{ "best_metric": null, "best_model_checkpoint": null, "epoch": 5.0, "global_step": 745, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01, "learning_rate": 1.997315436241611e-05, "loss": 3.1953, "step": 1 }, { "epoch": 0.01, "learning_rate": 1.9946308724832216e-05, "loss": 3.1953, "step": 2 }, { "epoch": 0.02, "learning_rate": 1.9919463087248324e-05, "loss": 3.1523, "step": 3 }, { "epoch": 0.03, "learning_rate": 1.989261744966443e-05, "loss": 3.1562, "step": 4 }, { "epoch": 0.03, "learning_rate": 1.986577181208054e-05, "loss": 3.043, "step": 5 }, { "epoch": 0.04, "learning_rate": 1.9838926174496646e-05, "loss": 3.0391, "step": 6 }, { "epoch": 0.05, "learning_rate": 1.9812080536912754e-05, "loss": 3.0312, "step": 7 }, { "epoch": 0.05, "learning_rate": 1.978523489932886e-05, "loss": 2.9473, "step": 8 }, { "epoch": 0.06, "learning_rate": 1.975838926174497e-05, "loss": 2.9316, "step": 9 }, { "epoch": 0.07, "learning_rate": 1.9731543624161076e-05, "loss": 2.9316, "step": 10 }, { "epoch": 0.07, "learning_rate": 1.9704697986577183e-05, "loss": 2.9062, "step": 11 }, { "epoch": 0.08, "learning_rate": 1.967785234899329e-05, "loss": 2.8984, "step": 12 }, { "epoch": 0.09, "learning_rate": 1.9651006711409398e-05, "loss": 2.8652, "step": 13 }, { "epoch": 0.09, "learning_rate": 1.9624161073825505e-05, "loss": 2.8125, "step": 14 }, { "epoch": 0.1, "learning_rate": 1.9597315436241613e-05, "loss": 2.7734, "step": 15 }, { "epoch": 0.11, "learning_rate": 1.957046979865772e-05, "loss": 2.7773, "step": 16 }, { "epoch": 0.11, "learning_rate": 1.9543624161073828e-05, "loss": 2.75, "step": 17 }, { "epoch": 0.12, "learning_rate": 1.9516778523489935e-05, "loss": 2.7695, "step": 18 }, { "epoch": 0.13, "learning_rate": 1.9489932885906042e-05, "loss": 2.7285, "step": 19 }, { "epoch": 0.13, "learning_rate": 1.946308724832215e-05, "loss": 2.7148, "step": 20 }, { "epoch": 0.14, "learning_rate": 1.9436241610738257e-05, "loss": 2.7031, "step": 21 }, { "epoch": 0.15, "learning_rate": 1.9409395973154365e-05, "loss": 2.6816, "step": 22 }, { "epoch": 0.15, "learning_rate": 1.9382550335570472e-05, "loss": 2.6738, "step": 23 }, { "epoch": 0.16, "learning_rate": 1.935570469798658e-05, "loss": 2.6895, "step": 24 }, { "epoch": 0.17, "learning_rate": 1.9328859060402687e-05, "loss": 2.668, "step": 25 }, { "epoch": 0.17, "learning_rate": 1.9302013422818794e-05, "loss": 2.6699, "step": 26 }, { "epoch": 0.18, "learning_rate": 1.9275167785234902e-05, "loss": 2.625, "step": 27 }, { "epoch": 0.19, "learning_rate": 1.924832214765101e-05, "loss": 2.623, "step": 28 }, { "epoch": 0.19, "learning_rate": 1.9221476510067117e-05, "loss": 2.6055, "step": 29 }, { "epoch": 0.2, "learning_rate": 1.919463087248322e-05, "loss": 2.5723, "step": 30 }, { "epoch": 0.21, "learning_rate": 1.916778523489933e-05, "loss": 2.5762, "step": 31 }, { "epoch": 0.21, "learning_rate": 1.914093959731544e-05, "loss": 2.543, "step": 32 }, { "epoch": 0.22, "learning_rate": 1.9114093959731546e-05, "loss": 2.5742, "step": 33 }, { "epoch": 0.23, "learning_rate": 1.9087248322147654e-05, "loss": 2.5508, "step": 34 }, { "epoch": 0.23, "learning_rate": 1.9060402684563758e-05, "loss": 2.541, "step": 35 }, { "epoch": 0.24, "learning_rate": 1.903355704697987e-05, "loss": 2.5332, "step": 36 }, { "epoch": 0.25, "learning_rate": 1.9006711409395976e-05, "loss": 2.5449, "step": 37 }, { "epoch": 0.26, "learning_rate": 1.8979865771812083e-05, "loss": 2.4922, "step": 38 }, { "epoch": 0.26, "learning_rate": 1.895302013422819e-05, "loss": 2.5156, "step": 39 }, { "epoch": 0.27, "learning_rate": 1.8926174496644295e-05, "loss": 2.502, "step": 40 }, { "epoch": 0.28, "learning_rate": 1.8899328859060406e-05, "loss": 2.4941, "step": 41 }, { "epoch": 0.28, "learning_rate": 1.8872483221476513e-05, "loss": 2.4785, "step": 42 }, { "epoch": 0.29, "learning_rate": 1.884563758389262e-05, "loss": 2.4805, "step": 43 }, { "epoch": 0.3, "learning_rate": 1.8818791946308724e-05, "loss": 2.4805, "step": 44 }, { "epoch": 0.3, "learning_rate": 1.8791946308724832e-05, "loss": 2.4668, "step": 45 }, { "epoch": 0.31, "learning_rate": 1.8765100671140943e-05, "loss": 2.4805, "step": 46 }, { "epoch": 0.32, "learning_rate": 1.873825503355705e-05, "loss": 2.4531, "step": 47 }, { "epoch": 0.32, "learning_rate": 1.8711409395973157e-05, "loss": 2.4375, "step": 48 }, { "epoch": 0.33, "learning_rate": 1.868456375838926e-05, "loss": 2.4434, "step": 49 }, { "epoch": 0.34, "learning_rate": 1.865771812080537e-05, "loss": 2.4258, "step": 50 }, { "epoch": 0.34, "learning_rate": 1.863087248322148e-05, "loss": 2.4453, "step": 51 }, { "epoch": 0.35, "learning_rate": 1.8604026845637587e-05, "loss": 2.4297, "step": 52 }, { "epoch": 0.36, "learning_rate": 1.857718120805369e-05, "loss": 2.4316, "step": 53 }, { "epoch": 0.36, "learning_rate": 1.85503355704698e-05, "loss": 2.4121, "step": 54 }, { "epoch": 0.37, "learning_rate": 1.8523489932885906e-05, "loss": 2.4258, "step": 55 }, { "epoch": 0.38, "learning_rate": 1.8496644295302017e-05, "loss": 2.4121, "step": 56 }, { "epoch": 0.38, "learning_rate": 1.8469798657718124e-05, "loss": 2.3984, "step": 57 }, { "epoch": 0.39, "learning_rate": 1.8442953020134228e-05, "loss": 2.4082, "step": 58 }, { "epoch": 0.4, "learning_rate": 1.8416107382550336e-05, "loss": 2.3945, "step": 59 }, { "epoch": 0.4, "learning_rate": 1.8389261744966443e-05, "loss": 2.4277, "step": 60 }, { "epoch": 0.41, "learning_rate": 1.8362416107382554e-05, "loss": 2.3809, "step": 61 }, { "epoch": 0.42, "learning_rate": 1.833557046979866e-05, "loss": 2.3945, "step": 62 }, { "epoch": 0.42, "learning_rate": 1.8308724832214765e-05, "loss": 2.3691, "step": 63 }, { "epoch": 0.43, "learning_rate": 1.8281879194630873e-05, "loss": 2.3809, "step": 64 }, { "epoch": 0.44, "learning_rate": 1.825503355704698e-05, "loss": 2.375, "step": 65 }, { "epoch": 0.44, "learning_rate": 1.822818791946309e-05, "loss": 2.3711, "step": 66 }, { "epoch": 0.45, "learning_rate": 1.8201342281879195e-05, "loss": 2.3711, "step": 67 }, { "epoch": 0.46, "learning_rate": 1.8174496644295302e-05, "loss": 2.3711, "step": 68 }, { "epoch": 0.46, "learning_rate": 1.814765100671141e-05, "loss": 2.377, "step": 69 }, { "epoch": 0.47, "learning_rate": 1.8120805369127517e-05, "loss": 2.3535, "step": 70 }, { "epoch": 0.48, "learning_rate": 1.8093959731543628e-05, "loss": 2.3359, "step": 71 }, { "epoch": 0.48, "learning_rate": 1.8067114093959732e-05, "loss": 2.3613, "step": 72 }, { "epoch": 0.49, "learning_rate": 1.804026845637584e-05, "loss": 2.3574, "step": 73 }, { "epoch": 0.5, "learning_rate": 1.8013422818791947e-05, "loss": 2.3516, "step": 74 }, { "epoch": 0.5, "learning_rate": 1.7986577181208054e-05, "loss": 2.3594, "step": 75 }, { "epoch": 0.51, "learning_rate": 1.795973154362416e-05, "loss": 2.3359, "step": 76 }, { "epoch": 0.52, "learning_rate": 1.793288590604027e-05, "loss": 2.3438, "step": 77 }, { "epoch": 0.52, "learning_rate": 1.7906040268456376e-05, "loss": 2.3379, "step": 78 }, { "epoch": 0.53, "learning_rate": 1.7879194630872484e-05, "loss": 2.3359, "step": 79 }, { "epoch": 0.54, "learning_rate": 1.7852348993288595e-05, "loss": 2.3496, "step": 80 }, { "epoch": 0.54, "learning_rate": 1.78255033557047e-05, "loss": 2.3281, "step": 81 }, { "epoch": 0.55, "learning_rate": 1.7798657718120806e-05, "loss": 2.3359, "step": 82 }, { "epoch": 0.56, "learning_rate": 1.7771812080536913e-05, "loss": 2.3457, "step": 83 }, { "epoch": 0.56, "learning_rate": 1.774496644295302e-05, "loss": 2.3223, "step": 84 }, { "epoch": 0.57, "learning_rate": 1.771812080536913e-05, "loss": 2.3438, "step": 85 }, { "epoch": 0.58, "learning_rate": 1.7691275167785236e-05, "loss": 2.3242, "step": 86 }, { "epoch": 0.58, "learning_rate": 1.7664429530201343e-05, "loss": 2.3379, "step": 87 }, { "epoch": 0.59, "learning_rate": 1.763758389261745e-05, "loss": 2.3438, "step": 88 }, { "epoch": 0.6, "learning_rate": 1.7610738255033558e-05, "loss": 2.3145, "step": 89 }, { "epoch": 0.6, "learning_rate": 1.7583892617449665e-05, "loss": 2.2949, "step": 90 }, { "epoch": 0.61, "learning_rate": 1.7557046979865773e-05, "loss": 2.3066, "step": 91 }, { "epoch": 0.62, "learning_rate": 1.753020134228188e-05, "loss": 2.3027, "step": 92 }, { "epoch": 0.62, "learning_rate": 1.7503355704697988e-05, "loss": 2.2949, "step": 93 }, { "epoch": 