{ "best_metric": null, "best_model_checkpoint": null, "epoch": 12.0, "global_step": 3480, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 1.904761904761905e-07, "loss": 2.6677, "step": 1 }, { "epoch": 0.01, "learning_rate": 3.80952380952381e-07, "loss": 2.6284, "step": 2 }, { "epoch": 0.01, "learning_rate": 5.714285714285715e-07, "loss": 2.5856, "step": 3 }, { "epoch": 0.01, "learning_rate": 7.61904761904762e-07, "loss": 2.5541, "step": 4 }, { "epoch": 0.02, "learning_rate": 9.523809523809525e-07, "loss": 2.5865, "step": 5 }, { "epoch": 0.02, "learning_rate": 1.142857142857143e-06, "loss": 2.632, "step": 6 }, { "epoch": 0.02, "learning_rate": 1.3333333333333334e-06, "loss": 2.4835, "step": 7 }, { "epoch": 0.03, "learning_rate": 1.523809523809524e-06, "loss": 2.401, "step": 8 }, { "epoch": 0.03, "learning_rate": 1.7142857142857145e-06, "loss": 2.1792, "step": 9 }, { "epoch": 0.03, "learning_rate": 1.904761904761905e-06, "loss": 2.1515, "step": 10 }, { "epoch": 0.04, "learning_rate": 2.0952380952380955e-06, "loss": 1.88, "step": 11 }, { "epoch": 0.04, "learning_rate": 2.285714285714286e-06, "loss": 1.819, "step": 12 }, { "epoch": 0.04, "learning_rate": 2.4761904761904764e-06, "loss": 1.8622, "step": 13 }, { "epoch": 0.05, "learning_rate": 2.666666666666667e-06, "loss": 1.7666, "step": 14 }, { "epoch": 0.05, "learning_rate": 2.8571428571428573e-06, "loss": 1.6463, "step": 15 }, { "epoch": 0.06, "learning_rate": 3.047619047619048e-06, "loss": 1.6241, "step": 16 }, { "epoch": 0.06, "learning_rate": 3.2380952380952385e-06, "loss": 1.6968, "step": 17 }, { "epoch": 0.06, "learning_rate": 3.428571428571429e-06, "loss": 1.827, "step": 18 }, { "epoch": 0.07, "learning_rate": 3.6190476190476194e-06, "loss": 1.7846, "step": 19 }, { "epoch": 0.07, "learning_rate": 3.80952380952381e-06, "loss": 1.5993, "step": 20 }, { "epoch": 0.07, "learning_rate": 4.000000000000001e-06, "loss": 1.6619, "step": 21 }, { "epoch": 0.08, "learning_rate": 4.190476190476191e-06, "loss": 1.5851, "step": 22 }, { "epoch": 0.08, "learning_rate": 4.3809523809523815e-06, "loss": 1.5793, "step": 23 }, { "epoch": 0.08, "learning_rate": 4.571428571428572e-06, "loss": 1.6287, "step": 24 }, { "epoch": 0.09, "learning_rate": 4.761904761904762e-06, "loss": 1.5258, "step": 25 }, { "epoch": 0.09, "learning_rate": 4.952380952380953e-06, "loss": 1.4903, "step": 26 }, { "epoch": 0.09, "learning_rate": 5.142857142857142e-06, "loss": 1.4062, "step": 27 }, { "epoch": 0.1, "learning_rate": 5.333333333333334e-06, "loss": 1.5041, "step": 28 }, { "epoch": 0.1, "learning_rate": 5.523809523809525e-06, "loss": 1.6663, "step": 29 }, { "epoch": 0.1, "learning_rate": 5.7142857142857145e-06, "loss": 1.4352, "step": 30 }, { "epoch": 0.11, "learning_rate": 5.904761904761905e-06, "loss": 1.6159, "step": 31 }, { "epoch": 0.11, "learning_rate": 6.095238095238096e-06, "loss": 1.4788, "step": 32 }, { "epoch": 0.11, "learning_rate": 6.285714285714286e-06, "loss": 1.7855, "step": 33 }, { "epoch": 0.12, "learning_rate": 6.476190476190477e-06, "loss": 1.5745, "step": 34 }, { "epoch": 0.12, "learning_rate": 6.666666666666667e-06, "loss": 1.3839, "step": 35 }, { "epoch": 0.12, "learning_rate": 6.857142857142858e-06, "loss": 1.5843, "step": 36 }, { "epoch": 0.13, "learning_rate": 7.047619047619048e-06, "loss": 1.5361, "step": 37 }, { "epoch": 0.13, "learning_rate": 7.238095238095239e-06, "loss": 1.5176, "step": 38 }, { "epoch": 0.13, "learning_rate": 7.428571428571429e-06, "loss": 1.3972, "step": 39 }, { "epoch": 0.14, "learning_rate": 7.61904761904762e-06, "loss": 1.4516, "step": 40 }, { "epoch": 0.14, "learning_rate": 7.809523809523811e-06, "loss": 1.4685, "step": 41 }, { "epoch": 0.14, "learning_rate": 8.000000000000001e-06, "loss": 1.4953, "step": 42 }, { "epoch": 0.15, "learning_rate": 8.190476190476192e-06, "loss": 1.4643, "step": 43 }, { "epoch": 0.15, "learning_rate": 8.380952380952382e-06, "loss": 1.5037, "step": 44 }, { "epoch": 0.16, "learning_rate": 8.571428571428571e-06, "loss": 1.4227, "step": 45 }, { "epoch": 0.16, "learning_rate": 8.761904761904763e-06, "loss": 1.2973, "step": 46 }, { "epoch": 0.16, "learning_rate": 8.952380952380953e-06, "loss": 1.4621, "step": 47 }, { "epoch": 0.17, "learning_rate": 9.142857142857144e-06, "loss": 1.3477, "step": 48 }, { "epoch": 0.17, "learning_rate": 9.333333333333334e-06, "loss": 1.3225, "step": 49 }, { "epoch": 0.17, "learning_rate": 9.523809523809525e-06, "loss": 1.3506, "step": 50 }, { "epoch": 0.18, "learning_rate": 9.714285714285715e-06, "loss": 1.3848, "step": 51 }, { "epoch": 0.18, "learning_rate": 9.904761904761906e-06, "loss": 1.2545, "step": 52 }, { "epoch": 0.18, "learning_rate": 1.0095238095238096e-05, "loss": 1.3143, "step": 53 }, { "epoch": 0.19, "learning_rate": 1.0285714285714285e-05, "loss": 1.5702, "step": 54 }, { "epoch": 0.19, "learning_rate": 1.0476190476190477e-05, "loss": 1.4382, "step": 55 }, { "epoch": 0.19, "learning_rate": 1.0666666666666667e-05, "loss": 1.4677, "step": 56 }, { "epoch": 0.2, "learning_rate": 1.0857142857142858e-05, "loss": 1.3729, "step": 57 }, { "epoch": 0.2, "learning_rate": 1.104761904761905e-05, "loss": 1.3802, "step": 58 }, { "epoch": 0.2, "learning_rate": 1.1238095238095239e-05, "loss": 1.3365, "step": 59 }, { "epoch": 0.21, "learning_rate": 1.1428571428571429e-05, "loss": 1.3134, "step": 60 }, { "epoch": 0.21, "learning_rate": 1.1619047619047621e-05, "loss": 1.394, "step": 61 }, { "epoch": 0.21, "learning_rate": 1.180952380952381e-05, "loss": 1.2911, "step": 62 }, { "epoch": 0.22, "learning_rate": 1.2e-05, "loss": 1.3986, "step": 63 }, { "epoch": 0.22, "learning_rate": 1.2190476190476192e-05, "loss": 1.3676, "step": 64 }, { "epoch": 0.22, "learning_rate": 1.2380952380952383e-05, "loss": 1.4231, "step": 65 }, { "epoch": 0.23, "learning_rate": 1.2571428571428572e-05, "loss": 1.1589, "step": 66 }, { "epoch": 0.23, "learning_rate": 1.2761904761904762e-05, "loss": 1.5108, "step": 67 }, { "epoch": 0.23, "learning_rate": 1.2952380952380954e-05, "loss": 1.3699, "step": 68 }, { "epoch": 0.24, "learning_rate": 1.3142857142857145e-05, "loss": 1.1858, "step": 69 }, { "epoch": 0.24, "learning_rate": 1.3333333333333333e-05, "loss": 1.4158, "step": 70 }, { "epoch": 0.24, "learning_rate": 1.3523809523809525e-05, "loss": 1.1927, "step": 71 }, { "epoch": 0.25, "learning_rate": 1.3714285714285716e-05, "loss": 1.2916, "step": 72 }, { "epoch": 0.25, "learning_rate": 1.3904761904761905e-05, "loss": 1.367, "step": 73 }, { "epoch": 0.26, "learning_rate": 1.4095238095238097e-05, "loss": 1.3799, "step": 74 }, { "epoch": 0.26, "learning_rate": 1.4285714285714287e-05, "loss": 1.342, "step": 75 }, { "epoch": 0.26, "learning_rate": 1.4476190476190478e-05, "loss": 1.3428, "step": 76 }, { "epoch": 0.27, "learning_rate": 1.4666666666666666e-05, "loss": 1.3155, "step": 77 }, { "epoch": 0.27, "learning_rate": 1.4857142857142858e-05, "loss": 1.3361, "step": 78 }, { "epoch": 0.27, "learning_rate": 1.5047619047619049e-05, "loss": 1.2827, "step": 79 }, { "epoch": 0.28, "learning_rate": 1.523809523809524e-05, "loss": 1.3093, "step": 80 }, { "epoch": 0.28, "learning_rate": 1.542857142857143e-05, "loss": 1.3409, "step": 81 }, { "epoch": 0.28, "learning_rate": 1.5619047619047622e-05, "loss": 1.3673, "step": 82 }, { "epoch": 0.29, "learning_rate": 1.580952380952381e-05, "loss": 1.4359, "step": 83 }, { "epoch": 0.29, "learning_rate": 1.6000000000000003e-05, "loss": 1.2387, "step": 84 }, { "epoch": 0.29, "learning_rate": 1.6190476190476193e-05, "loss": 1.4272, "step": 85 }, { "epoch": 0.3, "learning_rate": 1.6380952380952384e-05, "loss": 1.4308, "step": 86 }, { "epoch": 0.3, "learning_rate": 1.6571428571428574e-05, "loss": 1.4227, "step": 87 }, { "epoch": 0.3, "learning_rate": 1.6761904761904764e-05, "loss": 1.3882, "step": 88 }, { "epoch": 0.31, "learning_rate": 1.6952380952380955e-05, "loss": 1.2234, "step": 89 }, { "epoch": 0.31, "learning_rate": 1.7142857142857142e-05, "loss": 1.3993, "step": 90 }, { "epoch": 0.31, "learning_rate": 1.7333333333333336e-05, "loss": 1.2739, "step": 91 }, { "epoch": 0.32, "learning_rate": 1.7523809523809526e-05, "loss": 1.2929, "step": 92 }, { "epoch": 0.32, "learning_rate": 1.7714285714285717e-05, "loss": 1.3247, "step": 93 }, { "epoch": 0.32, "learning_rate": 1.7904761904761907e-05, "loss": 1.3627, "step": 94 }, { "epoch": 0.33, "learning_rate": 1.8095238095238097e-05, "loss": 1.2955, "step": 95 }, { "epoch": 0.33, "learning_rate": 1.8285714285714288e-05, "loss": 1.3403, "step": 96 }, { "epoch": 0.33, "learning_rate": 1.8476190476190478e-05, "loss": 1.3244, "step": 97 }, { "epoch": 0.34, "learning_rate": 1.866666666666667e-05, "loss": 1.2245, "step": 98 }, { "epoch": 0.34, "learning_rate": 1.885714285714286e-05, "loss": 1.3188, "step": 99 }, { "epoch": 0.34, "learning_rate": 1.904761904761905e-05, "loss": 1.3082, "step": 100 }, { "epoch": 0.35, "learning_rate": 1.923809523809524e-05, "loss": 1.2401, "step": 101 }, { "epoch": 0.35, "learning_rate": 1.942857142857143e-05, "loss": 1.2955, "step": 102 }, { "epoch": 0.36, "learning_rate": 1.961904761904762e-05, "loss": 1.3467, "step": 103 }, { "epoch": 0.36, "learning_rate": 1.980952380952381e-05, "loss": 1.2793, "step": 104 }, { "epoch": 0.36, "learning_rate": 2e-05, "loss": 1.282, "step": 105 }, { "epoch": 0.37, "learning_rate": 1.9999995667663676e-05, "loss": 1.2427, "step": 106 }, { "epoch": 0.37, "learning_rate": 1.9999982670658457e-05, "loss": 1.3705, "step": 107 }, { "epoch": 0.37, "learning_rate": 1.9999961008995607e-05, "loss": 1.2572, "step": 108 }, { "epoch": 0.38, "learning_rate": 1.9999930682693892e-05, "loss": 1.3193, "step": 109 }, { "epoch": 0.38, "learning_rate": 1.999989169177959e-05, "loss": 1.3349, "step": 110 }, { "epoch": 0.38, "learning_rate": 1.9999844036286483e-05, "loss": 1.307, "step": 111 }, { "epoch": 0.39, "learning_rate": 1.9999787716255867e-05, "loss": 1.3953, "step": 112 }, { "epoch": 0.39, "learning_rate": 1.999972273173654e-05, "loss": 1.3307, "step": 113 }, { "epoch": 0.39, "learning_rate": 1.9999649082784807e-05, "loss": 1.3176, "step": 114 }, { "epoch": 0.4, "learning_rate": 1.9999566769464483e-05, "loss": 1.3142, "step": 115 }, { "epoch": 0.4, "learning_rate": 1.9999475791846896e-05, "loss": 1.2715, "step": 116 }, { "epoch": 0.4, "learning_rate": 1.9999376150010868e-05, "loss": 1.3684, "step": 117 }, { "epoch": 0.41, "learning_rate": 1.9999267844042734e-05, "loss": 1.2952, "step": 118 }, { "epoch": 0.41, "learning_rate": 1.9999150874036344e-05, "loss": 1.0749, "step": 119 }, { "epoch": 0.41, "learning_rate": 1.9999025240093045e-05, "loss": 1.1719, "step": 120 }, { "epoch": 0.42, "learning_rate": 1.9998890942321693e-05, "loss": 1.3597, "step": 121 }, { "epoch": 0.42, "learning_rate": 1.9998747980838655e-05, "loss": 1.2331, "step": 122 }, { "epoch": 0.42, "learning_rate": 1.9998596355767805e-05, "loss": 1.1528, "step": 123 }, { "epoch": 0.43, "learning_rate": 1.9998436067240518e-05, "loss": 1.3303, "step": 124 }, { "epoch": 0.43, "learning_rate": 1.999826711539568e-05, "loss": 1.3337, "step": 125 }, { "epoch": 0.43, "learning_rate": 1.999808950037968e-05, "loss": 1.1301, "step": 126 }, { "epoch": 0.44, "learning_rate": 1.9997903222346418e-05, "loss": 1.4194, "step": 127 }, { "epoch": 0.44, "learning_rate": 1.9997708281457293e-05, "loss": 1.3396, "step": 128 }, { "epoch": 0.44, "learning_rate": 1.9997504677881224e-05, "loss": 1.2695, "step": 129 }, { "epoch": 0.45, "learning_rate": 1.999729241179462e-05, "loss": 1.2832, "step": 130 }, { "epoch": 0.45, "learning_rate": 1.99970714833814e-05, "loss": 1.2267, "step": 131 }, { "epoch": 0.46, "learning_rate": 1.9996841892833e-05, "loss": 1.3401, "step": 132 }, { "epoch": 0.46, "learning_rate": 1.999660364034835e-05, "loss": 1.3008, "step": 133 }, { "epoch": 0.46, "learning_rate": 1.999635672613388e-05, "loss": 1.3397, "step": 134 }, { "epoch": 0.47, "learning_rate": 1.9996101150403543e-05, "loss": 1.2069, "step": 135 }, { "epoch": 0.47, "learning_rate": 1.9995836913378786e-05, "loss": 1.3959, "step": 136 }, { "epoch": 0.47, "learning_rate": 1.9995564015288555e-05, "loss": 1.3376, "step": 137 }, { "epoch": 0.48, "learning_rate": 1.9995282456369313e-05, "loss": 1.3011, "step": 138 }, { "epoch": 0.48, "learning_rate": 1.9994992236865017e-05, "loss": 1.4596, "step": 139 }, { "epoch": 0.48, "learning_rate": 1.999469335702714e-05, "loss": 1.2458, "step": 140 }, { "epoch": 0.49, "learning_rate": 1.9994385817114644e-05, "loss": 1.3178, "step": 141 }, { "epoch": 0.49, "learning_rate": 1.999406961739401e-05, "loss": 1.2166, "step": 142 }, { "epoch": 0.49, "learning_rate": 1.9993744758139203e-05, "loss": 1.4431, "step": 143 }, { "epoch": 0.5, "learning_rate": 1.9993411239631713e-05, "loss": 1.2514, "step": 144 }, { "epoch": 0.5, "learning_rate": 1.999306906216052e-05, "loss": 1.2483, "step": 145 }, { "epoch": 0.5, "learning_rate": 1.999271822602211e-05, "loss": 1.3231, "step": 146 }, { "epoch": 0.51, "learning_rate": 1.999235873152047e-05, "loss": 1.2121, "step": 147 }, { "epoch": 0.51, "learning_rate": 1.999199057896709e-05, "loss": 1.1671, "step": 148 }, { "epoch": 0.51, "learning_rate": 1.9991613768680965e-05, "loss": 1.2598, "step": 149 }, { "epoch": 0.52, "learning_rate": 1.9991228300988586e-05, "loss": 1.2223, "step": 150 }, { "epoch": 0.52, "learning_rate": 1.999083417622395e-05, "loss": 1.3249, "step": 151 }, { "epoch": 0.52, "learning_rate": 1.9990431394728547e-05, "loss": 1.4458, "step": 152 }, { "epoch": 0.53, "learning_rate": 1.9990019956851384e-05, "loss": 1.1747, "step": 153 }, { "epoch": 0.53, "learning_rate": 1.998959986294895e-05, "loss": 1.1985, "step": 154 }, { "epoch": 0.53, "learning_rate": 1.998917111338525e-05, "loss": 1.358, "step": 155 }, { "epoch": 0.54, "learning_rate": 1.9988733708531772e-05, "loss": 1.338, "step": 156 }, { "epoch": 0.54, "learning_rate": 1.9988287648767523e-05, "loss": 1.2886, "step": 157 }, { "epoch": 0.54, "learning_rate": 1.9987832934478992e-05, "loss": 1.2624, "step": 158 }, { "epoch": 0.55, "learning_rate": 1.998736956606018e-05, "loss": 1.1608, "step": 159 }, { "epoch": 0.55, "learning_rate": 1.998689754391257e-05, "loss": 1.3064, "step": 160 }, { "epoch": 0.56, "learning_rate": 1.9986416868445167e-05, "loss": 1.2455, "step": 161 }, { "epoch": 0.56, "learning_rate": 1.9985927540074453e-05, "loss": 1.1564, "step": 162 }, { "epoch": 0.56, "learning_rate": 1.998542955922442e-05, "loss": 1.3674, "step": 163 }, { "epoch": 0.57, "learning_rate": 1.9984922926326543e-05, "loss": 1.1626, "step": 164 }, { "epoch": 0.57, "learning_rate": 1.9984407641819812e-05, "loss": 1.2604, "step": 165 }, { "epoch": 0.57, "learning_rate": 1.99838837061507e-05, "loss": 1.301, "step": 166 }, { "epoch": 0.58, "learning_rate": 1.998335111977318e-05, "loss": 1.3197, "step": 167 }, { "epoch": 0.58, "learning_rate": 1.998280988314872e-05, "loss": 1.2998, "step": 168 }, { "epoch": 0.58, "learning_rate": 1.998225999674629e-05, "loss": 1.3085, "step": 169 }, { "epoch": 0.59, "learning_rate": 1.998170146104234e-05, "loss": 1.4856, "step": 170 }, { "epoch": 0.59, "learning_rate": 1.9981134276520828e-05, "loss": 1.2919, "step": 171 }, { "epoch": 0.59, "learning_rate": 1.99805584436732e-05, "loss": 1.2869, "step": 172 }, { "epoch": 0.6, "learning_rate": 1.9979973962998396e-05, "loss": 1.1668, "step": 173 }, { "epoch": 0.6, "learning_rate": 1.9979380835002846e-05, "loss": 1.2876, "step": 174 }, { "epoch": 0.6, "learning_rate": 1.9978779060200483e-05, "loss": 1.4127, "step": 175 }, { "epoch": 0.61, "learning_rate": 1.997816863911272e-05, "loss": 1.1729, "step": 176 }, { "epoch": 0.61, "learning_rate": 1.997754957226847e-05, "loss": 1.2415, "step": 177 }, { "epoch": 0.61, "learning_rate": 1.997692186020413e-05, "loss": 1.3111, "step": 178 }, { "epoch": 0.62, "learning_rate": 1.9976285503463593e-05, "loss": 1.3244, "step": 179 }, { "epoch": 0.62, "learning_rate": 1.9975640502598243e-05, "loss": 1.1277, "step": 180 }, { "epoch": 0.62, "learning_rate": 1.9974986858166954e-05, "loss": 1.2408, "step": 181 }, { "epoch": 0.63, "learning_rate": 1.9974324570736087e-05, "loss": 1.1875, "step": 182 }, { "epoch": 0.63, "learning_rate": 1.9973653640879486e-05, "loss": 1.2715, "step": 183 }, { "epoch": 0.63, "learning_rate": 1.9972974069178498e-05, "loss": 1.2486, "step": 184 }, { "epoch": 0.64, "learning_rate": 1.9972285856221944e-05, "loss": 1.1248, "step": 185 }, { "epoch": 0.64, "learning_rate": 1.997158900260614e-05, "loss": 1.3108, "step": 186 }, { "epoch": 0.64, "learning_rate": 1.997088350893489e-05, "loss": 1.3548, "step": 187 }, { "epoch": 0.65, "learning_rate": 1.9970169375819475e-05, "loss": 1.2499, "step": 188 }, { "epoch": 0.65, "learning_rate": 1.9969446603878673e-05, "loss": 1.2364, "step": 189 }, { "epoch": 0.66, "learning_rate": 1.9968715193738738e-05, "loss": 1.0131, "step": 190 }, { "epoch": 0.66, "learning_rate": 1.9967975146033417e-05, "loss": 1.3815, "step": 191 }, { "epoch": 0.66, "learning_rate": 1.9967226461403934e-05, "loss": 1.2856, "step": 192 }, { "epoch": 0.67, "learning_rate": 1.9966469140499e-05, "loss": 1.1579, "step": 193 }, { "epoch": 0.67, "learning_rate": 1.9965703183974813e-05, "loss": 1.2069, "step": 194 }, { "epoch": 0.67, "learning_rate": 1.9964928592495046e-05, "loss": 1.2146, "step": 195 }, { "epoch": 0.68, "learning_rate": 1.9964145366730854e-05, "loss": 1.0996, "step": 196 }, { "epoch": 0.68, "learning_rate": 1.9963353507360884e-05, "loss": 1.2706, "step": 197 }, { "epoch": 0.68, "learning_rate": 1.996255301507125e-05, "loss": 1.2786, "step": 198 }, { "epoch": 0.69, "learning_rate": 1.9961743890555553e-05, "loss": 1.2, "step": 199 }, { "epoch": 0.69, "learning_rate": 1.9960926134514875e-05, "loss": 1.307, "step": 200 }, { "epoch": 0.69, "learning_rate": 1.9960099747657774e-05, "loss": 1.2274, "step": 201 }, { "epoch": 0.7, "learning_rate": 1.995926473070029e-05, "loss": 1.2593, "step": 202 }, { "epoch": 0.7, "learning_rate": 1.9958421084365928e-05, "loss": 1.0893, "step": 203 }, { "epoch": 0.7, "learning_rate": 