning_rate": 1.2061440512449196e-06, + "loss": 0.1365, + "step": 12202 + }, + { + "epoch": 1.56, + "learning_rate": 1.205469009311866e-06, + "loss": 0.1263, + "step": 12203 + }, + { + "epoch": 1.56, + "learning_rate": 1.20479413043826e-06, + "loss": 0.1339, + "step": 12204 + }, + { + "epoch": 1.56, + "learning_rate": 1.2041194146531026e-06, + "loss": 0.1372, + "step": 12205 + }, + { + "epoch": 1.56, + "learning_rate": 1.2034448619853873e-06, + "loss": 0.1422, + "step": 12206 + }, + { + "epoch": 1.56, + "learning_rate": 1.202770472464101e-06, + "loss": 0.133, + "step": 12207 + }, + { + "epoch": 1.56, + "learning_rate": 1.2020962461182268e-06, + "loss": 0.1399, + "step": 12208 + }, + { + "epoch": 1.56, + "learning_rate": 1.201422182976732e-06, + "loss": 0.1443, + "step": 12209 + }, + { + "epoch": 1.56, + "learning_rate": 1.200748283068588e-06, + "loss": 0.117, + "step": 12210 + }, + { + "epoch": 1.56, + "learning_rate": 1.2000745464227515e-06, + "loss": 0.1434, + "step": 12211 + }, + { + "epoch": 1.56, + "learning_rate": 1.1994009730681744e-06, + "loss": 0.1191, + "step": 12212 + }, + { + "epoch": 1.56, + "learning_rate": 1.198727563033802e-06, + "loss": 0.1423, + "step": 12213 + }, + { + "epoch": 1.56, + "learning_rate": 1.1980543163485726e-06, + "loss": 0.1378, + "step": 12214 + }, + { + "epoch": 1.56, + "learning_rate": 1.1973812330414159e-06, + "loss": 0.1326, + "step": 12215 + }, + { + "epoch": 1.56, + "learning_rate": 1.1967083131412566e-06, + "loss": 0.1373, + "step": 12216 + }, + { + "epoch": 1.56, + "learning_rate": 1.1960355566770104e-06, + "loss": 0.1424, + "step": 12217 + }, + { + "epoch": 1.56, + "learning_rate": 1.1953629636775893e-06, + "loss": 0.1275, + "step": 12218 + }, + { + "epoch": 1.56, + "learning_rate": 1.1946905341718951e-06, + "loss": 0.13, + "step": 12219 + }, + { + "epoch": 1.56, + "learning_rate": 1.1940182681888235e-06, + "loss": 0.1446, + "step": 12220 + }, + { + "epoch": 1.56, + "learning_rate": 1.1933461657572637e-06, + "loss": 0.12, + "step": 12221 + }, + { + "epoch": 1.56, + "learning_rate": 1.1926742269060965e-06, + "loss": 0.1291, + "step": 12222 + }, + { + "epoch": 1.56, + "learning_rate": 1.1920024516641976e-06, + "loss": 0.1198, + "step": 12223 + }, + { + "epoch": 1.56, + "learning_rate": 1.1913308400604339e-06, + "loss": 0.1168, + "step": 12224 + }, + { + "epoch": 1.56, + "learning_rate": 1.1906593921236649e-06, + "loss": 0.1365, + "step": 12225 + }, + { + "epoch": 1.56, + "learning_rate": 1.1899881078827485e-06, + "loss": 0.1267, + "step": 12226 + }, + { + "epoch": 1.57, + "learning_rate": 1.189316987366526e-06, + "loss": 0.1257, + "step": 12227 + }, + { + "epoch": 1.57, + "learning_rate": 1.1886460306038405e-06, + "loss": 0.1291, + "step": 12228 + }, + { + "epoch": 1.57, + "learning_rate": 1.1879752376235231e-06, + "loss": 0.1331, + "step": 12229 + }, + { + "epoch": 1.57, + "learning_rate": 1.1873046084544004e-06, + "loss": 0.137, + "step": 12230 + }, + { + "epoch": 1.57, + "learning_rate": 1.1866341431252892e-06, + "loss": 0.1346, + "step": 12231 + }, + { + "epoch": 1.57, + "learning_rate": 1.185963841665001e-06, + "loss": 0.1394, + "step": 12232 + }, + { + "epoch": 1.57, + "learning_rate": 1.1852937041023433e-06, + "loss": 0.1327, + "step": 12233 + }, + { + "epoch": 1.57, + "learning_rate": 1.1846237304661095e-06, + "loss": 0.1354, + "step": 12234 + }, + { + "epoch": 1.57, + "learning_rate": 1.1839539207850898e-06, + "loss": 0.1483, + "step": 12235 + }, + { + "epoch": 1.57, + "learning_rate": 1.1832842750880702e-06, + "loss": 0.131, + "step": 12236 + }, + { + "epoch": 1.57, + "learning_rate": 1.1826147934038262e-06, + "loss": 0.157, + "step": 12237 + }, + { + "epoch": 1.57, + "learning_rate": 1.181945475761126e-06, + "loss": 0.1478, + "step": 12238 + }, + { + "epoch": 1.57, + "learning_rate": 1.181276322188732e-06, + "loss": 0.1533, + "step": 12239 + }, + { + "epoch": 1.57, + "learning_rate": 1.1806073327153988e-06, + "loss": 0.1183, + "step": 12240 + }, + { + "epoch": 1.57, + "learning_rate": 1.1799385073698749e-06, + "loss": 0.134, + "step": 12241 + }, + { + "epoch": 1.57, + "learning_rate": 1.1792698461809e-06, + "loss": 0.1452, + "step": 12242 + }, + { + "epoch": 1.57, + "learning_rate": 1.1786013491772103e-06, + "loss": 0.1321, + "step": 12243 + }, + { + "epoch": 1.57, + "learning_rate": 1.1779330163875325e-06, + "loss": 0.1349, + "step": 12244 + }, + { + "epoch": 1.57, + "learning_rate": 1.1772648478405824e-06, + "loss": 0.1393, + "step": 12245 + }, + { + "epoch": 1.57, + "learning_rate": 1.176596843565077e-06, + "loss": 0.1335, + "step": 12246 + }, + { + "epoch": 1.57, + "learning_rate": 1.1759290035897208e-06, + "loss": 0.1332, + "step": 12247 + }, + { + "epoch": 1.57, + "learning_rate": 1.1752613279432112e-06, + "loss": 0.1338, + "step": 12248 + }, + { + "epoch": 1.57, + "learning_rate": 1.1745938166542414e-06, + "loss": 0.14, + "step": 12249 + }, + { + "epoch": 1.57, + "learning_rate": 1.173926469751493e-06, + "loss": 0.1165, + "step": 12250 + }, + { + "epoch": 1.57, + "learning_rate": 1.1732592872636478e-06, + "loss": 0.1427, + "step": 12251 + }, + { + "epoch": 1.57, + "learning_rate": 1.172592269219373e-06, + "loss": 0.1241, + "step": 12252 + }, + { + "epoch": 1.57, + "learning_rate": 1.1719254156473302e-06, + "loss": 0.1214, + "step": 12253 + }, + { + "epoch": 1.57, + "learning_rate": 1.1712587265761799e-06, + "loss": 0.1313, + "step": 12254 + }, + { + "epoch": 1.57, + "learning_rate": 1.1705922020345688e-06, + "loss": 0.1253, + "step": 12255 + }, + { + "epoch": 1.57, + "learning_rate": 1.16992584205114e-06, + "loss": 0.1394, + "step": 12256 + }, + { + "epoch": 1.57, + "learning_rate": 1.1692596466545275e-06, + "loss": 0.133, + "step": 12257 + }, + { + "epoch": 1.57, + "learning_rate": 1.168593615873358e-06, + "loss": 0.1457, + "step": 12258 + }, + { + "epoch": 1.57, + "learning_rate": 1.1679277497362563e-06, + "loss": 0.1373, + "step": 12259 + }, + { + "epoch": 1.57, + "learning_rate": 1.167262048271831e-06, + "loss": 0.1351, + "step": 12260 + }, + { + "epoch": 1.57, + "learning_rate": 1.166596511508693e-06, + "loss": 0.1239, + "step": 12261 + }, + { + "epoch": 1.57, + "learning_rate": 1.1659311394754418e-06, + "loss": 0.1259, + "step": 12262 + }, + { + "epoch": 1.57, + "learning_rate": 1.1652659322006659e-06, + "loss": 0.1227, + "step": 12263 + }, + { + "epoch": 1.57, + "learning_rate": 1.1646008897129546e-06, + "loss": 0.1388, + "step": 12264 + }, + { + "epoch": 1.57, + "learning_rate": 1.1639360120408843e-06, + "loss": 0.1329, + "step": 12265 + }, + { + "epoch": 1.57, + "learning_rate": 1.1632712992130278e-06, + "loss": 0.1247, + "step": 12266 + }, + { + "epoch": 1.57, + "learning_rate": 1.1626067512579481e-06, + "loss": 0.1154, + "step": 12267 + }, + { + "epoch": 1.57, + "learning_rate": 1.1619423682042008e-06, + "loss": 0.1276, + "step": 12268 + }, + { + "epoch": 1.57, + "learning_rate": 1.161278150080341e-06, + "loss": 0.1301, + "step": 12269 + }, + { + "epoch": 1.57, + "learning_rate": 1.160614096914906e-06, + "loss": 0.1485, + "step": 12270 + }, + { + "epoch": 1.57, + "learning_rate": 1.1599502087364345e-06, + "loss": 0.1296, + "step": 12271 + }, + { + "epoch": 1.57, + "learning_rate": 1.1592864855734553e-06, + "loss": 0.1355, + "step": 12272 + }, + { + "epoch": 1.57, + "learning_rate": 1.1586229274544898e-06, + "loss": 0.1363, + "step": 12273 + }, + { + "epoch": 1.57, + "learning_rate": 1.157959534408052e-06, + "loss": 0.1328, + "step": 12274 + }, + { + "epoch": 1.57, + "learning_rate": 1.1572963064626497e-06, + "loss": 0.1198, + "step": 12275 + }, + { + "epoch": 1.57, + "learning_rate": 1.1566332436467815e-06, + "loss": 0.1246, + "step": 12276 + }, + { + "epoch": 1.57, + "learning_rate": 1.155970345988946e-06, + "loss": 0.1389, + "step": 12277 + }, + { + "epoch": 1.57, + "learning_rate": 1.1553076135176222e-06, + "loss": 0.1287, + "step": 12278 + }, + { + "epoch": 1.57, + "learning_rate": 1.1546450462612951e-06, + "loss": 0.1398, + "step": 12279 + }, + { + "epoch": 1.57, + "learning_rate": 1.1539826442484337e-06, + "loss": 0.1403, + "step": 12280 + }, + { + "epoch": 1.57, + "learning_rate": 1.1533204075075039e-06, + "loss": 0.1259, + "step": 12281 + }, + { + "epoch": 1.57, + "learning_rate": 1.1526583360669635e-06, + "loss": 0.1442, + "step": 12282 + }, + { + "epoch": 1.57, + "learning_rate": 1.1519964299552611e-06, + "loss": 0.1301, + "step": 12283 + }, + { + "epoch": 1.57, + "learning_rate": 1.151334689200845e-06, + "loss": 0.1467, + "step": 12284 + }, + { + "epoch": 1.57, + "learning_rate": 1.1506731138321474e-06, + "loss": 0.1369, + "step": 12285 + }, + { + "epoch": 1.57, + "learning_rate": 1.1500117038775977e-06, + "loss": 0.1287, + "step": 12286 + }, + { + "epoch": 1.57, + "learning_rate": 1.149350459365622e-06, + "loss": 0.1415, + "step": 12287 + }, + { + "epoch": 1.57, + "learning_rate": 1.1486893803246302e-06, + "loss": 0.1313, + "step": 12288 + }, + { + "epoch": 1.57, + "learning_rate": 1.1480284667830343e-06, + "loss": 0.1099, + "step": 12289 + }, + { + "epoch": 1.57, + "learning_rate": 1.1473677187692345e-06, + "loss": 0.139, + "step": 12290 + }, + { + "epoch": 1.57, + "learning_rate": 1.1467071363116234e-06, + "loss": 0.1462, + "step": 12291 + }, + { + "epoch": 1.57, + "learning_rate": 1.1460467194385889e-06, + "loss": 0.1331, + "step": 12292 + }, + { + "epoch": 1.57, + "learning_rate": 1.1453864681785087e-06, + "loss": 0.1335, + "step": 12293 + }, + { + "epoch": 1.57, + "learning_rate": 1.1447263825597577e-06, + "loss": 0.1326, + "step": 12294 + }, + { + "epoch": 1.57, + "learning_rate": 1.1440664626107017e-06, + "loss": 0.1291, + "step": 12295 + }, + { + "epoch": 1.57, + "learning_rate": 1.143406708359695e-06, + "loss": 0.1398, + "step": 12296 + }, + { + "epoch": 1.57, + "learning_rate": 1.142747119835092e-06, + "loss": 0.1273, + "step": 12297 + }, + { + "epoch": 1.57, + "learning_rate": 1.1420876970652361e-06, + "loss": 0.1309, + "step": 12298 + }, + { + "epoch": 1.57, + "learning_rate": 1.1414284400784643e-06, + "loss": 0.1221, + "step": 12299 + }, + { + "epoch": 1.57, + "learning_rate": 1.1407693489031052e-06, + "loss": 0.1329, + "step": 12300 + }, + { + "epoch": 1.57, + "learning_rate": 1.1401104235674808e-06, + "loss": 0.1393, + "step": 12301 + }, + { + "epoch": 1.57, + "learning_rate": 1.1394516640999114e-06, + "loss": 0.1262, + "step": 12302 + }, + { + "epoch": 1.57, + "learning_rate": 1.1387930705286998e-06, + "loss": 0.1278, + "step": 12303 + }, + { + "epoch": 1.57, + "learning_rate": 1.1381346428821482e-06, + "loss": 0.1372, + "step": 12304 + }, + { + "epoch": 1.58, + "learning_rate": 1.1374763811885547e-06, + "loss": 0.1483, + "step": 12305 + }, + { + "epoch": 1.58, + "learning_rate": 1.1368182854762005e-06, + "loss": 0.132, + "step": 12306 + }, + { + "epoch": 1.58, + "learning_rate": 1.1361603557733698e-06, + "loss": 0.1384, + "step": 12307 + }, + { + "epoch": 1.58, + "learning_rate": 1.135502592108334e-06, + "loss": 0.1275, + "step": 12308 + }, + { + "epoch": 1.58, + "learning_rate": 1.134844994509358e-06, + "loss": 0.1355, + "step": 12309 + }, + { + "epoch": 1.58, + "learning_rate": 1.1341875630047012e-06, + "loss": 0.1422, + "step": 12310 + }, + { + "epoch": 1.58, + "learning_rate": 1.1335302976226132e-06, + "loss": 0.1226, + "step": 12311 + }, + { + "epoch": 1.58, + "learning_rate": 1.1328731983913404e-06, + "loss": 0.1265, + "step": 12312 + }, + { + "epoch": 1.58, + "learning_rate": 1.13221626533912e-06, + "loss": 0.1431, + "step": 12313 + }, + { + "epoch": 1.58, + "learning_rate": 1.1315594984941786e-06, + "loss": 0.137, + "step": 12314 + }, + { + "epoch": 1.58, + "learning_rate": 1.1309028978847419e-06, + "loss": 0.1398, + "step": 12315 + }, + { + "epoch": 1.58, + "learning_rate": 1.1302464635390247e-06, + "loss": 0.1382, + "step": 12316 + }, + { + "epoch": 1.58, + "learning_rate": 1.1295901954852356e-06, + "loss": 0.1173, + "step": 12317 + }, + { + "epoch": 1.58, + "learning_rate": 1.1289340937515753e-06, + "loss": 0.1346, + "step": 12318 + }, + { + "epoch": 1.58, + "learning_rate": 1.1282781583662372e-06, + "loss": 0.1426, + "step": 12319 + }, + { + "epoch": 1.58, + "learning_rate": 1.1276223893574123e-06, + "loss": 0.1188, + "step": 12320 + }, + { + "epoch": 1.58, + "learning_rate": 1.1269667867532746e-06, + "loss": 0.1146, + "step": 12321 + }, + { + "epoch": 1.58, + "learning_rate": 1.1263113505820012e-06, + "loss": 0.1478, + "step": 12322 + }, + { + "epoch": 1.58, + "learning_rate": 1.1256560808717576e-06, + "loss": 0.122, + "step": 12323 + }, + { + "epoch": 1.58, + "learning_rate": 1.1250009776506982e-06, + "loss": 0.1498, + "step": 12324 + }, + { + "epoch": 1.58, + "learning_rate": 1.124346040946978e-06, + "loss": 0.136, + "step": 12325 + }, + { + "epoch": 1.58, + "learning_rate": 1.1236912707887404e-06, + "loss": 0.1445, + "step": 12326 + }, + { + "epoch": 1.58, + "learning_rate": 1.1230366672041216e-06, + "loss": 0.1354, + "step": 12327 + }, + { + "epoch": 1.58, + "learning_rate": 1.1223822302212517e-06, + "loss": 0.1451, + "step": 12328 + }, + { + "epoch": 1.58, + "learning_rate": 1.1217279598682518e-06, + "loss": 0.1393, + "step": 12329 + }, + { + "epoch": 1.58, + "learning_rate": 1.1210738561732405e-06, + "loss": 0.1371, + "step": 12330 + }, + { + "epoch": 1.58, + "learning_rate": 1.120419919164324e-06, + "loss": 0.145, + "step": 12331 + }, + { + "epoch": 1.58, + "learning_rate": 1.1197661488696043e-06, + "loss": 0.1258, + "step": 12332 + }, + { + "epoch": 1.58, + "learning_rate": 1.1191125453171748e-06, + "loss": 0.1416, + "step": 12333 + }, + { + "epoch": 1.58, + "learning_rate": 1.118459108535122e-06, + "loss": 0.1431, + "step": 12334 + }, + { + "epoch": 1.58, + "learning_rate": 1.1178058385515268e-06, + "loss": 0.1236, + "step": 12335 + }, + { + "epoch": 1.58, + "learning_rate": 1.1171527353944601e-06, + "loss": 0.1304, + "step": 12336 + }, + { + "epoch": 1.58, + "learning_rate": 1.1164997990919868e-06, + "loss": 0.1215, + "step": 12337 + }, + { + "epoch": 1.58, + "learning_rate": 1.1158470296721691e-06, + "loss": 0.1359, + "step": 12338 + }, + { + "epoch": 1.58, + "learning_rate": 1.1151944271630517e-06, + "loss": 0.1369, + "step": 12339 + }, + { + "epoch": 1.58, + "learning_rate": 1.1145419915926836e-06, + "loss": 0.1444, + "step": 12340 + }, + { + "epoch": 1.58, + "learning_rate": 1.1138897229890995e-06, + "loss": 0.1555, + "step": 12341 + }, + { + "epoch": 1.58, + "learning_rate": 1.1132376213803286e-06, + "loss": 0.1406, + "step": 12342 + }, + { + "epoch": 1.58, + "learning_rate": 1.1125856867943936e-06, + "loss": 0.1428, + "step": 12343 + }, + { + "epoch": 1.58, + "learning_rate": 1.1119339192593077e-06, + "loss": 0.1274, + "step": 12344 + }, + { + "epoch": 1.58, + "learning_rate": 1.111282318803083e-06, + "loss": 0.1394, + "step": 12345 + }, + { + "epoch": 1.58, + "learning_rate": 1.1106308854537167e-06, + "loss": 0.1436, + "step": 12346 + }, + { + "epoch": 1.58, + "learning_rate": 1.1099796192392021e-06, + "loss": 0.121, + "step": 12347 + }, + { + "epoch": 1.58, + "learning_rate": 1.109328520187528e-06, + "loss": 0.1169, + "step": 12348 + }, + { + "epoch": 1.58, + "learning_rate": 1.1086775883266725e-06, + "loss": 0.1318, + "step": 12349 + }, + { + "epoch": 1.58, + "learning_rate": 1.1080268236846076e-06, + "loss": 0.1215, + "step": 12350 + }, + { + "epoch": 1.58, + "learning_rate": 1.1073762262892979e-06, + "loss": 0.1257, + "step": 12351 + }, + { + "epoch": 1.58, + "learning_rate": 1.1067257961687005e-06, + "loss": 0.1269, + "step": 12352 + }, + { + "epoch": 1.58, + "learning_rate": 1.1060755333507673e-06, + "loss": 0.139, + "step": 12353 + }, + { + "epoch": 1.58, + "learning_rate": 1.1054254378634399e-06, + "loss": 0.1578, + "step": 12354 + }, + { + "epoch": 1.58, + "learning_rate": 1.1047755097346541e-06, + "loss": 0.1416, + "step": 12355 + }, + { + "epoch": 1.58, + "learning_rate": 1.1041257489923429e-06, + "loss": 0.1381, + "step": 12356 + }, + { + "epoch": 1.58, + "learning_rate": 1.1034761556644214e-06, + "loss": 0.1349, + "step": 12357 + }, + { + "epoch": 1.58, + "learning_rate": 1.1028267297788092e-06, + "loss": 0.1361, + "step": 12358 + }, + { + "epoch": 1.58, + "learning_rate": 1.102177471363412e-06, + "loss": 0.1163, + "step": 12359 + }, + { + "epoch": 1.58, + "learning_rate": 1.1015283804461297e-06, + "loss": 0.1213, + "step": 12360 + }, + { + "epoch": 1.58, + "learning_rate": 1.1008794570548554e-06, + "loss": 0.126, + "step": 12361 + }, + { + "epoch": 1.58, + "learning_rate": 1.100230701217473e-06, + "loss": 0.1325, + "step": 12362 + }, + { + "epoch": 1.58, + "learning_rate": 1.0995821129618656e-06, + "loss": 0.1339, + "step": 12363 + }, + { + "epoch": 1.58, + "learning_rate": 1.0989336923158999e-06, + "loss": 0.1289, + "step": 12364 + }, + { + "epoch": 1.58, + "learning_rate": 1.0982854393074399e-06, + "loss": 0.1246, + "step": 12365 + }, + { + "epoch": 1.58, + "learning_rate": 1.0976373539643465e-06, + "loss": 0.1339, + "step": 12366 + }, + { + "epoch": 1.58, + "learning_rate": 1.0969894363144661e-06, + "loss": 0.1321, + "step": 12367 + }, + { + "epoch": 1.58, + "learning_rate": 1.0963416863856425e-06, + "loss": 0.1368, + "step": 12368 + }, + { + "epoch": 1.58, + "learning_rate": 1.0956941042057106e-06, + "loss": 0.1379, + "step": 12369 + }, + { + "epoch": 1.58, + "learning_rate": 1.095046689802498e-06, + "loss": 0.1444, + "step": 12370 + }, + { + "epoch": 1.58, + "learning_rate": 1.0943994432038262e-06, + "loss": 0.1438, + "step": 12371 + }, + { + "epoch": 1.58, + "learning_rate": 1.0937523644375076e-06, + "loss": 0.1193, + "step": 12372 + }, + { + "epoch": 1.58, + "learning_rate": 1.0931054535313507e-06, + "loss": 0.1599, + "step": 12373 + }, + { + "epoch": 1.58, + "learning_rate": 1.0924587105131546e-06, + "loss": 0.1436, + "step": 12374 + }, + { + "epoch": 1.58, + "learning_rate": 1.0918121354107076e-06, + "loss": 0.1472, + "step": 12375 + }, + { + "epoch": 1.58, + "learning_rate": 1.091165728251799e-06, + "loss": 0.1333, + "step": 12376 + }, + { + "epoch": 1.58, + "learning_rate": 1.090519489064204e-06, + "loss": 0.1267, + "step": 12377 + }, + { + "epoch": 1.58, + "learning_rate": 1.0898734178756937e-06, + "loss": 0.1355, + "step": 12378 + }, + { + "epoch": 1.58, + "learning_rate": 1.0892275147140307e-06, + "loss": 0.1486, + "step": 12379 + }, + { + "epoch": 1.58, + "learning_rate": 1.0885817796069697e-06, + "loss": 0.14, + "step": 12380 + }, + { + "epoch": 1.58, + "learning_rate": 1.087936212582264e-06, + "loss": 0.1117, + "step": 12381 + }, + { + "epoch": 1.58, + "learning_rate": 1.0872908136676491e-06, + "loss": 0.1282, + "step": 12382 + }, + { + "epoch": 1.59, + "learning_rate": 1.0866455828908634e-06, + "loss": 0.1254, + "step": 12383 + }, + { + "epoch": 1.59, + "learning_rate": 1.086000520279632e-06, + "loss": 0.1338, + "step": 12384 + }, + { + "epoch": 1.59, + "learning_rate": 1.0853556258616755e-06, + "loss": 0.1466, + "step": 12385 + }, + { + "epoch": 1.59, + "learning_rate": 1.0847108996647066e-06, + "loss": 0.1508, + "step": 12386 + }, + { + "epoch": 1.59, + "learning_rate": 1.0840663417164293e-06, + "loss": 0.1425, + "step": 12387 + }, + { + "epoch": 1.59, + "learning_rate": 1.0834219520445432e-06, + "loss": 0.1254, + "step": 12388 + }, + { + "epoch": 1.59, + "learning_rate": 1.0827777306767384e-06, + "loss": 0.1377, + "step": 12389 + }, + { + "epoch": 1.59, + "learning_rate": 1.082133677640697e-06, + "loss": 0.1293, + "step": 12390 + }, + { + "epoch": 1.59, + "learning_rate": 1.0814897929640984e-06, + "loss": 0.1367, + "step": 12391 + }, + { + "epoch": 1.59, + "learning_rate": 1.0808460766746104e-06, + "loss": 0.1443, + "step": 12392 + }, + { + "epoch": 1.59, + "learning_rate": 1.0802025287998953e-06, + "loss": 0.1419, + "step": 12393 + }, + { + "epoch": 1.59, + "learning_rate": 1.0795591493676072e-06, + "loss": 0.1408, + "step": 12394 + }, + { + "epoch": 1.59, + "learning_rate": 1.078915938405392e-06, + "loss": 0.1287, + "step": 12395 + }, + { + "epoch": 1.59, + "learning_rate": 1.078272895940895e-06, + "loss": 0.124, + "step": 12396 + }, + { + "epoch": 1.59, + "learning_rate": 1.0776300220017437e-06, + "loss": 0.1471, + "step": 12397 + }, + { + "epoch": 1.59, + "learning_rate": 1.0769873166155653e-06, + "loss": 0.1352, + "step": 12398 + }, + { + "epoch": 1.59, + "learning_rate": 1.0763447798099813e-06, + "loss": 0.1451, + "step": 12399 + }, + { + "epoch": 1.59, + "learning_rate": 1.075702411612598e-06, + "loss": 0.1515, + "step": 12400 + }, + { + "epoch": 1.59, + "learning_rate": 1.0750602120510233e-06, + "loss": 0.1306, + "step": 12401 + }, + { + "epoch": 1.59, + "learning_rate": 1.0744181811528526e-06, + "loss": 0.143, + "step": 12402 + }, + { + "epoch": 1.59, + "learning_rate": 1.073776318945675e-06, + "loss": 0.1409, + "step": 12403 + }, + { + "epoch": 1.59, + "learning_rate": 1.0731346254570735e-06, + "loss": 0.1387, + "step": 12404 + }, + { + "epoch": 1.59, + "learning_rate": 1.0724931007146227e-06, + "loss": 0.1345, + "step": 12405 + }, + { + "epoch": 1.59, + "learning_rate": 1.0718517447458904e-06, + "loss": 0.1303, + "step": 12406 + }, + { + "epoch": 1.59, + "learning_rate": 1.071210557578437e-06, + "loss": 0.1296, + "step": 12407 + }, + { + "epoch": 1.59, + "learning_rate": 1.0705695392398146e-06, + "loss": 0.1407, + "step": 12408 + }, + { + "epoch": 1.59, + "learning_rate": 1.0699286897575718e-06, + "loss": 0.1446, + "step": 12409 + }, + { + "epoch": 1.59, + "learning_rate": 1.0692880091592457e-06, + "loss": 0.128, + "step": 12410 + }, + { + "epoch": 1.59, + "learning_rate": 1.068647497472368e-06, + "loss": 0.1505, + "step": 12411 + }, + { + "epoch": 1.59, + "learning_rate": 1.0680071547244636e-06, + "loss": 0.1433, + "step": 12412 + }, + { + "epoch": 1.59, + "learning_rate": 1.0673669809430465e-06, + "loss": 0.1324, + "step": 12413 + }, + { + "epoch": 1.59, + "learning_rate": 1.066726976155632e-06, + "loss": 0.1415, + "step": 12414 + }, + { + "epoch": 1.59, + "learning_rate": 1.0660871403897177e-06, + "loss": 0.1487, + "step": 12415 + }, + { + "epoch": 1.59, + "learning_rate": 1.0654474736727988e-06, + "loss": 0.1344, + "step": 12416 + }, + { + "epoch": 1.59, + "learning_rate": 1.0648079760323675e-06, + "loss": 0.1394, + "step": 12417 + }, + { + "epoch": 1.59, + "learning_rate": 1.064168647495899e-06, + "loss": 0.1329, + "step": 12418 + }, + { + "epoch": 1.59, + "learning_rate": 1.0635294880908702e-06, + "loss": 0.128, + "step": 12419 + }, + { + "epoch": 1.59, + "learning_rate": 1.0628904978447463e-06, + "loss": 0.1422, + "step": 12420 + }, + { + "epoch": 1.59, + "learning_rate": 1.0622516767849867e-06, + "loss": 0.1209, + "step": 12421 + }, + { + "epoch": 1.59, + "learning_rate": 1.0616130249390423e-06, + "loss": 0.1479, + "step": 12422 + }, + { + "epoch": 1.59, + "learning_rate": 1.0609745423343553e-06, + "loss": 0.1299, + "step": 12423 + }, + { + "epoch": 1.59, + "learning_rate": 1.0603362289983687e-06, + "loss": 0.1377, + "step": 12424 + }, + { + "epoch": 1.59, + "learning_rate": 1.0596980849585065e-06, + "loss": 0.1297, + "step": 12425 + }, + { + "epoch": 1.59, + "learning_rate": 1.0590601102421916e-06, + "loss": 0.1273, + "step": 12426 + }, + { + "epoch": 1.59, + "learning_rate": 1.0584223048768427e-06, + "loss": 0.1494, + "step": 12427 + }, + { + "epoch": 1.59, + "learning_rate": 1.0577846688898652e-06, + "loss": 0.1448, + "step": 12428 + }, + { + "epoch": 1.59, + "learning_rate": 1.0571472023086604e-06, + "loss": 0.1389, + "step": 12429 + }, + { + "epoch": 1.59, + "learning_rate": 1.0565099051606214e-06, + "loss": 0.1409, + "step": 12430 + }, + { + "epoch": 1.59, + "learning_rate": 1.055872777473133e-06, + "loss": 0.1335, + "step": 12431 + }, + { + "epoch": 1.59, + "learning_rate": 1.0552358192735784e-06, + "loss": 0.1224, + "step": 12432 + }, + { + "epoch": 1.59, + "learning_rate": 1.0545990305893233e-06, + "loss": 0.1366, + "step": 12433 + }, + { + "epoch": 1.59, + "learning_rate": 1.053962411447736e-06, + "loss": 0.1285, + "step": 12434 + }, + { + "epoch": 1.59, + "learning_rate": 1.0533259618761738e-06, + "loss": 0.1374, + "step": 12435 + }, + { + "epoch": 1.59, + "learning_rate": 1.0526896819019817e-06, + "loss": 0.1319, + "step": 12436 + }, + { + "epoch": 1.59, + "learning_rate": 1.0520535715525066e-06, + "loss": 0.139, + "step": 12437 + }, + { + "epoch": 1.59, + "learning_rate": 1.0514176308550817e-06, + "loss": 0.131, + "step": 12438 + }, + { + "epoch": 1.59, + "learning_rate": 1.0507818598370355e-06, + "loss": 0.1494, + "step": 12439 + }, + { + "epoch": 1.59, + "learning_rate": 1.0501462585256883e-06, + "loss": 0.141, + "step": 12440 + }, + { + "epoch": 1.59, + "learning_rate": 1.0495108269483518e-06, + "loss": 0.1263, + "step": 12441 + }, + { + "epoch": 1.59, + "learning_rate": 1.0488755651323358e-06, + "loss": 0.1384, + "step": 12442 + }, + { + "epoch": 1.59, + "learning_rate": 1.048240473104934e-06, + "loss": 0.1391, + "step": 12443 + }, + { + "epoch": 1.59, + "learning_rate": 1.0476055508934408e-06, + "loss": 0.1332, + "step": 12444 + }, + { + "epoch": 1.59, + "learning_rate": 1.04697079852514e-06, + "loss": 0.1358, + "step": 12445 + }, + { + "epoch": 1.59, + "learning_rate": 1.0463362160273076e-06, + "loss": 0.143, + "step": 12446 + }, + { + "epoch": 1.59, + "learning_rate": 1.0457018034272136e-06, + "loss": 0.141, + "step": 12447 + }, + { + "epoch": 1.59, + "learning_rate": 1.04506756075212e-06, + "loss": 0.1359, + "step": 12448 + }, + { + "epoch": 1.59, + "learning_rate": 1.0444334880292794e-06, + "loss": 0.1398, + "step": 12449 + }, + { + "epoch": 1.59, + "learning_rate": 1.0437995852859445e-06, + "loss": 0.1158, + "step": 12450 + }, + { + "epoch": 1.59, + "learning_rate": 1.0431658525493498e-06, + "loss": 0.1436, + "step": 12451 + }, + { + "epoch": 1.59, + "learning_rate": 1.0425322898467315e-06, + "loss": 0.1258, + "step": 12452 + }, + { + "epoch": 1.59, + "learning_rate": 1.0418988972053162e-06, + "loss": 0.1405, + "step": 12453 + }, + { + "epoch": 1.59, + "learning_rate": 1.0412656746523182e-06, + "loss": 0.1131, + "step": 12454 + }, + { + "epoch": 1.59, + "learning_rate": 1.0406326222149516e-06, + "loss": 0.1366, + "step": 12455 + }, + { + "epoch": 1.59, + "learning_rate": 1.0399997399204186e-06, + "loss": 0.1419, + "step": 12456 + }, + { + "epoch": 1.59, + "learning_rate": 1.0393670277959174e-06, + "loss": 0.1151, + "step": 12457 + }, + { + "epoch": 1.59, + "learning_rate": 1.038734485868635e-06, + "loss": 0.1405, + "step": 12458 + }, + { + "epoch": 1.59, + "learning_rate": 1.0381021141657526e-06, + "loss": 0.1432, + "step": 12459 + }, + { + "epoch": 1.59, + "learning_rate": 1.037469912714449e-06, + "loss": 0.1338, + "step": 12460 + }, + { + "epoch": 1.6, + "learning_rate": 1.0368378815418856e-06, + "loss": 0.1256, + "step": 12461 + }, + { + "epoch": 1.6, + "learning_rate": 1.036206020675226e-06, + "loss": 0.1374, + "step": 12462 + }, + { + "epoch": 1.6, + "learning_rate": 1.0355743301416215e-06, + "loss": 0.142, + "step": 12463 + }, + { + "epoch": 1.6, + "learning_rate": 1.0349428099682173e-06, + "loss": 0.129, + "step": 12464 + }, + { + "epoch": 1.6, + "learning_rate": 1.0343114601821513e-06, + "loss": 0.1337, + "step": 12465 + }, + { + "epoch": 1.6, + "learning_rate": 1.033680280810554e-06, + "loss": 0.1383, + "step": 12466 + }, + { + "epoch": 1.6, + "learning_rate": 1.0330492718805469e-06, + "loss": 0.1446, + "step": 12467 + }, + { + "epoch": 1.6, + "learning_rate": 1.0324184334192505e-06, + "loss": 0.1331, + "step": 12468 + }, + { + "epoch": 1.6, + "learning_rate": 1.0317877654537672e-06, + "loss": 0.1368, + "step": 12469 + }, + { + "epoch": 1.6, + "learning_rate": 1.031157268011203e-06, + "loss": 0.1366, + "step": 12470 + }, + { + "epoch": 1.6, + "learning_rate": 1.0305269411186502e-06, + "loss": 0.1364, + "step": 12471 + }, + { + "epoch": 1.6, + "learning_rate": 1.0298967848031948e-06, + "loss": 0.13, + "step": 12472 + }, + { + "epoch": 1.6, + "learning_rate": 1.0292667990919164e-06, + "loss": 0.1385, + "step": 12473 + }, + { + "epoch": 1.6, + "learning_rate": 1.0286369840118859e-06, + "loss": 0.137, + "step": 12474 + }, + { + "epoch": 1.6, + "learning_rate": 1.0280073395901719e-06, + "loss": 0.1401, + "step": 12475 + }, + { + "epoch": 1.6, + "learning_rate": 1.0273778658538263e-06, + "loss": 0.1394, + "step": 12476 + }, + { + "epoch": 1.6, + "learning_rate": 1.0267485628299007e-06, + "loss": 0.1252, + "step": 12477 + }, + { + "epoch": 1.6, + "learning_rate": 1.026119430545441e-06, + "loss": 0.1296, + "step": 12478 + }, + { + "epoch": 1.6, + "learning_rate": 1.025490469027477e-06, + "loss": 0.1431, + "step": 12479 + }, + { + "epoch": 1.6, + "learning_rate": 1.0248616783030403e-06, + "loss": 0.1235, + "step": 12480 + }, + { + "epoch": 1.6, + "learning_rate": 1.0242330583991507e-06, + "loss": 0.1363, + "step": 12481 + }, + { + "epoch": 1.6, + "learning_rate": 1.0236046093428204e-06, + "loss": 0.1285, + "step": 12482 + }, + { + "epoch": 1.6, + "learning_rate": 1.0229763311610563e-06, + "loss": 0.1343, + "step": 12483 + }, + { + "epoch": 1.6, + "learning_rate": 1.0223482238808557e-06, + "loss": 0.1198, + "step": 12484 + }, + { + "epoch": 1.6, + "learning_rate": 1.0217202875292115e-06, + "loss": 0.1333, + "step": 12485 + }, + { + "epoch": 1.6, + "learning_rate": 1.021092522133108e-06, + "loss": 0.1403, + "step": 12486 + }, + { + "epoch": 1.6, + "learning_rate": 1.0204649277195178e-06, + "loss": 0.1295, + "step": 12487 + }, + { + "epoch": 1.6, + "learning_rate": 1.0198375043154142e-06, + "loss": 0.1175, + "step": 12488 + }, + { + "epoch": 1.6, + "learning_rate": 1.0192102519477565e-06, + "loss": 0.1221, + "step": 12489 + }, + { + "epoch": 1.6, + "learning_rate": 1.0185831706435007e-06, + "loss": 0.1308, + "step": 12490 + }, + { + "epoch": 1.6, + "learning_rate": 1.0179562604295929e-06, + "loss": 0.1299, + "step": 12491 + }, + { + "epoch": 1.6, + "learning_rate": 1.0173295213329714e-06, + "loss": 0.1349, + "step": 12492 + }, + { + "epoch": 1.6, + "learning_rate": 1.0167029533805733e-06, + "loss": 0.1365, + "step": 12493 + }, + { + "epoch": 1.6, + "learning_rate": 1.016076556599318e-06, + "loss": 0.1404, + "step": 12494 + }, + { + "epoch": 1.6, + "learning_rate": 1.0154503310161269e-06, + "loss": 0.1351, + "step": 12495 + }, + { + "epoch": 1.6, + "learning_rate": 1.014824276657909e-06, + "loss": 0.1423, + "step": 12496 + }, + { + "epoch": 1.6, + "learning_rate": 1.0141983935515675e-06, + "loss": 0.1479, + "step": 12497 + }, + { + "epoch": 1.6, + "learning_rate": 1.0135726817239983e-06, + "loss": 0.1459, + "step": 12498 + }, + { + "epoch": 1.6, + "learning_rate": 1.0129471412020886e-06, + "loss": 0.1393, + "step": 12499 + }, + { + "epoch": 1.6, + "learning_rate": 1.0123217720127203e-06, + "loss": 0.1465, + "step": 12500 + }, + { + "epoch": 1.6, + "learning_rate": 1.011696574182766e-06, + "loss": 0.1243, + "step": 12501 + }, + { + "epoch": 1.6, + "learning_rate": 1.0110715477390915e-06, + "loss": 0.1274, + "step": 12502 + }, + { + "epoch": 1.6, + "learning_rate": 1.0104466927085577e-06, + "loss": 0.1326, + "step": 12503 + }, + { + "epoch": 1.6, + "learning_rate": 1.0098220091180145e-06, + "loss": 0.1317, + "step": 12504 + }, + { + "epoch": 1.6, + "learning_rate": 1.0091974969943064e-06, + "loss": 0.1306, + "step": 12505 + }, + { + "epoch": 1.6, + "learning_rate": 1.0085731563642697e-06, + "loss": 0.1264, + "step": 12506 + }, + { + "epoch": 1.6, + "learning_rate": 1.0079489872547338e-06, + "loss": 0.1347, + "step": 12507 + }, + { + "epoch": 1.6, + "learning_rate": 1.0073249896925208e-06, + "loss": 0.1387, + "step": 12508 + }, + { + "epoch": 1.6, + "learning_rate": 1.006701163704445e-06, + "loss": 0.1429, + "step": 12509 + }, + { + "epoch": 1.6, + "learning_rate": 1.0060775093173126e-06, + "loss": 0.134, + "step": 12510 + }, + { + "epoch": 1.6, + "learning_rate": 1.005454026557927e-06, + "loss": 0.1238, + "step": 12511 + }, + { + "epoch": 1.6, + "learning_rate": 1.0048307154530763e-06, + "loss": 0.1353, + "step": 12512 + }, + { + "epoch": 1.6, + "learning_rate": 1.0042075760295477e-06, + "loss": 0.1368, + "step": 12513 + }, + { + "epoch": 1.6, + "learning_rate": 1.0035846083141193e-06, + "loss": 0.1298, + "step": 12514 + }, + { + "epoch": 1.6, + "learning_rate": 1.002961812333561e-06, + "loss": 0.1303, + "step": 12515 + }, + { + "epoch": 1.6, + "learning_rate": 1.0023391881146349e-06, + "loss": 0.1543, + "step": 12516 + }, + { + "epoch": 1.6, + "learning_rate": 1.0017167356840974e-06, + "loss": 0.1323, + "step": 12517 + }, + { + "epoch": 1.6, + "learning_rate": 1.0010944550686968e-06, + "loss": 0.1235, + "step": 12518 + }, + { + "epoch": 1.6, + "learning_rate": 1.0004723462951732e-06, + "loss": 0.1226, + "step": 12519 + }, + { + "epoch": 1.6, + "learning_rate": 9.99850409390259e-07, + "loss": 0.1219, + "step": 12520 + }, + { + "epoch": 1.6, + "learning_rate": 9.992286443806825e-07, + "loss": 0.1345, + "step": 12521 + }, + { + "epoch": 1.6, + "learning_rate": 9.986070512931616e-07, + "loss": 0.1226, + "step": 12522 + }, + { + "epoch": 1.6, + "learning_rate": 9.97985630154407e-07, + "loss": 0.1412, + "step": 12523 + }, + { + "epoch": 1.6, + "learning_rate": 9.973643809911238e-07, + "loss": 0.1344, + "step": 12524 + }, + { + "epoch": 1.6, + "learning_rate": 9.967433038300067e-07, + "loss": 0.1397, + "step": 12525 + }, + { + "epoch": 1.6, + "learning_rate": 9.96122398697746e-07, + "loss": 0.1341, + "step": 12526 + }, + { + "epoch": 1.6, + "learning_rate": 9.955016656210226e-07, + "loss": 0.1242, + "step": 12527 + }, + { + "epoch": 1.6, + "learning_rate": 9.948811046265095e-07, + "loss": 0.1528, + "step": 12528 + }, + { + "epoch": 1.6, + "learning_rate": 9.942607157408784e-07, + "loss": 0.1476, + "step": 12529 + }, + { + "epoch": 1.6, + "learning_rate": 9.936404989907828e-07, + "loss": 0.1319, + "step": 12530 + }, + { + "epoch": 1.6, + "learning_rate": 9.930204544028787e-07, + "loss": 0.1498, + "step": 12531 + }, + { + "epoch": 1.6, + "learning_rate": 9.924005820038102e-07, + "loss": 0.1271, + "step": 12532 + }, + { + "epoch": 1.6, + "learning_rate": 9.917808818202135e-07, + "loss": 0.1201, + "step": 12533 + }, + { + "epoch": 1.6, + "learning_rate": 9.911613538787196e-07, + "loss": 0.1336, + "step": 12534 + }, + { + "epoch": 1.6, + "learning_rate": 9.905419982059488e-07, + "loss": 0.1468, + "step": 12535 + }, + { + "epoch": 1.6, + "learning_rate": 9.899228148285206e-07, + "loss": 0.1386, + "step": 12536 + }, + { + "epoch": 1.6, + "learning_rate": 9.89303803773039e-07, + "loss": 0.1394, + "step": 12537 + }, + { + "epoch": 1.6, + "learning_rate": 9.886849650661035e-07, + "loss": 0.1323, + "step": 12538 + }, + { + "epoch": 1.6, + "learning_rate": 9.880662987343103e-07, + "loss": 0.1388, + "step": 12539 + }, + { + "epoch": 1.61, + "learning_rate": 9.87447804804243e-07, + "loss": 0.1451, + "step": 12540 + }, + { + "epoch": 1.61, + "learning_rate": 9.868294833024805e-07, + "loss": 0.1135, + "step": 12541 + }, + { + "epoch": 1.61, + "learning_rate": 9.862113342555924e-07, + "loss": 0.1222, + "step": 12542 + }, + { + "epoch": 1.61, + "learning_rate": 9.855933576901428e-07, + "loss": 0.1375, + "step": 12543 + }, + { + "epoch": 1.61, + "learning_rate": 9.849755536326866e-07, + "loss": 0.1307, + "step": 12544 + }, + { + "epoch": 1.61, + "learning_rate": 9.843579221097722e-07, + "loss": 0.1407, + "step": 12545 + }, + { + "epoch": 1.61, + "learning_rate": 9.837404631479419e-07, + "loss": 0.1322, + "step": 12546 + }, + { + "epoch": 1.61, + "learning_rate": 9.831231767737305e-07, + "loss": 0.1397, + "step": 12547 + }, + { + "epoch": 1.61, + "learning_rate": 9.82506063013659e-07, + "loss": 0.1253, + "step": 12548 + }, + { + "epoch": 1.61, + "learning_rate": 9.818891218942511e-07, + "loss": 0.1262, + "step": 12549 + }, + { + "epoch": 1.61, + "learning_rate": 9.812723534420165e-07, + "loss": 0.1289, + "step": 12550 + }, + { + "epoch": 1.61, + "learning_rate": 9.806557576834591e-07, + "loss": 0.1276, + "step": 12551 + }, + { + "epoch": 1.61, + "learning_rate": 9.800393346450754e-07, + "loss": 0.1323, + "step": 12552 + }, + { + "epoch": 1.61, + "learning_rate": 9.794230843533525e-07, + "loss": 0.1178, + "step": 12553 + }, + { + "epoch": 1.61, + "learning_rate": 9.78807006834777e-07, + "loss": 0.1404, + "step": 12554 + }, + { + "epoch": 1.61, + "learning_rate": 9.781911021158181e-07, + "loss": 0.1311, + "step": 12555 + }, + { + "epoch": 1.61, + "learning_rate": 9.775753702229452e-07, + "loss": 0.1438, + "step": 12556 + }, + { + "epoch": 1.61, + "learning_rate": 9.769598111826166e-07, + "loss": 0.1416, + "step": 12557 + }, + { + "epoch": 1.61, + "learning_rate": 9.763444250212855e-07, + "loss": 0.1358, + "step": 12558 + }, + { + "epoch": 1.61, + "learning_rate": 9.757292117653955e-07, + "loss": 0.1425, + "step": 12559 + }, + { + "epoch": 1.61, + "learning_rate": 9.751141714413836e-07, + "loss": 0.1279, + "step": 12560 + }, + { + "epoch": 1.61, + "learning_rate": 9.7449930407568e-07, + "loss": 0.1261, + "step": 12561 + }, + { + "epoch": 1.61, + "learning_rate": 9.738846096947064e-07, + "loss": 0.1247, + "step": 12562 + }, + { + "epoch": 1.61, + "learning_rate": 9.732700883248763e-07, + "loss": 0.1306, + "step": 12563 + }, + { + "epoch": 1.61, + "learning_rate": 9.726557399925995e-07, + "loss": 0.1292, + "step": 12564 + }, + { + "epoch": 1.61, + "learning_rate": 9.72041564724277e-07, + "loss": 0.1507, + "step": 12565 + }, + { + "epoch": 1.61, + "learning_rate": 9.71427562546296e-07, + "loss": 0.135, + "step": 12566 + }, + { + "epoch": 1.61, + "learning_rate": 9.708137334850465e-07, + "loss": 0.1315, + "step": 12567 + }, + { + "epoch": 1.61, + "learning_rate": 9.702000775669041e-07, + "loss": 0.1456, + "step": 12568 + }, + { + "epoch": 1.61, + "learning_rate": 9.695865948182392e-07, + "loss": 0.1338, + "step": 12569 + }, + { + "epoch": 1.61, + "learning_rate": 9.689732852654143e-07, + "loss": 0.1479, + "step": 12570 + }, + { + "epoch": 1.61, + "learning_rate": 9.683601489347843e-07, + "loss": 0.1215, + "step": 12571 + }, + { + "epoch": 1.61, + "learning_rate": 9.677471858526998e-07, + "loss": 0.1477, + "step": 12572 + }, + { + "epoch": 1.61, + "learning_rate": 9.671343960454965e-07, + "loss": 0.1501, + "step": 12573 + }, + { + "epoch": 1.61, + "learning_rate": 9.66521779539511e-07, + "loss": 0.14, + "step": 12574 + }, + { + "epoch": 1.61, + "learning_rate": 9.659093363610678e-07, + "loss": 0.1298, + "step": 12575 + }, + { + "epoch": 1.61, + "learning_rate": 9.652970665364847e-07, + "loss": 0.1348, + "step": 12576 + }, + { + "epoch": 1.61, + "learning_rate": 9.646849700920729e-07, + "loss": 0.1421, + "step": 12577 + }, + { + "epoch": 1.61, + "learning_rate": 9.640730470541343e-07, + "loss": 0.1444, + "step": 12578 + }, + { + "epoch": 1.61, + "learning_rate": 9.63461297448966e-07, + "loss": 0.1318, + "step": 12579 + }, + { + "epoch": 1.61, + "learning_rate": 9.628497213028553e-07, + "loss": 0.1333, + "step": 12580 + }, + { + "epoch": 1.61, + "learning_rate": 9.622383186420818e-07, + "loss": 0.1347, + "step": 12581 + }, + { + "epoch": 1.61, + "learning_rate": 9.616270894929219e-07, + "loss": 0.136, + "step": 12582 + }, + { + "epoch": 1.61, + "learning_rate": 9.610160338816404e-07, + "loss": 0.1224, + "step": 12583 + }, + { + "epoch": 1.61, + "learning_rate": 9.604051518344948e-07, + "loss": 0.1482, + "step": 12584 + }, + { + "epoch": 1.61, + "learning_rate": 9.597944433777362e-07, + "loss": 0.1499, + "step": 12585 + }, + { + "epoch": 1.61, + "learning_rate": 9.59183908537607e-07, + "loss": 0.1435, + "step": 12586 + }, + { + "epoch": 1.61, + "learning_rate": 9.585735473403479e-07, + "loss": 0.1434, + "step": 12587 + }, + { + "epoch": 1.61, + "learning_rate": 9.579633598121824e-07, + "loss": 0.1311, + "step": 12588 + }, + { + "epoch": 1.61, + "learning_rate": 9.57353345979332e-07, + "loss": 0.123, + "step": 12589 + }, + { + "epoch": 1.61, + "learning_rate": 9.567435058680146e-07, + "loss": 0.1279, + "step": 12590 + }, + { + "epoch": 1.61, + "learning_rate": 9.56133839504431e-07, + "loss": 0.1309, + "step": 12591 + }, + { + "epoch": 1.61, + "learning_rate": 9.55524346914784e-07, + "loss": 0.1386, + "step": 12592 + }, + { + "epoch": 1.61, + "learning_rate": 9.549150281252633e-07, + "loss": 0.1359, + "step": 12593 + }, + { + "epoch": 1.61, + "learning_rate": 9.543058831620528e-07, + "loss": 0.1401, + "step": 12594 + }, + { + "epoch": 1.61, + "learning_rate": 9.536969120513284e-07, + "loss": 0.1355, + "step": 12595 + }, + { + "epoch": 1.61, + "learning_rate": 9.530881148192578e-07, + "loss": 0.1287, + "step": 12596 + }, + { + "epoch": 1.61, + "learning_rate": 9.524794914920072e-07, + "loss": 0.1309, + "step": 12597 + }, + { + "epoch": 1.61, + "learning_rate": 9.51871042095725e-07, + "loss": 0.1464, + "step": 12598 + }, + { + "epoch": 1.61, + "learning_rate": 9.512627666565588e-07, + "loss": 0.1325, + "step": 12599 + }, + { + "epoch": 1.61, + "learning_rate": 9.506546652006504e-07, + "loss": 0.1342, + "step": 12600 + }, + { + "epoch": 1.61, + "learning_rate": 9.500467377541289e-07, + "loss": 0.1458, + "step": 12601 + }, + { + "epoch": 1.61, + "learning_rate": 9.49438984343119e-07, + "loss": 0.136, + "step": 12602 + }, + { + "epoch": 1.61, + "learning_rate": 9.48831404993737e-07, + "loss": 0.1378, + "step": 12603 + }, + { + "epoch": 1.61, + "learning_rate": 9.482239997320903e-07, + "loss": 0.1273, + "step": 12604 + }, + { + "epoch": 1.61, + "learning_rate": 9.476167685842852e-07, + "loss": 0.1336, + "step": 12605 + }, + { + "epoch": 1.61, + "learning_rate": 9.470097115764099e-07, + "loss": 0.1569, + "step": 12606 + }, + { + "epoch": 1.61, + "learning_rate": 9.464028287345551e-07, + "loss": 0.1257, + "step": 12607 + }, + { + "epoch": 1.61, + "learning_rate": 9.457961200847998e-07, + "loss": 0.1376, + "step": 12608 + }, + { + "epoch": 1.61, + "learning_rate": 9.451895856532117e-07, + "loss": 0.133, + "step": 12609 + }, + { + "epoch": 1.61, + "learning_rate": 9.445832254658594e-07, + "loss": 0.1405, + "step": 12610 + }, + { + "epoch": 1.61, + "learning_rate": 9.439770395487974e-07, + "loss": 0.1469, + "step": 12611 + }, + { + "epoch": 1.61, + "learning_rate": 9.43371027928075e-07, + "loss": 0.1483, + "step": 12612 + }, + { + "epoch": 1.61, + "learning_rate": 9.427651906297347e-07, + "loss": 0.121, + "step": 12613 + }, + { + "epoch": 1.61, + "learning_rate": 9.421595276798084e-07, + "loss": 0.1288, + "step": 12614 + }, + { + "epoch": 1.61, + "learning_rate": 9.415540391043276e-07, + "loss": 0.1301, + "step": 12615 + }, + { + "epoch": 1.61, + "learning_rate": 9.40948724929307e-07, + "loss": 0.1374, + "step": 12616 + }, + { + "epoch": 1.61, + "learning_rate": 9.403435851807579e-07, + "loss": 0.137, + "step": 12617 + }, + { + "epoch": 1.62, + "learning_rate": 9.397386198846881e-07, + "loss": 0.1314, + "step": 12618 + }, + { + "epoch": 1.62, + "learning_rate": 9.39133829067092e-07, + "loss": 0.1399, + "step": 12619 + }, + { + "epoch": 1.62, + "learning_rate": 9.385292127539597e-07, + "loss": 0.1264, + "step": 12620 + }, + { + "epoch": 1.62, + "learning_rate": 9.379247709712725e-07, + "loss": 0.1406, + "step": 12621 + }, + { + "epoch": 1.62, + "learning_rate": 9.373205037450028e-07, + "loss": 0.1258, + "step": 12622 + }, + { + "epoch": 1.62, + "learning_rate": 9.367164111011223e-07, + "loss": 0.1261, + "step": 12623 + }, + { + "epoch": 1.62, + "learning_rate": 9.361124930655841e-07, + "loss": 0.1262, + "step": 12624 + }, + { + "epoch": 1.62, + "learning_rate": 9.355087496643444e-07, + "loss": 0.1249, + "step": 12625 + }, + { + "epoch": 1.62, + "learning_rate": 9.349051809233472e-07, + "loss": 0.1302, + "step": 12626 + }, + { + "epoch": 1.62, + "learning_rate": 9.34301786868525e-07, + "loss": 0.1253, + "step": 12627 + }, + { + "epoch": 1.62, + "learning_rate": 9.336985675258109e-07, + "loss": 0.1224, + "step": 12628 + }, + { + "epoch": 1.62, + "learning_rate": 9.330955229211259e-07, + "loss": 0.1264, + "step": 12629 + }, + { + "epoch": 1.62, + "learning_rate": 9.324926530803835e-07, + "loss": 0.1281, + "step": 12630 + }, + { + "epoch": 1.62, + "learning_rate": 9.31889958029491e-07, + "loss": 0.15, + "step": 12631 + }, + { + "epoch": 1.62, + "learning_rate": 9.312874377943454e-07, + "loss": 0.1344, + "step": 12632 + }, + { + "epoch": 1.62, + "learning_rate": 9.306850924008415e-07, + "loss": 0.1308, + "step": 12633 + }, + { + "epoch": 1.62, + "learning_rate": 9.300829218748625e-07, + "loss": 0.1134, + "step": 12634 + }, + { + "epoch": 1.62, + "learning_rate": 9.294809262422838e-07, + "loss": 0.1345, + "step": 12635 + }, + { + "epoch": 1.62, + "learning_rate": 9.288791055289759e-07, + "loss": 0.1408, + "step": 12636 + }, + { + "epoch": 1.62, + "learning_rate": 9.282774597607991e-07, + "loss": 0.1333, + "step": 12637 + }, + { + "epoch": 1.62, + "learning_rate": 9.276759889636084e-07, + "loss": 0.1275, + "step": 12638 + }, + { + "epoch": 1.62, + "learning_rate": 9.270746931632501e-07, + "loss": 0.1165, + "step": 12639 + }, + { + "epoch": 1.62, + "learning_rate": 9.264735723855617e-07, + "loss": 0.1337, + "step": 12640 + }, + { + "epoch": 1.62, + "learning_rate": 9.258726266563789e-07, + "loss": 0.1372, + "step": 12641 + }, + { + "epoch": 1.62, + "learning_rate": 9.2527185600152e-07, + "loss": 0.145, + "step": 12642 + }, + { + "epoch": 1.62, + "learning_rate": 9.246712604468061e-07, + "loss": 0.135, + "step": 12643 + }, + { + "epoch": 1.62, + "learning_rate": 9.240708400180437e-07, + "loss": 0.1334, + "step": 12644 + }, + { + "epoch": 1.62, + "learning_rate": 9.234705947410355e-07, + "loss": 0.1246, + "step": 12645 + }, + { + "epoch": 1.62, + "learning_rate": 9.228705246415742e-07, + "loss": 0.1477, + "step": 12646 + }, + { + "epoch": 1.62, + "learning_rate": 9.222706297454459e-07, + "loss": 0.1357, + "step": 12647 + }, + { + "epoch": 1.62, + "learning_rate": 9.216709100784326e-07, + "loss": 0.1334, + "step": 12648 + }, + { + "epoch": 1.62, + "learning_rate": 9.210713656663023e-07, + "loss": 0.1569, + "step": 12649 + }, + { + "epoch": 1.62, + "learning_rate": 9.20471996534818e-07, + "loss": 0.1453, + "step": 12650 + }, + { + "epoch": 1.62, + "learning_rate": 9.198728027097386e-07, + "loss": 0.1385, + "step": 12651 + }, + { + "epoch": 1.62, + "learning_rate": 9.192737842168126e-07, + "loss": 0.1401, + "step": 12652 + }, + { + "epoch": 1.62, + "learning_rate": 9.186749410817797e-07, + "loss": 0.1411, + "step": 12653 + }, + { + "epoch": 1.62, + "learning_rate": 9.180762733303745e-07, + "loss": 0.1408, + "step": 12654 + }, + { + "epoch": 1.62, + "learning_rate": 9.174777809883229e-07, + "loss": 0.1491, + "step": 12655 + }, + { + "epoch": 1.62, + "learning_rate": 9.168794640813428e-07, + "loss": 0.128, + "step": 12656 + }, + { + "epoch": 1.62, + "learning_rate": 9.162813226351447e-07, + "loss": 0.1452, + "step": 12657 + }, + { + "epoch": 1.62, + "learning_rate": 9.156833566754347e-07, + "loss": 0.1318, + "step": 12658 + }, + { + "epoch": 1.62, + "learning_rate": 9.150855662279079e-07, + "loss": 0.1348, + "step": 12659 + }, + { + "epoch": 1.62, + "learning_rate": 9.144879513182498e-07, + "loss": 0.1454, + "step": 12660 + }, + { + "epoch": 1.62, + "learning_rate": 9.138905119721442e-07, + "loss": 0.1285, + "step": 12661 + }, + { + "epoch": 1.62, + "learning_rate": 9.13293248215264e-07, + "loss": 0.1246, + "step": 12662 + }, + { + "epoch": 1.62, + "learning_rate": 9.126961600732742e-07, + "loss": 0.1324, + "step": 12663 + }, + { + "epoch": 1.62, + "learning_rate": 9.120992475718333e-07, + "loss": 0.1294, + "step": 12664 + }, + { + "epoch": 1.62, + "learning_rate": 9.115025107365904e-07, + "loss": 0.1198, + "step": 12665 + }, + { + "epoch": 1.62, + "learning_rate": 9.109059495931932e-07, + "loss": 0.1314, + "step": 12666 + }, + { + "epoch": 1.62, + "learning_rate": 9.103095641672732e-07, + "loss": 0.1252, + "step": 12667 + }, + { + "epoch": 1.62, + "learning_rate": 9.097133544844577e-07, + "loss": 0.1334, + "step": 12668 + }, + { + "epoch": 1.62, + "learning_rate": 9.091173205703708e-07, + "loss": 0.1348, + "step": 12669 + }, + { + "epoch": 1.62, + "learning_rate": 9.085214624506228e-07, + "loss": 0.1308, + "step": 12670 + }, + { + "epoch": 1.62, + "learning_rate": 9.079257801508201e-07, + "loss": 0.1376, + "step": 12671 + }, + { + "epoch": 1.62, + "learning_rate": 9.0733027369656e-07, + "loss": 0.1574, + "step": 12672 + }, + { + "epoch": 1.62, + "learning_rate": 9.067349431134331e-07, + "loss": 0.1389, + "step": 12673 + }, + { + "epoch": 1.62, + "learning_rate": 9.061397884270217e-07, + "loss": 0.1445, + "step": 12674 + }, + { + "epoch": 1.62, + "learning_rate": 9.055448096628999e-07, + "loss": 0.1293, + "step": 12675 + }, + { + "epoch": 1.62, + "learning_rate": 9.049500068466377e-07, + "loss": 0.149, + "step": 12676 + }, + { + "epoch": 1.62, + "learning_rate": 9.043553800037952e-07, + "loss": 0.1307, + "step": 12677 + }, + { + "epoch": 1.62, + "learning_rate": 9.037609291599214e-07, + "loss": 0.1317, + "step": 12678 + }, + { + "epoch": 1.62, + "learning_rate": 9.031666543405637e-07, + "loss": 0.1397, + "step": 12679 + }, + { + "epoch": 1.62, + "learning_rate": 9.025725555712595e-07, + "loss": 0.1481, + "step": 12680 + }, + { + "epoch": 1.62, + "learning_rate": 9.019786328775382e-07, + "loss": 0.1214, + "step": 12681 + }, + { + "epoch": 1.62, + "learning_rate": 9.013848862849217e-07, + "loss": 0.1374, + "step": 12682 + }, + { + "epoch": 1.62, + "learning_rate": 9.007913158189236e-07, + "loss": 0.1419, + "step": 12683 + }, + { + "epoch": 1.62, + "learning_rate": 9.001979215050544e-07, + "loss": 0.129, + "step": 12684 + }, + { + "epoch": 1.62, + "learning_rate": 8.996047033688083e-07, + "loss": 0.1256, + "step": 12685 + }, + { + "epoch": 1.62, + "learning_rate": 8.990116614356819e-07, + "loss": 0.1232, + "step": 12686 + }, + { + "epoch": 1.62, + "learning_rate": 8.984187957311579e-07, + "loss": 0.132, + "step": 12687 + }, + { + "epoch": 1.62, + "learning_rate": 8.978261062807131e-07, + "loss": 0.1384, + "step": 12688 + }, + { + "epoch": 1.62, + "learning_rate": 8.972335931098159e-07, + "loss": 0.1291, + "step": 12689 + }, + { + "epoch": 1.62, + "learning_rate": 8.966412562439291e-07, + "loss": 0.1254, + "step": 12690 + }, + { + "epoch": 1.62, + "learning_rate": 8.960490957085061e-07, + "loss": 0.1415, + "step": 12691 + }, + { + "epoch": 1.62, + "learning_rate": 8.954571115289934e-07, + "loss": 0.1395, + "step": 12692 + }, + { + "epoch": 1.62, + "learning_rate": 8.948653037308286e-07, + "loss": 0.1493, + "step": 12693 + }, + { + "epoch": 1.62, + "learning_rate": 8.942736723394458e-07, + "loss": 0.1432, + "step": 12694 + }, + { + "epoch": 1.62, + "learning_rate": 8.936822173802667e-07, + "loss": 0.1463, + "step": 12695 + }, + { + "epoch": 1.63, + "learning_rate": 8.930909388787084e-07, + "loss": 0.1393, + "step": 12696 + }, + { + "epoch": 1.63, + "learning_rate": 8.92499836860179e-07, + "loss": 0.1312, + "step": 12697 + }, + { + "epoch": 1.63, + "learning_rate": 8.919089113500795e-07, + "loss": 0.1448, + "step": 12698 + }, + { + "epoch": 1.63, + "learning_rate": 8.913181623738032e-07, + "loss": 0.1262, + "step": 12699 + }, + { + "epoch": 1.63, + "learning_rate": 8.907275899567363e-07, + "loss": 0.1357, + "step": 12700 + }, + { + "epoch": 1.63, + "learning_rate": 8.901371941242554e-07, + "loss": 0.1292, + "step": 12701 + }, + { + "epoch": 1.63, + "learning_rate": 8.895469749017344e-07, + "loss": 0.1279, + "step": 12702 + }, + { + "epoch": 1.63, + "learning_rate": 8.889569323145325e-07, + "loss": 0.1393, + "step": 12703 + }, + { + "epoch": 1.63, + "learning_rate": 8.883670663880078e-07, + "loss": 0.1474, + "step": 12704 + }, + { + "epoch": 1.63, + "learning_rate": 8.877773771475074e-07, + "loss": 0.1285, + "step": 12705 + }, + { + "epoch": 1.63, + "learning_rate": 8.871878646183718e-07, + "loss": 0.132, + "step": 12706 + }, + { + "epoch": 1.63, + "learning_rate": 8.865985288259332e-07, + "loss": 0.1346, + "step": 12707 + }, + { + "epoch": 1.63, + "learning_rate": 8.860093697955152e-07, + "loss": 0.1338, + "step": 12708 + }, + { + "epoch": 1.63, + "learning_rate": 8.854203875524403e-07, + "loss": 0.13, + "step": 12709 + }, + { + "epoch": 1.63, + "learning_rate": 8.848315821220133e-07, + "loss": 0.1184, + "step": 12710 + }, + { + "epoch": 1.63, + "learning_rate": 8.842429535295366e-07, + "loss": 0.1357, + "step": 12711 + }, + { + "epoch": 1.63, + "learning_rate": 8.836545018003084e-07, + "loss": 0.141, + "step": 12712 + }, + { + "epoch": 1.63, + "learning_rate": 8.830662269596135e-07, + "loss": 0.1491, + "step": 12713 + }, + { + "epoch": 1.63, + "learning_rate": 8.824781290327317e-07, + "loss": 0.1312, + "step": 12714 + }, + { + "epoch": 1.63, + "learning_rate": 8.818902080449348e-07, + "loss": 0.1374, + "step": 12715 + }, + { + "epoch": 1.63, + "learning_rate": 8.813024640214873e-07, + "loss": 0.1374, + "step": 12716 + }, + { + "epoch": 1.63, + "learning_rate": 8.807148969876455e-07, + "loss": 0.1343, + "step": 12717 + }, + { + "epoch": 1.63, + "learning_rate": 8.801275069686593e-07, + "loss": 0.1387, + "step": 12718 + }, + { + "epoch": 1.63, + "learning_rate": 8.795402939897679e-07, + "loss": 0.1328, + "step": 12719 + }, + { + "epoch": 1.63, + "learning_rate": 8.789532580762095e-07, + "loss": 0.1314, + "step": 12720 + }, + { + "epoch": 1.63, + "learning_rate": 8.783663992532048e-07, + "loss": 0.1466, + "step": 12721 + }, + { + "epoch": 1.63, + "learning_rate": 8.777797175459773e-07, + "loss": 0.1329, + "step": 12722 + }, + { + "epoch": 1.63, + "learning_rate": 8.771932129797356e-07, + "loss": 0.1398, + "step": 12723 + }, + { + "epoch": 1.63, + "learning_rate": 8.766068855796833e-07, + "loss": 0.119, + "step": 12724 + }, + { + "epoch": 1.63, + "learning_rate": 8.760207353710165e-07, + "loss": 0.1401, + "step": 12725 + }, + { + "epoch": 1.63, + "learning_rate": 8.754347623789222e-07, + "loss": 0.1317, + "step": 12726 + }, + { + "epoch": 1.63, + "learning_rate": 8.748489666285842e-07, + "loss": 0.1291, + "step": 12727 + }, + { + "epoch": 1.63, + "learning_rate": 8.742633481451728e-07, + "loss": 0.1511, + "step": 12728 + }, + { + "epoch": 1.63, + "learning_rate": 8.736779069538521e-07, + "loss": 0.1431, + "step": 12729 + }, + { + "epoch": 1.63, + "learning_rate": 8.730926430797826e-07, + "loss": 0.136, + "step": 12730 + }, + { + "epoch": 1.63, + "learning_rate": 8.72507556548114e-07, + "loss": 0.1518, + "step": 12731 + }, + { + "epoch": 1.63, + "learning_rate": 8.719226473839876e-07, + "loss": 0.1318, + "step": 12732 + }, + { + "epoch": 1.63, + "learning_rate": 8.713379156125385e-07, + "loss": 0.1359, + "step": 12733 + }, + { + "epoch": 1.63, + "learning_rate": 8.707533612588948e-07, + "loss": 0.133, + "step": 12734 + }, + { + "epoch": 1.63, + "learning_rate": 8.701689843481753e-07, + "loss": 0.1444, + "step": 12735 + }, + { + "epoch": 1.63, + "learning_rate": 8.695847849054906e-07, + "loss": 0.1236, + "step": 12736 + }, + { + "epoch": 1.63, + "learning_rate": 8.690007629559482e-07, + "loss": 0.1258, + "step": 12737 + }, + { + "epoch": 1.63, + "learning_rate": 8.684169185246444e-07, + "loss": 0.129, + "step": 12738 + }, + { + "epoch": 1.63, + "learning_rate": 8.67833251636665e-07, + "loss": 0.1516, + "step": 12739 + }, + { + "epoch": 1.63, + "learning_rate": 8.672497623170944e-07, + "loss": 0.1447, + "step": 12740 + }, + { + "epoch": 1.63, + "learning_rate": 8.666664505910055e-07, + "loss": 0.1233, + "step": 12741 + }, + { + "epoch": 1.63, + "learning_rate": 8.660833164834653e-07, + "loss": 0.1266, + "step": 12742 + }, + { + "epoch": 1.63, + "learning_rate": 8.65500360019531e-07, + "loss": 0.1302, + "step": 12743 + }, + { + "epoch": 1.63, + "learning_rate": 8.649175812242532e-07, + "loss": 0.1452, + "step": 12744 + }, + { + "epoch": 1.63, + "learning_rate": 8.643349801226791e-07, + "loss": 0.137, + "step": 12745 + }, + { + "epoch": 1.63, + "learning_rate": 8.637525567398392e-07, + "loss": 0.1318, + "step": 12746 + }, + { + "epoch": 1.63, + "learning_rate": 8.631703111007645e-07, + "loss": 0.1374, + "step": 12747 + }, + { + "epoch": 1.63, + "learning_rate": 8.625882432304749e-07, + "loss": 0.1516, + "step": 12748 + }, + { + "epoch": 1.63, + "learning_rate": 8.62006353153983e-07, + "loss": 0.1261, + "step": 12749 + }, + { + "epoch": 1.63, + "learning_rate": 8.61424640896294e-07, + "loss": 0.1431, + "step": 12750 + }, + { + "epoch": 1.63, + "learning_rate": 8.608431064824052e-07, + "loss": 0.1202, + "step": 12751 + }, + { + "epoch": 1.63, + "learning_rate": 8.602617499373056e-07, + "loss": 0.1372, + "step": 12752 + }, + { + "epoch": 1.63, + "learning_rate": 8.596805712859807e-07, + "loss": 0.1289, + "step": 12753 + }, + { + "epoch": 1.63, + "learning_rate": 8.590995705533994e-07, + "loss": 0.1036, + "step": 12754 + }, + { + "epoch": 1.63, + "learning_rate": 8.58518747764534e-07, + "loss": 0.1473, + "step": 12755 + }, + { + "epoch": 1.63, + "learning_rate": 8.579381029443412e-07, + "loss": 0.1244, + "step": 12756 + }, + { + "epoch": 1.63, + "learning_rate": 8.573576361177733e-07, + "loss": 0.1552, + "step": 12757 + }, + { + "epoch": 1.63, + "learning_rate": 8.567773473097735e-07, + "loss": 0.1208, + "step": 12758 + }, + { + "epoch": 1.63, + "learning_rate": 8.561972365452775e-07, + "loss": 0.1306, + "step": 12759 + }, + { + "epoch": 1.63, + "learning_rate": 8.556173038492171e-07, + "loss": 0.116, + "step": 12760 + }, + { + "epoch": 1.63, + "learning_rate": 8.550375492465102e-07, + "loss": 0.1391, + "step": 12761 + }, + { + "epoch": 1.63, + "learning_rate": 8.5445797276207e-07, + "loss": 0.1467, + "step": 12762 + }, + { + "epoch": 1.63, + "learning_rate": 8.538785744208062e-07, + "loss": 0.1275, + "step": 12763 + }, + { + "epoch": 1.63, + "learning_rate": 8.532993542476108e-07, + "loss": 0.1253, + "step": 12764 + }, + { + "epoch": 1.63, + "learning_rate": 8.527203122673789e-07, + "loss": 0.1253, + "step": 12765 + }, + { + "epoch": 1.63, + "learning_rate": 8.521414485049917e-07, + "loss": 0.1327, + "step": 12766 + }, + { + "epoch": 1.63, + "learning_rate": 8.51562762985324e-07, + "loss": 0.1334, + "step": 12767 + }, + { + "epoch": 1.63, + "learning_rate": 8.509842557332437e-07, + "loss": 0.1406, + "step": 12768 + }, + { + "epoch": 1.63, + "learning_rate": 8.504059267736097e-07, + "loss": 0.1427, + "step": 12769 + }, + { + "epoch": 1.63, + "learning_rate": 8.49827776131274e-07, + "loss": 0.1456, + "step": 12770 + }, + { + "epoch": 1.63, + "learning_rate": 8.492498038310843e-07, + "loss": 0.1424, + "step": 12771 + }, + { + "epoch": 1.63, + "learning_rate": 8.486720098978718e-07, + "loss": 0.1418, + "step": 12772 + }, + { + "epoch": 1.63, + "learning_rate": 8.480943943564701e-07, + "loss": 0.1447, + "step": 12773 + }, + { + "epoch": 1.64, + "learning_rate": 8.475169572316988e-07, + "loss": 0.1419, + "step": 12774 + }, + { + "epoch": 1.64, + "learning_rate": 8.469396985483724e-07, + "loss": 0.1332, + "step": 12775 + }, + { + "epoch": 1.64, + "learning_rate": 8.463626183312962e-07, + "loss": 0.1176, + "step": 12776 + }, + { + "epoch": 1.64, + "learning_rate": 8.457857166052674e-07, + "loss": 0.1333, + "step": 12777 + }, + { + "epoch": 1.64, + "learning_rate": 8.452089933950813e-07, + "loss": 0.1176, + "step": 12778 + }, + { + "epoch": 1.64, + "learning_rate": 8.446324487255164e-07, + "loss": 0.1281, + "step": 12779 + }, + { + "epoch": 1.64, + "learning_rate": 8.440560826213485e-07, + "loss": 0.1364, + "step": 12780 + }, + { + "epoch": 1.64, + "learning_rate": 8.434798951073492e-07, + "loss": 0.1203, + "step": 12781 + }, + { + "epoch": 1.64, + "learning_rate": 8.429038862082734e-07, + "loss": 0.1246, + "step": 12782 + }, + { + "epoch": 1.64, + "learning_rate": 8.423280559488767e-07, + "loss": 0.1421, + "step": 12783 + }, + { + "epoch": 1.64, + "learning_rate": 8.417524043539038e-07, + "loss": 0.1192, + "step": 12784 + }, + { + "epoch": 1.64, + "learning_rate": 8.411769314480905e-07, + "loss": 0.1382, + "step": 12785 + }, + { + "epoch": 1.64, + "learning_rate": 8.406016372561665e-07, + "loss": 0.144, + "step": 12786 + }, + { + "epoch": 1.64, + "learning_rate": 8.400265218028525e-07, + "loss": 0.1415, + "step": 12787 + }, + { + "epoch": 1.64, + "learning_rate": 8.394515851128654e-07, + "loss": 0.1187, + "step": 12788 + }, + { + "epoch": 1.64, + "learning_rate": 8.388768272109105e-07, + "loss": 0.1271, + "step": 12789 + }, + { + "epoch": 1.64, + "learning_rate": 8.383022481216829e-07, + "loss": 0.1459, + "step": 12790 + }, + { + "epoch": 1.64, + "learning_rate": 8.37727847869878e-07, + "loss": 0.1333, + "step": 12791 + }, + { + "epoch": 1.64, + "learning_rate": 8.371536264801772e-07, + "loss": 0.1308, + "step": 12792 + }, + { + "epoch": 1.64, + "learning_rate": 8.365795839772561e-07, + "loss": 0.1281, + "step": 12793 + }, + { + "epoch": 1.64, + "learning_rate": 8.36005720385783e-07, + "loss": 0.112, + "step": 12794 + }, + { + "epoch": 1.64, + "learning_rate": 8.354320357304163e-07, + "loss": 0.1277, + "step": 12795 + }, + { + "epoch": 1.64, + "learning_rate": 8.34858530035813e-07, + "loss": 0.1353, + "step": 12796 + }, + { + "epoch": 1.64, + "learning_rate": 8.342852033266119e-07, + "loss": 0.1232, + "step": 12797 + }, + { + "epoch": 1.64, + "learning_rate": 8.337120556274548e-07, + "loss": 0.1427, + "step": 12798 + }, + { + "epoch": 1.64, + "learning_rate": 8.331390869629702e-07, + "loss": 0.1339, + "step": 12799 + }, + { + "epoch": 1.64, + "learning_rate": 8.32566297357777e-07, + "loss": 0.1218, + "step": 12800 + }, + { + "epoch": 1.64, + "learning_rate": 8.319936868364925e-07, + "loss": 0.1338, + "step": 12801 + }, + { + "epoch": 1.64, + "learning_rate": 8.314212554237222e-07, + "loss": 0.1464, + "step": 12802 + }, + { + "epoch": 1.64, + "learning_rate": 8.308490031440641e-07, + "loss": 0.1354, + "step": 12803 + }, + { + "epoch": 1.64, + "learning_rate": 8.302769300221098e-07, + "loss": 0.1399, + "step": 12804 + }, + { + "epoch": 1.64, + "learning_rate": 8.29705036082441e-07, + "loss": 0.1219, + "step": 12805 + }, + { + "epoch": 1.64, + "learning_rate": 8.291333213496355e-07, + "loss": 0.118, + "step": 12806 + }, + { + "epoch": 1.64, + "learning_rate": 8.285617858482609e-07, + "loss": 0.1404, + "step": 12807 + }, + { + "epoch": 1.64, + "learning_rate": 8.279904296028757e-07, + "loss": 0.1363, + "step": 12808 + }, + { + "epoch": 1.64, + "learning_rate": 8.274192526380337e-07, + "loss": 0.137, + "step": 12809 + }, + { + "epoch": 1.64, + "learning_rate": 8.268482549782797e-07, + "loss": 0.1364, + "step": 12810 + }, + { + "epoch": 1.64, + "learning_rate": 8.262774366481496e-07, + "loss": 0.1415, + "step": 12811 + }, + { + "epoch": 1.64, + "learning_rate": 8.257067976721739e-07, + "loss": 0.1282, + "step": 12812 + }, + { + "epoch": 1.64, + "learning_rate": 8.251363380748723e-07, + "loss": 0.1476, + "step": 12813 + }, + { + "epoch": 1.64, + "learning_rate": 8.24566057880763e-07, + "loss": 0.1375, + "step": 12814 + }, + { + "epoch": 1.64, + "learning_rate": 8.239959571143463e-07, + "loss": 0.1338, + "step": 12815 + }, + { + "epoch": 1.64, + "learning_rate": 8.234260358001256e-07, + "loss": 0.1309, + "step": 12816 + }, + { + "epoch": 1.64, + "learning_rate": 8.228562939625906e-07, + "loss": 0.1582, + "step": 12817 + }, + { + "epoch": 1.64, + "learning_rate": 8.222867316262217e-07, + "loss": 0.1276, + "step": 12818 + }, + { + "epoch": 1.64, + "learning_rate": 8.217173488154972e-07, + "loss": 0.1262, + "step": 12819 + }, + { + "epoch": 1.64, + "learning_rate": 8.211481455548837e-07, + "loss": 0.1215, + "step": 12820 + }, + { + "epoch": 1.64, + "learning_rate": 8.205791218688414e-07, + "loss": 0.1309, + "step": 12821 + }, + { + "epoch": 1.64, + "learning_rate": 8.20010277781822e-07, + "loss": 0.1323, + "step": 12822 + }, + { + "epoch": 1.64, + "learning_rate": 8.194416133182693e-07, + "loss": 0.1436, + "step": 12823 + }, + { + "epoch": 1.64, + "learning_rate": 8.188731285026219e-07, + "loss": 0.124, + "step": 12824 + }, + { + "epoch": 1.64, + "learning_rate": 8.183048233593083e-07, + "loss": 0.1276, + "step": 12825 + }, + { + "epoch": 1.64, + "learning_rate": 8.177366979127499e-07, + "loss": 0.1241, + "step": 12826 + }, + { + "epoch": 1.64, + "learning_rate": 8.171687521873595e-07, + "loss": 0.1359, + "step": 12827 + }, + { + "epoch": 1.64, + "learning_rate": 8.166009862075435e-07, + "loss": 0.1339, + "step": 12828 + }, + { + "epoch": 1.64, + "learning_rate": 8.160333999977004e-07, + "loss": 0.1374, + "step": 12829 + }, + { + "epoch": 1.64, + "learning_rate": 8.154659935822201e-07, + "loss": 0.1506, + "step": 12830 + }, + { + "epoch": 1.64, + "learning_rate": 8.148987669854846e-07, + "loss": 0.1237, + "step": 12831 + }, + { + "epoch": 1.64, + "learning_rate": 8.143317202318718e-07, + "loss": 0.1249, + "step": 12832 + }, + { + "epoch": 1.64, + "learning_rate": 8.137648533457448e-07, + "loss": 0.1328, + "step": 12833 + }, + { + "epoch": 1.64, + "learning_rate": 8.131981663514665e-07, + "loss": 0.1581, + "step": 12834 + }, + { + "epoch": 1.64, + "learning_rate": 8.126316592733874e-07, + "loss": 0.1334, + "step": 12835 + }, + { + "epoch": 1.64, + "learning_rate": 8.120653321358519e-07, + "loss": 0.1378, + "step": 12836 + }, + { + "epoch": 1.64, + "learning_rate": 8.114991849631953e-07, + "loss": 0.1383, + "step": 12837 + }, + { + "epoch": 1.64, + "learning_rate": 8.109332177797469e-07, + "loss": 0.1389, + "step": 12838 + }, + { + "epoch": 1.64, + "learning_rate": 8.103674306098291e-07, + "loss": 0.1421, + "step": 12839 + }, + { + "epoch": 1.64, + "learning_rate": 8.098018234777533e-07, + "loss": 0.1416, + "step": 12840 + }, + { + "epoch": 1.64, + "learning_rate": 8.092363964078237e-07, + "loss": 0.1222, + "step": 12841 + }, + { + "epoch": 1.64, + "learning_rate": 8.086711494243405e-07, + "loss": 0.1231, + "step": 12842 + }, + { + "epoch": 1.64, + "learning_rate": 8.081060825515924e-07, + "loss": 0.1381, + "step": 12843 + }, + { + "epoch": 1.64, + "learning_rate": 8.075411958138623e-07, + "loss": 0.1528, + "step": 12844 + }, + { + "epoch": 1.64, + "learning_rate": 8.069764892354237e-07, + "loss": 0.1191, + "step": 12845 + }, + { + "epoch": 1.64, + "learning_rate": 8.064119628405443e-07, + "loss": 0.1396, + "step": 12846 + }, + { + "epoch": 1.64, + "learning_rate": 8.058476166534818e-07, + "loss": 0.1364, + "step": 12847 + }, + { + "epoch": 1.64, + "learning_rate": 8.052834506984874e-07, + "loss": 0.1422, + "step": 12848 + }, + { + "epoch": 1.64, + "learning_rate": 8.047194649998063e-07, + "loss": 0.1196, + "step": 12849 + }, + { + "epoch": 1.64, + "learning_rate": 8.041556595816741e-07, + "loss": 0.1162, + "step": 12850 + }, + { + "epoch": 1.64, + "learning_rate": 8.035920344683157e-07, + "loss": 0.1307, + "step": 12851 + }, + { + "epoch": 1.65, + "learning_rate": 8.030285896839546e-07, + "loss": 0.1258, + "step": 12852 + }, + { + "epoch": 1.65, + "learning_rate": 8.024653252528025e-07, + "loss": 0.1361, + "step": 12853 + }, + { + "epoch": 1.65, + "learning_rate": 8.019022411990634e-07, + "loss": 0.1283, + "step": 12854 + }, + { + "epoch": 1.65, + "learning_rate": 8.013393375469347e-07, + "loss": 0.1185, + "step": 12855 + }, + { + "epoch": 1.65, + "learning_rate": 8.007766143206047e-07, + "loss": 0.1254, + "step": 12856 + }, + { + "epoch": 1.65, + "learning_rate": 8.00214071544258e-07, + "loss": 0.1354, + "step": 12857 + }, + { + "epoch": 1.65, + "learning_rate": 7.996517092420636e-07, + "loss": 0.1367, + "step": 12858 + }, + { + "epoch": 1.65, + "learning_rate": 7.99089527438191e-07, + "loss": 0.1246, + "step": 12859 + }, + { + "epoch": 1.65, + "learning_rate": 7.985275261567971e-07, + "loss": 0.1407, + "step": 12860 + }, + { + "epoch": 1.65, + "learning_rate": 7.97965705422033e-07, + "loss": 0.1585, + "step": 12861 + }, + { + "epoch": 1.65, + "learning_rate": 7.974040652580412e-07, + "loss": 0.135, + "step": 12862 + }, + { + "epoch": 1.65, + "learning_rate": 7.968426056889561e-07, + "loss": 0.1217, + "step": 12863 + }, + { + "epoch": 1.65, + "learning_rate": 7.962813267389052e-07, + "loss": 0.1233, + "step": 12864 + }, + { + "epoch": 1.65, + "learning_rate": 7.957202284320076e-07, + "loss": 0.1303, + "step": 12865 + }, + { + "epoch": 1.65, + "learning_rate": 7.951593107923744e-07, + "loss": 0.1335, + "step": 12866 + }, + { + "epoch": 1.65, + "learning_rate": 7.945985738441114e-07, + "loss": 0.1257, + "step": 12867 + }, + { + "epoch": 1.65, + "learning_rate": 7.940380176113149e-07, + "loss": 0.1351, + "step": 12868 + }, + { + "epoch": 1.65, + "learning_rate": 7.93477642118069e-07, + "loss": 0.1445, + "step": 12869 + }, + { + "epoch": 1.65, + "learning_rate": 7.929174473884593e-07, + "loss": 0.1437, + "step": 12870 + }, + { + "epoch": 1.65, + "learning_rate": 7.923574334465562e-07, + "loss": 0.1378, + "step": 12871 + }, + { + "epoch": 1.65, + "learning_rate": 7.917976003164246e-07, + "loss": 0.1241, + "step": 12872 + }, + { + "epoch": 1.65, + "learning_rate": 7.912379480221228e-07, + "loss": 0.1452, + "step": 12873 + }, + { + "epoch": 1.65, + "learning_rate": 7.906784765876985e-07, + "loss": 0.1182, + "step": 12874 + }, + { + "epoch": 1.65, + "learning_rate": 7.90119186037197e-07, + "loss": 0.1292, + "step": 12875 + }, + { + "epoch": 1.65, + "learning_rate": 7.895600763946482e-07, + "loss": 0.1247, + "step": 12876 + }, + { + "epoch": 1.65, + "learning_rate": 7.890011476840809e-07, + "loss": 0.1459, + "step": 12877 + }, + { + "epoch": 1.65, + "learning_rate": 7.884423999295122e-07, + "loss": 0.1495, + "step": 12878 + }, + { + "epoch": 1.65, + "learning_rate": 7.878838331549538e-07, + "loss": 0.1401, + "step": 12879 + }, + { + "epoch": 1.65, + "learning_rate": 7.873254473844077e-07, + "loss": 0.1319, + "step": 12880 + }, + { + "epoch": 1.65, + "learning_rate": 7.867672426418693e-07, + "loss": 0.1319, + "step": 12881 + }, + { + "epoch": 1.65, + "learning_rate": 7.86209218951326e-07, + "loss": 0.1356, + "step": 12882 + }, + { + "epoch": 1.65, + "learning_rate": 7.856513763367569e-07, + "loss": 0.1152, + "step": 12883 + }, + { + "epoch": 1.65, + "learning_rate": 7.850937148221332e-07, + "loss": 0.1271, + "step": 12884 + }, + { + "epoch": 1.65, + "learning_rate": 7.845362344314206e-07, + "loss": 0.1372, + "step": 12885 + }, + { + "epoch": 1.65, + "learning_rate": 7.839789351885746e-07, + "loss": 0.1268, + "step": 12886 + }, + { + "epoch": 1.65, + "learning_rate": 7.834218171175428e-07, + "loss": 0.1316, + "step": 12887 + }, + { + "epoch": 1.65, + "learning_rate": 7.828648802422667e-07, + "loss": 0.119, + "step": 12888 + }, + { + "epoch": 1.65, + "learning_rate": 7.823081245866776e-07, + "loss": 0.1384, + "step": 12889 + }, + { + "epoch": 1.65, + "learning_rate": 7.817515501747041e-07, + "loss": 0.1183, + "step": 12890 + }, + { + "epoch": 1.65, + "learning_rate": 7.811951570302594e-07, + "loss": 0.1417, + "step": 12891 + }, + { + "epoch": 1.65, + "learning_rate": 7.806389451772539e-07, + "loss": 0.1271, + "step": 12892 + }, + { + "epoch": 1.65, + "learning_rate": 7.800829146395922e-07, + "loss": 0.122, + "step": 12893 + }, + { + "epoch": 1.65, + "learning_rate": 7.795270654411635e-07, + "loss": 0.133, + "step": 12894 + }, + { + "epoch": 1.65, + "learning_rate": 7.789713976058578e-07, + "loss": 0.1353, + "step": 12895 + }, + { + "epoch": 1.65, + "learning_rate": 7.784159111575512e-07, + "loss": 0.1349, + "step": 12896 + }, + { + "epoch": 1.65, + "learning_rate": 7.778606061201154e-07, + "loss": 0.1423, + "step": 12897 + }, + { + "epoch": 1.65, + "learning_rate": 7.773054825174126e-07, + "loss": 0.1424, + "step": 12898 + }, + { + "epoch": 1.65, + "learning_rate": 7.767505403732961e-07, + "loss": 0.1124, + "step": 12899 + }, + { + "epoch": 1.65, + "learning_rate": 7.761957797116171e-07, + "loss": 0.1317, + "step": 12900 + }, + { + "epoch": 1.65, + "learning_rate": 7.756412005562114e-07, + "loss": 0.13, + "step": 12901 + }, + { + "epoch": 1.65, + "learning_rate": 7.750868029309099e-07, + "loss": 0.123, + "step": 12902 + }, + { + "epoch": 1.65, + "learning_rate": 7.745325868595394e-07, + "loss": 0.1425, + "step": 12903 + }, + { + "epoch": 1.65, + "learning_rate": 7.739785523659144e-07, + "loss": 0.1473, + "step": 12904 + }, + { + "epoch": 1.65, + "learning_rate": 7.734246994738426e-07, + "loss": 0.1321, + "step": 12905 + }, + { + "epoch": 1.65, + "learning_rate": 7.728710282071244e-07, + "loss": 0.1316, + "step": 12906 + }, + { + "epoch": 1.65, + "learning_rate": 7.723175385895509e-07, + "loss": 0.121, + "step": 12907 + }, + { + "epoch": 1.65, + "learning_rate": 7.717642306449113e-07, + "loss": 0.1369, + "step": 12908 + }, + { + "epoch": 1.65, + "learning_rate": 7.712111043969772e-07, + "loss": 0.1272, + "step": 12909 + }, + { + "epoch": 1.65, + "learning_rate": 7.706581598695207e-07, + "loss": 0.1452, + "step": 12910 + }, + { + "epoch": 1.65, + "learning_rate": 7.701053970863037e-07, + "loss": 0.1335, + "step": 12911 + }, + { + "epoch": 1.65, + "learning_rate": 7.695528160710764e-07, + "loss": 0.1138, + "step": 12912 + }, + { + "epoch": 1.65, + "learning_rate": 7.690004168475868e-07, + "loss": 0.1299, + "step": 12913 + }, + { + "epoch": 1.65, + "learning_rate": 7.684481994395726e-07, + "loss": 0.1427, + "step": 12914 + }, + { + "epoch": 1.65, + "learning_rate": 7.678961638707633e-07, + "loss": 0.1541, + "step": 12915 + }, + { + "epoch": 1.65, + "learning_rate": 7.673443101648808e-07, + "loss": 0.1293, + "step": 12916 + }, + { + "epoch": 1.65, + "learning_rate": 7.667926383456392e-07, + "loss": 0.1451, + "step": 12917 + }, + { + "epoch": 1.65, + "learning_rate": 7.662411484367482e-07, + "loss": 0.1322, + "step": 12918 + }, + { + "epoch": 1.65, + "learning_rate": 7.656898404619029e-07, + "loss": 0.151, + "step": 12919 + }, + { + "epoch": 1.65, + "learning_rate": 7.651387144447942e-07, + "loss": 0.1237, + "step": 12920 + }, + { + "epoch": 1.65, + "learning_rate": 7.645877704091082e-07, + "loss": 0.1227, + "step": 12921 + }, + { + "epoch": 1.65, + "learning_rate": 7.640370083785175e-07, + "loss": 0.1398, + "step": 12922 + }, + { + "epoch": 1.65, + "learning_rate": 7.634864283766913e-07, + "loss": 0.1233, + "step": 12923 + }, + { + "epoch": 1.65, + "learning_rate": 7.629360304272882e-07, + "loss": 0.1169, + "step": 12924 + }, + { + "epoch": 1.65, + "learning_rate": 7.623858145539592e-07, + "loss": 0.1324, + "step": 12925 + }, + { + "epoch": 1.65, + "learning_rate": 7.618357807803517e-07, + "loss": 0.1337, + "step": 12926 + }, + { + "epoch": 1.65, + "learning_rate": 7.612859291300973e-07, + "loss": 0.1409, + "step": 12927 + }, + { + "epoch": 1.65, + "learning_rate": 7.607362596268281e-07, + "loss": 0.1291, + "step": 12928 + }, + { + "epoch": 1.65, + "learning_rate": 7.601867722941642e-07, + "loss": 0.1237, + "step": 12929 + }, + { + "epoch": 1.66, + "learning_rate": 7.596374671557144e-07, + "loss": 0.1408, + "step": 12930 + }, + { + "epoch": 1.66, + "learning_rate": 7.590883442350883e-07, + "loss": 0.1316, + "step": 12931 + }, + { + "epoch": 1.66, + "learning_rate": 7.585394035558807e-07, + "loss": 0.1419, + "step": 12932 + }, + { + "epoch": 1.66, + "learning_rate": 7.579906451416813e-07, + "loss": 0.1318, + "step": 12933 + }, + { + "epoch": 1.66, + "learning_rate": 7.57442069016071e-07, + "loss": 0.1207, + "step": 12934 + }, + { + "epoch": 1.66, + "learning_rate": 7.568936752026229e-07, + "loss": 0.1476, + "step": 12935 + }, + { + "epoch": 1.66, + "learning_rate": 7.563454637249056e-07, + "loss": 0.1592, + "step": 12936 + }, + { + "epoch": 1.66, + "learning_rate": 7.557974346064728e-07, + "loss": 0.1392, + "step": 12937 + }, + { + "epoch": 1.66, + "learning_rate": 7.552495878708776e-07, + "loss": 0.1246, + "step": 12938 + }, + { + "epoch": 1.66, + "learning_rate": 7.547019235416609e-07, + "loss": 0.1349, + "step": 12939 + }, + { + "epoch": 1.66, + "learning_rate": 7.541544416423574e-07, + "loss": 0.1179, + "step": 12940 + }, + { + "epoch": 1.66, + "learning_rate": 7.536071421964941e-07, + "loss": 0.1441, + "step": 12941 + }, + { + "epoch": 1.66, + "learning_rate": 7.530600252275888e-07, + "loss": 0.1258, + "step": 12942 + }, + { + "epoch": 1.66, + "learning_rate": 7.52513090759151e-07, + "loss": 0.1217, + "step": 12943 + }, + { + "epoch": 1.66, + "learning_rate": 7.519663388146886e-07, + "loss": 0.1404, + "step": 12944 + }, + { + "epoch": 1.66, + "learning_rate": 7.514197694176905e-07, + "loss": 0.1301, + "step": 12945 + }, + { + "epoch": 1.66, + "learning_rate": 7.50873382591648e-07, + "loss": 0.1278, + "step": 12946 + }, + { + "epoch": 1.66, + "learning_rate": 7.503271783600402e-07, + "loss": 0.1456, + "step": 12947 + }, + { + "epoch": 1.66, + "learning_rate": 7.497811567463381e-07, + "loss": 0.1437, + "step": 12948 + }, + { + "epoch": 1.66, + "learning_rate": 7.492353177740047e-07, + "loss": 0.1288, + "step": 12949 + }, + { + "epoch": 1.66, + "learning_rate": 7.486896614664962e-07, + "loss": 0.1483, + "step": 12950 + }, + { + "epoch": 1.66, + "learning_rate": 7.481441878472629e-07, + "loss": 0.1416, + "step": 12951 + }, + { + "epoch": 1.66, + "learning_rate": 7.475988969397424e-07, + "loss": 0.1365, + "step": 12952 + }, + { + "epoch": 1.66, + "learning_rate": 7.470537887673667e-07, + "loss": 0.1335, + "step": 12953 + }, + { + "epoch": 1.66, + "learning_rate": 7.465088633535639e-07, + "loss": 0.1344, + "step": 12954 + }, + { + "epoch": 1.66, + "learning_rate": 7.459641207217461e-07, + "loss": 0.1377, + "step": 12955 + }, + { + "epoch": 1.66, + "learning_rate": 7.454195608953252e-07, + "loss": 0.1383, + "step": 12956 + }, + { + "epoch": 1.66, + "learning_rate": 7.448751838977014e-07, + "loss": 0.1453, + "step": 12957 + }, + { + "epoch": 1.66, + "learning_rate": 7.443309897522671e-07, + "loss": 0.1329, + "step": 12958 + }, + { + "epoch": 1.66, + "learning_rate": 7.437869784824086e-07, + "loss": 0.1286, + "step": 12959 + }, + { + "epoch": 1.66, + "learning_rate": 7.432431501115012e-07, + "loss": 0.1388, + "step": 12960 + }, + { + "epoch": 1.66, + "learning_rate": 7.426995046629176e-07, + "loss": 0.1279, + "step": 12961 + }, + { + "epoch": 1.66, + "learning_rate": 7.421560421600182e-07, + "loss": 0.1384, + "step": 12962 + }, + { + "epoch": 1.66, + "learning_rate": 7.416127626261549e-07, + "loss": 0.1195, + "step": 12963 + }, + { + "epoch": 1.66, + "learning_rate": 7.410696660846761e-07, + "loss": 0.1446, + "step": 12964 + }, + { + "epoch": 1.66, + "learning_rate": 7.405267525589183e-07, + "loss": 0.1303, + "step": 12965 + }, + { + "epoch": 1.66, + "learning_rate": 7.399840220722127e-07, + "loss": 0.1349, + "step": 12966 + }, + { + "epoch": 1.66, + "learning_rate": 7.394414746478817e-07, + "loss": 0.1349, + "step": 12967 + }, + { + "epoch": 1.66, + "learning_rate": 7.388991103092374e-07, + "loss": 0.1381, + "step": 12968 + }, + { + "epoch": 1.66, + "learning_rate": 7.383569290795911e-07, + "loss": 0.135, + "step": 12969 + }, + { + "epoch": 1.66, + "learning_rate": 7.378149309822374e-07, + "loss": 0.1375, + "step": 12970 + }, + { + "epoch": 1.66, + "learning_rate": 7.372731160404672e-07, + "loss": 0.1312, + "step": 12971 + }, + { + "epoch": 1.66, + "learning_rate": 7.367314842775674e-07, + "loss": 0.1416, + "step": 12972 + }, + { + "epoch": 1.66, + "learning_rate": 7.361900357168084e-07, + "loss": 0.1369, + "step": 12973 + }, + { + "epoch": 1.66, + "learning_rate": 7.356487703814602e-07, + "loss": 0.1448, + "step": 12974 + }, + { + "epoch": 1.66, + "learning_rate": 7.351076882947817e-07, + "loss": 0.1118, + "step": 12975 + }, + { + "epoch": 1.66, + "learning_rate": 7.345667894800246e-07, + "loss": 0.1451, + "step": 12976 + }, + { + "epoch": 1.66, + "learning_rate": 7.340260739604316e-07, + "loss": 0.1291, + "step": 12977 + }, + { + "epoch": 1.66, + "learning_rate": 7.334855417592385e-07, + "loss": 0.1339, + "step": 12978 + }, + { + "epoch": 1.66, + "learning_rate": 7.329451928996745e-07, + "loss": 0.1244, + "step": 12979 + }, + { + "epoch": 1.66, + "learning_rate": 7.324050274049599e-07, + "loss": 0.1252, + "step": 12980 + }, + { + "epoch": 1.66, + "learning_rate": 7.318650452983039e-07, + "loss": 0.1148, + "step": 12981 + }, + { + "epoch": 1.66, + "learning_rate": 7.313252466029131e-07, + "loss": 0.1308, + "step": 12982 + }, + { + "epoch": 1.66, + "learning_rate": 7.307856313419837e-07, + "loss": 0.1291, + "step": 12983 + }, + { + "epoch": 1.66, + "learning_rate": 7.302461995387033e-07, + "loss": 0.1308, + "step": 12984 + }, + { + "epoch": 1.66, + "learning_rate": 7.297069512162535e-07, + "loss": 0.133, + "step": 12985 + }, + { + "epoch": 1.66, + "learning_rate": 7.291678863978052e-07, + "loss": 0.1377, + "step": 12986 + }, + { + "epoch": 1.66, + "learning_rate": 7.286290051065264e-07, + "loss": 0.1202, + "step": 12987 + }, + { + "epoch": 1.66, + "learning_rate": 7.280903073655704e-07, + "loss": 0.1216, + "step": 12988 + }, + { + "epoch": 1.66, + "learning_rate": 7.275517931980886e-07, + "loss": 0.1366, + "step": 12989 + }, + { + "epoch": 1.66, + "learning_rate": 7.270134626272229e-07, + "loss": 0.1371, + "step": 12990 + }, + { + "epoch": 1.66, + "learning_rate": 7.264753156761028e-07, + "loss": 0.1213, + "step": 12991 + }, + { + "epoch": 1.66, + "learning_rate": 7.25937352367857e-07, + "loss": 0.1318, + "step": 12992 + }, + { + "epoch": 1.66, + "learning_rate": 7.253995727256024e-07, + "loss": 0.1431, + "step": 12993 + }, + { + "epoch": 1.66, + "learning_rate": 7.24861976772448e-07, + "loss": 0.1272, + "step": 12994 + }, + { + "epoch": 1.66, + "learning_rate": 7.243245645314955e-07, + "loss": 0.1484, + "step": 12995 + }, + { + "epoch": 1.66, + "learning_rate": 7.23787336025838e-07, + "loss": 0.1374, + "step": 12996 + }, + { + "epoch": 1.66, + "learning_rate": 7.232502912785633e-07, + "loss": 0.153, + "step": 12997 + }, + { + "epoch": 1.66, + "learning_rate": 7.227134303127487e-07, + "loss": 0.1599, + "step": 12998 + }, + { + "epoch": 1.66, + "learning_rate": 7.22176753151464e-07, + "loss": 0.1462, + "step": 12999 + }, + { + "epoch": 1.66, + "learning_rate": 7.216402598177713e-07, + "loss": 0.1368, + "step": 13000 + }, + { + "epoch": 1.66, + "learning_rate": 7.21103950334725e-07, + "loss": 0.1316, + "step": 13001 + }, + { + "epoch": 1.66, + "learning_rate": 7.205678247253717e-07, + "loss": 0.1405, + "step": 13002 + }, + { + "epoch": 1.66, + "learning_rate": 7.200318830127495e-07, + "loss": 0.1447, + "step": 13003 + }, + { + "epoch": 1.66, + "learning_rate": 7.194961252198885e-07, + "loss": 0.1334, + "step": 13004 + }, + { + "epoch": 1.66, + "learning_rate": 7.189605513698139e-07, + "loss": 0.1358, + "step": 13005 + }, + { + "epoch": 1.66, + "learning_rate": 7.184251614855369e-07, + "loss": 0.1333, + "step": 13006 + }, + { + "epoch": 1.66, + "learning_rate": 7.178899555900675e-07, + "loss": 0.1401, + "step": 13007 + }, + { + "epoch": 1.67, + "learning_rate": 7.173549337064035e-07, + "loss": 0.1337, + "step": 13008 + }, + { + "epoch": 1.67, + "learning_rate": 7.168200958575361e-07, + "loss": 0.1348, + "step": 13009 + }, + { + "epoch": 1.67, + "learning_rate": 7.162854420664478e-07, + "loss": 0.1197, + "step": 13010 + }, + { + "epoch": 1.67, + "learning_rate": 7.157509723561134e-07, + "loss": 0.1339, + "step": 13011 + }, + { + "epoch": 1.67, + "learning_rate": 7.152166867495042e-07, + "loss": 0.1085, + "step": 13012 + }, + { + "epoch": 1.67, + "learning_rate": 7.146825852695749e-07, + "loss": 0.1314, + "step": 13013 + }, + { + "epoch": 1.67, + "learning_rate": 7.141486679392778e-07, + "loss": 0.1292, + "step": 13014 + }, + { + "epoch": 1.67, + "learning_rate": 7.136149347815591e-07, + "loss": 0.1271, + "step": 13015 + }, + { + "epoch": 1.67, + "learning_rate": 7.130813858193525e-07, + "loss": 0.1215, + "step": 13016 + }, + { + "epoch": 1.67, + "learning_rate": 7.125480210755858e-07, + "loss": 0.1412, + "step": 13017 + }, + { + "epoch": 1.67, + "learning_rate": 7.120148405731803e-07, + "loss": 0.15, + "step": 13018 + }, + { + "epoch": 1.67, + "learning_rate": 7.114818443350463e-07, + "loss": 0.125, + "step": 13019 + }, + { + "epoch": 1.67, + "learning_rate": 7.109490323840884e-07, + "loss": 0.1454, + "step": 13020 + }, + { + "epoch": 1.67, + "learning_rate": 7.104164047432022e-07, + "loss": 0.1391, + "step": 13021 + }, + { + "epoch": 1.67, + "learning_rate": 7.098839614352775e-07, + "loss": 0.117, + "step": 13022 + }, + { + "epoch": 1.67, + "learning_rate": 7.093517024831941e-07, + "loss": 0.1533, + "step": 13023 + }, + { + "epoch": 1.67, + "learning_rate": 7.088196279098225e-07, + "loss": 0.1337, + "step": 13024 + }, + { + "epoch": 1.67, + "learning_rate": 7.082877377380293e-07, + "loss": 0.127, + "step": 13025 + }, + { + "epoch": 1.67, + "learning_rate": 7.077560319906696e-07, + "loss": 0.1157, + "step": 13026 + }, + { + "epoch": 1.67, + "learning_rate": 7.072245106905928e-07, + "loss": 0.1262, + "step": 13027 + }, + { + "epoch": 1.67, + "learning_rate": 7.066931738606397e-07, + "loss": 0.1363, + "step": 13028 + }, + { + "epoch": 1.67, + "learning_rate": 7.061620215236415e-07, + "loss": 0.1324, + "step": 13029 + }, + { + "epoch": 1.67, + "learning_rate": 7.056310537024257e-07, + "loss": 0.1412, + "step": 13030 + }, + { + "epoch": 1.67, + "learning_rate": 7.051002704198074e-07, + "loss": 0.1313, + "step": 13031 + }, + { + "epoch": 1.67, + "learning_rate": 7.045696716985939e-07, + "loss": 0.1357, + "step": 13032 + }, + { + "epoch": 1.67, + "learning_rate": 7.040392575615896e-07, + "loss": 0.1358, + "step": 13033 + }, + { + "epoch": 1.67, + "learning_rate": 7.035090280315854e-07, + "loss": 0.1324, + "step": 13034 + }, + { + "epoch": 1.67, + "learning_rate": 7.029789831313677e-07, + "loss": 0.1412, + "step": 13035 + }, + { + "epoch": 1.67, + "learning_rate": 7.024491228837127e-07, + "loss": 0.1428, + "step": 13036 + }, + { + "epoch": 1.67, + "learning_rate": 7.0191944731139e-07, + "loss": 0.1314, + "step": 13037 + }, + { + "epoch": 1.67, + "learning_rate": 7.013899564371613e-07, + "loss": 0.1367, + "step": 13038 + }, + { + "epoch": 1.67, + "learning_rate": 7.008606502837784e-07, + "loss": 0.144, + "step": 13039 + }, + { + "epoch": 1.67, + "learning_rate": 7.003315288739893e-07, + "loss": 0.1314, + "step": 13040 + }, + { + "epoch": 1.67, + "learning_rate": 6.998025922305313e-07, + "loss": 0.1424, + "step": 13041 + }, + { + "epoch": 1.67, + "learning_rate": 6.992738403761307e-07, + "loss": 0.15, + "step": 13042 + }, + { + "epoch": 1.67, + "learning_rate": 6.987452733335126e-07, + "loss": 0.1289, + "step": 13043 + }, + { + "epoch": 1.67, + "learning_rate": 6.982168911253895e-07, + "loss": 0.135, + "step": 13044 + }, + { + "epoch": 1.67, + "learning_rate": 6.97688693774467e-07, + "loss": 0.1283, + "step": 13045 + }, + { + "epoch": 1.67, + "learning_rate": 6.971606813034432e-07, + "loss": 0.1318, + "step": 13046 + }, + { + "epoch": 1.67, + "learning_rate": 6.96632853735007e-07, + "loss": 0.1398, + "step": 13047 + }, + { + "epoch": 1.67, + "learning_rate": 6.961052110918432e-07, + "loss": 0.126, + "step": 13048 + }, + { + "epoch": 1.67, + "learning_rate": 6.955777533966212e-07, + "loss": 0.1258, + "step": 13049 + }, + { + "epoch": 1.67, + "learning_rate": 6.950504806720115e-07, + "loss": 0.1335, + "step": 13050 + }, + { + "epoch": 1.67, + "learning_rate": 6.945233929406697e-07, + "loss": 0.1368, + "step": 13051 + }, + { + "epoch": 1.67, + "learning_rate": 6.939964902252466e-07, + "loss": 0.1451, + "step": 13052 + }, + { + "epoch": 1.67, + "learning_rate": 6.934697725483846e-07, + "loss": 0.147, + "step": 13053 + }, + { + "epoch": 1.67, + "learning_rate": 6.929432399327174e-07, + "loss": 0.137, + "step": 13054 + }, + { + "epoch": 1.67, + "learning_rate": 6.924168924008712e-07, + "loss": 0.1313, + "step": 13055 + }, + { + "epoch": 1.67, + "learning_rate": 6.918907299754651e-07, + "loss": 0.1413, + "step": 13056 + }, + { + "epoch": 1.67, + "learning_rate": 6.913647526791078e-07, + "loss": 0.1218, + "step": 13057 + }, + { + "epoch": 1.67, + "learning_rate": 6.90838960534404e-07, + "loss": 0.1309, + "step": 13058 + }, + { + "epoch": 1.67, + "learning_rate": 