0.63, "learning_rate": 1.7476510067114095e-05, "loss": 2.3086, "step": 94 }, { "epoch": 0.64, "learning_rate": 1.7449664429530202e-05, "loss": 2.3086, "step": 95 }, { "epoch": 0.64, "learning_rate": 1.742281879194631e-05, "loss": 2.3066, "step": 96 }, { "epoch": 0.65, "learning_rate": 1.7395973154362417e-05, "loss": 2.2793, "step": 97 }, { "epoch": 0.66, "learning_rate": 1.7369127516778525e-05, "loss": 2.3008, "step": 98 }, { "epoch": 0.66, "learning_rate": 1.7342281879194632e-05, "loss": 2.2949, "step": 99 }, { "epoch": 0.67, "learning_rate": 1.731543624161074e-05, "loss": 2.3086, "step": 100 }, { "epoch": 0.68, "learning_rate": 1.7288590604026847e-05, "loss": 2.2988, "step": 101 }, { "epoch": 0.68, "learning_rate": 1.7261744966442954e-05, "loss": 2.2715, "step": 102 }, { "epoch": 0.69, "learning_rate": 1.7234899328859062e-05, "loss": 2.2949, "step": 103 }, { "epoch": 0.7, "learning_rate": 1.720805369127517e-05, "loss": 2.2793, "step": 104 }, { "epoch": 0.7, "learning_rate": 1.7181208053691277e-05, "loss": 2.2637, "step": 105 }, { "epoch": 0.71, "learning_rate": 1.7154362416107384e-05, "loss": 2.2773, "step": 106 }, { "epoch": 0.72, "learning_rate": 1.712751677852349e-05, "loss": 2.293, "step": 107 }, { "epoch": 0.72, "learning_rate": 1.71006711409396e-05, "loss": 2.2793, "step": 108 }, { "epoch": 0.73, "learning_rate": 1.7073825503355706e-05, "loss": 2.2773, "step": 109 }, { "epoch": 0.74, "learning_rate": 1.7046979865771814e-05, "loss": 2.3027, "step": 110 }, { "epoch": 0.74, "learning_rate": 1.702013422818792e-05, "loss": 2.2676, "step": 111 }, { "epoch": 0.75, "learning_rate": 1.699328859060403e-05, "loss": 2.2852, "step": 112 }, { "epoch": 0.76, "learning_rate": 1.6966442953020136e-05, "loss": 2.2715, "step": 113 }, { "epoch": 0.77, "learning_rate": 1.6939597315436243e-05, "loss": 2.2559, "step": 114 }, { "epoch": 0.77, "learning_rate": 1.691275167785235e-05, "loss": 2.2812, "step": 115 }, { "epoch": 0.78, "learning_rate": 1.6885906040268458e-05, "loss": 2.2676, "step": 116 }, { "epoch": 0.79, "learning_rate": 1.6859060402684565e-05, "loss": 2.2832, "step": 117 }, { "epoch": 0.79, "learning_rate": 1.6832214765100673e-05, "loss": 2.2617, "step": 118 }, { "epoch": 0.8, "learning_rate": 1.680536912751678e-05, "loss": 2.2656, "step": 119 }, { "epoch": 0.81, "learning_rate": 1.6778523489932888e-05, "loss": 2.2578, "step": 120 }, { "epoch": 0.81, "learning_rate": 1.6751677852348995e-05, "loss": 2.2383, "step": 121 }, { "epoch": 0.82, "learning_rate": 1.6724832214765103e-05, "loss": 2.2441, "step": 122 }, { "epoch": 0.83, "learning_rate": 1.669798657718121e-05, "loss": 2.2539, "step": 123 }, { "epoch": 0.83, "learning_rate": 1.6671140939597317e-05, "loss": 2.2441, "step": 124 }, { "epoch": 0.84, "learning_rate": 1.6644295302013425e-05, "loss": 2.2363, "step": 125 }, { "epoch": 0.85, "learning_rate": 1.6617449664429532e-05, "loss": 2.2539, "step": 126 }, { "epoch": 0.85, "learning_rate": 1.659060402684564e-05, "loss": 2.2539, "step": 127 }, { "epoch": 0.86, "learning_rate": 1.6563758389261747e-05, "loss": 2.248, "step": 128 }, { "epoch": 0.87, "learning_rate": 1.6536912751677854e-05, "loss": 2.2402, "step": 129 }, { "epoch": 0.87, "learning_rate": 1.6510067114093962e-05, "loss": 2.2578, "step": 130 }, { "epoch": 0.88, "learning_rate": 1.648322147651007e-05, "loss": 2.248, "step": 131 }, { "epoch": 0.89, "learning_rate": 1.6456375838926177e-05, "loss": 2.2793, "step": 132 }, { "epoch": 0.89, "learning_rate": 1.6429530201342284e-05, "loss": 2.2227, "step": 133 }, { "epoch": 0.9, "learning_rate": 1.640268456375839e-05, "loss": 2.2422, "step": 134 }, { "epoch": 0.91, "learning_rate": 1.63758389261745e-05, "loss": 2.2402, "step": 135 }, { "epoch": 0.91, "learning_rate": 1.6348993288590603e-05, "loss": 2.2461, "step": 136 }, { "epoch": 0.92, "learning_rate": 1.6322147651006714e-05, "loss": 2.2246, "step": 137 }, { "epoch": 0.93, "learning_rate": 1.629530201342282e-05, "loss": 2.2363, "step": 138 }, { "epoch": 0.93, "learning_rate": 1.626845637583893e-05, "loss": 2.2285, "step": 139 }, { "epoch": 0.94, "learning_rate": 1.6241610738255036e-05, "loss": 2.2461, "step": 140 }, { "epoch": 0.95, "learning_rate": 1.621476510067114e-05, "loss": 2.2129, "step": 141 }, { "epoch": 0.95, "learning_rate": 1.618791946308725e-05, "loss": 2.2246, "step": 142 }, { "epoch": 0.96, "learning_rate": 1.6161073825503358e-05, "loss": 2.2148, "step": 143 }, { "epoch": 0.97, "learning_rate": 1.6134228187919466e-05, "loss": 2.2148, "step": 144 }, { "epoch": 0.97, "learning_rate": 1.610738255033557e-05, "loss": 2.2207, "step": 145 }, { "epoch": 0.98, "learning_rate": 1.6080536912751677e-05, "loss": 2.1973, "step": 146 }, { "epoch": 0.99, "learning_rate": 1.6053691275167788e-05, "loss": 2.2109, "step": 147 }, { "epoch": 0.99, "learning_rate": 1.6026845637583895e-05, "loss": 2.2266, "step": 148 }, { "epoch": 1.0, "learning_rate": 1.6000000000000003e-05, "loss": 2.2227, "step": 149 }, { "epoch": 1.01, "learning_rate": 1.5973154362416107e-05, "loss": 2.209, "step": 150 }, { "epoch": 1.01, "learning_rate": 1.5946308724832214e-05, "loss": 2.207, "step": 151 }, { "epoch": 1.02, "learning_rate": 1.5919463087248325e-05, "loss": 2.1934, "step": 152 }, { "epoch": 1.03, "learning_rate": 1.5892617449664432e-05, "loss": 2.2129, "step": 153 }, { "epoch": 1.03, "learning_rate": 1.586577181208054e-05, "loss": 2.207, "step": 154 }, { "epoch": 1.04, "learning_rate": 1.5838926174496644e-05, "loss": 2.2324, "step": 155 }, { "epoch": 1.05, "learning_rate": 1.581208053691275e-05, "loss": 2.2031, "step": 156 }, { "epoch": 1.05, "learning_rate": 1.5785234899328862e-05, "loss": 2.2031, "step": 157 }, { "epoch": 1.06, "learning_rate": 1.575838926174497e-05, "loss": 2.1992, "step": 158 }, { "epoch": 1.07, "learning_rate": 1.5731543624161073e-05, "loss": 2.2031, "step": 159 }, { "epoch": 1.07, "learning_rate": 1.570469798657718e-05, "loss": 2.1836, "step": 160 }, { "epoch": 1.08, "learning_rate": 1.5677852348993288e-05, "loss": 2.2266, "step": 161 }, { "epoch": 1.09, "learning_rate": 1.56510067114094e-05, "loss": 2.2129, "step": 162 }, { "epoch": 1.09, "learning_rate": 1.5624161073825506e-05, "loss": 2.1973, "step": 163 }, { "epoch": 1.1, "learning_rate": 1.559731543624161e-05, "loss": 2.2109, "step": 164 }, { "epoch": 1.11, "learning_rate": 1.5570469798657718e-05, "loss": 2.1934, "step": 165 }, { "epoch": 1.11, "learning_rate": 1.554362416107383e-05, "loss": 2.209, "step": 166 }, { "epoch": 1.12, "learning_rate": 1.5516778523489936e-05, "loss": 2.1992, "step": 167 }, { "epoch": 1.13, "learning_rate": 1.548993288590604e-05, "loss": 2.1816, "step": 168 }, { "epoch": 1.13, "learning_rate": 1.5463087248322148e-05, "loss": 2.2109, "step": 169 }, { "epoch": 1.14, "learning_rate": 1.5436241610738255e-05, "loss": 2.1992, "step": 170 }, { "epoch": 1.15, "learning_rate": 1.5409395973154366e-05, "loss": 2.1699, "step": 171 }, { "epoch": 1.15, "learning_rate": 1.5382550335570473e-05, "loss": 2.1777, "step": 172 }, { "epoch": 1.16, "learning_rate": 1.5355704697986577e-05, "loss": 2.2148, "step": 173 }, { "epoch": 1.17, "learning_rate": 1.5328859060402685e-05, "loss": 2.1953, "step": 174 }, { "epoch": 1.17, "learning_rate": 1.5302013422818792e-05, "loss": 2.168, "step": 175 }, { "epoch": 1.18, "learning_rate": 1.5275167785234903e-05, "loss": 2.1797, "step": 176 }, { "epoch": 1.19, "learning_rate": 1.5248322147651009e-05, "loss": 2.2109, "step": 177 }, { "epoch": 1.19, "learning_rate": 1.5221476510067114e-05, "loss": 2.1895, "step": 178 }, { "epoch": 1.2, "learning_rate": 1.5194630872483223e-05, "loss": 2.1816, "step": 179 }, { "epoch": 1.21, "learning_rate": 1.516778523489933e-05, "loss": 2.1621, "step": 180 }, { "epoch": 1.21, "learning_rate": 1.5140939597315438e-05, "loss": 2.1816, "step": 181 }, { "epoch": 1.22, "learning_rate": 1.5114093959731544e-05, "loss": 2.1777, "step": 182 }, { "epoch": 1.23, "learning_rate": 1.5087248322147651e-05, "loss": 2.1777, "step": 183 }, { "epoch": 1.23, "learning_rate": 1.506040268456376e-05, "loss": 2.1738, "step": 184 }, { "epoch": 1.24, "learning_rate": 1.5033557046979868e-05, "loss": 2.1836, "step": 185 }, { "epoch": 1.25, "learning_rate": 1.5006711409395975e-05, "loss": 2.1797, "step": 186 }, { "epoch": 1.26, "learning_rate": 