1.9957568809385693e-05, "loss": 1.1677, "step": 204 }, { "epoch": 0.71, "learning_rate": 1.9956707906498046e-05, "loss": 1.2094, "step": 205 }, { "epoch": 0.71, "learning_rate": 1.9955838376448933e-05, "loss": 1.2178, "step": 206 }, { "epoch": 0.71, "learning_rate": 1.995496021999177e-05, "loss": 1.3003, "step": 207 }, { "epoch": 0.72, "learning_rate": 1.9954073437887457e-05, "loss": 1.109, "step": 208 }, { "epoch": 0.72, "learning_rate": 1.9953178030904357e-05, "loss": 1.1488, "step": 209 }, { "epoch": 0.72, "learning_rate": 1.9952273999818312e-05, "loss": 1.3261, "step": 210 }, { "epoch": 0.73, "learning_rate": 1.9951361345412636e-05, "loss": 1.2487, "step": 211 }, { "epoch": 0.73, "learning_rate": 1.9950440068478115e-05, "loss": 1.1897, "step": 212 }, { "epoch": 0.73, "learning_rate": 1.9949510169813006e-05, "loss": 1.2219, "step": 213 }, { "epoch": 0.74, "learning_rate": 1.9948571650223027e-05, "loss": 1.2271, "step": 214 }, { "epoch": 0.74, "learning_rate": 1.9947624510521385e-05, "loss": 1.2215, "step": 215 }, { "epoch": 0.74, "learning_rate": 1.9946668751528745e-05, "loss": 1.1, "step": 216 }, { "epoch": 0.75, "learning_rate": 1.994570437407323e-05, "loss": 1.22, "step": 217 }, { "epoch": 0.75, "learning_rate": 1.9944731378990452e-05, "loss": 1.2321, "step": 218 }, { "epoch": 0.76, "learning_rate": 1.994374976712348e-05, "loss": 1.1961, "step": 219 }, { "epoch": 0.76, "learning_rate": 1.9942759539322845e-05, "loss": 1.2253, "step": 220 }, { "epoch": 0.76, "learning_rate": 1.9941760696446546e-05, "loss": 1.1896, "step": 221 }, { "epoch": 0.77, "learning_rate": 1.9940753239360047e-05, "loss": 1.1826, "step": 222 }, { "epoch": 0.77, "learning_rate": 1.993973716893628e-05, "loss": 1.1959, "step": 223 }, { "epoch": 0.77, "learning_rate": 1.9938712486055632e-05, "loss": 1.1959, "step": 224 }, { "epoch": 0.78, "learning_rate": 1.9937679191605964e-05, "loss": 1.1937, "step": 225 }, { "epoch": 0.78, "learning_rate": 1.993663728648259e-05, "loss": 1.2367, "step": 226 }, { "epoch": 0.78, "learning_rate": 1.993558677158828e-05, "loss": 1.1979, "step": 227 }, { "epoch": 0.79, "learning_rate": 1.9934527647833276e-05, "loss": 1.1735, "step": 228 }, { "epoch": 0.79, "learning_rate": 1.9933459916135277e-05, "loss": 1.277, "step": 229 }, { "epoch": 0.79, "learning_rate": 1.9932383577419432e-05, "loss": 1.2691, "step": 230 }, { "epoch": 0.8, "learning_rate": 1.9931298632618355e-05, "loss": 1.2218, "step": 231 }, { "epoch": 0.8, "learning_rate": 1.9930205082672115e-05, "loss": 1.2659, "step": 232 }, { "epoch": 0.8, "learning_rate": 1.992910292852824e-05, "loss": 0.9988, "step": 233 }, { "epoch": 0.81, "learning_rate": 1.9927992171141707e-05, "loss": 1.0513, "step": 234 }, { "epoch": 0.81, "learning_rate": 1.9926872811474952e-05, "loss": 1.2633, "step": 235 }, { "epoch": 0.81, "learning_rate": 1.9925744850497866e-05, "loss": 1.1305, "step": 236 }, { "epoch": 0.82, "learning_rate": 1.9924608289187786e-05, "loss": 1.1505, "step": 237 }, { "epoch": 0.82, "learning_rate": 1.9923463128529507e-05, "loss": 1.2576, "step": 238 }, { "epoch": 0.82, "learning_rate": 1.9922309369515272e-05, "loss": 1.1034, "step": 239 }, { "epoch": 0.83, "learning_rate": 1.9921147013144782e-05, "loss": 1.3569, "step": 240 }, { "epoch": 0.83, "learning_rate": 1.991997606042517e-05, "loss": 1.2152, "step": 241 }, { "epoch": 0.83, "learning_rate": 1.9918796512371035e-05, "loss": 1.1143, "step": 242 }, { "epoch": 0.84, "learning_rate": 1.9917608370004417e-05, "loss": 1.1805, "step": 243 }, { "epoch": 0.84, "learning_rate": 1.99164116343548e-05, "loss": 1.1872, "step": 244 }, { "epoch": 0.84, "learning_rate": 1.9915206306459117e-05, "loss": 1.1894, "step": 245 }, { "epoch": 0.85, "learning_rate": 1.9913992387361747e-05, "loss": 1.2854, "step": 246 }, { "epoch": 0.85, "learning_rate": 1.9912769878114508e-05, "loss": 1.2307, "step": 247 }, { "epoch": 0.86, "learning_rate": 1.991153877977667e-05, "loss": 1.2782, "step": 248 }, { "epoch": 0.86, "learning_rate": 1.991029909341493e-05, "loss": 1.2873, "step": 249 }, { "epoch": 0.86, "learning_rate": 1.990905082010344e-05, "loss": 1.0803, "step": 250 }, { "epoch": 0.87, "learning_rate": 1.9907793960923795e-05, "loss": 1.1682, "step": 251 }, { "epoch": 0.87, "learning_rate": 1.990652851696501e-05, "loss": 1.1909, "step": 252 }, { "epoch": 0.87, "learning_rate": 1.990525448932356e-05, "loss": 1.2519, "step": 253 }, { "epoch": 0.88, "learning_rate": 1.9903971879103344e-05, "loss": 1.2881, "step": 254 }, { "epoch": 0.88, "learning_rate": 1.9902680687415704e-05, "loss": 1.2991, "step": 255 }, { "epoch": 0.88, "learning_rate": 1.9901380915379413e-05, "loss": 1.2386, "step": 256 }, { "epoch": 0.89, "learning_rate": 1.9900072564120686e-05, "loss": 1.2379, "step": 257 }, { "epoch": 0.89, "learning_rate": 1.989875563477316e-05, "loss": 1.0524, "step": 258 }, { "epoch": 0.89, "learning_rate": 1.9897430128477912e-05, "loss": 1.164, "step": 259 }, { "epoch": 0.9, "learning_rate": 1.9896096046383456e-05, "loss": 1.1651, "step": 260 }, { "epoch": 0.9, "learning_rate": 1.9894753389645723e-05, "loss": 1.2584, "step": 261 }, { "epoch": 0.9, "learning_rate": 1.9893402159428084e-05, "loss": 1.1623, "step": 262 }, { "epoch": 0.91, "learning_rate": 1.9892042356901337e-05, "loss": 1.0978, "step": 263 }, { "epoch": 0.91, "learning_rate": 1.9890673983243708e-05, "loss": 1.1073, "step": 264 }, { "epoch": 0.91, "learning_rate": 1.988929703964084e-05, "loss": 1.1571, "step": 265 }, { "epoch": 0.92, "learning_rate": 1.988791152728582e-05, "loss": 1.134, "step": 266 }, { "epoch": 0.92, "learning_rate": 1.988651744737914e-05, "loss": 1.1403, "step": 267 }, { "epoch": 0.92, "learning_rate": 1.988511480112873e-05, "loss": 1.2544, "step": 268 }, { "epoch": 0.93, "learning_rate": 1.9883703589749938e-05, "loss": 1.1921, "step": 269 }, { "epoch": 0.93, "learning_rate": 1.988228381446553e-05, "loss": 1.1709, "step": 270 }, { "epoch": 0.93, "learning_rate": 1.9880855476505694e-05, "loss": 1.2232, "step": 271 }, { "epoch": 0.94, "learning_rate": 1.9879418577108037e-05, "loss": 1.1804, "step": 272 }, { "epoch": 0.94, "learning_rate": 1.987797311751759e-05, "loss": 1.194, "step": 273 }, { "epoch": 0.94, "learning_rate": 1.987651909898679e-05, "loss": 1.2435, "step": 274 }, { "epoch": 0.95, "learning_rate": 1.9875056522775506e-05, "loss": 1.1141, "step": 275 }, { "epoch": 0.95, "learning_rate": 1.9873585390151003e-05, "loss": 1.2532, "step": 276 }, { "epoch": 0.96, "learning_rate": 1.9872105702387976e-05, "loss": 1.2792, "step": 277 }, { "epoch": 0.96, "learning_rate": 1.987061746076852e-05, "loss": 1.1113, "step": 278 }, { "epoch": 0.96, "learning_rate": 1.9869120666582153e-05, "loss": 1.2517, "step": 279 }, { "epoch": 0.97, "learning_rate": 1.9867615321125796e-05, "loss": 1.1326, "step": 280 }, { "epoch": 0.97, "learning_rate": 1.9866101425703776e-05, "loss": 1.2877, "step": 281 }, { "epoch": 0.97, "learning_rate": 1.9864578981627844e-05, "loss": 1.2429, "step": 282 }, { "epoch": 0.98, "learning_rate": 1.9863047990217143e-05, "loss": 1.0668, "step": 283 }, { "epoch": 0.98, "learning_rate": 1.9861508452798224e-05, "loss": 1.1143, "step": 284 }, { "epoch": 0.98, "learning_rate": 1.985996037070505e-05, "loss": 1.248, "step": 285 }, { "epoch": 0.99, "learning_rate": 1.9858403745278982e-05, "loss": 1.2112, "step": 286 }, { "epoch": 0.99, "learning_rate": 1.985683857786879e-05, "loss": 1.2108, "step": 287 }, { "epoch": 0.99, "learning_rate": 1.985526486983063e-05, "loss": 1.1086, "step": 288 }, { "epoch": 1.0, "learning_rate": 1.9853682622528074e-05, "loss": 1.2065, "step": 289 }, { "epoch": 1.0, "learning_rate": 1.985209183733209e-05, "loss": 1.1851, "step": 290 }, { "epoch": 1.0, "learning_rate": 1.9850492515621038e-05, "loss": 0.7343, "step": 291 }, { "epoch": 1.01, "learning_rate": 1.984888465878068e-05, "loss": 0.7512, "step": 292 }, { "epoch": 1.01, "learning_rate": 1.9847268268204168e-05, "loss": 0.7083, "step": 293 }, { "epoch": 1.01, "learning_rate": 1.9845643345292055e-05, "loss": 0.7229, "step": 294 }, { "epoch": 1.02, "learning_rate": 1.984400989145228e-05, "loss": 0.7095, "step": 295 }, { "epoch": 1.02, "learning_rate": 1.9842367908100182e-05, "loss": 0.7007, "step": 296 }, { "epoch": 1.02, "learning_rate": 1.9840717396658483e-05, "loss": 0.7599, "step": 297 }, { "epoch": 1.03, "learning_rate": 1.9839058358557296e-05, "loss": 0.6908, "step": 298 }, { "epoch": 1.03, "learning_rate": 1.9837390795234128e-05, "loss": 0.6812, "step": 299 }, { "epoch": 1.03, "learning_rate": 1.983571470813386e-05, "loss": 0.6357, "step": 300 }, { "epoch": 1.04, "learning_rate": 1.9834030098708773e-05, "loss": 0.6572, "step": 301 }, { "epoch": 1.04, "learning_rate": 1.9832336968418527e-05, "loss": 0.7172, "step": 302 }, { "epoch": 1.04, "learning_rate": 1.9830635318730155e-05, "loss": 0.6082, "step": 303 }, { "epoch": 1.05, "learning_rate": 1.9828925151118092e-05, "loss": 0.6748, "step": 304 }, { "epoch": 1.05, "learning_rate": 1.9827206467064133e-05, "loss": 0.765, "step": 305 }, { "epoch": 1.06, "learning_rate": 1.982547926805747e-05, "loss": 0.712, "step": 306 }, { "epoch": 1.06, "learning_rate": 1.9823743555594655e-05, "loss": 0.6817, "step": 307 }, { "epoch": 1.06, "learning_rate": 1.9821999331179635e-05, "loss": 0.7088, "step": 308 }, { "epoch": 1.07, "learning_rate": 1.982024659632372e-05, "loss": 0.7776, "step": 309 }, { "epoch": 1.07, "learning_rate": 1.9818485352545595e-05, "loss": 0.726, "step": 310 }, { "epoch": 1.07, "learning_rate": 1.981671560137132e-05, "loss": 0.7596, "step": 311 }, { "epoch": 1.08, "learning_rate": 1.981493734433433e-05, "loss": 0.6971, "step": 312 }, { "epoch": 1.08, "learning_rate": 1.9813150582975425e-05, "loss": 0.64, "step": 313 }, { "epoch": 1.08, "learning_rate": 1.9811355318842776e-05, "loss": 0.7429, "step": 314 }, { "epoch": 1.09, "learning_rate": 1.9809551553491918e-05, "loss": 0.6615, "step": 315 }, { "epoch": 1.09, "learning_rate": 1.9807739288485758e-05, "loss": 0.6789, "step": 316 }, { "epoch": 1.09, "learning_rate": 1.980591852539456e-05, "loss": 0.6526, "step": 317 }, { "epoch": 1.1, "learning_rate": 1.980408926579596e-05, "loss": 0.6812, "step": 318 }, { "epoch": 1.1, "learning_rate": 1.9802251511274946e-05, "loss": 0.7531, "step": 319 }, { "epoch": 1.1, "learning_rate": 1.980040526342388e-05, "loss": 0.7044, "step": 320 }, { "epoch": 1.11, "learning_rate": 1.979855052384247e-05, "loss": 0.7044, "step": 321 }, { "epoch": 1.11, "learning_rate": 1.979668729413779e-05, "loss": 0.6829, "step": 322 }, { "epoch": 1.11, "learning_rate": 1.9794815575924264e-05, "loss": 0.723, "step": 323 }, { "epoch": 1.12, "learning_rate": 1.9792935370823676e-05, "loss": 0.6113, "step": 324 }, { "epoch": 1.12, "learning_rate": 1.979104668046516e-05, "loss": 0.7492, "step": 325 }, { "epoch": 1.12, "learning_rate": 1.978914950648521e-05, "loss": 0.652, "step": 326 }, { "epoch": 1.13, "learning_rate": 1.9787243850527663e-05, "loss": 0.6816, "step": 327 }, { "epoch": 1.13, "learning_rate": 1.978532971424371e-05, "loss": 0.6936, "step": 328 }, { "epoch": 1.13, "learning_rate": 1.978340709929188e-05, "loss": 0.661, "step": 329 }, { "epoch": 1.14, "learning_rate": 1.9781476007338058e-05, "loss": 0.6927, "step": 330 }, { "epoch": 1.14, "learning_rate": 1.9779536440055474e-05, "loss": 0.6372, "step": 331 }, { "epoch": 1.14, "learning_rate": 1.9777588399124702e-05, "loss": 0.6379, "step": 332 }, { "epoch": 1.15, "learning_rate": 1.9775631886233655e-05, "loss": 0.6528, "step": 333 }, { "epoch": 1.15, "learning_rate": 1.977366690307758e-05, "loss": 0.741, "step": 334 }, { "epoch": 1.16, "learning_rate": 1.977169345135908e-05, "loss": 0.6967, "step": 335 }, { "epoch": 1.16, "learning_rate": 1.9769711532788083e-05, "loss": 0.7075, "step": 336 }, { "epoch": 1.16, "learning_rate": 1.9767721149081852e-05, "loss": 0.6554, "step": 337 }, { "epoch": 1.17, "learning_rate": 1.9765722301965e-05, "loss": 0.7454, "step": 338 }, { "epoch": 1.17, "learning_rate": 1.976371499316945e-05, "loss": 0.6421, "step": 339 }, { "epoch": 1.17, "learning_rate": 1.9761699224434476e-05, "loss": 0.6899, "step": 340 }, { "epoch": 1.18, "learning_rate": 1.975967499750668e-05, "loss": 0.6932, "step": 341 }, { "epoch": 1.18, "learning_rate": 1.9757642314139977e-05, "loss": 0.696, "step": 342 }, { "epoch": 1.18, "learning_rate": 1.975560117609563e-05, "loss": 0.644, "step": 343 }, { "epoch": 1.19, "learning_rate": 1.9753551585142214e-05, "loss": 0.7286, "step": 344 }, { "epoch": 1.19, "learning_rate": 1.9751493543055634e-05, "loss": 0.6811, "step": 345 }, { "epoch": 1.19, "learning_rate": 1.9749427051619118e-05, "loss": 0.68, "step": 346 }, { "epoch": 1.2, "learning_rate": 1.9747352112623207e-05, "loss": 0.6333, "step": 347 }, { "epoch": 1.2, "learning_rate": 1.9745268727865774e-05, "loss": 0.7593, "step": 348 }, { "epoch": 1.2, "learning_rate": 1.9743176899151998e-05, "loss": 0.7161, "step": 349 }, { "epoch": 1.21, "learning_rate": 1.9741076628294387e-05, "loss": 0.7151, "step": 350 }, { "epoch": 1.21, "learning_rate": 1.9738967917112752e-05, "loss": 0.7485, "step": 351 }, { "epoch": 1.21, "learning_rate": 1.9736850767434226e-05, "loss": 0.725, "step": 352 }, { "epoch": 1.22, "learning_rate": 1.9734725181093246e-05, "loss": 0.7805, "step": 353 }, { "epoch": 1.22, "learning_rate": 1.9732591159931564e-05, "loss": 0.7069, "step": 354 }, { "epoch": 1.22, "learning_rate": 1.973044870579824e-05, "loss": 0.6981, "step": 355 }, { "epoch": 1.23, "learning_rate": 1.972829782054964e-05, "loss": 0.7194, "step": 356 }, { "epoch": 1.23, "learning_rate": 1.9726138506049438e-05, "loss": 0.7016, "step": 357 }, { "epoch": 1.23, "learning_rate": 1.9723970764168606e-05, "loss": 0.6876, "step": 358 }, { "epoch": 1.24, "learning_rate": 1.9721794596785423e-05, "loss": 0.6618, "step": 359 }, { "epoch": 1.24, "learning_rate": 1.9719610005785466e-05, "loss": 0.6402, "step": 360 }, { "epoch": 1.24, "learning_rate": 1.971741699306161e-05, "loss": 0.7137, "step": 361 }, { "epoch": 1.25, "learning_rate": 1.9715215560514032e-05, "loss": 0.7174, "step": 362 }, { "epoch": 1.25, "learning_rate": 1.9713005710050203e-05, "loss": 0.75, "step": 363 }, { "epoch": 1.26, "learning_rate": 1.971078744358488e-05, "loss": 0.7121, "step": 364 }, { "epoch": 1.26, "learning_rate": 1.970856076304012e-05, "loss": 0.6689, "step": 365 }, { "epoch": 1.26, "learning_rate": 1.9706325670345276e-05, "loss": 0.7713, "step": 366 }, { "epoch": 1.27, "learning_rate": 1.9704082167436974e-05, "loss": 0.6505, "step": 367 }, { "epoch": 1.27, "learning_rate": 1.9701830256259136e-05, "loss": 0.638, "step": 368 }, { "epoch": 1.27, "learning_rate": 1.9699569938762975e-05, "loss": 0.7383, "step": 369 }, { "epoch": 1.28, "learning_rate": 1.969730121690698e-05, "loss": 0.6333, "step": 370 }, { "epoch": 1.28, "learning_rate": 1.969502409265692e-05, "loss": 0.7296, "step": 371 }, { "epoch": 1.28, "learning_rate": 1.9692738567985853e-05, "loss": 0.6462, "step": 372 }, { "epoch": 1.29, "learning_rate": 1.9690444644874112e-05, "loss": 0.8113, "step": 373 }, { "epoch": 1.29, "learning_rate": 1.9688142325309302e-05, "loss": 0.6363, "step": 374 }, { "epoch": 1.29, "learning_rate": 1.9685831611286312e-05, "loss": 0.7177, "step": 375 }, { "epoch": 1.3, "learning_rate": 1.9683512504807298e-05, "loss": 0.6961, "step": 376 }, { "epoch": 1.3, "learning_rate": 1.968118500788169e-05, "loss": 0.6869, "step": 377 }, { "epoch": 1.3, "learning_rate": 1.967884912252619e-05, "loss": 0.657, "step": 378 }, { "epoch": 1.31, "learning_rate": 1.967650485076476e-05, "loss": 0.785, "step": 379 }, { "epoch": 1.31, "learning_rate": 1.967415219462864e-05, "loss": 0.7045, "step": 380 }, { "epoch": 1.31, "learning_rate": 1.967179115615633e-05, "loss": 0.7022, "step": 381 }, { "epoch": 1.32, "learning_rate": 1.966942173739359e-05, "loss": 0.6417, "step": 382 }, { "epoch": 1.32, "learning_rate": 1.9667043940393445e-05, "loss": 0.7073, "step": 383 }, { "epoch": 1.32, "learning_rate": 1.9664657767216176e-05, "loss": 0.665, "step": 384 }, { "epoch": 1.33, "learning_rate": 1.966226321992933e-05, "loss": 0.6585, "step": 385 }, { "epoch": 1.33, "learning_rate": 1.9659860300607695e-05, "loss": 0.787, "step": 386 }, { "epoch": 1.33, "learning_rate": 1.9657449011333328e-05, "loss": 0.6646, "step": 387 }, { "epoch": 1.34, "learning_rate": 1.9655029354195534e-05, "loss": 0.781, "step": 388 }, { "epoch": 1.34, "learning_rate": 1.9652601331290864e-05, "loss": 0.7042, "step": 389 }, { "epoch": 1.34, "learning_rate": 1.9650164944723116e-05, "loss": 0.7232, "step": 390 }, { "epoch": 1.35, "learning_rate": 1.9647720196603343e-05, "loss": 0.6306, "step": 391 }, { "epoch": 1.35, "learning_rate": 1.9645267089049844e-05, "loss": 0.7539, "step": 392 }, { "epoch": 1.36, "learning_rate": 1.964280562418815e-05, "loss": 0.71, "step": 393 }, { "epoch": 1.36, "learning_rate": 1.964033580415104e-05, "loss": 0.6424, "step": 394 }, { "epoch": 1.36, "learning_rate": 1.9637857631078532e-05, "loss": 0.7122, "step": 395 }, { "epoch": 1.37, "learning_rate": 1.963537110711789e-05, "loss": 0.7191, "step": 396 }, { "epoch": 1.37, "learning_rate": 1.9632876234423592e-05, "loss": 0.6934, "step": 397 }, { "epoch": 1.37, "learning_rate": 1.9630373015157374e-05, "loss": 0.6344, "step": 398 }, { "epoch": 1.38, "learning_rate": 1.962786145148819e-05, "loss": 0.6586, "step": 399 }, { "epoch": 1.38, "learning_rate": 1.9625341545592226e-05, "loss": 0.7496, "step": 400 }, { "epoch": 1.38, "learning_rate": 1.9622813299652904e-05, "loss": 0.7141, "step": 401 }, { "epoch": 1.39, "learning_rate": 1.962027671586086e-05, "loss": 0.7671, "step": 402 }, { "epoch": 1.39, "learning_rate": 1.9617731796413962e-05, "loss": 0.726, "step": 403 }, { "epoch": 1.39, "learning_rate": 1.9615178543517303e-05, "loss": 0.6995, "step": 404 }, { "epoch": 1.4, "learning_rate": 1.961261695938319e-05, "loss": 0.6813, "step": 405 }, { "epoch": 1.4, "learning_rate": 1.9610047046231152e-05, "loss": 0.6808, "step": 406 }, { "epoch": 1.4, "learning_rate": 1.9607468806287936e-05, "loss": 