6.903133535639467e-07, + "loss": 0.1358, + "step": 13059 + }, + { + "epoch": 1.67, + "learning_rate": 6.897879317903233e-07, + "loss": 0.1295, + "step": 13060 + }, + { + "epoch": 1.67, + "learning_rate": 6.89262695236112e-07, + "loss": 0.1473, + "step": 13061 + }, + { + "epoch": 1.67, + "learning_rate": 6.887376439238813e-07, + "loss": 0.1356, + "step": 13062 + }, + { + "epoch": 1.67, + "learning_rate": 6.882127778761987e-07, + "loss": 0.1337, + "step": 13063 + }, + { + "epoch": 1.67, + "learning_rate": 6.876880971156147e-07, + "loss": 0.1387, + "step": 13064 + }, + { + "epoch": 1.67, + "learning_rate": 6.871636016646754e-07, + "loss": 0.138, + "step": 13065 + }, + { + "epoch": 1.67, + "learning_rate": 6.866392915459241e-07, + "loss": 0.1393, + "step": 13066 + }, + { + "epoch": 1.67, + "learning_rate": 6.861151667818866e-07, + "loss": 0.1376, + "step": 13067 + }, + { + "epoch": 1.67, + "learning_rate": 6.855912273950893e-07, + "loss": 0.1344, + "step": 13068 + }, + { + "epoch": 1.67, + "learning_rate": 6.850674734080454e-07, + "loss": 0.1401, + "step": 13069 + }, + { + "epoch": 1.67, + "learning_rate": 6.845439048432617e-07, + "loss": 0.1361, + "step": 13070 + }, + { + "epoch": 1.67, + "learning_rate": 6.840205217232376e-07, + "loss": 0.1426, + "step": 13071 + }, + { + "epoch": 1.67, + "learning_rate": 6.834973240704629e-07, + "loss": 0.1281, + "step": 13072 + }, + { + "epoch": 1.67, + "learning_rate": 6.829743119074239e-07, + "loss": 0.1311, + "step": 13073 + }, + { + "epoch": 1.67, + "learning_rate": 6.824514852565922e-07, + "loss": 0.1383, + "step": 13074 + }, + { + "epoch": 1.67, + "learning_rate": 6.819288441404343e-07, + "loss": 0.1174, + "step": 13075 + }, + { + "epoch": 1.67, + "learning_rate": 6.814063885814127e-07, + "loss": 0.1301, + "step": 13076 + }, + { + "epoch": 1.67, + "learning_rate": 6.80884118601976e-07, + "loss": 0.1484, + "step": 13077 + }, + { + "epoch": 1.67, + "learning_rate": 6.803620342245676e-07, + "loss": 0.1391, + "step": 13078 + }, + { + "epoch": 1.67, + "learning_rate": 6.798401354716233e-07, + "loss": 0.1412, + "step": 13079 + }, + { + "epoch": 1.67, + "learning_rate": 6.793184223655691e-07, + "loss": 0.1281, + "step": 13080 + }, + { + "epoch": 1.67, + "learning_rate": 6.78796894928827e-07, + "loss": 0.1271, + "step": 13081 + }, + { + "epoch": 1.67, + "learning_rate": 6.782755531838047e-07, + "loss": 0.1313, + "step": 13082 + }, + { + "epoch": 1.67, + "learning_rate": 6.77754397152906e-07, + "loss": 0.1351, + "step": 13083 + }, + { + "epoch": 1.67, + "learning_rate": 6.772334268585296e-07, + "loss": 0.1455, + "step": 13084 + }, + { + "epoch": 1.67, + "learning_rate": 6.767126423230574e-07, + "loss": 0.1328, + "step": 13085 + }, + { + "epoch": 1.68, + "learning_rate": 6.76192043568873e-07, + "loss": 0.1383, + "step": 13086 + }, + { + "epoch": 1.68, + "learning_rate": 6.756716306183459e-07, + "loss": 0.1264, + "step": 13087 + }, + { + "epoch": 1.68, + "learning_rate": 6.751514034938395e-07, + "loss": 0.1323, + "step": 13088 + }, + { + "epoch": 1.68, + "learning_rate": 6.746313622177097e-07, + "loss": 0.1345, + "step": 13089 + }, + { + "epoch": 1.68, + "learning_rate": 6.741115068123017e-07, + "loss": 0.1462, + "step": 13090 + }, + { + "epoch": 1.68, + "learning_rate": 6.73591837299959e-07, + "loss": 0.1262, + "step": 13091 + }, + { + "epoch": 1.68, + "learning_rate": 6.730723537030092e-07, + "loss": 0.1486, + "step": 13092 + }, + { + "epoch": 1.68, + "learning_rate": 6.725530560437759e-07, + "loss": 0.1322, + "step": 13093 + }, + { + "epoch": 1.68, + "learning_rate": 6.720339443445772e-07, + "loss": 0.1231, + "step": 13094 + }, + { + "epoch": 1.68, + "learning_rate": 6.71515018627718e-07, + "loss": 0.1371, + "step": 13095 + }, + { + "epoch": 1.68, + "learning_rate": 6.709962789154989e-07, + "loss": 0.1341, + "step": 13096 + }, + { + "epoch": 1.68, + "learning_rate": 6.704777252302108e-07, + "loss": 0.1269, + "step": 13097 + }, + { + "epoch": 1.68, + "learning_rate": 6.699593575941365e-07, + "loss": 0.1278, + "step": 13098 + }, + { + "epoch": 1.68, + "learning_rate": 6.694411760295538e-07, + "loss": 0.1343, + "step": 13099 + }, + { + "epoch": 1.68, + "learning_rate": 6.689231805587265e-07, + "loss": 0.1232, + "step": 13100 + }, + { + "epoch": 1.68, + "learning_rate": 6.684053712039168e-07, + "loss": 0.1405, + "step": 13101 + }, + { + "epoch": 1.68, + "learning_rate": 6.678877479873769e-07, + "loss": 0.133, + "step": 13102 + }, + { + "epoch": 1.68, + "learning_rate": 6.673703109313456e-07, + "loss": 0.1282, + "step": 13103 + }, + { + "epoch": 1.68, + "learning_rate": 6.66853060058063e-07, + "loss": 0.121, + "step": 13104 + }, + { + "epoch": 1.68, + "learning_rate": 6.663359953897547e-07, + "loss": 0.1249, + "step": 13105 + }, + { + "epoch": 1.68, + "learning_rate": 6.658191169486405e-07, + "loss": 0.1412, + "step": 13106 + }, + { + "epoch": 1.68, + "learning_rate": 6.653024247569312e-07, + "loss": 0.1444, + "step": 13107 + }, + { + "epoch": 1.68, + "learning_rate": 6.647859188368294e-07, + "loss": 0.1383, + "step": 13108 + }, + { + "epoch": 1.68, + "learning_rate": 6.642695992105347e-07, + "loss": 0.1336, + "step": 13109 + }, + { + "epoch": 1.68, + "learning_rate": 6.637534659002287e-07, + "loss": 0.1292, + "step": 13110 + }, + { + "epoch": 1.68, + "learning_rate": 6.632375189280948e-07, + "loss": 0.1434, + "step": 13111 + }, + { + "epoch": 1.68, + "learning_rate": 6.627217583163031e-07, + "loss": 0.1289, + "step": 13112 + }, + { + "epoch": 1.68, + "learning_rate": 6.622061840870169e-07, + "loss": 0.1231, + "step": 13113 + }, + { + "epoch": 1.68, + "learning_rate": 6.61690796262392e-07, + "loss": 0.1345, + "step": 13114 + }, + { + "epoch": 1.68, + "learning_rate": 6.61175594864576e-07, + "loss": 0.1252, + "step": 13115 + }, + { + "epoch": 1.68, + "learning_rate": 6.606605799157062e-07, + "loss": 0.1404, + "step": 13116 + }, + { + "epoch": 1.68, + "learning_rate": 6.601457514379173e-07, + "loss": 0.1332, + "step": 13117 + }, + { + "epoch": 1.68, + "learning_rate": 6.596311094533292e-07, + "loss": 0.1309, + "step": 13118 + }, + { + "epoch": 1.68, + "learning_rate": 6.591166539840599e-07, + "loss": 0.132, + "step": 13119 + }, + { + "epoch": 1.68, + "learning_rate": 6.586023850522156e-07, + "loss": 0.1336, + "step": 13120 + }, + { + "epoch": 1.68, + "learning_rate": 6.580883026798957e-07, + "loss": 0.136, + "step": 13121 + }, + { + "epoch": 1.68, + "learning_rate": 6.575744068891909e-07, + "loss": 0.1327, + "step": 13122 + }, + { + "epoch": 1.68, + "learning_rate": 6.570606977021842e-07, + "loss": 0.134, + "step": 13123 + }, + { + "epoch": 1.68, + "learning_rate": 6.565471751409541e-07, + "loss": 0.1257, + "step": 13124 + }, + { + "epoch": 1.68, + "learning_rate": 6.56033839227564e-07, + "loss": 0.1287, + "step": 13125 + }, + { + "epoch": 1.68, + "learning_rate": 6.555206899840727e-07, + "loss": 0.1139, + "step": 13126 + }, + { + "epoch": 1.68, + "learning_rate": 6.550077274325345e-07, + "loss": 0.1353, + "step": 13127 + }, + { + "epoch": 1.68, + "learning_rate": 6.544949515949911e-07, + "loss": 0.1277, + "step": 13128 + }, + { + "epoch": 1.68, + "learning_rate": 6.539823624934777e-07, + "loss": 0.1327, + "step": 13129 + }, + { + "epoch": 1.68, + "learning_rate": 6.53469960150021e-07, + "loss": 0.124, + "step": 13130 + }, + { + "epoch": 1.68, + "learning_rate": 6.529577445866409e-07, + "loss": 0.1197, + "step": 13131 + }, + { + "epoch": 1.68, + "learning_rate": 6.524457158253472e-07, + "loss": 0.1357, + "step": 13132 + }, + { + "epoch": 1.68, + "learning_rate": 6.519338738881442e-07, + "loss": 0.1312, + "step": 13133 + }, + { + "epoch": 1.68, + "learning_rate": 6.514222187970248e-07, + "loss": 0.1482, + "step": 13134 + }, + { + "epoch": 1.68, + "learning_rate": 6.509107505739798e-07, + "loss": 0.1431, + "step": 13135 + }, + { + "epoch": 1.68, + "learning_rate": 6.503994692409838e-07, + "loss": 0.1316, + "step": 13136 + }, + { + "epoch": 1.68, + "learning_rate": 6.498883748200102e-07, + "loss": 0.1221, + "step": 13137 + }, + { + "epoch": 1.68, + "learning_rate": 6.493774673330217e-07, + "loss": 0.1445, + "step": 13138 + }, + { + "epoch": 1.68, + "learning_rate": 6.488667468019727e-07, + "loss": 0.1363, + "step": 13139 + }, + { + "epoch": 1.68, + "learning_rate": 6.483562132488103e-07, + "loss": 0.1307, + "step": 13140 + }, + { + "epoch": 1.68, + "learning_rate": 6.478458666954718e-07, + "loss": 0.1342, + "step": 13141 + }, + { + "epoch": 1.68, + "learning_rate": 6.473357071638914e-07, + "loss": 0.145, + "step": 13142 + }, + { + "epoch": 1.68, + "learning_rate": 6.468257346759888e-07, + "loss": 0.124, + "step": 13143 + }, + { + "epoch": 1.68, + "learning_rate": 6.46315949253678e-07, + "loss": 0.1402, + "step": 13144 + }, + { + "epoch": 1.68, + "learning_rate": 6.458063509188678e-07, + "loss": 0.1312, + "step": 13145 + }, + { + "epoch": 1.68, + "learning_rate": 6.452969396934567e-07, + "loss": 0.158, + "step": 13146 + }, + { + "epoch": 1.68, + "learning_rate": 6.447877155993343e-07, + "loss": 0.1335, + "step": 13147 + }, + { + "epoch": 1.68, + "learning_rate": 6.442786786583832e-07, + "loss": 0.1366, + "step": 13148 + }, + { + "epoch": 1.68, + "learning_rate": 6.437698288924777e-07, + "loss": 0.1349, + "step": 13149 + }, + { + "epoch": 1.68, + "learning_rate": 6.432611663234851e-07, + "loss": 0.1279, + "step": 13150 + }, + { + "epoch": 1.68, + "learning_rate": 6.427526909732617e-07, + "loss": 0.1397, + "step": 13151 + }, + { + "epoch": 1.68, + "learning_rate": 6.422444028636604e-07, + "loss": 0.1464, + "step": 13152 + }, + { + "epoch": 1.68, + "learning_rate": 6.417363020165235e-07, + "loss": 0.1332, + "step": 13153 + }, + { + "epoch": 1.68, + "learning_rate": 6.412283884536818e-07, + "loss": 0.1345, + "step": 13154 + }, + { + "epoch": 1.68, + "learning_rate": 6.407206621969648e-07, + "loss": 0.1377, + "step": 13155 + }, + { + "epoch": 1.68, + "learning_rate": 6.402131232681897e-07, + "loss": 0.131, + "step": 13156 + }, + { + "epoch": 1.68, + "learning_rate": 6.397057716891669e-07, + "loss": 0.1247, + "step": 13157 + }, + { + "epoch": 1.68, + "learning_rate": 6.391986074816975e-07, + "loss": 0.1242, + "step": 13158 + }, + { + "epoch": 1.68, + "learning_rate": 6.38691630667575e-07, + "loss": 0.1465, + "step": 13159 + }, + { + "epoch": 1.68, + "learning_rate": 6.381848412685882e-07, + "loss": 0.1209, + "step": 13160 + }, + { + "epoch": 1.68, + "learning_rate": 6.376782393065111e-07, + "loss": 0.126, + "step": 13161 + }, + { + "epoch": 1.68, + "learning_rate": 6.371718248031167e-07, + "loss": 0.1292, + "step": 13162 + }, + { + "epoch": 1.68, + "learning_rate": 6.36665597780165e-07, + "loss": 0.1271, + "step": 13163 + }, + { + "epoch": 1.68, + "learning_rate": 6.36159558259411e-07, + "loss": 0.1284, + "step": 13164 + }, + { + "epoch": 1.69, + "learning_rate": 6.35653706262599e-07, + "loss": 0.139, + "step": 13165 + }, + { + "epoch": 1.69, + "learning_rate": 6.351480418114675e-07, + "loss": 0.1287, + "step": 13166 + }, + { + "epoch": 1.69, + "learning_rate": 6.346425649277454e-07, + "loss": 0.1276, + "step": 13167 + }, + { + "epoch": 1.69, + "learning_rate": 6.341372756331543e-07, + "loss": 0.1348, + "step": 13168 + }, + { + "epoch": 1.69, + "learning_rate": 6.336321739494072e-07, + "loss": 0.1386, + "step": 13169 + }, + { + "epoch": 1.69, + "learning_rate": 6.331272598982108e-07, + "loss": 0.1313, + "step": 13170 + }, + { + "epoch": 1.69, + "learning_rate": 6.326225335012615e-07, + "loss": 0.1383, + "step": 13171 + }, + { + "epoch": 1.69, + "learning_rate": 6.321179947802492e-07, + "loss": 0.1288, + "step": 13172 + }, + { + "epoch": 1.69, + "learning_rate": 6.316136437568538e-07, + "loss": 0.1272, + "step": 13173 + }, + { + "epoch": 1.69, + "learning_rate": 6.31109480452749e-07, + "loss": 0.1282, + "step": 13174 + }, + { + "epoch": 1.69, + "learning_rate": 6.306055048896004e-07, + "loss": 0.1447, + "step": 13175 + }, + { + "epoch": 1.69, + "learning_rate": 6.301017170890639e-07, + "loss": 0.1521, + "step": 13176 + }, + { + "epoch": 1.69, + "learning_rate": 6.295981170727883e-07, + "loss": 0.141, + "step": 13177 + }, + { + "epoch": 1.69, + "learning_rate": 6.290947048624169e-07, + "loss": 0.1403, + "step": 13178 + }, + { + "epoch": 1.69, + "learning_rate": 6.285914804795784e-07, + "loss": 0.1122, + "step": 13179 + }, + { + "epoch": 1.69, + "learning_rate": 6.280884439459006e-07, + "loss": 0.1408, + "step": 13180 + }, + { + "epoch": 1.69, + "learning_rate": 6.275855952829995e-07, + "loss": 0.1536, + "step": 13181 + }, + { + "epoch": 1.69, + "learning_rate": 6.270829345124829e-07, + "loss": 0.1548, + "step": 13182 + }, + { + "epoch": 1.69, + "learning_rate": 6.265804616559518e-07, + "loss": 0.1379, + "step": 13183 + }, + { + "epoch": 1.69, + "learning_rate": 6.260781767349983e-07, + "loss": 0.1293, + "step": 13184 + }, + { + "epoch": 1.69, + "learning_rate": 6.255760797712068e-07, + "loss": 0.1357, + "step": 13185 + }, + { + "epoch": 1.69, + "learning_rate": 6.250741707861535e-07, + "loss": 0.1321, + "step": 13186 + }, + { + "epoch": 1.69, + "learning_rate": 6.245724498014055e-07, + "loss": 0.126, + "step": 13187 + }, + { + "epoch": 1.69, + "learning_rate": 6.240709168385251e-07, + "loss": 0.1243, + "step": 13188 + }, + { + "epoch": 1.69, + "learning_rate": 6.235695719190632e-07, + "loss": 0.1304, + "step": 13189 + }, + { + "epoch": 1.69, + "learning_rate": 6.230684150645633e-07, + "loss": 0.13, + "step": 13190 + }, + { + "epoch": 1.69, + "learning_rate": 6.22567446296562e-07, + "loss": 0.127, + "step": 13191 + }, + { + "epoch": 1.69, + "learning_rate": 6.220666656365865e-07, + "loss": 0.1292, + "step": 13192 + }, + { + "epoch": 1.69, + "learning_rate": 6.215660731061563e-07, + "loss": 0.1318, + "step": 13193 + }, + { + "epoch": 1.69, + "learning_rate": 6.210656687267835e-07, + "loss": 0.1352, + "step": 13194 + }, + { + "epoch": 1.69, + "learning_rate": 6.2056545251997e-07, + "loss": 0.1294, + "step": 13195 + }, + { + "epoch": 1.69, + "learning_rate": 6.200654245072146e-07, + "loss": 0.1392, + "step": 13196 + }, + { + "epoch": 1.69, + "learning_rate": 6.195655847100008e-07, + "loss": 0.1388, + "step": 13197 + }, + { + "epoch": 1.69, + "learning_rate": 6.1906593314981e-07, + "loss": 0.1236, + "step": 13198 + }, + { + "epoch": 1.69, + "learning_rate": 6.185664698481137e-07, + "loss": 0.128, + "step": 13199 + }, + { + "epoch": 1.69, + "learning_rate": 6.180671948263739e-07, + "loss": 0.1397, + "step": 13200 + }, + { + "epoch": 1.69, + "learning_rate": 6.175681081060453e-07, + "loss": 0.1343, + "step": 13201 + }, + { + "epoch": 1.69, + "learning_rate": 6.170692097085751e-07, + "loss": 0.1345, + "step": 13202 + }, + { + "epoch": 1.69, + "learning_rate": 6.165704996554039e-07, + "loss": 0.1335, + "step": 13203 + }, + { + "epoch": 1.69, + "learning_rate": 6.160719779679597e-07, + "loss": 0.1236, + "step": 13204 + }, + { + "epoch": 1.69, + "learning_rate": 6.155736446676652e-07, + "loss": 0.1252, + "step": 13205 + }, + { + "epoch": 1.69, + "learning_rate": 6.150754997759367e-07, + "loss": 0.1391, + "step": 13206 + }, + { + "epoch": 1.69, + "learning_rate": 6.145775433141798e-07, + "loss": 0.1397, + "step": 13207 + }, + { + "epoch": 1.69, + "learning_rate": 6.140797753037925e-07, + "loss": 0.1255, + "step": 13208 + }, + { + "epoch": 1.69, + "learning_rate": 6.135821957661658e-07, + "loss": 0.139, + "step": 13209 + }, + { + "epoch": 1.69, + "learning_rate": 6.130848047226806e-07, + "loss": 0.1436, + "step": 13210 + }, + { + "epoch": 1.69, + "learning_rate": 6.125876021947119e-07, + "loss": 0.1408, + "step": 13211 + }, + { + "epoch": 1.69, + "learning_rate": 6.120905882036244e-07, + "loss": 0.125, + "step": 13212 + }, + { + "epoch": 1.69, + "learning_rate": 6.115937627707775e-07, + "loss": 0.1379, + "step": 13213 + }, + { + "epoch": 1.69, + "learning_rate": 6.110971259175208e-07, + "loss": 0.132, + "step": 13214 + }, + { + "epoch": 1.69, + "learning_rate": 6.106006776651934e-07, + "loss": 0.1447, + "step": 13215 + }, + { + "epoch": 1.69, + "learning_rate": 6.101044180351318e-07, + "loss": 0.14, + "step": 13216 + }, + { + "epoch": 1.69, + "learning_rate": 6.096083470486602e-07, + "loss": 0.1415, + "step": 13217 + }, + { + "epoch": 1.69, + "learning_rate": 6.091124647270958e-07, + "loss": 0.1275, + "step": 13218 + }, + { + "epoch": 1.69, + "learning_rate": 6.086167710917479e-07, + "loss": 0.145, + "step": 13219 + }, + { + "epoch": 1.69, + "learning_rate": 6.081212661639163e-07, + "loss": 0.1284, + "step": 13220 + }, + { + "epoch": 1.69, + "learning_rate": 6.076259499648968e-07, + "loss": 0.126, + "step": 13221 + }, + { + "epoch": 1.69, + "learning_rate": 6.071308225159712e-07, + "loss": 0.1194, + "step": 13222 + }, + { + "epoch": 1.69, + "learning_rate": 6.066358838384184e-07, + "loss": 0.1185, + "step": 13223 + }, + { + "epoch": 1.69, + "learning_rate": 6.061411339535062e-07, + "loss": 0.1232, + "step": 13224 + }, + { + "epoch": 1.69, + "learning_rate": 6.056465728824951e-07, + "loss": 0.1342, + "step": 13225 + }, + { + "epoch": 1.69, + "learning_rate": 6.051522006466376e-07, + "loss": 0.1236, + "step": 13226 + }, + { + "epoch": 1.69, + "learning_rate": 6.046580172671773e-07, + "loss": 0.1439, + "step": 13227 + }, + { + "epoch": 1.69, + "learning_rate": 6.041640227653517e-07, + "loss": 0.156, + "step": 13228 + }, + { + "epoch": 1.69, + "learning_rate": 6.036702171623876e-07, + "loss": 0.1198, + "step": 13229 + }, + { + "epoch": 1.69, + "learning_rate": 6.031766004795047e-07, + "loss": 0.1398, + "step": 13230 + }, + { + "epoch": 1.69, + "learning_rate": 6.026831727379168e-07, + "loss": 0.1186, + "step": 13231 + }, + { + "epoch": 1.69, + "learning_rate": 6.021899339588266e-07, + "loss": 0.1291, + "step": 13232 + }, + { + "epoch": 1.69, + "learning_rate": 6.016968841634279e-07, + "loss": 0.1122, + "step": 13233 + }, + { + "epoch": 1.69, + "learning_rate": 6.012040233729105e-07, + "loss": 0.1232, + "step": 13234 + }, + { + "epoch": 1.69, + "learning_rate": 6.007113516084528e-07, + "loss": 0.1241, + "step": 13235 + }, + { + "epoch": 1.69, + "learning_rate": 6.002188688912264e-07, + "loss": 0.1293, + "step": 13236 + }, + { + "epoch": 1.69, + "learning_rate": 5.997265752423936e-07, + "loss": 0.1214, + "step": 13237 + }, + { + "epoch": 1.69, + "learning_rate": 5.992344706831088e-07, + "loss": 0.1311, + "step": 13238 + }, + { + "epoch": 1.69, + "learning_rate": 5.987425552345222e-07, + "loss": 0.1288, + "step": 13239 + }, + { + "epoch": 1.69, + "learning_rate": 5.98250828917768e-07, + "loss": 0.138, + "step": 13240 + }, + { + "epoch": 1.69, + "learning_rate": 5.977592917539799e-07, + "loss": 0.1296, + "step": 13241 + }, + { + "epoch": 1.69, + "learning_rate": 5.972679437642793e-07, + "loss": 0.1242, + "step": 13242 + }, + { + "epoch": 1.7, + "learning_rate": 5.967767849697803e-07, + "loss": 0.1351, + "step": 13243 + }, + { + "epoch": 1.7, + "learning_rate": 5.962858153915896e-07, + "loss": 0.1325, + "step": 13244 + }, + { + "epoch": 1.7, + "learning_rate": 5.957950350508052e-07, + "loss": 0.1453, + "step": 13245 + }, + { + "epoch": 1.7, + "learning_rate": 5.953044439685157e-07, + "loss": 0.1431, + "step": 13246 + }, + { + "epoch": 1.7, + "learning_rate": 5.948140421658061e-07, + "loss": 0.14, + "step": 13247 + }, + { + "epoch": 1.7, + "learning_rate": 5.943238296637455e-07, + "loss": 0.1316, + "step": 13248 + }, + { + "epoch": 1.7, + "learning_rate": 5.938338064834037e-07, + "loss": 0.1346, + "step": 13249 + }, + { + "epoch": 1.7, + "learning_rate": 5.933439726458357e-07, + "loss": 0.1412, + "step": 13250 + }, + { + "epoch": 1.7, + "learning_rate": 5.928543281720917e-07, + "loss": 0.1161, + "step": 13251 + }, + { + "epoch": 1.7, + "learning_rate": 5.923648730832121e-07, + "loss": 0.1317, + "step": 13252 + }, + { + "epoch": 1.7, + "learning_rate": 5.918756074002291e-07, + "loss": 0.1417, + "step": 13253 + }, + { + "epoch": 1.7, + "learning_rate": 5.913865311441714e-07, + "loss": 0.1426, + "step": 13254 + }, + { + "epoch": 1.7, + "learning_rate": 5.908976443360515e-07, + "loss": 0.136, + "step": 13255 + }, + { + "epoch": 1.7, + "learning_rate": 5.904089469968782e-07, + "loss": 0.1475, + "step": 13256 + }, + { + "epoch": 1.7, + "learning_rate": 5.899204391476554e-07, + "loss": 0.1238, + "step": 13257 + }, + { + "epoch": 1.7, + "learning_rate": 5.894321208093712e-07, + "loss": 0.1321, + "step": 13258 + }, + { + "epoch": 1.7, + "learning_rate": 5.889439920030127e-07, + "loss": 0.1207, + "step": 13259 + }, + { + "epoch": 1.7, + "learning_rate": 5.884560527495542e-07, + "loss": 0.1484, + "step": 13260 + }, + { + "epoch": 1.7, + "learning_rate": 5.879683030699645e-07, + "loss": 0.1244, + "step": 13261 + }, + { + "epoch": 1.7, + "learning_rate": 5.874807429852031e-07, + "loss": 0.1246, + "step": 13262 + }, + { + "epoch": 1.7, + "learning_rate": 5.869933725162203e-07, + "loss": 0.1407, + "step": 13263 + }, + { + "epoch": 1.7, + "learning_rate": 5.865061916839615e-07, + "loss": 0.1323, + "step": 13264 + }, + { + "epoch": 1.7, + "learning_rate": 5.860192005093624e-07, + "loss": 0.1372, + "step": 13265 + }, + { + "epoch": 1.7, + "learning_rate": 5.855323990133465e-07, + "loss": 0.1386, + "step": 13266 + }, + { + "epoch": 1.7, + "learning_rate": 5.850457872168358e-07, + "loss": 0.1262, + "step": 13267 + }, + { + "epoch": 1.7, + "learning_rate": 5.845593651407405e-07, + "loss": 0.1323, + "step": 13268 + }, + { + "epoch": 1.7, + "learning_rate": 5.840731328059629e-07, + "loss": 0.145, + "step": 13269 + }, + { + "epoch": 1.7, + "learning_rate": 5.835870902333974e-07, + "loss": 0.1367, + "step": 13270 + }, + { + "epoch": 1.7, + "learning_rate": 5.831012374439293e-07, + "loss": 0.1226, + "step": 13271 + }, + { + "epoch": 1.7, + "learning_rate": 5.826155744584405e-07, + "loss": 0.1455, + "step": 13272 + }, + { + "epoch": 1.7, + "learning_rate": 5.821301012977965e-07, + "loss": 0.1302, + "step": 13273 + }, + { + "epoch": 1.7, + "learning_rate": 5.816448179828616e-07, + "loss": 0.1304, + "step": 13274 + }, + { + "epoch": 1.7, + "learning_rate": 5.811597245344908e-07, + "loss": 0.1467, + "step": 13275 + }, + { + "epoch": 1.7, + "learning_rate": 5.806748209735252e-07, + "loss": 0.1414, + "step": 13276 + }, + { + "epoch": 1.7, + "learning_rate": 5.801901073208066e-07, + "loss": 0.1317, + "step": 13277 + }, + { + "epoch": 1.7, + "learning_rate": 5.797055835971621e-07, + "loss": 0.1531, + "step": 13278 + }, + { + "epoch": 1.7, + "learning_rate": 5.792212498234134e-07, + "loss": 0.1414, + "step": 13279 + }, + { + "epoch": 1.7, + "learning_rate": 5.787371060203728e-07, + "loss": 0.1107, + "step": 13280 + }, + { + "epoch": 1.7, + "learning_rate": 5.782531522088452e-07, + "loss": 0.1433, + "step": 13281 + }, + { + "epoch": 1.7, + "learning_rate": 5.777693884096275e-07, + "loss": 0.1297, + "step": 13282 + }, + { + "epoch": 1.7, + "learning_rate": 5.772858146435095e-07, + "loss": 0.1285, + "step": 13283 + }, + { + "epoch": 1.7, + "learning_rate": 5.768024309312681e-07, + "loss": 0.1337, + "step": 13284 + }, + { + "epoch": 1.7, + "learning_rate": 5.763192372936782e-07, + "loss": 0.1381, + "step": 13285 + }, + { + "epoch": 1.7, + "learning_rate": 5.758362337515028e-07, + "loss": 0.138, + "step": 13286 + }, + { + "epoch": 1.7, + "learning_rate": 5.753534203254973e-07, + "loss": 0.1472, + "step": 13287 + }, + { + "epoch": 1.7, + "learning_rate": 5.748707970364092e-07, + "loss": 0.1437, + "step": 13288 + }, + { + "epoch": 1.7, + "learning_rate": 5.74388363904978e-07, + "loss": 0.1256, + "step": 13289 + }, + { + "epoch": 1.7, + "learning_rate": 5.73906120951937e-07, + "loss": 0.1306, + "step": 13290 + }, + { + "epoch": 1.7, + "learning_rate": 5.734240681980052e-07, + "loss": 0.13, + "step": 13291 + }, + { + "epoch": 1.7, + "learning_rate": 5.729422056639006e-07, + "loss": 0.1243, + "step": 13292 + }, + { + "epoch": 1.7, + "learning_rate": 5.724605333703303e-07, + "loss": 0.1472, + "step": 13293 + }, + { + "epoch": 1.7, + "learning_rate": 5.719790513379891e-07, + "loss": 0.1506, + "step": 13294 + }, + { + "epoch": 1.7, + "learning_rate": 5.714977595875715e-07, + "loss": 0.1271, + "step": 13295 + }, + { + "epoch": 1.7, + "learning_rate": 5.710166581397575e-07, + "loss": 0.131, + "step": 13296 + }, + { + "epoch": 1.7, + "learning_rate": 5.705357470152218e-07, + "loss": 0.138, + "step": 13297 + }, + { + "epoch": 1.7, + "learning_rate": 5.700550262346294e-07, + "loss": 0.1255, + "step": 13298 + }, + { + "epoch": 1.7, + "learning_rate": 5.695744958186383e-07, + "loss": 0.1176, + "step": 13299 + }, + { + "epoch": 1.7, + "learning_rate": 5.690941557878988e-07, + "loss": 0.1318, + "step": 13300 + }, + { + "epoch": 1.7, + "learning_rate": 5.686140061630519e-07, + "loss": 0.151, + "step": 13301 + }, + { + "epoch": 1.7, + "learning_rate": 5.6813404696473e-07, + "loss": 0.1311, + "step": 13302 + }, + { + "epoch": 1.7, + "learning_rate": 5.676542782135585e-07, + "loss": 0.1371, + "step": 13303 + }, + { + "epoch": 1.7, + "learning_rate": 5.671746999301542e-07, + "loss": 0.1334, + "step": 13304 + }, + { + "epoch": 1.7, + "learning_rate": 5.666953121351254e-07, + "loss": 0.1271, + "step": 13305 + }, + { + "epoch": 1.7, + "learning_rate": 5.662161148490725e-07, + "loss": 0.1304, + "step": 13306 + }, + { + "epoch": 1.7, + "learning_rate": 5.657371080925866e-07, + "loss": 0.1422, + "step": 13307 + }, + { + "epoch": 1.7, + "learning_rate": 5.652582918862548e-07, + "loss": 0.1321, + "step": 13308 + }, + { + "epoch": 1.7, + "learning_rate": 5.647796662506493e-07, + "loss": 0.1364, + "step": 13309 + }, + { + "epoch": 1.7, + "learning_rate": 5.6430123120634e-07, + "loss": 0.1362, + "step": 13310 + }, + { + "epoch": 1.7, + "learning_rate": 5.638229867738854e-07, + "loss": 0.1388, + "step": 13311 + }, + { + "epoch": 1.7, + "learning_rate": 5.633449329738372e-07, + "loss": 0.1212, + "step": 13312 + }, + { + "epoch": 1.7, + "learning_rate": 5.628670698267386e-07, + "loss": 0.123, + "step": 13313 + }, + { + "epoch": 1.7, + "learning_rate": 5.623893973531225e-07, + "loss": 0.1254, + "step": 13314 + }, + { + "epoch": 1.7, + "learning_rate": 5.619119155735192e-07, + "loss": 0.1325, + "step": 13315 + }, + { + "epoch": 1.7, + "learning_rate": 5.61434624508444e-07, + "loss": 0.1355, + "step": 13316 + }, + { + "epoch": 1.7, + "learning_rate": 5.609575241784071e-07, + "loss": 0.1419, + "step": 13317 + }, + { + "epoch": 1.7, + "learning_rate": 5.604806146039126e-07, + "loss": 0.1322, + "step": 13318 + }, + { + "epoch": 1.7, + "learning_rate": 5.600038958054538e-07, + "loss": 0.1576, + "step": 13319 + }, + { + "epoch": 1.7, + "learning_rate": 5.595273678035156e-07, + "loss": 0.1203, + "step": 13320 + }, + { + "epoch": 1.71, + "learning_rate": 5.590510306185765e-07, + "loss": 0.1333, + "step": 13321 + }, + { + "epoch": 1.71, + "learning_rate": 5.585748842711047e-07, + "loss": 0.142, + "step": 13322 + }, + { + "epoch": 1.71, + "learning_rate": 5.580989287815619e-07, + "loss": 0.1409, + "step": 13323 + }, + { + "epoch": 1.71, + "learning_rate": 5.576231641703994e-07, + "loss": 0.1445, + "step": 13324 + }, + { + "epoch": 1.71, + "learning_rate": 5.571475904580648e-07, + "loss": 0.1295, + "step": 13325 + }, + { + "epoch": 1.71, + "learning_rate": 5.566722076649933e-07, + "loss": 0.1451, + "step": 13326 + }, + { + "epoch": 1.71, + "learning_rate": 5.561970158116114e-07, + "loss": 0.1384, + "step": 13327 + }, + { + "epoch": 1.71, + "learning_rate": 5.557220149183412e-07, + "loss": 0.1255, + "step": 13328 + }, + { + "epoch": 1.71, + "learning_rate": 5.552472050055946e-07, + "loss": 0.1257, + "step": 13329 + }, + { + "epoch": 1.71, + "learning_rate": 5.547725860937741e-07, + "loss": 0.1288, + "step": 13330 + }, + { + "epoch": 1.71, + "learning_rate": 5.542981582032759e-07, + "loss": 0.1396, + "step": 13331 + }, + { + "epoch": 1.71, + "learning_rate": 5.538239213544855e-07, + "loss": 0.1503, + "step": 13332 + }, + { + "epoch": 1.71, + "learning_rate": 5.533498755677857e-07, + "loss": 0.1492, + "step": 13333 + }, + { + "epoch": 1.71, + "learning_rate": 5.528760208635436e-07, + "loss": 0.1285, + "step": 13334 + }, + { + "epoch": 1.71, + "learning_rate": 5.524023572621229e-07, + "loss": 0.1539, + "step": 13335 + }, + { + "epoch": 1.71, + "learning_rate": 5.519288847838783e-07, + "loss": 0.1309, + "step": 13336 + }, + { + "epoch": 1.71, + "learning_rate": 5.514556034491569e-07, + "loss": 0.1493, + "step": 13337 + }, + { + "epoch": 1.71, + "learning_rate": 5.509825132782948e-07, + "loss": 0.1285, + "step": 13338 + }, + { + "epoch": 1.71, + "learning_rate": 5.505096142916233e-07, + "loss": 0.1443, + "step": 13339 + }, + { + "epoch": 1.71, + "learning_rate": 5.50036906509463e-07, + "loss": 0.1363, + "step": 13340 + }, + { + "epoch": 1.71, + "learning_rate": 5.495643899521269e-07, + "loss": 0.1323, + "step": 13341 + }, + { + "epoch": 1.71, + "learning_rate": 5.4909206463992e-07, + "loss": 0.1348, + "step": 13342 + }, + { + "epoch": 1.71, + "learning_rate": 5.486199305931411e-07, + "loss": 0.1454, + "step": 13343 + }, + { + "epoch": 1.71, + "learning_rate": 5.481479878320784e-07, + "loss": 0.1092, + "step": 13344 + }, + { + "epoch": 1.71, + "learning_rate": 5.476762363770088e-07, + "loss": 0.1299, + "step": 13345 + }, + { + "epoch": 1.71, + "learning_rate": 5.472046762482092e-07, + "loss": 0.1383, + "step": 13346 + }, + { + "epoch": 1.71, + "learning_rate": 5.467333074659409e-07, + "loss": 0.1251, + "step": 13347 + }, + { + "epoch": 1.71, + "learning_rate": 5.462621300504606e-07, + "loss": 0.1324, + "step": 13348 + }, + { + "epoch": 1.71, + "learning_rate": 5.457911440220154e-07, + "loss": 0.1295, + "step": 13349 + }, + { + "epoch": 1.71, + "learning_rate": 5.453203494008435e-07, + "loss": 0.1362, + "step": 13350 + }, + { + "epoch": 1.71, + "learning_rate": 5.4484974620718e-07, + "loss": 0.1299, + "step": 13351 + }, + { + "epoch": 1.71, + "learning_rate": 5.443793344612425e-07, + "loss": 0.1477, + "step": 13352 + }, + { + "epoch": 1.71, + "learning_rate": 5.439091141832498e-07, + "loss": 0.141, + "step": 13353 + }, + { + "epoch": 1.71, + "learning_rate": 5.434390853934063e-07, + "loss": 0.1273, + "step": 13354 + }, + { + "epoch": 1.71, + "learning_rate": 5.429692481119103e-07, + "loss": 0.1346, + "step": 13355 + }, + { + "epoch": 1.71, + "learning_rate": 5.424996023589524e-07, + "loss": 0.1378, + "step": 13356 + }, + { + "epoch": 1.71, + "learning_rate": 5.420301481547141e-07, + "loss": 0.1356, + "step": 13357 + }, + { + "epoch": 1.71, + "learning_rate": 5.415608855193688e-07, + "loss": 0.1335, + "step": 13358 + }, + { + "epoch": 1.71, + "learning_rate": 5.410918144730815e-07, + "loss": 0.134, + "step": 13359 + }, + { + "epoch": 1.71, + "learning_rate": 5.406229350360087e-07, + "loss": 0.131, + "step": 13360 + }, + { + "epoch": 1.71, + "learning_rate": 5.401542472283006e-07, + "loss": 0.1462, + "step": 13361 + }, + { + "epoch": 1.71, + "learning_rate": 5.39685751070097e-07, + "loss": 0.1176, + "step": 13362 + }, + { + "epoch": 1.71, + "learning_rate": 5.392174465815308e-07, + "loss": 0.1256, + "step": 13363 + }, + { + "epoch": 1.71, + "learning_rate": 5.387493337827254e-07, + "loss": 0.1331, + "step": 13364 + }, + { + "epoch": 1.71, + "learning_rate": 5.382814126937969e-07, + "loss": 0.1417, + "step": 13365 + }, + { + "epoch": 1.71, + "learning_rate": 5.378136833348529e-07, + "loss": 0.1307, + "step": 13366 + }, + { + "epoch": 1.71, + "learning_rate": 5.373461457259926e-07, + "loss": 0.1347, + "step": 13367 + }, + { + "epoch": 1.71, + "learning_rate": 5.368787998873065e-07, + "loss": 0.1345, + "step": 13368 + }, + { + "epoch": 1.71, + "learning_rate": 5.364116458388802e-07, + "loss": 0.1263, + "step": 13369 + }, + { + "epoch": 1.71, + "learning_rate": 5.359446836007842e-07, + "loss": 0.1406, + "step": 13370 + }, + { + "epoch": 1.71, + "learning_rate": 5.354779131930882e-07, + "loss": 0.1353, + "step": 13371 + }, + { + "epoch": 1.71, + "learning_rate": 5.350113346358493e-07, + "loss": 0.1279, + "step": 13372 + }, + { + "epoch": 1.71, + "learning_rate": 5.345449479491177e-07, + "loss": 0.1154, + "step": 13373 + }, + { + "epoch": 1.71, + "learning_rate": 5.340787531529346e-07, + "loss": 0.1319, + "step": 13374 + }, + { + "epoch": 1.71, + "learning_rate": 5.336127502673328e-07, + "loss": 0.136, + "step": 13375 + }, + { + "epoch": 1.71, + "learning_rate": 5.331469393123401e-07, + "loss": 0.1444, + "step": 13376 + }, + { + "epoch": 1.71, + "learning_rate": 5.326813203079706e-07, + "loss": 0.1291, + "step": 13377 + }, + { + "epoch": 1.71, + "learning_rate": 5.322158932742328e-07, + "loss": 0.1381, + "step": 13378 + }, + { + "epoch": 1.71, + "learning_rate": 5.3175065823113e-07, + "loss": 0.1365, + "step": 13379 + }, + { + "epoch": 1.71, + "learning_rate": 5.312856151986523e-07, + "loss": 0.1283, + "step": 13380 + }, + { + "epoch": 1.71, + "learning_rate": 5.308207641967839e-07, + "loss": 0.1379, + "step": 13381 + }, + { + "epoch": 1.71, + "learning_rate": 5.303561052455009e-07, + "loss": 0.1221, + "step": 13382 + }, + { + "epoch": 1.71, + "learning_rate": 5.298916383647695e-07, + "loss": 0.1283, + "step": 13383 + }, + { + "epoch": 1.71, + "learning_rate": 5.294273635745517e-07, + "loss": 0.1251, + "step": 13384 + }, + { + "epoch": 1.71, + "learning_rate": 5.289632808947959e-07, + "loss": 0.1394, + "step": 13385 + }, + { + "epoch": 1.71, + "learning_rate": 5.284993903454444e-07, + "loss": 0.124, + "step": 13386 + }, + { + "epoch": 1.71, + "learning_rate": 5.280356919464341e-07, + "loss": 0.1117, + "step": 13387 + }, + { + "epoch": 1.71, + "learning_rate": 5.275721857176885e-07, + "loss": 0.1401, + "step": 13388 + }, + { + "epoch": 1.71, + "learning_rate": 5.271088716791273e-07, + "loss": 0.1284, + "step": 13389 + }, + { + "epoch": 1.71, + "learning_rate": 5.266457498506594e-07, + "loss": 0.1216, + "step": 13390 + }, + { + "epoch": 1.71, + "learning_rate": 5.261828202521868e-07, + "loss": 0.1256, + "step": 13391 + }, + { + "epoch": 1.71, + "learning_rate": 5.257200829036018e-07, + "loss": 0.1204, + "step": 13392 + }, + { + "epoch": 1.71, + "learning_rate": 5.252575378247887e-07, + "loss": 0.1279, + "step": 13393 + }, + { + "epoch": 1.71, + "learning_rate": 5.24795185035627e-07, + "loss": 0.144, + "step": 13394 + }, + { + "epoch": 1.71, + "learning_rate": 5.243330245559819e-07, + "loss": 0.1385, + "step": 13395 + }, + { + "epoch": 1.71, + "learning_rate": 5.238710564057137e-07, + "loss": 0.1413, + "step": 13396 + }, + { + "epoch": 1.71, + "learning_rate": 5.234092806046759e-07, + "loss": 0.1293, + "step": 13397 + }, + { + "epoch": 1.71, + "learning_rate": 5.229476971727115e-07, + "loss": 0.1311, + "step": 13398 + }, + { + "epoch": 1.72, + "learning_rate": 5.224863061296553e-07, + "loss": 0.1275, + "step": 13399 + }, + { + "epoch": 1.72, + "learning_rate": 5.220251074953348e-07, + "loss": 0.1327, + "step": 13400 + }, + { + "epoch": 1.72, + "learning_rate": 5.215641012895667e-07, + "loss": 0.1264, + "step": 13401 + }, + { + "epoch": 1.72, + "learning_rate": 5.211032875321659e-07, + "loss": 0.1348, + "step": 13402 + }, + { + "epoch": 1.72, + "learning_rate": 5.206426662429298e-07, + "loss": 0.1271, + "step": 13403 + }, + { + "epoch": 1.72, + "learning_rate": 5.201822374416549e-07, + "loss": 0.1324, + "step": 13404 + }, + { + "epoch": 1.72, + "learning_rate": 5.197220011481274e-07, + "loss": 0.1379, + "step": 13405 + }, + { + "epoch": 1.72, + "learning_rate": 5.192619573821223e-07, + "loss": 0.1323, + "step": 13406 + }, + { + "epoch": 1.72, + "learning_rate": 5.188021061634102e-07, + "loss": 0.1279, + "step": 13407 + }, + { + "epoch": 1.72, + "learning_rate": 5.183424475117521e-07, + "loss": 0.1383, + "step": 13408 + }, + { + "epoch": 1.72, + "learning_rate": 5.178829814469006e-07, + "loss": 0.1349, + "step": 13409 + }, + { + "epoch": 1.72, + "learning_rate": 5.174237079885991e-07, + "loss": 0.1169, + "step": 13410 + }, + { + "epoch": 1.72, + "learning_rate": 5.169646271565831e-07, + "loss": 0.1399, + "step": 13411 + }, + { + "epoch": 1.72, + "learning_rate": 5.165057389705835e-07, + "loss": 0.1379, + "step": 13412 + }, + { + "epoch": 1.72, + "learning_rate": 5.160470434503156e-07, + "loss": 0.1244, + "step": 13413 + }, + { + "epoch": 1.72, + "learning_rate": 5.155885406154937e-07, + "loss": 0.1423, + "step": 13414 + }, + { + "epoch": 1.72, + "learning_rate": 5.151302304858192e-07, + "loss": 0.1316, + "step": 13415 + }, + { + "epoch": 1.72, + "learning_rate": 5.146721130809873e-07, + "loss": 0.1389, + "step": 13416 + }, + { + "epoch": 1.72, + "learning_rate": 5.142141884206842e-07, + "loss": 0.1309, + "step": 13417 + }, + { + "epoch": 1.72, + "learning_rate": 5.137564565245873e-07, + "loss": 0.1265, + "step": 13418 + }, + { + "epoch": 1.72, + "learning_rate": 5.132989174123659e-07, + "loss": 0.1292, + "step": 13419 + }, + { + "epoch": 1.72, + "learning_rate": 5.128415711036849e-07, + "loss": 0.1222, + "step": 13420 + }, + { + "epoch": 1.72, + "learning_rate": 5.12384417618193e-07, + "loss": 0.1438, + "step": 13421 + }, + { + "epoch": 1.72, + "learning_rate": 5.119274569755378e-07, + "loss": 0.1326, + "step": 13422 + }, + { + "epoch": 1.72, + "learning_rate": 5.114706891953552e-07, + "loss": 0.1327, + "step": 13423 + }, + { + "epoch": 1.72, + "learning_rate": 5.110141142972735e-07, + "loss": 0.1333, + "step": 13424 + }, + { + "epoch": 1.72, + "learning_rate": 5.105577323009131e-07, + "loss": 0.1192, + "step": 13425 + }, + { + "epoch": 1.72, + "learning_rate": 5.101015432258843e-07, + "loss": 0.1337, + "step": 13426 + }, + { + "epoch": 1.72, + "learning_rate": 5.096455470917943e-07, + "loss": 0.1339, + "step": 13427 + }, + { + "epoch": 1.72, + "learning_rate": 5.091897439182342e-07, + "loss": 0.1354, + "step": 13428 + }, + { + "epoch": 1.72, + "learning_rate": 5.087341337247914e-07, + "loss": 0.1262, + "step": 13429 + }, + { + "epoch": 1.72, + "learning_rate": 5.082787165310471e-07, + "loss": 0.1302, + "step": 13430 + }, + { + "epoch": 1.72, + "learning_rate": 5.078234923565684e-07, + "loss": 0.1238, + "step": 13431 + }, + { + "epoch": 1.72, + "learning_rate": 5.073684612209201e-07, + "loss": 0.1473, + "step": 13432 + }, + { + "epoch": 1.72, + "learning_rate": 5.069136231436539e-07, + "loss": 0.1236, + "step": 13433 + }, + { + "epoch": 1.72, + "learning_rate": 5.064589781443163e-07, + "loss": 0.1276, + "step": 13434 + }, + { + "epoch": 1.72, + "learning_rate": 5.060045262424446e-07, + "loss": 0.1346, + "step": 13435 + }, + { + "epoch": 1.72, + "learning_rate": 5.055502674575663e-07, + "loss": 0.1416, + "step": 13436 + }, + { + "epoch": 1.72, + "learning_rate": 5.05096201809202e-07, + "loss": 0.1293, + "step": 13437 + }, + { + "epoch": 1.72, + "learning_rate": 5.046423293168667e-07, + "loss": 0.1413, + "step": 13438 + }, + { + "epoch": 1.72, + "learning_rate": 5.041886500000603e-07, + "loss": 0.1429, + "step": 13439 + }, + { + "epoch": 1.72, + "learning_rate": 5.037351638782812e-07, + "loss": 0.1345, + "step": 13440 + }, + { + "epoch": 1.72, + "learning_rate": 5.032818709710152e-07, + "loss": 0.1369, + "step": 13441 + }, + { + "epoch": 1.72, + "learning_rate": 5.028287712977425e-07, + "loss": 0.1291, + "step": 13442 + }, + { + "epoch": 1.72, + "learning_rate": 5.023758648779336e-07, + "loss": 0.129, + "step": 13443 + }, + { + "epoch": 1.72, + "learning_rate": 5.019231517310491e-07, + "loss": 0.1358, + "step": 13444 + }, + { + "epoch": 1.72, + "learning_rate": 5.014706318765466e-07, + "loss": 0.1415, + "step": 13445 + }, + { + "epoch": 1.72, + "learning_rate": 5.010183053338685e-07, + "loss": 0.1326, + "step": 13446 + }, + { + "epoch": 1.72, + "learning_rate": 5.00566172122453e-07, + "loss": 0.1293, + "step": 13447 + }, + { + "epoch": 1.72, + "learning_rate": 5.001142322617314e-07, + "loss": 0.1281, + "step": 13448 + }, + { + "epoch": 1.72, + "learning_rate": 4.996624857711219e-07, + "loss": 0.122, + "step": 13449 + }, + { + "epoch": 1.72, + "learning_rate": 4.992109326700384e-07, + "loss": 0.1287, + "step": 13450 + }, + { + "epoch": 1.72, + "learning_rate": 4.987595729778849e-07, + "loss": 0.1563, + "step": 13451 + }, + { + "epoch": 1.72, + "learning_rate": 4.983084067140575e-07, + "loss": 0.1251, + "step": 13452 + }, + { + "epoch": 1.72, + "learning_rate": 4.978574338979442e-07, + "loss": 0.1315, + "step": 13453 + }, + { + "epoch": 1.72, + "learning_rate": 4.97406654548922e-07, + "loss": 0.1496, + "step": 13454 + }, + { + "epoch": 1.72, + "learning_rate": 4.96956068686365e-07, + "loss": 0.1294, + "step": 13455 + }, + { + "epoch": 1.72, + "learning_rate": 4.965056763296356e-07, + "loss": 0.1415, + "step": 13456 + }, + { + "epoch": 1.72, + "learning_rate": 4.960554774980853e-07, + "loss": 0.1388, + "step": 13457 + }, + { + "epoch": 1.72, + "learning_rate": 4.956054722110626e-07, + "loss": 0.1123, + "step": 13458 + }, + { + "epoch": 1.72, + "learning_rate": 4.951556604879049e-07, + "loss": 0.1334, + "step": 13459 + }, + { + "epoch": 1.72, + "learning_rate": 4.94706042347941e-07, + "loss": 0.1309, + "step": 13460 + }, + { + "epoch": 1.72, + "learning_rate": 4.942566178104924e-07, + "loss": 0.1427, + "step": 13461 + }, + { + "epoch": 1.72, + "learning_rate": 4.938073868948707e-07, + "loss": 0.1265, + "step": 13462 + }, + { + "epoch": 1.72, + "learning_rate": 4.933583496203831e-07, + "loss": 0.1276, + "step": 13463 + }, + { + "epoch": 1.72, + "learning_rate": 4.929095060063227e-07, + "loss": 0.1434, + "step": 13464 + }, + { + "epoch": 1.72, + "learning_rate": 4.92460856071979e-07, + "loss": 0.1394, + "step": 13465 + }, + { + "epoch": 1.72, + "learning_rate": 4.920123998366327e-07, + "loss": 0.13, + "step": 13466 + }, + { + "epoch": 1.72, + "learning_rate": 4.915641373195512e-07, + "loss": 0.1469, + "step": 13467 + }, + { + "epoch": 1.72, + "learning_rate": 4.911160685400008e-07, + "loss": 0.1281, + "step": 13468 + }, + { + "epoch": 1.72, + "learning_rate": 4.906681935172342e-07, + "loss": 0.139, + "step": 13469 + }, + { + "epoch": 1.72, + "learning_rate": 4.902205122704983e-07, + "loss": 0.1396, + "step": 13470 + }, + { + "epoch": 1.72, + "learning_rate": 4.897730248190313e-07, + "loss": 0.1211, + "step": 13471 + }, + { + "epoch": 1.72, + "learning_rate": 4.893257311820609e-07, + "loss": 0.148, + "step": 13472 + }, + { + "epoch": 1.72, + "learning_rate": 4.888786313788108e-07, + "loss": 0.1317, + "step": 13473 + }, + { + "epoch": 1.72, + "learning_rate": 4.88431725428492e-07, + "loss": 0.1316, + "step": 13474 + }, + { + "epoch": 1.72, + "learning_rate": 4.879850133503106e-07, + "loss": 0.1233, + "step": 13475 + }, + { + "epoch": 1.72, + "learning_rate": 4.875384951634616e-07, + "loss": 0.1501, + "step": 13476 + }, + { + "epoch": 1.73, + "learning_rate": 4.870921708871334e-07, + "loss": 0.1309, + "step": 13477 + }, + { + "epoch": 1.73, + "learning_rate": 4.866460405405054e-07, + "loss": 0.1177, + "step": 13478 + }, + { + "epoch": 1.73, + "learning_rate": 4.862001041427488e-07, + "loss": 0.1261, + "step": 13479 + }, + { + "epoch": 1.73, + "learning_rate": 4.857543617130256e-07, + "loss": 0.1133, + "step": 13480 + }, + { + "epoch": 1.73, + "learning_rate": 4.85308813270493e-07, + "loss": 0.1247, + "step": 13481 + }, + { + "epoch": 1.73, + "learning_rate": 4.848634588342932e-07, + "loss": 0.1469, + "step": 13482 + }, + { + "epoch": 1.73, + "learning_rate": 4.844182984235679e-07, + "loss": 0.1381, + "step": 13483 + }, + { + "epoch": 1.73, + "learning_rate": 4.839733320574457e-07, + "loss": 0.1188, + "step": 13484 + }, + { + "epoch": 1.73, + "learning_rate": 4.835285597550454e-07, + "loss": 0.1332, + "step": 13485 + }, + { + "epoch": 1.73, + "learning_rate": 4.830839815354827e-07, + "loss": 0.137, + "step": 13486 + }, + { + "epoch": 1.73, + "learning_rate": 4.826395974178605e-07, + "loss": 0.1234, + "step": 13487 + }, + { + "epoch": 1.73, + "learning_rate": 4.821954074212759e-07, + "loss": 0.1397, + "step": 13488 + }, + { + "epoch": 1.73, + "learning_rate": 4.817514115648164e-07, + "loss": 0.1294, + "step": 