1.4979865771812081e-05, "loss": 2.1738, "step": 187 }, { "epoch": 1.26, "learning_rate": 1.4953020134228188e-05, "loss": 2.1914, "step": 188 }, { "epoch": 1.27, "learning_rate": 1.4926174496644297e-05, "loss": 2.1719, "step": 189 }, { "epoch": 1.28, "learning_rate": 1.4899328859060405e-05, "loss": 2.1777, "step": 190 }, { "epoch": 1.28, "learning_rate": 1.487248322147651e-05, "loss": 2.1504, "step": 191 }, { "epoch": 1.29, "learning_rate": 1.4845637583892618e-05, "loss": 2.1992, "step": 192 }, { "epoch": 1.3, "learning_rate": 1.4818791946308725e-05, "loss": 2.1855, "step": 193 }, { "epoch": 1.3, "learning_rate": 1.4791946308724835e-05, "loss": 2.1777, "step": 194 }, { "epoch": 1.31, "learning_rate": 1.4765100671140942e-05, "loss": 2.1504, "step": 195 }, { "epoch": 1.32, "learning_rate": 1.4738255033557048e-05, "loss": 2.168, "step": 196 }, { "epoch": 1.32, "learning_rate": 1.4711409395973155e-05, "loss": 2.168, "step": 197 }, { "epoch": 1.33, "learning_rate": 1.4684563758389262e-05, "loss": 2.1777, "step": 198 }, { "epoch": 1.34, "learning_rate": 1.4657718120805372e-05, "loss": 2.1621, "step": 199 }, { "epoch": 1.34, "learning_rate": 1.4630872483221479e-05, "loss": 2.1758, "step": 200 }, { "epoch": 1.35, "learning_rate": 1.4604026845637585e-05, "loss": 2.1719, "step": 201 }, { "epoch": 1.36, "learning_rate": 1.4577181208053692e-05, "loss": 2.1777, "step": 202 }, { "epoch": 1.36, "learning_rate": 1.45503355704698e-05, "loss": 2.1445, "step": 203 }, { "epoch": 1.37, "learning_rate": 1.4523489932885909e-05, "loss": 2.1562, "step": 204 }, { "epoch": 1.38, "learning_rate": 1.4496644295302014e-05, "loss": 2.1758, "step": 205 }, { "epoch": 1.38, "learning_rate": 1.4469798657718122e-05, "loss": 2.1738, "step": 206 }, { "epoch": 1.39, "learning_rate": 1.444295302013423e-05, "loss": 2.1562, "step": 207 }, { "epoch": 1.4, "learning_rate": 1.4416107382550337e-05, "loss": 2.1758, "step": 208 }, { "epoch": 1.4, "learning_rate": 1.4389261744966446e-05, "loss": 2.1621, "step": 209 }, { "epoch": 1.41, "learning_rate": 1.4362416107382551e-05, "loss": 2.166, "step": 210 }, { "epoch": 1.42, "learning_rate": 1.4335570469798659e-05, "loss": 2.1582, "step": 211 }, { "epoch": 1.42, "learning_rate": 1.4308724832214766e-05, "loss": 2.1582, "step": 212 }, { "epoch": 1.43, "learning_rate": 1.4281879194630874e-05, "loss": 2.1562, "step": 213 }, { "epoch": 1.44, "learning_rate": 1.425503355704698e-05, "loss": 2.1641, "step": 214 }, { "epoch": 1.44, "learning_rate": 1.4228187919463088e-05, "loss": 2.1777, "step": 215 }, { "epoch": 1.45, "learning_rate": 1.4201342281879196e-05, "loss": 2.1426, "step": 216 }, { "epoch": 1.46, "learning_rate": 1.4174496644295303e-05, "loss": 2.1504, "step": 217 }, { "epoch": 1.46, "learning_rate": 1.414765100671141e-05, "loss": 2.1641, "step": 218 }, { "epoch": 1.47, "learning_rate": 1.4120805369127516e-05, "loss": 2.1484, "step": 219 }, { "epoch": 1.48, "learning_rate": 1.4093959731543626e-05, "loss": 2.1484, "step": 220 }, { "epoch": 1.48, "learning_rate": 1.4067114093959733e-05, "loss": 2.1289, "step": 221 }, { "epoch": 1.49, "learning_rate": 1.404026845637584e-05, "loss": 2.1426, "step": 222 }, { "epoch": 1.5, "learning_rate": 1.4013422818791948e-05, "loss": 2.1367, "step": 223 }, { "epoch": 1.5, "learning_rate": 1.3986577181208053e-05, "loss": 2.168, "step": 224 }, { "epoch": 1.51, "learning_rate": 1.3959731543624163e-05, "loss": 2.123, "step": 225 }, { "epoch": 1.52, "learning_rate": 1.393288590604027e-05, "loss": 2.1484, "step": 226 }, { "epoch": 1.52, "learning_rate": 1.3906040268456377e-05, "loss": 2.1641, "step": 227 }, { "epoch": 1.53, "learning_rate": 1.3879194630872483e-05, "loss": 2.1367, "step": 228 }, { "epoch": 1.54, "learning_rate": 1.385234899328859e-05, "loss": 2.1543, "step": 229 }, { "epoch": 1.54, "learning_rate": 1.38255033557047e-05, "loss": 2.166, "step": 230 }, { "epoch": 1.55, "learning_rate": 1.3798657718120807e-05, "loss": 2.1094, "step": 231 }, { "epoch": 1.56, "learning_rate": 1.3771812080536914e-05, "loss": 2.1289, "step": 232 }, { "epoch": 1.56, "learning_rate": 1.374496644295302e-05, "loss": 2.1484, "step": 233 }, { "epoch": 1.57, "learning_rate": 1.3718120805369128e-05, "loss": 2.1348, "step": 234 }, { "epoch": 1.58, "learning_rate": 1.3691275167785237e-05, "loss": 2.125, "step": 235 }, { "epoch": 1.58, "learning_rate": 1.3664429530201344e-05, "loss": 2.1426, "step": 236 }, { "epoch": 1.59, "learning_rate": 1.363758389261745e-05, "loss": 2.1504, "step": 237 }, { "epoch": 1.6, "learning_rate": 1.3610738255033557e-05, "loss": 2.1328, "step": 238 }, { "epoch": 1.6, "learning_rate": 1.3583892617449665e-05, "loss": 2.1406, "step": 239 }, { "epoch": 1.61, "learning_rate": 1.3557046979865774e-05, "loss": 2.1504, "step": 240 }, { "epoch": 1.62, "learning_rate": 1.3530201342281881e-05, "loss": 2.127, "step": 241 }, { "epoch": 1.62, "learning_rate": 1.3503355704697987e-05, "loss": 2.1211, "step": 242 }, { "epoch": 1.63, "learning_rate": 1.3476510067114094e-05, "loss": 2.1367, "step": 243 }, { "epoch": 1.64, "learning_rate": 1.3449664429530202e-05, "loss": 2.1406, "step": 244 }, { "epoch": 1.64, "learning_rate": 1.342281879194631e-05, "loss": 2.125, "step": 245 }, { "epoch": 1.65, "learning_rate": 1.3395973154362418e-05, "loss": 2.1445, "step": 246 }, { "epoch": 1.66, "learning_rate": 1.3369127516778524e-05, "loss": 2.1328, "step": 247 }, { "epoch": 1.66, "learning_rate": 1.3342281879194631e-05, "loss": 2.1328, "step": 248 }, { "epoch": 1.67, "learning_rate": 1.331543624161074e-05, "loss": 2.127, "step": 249 }, { "epoch": 1.68, "learning_rate": 1.3288590604026848e-05, "loss": 2.1309, "step": 250 }, { "epoch": 1.68, "learning_rate": 1.3261744966442954e-05, "loss": 2.1426, "step": 251 }, { "epoch": 1.69, "learning_rate": 1.3234899328859061e-05, "loss": 2.1289, "step": 252 }, { "epoch": 1.7, "learning_rate": 1.3208053691275168e-05, "loss": 2.1387, "step": 253 }, { "epoch": 1.7, "learning_rate": 1.3181208053691278e-05, "loss": 2.1172, "step": 254 }, { "epoch": 1.71, "learning_rate": 1.3154362416107385e-05, "loss": 2.1309, "step": 255 }, { "epoch": 1.72, "learning_rate": 1.312751677852349e-05, "loss": 2.1309, "step": 256 }, { "epoch": 1.72, "learning_rate": 1.3100671140939598e-05, "loss": 2.1074, "step": 257 }, { "epoch": 1.73, "learning_rate": 1.3073825503355706e-05, "loss": 2.0977, "step": 258 }, { "epoch": 1.74, "learning_rate": 1.3046979865771815e-05, "loss": 2.1133, "step": 259 }, { "epoch": 1.74, "learning_rate": 1.302013422818792e-05, "loss": 2.123, "step": 260 }, { "epoch": 1.75, "learning_rate": 1.2993288590604028e-05, "loss": 2.127, "step": 261 }, { "epoch": 1.76, "learning_rate": 1.2966442953020135e-05, "loss": 2.1191, "step": 262 }, { "epoch": 1.77, "learning_rate": 1.2939597315436243e-05, "loss": 2.0938, "step": 263 }, { "epoch": 1.77, "learning_rate": 1.2912751677852352e-05, "loss": 2.1367, "step": 264 }, { "epoch": 1.78, "learning_rate": 1.2885906040268457e-05, "loss": 2.1094, "step": 265 }, { "epoch": 1.79, "learning_rate": 1.2859060402684565e-05, "loss": 2.1035, "step": 266 }, { "epoch": 1.79, "learning_rate": 1.2832214765100672e-05, "loss": 2.1074, "step": 267 }, { "epoch": 1.8, "learning_rate": 1.280536912751678e-05, "loss": 2.1348, "step": 268 }, { "epoch": 1.81, "learning_rate": 1.2778523489932889e-05, "loss": 2.1309, "step": 269 }, { "epoch": 1.81, "learning_rate": 1.2751677852348994e-05, "loss": 2.1055, "step": 270 }, { "epoch": 1.82, "learning_rate": 1.2724832214765102e-05, "loss": 2.125, "step": 271 }, { "epoch": 1.83, "learning_rate": 1.269798657718121e-05, "loss": 2.0957, "step": 272 }, { "epoch": 1.83, "learning_rate": 1.2671140939597317e-05, "loss": 2.1309, "step": 273 }, { "epoch": 1.84, "learning_rate": 1.2644295302013422e-05, "loss": 2.1191, "step": 274 }, { "epoch": 1.85, "learning_rate": 1.2617449664429532e-05, "loss": 2.1211, "step": 275 }, { "epoch": 1.85, "learning_rate": 1.2590604026845639e-05, "loss": 2.1348, "step": 276 }, { "epoch": 1.86, "learning_rate": 1.2563758389261746e-05, "loss": 2.1191, "step": 277 }, { "epoch": 1.87, "learning_rate": 1.2536912751677854e-05, "loss": 2.1035, "step": 278 }, { "epoch": 1.87, "learning_rate": 1.251006711409396e-05, "loss": 2.1094, "step": 279 }, { "epoch": 1.88, "learning_rate": 1.2483221476510069e-05, "loss": 