0.6874, "step": 407 }, { "epoch": 1.41, "learning_rate": 1.96048822417875e-05, "loss": 0.6684, "step": 408 }, { "epoch": 1.41, "learning_rate": 1.9602287354971018e-05, "loss": 0.6834, "step": 409 }, { "epoch": 1.41, "learning_rate": 1.9599684148086876e-05, "loss": 0.6572, "step": 410 }, { "epoch": 1.42, "learning_rate": 1.9597072623390668e-05, "loss": 0.7358, "step": 411 }, { "epoch": 1.42, "learning_rate": 1.959445278314519e-05, "loss": 0.7033, "step": 412 }, { "epoch": 1.42, "learning_rate": 1.959182462962046e-05, "loss": 0.6698, "step": 413 }, { "epoch": 1.43, "learning_rate": 1.958918816509367e-05, "loss": 0.6299, "step": 414 }, { "epoch": 1.43, "learning_rate": 1.9586543391849243e-05, "loss": 0.6512, "step": 415 }, { "epoch": 1.43, "learning_rate": 1.958389031217878e-05, "loss": 0.8226, "step": 416 }, { "epoch": 1.44, "learning_rate": 1.95812289283811e-05, "loss": 0.6673, "step": 417 }, { "epoch": 1.44, "learning_rate": 1.957855924276219e-05, "loss": 0.6959, "step": 418 }, { "epoch": 1.44, "learning_rate": 1.9575881257635254e-05, "loss": 0.6946, "step": 419 }, { "epoch": 1.45, "learning_rate": 1.9573194975320672e-05, "loss": 0.6767, "step": 420 }, { "epoch": 1.45, "learning_rate": 1.957050039814603e-05, "loss": 0.6647, "step": 421 }, { "epoch": 1.46, "learning_rate": 1.9567797528446083e-05, "loss": 0.7477, "step": 422 }, { "epoch": 1.46, "learning_rate": 1.956508636856278e-05, "loss": 0.65, "step": 423 }, { "epoch": 1.46, "learning_rate": 1.9562366920845256e-05, "loss": 0.7328, "step": 424 }, { "epoch": 1.47, "learning_rate": 1.9559639187649817e-05, "loss": 0.7052, "step": 425 }, { "epoch": 1.47, "learning_rate": 1.9556903171339963e-05, "loss": 0.7365, "step": 426 }, { "epoch": 1.47, "learning_rate": 1.9554158874286353e-05, "loss": 0.6195, "step": 427 }, { "epoch": 1.48, "learning_rate": 1.9551406298866838e-05, "loss": 0.7432, "step": 428 }, { "epoch": 1.48, "learning_rate": 1.9548645447466433e-05, "loss": 0.7367, "step": 429 }, { "epoch": 1.48, "learning_rate": 1.954587632247732e-05, "loss": 0.6919, "step": 430 }, { "epoch": 1.49, "learning_rate": 1.9543098926298864e-05, "loss": 0.7414, "step": 431 }, { "epoch": 1.49, "learning_rate": 1.954031326133758e-05, "loss": 0.7284, "step": 432 }, { "epoch": 1.49, "learning_rate": 1.9537519330007163e-05, "loss": 0.739, "step": 433 }, { "epoch": 1.5, "learning_rate": 1.9534717134728455e-05, "loss": 0.6371, "step": 434 }, { "epoch": 1.5, "learning_rate": 1.9531906677929472e-05, "loss": 0.6845, "step": 435 }, { "epoch": 1.5, "learning_rate": 1.952908796204538e-05, "loss": 0.7606, "step": 436 }, { "epoch": 1.51, "learning_rate": 1.9526260989518506e-05, "loss": 0.6839, "step": 437 }, { "epoch": 1.51, "learning_rate": 1.9523425762798328e-05, "loss": 0.7266, "step": 438 }, { "epoch": 1.51, "learning_rate": 1.9520582284341478e-05, "loss": 0.5924, "step": 439 }, { "epoch": 1.52, "learning_rate": 1.951773055661174e-05, "loss": 0.7233, "step": 440 }, { "epoch": 1.52, "learning_rate": 1.951487058208003e-05, "loss": 0.6601, "step": 441 }, { "epoch": 1.52, "learning_rate": 1.951200236322444e-05, "loss": 0.7587, "step": 442 }, { "epoch": 1.53, "learning_rate": 1.9509125902530178e-05, "loss": 0.7544, "step": 443 }, { "epoch": 1.53, "learning_rate": 1.95062412024896e-05, "loss": 0.6956, "step": 444 }, { "epoch": 1.53, "learning_rate": 1.9503348265602212e-05, "loss": 0.6863, "step": 445 }, { "epoch": 1.54, "learning_rate": 1.9500447094374645e-05, "loss": 0.7986, "step": 446 }, { "epoch": 1.54, "learning_rate": 1.949753769132067e-05, "loss": 0.7199, "step": 447 }, { "epoch": 1.54, "learning_rate": 1.949462005896119e-05, "loss": 0.6628, "step": 448 }, { "epoch": 1.55, "learning_rate": 1.9491694199824232e-05, "loss": 0.7378, "step": 449 }, { "epoch": 1.55, "learning_rate": 1.9488760116444966e-05, "loss": 0.7213, "step": 450 }, { "epoch": 1.56, "learning_rate": 1.9485817811365676e-05, "loss": 0.6956, "step": 451 }, { "epoch": 1.56, "learning_rate": 1.9482867287135772e-05, "loss": 0.7118, "step": 452 }, { "epoch": 1.56, "learning_rate": 1.9479908546311783e-05, "loss": 0.6999, "step": 453 }, { "epoch": 1.57, "learning_rate": 1.947694159145737e-05, "loss": 0.6654, "step": 454 }, { "epoch": 1.57, "learning_rate": 1.9473966425143292e-05, "loss": 0.7016, "step": 455 }, { "epoch": 1.57, "learning_rate": 1.9470983049947446e-05, "loss": 0.7339, "step": 456 }, { "epoch": 1.58, "learning_rate": 1.9467991468454817e-05, "loss": 0.7383, "step": 457 }, { "epoch": 1.58, "learning_rate": 1.9464991683257514e-05, "loss": 0.635, "step": 458 }, { "epoch": 1.58, "learning_rate": 1.946198369695476e-05, "loss": 0.7277, "step": 459 }, { "epoch": 1.59, "learning_rate": 1.9458967512152872e-05, "loss": 0.6761, "step": 460 }, { "epoch": 1.59, "learning_rate": 1.9455943131465272e-05, "loss": 0.738, "step": 461 }, { "epoch": 1.59, "learning_rate": 1.9452910557512497e-05, "loss": 0.7039, "step": 462 }, { "epoch": 1.6, "learning_rate": 1.9449869792922162e-05, "loss": 0.656, "step": 463 }, { "epoch": 1.6, "learning_rate": 1.9446820840328993e-05, "loss": 0.7944, "step": 464 }, { "epoch": 1.6, "learning_rate": 1.944376370237481e-05, "loss": 0.6946, "step": 465 }, { "epoch": 1.61, "learning_rate": 1.9440698381708526e-05, "loss": 0.6451, "step": 466 }, { "epoch": 1.61, "learning_rate": 1.9437624880986135e-05, "loss": 0.724, "step": 467 }, { "epoch": 1.61, "learning_rate": 1.9434543202870726e-05, "loss": 0.6424, "step": 468 }, { "epoch": 1.62, "learning_rate": 1.9431453350032476e-05, "loss": 0.7673, "step": 469 }, { "epoch": 1.62, "learning_rate": 1.9428355325148632e-05, "loss": 0.7617, "step": 470 }, { "epoch": 1.62, "learning_rate": 1.9425249130903544e-05, "loss": 0.7686, "step": 471 }, { "epoch": 1.63, "learning_rate": 1.9422134769988617e-05, "loss": 0.8088, "step": 472 }, { "epoch": 1.63, "learning_rate": 1.9419012245102347e-05, "loss": 0.6805, "step": 473 }, { "epoch": 1.63, "learning_rate": 1.9415881558950302e-05, "loss": 0.654, "step": 474 }, { "epoch": 1.64, "learning_rate": 1.941274271424512e-05, "loss": 0.6434, "step": 475 }, { "epoch": 1.64, "learning_rate": 1.9409595713706496e-05, "loss": 0.6466, "step": 476 }, { "epoch": 1.64, "learning_rate": 1.9406440560061214e-05, "loss": 0.7267, "step": 477 }, { "epoch": 1.65, "learning_rate": 1.940327725604311e-05, "loss": 0.7206, "step": 478 }, { "epoch": 1.65, "learning_rate": 1.9400105804393083e-05, "loss": 0.6717, "step": 479 }, { "epoch": 1.66, "learning_rate": 1.9396926207859085e-05, "loss": 0.7631, "step": 480 }, { "epoch": 1.66, "learning_rate": 1.939373846919614e-05, "loss": 0.6765, "step": 481 }, { "epoch": 1.66, "learning_rate": 1.939054259116632e-05, "loss": 0.697, "step": 482 }, { "epoch": 1.67, "learning_rate": 1.9387338576538743e-05, "loss": 0.7574, "step": 483 }, { "epoch": 1.67, "learning_rate": 1.938412642808959e-05, "loss": 0.7073, "step": 484 }, { "epoch": 1.67, "learning_rate": 1.938090614860207e-05, "loss": 0.5954, "step": 485 }, { "epoch": 1.68, "learning_rate": 1.937767774086646e-05, "loss": 0.7531, "step": 486 }, { "epoch": 1.68, "learning_rate": 1.937444120768007e-05, "loss": 0.7187, "step": 487 }, { "epoch": 1.68, "learning_rate": 1.9371196551847248e-05, "loss": 0.6545, "step": 488 }, { "epoch": 1.69, "learning_rate": 1.936794377617938e-05, "loss": 0.7226, "step": 489 }, { "epoch": 1.69, "learning_rate": 1.9364682883494892e-05, "loss": 0.7766, "step": 490 }, { "epoch": 1.69, "learning_rate": 1.936141387661924e-05, "loss": 0.6742, "step": 491 }, { "epoch": 1.7, "learning_rate": 1.935813675838491e-05, "loss": 0.7205, "step": 492 }, { "epoch": 1.7, "learning_rate": 1.935485153163142e-05, "loss": 0.6389, "step": 493 }, { "epoch": 1.7, "learning_rate": 1.935155819920531e-05, "loss": 0.677, "step": 494 }, { "epoch": 1.71, "learning_rate": 1.9348256763960146e-05, "loss": 0.6894, "step": 495 }, { "epoch": 1.71, "learning_rate": 1.934494722875651e-05, "loss": 0.6503, "step": 496 }, { "epoch": 1.71, "learning_rate": 1.9341629596462015e-05, "loss": 0.6799, "step": 497 }, { "epoch": 1.72, "learning_rate": 1.933830386995127e-05, "loss": 0.6777, "step": 498 }, { "epoch": 1.72, "learning_rate": 1.933497005210591e-05, "loss": 0.6925, "step": 499 }, { "epoch": 1.72, "learning_rate": 1.9331628145814587e-05, "loss": 0.6817, "step": 500 }, { "epoch": 1.73, "learning_rate": 1.9328278153972947e-05, "loss": 0.5892, "step": 501 }, { "epoch": 1.73, "learning_rate": 1.9324920079483647e-05, "loss": 0.746, "step": 502 }, { "epoch": 1.73, "learning_rate": 1.9321553925256355e-05, "loss": 0.7821, "step": 503 }, { "epoch": 1.74, "learning_rate": 1.9318179694207726e-05, "loss": 0.6536, "step": 504 }, { "epoch": 1.74, "learning_rate": 1.9314797389261426e-05, "loss": 0.7395, "step": 505 }, { "epoch": 1.74, "learning_rate": 1.931140701334811e-05, "loss": 0.8165, "step": 506 }, { "epoch": 1.75, "learning_rate": 1.9308008569405424e-05, "loss": 0.7218, "step": 507 }, { "epoch": 1.75, "learning_rate": 1.9304602060378013e-05, "loss": 0.6668, "step": 508 }, { "epoch": 1.76, "learning_rate": 1.9301187489217508e-05, "loss": 0.617, "step": 509 }, { "epoch": 1.76, "learning_rate": 1.9297764858882516e-05, "loss": 0.6638, "step": 510 }, { "epoch": 1.76, "learning_rate": 1.9294334172338637e-05, "loss": 0.6733, "step": 511 }, { "epoch": 1.77, "learning_rate": 1.929089543255845e-05, "loss": 0.695, "step": 512 }, { "epoch": 1.77, "learning_rate": 1.9287448642521513e-05, "loss": 0.7118, "step": 513 }, { "epoch": 1.77, "learning_rate": 1.9283993805214353e-05, "loss": 0.6789, "step": 514 }, { "epoch": 1.78, "learning_rate": 1.928053092363047e-05, "loss": 0.7322, "step": 515 }, { "epoch": 1.78, "learning_rate": 1.9277060000770342e-05, "loss": 0.6963, "step": 516 }, { "epoch": 1.78, "learning_rate": 1.9273581039641412e-05, "loss": 0.746, "step": 517 }, { "epoch": 1.79, "learning_rate": 1.927009404325808e-05, "loss": 0.6681, "step": 518 }, { "epoch": 1.79, "learning_rate": 1.9266599014641724e-05, "loss": 0.7509, "step": 519 }, { "epoch": 1.79, "learning_rate": 1.926309595682066e-05, "loss": 0.6142, "step": 520 }, { "epoch": 1.8, "learning_rate": 1.925958487283018e-05, "loss": 0.6667, "step": 521 }, { "epoch": 1.8, "learning_rate": 1.9256065765712524e-05, "loss": 0.6588, "step": 522 }, { "epoch": 1.8, "learning_rate": 1.9252538638516878e-05, "loss": 0.761, "step": 523 }, { "epoch": 1.81, "learning_rate": 1.9249003494299385e-05, "loss": 0.7088, "step": 524 }, { "epoch": 1.81, "learning_rate": 1.9245460336123136e-05, "loss": 0.787, "step": 525 }, { "epoch": 1.81, "learning_rate": 1.9241909167058154e-05, "loss": 0.7178, "step": 526 }, { "epoch": 1.82, "learning_rate": 1.923834999018141e-05, "loss": 0.7174, "step": 527 }, { "epoch": 1.82, "learning_rate": 1.9234782808576823e-05, "loss": 0.652, "step": 528 }, { "epoch": 1.82, "learning_rate": 1.9231207625335235e-05, "loss": 0.7035, "step": 529 }, { "epoch": 1.83, "learning_rate": 1.9227624443554425e-05, "loss": 0.6668, "step": 530 }, { "epoch": 1.83, "learning_rate": 1.9224033266339103e-05, "loss": 0.752, "step": 531 }, { "epoch": 1.83, "learning_rate": 1.9220434096800903e-05, "loss": 0.6964, "step": 532 }, { "epoch": 1.84, "learning_rate": 1.9216826938058394e-05, "loss": 0.6152, "step": 533 }, { "epoch": 1.84, "learning_rate": 1.9213211793237056e-05, "loss": 0.7001, "step": 534 }, { "epoch": 1.84, "learning_rate": 1.9209588665469294e-05, "loss": 0.7193, "step": 535 }, { "epoch": 1.85, "learning_rate": 1.9205957557894433e-05, "loss": 0.6905, "step": 536 }, { "epoch": 1.85, "learning_rate": 1.9202318473658707e-05, "loss": 0.6505, "step": 537 }, { "epoch": 1.86, "learning_rate": 1.919867141591526e-05, "loss": 0.7074, "step": 538 }, { "epoch": 1.86, "learning_rate": 1.9195016387824154e-05, "loss": 0.7218, "step": 539 }, { "epoch": 1.86, "learning_rate": 1.9191353392552346e-05, "loss": 0.6711, "step": 540 }, { "epoch": 1.87, "learning_rate": 1.9187682433273704e-05, "loss": 0.8002, "step": 541 }, { "epoch": 1.87, "learning_rate": 1.9184003513168995e-05, "loss": 0.7491, "step": 542 }, { "epoch": 1.87, "learning_rate": 1.9180316635425883e-05, "loss": 0.6503, "step": 543 }, { "epoch": 1.88, "learning_rate": 1.9176621803238924e-05, "loss": 0.6792, "step": 544 }, { "epoch": 1.88, "learning_rate": 1.9172919019809572e-05, "loss": 0.743, "step": 545 }, { "epoch": 1.88, "learning_rate": 1.9169208288346168e-05, "loss": 0.751, "step": 546 }, { "epoch": 1.89, "learning_rate": 1.9165489612063932e-05, "loss": 0.6516, "step": 547 }, { "epoch": 1.89, "learning_rate": 1.9161762994184986e-05, "loss": 0.6285, "step": 548 }, { "epoch": 1.89, "learning_rate": 1.9158028437938316e-05, "loss": 0.7292, "step": 549 }, { "epoch": 1.9, "learning_rate": 1.9154285946559792e-05, "loss": 0.6948, "step": 550 }, { "epoch": 1.9, "learning_rate": 1.9150535523292165e-05, "loss": 0.7495, "step": 551 }, { "epoch": 1.9, "learning_rate": 1.914677717138505e-05, "loss": 0.6467, "step": 552 }, { "epoch": 1.91, "learning_rate": 1.9143010894094938e-05, "loss": 0.7425, "step": 553 }, { "epoch": 1.91, "learning_rate": 1.9139236694685184e-05, "loss": 0.6943, "step": 554 }, { "epoch": 1.91, "learning_rate": 1.913545457642601e-05, "loss": 0.7633, "step": 555 }, { "epoch": 1.92, "learning_rate": 1.9131664542594496e-05, "loss": 0.6327, "step": 556 }, { "epoch": 1.92, "learning_rate": 1.912786659647458e-05, "loss": 0.7023, "step": 557 }, { "epoch": 1.92, "learning_rate": 1.9124060741357065e-05, "loss": 0.7677, "step": 558 }, { "epoch": 1.93, "learning_rate": 1.912024698053959e-05, "loss": 0.718, "step": 559 }, { "epoch": 1.93, "learning_rate": 1.911642531732666e-05, "loss": 0.7192, "step": 560 }, { "epoch": 1.93, "learning_rate": 1.9112595755029625e-05, "loss": 0.6936, "step": 561 }, { "epoch": 1.94, "learning_rate": 1.9108758296966666e-05, "loss": 0.6841, "step": 562 }, { "epoch": 1.94, "learning_rate": 1.910491294646282e-05, "loss": 0.8081, "step": 563 }, { "epoch": 1.94, "learning_rate": 1.9101059706849957e-05, "loss": 0.6954, "step": 564 }, { "epoch": 1.95, "learning_rate": 1.9097198581466785e-05, "loss": 0.7887, "step": 565 }, { "epoch": 1.95, "learning_rate": 1.909332957365884e-05, "loss": 0.6479, "step": 566 }, { "epoch": 1.96, "learning_rate": 1.908945268677849e-05, "loss": 0.7737, "step": 567 }, { "epoch": 1.96, "learning_rate": 1.9085567924184932e-05, "loss": 0.7327, "step": 568 }, { "epoch": 1.96, "learning_rate": 1.9081675289244183e-05, "loss": 0.7384, "step": 569 }, { "epoch": 1.97, "learning_rate": 1.907777478532909e-05, "loss": 0.6795, "step": 570 }, { "epoch": 1.97, "learning_rate": 1.9073866415819303e-05, "loss": 0.679, "step": 571 }, { "epoch": 1.97, "learning_rate": 1.9069950184101305e-05, "loss": 0.8291, "step": 572 }, { "epoch": 1.98, "learning_rate": 1.906602609356838e-05, "loss": 0.6748, "step": 573 }, { "epoch": 1.98, "learning_rate": 1.906209414762062e-05, "loss": 0.7224, "step": 574 }, { "epoch": 1.98, "learning_rate": 1.9058154349664932e-05, "loss": 0.783, "step": 575 }, { "epoch": 1.99, "learning_rate": 1.905420670311502e-05, "loss": 0.7554, "step": 576 }, { "epoch": 1.99, "learning_rate": 1.905025121139139e-05, "loss": 0.6499, "step": 577 }, { "epoch": 1.99, "learning_rate": 1.9046287877921344e-05, "loss": 0.7685, "step": 578 }, { "epoch": 2.0, "learning_rate": 1.9042316706138987e-05, "loss": 0.6356, "step": 579 }, { "epoch": 2.0, "learning_rate": 1.9038337699485207e-05, "loss": 0.5548, "step": 580 }, { "epoch": 2.0, "learning_rate": 1.903435086140768e-05, "loss": 0.3445, "step": 581 }, { "epoch": 2.01, "learning_rate": 1.9030356195360875e-05, "loss": 0.3504, "step": 582 }, { "epoch": 2.01, "learning_rate": 1.9026353704806032e-05, "loss": 0.3291, "step": 583 }, { "epoch": 2.01, "learning_rate": 1.902234339321119e-05, "loss": 0.3163, "step": 584 }, { "epoch": 2.02, "learning_rate": 1.901832526405114e-05, "loss": 0.3535, "step": 585 }, { "epoch": 2.02, "learning_rate": 1.9014299320807467e-05, "loss": 0.3166, "step": 586 }, { "epoch": 2.02, "learning_rate": 1.9010265566968518e-05, "loss": 0.327, "step": 587 }, { "epoch": 2.03, "learning_rate": 1.9006224006029404e-05, "loss": 0.2785, "step": 588 }, { "epoch": 2.03, "learning_rate": 1.9002174641492015e-05, "loss": 0.2955, "step": 589 }, { "epoch": 2.03, "learning_rate": 1.8998117476864984e-05, "loss": 0.2747, "step": 590 }, { "epoch": 2.04, "learning_rate": 1.899405251566371e-05, "loss": 0.2947, "step": 591 }, { "epoch": 2.04, "learning_rate": 1.8989979761410356e-05, "loss": 0.2931, "step": 592 }, { "epoch": 2.04, "learning_rate": 1.898589921763383e-05, "loss": 0.3029, "step": 593 }, { "epoch": 2.05, "learning_rate": 1.8981810887869784e-05, "loss": 0.2931, "step": 594 }, { "epoch": 2.05, "learning_rate": 1.897771477566063e-05, "loss": 0.2532, "step": 595 }, { "epoch": 2.06, "learning_rate": 1.8973610884555505e-05, "loss": 0.3408, "step": 596 }, { "epoch": 2.06, "learning_rate": 1.8969499218110302e-05, "loss": 0.3068, "step": 597 }, { "epoch": 2.06, "learning_rate": 1.896537977988764e-05, "loss": 0.2712, "step": 598 }, { "epoch": 2.07, "learning_rate": 1.896125257345689e-05, "loss": 0.3098, "step": 599 }, { "epoch": 2.07, "learning_rate": 1.895711760239413e-05, "loss": 0.2649, "step": 600 }, { "epoch": 2.07, "learning_rate": 1.895297487028218e-05, "loss": 0.2977, "step": 601 }, { "epoch": 2.08, "learning_rate": 1.8948824380710582e-05, "loss": 0.2336, "step": 602 }, { "epoch": 2.08, "learning_rate": 1.89446661372756e-05, "loss": 0.3687, "step": 603 }, { "epoch": 2.08, "learning_rate": 1.8940500143580215e-05, "loss": 0.3082, "step": 604 }, { "epoch": 2.09, "learning_rate": 1.8936326403234125e-05, "loss": 0.2884, "step": 605 }, { "epoch": 2.09, "learning_rate": 1.893214491985374e-05, "loss": 0.316, "step": 606 }, { "epoch": 2.09, "learning_rate": 1.8927955697062172e-05, "loss": 0.336, "step": 607 }, { "epoch": 2.1, "learning_rate": 1.892375873848925e-05, "loss": 0.3065, "step": 608 }, { "epoch": 2.1, "learning_rate": 1.8919554047771508e-05, "loss": 0.2622, "step": 609 }, { "epoch": 2.1, "learning_rate": 