13489 + }, + { + "epoch": 1.73, + "learning_rate": 4.813076098675601e-07, + "loss": 0.1406, + "step": 13490 + }, + { + "epoch": 1.73, + "learning_rate": 4.808640023485805e-07, + "loss": 0.1303, + "step": 13491 + }, + { + "epoch": 1.73, + "learning_rate": 4.804205890269398e-07, + "loss": 0.1298, + "step": 13492 + }, + { + "epoch": 1.73, + "learning_rate": 4.799773699216914e-07, + "loss": 0.1362, + "step": 13493 + }, + { + "epoch": 1.73, + "learning_rate": 4.795343450518825e-07, + "loss": 0.1245, + "step": 13494 + }, + { + "epoch": 1.73, + "learning_rate": 4.790915144365504e-07, + "loss": 0.1328, + "step": 13495 + }, + { + "epoch": 1.73, + "learning_rate": 4.786488780947246e-07, + "loss": 0.1304, + "step": 13496 + }, + { + "epoch": 1.73, + "learning_rate": 4.782064360454258e-07, + "loss": 0.1251, + "step": 13497 + }, + { + "epoch": 1.73, + "learning_rate": 4.777641883076661e-07, + "loss": 0.1312, + "step": 13498 + }, + { + "epoch": 1.73, + "learning_rate": 4.773221349004531e-07, + "loss": 0.1276, + "step": 13499 + }, + { + "epoch": 1.73, + "learning_rate": 4.768802758427782e-07, + "loss": 0.1397, + "step": 13500 + }, + { + "epoch": 1.73, + "learning_rate": 4.7643861115363234e-07, + "loss": 0.1401, + "step": 13501 + }, + { + "epoch": 1.73, + "learning_rate": 4.759971408519937e-07, + "loss": 0.1287, + "step": 13502 + }, + { + "epoch": 1.73, + "learning_rate": 4.755558649568337e-07, + "loss": 0.1348, + "step": 13503 + }, + { + "epoch": 1.73, + "learning_rate": 4.7511478348711447e-07, + "loss": 0.1209, + "step": 13504 + }, + { + "epoch": 1.73, + "learning_rate": 4.7467389646178976e-07, + "loss": 0.1149, + "step": 13505 + }, + { + "epoch": 1.73, + "learning_rate": 4.742332038998082e-07, + "loss": 0.1252, + "step": 13506 + }, + { + "epoch": 1.73, + "learning_rate": 4.7379270582010416e-07, + "loss": 0.1339, + "step": 13507 + }, + { + "epoch": 1.73, + "learning_rate": 4.7335240224160695e-07, + "loss": 0.1269, + "step": 13508 + }, + { + "epoch": 1.73, + "learning_rate": 4.729122931832392e-07, + "loss": 0.1281, + "step": 13509 + }, + { + "epoch": 1.73, + "learning_rate": 4.7247237866391236e-07, + "loss": 0.1408, + "step": 13510 + }, + { + "epoch": 1.73, + "learning_rate": 4.7203265870253144e-07, + "loss": 0.1303, + "step": 13511 + }, + { + "epoch": 1.73, + "learning_rate": 4.715931333179913e-07, + "loss": 0.1356, + "step": 13512 + }, + { + "epoch": 1.73, + "learning_rate": 4.7115380252917897e-07, + "loss": 0.1277, + "step": 13513 + }, + { + "epoch": 1.73, + "learning_rate": 4.707146663549744e-07, + "loss": 0.1277, + "step": 13514 + }, + { + "epoch": 1.73, + "learning_rate": 4.7027572481424753e-07, + "loss": 0.1455, + "step": 13515 + }, + { + "epoch": 1.73, + "learning_rate": 4.6983697792586103e-07, + "loss": 0.1386, + "step": 13516 + }, + { + "epoch": 1.73, + "learning_rate": 4.6939842570867034e-07, + "loss": 0.131, + "step": 13517 + }, + { + "epoch": 1.73, + "learning_rate": 4.6896006818151706e-07, + "loss": 0.1393, + "step": 13518 + }, + { + "epoch": 1.73, + "learning_rate": 4.685219053632423e-07, + "loss": 0.1228, + "step": 13519 + }, + { + "epoch": 1.73, + "learning_rate": 4.6808393727267307e-07, + "loss": 0.1246, + "step": 13520 + }, + { + "epoch": 1.73, + "learning_rate": 4.676461639286306e-07, + "loss": 0.131, + "step": 13521 + }, + { + "epoch": 1.73, + "learning_rate": 4.6720858534992584e-07, + "loss": 0.1427, + "step": 13522 + }, + { + "epoch": 1.73, + "learning_rate": 4.667712015553627e-07, + "loss": 0.1224, + "step": 13523 + }, + { + "epoch": 1.73, + "learning_rate": 4.663340125637389e-07, + "loss": 0.1243, + "step": 13524 + }, + { + "epoch": 1.73, + "learning_rate": 4.658970183938383e-07, + "loss": 0.1381, + "step": 13525 + }, + { + "epoch": 1.73, + "learning_rate": 4.654602190644408e-07, + "loss": 0.1322, + "step": 13526 + }, + { + "epoch": 1.73, + "learning_rate": 4.650236145943171e-07, + "loss": 0.1277, + "step": 13527 + }, + { + "epoch": 1.73, + "learning_rate": 4.6458720500222873e-07, + "loss": 0.1226, + "step": 13528 + }, + { + "epoch": 1.73, + "learning_rate": 4.6415099030692914e-07, + "loss": 0.1204, + "step": 13529 + }, + { + "epoch": 1.73, + "learning_rate": 4.6371497052716265e-07, + "loss": 0.1446, + "step": 13530 + }, + { + "epoch": 1.73, + "learning_rate": 4.6327914568166763e-07, + "loss": 0.1303, + "step": 13531 + }, + { + "epoch": 1.73, + "learning_rate": 4.628435157891709e-07, + "loss": 0.1162, + "step": 13532 + }, + { + "epoch": 1.73, + "learning_rate": 4.624080808683923e-07, + "loss": 0.1349, + "step": 13533 + }, + { + "epoch": 1.73, + "learning_rate": 4.619728409380453e-07, + "loss": 0.1232, + "step": 13534 + }, + { + "epoch": 1.73, + "learning_rate": 4.615377960168321e-07, + "loss": 0.1254, + "step": 13535 + }, + { + "epoch": 1.73, + "learning_rate": 4.611029461234473e-07, + "loss": 0.1242, + "step": 13536 + }, + { + "epoch": 1.73, + "learning_rate": 4.6066829127657807e-07, + "loss": 0.1285, + "step": 13537 + }, + { + "epoch": 1.73, + "learning_rate": 4.6023383149490066e-07, + "loss": 0.129, + "step": 13538 + }, + { + "epoch": 1.73, + "learning_rate": 4.597995667970878e-07, + "loss": 0.1335, + "step": 13539 + }, + { + "epoch": 1.73, + "learning_rate": 4.5936549720179855e-07, + "loss": 0.1315, + "step": 13540 + }, + { + "epoch": 1.73, + "learning_rate": 4.589316227276852e-07, + "loss": 0.1513, + "step": 13541 + }, + { + "epoch": 1.73, + "learning_rate": 4.584979433933956e-07, + "loss": 0.1143, + "step": 13542 + }, + { + "epoch": 1.73, + "learning_rate": 4.5806445921756146e-07, + "loss": 0.1145, + "step": 13543 + }, + { + "epoch": 1.73, + "learning_rate": 4.5763117021881467e-07, + "loss": 0.1306, + "step": 13544 + }, + { + "epoch": 1.73, + "learning_rate": 4.571980764157724e-07, + "loss": 0.135, + "step": 13545 + }, + { + "epoch": 1.73, + "learning_rate": 4.567651778270465e-07, + "loss": 0.1431, + "step": 13546 + }, + { + "epoch": 1.73, + "learning_rate": 4.563324744712389e-07, + "loss": 0.1256, + "step": 13547 + }, + { + "epoch": 1.73, + "learning_rate": 4.5589996636694387e-07, + "loss": 0.1173, + "step": 13548 + }, + { + "epoch": 1.73, + "learning_rate": 4.5546765353274846e-07, + "loss": 0.1358, + "step": 13549 + }, + { + "epoch": 1.73, + "learning_rate": 4.5503553598722826e-07, + "loss": 0.1293, + "step": 13550 + }, + { + "epoch": 1.73, + "learning_rate": 4.546036137489529e-07, + "loss": 0.1418, + "step": 13551 + }, + { + "epoch": 1.73, + "learning_rate": 4.5417188683648417e-07, + "loss": 0.1301, + "step": 13552 + }, + { + "epoch": 1.73, + "learning_rate": 4.5374035526837334e-07, + "loss": 0.1319, + "step": 13553 + }, + { + "epoch": 1.73, + "learning_rate": 4.5330901906316506e-07, + "loss": 0.1382, + "step": 13554 + }, + { + "epoch": 1.74, + "learning_rate": 4.528778782393939e-07, + "loss": 0.1309, + "step": 13555 + }, + { + "epoch": 1.74, + "learning_rate": 4.5244693281558615e-07, + "loss": 0.1205, + "step": 13556 + }, + { + "epoch": 1.74, + "learning_rate": 4.5201618281026374e-07, + "loss": 0.1311, + "step": 13557 + }, + { + "epoch": 1.74, + "learning_rate": 4.5158562824193395e-07, + "loss": 0.1304, + "step": 13558 + }, + { + "epoch": 1.74, + "learning_rate": 4.511552691290988e-07, + "loss": 0.1401, + "step": 13559 + }, + { + "epoch": 1.74, + "learning_rate": 4.507251054902539e-07, + "loss": 0.1366, + "step": 13560 + }, + { + "epoch": 1.74, + "learning_rate": 4.5029513734388187e-07, + "loss": 0.1374, + "step": 13561 + }, + { + "epoch": 1.74, + "learning_rate": 4.498653647084611e-07, + "loss": 0.1262, + "step": 13562 + }, + { + "epoch": 1.74, + "learning_rate": 4.494357876024591e-07, + "loss": 0.1261, + "step": 13563 + }, + { + "epoch": 1.74, + "learning_rate": 4.490064060443361e-07, + "loss": 0.1337, + "step": 13564 + }, + { + "epoch": 1.74, + "learning_rate": 4.4857722005254345e-07, + "loss": 0.131, + "step": 13565 + }, + { + "epoch": 1.74, + "learning_rate": 4.4814822964552363e-07, + "loss": 0.1385, + "step": 13566 + }, + { + "epoch": 1.74, + "learning_rate": 4.47719434841713e-07, + "loss": 0.139, + "step": 13567 + }, + { + "epoch": 1.74, + "learning_rate": 4.4729083565953626e-07, + "loss": 0.1325, + "step": 13568 + }, + { + "epoch": 1.74, + "learning_rate": 4.468624321174109e-07, + "loss": 0.1277, + "step": 13569 + }, + { + "epoch": 1.74, + "learning_rate": 4.4643422423374825e-07, + "loss": 0.126, + "step": 13570 + }, + { + "epoch": 1.74, + "learning_rate": 4.460062120269476e-07, + "loss": 0.1375, + "step": 13571 + }, + { + "epoch": 1.74, + "learning_rate": 4.4557839551540303e-07, + "loss": 0.1249, + "step": 13572 + }, + { + "epoch": 1.74, + "learning_rate": 4.4515077471749767e-07, + "loss": 0.1291, + "step": 13573 + }, + { + "epoch": 1.74, + "learning_rate": 4.4472334965160736e-07, + "loss": 0.1315, + "step": 13574 + }, + { + "epoch": 1.74, + "learning_rate": 4.442961203361013e-07, + "loss": 0.1302, + "step": 13575 + }, + { + "epoch": 1.74, + "learning_rate": 4.438690867893347e-07, + "loss": 0.1369, + "step": 13576 + }, + { + "epoch": 1.74, + "learning_rate": 4.4344224902966194e-07, + "loss": 0.1395, + "step": 13577 + }, + { + "epoch": 1.74, + "learning_rate": 4.430156070754249e-07, + "loss": 0.1306, + "step": 13578 + }, + { + "epoch": 1.74, + "learning_rate": 4.4258916094495394e-07, + "loss": 0.1435, + "step": 13579 + }, + { + "epoch": 1.74, + "learning_rate": 4.421629106565778e-07, + "loss": 0.1364, + "step": 13580 + }, + { + "epoch": 1.74, + "learning_rate": 4.417368562286117e-07, + "loss": 0.1326, + "step": 13581 + }, + { + "epoch": 1.74, + "learning_rate": 4.4131099767936504e-07, + "loss": 0.1283, + "step": 13582 + }, + { + "epoch": 1.74, + "learning_rate": 4.4088533502713803e-07, + "loss": 0.1445, + "step": 13583 + }, + { + "epoch": 1.74, + "learning_rate": 4.4045986829022e-07, + "loss": 0.1297, + "step": 13584 + }, + { + "epoch": 1.74, + "learning_rate": 4.400345974868986e-07, + "loss": 0.1391, + "step": 13585 + }, + { + "epoch": 1.74, + "learning_rate": 4.396095226354441e-07, + "loss": 0.1319, + "step": 13586 + }, + { + "epoch": 1.74, + "learning_rate": 4.391846437541258e-07, + "loss": 0.1276, + "step": 13587 + }, + { + "epoch": 1.74, + "learning_rate": 4.3875996086120085e-07, + "loss": 0.1608, + "step": 13588 + }, + { + "epoch": 1.74, + "learning_rate": 4.38335473974919e-07, + "loss": 0.1326, + "step": 13589 + }, + { + "epoch": 1.74, + "learning_rate": 4.379111831135213e-07, + "loss": 0.1364, + "step": 13590 + }, + { + "epoch": 1.74, + "learning_rate": 4.374870882952398e-07, + "loss": 0.1279, + "step": 13591 + }, + { + "epoch": 1.74, + "learning_rate": 4.370631895382993e-07, + "loss": 0.1316, + "step": 13592 + }, + { + "epoch": 1.74, + "learning_rate": 4.3663948686091694e-07, + "loss": 0.1268, + "step": 13593 + }, + { + "epoch": 1.74, + "learning_rate": 4.362159802812971e-07, + "loss": 0.1229, + "step": 13594 + }, + { + "epoch": 1.74, + "learning_rate": 4.357926698176418e-07, + "loss": 0.1296, + "step": 13595 + }, + { + "epoch": 1.74, + "learning_rate": 4.3536955548814153e-07, + "loss": 0.1279, + "step": 13596 + }, + { + "epoch": 1.74, + "learning_rate": 4.3494663731097564e-07, + "loss": 0.1481, + "step": 13597 + }, + { + "epoch": 1.74, + "learning_rate": 4.3452391530432016e-07, + "loss": 0.1416, + "step": 13598 + }, + { + "epoch": 1.74, + "learning_rate": 4.341013894863405e-07, + "loss": 0.1275, + "step": 13599 + }, + { + "epoch": 1.74, + "learning_rate": 4.3367905987519275e-07, + "loss": 0.1244, + "step": 13600 + }, + { + "epoch": 1.74, + "learning_rate": 4.332569264890252e-07, + "loss": 0.1229, + "step": 13601 + }, + { + "epoch": 1.74, + "learning_rate": 4.328349893459777e-07, + "loss": 0.125, + "step": 13602 + }, + { + "epoch": 1.74, + "learning_rate": 4.3241324846418355e-07, + "loss": 0.1457, + "step": 13603 + }, + { + "epoch": 1.74, + "learning_rate": 4.3199170386176325e-07, + "loss": 0.1426, + "step": 13604 + }, + { + "epoch": 1.74, + "learning_rate": 4.31570355556834e-07, + "loss": 0.1316, + "step": 13605 + }, + { + "epoch": 1.74, + "learning_rate": 4.3114920356750076e-07, + "loss": 0.1139, + "step": 13606 + }, + { + "epoch": 1.74, + "learning_rate": 4.3072824791186187e-07, + "loss": 0.1411, + "step": 13607 + }, + { + "epoch": 1.74, + "learning_rate": 4.3030748860800606e-07, + "loss": 0.1414, + "step": 13608 + }, + { + "epoch": 1.74, + "learning_rate": 4.2988692567401515e-07, + "loss": 0.1398, + "step": 13609 + }, + { + "epoch": 1.74, + "learning_rate": 4.294665591279601e-07, + "loss": 0.1233, + "step": 13610 + }, + { + "epoch": 1.74, + "learning_rate": 4.290463889879082e-07, + "loss": 0.1526, + "step": 13611 + }, + { + "epoch": 1.74, + "learning_rate": 4.286264152719111e-07, + "loss": 0.1585, + "step": 13612 + }, + { + "epoch": 1.74, + "learning_rate": 4.2820663799801876e-07, + "loss": 0.137, + "step": 13613 + }, + { + "epoch": 1.74, + "learning_rate": 4.2778705718426907e-07, + "loss": 0.1268, + "step": 13614 + }, + { + "epoch": 1.74, + "learning_rate": 4.273676728486925e-07, + "loss": 0.1295, + "step": 13615 + }, + { + "epoch": 1.74, + "learning_rate": 4.2694848500931086e-07, + "loss": 0.139, + "step": 13616 + }, + { + "epoch": 1.74, + "learning_rate": 4.2652949368413634e-07, + "loss": 0.1365, + "step": 13617 + }, + { + "epoch": 1.74, + "learning_rate": 4.2611069889117727e-07, + "loss": 0.1397, + "step": 13618 + }, + { + "epoch": 1.74, + "learning_rate": 4.2569210064842716e-07, + "loss": 0.1279, + "step": 13619 + }, + { + "epoch": 1.74, + "learning_rate": 4.252736989738737e-07, + "loss": 0.1378, + "step": 13620 + }, + { + "epoch": 1.74, + "learning_rate": 4.2485549388549927e-07, + "loss": 0.1243, + "step": 13621 + }, + { + "epoch": 1.74, + "learning_rate": 4.244374854012734e-07, + "loss": 0.1295, + "step": 13622 + }, + { + "epoch": 1.74, + "learning_rate": 4.2401967353915885e-07, + "loss": 0.1359, + "step": 13623 + }, + { + "epoch": 1.74, + "learning_rate": 4.236020583171108e-07, + "loss": 0.1407, + "step": 13624 + }, + { + "epoch": 1.74, + "learning_rate": 4.2318463975307423e-07, + "loss": 0.1397, + "step": 13625 + }, + { + "epoch": 1.74, + "learning_rate": 4.227674178649865e-07, + "loss": 0.145, + "step": 13626 + }, + { + "epoch": 1.74, + "learning_rate": 4.2235039267077615e-07, + "loss": 0.1165, + "step": 13627 + }, + { + "epoch": 1.74, + "learning_rate": 4.219335641883654e-07, + "loss": 0.1323, + "step": 13628 + }, + { + "epoch": 1.74, + "learning_rate": 4.215169324356666e-07, + "loss": 0.1466, + "step": 13629 + }, + { + "epoch": 1.74, + "learning_rate": 4.2110049743057933e-07, + "loss": 0.1236, + "step": 13630 + }, + { + "epoch": 1.74, + "learning_rate": 4.206842591910032e-07, + "loss": 0.1311, + "step": 13631 + }, + { + "epoch": 1.74, + "learning_rate": 4.202682177348227e-07, + "loss": 0.123, + "step": 13632 + }, + { + "epoch": 1.75, + "learning_rate": 4.198523730799164e-07, + "loss": 0.1292, + "step": 13633 + }, + { + "epoch": 1.75, + "learning_rate": 4.194367252441545e-07, + "loss": 0.146, + "step": 13634 + }, + { + "epoch": 1.75, + "learning_rate": 4.1902127424539695e-07, + "loss": 0.1163, + "step": 13635 + }, + { + "epoch": 1.75, + "learning_rate": 4.186060201014991e-07, + "loss": 0.1309, + "step": 13636 + }, + { + "epoch": 1.75, + "learning_rate": 4.181909628303027e-07, + "loss": 0.1433, + "step": 13637 + }, + { + "epoch": 1.75, + "learning_rate": 4.177761024496452e-07, + "loss": 0.1403, + "step": 13638 + }, + { + "epoch": 1.75, + "learning_rate": 4.1736143897735394e-07, + "loss": 0.1409, + "step": 13639 + }, + { + "epoch": 1.75, + "learning_rate": 4.1694697243124804e-07, + "loss": 0.1273, + "step": 13640 + }, + { + "epoch": 1.75, + "learning_rate": 4.1653270282913715e-07, + "loss": 0.1448, + "step": 13641 + }, + { + "epoch": 1.75, + "learning_rate": 4.1611863018882424e-07, + "loss": 0.1291, + "step": 13642 + }, + { + "epoch": 1.75, + "learning_rate": 4.157047545281029e-07, + "loss": 0.1258, + "step": 13643 + }, + { + "epoch": 1.75, + "learning_rate": 4.152910758647577e-07, + "loss": 0.1299, + "step": 13644 + }, + { + "epoch": 1.75, + "learning_rate": 4.14877594216565e-07, + "loss": 0.1312, + "step": 13645 + }, + { + "epoch": 1.75, + "learning_rate": 4.14464309601294e-07, + "loss": 0.1308, + "step": 13646 + }, + { + "epoch": 1.75, + "learning_rate": 4.14051222036706e-07, + "loss": 0.1247, + "step": 13647 + }, + { + "epoch": 1.75, + "learning_rate": 4.1363833154054786e-07, + "loss": 0.1253, + "step": 13648 + }, + { + "epoch": 1.75, + "learning_rate": 4.1322563813056606e-07, + "loss": 0.1206, + "step": 13649 + }, + { + "epoch": 1.75, + "learning_rate": 4.1281314182449405e-07, + "loss": 0.1404, + "step": 13650 + }, + { + "epoch": 1.75, + "learning_rate": 4.1240084264005774e-07, + "loss": 0.1378, + "step": 13651 + }, + { + "epoch": 1.75, + "learning_rate": 4.1198874059497405e-07, + "loss": 0.1226, + "step": 13652 + }, + { + "epoch": 1.75, + "learning_rate": 4.1157683570695105e-07, + "loss": 0.1294, + "step": 13653 + }, + { + "epoch": 1.75, + "learning_rate": 4.111651279936929e-07, + "loss": 0.1229, + "step": 13654 + }, + { + "epoch": 1.75, + "learning_rate": 4.1075361747288657e-07, + "loss": 0.1468, + "step": 13655 + }, + { + "epoch": 1.75, + "learning_rate": 4.103423041622195e-07, + "loss": 0.1232, + "step": 13656 + }, + { + "epoch": 1.75, + "learning_rate": 4.099311880793655e-07, + "loss": 0.1242, + "step": 13657 + }, + { + "epoch": 1.75, + "learning_rate": 4.0952026924199027e-07, + "loss": 0.1253, + "step": 13658 + }, + { + "epoch": 1.75, + "learning_rate": 4.091095476677531e-07, + "loss": 0.1344, + "step": 13659 + }, + { + "epoch": 1.75, + "learning_rate": 4.0869902337430323e-07, + "loss": 0.1215, + "step": 13660 + }, + { + "epoch": 1.75, + "learning_rate": 4.082886963792815e-07, + "loss": 0.1272, + "step": 13661 + }, + { + "epoch": 1.75, + "learning_rate": 4.0787856670032044e-07, + "loss": 0.1416, + "step": 13662 + }, + { + "epoch": 1.75, + "learning_rate": 4.0746863435504434e-07, + "loss": 0.1103, + "step": 13663 + }, + { + "epoch": 1.75, + "learning_rate": 4.070588993610697e-07, + "loss": 0.106, + "step": 13664 + }, + { + "epoch": 1.75, + "learning_rate": 4.066493617360029e-07, + "loss": 0.1163, + "step": 13665 + }, + { + "epoch": 1.75, + "learning_rate": 4.062400214974432e-07, + "loss": 0.1706, + "step": 13666 + }, + { + "epoch": 1.75, + "learning_rate": 4.0583087866298056e-07, + "loss": 0.1248, + "step": 13667 + }, + { + "epoch": 1.75, + "learning_rate": 4.054219332501974e-07, + "loss": 0.1182, + "step": 13668 + }, + { + "epoch": 1.75, + "learning_rate": 4.050131852766659e-07, + "loss": 0.1292, + "step": 13669 + }, + { + "epoch": 1.75, + "learning_rate": 4.046046347599514e-07, + "loss": 0.1211, + "step": 13670 + }, + { + "epoch": 1.75, + "learning_rate": 4.0419628171760927e-07, + "loss": 0.1386, + "step": 13671 + }, + { + "epoch": 1.75, + "learning_rate": 4.0378812616719056e-07, + "loss": 0.1424, + "step": 13672 + }, + { + "epoch": 1.75, + "learning_rate": 4.0338016812623007e-07, + "loss": 0.1382, + "step": 13673 + }, + { + "epoch": 1.75, + "learning_rate": 4.029724076122621e-07, + "loss": 0.1323, + "step": 13674 + }, + { + "epoch": 1.75, + "learning_rate": 4.025648446428082e-07, + "loss": 0.1157, + "step": 13675 + }, + { + "epoch": 1.75, + "learning_rate": 4.021574792353816e-07, + "loss": 0.1318, + "step": 13676 + }, + { + "epoch": 1.75, + "learning_rate": 4.017503114074883e-07, + "loss": 0.1196, + "step": 13677 + }, + { + "epoch": 1.75, + "learning_rate": 4.0134334117662375e-07, + "loss": 0.1258, + "step": 13678 + }, + { + "epoch": 1.75, + "learning_rate": 4.009365685602795e-07, + "loss": 0.1365, + "step": 13679 + }, + { + "epoch": 1.75, + "learning_rate": 4.005299935759327e-07, + "loss": 0.1544, + "step": 13680 + }, + { + "epoch": 1.75, + "learning_rate": 4.001236162410549e-07, + "loss": 0.1305, + "step": 13681 + }, + { + "epoch": 1.75, + "learning_rate": 3.997174365731105e-07, + "loss": 0.1251, + "step": 13682 + }, + { + "epoch": 1.75, + "learning_rate": 3.993114545895532e-07, + "loss": 0.1291, + "step": 13683 + }, + { + "epoch": 1.75, + "learning_rate": 3.989056703078292e-07, + "loss": 0.1266, + "step": 13684 + }, + { + "epoch": 1.75, + "learning_rate": 3.985000837453756e-07, + "loss": 0.1356, + "step": 13685 + }, + { + "epoch": 1.75, + "learning_rate": 3.9809469491962126e-07, + "loss": 0.1181, + "step": 13686 + }, + { + "epoch": 1.75, + "learning_rate": 3.976895038479872e-07, + "loss": 0.1244, + "step": 13687 + }, + { + "epoch": 1.75, + "learning_rate": 3.9728451054788396e-07, + "loss": 0.1184, + "step": 13688 + }, + { + "epoch": 1.75, + "learning_rate": 3.968797150367171e-07, + "loss": 0.1274, + "step": 13689 + }, + { + "epoch": 1.75, + "learning_rate": 3.9647511733188147e-07, + "loss": 0.1372, + "step": 13690 + }, + { + "epoch": 1.75, + "learning_rate": 3.960707174507611e-07, + "loss": 0.1259, + "step": 13691 + }, + { + "epoch": 1.75, + "learning_rate": 3.9566651541073586e-07, + "loss": 0.1288, + "step": 13692 + }, + { + "epoch": 1.75, + "learning_rate": 3.9526251122917526e-07, + "loss": 0.1292, + "step": 13693 + }, + { + "epoch": 1.75, + "learning_rate": 3.948587049234398e-07, + "loss": 0.1463, + "step": 13694 + }, + { + "epoch": 1.75, + "learning_rate": 3.944550965108818e-07, + "loss": 0.1296, + "step": 13695 + }, + { + "epoch": 1.75, + "learning_rate": 3.940516860088445e-07, + "loss": 0.1363, + "step": 13696 + }, + { + "epoch": 1.75, + "learning_rate": 3.936484734346663e-07, + "loss": 0.1191, + "step": 13697 + }, + { + "epoch": 1.75, + "learning_rate": 3.932454588056711e-07, + "loss": 0.1307, + "step": 13698 + }, + { + "epoch": 1.75, + "learning_rate": 3.928426421391773e-07, + "loss": 0.1422, + "step": 13699 + }, + { + "epoch": 1.75, + "learning_rate": 3.924400234524972e-07, + "loss": 0.1225, + "step": 13700 + }, + { + "epoch": 1.75, + "learning_rate": 3.9203760276293024e-07, + "loss": 0.1142, + "step": 13701 + }, + { + "epoch": 1.75, + "learning_rate": 3.9163538008777035e-07, + "loss": 0.1275, + "step": 13702 + }, + { + "epoch": 1.75, + "learning_rate": 3.9123335544430153e-07, + "loss": 0.1323, + "step": 13703 + }, + { + "epoch": 1.75, + "learning_rate": 3.9083152884979935e-07, + "loss": 0.1435, + "step": 13704 + }, + { + "epoch": 1.75, + "learning_rate": 3.9042990032153227e-07, + "loss": 0.1269, + "step": 13705 + }, + { + "epoch": 1.75, + "learning_rate": 3.9002846987675704e-07, + "loss": 0.1405, + "step": 13706 + }, + { + "epoch": 1.75, + "learning_rate": 3.8962723753272645e-07, + "loss": 0.1268, + "step": 13707 + }, + { + "epoch": 1.75, + "learning_rate": 3.892262033066818e-07, + "loss": 0.1436, + "step": 13708 + }, + { + "epoch": 1.75, + "learning_rate": 3.8882536721585486e-07, + "loss": 0.1268, + "step": 13709 + }, + { + "epoch": 1.75, + "learning_rate": 3.884247292774718e-07, + "loss": 0.1392, + "step": 13710 + }, + { + "epoch": 1.76, + "learning_rate": 3.8802428950874884e-07, + "loss": 0.1259, + "step": 13711 + }, + { + "epoch": 1.76, + "learning_rate": 3.876240479268939e-07, + "loss": 0.1389, + "step": 13712 + }, + { + "epoch": 1.76, + "learning_rate": 3.872240045491055e-07, + "loss": 0.13, + "step": 13713 + }, + { + "epoch": 1.76, + "learning_rate": 3.868241593925742e-07, + "loss": 0.1266, + "step": 13714 + }, + { + "epoch": 1.76, + "learning_rate": 3.8642451247448477e-07, + "loss": 0.1297, + "step": 13715 + }, + { + "epoch": 1.76, + "learning_rate": 3.8602506381200666e-07, + "loss": 0.1357, + "step": 13716 + }, + { + "epoch": 1.76, + "learning_rate": 3.8562581342230897e-07, + "loss": 0.1244, + "step": 13717 + }, + { + "epoch": 1.76, + "learning_rate": 3.8522676132254635e-07, + "loss": 0.1413, + "step": 13718 + }, + { + "epoch": 1.76, + "learning_rate": 3.848279075298678e-07, + "loss": 0.1252, + "step": 13719 + }, + { + "epoch": 1.76, + "learning_rate": 3.8442925206141237e-07, + "loss": 0.1339, + "step": 13720 + }, + { + "epoch": 1.76, + "learning_rate": 3.840307949343114e-07, + "loss": 0.1322, + "step": 13721 + }, + { + "epoch": 1.76, + "learning_rate": 3.8363253616568784e-07, + "loss": 0.1432, + "step": 13722 + }, + { + "epoch": 1.76, + "learning_rate": 3.8323447577265525e-07, + "loss": 0.1287, + "step": 13723 + }, + { + "epoch": 1.76, + "learning_rate": 3.828366137723183e-07, + "loss": 0.1447, + "step": 13724 + }, + { + "epoch": 1.76, + "learning_rate": 3.82438950181776e-07, + "loss": 0.1355, + "step": 13725 + }, + { + "epoch": 1.76, + "learning_rate": 3.820414850181153e-07, + "loss": 0.1324, + "step": 13726 + }, + { + "epoch": 1.76, + "learning_rate": 3.8164421829841756e-07, + "loss": 0.1297, + "step": 13727 + }, + { + "epoch": 1.76, + "learning_rate": 3.81247150039753e-07, + "loss": 0.1348, + "step": 13728 + }, + { + "epoch": 1.76, + "learning_rate": 3.80850280259184e-07, + "loss": 0.1293, + "step": 13729 + }, + { + "epoch": 1.76, + "learning_rate": 3.8045360897376814e-07, + "loss": 0.1382, + "step": 13730 + }, + { + "epoch": 1.76, + "learning_rate": 3.800571362005473e-07, + "loss": 0.1211, + "step": 13731 + }, + { + "epoch": 1.76, + "learning_rate": 3.7966086195656e-07, + "loss": 0.1343, + "step": 13732 + }, + { + "epoch": 1.76, + "learning_rate": 3.7926478625883725e-07, + "loss": 0.1373, + "step": 13733 + }, + { + "epoch": 1.76, + "learning_rate": 3.7886890912439633e-07, + "loss": 0.1467, + "step": 13734 + }, + { + "epoch": 1.76, + "learning_rate": 3.784732305702504e-07, + "loss": 0.1314, + "step": 13735 + }, + { + "epoch": 1.76, + "learning_rate": 3.7807775061340257e-07, + "loss": 0.1428, + "step": 13736 + }, + { + "epoch": 1.76, + "learning_rate": 3.776824692708475e-07, + "loss": 0.1268, + "step": 13737 + }, + { + "epoch": 1.76, + "learning_rate": 3.772873865595711e-07, + "loss": 0.1397, + "step": 13738 + }, + { + "epoch": 1.76, + "learning_rate": 3.768925024965503e-07, + "loss": 0.1357, + "step": 13739 + }, + { + "epoch": 1.76, + "learning_rate": 3.76497817098756e-07, + "loss": 0.1224, + "step": 13740 + }, + { + "epoch": 1.76, + "learning_rate": 3.761033303831474e-07, + "loss": 0.1154, + "step": 13741 + }, + { + "epoch": 1.76, + "learning_rate": 3.7570904236667536e-07, + "loss": 0.1222, + "step": 13742 + }, + { + "epoch": 1.76, + "learning_rate": 3.7531495306628584e-07, + "loss": 0.1435, + "step": 13743 + }, + { + "epoch": 1.76, + "learning_rate": 3.749210624989125e-07, + "loss": 0.1212, + "step": 13744 + }, + { + "epoch": 1.76, + "learning_rate": 3.7452737068148173e-07, + "loss": 0.114, + "step": 13745 + }, + { + "epoch": 1.76, + "learning_rate": 3.741338776309111e-07, + "loss": 0.1267, + "step": 13746 + }, + { + "epoch": 1.76, + "learning_rate": 3.7374058336410945e-07, + "loss": 0.1306, + "step": 13747 + }, + { + "epoch": 1.76, + "learning_rate": 3.733474878979798e-07, + "loss": 0.1226, + "step": 13748 + }, + { + "epoch": 1.76, + "learning_rate": 3.729545912494115e-07, + "loss": 0.127, + "step": 13749 + }, + { + "epoch": 1.76, + "learning_rate": 3.7256189343528926e-07, + "loss": 0.1356, + "step": 13750 + }, + { + "epoch": 1.76, + "learning_rate": 3.721693944724897e-07, + "loss": 0.1313, + "step": 13751 + }, + { + "epoch": 1.76, + "learning_rate": 3.717770943778759e-07, + "loss": 0.1357, + "step": 13752 + }, + { + "epoch": 1.76, + "learning_rate": 3.7138499316830946e-07, + "loss": 0.1337, + "step": 13753 + }, + { + "epoch": 1.76, + "learning_rate": 3.7099309086063794e-07, + "loss": 0.134, + "step": 13754 + }, + { + "epoch": 1.76, + "learning_rate": 3.706013874717024e-07, + "loss": 0.1228, + "step": 13755 + }, + { + "epoch": 1.76, + "learning_rate": 3.702098830183359e-07, + "loss": 0.1421, + "step": 13756 + }, + { + "epoch": 1.76, + "learning_rate": 3.698185775173607e-07, + "loss": 0.1403, + "step": 13757 + }, + { + "epoch": 1.76, + "learning_rate": 3.694274709855944e-07, + "loss": 0.1245, + "step": 13758 + }, + { + "epoch": 1.76, + "learning_rate": 3.6903656343984293e-07, + "loss": 0.1201, + "step": 13759 + }, + { + "epoch": 1.76, + "learning_rate": 3.6864585489690297e-07, + "loss": 0.116, + "step": 13760 + }, + { + "epoch": 1.76, + "learning_rate": 3.6825534537356545e-07, + "loss": 0.1244, + "step": 13761 + }, + { + "epoch": 1.76, + "learning_rate": 3.678650348866114e-07, + "loss": 0.1365, + "step": 13762 + }, + { + "epoch": 1.76, + "learning_rate": 3.6747492345281297e-07, + "loss": 0.1305, + "step": 13763 + }, + { + "epoch": 1.76, + "learning_rate": 3.670850110889346e-07, + "loss": 0.1272, + "step": 13764 + }, + { + "epoch": 1.76, + "learning_rate": 3.6669529781173053e-07, + "loss": 0.1302, + "step": 13765 + }, + { + "epoch": 1.76, + "learning_rate": 3.6630578363794965e-07, + "loss": 0.1173, + "step": 13766 + }, + { + "epoch": 1.76, + "learning_rate": 3.659164685843275e-07, + "loss": 0.1501, + "step": 13767 + }, + { + "epoch": 1.76, + "learning_rate": 3.655273526675962e-07, + "loss": 0.1116, + "step": 13768 + }, + { + "epoch": 1.76, + "learning_rate": 3.651384359044774e-07, + "loss": 0.1388, + "step": 13769 + }, + { + "epoch": 1.76, + "learning_rate": 3.647497183116799e-07, + "loss": 0.141, + "step": 13770 + }, + { + "epoch": 1.76, + "learning_rate": 3.6436119990591214e-07, + "loss": 0.1309, + "step": 13771 + }, + { + "epoch": 1.76, + "learning_rate": 3.639728807038667e-07, + "loss": 0.1492, + "step": 13772 + }, + { + "epoch": 1.76, + "learning_rate": 3.6358476072223205e-07, + "loss": 0.1231, + "step": 13773 + }, + { + "epoch": 1.76, + "learning_rate": 3.631968399776864e-07, + "loss": 0.1383, + "step": 13774 + }, + { + "epoch": 1.76, + "learning_rate": 3.628091184868976e-07, + "loss": 0.1419, + "step": 13775 + }, + { + "epoch": 1.76, + "learning_rate": 3.6242159626653004e-07, + "loss": 0.128, + "step": 13776 + }, + { + "epoch": 1.76, + "learning_rate": 3.6203427333323495e-07, + "loss": 0.1236, + "step": 13777 + }, + { + "epoch": 1.76, + "learning_rate": 3.616471497036561e-07, + "loss": 0.1361, + "step": 13778 + }, + { + "epoch": 1.76, + "learning_rate": 3.6126022539442975e-07, + "loss": 0.1377, + "step": 13779 + }, + { + "epoch": 1.76, + "learning_rate": 3.6087350042218194e-07, + "loss": 0.1113, + "step": 13780 + }, + { + "epoch": 1.76, + "learning_rate": 3.6048697480353225e-07, + "loss": 0.1357, + "step": 13781 + }, + { + "epoch": 1.76, + "learning_rate": 3.601006485550895e-07, + "loss": 0.1209, + "step": 13782 + }, + { + "epoch": 1.76, + "learning_rate": 3.597145216934556e-07, + "loss": 0.134, + "step": 13783 + }, + { + "epoch": 1.76, + "learning_rate": 3.593285942352237e-07, + "loss": 0.1364, + "step": 13784 + }, + { + "epoch": 1.76, + "learning_rate": 3.5894286619697627e-07, + "loss": 0.1374, + "step": 13785 + }, + { + "epoch": 1.76, + "learning_rate": 3.585573375952911e-07, + "loss": 0.1219, + "step": 13786 + }, + { + "epoch": 1.76, + "learning_rate": 3.581720084467344e-07, + "loss": 0.1204, + "step": 13787 + }, + { + "epoch": 1.76, + "learning_rate": 3.57786878767864e-07, + "loss": 0.1276, + "step": 13788 + }, + { + "epoch": 1.76, + "learning_rate": 3.5740194857523e-07, + "loss": 0.1477, + "step": 13789 + }, + { + "epoch": 1.77, + "learning_rate": 3.570172178853731e-07, + "loss": 0.1309, + "step": 13790 + }, + { + "epoch": 1.77, + "learning_rate": 3.56632686714829e-07, + "loss": 0.1107, + "step": 13791 + }, + { + "epoch": 1.77, + "learning_rate": 3.5624835508011824e-07, + "loss": 0.1383, + "step": 13792 + }, + { + "epoch": 1.77, + "learning_rate": 3.5586422299775714e-07, + "loss": 0.1282, + "step": 13793 + }, + { + "epoch": 1.77, + "learning_rate": 3.554802904842547e-07, + "loss": 0.151, + "step": 13794 + }, + { + "epoch": 1.77, + "learning_rate": 3.5509655755610773e-07, + "loss": 0.1415, + "step": 13795 + }, + { + "epoch": 1.77, + "learning_rate": 3.547130242298064e-07, + "loss": 0.1468, + "step": 13796 + }, + { + "epoch": 1.77, + "learning_rate": 3.5432969052183186e-07, + "loss": 0.1426, + "step": 13797 + }, + { + "epoch": 1.77, + "learning_rate": 3.539465564486577e-07, + "loss": 0.1392, + "step": 13798 + }, + { + "epoch": 1.77, + "learning_rate": 3.5356362202674687e-07, + "loss": 0.1265, + "step": 13799 + }, + { + "epoch": 1.77, + "learning_rate": 3.5318088727255506e-07, + "loss": 0.1265, + "step": 13800 + }, + { + "epoch": 1.77, + "learning_rate": 3.527983522025291e-07, + "loss": 0.1269, + "step": 13801 + }, + { + "epoch": 1.77, + "learning_rate": 3.5241601683310924e-07, + "loss": 0.1252, + "step": 13802 + }, + { + "epoch": 1.77, + "learning_rate": 3.520338811807222e-07, + "loss": 0.1524, + "step": 13803 + }, + { + "epoch": 1.77, + "learning_rate": 3.516519452617922e-07, + "loss": 0.135, + "step": 13804 + }, + { + "epoch": 1.77, + "learning_rate": 3.5127020909273e-07, + "loss": 0.1216, + "step": 13805 + }, + { + "epoch": 1.77, + "learning_rate": 3.508886726899402e-07, + "loss": 0.1174, + "step": 13806 + }, + { + "epoch": 1.77, + "learning_rate": 3.5050733606981855e-07, + "loss": 0.1357, + "step": 13807 + }, + { + "epoch": 1.77, + "learning_rate": 3.501261992487509e-07, + "loss": 0.1314, + "step": 13808 + }, + { + "epoch": 1.77, + "learning_rate": 3.4974526224311744e-07, + "loss": 0.1356, + "step": 13809 + }, + { + "epoch": 1.77, + "learning_rate": 3.493645250692862e-07, + "loss": 0.1286, + "step": 13810 + }, + { + "epoch": 1.77, + "learning_rate": 3.4898398774361854e-07, + "loss": 0.1443, + "step": 13811 + }, + { + "epoch": 1.77, + "learning_rate": 3.486036502824675e-07, + "loss": 0.1446, + "step": 13812 + }, + { + "epoch": 1.77, + "learning_rate": 3.4822351270217656e-07, + "loss": 0.1457, + "step": 13813 + }, + { + "epoch": 1.77, + "learning_rate": 3.478435750190817e-07, + "loss": 0.1353, + "step": 13814 + }, + { + "epoch": 1.77, + "learning_rate": 3.474638372495098e-07, + "loss": 0.1375, + "step": 13815 + }, + { + "epoch": 1.77, + "learning_rate": 3.4708429940977785e-07, + "loss": 0.1394, + "step": 13816 + }, + { + "epoch": 1.77, + "learning_rate": 3.467049615161966e-07, + "loss": 0.1254, + "step": 13817 + }, + { + "epoch": 1.77, + "learning_rate": 3.463258235850653e-07, + "loss": 0.1193, + "step": 13818 + }, + { + "epoch": 1.77, + "learning_rate": 3.459468856326792e-07, + "loss": 0.1326, + "step": 13819 + }, + { + "epoch": 1.77, + "learning_rate": 3.455681476753209e-07, + "loss": 0.1478, + "step": 13820 + }, + { + "epoch": 1.77, + "learning_rate": 3.451896097292634e-07, + "loss": 0.1223, + "step": 13821 + }, + { + "epoch": 1.77, + "learning_rate": 3.448112718107766e-07, + "loss": 0.1207, + "step": 13822 + }, + { + "epoch": 1.77, + "learning_rate": 3.444331339361168e-07, + "loss": 0.1423, + "step": 13823 + }, + { + "epoch": 1.77, + "learning_rate": 3.4405519612153326e-07, + "loss": 0.1469, + "step": 13824 + }, + { + "epoch": 1.77, + "learning_rate": 3.4367745838326807e-07, + "loss": 0.1101, + "step": 13825 + }, + { + "epoch": 1.77, + "learning_rate": 3.432999207375515e-07, + "loss": 0.1402, + "step": 13826 + }, + { + "epoch": 1.77, + "learning_rate": 3.4292258320061e-07, + "loss": 0.1287, + "step": 13827 + }, + { + "epoch": 1.77, + "learning_rate": 3.425454457886551e-07, + "loss": 0.1198, + "step": 13828 + }, + { + "epoch": 1.77, + "learning_rate": 3.4216850851789663e-07, + "loss": 0.1196, + "step": 13829 + }, + { + "epoch": 1.77, + "learning_rate": 3.4179177140453045e-07, + "loss": 0.131, + "step": 13830 + }, + { + "epoch": 1.77, + "learning_rate": 3.414152344647459e-07, + "loss": 0.144, + "step": 13831 + }, + { + "epoch": 1.77, + "learning_rate": 3.410388977147244e-07, + "loss": 0.1236, + "step": 13832 + }, + { + "epoch": 1.77, + "learning_rate": 3.406627611706376e-07, + "loss": 0.1371, + "step": 13833 + }, + { + "epoch": 1.77, + "learning_rate": 3.402868248486485e-07, + "loss": 0.1267, + "step": 13834 + }, + { + "epoch": 1.77, + "learning_rate": 3.3991108876491263e-07, + "loss": 0.1262, + "step": 13835 + }, + { + "epoch": 1.77, + "learning_rate": 3.3953555293557483e-07, + "loss": 0.1366, + "step": 13836 + }, + { + "epoch": 1.77, + "learning_rate": 3.391602173767744e-07, + "loss": 0.1249, + "step": 13837 + }, + { + "epoch": 1.77, + "learning_rate": 3.387850821046401e-07, + "loss": 0.1401, + "step": 13838 + }, + { + "epoch": 1.77, + "learning_rate": 3.3841014713529184e-07, + "loss": 0.1251, + "step": 13839 + }, + { + "epoch": 1.77, + "learning_rate": 3.380354124848412e-07, + "loss": 0.1344, + "step": 13840 + }, + { + "epoch": 1.77, + "learning_rate": 3.376608781693913e-07, + "loss": 0.1297, + "step": 13841 + }, + { + "epoch": 1.77, + "learning_rate": 3.372865442050377e-07, + "loss": 0.1218, + "step": 13842 + }, + { + "epoch": 1.77, + "learning_rate": 3.3691241060786586e-07, + "loss": 0.1312, + "step": 13843 + }, + { + "epoch": 1.77, + "learning_rate": 3.3653847739395174e-07, + "loss": 0.1167, + "step": 13844 + }, + { + "epoch": 1.77, + "learning_rate": 3.36164744579367e-07, + "loss": 0.1277, + "step": 13845 + }, + { + "epoch": 1.77, + "learning_rate": 3.357912121801682e-07, + "loss": 0.1286, + "step": 13846 + }, + { + "epoch": 1.77, + "learning_rate": 3.354178802124103e-07, + "loss": 0.1334, + "step": 13847 + }, + { + "epoch": 1.77, + "learning_rate": 3.350447486921338e-07, + "loss": 0.1325, + "step": 13848 + }, + { + "epoch": 1.77, + "learning_rate": 3.346718176353747e-07, + "loss": 0.1422, + "step": 13849 + }, + { + "epoch": 1.77, + "learning_rate": 3.342990870581575e-07, + "loss": 0.1353, + "step": 13850 + }, + { + "epoch": 1.77, + "learning_rate": 3.339265569764993e-07, + "loss": 0.1244, + "step": 13851 + }, + { + "epoch": 1.77, + "learning_rate": 3.3355422740640905e-07, + "loss": 0.129, + "step": 13852 + }, + { + "epoch": 1.77, + "learning_rate": 3.331820983638867e-07, + "loss": 0.1369, + "step": 13853 + }, + { + "epoch": 1.77, + "learning_rate": 3.3281016986492165e-07, + "loss": 0.1406, + "step": 13854 + }, + { + "epoch": 1.77, + "learning_rate": 3.3243844192549947e-07, + "loss": 0.1385, + "step": 13855 + }, + { + "epoch": 1.77, + "learning_rate": 3.3206691456159233e-07, + "loss": 0.1295, + "step": 13856 + }, + { + "epoch": 1.77, + "learning_rate": 3.316955877891659e-07, + "loss": 0.1294, + "step": 13857 + }, + { + "epoch": 1.77, + "learning_rate": 3.313244616241773e-07, + "loss": 0.1195, + "step": 13858 + }, + { + "epoch": 1.77, + "learning_rate": 3.3095353608257385e-07, + "loss": 0.1434, + "step": 13859 + }, + { + "epoch": 1.77, + "learning_rate": 3.3058281118029553e-07, + "loss": 0.131, + "step": 13860 + }, + { + "epoch": 1.77, + "learning_rate": 3.302122869332736e-07, + "loss": 0.1395, + "step": 13861 + }, + { + "epoch": 1.77, + "learning_rate": 3.2984196335742844e-07, + "loss": 0.1524, + "step": 13862 + }, + { + "epoch": 1.77, + "learning_rate": 3.294718404686775e-07, + "loss": 0.1432, + "step": 13863 + }, + { + "epoch": 1.77, + "learning_rate": 3.2910191828292083e-07, + "loss": 0.128, + "step": 13864 + }, + { + "epoch": 1.77, + "learning_rate": 3.2873219681605894e-07, + "loss": 0.129, + "step": 13865 + }, + { + "epoch": 1.77, + "learning_rate": 3.283626760839775e-07, + "loss": 0.1252, + "step": 13866 + }, + { + "epoch": 1.77, + "learning_rate": 3.279933561025567e-07, + "loss": 0.1237, + "step": 13867 + }, + { + "epoch": 1.78, + "learning_rate": 3.276242368876664e-07, + "loss": 0.131, + "step": 13868 + }, + { + "epoch": 1.78, + "learning_rate": 3.2725531845516744e-07, + "loss": 0.1306, + "step": 13869 + }, + { + "epoch": 1.78, + "learning_rate": 3.2688660082091594e-07, + "loss": 0.1464, + "step": 13870 + }, + { + "epoch": 1.78, + "learning_rate": 3.2651808400075426e-07, + "loss": 0.1401, + "step": 13871 + }, + { + "epoch": 1.78, + "learning_rate": 3.2614976801051745e-07, + "loss": 0.1433, + "step": 13872 + }, + { + "epoch": 1.78, + "learning_rate": 3.257816528660357e-07, + "loss": 0.1275, + "step": 13873 + }, + { + "epoch": 1.78, + "learning_rate": 3.254137385831263e-07, + "loss": 0.1385, + "step": 13874 + }, + { + "epoch": 1.78, + "learning_rate": 3.250460251775994e-07, + "loss": 0.1231, + "step": 13875 + }, + { + "epoch": 1.78, + "learning_rate": 3.246785126652563e-07, + "loss": 0.139, + "step": 13876 + }, + { + "epoch": 1.78, + "learning_rate": 3.243112010618893e-07, + "loss": 0.1286, + "step": 13877 + }, + { + "epoch": 1.78, + "learning_rate": 3.239440903832852e-07, + "loss": 0.1255, + "step": 13878 + }, + { + "epoch": 1.78, + "learning_rate": 3.2357718064521594e-07, + "loss": 0.1282, + "step": 13879 + }, + { + "epoch": 1.78, + "learning_rate": 3.2321047186345047e-07, + "loss": 0.1269, + "step": 13880 + }, + { + "epoch": 1.78, + "learning_rate": 3.2284396405374787e-07, + "loss": 0.1304, + "step": 13881 + }, + { + "epoch": 1.78, + "learning_rate": 3.2247765723185556e-07, + "loss": 0.1088, + "step": 13882 + }, + { + "epoch": 1.78, + "learning_rate": 3.221115514135159e-07, + "loss": 0.1055, + "step": 13883 + }, + { + "epoch": 1.78, + "learning_rate": 3.217456466144614e-07, + "loss": 0.1469, + "step": 13884 + }, + { + "epoch": 1.78, + "learning_rate": 3.213799428504155e-07, + "loss": 0.1327, + "step": 13885 + }, + { + "epoch": 1.78, + "learning_rate": 3.210144401370935e-07, + "loss": 0.1353, + "step": 13886 + }, + { + "epoch": 1.78, + "learning_rate": 3.206491384902005e-07, + "loss": 0.1299, + "step": 13887 + }, + { + "epoch": 1.78, + "learning_rate": 3.202840379254374e-07, + "loss": 0.1365, + "step": 13888 + }, + { + "epoch": 1.78, + "learning_rate": 3.199191384584893e-07, + "loss": 0.1316, + "step": 13889 + }, + { + "epoch": 1.78, + "learning_rate": 3.1955444010504044e-07, + "loss": 0.1327, + "step": 13890 + }, + { + "epoch": 1.78, + "learning_rate": 3.19189942880761e-07, + "loss": 0.1276, + "step": 13891 + }, + { + "epoch": 1.78, + "learning_rate": 3.18825646801314e-07, + "loss": 0.147, + "step": 13892 + }, + { + "epoch": 1.78, + "learning_rate": 3.184615518823547e-07, + "loss": 0.1325, + "step": 13893 + }, + { + "epoch": 1.78, + "learning_rate": 3.180976581395295e-07, + "loss": 0.1331, + "step": 13894 + }, + { + "epoch": 1.78, + "learning_rate": 3.177339655884737e-07, + "loss": 0.1316, + "step": 13895 + }, + { + "epoch": 1.78, + "learning_rate": 3.173704742448186e-07, + "loss": 0.1547, + "step": 13896 + }, + { + "epoch": 1.78, + "learning_rate": 3.170071841241823e-07, + "loss": 0.1229, + "step": 13897 + }, + { + "epoch": 1.78, + "learning_rate": 3.1664409524217677e-07, + "loss": 0.1286, + "step": 13898 + }, + { + "epoch": 1.78, + "learning_rate": 3.1628120761440616e-07, + "loss": 0.1364, + "step": 13899 + }, + { + "epoch": 1.78, + "learning_rate": 3.1591852125646196e-07, + "loss": 0.1287, + "step": 13900 + }, + { + "epoch": 1.78, + "learning_rate": 3.1555603618393106e-07, + "loss": 0.125, + "step": 13901 + }, + { + "epoch": 1.78, + "learning_rate": 3.151937524123905e-07, + "loss": 0.1415, + "step": 13902 + }, + { + "epoch": 1.78, + "learning_rate": 3.148316699574078e-07, + "loss": 0.1277, + "step": 13903 + }, + { + "epoch": 1.78, + "learning_rate": 3.144697888345427e-07, + "loss": 0.1497, + "step": 13904 + }, + { + "epoch": 1.78, + "learning_rate": 3.1410810905934564e-07, + "loss": 0.1349, + "step": 13905 + }, + { + "epoch": 1.78, + "learning_rate": 3.137466306473602e-07, + "loss": 0.1322, + "step": 13906 + }, + { + "epoch": 1.78, + "learning_rate": 3.1338535361411737e-07, + "loss": 0.1375, + "step": 13907 + }, + { + "epoch": 1.78, + "learning_rate": 3.1302427797514465e-07, + "loss": 0.1197, + "step": 13908 + }, + { + "epoch": 1.78, + "learning_rate": 3.1266340374595693e-07, + "loss": 0.1238, + "step": 13909 + }, + { + "epoch": 1.78, + "learning_rate": 3.1230273094206233e-07, + "loss": 0.1374, + "step": 13910 + }, + { + "epoch": 1.78, + "learning_rate": 3.1194225957895895e-07, + "loss": 0.1439, + "step": 13911 + }, + { + "epoch": 1.78, + "learning_rate": 3.115819896721378e-07, + "loss": 0.1271, + "step": 13912 + }, + { + "epoch": 1.78, + "learning_rate": 3.1122192123707985e-07, + "loss": 0.1378, + "step": 13913 + }, + { + "epoch": 1.78, + "learning_rate": 3.108620542892593e-07, + "loss": 0.1275, + "step": 13914 + }, + { + "epoch": 1.78, + "learning_rate": 3.105023888441383e-07, + "loss": 0.147, + "step": 13915 + }, + { + "epoch": 1.78, + "learning_rate": 3.1014292491717444e-07, + "loss": 0.1456, + "step": 13916 + }, + { + "epoch": 