2.1133, "step": 280 }, { "epoch": 1.89, "learning_rate": 1.2456375838926176e-05, "loss": 2.1191, "step": 281 }, { "epoch": 1.89, "learning_rate": 1.2429530201342283e-05, "loss": 2.082, "step": 282 }, { "epoch": 1.9, "learning_rate": 1.2402684563758389e-05, "loss": 2.1133, "step": 283 }, { "epoch": 1.91, "learning_rate": 1.2375838926174497e-05, "loss": 2.1113, "step": 284 }, { "epoch": 1.91, "learning_rate": 1.2348993288590606e-05, "loss": 2.0996, "step": 285 }, { "epoch": 1.92, "learning_rate": 1.2322147651006713e-05, "loss": 2.1094, "step": 286 }, { "epoch": 1.93, "learning_rate": 1.229530201342282e-05, "loss": 2.0918, "step": 287 }, { "epoch": 1.93, "learning_rate": 1.2268456375838926e-05, "loss": 2.0938, "step": 288 }, { "epoch": 1.94, "learning_rate": 1.2241610738255034e-05, "loss": 2.1152, "step": 289 }, { "epoch": 1.95, "learning_rate": 1.2214765100671143e-05, "loss": 2.1016, "step": 290 }, { "epoch": 1.95, "learning_rate": 1.218791946308725e-05, "loss": 2.1152, "step": 291 }, { "epoch": 1.96, "learning_rate": 1.2161073825503358e-05, "loss": 2.1016, "step": 292 }, { "epoch": 1.97, "learning_rate": 1.2134228187919463e-05, "loss": 2.1055, "step": 293 }, { "epoch": 1.97, "learning_rate": 1.210738255033557e-05, "loss": 2.0938, "step": 294 }, { "epoch": 1.98, "learning_rate": 1.208053691275168e-05, "loss": 2.1211, "step": 295 }, { "epoch": 1.99, "learning_rate": 1.2053691275167787e-05, "loss": 2.1016, "step": 296 }, { "epoch": 1.99, "learning_rate": 1.2026845637583893e-05, "loss": 2.1152, "step": 297 }, { "epoch": 2.0, "learning_rate": 1.2e-05, "loss": 2.0957, "step": 298 }, { "epoch": 2.01, "learning_rate": 1.1973154362416108e-05, "loss": 2.0938, "step": 299 }, { "epoch": 2.01, "learning_rate": 1.1946308724832217e-05, "loss": 2.0859, "step": 300 }, { "epoch": 2.02, "learning_rate": 1.1919463087248324e-05, "loss": 2.0879, "step": 301 }, { "epoch": 2.03, "learning_rate": 1.189261744966443e-05, "loss": 2.082, "step": 302 }, { "epoch": 2.03, "learning_rate": 1.1865771812080537e-05, "loss": 2.1074, "step": 303 }, { "epoch": 2.04, "learning_rate": 1.1838926174496645e-05, "loss": 2.1016, "step": 304 }, { "epoch": 2.05, "learning_rate": 1.1812080536912754e-05, "loss": 2.0957, "step": 305 }, { "epoch": 2.05, "learning_rate": 1.178523489932886e-05, "loss": 2.0684, "step": 306 }, { "epoch": 2.06, "learning_rate": 1.1758389261744967e-05, "loss": 2.0898, "step": 307 }, { "epoch": 2.07, "learning_rate": 1.1731543624161074e-05, "loss": 2.0977, "step": 308 }, { "epoch": 2.07, "learning_rate": 1.1704697986577182e-05, "loss": 2.1074, "step": 309 }, { "epoch": 2.08, "learning_rate": 1.1677852348993291e-05, "loss": 2.125, "step": 310 }, { "epoch": 2.09, "learning_rate": 1.1651006711409397e-05, "loss": 2.1016, "step": 311 }, { "epoch": 2.09, "learning_rate": 1.1624161073825504e-05, "loss": 2.1035, "step": 312 }, { "epoch": 2.1, "learning_rate": 1.1597315436241611e-05, "loss": 2.084, "step": 313 }, { "epoch": 2.11, "learning_rate": 1.1570469798657719e-05, "loss": 2.0762, "step": 314 }, { "epoch": 2.11, "learning_rate": 1.1543624161073828e-05, "loss": 2.1133, "step": 315 }, { "epoch": 2.12, "learning_rate": 1.1516778523489934e-05, "loss": 2.1016, "step": 316 }, { "epoch": 2.13, "learning_rate": 1.1489932885906041e-05, "loss": 2.0742, "step": 317 }, { "epoch": 2.13, "learning_rate": 1.1463087248322149e-05, "loss": 2.0771, "step": 318 }, { "epoch": 2.14, "learning_rate": 1.1436241610738256e-05, "loss": 2.0879, "step": 319 }, { "epoch": 2.15, "learning_rate": 1.1409395973154362e-05, "loss": 2.0957, "step": 320 }, { "epoch": 2.15, "learning_rate": 1.138255033557047e-05, "loss": 2.0879, "step": 321 }, { "epoch": 2.16, "learning_rate": 1.1355704697986578e-05, "loss": 2.082, "step": 322 }, { "epoch": 2.17, "learning_rate": 1.1328859060402686e-05, "loss": 2.0996, "step": 323 }, { "epoch": 2.17, "learning_rate": 1.1302013422818795e-05, "loss": 2.0801, "step": 324 }, { "epoch": 2.18, "learning_rate": 1.1275167785234899e-05, "loss": 2.1113, "step": 325 }, { "epoch": 2.19, "learning_rate": 1.1248322147651008e-05, "loss": 2.0996, "step": 326 }, { "epoch": 2.19, "learning_rate": 1.1221476510067115e-05, "loss": 2.0762, "step": 327 }, { "epoch": 2.2, "learning_rate": 1.1194630872483223e-05, "loss": 2.1094, "step": 328 }, { "epoch": 2.21, "learning_rate": 1.1167785234899328e-05, "loss": 2.082, "step": 329 }, { "epoch": 2.21, "learning_rate": 1.1140939597315436e-05, "loss": 2.0527, "step": 330 }, { "epoch": 2.22, "learning_rate": 1.1114093959731545e-05, "loss": 2.0859, "step": 331 }, { "epoch": 2.23, "learning_rate": 1.1087248322147652e-05, "loss": 2.0508, "step": 332 }, { "epoch": 2.23, "learning_rate": 1.106040268456376e-05, "loss": 2.0977, "step": 333 }, { "epoch": 2.24, "learning_rate": 1.1033557046979865e-05, "loss": 2.0889, "step": 334 }, { "epoch": 2.25, "learning_rate": 1.1006711409395975e-05, "loss": 2.082, "step": 335 }, { "epoch": 2.26, "learning_rate": 1.0979865771812082e-05, "loss": 2.0742, "step": 336 }, { "epoch": 2.26, "learning_rate": 1.095302013422819e-05, "loss": 2.0879, "step": 337 }, { "epoch": 2.27, "learning_rate": 1.0926174496644297e-05, "loss": 2.082, "step": 338 }, { "epoch": 2.28, "learning_rate": 1.0899328859060403e-05, "loss": 2.0879, "step": 339 }, { "epoch": 2.28, "learning_rate": 1.0872483221476512e-05, "loss": 2.082, "step": 340 }, { "epoch": 2.29, "learning_rate": 1.0845637583892619e-05, "loss": 2.082, "step": 341 }, { "epoch": 2.3, "learning_rate": 1.0818791946308726e-05, "loss": 2.0547, "step": 342 }, { "epoch": 2.3, "learning_rate": 1.0791946308724832e-05, "loss": 2.0645, "step": 343 }, { "epoch": 2.31, "learning_rate": 1.076510067114094e-05, "loss": 2.0703, "step": 344 }, { "epoch": 2.32, "learning_rate": 1.0738255033557049e-05, "loss": 2.084, "step": 345 }, { "epoch": 2.32, "learning_rate": 1.0711409395973156e-05, "loss": 2.0762, "step": 346 }, { "epoch": 2.33, "learning_rate": 1.0684563758389264e-05, "loss": 2.0723, "step": 347 }, { "epoch": 2.34, "learning_rate": 1.065771812080537e-05, "loss": 2.0723, "step": 348 }, { "epoch": 2.34, "learning_rate": 1.0630872483221477e-05, "loss": 2.0723, "step": 349 }, { "epoch": 2.35, "learning_rate": 1.0604026845637586e-05, "loss": 2.084, "step": 350 }, { "epoch": 2.36, "learning_rate": 1.0577181208053693e-05, "loss": 2.0781, "step": 351 }, { "epoch": 2.36, "learning_rate": 1.0550335570469799e-05, "loss": 2.0742, "step": 352 }, { "epoch": 2.37, "learning_rate": 1.0523489932885906e-05, "loss": 2.0869, "step": 353 }, { "epoch": 2.38, "learning_rate": 1.0496644295302014e-05, "loss": 2.0625, "step": 354 }, { "epoch": 2.38, "learning_rate": 1.0469798657718123e-05, "loss": 2.0859, "step": 355 }, { "epoch": 2.39, "learning_rate": 1.044295302013423e-05, "loss": 2.0801, "step": 356 }, { "epoch": 2.4, "learning_rate": 1.0416107382550336e-05, "loss": 2.0566, "step": 357 }, { "epoch": 2.4, "learning_rate": 1.0389261744966443e-05, "loss": 2.0859, "step": 358 }, { "epoch": 2.41, "learning_rate": 1.036241610738255e-05, "loss": 2.084, "step": 359 }, { "epoch": 2.42, "learning_rate": 1.033557046979866e-05, "loss": 2.0762, "step": 360 }, { "epoch": 2.42, "learning_rate": 1.0308724832214767e-05, "loss": 2.0703, "step": 361 }, { "epoch": 2.43, "learning_rate": 1.0281879194630873e-05, "loss": 2.0762, "step": 362 }, { "epoch": 2.44, "learning_rate": 1.025503355704698e-05, "loss": 2.0762, "step": 363 }, { "epoch": 2.44, "learning_rate": 1.0228187919463088e-05, "loss": 2.0664, "step": 364 }, { "epoch": 2.45, "learning_rate": 1.0201342281879197e-05, "loss": 2.0586, "step": 365 }, { "epoch": 2.46, "learning_rate": 1.0174496644295303e-05, "loss": 2.0664, "step": 366 }, { "epoch": 2.46, "learning_rate": 1.014765100671141e-05, "loss": 2.0684, "step": 367 }, { "epoch": 2.47, "learning_rate": 1.0120805369127517e-05, "loss": 2.0605, "step": 368 }, { "epoch": 2.48, "learning_rate": 1.0093959731543625e-05, "loss": 2.0625, "step": 369 }, { "epoch": 2.48, "learning_rate": 1.0067114093959734e-05, "loss": 2.0859, "step": 370 }, { "epoch": 2.49, "learning_rate": 1.004026845637584e-05, "loss": 2.0527, "step": 371 }, { "epoch": 2.5, "learning_rate": 1.0013422818791947e-05, "loss": 2.0703, "step": 372 }, { "epoch": 2.5, "learning_rate": 9.986577181208055e-06, "loss": 2.0684, "step": 373 }, { "epoch": 2.51, "learning_rate": 9.959731543624162e-06, "loss": 2.0488, "step": 374 }, { "epoch": 2.52, "learning_rate": 9.93288590604027e-06, "loss": 2.0762, "step": 375 }, { "epoch": 2.52, "learning_rate": 9.906040268456377e-06, "loss": 2.0508, "step": 376 }, { "epoch": 2.53, "learning_rate": 9.879194630872484e-06, "loss": 2.0605, "step": 377 }, { "epoch": 2.54, "learning_rate": 9.852348993288592e-06, "loss": 2.0508, "step": 378 }, { "epoch": 2.54, "learning_rate": 9.825503355704699e-06, "loss": 2.0508, "step": 379 }, { "epoch": 2.55, "learning_rate": 9.798657718120806e-06, "loss": 2.0664, "step": 380 }, { "epoch": 2.56, "learning_rate": 9.771812080536914e-06, "loss": 2.0664, "step": 381 }, { "epoch": 2.56, "learning_rate": 9.744966442953021e-06, "loss": 2.0859, "step": 382 }, { "epoch": 2.57, "learning_rate": 9.718120805369129e-06, "loss": 2.0859, "step": 383 }, { "epoch": 2.58, "learning_rate": 9.691275167785236e-06, "loss": 2.0566, "step": 384 }, { "epoch": 2.58, "learning_rate": 9.664429530201343e-06, "loss": 2.0703, "step": 385 }, { "epoch": 2.59, "learning_rate": 9.637583892617451e-06, "loss": 2.0645, "step": 386 }, { "epoch": 2.6, "learning_rate": 9.610738255033558e-06, "loss": 2.0645, "step": 387 }, { "epoch": 2.6, "learning_rate": 9.583892617449666e-06, "loss": 2.0566, "step": 388 }, { "epoch": 2.61, "learning_rate": 9.557046979865773e-06, "loss": 2.0605, "step": 389 }, { "epoch": 2.62, "learning_rate": 9.530201342281879e-06, "loss": 2.0625, "step": 390 }, { "epoch": 2.62, "learning_rate": 9.503355704697988e-06, "loss": 2.0684, "step": 391 }, { "epoch": 2.63, "learning_rate": 9.476510067114095e-06, "loss": 2.0566, "step": 392 }, { "epoch": 2.64, "learning_rate": 9.449664429530203e-06, "loss": 2.0547, "step": 393 }, { "epoch": 2.64, "learning_rate": 9.42281879194631e-06, "loss": 2.0547, "step": 394 }, { "epoch": 2.65, "learning_rate": 9.395973154362416e-06, "loss": 2.0742, "step": 395 }, { "epoch": 2.66, "learning_rate": 9.369127516778525e-06, "loss": 2.084, "step": 396 }, { "epoch": 2.66, "learning_rate": 9.34228187919463e-06, "loss": 2.0518, "step": 397 }, { "epoch": 2.67, "learning_rate": 9.31543624161074e-06, "loss": 2.0439, "step": 398 }, { "epoch": 2.68, "learning_rate": 9.288590604026846e-06, "loss": 2.0645, "step": 399 }, { "epoch": 2.68, "learning_rate": 9.261744966442953e-06, "loss": 2.0605, "step": 400 }, { "epoch": 2.69, "learning_rate": 9.234899328859062e-06, "loss": 2.0664, "step": 401 }, { "epoch": 2.7, "learning_rate": 9.208053691275168e-06, "loss": 2.0645, "step": 402 }, { "epoch": 2.7, "learning_rate": 9.181208053691277e-06, "loss": 2.0527, "step": 403 }, { "epoch": 2.71, "learning_rate": 9.154362416107383e-06, "loss": 2.0605, "step": 404 }, { "epoch": 2.72, "learning_rate": 9.12751677852349e-06, "loss": 2.0381, "step": 405 }, { "epoch": 2.72, "learning_rate": 9.100671140939597e-06, "loss": 2.0352, "step": 406 }, { "epoch": 2.73, "learning_rate": 9.073825503355705e-06, "loss": 2.0352, "step": 407 }, { "epoch": 2.74, "learning_rate": 9.046979865771814e-06, "loss": 2.0439, "step": 408 }, { "epoch": 2.74, "learning_rate": 9.02013422818792e-06, "loss": 2.0332, "step": 409 }, { "epoch": 2.75, "learning_rate": 8.993288590604027e-06, "loss": 2.0566, "step": 410 }, { "epoch": 2.76, "learning_rate": 8.966442953020134e-06, "loss": 2.0625, "step": 411 }, { "epoch": 2.77, "learning_rate": 8.939597315436242e-06, "loss": 2.0488, "step": 412 }, { "epoch": 2.77, "learning_rate": 8.91275167785235e-06, "loss": 2.0488, "step": 413 }, { "epoch": 2.78, "learning_rate": 8.885906040268457e-06, "loss": 2.0664, "step": 414 }, { "epoch": 2.79, "learning_rate": 8.859060402684566e-06, "loss": 2.0645, "step": 415 }, { "epoch": 2.79, "learning_rate": 8.832214765100672e-06, "loss": 2.0625, "step": 416 }, { "epoch": 2.8, "learning_rate": 8.805369127516779e-06, "loss": 2.0547, "step": 417 }, { "epoch": 2.81, "learning_rate": 8.778523489932886e-06, "loss": 2.0645, "step": 418 }, { "epoch": 2.81, "learning_rate": 8.751677852348994e-06, "loss": 2.0459, "step": 419 }, { "epoch": 2.82, "learning_rate": 8.724832214765101e-06, "loss": 2.043, "step": 420 }, { "epoch": 2.83, "learning_rate": 8.697986577181209e-06, "loss": 2.0645, "step": 421 }, { "epoch": 2.83, "learning_rate": 8.671140939597316e-06, "loss": 2.0605, "step": 422 }, { "epoch": 2.84, "learning_rate": 8.644295302013423e-06, "loss": 2.0684, "step": 423 }, { "epoch": 2.85, "learning_rate": 8.617449664429531e-06, "loss": 2.0508, "step": 424 }, { "epoch": 2.85, "learning_rate": 8.590604026845638e-06, "loss": 2.0703, "step": 425 }, { "epoch": 2.86, "learning_rate": 8.563758389261746e-06, "loss": 2.0488, "step": 426 }, { "epoch": 2.87, "learning_rate": 8.536912751677853e-06, "loss": 2.0381, "step": 427 }, { "epoch": 2.87, "learning_rate": 8.51006711409396e-06, "loss": 2.04, "step": 428 }, { "epoch": 2.88, "learning_rate": 8.483221476510068e-06, "loss": 2.0566, "step": 429 }, { "epoch": 2.89, "learning_rate": 8.456375838926175e-06, "loss": 2.0547, "step": 430 }, { "epoch": 2.89, "learning_rate": 8.429530201342283e-06, "loss": 2.0449, "step": 431 }, { "epoch": 2.9, "learning_rate": 8.40268456375839e-06, "loss": 2.0352, "step": 432 }, { "epoch": 2.91, "learning_rate": 8.375838926174498e-06, "loss": 2.0605, "step": 433 }, { "epoch": 2.91, "learning_rate": 8.348993288590605e-06, "loss": 2.0684, "step": 434 }, { "epoch": 2.92, "learning_rate": 8.322147651006712e-06, "loss": 2.0508, "step": 435 }, { "epoch": 2.93, "learning_rate": 8.29530201342282e-06, "loss": 2.0664, "step": 436 }, { "epoch": 2.93, "learning_rate": 8.268456375838927e-06, "loss": 2.04, "step": 437 }, { "epoch": 2.94, "learning_rate": 8.241610738255035e-06, "loss": 2.0371, "step": 438 }, { "epoch": 2.95, "learning_rate": 8.214765100671142e-06, "loss": 2.0361, "step": 439 }, { "epoch": 2.95, "learning_rate": 8.18791946308725e-06, "loss": 2.0645, "step": 440 }, { "epoch": 2.96, "learning_rate": 8.161073825503357e-06, "loss": 2.0527, "step": 441 }, { "epoch": 2.97, "learning_rate": 8.134228187919464e-06, "loss": 2.0518, "step": 442 }, { "epoch": 2.97, "learning_rate": 8.10738255033557e-06, "loss": 2.0508, "step": 443 }, { "epoch": 2.98, "learning_rate": 8.080536912751679e-06, "loss": 2.0566, "step": 444 }, { "epoch": 2.99, "learning_rate": 8.053691275167785e-06, "loss": 2.042, "step": 445 }, { "epoch": 2.99, "learning_rate": 8.026845637583894e-06, "loss": 2.0527, "step": 446 }, { "epoch": 3.0, "learning_rate": 8.000000000000001e-06, "loss": 2.0342, "step": 447 }, { "epoch": 3.01, "learning_rate": 7.973154362416107e-06, "loss": 2.0391, "step": 448 }, { "epoch": 3.01, "learning_rate": 7.946308724832216e-06, "loss": 2.0361, "step": 449 }, { "epoch": 3.02, "learning_rate": 7.919463087248322e-06, "loss": 2.0645, "step": 450 }, { "epoch": 3.03, "learning_rate": 7.892617449664431e-06, "loss": 2.041, "step": 451 }, { "epoch": 3.03, "learning_rate": 7.865771812080537e-06, "loss": 2.0312, "step": 452 }, { "epoch": 3.04, "learning_rate": 7.838926174496644e-06, "loss": 2.0371, "step": 453 }, { "epoch": 3.05, "learning_rate": 7.812080536912753e-06, "loss": 2.0566, "step": 454 }, { "epoch": 3.05, "learning_rate": 7.785234899328859e-06, "loss": 2.0273, "step": 455 }, { "epoch": 3.06, "learning_rate": 7.758389261744968e-06, "loss": 2.0352, "step": 456 }, { "epoch": 3.07, "learning_rate": 7.731543624161074e-06, "loss": 2.0361, "step": 457 }, { "epoch": 3.07, "learning_rate": 7.704697986577183e-06, "loss": 2.0146, "step": 458 }, { "epoch": 3.08, "learning_rate": 7.677852348993289e-06, "loss": 2.0547, "step": 459 }, { "epoch": 3.09, "learning_rate": 7.651006711409396e-06, "loss": 2.0439, "step": 460 }, { "epoch": 3.09, "learning_rate": 7.624161073825504e-06, "loss": 2.0361, "step": 461 }, { "epoch": 3.1, "learning_rate": 7.597315436241612e-06, "loss": 2.0527, "step": 462 }, { "epoch": 3.11, "learning_rate": 7.570469798657719e-06, "loss": 2.0508, "step": 463 }, { "epoch": 3.11, "learning_rate": 7.543624161073826e-06, "loss": 2.0547, "step": 464 }, { "epoch": 3.12, "learning_rate": 7.516778523489934e-06, "loss": 2.0566, "step": 465 }, { "epoch": 3.13, "learning_rate": 7.4899328859060405e-06, "loss": 2.0547, "step": 466 }, { "epoch": 3.13, "learning_rate": 7.463087248322149e-06, "loss": 2.0234, "step": 467 }, { "epoch": 