1.8915341628552166e-05, "loss": 0.2963, "step": 610 }, { "epoch": 2.11, "learning_rate": 1.8911121484481145e-05, "loss": 0.3352, "step": 611 }, { "epoch": 2.11, "learning_rate": 1.890689361921507e-05, "loss": 0.3059, "step": 612 }, { "epoch": 2.11, "learning_rate": 1.8902658036417236e-05, "loss": 0.322, "step": 613 }, { "epoch": 2.12, "learning_rate": 1.8898414739757648e-05, "loss": 0.3049, "step": 614 }, { "epoch": 2.12, "learning_rate": 1.889416373291298e-05, "loss": 0.3014, "step": 615 }, { "epoch": 2.12, "learning_rate": 1.8889905019566584e-05, "loss": 0.3134, "step": 616 }, { "epoch": 2.13, "learning_rate": 1.8885638603408502e-05, "loss": 0.307, "step": 617 }, { "epoch": 2.13, "learning_rate": 1.8881364488135448e-05, "loss": 0.3042, "step": 618 }, { "epoch": 2.13, "learning_rate": 1.8877082677450795e-05, "loss": 0.3358, "step": 619 }, { "epoch": 2.14, "learning_rate": 1.8872793175064594e-05, "loss": 0.3036, "step": 620 }, { "epoch": 2.14, "learning_rate": 1.886849598469356e-05, "loss": 0.3028, "step": 621 }, { "epoch": 2.14, "learning_rate": 1.8864191110061066e-05, "loss": 0.2709, "step": 622 }, { "epoch": 2.15, "learning_rate": 1.8859878554897147e-05, "loss": 0.2613, "step": 623 }, { "epoch": 2.15, "learning_rate": 1.8855558322938492e-05, "loss": 0.2843, "step": 624 }, { "epoch": 2.16, "learning_rate": 1.8851230417928433e-05, "loss": 0.3019, "step": 625 }, { "epoch": 2.16, "learning_rate": 1.884689484361697e-05, "loss": 0.3174, "step": 626 }, { "epoch": 2.16, "learning_rate": 1.8842551603760725e-05, "loss": 0.2937, "step": 627 }, { "epoch": 2.17, "learning_rate": 1.883820070212298e-05, "loss": 0.3031, "step": 628 }, { "epoch": 2.17, "learning_rate": 1.8833842142473643e-05, "loss": 0.2512, "step": 629 }, { "epoch": 2.17, "learning_rate": 1.8829475928589272e-05, "loss": 0.3677, "step": 630 }, { "epoch": 2.18, "learning_rate": 1.882510206425304e-05, "loss": 0.3406, "step": 631 }, { "epoch": 2.18, "learning_rate": 1.882072055325476e-05, "loss": 0.3419, "step": 632 }, { "epoch": 2.18, "learning_rate": 1.881633139939087e-05, "loss": 0.289, "step": 633 }, { "epoch": 2.19, "learning_rate": 1.8811934606464425e-05, "loss": 0.2963, "step": 634 }, { "epoch": 2.19, "learning_rate": 1.880753017828511e-05, "loss": 0.3507, "step": 635 }, { "epoch": 2.19, "learning_rate": 1.8803118118669203e-05, "loss": 0.3018, "step": 636 }, { "epoch": 2.2, "learning_rate": 1.879869843143962e-05, "loss": 0.261, "step": 637 }, { "epoch": 2.2, "learning_rate": 1.8794271120425874e-05, "loss": 0.3003, "step": 638 }, { "epoch": 2.2, "learning_rate": 1.878983618946409e-05, "loss": 0.2976, "step": 639 }, { "epoch": 2.21, "learning_rate": 1.8785393642396976e-05, "loss": 0.3536, "step": 640 }, { "epoch": 2.21, "learning_rate": 1.8780943483073867e-05, "loss": 0.301, "step": 641 }, { "epoch": 2.21, "learning_rate": 1.8776485715350672e-05, "loss": 0.3021, "step": 642 }, { "epoch": 2.22, "learning_rate": 1.8772020343089906e-05, "loss": 0.3237, "step": 643 }, { "epoch": 2.22, "learning_rate": 1.8767547370160667e-05, "loss": 0.3525, "step": 644 }, { "epoch": 2.22, "learning_rate": 1.8763066800438638e-05, "loss": 0.3945, "step": 645 }, { "epoch": 2.23, "learning_rate": 1.875857863780609e-05, "loss": 0.3209, "step": 646 }, { "epoch": 2.23, "learning_rate": 1.8754082886151857e-05, "loss": 0.2923, "step": 647 }, { "epoch": 2.23, "learning_rate": 1.874957954937138e-05, "loss": 0.3017, "step": 648 }, { "epoch": 2.24, "learning_rate": 1.874506863136664e-05, "loss": 0.2917, "step": 649 }, { "epoch": 2.24, "learning_rate": 1.8740550136046195e-05, "loss": 0.2908, "step": 650 }, { "epoch": 2.24, "learning_rate": 1.8736024067325188e-05, "loss": 0.348, "step": 651 }, { "epoch": 2.25, "learning_rate": 1.87314904291253e-05, "loss": 0.3147, "step": 652 }, { "epoch": 2.25, "learning_rate": 1.8726949225374782e-05, "loss": 0.3156, "step": 653 }, { "epoch": 2.26, "learning_rate": 1.8722400460008437e-05, "loss": 0.3469, "step": 654 }, { "epoch": 2.26, "learning_rate": 1.8717844136967626e-05, "loss": 0.2814, "step": 655 }, { "epoch": 2.26, "learning_rate": 1.8713280260200245e-05, "loss": 0.2785, "step": 656 }, { "epoch": 2.27, "learning_rate": 1.8708708833660755e-05, "loss": 0.3207, "step": 657 }, { "epoch": 2.27, "learning_rate": 1.8704129861310137e-05, "loss": 0.2985, "step": 658 }, { "epoch": 2.27, "learning_rate": 1.8699543347115932e-05, "loss": 0.3012, "step": 659 }, { "epoch": 2.28, "learning_rate": 1.869494929505219e-05, "loss": 0.3129, "step": 660 }, { "epoch": 2.28, "learning_rate": 1.8690347709099522e-05, "loss": 0.3005, "step": 661 }, { "epoch": 2.28, "learning_rate": 1.8685738593245038e-05, "loss": 0.2954, "step": 662 }, { "epoch": 2.29, "learning_rate": 1.8681121951482397e-05, "loss": 0.2678, "step": 663 }, { "epoch": 2.29, "learning_rate": 1.867649778781176e-05, "loss": 0.3719, "step": 664 }, { "epoch": 2.29, "learning_rate": 1.8671866106239812e-05, "loss": 0.3246, "step": 665 }, { "epoch": 2.3, "learning_rate": 1.8667226910779767e-05, "loss": 0.2723, "step": 666 }, { "epoch": 2.3, "learning_rate": 1.866258020545132e-05, "loss": 0.3147, "step": 667 }, { "epoch": 2.3, "learning_rate": 1.86579259942807e-05, "loss": 0.3049, "step": 668 }, { "epoch": 2.31, "learning_rate": 1.8653264281300622e-05, "loss": 0.3339, "step": 669 }, { "epoch": 2.31, "learning_rate": 1.8648595070550312e-05, "loss": 0.3354, "step": 670 }, { "epoch": 2.31, "learning_rate": 1.8643918366075485e-05, "loss": 0.3176, "step": 671 }, { "epoch": 2.32, "learning_rate": 1.8639234171928355e-05, "loss": 0.2774, "step": 672 }, { "epoch": 2.32, "learning_rate": 1.863454249216762e-05, "loss": 0.2808, "step": 673 }, { "epoch": 2.32, "learning_rate": 1.8629843330858472e-05, "loss": 0.3206, "step": 674 }, { "epoch": 2.33, "learning_rate": 1.8625136692072577e-05, "loss": 0.3595, "step": 675 }, { "epoch": 2.33, "learning_rate": 1.8620422579888082e-05, "loss": 0.3003, "step": 676 }, { "epoch": 2.33, "learning_rate": 1.8615700998389612e-05, "loss": 0.3475, "step": 677 }, { "epoch": 2.34, "learning_rate": 1.8610971951668265e-05, "loss": 0.2942, "step": 678 }, { "epoch": 2.34, "learning_rate": 1.8606235443821602e-05, "loss": 0.3123, "step": 679 }, { "epoch": 2.34, "learning_rate": 1.860149147895366e-05, "loss": 0.2984, "step": 680 }, { "epoch": 2.35, "learning_rate": 1.8596740061174912e-05, "loss": 0.3126, "step": 681 }, { "epoch": 2.35, "learning_rate": 1.8591981194602322e-05, "loss": 0.3477, "step": 682 }, { "epoch": 2.36, "learning_rate": 1.858721488335929e-05, "loss": 0.328, "step": 683 }, { "epoch": 2.36, "learning_rate": 1.8582441131575658e-05, "loss": 0.3073, "step": 684 }, { "epoch": 2.36, "learning_rate": 1.8577659943387737e-05, "loss": 0.3348, "step": 685 }, { "epoch": 2.37, "learning_rate": 1.8572871322938267e-05, "loss": 0.3657, "step": 686 }, { "epoch": 2.37, "learning_rate": 1.856807527437643e-05, "loss": 0.342, "step": 687 }, { "epoch": 2.37, "learning_rate": 1.8563271801857844e-05, "loss": 0.3195, "step": 688 }, { "epoch": 2.38, "learning_rate": 1.8558460909544564e-05, "loss": 0.3455, "step": 689 }, { "epoch": 2.38, "learning_rate": 1.855364260160507e-05, "loss": 0.3452, "step": 690 }, { "epoch": 2.38, "learning_rate": 1.8548816882214262e-05, "loss": 0.3686, "step": 691 }, { "epoch": 2.39, "learning_rate": 1.8543983755553474e-05, "loss": 0.2907, "step": 692 }, { "epoch": 2.39, "learning_rate": 1.8539143225810453e-05, "loss": 0.3427, "step": 693 }, { "epoch": 2.39, "learning_rate": 1.8534295297179354e-05, "loss": 0.366, "step": 694 }, { "epoch": 2.4, "learning_rate": 1.852943997386075e-05, "loss": 0.362, "step": 695 }, { "epoch": 2.4, "learning_rate": 1.8524577260061628e-05, "loss": 0.3233, "step": 696 }, { "epoch": 2.4, "learning_rate": 1.851970715999536e-05, "loss": 0.3113, "step": 697 }, { "epoch": 2.41, "learning_rate": 1.851482967788173e-05, "loss": 0.256, "step": 698 }, { "epoch": 2.41, "learning_rate": 1.850994481794692e-05, "loss": 0.2707, "step": 699 }, { "epoch": 2.41, "learning_rate": 1.85050525844235e-05, "loss": 0.27, "step": 700 }, { "epoch": 2.42, "learning_rate": 1.850015298155043e-05, "loss": 0.3228, "step": 701 }, { "epoch": 2.42, "learning_rate": 1.8495246013573057e-05, "loss": 0.3385, "step": 702 }, { "epoch": 2.42, "learning_rate": 1.8490331684743105e-05, "loss": 0.3488, "step": 703 }, { "epoch": 2.43, "learning_rate": 1.848540999931868e-05, "loss": 0.3022, "step": 704 }, { "epoch": 2.43, "learning_rate": 1.848048096156426e-05, "loss": 0.3524, "step": 705 }, { "epoch": 2.43, "learning_rate": 1.84755445757507e-05, "loss": 0.3235, "step": 706 }, { "epoch": 2.44, "learning_rate": 1.8470600846155213e-05, "loss": 0.2786, "step": 707 }, { "epoch": 2.44, "learning_rate": 1.8465649777061377e-05, "loss": 0.2982, "step": 708 }, { "epoch": 2.44, "learning_rate": 1.846069137275914e-05, "loss": 0.3124, "step": 709 }, { "epoch": 2.45, "learning_rate": 1.8455725637544784e-05, "loss": 0.3215, "step": 710 }, { "epoch": 2.45, "learning_rate": 1.8450752575720967e-05, "loss": 0.3181, "step": 711 }, { "epoch": 2.46, "learning_rate": 1.8445772191596676e-05, "loss": 0.3211, "step": 712 }, { "epoch": 2.46, "learning_rate": 1.8440784489487256e-05, "loss": 0.308, "step": 713 }, { "epoch": 2.46, "learning_rate": 1.843578947371439e-05, "loss": 0.3133, "step": 714 }, { "epoch": 2.47, "learning_rate": 1.8430787148606087e-05, "loss": 0.3085, "step": 715 }, { "epoch": 2.47, "learning_rate": 1.8425777518496707e-05, "loss": 0.3024, "step": 716 }, { "epoch": 2.47, "learning_rate": 1.8420760587726925e-05, "loss": 0.3138, "step": 717 }, { "epoch": 2.48, "learning_rate": 1.841573636064375e-05, "loss": 0.2737, "step": 718 }, { "epoch": 2.48, "learning_rate": 1.8410704841600506e-05, "loss": 0.3332, "step": 719 }, { "epoch": 2.48, "learning_rate": 1.8405666034956842e-05, "loss": 0.3205, "step": 720 }, { "epoch": 2.49, "learning_rate": 1.8400619945078725e-05, "loss": 0.3418, "step": 721 }, { "epoch": 2.49, "learning_rate": 1.8395566576338416e-05, "loss": 0.3023, "step": 722 }, { "epoch": 2.49, "learning_rate": 1.8390505933114503e-05, "loss": 0.3298, "step": 723 }, { "epoch": 2.5, "learning_rate": 1.8385438019791862e-05, "loss": 0.2921, "step": 724 }, { "epoch": 2.5, "learning_rate": 1.8380362840761675e-05, "loss": 0.3397, "step": 725 }, { "epoch": 2.5, "learning_rate": 1.837528040042142e-05, "loss": 0.3264, "step": 726 }, { "epoch": 2.51, "learning_rate": 1.8370190703174862e-05, "loss": 0.3337, "step": 727 }, { "epoch": 2.51, "learning_rate": 1.836509375343206e-05, "loss": 0.2954, "step": 728 }, { "epoch": 2.51, "learning_rate": 1.8359989555609355e-05, "loss": 0.3333, "step": 729 }, { "epoch": 2.52, "learning_rate": 1.8354878114129368e-05, "loss": 0.3365, "step": 730 }, { "epoch": 2.52, "learning_rate": 1.834975943342099e-05, "loss": 0.2983, "step": 731 }, { "epoch": 2.52, "learning_rate": 1.834463351791939e-05, "loss": 0.2924, "step": 732 }, { "epoch": 2.53, "learning_rate": 1.8339500372066018e-05, "loss": 0.2817, "step": 733 }, { "epoch": 2.53, "learning_rate": 1.8334360000308563e-05, "loss": 0.3146, "step": 734 }, { "epoch": 2.53, "learning_rate": 1.8329212407100996e-05, "loss": 0.3219, "step": 735 }, { "epoch": 2.54, "learning_rate": 1.8324057596903534e-05, "loss": 0.3792, "step": 736 }, { "epoch": 2.54, "learning_rate": 1.8318895574182657e-05, "loss": 0.3396, "step": 737 }, { "epoch": 2.54, "learning_rate": 1.8313726343411085e-05, "loss": 0.3006, "step": 738 }, { "epoch": 2.55, "learning_rate": 1.830854990906779e-05, "loss": 0.3356, "step": 739 }, { "epoch": 2.55, "learning_rate": 1.8303366275637977e-05, "loss": 0.3694, "step": 740 }, { "epoch": 2.56, "learning_rate": 1.82981754476131e-05, "loss": 0.3364, "step": 741 }, { "epoch": 2.56, "learning_rate": 1.829297742949084e-05, "loss": 0.3412, "step": 742 }, { "epoch": 2.56, "learning_rate": 1.8287772225775105e-05, "loss": 0.3779, "step": 743 }, { "epoch": 2.57, "learning_rate": 1.8282559840976043e-05, "loss": 0.3142, "step": 744 }, { "epoch": 2.57, "learning_rate": 1.827734027961001e-05, "loss": 0.3578, "step": 745 }, { "epoch": 2.57, "learning_rate": 1.827211354619958e-05, "loss": 0.3569, "step": 746 }, { "epoch": 2.58, "learning_rate": 1.8266879645273557e-05, "loss": 0.3051, "step": 747 }, { "epoch": 2.58, "learning_rate": 1.8261638581366937e-05, "loss": 0.3327, "step": 748 }, { "epoch": 2.58, "learning_rate": 1.825639035902093e-05, "loss": 0.34, "step": 749 }, { "epoch": 2.59, "learning_rate": 1.8251134982782952e-05, "loss": 0.3269, "step": 750 }, { "epoch": 2.59, "learning_rate": 1.8245872457206614e-05, "loss": 0.2926, "step": 751 }, { "epoch": 2.59, "learning_rate": 1.8240602786851726e-05, "loss": 0.2558, "step": 752 }, { "epoch": 2.6, "learning_rate": 1.8235325976284276e-05, "loss": 0.3286, "step": 753 }, { "epoch": 2.6, "learning_rate": 1.8230042030076454e-05, "loss": 0.3168, "step": 754 }, { "epoch": 2.6, "learning_rate": 1.8224750952806626e-05, "loss": 0.3998, "step": 755 }, { "epoch": 2.61, "learning_rate": 1.8219452749059332e-05, "loss": 0.2971, "step": 756 }, { "epoch": 2.61, "learning_rate": 1.82141474234253e-05, "loss": 0.356, "step": 757 }, { "epoch": 2.61, "learning_rate": 1.8208834980501417e-05, "loss": 0.3807, "step": 758 }, { "epoch": 2.62, "learning_rate": 1.8203515424890738e-05, "loss": 0.3043, "step": 759 }, { "epoch": 2.62, "learning_rate": 1.8198188761202487e-05, "loss": 0.3252, "step": 760 }, { "epoch": 2.62, "learning_rate": 1.8192854994052047e-05, "loss": 0.331, "step": 761 }, { "epoch": 2.63, "learning_rate": 1.8187514128060946e-05, "loss": 0.3487, "step": 762 }, { "epoch": 2.63, "learning_rate": 1.8182166167856875e-05, "loss": 0.2814, "step": 763 }, { "epoch": 2.63, "learning_rate": 1.8176811118073664e-05, "loss": 0.3439, "step": 764 }, { "epoch": 2.64, "learning_rate": 1.8171448983351284e-05, "loss": 0.3069, "step": 765 }, { "epoch": 2.64, "learning_rate": 1.816607976833586e-05, "loss": 0.3647, "step": 766 }, { "epoch": 2.64, "learning_rate": 1.816070347767963e-05, "loss": 0.3498, "step": 767 }, { "epoch": 2.65, "learning_rate": 1.8155320116040983e-05, "loss": 0.3732, "step": 768 }, { "epoch": 2.65, "learning_rate": 1.814992968808442e-05, "loss": 0.3235, "step": 769 }, { "epoch": 2.66, "learning_rate": 1.814453219848057e-05, "loss": 0.3175, "step": 770 }, { "epoch": 2.66, "learning_rate": 1.8139127651906183e-05, "loss": 0.3544, "step": 771 }, { "epoch": 2.66, "learning_rate": 1.8133716053044123e-05, "loss": 0.3301, "step": 772 }, { "epoch": 2.67, "learning_rate": 1.812829740658336e-05, "loss": 0.3047, "step": 773 }, { "epoch": 2.67, "learning_rate": 1.812287171721897e-05, "loss": 0.3145, "step": 774 }, { "epoch": 2.67, "learning_rate": 1.811743898965215e-05, "loss": 0.3478, "step": 775 }, { "epoch": 2.68, "learning_rate": 1.8111999228590167e-05, "loss": 0.3531, "step": 776 }, { "epoch": 2.68, "learning_rate": 1.81065524387464e-05, "loss": 0.4163, "step": 777 }, { "epoch": 2.68, "learning_rate": 1.8101098624840318e-05, "loss": 0.34, "step": 778 }, { "epoch": 2.69, "learning_rate": 1.809563779159746e-05, "loss": 0.2707, "step": 779 }, { "epoch": 2.69, "learning_rate": 1.8090169943749477e-05, "loss": 0.3973, "step": 780 }, { "epoch": 2.69, "learning_rate": 1.8084695086034064e-05, "loss": 0.3142, "step": 781 }, { "epoch": 2.7, "learning_rate": 1.8079213223195018e-05, "loss": 0.3138, "step": 782 }, { "epoch": 2.7, "learning_rate": 1.8073724359982184e-05, "loss": 0.2876, "step": 783 }, { "epoch": 2.7, "learning_rate": 1.806822850115149e-05, "loss": 0.354, "step": 784 }, { "epoch": 2.71, "learning_rate": 1.8062725651464913e-05, "loss": 0.326, "step": 785 }, { "epoch": 2.71, "learning_rate": 1.8057215815690494e-05, "loss": 0.385, "step": 786 }, { "epoch": 2.71, "learning_rate": 1.8051698998602324e-05, "loss": 0.3341, "step": 787 }, { "epoch": 2.72, "learning_rate": 1.804617520498055e-05, "loss": 0.3058, "step": 788 }, { "epoch": 2.72, "learning_rate": 1.8040644439611348e-05, "loss": 0.3593, "step": 789 }, { "epoch": 2.72, "learning_rate": 1.8035106707286957e-05, "loss": 0.3193, "step": 790 }, { "epoch": 2.73, "learning_rate": 1.8029562012805627e-05, "loss": 0.3916, "step": 791 }, { "epoch": 2.73, "learning_rate": 1.802401036097167e-05, "loss": 0.3466, "step": 792 }, { "epoch": 2.73, "learning_rate": 1.8018451756595395e-05, "loss": 0.357, "step": 793 }, { "epoch": 2.74, "learning_rate": 1.8012886204493164e-05, "loss": 0.3643, "step": 794 }, { "epoch": 2.74, "learning_rate": 1.8007313709487334e-05, "loss": 0.2961, "step": 795 }, { "epoch": 2.74, "learning_rate": 1.8001734276406302e-05, "loss": 0.3252, "step": 796 }, { "epoch": 2.75, "learning_rate": 1.7996147910084458e-05, "loss": 0.3616, "step": 797 }, { "epoch": 2.75, "learning_rate": 1.79905546153622e-05, "loss": 0.3091, "step": 798 }, { "epoch": 2.76, "learning_rate": 1.798495439708594e-05, "loss": 0.37, "step": 799 }, { "epoch": 2.76, "learning_rate": 1.7979347260108088e-05, "loss": 0.3167, "step": 800 }, { "epoch": 2.76, "learning_rate": 1.7973733209287036e-05, "loss": 0.3335, "step": 801 }, { "epoch": 2.77, "learning_rate": 1.7968112249487183e-05, "loss": 0.364, "step": 802 }, { "epoch": 2.77, "learning_rate": 1.7962484385578904e-05, "loss": 0.3602, "step": 803 }, { "epoch": 2.77, "learning_rate": 1.7956849622438554e-05, "loss": 0.3745, "step": 804 }, { "epoch": 2.78, "learning_rate": 1.795120796494848e-05, "loss": 0.2904, "step": 805 }, { "epoch": 2.78, "learning_rate": 1.7945559417996984e-05, "loss": 0.3567, "step": 806 }, { "epoch": 2.78, "learning_rate": 1.7939903986478354e-05, "loss": 0.3896, "step": 807 }, { "epoch": 2.79, "learning_rate": 1.7934241675292834e-05, "loss": 0.3144, "step": 808 }, { "epoch": 2.79, "learning_rate": 1.792857248934663e-05, "loss": 0.2927, "step": 809 }, { "epoch": 2.79, "learning_rate": 1.792289643355191e-05, "loss": 0.2922, "step": 810 }, { "epoch": 2.8, "learning_rate": 1.7917213512826785e-05, "loss": 0.317, "step": 811 }, { "epoch": 2.8, "learning_rate": 1.7911523732095322e-05, "loss": 0.2877, "step": 812 }, { "epoch": 2.8, "learning_rate": 