1.78, + "learning_rate": 3.0978366252381376e-07, + "loss": 0.1267, + "step": 13917 + }, + { + "epoch": 1.78, + "learning_rate": 3.0942460167949495e-07, + "loss": 0.1447, + "step": 13918 + }, + { + "epoch": 1.78, + "learning_rate": 3.0906574239964795e-07, + "loss": 0.1317, + "step": 13919 + }, + { + "epoch": 1.78, + "learning_rate": 3.08707084699692e-07, + "loss": 0.1219, + "step": 13920 + }, + { + "epoch": 1.78, + "learning_rate": 3.083486285950421e-07, + "loss": 0.1206, + "step": 13921 + }, + { + "epoch": 1.78, + "learning_rate": 3.0799037410109976e-07, + "loss": 0.1223, + "step": 13922 + }, + { + "epoch": 1.78, + "learning_rate": 3.076323212332605e-07, + "loss": 0.1141, + "step": 13923 + }, + { + "epoch": 1.78, + "learning_rate": 3.072744700069119e-07, + "loss": 0.1172, + "step": 13924 + }, + { + "epoch": 1.78, + "learning_rate": 3.06916820437429e-07, + "loss": 0.1355, + "step": 13925 + }, + { + "epoch": 1.78, + "learning_rate": 3.065593725401833e-07, + "loss": 0.1295, + "step": 13926 + }, + { + "epoch": 1.78, + "learning_rate": 3.0620212633053424e-07, + "loss": 0.1444, + "step": 13927 + }, + { + "epoch": 1.78, + "learning_rate": 3.0584508182383346e-07, + "loss": 0.1296, + "step": 13928 + }, + { + "epoch": 1.78, + "learning_rate": 3.054882390354241e-07, + "loss": 0.1394, + "step": 13929 + }, + { + "epoch": 1.78, + "learning_rate": 3.0513159798063906e-07, + "loss": 0.1243, + "step": 13930 + }, + { + "epoch": 1.78, + "learning_rate": 3.0477515867480655e-07, + "loss": 0.1385, + "step": 13931 + }, + { + "epoch": 1.78, + "learning_rate": 3.0441892113324265e-07, + "loss": 0.1204, + "step": 13932 + }, + { + "epoch": 1.78, + "learning_rate": 3.0406288537125403e-07, + "loss": 0.1236, + "step": 13933 + }, + { + "epoch": 1.78, + "learning_rate": 3.0370705140414293e-07, + "loss": 0.1229, + "step": 13934 + }, + { + "epoch": 1.78, + "learning_rate": 3.0335141924719813e-07, + "loss": 0.1335, + "step": 13935 + }, + { + "epoch": 1.78, + "learning_rate": 3.029959889157036e-07, + "loss": 0.1241, + "step": 13936 + }, + { + "epoch": 1.78, + "learning_rate": 3.026407604249315e-07, + "loss": 0.1228, + "step": 13937 + }, + { + "epoch": 1.78, + "learning_rate": 3.0228573379014745e-07, + "loss": 0.1373, + "step": 13938 + }, + { + "epoch": 1.78, + "learning_rate": 3.019309090266087e-07, + "loss": 0.1299, + "step": 13939 + }, + { + "epoch": 1.78, + "learning_rate": 3.015762861495608e-07, + "loss": 0.1342, + "step": 13940 + }, + { + "epoch": 1.78, + "learning_rate": 3.0122186517424435e-07, + "loss": 0.1328, + "step": 13941 + }, + { + "epoch": 1.78, + "learning_rate": 3.0086764611589047e-07, + "loss": 0.1216, + "step": 13942 + }, + { + "epoch": 1.78, + "learning_rate": 3.0051362898971704e-07, + "loss": 0.133, + "step": 13943 + }, + { + "epoch": 1.78, + "learning_rate": 3.0015981381094073e-07, + "loss": 0.141, + "step": 13944 + }, + { + "epoch": 1.78, + "learning_rate": 2.9980620059476384e-07, + "loss": 0.1266, + "step": 13945 + }, + { + "epoch": 1.79, + "learning_rate": 2.9945278935638255e-07, + "loss": 0.1329, + "step": 13946 + }, + { + "epoch": 1.79, + "learning_rate": 2.990995801109836e-07, + "loss": 0.1309, + "step": 13947 + }, + { + "epoch": 1.79, + "learning_rate": 2.987465728737443e-07, + "loss": 0.1395, + "step": 13948 + }, + { + "epoch": 1.79, + "learning_rate": 2.9839376765983583e-07, + "loss": 0.1326, + "step": 13949 + }, + { + "epoch": 1.79, + "learning_rate": 2.980411644844189e-07, + "loss": 0.1404, + "step": 13950 + }, + { + "epoch": 1.79, + "learning_rate": 2.976887633626435e-07, + "loss": 0.1237, + "step": 13951 + }, + { + "epoch": 1.79, + "learning_rate": 2.973365643096554e-07, + "loss": 0.127, + "step": 13952 + }, + { + "epoch": 1.79, + "learning_rate": 2.9698456734058856e-07, + "loss": 0.1218, + "step": 13953 + }, + { + "epoch": 1.79, + "learning_rate": 2.9663277247056923e-07, + "loss": 0.129, + "step": 13954 + }, + { + "epoch": 1.79, + "learning_rate": 2.9628117971471416e-07, + "loss": 0.1384, + "step": 13955 + }, + { + "epoch": 1.79, + "learning_rate": 2.959297890881319e-07, + "loss": 0.1306, + "step": 13956 + }, + { + "epoch": 1.79, + "learning_rate": 2.955786006059247e-07, + "loss": 0.127, + "step": 13957 + }, + { + "epoch": 1.79, + "learning_rate": 2.952276142831806e-07, + "loss": 0.1192, + "step": 13958 + }, + { + "epoch": 1.79, + "learning_rate": 2.9487683013498523e-07, + "loss": 0.1278, + "step": 13959 + }, + { + "epoch": 1.79, + "learning_rate": 2.9452624817641163e-07, + "loss": 0.1375, + "step": 13960 + }, + { + "epoch": 1.79, + "learning_rate": 2.9417586842252375e-07, + "loss": 0.1204, + "step": 13961 + }, + { + "epoch": 1.79, + "learning_rate": 2.9382569088837966e-07, + "loss": 0.1327, + "step": 13962 + }, + { + "epoch": 1.79, + "learning_rate": 2.934757155890272e-07, + "loss": 0.1236, + "step": 13963 + }, + { + "epoch": 1.79, + "learning_rate": 2.93125942539505e-07, + "loss": 0.1385, + "step": 13964 + }, + { + "epoch": 1.79, + "learning_rate": 2.9277637175484376e-07, + "loss": 0.126, + "step": 13965 + }, + { + "epoch": 1.79, + "learning_rate": 2.924270032500648e-07, + "loss": 0.114, + "step": 13966 + }, + { + "epoch": 1.79, + "learning_rate": 2.9207783704018223e-07, + "loss": 0.1242, + "step": 13967 + }, + { + "epoch": 1.79, + "learning_rate": 2.9172887314020017e-07, + "loss": 0.141, + "step": 13968 + }, + { + "epoch": 1.79, + "learning_rate": 2.913801115651144e-07, + "loss": 0.1275, + "step": 13969 + }, + { + "epoch": 1.79, + "learning_rate": 2.910315523299123e-07, + "loss": 0.1188, + "step": 13970 + }, + { + "epoch": 1.79, + "learning_rate": 2.906831954495715e-07, + "loss": 0.1357, + "step": 13971 + }, + { + "epoch": 1.79, + "learning_rate": 2.9033504093906207e-07, + "loss": 0.1374, + "step": 13972 + }, + { + "epoch": 1.79, + "learning_rate": 2.8998708881334437e-07, + "loss": 0.1215, + "step": 13973 + }, + { + "epoch": 1.79, + "learning_rate": 2.896393390873714e-07, + "loss": 0.1469, + "step": 13974 + }, + { + "epoch": 1.79, + "learning_rate": 2.892917917760873e-07, + "loss": 0.1322, + "step": 13975 + }, + { + "epoch": 1.79, + "learning_rate": 2.8894444689442526e-07, + "loss": 0.1264, + "step": 13976 + }, + { + "epoch": 1.79, + "learning_rate": 2.885973044573126e-07, + "loss": 0.1423, + "step": 13977 + }, + { + "epoch": 1.79, + "learning_rate": 2.8825036447966745e-07, + "loss": 0.1357, + "step": 13978 + }, + { + "epoch": 1.79, + "learning_rate": 2.8790362697639685e-07, + "loss": 0.1426, + "step": 13979 + }, + { + "epoch": 1.79, + "learning_rate": 2.8755709196240264e-07, + "loss": 0.1385, + "step": 13980 + }, + { + "epoch": 1.79, + "learning_rate": 2.8721075945257414e-07, + "loss": 0.1376, + "step": 13981 + }, + { + "epoch": 1.79, + "learning_rate": 2.868646294617966e-07, + "loss": 0.1429, + "step": 13982 + }, + { + "epoch": 1.79, + "learning_rate": 2.86518702004942e-07, + "loss": 0.1303, + "step": 13983 + }, + { + "epoch": 1.79, + "learning_rate": 2.8617297709687577e-07, + "loss": 0.1416, + "step": 13984 + }, + { + "epoch": 1.79, + "learning_rate": 2.858274547524559e-07, + "loss": 0.1344, + "step": 13985 + }, + { + "epoch": 1.79, + "learning_rate": 2.854821349865289e-07, + "loss": 0.1162, + "step": 13986 + }, + { + "epoch": 1.79, + "learning_rate": 2.8513701781393456e-07, + "loss": 0.1302, + "step": 13987 + }, + { + "epoch": 1.79, + "learning_rate": 2.8479210324950266e-07, + "loss": 0.1329, + "step": 13988 + }, + { + "epoch": 1.79, + "learning_rate": 2.8444739130805587e-07, + "loss": 0.1374, + "step": 13989 + }, + { + "epoch": 1.79, + "learning_rate": 2.841028820044067e-07, + "loss": 0.1225, + "step": 13990 + }, + { + "epoch": 1.79, + "learning_rate": 2.837585753533589e-07, + "loss": 0.1422, + "step": 13991 + }, + { + "epoch": 1.79, + "learning_rate": 2.8341447136970954e-07, + "loss": 0.1221, + "step": 13992 + }, + { + "epoch": 1.79, + "learning_rate": 2.8307057006824514e-07, + "loss": 0.1402, + "step": 13993 + }, + { + "epoch": 1.79, + "learning_rate": 2.827268714637421e-07, + "loss": 0.1404, + "step": 13994 + }, + { + "epoch": 1.79, + "learning_rate": 2.823833755709721e-07, + "loss": 0.1333, + "step": 13995 + }, + { + "epoch": 1.79, + "learning_rate": 2.820400824046954e-07, + "loss": 0.1396, + "step": 13996 + }, + { + "epoch": 1.79, + "learning_rate": 2.816969919796636e-07, + "loss": 0.1373, + "step": 13997 + }, + { + "epoch": 1.79, + "learning_rate": 2.813541043106205e-07, + "loss": 0.1336, + "step": 13998 + }, + { + "epoch": 1.79, + "learning_rate": 2.810114194122998e-07, + "loss": 0.1381, + "step": 13999 + }, + { + "epoch": 1.79, + "learning_rate": 2.806689372994292e-07, + "loss": 0.1478, + "step": 14000 + }, + { + "epoch": 1.79, + "learning_rate": 2.803266579867242e-07, + "loss": 0.1466, + "step": 14001 + }, + { + "epoch": 1.79, + "learning_rate": 2.7998458148889354e-07, + "loss": 0.1354, + "step": 14002 + }, + { + "epoch": 1.79, + "learning_rate": 2.796427078206382e-07, + "loss": 0.1343, + "step": 14003 + }, + { + "epoch": 1.79, + "learning_rate": 2.793010369966487e-07, + "loss": 0.1395, + "step": 14004 + }, + { + "epoch": 1.79, + "learning_rate": 2.789595690316066e-07, + "loss": 0.125, + "step": 14005 + }, + { + "epoch": 1.79, + "learning_rate": 2.7861830394018627e-07, + "loss": 0.1218, + "step": 14006 + }, + { + "epoch": 1.79, + "learning_rate": 2.7827724173705273e-07, + "loss": 0.1473, + "step": 14007 + }, + { + "epoch": 1.79, + "learning_rate": 2.779363824368619e-07, + "loss": 0.1318, + "step": 14008 + }, + { + "epoch": 1.79, + "learning_rate": 2.7759572605426057e-07, + "loss": 0.1296, + "step": 14009 + }, + { + "epoch": 1.79, + "learning_rate": 2.7725527260388905e-07, + "loss": 0.1313, + "step": 14010 + }, + { + "epoch": 1.79, + "learning_rate": 2.7691502210037744e-07, + "loss": 0.12, + "step": 14011 + }, + { + "epoch": 1.79, + "learning_rate": 2.7657497455834457e-07, + "loss": 0.1219, + "step": 14012 + }, + { + "epoch": 1.79, + "learning_rate": 2.762351299924054e-07, + "loss": 0.1303, + "step": 14013 + }, + { + "epoch": 1.79, + "learning_rate": 2.7589548841716274e-07, + "loss": 0.1185, + "step": 14014 + }, + { + "epoch": 1.79, + "learning_rate": 2.755560498472126e-07, + "loss": 0.1242, + "step": 14015 + }, + { + "epoch": 1.79, + "learning_rate": 2.752168142971406e-07, + "loss": 0.1217, + "step": 14016 + }, + { + "epoch": 1.79, + "learning_rate": 2.7487778178152457e-07, + "loss": 0.1107, + "step": 14017 + }, + { + "epoch": 1.79, + "learning_rate": 2.7453895231493445e-07, + "loss": 0.1327, + "step": 14018 + }, + { + "epoch": 1.79, + "learning_rate": 2.7420032591192856e-07, + "loss": 0.1258, + "step": 14019 + }, + { + "epoch": 1.79, + "learning_rate": 2.7386190258706033e-07, + "loss": 0.1356, + "step": 14020 + }, + { + "epoch": 1.79, + "learning_rate": 2.735236823548715e-07, + "loss": 0.1432, + "step": 14021 + }, + { + "epoch": 1.79, + "learning_rate": 2.73185665229897e-07, + "loss": 0.1338, + "step": 14022 + }, + { + "epoch": 1.79, + "learning_rate": 2.7284785122666136e-07, + "loss": 0.1313, + "step": 14023 + }, + { + "epoch": 1.8, + "learning_rate": 2.7251024035968134e-07, + "loss": 0.1493, + "step": 14024 + }, + { + "epoch": 1.8, + "learning_rate": 2.721728326434653e-07, + "loss": 0.1265, + "step": 14025 + }, + { + "epoch": 1.8, + "learning_rate": 2.718356280925116e-07, + "loss": 0.1418, + "step": 14026 + }, + { + "epoch": 1.8, + "learning_rate": 2.71498626721311e-07, + "loss": 0.1306, + "step": 14027 + }, + { + "epoch": 1.8, + "learning_rate": 2.711618285443457e-07, + "loss": 0.1284, + "step": 14028 + }, + { + "epoch": 1.8, + "learning_rate": 2.7082523357608856e-07, + "loss": 0.1167, + "step": 14029 + }, + { + "epoch": 1.8, + "learning_rate": 2.7048884183100313e-07, + "loss": 0.1435, + "step": 14030 + }, + { + "epoch": 1.8, + "learning_rate": 2.70152653323546e-07, + "loss": 0.148, + "step": 14031 + }, + { + "epoch": 1.8, + "learning_rate": 2.6981666806816185e-07, + "loss": 0.1389, + "step": 14032 + }, + { + "epoch": 1.8, + "learning_rate": 2.694808860792919e-07, + "loss": 0.1446, + "step": 14033 + }, + { + "epoch": 1.8, + "learning_rate": 2.6914530737136346e-07, + "loss": 0.1399, + "step": 14034 + }, + { + "epoch": 1.8, + "learning_rate": 2.6880993195879614e-07, + "loss": 0.1286, + "step": 14035 + }, + { + "epoch": 1.8, + "learning_rate": 2.684747598560045e-07, + "loss": 0.1311, + "step": 14036 + }, + { + "epoch": 1.8, + "learning_rate": 2.6813979107738864e-07, + "loss": 0.1293, + "step": 14037 + }, + { + "epoch": 1.8, + "learning_rate": 2.678050256373449e-07, + "loss": 0.1312, + "step": 14038 + }, + { + "epoch": 1.8, + "learning_rate": 2.674704635502584e-07, + "loss": 0.1494, + "step": 14039 + }, + { + "epoch": 1.8, + "learning_rate": 2.6713610483050654e-07, + "loss": 0.1294, + "step": 14040 + }, + { + "epoch": 1.8, + "learning_rate": 2.668019494924562e-07, + "loss": 0.1347, + "step": 14041 + }, + { + "epoch": 1.8, + "learning_rate": 2.6646799755046746e-07, + "loss": 0.1334, + "step": 14042 + }, + { + "epoch": 1.8, + "learning_rate": 2.661342490188917e-07, + "loss": 0.1245, + "step": 14043 + }, + { + "epoch": 1.8, + "learning_rate": 2.658007039120697e-07, + "loss": 0.1565, + "step": 14044 + }, + { + "epoch": 1.8, + "learning_rate": 2.654673622443349e-07, + "loss": 0.1274, + "step": 14045 + }, + { + "epoch": 1.8, + "learning_rate": 2.65134224030012e-07, + "loss": 0.1152, + "step": 14046 + }, + { + "epoch": 1.8, + "learning_rate": 2.6480128928341675e-07, + "loss": 0.1385, + "step": 14047 + }, + { + "epoch": 1.8, + "learning_rate": 2.6446855801885606e-07, + "loss": 0.1473, + "step": 14048 + }, + { + "epoch": 1.8, + "learning_rate": 2.64136030250628e-07, + "loss": 0.132, + "step": 14049 + }, + { + "epoch": 1.8, + "learning_rate": 2.638037059930215e-07, + "loss": 0.1393, + "step": 14050 + }, + { + "epoch": 1.8, + "learning_rate": 2.634715852603187e-07, + "loss": 0.138, + "step": 14051 + }, + { + "epoch": 1.8, + "learning_rate": 2.631396680667908e-07, + "loss": 0.1308, + "step": 14052 + }, + { + "epoch": 1.8, + "learning_rate": 2.6280795442669925e-07, + "loss": 0.1224, + "step": 14053 + }, + { + "epoch": 1.8, + "learning_rate": 2.6247644435430263e-07, + "loss": 0.1334, + "step": 14054 + }, + { + "epoch": 1.8, + "learning_rate": 2.621451378638418e-07, + "loss": 0.121, + "step": 14055 + }, + { + "epoch": 1.8, + "learning_rate": 2.618140349695575e-07, + "loss": 0.1283, + "step": 14056 + }, + { + "epoch": 1.8, + "learning_rate": 2.6148313568567674e-07, + "loss": 0.1348, + "step": 14057 + }, + { + "epoch": 1.8, + "learning_rate": 2.611524400264187e-07, + "loss": 0.137, + "step": 14058 + }, + { + "epoch": 1.8, + "learning_rate": 2.6082194800599424e-07, + "loss": 0.136, + "step": 14059 + }, + { + "epoch": 1.8, + "learning_rate": 2.6049165963860425e-07, + "loss": 0.1278, + "step": 14060 + }, + { + "epoch": 1.8, + "learning_rate": 2.601615749384451e-07, + "loss": 0.1158, + "step": 14061 + }, + { + "epoch": 1.8, + "learning_rate": 2.5983169391969823e-07, + "loss": 0.1315, + "step": 14062 + }, + { + "epoch": 1.8, + "learning_rate": 2.595020165965401e-07, + "loss": 0.1277, + "step": 14063 + }, + { + "epoch": 1.8, + "learning_rate": 2.591725429831382e-07, + "loss": 0.1361, + "step": 14064 + }, + { + "epoch": 1.8, + "learning_rate": 2.5884327309365074e-07, + "loss": 0.1316, + "step": 14065 + }, + { + "epoch": 1.8, + "learning_rate": 2.5851420694222697e-07, + "loss": 0.1288, + "step": 14066 + }, + { + "epoch": 1.8, + "learning_rate": 2.581853445430077e-07, + "loss": 0.14, + "step": 14067 + }, + { + "epoch": 1.8, + "learning_rate": 2.5785668591012393e-07, + "loss": 0.1408, + "step": 14068 + }, + { + "epoch": 1.8, + "learning_rate": 2.57528231057701e-07, + "loss": 0.1315, + "step": 14069 + }, + { + "epoch": 1.8, + "learning_rate": 2.571999799998509e-07, + "loss": 0.1298, + "step": 14070 + }, + { + "epoch": 1.8, + "learning_rate": 2.568719327506808e-07, + "loss": 0.1307, + "step": 14071 + }, + { + "epoch": 1.8, + "learning_rate": 2.565440893242882e-07, + "loss": 0.1372, + "step": 14072 + }, + { + "epoch": 1.8, + "learning_rate": 2.5621644973475914e-07, + "loss": 0.1244, + "step": 14073 + }, + { + "epoch": 1.8, + "learning_rate": 2.558890139961745e-07, + "loss": 0.1331, + "step": 14074 + }, + { + "epoch": 1.8, + "learning_rate": 2.5556178212260474e-07, + "loss": 0.1365, + "step": 14075 + }, + { + "epoch": 1.8, + "learning_rate": 2.552347541281114e-07, + "loss": 0.1453, + "step": 14076 + }, + { + "epoch": 1.8, + "learning_rate": 2.549079300267482e-07, + "loss": 0.1241, + "step": 14077 + }, + { + "epoch": 1.8, + "learning_rate": 2.5458130983255835e-07, + "loss": 0.1269, + "step": 14078 + }, + { + "epoch": 1.8, + "learning_rate": 2.5425489355957956e-07, + "loss": 0.123, + "step": 14079 + }, + { + "epoch": 1.8, + "learning_rate": 2.539286812218361e-07, + "loss": 0.1367, + "step": 14080 + }, + { + "epoch": 1.8, + "learning_rate": 2.5360267283334796e-07, + "loss": 0.134, + "step": 14081 + }, + { + "epoch": 1.8, + "learning_rate": 2.5327686840812326e-07, + "loss": 0.131, + "step": 14082 + }, + { + "epoch": 1.8, + "learning_rate": 2.5295126796016366e-07, + "loss": 0.1135, + "step": 14083 + }, + { + "epoch": 1.8, + "learning_rate": 2.526258715034602e-07, + "loss": 0.1244, + "step": 14084 + }, + { + "epoch": 1.8, + "learning_rate": 2.523006790519955e-07, + "loss": 0.1398, + "step": 14085 + }, + { + "epoch": 1.8, + "learning_rate": 2.5197569061974404e-07, + "loss": 0.1485, + "step": 14086 + }, + { + "epoch": 1.8, + "learning_rate": 2.5165090622067343e-07, + "loss": 0.1271, + "step": 14087 + }, + { + "epoch": 1.8, + "learning_rate": 2.513263258687365e-07, + "loss": 0.1241, + "step": 14088 + }, + { + "epoch": 1.8, + "learning_rate": 2.510019495778837e-07, + "loss": 0.1406, + "step": 14089 + }, + { + "epoch": 1.8, + "learning_rate": 2.5067777736205444e-07, + "loss": 0.1259, + "step": 14090 + }, + { + "epoch": 1.8, + "learning_rate": 2.503538092351782e-07, + "loss": 0.1324, + "step": 14091 + }, + { + "epoch": 1.8, + "learning_rate": 2.5003004521117646e-07, + "loss": 0.1234, + "step": 14092 + }, + { + "epoch": 1.8, + "learning_rate": 2.4970648530396157e-07, + "loss": 0.1237, + "step": 14093 + }, + { + "epoch": 1.8, + "learning_rate": 2.4938312952744016e-07, + "loss": 0.1203, + "step": 14094 + }, + { + "epoch": 1.8, + "learning_rate": 2.490599778955055e-07, + "loss": 0.109, + "step": 14095 + }, + { + "epoch": 1.8, + "learning_rate": 2.4873703042204323e-07, + "loss": 0.1341, + "step": 14096 + }, + { + "epoch": 1.8, + "learning_rate": 2.484142871209344e-07, + "loss": 0.1311, + "step": 14097 + }, + { + "epoch": 1.8, + "learning_rate": 2.480917480060441e-07, + "loss": 0.1305, + "step": 14098 + }, + { + "epoch": 1.8, + "learning_rate": 2.477694130912356e-07, + "loss": 0.1438, + "step": 14099 + }, + { + "epoch": 1.8, + "learning_rate": 2.474472823903584e-07, + "loss": 0.1286, + "step": 14100 + }, + { + "epoch": 1.8, + "learning_rate": 2.4712535591725706e-07, + "loss": 0.134, + "step": 14101 + }, + { + "epoch": 1.81, + "learning_rate": 2.4680363368576376e-07, + "loss": 0.1322, + "step": 14102 + }, + { + "epoch": 1.81, + "learning_rate": 2.464821157097036e-07, + "loss": 0.1463, + "step": 14103 + }, + { + "epoch": 1.81, + "learning_rate": 2.461608020028944e-07, + "loss": 0.133, + "step": 14104 + }, + { + "epoch": 1.81, + "learning_rate": 2.458396925791434e-07, + "loss": 0.1516, + "step": 14105 + }, + { + "epoch": 1.81, + "learning_rate": 2.4551878745224745e-07, + "loss": 0.1394, + "step": 14106 + }, + { + "epoch": 1.81, + "learning_rate": 2.4519808663599876e-07, + "loss": 0.1359, + "step": 14107 + }, + { + "epoch": 1.81, + "learning_rate": 2.44877590144178e-07, + "loss": 0.1369, + "step": 14108 + }, + { + "epoch": 1.81, + "learning_rate": 2.445572979905575e-07, + "loss": 0.1413, + "step": 14109 + }, + { + "epoch": 1.81, + "learning_rate": 2.442372101889007e-07, + "loss": 0.1277, + "step": 14110 + }, + { + "epoch": 1.81, + "learning_rate": 2.4391732675296207e-07, + "loss": 0.1317, + "step": 14111 + }, + { + "epoch": 1.81, + "learning_rate": 2.4359764769648907e-07, + "loss": 0.1296, + "step": 14112 + }, + { + "epoch": 1.81, + "learning_rate": 2.4327817303321786e-07, + "loss": 0.1322, + "step": 14113 + }, + { + "epoch": 1.81, + "learning_rate": 2.4295890277687695e-07, + "loss": 0.1322, + "step": 14114 + }, + { + "epoch": 1.81, + "learning_rate": 2.4263983694118754e-07, + "loss": 0.122, + "step": 14115 + }, + { + "epoch": 1.81, + "learning_rate": 2.423209755398587e-07, + "loss": 0.133, + "step": 14116 + }, + { + "epoch": 1.81, + "learning_rate": 2.4200231858659384e-07, + "loss": 0.1273, + "step": 14117 + }, + { + "epoch": 1.81, + "learning_rate": 2.416838660950854e-07, + "loss": 0.1199, + "step": 14118 + }, + { + "epoch": 1.81, + "learning_rate": 2.4136561807901916e-07, + "loss": 0.1283, + "step": 14119 + }, + { + "epoch": 1.81, + "learning_rate": 2.410475745520702e-07, + "loss": 0.1256, + "step": 14120 + }, + { + "epoch": 1.81, + "learning_rate": 2.4072973552790535e-07, + "loss": 0.1308, + "step": 14121 + }, + { + "epoch": 1.81, + "learning_rate": 2.4041210102018375e-07, + "loss": 0.1376, + "step": 14122 + }, + { + "epoch": 1.81, + "learning_rate": 2.40094671042555e-07, + "loss": 0.1294, + "step": 14123 + }, + { + "epoch": 1.81, + "learning_rate": 2.397774456086577e-07, + "loss": 0.1387, + "step": 14124 + }, + { + "epoch": 1.81, + "learning_rate": 2.3946042473212526e-07, + "loss": 0.1443, + "step": 14125 + }, + { + "epoch": 1.81, + "learning_rate": 2.391436084265814e-07, + "loss": 0.1281, + "step": 14126 + }, + { + "epoch": 1.81, + "learning_rate": 2.3882699670563947e-07, + "loss": 0.122, + "step": 14127 + }, + { + "epoch": 1.81, + "learning_rate": 2.385105895829054e-07, + "loss": 0.1181, + "step": 14128 + }, + { + "epoch": 1.81, + "learning_rate": 2.3819438707197495e-07, + "loss": 0.1386, + "step": 14129 + }, + { + "epoch": 1.81, + "learning_rate": 2.378783891864378e-07, + "loss": 0.1388, + "step": 14130 + }, + { + "epoch": 1.81, + "learning_rate": 2.3756259593987086e-07, + "loss": 0.1317, + "step": 14131 + }, + { + "epoch": 1.81, + "learning_rate": 2.372470073458466e-07, + "loss": 0.1193, + "step": 14132 + }, + { + "epoch": 1.81, + "learning_rate": 2.3693162341792532e-07, + "loss": 0.1402, + "step": 14133 + }, + { + "epoch": 1.81, + "learning_rate": 2.3661644416966057e-07, + "loss": 0.1308, + "step": 14134 + }, + { + "epoch": 1.81, + "learning_rate": 2.3630146961459543e-07, + "loss": 0.1217, + "step": 14135 + }, + { + "epoch": 1.81, + "learning_rate": 2.3598669976626576e-07, + "loss": 0.1354, + "step": 14136 + }, + { + "epoch": 1.81, + "learning_rate": 2.3567213463819738e-07, + "loss": 0.1306, + "step": 14137 + }, + { + "epoch": 1.81, + "learning_rate": 2.353577742439084e-07, + "loss": 0.1312, + "step": 14138 + }, + { + "epoch": 1.81, + "learning_rate": 2.3504361859690628e-07, + "loss": 0.1324, + "step": 14139 + }, + { + "epoch": 1.81, + "learning_rate": 2.347296677106925e-07, + "loss": 0.1428, + "step": 14140 + }, + { + "epoch": 1.81, + "learning_rate": 2.344159215987585e-07, + "loss": 0.1499, + "step": 14141 + }, + { + "epoch": 1.81, + "learning_rate": 2.341023802745851e-07, + "loss": 0.1526, + "step": 14142 + }, + { + "epoch": 1.81, + "learning_rate": 2.3378904375164714e-07, + "loss": 0.1267, + "step": 14143 + }, + { + "epoch": 1.81, + "learning_rate": 2.3347591204340881e-07, + "loss": 0.1259, + "step": 14144 + }, + { + "epoch": 1.81, + "learning_rate": 2.3316298516332604e-07, + "loss": 0.1332, + "step": 14145 + }, + { + "epoch": 1.81, + "learning_rate": 2.3285026312484583e-07, + "loss": 0.1226, + "step": 14146 + }, + { + "epoch": 1.81, + "learning_rate": 2.3253774594140633e-07, + "loss": 0.1177, + "step": 14147 + }, + { + "epoch": 1.81, + "learning_rate": 2.32225433626439e-07, + "loss": 0.1407, + "step": 14148 + }, + { + "epoch": 1.81, + "learning_rate": 2.3191332619336204e-07, + "loss": 0.1188, + "step": 14149 + }, + { + "epoch": 1.81, + "learning_rate": 2.3160142365558914e-07, + "loss": 0.1242, + "step": 14150 + }, + { + "epoch": 1.81, + "learning_rate": 2.312897260265229e-07, + "loss": 0.1255, + "step": 14151 + }, + { + "epoch": 1.81, + "learning_rate": 2.309782333195576e-07, + "loss": 0.1325, + "step": 14152 + }, + { + "epoch": 1.81, + "learning_rate": 2.3066694554807867e-07, + "loss": 0.1319, + "step": 14153 + }, + { + "epoch": 1.81, + "learning_rate": 2.3035586272546207e-07, + "loss": 0.1497, + "step": 14154 + }, + { + "epoch": 1.81, + "learning_rate": 2.300449848650782e-07, + "loss": 0.1271, + "step": 14155 + }, + { + "epoch": 1.81, + "learning_rate": 2.2973431198028417e-07, + "loss": 0.1334, + "step": 14156 + }, + { + "epoch": 1.81, + "learning_rate": 2.2942384408442986e-07, + "loss": 0.1186, + "step": 14157 + }, + { + "epoch": 1.81, + "learning_rate": 2.2911358119085792e-07, + "loss": 0.1151, + "step": 14158 + }, + { + "epoch": 1.81, + "learning_rate": 2.2880352331290102e-07, + "loss": 0.136, + "step": 14159 + }, + { + "epoch": 1.81, + "learning_rate": 2.2849367046388294e-07, + "loss": 0.1202, + "step": 14160 + }, + { + "epoch": 1.81, + "learning_rate": 2.2818402265711858e-07, + "loss": 0.1297, + "step": 14161 + }, + { + "epoch": 1.81, + "learning_rate": 2.27874579905914e-07, + "loss": 0.1249, + "step": 14162 + }, + { + "epoch": 1.81, + "learning_rate": 2.2756534222356687e-07, + "loss": 0.1215, + "step": 14163 + }, + { + "epoch": 1.81, + "learning_rate": 2.2725630962336542e-07, + "loss": 0.1305, + "step": 14164 + }, + { + "epoch": 1.81, + "learning_rate": 2.2694748211858964e-07, + "loss": 0.1423, + "step": 14165 + }, + { + "epoch": 1.81, + "learning_rate": 2.2663885972251165e-07, + "loss": 0.1324, + "step": 14166 + }, + { + "epoch": 1.81, + "learning_rate": 2.2633044244839143e-07, + "loss": 0.1337, + "step": 14167 + }, + { + "epoch": 1.81, + "learning_rate": 2.2602223030948445e-07, + "loss": 0.1214, + "step": 14168 + }, + { + "epoch": 1.81, + "learning_rate": 2.2571422331903458e-07, + "loss": 0.1374, + "step": 14169 + }, + { + "epoch": 1.81, + "learning_rate": 2.2540642149027735e-07, + "loss": 0.128, + "step": 14170 + }, + { + "epoch": 1.81, + "learning_rate": 2.2509882483643942e-07, + "loss": 0.1342, + "step": 14171 + }, + { + "epoch": 1.81, + "learning_rate": 2.2479143337073904e-07, + "loss": 0.125, + "step": 14172 + }, + { + "epoch": 1.81, + "learning_rate": 2.2448424710638684e-07, + "loss": 0.1248, + "step": 14173 + }, + { + "epoch": 1.81, + "learning_rate": 2.2417726605658164e-07, + "loss": 0.1289, + "step": 14174 + }, + { + "epoch": 1.81, + "learning_rate": 2.2387049023451458e-07, + "loss": 0.124, + "step": 14175 + }, + { + "epoch": 1.81, + "learning_rate": 2.2356391965337064e-07, + "loss": 0.1253, + "step": 14176 + }, + { + "epoch": 1.81, + "learning_rate": 2.2325755432632267e-07, + "loss": 0.1323, + "step": 14177 + }, + { + "epoch": 1.81, + "learning_rate": 2.2295139426653622e-07, + "loss": 0.1189, + "step": 14178 + }, + { + "epoch": 1.81, + "learning_rate": 2.226454394871669e-07, + "loss": 0.1182, + "step": 14179 + }, + { + "epoch": 1.82, + "learning_rate": 2.2233969000136357e-07, + "loss": 0.1144, + "step": 14180 + }, + { + "epoch": 1.82, + "learning_rate": 2.2203414582226357e-07, + "loss": 0.1284, + "step": 14181 + }, + { + "epoch": 1.82, + "learning_rate": 2.2172880696299692e-07, + "loss": 0.1423, + "step": 14182 + }, + { + "epoch": 1.82, + "learning_rate": 2.2142367343668592e-07, + "loss": 0.1272, + "step": 14183 + }, + { + "epoch": 1.82, + "learning_rate": 2.2111874525644228e-07, + "loss": 0.1269, + "step": 14184 + }, + { + "epoch": 1.82, + "learning_rate": 2.2081402243536833e-07, + "loss": 0.1218, + "step": 14185 + }, + { + "epoch": 1.82, + "learning_rate": 2.2050950498656078e-07, + "loss": 0.118, + "step": 14186 + }, + { + "epoch": 1.82, + "learning_rate": 2.2020519292310361e-07, + "loss": 0.1306, + "step": 14187 + }, + { + "epoch": 1.82, + "learning_rate": 2.199010862580747e-07, + "loss": 0.127, + "step": 14188 + }, + { + "epoch": 1.82, + "learning_rate": 2.1959718500454196e-07, + "loss": 0.1378, + "step": 14189 + }, + { + "epoch": 1.82, + "learning_rate": 2.1929348917556436e-07, + "loss": 0.1489, + "step": 14190 + }, + { + "epoch": 1.82, + "learning_rate": 2.189899987841937e-07, + "loss": 0.1323, + "step": 14191 + }, + { + "epoch": 1.82, + "learning_rate": 2.186867138434695e-07, + "loss": 0.1341, + "step": 14192 + }, + { + "epoch": 1.82, + "learning_rate": 2.183836343664264e-07, + "loss": 0.1203, + "step": 14193 + }, + { + "epoch": 1.82, + "learning_rate": 2.1808076036608783e-07, + "loss": 0.1359, + "step": 14194 + }, + { + "epoch": 1.82, + "learning_rate": 2.1777809185546894e-07, + "loss": 0.1369, + "step": 14195 + }, + { + "epoch": 1.82, + "learning_rate": 2.17475628847576e-07, + "loss": 0.1252, + "step": 14196 + }, + { + "epoch": 1.82, + "learning_rate": 2.171733713554064e-07, + "loss": 0.138, + "step": 14197 + }, + { + "epoch": 1.82, + "learning_rate": 2.1687131939194862e-07, + "loss": 0.1346, + "step": 14198 + }, + { + "epoch": 1.82, + "learning_rate": 2.165694729701834e-07, + "loss": 0.1442, + "step": 14199 + }, + { + "epoch": 1.82, + "learning_rate": 2.1626783210308032e-07, + "loss": 0.1163, + "step": 14200 + }, + { + "epoch": 1.82, + "learning_rate": 2.15966396803603e-07, + "loss": 0.127, + "step": 14201 + }, + { + "epoch": 1.82, + "learning_rate": 2.1566516708470487e-07, + "loss": 0.1376, + "step": 14202 + }, + { + "epoch": 1.82, + "learning_rate": 2.1536414295932896e-07, + "loss": 0.1438, + "step": 14203 + }, + { + "epoch": 1.82, + "learning_rate": 2.1506332444041212e-07, + "loss": 0.1284, + "step": 14204 + }, + { + "epoch": 1.82, + "learning_rate": 2.1476271154088013e-07, + "loss": 0.1245, + "step": 14205 + }, + { + "epoch": 1.82, + "learning_rate": 2.1446230427365323e-07, + "loss": 0.1267, + "step": 14206 + }, + { + "epoch": 1.82, + "learning_rate": 2.1416210265163828e-07, + "loss": 0.1361, + "step": 14207 + }, + { + "epoch": 1.82, + "learning_rate": 2.1386210668773554e-07, + "loss": 0.1427, + "step": 14208 + }, + { + "epoch": 1.82, + "learning_rate": 2.1356231639483917e-07, + "loss": 0.1232, + "step": 14209 + }, + { + "epoch": 1.82, + "learning_rate": 2.1326273178582822e-07, + "loss": 0.1165, + "step": 14210 + }, + { + "epoch": 1.82, + "learning_rate": 2.1296335287357918e-07, + "loss": 0.1476, + "step": 14211 + }, + { + "epoch": 1.82, + "learning_rate": 2.1266417967095665e-07, + "loss": 0.1321, + "step": 14212 + }, + { + "epoch": 1.82, + "learning_rate": 2.123652121908154e-07, + "loss": 0.1463, + "step": 14213 + }, + { + "epoch": 1.82, + "learning_rate": 2.1206645044600404e-07, + "loss": 0.1194, + "step": 14214 + }, + { + "epoch": 1.82, + "learning_rate": 2.1176789444936065e-07, + "loss": 0.1491, + "step": 14215 + }, + { + "epoch": 1.82, + "learning_rate": 2.114695442137149e-07, + "loss": 0.1271, + "step": 14216 + }, + { + "epoch": 1.82, + "learning_rate": 2.1117139975188716e-07, + "loss": 0.1433, + "step": 14217 + }, + { + "epoch": 1.82, + "learning_rate": 2.1087346107668937e-07, + "loss": 0.129, + "step": 14218 + }, + { + "epoch": 1.82, + "learning_rate": 2.1057572820092576e-07, + "loss": 0.1342, + "step": 14219 + }, + { + "epoch": 1.82, + "learning_rate": 2.1027820113738884e-07, + "loss": 0.1379, + "step": 14220 + }, + { + "epoch": 1.82, + "learning_rate": 2.099808798988656e-07, + "loss": 0.1269, + "step": 14221 + }, + { + "epoch": 1.82, + "learning_rate": 2.0968376449813198e-07, + "loss": 0.1291, + "step": 14222 + }, + { + "epoch": 1.82, + "learning_rate": 2.093868549479544e-07, + "loss": 0.1405, + "step": 14223 + }, + { + "epoch": 1.82, + "learning_rate": 2.0909015126109488e-07, + "loss": 0.1344, + "step": 14224 + }, + { + "epoch": 1.82, + "learning_rate": 2.0879365345030044e-07, + "loss": 0.1303, + "step": 14225 + }, + { + "epoch": 1.82, + "learning_rate": 2.0849736152831256e-07, + "loss": 0.1295, + "step": 14226 + }, + { + "epoch": 1.82, + "learning_rate": 2.0820127550786551e-07, + "loss": 0.1281, + "step": 14227 + }, + { + "epoch": 1.82, + "learning_rate": 2.0790539540168074e-07, + "loss": 0.1321, + "step": 14228 + }, + { + "epoch": 1.82, + "learning_rate": 2.0760972122247425e-07, + "loss": 0.1187, + "step": 14229 + }, + { + "epoch": 1.82, + "learning_rate": 2.0731425298295083e-07, + "loss": 0.1365, + "step": 14230 + }, + { + "epoch": 1.82, + "learning_rate": 2.070189906958081e-07, + "loss": 0.1293, + "step": 14231 + }, + { + "epoch": 1.82, + "learning_rate": 2.0672393437373372e-07, + "loss": 0.1318, + "step": 14232 + }, + { + "epoch": 1.82, + "learning_rate": 2.06429084029407e-07, + "loss": 0.1385, + "step": 14233 + }, + { + "epoch": 1.82, + "learning_rate": 2.061344396754994e-07, + "loss": 0.1232, + "step": 14234 + }, + { + "epoch": 1.82, + "learning_rate": 2.058400013246703e-07, + "loss": 0.1499, + "step": 14235 + }, + { + "epoch": 1.82, + "learning_rate": 2.0554576898957346e-07, + "loss": 0.1333, + "step": 14236 + }, + { + "epoch": 1.82, + "learning_rate": 2.052517426828532e-07, + "loss": 0.1337, + "step": 14237 + }, + { + "epoch": 1.82, + "learning_rate": 2.0495792241714386e-07, + "loss": 0.1372, + "step": 14238 + }, + { + "epoch": 1.82, + "learning_rate": 2.04664308205072e-07, + "loss": 0.1239, + "step": 14239 + }, + { + "epoch": 1.82, + "learning_rate": 2.0437090005925475e-07, + "loss": 0.1425, + "step": 14240 + }, + { + "epoch": 1.82, + "learning_rate": 2.0407769799229925e-07, + "loss": 0.1466, + "step": 14241 + }, + { + "epoch": 1.82, + "learning_rate": 2.0378470201680767e-07, + "loss": 0.1326, + "step": 14242 + }, + { + "epoch": 1.82, + "learning_rate": 2.0349191214536767e-07, + "loss": 0.1286, + "step": 14243 + }, + { + "epoch": 1.82, + "learning_rate": 2.0319932839056365e-07, + "loss": 0.119, + "step": 14244 + }, + { + "epoch": 1.82, + "learning_rate": 2.029069507649678e-07, + "loss": 0.1194, + "step": 14245 + }, + { + "epoch": 1.82, + "learning_rate": 2.0261477928114282e-07, + "loss": 0.1169, + "step": 14246 + }, + { + "epoch": 1.82, + "learning_rate": 2.0232281395164587e-07, + "loss": 0.1198, + "step": 14247 + }, + { + "epoch": 1.82, + "learning_rate": 2.0203105478902252e-07, + "loss": 0.1334, + "step": 14248 + }, + { + "epoch": 1.82, + "learning_rate": 2.0173950180581047e-07, + "loss": 0.132, + "step": 14249 + }, + { + "epoch": 1.82, + "learning_rate": 2.0144815501453863e-07, + "loss": 0.1159, + "step": 14250 + }, + { + "epoch": 1.82, + "learning_rate": 2.0115701442772528e-07, + "loss": 0.1224, + "step": 14251 + }, + { + "epoch": 1.82, + "learning_rate": 2.0086608005788376e-07, + "loss": 0.1222, + "step": 14252 + }, + { + "epoch": 1.82, + "learning_rate": 2.0057535191751465e-07, + "loss": 0.139, + "step": 14253 + }, + { + "epoch": 1.82, + "learning_rate": 2.002848300191118e-07, + "loss": 0.1426, + "step": 14254 + }, + { + "epoch": 1.82, + "learning_rate": 1.9999451437515915e-07, + "loss": 0.1286, + "step": 14255 + }, + { + "epoch": 1.82, + "learning_rate": 1.997044049981328e-07, + "loss": 0.1278, + "step": 14256 + }, + { + "epoch": 1.82, + "learning_rate": 1.994145019004984e-07, + "loss": 0.1365, + "step": 14257 + }, + { + "epoch": 1.83, + "learning_rate": 1.9912480509471476e-07, + "loss": 0.1377, + "step": 14258 + }, + { + "epoch": 1.83, + "learning_rate": 1.988353145932298e-07, + "loss": 0.1397, + "step": 14259 + }, + { + "epoch": 1.83, + "learning_rate": 1.985460304084852e-07, + "loss": 0.1309, + "step": 14260 + }, + { + "epoch": 1.83, + "learning_rate": 1.9825695255290934e-07, + "loss": 0.1257, + "step": 14261 + }, + { + "epoch": 1.83, + "learning_rate": 1.9796808103892783e-07, + "loss": 0.122, + "step": 14262 + }, + { + "epoch": 1.83, + "learning_rate": 1.9767941587895246e-07, + "loss": 0.1451, + "step": 14263 + }, + { + "epoch": 1.83, + "learning_rate": 1.9739095708538714e-07, + "loss": 0.1326, + "step": 14264 + }, + { + "epoch": 1.83, + "learning_rate": 1.9710270467062865e-07, + "loss": 0.1395, + "step": 14265 + }, + { + "epoch": 1.83, + "learning_rate": 1.9681465864706372e-07, + "loss": 0.1226, + "step": 14266 + }, + { + "epoch": 1.83, + "learning_rate": 1.9652681902707028e-07, + "loss": 0.136, + "step": 14267 + }, + { + "epoch": 1.83, + "learning_rate": 1.9623918582301726e-07, + "loss": 0.122, + "step": 14268 + }, + { + "epoch": 1.83, + "learning_rate": 1.9595175904726481e-07, + "loss": 0.1326, + "step": 14269 + }, + { + "epoch": 1.83, + "learning_rate": 1.9566453871216417e-07, + "loss": 0.1144, + "step": 14270 + }, + { + "epoch": 1.83, + "learning_rate": 1.953775248300588e-07, + "loss": 0.1306, + "step": 14271 + }, + { + "epoch": 1.83, + "learning_rate": 1.9509071741328155e-07, + "loss": 0.1333, + "step": 14272 + }, + { + "epoch": 1.83, + "learning_rate": 1.9480411647415708e-07, + "loss": 0.1166, + "step": 14273 + }, + { + "epoch": 1.83, + "learning_rate": 1.9451772202500163e-07, + "loss": 0.1399, + "step": 14274 + }, + { + "epoch": 1.83, + "learning_rate": 1.94231534078122e-07, + "loss": 0.1256, + "step": 14275 + }, + { + "epoch": 1.83, + "learning_rate": 1.9394555264581672e-07, + "loss": 0.1323, + "step": 14276 + }, + { + "epoch": 1.83, + "learning_rate": 1.936597777403737e-07, + "loss": 0.1348, + "step": 14277 + }, + { + "epoch": 1.83, + "learning_rate": 1.9337420937407536e-07, + "loss": 0.1209, + "step": 14278 + }, + { + "epoch": 1.83, + "learning_rate": 1.9308884755919132e-07, + "loss": 0.1325, + "step": 14279 + }, + { + "epoch": 1.83, + "learning_rate": 1.9280369230798568e-07, + "loss": 0.1265, + "step": 14280 + }, + { + "epoch": 1.83, + "learning_rate": 1.925187436327114e-07, + "loss": 0.1307, + "step": 14281 + }, + { + "epoch": 1.83, + "learning_rate": 1.9223400154561313e-07, + "loss": 0.1279, + "step": 14282 + }, + { + "epoch": 1.83, + "learning_rate": 1.9194946605892773e-07, + "loss": 0.1266, + "step": 14283 + }, + { + "epoch": 1.83, + "learning_rate": 1.9166513718488155e-07, + "loss": 0.1344, + "step": 14284 + }, + { + "epoch": 1.83, + "learning_rate": 1.9138101493569428e-07, + "loss": 0.1319, + "step": 14285 + }, + { + "epoch": 1.83, + "learning_rate": 1.9109709932357333e-07, + "loss": 0.141, + "step": 14286 + }, + { + "epoch": 1.83, + "learning_rate": 1.9081339036071956e-07, + "loss": 0.1299, + "step": 14287 + }, + { + "epoch": 1.83, + "learning_rate": 1.9052988805932538e-07, + "loss": 0.1184, + "step": 14288 + }, + { + "epoch": 1.83, + "learning_rate": 1.902465924315733e-07, + "loss": 0.1367, + "step": 14289 + }, + { + "epoch": 1.83, + "learning_rate": 1.899635034896369e-07, + "loss": 0.1314, + "step": 14290 + }, + { + "epoch": 1.83, + "learning_rate": 1.8968062124568142e-07, + "loss": 0.1289, + "step": 14291 + }, + { + "epoch": 1.83, + "learning_rate": 1.8939794571186332e-07, + "loss": 0.1322, + "step": 14292 + }, + { + "epoch": 1.83, + "learning_rate": 1.8911547690032838e-07, + "loss": 0.1397, + "step": 14293 + }, + { + "epoch": 1.83, + "learning_rate": 1.8883321482321583e-07, + "loss": 0.1455, + "step": 14294 + }, + { + "epoch": 1.83, + "learning_rate": 1.8855115949265535e-07, + "loss": 0.1354, + "step": 14295 + }, + { + "epoch": 1.83, + "learning_rate": 1.882693109207684e-07, + "loss": 0.1298, + "step": 14296 + }, + { + "epoch": 1.83, + "learning_rate": 1.879876691196636e-07, + "loss": 0.1073, + "step": 14297 + }, + { + "epoch": 1.83, + "learning_rate": 1.8770623410144628e-07, + "loss": 0.1425, + "step": 14298 + }, + { + "epoch": 1.83, + "learning_rate": 1.8742500587820955e-07, + "loss": 0.1285, + "step": 14299 + }, + { + "epoch": 1.83, + "learning_rate": 1.8714398446203873e-07, + "loss": 0.1518, + "step": 14300 + }, + { + "epoch": 1.83, + "learning_rate": 1.8686316986500974e-07, + "loss": 0.1396, + "step": 14301 + }, + { + "epoch": 1.83, + "learning_rate": 1.86582562099189e-07, + "loss": 0.1251, + "step": 14302 + }, + { + "epoch": 1.83, + "learning_rate": 1.8630216117663747e-07, + "loss": 0.1233, + "step": 14303 + }, + { + "epoch": 1.83, + "learning_rate": 1.86021967109401e-07, + "loss": 0.1298, + "step": 14304 + }, + { + "epoch": 1.83, + "learning_rate": 1.8574197990952225e-07, + "loss": 0.1311, + "step": 14305 + }, + { + "epoch": 1.83, + "learning_rate": 1.8546219958903267e-07, + "loss": 0.149, + "step": 14306 + }, + { + "epoch": 1.83, + "learning_rate": 1.8518262615995541e-07, + "loss": 0.1509, + "step": 14307 + }, + { + "epoch": 1.83, + "learning_rate": 1.8490325963430368e-07, + "loss": 0.1253, + "step": 14308 + }, + { + "epoch": 1.83, + "learning_rate": 1.8462410002408228e-07, + "loss": 0.136, + "step": 14309 + }, + { + "epoch": 1.83, + "learning_rate": 1.843451473412877e-07, + "loss": 0.1297, + "step": 14310 + }, + { + "epoch": 1.83, + "learning_rate": 1.8406640159790767e-07, + "loss": 0.12, + "step": 14311 + }, + { + "epoch": 1.83, + "learning_rate": 1.837878628059192e-07, + "loss": 0.1125, + "step": 14312 + }, + { + "epoch": 1.83, + "learning_rate": 1.835095309772933e-07, + "loss": 0.1288, + "step": 14313 + }, + { + "epoch": 1.83, + "learning_rate": 1.8323140612399038e-07, + "loss": 0.1285, + "step": 14314 + }, + { + "epoch": 1.83, + "learning_rate": 1.829534882579598e-07, + "loss": 0.1336, + "step": 14315 + }, + { + "epoch": 1.83, + "learning_rate": 1.8267577739114695e-07, + "loss": 0.1326, + "step": 14316 + }, + { + "epoch": 1.83, + "learning_rate": 1.8239827353548457e-07, + "loss": 0.1202, + "step": 14317 + }, + { + "epoch": 1.83, + "learning_rate": 1.8212097670289807e-07, + "loss": 0.1196, + "step": 14318 + }, + { + "epoch": 1.83, + "learning_rate": 1.8184388690530242e-07, + "loss": 0.1365, + "step": 14319 + }, + { + "epoch": 1.83, + "learning_rate": 1.8156700415460582e-07, + "loss": 0.1303, + "step": 14320 + }, + { + "epoch": 1.83, + "learning_rate": 1.812903284627071e-07, + "loss": 0.132, + "step": 14321 + }, + { + "epoch": 1.83, + "learning_rate": 1.8101385984149343e-07, + "loss": 0.1304, + "step": 14322 + }, + { + "epoch": 1.83, + "learning_rate": 1.8073759830284754e-07, + "loss": 0.1384, + "step": 14323 + }, + { + "epoch": 1.83, + "learning_rate": 1.804615438586399e-07, + "loss": 0.1309, + "step": 14324 + }, + { + "epoch": 1.83, + "learning_rate": 1.801856965207338e-07, + "loss": 0.1436, + "step": 14325 + }, + { + "epoch": 1.83, + "learning_rate": 1.79910056300982e-07, + "loss": 0.1427, + "step": 14326 + }, + { + "epoch": 1.83, + "learning_rate": 1.796346232112306e-07, + "loss": 0.1529, + "step": 14327 + }, + { + "epoch": 1.83, + "learning_rate": 1.7935939726331453e-07, + "loss": 0.1144, + "step": 14328 + }, + { + "epoch": 1.83, + "learning_rate": 1.7908437846906158e-07, + "loss": 0.1376, + "step": 14329 + }, + { + "epoch": 1.83, + "learning_rate": 1.7880956684028894e-07, + "loss": 0.1262, + "step": 14330 + }, + { + "epoch": 1.83, + "learning_rate": 1.7853496238880718e-07, + "loss": 0.1398, + "step": 14331 + }, + { + "epoch": 1.83, + "learning_rate": 1.7826056512641633e-07, + "loss": 0.1394, + "step": 14332 + }, + { + "epoch": 1.83, + "learning_rate": 1.7798637506490745e-07, + "loss": 0.1455, + "step": 14333 + }, + { + "epoch": 1.83, + "learning_rate": 1.7771239221606285e-07, + "loss": 0.1417, + "step": 14334 + }, + { + "epoch": 1.83, + "learning_rate": 1.7743861659165695e-07, + "loss": 0.1389, + "step": 14335 + }, + { + "epoch": 1.84, + "learning_rate": 1.7716504820345427e-07, + "loss": 0.1302, + "step": 14336 + }, + { + "epoch": 1.84, + "learning_rate": 1.768916870632098e-07, + "loss": 0.1062, + "step": 14337 + }, + { + "epoch": 1.84, + "learning_rate": 1.7661853318267142e-07, + "loss": 0.1257, + "step": 14338 + }, + { + "epoch": 1.84, + "learning_rate": 1.7634558657357748e-07, + "loss": 0.1528, + "step": 14339 + }, + { + "epoch": 1.84, + "learning_rate": 1.7607284724765583e-07, + "loss": 0.1358, + "step": 14340 + }, + { + "epoch": 1.84, + "learning_rate": 1.7580031521662765e-07, + "loss": 0.1291, + "step": 14341 + }, + { + "epoch": 1.84, + "learning_rate": 1.7552799049220415e-07, + "loss": 0.1394, + "step": 14342 + }, + { + "epoch": 1.84, + "learning_rate": 1.752558730860876e-07, + "loss": 0.1222, + "step": 14343 + }, + { + "epoch": 1.84, + "learning_rate": 1.7498396300997146e-07, + "loss": 