3.14, "learning_rate": 7.436241610738255e-06, "loss": 2.043, "step": 468 }, { "epoch": 3.15, "learning_rate": 7.409395973154363e-06, "loss": 2.0371, "step": 469 }, { "epoch": 3.15, "learning_rate": 7.382550335570471e-06, "loss": 2.0352, "step": 470 }, { "epoch": 3.16, "learning_rate": 7.3557046979865775e-06, "loss": 2.043, "step": 471 }, { "epoch": 3.17, "learning_rate": 7.328859060402686e-06, "loss": 2.0537, "step": 472 }, { "epoch": 3.17, "learning_rate": 7.302013422818792e-06, "loss": 2.0449, "step": 473 }, { "epoch": 3.18, "learning_rate": 7.2751677852349e-06, "loss": 2.0273, "step": 474 }, { "epoch": 3.19, "learning_rate": 7.248322147651007e-06, "loss": 2.0322, "step": 475 }, { "epoch": 3.19, "learning_rate": 7.221476510067115e-06, "loss": 2.0381, "step": 476 }, { "epoch": 3.2, "learning_rate": 7.194630872483223e-06, "loss": 2.0381, "step": 477 }, { "epoch": 3.21, "learning_rate": 7.167785234899329e-06, "loss": 2.0439, "step": 478 }, { "epoch": 3.21, "learning_rate": 7.140939597315437e-06, "loss": 2.04, "step": 479 }, { "epoch": 3.22, "learning_rate": 7.114093959731544e-06, "loss": 2.0352, "step": 480 }, { "epoch": 3.23, "learning_rate": 7.087248322147652e-06, "loss": 2.04, "step": 481 }, { "epoch": 3.23, "learning_rate": 7.060402684563758e-06, "loss": 2.0117, "step": 482 }, { "epoch": 3.24, "learning_rate": 7.0335570469798665e-06, "loss": 2.0342, "step": 483 }, { "epoch": 3.25, "learning_rate": 7.006711409395974e-06, "loss": 2.0146, "step": 484 }, { "epoch": 3.26, "learning_rate": 6.979865771812081e-06, "loss": 2.0518, "step": 485 }, { "epoch": 3.26, "learning_rate": 6.953020134228189e-06, "loss": 2.0283, "step": 486 }, { "epoch": 3.27, "learning_rate": 6.926174496644295e-06, "loss": 2.0322, "step": 487 }, { "epoch": 3.28, "learning_rate": 6.8993288590604035e-06, "loss": 2.0508, "step": 488 }, { "epoch": 3.28, "learning_rate": 6.87248322147651e-06, "loss": 2.0264, "step": 489 }, { "epoch": 3.29, "learning_rate": 6.845637583892618e-06, "loss": 2.041, "step": 490 }, { "epoch": 3.3, "learning_rate": 6.818791946308725e-06, "loss": 2.0264, "step": 491 }, { "epoch": 3.3, "learning_rate": 6.791946308724832e-06, "loss": 2.0371, "step": 492 }, { "epoch": 3.31, "learning_rate": 6.765100671140941e-06, "loss": 2.0371, "step": 493 }, { "epoch": 3.32, "learning_rate": 6.738255033557047e-06, "loss": 2.042, "step": 494 }, { "epoch": 3.32, "learning_rate": 6.711409395973155e-06, "loss": 2.0107, "step": 495 }, { "epoch": 3.33, "learning_rate": 6.684563758389262e-06, "loss": 2.0176, "step": 496 }, { "epoch": 3.34, "learning_rate": 6.65771812080537e-06, "loss": 2.0273, "step": 497 }, { "epoch": 3.34, "learning_rate": 6.630872483221477e-06, "loss": 2.0469, "step": 498 }, { "epoch": 3.35, "learning_rate": 6.604026845637584e-06, "loss": 2.0205, "step": 499 }, { "epoch": 3.36, "learning_rate": 6.5771812080536925e-06, "loss": 2.0137, "step": 500 }, { "epoch": 3.36, "learning_rate": 6.550335570469799e-06, "loss": 2.0352, "step": 501 }, { "epoch": 3.37, "learning_rate": 6.523489932885907e-06, "loss": 2.0547, "step": 502 }, { "epoch": 3.38, "learning_rate": 6.496644295302014e-06, "loss": 2.0137, "step": 503 }, { "epoch": 3.38, "learning_rate": 6.469798657718121e-06, "loss": 2.0029, "step": 504 }, { "epoch": 3.39, "learning_rate": 6.442953020134229e-06, "loss": 2.0176, "step": 505 }, { "epoch": 3.4, "learning_rate": 6.416107382550336e-06, "loss": 2.0283, "step": 506 }, { "epoch": 3.4, "learning_rate": 6.389261744966444e-06, "loss": 2.0488, "step": 507 }, { "epoch": 3.41, "learning_rate": 6.362416107382551e-06, "loss": 2.0371, "step": 508 }, { "epoch": 3.42, "learning_rate": 6.335570469798658e-06, "loss": 2.0107, "step": 509 }, { "epoch": 3.42, "learning_rate": 6.308724832214766e-06, "loss": 2.0273, "step": 510 }, { "epoch": 3.43, "learning_rate": 6.281879194630873e-06, "loss": 2.0508, "step": 511 }, { "epoch": 3.44, "learning_rate": 6.25503355704698e-06, "loss": 2.0342, "step": 512 }, { "epoch": 3.44, "learning_rate": 6.228187919463088e-06, "loss": 2.0586, "step": 513 }, { "epoch": 3.45, "learning_rate": 6.2013422818791946e-06, "loss": 2.0107, "step": 514 }, { "epoch": 3.46, "learning_rate": 6.174496644295303e-06, "loss": 2.0547, "step": 515 }, { "epoch": 3.46, "learning_rate": 6.14765100671141e-06, "loss": 2.0273, "step": 516 }, { "epoch": 3.47, "learning_rate": 6.120805369127517e-06, "loss": 2.0371, "step": 517 }, { "epoch": 3.48, "learning_rate": 6.093959731543625e-06, "loss": 2.0098, "step": 518 }, { "epoch": 3.48, "learning_rate": 6.067114093959732e-06, "loss": 2.0293, "step": 519 }, { "epoch": 3.49, "learning_rate": 6.04026845637584e-06, "loss": 2.0186, "step": 520 }, { "epoch": 3.5, "learning_rate": 6.0134228187919464e-06, "loss": 2.0146, "step": 521 }, { "epoch": 3.5, "learning_rate": 5.986577181208054e-06, "loss": 2.0361, "step": 522 }, { "epoch": 3.51, "learning_rate": 5.959731543624162e-06, "loss": 2.0117, "step": 523 }, { "epoch": 3.52, "learning_rate": 5.932885906040269e-06, "loss": 2.0146, "step": 524 }, { "epoch": 3.52, "learning_rate": 5.906040268456377e-06, "loss": 2.0264, "step": 525 }, { "epoch": 3.53, "learning_rate": 5.8791946308724835e-06, "loss": 2.0264, "step": 526 }, { "epoch": 3.54, "learning_rate": 5.852348993288591e-06, "loss": 2.0439, "step": 527 }, { "epoch": 3.54, "learning_rate": 5.825503355704698e-06, "loss": 2.0283, "step": 528 }, { "epoch": 3.55, "learning_rate": 5.798657718120806e-06, "loss": 2.0264, "step": 529 }, { "epoch": 3.56, "learning_rate": 5.771812080536914e-06, "loss": 2.0273, "step": 530 }, { "epoch": 3.56, "learning_rate": 5.7449664429530206e-06, "loss": 2.0254, "step": 531 }, { "epoch": 3.57, "learning_rate": 5.718120805369128e-06, "loss": 2.0146, "step": 532 }, { "epoch": 3.58, "learning_rate": 5.691275167785235e-06, "loss": 2.0273, "step": 533 }, { "epoch": 3.58, "learning_rate": 5.664429530201343e-06, "loss": 2.0439, "step": 534 }, { "epoch": 3.59, "learning_rate": 5.637583892617449e-06, "loss": 2.0293, "step": 535 }, { "epoch": 3.6, "learning_rate": 5.610738255033558e-06, "loss": 2.0254, "step": 536 }, { "epoch": 3.6, "learning_rate": 5.583892617449664e-06, "loss": 2.0283, "step": 537 }, { "epoch": 3.61, "learning_rate": 5.5570469798657725e-06, "loss": 2.0088, "step": 538 }, { "epoch": 3.62, "learning_rate": 5.53020134228188e-06, "loss": 2.0166, "step": 539 }, { "epoch": 3.62, "learning_rate": 5.503355704697987e-06, "loss": 2.0283, "step": 540 }, { "epoch": 3.63, "learning_rate": 5.476510067114095e-06, "loss": 2.002, "step": 541 }, { "epoch": 3.64, "learning_rate": 5.449664429530201e-06, "loss": 2.0205, "step": 542 }, { "epoch": 3.64, "learning_rate": 5.4228187919463095e-06, "loss": 2.0234, "step": 543 }, { "epoch": 3.65, "learning_rate": 5.395973154362416e-06, "loss": 2.043, "step": 544 }, { "epoch": 3.66, "learning_rate": 5.369127516778524e-06, "loss": 2.0127, "step": 545 }, { "epoch": 3.66, "learning_rate": 5.342281879194632e-06, "loss": 2.041, "step": 546 }, { "epoch": 3.67, "learning_rate": 5.315436241610738e-06, "loss": 2.0322, "step": 547 }, { "epoch": 3.68, "learning_rate": 5.2885906040268466e-06, "loss": 2.0332, "step": 548 }, { "epoch": 3.68, "learning_rate": 5.261744966442953e-06, "loss": 2.0244, "step": 549 }, { "epoch": 3.69, "learning_rate": 5.234899328859061e-06, "loss": 2.0244, "step": 550 }, { "epoch": 3.7, "learning_rate": 5.208053691275168e-06, "loss": 2.0195, "step": 551 }, { "epoch": 3.7, "learning_rate": 5.181208053691275e-06, "loss": 2.0254, "step": 552 }, { "epoch": 3.71, "learning_rate": 5.154362416107384e-06, "loss": 2.04, "step": 553 }, { "epoch": 3.72, "learning_rate": 5.12751677852349e-06, "loss": 2.0244, "step": 554 }, { "epoch": 3.72, "learning_rate": 5.1006711409395985e-06, "loss": 1.9902, "step": 555 }, { "epoch": 3.73, "learning_rate": 5.073825503355705e-06, "loss": 2.0127, "step": 556 }, { "epoch": 3.74, "learning_rate": 5.0469798657718124e-06, "loss": 2.0039, "step": 557 }, { "epoch": 3.74, "learning_rate": 5.02013422818792e-06, "loss": 2.0225, "step": 558 }, { "epoch": 3.75, "learning_rate": 4.993288590604027e-06, "loss": 2.0176, "step": 559 }, { "epoch": 3.76, "learning_rate": 4.966442953020135e-06, "loss": 2.0107, "step": 560 }, { "epoch": 3.77, "learning_rate": 4.939597315436242e-06, "loss": 2.0273, "step": 561 }, { "epoch": 