1.7905827096287532e-05, "loss": 0.3419, "step": 813 }, { "epoch": 2.81, "learning_rate": 1.790012361033936e-05, "loss": 0.3347, "step": 814 }, { "epoch": 2.81, "learning_rate": 1.7894413279192693e-05, "loss": 0.3244, "step": 815 }, { "epoch": 2.81, "learning_rate": 1.7888696107795343e-05, "loss": 0.2911, "step": 816 }, { "epoch": 2.82, "learning_rate": 1.7882972101101054e-05, "loss": 0.3225, "step": 817 }, { "epoch": 2.82, "learning_rate": 1.787724126406949e-05, "loss": 0.2958, "step": 818 }, { "epoch": 2.82, "learning_rate": 1.7871503601666233e-05, "loss": 0.3017, "step": 819 }, { "epoch": 2.83, "learning_rate": 1.7865759118862784e-05, "loss": 0.3398, "step": 820 }, { "epoch": 2.83, "learning_rate": 1.786000782063654e-05, "loss": 0.2627, "step": 821 }, { "epoch": 2.83, "learning_rate": 1.785424971197082e-05, "loss": 0.3112, "step": 822 }, { "epoch": 2.84, "learning_rate": 1.7848484797854838e-05, "loss": 0.3737, "step": 823 }, { "epoch": 2.84, "learning_rate": 1.7842713083283695e-05, "loss": 0.3143, "step": 824 }, { "epoch": 2.84, "learning_rate": 1.78369345732584e-05, "loss": 0.3099, "step": 825 }, { "epoch": 2.85, "learning_rate": 1.7831149272785843e-05, "loss": 0.2939, "step": 826 }, { "epoch": 2.85, "learning_rate": 1.7825357186878788e-05, "loss": 0.3187, "step": 827 }, { "epoch": 2.86, "learning_rate": 1.7819558320555902e-05, "loss": 0.3053, "step": 828 }, { "epoch": 2.86, "learning_rate": 1.7813752678841702e-05, "loss": 0.406, "step": 829 }, { "epoch": 2.86, "learning_rate": 1.7807940266766595e-05, "loss": 0.3401, "step": 830 }, { "epoch": 2.87, "learning_rate": 1.780212108936684e-05, "loss": 0.3295, "step": 831 }, { "epoch": 2.87, "learning_rate": 1.779629515168456e-05, "loss": 0.3415, "step": 832 }, { "epoch": 2.87, "learning_rate": 1.7790462458767747e-05, "loss": 0.3239, "step": 833 }, { "epoch": 2.88, "learning_rate": 1.7784623015670237e-05, "loss": 0.3762, "step": 834 }, { "epoch": 2.88, "learning_rate": 1.7778776827451715e-05, "loss": 0.3866, "step": 835 }, { "epoch": 2.88, "learning_rate": 1.777292389917771e-05, "loss": 0.3316, "step": 836 }, { "epoch": 2.89, "learning_rate": 1.7767064235919594e-05, "loss": 0.2515, "step": 837 }, { "epoch": 2.89, "learning_rate": 1.776119784275457e-05, "loss": 0.3082, "step": 838 }, { "epoch": 2.89, "learning_rate": 1.7755324724765688e-05, "loss": 0.2904, "step": 839 }, { "epoch": 2.9, "learning_rate": 1.7749444887041797e-05, "loss": 0.3226, "step": 840 }, { "epoch": 2.9, "learning_rate": 1.7743558334677594e-05, "loss": 0.2866, "step": 841 }, { "epoch": 2.9, "learning_rate": 1.773766507277358e-05, "loss": 0.3997, "step": 842 }, { "epoch": 2.91, "learning_rate": 1.7731765106436073e-05, "loss": 0.3232, "step": 843 }, { "epoch": 2.91, "learning_rate": 1.7725858440777204e-05, "loss": 0.3011, "step": 844 }, { "epoch": 2.91, "learning_rate": 1.7719945080914902e-05, "loss": 0.3502, "step": 845 }, { "epoch": 2.92, "learning_rate": 1.7714025031972904e-05, "loss": 0.33, "step": 846 }, { "epoch": 2.92, "learning_rate": 1.7708098299080732e-05, "loss": 0.3447, "step": 847 }, { "epoch": 2.92, "learning_rate": 1.770216488737371e-05, "loss": 0.3093, "step": 848 }, { "epoch": 2.93, "learning_rate": 1.7696224801992947e-05, "loss": 0.3293, "step": 849 }, { "epoch": 2.93, "learning_rate": 1.7690278048085327e-05, "loss": 0.3167, "step": 850 }, { "epoch": 2.93, "learning_rate": 1.7684324630803523e-05, "loss": 0.3051, "step": 851 }, { "epoch": 2.94, "learning_rate": 1.767836455530598e-05, "loss": 0.3119, "step": 852 }, { "epoch": 2.94, "learning_rate": 1.767239782675689e-05, "loss": 0.3049, "step": 853 }, { "epoch": 2.94, "learning_rate": 1.766642445032625e-05, "loss": 0.3235, "step": 854 }, { "epoch": 2.95, "learning_rate": 1.766044443118978e-05, "loss": 0.3723, "step": 855 }, { "epoch": 2.95, "learning_rate": 1.7654457774528978e-05, "loss": 0.3936, "step": 856 }, { "epoch": 2.96, "learning_rate": 1.7648464485531087e-05, "loss": 0.3072, "step": 857 }, { "epoch": 2.96, "learning_rate": 1.764246456938909e-05, "loss": 0.3227, "step": 858 }, { "epoch": 2.96, "learning_rate": 1.7636458031301725e-05, "loss": 0.358, "step": 859 }, { "epoch": 2.97, "learning_rate": 1.763044487647345e-05, "loss": 0.3375, "step": 860 }, { "epoch": 2.97, "learning_rate": 1.762442511011448e-05, "loss": 0.3773, "step": 861 }, { "epoch": 2.97, "learning_rate": 1.7618398737440736e-05, "loss": 0.38, "step": 862 }, { "epoch": 2.98, "learning_rate": 1.7612365763673875e-05, "loss": 0.325, "step": 863 }, { "epoch": 2.98, "learning_rate": 1.7606326194041274e-05, "loss": 0.3278, "step": 864 }, { "epoch": 2.98, "learning_rate": 1.7600280033776018e-05, "loss": 0.3437, "step": 865 }, { "epoch": 2.99, "learning_rate": 1.759422728811691e-05, "loss": 0.3404, "step": 866 }, { "epoch": 2.99, "learning_rate": 1.7588167962308458e-05, "loss": 0.3472, "step": 867 }, { "epoch": 2.99, "learning_rate": 1.7582102061600862e-05, "loss": 0.3474, "step": 868 }, { "epoch": 3.0, "learning_rate": 1.7576029591250036e-05, "loss": 0.3618, "step": 869 }, { "epoch": 3.0, "learning_rate": 1.7569950556517566e-05, "loss": 0.2289, "step": 870 }, { "epoch": 3.0, "learning_rate": 1.7563864962670747e-05, "loss": 0.1231, "step": 871 }, { "epoch": 3.01, "learning_rate": 1.755777281498254e-05, "loss": 0.1747, "step": 872 }, { "epoch": 3.01, "learning_rate": 1.7551674118731592e-05, "loss": 0.134, "step": 873 }, { "epoch": 3.01, "learning_rate": 1.7545568879202228e-05, "loss": 0.144, "step": 874 }, { "epoch": 3.02, "learning_rate": 1.7539457101684434e-05, "loss": 0.1723, "step": 875 }, { "epoch": 3.02, "learning_rate": 1.7533338791473872e-05, "loss": 0.1318, "step": 876 }, { "epoch": 3.02, "learning_rate": 1.7527213953871848e-05, "loss": 0.1658, "step": 877 }, { "epoch": 3.03, "learning_rate": 1.7521082594185337e-05, "loss": 0.1418, "step": 878 }, { "epoch": 3.03, "learning_rate": 1.7514944717726962e-05, "loss": 0.1399, "step": 879 }, { "epoch": 3.03, "learning_rate": 1.7508800329814993e-05, "loss": 0.1534, "step": 880 }, { "epoch": 3.04, "learning_rate": 1.7502649435773343e-05, "loss": 0.1654, "step": 881 }, { "epoch": 3.04, "learning_rate": 1.749649204093155e-05, "loss": 0.1466, "step": 882 }, { "epoch": 3.04, "learning_rate": 1.749032815062481e-05, "loss": 0.1438, "step": 883 }, { "epoch": 3.05, "learning_rate": 1.748415777019392e-05, "loss": 0.1409, "step": 884 }, { "epoch": 3.05, "learning_rate": 1.747798090498532e-05, "loss": 0.1438, "step": 885 }, { "epoch": 3.06, "learning_rate": 1.7471797560351058e-05, "loss": 0.119, "step": 886 }, { "epoch": 3.06, "learning_rate": 1.74656077416488e-05, "loss": 0.1355, "step": 887 }, { "epoch": 3.06, "learning_rate": 1.7459411454241822e-05, "loss": 0.1726, "step": 888 }, { "epoch": 3.07, "learning_rate": 1.7453208703499006e-05, "loss": 0.1519, "step": 889 }, { "epoch": 3.07, "learning_rate": 1.744699949479483e-05, "loss": 0.1733, "step": 890 }, { "epoch": 3.07, "learning_rate": 1.7440783833509366e-05, "loss": 0.1548, "step": 891 }, { "epoch": 3.08, "learning_rate": 1.743456172502829e-05, "loss": 0.14, "step": 892 }, { "epoch": 3.08, "learning_rate": 1.7428333174742847e-05, "loss": 0.149, "step": 893 }, { "epoch": 3.08, "learning_rate": 1.7422098188049885e-05, "loss": 0.1597, "step": 894 }, { "epoch": 3.09, "learning_rate": 1.7415856770351797e-05, "loss": 0.1451, "step": 895 }, { "epoch": 3.09, "learning_rate": 1.740960892705658e-05, "loss": 0.1353, "step": 896 }, { "epoch": 3.09, "learning_rate": 1.7403354663577782e-05, "loss": 0.1338, "step": 897 }, { "epoch": 3.1, "learning_rate": 1.739709398533452e-05, "loss": 0.1499, "step": 898 }, { "epoch": 3.1, "learning_rate": 1.739082689775146e-05, "loss": 0.1782, "step": 899 }, { "epoch": 3.1, "learning_rate": 1.7384553406258842e-05, "loss": 0.149, "step": 900 }, { "epoch": 3.11, "learning_rate": 1.7378273516292425e-05, "loss": 0.154, "step": 901 }, { "epoch": 3.11, "learning_rate": 1.7371987233293538e-05, "loss": 0.1448, "step": 902 }, { "epoch": 3.11, "learning_rate": 1.7365694562709034e-05, "loss": 0.1625, "step": 903 }, { "epoch": 3.12, "learning_rate": 1.735939550999131e-05, "loss": 0.1508, "step": 904 }, { "epoch": 3.12, "learning_rate": 1.735309008059829e-05, "loss": 0.1476, "step": 905 }, { "epoch": 3.12, "learning_rate": 1.7346778279993417e-05, "loss": 0.1299, "step": 906 }, { "epoch": 3.13, "learning_rate": 1.734046011364566e-05, "loss": 0.1755, "step": 907 }, { "epoch": 3.13, "learning_rate": 1.733413558702951e-05, "loss": 0.1429, "step": 908 }, { "epoch": 3.13, "learning_rate": 1.732780470562496e-05, "loss": 0.1647, "step": 909 }, { "epoch": 3.14, "learning_rate": 1.7321467474917502e-05, "loss": 0.1332, "step": 910 }, { "epoch": 3.14, "learning_rate": 1.7315123900398153e-05, "loss": 0.1377, "step": 911 }, { "epoch": 3.14, "learning_rate": 1.7308773987563406e-05, "loss": 0.1991, "step": 912 }, { "epoch": 3.15, "learning_rate": 1.7302417741915246e-05, "loss": 0.1782, "step": 913 }, { "epoch": 3.15, "learning_rate": 1.7296055168961164e-05, "loss": 0.1478, "step": 914 }, { "epoch": 3.16, "learning_rate": 1.7289686274214116e-05, "loss": 0.1334, "step": 915 }, { "epoch": 3.16, "learning_rate": 1.7283311063192542e-05, "loss": 0.1273, "step": 916 }, { "epoch": 3.16, "learning_rate": 1.727692954142035e-05, "loss": 0.1089, "step": 917 }, { "epoch": 3.17, "learning_rate": 1.727054171442692e-05, "loss": 0.1645, "step": 918 }, { "epoch": 3.17, "learning_rate": 1.7264147587747097e-05, "loss": 0.1499, "step": 919 }, { "epoch": 3.17, "learning_rate": 1.7257747166921186e-05, "loss": 0.1378, "step": 920 }, { "epoch": 3.18, "learning_rate": 1.7251340457494934e-05, "loss": 0.1473, "step": 921 }, { "epoch": 3.18, "learning_rate": 1.7244927465019552e-05, "loss": 0.1397, "step": 922 }, { "epoch": 3.18, "learning_rate": 1.7238508195051687e-05, "loss": 0.1349, "step": 923 }, { "epoch": 3.19, "learning_rate": 1.7232082653153422e-05, "loss": 0.1866, "step": 924 }, { "epoch": 3.19, "learning_rate": 1.722565084489228e-05, "loss": 0.1783, "step": 925 }, { "epoch": 3.19, "learning_rate": 1.721921277584122e-05, "loss": 0.1518, "step": 926 }, { "epoch": 3.2, "learning_rate": 1.721276845157861e-05, "loss": 0.1508, "step": 927 }, { "epoch": 3.2, "learning_rate": 1.7206317877688243e-05, "loss": 0.1871, "step": 928 }, { "epoch": 3.2, "learning_rate": 1.7199861059759338e-05, "loss": 0.15, "step": 929 }, { "epoch": 3.21, "learning_rate": 1.7193398003386514e-05, "loss": 0.1662, "step": 930 }, { "epoch": 3.21, "learning_rate": 1.7186928714169795e-05, "loss": 0.1258, "step": 931 }, { "epoch": 3.21, "learning_rate": 1.7180453197714614e-05, "loss": 0.1721, "step": 932 }, { "epoch": 3.22, "learning_rate": 1.717397145963179e-05, "loss": 0.1678, "step": 933 }, { "epoch": 3.22, "learning_rate": 1.716748350553753e-05, "loss": 0.1143, "step": 934 }, { "epoch": 3.22, "learning_rate": 1.716098934105345e-05, "loss": 0.1763, "step": 935 }, { "epoch": 3.23, "learning_rate": 1.715448897180652e-05, "loss": 0.1506, "step": 936 }, { "epoch": 3.23, "learning_rate": 1.71479824034291e-05, "loss": 0.148, "step": 937 }, { "epoch": 3.23, "learning_rate": 1.7141469641558916e-05, "loss": 0.152, "step": 938 }, { "epoch": 3.24, "learning_rate": 1.7134950691839063e-05, "loss": 0.1312, "step": 939 }, { "epoch": 3.24, "learning_rate": 1.7128425559918006e-05, "loss": 0.1621, "step": 940 }, { "epoch": 3.24, "learning_rate": 1.7121894251449543e-05, "loss": 0.1565, "step": 941 }, { "epoch": 3.25, "learning_rate": 1.7115356772092858e-05, "loss": 0.14, "step": 942 }, { "epoch": 3.25, "learning_rate": 1.710881312751244e-05, "loss": 0.1351, "step": 943 }, { "epoch": 3.26, "learning_rate": 1.7102263323378164e-05, "loss": 0.1291, "step": 944 }, { "epoch": 3.26, "learning_rate": 1.709570736536521e-05, "loss": 0.1717, "step": 945 }, { "epoch": 3.26, "learning_rate": 1.7089145259154103e-05, "loss": 0.1327, "step": 946 }, { "epoch": 3.27, "learning_rate": 1.7082577010430694e-05, "loss": 0.1697, "step": 947 }, { "epoch": 3.27, "learning_rate": 1.7076002624886156e-05, "loss": 0.1314, "step": 948 }, { "epoch": 3.27, "learning_rate": 1.7069422108216973e-05, "loss": 0.1554, "step": 949 }, { "epoch": 3.28, "learning_rate": 1.7062835466124953e-05, "loss": 0.1514, "step": 950 }, { "epoch": 3.28, "learning_rate": 1.705624270431721e-05, "loss": 0.1517, "step": 951 }, { "epoch": 3.28, "learning_rate": 1.7049643828506146e-05, "loss": 0.1475, "step": 952 }, { "epoch": 3.29, "learning_rate": 1.7043038844409476e-05, "loss": 0.1891, "step": 953 }, { "epoch": 3.29, "learning_rate": 1.7036427757750205e-05, "loss": 0.1606, "step": 954 }, { "epoch": 3.29, "learning_rate": 1.702981057425662e-05, "loss": 0.133, "step": 955 }, { "epoch": 3.3, "learning_rate": 1.7023187299662294e-05, "loss": 0.1698, "step": 956 }, { "epoch": 3.3, "learning_rate": 1.7016557939706075e-05, "loss": 0.1815, "step": 957 }, { "epoch": 3.3, "learning_rate": 1.7009922500132093e-05, "loss": 0.1489, "step": 958 }, { "epoch": 3.31, "learning_rate": 1.7003280986689733e-05, "loss": 0.1292, "step": 959 }, { "epoch": 3.31, "learning_rate": 1.6996633405133656e-05, "loss": 0.1237, "step": 960 }, { "epoch": 3.31, "learning_rate": 1.6989979761223767e-05, "loss": 0.165, "step": 961 }, { "epoch": 3.32, "learning_rate": 1.6983320060725234e-05, "loss": 0.1371, "step": 962 }, { "epoch": 3.32, "learning_rate": 1.6976654309408464e-05, "loss": 0.1493, "step": 963 }, { "epoch": 3.32, "learning_rate": 1.6969982513049123e-05, "loss": 0.135, "step": 964 }, { "epoch": 3.33, "learning_rate": 1.6963304677428096e-05, "loss": 0.1762, "step": 965 }, { "epoch": 3.33, "learning_rate": 1.695662080833151e-05, "loss": 0.1691, "step": 966 }, { "epoch": 3.33, "learning_rate": 1.694993091155072e-05, "loss": 0.1541, "step": 967 }, { "epoch": 3.34, "learning_rate": 1.6943234992882304e-05, "loss": 0.1433, "step": 968 }, { "epoch": 3.34, "learning_rate": 1.693653305812805e-05, "loss": 0.1479, "step": 969 }, { "epoch": 3.34, "learning_rate": 1.6929825113094972e-05, "loss": 0.1889, "step": 970 }, { "epoch": 3.35, "learning_rate": 1.6923111163595283e-05, "loss": 0.122, "step": 971 }, { "epoch": 3.35, "learning_rate": 1.6916391215446403e-05, "loss": 0.1653, "step": 972 }, { "epoch": 3.36, "learning_rate": 1.690966527447094e-05, "loss": 0.1504, "step": 973 }, { "epoch": 3.36, "learning_rate": 1.6902933346496707e-05, "loss": 0.1844, "step": 974 }, { "epoch": 3.36, "learning_rate": 1.68961954373567e-05, "loss": 0.1434, "step": 975 }, { "epoch": 3.37, "learning_rate": 1.6889451552889092e-05, "loss": 0.1765, "step": 976 }, { "epoch": 3.37, "learning_rate": 1.6882701698937242e-05, "loss": 0.1516, "step": 977 }, { "epoch": 3.37, "learning_rate": 1.6875945881349676e-05, "loss": 0.1512, "step": 978 }, { "epoch": 3.38, "learning_rate": 1.686918410598009e-05, "loss": 0.1417, "step": 979 }, { "epoch": 3.38, "learning_rate": 1.686241637868734e-05, "loss": 0.1451, "step": 980 }, { "epoch": 3.38, "learning_rate": 1.6855642705335438e-05, "loss": 0.1475, "step": 981 }, { "epoch": 3.39, "learning_rate": 1.6848863091793553e-05, "loss": 0.1345, "step": 982 }, { "epoch": 3.39, "learning_rate": 1.6842077543936e-05, "loss": 0.1407, "step": 983 }, { "epoch": 3.39, "learning_rate": 1.6835286067642228e-05, "loss": 0.1588, "step": 984 }, { "epoch": 3.4, "learning_rate": 1.6828488668796836e-05, "loss": 0.148, "step": 985 }, { "epoch": 3.4, "learning_rate": 1.6821685353289542e-05, "loss": 0.169, "step": 986 }, { "epoch": 3.4, "learning_rate": 1.68148761270152e-05, "loss": 0.1541, "step": 987 }, { "epoch": 3.41, "learning_rate": 1.6808060995873776e-05, "loss": 0.2126, "step": 988 }, { "epoch": 3.41, "learning_rate": 1.6801239965770366e-05, "loss": 0.1361, "step": 989 }, { "epoch": 3.41, "learning_rate": 1.6794413042615168e-05, "loss": 0.1915, "step": 990 }, { "epoch": 3.42, "learning_rate": 1.678758023232348e-05, "loss": 0.1406, "step": 991 }, { "epoch": 3.42, "learning_rate": 1.6780741540815716e-05, "loss": 0.1581, "step": 992 }, { "epoch": 3.42, "learning_rate": 1.6773896974017373e-05, "loss": 0.1769, "step": 993 }, { "epoch": 3.43, "learning_rate": 1.676704653785905e-05, "loss": 0.2087, "step": 994 }, { "epoch": 3.43, "learning_rate": 1.6760190238276418e-05, "loss": 0.1833, "step": 995 }, { "epoch": 3.43, "learning_rate": 1.6753328081210244e-05, "loss": 0.1739, "step": 996 }, { "epoch": 3.44, "learning_rate": 1.674646007260636e-05, "loss": 0.1388, "step": 997 }, { "epoch": 3.44, "learning_rate": 1.6739586218415665e-05, "loss": 0.1703, "step": 998 }, { "epoch": 3.44, "learning_rate": 1.6732706524594138e-05, "loss": 0.1588, "step": 999 }, { "epoch": 3.45, "learning_rate": 1.6725820997102804e-05, "loss": 0.1476, "step": 1000 }, { "epoch": 3.45, "learning_rate": 1.6718929641907744e-05, "loss": 0.171, "step": 1001 }, { "epoch": 3.46, "learning_rate": 1.6712032464980094e-05, "loss": 0.1707, "step": 1002 }, { "epoch": 3.46, "learning_rate": 1.6705129472296033e-05, "loss": 0.1718, "step": 1003 }, { "epoch": 3.46, "learning_rate": 1.6698220669836782e-05, "loss": 0.1327, "step": 1004 }, { "epoch": 3.47, "learning_rate": 1.6691306063588583e-05, "loss": 0.2167, "step": 1005 }, { "epoch": 3.47, "learning_rate": 1.6684385659542724e-05, "loss": 0.1735, "step": 1006 }, { "epoch": 3.47, "learning_rate": 1.6677459463695504e-05, "loss": 0.1261, "step": 1007 }, { "epoch": 3.48, "learning_rate": 1.6670527482048246e-05, "loss": 0.1609, "step": 1008 }, { "epoch": 3.48, "learning_rate": 1.6663589720607287e-05, "loss": 0.1767, "step": 1009 }, { "epoch": 3.48, "learning_rate": 1.665664618538397e-05, "loss": 0.1801, "step": 1010 }, { "epoch": 3.49, "learning_rate": 1.6649696882394635e-05, "loss": 0.1658, "step": 1011 }, { "epoch": 3.49, "learning_rate": 1.6642741817660634e-05, "loss": 0.1746, "step": 1012 }, { "epoch": 3.49, "learning_rate": 1.66357809972083e-05, "loss": 0.2139, "step": 1013 }, { "epoch": 3.5, "learning_rate": 1.6628814427068954e-05, "loss": 0.1981, "step": 1014 }, { "epoch": 3.5, "learning_rate": 1.6621842113278902e-05, "loss": 0.1702, "step": 1015 }, { "epoch": 3.5, "learning_rate": 