0.1356, + "step": 14344 + }, + { + "epoch": 1.84, + "learning_rate": 1.747122602755391e-07, + "loss": 0.1221, + "step": 14345 + }, + { + "epoch": 1.84, + "learning_rate": 1.7444076489446958e-07, + "loss": 0.1355, + "step": 14346 + }, + { + "epoch": 1.84, + "learning_rate": 1.7416947687842633e-07, + "loss": 0.1245, + "step": 14347 + }, + { + "epoch": 1.84, + "learning_rate": 1.738983962390678e-07, + "loss": 0.1407, + "step": 14348 + }, + { + "epoch": 1.84, + "learning_rate": 1.736275229880441e-07, + "loss": 0.1339, + "step": 14349 + }, + { + "epoch": 1.84, + "learning_rate": 1.733568571369948e-07, + "loss": 0.1274, + "step": 14350 + }, + { + "epoch": 1.84, + "learning_rate": 1.7308639869755062e-07, + "loss": 0.1254, + "step": 14351 + }, + { + "epoch": 1.84, + "learning_rate": 1.728161476813345e-07, + "loss": 0.1322, + "step": 14352 + }, + { + "epoch": 1.84, + "learning_rate": 1.7254610409995875e-07, + "loss": 0.1224, + "step": 14353 + }, + { + "epoch": 1.84, + "learning_rate": 1.7227626796502807e-07, + "loss": 0.1304, + "step": 14354 + }, + { + "epoch": 1.84, + "learning_rate": 1.720066392881381e-07, + "loss": 0.1264, + "step": 14355 + }, + { + "epoch": 1.84, + "learning_rate": 1.7173721808087573e-07, + "loss": 0.1258, + "step": 14356 + }, + { + "epoch": 1.84, + "learning_rate": 1.7146800435481837e-07, + "loss": 0.1245, + "step": 14357 + }, + { + "epoch": 1.84, + "learning_rate": 1.7119899812153394e-07, + "loss": 0.129, + "step": 14358 + }, + { + "epoch": 1.84, + "learning_rate": 1.7093019939258327e-07, + "loss": 0.1556, + "step": 14359 + }, + { + "epoch": 1.84, + "learning_rate": 1.706616081795165e-07, + "loss": 0.1145, + "step": 14360 + }, + { + "epoch": 1.84, + "learning_rate": 1.7039322449387664e-07, + "loss": 0.1196, + "step": 14361 + }, + { + "epoch": 1.84, + "learning_rate": 1.7012504834719556e-07, + "loss": 0.1662, + "step": 14362 + }, + { + "epoch": 1.84, + "learning_rate": 1.6985707975099742e-07, + "loss": 0.1203, + "step": 14363 + }, + { + "epoch": 1.84, + "learning_rate": 1.6958931871679908e-07, + "loss": 0.1266, + "step": 14364 + }, + { + "epoch": 1.84, + "learning_rate": 1.6932176525610465e-07, + "loss": 0.1158, + "step": 14365 + }, + { + "epoch": 1.84, + "learning_rate": 1.6905441938041222e-07, + "loss": 0.1287, + "step": 14366 + }, + { + "epoch": 1.84, + "learning_rate": 1.687872811012109e-07, + "loss": 0.1132, + "step": 14367 + }, + { + "epoch": 1.84, + "learning_rate": 1.685203504299804e-07, + "loss": 0.1594, + "step": 14368 + }, + { + "epoch": 1.84, + "learning_rate": 1.6825362737818985e-07, + "loss": 0.135, + "step": 14369 + }, + { + "epoch": 1.84, + "learning_rate": 1.6798711195730233e-07, + "loss": 0.1254, + "step": 14370 + }, + { + "epoch": 1.84, + "learning_rate": 1.677208041787698e-07, + "loss": 0.1322, + "step": 14371 + }, + { + "epoch": 1.84, + "learning_rate": 1.6745470405403697e-07, + "loss": 0.151, + "step": 14372 + }, + { + "epoch": 1.84, + "learning_rate": 1.6718881159453693e-07, + "loss": 0.1412, + "step": 14373 + }, + { + "epoch": 1.84, + "learning_rate": 1.6692312681169775e-07, + "loss": 0.1285, + "step": 14374 + }, + { + "epoch": 1.84, + "learning_rate": 1.6665764971693587e-07, + "loss": 0.1231, + "step": 14375 + }, + { + "epoch": 1.84, + "learning_rate": 1.6639238032165883e-07, + "loss": 0.1094, + "step": 14376 + }, + { + "epoch": 1.84, + "learning_rate": 1.6612731863726638e-07, + "loss": 0.1162, + "step": 14377 + }, + { + "epoch": 1.84, + "learning_rate": 1.6586246467514833e-07, + "loss": 0.1297, + "step": 14378 + }, + { + "epoch": 1.84, + "learning_rate": 1.6559781844668666e-07, + "loss": 0.1238, + "step": 14379 + }, + { + "epoch": 1.84, + "learning_rate": 1.6533337996325337e-07, + "loss": 0.1235, + "step": 14380 + }, + { + "epoch": 1.84, + "learning_rate": 1.650691492362122e-07, + "loss": 0.1275, + "step": 14381 + }, + { + "epoch": 1.84, + "learning_rate": 1.6480512627691792e-07, + "loss": 0.1304, + "step": 14382 + }, + { + "epoch": 1.84, + "learning_rate": 1.6454131109671534e-07, + "loss": 0.1318, + "step": 14383 + }, + { + "epoch": 1.84, + "learning_rate": 1.6427770370694208e-07, + "loss": 0.1377, + "step": 14384 + }, + { + "epoch": 1.84, + "learning_rate": 1.6401430411892572e-07, + "loss": 0.1442, + "step": 14385 + }, + { + "epoch": 1.84, + "learning_rate": 1.63751112343985e-07, + "loss": 0.1522, + "step": 14386 + }, + { + "epoch": 1.84, + "learning_rate": 1.6348812839342976e-07, + "loss": 0.1416, + "step": 14387 + }, + { + "epoch": 1.84, + "learning_rate": 1.6322535227856152e-07, + "loss": 0.1521, + "step": 14388 + }, + { + "epoch": 1.84, + "learning_rate": 1.6296278401067122e-07, + "loss": 0.1141, + "step": 14389 + }, + { + "epoch": 1.84, + "learning_rate": 1.6270042360104377e-07, + "loss": 0.1326, + "step": 14390 + }, + { + "epoch": 1.84, + "learning_rate": 1.624382710609512e-07, + "loss": 0.1269, + "step": 14391 + }, + { + "epoch": 1.84, + "learning_rate": 1.621763264016607e-07, + "loss": 0.1277, + "step": 14392 + }, + { + "epoch": 1.84, + "learning_rate": 1.6191458963442762e-07, + "loss": 0.1234, + "step": 14393 + }, + { + "epoch": 1.84, + "learning_rate": 1.6165306077049969e-07, + "loss": 0.1402, + "step": 14394 + }, + { + "epoch": 1.84, + "learning_rate": 1.6139173982111567e-07, + "loss": 0.129, + "step": 14395 + }, + { + "epoch": 1.84, + "learning_rate": 1.611306267975038e-07, + "loss": 0.1331, + "step": 14396 + }, + { + "epoch": 1.84, + "learning_rate": 1.6086972171088678e-07, + "loss": 0.1147, + "step": 14397 + }, + { + "epoch": 1.84, + "learning_rate": 1.606090245724745e-07, + "loss": 0.1312, + "step": 14398 + }, + { + "epoch": 1.84, + "learning_rate": 1.603485353934703e-07, + "loss": 0.1351, + "step": 14399 + }, + { + "epoch": 1.84, + "learning_rate": 1.6008825418506846e-07, + "loss": 0.1316, + "step": 14400 + }, + { + "epoch": 1.84, + "learning_rate": 1.5982818095845286e-07, + "loss": 0.1316, + "step": 14401 + }, + { + "epoch": 1.84, + "learning_rate": 1.5956831572480013e-07, + "loss": 0.1119, + "step": 14402 + }, + { + "epoch": 1.84, + "learning_rate": 1.5930865849527744e-07, + "loss": 0.1423, + "step": 14403 + }, + { + "epoch": 1.84, + "learning_rate": 1.5904920928104196e-07, + "loss": 0.1252, + "step": 14404 + }, + { + "epoch": 1.84, + "learning_rate": 1.5878996809324366e-07, + "loss": 0.1412, + "step": 14405 + }, + { + "epoch": 1.84, + "learning_rate": 1.5853093494302195e-07, + "loss": 0.1136, + "step": 14406 + }, + { + "epoch": 1.84, + "learning_rate": 1.582721098415091e-07, + "loss": 0.1344, + "step": 14407 + }, + { + "epoch": 1.84, + "learning_rate": 1.5801349279982726e-07, + "loss": 0.122, + "step": 14408 + }, + { + "epoch": 1.84, + "learning_rate": 1.577550838290881e-07, + "loss": 0.1222, + "step": 14409 + }, + { + "epoch": 1.84, + "learning_rate": 1.5749688294039778e-07, + "loss": 0.1322, + "step": 14410 + }, + { + "epoch": 1.84, + "learning_rate": 1.5723889014485128e-07, + "loss": 0.1323, + "step": 14411 + }, + { + "epoch": 1.84, + "learning_rate": 1.5698110545353474e-07, + "loss": 0.1335, + "step": 14412 + }, + { + "epoch": 1.84, + "learning_rate": 1.567235288775265e-07, + "loss": 0.1212, + "step": 14413 + }, + { + "epoch": 1.84, + "learning_rate": 1.564661604278944e-07, + "loss": 0.141, + "step": 14414 + }, + { + "epoch": 1.85, + "learning_rate": 1.5620900011569906e-07, + "loss": 0.147, + "step": 14415 + }, + { + "epoch": 1.85, + "learning_rate": 1.5595204795199047e-07, + "loss": 0.1413, + "step": 14416 + }, + { + "epoch": 1.85, + "learning_rate": 1.5569530394780986e-07, + "loss": 0.1271, + "step": 14417 + }, + { + "epoch": 1.85, + "learning_rate": 1.5543876811419222e-07, + "loss": 0.1276, + "step": 14418 + }, + { + "epoch": 1.85, + "learning_rate": 1.5518244046215936e-07, + "loss": 0.1387, + "step": 14419 + }, + { + "epoch": 1.85, + "learning_rate": 1.5492632100272686e-07, + "loss": 0.1379, + "step": 14420 + }, + { + "epoch": 1.85, + "learning_rate": 1.546704097469015e-07, + "loss": 0.1242, + "step": 14421 + }, + { + "epoch": 1.85, + "learning_rate": 1.544147067056795e-07, + "loss": 0.1355, + "step": 14422 + }, + { + "epoch": 1.85, + "learning_rate": 1.5415921189004922e-07, + "loss": 0.1456, + "step": 14423 + }, + { + "epoch": 1.85, + "learning_rate": 1.539039253109892e-07, + "loss": 0.1198, + "step": 14424 + }, + { + "epoch": 1.85, + "learning_rate": 1.5364884697947113e-07, + "loss": 0.126, + "step": 14425 + }, + { + "epoch": 1.85, + "learning_rate": 1.533939769064563e-07, + "loss": 0.1374, + "step": 14426 + }, + { + "epoch": 1.85, + "learning_rate": 1.5313931510289482e-07, + "loss": 0.1402, + "step": 14427 + }, + { + "epoch": 1.85, + "learning_rate": 1.528848615797318e-07, + "loss": 0.1319, + "step": 14428 + }, + { + "epoch": 1.85, + "learning_rate": 1.526306163479019e-07, + "loss": 0.141, + "step": 14429 + }, + { + "epoch": 1.85, + "learning_rate": 1.523765794183296e-07, + "loss": 0.1263, + "step": 14430 + }, + { + "epoch": 1.85, + "learning_rate": 1.521227508019324e-07, + "loss": 0.145, + "step": 14431 + }, + { + "epoch": 1.85, + "learning_rate": 1.518691305096165e-07, + "loss": 0.1266, + "step": 14432 + }, + { + "epoch": 1.85, + "learning_rate": 1.5161571855228264e-07, + "loss": 0.1314, + "step": 14433 + }, + { + "epoch": 1.85, + "learning_rate": 1.5136251494081822e-07, + "loss": 0.1509, + "step": 14434 + }, + { + "epoch": 1.85, + "learning_rate": 1.5110951968610564e-07, + "loss": 0.1282, + "step": 14435 + }, + { + "epoch": 1.85, + "learning_rate": 1.5085673279901626e-07, + "loss": 0.128, + "step": 14436 + }, + { + "epoch": 1.85, + "learning_rate": 1.5060415429041186e-07, + "loss": 0.1203, + "step": 14437 + }, + { + "epoch": 1.85, + "learning_rate": 1.503517841711477e-07, + "loss": 0.1208, + "step": 14438 + }, + { + "epoch": 1.85, + "learning_rate": 1.5009962245206845e-07, + "loss": 0.1128, + "step": 14439 + }, + { + "epoch": 1.85, + "learning_rate": 1.4984766914400928e-07, + "loss": 0.1173, + "step": 14440 + }, + { + "epoch": 1.85, + "learning_rate": 1.4959592425779768e-07, + "loss": 0.1276, + "step": 14441 + }, + { + "epoch": 1.85, + "learning_rate": 1.4934438780425108e-07, + "loss": 0.1233, + "step": 14442 + }, + { + "epoch": 1.85, + "learning_rate": 1.4909305979417976e-07, + "loss": 0.1324, + "step": 14443 + }, + { + "epoch": 1.85, + "learning_rate": 1.488419402383834e-07, + "loss": 0.1085, + "step": 14444 + }, + { + "epoch": 1.85, + "learning_rate": 1.4859102914765278e-07, + "loss": 0.1298, + "step": 14445 + }, + { + "epoch": 1.85, + "learning_rate": 1.4834032653276986e-07, + "loss": 0.1381, + "step": 14446 + }, + { + "epoch": 1.85, + "learning_rate": 1.4808983240450881e-07, + "loss": 0.1271, + "step": 14447 + }, + { + "epoch": 1.85, + "learning_rate": 1.4783954677363376e-07, + "loss": 0.1507, + "step": 14448 + }, + { + "epoch": 1.85, + "learning_rate": 1.4758946965089894e-07, + "loss": 0.1278, + "step": 14449 + }, + { + "epoch": 1.85, + "learning_rate": 1.473396010470518e-07, + "loss": 0.1249, + "step": 14450 + }, + { + "epoch": 1.85, + "learning_rate": 1.470899409728299e-07, + "loss": 0.1216, + "step": 14451 + }, + { + "epoch": 1.85, + "learning_rate": 1.4684048943896022e-07, + "loss": 0.1312, + "step": 14452 + }, + { + "epoch": 1.85, + "learning_rate": 1.4659124645616418e-07, + "loss": 0.1349, + "step": 14453 + }, + { + "epoch": 1.85, + "learning_rate": 1.4634221203515097e-07, + "loss": 0.1183, + "step": 14454 + }, + { + "epoch": 1.85, + "learning_rate": 1.4609338618662318e-07, + "loss": 0.1308, + "step": 14455 + }, + { + "epoch": 1.85, + "learning_rate": 1.458447689212722e-07, + "loss": 0.1399, + "step": 14456 + }, + { + "epoch": 1.85, + "learning_rate": 1.455963602497823e-07, + "loss": 0.1303, + "step": 14457 + }, + { + "epoch": 1.85, + "learning_rate": 1.4534816018282882e-07, + "loss": 0.141, + "step": 14458 + }, + { + "epoch": 1.85, + "learning_rate": 1.4510016873107657e-07, + "loss": 0.1296, + "step": 14459 + }, + { + "epoch": 1.85, + "learning_rate": 1.4485238590518147e-07, + "loss": 0.153, + "step": 14460 + }, + { + "epoch": 1.85, + "learning_rate": 1.4460481171579334e-07, + "loss": 0.1318, + "step": 14461 + }, + { + "epoch": 1.85, + "learning_rate": 1.4435744617354975e-07, + "loss": 0.1253, + "step": 14462 + }, + { + "epoch": 1.85, + "learning_rate": 1.4411028928908054e-07, + "loss": 0.1241, + "step": 14463 + }, + { + "epoch": 1.85, + "learning_rate": 1.4386334107300727e-07, + "loss": 0.1392, + "step": 14464 + }, + { + "epoch": 1.85, + "learning_rate": 1.4361660153594137e-07, + "loss": 0.1431, + "step": 14465 + }, + { + "epoch": 1.85, + "learning_rate": 1.4337007068848607e-07, + "loss": 0.1234, + "step": 14466 + }, + { + "epoch": 1.85, + "learning_rate": 1.4312374854123456e-07, + "loss": 0.1329, + "step": 14467 + }, + { + "epoch": 1.85, + "learning_rate": 1.4287763510477225e-07, + "loss": 0.1275, + "step": 14468 + }, + { + "epoch": 1.85, + "learning_rate": 1.4263173038967627e-07, + "loss": 0.1265, + "step": 14469 + }, + { + "epoch": 1.85, + "learning_rate": 1.42386034406512e-07, + "loss": 0.1254, + "step": 14470 + }, + { + "epoch": 1.85, + "learning_rate": 1.421405471658388e-07, + "loss": 0.1482, + "step": 14471 + }, + { + "epoch": 1.85, + "learning_rate": 1.4189526867820491e-07, + "loss": 0.1411, + "step": 14472 + }, + { + "epoch": 1.85, + "learning_rate": 1.4165019895415133e-07, + "loss": 0.1186, + "step": 14473 + }, + { + "epoch": 1.85, + "learning_rate": 1.4140533800420853e-07, + "loss": 0.1281, + "step": 14474 + }, + { + "epoch": 1.85, + "learning_rate": 1.4116068583889865e-07, + "loss": 0.1195, + "step": 14475 + }, + { + "epoch": 1.85, + "learning_rate": 1.409162424687366e-07, + "loss": 0.1201, + "step": 14476 + }, + { + "epoch": 1.85, + "learning_rate": 1.4067200790422454e-07, + "loss": 0.1653, + "step": 14477 + }, + { + "epoch": 1.85, + "learning_rate": 1.4042798215585796e-07, + "loss": 0.1321, + "step": 14478 + }, + { + "epoch": 1.85, + "learning_rate": 1.401841652341246e-07, + "loss": 0.1287, + "step": 14479 + }, + { + "epoch": 1.85, + "learning_rate": 1.3994055714950105e-07, + "loss": 0.1327, + "step": 14480 + }, + { + "epoch": 1.85, + "learning_rate": 1.3969715791245565e-07, + "loss": 0.142, + "step": 14481 + }, + { + "epoch": 1.85, + "learning_rate": 1.3945396753344776e-07, + "loss": 0.119, + "step": 14482 + }, + { + "epoch": 1.85, + "learning_rate": 1.3921098602292793e-07, + "loss": 0.1235, + "step": 14483 + }, + { + "epoch": 1.85, + "learning_rate": 1.389682133913378e-07, + "loss": 0.12, + "step": 14484 + }, + { + "epoch": 1.85, + "learning_rate": 1.3872564964910905e-07, + "loss": 0.1325, + "step": 14485 + }, + { + "epoch": 1.85, + "learning_rate": 1.384832948066661e-07, + "loss": 0.1176, + "step": 14486 + }, + { + "epoch": 1.85, + "learning_rate": 1.382411488744234e-07, + "loss": 0.1186, + "step": 14487 + }, + { + "epoch": 1.85, + "learning_rate": 1.3799921186278597e-07, + "loss": 0.125, + "step": 14488 + }, + { + "epoch": 1.85, + "learning_rate": 1.3775748378215047e-07, + "loss": 0.1208, + "step": 14489 + }, + { + "epoch": 1.85, + "learning_rate": 1.3751596464290529e-07, + "loss": 0.1255, + "step": 14490 + }, + { + "epoch": 1.85, + "learning_rate": 1.372746544554282e-07, + "loss": 0.1269, + "step": 14491 + }, + { + "epoch": 1.85, + "learning_rate": 1.3703355323008872e-07, + "loss": 0.1303, + "step": 14492 + }, + { + "epoch": 1.86, + "learning_rate": 1.3679266097724797e-07, + "loss": 0.128, + "step": 14493 + }, + { + "epoch": 1.86, + "learning_rate": 1.3655197770725826e-07, + "loss": 0.1238, + "step": 14494 + }, + { + "epoch": 1.86, + "learning_rate": 1.363115034304602e-07, + "loss": 0.1279, + "step": 14495 + }, + { + "epoch": 1.86, + "learning_rate": 1.3607123815718993e-07, + "loss": 0.1299, + "step": 14496 + }, + { + "epoch": 1.86, + "learning_rate": 1.358311818977709e-07, + "loss": 0.1183, + "step": 14497 + }, + { + "epoch": 1.86, + "learning_rate": 1.3559133466251874e-07, + "loss": 0.1442, + "step": 14498 + }, + { + "epoch": 1.86, + "learning_rate": 1.3535169646174073e-07, + "loss": 0.128, + "step": 14499 + }, + { + "epoch": 1.86, + "learning_rate": 1.3511226730573478e-07, + "loss": 0.1331, + "step": 14500 + }, + { + "epoch": 1.86, + "learning_rate": 1.3487304720478933e-07, + "loss": 0.1294, + "step": 14501 + }, + { + "epoch": 1.86, + "learning_rate": 1.346340361691839e-07, + "loss": 0.1341, + "step": 14502 + }, + { + "epoch": 1.86, + "learning_rate": 1.343952342091892e-07, + "loss": 0.1407, + "step": 14503 + }, + { + "epoch": 1.86, + "learning_rate": 1.3415664133506812e-07, + "loss": 0.1264, + "step": 14504 + }, + { + "epoch": 1.86, + "learning_rate": 1.3391825755707356e-07, + "loss": 0.1389, + "step": 14505 + }, + { + "epoch": 1.86, + "learning_rate": 1.3368008288544843e-07, + "loss": 0.1291, + "step": 14506 + }, + { + "epoch": 1.86, + "learning_rate": 1.3344211733042788e-07, + "loss": 0.1233, + "step": 14507 + }, + { + "epoch": 1.86, + "learning_rate": 1.3320436090223765e-07, + "loss": 0.1125, + "step": 14508 + }, + { + "epoch": 1.86, + "learning_rate": 1.3296681361109564e-07, + "loss": 0.1396, + "step": 14509 + }, + { + "epoch": 1.86, + "learning_rate": 1.327294754672087e-07, + "loss": 0.1327, + "step": 14510 + }, + { + "epoch": 1.86, + "learning_rate": 1.324923464807759e-07, + "loss": 0.1273, + "step": 14511 + }, + { + "epoch": 1.86, + "learning_rate": 1.3225542666198854e-07, + "loss": 0.1333, + "step": 14512 + }, + { + "epoch": 1.86, + "learning_rate": 1.3201871602102512e-07, + "loss": 0.1316, + "step": 14513 + }, + { + "epoch": 1.86, + "learning_rate": 1.3178221456806028e-07, + "loss": 0.1371, + "step": 14514 + }, + { + "epoch": 1.86, + "learning_rate": 1.3154592231325535e-07, + "loss": 0.1466, + "step": 14515 + }, + { + "epoch": 1.86, + "learning_rate": 1.3130983926676445e-07, + "loss": 0.1356, + "step": 14516 + }, + { + "epoch": 1.86, + "learning_rate": 1.310739654387333e-07, + "loss": 0.1359, + "step": 14517 + }, + { + "epoch": 1.86, + "learning_rate": 1.308383008392977e-07, + "loss": 0.1279, + "step": 14518 + }, + { + "epoch": 1.86, + "learning_rate": 1.3060284547858403e-07, + "loss": 0.1458, + "step": 14519 + }, + { + "epoch": 1.86, + "learning_rate": 1.3036759936671084e-07, + "loss": 0.1395, + "step": 14520 + }, + { + "epoch": 1.86, + "learning_rate": 1.3013256251378725e-07, + "loss": 0.135, + "step": 14521 + }, + { + "epoch": 1.86, + "learning_rate": 1.2989773492991298e-07, + "loss": 0.1227, + "step": 14522 + }, + { + "epoch": 1.86, + "learning_rate": 1.2966311662517994e-07, + "loss": 0.1251, + "step": 14523 + }, + { + "epoch": 1.86, + "learning_rate": 1.2942870760966952e-07, + "loss": 0.1465, + "step": 14524 + }, + { + "epoch": 1.86, + "learning_rate": 1.2919450789345477e-07, + "loss": 0.1372, + "step": 14525 + }, + { + "epoch": 1.86, + "learning_rate": 1.289605174865993e-07, + "loss": 0.1157, + "step": 14526 + }, + { + "epoch": 1.86, + "learning_rate": 1.2872673639915955e-07, + "loss": 0.146, + "step": 14527 + }, + { + "epoch": 1.86, + "learning_rate": 1.2849316464118078e-07, + "loss": 0.1237, + "step": 14528 + }, + { + "epoch": 1.86, + "learning_rate": 1.282598022226994e-07, + "loss": 0.15, + "step": 14529 + }, + { + "epoch": 1.86, + "learning_rate": 1.2802664915374575e-07, + "loss": 0.1328, + "step": 14530 + }, + { + "epoch": 1.86, + "learning_rate": 1.2779370544433567e-07, + "loss": 0.1205, + "step": 14531 + }, + { + "epoch": 1.86, + "learning_rate": 1.275609711044823e-07, + "loss": 0.131, + "step": 14532 + }, + { + "epoch": 1.86, + "learning_rate": 1.2732844614418482e-07, + "loss": 0.1238, + "step": 14533 + }, + { + "epoch": 1.86, + "learning_rate": 1.270961305734364e-07, + "loss": 0.1225, + "step": 14534 + }, + { + "epoch": 1.86, + "learning_rate": 1.2686402440222013e-07, + "loss": 0.1478, + "step": 14535 + }, + { + "epoch": 1.86, + "learning_rate": 1.2663212764050858e-07, + "loss": 0.1292, + "step": 14536 + }, + { + "epoch": 1.86, + "learning_rate": 1.2640044029826937e-07, + "loss": 0.1286, + "step": 14537 + }, + { + "epoch": 1.86, + "learning_rate": 1.261689623854573e-07, + "loss": 0.1327, + "step": 14538 + }, + { + "epoch": 1.86, + "learning_rate": 1.2593769391201827e-07, + "loss": 0.1263, + "step": 14539 + }, + { + "epoch": 1.86, + "learning_rate": 1.257066348878927e-07, + "loss": 0.1271, + "step": 14540 + }, + { + "epoch": 1.86, + "learning_rate": 1.254757853230082e-07, + "loss": 0.1344, + "step": 14541 + }, + { + "epoch": 1.86, + "learning_rate": 1.252451452272857e-07, + "loss": 0.1271, + "step": 14542 + }, + { + "epoch": 1.86, + "learning_rate": 1.2501471461063564e-07, + "loss": 0.133, + "step": 14543 + }, + { + "epoch": 1.86, + "learning_rate": 1.247844934829606e-07, + "loss": 0.1269, + "step": 14544 + }, + { + "epoch": 1.86, + "learning_rate": 1.2455448185415386e-07, + "loss": 0.1321, + "step": 14545 + }, + { + "epoch": 1.86, + "learning_rate": 1.2432467973409857e-07, + "loss": 0.1406, + "step": 14546 + }, + { + "epoch": 1.86, + "learning_rate": 1.2409508713267072e-07, + "loss": 0.1192, + "step": 14547 + }, + { + "epoch": 1.86, + "learning_rate": 1.238657040597374e-07, + "loss": 0.1388, + "step": 14548 + }, + { + "epoch": 1.86, + "learning_rate": 1.2363653052515302e-07, + "loss": 0.1469, + "step": 14549 + }, + { + "epoch": 1.86, + "learning_rate": 1.234075665387674e-07, + "loss": 0.1382, + "step": 14550 + }, + { + "epoch": 1.86, + "learning_rate": 1.2317881211041993e-07, + "loss": 0.1411, + "step": 14551 + }, + { + "epoch": 1.86, + "learning_rate": 1.2295026724993998e-07, + "loss": 0.1415, + "step": 14552 + }, + { + "epoch": 1.86, + "learning_rate": 1.2272193196714854e-07, + "loss": 0.1268, + "step": 14553 + }, + { + "epoch": 1.86, + "learning_rate": 1.2249380627185781e-07, + "loss": 0.1263, + "step": 14554 + }, + { + "epoch": 1.86, + "learning_rate": 1.2226589017387158e-07, + "loss": 0.1221, + "step": 14555 + }, + { + "epoch": 1.86, + "learning_rate": 1.2203818368298315e-07, + "loss": 0.1396, + "step": 14556 + }, + { + "epoch": 1.86, + "learning_rate": 1.2181068680897745e-07, + "loss": 0.1307, + "step": 14557 + }, + { + "epoch": 1.86, + "learning_rate": 1.2158339956163113e-07, + "loss": 0.1271, + "step": 14558 + }, + { + "epoch": 1.86, + "learning_rate": 1.2135632195071133e-07, + "loss": 0.1318, + "step": 14559 + }, + { + "epoch": 1.86, + "learning_rate": 1.211294539859753e-07, + "loss": 0.1284, + "step": 14560 + }, + { + "epoch": 1.86, + "learning_rate": 1.2090279567717246e-07, + "loss": 0.1166, + "step": 14561 + }, + { + "epoch": 1.86, + "learning_rate": 1.2067634703404218e-07, + "loss": 0.1439, + "step": 14562 + }, + { + "epoch": 1.86, + "learning_rate": 1.204501080663173e-07, + "loss": 0.1225, + "step": 14563 + }, + { + "epoch": 1.86, + "learning_rate": 1.202240787837178e-07, + "loss": 0.1393, + "step": 14564 + }, + { + "epoch": 1.86, + "learning_rate": 1.1999825919595808e-07, + "loss": 0.1366, + "step": 14565 + }, + { + "epoch": 1.86, + "learning_rate": 1.1977264931274158e-07, + "loss": 0.1295, + "step": 14566 + }, + { + "epoch": 1.86, + "learning_rate": 1.1954724914376215e-07, + "loss": 0.1279, + "step": 14567 + }, + { + "epoch": 1.86, + "learning_rate": 1.1932205869870762e-07, + "loss": 0.1406, + "step": 14568 + }, + { + "epoch": 1.86, + "learning_rate": 1.1909707798725412e-07, + "loss": 0.1286, + "step": 14569 + }, + { + "epoch": 1.86, + "learning_rate": 1.1887230701906893e-07, + "loss": 0.1387, + "step": 14570 + }, + { + "epoch": 1.87, + "learning_rate": 1.186477458038121e-07, + "loss": 0.1407, + "step": 14571 + }, + { + "epoch": 1.87, + "learning_rate": 1.1842339435113259e-07, + "loss": 0.132, + "step": 14572 + }, + { + "epoch": 1.87, + "learning_rate": 1.1819925267067211e-07, + "loss": 0.105, + "step": 14573 + }, + { + "epoch": 1.87, + "learning_rate": 1.1797532077206187e-07, + "loss": 0.1292, + "step": 14574 + }, + { + "epoch": 1.87, + "learning_rate": 1.177515986649247e-07, + "loss": 0.1249, + "step": 14575 + }, + { + "epoch": 1.87, + "learning_rate": 1.1752808635887514e-07, + "loss": 0.1378, + "step": 14576 + }, + { + "epoch": 1.87, + "learning_rate": 1.1730478386351719e-07, + "loss": 0.1391, + "step": 14577 + }, + { + "epoch": 1.87, + "learning_rate": 1.1708169118844759e-07, + "loss": 0.1389, + "step": 14578 + }, + { + "epoch": 1.87, + "learning_rate": 1.1685880834325203e-07, + "loss": 0.1427, + "step": 14579 + }, + { + "epoch": 1.87, + "learning_rate": 1.1663613533750839e-07, + "loss": 0.1274, + "step": 14580 + }, + { + "epoch": 1.87, + "learning_rate": 1.1641367218078736e-07, + "loss": 0.1266, + "step": 14581 + }, + { + "epoch": 1.87, + "learning_rate": 1.1619141888264574e-07, + "loss": 0.1332, + "step": 14582 + }, + { + "epoch": 1.87, + "learning_rate": 1.1596937545263587e-07, + "loss": 0.152, + "step": 14583 + }, + { + "epoch": 1.87, + "learning_rate": 1.1574754190030014e-07, + "loss": 0.1498, + "step": 14584 + }, + { + "epoch": 1.87, + "learning_rate": 1.1552591823516978e-07, + "loss": 0.1363, + "step": 14585 + }, + { + "epoch": 1.87, + "learning_rate": 1.1530450446676889e-07, + "loss": 0.1486, + "step": 14586 + }, + { + "epoch": 1.87, + "learning_rate": 1.1508330060461204e-07, + "loss": 0.1297, + "step": 14587 + }, + { + "epoch": 1.87, + "learning_rate": 1.1486230665820552e-07, + "loss": 0.1457, + "step": 14588 + }, + { + "epoch": 1.87, + "learning_rate": 1.1464152263704565e-07, + "loss": 0.1131, + "step": 14589 + }, + { + "epoch": 1.87, + "learning_rate": 1.1442094855061925e-07, + "loss": 0.1268, + "step": 14590 + }, + { + "epoch": 1.87, + "learning_rate": 1.1420058440840598e-07, + "loss": 0.1265, + "step": 14591 + }, + { + "epoch": 1.87, + "learning_rate": 1.1398043021987438e-07, + "loss": 0.1243, + "step": 14592 + }, + { + "epoch": 1.87, + "learning_rate": 1.1376048599448519e-07, + "loss": 0.1377, + "step": 14593 + }, + { + "epoch": 1.87, + "learning_rate": 1.1354075174169088e-07, + "loss": 0.1333, + "step": 14594 + }, + { + "epoch": 1.87, + "learning_rate": 1.1332122747093277e-07, + "loss": 0.1309, + "step": 14595 + }, + { + "epoch": 1.87, + "learning_rate": 1.1310191319164498e-07, + "loss": 0.1192, + "step": 14596 + }, + { + "epoch": 1.87, + "learning_rate": 1.1288280891325165e-07, + "loss": 0.1265, + "step": 14597 + }, + { + "epoch": 1.87, + "learning_rate": 1.1266391464516802e-07, + "loss": 0.1454, + "step": 14598 + }, + { + "epoch": 1.87, + "learning_rate": 1.12445230396801e-07, + "loss": 0.1235, + "step": 14599 + }, + { + "epoch": 1.87, + "learning_rate": 1.1222675617754752e-07, + "loss": 0.1256, + "step": 14600 + }, + { + "epoch": 1.87, + "learning_rate": 1.1200849199679564e-07, + "loss": 0.1155, + "step": 14601 + }, + { + "epoch": 1.87, + "learning_rate": 1.1179043786392507e-07, + "loss": 0.1198, + "step": 14602 + }, + { + "epoch": 1.87, + "learning_rate": 1.1157259378830665e-07, + "loss": 0.1375, + "step": 14603 + }, + { + "epoch": 1.87, + "learning_rate": 1.1135495977930011e-07, + "loss": 0.147, + "step": 14604 + }, + { + "epoch": 1.87, + "learning_rate": 1.1113753584625853e-07, + "loss": 0.1175, + "step": 14605 + }, + { + "epoch": 1.87, + "learning_rate": 1.1092032199852609e-07, + "loss": 0.1317, + "step": 14606 + }, + { + "epoch": 1.87, + "learning_rate": 1.1070331824543534e-07, + "loss": 0.1325, + "step": 14607 + }, + { + "epoch": 1.87, + "learning_rate": 1.1048652459631216e-07, + "loss": 0.1415, + "step": 14608 + }, + { + "epoch": 1.87, + "learning_rate": 1.1026994106047296e-07, + "loss": 0.1184, + "step": 14609 + }, + { + "epoch": 1.87, + "learning_rate": 1.1005356764722364e-07, + "loss": 0.121, + "step": 14610 + }, + { + "epoch": 1.87, + "learning_rate": 1.0983740436586343e-07, + "loss": 0.1295, + "step": 14611 + }, + { + "epoch": 1.87, + "learning_rate": 1.0962145122568046e-07, + "loss": 0.1527, + "step": 14612 + }, + { + "epoch": 1.87, + "learning_rate": 1.0940570823595565e-07, + "loss": 0.1445, + "step": 14613 + }, + { + "epoch": 1.87, + "learning_rate": 1.0919017540595933e-07, + "loss": 0.131, + "step": 14614 + }, + { + "epoch": 1.87, + "learning_rate": 1.0897485274495357e-07, + "loss": 0.133, + "step": 14615 + }, + { + "epoch": 1.87, + "learning_rate": 1.0875974026219149e-07, + "loss": 0.1315, + "step": 14616 + }, + { + "epoch": 1.87, + "learning_rate": 1.0854483796691629e-07, + "loss": 0.1315, + "step": 14617 + }, + { + "epoch": 1.87, + "learning_rate": 1.0833014586836388e-07, + "loss": 0.1344, + "step": 14618 + }, + { + "epoch": 1.87, + "learning_rate": 1.0811566397575912e-07, + "loss": 0.1211, + "step": 14619 + }, + { + "epoch": 1.87, + "learning_rate": 1.0790139229831909e-07, + "loss": 0.1524, + "step": 14620 + }, + { + "epoch": 1.87, + "learning_rate": 1.0768733084525196e-07, + "loss": 0.1243, + "step": 14621 + }, + { + "epoch": 1.87, + "learning_rate": 1.0747347962575539e-07, + "loss": 0.1402, + "step": 14622 + }, + { + "epoch": 1.87, + "learning_rate": 1.0725983864901978e-07, + "loss": 0.1356, + "step": 14623 + }, + { + "epoch": 1.87, + "learning_rate": 1.0704640792422616e-07, + "loss": 0.137, + "step": 14624 + }, + { + "epoch": 1.87, + "learning_rate": 1.0683318746054439e-07, + "loss": 0.1274, + "step": 14625 + }, + { + "epoch": 1.87, + "learning_rate": 1.066201772671388e-07, + "loss": 0.1392, + "step": 14626 + }, + { + "epoch": 1.87, + "learning_rate": 1.0640737735316264e-07, + "loss": 0.1123, + "step": 14627 + }, + { + "epoch": 1.87, + "learning_rate": 1.0619478772776027e-07, + "loss": 0.1495, + "step": 14628 + }, + { + "epoch": 1.87, + "learning_rate": 1.0598240840006658e-07, + "loss": 0.1319, + "step": 14629 + }, + { + "epoch": 1.87, + "learning_rate": 1.0577023937920816e-07, + "loss": 0.125, + "step": 14630 + }, + { + "epoch": 1.87, + "learning_rate": 1.055582806743033e-07, + "loss": 0.1379, + "step": 14631 + }, + { + "epoch": 1.87, + "learning_rate": 1.0534653229445913e-07, + "loss": 0.1347, + "step": 14632 + }, + { + "epoch": 1.87, + "learning_rate": 1.0513499424877505e-07, + "loss": 0.1401, + "step": 14633 + }, + { + "epoch": 1.87, + "learning_rate": 1.0492366654634211e-07, + "loss": 0.1241, + "step": 14634 + }, + { + "epoch": 1.87, + "learning_rate": 1.0471254919624141e-07, + "loss": 0.1392, + "step": 14635 + }, + { + "epoch": 1.87, + "learning_rate": 1.0450164220754456e-07, + "loss": 0.1254, + "step": 14636 + }, + { + "epoch": 1.87, + "learning_rate": 1.0429094558931485e-07, + "loss": 0.1268, + "step": 14637 + }, + { + "epoch": 1.87, + "learning_rate": 1.0408045935060674e-07, + "loss": 0.1179, + "step": 14638 + }, + { + "epoch": 1.87, + "learning_rate": 1.0387018350046519e-07, + "loss": 0.1279, + "step": 14639 + }, + { + "epoch": 1.87, + "learning_rate": 1.0366011804792631e-07, + "loss": 0.1216, + "step": 14640 + }, + { + "epoch": 1.87, + "learning_rate": 1.0345026300201622e-07, + "loss": 0.1368, + "step": 14641 + }, + { + "epoch": 1.87, + "learning_rate": 1.0324061837175436e-07, + "loss": 0.1472, + "step": 14642 + }, + { + "epoch": 1.87, + "learning_rate": 1.0303118416614798e-07, + "loss": 0.124, + "step": 14643 + }, + { + "epoch": 1.87, + "learning_rate": 1.0282196039419823e-07, + "loss": 0.1352, + "step": 14644 + }, + { + "epoch": 1.87, + "learning_rate": 1.0261294706489511e-07, + "loss": 0.1515, + "step": 14645 + }, + { + "epoch": 1.87, + "learning_rate": 1.0240414418722088e-07, + "loss": 0.1304, + "step": 14646 + }, + { + "epoch": 1.87, + "learning_rate": 1.021955517701484e-07, + "loss": 0.1274, + "step": 14647 + }, + { + "epoch": 1.87, + "learning_rate": 1.0198716982264045e-07, + "loss": 0.1321, + "step": 14648 + }, + { + "epoch": 1.88, + "learning_rate": 1.0177899835365323e-07, + "loss": 0.1298, + "step": 14649 + }, + { + "epoch": 1.88, + "learning_rate": 1.015710373721307e-07, + "loss": 0.1185, + "step": 14650 + }, + { + "epoch": 1.88, + "learning_rate": 1.0136328688700958e-07, + "loss": 0.1265, + "step": 14651 + }, + { + "epoch": 1.88, + "learning_rate": 1.0115574690721886e-07, + "loss": 0.1345, + "step": 14652 + }, + { + "epoch": 1.88, + "learning_rate": 1.0094841744167583e-07, + "loss": 0.1501, + "step": 14653 + }, + { + "epoch": 1.88, + "learning_rate": 1.0074129849928948e-07, + "loss": 0.1469, + "step": 14654 + }, + { + "epoch": 1.88, + "learning_rate": 1.005343900889616e-07, + "loss": 0.1184, + "step": 14655 + }, + { + "epoch": 1.88, + "learning_rate": 1.0032769221958227e-07, + "loss": 0.1372, + "step": 14656 + }, + { + "epoch": 1.88, + "learning_rate": 1.0012120490003385e-07, + "loss": 0.1333, + "step": 14657 + }, + { + "epoch": 1.88, + "learning_rate": 9.99149281391898e-08, + "loss": 0.1121, + "step": 14658 + }, + { + "epoch": 1.88, + "learning_rate": 9.970886194591467e-08, + "loss": 0.1235, + "step": 14659 + }, + { + "epoch": 1.88, + "learning_rate": 9.950300632906363e-08, + "loss": 0.125, + "step": 14660 + }, + { + "epoch": 1.88, + "learning_rate": 9.92973612974818e-08, + "loss": 0.1295, + "step": 14661 + }, + { + "epoch": 1.88, + "learning_rate": 9.909192686000713e-08, + "loss": 0.1312, + "step": 14662 + }, + { + "epoch": 1.88, + "learning_rate": 9.888670302546754e-08, + "loss": 0.1254, + "step": 14663 + }, + { + "epoch": 1.88, + "learning_rate": 9.8681689802681e-08, + "loss": 0.1166, + "step": 14664 + }, + { + "epoch": 1.88, + "learning_rate": 9.847688720045878e-08, + "loss": 0.1474, + "step": 14665 + }, + { + "epoch": 1.88, + "learning_rate": 9.827229522759996e-08, + "loss": 0.1468, + "step": 14666 + }, + { + "epoch": 1.88, + "learning_rate": 9.806791389289861e-08, + "loss": 0.122, + "step": 14667 + }, + { + "epoch": 1.88, + "learning_rate": 9.786374320513547e-08, + "loss": 0.133, + "step": 14668 + }, + { + "epoch": 1.88, + "learning_rate": 9.765978317308522e-08, + "loss": 0.141, + "step": 14669 + }, + { + "epoch": 1.88, + "learning_rate": 9.745603380551194e-08, + "loss": 0.1344, + "step": 14670 + }, + { + "epoch": 1.88, + "learning_rate": 9.72524951111714e-08, + "loss": 0.1275, + "step": 14671 + }, + { + "epoch": 1.88, + "learning_rate": 9.704916709881052e-08, + "loss": 0.1335, + "step": 14672 + }, + { + "epoch": 1.88, + "learning_rate": 9.684604977716616e-08, + "loss": 0.1564, + "step": 14673 + }, + { + "epoch": 1.88, + "learning_rate": 9.664314315496692e-08, + "loss": 0.132, + "step": 14674 + }, + { + "epoch": 1.88, + "learning_rate": 9.644044724093249e-08, + "loss": 0.1447, + "step": 14675 + }, + { + "epoch": 1.88, + "learning_rate": 9.6237962043772e-08, + "loss": 0.128, + "step": 14676 + }, + { + "epoch": 1.88, + "learning_rate": 9.603568757218795e-08, + "loss": 0.1415, + "step": 14677 + }, + { + "epoch": 1.88, + "learning_rate": 9.583362383487283e-08, + "loss": 0.1273, + "step": 14678 + }, + { + "epoch": 1.88, + "learning_rate": 9.5631770840508e-08, + "loss": 0.1393, + "step": 14679 + }, + { + "epoch": 1.88, + "learning_rate": 9.543012859776934e-08, + "loss": 0.1313, + "step": 14680 + }, + { + "epoch": 1.88, + "learning_rate": 9.5228697115321e-08, + "loss": 0.1365, + "step": 14681 + }, + { + "epoch": 1.88, + "learning_rate": 9.502747640181887e-08, + "loss": 0.1111, + "step": 14682 + }, + { + "epoch": 1.88, + "learning_rate": 9.482646646591042e-08, + "loss": 0.135, + "step": 14683 + }, + { + "epoch": 1.88, + "learning_rate": 9.462566731623213e-08, + "loss": 0.1325, + "step": 14684 + }, + { + "epoch": 1.88, + "learning_rate": 9.442507896141484e-08, + "loss": 0.1346, + "step": 14685 + }, + { + "epoch": 1.88, + "learning_rate": 9.422470141007667e-08, + "loss": 0.1437, + "step": 14686 + }, + { + "epoch": 1.88, + "learning_rate": 9.402453467082906e-08, + "loss": 0.1284, + "step": 14687 + }, + { + "epoch": 1.88, + "learning_rate": 9.382457875227346e-08, + "loss": 0.1183, + "step": 14688 + }, + { + "epoch": 1.88, + "learning_rate": 9.36248336630019e-08, + "loss": 0.1274, + "step": 14689 + }, + { + "epoch": 1.88, + "learning_rate": 9.342529941159862e-08, + "loss": 0.1487, + "step": 14690 + }, + { + "epoch": 1.88, + "learning_rate": 9.322597600663785e-08, + "loss": 0.1323, + "step": 14691 + }, + { + "epoch": 1.88, + "learning_rate": 9.3026863456685e-08, + "loss": 0.1331, + "step": 14692 + }, + { + "epoch": 1.88, + "learning_rate": 9.282796177029596e-08, + "loss": 0.1314, + "step": 14693 + }, + { + "epoch": 1.88, + "learning_rate": 9.262927095601782e-08, + "loss": 0.1564, + "step": 14694 + }, + { + "epoch": 1.88, + "learning_rate": 9.243079102238983e-08, + "loss": 0.1495, + "step": 14695 + }, + { + "epoch": 1.88, + "learning_rate": 9.22325219779402e-08, + "loss": 0.1164, + "step": 14696 + }, + { + "epoch": 1.88, + "learning_rate": 9.20344638311893e-08, + "loss": 0.1249, + "step": 14697 + }, + { + "epoch": 1.88, + "learning_rate": 9.183661659064869e-08, + "loss": 0.14, + "step": 14698 + }, + { + "epoch": 1.88, + "learning_rate": 9.163898026481876e-08, + "loss": 0.1188, + "step": 14699 + }, + { + "epoch": 1.88, + "learning_rate": 9.144155486219442e-08, + "loss": 0.1278, + "step": 14700 + }, + { + "epoch": 1.88, + "learning_rate": 9.124434039125774e-08, + "loss": 0.1455, + "step": 14701 + }, + { + "epoch": 1.88, + "learning_rate": 9.104733686048417e-08, + "loss": 0.1332, + "step": 14702 + }, + { + "epoch": 1.88, + "learning_rate": 9.085054427833972e-08, + "loss": 0.1557, + "step": 14703 + }, + { + "epoch": 1.88, + "learning_rate": 9.065396265327986e-08, + "loss": 0.1194, + "step": 14704 + }, + { + "epoch": 1.88, + "learning_rate": 9.045759199375393e-08, + "loss": 0.1412, + "step": 14705 + }, + { + "epoch": 1.88, + "learning_rate": 9.02614323081985e-08, + "loss": 0.1226, + "step": 14706 + }, + { + "epoch": 1.88, + "learning_rate": 9.006548360504463e-08, + "loss": 0.1278, + "step": 14707 + }, + { + "epoch": 1.88, + "learning_rate": 8.986974589271169e-08, + "loss": 0.1249, + "step": 14708 + }, + { + "epoch": 1.88, + "learning_rate": 8.967421917961072e-08, + "loss": 0.1176, + "step": 14709 + }, + { + "epoch": 1.88, + "learning_rate": 8.947890347414556e-08, + "loss": 0.1375, + "step": 14710 + }, + { + "epoch": 1.88, + "learning_rate": 8.928379878470727e-08, + "loss": 0.1185, + "step": 14711 + }, + { + "epoch": 1.88, + "learning_rate": 8.908890511968083e-08, + "loss": 0.1141, + "step": 14712 + }, + { + "epoch": 1.88, + "learning_rate": 8.889422248744173e-08, + "loss": 0.1145, + "step": 14713 + }, + { + "epoch": 1.88, + "learning_rate": 8.869975089635552e-08, + "loss": 0.1273, + "step": 14714 + }, + { + "epoch": 1.88, + "learning_rate": 8.85054903547794e-08, + "loss": 0.142, + "step": 14715 + }, + { + "epoch": 1.88, + "learning_rate": 8.831144087106003e-08, + "loss": 0.134, + "step": 14716 + }, + { + "epoch": 1.88, + "learning_rate": 8.811760245353739e-08, + "loss": 0.1496, + "step": 14717 + }, + { + "epoch": 1.88, + "learning_rate": 8.792397511054097e-08, + "loss": 0.1288, + "step": 14718 + }, + { + "epoch": 1.88, + "learning_rate": 8.773055885039072e-08, + "loss": 0.1292, + "step": 14719 + }, + { + "epoch": 1.88, + "learning_rate": 8.753735368139838e-08, + "loss": 0.1342, + "step": 14720 + }, + { + "epoch": 1.88, + "learning_rate": 8.734435961186782e-08, + "loss": 0.1313, + "step": 14721 + }, + { + "epoch": 1.88, + "learning_rate": 8.715157665008967e-08, + "loss": 0.1333, + "step": 14722 + }, + { + "epoch": 1.88, + "learning_rate": 8.69590048043506e-08, + "loss": 0.133, + "step": 14723 + }, + { + "epoch": 1.88, + "learning_rate": 8.676664408292457e-08, + "loss": 0.1364, + "step": 14724 + }, + { + "epoch": 1.88, + "learning_rate": 8.657449449407884e-08, + "loss": 0.1319, + "step": 14725 + }, + { + "epoch": 1.88, + "learning_rate": 8.63825560460696e-08, + "loss": 0.1259, + "step": 14726 + }, + { + "epoch": 1.89, + "learning_rate": 8.619082874714413e-08, + "loss": 0.1102, + "step": 14727 + }, + { + "epoch": 1.89, + "learning_rate": 8.599931260554417e-08, + "loss": 0.1215, + "step": 14728 + }, + { + "epoch": 1.89, + "learning_rate": 8.580800762949704e-08, + "loss": 0.1312, + "step": 14729 + }, + { + "epoch": 1.89, + "learning_rate": 8.561691382722337e-08, + "loss": 0.1295, + "step": 14730 + }, + { + "epoch": 1.89, + "learning_rate": 8.542603120693716e-08, + "loss": 0.1309, + "step": 14731 + }, + { + "epoch": 1.89, + "learning_rate": 8.523535977683905e-08, + "loss": 0.134, + "step": 14732 + }, + { + "epoch": 1.89, + "learning_rate": 8.504489954512363e-08, + "loss": 0.1181, + "step": 14733 + }, + { + "epoch": 1.89, + "learning_rate": 8.485465051997488e-08, + "loss": 0.124, + "step": 14734 + }, + { + "epoch": 1.89, + "learning_rate": 8.466461270956794e-08, + "loss": 0.1436, + "step": 14735 + }, + { + "epoch": 1.89, + "learning_rate": 8.447478612207072e-08, + "loss": 0.1352, + "step": 14736 + }, + { + "epoch": 1.89, + "learning_rate": 8.428517076563836e-08, + "loss": 0.1364, + "step": 14737 + }, + { + "epoch": 1.89, + "learning_rate": 8.409576664842045e-08, + "loss": 0.1327, + "step": 14738 + }, + { + "epoch": 1.89, + "learning_rate": 8.39065737785566e-08, + "loss": 0.1227, + "step": 14739 + }, + { + "epoch": 1.89, + "learning_rate": 8.371759216417474e-08, + "loss": 0.1237, + "step": 14740 + }, + { + "epoch": 1.89, + "learning_rate": 8.352882181339783e-08, + "loss": 0.1341, + "step": 14741 + }, + { + "epoch": 1.89, + "learning_rate": 8.334026273433659e-08, + "loss": 0.131, + "step": 14742 + }, + { + "epoch": 1.89, + "learning_rate": 8.315191493509456e-08, + "loss": 0.1373, + "step": 14743 + }, + { + "epoch": 1.89, + "learning_rate": 8.296377842376524e-08, + "loss": 0.1501, + "step": 14744 + }, + { + "epoch": 1.89, + "learning_rate": 8.277585320843273e-08, + "loss": 0.1492, + "step": 14745 + }, + { + "epoch": 1.89, + "learning_rate": 8.258813929717391e-08, + "loss": 0.1367, + "step": 14746 + }, + { + "epoch": 1.89, + "learning_rate": 8.240063669805343e-08, + "loss": 0.127, + "step": 14747 + }, + { + "epoch": 1.89, + "learning_rate": 8.221334541912984e-08, + "loss": 0.1444, + "step": 14748 + }, + { + "epoch": 1.89, + "learning_rate": 8.202626546845172e-08, + "loss": 0.1448, + "step": 14749 + }, + { + "epoch": 1.89, + "learning_rate": 8.183939685405762e-08, + "loss": 0.1335, + "step": 14750 + }, + { + "epoch": 1.89, + "learning_rate": 8.165273958397835e-08, + "loss": 0.1259, + "step": 14751 + }, + { + "epoch": 1.89, + "learning_rate": 8.146629366623415e-08, + "loss": 0.1355, + "step": 14752 + }, + { + "epoch": 1.89, + "learning_rate": 8.128005910883751e-08, + "loss": 0.1236, + "step": 14753 + }, + { + "epoch": 1.89, + "learning_rate": 8.109403591979148e-08, + "loss": 0.1237, + "step": 14754 + }, + { + "epoch": 1.89, + "learning_rate": 8.090822410708965e-08, + "loss": 0.131, + "step": 14755 + }, + { + "epoch": 1.89, + "learning_rate": 8.072262367871675e-08, + "loss": 0.1366, + "step": 14756 + }, + { + "epoch": 1.89, + "learning_rate": 8.053723464264863e-08, + "loss": 0.1291, + "step": 14757 + }, + { + "epoch": 1.89, + "learning_rate": 8.035205700685167e-08, + "loss": 0.1287, + "step": 14758 + }, + { + "epoch": 1.89, + "learning_rate": 8.016709077928397e-08, + "loss": 0.151, + "step": 14759 + }, + { + "epoch": 1.89, + "learning_rate": 7.998233596789251e-08, + "loss": 0.1348, + "step": 14760 + }, + { + "epoch": 1.89, + "learning_rate": 7.97977925806187e-08, + "loss": 0.1391, + "step": 14761 + }, + { + "epoch": 1.89, + "learning_rate": 7.961346062539066e-08, + "loss": 0.1206, + "step": 14762 + }, + { + "epoch": 1.89, + "learning_rate": 7.942934011013037e-08, + "loss": 0.133, + "step": 14763 + }, + { + "epoch": 1.89, + "learning_rate": 7.924543104275095e-08, + "loss": 0.1263, + "step": 14764 + }, + { + "epoch": 1.89, + "learning_rate": 7.906173343115386e-08, + "loss": 0.1376, + "step": 14765 + }, + { + "epoch": 1.89, + "learning_rate": 7.88782472832339e-08, + "loss": 0.1308, + "step": 14766 + }, + { + "epoch": 1.89, + "learning_rate": 7.86949726068753e-08, + "loss": 0.1319, + "step": 14767 + }, + { + "epoch": 1.89, + "learning_rate": 7.851190940995402e-08, + "loss": 0.1285, + "step": 14768 + }, + { + "epoch": 1.89, + "learning_rate": 7.832905770033705e-08, + "loss": 0.1416, + "step": 14769 + }, + { + "epoch": 1.89, + "learning_rate": 7.814641748588148e-08, + "loss": 0.1255, + "step": 14770 + }, + { + "epoch": 1.89, + "learning_rate": 7.796398877443545e-08, + "loss": 