3.77, "learning_rate": 4.9127516778523495e-06, "loss": 2.0078, "step": 562 }, { "epoch": 3.78, "learning_rate": 4.885906040268457e-06, "loss": 2.0361, "step": 563 }, { "epoch": 3.79, "learning_rate": 4.859060402684564e-06, "loss": 2.0352, "step": 564 }, { "epoch": 3.79, "learning_rate": 4.832214765100672e-06, "loss": 2.0381, "step": 565 }, { "epoch": 3.8, "learning_rate": 4.805369127516779e-06, "loss": 2.0215, "step": 566 }, { "epoch": 3.81, "learning_rate": 4.7785234899328866e-06, "loss": 2.0195, "step": 567 }, { "epoch": 3.81, "learning_rate": 4.751677852348994e-06, "loss": 2.0107, "step": 568 }, { "epoch": 3.82, "learning_rate": 4.724832214765101e-06, "loss": 2.0039, "step": 569 }, { "epoch": 3.83, "learning_rate": 4.697986577181208e-06, "loss": 2.0186, "step": 570 }, { "epoch": 3.83, "learning_rate": 4.671140939597315e-06, "loss": 2.0234, "step": 571 }, { "epoch": 3.84, "learning_rate": 4.644295302013423e-06, "loss": 2.0234, "step": 572 }, { "epoch": 3.85, "learning_rate": 4.617449664429531e-06, "loss": 2.0039, "step": 573 }, { "epoch": 3.85, "learning_rate": 4.5906040268456384e-06, "loss": 2.0039, "step": 574 }, { "epoch": 3.86, "learning_rate": 4.563758389261745e-06, "loss": 2.0215, "step": 575 }, { "epoch": 3.87, "learning_rate": 4.536912751677852e-06, "loss": 2.0215, "step": 576 }, { "epoch": 3.87, "learning_rate": 4.51006711409396e-06, "loss": 2.0146, "step": 577 }, { "epoch": 3.88, "learning_rate": 4.483221476510067e-06, "loss": 2.0391, "step": 578 }, { "epoch": 3.89, "learning_rate": 4.456375838926175e-06, "loss": 2.0137, "step": 579 }, { "epoch": 3.89, "learning_rate": 4.429530201342283e-06, "loss": 2.0107, "step": 580 }, { "epoch": 3.9, "learning_rate": 4.4026845637583895e-06, "loss": 2.0176, "step": 581 }, { "epoch": 3.91, "learning_rate": 4.375838926174497e-06, "loss": 2.0273, "step": 582 }, { "epoch": 3.91, "learning_rate": 4.348993288590604e-06, "loss": 2.0098, "step": 583 }, { "epoch": 3.92, "learning_rate": 4.322147651006712e-06, "loss": 2.0215, "step": 584 }, { "epoch": 3.93, "learning_rate": 4.295302013422819e-06, "loss": 2.0107, "step": 585 }, { "epoch": 3.93, "learning_rate": 4.2684563758389265e-06, "loss": 2.0293, "step": 586 }, { "epoch": 3.94, "learning_rate": 4.241610738255034e-06, "loss": 2.0312, "step": 587 }, { "epoch": 3.95, "learning_rate": 4.214765100671141e-06, "loss": 2.0156, "step": 588 }, { "epoch": 3.95, "learning_rate": 4.187919463087249e-06, "loss": 1.9922, "step": 589 }, { "epoch": 3.96, "learning_rate": 4.161073825503356e-06, "loss": 2.0225, "step": 590 }, { "epoch": 3.97, "learning_rate": 4.134228187919464e-06, "loss": 2.0391, "step": 591 }, { "epoch": 3.97, "learning_rate": 4.107382550335571e-06, "loss": 2.0293, "step": 592 }, { "epoch": 3.98, "learning_rate": 4.0805369127516784e-06, "loss": 2.0166, "step": 593 }, { "epoch": 3.99, "learning_rate": 4.053691275167785e-06, "loss": 2.001, "step": 594 }, { "epoch": 3.99, "learning_rate": 4.026845637583892e-06, "loss": 2.0215, "step": 595 }, { "epoch": 4.0, "learning_rate": 4.000000000000001e-06, "loss": 2.0166, "step": 596 }, { "epoch": 4.01, "learning_rate": 3.973154362416108e-06, "loss": 2.0088, "step": 597 }, { "epoch": 4.01, "learning_rate": 3.9463087248322155e-06, "loss": 2.0156, "step": 598 }, { "epoch": 4.02, "learning_rate": 3.919463087248322e-06, "loss": 2.0332, "step": 599 }, { "epoch": 4.03, "learning_rate": 3.8926174496644295e-06, "loss": 1.9951, "step": 600 }, { "epoch": 4.03, "learning_rate": 3.865771812080537e-06, "loss": 2.0215, "step": 601 }, { "epoch": 4.04, "learning_rate": 3.838926174496644e-06, "loss": 2.0146, "step": 602 }, { "epoch": 4.05, "learning_rate": 3.812080536912752e-06, "loss": 2.0332, "step": 603 }, { "epoch": 4.05, "learning_rate": 3.7852348993288595e-06, "loss": 2.0449, "step": 604 }, { "epoch": 4.06, "learning_rate": 3.758389261744967e-06, "loss": 2.0225, "step": 605 }, { "epoch": 4.07, "learning_rate": 3.7315436241610744e-06, "loss": 2.001, "step": 606 }, { "epoch": 4.07, "learning_rate": 3.7046979865771814e-06, "loss": 2.0146, "step": 607 }, { "epoch": 4.08, "learning_rate": 3.6778523489932888e-06, "loss": 1.9932, "step": 608 }, { "epoch": 4.09, "learning_rate": 3.651006711409396e-06, "loss": 2.0029, "step": 609 }, { "epoch": 4.09, "learning_rate": 3.6241610738255036e-06, "loss": 2.0029, "step": 610 }, { "epoch": 4.1, "learning_rate": 3.5973154362416114e-06, "loss": 2.0186, "step": 611 }, { "epoch": 4.11, "learning_rate": 3.5704697986577184e-06, "loss": 2.0117, "step": 612 }, { "epoch": 4.11, "learning_rate": 3.543624161073826e-06, "loss": 2.0186, "step": 613 }, { "epoch": 4.12, "learning_rate": 3.5167785234899332e-06, "loss": 1.999, "step": 614 }, { "epoch": 4.13, "learning_rate": 3.4899328859060407e-06, "loss": 2.0312, "step": 615 }, { "epoch": 4.13, "learning_rate": 3.4630872483221476e-06, "loss": 2.0234, "step": 616 }, { "epoch": 4.14, "learning_rate": 3.436241610738255e-06, "loss": 2.0225, "step": 617 }, { "epoch": 4.15, "learning_rate": 3.4093959731543625e-06, "loss": 2.0322, "step": 618 }, { "epoch": 4.15, "learning_rate": 3.3825503355704703e-06, "loss": 2.0186, "step": 619 }, { "epoch": 4.16, "learning_rate": 3.3557046979865777e-06, "loss": 2.001, "step": 620 }, { "epoch": 4.17, "learning_rate": 3.328859060402685e-06, "loss": 1.9971, "step": 621 }, { "epoch": 4.17, "learning_rate": 3.302013422818792e-06, "loss": 2.0117, "step": 622 }, { "epoch": 4.18, "learning_rate": 3.2751677852348995e-06, "loss": 1.9941, "step": 623 }, { "epoch": 4.19, "learning_rate": 3.248322147651007e-06, "loss": 2.0127, "step": 624 }, { "epoch": 4.19, "learning_rate": 3.2214765100671143e-06, "loss": 1.9932, "step": 625 }, { "epoch": 4.2, "learning_rate": 3.194630872483222e-06, "loss": 1.9932, "step": 626 }, { "epoch": 4.21, "learning_rate": 3.167785234899329e-06, "loss": 2.0059, "step": 627 }, { "epoch": 4.21, "learning_rate": 3.1409395973154366e-06, "loss": 1.9932, "step": 628 }, { "epoch": 4.22, "learning_rate": 3.114093959731544e-06, "loss": 2.0293, "step": 629 }, { "epoch": 4.23, "learning_rate": 3.0872483221476514e-06, "loss": 2.0, "step": 630 }, { "epoch": 4.23, "learning_rate": 3.0604026845637584e-06, "loss": 2.0156, "step": 631 }, { "epoch": 4.24, "learning_rate": 3.033557046979866e-06, "loss": 2.0303, "step": 632 }, { "epoch": 4.25, "learning_rate": 3.0067114093959732e-06, "loss": 2.0186, "step": 633 }, { "epoch": 4.26, "learning_rate": 2.979865771812081e-06, "loss": 2.0068, "step": 634 }, { "epoch": 4.26, "learning_rate": 2.9530201342281885e-06, "loss": 2.0381, "step": 635 }, { "epoch": 4.27, "learning_rate": 2.9261744966442955e-06, "loss": 2.0088, "step": 636 }, { "epoch": 4.28, "learning_rate": 2.899328859060403e-06, "loss": 1.9971, "step": 637 }, { "epoch": 4.28, "learning_rate": 2.8724832214765103e-06, "loss": 2.0293, "step": 638 }, { "epoch": 4.29, "learning_rate": 2.8456375838926177e-06, "loss": 1.9961, "step": 639 }, { "epoch": 4.3, "learning_rate": 2.8187919463087247e-06, "loss": 2.0117, "step": 640 }, { "epoch": 4.3, "learning_rate": 2.791946308724832e-06, "loss": 2.0068, "step": 641 }, { "epoch": 4.31, "learning_rate": 2.76510067114094e-06, "loss": 2.002, "step": 642 }, { "epoch": 4.32, "learning_rate": 2.7382550335570473e-06, "loss": 2.001, "step": 643 }, { "epoch": 4.32, "learning_rate": 2.7114093959731548e-06, "loss": 1.998, "step": 644 }, { "epoch": 4.33, "learning_rate": 2.684563758389262e-06, "loss": 2.0156, "step": 645 }, { "epoch": 4.34, "learning_rate": 2.657718120805369e-06, "loss": 2.0322, "step": 646 }, { "epoch": 4.34, "learning_rate": 2.6308724832214766e-06, "loss": 2.0156, "step": 647 }, { "epoch": 4.35, "learning_rate": 2.604026845637584e-06, "loss": 2.001, "step": 648 }, { "epoch": 4.36, "learning_rate": 2.577181208053692e-06, "loss": 1.9922, "step": 649 }, { "epoch": 4.36, "learning_rate": 2.5503355704697992e-06, "loss": 1.9883, "step": 650 }, { "epoch": 4.37, "learning_rate": 2.5234899328859062e-06, "loss": 2.0176, "step": 651 }, { "epoch": 4.38, "learning_rate": 2.4966442953020136e-06, "loss": 2.0039, "step": 652 }, { "epoch": 4.38, "learning_rate": 2.469798657718121e-06, "loss": 1.9961, "step": 653 }, { "epoch": 4.39, "learning_rate": 2.4429530201342285e-06, "loss": 2.002, "step": 654 }, { "epoch": 4.4, "learning_rate": 2.416107382550336e-06, "loss": 