1.6614864061879427e-05, "loss": 0.1529, "step": 1016 }, { "epoch": 3.51, "learning_rate": 1.6607880278916778e-05, "loss": 0.1331, "step": 1017 }, { "epoch": 3.51, "learning_rate": 1.660089077044218e-05, "loss": 0.1838, "step": 1018 }, { "epoch": 3.51, "learning_rate": 1.659389554251181e-05, "loss": 0.1801, "step": 1019 }, { "epoch": 3.52, "learning_rate": 1.6586894601186804e-05, "loss": 0.1702, "step": 1020 }, { "epoch": 3.52, "learning_rate": 1.657988795253325e-05, "loss": 0.2102, "step": 1021 }, { "epoch": 3.52, "learning_rate": 1.6572875602622183e-05, "loss": 0.1759, "step": 1022 }, { "epoch": 3.53, "learning_rate": 1.6565857557529567e-05, "loss": 0.1644, "step": 1023 }, { "epoch": 3.53, "learning_rate": 1.6558833823336308e-05, "loss": 0.1929, "step": 1024 }, { "epoch": 3.53, "learning_rate": 1.655180440612825e-05, "loss": 0.1616, "step": 1025 }, { "epoch": 3.54, "learning_rate": 1.654476931199615e-05, "loss": 0.1775, "step": 1026 }, { "epoch": 3.54, "learning_rate": 1.6537728547035683e-05, "loss": 0.165, "step": 1027 }, { "epoch": 3.54, "learning_rate": 1.6530682117347445e-05, "loss": 0.1717, "step": 1028 }, { "epoch": 3.55, "learning_rate": 1.652363002903693e-05, "loss": 0.1409, "step": 1029 }, { "epoch": 3.55, "learning_rate": 1.6516572288214555e-05, "loss": 0.1673, "step": 1030 }, { "epoch": 3.56, "learning_rate": 1.6509508900995607e-05, "loss": 0.1715, "step": 1031 }, { "epoch": 3.56, "learning_rate": 1.650243987350029e-05, "loss": 0.17, "step": 1032 }, { "epoch": 3.56, "learning_rate": 1.649536521185368e-05, "loss": 0.1493, "step": 1033 }, { "epoch": 3.57, "learning_rate": 1.648828492218574e-05, "loss": 0.2168, "step": 1034 }, { "epoch": 3.57, "learning_rate": 1.6481199010631312e-05, "loss": 0.1523, "step": 1035 }, { "epoch": 3.57, "learning_rate": 1.6474107483330103e-05, "loss": 0.1905, "step": 1036 }, { "epoch": 3.58, "learning_rate": 1.6467010346426688e-05, "loss": 0.2022, "step": 1037 }, { "epoch": 3.58, "learning_rate": 1.6459907606070513e-05, "loss": 0.1816, "step": 1038 }, { "epoch": 3.58, "learning_rate": 1.6452799268415857e-05, "loss": 0.1281, "step": 1039 }, { "epoch": 3.59, "learning_rate": 1.644568533962187e-05, "loss": 0.2052, "step": 1040 }, { "epoch": 3.59, "learning_rate": 1.643856582585254e-05, "loss": 0.1501, "step": 1041 }, { "epoch": 3.59, "learning_rate": 1.6431440733276686e-05, "loss": 0.1759, "step": 1042 }, { "epoch": 3.6, "learning_rate": 1.6424310068067973e-05, "loss": 0.1481, "step": 1043 }, { "epoch": 3.6, "learning_rate": 1.6417173836404888e-05, "loss": 0.1564, "step": 1044 }, { "epoch": 3.6, "learning_rate": 1.6410032044470735e-05, "loss": 0.201, "step": 1045 }, { "epoch": 3.61, "learning_rate": 1.6402884698453656e-05, "loss": 0.1345, "step": 1046 }, { "epoch": 3.61, "learning_rate": 1.6395731804546582e-05, "loss": 0.2473, "step": 1047 }, { "epoch": 3.61, "learning_rate": 1.6388573368947267e-05, "loss": 0.187, "step": 1048 }, { "epoch": 3.62, "learning_rate": 1.6381409397858257e-05, "loss": 0.1985, "step": 1049 }, { "epoch": 3.62, "learning_rate": 1.63742398974869e-05, "loss": 0.1689, "step": 1050 }, { "epoch": 3.62, "learning_rate": 1.6367064874045332e-05, "loss": 0.1647, "step": 1051 }, { "epoch": 3.63, "learning_rate": 1.635988433375048e-05, "loss": 0.1529, "step": 1052 }, { "epoch": 3.63, "learning_rate": 1.6352698282824045e-05, "loss": 0.1553, "step": 1053 }, { "epoch": 3.63, "learning_rate": 1.6345506727492503e-05, "loss": 0.1377, "step": 1054 }, { "epoch": 3.64, "learning_rate": 1.63383096739871e-05, "loss": 0.1559, "step": 1055 }, { "epoch": 3.64, "learning_rate": 1.6331107128543856e-05, "loss": 0.1695, "step": 1056 }, { "epoch": 3.64, "learning_rate": 1.6323899097403536e-05, "loss": 0.2072, "step": 1057 }, { "epoch": 3.65, "learning_rate": 1.6316685586811657e-05, "loss": 0.1872, "step": 1058 }, { "epoch": 3.65, "learning_rate": 1.6309466603018497e-05, "loss": 0.1464, "step": 1059 }, { "epoch": 3.66, "learning_rate": 1.6302242152279068e-05, "loss": 0.1442, "step": 1060 }, { "epoch": 3.66, "learning_rate": 1.6295012240853116e-05, "loss": 0.2276, "step": 1061 }, { "epoch": 3.66, "learning_rate": 1.628777687500513e-05, "loss": 0.1719, "step": 1062 }, { "epoch": 3.67, "learning_rate": 1.628053606100431e-05, "loss": 0.1626, "step": 1063 }, { "epoch": 3.67, "learning_rate": 1.6273289805124588e-05, "loss": 0.1898, "step": 1064 }, { "epoch": 3.67, "learning_rate": 1.6266038113644605e-05, "loss": 0.1949, "step": 1065 }, { "epoch": 3.68, "learning_rate": 1.625878099284772e-05, "loss": 0.1612, "step": 1066 }, { "epoch": 3.68, "learning_rate": 1.6251518449021985e-05, "loss": 0.1743, "step": 1067 }, { "epoch": 3.68, "learning_rate": 1.624425048846016e-05, "loss": 0.195, "step": 1068 }, { "epoch": 3.69, "learning_rate": 1.6236977117459693e-05, "loss": 0.1793, "step": 1069 }, { "epoch": 3.69, "learning_rate": 1.622969834232272e-05, "loss": 0.183, "step": 1070 }, { "epoch": 3.69, "learning_rate": 1.6222414169356066e-05, "loss": 0.1993, "step": 1071 }, { "epoch": 3.7, "learning_rate": 1.6215124604871224e-05, "loss": 0.197, "step": 1072 }, { "epoch": 3.7, "learning_rate": 1.6207829655184366e-05, "loss": 0.1598, "step": 1073 }, { "epoch": 3.7, "learning_rate": 1.620052932661633e-05, "loss": 0.1494, "step": 1074 }, { "epoch": 3.71, "learning_rate": 1.6193223625492604e-05, "loss": 0.1651, "step": 1075 }, { "epoch": 3.71, "learning_rate": 1.618591255814334e-05, "loss": 0.2054, "step": 1076 }, { "epoch": 3.71, "learning_rate": 1.6178596130903345e-05, "loss": 0.1595, "step": 1077 }, { "epoch": 3.72, "learning_rate": 1.6171274350112057e-05, "loss": 0.1999, "step": 1078 }, { "epoch": 3.72, "learning_rate": 1.616394722211357e-05, "loss": 0.1599, "step": 1079 }, { "epoch": 3.72, "learning_rate": 1.6156614753256583e-05, "loss": 0.1413, "step": 1080 }, { "epoch": 3.73, "learning_rate": 1.6149276949894456e-05, "loss": 0.158, "step": 1081 }, { "epoch": 3.73, "learning_rate": 1.6141933818385147e-05, "loss": 0.174, "step": 1082 }, { "epoch": 3.73, "learning_rate": 1.6134585365091243e-05, "loss": 0.1735, "step": 1083 }, { "epoch": 3.74, "learning_rate": 1.612723159637994e-05, "loss": 0.1807, "step": 1084 }, { "epoch": 3.74, "learning_rate": 1.611987251862303e-05, "loss": 0.17, "step": 1085 }, { "epoch": 3.74, "learning_rate": 1.611250813819692e-05, "loss": 0.1619, "step": 1086 }, { "epoch": 3.75, "learning_rate": 1.6105138461482598e-05, "loss": 0.1561, "step": 1087 }, { "epoch": 3.75, "learning_rate": 1.6097763494865656e-05, "loss": 0.1632, "step": 1088 }, { "epoch": 3.76, "learning_rate": 1.6090383244736256e-05, "loss": 0.2062, "step": 1089 }, { "epoch": 3.76, "learning_rate": 1.6082997717489145e-05, "loss": 0.1637, "step": 1090 }, { "epoch": 3.76, "learning_rate": 1.607560691952364e-05, "loss": 0.1574, "step": 1091 }, { "epoch": 3.77, "learning_rate": 1.6068210857243625e-05, "loss": 0.188, "step": 1092 }, { "epoch": 3.77, "learning_rate": 1.6060809537057546e-05, "loss": 0.2099, "step": 1093 }, { "epoch": 3.77, "learning_rate": 1.6053402965378402e-05, "loss": 0.1718, "step": 1094 }, { "epoch": 3.78, "learning_rate": 1.6045991148623752e-05, "loss": 0.1951, "step": 1095 }, { "epoch": 3.78, "learning_rate": 1.6038574093215683e-05, "loss": 0.1916, "step": 1096 }, { "epoch": 3.78, "learning_rate": 1.603115180558084e-05, "loss": 0.1556, "step": 1097 }, { "epoch": 3.79, "learning_rate": 1.6023724292150387e-05, "loss": 0.2025, "step": 1098 }, { "epoch": 3.79, "learning_rate": 1.6016291559360023e-05, "loss": 0.2086, "step": 1099 }, { "epoch": 3.79, "learning_rate": 1.600885361364997e-05, "loss": 0.2026, "step": 1100 }, { "epoch": 3.8, "learning_rate": 1.6001410461464955e-05, "loss": 0.1646, "step": 1101 }, { "epoch": 3.8, "learning_rate": 1.599396210925424e-05, "loss": 0.1472, "step": 1102 }, { "epoch": 3.8, "learning_rate": 1.5986508563471567e-05, "loss": 0.1425, "step": 1103 }, { "epoch": 3.81, "learning_rate": 1.597904983057519e-05, "loss": 0.1388, "step": 1104 }, { "epoch": 3.81, "learning_rate": 1.5971585917027864e-05, "loss": 0.1455, "step": 1105 }, { "epoch": 3.81, "learning_rate": 1.596411682929682e-05, "loss": 0.2155, "step": 1106 }, { "epoch": 3.82, "learning_rate": 1.5956642573853784e-05, "loss": 0.1526, "step": 1107 }, { "epoch": 3.82, "learning_rate": 1.5949163157174944e-05, "loss": 0.2061, "step": 1108 }, { "epoch": 3.82, "learning_rate": 1.5941678585740976e-05, "loss": 0.1819, "step": 1109 }, { "epoch": 3.83, "learning_rate": 1.5934188866037017e-05, "loss": 0.1787, "step": 1110 }, { "epoch": 3.83, "learning_rate": 1.5926694004552665e-05, "loss": 0.1562, "step": 1111 }, { "epoch": 3.83, "learning_rate": 1.5919194007781958e-05, "loss": 0.1767, "step": 1112 }, { "epoch": 3.84, "learning_rate": 1.591168888222342e-05, "loss": 0.1778, "step": 1113 }, { "epoch": 3.84, "learning_rate": 1.5904178634379982e-05, "loss": 0.1607, "step": 1114 }, { "epoch": 3.84, "learning_rate": 1.5896663270759034e-05, "loss": 0.156, "step": 1115 }, { "epoch": 3.85, "learning_rate": 1.5889142797872387e-05, "loss": 0.1328, "step": 1116 }, { "epoch": 3.85, "learning_rate": 1.588161722223629e-05, "loss": 0.227, "step": 1117 }, { "epoch": 3.86, "learning_rate": 1.5874086550371407e-05, "loss": 0.1495, "step": 1118 }, { "epoch": 3.86, "learning_rate": 1.5866550788802815e-05, "loss": 0.1349, "step": 1119 }, { "epoch": 3.86, "learning_rate": 1.5859009944060005e-05, "loss": 0.1755, "step": 1120 }, { "epoch": 3.87, "learning_rate": 1.585146402267688e-05, "loss": 0.1316, "step": 1121 }, { "epoch": 3.87, "learning_rate": 1.5843913031191722e-05, "loss": 0.2185, "step": 1122 }, { "epoch": 3.87, "learning_rate": 1.5836356976147226e-05, "loss": 0.1886, "step": 1123 }, { "epoch": 3.88, "learning_rate": 1.5828795864090466e-05, "loss": 0.1728, "step": 1124 }, { "epoch": 3.88, "learning_rate": 1.5821229701572897e-05, "loss": 0.2339, "step": 1125 }, { "epoch": 3.88, "learning_rate": 1.5813658495150347e-05, "loss": 0.1387, "step": 1126 }, { "epoch": 3.89, "learning_rate": 1.5806082251383023e-05, "loss": 0.1437, "step": 1127 }, { "epoch": 3.89, "learning_rate": 1.5798500976835493e-05, "loss": 0.195, "step": 1128 }, { "epoch": 3.89, "learning_rate": 1.579091467807668e-05, "loss": 0.1605, "step": 1129 }, { "epoch": 3.9, "learning_rate": 1.5783323361679865e-05, "loss": 0.1807, "step": 1130 }, { "epoch": 3.9, "learning_rate": 1.5775727034222675e-05, "loss": 0.1763, "step": 1131 }, { "epoch": 3.9, "learning_rate": 1.5768125702287082e-05, "loss": 0.1741, "step": 1132 }, { "epoch": 3.91, "learning_rate": 1.576051937245939e-05, "loss": 0.1759, "step": 1133 }, { "epoch": 3.91, "learning_rate": 1.575290805133023e-05, "loss": 0.2288, "step": 1134 }, { "epoch": 3.91, "learning_rate": 1.5745291745494563e-05, "loss": 0.2291, "step": 1135 }, { "epoch": 3.92, "learning_rate": 1.5737670461551676e-05, "loss": 0.1796, "step": 1136 }, { "epoch": 3.92, "learning_rate": 1.5730044206105156e-05, "loss": 0.1514, "step": 1137 }, { "epoch": 3.92, "learning_rate": 1.5722412985762904e-05, "loss": 0.1615, "step": 1138 }, { "epoch": 3.93, "learning_rate": 1.5714776807137128e-05, "loss": 0.1399, "step": 1139 }, { "epoch": 3.93, "learning_rate": 1.570713567684432e-05, "loss": 0.1702, "step": 1140 }, { "epoch": 3.93, "learning_rate": 1.569948960150527e-05, "loss": 0.1451, "step": 1141 }, { "epoch": 3.94, "learning_rate": 1.5691838587745058e-05, "loss": 0.1724, "step": 1142 }, { "epoch": 3.94, "learning_rate": 1.568418264219303e-05, "loss": 0.1296, "step": 1143 }, { "epoch": 3.94, "learning_rate": 1.5676521771482818e-05, "loss": 0.1548, "step": 1144 }, { "epoch": 3.95, "learning_rate": 1.566885598225231e-05, "loss": 0.1759, "step": 1145 }, { "epoch": 3.95, "learning_rate": 1.5661185281143666e-05, "loss": 0.1836, "step": 1146 }, { "epoch": 3.96, "learning_rate": 1.56535096748033e-05, "loss": 0.1944, "step": 1147 }, { "epoch": 3.96, "learning_rate": 1.564582916988186e-05, "loss": 0.1884, "step": 1148 }, { "epoch": 3.96, "learning_rate": 1.5638143773034268e-05, "loss": 0.1956, "step": 1149 }, { "epoch": 3.97, "learning_rate": 1.5630453490919663e-05, "loss": 0.1727, "step": 1150 }, { "epoch": 3.97, "learning_rate": 1.562275833020142e-05, "loss": 0.1415, "step": 1151 }, { "epoch": 3.97, "learning_rate": 1.5615058297547144e-05, "loss": 0.1482, "step": 1152 }, { "epoch": 3.98, "learning_rate": 1.5607353399628668e-05, "loss": 0.1352, "step": 1153 }, { "epoch": 3.98, "learning_rate": 1.5599643643122023e-05, "loss": 0.1824, "step": 1154 }, { "epoch": 3.98, "learning_rate": 1.5591929034707468e-05, "loss": 0.1267, "step": 1155 }, { "epoch": 3.99, "learning_rate": 1.558420958106946e-05, "loss": 0.1811, "step": 1156 }, { "epoch": 3.99, "learning_rate": 1.557648528889665e-05, "loss": 0.159, "step": 1157 }, { "epoch": 3.99, "learning_rate": 1.556875616488188e-05, "loss": 0.173, "step": 1158 }, { "epoch": 4.0, "learning_rate": 1.556102221572219e-05, "loss": 0.1551, "step": 1159 }, { "epoch": 4.0, "learning_rate": 1.5553283448118795e-05, "loss": 0.0933, "step": 1160 }, { "epoch": 4.0, "learning_rate": 1.5545539868777075e-05, "loss": 0.1188, "step": 1161 }, { "epoch": 4.01, "learning_rate": 1.5537791484406593e-05, "loss": 0.0854, "step": 1162 }, { "epoch": 4.01, "learning_rate": 1.553003830172107e-05, "loss": 0.0928, "step": 1163 }, { "epoch": 4.01, "learning_rate": 1.5522280327438388e-05, "loss": 0.0678, "step": 1164 }, { "epoch": 4.02, "learning_rate": 1.5514517568280573e-05, "loss": 0.0707, "step": 1165 }, { "epoch": 4.02, "learning_rate": 1.5506750030973805e-05, "loss": 0.0773, "step": 1166 }, { "epoch": 4.02, "learning_rate": 1.54989777222484e-05, "loss": 0.055, "step": 1167 }, { "epoch": 4.03, "learning_rate": 1.549120064883881e-05, "loss": 0.0588, "step": 1168 }, { "epoch": 4.03, "learning_rate": 1.5483418817483607e-05, "loss": 0.0614, "step": 1169 }, { "epoch": 4.03, "learning_rate": 1.5475632234925505e-05, "loss": 0.0555, "step": 1170 }, { "epoch": 4.04, "learning_rate": 1.5467840907911313e-05, "loss": 0.0651, "step": 1171 }, { "epoch": 4.04, "learning_rate": 1.546004484319197e-05, "loss": 0.0827, "step": 1172 }, { "epoch": 4.04, "learning_rate": 1.5452244047522504e-05, "loss": 0.0809, "step": 1173 }, { "epoch": 4.05, "learning_rate": 1.5444438527662046e-05, "loss": 0.0744, "step": 1174 }, { "epoch": 4.05, "learning_rate": 1.5436628290373835e-05, "loss": 0.0887, "step": 1175 }, { "epoch": 4.06, "learning_rate": 1.5428813342425177e-05, "loss": 0.0673, "step": 1176 }, { "epoch": 4.06, "learning_rate": 1.542099369058747e-05, "loss": 0.0916, "step": 1177 }, { "epoch": 4.06, "learning_rate": 1.5413169341636186e-05, "loss": 0.0426, "step": 1178 }, { "epoch": 4.07, "learning_rate": 1.540534030235087e-05, "loss": 0.0721, "step": 1179 }, { "epoch": 4.07, "learning_rate": 1.539750657951513e-05, "loss": 0.0738, "step": 1180 }, { "epoch": 4.07, "learning_rate": 1.5389668179916624e-05, "loss": 0.0632, "step": 1181 }, { "epoch": 4.08, "learning_rate": 1.5381825110347072e-05, "loss": 0.0618, "step": 1182 }, { "epoch": 4.08, "learning_rate": 1.537397737760224e-05, "loss": 0.0435, "step": 1183 }, { "epoch": 4.08, "learning_rate": 1.5366124988481924e-05, "loss": 0.0715, "step": 1184 }, { "epoch": 4.09, "learning_rate": 1.5358267949789968e-05, "loss": 0.0712, "step": 1185 }, { "epoch": 4.09, "learning_rate": 1.5350406268334235e-05, "loss": 0.0793, "step": 1186 }, { "epoch": 4.09, "learning_rate": 1.534253995092662e-05, "loss": 0.0572, "step": 1187 }, { "epoch": 4.1, "learning_rate": 1.533466900438303e-05, "loss": 0.0684, "step": 1188 }, { "epoch": 4.1, "learning_rate": 1.5326793435523374e-05, "loss": 0.073, "step": 1189 }, { "epoch": 4.1, "learning_rate": 1.531891325117158e-05, "loss": 0.0821, "step": 1190 }, { "epoch": 4.11, "learning_rate": 1.5311028458155567e-05, "loss": 0.0625, "step": 1191 }, { "epoch": 4.11, "learning_rate": 1.530313906330726e-05, "loss": 0.0665, "step": 1192 }, { "epoch": 4.11, "learning_rate": 1.5295245073462546e-05, "loss": 0.068, "step": 1193 }, { "epoch": 4.12, "learning_rate": 1.528734649546132e-05, "loss": 0.0643, "step": 1194 }, { "epoch": 4.12, "learning_rate": 1.5279443336147437e-05, "loss": 0.0903, "step": 1195 }, { "epoch": 4.12, "learning_rate": 1.5271535602368724e-05, "loss": 0.0612, "step": 1196 }, { "epoch": 4.13, "learning_rate": 1.526362330097698e-05, "loss": 0.05, "step": 1197 }, { "epoch": 4.13, "learning_rate": 1.5255706438827953e-05, "loss": 0.0665, "step": 1198 }, { "epoch": 4.13, "learning_rate": 1.5247785022781343e-05, "loss": 0.0465, "step": 1199 }, { "epoch": 4.14, "learning_rate": 1.5239859059700794e-05, "loss": 0.0861, "step": 1200 }, { "epoch": 4.14, "learning_rate": 1.52319285564539e-05, "loss": 0.0705, "step": 1201 }, { "epoch": 4.14, "learning_rate": 1.5223993519912177e-05, "loss": 0.0665, "step": 1202 }, { "epoch": 4.15, "learning_rate": 1.5216053956951081e-05, "loss": 0.0673, "step": 1203 }, { "epoch": 4.15, "learning_rate": 1.520810987444998e-05, "loss": 0.0753, "step": 1204 }, { "epoch": 4.16, "learning_rate": 1.5200161279292154e-05, "loss": 0.0841, "step": 1205 }, { "epoch": 4.16, "learning_rate": 1.5192208178364815e-05, "loss": 0.0735, "step": 1206 }, { "epoch": 4.16, "learning_rate": 1.5184250578559056e-05, "loss": 0.0756, "step": 1207 }, { "epoch": 4.17, "learning_rate": 1.5176288486769877e-05, "loss": 0.0629, "step": 1208 }, { "epoch": 4.17, "learning_rate": 1.5168321909896171e-05, "loss": 0.111, "step": 1209 }, { "epoch": 4.17, "learning_rate": 1.5160350854840715e-05, "loss": 0.0941, "step": 1210 }, { "epoch": 4.18, "learning_rate": 1.5152375328510169e-05, "loss": 0.0535, "step": 1211 }, { "epoch": 4.18, "learning_rate": 1.5144395337815066e-05, "loss": 0.0873, "step": 1212 }, { "epoch": 4.18, "learning_rate": 1.5136410889669804e-05, "loss": 0.1017, "step": 1213 }, { "epoch": 4.19, "learning_rate": 1.5128421990992647e-05, "loss": 0.0481, "step": 1214 }, { "epoch": 4.19, "learning_rate": 1.5120428648705716e-05, "loss": 0.0756, "step": 1215 }, { "epoch": 4.19, "learning_rate": 1.511243086973498e-05, "loss": 0.0722, "step": 