0.132, + "step": 14771 + }, + { + "epoch": 1.89, + "learning_rate": 7.778177157383993e-08, + "loss": 0.1332, + "step": 14772 + }, + { + "epoch": 1.89, + "learning_rate": 7.759976589192309e-08, + "loss": 0.132, + "step": 14773 + }, + { + "epoch": 1.89, + "learning_rate": 7.7417971736507e-08, + "loss": 0.1325, + "step": 14774 + }, + { + "epoch": 1.89, + "learning_rate": 7.723638911540432e-08, + "loss": 0.1218, + "step": 14775 + }, + { + "epoch": 1.89, + "learning_rate": 7.705501803641769e-08, + "loss": 0.1372, + "step": 14776 + }, + { + "epoch": 1.89, + "learning_rate": 7.687385850734086e-08, + "loss": 0.1314, + "step": 14777 + }, + { + "epoch": 1.89, + "learning_rate": 7.669291053595818e-08, + "loss": 0.13, + "step": 14778 + }, + { + "epoch": 1.89, + "learning_rate": 7.651217413004674e-08, + "loss": 0.1248, + "step": 14779 + }, + { + "epoch": 1.89, + "learning_rate": 7.633164929737202e-08, + "loss": 0.1254, + "step": 14780 + }, + { + "epoch": 1.89, + "learning_rate": 7.615133604569113e-08, + "loss": 0.1248, + "step": 14781 + }, + { + "epoch": 1.89, + "learning_rate": 7.597123438275399e-08, + "loss": 0.1261, + "step": 14782 + }, + { + "epoch": 1.89, + "learning_rate": 7.579134431629942e-08, + "loss": 0.1313, + "step": 14783 + }, + { + "epoch": 1.89, + "learning_rate": 7.561166585405789e-08, + "loss": 0.1324, + "step": 14784 + }, + { + "epoch": 1.89, + "learning_rate": 7.543219900374987e-08, + "loss": 0.1302, + "step": 14785 + }, + { + "epoch": 1.89, + "learning_rate": 7.525294377308812e-08, + "loss": 0.1367, + "step": 14786 + }, + { + "epoch": 1.89, + "learning_rate": 7.507390016977478e-08, + "loss": 0.1342, + "step": 14787 + }, + { + "epoch": 1.89, + "learning_rate": 7.489506820150483e-08, + "loss": 0.1427, + "step": 14788 + }, + { + "epoch": 1.89, + "learning_rate": 7.47164478759621e-08, + "loss": 0.1324, + "step": 14789 + }, + { + "epoch": 1.89, + "learning_rate": 7.453803920082381e-08, + "loss": 0.1394, + "step": 14790 + }, + { + "epoch": 1.89, + "learning_rate": 7.435984218375436e-08, + "loss": 0.1199, + "step": 14791 + }, + { + "epoch": 1.89, + "learning_rate": 7.418185683241319e-08, + "loss": 0.1267, + "step": 14792 + }, + { + "epoch": 1.89, + "learning_rate": 7.400408315444807e-08, + "loss": 0.1321, + "step": 14793 + }, + { + "epoch": 1.89, + "learning_rate": 7.382652115749789e-08, + "loss": 0.1306, + "step": 14794 + }, + { + "epoch": 1.89, + "learning_rate": 7.364917084919376e-08, + "loss": 0.1211, + "step": 14795 + }, + { + "epoch": 1.89, + "learning_rate": 7.347203223715571e-08, + "loss": 0.1198, + "step": 14796 + }, + { + "epoch": 1.89, + "learning_rate": 7.329510532899708e-08, + "loss": 0.132, + "step": 14797 + }, + { + "epoch": 1.89, + "learning_rate": 7.311839013231959e-08, + "loss": 0.133, + "step": 14798 + }, + { + "epoch": 1.89, + "learning_rate": 7.294188665471769e-08, + "loss": 0.1394, + "step": 14799 + }, + { + "epoch": 1.89, + "learning_rate": 7.276559490377644e-08, + "loss": 0.1295, + "step": 14800 + }, + { + "epoch": 1.89, + "learning_rate": 7.258951488707089e-08, + "loss": 0.1296, + "step": 14801 + }, + { + "epoch": 1.89, + "learning_rate": 7.241364661216776e-08, + "loss": 0.1202, + "step": 14802 + }, + { + "epoch": 1.89, + "learning_rate": 7.223799008662491e-08, + "loss": 0.134, + "step": 14803 + }, + { + "epoch": 1.89, + "learning_rate": 7.206254531799018e-08, + "loss": 0.1258, + "step": 14804 + }, + { + "epoch": 1.9, + "learning_rate": 7.188731231380253e-08, + "loss": 0.1346, + "step": 14805 + }, + { + "epoch": 1.9, + "learning_rate": 7.171229108159262e-08, + "loss": 0.1469, + "step": 14806 + }, + { + "epoch": 1.9, + "learning_rate": 7.153748162888164e-08, + "loss": 0.1329, + "step": 14807 + }, + { + "epoch": 1.9, + "learning_rate": 7.136288396318192e-08, + "loss": 0.1244, + "step": 14808 + }, + { + "epoch": 1.9, + "learning_rate": 7.118849809199524e-08, + "loss": 0.1322, + "step": 14809 + }, + { + "epoch": 1.9, + "learning_rate": 7.10143240228156e-08, + "loss": 0.1248, + "step": 14810 + }, + { + "epoch": 1.9, + "learning_rate": 7.084036176312814e-08, + "loss": 0.1228, + "step": 14811 + }, + { + "epoch": 1.9, + "learning_rate": 7.066661132040853e-08, + "loss": 0.1208, + "step": 14812 + }, + { + "epoch": 1.9, + "learning_rate": 7.049307270212246e-08, + "loss": 0.1278, + "step": 14813 + }, + { + "epoch": 1.9, + "learning_rate": 7.031974591572732e-08, + "loss": 0.1282, + "step": 14814 + }, + { + "epoch": 1.9, + "learning_rate": 7.014663096867214e-08, + "loss": 0.1245, + "step": 14815 + }, + { + "epoch": 1.9, + "learning_rate": 6.99737278683954e-08, + "loss": 0.1194, + "step": 14816 + }, + { + "epoch": 1.9, + "learning_rate": 6.980103662232728e-08, + "loss": 0.1094, + "step": 14817 + }, + { + "epoch": 1.9, + "learning_rate": 6.962855723788909e-08, + "loss": 0.1332, + "step": 14818 + }, + { + "epoch": 1.9, + "learning_rate": 6.945628972249208e-08, + "loss": 0.1326, + "step": 14819 + }, + { + "epoch": 1.9, + "learning_rate": 6.928423408353979e-08, + "loss": 0.1265, + "step": 14820 + }, + { + "epoch": 1.9, + "learning_rate": 6.91123903284241e-08, + "loss": 0.1296, + "step": 14821 + }, + { + "epoch": 1.9, + "learning_rate": 6.894075846453185e-08, + "loss": 0.1328, + "step": 14822 + }, + { + "epoch": 1.9, + "learning_rate": 6.876933849923662e-08, + "loss": 0.1192, + "step": 14823 + }, + { + "epoch": 1.9, + "learning_rate": 6.859813043990526e-08, + "loss": 0.1436, + "step": 14824 + }, + { + "epoch": 1.9, + "learning_rate": 6.842713429389525e-08, + "loss": 0.134, + "step": 14825 + }, + { + "epoch": 1.9, + "learning_rate": 6.825635006855458e-08, + "loss": 0.1345, + "step": 14826 + }, + { + "epoch": 1.9, + "learning_rate": 6.808577777122183e-08, + "loss": 0.1358, + "step": 14827 + }, + { + "epoch": 1.9, + "learning_rate": 6.79154174092278e-08, + "loss": 0.1343, + "step": 14828 + }, + { + "epoch": 1.9, + "learning_rate": 6.77452689898922e-08, + "loss": 0.1267, + "step": 14829 + }, + { + "epoch": 1.9, + "learning_rate": 6.757533252052695e-08, + "loss": 0.1464, + "step": 14830 + }, + { + "epoch": 1.9, + "learning_rate": 6.74056080084351e-08, + "loss": 0.1432, + "step": 14831 + }, + { + "epoch": 1.9, + "learning_rate": 6.723609546090915e-08, + "loss": 0.1229, + "step": 14832 + }, + { + "epoch": 1.9, + "learning_rate": 6.706679488523494e-08, + "loss": 0.1336, + "step": 14833 + }, + { + "epoch": 1.9, + "learning_rate": 6.689770628868609e-08, + "loss": 0.1346, + "step": 14834 + }, + { + "epoch": 1.9, + "learning_rate": 6.672882967852956e-08, + "loss": 0.1243, + "step": 14835 + }, + { + "epoch": 1.9, + "learning_rate": 6.656016506202234e-08, + "loss": 0.1261, + "step": 14836 + }, + { + "epoch": 1.9, + "learning_rate": 6.639171244641252e-08, + "loss": 0.1154, + "step": 14837 + }, + { + "epoch": 1.9, + "learning_rate": 6.622347183893818e-08, + "loss": 0.1206, + "step": 14838 + }, + { + "epoch": 1.9, + "learning_rate": 6.605544324682855e-08, + "loss": 0.1295, + "step": 14839 + }, + { + "epoch": 1.9, + "learning_rate": 6.58876266773062e-08, + "loss": 0.1253, + "step": 14840 + }, + { + "epoch": 1.9, + "learning_rate": 6.572002213758144e-08, + "loss": 0.1286, + "step": 14841 + }, + { + "epoch": 1.9, + "learning_rate": 6.555262963485576e-08, + "loss": 0.1349, + "step": 14842 + }, + { + "epoch": 1.9, + "learning_rate": 6.53854491763234e-08, + "loss": 0.124, + "step": 14843 + }, + { + "epoch": 1.9, + "learning_rate": 6.521848076916859e-08, + "loss": 0.1394, + "step": 14844 + }, + { + "epoch": 1.9, + "learning_rate": 6.505172442056562e-08, + "loss": 0.1282, + "step": 14845 + }, + { + "epoch": 1.9, + "learning_rate": 6.488518013768096e-08, + "loss": 0.1256, + "step": 14846 + }, + { + "epoch": 1.9, + "learning_rate": 6.471884792767169e-08, + "loss": 0.1363, + "step": 14847 + }, + { + "epoch": 1.9, + "learning_rate": 6.455272779768429e-08, + "loss": 0.1255, + "step": 14848 + }, + { + "epoch": 1.9, + "learning_rate": 6.438681975485805e-08, + "loss": 0.1496, + "step": 14849 + }, + { + "epoch": 1.9, + "learning_rate": 6.422112380632228e-08, + "loss": 0.1232, + "step": 14850 + }, + { + "epoch": 1.9, + "learning_rate": 6.40556399591985e-08, + "loss": 0.131, + "step": 14851 + }, + { + "epoch": 1.9, + "learning_rate": 6.389036822059546e-08, + "loss": 0.1437, + "step": 14852 + }, + { + "epoch": 1.9, + "learning_rate": 6.372530859761694e-08, + "loss": 0.1243, + "step": 14853 + }, + { + "epoch": 1.9, + "learning_rate": 6.356046109735614e-08, + "loss": 0.1149, + "step": 14854 + }, + { + "epoch": 1.9, + "learning_rate": 6.339582572689573e-08, + "loss": 0.1452, + "step": 14855 + }, + { + "epoch": 1.9, + "learning_rate": 6.323140249331116e-08, + "loss": 0.1359, + "step": 14856 + }, + { + "epoch": 1.9, + "learning_rate": 6.306719140366791e-08, + "loss": 0.1287, + "step": 14857 + }, + { + "epoch": 1.9, + "learning_rate": 6.290319246502363e-08, + "loss": 0.1215, + "step": 14858 + }, + { + "epoch": 1.9, + "learning_rate": 6.273940568442327e-08, + "loss": 0.1355, + "step": 14859 + }, + { + "epoch": 1.9, + "learning_rate": 6.25758310689073e-08, + "loss": 0.1336, + "step": 14860 + }, + { + "epoch": 1.9, + "learning_rate": 6.241246862550398e-08, + "loss": 0.1346, + "step": 14861 + }, + { + "epoch": 1.9, + "learning_rate": 6.224931836123327e-08, + "loss": 0.1319, + "step": 14862 + }, + { + "epoch": 1.9, + "learning_rate": 6.208638028310677e-08, + "loss": 0.1282, + "step": 14863 + }, + { + "epoch": 1.9, + "learning_rate": 6.192365439812553e-08, + "loss": 0.1377, + "step": 14864 + }, + { + "epoch": 1.9, + "learning_rate": 6.176114071328287e-08, + "loss": 0.1349, + "step": 14865 + }, + { + "epoch": 1.9, + "learning_rate": 6.159883923556154e-08, + "loss": 0.1238, + "step": 14866 + }, + { + "epoch": 1.9, + "learning_rate": 6.143674997193649e-08, + "loss": 0.1193, + "step": 14867 + }, + { + "epoch": 1.9, + "learning_rate": 6.127487292937328e-08, + "loss": 0.1187, + "step": 14868 + }, + { + "epoch": 1.9, + "learning_rate": 6.111320811482802e-08, + "loss": 0.113, + "step": 14869 + }, + { + "epoch": 1.9, + "learning_rate": 6.095175553524735e-08, + "loss": 0.1274, + "step": 14870 + }, + { + "epoch": 1.9, + "learning_rate": 6.079051519757018e-08, + "loss": 0.1347, + "step": 14871 + }, + { + "epoch": 1.9, + "learning_rate": 6.062948710872373e-08, + "loss": 0.1338, + "step": 14872 + }, + { + "epoch": 1.9, + "learning_rate": 6.046867127563027e-08, + "loss": 0.1141, + "step": 14873 + }, + { + "epoch": 1.9, + "learning_rate": 6.030806770519815e-08, + "loss": 0.1386, + "step": 14874 + }, + { + "epoch": 1.9, + "learning_rate": 6.014767640432905e-08, + "loss": 0.1446, + "step": 14875 + }, + { + "epoch": 1.9, + "learning_rate": 5.998749737991693e-08, + "loss": 0.149, + "step": 14876 + }, + { + "epoch": 1.9, + "learning_rate": 5.98275306388435e-08, + "loss": 0.1436, + "step": 14877 + }, + { + "epoch": 1.9, + "learning_rate": 5.96677761879838e-08, + "loss": 0.1241, + "step": 14878 + }, + { + "epoch": 1.9, + "learning_rate": 5.9508234034202364e-08, + "loss": 0.1288, + "step": 14879 + }, + { + "epoch": 1.9, + "learning_rate": 5.9348904184354795e-08, + "loss": 0.128, + "step": 14880 + }, + { + "epoch": 1.9, + "learning_rate": 5.918978664528841e-08, + "loss": 0.1415, + "step": 14881 + }, + { + "epoch": 1.9, + "learning_rate": 5.903088142384106e-08, + "loss": 0.1312, + "step": 14882 + }, + { + "epoch": 1.91, + "learning_rate": 5.887218852684007e-08, + "loss": 0.1294, + "step": 14883 + }, + { + "epoch": 1.91, + "learning_rate": 5.871370796110665e-08, + "loss": 0.125, + "step": 14884 + }, + { + "epoch": 1.91, + "learning_rate": 5.855543973344924e-08, + "loss": 0.1305, + "step": 14885 + }, + { + "epoch": 1.91, + "learning_rate": 5.8397383850670176e-08, + "loss": 0.1407, + "step": 14886 + }, + { + "epoch": 1.91, + "learning_rate": 5.823954031956069e-08, + "loss": 0.1364, + "step": 14887 + }, + { + "epoch": 1.91, + "learning_rate": 5.808190914690426e-08, + "loss": 0.1442, + "step": 14888 + }, + { + "epoch": 1.91, + "learning_rate": 5.7924490339474335e-08, + "loss": 0.1325, + "step": 14889 + }, + { + "epoch": 1.91, + "learning_rate": 5.776728390403552e-08, + "loss": 0.1254, + "step": 14890 + }, + { + "epoch": 1.91, + "learning_rate": 5.761028984734407e-08, + "loss": 0.1454, + "step": 14891 + }, + { + "epoch": 1.91, + "learning_rate": 5.74535081761457e-08, + "loss": 0.1424, + "step": 14892 + }, + { + "epoch": 1.91, + "learning_rate": 5.7296938897177245e-08, + "loss": 0.1102, + "step": 14893 + }, + { + "epoch": 1.91, + "learning_rate": 5.7140582017167764e-08, + "loss": 0.1249, + "step": 14894 + }, + { + "epoch": 1.91, + "learning_rate": 5.6984437542835225e-08, + "loss": 0.1206, + "step": 14895 + }, + { + "epoch": 1.91, + "learning_rate": 5.682850548089036e-08, + "loss": 0.1147, + "step": 14896 + }, + { + "epoch": 1.91, + "learning_rate": 5.6672785838033925e-08, + "loss": 0.1337, + "step": 14897 + }, + { + "epoch": 1.91, + "learning_rate": 5.651727862095668e-08, + "loss": 0.1245, + "step": 14898 + }, + { + "epoch": 1.91, + "learning_rate": 5.636198383634217e-08, + "loss": 0.1351, + "step": 14899 + }, + { + "epoch": 1.91, + "learning_rate": 5.620690149086283e-08, + "loss": 0.1368, + "step": 14900 + }, + { + "epoch": 1.91, + "learning_rate": 5.6052031591183884e-08, + "loss": 0.1419, + "step": 14901 + }, + { + "epoch": 1.91, + "learning_rate": 5.5897374143960013e-08, + "loss": 0.1209, + "step": 14902 + }, + { + "epoch": 1.91, + "learning_rate": 5.574292915583646e-08, + "loss": 0.1154, + "step": 14903 + }, + { + "epoch": 1.91, + "learning_rate": 5.558869663345123e-08, + "loss": 0.1304, + "step": 14904 + }, + { + "epoch": 1.91, + "learning_rate": 5.543467658343127e-08, + "loss": 0.129, + "step": 14905 + }, + { + "epoch": 1.91, + "learning_rate": 5.5280869012395154e-08, + "loss": 0.1216, + "step": 14906 + }, + { + "epoch": 1.91, + "learning_rate": 5.5127273926953165e-08, + "loss": 0.1198, + "step": 14907 + }, + { + "epoch": 1.91, + "learning_rate": 5.4973891333704453e-08, + "loss": 0.1265, + "step": 14908 + }, + { + "epoch": 1.91, + "learning_rate": 5.482072123924098e-08, + "loss": 0.1212, + "step": 14909 + }, + { + "epoch": 1.91, + "learning_rate": 5.46677636501447e-08, + "loss": 0.1379, + "step": 14910 + }, + { + "epoch": 1.91, + "learning_rate": 5.4515018572988687e-08, + "loss": 0.1419, + "step": 14911 + }, + { + "epoch": 1.91, + "learning_rate": 5.436248601433658e-08, + "loss": 0.1601, + "step": 14912 + }, + { + "epoch": 1.91, + "learning_rate": 5.4210165980742025e-08, + "loss": 0.1467, + "step": 14913 + }, + { + "epoch": 1.91, + "learning_rate": 5.405805847875256e-08, + "loss": 0.1318, + "step": 14914 + }, + { + "epoch": 1.91, + "learning_rate": 5.3906163514902966e-08, + "loss": 0.1387, + "step": 14915 + }, + { + "epoch": 1.91, + "learning_rate": 5.3754481095721344e-08, + "loss": 0.1329, + "step": 14916 + }, + { + "epoch": 1.91, + "learning_rate": 5.3603011227725265e-08, + "loss": 0.1282, + "step": 14917 + }, + { + "epoch": 1.91, + "learning_rate": 5.3451753917423964e-08, + "loss": 0.1131, + "step": 14918 + }, + { + "epoch": 1.91, + "learning_rate": 5.330070917131724e-08, + "loss": 0.1373, + "step": 14919 + }, + { + "epoch": 1.91, + "learning_rate": 5.3149876995896575e-08, + "loss": 0.1266, + "step": 14920 + }, + { + "epoch": 1.91, + "learning_rate": 5.299925739764233e-08, + "loss": 0.1419, + "step": 14921 + }, + { + "epoch": 1.91, + "learning_rate": 5.284885038302823e-08, + "loss": 0.1163, + "step": 14922 + }, + { + "epoch": 1.91, + "learning_rate": 5.269865595851631e-08, + "loss": 0.1242, + "step": 14923 + }, + { + "epoch": 1.91, + "learning_rate": 5.2548674130561974e-08, + "loss": 0.12, + "step": 14924 + }, + { + "epoch": 1.91, + "learning_rate": 5.239890490560895e-08, + "loss": 0.1341, + "step": 14925 + }, + { + "epoch": 1.91, + "learning_rate": 5.224934829009376e-08, + "loss": 0.1105, + "step": 14926 + }, + { + "epoch": 1.91, + "learning_rate": 5.21000042904446e-08, + "loss": 0.12, + "step": 14927 + }, + { + "epoch": 1.91, + "learning_rate": 5.195087291307632e-08, + "loss": 0.1454, + "step": 14928 + }, + { + "epoch": 1.91, + "learning_rate": 5.1801954164399925e-08, + "loss": 0.1261, + "step": 14929 + }, + { + "epoch": 1.91, + "learning_rate": 5.165324805081362e-08, + "loss": 0.1204, + "step": 14930 + }, + { + "epoch": 1.91, + "learning_rate": 5.1504754578707294e-08, + "loss": 0.1294, + "step": 14931 + }, + { + "epoch": 1.91, + "learning_rate": 5.135647375446307e-08, + "loss": 0.1487, + "step": 14932 + }, + { + "epoch": 1.91, + "learning_rate": 5.120840558445195e-08, + "loss": 0.1254, + "step": 14933 + }, + { + "epoch": 1.91, + "learning_rate": 5.106055007503774e-08, + "loss": 0.1254, + "step": 14934 + }, + { + "epoch": 1.91, + "learning_rate": 5.091290723257314e-08, + "loss": 0.1268, + "step": 14935 + }, + { + "epoch": 1.91, + "learning_rate": 5.076547706340307e-08, + "loss": 0.1309, + "step": 14936 + }, + { + "epoch": 1.91, + "learning_rate": 5.061825957386302e-08, + "loss": 0.1441, + "step": 14937 + }, + { + "epoch": 1.91, + "learning_rate": 5.047125477027959e-08, + "loss": 0.1295, + "step": 14938 + }, + { + "epoch": 1.91, + "learning_rate": 5.0324462658969395e-08, + "loss": 0.1338, + "step": 14939 + }, + { + "epoch": 1.91, + "learning_rate": 5.017788324624073e-08, + "loss": 0.1497, + "step": 14940 + }, + { + "epoch": 1.91, + "learning_rate": 5.003151653839189e-08, + "loss": 0.1336, + "step": 14941 + }, + { + "epoch": 1.91, + "learning_rate": 4.988536254171284e-08, + "loss": 0.1324, + "step": 14942 + }, + { + "epoch": 1.91, + "learning_rate": 4.9739421262484656e-08, + "loss": 0.1342, + "step": 14943 + }, + { + "epoch": 1.91, + "learning_rate": 4.959369270697789e-08, + "loss": 0.1338, + "step": 14944 + }, + { + "epoch": 1.91, + "learning_rate": 4.944817688145642e-08, + "loss": 0.1156, + "step": 14945 + }, + { + "epoch": 1.91, + "learning_rate": 4.93028737921708e-08, + "loss": 0.1215, + "step": 14946 + }, + { + "epoch": 1.91, + "learning_rate": 4.915778344536715e-08, + "loss": 0.1332, + "step": 14947 + }, + { + "epoch": 1.91, + "learning_rate": 4.9012905847279913e-08, + "loss": 0.1218, + "step": 14948 + }, + { + "epoch": 1.91, + "learning_rate": 4.886824100413412e-08, + "loss": 0.1322, + "step": 14949 + }, + { + "epoch": 1.91, + "learning_rate": 4.872378892214702e-08, + "loss": 0.1202, + "step": 14950 + }, + { + "epoch": 1.91, + "learning_rate": 4.8579549607525866e-08, + "loss": 0.1208, + "step": 14951 + }, + { + "epoch": 1.91, + "learning_rate": 4.843552306646904e-08, + "loss": 0.1354, + "step": 14952 + }, + { + "epoch": 1.91, + "learning_rate": 4.829170930516491e-08, + "loss": 0.1397, + "step": 14953 + }, + { + "epoch": 1.91, + "learning_rate": 4.814810832979411e-08, + "loss": 0.1269, + "step": 14954 + }, + { + "epoch": 1.91, + "learning_rate": 4.8004720146527795e-08, + "loss": 0.1319, + "step": 14955 + }, + { + "epoch": 1.91, + "learning_rate": 4.786154476152716e-08, + "loss": 0.1212, + "step": 14956 + }, + { + "epoch": 1.91, + "learning_rate": 4.771858218094505e-08, + "loss": 0.1468, + "step": 14957 + }, + { + "epoch": 1.91, + "learning_rate": 4.7575832410924893e-08, + "loss": 0.1375, + "step": 14958 + }, + { + "epoch": 1.91, + "learning_rate": 4.743329545760122e-08, + "loss": 0.1385, + "step": 14959 + }, + { + "epoch": 1.91, + "learning_rate": 4.7290971327098035e-08, + "loss": 0.1262, + "step": 14960 + }, + { + "epoch": 1.92, + "learning_rate": 4.71488600255321e-08, + "loss": 0.1276, + "step": 14961 + }, + { + "epoch": 1.92, + "learning_rate": 4.7006961559010745e-08, + "loss": 0.1472, + "step": 14962 + }, + { + "epoch": 1.92, + "learning_rate": 4.686527593363133e-08, + "loss": 0.1175, + "step": 14963 + }, + { + "epoch": 1.92, + "learning_rate": 4.67238031554812e-08, + "loss": 0.1439, + "step": 14964 + }, + { + "epoch": 1.92, + "learning_rate": 4.6582543230641596e-08, + "loss": 0.1278, + "step": 14965 + }, + { + "epoch": 1.92, + "learning_rate": 4.644149616518212e-08, + "loss": 0.1318, + "step": 14966 + }, + { + "epoch": 1.92, + "learning_rate": 4.630066196516347e-08, + "loss": 0.119, + "step": 14967 + }, + { + "epoch": 1.92, + "learning_rate": 4.6160040636637484e-08, + "loss": 0.1348, + "step": 14968 + }, + { + "epoch": 1.92, + "learning_rate": 4.6019632185647645e-08, + "loss": 0.1397, + "step": 14969 + }, + { + "epoch": 1.92, + "learning_rate": 4.587943661822747e-08, + "loss": 0.1293, + "step": 14970 + }, + { + "epoch": 1.92, + "learning_rate": 4.5739453940401024e-08, + "loss": 0.1282, + "step": 14971 + }, + { + "epoch": 1.92, + "learning_rate": 4.5599684158184055e-08, + "loss": 0.1239, + "step": 14972 + }, + { + "epoch": 1.92, + "learning_rate": 4.5460127277582863e-08, + "loss": 0.1238, + "step": 14973 + }, + { + "epoch": 1.92, + "learning_rate": 4.532078330459433e-08, + "loss": 0.1263, + "step": 14974 + }, + { + "epoch": 1.92, + "learning_rate": 4.518165224520643e-08, + "loss": 0.1236, + "step": 14975 + }, + { + "epoch": 1.92, + "learning_rate": 4.504273410539772e-08, + "loss": 0.1366, + "step": 14976 + }, + { + "epoch": 1.92, + "learning_rate": 4.490402889113787e-08, + "loss": 0.1427, + "step": 14977 + }, + { + "epoch": 1.92, + "learning_rate": 4.4765536608388227e-08, + "loss": 0.1207, + "step": 14978 + }, + { + "epoch": 1.92, + "learning_rate": 4.4627257263098465e-08, + "loss": 0.1285, + "step": 14979 + }, + { + "epoch": 1.92, + "learning_rate": 4.448919086121217e-08, + "loss": 0.1536, + "step": 14980 + }, + { + "epoch": 1.92, + "learning_rate": 4.435133740866182e-08, + "loss": 0.134, + "step": 14981 + }, + { + "epoch": 1.92, + "learning_rate": 4.4213696911371006e-08, + "loss": 0.135, + "step": 14982 + }, + { + "epoch": 1.92, + "learning_rate": 4.4076269375255e-08, + "loss": 0.1295, + "step": 14983 + }, + { + "epoch": 1.92, + "learning_rate": 4.393905480621907e-08, + "loss": 0.122, + "step": 14984 + }, + { + "epoch": 1.92, + "learning_rate": 4.380205321016018e-08, + "loss": 0.1505, + "step": 14985 + }, + { + "epoch": 1.92, + "learning_rate": 4.366526459296472e-08, + "loss": 0.1254, + "step": 14986 + }, + { + "epoch": 1.92, + "learning_rate": 4.352868896051077e-08, + "loss": 0.131, + "step": 14987 + }, + { + "epoch": 1.92, + "learning_rate": 4.3392326318668076e-08, + "loss": 0.1325, + "step": 14988 + }, + { + "epoch": 1.92, + "learning_rate": 4.3256176673295846e-08, + "loss": 0.1236, + "step": 14989 + }, + { + "epoch": 1.92, + "learning_rate": 4.312024003024551e-08, + "loss": 0.1313, + "step": 14990 + }, + { + "epoch": 1.92, + "learning_rate": 4.2984516395357944e-08, + "loss": 0.1226, + "step": 14991 + }, + { + "epoch": 1.92, + "learning_rate": 4.284900577446516e-08, + "loss": 0.1379, + "step": 14992 + }, + { + "epoch": 1.92, + "learning_rate": 4.271370817339082e-08, + "loss": 0.1332, + "step": 14993 + }, + { + "epoch": 1.92, + "learning_rate": 4.2578623597949174e-08, + "loss": 0.1398, + "step": 14994 + }, + { + "epoch": 1.92, + "learning_rate": 4.244375205394502e-08, + "loss": 0.135, + "step": 14995 + }, + { + "epoch": 1.92, + "learning_rate": 4.230909354717372e-08, + "loss": 0.1299, + "step": 14996 + }, + { + "epoch": 1.92, + "learning_rate": 4.217464808342175e-08, + "loss": 0.1363, + "step": 14997 + }, + { + "epoch": 1.92, + "learning_rate": 4.204041566846673e-08, + "loss": 0.1476, + "step": 14998 + }, + { + "epoch": 1.92, + "learning_rate": 4.1906396308077356e-08, + "loss": 0.1217, + "step": 14999 + }, + { + "epoch": 1.92, + "learning_rate": 4.177259000801237e-08, + "loss": 0.1354, + "step": 15000 + }, + { + "epoch": 1.92, + "learning_rate": 4.163899677402161e-08, + "loss": 0.1426, + "step": 15001 + }, + { + "epoch": 1.92, + "learning_rate": 4.150561661184604e-08, + "loss": 0.1402, + "step": 15002 + }, + { + "epoch": 1.92, + "learning_rate": 4.1372449527217754e-08, + "loss": 0.1389, + "step": 15003 + }, + { + "epoch": 1.92, + "learning_rate": 4.123949552585826e-08, + "loss": 0.133, + "step": 15004 + }, + { + "epoch": 1.92, + "learning_rate": 4.1106754613481347e-08, + "loss": 0.1333, + "step": 15005 + }, + { + "epoch": 1.92, + "learning_rate": 4.097422679579188e-08, + "loss": 0.1255, + "step": 15006 + }, + { + "epoch": 1.92, + "learning_rate": 4.0841912078483645e-08, + "loss": 0.1287, + "step": 15007 + }, + { + "epoch": 1.92, + "learning_rate": 4.0709810467243204e-08, + "loss": 0.1396, + "step": 15008 + }, + { + "epoch": 1.92, + "learning_rate": 4.0577921967747126e-08, + "loss": 0.1384, + "step": 15009 + }, + { + "epoch": 1.92, + "learning_rate": 4.0446246585663093e-08, + "loss": 0.1231, + "step": 15010 + }, + { + "epoch": 1.92, + "learning_rate": 4.031478432664937e-08, + "loss": 0.1202, + "step": 15011 + }, + { + "epoch": 1.92, + "learning_rate": 4.018353519635476e-08, + "loss": 0.113, + "step": 15012 + }, + { + "epoch": 1.92, + "learning_rate": 4.0052499200420314e-08, + "loss": 0.1325, + "step": 15013 + }, + { + "epoch": 1.92, + "learning_rate": 3.9921676344475966e-08, + "loss": 0.132, + "step": 15014 + }, + { + "epoch": 1.92, + "learning_rate": 3.979106663414389e-08, + "loss": 0.1106, + "step": 15015 + }, + { + "epoch": 1.92, + "learning_rate": 3.9660670075036823e-08, + "loss": 0.1288, + "step": 15016 + }, + { + "epoch": 1.92, + "learning_rate": 3.953048667275805e-08, + "loss": 0.1465, + "step": 15017 + }, + { + "epoch": 1.92, + "learning_rate": 3.9400516432901434e-08, + "loss": 0.1518, + "step": 15018 + }, + { + "epoch": 1.92, + "learning_rate": 3.927075936105307e-08, + "loss": 0.1259, + "step": 15019 + }, + { + "epoch": 1.92, + "learning_rate": 3.914121546278793e-08, + "loss": 0.128, + "step": 15020 + }, + { + "epoch": 1.92, + "learning_rate": 3.901188474367323e-08, + "loss": 0.1294, + "step": 15021 + }, + { + "epoch": 1.92, + "learning_rate": 3.8882767209266756e-08, + "loss": 0.1324, + "step": 15022 + }, + { + "epoch": 1.92, + "learning_rate": 3.875386286511684e-08, + "loss": 0.1473, + "step": 15023 + }, + { + "epoch": 1.92, + "learning_rate": 3.8625171716762385e-08, + "loss": 0.1393, + "step": 15024 + }, + { + "epoch": 1.92, + "learning_rate": 3.849669376973397e-08, + "loss": 0.1194, + "step": 15025 + }, + { + "epoch": 1.92, + "learning_rate": 3.836842902955273e-08, + "loss": 0.1282, + "step": 15026 + }, + { + "epoch": 1.92, + "learning_rate": 3.8240377501729817e-08, + "loss": 0.1189, + "step": 15027 + }, + { + "epoch": 1.92, + "learning_rate": 3.8112539191768604e-08, + "loss": 0.1224, + "step": 15028 + }, + { + "epoch": 1.92, + "learning_rate": 3.7984914105162474e-08, + "loss": 0.1189, + "step": 15029 + }, + { + "epoch": 1.92, + "learning_rate": 3.785750224739482e-08, + "loss": 0.1305, + "step": 15030 + }, + { + "epoch": 1.92, + "learning_rate": 3.7730303623942364e-08, + "loss": 0.1434, + "step": 15031 + }, + { + "epoch": 1.92, + "learning_rate": 3.760331824027019e-08, + "loss": 0.1339, + "step": 15032 + }, + { + "epoch": 1.92, + "learning_rate": 3.7476546101835045e-08, + "loss": 0.1365, + "step": 15033 + }, + { + "epoch": 1.92, + "learning_rate": 3.7349987214084784e-08, + "loss": 0.1368, + "step": 15034 + }, + { + "epoch": 1.92, + "learning_rate": 3.722364158245839e-08, + "loss": 0.1291, + "step": 15035 + }, + { + "epoch": 1.92, + "learning_rate": 3.709750921238486e-08, + "loss": 0.1473, + "step": 15036 + }, + { + "epoch": 1.92, + "learning_rate": 3.697159010928375e-08, + "loss": 0.1544, + "step": 15037 + }, + { + "epoch": 1.92, + "learning_rate": 3.6845884278566836e-08, + "loss": 0.1139, + "step": 15038 + }, + { + "epoch": 1.92, + "learning_rate": 3.672039172563646e-08, + "loss": 0.1345, + "step": 15039 + }, + { + "epoch": 1.93, + "learning_rate": 3.659511245588387e-08, + "loss": 0.121, + "step": 15040 + }, + { + "epoch": 1.93, + "learning_rate": 3.647004647469365e-08, + "loss": 0.1286, + "step": 15041 + }, + { + "epoch": 1.93, + "learning_rate": 3.634519378744039e-08, + "loss": 0.1227, + "step": 15042 + }, + { + "epoch": 1.93, + "learning_rate": 3.622055439948813e-08, + "loss": 0.1328, + "step": 15043 + }, + { + "epoch": 1.93, + "learning_rate": 3.609612831619369e-08, + "loss": 0.1603, + "step": 15044 + }, + { + "epoch": 1.93, + "learning_rate": 3.597191554290391e-08, + "loss": 0.1565, + "step": 15045 + }, + { + "epoch": 1.93, + "learning_rate": 3.584791608495675e-08, + "loss": 0.1562, + "step": 15046 + }, + { + "epoch": 1.93, + "learning_rate": 3.5724129947680156e-08, + "loss": 0.1295, + "step": 15047 + }, + { + "epoch": 1.93, + "learning_rate": 3.560055713639321e-08, + "loss": 0.1222, + "step": 15048 + }, + { + "epoch": 1.93, + "learning_rate": 3.547719765640778e-08, + "loss": 0.1391, + "step": 15049 + }, + { + "epoch": 1.93, + "learning_rate": 3.5354051513022405e-08, + "loss": 0.1226, + "step": 15050 + }, + { + "epoch": 1.93, + "learning_rate": 3.523111871153118e-08, + "loss": 0.1343, + "step": 15051 + }, + { + "epoch": 1.93, + "learning_rate": 3.510839925721543e-08, + "loss": 0.1287, + "step": 15052 + }, + { + "epoch": 1.93, + "learning_rate": 3.4985893155349835e-08, + "loss": 0.1216, + "step": 15053 + }, + { + "epoch": 1.93, + "learning_rate": 3.4863600411197404e-08, + "loss": 0.1359, + "step": 15054 + }, + { + "epoch": 1.93, + "learning_rate": 3.474152103001449e-08, + "loss": 0.137, + "step": 15055 + }, + { + "epoch": 1.93, + "learning_rate": 3.461965501704634e-08, + "loss": 0.1314, + "step": 15056 + }, + { + "epoch": 1.93, + "learning_rate": 3.449800237753043e-08, + "loss": 0.1486, + "step": 15057 + }, + { + "epoch": 1.93, + "learning_rate": 3.4376563116693685e-08, + "loss": 0.1292, + "step": 15058 + }, + { + "epoch": 1.93, + "learning_rate": 3.425533723975527e-08, + "loss": 0.1368, + "step": 15059 + }, + { + "epoch": 1.93, + "learning_rate": 3.413432475192435e-08, + "loss": 0.144, + "step": 15060 + }, + { + "epoch": 1.93, + "learning_rate": 3.401352565840121e-08, + "loss": 0.1346, + "step": 15061 + }, + { + "epoch": 1.93, + "learning_rate": 3.3892939964376704e-08, + "loss": 0.1418, + "step": 15062 + }, + { + "epoch": 1.93, + "learning_rate": 3.377256767503223e-08, + "loss": 0.1208, + "step": 15063 + }, + { + "epoch": 1.93, + "learning_rate": 3.365240879554144e-08, + "loss": 0.126, + "step": 15064 + }, + { + "epoch": 1.93, + "learning_rate": 3.353246333106741e-08, + "loss": 0.1284, + "step": 15065 + }, + { + "epoch": 1.93, + "learning_rate": 3.3412731286763256e-08, + "loss": 0.1252, + "step": 15066 + }, + { + "epoch": 1.93, + "learning_rate": 3.329321266777652e-08, + "loss": 0.1243, + "step": 15067 + }, + { + "epoch": 1.93, + "learning_rate": 3.3173907479240875e-08, + "loss": 0.123, + "step": 15068 + }, + { + "epoch": 1.93, + "learning_rate": 3.3054815726285e-08, + "loss": 0.1177, + "step": 15069 + }, + { + "epoch": 1.93, + "learning_rate": 3.2935937414025345e-08, + "loss": 0.1358, + "step": 15070 + }, + { + "epoch": 1.93, + "learning_rate": 3.281727254757061e-08, + "loss": 0.1499, + "step": 15071 + }, + { + "epoch": 1.93, + "learning_rate": 3.269882113202005e-08, + "loss": 0.1355, + "step": 15072 + }, + { + "epoch": 1.93, + "learning_rate": 3.258058317246404e-08, + "loss": 0.1287, + "step": 15073 + }, + { + "epoch": 1.93, + "learning_rate": 3.2462558673983516e-08, + "loss": 0.1177, + "step": 15074 + }, + { + "epoch": 1.93, + "learning_rate": 3.234474764165052e-08, + "loss": 0.1293, + "step": 15075 + }, + { + "epoch": 1.93, + "learning_rate": 3.222715008052657e-08, + "loss": 0.1435, + "step": 15076 + }, + { + "epoch": 1.93, + "learning_rate": 3.2109765995665957e-08, + "loss": 0.1245, + "step": 15077 + }, + { + "epoch": 1.93, + "learning_rate": 3.1992595392112966e-08, + "loss": 0.1282, + "step": 15078 + }, + { + "epoch": 1.93, + "learning_rate": 3.1875638274902476e-08, + "loss": 0.1291, + "step": 15079 + }, + { + "epoch": 1.93, + "learning_rate": 3.1758894649060456e-08, + "loss": 0.1316, + "step": 15080 + }, + { + "epoch": 1.93, + "learning_rate": 3.164236451960345e-08, + "loss": 0.1461, + "step": 15081 + }, + { + "epoch": 1.93, + "learning_rate": 3.152604789153912e-08, + "loss": 0.1259, + "step": 15082 + }, + { + "epoch": 1.93, + "learning_rate": 3.140994476986625e-08, + "loss": 0.1509, + "step": 15083 + }, + { + "epoch": 1.93, + "learning_rate": 3.129405515957307e-08, + "loss": 0.139, + "step": 15084 + }, + { + "epoch": 1.93, + "learning_rate": 3.117837906564114e-08, + "loss": 0.1448, + "step": 15085 + }, + { + "epoch": 1.93, + "learning_rate": 3.106291649303983e-08, + "loss": 0.1372, + "step": 15086 + }, + { + "epoch": 1.93, + "learning_rate": 3.094766744673128e-08, + "loss": 0.1247, + "step": 15087 + }, + { + "epoch": 1.93, + "learning_rate": 3.083263193166819e-08, + "loss": 0.1442, + "step": 15088 + }, + { + "epoch": 1.93, + "learning_rate": 3.071780995279439e-08, + "loss": 0.1248, + "step": 15089 + }, + { + "epoch": 1.93, + "learning_rate": 3.060320151504315e-08, + "loss": 0.1376, + "step": 15090 + }, + { + "epoch": 1.93, + "learning_rate": 3.0488806623339414e-08, + "loss": 0.1351, + "step": 15091 + }, + { + "epoch": 1.93, + "learning_rate": 3.0374625282599826e-08, + "loss": 0.1353, + "step": 15092 + }, + { + "epoch": 1.93, + "learning_rate": 3.026065749773044e-08, + "loss": 0.125, + "step": 15093 + }, + { + "epoch": 1.93, + "learning_rate": 3.014690327362846e-08, + "loss": 0.1254, + "step": 15094 + }, + { + "epoch": 1.93, + "learning_rate": 3.003336261518275e-08, + "loss": 0.1425, + "step": 15095 + }, + { + "epoch": 1.93, + "learning_rate": 2.992003552727219e-08, + "loss": 0.1312, + "step": 15096 + }, + { + "epoch": 1.93, + "learning_rate": 2.980692201476676e-08, + "loss": 0.1246, + "step": 15097 + }, + { + "epoch": 1.93, + "learning_rate": 2.969402208252703e-08, + "loss": 0.1301, + "step": 15098 + }, + { + "epoch": 1.93, + "learning_rate": 2.9581335735404672e-08, + "loss": 0.1426, + "step": 15099 + }, + { + "epoch": 1.93, + "learning_rate": 2.9468862978241917e-08, + "loss": 0.1425, + "step": 15100 + }, + { + "epoch": 1.93, + "learning_rate": 2.9356603815872132e-08, + "loss": 0.136, + "step": 15101 + }, + { + "epoch": 1.93, + "learning_rate": 2.9244558253119226e-08, + "loss": 0.1305, + "step": 15102 + }, + { + "epoch": 1.93, + "learning_rate": 2.9132726294798242e-08, + "loss": 0.1384, + "step": 15103 + }, + { + "epoch": 1.93, + "learning_rate": 2.9021107945714777e-08, + "loss": 0.1469, + "step": 15104 + }, + { + "epoch": 1.93, + "learning_rate": 2.8909703210664995e-08, + "loss": 0.1328, + "step": 15105 + }, + { + "epoch": 1.93, + "learning_rate": 2.8798512094436738e-08, + "loss": 0.1271, + "step": 15106 + }, + { + "epoch": 1.93, + "learning_rate": 2.8687534601807842e-08, + "loss": 0.1434, + "step": 15107 + }, + { + "epoch": 1.93, + "learning_rate": 2.8576770737547276e-08, + "loss": 0.1192, + "step": 15108 + }, + { + "epoch": 1.93, + "learning_rate": 2.8466220506414565e-08, + "loss": 0.1332, + "step": 15109 + }, + { + "epoch": 1.93, + "learning_rate": 2.8355883913160907e-08, + "loss": 0.1409, + "step": 15110 + }, + { + "epoch": 1.93, + "learning_rate": 2.8245760962527514e-08, + "loss": 0.1225, + "step": 15111 + }, + { + "epoch": 1.93, + "learning_rate": 2.813585165924615e-08, + "loss": 0.1268, + "step": 15112 + }, + { + "epoch": 1.93, + "learning_rate": 2.802615600804026e-08, + "loss": 0.1387, + "step": 15113 + }, + { + "epoch": 1.93, + "learning_rate": 2.79166740136233e-08, + "loss": 0.136, + "step": 15114 + }, + { + "epoch": 1.93, + "learning_rate": 2.780740568070095e-08, + "loss": 0.1345, + "step": 15115 + }, + { + "epoch": 1.93, + "learning_rate": 2.769835101396723e-08, + "loss": 0.1318, + "step": 15116 + }, + { + "epoch": 1.93, + "learning_rate": 2.75895100181095e-08, + "loss": 0.1162, + "step": 15117 + }, + { + "epoch": 1.94, + "learning_rate": 2.7480882697805133e-08, + "loss": 0.1371, + "step": 15118 + }, + { + "epoch": 1.94, + "learning_rate": 2.7372469057721506e-08, + "loss": 0.1285, + "step": 15119 + }, + { + "epoch": 1.94, + "learning_rate": 2.7264269102517117e-08, + "loss": 0.1233, + "step": 15120 + }, + { + "epoch": 1.94, + "learning_rate": 2.7156282836842683e-08, + "loss": 0.1171, + "step": 15121 + }, + { + "epoch": 1.94, + "learning_rate": 2.704851026533728e-08, + "loss": 0.1437, + "step": 15122 + }, + { + "epoch": 1.94, + "learning_rate": 2.6940951392632753e-08, + "loss": 0.1354, + "step": 15123 + }, + { + "epoch": 1.94, + "learning_rate": 2.6833606223351515e-08, + "loss": 0.141, + "step": 15124 + }, + { + "epoch": 1.94, + "learning_rate": 2.6726474762105992e-08, + "loss": 0.1283, + "step": 15125 + }, + { + "epoch": 1.94, + "learning_rate": 2.661955701349972e-08, + "loss": 0.1189, + "step": 15126 + }, + { + "epoch": 1.94, + "learning_rate": 2.6512852982127357e-08, + "loss": 0.1455, + "step": 15127 + }, + { + "epoch": 1.94, + "learning_rate": 2.6406362672574125e-08, + "loss": 0.1307, + "step": 15128 + }, + { + "epoch": 1.94, + "learning_rate": 2.6300086089416366e-08, + "loss": 0.1384, + "step": 15129 + }, + { + "epoch": 1.94, + "learning_rate": 2.6194023237221533e-08, + "loss": 0.1123, + "step": 15130 + }, + { + "epoch": 1.94, + "learning_rate": 2.6088174120545985e-08, + "loss": 0.1344, + "step": 15131 + }, + { + "epoch": 1.94, + "learning_rate": 2.5982538743939413e-08, + "loss": 0.132, + "step": 15132 + }, + { + "epoch": 1.94, + "learning_rate": 2.5877117111940964e-08, + "loss": 0.1348, + "step": 15133 + }, + { + "epoch": 1.94, + "learning_rate": 2.577190922908035e-08, + "loss": 0.142, + "step": 15134 + }, + { + "epoch": 1.94, + "learning_rate": 2.5666915099879508e-08, + "loss": 0.1385, + "step": 15135 + }, + { + "epoch": 1.94, + "learning_rate": 2.556213472884983e-08, + "loss": 0.119, + "step": 15136 + }, + { + "epoch": 1.94, + "learning_rate": 2.5457568120493825e-08, + "loss": 0.13, + "step": 15137 + }, + { + "epoch": 1.94, + "learning_rate": 2.5353215279304566e-08, + "loss": 0.1226, + "step": 15138 + }, + { + "epoch": 1.94, + "learning_rate": 2.5249076209767353e-08, + "loss": 0.1318, + "step": 15139 + }, + { + "epoch": 1.94, + "learning_rate": 2.5145150916356386e-08, + "loss": 0.1225, + "step": 15140 + }, + { + "epoch": 1.94, + "learning_rate": 2.5041439403537537e-08, + "loss": 0.1265, + "step": 15141 + }, + { + "epoch": 1.94, + "learning_rate": 2.493794167576835e-08, + "loss": 0.1383, + "step": 15142 + }, + { + "epoch": 1.94, + "learning_rate": 2.4834657737495828e-08, + "loss": 0.1274, + "step": 15143 + }, + { + "epoch": 1.94, + "learning_rate": 2.473158759315808e-08, + "loss": 0.1345, + "step": 15144 + }, + { + "epoch": 1.94, + "learning_rate": 2.4628731247184902e-08, + "loss": 0.1334, + "step": 15145 + }, + { + "epoch": 1.94, + "learning_rate": 2.452608870399553e-08, + "loss": 0.1248, + "step": 15146 + }, + { + "epoch": 1.94, + "learning_rate": 2.4423659968001446e-08, + "loss": 0.1235, + "step": 15147 + }, + { + "epoch": 1.94, + "learning_rate": 2.4321445043603565e-08, + "loss": 0.12, + "step": 15148 + }, + { + "epoch": 1.94, + "learning_rate": 2.421944393519504e-08, + "loss": 0.1297, + "step": 15149 + }, + { + "epoch": 1.94, + "learning_rate": 2.411765664715793e-08, + "loss": 0.1157, + "step": 15150 + }, + { + "epoch": 1.94, + "learning_rate": 2.401608318386761e-08, + "loss": 0.1209, + "step": 15151 + }, + { + "epoch": 1.94, + "learning_rate": 2.3914723549687825e-08, + "loss": 0.1312, + "step": 15152 + }, + { + "epoch": 1.94, + "learning_rate": 2.381357774897508e-08, + "loss": 0.1387, + "step": 15153 + }, + { + "epoch": 1.94, + "learning_rate": 2.3712645786075905e-08, + "loss": 0.1473, + "step": 15154 + }, + { + "epoch": 1.94, + "learning_rate": 2.3611927665326275e-08, + "loss": 0.129, + "step": 15155 + }, + { + "epoch": 1.94, + "learning_rate": 2.3511423391055498e-08, + "loss": 0.126, + "step": 15156 + }, + { + "epoch": 1.94, + "learning_rate": 2.341113296758235e-08, + "loss": 0.1419, + "step": 15157 + }, + { + "epoch": 1.94, + "learning_rate": 2.3311056399216158e-08, + "loss": 0.1302, + "step": 15158 + }, + { + "epoch": 1.94, + "learning_rate": 2.3211193690257373e-08, + "loss": 0.1231, + "step": 15159 + }, + { + "epoch": 1.94, + "learning_rate": 2.3111544844997003e-08, + "loss": 0.1466, + "step": 15160 + }, + { + "epoch": 1.94, + "learning_rate": 2.3012109867718845e-08, + "loss": 0.1353, + "step": 15161 + }, + { + "epoch": 1.94, + "learning_rate": 2.291288876269393e-08, + "loss": 0.1406, + "step": 15162 + }, + { + "epoch": 1.94, + "learning_rate": 2.2813881534186622e-08, + "loss": 0.1168, + "step": 15163 + }, + { + "epoch": 1.94, + "learning_rate": 2.271508818645185e-08, + "loss": 0.1379, + "step": 15164 + }, + { + "epoch": 1.94, + "learning_rate": 2.2616508723734555e-08, + "loss": 0.1427, + "step": 15165 + }, + { + "epoch": 1.94, + "learning_rate": 2.2518143150271344e-08, + "loss": 0.1231, + "step": 15166 + }, + { + "epoch": 1.94, + "learning_rate": 2.2419991470289393e-08, + "loss": 0.1242, + "step": 15167 + }, + { + "epoch": 1.94, + "learning_rate": 2.232205368800533e-08, + "loss": 0.1246, + "step": 15168 + }, + { + "epoch": 1.94, + "learning_rate": 2.222432980762912e-08, + "loss": 0.1276, + "step": 15169 + }, + { + "epoch": 1.94, + "learning_rate": 2.2126819833358516e-08, + "loss": 0.1314, + "step": 15170 + }, + { + "epoch": 1.94, + "learning_rate": 2.2029523769385718e-08, + "loss": 0.1439, + "step": 15171 + }, + { + "epoch": 1.94, + "learning_rate": 2.1932441619890722e-08, + "loss": 0.1346, + "step": 15172 + }, + { + "epoch": 1.94, + "learning_rate": 2.1835573389045185e-08, + "loss": 0.1162, + "step": 15173 + }, + { + "epoch": 1.94, + "learning_rate": 2.1738919081012446e-08, + "loss": 0.1246, + "step": 15174 + }, + { + "epoch": 1.94, + "learning_rate": 2.1642478699944736e-08, + "loss": 0.1361, + "step": 15175 + }, + { + "epoch": 1.94, + "learning_rate": 2.1546252249988186e-08, + "loss": 0.1427, + "step": 15176 + }, + { + "epoch": 1.94, + "learning_rate": 2.1450239735276158e-08, + "loss": 0.1295, + "step": 15177 + }, + { + "epoch": 1.94, + "learning_rate": 2.135444115993479e-08, + "loss": 0.1421, + "step": 15178 + }, + { + "epoch": 1.94, + "learning_rate": 2.1258856528081906e-08, + "loss": 0.1342, + "step": 15179 + }, + { + "epoch": 1.94, + "learning_rate": 2.116348584382366e-08, + "loss": 0.1157, + "step": 15180 + }, + { + "epoch": 1.94, + "learning_rate": 2.1068329111259e-08, + "loss": 0.1454, + "step": 15181 + }, + { + "epoch": 1.94, + "learning_rate": 2.097338633447743e-08, + "loss": 0.1096, + "step": 15182 + }, + { + "epoch": 1.94, + "learning_rate": 2.087865751755791e-08, + "loss": 0.1506, + "step": 15183 + }, + { + "epoch": 1.94, + "learning_rate": 2.0784142664571626e-08, + "loss": 0.1359, + "step": 15184 + }, + { + "epoch": 1.94, + "learning_rate": 2.0689841779579777e-08, + "loss": 0.1392, + "step": 15185 + }, + { + "epoch": 1.94, + "learning_rate": 2.059575486663523e-08, + "loss": 0.1112, + "step": 15186 + }, + { + "epoch": 1.94, + "learning_rate": 2.0501881929780865e-08, + "loss": 0.1343, + "step": 15187 + }, + { + "epoch": 1.94, + "learning_rate": 2.040822297305012e-08, + "loss": 0.1433, + "step": 15188 + }, + { + "epoch": 1.94, + "learning_rate": 2.031477800046866e-08, + "loss": 0.1327, + "step": 15189 + }, + { + "epoch": 1.94, + "learning_rate": 2.0221547016051614e-08, + "loss": 0.134, + "step": 15190 + }, + { + "epoch": 1.94, + "learning_rate": 2.012853002380466e-08, + "loss": 0.134, + "step": 15191 + }, + { + "epoch": 1.94, + "learning_rate": 2.003572702772627e-08, + "loss": 0.1296, + "step": 15192 + }, + { + "epoch": 1.94, + "learning_rate": 1.9943138031803255e-08, + "loss": 0.1256, + "step": 15193 + }, + { + "epoch": 1.94, + "learning_rate": 1.9850763040014654e-08, + "loss": 0.134, + "step": 15194 + }, + { + "epoch": 1.94, + "learning_rate": 1.9758602056330623e-08, + "loss": 0.1272, + "step": 15195 + }, + { + "epoch": 1.95, + "learning_rate": 1.9666655084710772e-08, + "loss": 0.1238, + "step": 15196 + }, + { + "epoch": 1.95, + "learning_rate": 1.957492212910639e-08, + "loss": 0.1274, + "step": 15197 + }, + { + "epoch": 1.95, + "learning_rate": 1.9483403193459873e-08, + "loss": 0.1369, + "step": 15198 + }, + { + "epoch": 1.95, + "learning_rate": 1.939209828170363e-08, + "loss": 0.1291, + "step": 15199 + }, + { + "epoch": 1.95, + "learning_rate": 