2.0205, "step": 655 }, { "epoch": 4.4, "learning_rate": 2.3892617449664433e-06, "loss": 1.9971, "step": 656 }, { "epoch": 4.41, "learning_rate": 2.3624161073825507e-06, "loss": 2.0088, "step": 657 }, { "epoch": 4.42, "learning_rate": 2.3355704697986577e-06, "loss": 2.0254, "step": 658 }, { "epoch": 4.42, "learning_rate": 2.3087248322147655e-06, "loss": 2.0117, "step": 659 }, { "epoch": 4.43, "learning_rate": 2.2818791946308725e-06, "loss": 1.9961, "step": 660 }, { "epoch": 4.44, "learning_rate": 2.25503355704698e-06, "loss": 2.0059, "step": 661 }, { "epoch": 4.44, "learning_rate": 2.2281879194630873e-06, "loss": 2.0029, "step": 662 }, { "epoch": 4.45, "learning_rate": 2.2013422818791947e-06, "loss": 2.0098, "step": 663 }, { "epoch": 4.46, "learning_rate": 2.174496644295302e-06, "loss": 2.0254, "step": 664 }, { "epoch": 4.46, "learning_rate": 2.1476510067114096e-06, "loss": 2.0107, "step": 665 }, { "epoch": 4.47, "learning_rate": 2.120805369127517e-06, "loss": 2.0059, "step": 666 }, { "epoch": 4.48, "learning_rate": 2.0939597315436244e-06, "loss": 2.0107, "step": 667 }, { "epoch": 4.48, "learning_rate": 2.067114093959732e-06, "loss": 1.9922, "step": 668 }, { "epoch": 4.49, "learning_rate": 2.0402684563758392e-06, "loss": 2.0137, "step": 669 }, { "epoch": 4.5, "learning_rate": 2.013422818791946e-06, "loss": 1.9912, "step": 670 }, { "epoch": 4.5, "learning_rate": 1.986577181208054e-06, "loss": 2.0146, "step": 671 }, { "epoch": 4.51, "learning_rate": 1.959731543624161e-06, "loss": 2.0039, "step": 672 }, { "epoch": 4.52, "learning_rate": 1.9328859060402684e-06, "loss": 1.9961, "step": 673 }, { "epoch": 4.52, "learning_rate": 1.906040268456376e-06, "loss": 2.0254, "step": 674 }, { "epoch": 4.53, "learning_rate": 1.8791946308724835e-06, "loss": 2.0156, "step": 675 }, { "epoch": 4.54, "learning_rate": 1.8523489932885907e-06, "loss": 2.001, "step": 676 }, { "epoch": 4.54, "learning_rate": 1.825503355704698e-06, "loss": 2.0029, "step": 677 }, { "epoch": 4.55, "learning_rate": 1.7986577181208057e-06, "loss": 2.0068, "step": 678 }, { "epoch": 4.56, "learning_rate": 1.771812080536913e-06, "loss": 2.0234, "step": 679 }, { "epoch": 4.56, "learning_rate": 1.7449664429530203e-06, "loss": 1.9824, "step": 680 }, { "epoch": 4.57, "learning_rate": 1.7181208053691275e-06, "loss": 2.0049, "step": 681 }, { "epoch": 4.58, "learning_rate": 1.6912751677852351e-06, "loss": 2.0029, "step": 682 }, { "epoch": 4.58, "learning_rate": 1.6644295302013426e-06, "loss": 2.0205, "step": 683 }, { "epoch": 4.59, "learning_rate": 1.6375838926174498e-06, "loss": 2.0029, "step": 684 }, { "epoch": 4.6, "learning_rate": 1.6107382550335572e-06, "loss": 2.0166, "step": 685 }, { "epoch": 4.6, "learning_rate": 1.5838926174496646e-06, "loss": 2.0059, "step": 686 }, { "epoch": 4.61, "learning_rate": 1.557046979865772e-06, "loss": 2.0186, "step": 687 }, { "epoch": 4.62, "learning_rate": 1.5302013422818792e-06, "loss": 2.0088, "step": 688 }, { "epoch": 4.62, "learning_rate": 1.5033557046979866e-06, "loss": 1.9961, "step": 689 }, { "epoch": 4.63, "learning_rate": 1.4765100671140942e-06, "loss": 2.0107, "step": 690 }, { "epoch": 4.64, "learning_rate": 1.4496644295302014e-06, "loss": 2.0234, "step": 691 }, { "epoch": 4.64, "learning_rate": 1.4228187919463088e-06, "loss": 2.0098, "step": 692 }, { "epoch": 4.65, "learning_rate": 1.395973154362416e-06, "loss": 2.0234, "step": 693 }, { "epoch": 4.66, "learning_rate": 1.3691275167785237e-06, "loss": 2.0254, "step": 694 }, { "epoch": 4.66, "learning_rate": 1.342281879194631e-06, "loss": 2.0029, "step": 695 }, { "epoch": 4.67, "learning_rate": 1.3154362416107383e-06, "loss": 2.0146, "step": 696 }, { "epoch": 4.68, "learning_rate": 1.288590604026846e-06, "loss": 2.0, "step": 697 }, { "epoch": 4.68, "learning_rate": 1.2617449664429531e-06, "loss": 2.0098, "step": 698 }, { "epoch": 4.69, "learning_rate": 1.2348993288590605e-06, "loss": 2.0293, "step": 699 }, { "epoch": 4.7, "learning_rate": 1.208053691275168e-06, "loss": 2.0059, "step": 700 }, { "epoch": 4.7, "learning_rate": 1.1812080536912753e-06, "loss": 1.9971, "step": 701 }, { "epoch": 4.71, "learning_rate": 1.1543624161073828e-06, "loss": 2.0303, "step": 702 }, { "epoch": 4.72, "learning_rate": 1.12751677852349e-06, "loss": 2.0088, "step": 703 }, { "epoch": 4.72, "learning_rate": 1.1006711409395974e-06, "loss": 2.0068, "step": 704 }, { "epoch": 4.73, "learning_rate": 1.0738255033557048e-06, "loss": 1.9951, "step": 705 }, { "epoch": 4.74, "learning_rate": 1.0469798657718122e-06, "loss": 2.0264, "step": 706 }, { "epoch": 4.74, "learning_rate": 1.0201342281879196e-06, "loss": 1.9951, "step": 707 }, { "epoch": 4.75, "learning_rate": 9.93288590604027e-07, "loss": 1.999, "step": 708 }, { "epoch": 4.76, "learning_rate": 9.664429530201342e-07, "loss": 2.0, "step": 709 }, { "epoch": 4.77, "learning_rate": 9.395973154362417e-07, "loss": 2.002, "step": 710 }, { "epoch": 4.77, "learning_rate": 9.12751677852349e-07, "loss": 2.0156, "step": 711 }, { "epoch": 4.78, "learning_rate": 8.859060402684565e-07, "loss": 2.0117, "step": 712 }, { "epoch": 4.79, "learning_rate": 8.590604026845638e-07, "loss": 1.9902, "step": 713 }, { "epoch": 4.79, "learning_rate": 8.322147651006713e-07, "loss": 1.9932, "step": 714 }, { "epoch": 4.8, "learning_rate": 8.053691275167786e-07, "loss": 2.001, "step": 715 }, { "epoch": 4.81, "learning_rate": 7.78523489932886e-07, "loss": 2.0059, "step": 716 }, { "epoch": 4.81, "learning_rate": 7.516778523489933e-07, "loss": 2.0078, "step": 717 }, { "epoch": 4.82, "learning_rate": 7.248322147651007e-07, "loss": 2.0049, "step": 718 }, { "epoch": 4.83, "learning_rate": 6.97986577181208e-07, "loss": 2.002, "step": 719 }, { "epoch": 4.83, "learning_rate": 6.711409395973155e-07, "loss": 2.0117, "step": 720 }, { "epoch": 4.84, "learning_rate": 6.44295302013423e-07, "loss": 1.9932, "step": 721 }, { "epoch": 4.85, "learning_rate": 6.174496644295303e-07, "loss": 1.998, "step": 722 }, { "epoch": 4.85, "learning_rate": 5.906040268456377e-07, "loss": 2.0146, "step": 723 }, { "epoch": 4.86, "learning_rate": 5.63758389261745e-07, "loss": 2.0049, "step": 724 }, { "epoch": 4.87, "learning_rate": 5.369127516778524e-07, "loss": 1.999, "step": 725 }, { "epoch": 4.87, "learning_rate": 5.100671140939598e-07, "loss": 2.0176, "step": 726 }, { "epoch": 4.88, "learning_rate": 4.832214765100671e-07, "loss": 2.0098, "step": 727 }, { "epoch": 4.89, "learning_rate": 4.563758389261745e-07, "loss": 2.0068, "step": 728 }, { "epoch": 4.89, "learning_rate": 4.295302013422819e-07, "loss": 2.0303, "step": 729 }, { "epoch": 4.9, "learning_rate": 4.026845637583893e-07, "loss": 2.0137, "step": 730 }, { "epoch": 4.91, "learning_rate": 3.7583892617449665e-07, "loss": 2.0098, "step": 731 }, { "epoch": 4.91, "learning_rate": 3.48993288590604e-07, "loss": 2.0244, "step": 732 }, { "epoch": 4.92, "learning_rate": 3.221476510067115e-07, "loss": 1.9922, "step": 733 }, { "epoch": 4.93, "learning_rate": 2.9530201342281884e-07, "loss": 1.998, "step": 734 }, { "epoch": 4.93, "learning_rate": 2.684563758389262e-07, "loss": 1.9961, "step": 735 }, { "epoch": 4.94, "learning_rate": 2.4161073825503355e-07, "loss": 1.9951, "step": 736 }, { "epoch": 4.95, "learning_rate": 2.1476510067114094e-07, "loss": 2.0117, "step": 737 }, { "epoch": 4.95, "learning_rate": 1.8791946308724833e-07, "loss": 2.0049, "step": 738 }, { "epoch": 4.96, "learning_rate": 1.6107382550335574e-07, "loss": 2.0146, "step": 739 }, { "epoch": 4.97, "learning_rate": 1.342281879194631e-07, "loss": 2.0303, "step": 740 }, { "epoch": 4.97, "learning_rate": 1.0738255033557047e-07, "loss": 2.0078, "step": 741 }, { "epoch": 4.98, "learning_rate": 8.053691275167787e-08, "loss": 2.0039, "step": 742 }, { "epoch": 4.99, "learning_rate": 5.3691275167785235e-08, "loss": 1.998, "step": 743 }, { "epoch": 4.99, "learning_rate": 2.6845637583892618e-08, "loss": 2.0186, "step": 744 }, { "epoch": 5.0, "learning_rate": 0.0, "loss": 1.9941, "step": 745 }, { "epoch": 5.0, "step": 745, "total_flos": 1.4940678387662848e+17, "train_loss": 2.1389746749161076, "train_runtime": 581.9582, "train_samples_per_second": 655.013, "train_steps_per_second": 1.28 } ], "max_steps": 745, "num_train_epochs": 5, "total_flos": 1.4940678387662848e+17, "trial_name": null, "trial_params": null }