1216 }, { "epoch": 4.2, "learning_rate": 1.510442866101025e-05, "loss": 0.0835, "step": 1217 }, { "epoch": 4.2, "learning_rate": 1.5096422029465178e-05, "loss": 0.0581, "step": 1218 }, { "epoch": 4.2, "learning_rate": 1.5088410982037251e-05, "loss": 0.0941, "step": 1219 }, { "epoch": 4.21, "learning_rate": 1.508039552566778e-05, "loss": 0.0705, "step": 1220 }, { "epoch": 4.21, "learning_rate": 1.5072375667301893e-05, "loss": 0.0569, "step": 1221 }, { "epoch": 4.21, "learning_rate": 1.5064351413888533e-05, "loss": 0.0652, "step": 1222 }, { "epoch": 4.22, "learning_rate": 1.5056322772380458e-05, "loss": 0.0507, "step": 1223 }, { "epoch": 4.22, "learning_rate": 1.504828974973422e-05, "loss": 0.0402, "step": 1224 }, { "epoch": 4.22, "learning_rate": 1.5040252352910168e-05, "loss": 0.0599, "step": 1225 }, { "epoch": 4.23, "learning_rate": 1.5032210588872449e-05, "loss": 0.0512, "step": 1226 }, { "epoch": 4.23, "learning_rate": 1.5024164464588982e-05, "loss": 0.0814, "step": 1227 }, { "epoch": 4.23, "learning_rate": 1.5016113987031475e-05, "loss": 0.0518, "step": 1228 }, { "epoch": 4.24, "learning_rate": 1.50080591631754e-05, "loss": 0.0729, "step": 1229 }, { "epoch": 4.24, "learning_rate": 1.5000000000000002e-05, "loss": 0.0406, "step": 1230 }, { "epoch": 4.24, "learning_rate": 1.4991936504488278e-05, "loss": 0.0791, "step": 1231 }, { "epoch": 4.25, "learning_rate": 1.4983868683626988e-05, "loss": 0.0697, "step": 1232 }, { "epoch": 4.25, "learning_rate": 1.4975796544406627e-05, "loss": 0.0806, "step": 1233 }, { "epoch": 4.26, "learning_rate": 1.4967720093821446e-05, "loss": 0.0745, "step": 1234 }, { "epoch": 4.26, "learning_rate": 1.4959639338869423e-05, "loss": 0.0632, "step": 1235 }, { "epoch": 4.26, "learning_rate": 1.4951554286552266e-05, "loss": 0.087, "step": 1236 }, { "epoch": 4.27, "learning_rate": 1.4943464943875412e-05, "loss": 0.071, "step": 1237 }, { "epoch": 4.27, "learning_rate": 1.4935371317848009e-05, "loss": 0.0432, "step": 1238 }, { "epoch": 4.27, "learning_rate": 1.4927273415482916e-05, "loss": 0.0695, "step": 1239 }, { "epoch": 4.28, "learning_rate": 1.4919171243796706e-05, "loss": 0.0627, "step": 1240 }, { "epoch": 4.28, "learning_rate": 1.4911064809809644e-05, "loss": 0.0968, "step": 1241 }, { "epoch": 4.28, "learning_rate": 1.4902954120545687e-05, "loss": 0.0653, "step": 1242 }, { "epoch": 4.29, "learning_rate": 1.4894839183032485e-05, "loss": 0.0757, "step": 1243 }, { "epoch": 4.29, "learning_rate": 1.4886720004301368e-05, "loss": 0.106, "step": 1244 }, { "epoch": 4.29, "learning_rate": 1.4878596591387329e-05, "loss": 0.081, "step": 1245 }, { "epoch": 4.3, "learning_rate": 1.4870468951329046e-05, "loss": 0.0616, "step": 1246 }, { "epoch": 4.3, "learning_rate": 1.4862337091168854e-05, "loss": 0.0844, "step": 1247 }, { "epoch": 4.3, "learning_rate": 1.485420101795274e-05, "loss": 0.0736, "step": 1248 }, { "epoch": 4.31, "learning_rate": 1.484606073873035e-05, "loss": 0.048, "step": 1249 }, { "epoch": 4.31, "learning_rate": 1.4837916260554966e-05, "loss": 0.0816, "step": 1250 }, { "epoch": 4.31, "learning_rate": 1.4829767590483508e-05, "loss": 0.0691, "step": 1251 }, { "epoch": 4.32, "learning_rate": 1.4821614735576541e-05, "loss": 0.0754, "step": 1252 }, { "epoch": 4.32, "learning_rate": 1.481345770289824e-05, "loss": 0.0955, "step": 1253 }, { "epoch": 4.32, "learning_rate": 1.4805296499516408e-05, "loss": 0.0813, "step": 1254 }, { "epoch": 4.33, "learning_rate": 1.4797131132502464e-05, "loss": 0.0814, "step": 1255 }, { "epoch": 4.33, "learning_rate": 1.4788961608931427e-05, "loss": 0.0723, "step": 1256 }, { "epoch": 4.33, "learning_rate": 1.4780787935881925e-05, "loss": 0.0723, "step": 1257 }, { "epoch": 4.34, "learning_rate": 1.4772610120436173e-05, "loss": 0.0518, "step": 1258 }, { "epoch": 4.34, "learning_rate": 1.4764428169679987e-05, "loss": 0.0949, "step": 1259 }, { "epoch": 4.34, "learning_rate": 1.4756242090702756e-05, "loss": 0.1187, "step": 1260 }, { "epoch": 4.35, "learning_rate": 1.4748051890597447e-05, "loss": 0.0634, "step": 1261 }, { "epoch": 4.35, "learning_rate": 1.4739857576460605e-05, "loss": 0.0684, "step": 1262 }, { "epoch": 4.36, "learning_rate": 1.4731659155392332e-05, "loss": 0.0567, "step": 1263 }, { "epoch": 4.36, "learning_rate": 1.4723456634496294e-05, "loss": 0.0677, "step": 1264 }, { "epoch": 4.36, "learning_rate": 1.4715250020879705e-05, "loss": 0.0685, "step": 1265 }, { "epoch": 4.37, "learning_rate": 1.470703932165333e-05, "loss": 0.0526, "step": 1266 }, { "epoch": 4.37, "learning_rate": 1.4698824543931463e-05, "loss": 0.0692, "step": 1267 }, { "epoch": 4.37, "learning_rate": 1.4690605694831948e-05, "loss": 0.0727, "step": 1268 }, { "epoch": 4.38, "learning_rate": 1.4682382781476146e-05, "loss": 0.083, "step": 1269 }, { "epoch": 4.38, "learning_rate": 1.4674155810988944e-05, "loss": 0.0707, "step": 1270 }, { "epoch": 4.38, "learning_rate": 1.4665924790498738e-05, "loss": 0.0629, "step": 1271 }, { "epoch": 4.39, "learning_rate": 1.4657689727137443e-05, "loss": 0.0561, "step": 1272 }, { "epoch": 4.39, "learning_rate": 1.464945062804047e-05, "loss": 0.1113, "step": 1273 }, { "epoch": 4.39, "learning_rate": 1.464120750034673e-05, "loss": 0.0493, "step": 1274 }, { "epoch": 4.4, "learning_rate": 1.463296035119862e-05, "loss": 0.0733, "step": 1275 }, { "epoch": 4.4, "learning_rate": 1.4624709187742026e-05, "loss": 0.0733, "step": 1276 }, { "epoch": 4.4, "learning_rate": 1.4616454017126312e-05, "loss": 0.0532, "step": 1277 }, { "epoch": 4.41, "learning_rate": 1.4608194846504311e-05, "loss": 0.0594, "step": 1278 }, { "epoch": 4.41, "learning_rate": 1.4599931683032327e-05, "loss": 0.0984, "step": 1279 }, { "epoch": 4.41, "learning_rate": 1.4591664533870118e-05, "loss": 0.0752, "step": 1280 }, { "epoch": 4.42, "learning_rate": 1.4583393406180898e-05, "loss": 0.0957, "step": 1281 }, { "epoch": 4.42, "learning_rate": 1.4575118307131332e-05, "loss": 0.0548, "step": 1282 }, { "epoch": 4.42, "learning_rate": 1.4566839243891524e-05, "loss": 0.0803, "step": 1283 }, { "epoch": 4.43, "learning_rate": 1.4558556223635004e-05, "loss": 0.0972, "step": 1284 }, { "epoch": 4.43, "learning_rate": 1.4550269253538739e-05, "loss": 0.08, "step": 1285 }, { "epoch": 4.43, "learning_rate": 1.454197834078312e-05, "loss": 0.0816, "step": 1286 }, { "epoch": 4.44, "learning_rate": 1.4533683492551954e-05, "loss": 0.1073, "step": 1287 }, { "epoch": 4.44, "learning_rate": 1.452538471603245e-05, "loss": 0.0652, "step": 1288 }, { "epoch": 4.44, "learning_rate": 1.4517082018415231e-05, "loss": 0.0637, "step": 1289 }, { "epoch": 4.45, "learning_rate": 1.4508775406894308e-05, "loss": 0.0898, "step": 1290 }, { "epoch": 4.45, "learning_rate": 1.4500464888667094e-05, "loss": 0.1062, "step": 1291 }, { "epoch": 4.46, "learning_rate": 1.4492150470934374e-05, "loss": 0.0652, "step": 1292 }, { "epoch": 4.46, "learning_rate": 1.4483832160900326e-05, "loss": 0.0512, "step": 1293 }, { "epoch": 4.46, "learning_rate": 1.4475509965772487e-05, "loss": 0.0666, "step": 1294 }, { "epoch": 4.47, "learning_rate": 1.4467183892761769e-05, "loss": 0.0645, "step": 1295 }, { "epoch": 4.47, "learning_rate": 1.4458853949082443e-05, "loss": 0.0898, "step": 1296 }, { "epoch": 4.47, "learning_rate": 1.4450520141952132e-05, "loss": 0.0966, "step": 1297 }, { "epoch": 4.48, "learning_rate": 1.4442182478591802e-05, "loss": 0.0776, "step": 1298 }, { "epoch": 4.48, "learning_rate": 1.4433840966225772e-05, "loss": 0.109, "step": 1299 }, { "epoch": 4.48, "learning_rate": 1.442549561208169e-05, "loss": 0.0879, "step": 1300 }, { "epoch": 4.49, "learning_rate": 1.4417146423390529e-05, "loss": 0.0749, "step": 1301 }, { "epoch": 4.49, "learning_rate": 1.4408793407386587e-05, "loss": 0.0571, "step": 1302 }, { "epoch": 4.49, "learning_rate": 1.440043657130748e-05, "loss": 0.0976, "step": 1303 }, { "epoch": 4.5, "learning_rate": 1.4392075922394133e-05, "loss": 0.0782, "step": 1304 }, { "epoch": 4.5, "learning_rate": 1.4383711467890776e-05, "loss": 0.0645, "step": 1305 }, { "epoch": 4.5, "learning_rate": 1.4375343215044932e-05, "loss": 0.0925, "step": 1306 }, { "epoch": 4.51, "learning_rate": 1.436697117110742e-05, "loss": 0.066, "step": 1307 }, { "epoch": 4.51, "learning_rate": 1.4358595343332342e-05, "loss": 0.1295, "step": 1308 }, { "epoch": 4.51, "learning_rate": 1.4350215738977077e-05, "loss": 0.055, "step": 1309 }, { "epoch": 4.52, "learning_rate": 1.4341832365302282e-05, "loss": 0.069, "step": 1310 }, { "epoch": 4.52, "learning_rate": 1.4333445229571874e-05, "loss": 0.0637, "step": 1311 }, { "epoch": 4.52, "learning_rate": 1.4325054339053028e-05, "loss": 0.0627, "step": 1312 }, { "epoch": 4.53, "learning_rate": 1.431665970101618e-05, "loss": 0.0631, "step": 1313 }, { "epoch": 4.53, "learning_rate": 1.4308261322735006e-05, "loss": 0.0832, "step": 1314 }, { "epoch": 4.53, "learning_rate": 1.4299859211486429e-05, "loss": 0.0634, "step": 1315 }, { "epoch": 4.54, "learning_rate": 1.4291453374550602e-05, "loss": 0.0823, "step": 1316 }, { "epoch": 4.54, "learning_rate": 1.4283043819210905e-05, "loss": 0.0784, "step": 1317 }, { "epoch": 4.54, "learning_rate": 1.4274630552753946e-05, "loss": 0.0656, "step": 1318 }, { "epoch": 4.55, "learning_rate": 1.4266213582469543e-05, "loss": 0.0697, "step": 1319 }, { "epoch": 4.55, "learning_rate": 1.4257792915650728e-05, "loss": 0.0639, "step": 1320 }, { "epoch": 4.56, "learning_rate": 1.424936855959373e-05, "loss": 0.0655, "step": 1321 }, { "epoch": 4.56, "learning_rate": 1.4240940521597982e-05, "loss": 0.0836, "step": 1322 }, { "epoch": 4.56, "learning_rate": 1.4232508808966097e-05, "loss": 0.0508, "step": 1323 }, { "epoch": 4.57, "learning_rate": 1.422407342900388e-05, "loss": 0.0831, "step": 1324 }, { "epoch": 4.57, "learning_rate": 1.4215634389020314e-05, "loss": 0.083, "step": 1325 }, { "epoch": 4.57, "learning_rate": 1.420719169632755e-05, "loss": 0.0721, "step": 1326 }, { "epoch": 4.58, "learning_rate": 1.4198745358240903e-05, "loss": 0.0735, "step": 1327 }, { "epoch": 4.58, "learning_rate": 1.419029538207885e-05, "loss": 0.0625, "step": 1328 }, { "epoch": 4.58, "learning_rate": 1.4181841775163014e-05, "loss": 0.1029, "step": 1329 }, { "epoch": 4.59, "learning_rate": 1.417338454481818e-05, "loss": 0.0592, "step": 1330 }, { "epoch": 4.59, "learning_rate": 1.4164923698372253e-05, "loss": 0.1084, "step": 1331 }, { "epoch": 4.59, "learning_rate": 1.415645924315628e-05, "loss": 0.0692, "step": 1332 }, { "epoch": 4.6, "learning_rate": 1.4147991186504435e-05, "loss": 0.0595, "step": 1333 }, { "epoch": 4.6, "learning_rate": 1.4139519535754012e-05, "loss": 0.0575, "step": 1334 }, { "epoch": 4.6, "learning_rate": 1.413104429824542e-05, "loss": 0.0411, "step": 1335 }, { "epoch": 4.61, "learning_rate": 1.4122565481322173e-05, "loss": 0.0884, "step": 1336 }, { "epoch": 4.61, "learning_rate": 1.4114083092330889e-05, "loss": 0.0966, "step": 1337 }, { "epoch": 4.61, "learning_rate": 1.4105597138621281e-05, "loss": 0.09, "step": 1338 }, { "epoch": 4.62, "learning_rate": 1.409710762754615e-05, "loss": 0.0879, "step": 1339 }, { "epoch": 4.62, "learning_rate": 1.408861456646138e-05, "loss": 0.0636, "step": 1340 }, { "epoch": 4.62, "learning_rate": 1.4080117962725929e-05, "loss": 0.0782, "step": 1341 }, { "epoch": 4.63, "learning_rate": 1.4071617823701829e-05, "loss": 0.0926, "step": 1342 }, { "epoch": 4.63, "learning_rate": 1.4063114156754164e-05, "loss": 0.0677, "step": 1343 }, { "epoch": 4.63, "learning_rate": 1.4054606969251095e-05, "loss": 0.0948, "step": 1344 }, { "epoch": 4.64, "learning_rate": 1.4046096268563814e-05, "loss": 0.0623, "step": 1345 }, { "epoch": 4.64, "learning_rate": 1.4037582062066565e-05, "loss": 0.0661, "step": 1346 }, { "epoch": 4.64, "learning_rate": 1.4029064357136628e-05, "loss": 0.0622, "step": 1347 }, { "epoch": 4.65, "learning_rate": 1.4020543161154318e-05, "loss": 0.0612, "step": 1348 }, { "epoch": 4.65, "learning_rate": 1.4012018481502975e-05, "loss": 0.0796, "step": 1349 }, { "epoch": 4.66, "learning_rate": 1.4003490325568953e-05, "loss": 0.059, "step": 1350 }, { "epoch": 4.66, "learning_rate": 1.3994958700741617e-05, "loss": 0.0697, "step": 1351 }, { "epoch": 4.66, "learning_rate": 1.3986423614413341e-05, "loss": 0.1092, "step": 1352 }, { "epoch": 4.67, "learning_rate": 1.39778850739795e-05, "loss": 0.1087, "step": 1353 }, { "epoch": 4.67, "learning_rate": 1.3969343086838458e-05, "loss": 0.083, "step": 1354 }, { "epoch": 4.67, "learning_rate": 1.396079766039157e-05, "loss": 0.0609, "step": 1355 }, { "epoch": 4.68, "learning_rate": 1.3952248802043166e-05, "loss": 0.0815, "step": 1356 }, { "epoch": 4.68, "learning_rate": 1.3943696519200553e-05, "loss": 0.0538, "step": 1357 }, { "epoch": 4.68, "learning_rate": 1.3935140819274005e-05, "loss": 0.0938, "step": 1358 }, { "epoch": 4.69, "learning_rate": 1.3926581709676752e-05, "loss": 0.089, "step": 1359 }, { "epoch": 4.69, "learning_rate": 1.3918019197824985e-05, "loss": 0.0756, "step": 1360 }, { "epoch": 4.69, "learning_rate": 1.3909453291137842e-05, "loss": 0.0523, "step": 1361 }, { "epoch": 4.7, "learning_rate": 1.3900883997037398e-05, "loss": 0.0814, "step": 1362 }, { "epoch": 4.7, "learning_rate": 1.3892311322948666e-05, "loss": 0.0739, "step": 1363 }, { "epoch": 4.7, "learning_rate": 1.388373527629959e-05, "loss": 0.0554, "step": 1364 }, { "epoch": 4.71, "learning_rate": 1.3875155864521031e-05, "loss": 0.0846, "step": 1365 }, { "epoch": 4.71, "learning_rate": 1.3866573095046766e-05, "loss": 0.0583, "step": 1366 }, { "epoch": 4.71, "learning_rate": 1.385798697531349e-05, "loss": 0.0565, "step": 1367 }, { "epoch": 4.72, "learning_rate": 1.3849397512760797e-05, "loss": 0.0862, "step": 1368 }, { "epoch": 4.72, "learning_rate": 1.3840804714831164e-05, "loss": 0.0739, "step": 1369 }, { "epoch": 4.72, "learning_rate": 1.3832208588969975e-05, "loss": 0.0997, "step": 1370 }, { "epoch": 4.73, "learning_rate": 1.3823609142625492e-05, "loss": 0.0705, "step": 1371 }, { "epoch": 4.73, "learning_rate": 1.3815006383248855e-05, "loss": 0.073, "step": 1372 }, { "epoch": 4.73, "learning_rate": 1.3806400318294069e-05, "loss": 0.0637, "step": 1373 }, { "epoch": 4.74, "learning_rate": 1.3797790955218014e-05, "loss": 0.0765, "step": 1374 }, { "epoch": 4.74, "learning_rate": 1.3789178301480415e-05, "loss": 0.0799, "step": 1375 }, { "epoch": 4.74, "learning_rate": 1.3780562364543857e-05, "loss": 0.0707, "step": 1376 }, { "epoch": 4.75, "learning_rate": 1.3771943151873768e-05, "loss": 0.0866, "step": 1377 }, { "epoch": 4.75, "learning_rate": 1.3763320670938413e-05, "loss": 0.0749, "step": 1378 }, { "epoch": 4.76, "learning_rate": 1.3754694929208891e-05, "loss": 0.067, "step": 1379 }, { "epoch": 4.76, "learning_rate": 1.3746065934159123e-05, "loss": 0.0597, "step": 1380 }, { "epoch": 4.76, "learning_rate": 1.373743369326585e-05, "loss": 0.0844, "step": 1381 }, { "epoch": 4.77, "learning_rate": 1.3728798214008628e-05, "loss": 0.0766, "step": 1382 }, { "epoch": 4.77, "learning_rate": 1.3720159503869816e-05, "loss": 0.0878, "step": 1383 }, { "epoch": 4.77, "learning_rate": 1.3711517570334574e-05, "loss": 0.0761, "step": 1384 }, { "epoch": 4.78, "learning_rate": 1.3702872420890853e-05, "loss": 0.0657, "step": 1385 }, { "epoch": 4.78, "learning_rate": 1.3694224063029396e-05, "loss": 0.0824, "step": 1386 }, { "epoch": 4.78, "learning_rate": 1.3685572504243718e-05, "loss": 0.0567, "step": 1387 }, { "epoch": 4.79, "learning_rate": 1.3676917752030114e-05, "loss": 0.0903, "step": 1388 }, { "epoch": 4.79, "learning_rate": 1.3668259813887644e-05, "loss": 0.0748, "step": 1389 }, { "epoch": 4.79, "learning_rate": 1.3659598697318122e-05, "loss": 0.1009, "step": 1390 }, { "epoch": 4.8, "learning_rate": 1.3650934409826129e-05, "loss": 0.0655, "step": 1391 }, { "epoch": 4.8, "learning_rate": 1.3642266958918985e-05, "loss": 0.0721, "step": 1392 }, { "epoch": 4.8, "learning_rate": 1.3633596352106748e-05, "loss": 0.0918, "step": 1393 }, { "epoch": 4.81, "learning_rate": 1.362492259690222e-05, "loss": 0.0602, "step": 1394 }, { "epoch": 4.81, "learning_rate": 1.3616245700820922e-05, "loss": 0.0594, "step": 1395 }, { "epoch": 4.81, "learning_rate": 1.3607565671381107e-05, "loss": 0.062, "step": 1396 }, { "epoch": 4.82, "learning_rate": 1.3598882516103731e-05, "loss": 0.0742, "step": 1397 }, { "epoch": 4.82, "learning_rate": 1.3590196242512463e-05, "loss": 0.0867, "step": 1398 }, { "epoch": 4.82, "learning_rate": 1.3581506858133677e-05, "loss": 0.0698, "step": 1399 }, { "epoch": 4.83, "learning_rate": 1.3572814370496441e-05, "loss": 0.0706, "step": 1400 }, { "epoch": 4.83, "learning_rate": 1.3564118787132507e-05, "loss": 0.0559, "step": 1401 }, { "epoch": 4.83, "learning_rate": 1.355542011557632e-05, "loss": 0.0725, "step": 1402 }, { "epoch": 4.84, "learning_rate": 1.3546718363364986e-05, "loss": 0.0938, "step": 1403 }, { "epoch": 4.84, "learning_rate": 1.3538013538038295e-05, "loss": 0.0619, "step": 1404 }, { "epoch": 4.84, "learning_rate": 1.3529305647138689e-05, "loss": 0.0703, "step": 1405 }, { "epoch": 4.85, "learning_rate": 1.3520594698211274e-05, "loss": 0.088, "step": 1406 }, { "epoch": 4.85, "learning_rate": 1.3511880698803801e-05, "loss": 0.0813, "step": 1407 }, { "epoch": 4.86, "learning_rate": 1.3503163656466662e-05, "loss": 0.0606, "step": 1408 }, { "epoch": 4.86, "learning_rate": 1.3494443578752893e-05, "loss": 0.0488, "step": 1409 }, { "epoch": 4.86, "learning_rate": 1.3485720473218153e-05, "loss": 0.0792, "step": 1410 }, { "epoch": 4.87, "learning_rate": 1.3476994347420731e-05, "loss": 0.0982, "step": 1411 }, { "epoch": 4.87, "learning_rate": 1.3468265208921526e-05, "loss": 0.0873, "step": 1412 }, { "epoch": 4.87, "learning_rate": 1.3459533065284049e-05, "loss": 0.0806, "step": 1413 }, { "epoch": 4.88, "learning_rate": 1.3450797924074421e-05, "loss": 0.0695, "step": 1414 }, { "epoch": 4.88, "learning_rate": 1.3442059792861356e-05, "loss": 0.0733, "step": 1415 }, { "epoch": 4.88, "learning_rate": 1.3433318679216154e-05, "loss": 0.0601, "step": 1416 }, { "epoch": 