1.9301007397761197e-08, + "loss": 0.1316, + "step": 15200 + }, + { + "epoch": 1.95, + "learning_rate": 1.9210130545547213e-08, + "loss": 0.1311, + "step": 15201 + }, + { + "epoch": 1.95, + "learning_rate": 1.9119467728966888e-08, + "loss": 0.1291, + "step": 15202 + }, + { + "epoch": 1.95, + "learning_rate": 1.9029018951915446e-08, + "loss": 0.1254, + "step": 15203 + }, + { + "epoch": 1.95, + "learning_rate": 1.8938784218281435e-08, + "loss": 0.116, + "step": 15204 + }, + { + "epoch": 1.95, + "learning_rate": 1.884876353194065e-08, + "loss": 0.1432, + "step": 15205 + }, + { + "epoch": 1.95, + "learning_rate": 1.875895689676166e-08, + "loss": 0.1255, + "step": 15206 + }, + { + "epoch": 1.95, + "learning_rate": 1.866936431660471e-08, + "loss": 0.1256, + "step": 15207 + }, + { + "epoch": 1.95, + "learning_rate": 1.8579985795318946e-08, + "loss": 0.1369, + "step": 15208 + }, + { + "epoch": 1.95, + "learning_rate": 1.849082133674518e-08, + "loss": 0.1237, + "step": 15209 + }, + { + "epoch": 1.95, + "learning_rate": 1.8401870944715903e-08, + "loss": 0.1181, + "step": 15210 + }, + { + "epoch": 1.95, + "learning_rate": 1.8313134623051955e-08, + "loss": 0.1371, + "step": 15211 + }, + { + "epoch": 1.95, + "learning_rate": 1.822461237556805e-08, + "loss": 0.1514, + "step": 15212 + }, + { + "epoch": 1.95, + "learning_rate": 1.813630420606727e-08, + "loss": 0.1285, + "step": 15213 + }, + { + "epoch": 1.95, + "learning_rate": 1.80482101183449e-08, + "loss": 0.1104, + "step": 15214 + }, + { + "epoch": 1.95, + "learning_rate": 1.7960330116186807e-08, + "loss": 0.1309, + "step": 15215 + }, + { + "epoch": 1.95, + "learning_rate": 1.7872664203368305e-08, + "loss": 0.1382, + "step": 15216 + }, + { + "epoch": 1.95, + "learning_rate": 1.7785212383656934e-08, + "loss": 0.1359, + "step": 15217 + }, + { + "epoch": 1.95, + "learning_rate": 1.7697974660811357e-08, + "loss": 0.131, + "step": 15218 + }, + { + "epoch": 1.95, + "learning_rate": 1.761095103858024e-08, + "loss": 0.1351, + "step": 15219 + }, + { + "epoch": 1.95, + "learning_rate": 1.7524141520702808e-08, + "loss": 0.1355, + "step": 15220 + }, + { + "epoch": 1.95, + "learning_rate": 1.743754611090942e-08, + "loss": 0.1354, + "step": 15221 + }, + { + "epoch": 1.95, + "learning_rate": 1.7351164812921538e-08, + "loss": 0.1207, + "step": 15222 + }, + { + "epoch": 1.95, + "learning_rate": 1.726499763045064e-08, + "loss": 0.1367, + "step": 15223 + }, + { + "epoch": 1.95, + "learning_rate": 1.717904456720043e-08, + "loss": 0.1326, + "step": 15224 + }, + { + "epoch": 1.95, + "learning_rate": 1.7093305626864065e-08, + "loss": 0.1538, + "step": 15225 + }, + { + "epoch": 1.95, + "learning_rate": 1.7007780813125817e-08, + "loss": 0.1226, + "step": 15226 + }, + { + "epoch": 1.95, + "learning_rate": 1.692247012966053e-08, + "loss": 0.1184, + "step": 15227 + }, + { + "epoch": 1.95, + "learning_rate": 1.6837373580135265e-08, + "loss": 0.121, + "step": 15228 + }, + { + "epoch": 1.95, + "learning_rate": 1.675249116820543e-08, + "loss": 0.1317, + "step": 15229 + }, + { + "epoch": 1.95, + "learning_rate": 1.666782289751978e-08, + "loss": 0.127, + "step": 15230 + }, + { + "epoch": 1.95, + "learning_rate": 1.6583368771716513e-08, + "loss": 0.1219, + "step": 15231 + }, + { + "epoch": 1.95, + "learning_rate": 1.6499128794423836e-08, + "loss": 0.1403, + "step": 15232 + }, + { + "epoch": 1.95, + "learning_rate": 1.6415102969263297e-08, + "loss": 0.1291, + "step": 15233 + }, + { + "epoch": 1.95, + "learning_rate": 1.6331291299844233e-08, + "loss": 0.1292, + "step": 15234 + }, + { + "epoch": 1.95, + "learning_rate": 1.6247693789768758e-08, + "loss": 0.1189, + "step": 15235 + }, + { + "epoch": 1.95, + "learning_rate": 1.616431044262956e-08, + "loss": 0.1486, + "step": 15236 + }, + { + "epoch": 1.95, + "learning_rate": 1.6081141262009326e-08, + "loss": 0.1423, + "step": 15237 + }, + { + "epoch": 1.95, + "learning_rate": 1.5998186251482416e-08, + "loss": 0.1382, + "step": 15238 + }, + { + "epoch": 1.95, + "learning_rate": 1.5915445414613208e-08, + "loss": 0.1468, + "step": 15239 + }, + { + "epoch": 1.95, + "learning_rate": 1.5832918754958293e-08, + "loss": 0.1397, + "step": 15240 + }, + { + "epoch": 1.95, + "learning_rate": 1.5750606276062063e-08, + "loss": 0.1321, + "step": 15241 + }, + { + "epoch": 1.95, + "learning_rate": 1.5668507981463354e-08, + "loss": 0.115, + "step": 15242 + }, + { + "epoch": 1.95, + "learning_rate": 1.5586623874689345e-08, + "loss": 0.1376, + "step": 15243 + }, + { + "epoch": 1.95, + "learning_rate": 1.550495395925944e-08, + "loss": 0.1332, + "step": 15244 + }, + { + "epoch": 1.95, + "learning_rate": 1.54234982386825e-08, + "loss": 0.1119, + "step": 15245 + }, + { + "epoch": 1.95, + "learning_rate": 1.5342256716459058e-08, + "loss": 0.127, + "step": 15246 + }, + { + "epoch": 1.95, + "learning_rate": 1.5261229396079657e-08, + "loss": 0.114, + "step": 15247 + }, + { + "epoch": 1.95, + "learning_rate": 1.518041628102762e-08, + "loss": 0.1296, + "step": 15248 + }, + { + "epoch": 1.95, + "learning_rate": 1.5099817374774615e-08, + "loss": 0.1292, + "step": 15249 + }, + { + "epoch": 1.95, + "learning_rate": 1.501943268078454e-08, + "loss": 0.1527, + "step": 15250 + }, + { + "epoch": 1.95, + "learning_rate": 1.4939262202511297e-08, + "loss": 0.1169, + "step": 15251 + }, + { + "epoch": 1.95, + "learning_rate": 1.4859305943400459e-08, + "loss": 0.1221, + "step": 15252 + }, + { + "epoch": 1.95, + "learning_rate": 1.4779563906888172e-08, + "loss": 0.1181, + "step": 15253 + }, + { + "epoch": 1.95, + "learning_rate": 1.4700036096400028e-08, + "loss": 0.1302, + "step": 15254 + }, + { + "epoch": 1.95, + "learning_rate": 1.4620722515354957e-08, + "loss": 0.1401, + "step": 15255 + }, + { + "epoch": 1.95, + "learning_rate": 1.454162316715968e-08, + "loss": 0.1251, + "step": 15256 + }, + { + "epoch": 1.95, + "learning_rate": 1.4462738055214254e-08, + "loss": 0.1421, + "step": 15257 + }, + { + "epoch": 1.95, + "learning_rate": 1.4384067182908746e-08, + "loss": 0.146, + "step": 15258 + }, + { + "epoch": 1.95, + "learning_rate": 1.4305610553623228e-08, + "loss": 0.1214, + "step": 15259 + }, + { + "epoch": 1.95, + "learning_rate": 1.4227368170728894e-08, + "loss": 0.1288, + "step": 15260 + }, + { + "epoch": 1.95, + "learning_rate": 1.4149340037589166e-08, + "loss": 0.1421, + "step": 15261 + }, + { + "epoch": 1.95, + "learning_rate": 1.4071526157556358e-08, + "loss": 0.1332, + "step": 15262 + }, + { + "epoch": 1.95, + "learning_rate": 1.3993926533973912e-08, + "loss": 0.1434, + "step": 15263 + }, + { + "epoch": 1.95, + "learning_rate": 1.3916541170176934e-08, + "loss": 0.1399, + "step": 15264 + }, + { + "epoch": 1.95, + "learning_rate": 1.3839370069490543e-08, + "loss": 0.1298, + "step": 15265 + }, + { + "epoch": 1.95, + "learning_rate": 1.3762413235232086e-08, + "loss": 0.1257, + "step": 15266 + }, + { + "epoch": 1.95, + "learning_rate": 1.3685670670706697e-08, + "loss": 0.1236, + "step": 15267 + }, + { + "epoch": 1.95, + "learning_rate": 1.3609142379213957e-08, + "loss": 0.1223, + "step": 15268 + }, + { + "epoch": 1.95, + "learning_rate": 1.3532828364041239e-08, + "loss": 0.1332, + "step": 15269 + }, + { + "epoch": 1.95, + "learning_rate": 1.3456728628468141e-08, + "loss": 0.1497, + "step": 15270 + }, + { + "epoch": 1.95, + "learning_rate": 1.3380843175765379e-08, + "loss": 0.1328, + "step": 15271 + }, + { + "epoch": 1.95, + "learning_rate": 1.3305172009193678e-08, + "loss": 0.1353, + "step": 15272 + }, + { + "epoch": 1.95, + "learning_rate": 1.3229715132004328e-08, + "loss": 0.13, + "step": 15273 + }, + { + "epoch": 1.96, + "learning_rate": 1.3154472547440289e-08, + "loss": 0.1196, + "step": 15274 + }, + { + "epoch": 1.96, + "learning_rate": 1.3079444258735086e-08, + "loss": 0.1321, + "step": 15275 + }, + { + "epoch": 1.96, + "learning_rate": 1.3004630269112806e-08, + "loss": 0.1236, + "step": 15276 + }, + { + "epoch": 1.96, + "learning_rate": 1.29300305817881e-08, + "loss": 0.1145, + "step": 15277 + }, + { + "epoch": 1.96, + "learning_rate": 1.2855645199966738e-08, + "loss": 0.1357, + "step": 15278 + }, + { + "epoch": 1.96, + "learning_rate": 1.2781474126845051e-08, + "loss": 0.1379, + "step": 15279 + }, + { + "epoch": 1.96, + "learning_rate": 1.270751736561049e-08, + "loss": 0.1282, + "step": 15280 + }, + { + "epoch": 1.96, + "learning_rate": 1.2633774919441622e-08, + "loss": 0.1389, + "step": 15281 + }, + { + "epoch": 1.96, + "learning_rate": 1.256024679150647e-08, + "loss": 0.1166, + "step": 15282 + }, + { + "epoch": 1.96, + "learning_rate": 1.2486932984965282e-08, + "loss": 0.1432, + "step": 15283 + }, + { + "epoch": 1.96, + "learning_rate": 1.241383350296832e-08, + "loss": 0.1362, + "step": 15284 + }, + { + "epoch": 1.96, + "learning_rate": 1.2340948348656955e-08, + "loss": 0.1168, + "step": 15285 + }, + { + "epoch": 1.96, + "learning_rate": 1.2268277525163685e-08, + "loss": 0.139, + "step": 15286 + }, + { + "epoch": 1.96, + "learning_rate": 1.21958210356099e-08, + "loss": 0.1168, + "step": 15287 + }, + { + "epoch": 1.96, + "learning_rate": 1.2123578883110887e-08, + "loss": 0.1428, + "step": 15288 + }, + { + "epoch": 1.96, + "learning_rate": 1.2051551070769719e-08, + "loss": 0.1154, + "step": 15289 + }, + { + "epoch": 1.96, + "learning_rate": 1.1979737601682252e-08, + "loss": 0.1213, + "step": 15290 + }, + { + "epoch": 1.96, + "learning_rate": 1.1908138478934905e-08, + "loss": 0.1401, + "step": 15291 + }, + { + "epoch": 1.96, + "learning_rate": 1.1836753705602998e-08, + "loss": 0.1397, + "step": 15292 + }, + { + "epoch": 1.96, + "learning_rate": 1.1765583284755743e-08, + "loss": 0.1444, + "step": 15293 + }, + { + "epoch": 1.96, + "learning_rate": 1.1694627219450694e-08, + "loss": 0.1378, + "step": 15294 + }, + { + "epoch": 1.96, + "learning_rate": 1.1623885512737076e-08, + "loss": 0.1393, + "step": 15295 + }, + { + "epoch": 1.96, + "learning_rate": 1.1553358167654683e-08, + "loss": 0.1303, + "step": 15296 + }, + { + "epoch": 1.96, + "learning_rate": 1.1483045187233866e-08, + "loss": 0.1543, + "step": 15297 + }, + { + "epoch": 1.96, + "learning_rate": 1.1412946574497208e-08, + "loss": 0.1362, + "step": 15298 + }, + { + "epoch": 1.96, + "learning_rate": 1.134306233245619e-08, + "loss": 0.1294, + "step": 15299 + }, + { + "epoch": 1.96, + "learning_rate": 1.1273392464114518e-08, + "loss": 0.1318, + "step": 15300 + }, + { + "epoch": 1.96, + "learning_rate": 1.1203936972465356e-08, + "loss": 0.1166, + "step": 15301 + }, + { + "epoch": 1.96, + "learning_rate": 1.1134695860493539e-08, + "loss": 0.1274, + "step": 15302 + }, + { + "epoch": 1.96, + "learning_rate": 1.1065669131175016e-08, + "loss": 0.1392, + "step": 15303 + }, + { + "epoch": 1.96, + "learning_rate": 1.0996856787475197e-08, + "loss": 0.1286, + "step": 15304 + }, + { + "epoch": 1.96, + "learning_rate": 1.0928258832351712e-08, + "loss": 0.1265, + "step": 15305 + }, + { + "epoch": 1.96, + "learning_rate": 1.0859875268752206e-08, + "loss": 0.14, + "step": 15306 + }, + { + "epoch": 1.96, + "learning_rate": 1.079170609961544e-08, + "loss": 0.137, + "step": 15307 + }, + { + "epoch": 1.96, + "learning_rate": 1.072375132787018e-08, + "loss": 0.1378, + "step": 15308 + }, + { + "epoch": 1.96, + "learning_rate": 1.0656010956437979e-08, + "loss": 0.1225, + "step": 15309 + }, + { + "epoch": 1.96, + "learning_rate": 1.0588484988228175e-08, + "loss": 0.1212, + "step": 15310 + }, + { + "epoch": 1.96, + "learning_rate": 1.0521173426142894e-08, + "loss": 0.131, + "step": 15311 + }, + { + "epoch": 1.96, + "learning_rate": 1.0454076273075375e-08, + "loss": 0.1306, + "step": 15312 + }, + { + "epoch": 1.96, + "learning_rate": 1.0387193531908313e-08, + "loss": 0.1218, + "step": 15313 + }, + { + "epoch": 1.96, + "learning_rate": 1.0320525205516629e-08, + "loss": 0.122, + "step": 15314 + }, + { + "epoch": 1.96, + "learning_rate": 1.025407129676359e-08, + "loss": 0.1214, + "step": 15315 + }, + { + "epoch": 1.96, + "learning_rate": 1.018783180850691e-08, + "loss": 0.1243, + "step": 15316 + }, + { + "epoch": 1.96, + "learning_rate": 1.0121806743591534e-08, + "loss": 0.1215, + "step": 15317 + }, + { + "epoch": 1.96, + "learning_rate": 1.0055996104854637e-08, + "loss": 0.1245, + "step": 15318 + }, + { + "epoch": 1.96, + "learning_rate": 9.990399895125624e-09, + "loss": 0.118, + "step": 15319 + }, + { + "epoch": 1.96, + "learning_rate": 9.925018117221686e-09, + "loss": 0.111, + "step": 15320 + }, + { + "epoch": 1.96, + "learning_rate": 9.859850773953905e-09, + "loss": 0.1334, + "step": 15321 + }, + { + "epoch": 1.96, + "learning_rate": 9.794897868121711e-09, + "loss": 0.1283, + "step": 15322 + }, + { + "epoch": 1.96, + "learning_rate": 9.73015940251676e-09, + "loss": 0.1409, + "step": 15323 + }, + { + "epoch": 1.96, + "learning_rate": 9.665635379920157e-09, + "loss": 0.145, + "step": 15324 + }, + { + "epoch": 1.96, + "learning_rate": 9.6013258031058e-09, + "loss": 0.1368, + "step": 15325 + }, + { + "epoch": 1.96, + "learning_rate": 9.537230674836473e-09, + "loss": 0.1241, + "step": 15326 + }, + { + "epoch": 1.96, + "learning_rate": 9.473349997867198e-09, + "loss": 0.1295, + "step": 15327 + }, + { + "epoch": 1.96, + "learning_rate": 9.409683774941891e-09, + "loss": 0.1409, + "step": 15328 + }, + { + "epoch": 1.96, + "learning_rate": 9.346232008797252e-09, + "loss": 0.1294, + "step": 15329 + }, + { + "epoch": 1.96, + "learning_rate": 9.282994702159986e-09, + "loss": 0.1268, + "step": 15330 + }, + { + "epoch": 1.96, + "learning_rate": 9.219971857747368e-09, + "loss": 0.1371, + "step": 15331 + }, + { + "epoch": 1.96, + "learning_rate": 9.157163478267783e-09, + "loss": 0.1476, + "step": 15332 + }, + { + "epoch": 1.96, + "learning_rate": 9.094569566419632e-09, + "loss": 0.1256, + "step": 15333 + }, + { + "epoch": 1.96, + "learning_rate": 9.032190124893536e-09, + "loss": 0.1417, + "step": 15334 + }, + { + "epoch": 1.96, + "learning_rate": 8.970025156369578e-09, + "loss": 0.1299, + "step": 15335 + }, + { + "epoch": 1.96, + "learning_rate": 8.908074663519505e-09, + "loss": 0.1339, + "step": 15336 + }, + { + "epoch": 1.96, + "learning_rate": 8.846338649005082e-09, + "loss": 0.1297, + "step": 15337 + }, + { + "epoch": 1.96, + "learning_rate": 8.784817115479183e-09, + "loss": 0.1386, + "step": 15338 + }, + { + "epoch": 1.96, + "learning_rate": 8.723510065585806e-09, + "loss": 0.1225, + "step": 15339 + }, + { + "epoch": 1.96, + "learning_rate": 8.662417501959507e-09, + "loss": 0.1326, + "step": 15340 + }, + { + "epoch": 1.96, + "learning_rate": 8.601539427225414e-09, + "loss": 0.1373, + "step": 15341 + }, + { + "epoch": 1.96, + "learning_rate": 8.540875843999208e-09, + "loss": 0.1438, + "step": 15342 + }, + { + "epoch": 1.96, + "learning_rate": 8.480426754888805e-09, + "loss": 0.1407, + "step": 15343 + }, + { + "epoch": 1.96, + "learning_rate": 8.42019216249046e-09, + "loss": 0.1264, + "step": 15344 + }, + { + "epoch": 1.96, + "learning_rate": 8.360172069393768e-09, + "loss": 0.1233, + "step": 15345 + }, + { + "epoch": 1.96, + "learning_rate": 8.300366478177779e-09, + "loss": 0.1272, + "step": 15346 + }, + { + "epoch": 1.96, + "learning_rate": 8.240775391411548e-09, + "loss": 0.12, + "step": 15347 + }, + { + "epoch": 1.96, + "learning_rate": 8.18139881165636e-09, + "loss": 0.1301, + "step": 15348 + }, + { + "epoch": 1.96, + "learning_rate": 8.122236741464618e-09, + "loss": 0.1325, + "step": 15349 + }, + { + "epoch": 1.96, + "learning_rate": 8.063289183377065e-09, + "loss": 0.131, + "step": 15350 + }, + { + "epoch": 1.96, + "learning_rate": 8.004556139927788e-09, + "loss": 0.1229, + "step": 15351 + }, + { + "epoch": 1.97, + "learning_rate": 7.946037613640878e-09, + "loss": 0.1362, + "step": 15352 + }, + { + "epoch": 1.97, + "learning_rate": 7.887733607030435e-09, + "loss": 0.1309, + "step": 15353 + }, + { + "epoch": 1.97, + "learning_rate": 7.82964412260223e-09, + "loss": 0.1158, + "step": 15354 + }, + { + "epoch": 1.97, + "learning_rate": 7.77176916285205e-09, + "loss": 0.138, + "step": 15355 + }, + { + "epoch": 1.97, + "learning_rate": 7.714108730267345e-09, + "loss": 0.1352, + "step": 15356 + }, + { + "epoch": 1.97, + "learning_rate": 7.656662827326134e-09, + "loss": 0.1158, + "step": 15357 + }, + { + "epoch": 1.97, + "learning_rate": 7.599431456495888e-09, + "loss": 0.139, + "step": 15358 + }, + { + "epoch": 1.97, + "learning_rate": 7.542414620237414e-09, + "loss": 0.1261, + "step": 15359 + }, + { + "epoch": 1.97, + "learning_rate": 7.485612321000424e-09, + "loss": 0.1455, + "step": 15360 + }, + { + "epoch": 1.97, + "learning_rate": 7.4290245612246294e-09, + "loss": 0.1342, + "step": 15361 + }, + { + "epoch": 1.97, + "learning_rate": 7.372651343343639e-09, + "loss": 0.1333, + "step": 15362 + }, + { + "epoch": 1.97, + "learning_rate": 7.316492669778297e-09, + "loss": 0.1357, + "step": 15363 + }, + { + "epoch": 1.97, + "learning_rate": 7.260548542943335e-09, + "loss": 0.1396, + "step": 15364 + }, + { + "epoch": 1.97, + "learning_rate": 7.2048189652412784e-09, + "loss": 0.1328, + "step": 15365 + }, + { + "epoch": 1.97, + "learning_rate": 7.149303939067986e-09, + "loss": 0.1455, + "step": 15366 + }, + { + "epoch": 1.97, + "learning_rate": 7.094003466808774e-09, + "loss": 0.1266, + "step": 15367 + }, + { + "epoch": 1.97, + "learning_rate": 7.038917550840074e-09, + "loss": 0.1267, + "step": 15368 + }, + { + "epoch": 1.97, + "learning_rate": 6.984046193528881e-09, + "loss": 0.136, + "step": 15369 + }, + { + "epoch": 1.97, + "learning_rate": 6.9293893972338654e-09, + "loss": 0.124, + "step": 15370 + }, + { + "epoch": 1.97, + "learning_rate": 6.874947164302592e-09, + "loss": 0.1195, + "step": 15371 + }, + { + "epoch": 1.97, + "learning_rate": 6.820719497074857e-09, + "loss": 0.1326, + "step": 15372 + }, + { + "epoch": 1.97, + "learning_rate": 6.7667063978815724e-09, + "loss": 0.1439, + "step": 15373 + }, + { + "epoch": 1.97, + "learning_rate": 6.712907869043661e-09, + "loss": 0.1388, + "step": 15374 + }, + { + "epoch": 1.97, + "learning_rate": 6.659323912872606e-09, + "loss": 0.1168, + "step": 15375 + }, + { + "epoch": 1.97, + "learning_rate": 6.60595453167101e-09, + "loss": 0.1475, + "step": 15376 + }, + { + "epoch": 1.97, + "learning_rate": 6.552799727732595e-09, + "loss": 0.138, + "step": 15377 + }, + { + "epoch": 1.97, + "learning_rate": 6.4998595033410886e-09, + "loss": 0.1427, + "step": 15378 + }, + { + "epoch": 1.97, + "learning_rate": 6.447133860771893e-09, + "loss": 0.126, + "step": 15379 + }, + { + "epoch": 1.97, + "learning_rate": 6.394622802290973e-09, + "loss": 0.1339, + "step": 15380 + }, + { + "epoch": 1.97, + "learning_rate": 6.342326330153747e-09, + "loss": 0.1315, + "step": 15381 + }, + { + "epoch": 1.97, + "learning_rate": 6.290244446608973e-09, + "loss": 0.1258, + "step": 15382 + }, + { + "epoch": 1.97, + "learning_rate": 6.238377153893749e-09, + "loss": 0.1322, + "step": 15383 + }, + { + "epoch": 1.97, + "learning_rate": 6.186724454236847e-09, + "loss": 0.1447, + "step": 15384 + }, + { + "epoch": 1.97, + "learning_rate": 6.13528634985816e-09, + "loss": 0.1238, + "step": 15385 + }, + { + "epoch": 1.97, + "learning_rate": 6.084062842968696e-09, + "loss": 0.1165, + "step": 15386 + }, + { + "epoch": 1.97, + "learning_rate": 6.0330539357689175e-09, + "loss": 0.1376, + "step": 15387 + }, + { + "epoch": 1.97, + "learning_rate": 5.98225963045096e-09, + "loss": 0.1268, + "step": 15388 + }, + { + "epoch": 1.97, + "learning_rate": 5.9316799291969654e-09, + "loss": 0.1308, + "step": 15389 + }, + { + "epoch": 1.97, + "learning_rate": 5.881314834181862e-09, + "loss": 0.1394, + "step": 15390 + }, + { + "epoch": 1.97, + "learning_rate": 5.831164347568918e-09, + "loss": 0.1485, + "step": 15391 + }, + { + "epoch": 1.97, + "learning_rate": 5.781228471513633e-09, + "loss": 0.1414, + "step": 15392 + }, + { + "epoch": 1.97, + "learning_rate": 5.731507208160958e-09, + "loss": 0.1221, + "step": 15393 + }, + { + "epoch": 1.97, + "learning_rate": 5.682000559649181e-09, + "loss": 0.1273, + "step": 15394 + }, + { + "epoch": 1.97, + "learning_rate": 5.63270852810438e-09, + "loss": 0.1341, + "step": 15395 + }, + { + "epoch": 1.97, + "learning_rate": 5.583631115644861e-09, + "loss": 0.1297, + "step": 15396 + }, + { + "epoch": 1.97, + "learning_rate": 5.534768324380046e-09, + "loss": 0.1357, + "step": 15397 + }, + { + "epoch": 1.97, + "learning_rate": 5.486120156409924e-09, + "loss": 0.1325, + "step": 15398 + }, + { + "epoch": 1.97, + "learning_rate": 5.437686613823934e-09, + "loss": 0.1436, + "step": 15399 + }, + { + "epoch": 1.97, + "learning_rate": 5.389467698704298e-09, + "loss": 0.116, + "step": 15400 + }, + { + "epoch": 1.97, + "learning_rate": 5.341463413123249e-09, + "loss": 0.1366, + "step": 15401 + }, + { + "epoch": 1.97, + "learning_rate": 5.29367375914247e-09, + "loss": 0.129, + "step": 15402 + }, + { + "epoch": 1.97, + "learning_rate": 5.246098738816985e-09, + "loss": 0.1206, + "step": 15403 + }, + { + "epoch": 1.97, + "learning_rate": 5.198738354190158e-09, + "loss": 0.1349, + "step": 15404 + }, + { + "epoch": 1.97, + "learning_rate": 5.151592607298139e-09, + "loss": 0.1236, + "step": 15405 + }, + { + "epoch": 1.97, + "learning_rate": 5.104661500165975e-09, + "loss": 0.1282, + "step": 15406 + }, + { + "epoch": 1.97, + "learning_rate": 5.057945034810385e-09, + "loss": 0.1256, + "step": 15407 + }, + { + "epoch": 1.97, + "learning_rate": 5.0114432132397636e-09, + "loss": 0.1272, + "step": 15408 + }, + { + "epoch": 1.97, + "learning_rate": 4.9651560374514015e-09, + "loss": 0.1288, + "step": 15409 + }, + { + "epoch": 1.97, + "learning_rate": 4.919083509434819e-09, + "loss": 0.1199, + "step": 15410 + }, + { + "epoch": 1.97, + "learning_rate": 4.873225631170098e-09, + "loss": 0.1327, + "step": 15411 + }, + { + "epoch": 1.97, + "learning_rate": 4.827582404627884e-09, + "loss": 0.1107, + "step": 15412 + }, + { + "epoch": 1.97, + "learning_rate": 4.782153831768832e-09, + "loss": 0.1429, + "step": 15413 + }, + { + "epoch": 1.97, + "learning_rate": 4.736939914545824e-09, + "loss": 0.1183, + "step": 15414 + }, + { + "epoch": 1.97, + "learning_rate": 4.691940654901195e-09, + "loss": 0.141, + "step": 15415 + }, + { + "epoch": 1.97, + "learning_rate": 4.647156054769508e-09, + "loss": 0.1351, + "step": 15416 + }, + { + "epoch": 1.97, + "learning_rate": 4.602586116074781e-09, + "loss": 0.1394, + "step": 15417 + }, + { + "epoch": 1.97, + "learning_rate": 4.558230840731592e-09, + "loss": 0.1269, + "step": 15418 + }, + { + "epoch": 1.97, + "learning_rate": 4.514090230647305e-09, + "loss": 0.1287, + "step": 15419 + }, + { + "epoch": 1.97, + "learning_rate": 4.470164287717627e-09, + "loss": 0.1314, + "step": 15420 + }, + { + "epoch": 1.97, + "learning_rate": 4.4264530138310445e-09, + "loss": 0.1277, + "step": 15421 + }, + { + "epoch": 1.97, + "learning_rate": 4.382956410865502e-09, + "loss": 0.1313, + "step": 15422 + }, + { + "epoch": 1.97, + "learning_rate": 4.339674480690059e-09, + "loss": 0.124, + "step": 15423 + }, + { + "epoch": 1.97, + "learning_rate": 4.296607225164895e-09, + "loss": 0.1392, + "step": 15424 + }, + { + "epoch": 1.97, + "learning_rate": 4.253754646140196e-09, + "loss": 0.1087, + "step": 15425 + }, + { + "epoch": 1.97, + "learning_rate": 4.211116745458377e-09, + "loss": 0.1288, + "step": 15426 + }, + { + "epoch": 1.97, + "learning_rate": 4.168693524950196e-09, + "loss": 0.1296, + "step": 15427 + }, + { + "epoch": 1.97, + "learning_rate": 4.1264849864403044e-09, + "loss": 0.1279, + "step": 15428 + }, + { + "epoch": 1.97, + "learning_rate": 4.084491131741697e-09, + "loss": 0.1315, + "step": 15429 + }, + { + "epoch": 1.98, + "learning_rate": 4.042711962658486e-09, + "loss": 0.1113, + "step": 15430 + }, + { + "epoch": 1.98, + "learning_rate": 4.001147480987011e-09, + "loss": 0.1349, + "step": 15431 + }, + { + "epoch": 1.98, + "learning_rate": 3.959797688513067e-09, + "loss": 0.1421, + "step": 15432 + }, + { + "epoch": 1.98, + "learning_rate": 3.9186625870130115e-09, + "loss": 0.1489, + "step": 15433 + }, + { + "epoch": 1.98, + "learning_rate": 3.877742178254873e-09, + "loss": 0.1192, + "step": 15434 + }, + { + "epoch": 1.98, + "learning_rate": 3.837036463997246e-09, + "loss": 0.1257, + "step": 15435 + }, + { + "epoch": 1.98, + "learning_rate": 3.796545445989286e-09, + "loss": 0.12, + "step": 15436 + }, + { + "epoch": 1.98, + "learning_rate": 3.756269125970713e-09, + "loss": 0.1274, + "step": 15437 + }, + { + "epoch": 1.98, + "learning_rate": 3.7162075056729196e-09, + "loss": 0.1332, + "step": 15438 + }, + { + "epoch": 1.98, + "learning_rate": 3.6763605868167516e-09, + "loss": 0.1369, + "step": 15439 + }, + { + "epoch": 1.98, + "learning_rate": 3.636728371114173e-09, + "loss": 0.1285, + "step": 15440 + }, + { + "epoch": 1.98, + "learning_rate": 3.5973108602699313e-09, + "loss": 0.127, + "step": 15441 + }, + { + "epoch": 1.98, + "learning_rate": 3.558108055976006e-09, + "loss": 0.1307, + "step": 15442 + }, + { + "epoch": 1.98, + "learning_rate": 3.5191199599182712e-09, + "loss": 0.1274, + "step": 15443 + }, + { + "epoch": 1.98, + "learning_rate": 3.4803465737714983e-09, + "loss": 0.1307, + "step": 15444 + }, + { + "epoch": 1.98, + "learning_rate": 3.4417878992021315e-09, + "loss": 0.1472, + "step": 15445 + }, + { + "epoch": 1.98, + "learning_rate": 3.403443937867179e-09, + "loss": 0.1358, + "step": 15446 + }, + { + "epoch": 1.98, + "learning_rate": 3.365314691414212e-09, + "loss": 0.1324, + "step": 15447 + }, + { + "epoch": 1.98, + "learning_rate": 3.3274001614819195e-09, + "loss": 0.124, + "step": 15448 + }, + { + "epoch": 1.98, + "learning_rate": 3.289700349698999e-09, + "loss": 0.13, + "step": 15449 + }, + { + "epoch": 1.98, + "learning_rate": 3.252215257686375e-09, + "loss": 0.1204, + "step": 15450 + }, + { + "epoch": 1.98, + "learning_rate": 3.2149448870544273e-09, + "loss": 0.1248, + "step": 15451 + }, + { + "epoch": 1.98, + "learning_rate": 3.1778892394046525e-09, + "loss": 0.1329, + "step": 15452 + }, + { + "epoch": 1.98, + "learning_rate": 3.1410483163291093e-09, + "loss": 0.1401, + "step": 15453 + }, + { + "epoch": 1.98, + "learning_rate": 3.104422119411532e-09, + "loss": 0.1271, + "step": 15454 + }, + { + "epoch": 1.98, + "learning_rate": 3.0680106502256613e-09, + "loss": 0.1377, + "step": 15455 + }, + { + "epoch": 1.98, + "learning_rate": 3.0318139103363564e-09, + "loss": 0.144, + "step": 15456 + }, + { + "epoch": 1.98, + "learning_rate": 2.9958319012984847e-09, + "loss": 0.147, + "step": 15457 + }, + { + "epoch": 1.98, + "learning_rate": 2.9600646246591425e-09, + "loss": 0.1427, + "step": 15458 + }, + { + "epoch": 1.98, + "learning_rate": 2.9245120819543226e-09, + "loss": 0.144, + "step": 15459 + }, + { + "epoch": 1.98, + "learning_rate": 2.8891742747128025e-09, + "loss": 0.122, + "step": 15460 + }, + { + "epoch": 1.98, + "learning_rate": 2.854051204452257e-09, + "loss": 0.1263, + "step": 15461 + }, + { + "epoch": 1.98, + "learning_rate": 2.8191428726820347e-09, + "loss": 0.1451, + "step": 15462 + }, + { + "epoch": 1.98, + "learning_rate": 2.7844492809031567e-09, + "loss": 0.1375, + "step": 15463 + }, + { + "epoch": 1.98, + "learning_rate": 2.749970430605542e-09, + "loss": 0.1351, + "step": 15464 + }, + { + "epoch": 1.98, + "learning_rate": 2.715706323271339e-09, + "loss": 0.1211, + "step": 15465 + }, + { + "epoch": 1.98, + "learning_rate": 2.681656960372703e-09, + "loss": 0.126, + "step": 15466 + }, + { + "epoch": 1.98, + "learning_rate": 2.6478223433734627e-09, + "loss": 0.1303, + "step": 15467 + }, + { + "epoch": 1.98, + "learning_rate": 2.614202473726346e-09, + "loss": 0.13, + "step": 15468 + }, + { + "epoch": 1.98, + "learning_rate": 2.5807973528768626e-09, + "loss": 0.1413, + "step": 15469 + }, + { + "epoch": 1.98, + "learning_rate": 2.547606982260531e-09, + "loss": 0.1259, + "step": 15470 + }, + { + "epoch": 1.98, + "learning_rate": 2.5146313633028775e-09, + "loss": 0.1527, + "step": 15471 + }, + { + "epoch": 1.98, + "learning_rate": 2.481870497422212e-09, + "loss": 0.1409, + "step": 15472 + }, + { + "epoch": 1.98, + "learning_rate": 2.449324386025187e-09, + "loss": 0.1359, + "step": 15473 + }, + { + "epoch": 1.98, + "learning_rate": 2.416993030511239e-09, + "loss": 0.1381, + "step": 15474 + }, + { + "epoch": 1.98, + "learning_rate": 2.3848764322687014e-09, + "loss": 0.131, + "step": 15475 + }, + { + "epoch": 1.98, + "learning_rate": 2.3529745926786916e-09, + "loss": 0.1248, + "step": 15476 + }, + { + "epoch": 1.98, + "learning_rate": 2.3212875131117805e-09, + "loss": 0.1339, + "step": 15477 + }, + { + "epoch": 1.98, + "learning_rate": 2.2898151949296566e-09, + "loss": 0.1249, + "step": 15478 + }, + { + "epoch": 1.98, + "learning_rate": 2.258557639484571e-09, + "loss": 0.131, + "step": 15479 + }, + { + "epoch": 1.98, + "learning_rate": 2.227514848119894e-09, + "loss": 0.1285, + "step": 15480 + }, + { + "epoch": 1.98, + "learning_rate": 2.196686822169003e-09, + "loss": 0.1188, + "step": 15481 + }, + { + "epoch": 1.98, + "learning_rate": 2.1660735629580598e-09, + "loss": 0.1241, + "step": 15482 + }, + { + "epoch": 1.98, + "learning_rate": 2.1356750718010133e-09, + "loss": 0.1265, + "step": 15483 + }, + { + "epoch": 1.98, + "learning_rate": 2.1054913500051512e-09, + "loss": 0.1314, + "step": 15484 + }, + { + "epoch": 1.98, + "learning_rate": 2.0755223988672136e-09, + "loss": 0.1395, + "step": 15485 + }, + { + "epoch": 1.98, + "learning_rate": 2.0457682196750595e-09, + "loss": 0.1345, + "step": 15486 + }, + { + "epoch": 1.98, + "learning_rate": 2.0162288137071105e-09, + "loss": 0.1187, + "step": 15487 + }, + { + "epoch": 1.98, + "learning_rate": 1.9869041822329073e-09, + "loss": 0.1432, + "step": 15488 + }, + { + "epoch": 1.98, + "learning_rate": 1.957794326513107e-09, + "loss": 0.1353, + "step": 15489 + }, + { + "epoch": 1.98, + "learning_rate": 1.928899247797822e-09, + "loss": 0.1257, + "step": 15490 + }, + { + "epoch": 1.98, + "learning_rate": 1.9002189473288356e-09, + "loss": 0.133, + "step": 15491 + }, + { + "epoch": 1.98, + "learning_rate": 1.8717534263390513e-09, + "loss": 0.1293, + "step": 15492 + }, + { + "epoch": 1.98, + "learning_rate": 1.8435026860513794e-09, + "loss": 0.122, + "step": 15493 + }, + { + "epoch": 1.98, + "learning_rate": 1.8154667276798488e-09, + "loss": 0.1321, + "step": 15494 + }, + { + "epoch": 1.98, + "learning_rate": 1.7876455524290514e-09, + "loss": 0.136, + "step": 15495 + }, + { + "epoch": 1.98, + "learning_rate": 1.7600391614952529e-09, + "loss": 0.1264, + "step": 15496 + }, + { + "epoch": 1.98, + "learning_rate": 1.7326475560636157e-09, + "loss": 0.1302, + "step": 15497 + }, + { + "epoch": 1.98, + "learning_rate": 1.7054707373126423e-09, + "loss": 0.12, + "step": 15498 + }, + { + "epoch": 1.98, + "learning_rate": 1.6785087064086213e-09, + "loss": 0.1344, + "step": 15499 + }, + { + "epoch": 1.98, + "learning_rate": 1.6517614645111812e-09, + "loss": 0.1301, + "step": 15500 + }, + { + "epoch": 1.98, + "learning_rate": 1.6252290127699577e-09, + "loss": 0.1368, + "step": 15501 + }, + { + "epoch": 1.98, + "learning_rate": 1.5989113523240396e-09, + "loss": 0.1353, + "step": 15502 + }, + { + "epoch": 1.98, + "learning_rate": 1.5728084843052992e-09, + "loss": 0.1226, + "step": 15503 + }, + { + "epoch": 1.98, + "learning_rate": 1.546920409834507e-09, + "loss": 0.118, + "step": 15504 + }, + { + "epoch": 1.98, + "learning_rate": 1.5212471300252163e-09, + "loss": 0.1478, + "step": 15505 + }, + { + "epoch": 1.98, + "learning_rate": 1.4957886459798787e-09, + "loss": 0.1505, + "step": 15506 + }, + { + "epoch": 1.98, + "learning_rate": 1.4705449587931742e-09, + "loss": 0.1232, + "step": 15507 + }, + { + "epoch": 1.99, + "learning_rate": 1.4455160695492354e-09, + "loss": 0.1358, + "step": 15508 + }, + { + "epoch": 1.99, + "learning_rate": 1.4207019793238686e-09, + "loss": 0.1348, + "step": 15509 + }, + { + "epoch": 1.99, + "learning_rate": 1.3961026891828878e-09, + "loss": 0.1295, + "step": 15510 + }, + { + "epoch": 1.99, + "learning_rate": 1.3717182001843355e-09, + "loss": 0.1209, + "step": 15511 + }, + { + "epoch": 1.99, + "learning_rate": 1.347548513375707e-09, + "loss": 0.1516, + "step": 15512 + }, + { + "epoch": 1.99, + "learning_rate": 1.3235936297956165e-09, + "loss": 0.1402, + "step": 15513 + }, + { + "epoch": 1.99, + "learning_rate": 1.299853550472685e-09, + "loss": 0.1303, + "step": 15514 + }, + { + "epoch": 1.99, + "learning_rate": 1.276328276428318e-09, + "loss": 0.1348, + "step": 15515 + }, + { + "epoch": 1.99, + "learning_rate": 1.2530178086728183e-09, + "loss": 0.1265, + "step": 15516 + }, + { + "epoch": 1.99, + "learning_rate": 1.2299221482076074e-09, + "loss": 0.12, + "step": 15517 + }, + { + "epoch": 1.99, + "learning_rate": 1.2070412960257793e-09, + "loss": 0.1364, + "step": 15518 + }, + { + "epoch": 1.99, + "learning_rate": 1.1843752531104368e-09, + "loss": 0.1467, + "step": 15519 + }, + { + "epoch": 1.99, + "learning_rate": 1.1619240204352455e-09, + "loss": 0.1431, + "step": 15520 + }, + { + "epoch": 1.99, + "learning_rate": 1.1396875989655443e-09, + "loss": 0.1483, + "step": 15521 + }, + { + "epoch": 1.99, + "learning_rate": 1.1176659896561247e-09, + "loss": 0.1263, + "step": 15522 + }, + { + "epoch": 1.99, + "learning_rate": 1.0958591934534525e-09, + "loss": 0.1291, + "step": 15523 + }, + { + "epoch": 1.99, + "learning_rate": 1.0742672112951103e-09, + "loss": 0.1221, + "step": 15524 + }, + { + "epoch": 1.99, + "learning_rate": 1.052890044109245e-09, + "loss": 0.1274, + "step": 15525 + }, + { + "epoch": 1.99, + "learning_rate": 1.0317276928134557e-09, + "loss": 0.144, + "step": 15526 + }, + { + "epoch": 1.99, + "learning_rate": 1.0107801583175702e-09, + "loss": 0.1298, + "step": 15527 + }, + { + "epoch": 1.99, + "learning_rate": 9.900474415219795e-10, + "loss": 0.125, + "step": 15528 + }, + { + "epoch": 1.99, + "learning_rate": 9.695295433170826e-10, + "loss": 0.125, + "step": 15529 + }, + { + "epoch": 1.99, + "learning_rate": 9.492264645855065e-10, + "loss": 0.127, + "step": 15530 + }, + { + "epoch": 1.99, + "learning_rate": 9.291382061987763e-10, + "loss": 0.1302, + "step": 15531 + }, + { + "epoch": 1.99, + "learning_rate": 9.092647690206457e-10, + "loss": 0.1323, + "step": 15532 + }, + { + "epoch": 1.99, + "learning_rate": 8.896061539048762e-10, + "loss": 0.1399, + "step": 15533 + }, + { + "epoch": 1.99, + "learning_rate": 8.701623616963472e-10, + "loss": 0.122, + "step": 15534 + }, + { + "epoch": 1.99, + "learning_rate": 8.509333932310571e-10, + "loss": 0.1349, + "step": 15535 + }, + { + "epoch": 1.99, + "learning_rate": 8.319192493344563e-10, + "loss": 0.1236, + "step": 15536 + }, + { + "epoch": 1.99, + "learning_rate": 8.131199308236692e-10, + "loss": 0.1337, + "step": 15537 + }, + { + "epoch": 1.99, + "learning_rate": 7.945354385074933e-10, + "loss": 0.1185, + "step": 15538 + }, + { + "epoch": 1.99, + "learning_rate": 7.761657731836236e-10, + "loss": 0.1179, + "step": 15539 + }, + { + "epoch": 1.99, + "learning_rate": 7.580109356419841e-10, + "loss": 0.1506, + "step": 15540 + }, + { + "epoch": 1.99, + "learning_rate": 7.400709266625062e-10, + "loss": 0.1269, + "step": 15541 + }, + { + "epoch": 1.99, + "learning_rate": 7.223457470156847e-10, + "loss": 0.1249, + "step": 15542 + }, + { + "epoch": 1.99, + "learning_rate": 7.04835397464243e-10, + "loss": 0.1347, + "step": 15543 + }, + { + "epoch": 1.99, + "learning_rate": 6.87539878759802e-10, + "loss": 0.1285, + "step": 15544 + }, + { + "epoch": 1.99, + "learning_rate": 6.704591916462111e-10, + "loss": 0.1194, + "step": 15545 + }, + { + "epoch": 1.99, + "learning_rate": 6.535933368567726e-10, + "loss": 0.1294, + "step": 15546 + }, + { + "epoch": 1.99, + "learning_rate": 6.369423151164622e-10, + "loss": 0.1291, + "step": 15547 + }, + { + "epoch": 1.99, + "learning_rate": 6.205061271408186e-10, + "loss": 0.134, + "step": 15548 + }, + { + "epoch": 1.99, + "learning_rate": 6.042847736364987e-10, + "loss": 0.1255, + "step": 15549 + }, + { + "epoch": 1.99, + "learning_rate": 5.882782553001676e-10, + "loss": 0.1275, + "step": 15550 + }, + { + "epoch": 1.99, + "learning_rate": 5.724865728201634e-10, + "loss": 0.1349, + "step": 15551 + }, + { + "epoch": 1.99, + "learning_rate": 5.569097268742773e-10, + "loss": 0.1292, + "step": 15552 + }, + { + "epoch": 1.99, + "learning_rate": 5.415477181325291e-10, + "loss": 0.1341, + "step": 15553 + }, + { + "epoch": 1.99, + "learning_rate": 5.264005472549461e-10, + "loss": 0.1462, + "step": 15554 + }, + { + "epoch": 1.99, + "learning_rate": 5.114682148921191e-10, + "loss": 0.1305, + "step": 15555 + }, + { + "epoch": 1.99, + "learning_rate": 4.967507216863121e-10, + "loss": 0.1338, + "step": 15556 + }, + { + "epoch": 1.99, + "learning_rate": 4.822480682692421e-10, + "loss": 0.13, + "step": 15557 + }, + { + "epoch": 1.99, + "learning_rate": 4.679602552648543e-10, + "loss": 0.1427, + "step": 15558 + }, + { + "epoch": 1.99, + "learning_rate": 4.538872832865471e-10, + "loss": 0.1384, + "step": 15559 + }, + { + "epoch": 1.99, + "learning_rate": 4.4002915293939186e-10, + "loss": 0.1486, + "step": 15560 + }, + { + "epoch": 1.99, + "learning_rate": 4.2638586481846823e-10, + "loss": 0.1324, + "step": 15561 + }, + { + "epoch": 1.99, + "learning_rate": 4.1295741951108417e-10, + "loss": 0.1255, + "step": 15562 + }, + { + "epoch": 1.99, + "learning_rate": 3.9974381759289027e-10, + "loss": 0.1321, + "step": 15563 + }, + { + "epoch": 1.99, + "learning_rate": 3.867450596328759e-10, + "loss": 0.1463, + "step": 15564 + }, + { + "epoch": 1.99, + "learning_rate": 3.739611461889281e-10, + "loss": 0.1343, + "step": 15565 + }, + { + "epoch": 1.99, + "learning_rate": 3.6139207781060723e-10, + "loss": 0.1394, + "step": 15566 + }, + { + "epoch": 1.99, + "learning_rate": 3.490378550380369e-10, + "loss": 0.1395, + "step": 15567 + }, + { + "epoch": 1.99, + "learning_rate": 3.368984784024587e-10, + "loss": 0.1362, + "step": 15568 + }, + { + "epoch": 1.99, + "learning_rate": 3.2497394842512244e-10, + "loss": 0.1296, + "step": 15569 + }, + { + "epoch": 1.99, + "learning_rate": 3.1326426561839597e-10, + "loss": 0.1237, + "step": 15570 + }, + { + "epoch": 1.99, + "learning_rate": 3.017694304852103e-10, + "loss": 0.1282, + "step": 15571 + }, + { + "epoch": 1.99, + "learning_rate": 2.9048944352072505e-10, + "loss": 0.1152, + "step": 15572 + }, + { + "epoch": 1.99, + "learning_rate": 2.794243052084422e-10, + "loss": 0.1191, + "step": 15573 + }, + { + "epoch": 1.99, + "learning_rate": 2.685740160240924e-10, + "loss": 0.1223, + "step": 15574 + }, + { + "epoch": 1.99, + "learning_rate": 2.5793857643396924e-10, + "loss": 0.135, + "step": 15575 + }, + { + "epoch": 1.99, + "learning_rate": 2.475179868960398e-10, + "loss": 0.1272, + "step": 15576 + }, + { + "epoch": 1.99, + "learning_rate": 2.3731224785661365e-10, + "loss": 0.1364, + "step": 15577 + }, + { + "epoch": 1.99, + "learning_rate": 2.273213597553392e-10, + "loss": 0.1336, + "step": 15578 + }, + { + "epoch": 1.99, + "learning_rate": 2.1754532302076247e-10, + "loss": 0.1268, + "step": 15579 + }, + { + "epoch": 1.99, + "learning_rate": 2.0798413807365802e-10, + "loss": 0.1109, + "step": 15580 + }, + { + "epoch": 1.99, + "learning_rate": 1.9863780532480836e-10, + "loss": 0.1345, + "step": 15581 + }, + { + "epoch": 1.99, + "learning_rate": 1.89506325175004e-10, + "loss": 0.1342, + "step": 15582 + }, + { + "epoch": 1.99, + "learning_rate": 1.80589698017819e-10, + "loss": 0.1243, + "step": 15583 + }, + { + "epoch": 1.99, + "learning_rate": 1.718879242357252e-10, + "loss": 0.1236, + "step": 15584 + }, + { + "epoch": 1.99, + "learning_rate": 1.6340100420286776e-10, + "loss": 0.1306, + "step": 15585 + }, + { + "epoch": 2.0, + "learning_rate": 1.5512893828395493e-10, + "loss": 0.1254, + "step": 15586 + }, + { + "epoch": 2.0, + "learning_rate": 1.470717268342581e-10, + "loss": 0.1268, + "step": 15587 + }, + { + "epoch": 2.0, + "learning_rate": 1.392293702001668e-10, + "loss": 0.1342, + "step": 15588 + }, + { + "epoch": 2.0, + "learning_rate": 1.316018687191889e-10, + "loss": 0.1376, + "step": 15589 + }, + { + "epoch": 2.0, + "learning_rate": 1.2418922271772993e-10, + "loss": 0.1133, + "step": 15590 + }, + { + "epoch": 2.0, + "learning_rate": 1.1699143251553414e-10, + "loss": 0.1363, + "step": 15591 + }, + { + "epoch": 2.0, + "learning_rate": 1.1000849842179862e-10, + "loss": 0.1077, + "step": 15592 + }, + { + "epoch": 2.0, + "learning_rate": 1.032404207362836e-10, + "loss": 0.1296, + "step": 15593 + }, + { + "epoch": 2.0, + "learning_rate": 9.668719974986751e-11, + "loss": 0.1346, + "step": 15594 + }, + { + "epoch": 2.0, + "learning_rate": 9.03488357439919e-11, + "loss": 0.123, + "step": 15595 + }, + { + "epoch": 2.0, + "learning_rate": 8.422532899121649e-11, + "loss": 0.1187, + "step": 15596 + }, + { + "epoch": 2.0, + "learning_rate": 7.831667975466417e-11, + "loss": 0.1262, + "step": 15597 + }, + { + "epoch": 2.0, + "learning_rate": 7.2622888288576e-11, + "loss": 0.1343, + "step": 15598 + }, + { + "epoch": 2.0, + "learning_rate": 6.714395483720105e-11, + "loss": 0.1336, + "step": 15599 + }, + { + "epoch": 2.0, + "learning_rate": 6.187987963590658e-11, + "loss": 0.1287, + "step": 15600 + }, + { + "epoch": 2.0, + "learning_rate": 5.6830662911178115e-11, + "loss": 0.1157, + "step": 15601 + }, + { + "epoch": 2.0, + "learning_rate": 5.199630488006424e-11, + "loss": 0.131, + "step": 15602 + }, + { + "epoch": 2.0, + "learning_rate": 4.737680575017667e-11, + "loss": 0.1225, + "step": 15603 + }, + { + "epoch": 2.0, + "learning_rate": 4.297216571969021e-11, + "loss": 0.1254, + "step": 15604 + }, + { + "epoch": 2.0, + "learning_rate": 3.878238497845299e-11, + "loss": 0.1332, + "step": 15605 + }, + { + "epoch": 2.0, + "learning_rate": 3.4807463705766044e-11, + "loss": 0.121, + "step": 15606 + }, + { + "epoch": 2.0, + "learning_rate": 3.104740207371393e-11, + "loss": 0.1334, + "step": 15607 + }, + { + "epoch": 2.0, + "learning_rate": 2.7502200242723874e-11, + "loss": 0.1259, + "step": 15608 + }, + { + "epoch": 2.0, + "learning_rate": 2.417185836545155e-11, + "loss": 0.1382, + "step": 15609 + }, + { + "epoch": 2.0, + "learning_rate": 2.1056376585115723e-11, + "loss": 0.1429, + "step": 15610 + }, + { + "epoch": 2.0, + "learning_rate": 1.815575503549827e-11, + "loss": 0.1396, + "step": 15611 + }, + { + "epoch": 2.0, + "learning_rate": 1.5469993840944163e-11, + "loss": 0.1191, + "step": 15612 + }, + { + "epoch": 2.0, + "learning_rate": 1.2999093117471717e-11, + "loss": 0.1251, + "step": 15613 + }, + { + "epoch": 2.0, + "learning_rate": 1.0743052971107225e-11, + "loss": 0.1364, + "step": 15614 + }, + { + "epoch": 2.0, + "learning_rate": 8.701873498995205e-12, + "loss": 0.1239, + "step": 15615 + }, + { + "epoch": 2.0, + "learning_rate": 6.875554787733052e-12, + "loss": 0.134, + "step": 15616 + }, + { + "epoch": 2.0, + "learning_rate": 5.2640969172568225e-12, + "loss": 0.1263, + "step": 15617 + }, + { + "epoch": 2.0, + "learning_rate": 3.867499955845233e-12, + "loss": 0.1328, + "step": 15618 + }, + { + "epoch": 2.0, + "learning_rate": 2.6857639640054387e-12, + "loss": 0.1378, + "step": 15619 + }, + { + "epoch": 2.0, + "learning_rate": 1.7188889922525876e-12, + "loss": 0.1276, + "step": 15620 + }, + { + "epoch": 2.0, + "learning_rate": 9.668750822200423e-13, + "loss": 0.1175, + "step": 15621 + }, + { + "epoch": 2.0, + "learning_rate": 4.2972226665938255e-13, + "loss": 0.1446, + "step": 15622 + }, + { + "epoch": 2.0, + "learning_rate": 1.0743056777506866e-13, + "loss": 0.1241, + "step": 15623 + }, + { + "epoch": 2.0, + "learning_rate": 0.0, + "loss": 0.123, + "step": 15624 + }, + { + "epoch": 2.0, + "step": 15624, + "total_flos": 4.2072801811502203e+18, + "train_loss": 0.2387994606342573, + "train_runtime": 108150.0623, + "train_samples_per_second": 18.493, + "train_steps_per_second": 0.144 + } + ], + "max_steps": 15624, + "num_train_epochs": 2, + "total_flos": 4.2072801811502203e+18, + "trial_name": null, + "trial_params": null +}