4.89, "learning_rate": 1.342457459071271e-05, "loss": 0.0566, "step": 1417 }, { "epoch": 4.89, "learning_rate": 1.3415827534927486e-05, "loss": 0.0935, "step": 1418 }, { "epoch": 4.89, "learning_rate": 1.340707751943952e-05, "loss": 0.0571, "step": 1419 }, { "epoch": 4.9, "learning_rate": 1.3398324551830416e-05, "loss": 0.0594, "step": 1420 }, { "epoch": 4.9, "learning_rate": 1.3389568639684327e-05, "loss": 0.0697, "step": 1421 }, { "epoch": 4.9, "learning_rate": 1.3380809790587975e-05, "loss": 0.0754, "step": 1422 }, { "epoch": 4.91, "learning_rate": 1.3372048012130608e-05, "loss": 0.0542, "step": 1423 }, { "epoch": 4.91, "learning_rate": 1.3363283311904024e-05, "loss": 0.08, "step": 1424 }, { "epoch": 4.91, "learning_rate": 1.3354515697502552e-05, "loss": 0.0718, "step": 1425 }, { "epoch": 4.92, "learning_rate": 1.3345745176523035e-05, "loss": 0.0631, "step": 1426 }, { "epoch": 4.92, "learning_rate": 1.3336971756564846e-05, "loss": 0.0675, "step": 1427 }, { "epoch": 4.92, "learning_rate": 1.3328195445229869e-05, "loss": 0.0627, "step": 1428 }, { "epoch": 4.93, "learning_rate": 1.3319416250122484e-05, "loss": 0.0995, "step": 1429 }, { "epoch": 4.93, "learning_rate": 1.3310634178849583e-05, "loss": 0.0757, "step": 1430 }, { "epoch": 4.93, "learning_rate": 1.3301849239020537e-05, "loss": 0.092, "step": 1431 }, { "epoch": 4.94, "learning_rate": 1.3293061438247215e-05, "loss": 0.1205, "step": 1432 }, { "epoch": 4.94, "learning_rate": 1.3284270784143953e-05, "loss": 0.0792, "step": 1433 }, { "epoch": 4.94, "learning_rate": 1.327547728432757e-05, "loss": 0.0532, "step": 1434 }, { "epoch": 4.95, "learning_rate": 1.3266680946417346e-05, "loss": 0.0508, "step": 1435 }, { "epoch": 4.95, "learning_rate": 1.325788177803501e-05, "loss": 0.07, "step": 1436 }, { "epoch": 4.96, "learning_rate": 1.3249079786804765e-05, "loss": 0.0619, "step": 1437 }, { "epoch": 4.96, "learning_rate": 1.3240274980353244e-05, "loss": 0.0823, "step": 1438 }, { "epoch": 4.96, "learning_rate": 1.3231467366309523e-05, "loss": 0.0819, "step": 1439 }, { "epoch": 4.97, "learning_rate": 1.3222656952305113e-05, "loss": 0.1193, "step": 1440 }, { "epoch": 4.97, "learning_rate": 1.3213843745973946e-05, "loss": 0.0854, "step": 1441 }, { "epoch": 4.97, "learning_rate": 1.320502775495238e-05, "loss": 0.0528, "step": 1442 }, { "epoch": 4.98, "learning_rate": 1.319620898687918e-05, "loss": 0.0744, "step": 1443 }, { "epoch": 4.98, "learning_rate": 1.3187387449395524e-05, "loss": 0.0853, "step": 1444 }, { "epoch": 4.98, "learning_rate": 1.317856315014498e-05, "loss": 0.0779, "step": 1445 }, { "epoch": 4.99, "learning_rate": 1.316973609677352e-05, "loss": 0.0687, "step": 1446 }, { "epoch": 4.99, "learning_rate": 1.3160906296929493e-05, "loss": 0.1051, "step": 1447 }, { "epoch": 4.99, "learning_rate": 1.315207375826363e-05, "loss": 0.0541, "step": 1448 }, { "epoch": 5.0, "learning_rate": 1.3143238488429042e-05, "loss": 0.0927, "step": 1449 }, { "epoch": 5.0, "learning_rate": 1.3134400495081197e-05, "loss": 0.0911, "step": 1450 }, { "epoch": 5.0, "learning_rate": 1.3125559785877929e-05, "loss": 0.0325, "step": 1451 }, { "epoch": 5.01, "learning_rate": 1.3116716368479418e-05, "loss": 0.0254, "step": 1452 }, { "epoch": 5.01, "learning_rate": 1.3107870250548205e-05, "loss": 0.0271, "step": 1453 }, { "epoch": 5.01, "learning_rate": 1.3099021439749156e-05, "loss": 0.0276, "step": 1454 }, { "epoch": 5.02, "learning_rate": 1.3090169943749475e-05, "loss": 0.0488, "step": 1455 }, { "epoch": 5.02, "learning_rate": 1.3081315770218696e-05, "loss": 0.0432, "step": 1456 }, { "epoch": 5.02, "learning_rate": 1.3072458926828668e-05, "loss": 0.0402, "step": 1457 }, { "epoch": 5.03, "learning_rate": 1.306359942125356e-05, "loss": 0.037, "step": 1458 }, { "epoch": 5.03, "learning_rate": 1.3054737261169838e-05, "loss": 0.055, "step": 1459 }, { "epoch": 5.03, "learning_rate": 1.3045872454256278e-05, "loss": 0.0342, "step": 1460 }, { "epoch": 5.04, "learning_rate": 1.3037005008193944e-05, "loss": 0.0281, "step": 1461 }, { "epoch": 5.04, "learning_rate": 1.3028134930666188e-05, "loss": 0.0272, "step": 1462 }, { "epoch": 5.04, "learning_rate": 1.3019262229358638e-05, "loss": 0.022, "step": 1463 }, { "epoch": 5.05, "learning_rate": 1.3010386911959207e-05, "loss": 0.0294, "step": 1464 }, { "epoch": 5.05, "learning_rate": 1.3001508986158057e-05, "loss": 0.0396, "step": 1465 }, { "epoch": 5.06, "learning_rate": 1.299262845964763e-05, "loss": 0.0246, "step": 1466 }, { "epoch": 5.06, "learning_rate": 1.2983745340122604e-05, "loss": 0.0246, "step": 1467 }, { "epoch": 5.06, "learning_rate": 1.2974859635279914e-05, "loss": 0.0359, "step": 1468 }, { "epoch": 5.07, "learning_rate": 1.2965971352818736e-05, "loss": 0.0204, "step": 1469 }, { "epoch": 5.07, "learning_rate": 1.2957080500440469e-05, "loss": 0.0371, "step": 1470 }, { "epoch": 5.07, "learning_rate": 1.294818708584875e-05, "loss": 0.0269, "step": 1471 }, { "epoch": 5.08, "learning_rate": 1.2939291116749431e-05, "loss": 0.0396, "step": 1472 }, { "epoch": 5.08, "learning_rate": 1.2930392600850574e-05, "loss": 0.0222, "step": 1473 }, { "epoch": 5.08, "learning_rate": 1.2921491545862462e-05, "loss": 0.0315, "step": 1474 }, { "epoch": 5.09, "learning_rate": 1.2912587959497556e-05, "loss": 0.0315, "step": 1475 }, { "epoch": 5.09, "learning_rate": 1.2903681849470528e-05, "loss": 0.0273, "step": 1476 }, { "epoch": 5.09, "learning_rate": 1.2894773223498232e-05, "loss": 0.0291, "step": 1477 }, { "epoch": 5.1, "learning_rate": 1.2885862089299694e-05, "loss": 0.028, "step": 1478 }, { "epoch": 5.1, "learning_rate": 1.287694845459613e-05, "loss": 0.0271, "step": 1479 }, { "epoch": 5.1, "learning_rate": 1.2868032327110904e-05, "loss": 0.0292, "step": 1480 }, { "epoch": 5.11, "learning_rate": 1.2859113714569553e-05, "loss": 0.0323, "step": 1481 }, { "epoch": 5.11, "learning_rate": 1.2850192624699762e-05, "loss": 0.0332, "step": 1482 }, { "epoch": 5.11, "learning_rate": 1.2841269065231363e-05, "loss": 0.0452, "step": 1483 }, { "epoch": 5.12, "learning_rate": 1.2832343043896329e-05, "loss": 0.0394, "step": 1484 }, { "epoch": 5.12, "learning_rate": 1.2823414568428767e-05, "loss": 0.0459, "step": 1485 }, { "epoch": 5.12, "learning_rate": 1.2814483646564902e-05, "loss": 0.0376, "step": 1486 }, { "epoch": 5.13, "learning_rate": 1.2805550286043094e-05, "loss": 0.0303, "step": 1487 }, { "epoch": 5.13, "learning_rate": 1.27966144946038e-05, "loss": 0.0404, "step": 1488 }, { "epoch": 5.13, "learning_rate": 1.2787676279989594e-05, "loss": 0.0335, "step": 1489 }, { "epoch": 5.14, "learning_rate": 1.277873564994515e-05, "loss": 0.0354, "step": 1490 }, { "epoch": 5.14, "learning_rate": 1.2769792612217224e-05, "loss": 0.0244, "step": 1491 }, { "epoch": 5.14, "learning_rate": 1.2760847174554671e-05, "loss": 0.0171, "step": 1492 }, { "epoch": 5.15, "learning_rate": 1.2751899344708418e-05, "loss": 0.0463, "step": 1493 }, { "epoch": 5.15, "learning_rate": 1.2742949130431468e-05, "loss": 0.0401, "step": 1494 }, { "epoch": 5.16, "learning_rate": 1.2733996539478883e-05, "loss": 0.0424, "step": 1495 }, { "epoch": 5.16, "learning_rate": 1.2725041579607798e-05, "loss": 0.0286, "step": 1496 }, { "epoch": 5.16, "learning_rate": 1.2716084258577388e-05, "loss": 0.0425, "step": 1497 }, { "epoch": 5.17, "learning_rate": 1.270712458414888e-05, "loss": 0.019, "step": 1498 }, { "epoch": 5.17, "learning_rate": 1.2698162564085536e-05, "loss": 0.0409, "step": 1499 }, { "epoch": 5.17, "learning_rate": 1.2689198206152657e-05, "loss": 0.0428, "step": 1500 }, { "epoch": 5.18, "learning_rate": 1.2680231518117564e-05, "loss": 0.0151, "step": 1501 }, { "epoch": 5.18, "learning_rate": 1.26712625077496e-05, "loss": 0.0215, "step": 1502 }, { "epoch": 5.18, "learning_rate": 1.2662291182820115e-05, "loss": 0.0259, "step": 1503 }, { "epoch": 5.19, "learning_rate": 1.2653317551102471e-05, "loss": 0.0198, "step": 1504 }, { "epoch": 5.19, "learning_rate": 1.2644341620372025e-05, "loss": 0.0236, "step": 1505 }, { "epoch": 5.19, "learning_rate": 1.263536339840613e-05, "loss": 0.0405, "step": 1506 }, { "epoch": 5.2, "learning_rate": 1.2626382892984114e-05, "loss": 0.0326, "step": 1507 }, { "epoch": 5.2, "learning_rate": 1.2617400111887302e-05, "loss": 0.0297, "step": 1508 }, { "epoch": 5.2, "learning_rate": 1.2608415062898971e-05, "loss": 0.0388, "step": 1509 }, { "epoch": 5.21, "learning_rate": 1.2599427753804377e-05, "loss": 0.0371, "step": 1510 }, { "epoch": 5.21, "learning_rate": 1.2590438192390723e-05, "loss": 0.0307, "step": 1511 }, { "epoch": 5.21, "learning_rate": 1.2581446386447178e-05, "loss": 0.0392, "step": 1512 }, { "epoch": 5.22, "learning_rate": 1.2572452343764844e-05, "loss": 0.0249, "step": 1513 }, { "epoch": 5.22, "learning_rate": 1.2563456072136759e-05, "loss": 0.0184, "step": 1514 }, { "epoch": 5.22, "learning_rate": 1.2554457579357906e-05, "loss": 0.0297, "step": 1515 }, { "epoch": 5.23, "learning_rate": 1.2545456873225181e-05, "loss": 0.0241, "step": 1516 }, { "epoch": 5.23, "learning_rate": 1.25364539615374e-05, "loss": 0.0249, "step": 1517 }, { "epoch": 5.23, "learning_rate": 1.2527448852095295e-05, "loss": 0.0321, "step": 1518 }, { "epoch": 5.24, "learning_rate": 1.2518441552701493e-05, "loss": 0.032, "step": 1519 }, { "epoch": 5.24, "learning_rate": 1.2509432071160527e-05, "loss": 0.0361, "step": 1520 }, { "epoch": 5.24, "learning_rate": 1.2500420415278822e-05, "loss": 0.0173, "step": 1521 }, { "epoch": 5.25, "learning_rate": 1.2491406592864679e-05, "loss": 0.0376, "step": 1522 }, { "epoch": 5.25, "learning_rate": 1.2482390611728277e-05, "loss": 0.0284, "step": 1523 }, { "epoch": 5.26, "learning_rate": 1.2473372479681671e-05, "loss": 0.0183, "step": 1524 }, { "epoch": 5.26, "learning_rate": 1.246435220453878e-05, "loss": 0.0383, "step": 1525 }, { "epoch": 5.26, "learning_rate": 1.2455329794115372e-05, "loss": 0.0336, "step": 1526 }, { "epoch": 5.27, "learning_rate": 1.2446305256229074e-05, "loss": 0.0632, "step": 1527 }, { "epoch": 5.27, "learning_rate": 1.2437278598699352e-05, "loss": 0.0409, "step": 1528 }, { "epoch": 5.27, "learning_rate": 1.2428249829347509e-05, "loss": 0.029, "step": 1529 }, { "epoch": 5.28, "learning_rate": 1.2419218955996677e-05, "loss": 0.0418, "step": 1530 }, { "epoch": 5.28, "learning_rate": 1.2410185986471817e-05, "loss": 0.0202, "step": 1531 }, { "epoch": 5.28, "learning_rate": 1.2401150928599695e-05, "loss": 0.0276, "step": 1532 }, { "epoch": 5.29, "learning_rate": 1.2392113790208895e-05, "loss": 0.0267, "step": 1533 }, { "epoch": 5.29, "learning_rate": 1.2383074579129801e-05, "loss": 0.0445, "step": 1534 }, { "epoch": 5.29, "learning_rate": 1.2374033303194597e-05, "loss": 0.0415, "step": 1535 }, { "epoch": 5.3, "learning_rate": 1.236498997023725e-05, "loss": 0.0237, "step": 1536 }, { "epoch": 5.3, "learning_rate": 1.235594458809351e-05, "loss": 0.019, "step": 1537 }, { "epoch": 5.3, "learning_rate": 1.2346897164600908e-05, "loss": 0.0399, "step": 1538 }, { "epoch": 5.31, "learning_rate": 1.2337847707598738e-05, "loss": 0.014, "step": 1539 }, { "epoch": 5.31, "learning_rate": 1.232879622492806e-05, "loss": 0.0339, "step": 1540 }, { "epoch": 5.31, "learning_rate": 1.2319742724431689e-05, "loss": 0.0223, "step": 1541 }, { "epoch": 5.32, "learning_rate": 1.2310687213954182e-05, "loss": 0.0341, "step": 1542 }, { "epoch": 5.32, "learning_rate": 1.2301629701341844e-05, "loss": 0.0363, "step": 1543 }, { "epoch": 5.32, "learning_rate": 1.2292570194442714e-05, "loss": 0.0285, "step": 1544 }, { "epoch": 5.33, "learning_rate": 1.2283508701106559e-05, "loss": 0.0256, "step": 1545 }, { "epoch": 5.33, "learning_rate": 1.2274445229184864e-05, "loss": 0.0241, "step": 1546 }, { "epoch": 5.33, "learning_rate": 1.2265379786530833e-05, "loss": 0.0385, "step": 1547 }, { "epoch": 5.34, "learning_rate": 1.2256312380999376e-05, "loss": 0.0347, "step": 1548 }, { "epoch": 5.34, "learning_rate": 1.2247243020447104e-05, "loss": 0.0183, "step": 1549 }, { "epoch": 5.34, "learning_rate": 1.2238171712732316e-05, "loss": 0.023, "step": 1550 }, { "epoch": 5.35, "learning_rate": 1.2229098465715005e-05, "loss": 0.0534, "step": 1551 }, { "epoch": 5.35, "learning_rate": 1.2220023287256844e-05, "loss": 0.0371, "step": 1552 }, { "epoch": 5.36, "learning_rate": 1.2210946185221177e-05, "loss": 0.0373, "step": 1553 }, { "epoch": 5.36, "learning_rate": 1.2201867167473015e-05, "loss": 0.0309, "step": 1554 }, { "epoch": 5.36, "learning_rate": 1.2192786241879033e-05, "loss": 0.0214, "step": 1555 }, { "epoch": 5.37, "learning_rate": 1.2183703416307556e-05, "loss": 0.0239, "step": 1556 }, { "epoch": 5.37, "learning_rate": 1.217461869862855e-05, "loss": 0.0252, "step": 1557 }, { "epoch": 5.37, "learning_rate": 1.2165532096713625e-05, "loss": 0.0275, "step": 1558 }, { "epoch": 5.38, "learning_rate": 1.2156443618436033e-05, "loss": 0.0248, "step": 1559 }, { "epoch": 5.38, "learning_rate": 1.2147353271670634e-05, "loss": 0.0235, "step": 1560 }, { "epoch": 5.38, "learning_rate": 1.213826106429392e-05, "loss": 0.0322, "step": 1561 }, { "epoch": 5.39, "learning_rate": 1.2129167004183987e-05, "loss": 0.0295, "step": 1562 }, { "epoch": 5.39, "learning_rate": 1.212007109922055e-05, "loss": 0.0303, "step": 1563 }, { "epoch": 5.39, "learning_rate": 1.2110973357284902e-05, "loss": 0.0276, "step": 1564 }, { "epoch": 5.4, "learning_rate": 1.210187378625994e-05, "loss": 0.0358, "step": 1565 }, { "epoch": 5.4, "learning_rate": 1.2092772394030153e-05, "loss": 0.0273, "step": 1566 }, { "epoch": 5.4, "learning_rate": 1.2083669188481593e-05, "loss": 0.0242, "step": 1567 }, { "epoch": 5.41, "learning_rate": 1.2074564177501888e-05, "loss": 0.0282, "step": 1568 }, { "epoch": 5.41, "learning_rate": 1.2065457368980236e-05, "loss": 0.0251, "step": 1569 }, { "epoch": 5.41, "learning_rate": 1.2056348770807386e-05, "loss": 0.0311, "step": 1570 }, { "epoch": 5.42, "learning_rate": 1.2047238390875643e-05, "loss": 0.0393, "step": 1571 }, { "epoch": 5.42, "learning_rate": 1.203812623707885e-05, "loss": 0.0216, "step": 1572 }, { "epoch": 5.42, "learning_rate": 1.202901231731239e-05, "loss": 0.0276, "step": 1573 }, { "epoch": 5.43, "learning_rate": 1.2019896639473179e-05, "loss": 0.0332, "step": 1574 }, { "epoch": 5.43, "learning_rate": 1.2010779211459649e-05, "loss": 0.0343, "step": 1575 }, { "epoch": 5.43, "learning_rate": 1.2001660041171754e-05, "loss": 0.032, "step": 1576 }, { "epoch": 5.44, "learning_rate": 1.1992539136510961e-05, "loss": 0.0339, "step": 1577 }, { "epoch": 5.44, "learning_rate": 1.1983416505380234e-05, "loss": 0.0285, "step": 1578 }, { "epoch": 5.44, "learning_rate": 1.197429215568403e-05, "loss": 0.0315, "step": 1579 }, { "epoch": 5.45, "learning_rate": 1.1965166095328302e-05, "loss": 0.041, "step": 1580 }, { "epoch": 5.45, "learning_rate": 1.1956038332220484e-05, "loss": 0.0202, "step": 1581 }, { "epoch": 5.46, "learning_rate": 1.194690887426948e-05, "loss": 0.0311, "step": 1582 }, { "epoch": 5.46, "learning_rate": 1.1937777729385671e-05, "loss": 0.0275, "step": 1583 }, { "epoch": 5.46, "learning_rate": 1.192864490548089e-05, "loss": 0.0498, "step": 1584 }, { "epoch": 5.47, "learning_rate": 1.1919510410468435e-05, "loss": 0.0428, "step": 1585 }, { "epoch": 5.47, "learning_rate": 1.1910374252263047e-05, "loss": 0.0395, "step": 1586 }, { "epoch": 5.47, "learning_rate": 1.1901236438780902e-05, "loss": 0.0521, "step": 1587 }, { "epoch": 5.48, "learning_rate": 1.1892096977939624e-05, "loss": 0.0149, "step": 1588 }, { "epoch": 5.48, "learning_rate": 1.1882955877658252e-05, "loss": 0.0449, "step": 1589 }, { "epoch": 5.48, "learning_rate": 1.187381314585725e-05, "loss": 0.037, "step": 1590 }, { "epoch": 5.49, "learning_rate": 1.1864668790458493e-05, "loss": 0.0228, "step": 1591 }, { "epoch": 5.49, "learning_rate": 1.1855522819385274e-05, "loss": 0.0422, "step": 1592 }, { "epoch": 5.49, "learning_rate": 1.184637524056227e-05, "loss": 0.0259, "step": 1593 }, { "epoch": 5.5, "learning_rate": 1.1837226061915562e-05, "loss": 0.0186, "step": 1594 }, { "epoch": 5.5, "learning_rate": 1.1828075291372616e-05, "loss": 0.0377, "step": 1595 }, { "epoch": 5.5, "learning_rate": 1.181892293686227e-05, "loss": 0.0282, "step": 1596 }, { "epoch": 5.51, "learning_rate": 1.1809769006314743e-05, "loss": 0.0213, "step": 1597 }, { "epoch": 5.51, "learning_rate": 1.1800613507661615e-05, "loss": 0.031, "step": 1598 }, { "epoch": 5.51, "learning_rate": 1.1791456448835825e-05, "loss": 0.0304, "step": 1599 }, { "epoch": 5.52, "learning_rate": 1.1782297837771668e-05, "loss": 0.0449, "step": 1600 }, { "epoch": 5.52, "learning_rate": 1.1773137682404776e-05, "loss": 0.0405, "step": 1601 }, { "epoch": 5.52, "learning_rate": 1.1763975990672125e-05, "loss": 0.0216, "step": 1602 }, { "epoch": 5.53, "learning_rate": 1.1754812770512026e-05, "loss": 0.0376, "step": 1603 }, { "epoch": 5.53, "learning_rate": 1.1745648029864101e-05, "loss": 0.0557, "step": 1604 }, { "epoch": 5.53, "learning_rate": 1.1736481776669307e-05, "loss": 0.0212, "step": 1605 }, { "epoch": 5.54, "learning_rate": 1.1727314018869894e-05, "loss": 0.0245, "step": 1606 }, { "epoch": 5.54, "learning_rate": 1.1718144764409428e-05, "loss": 0.0351, "step": 1607 }, { "epoch": 5.54, "learning_rate": 1.1708974021232768e-05, "loss": 0.037, "step": 1608 }, { "epoch": 5.55, "learning_rate": 1.169980179728606e-05, "loss": 0.0402, "step": 1609 }, { "epoch": 5.55, "learning_rate": 1.169062810051674e-05, "loss": 0.0189, "step": 1610 }, { "epoch": 5.56, "learning_rate": 1.1681452938873516e-05, "loss": 0.0219, "step": 1611 }, { "epoch": 5.56, "learning_rate": 1.1672276320306362e-05, "loss": 0.0353, "step": 1612 }, { "epoch": 5.56, "learning_rate": 1.1663098252766517e-05, "loss": 0.0468, "step": 1613 }, { "epoch": 5.57, "learning_rate": 1.1653918744206478e-05, "loss": 0.0351, "step": 1614 }, { "epoch": 5.57, "learning_rate": 1.1644737802579989e-05, "loss": 0.027, "step": 1615 }, { "epoch": 5.57, "learning_rate": 1.1635555435842036e-05, "loss": 0.0278, "step": 1616 }, { "epoch": 5.58, "learning_rate": 1.1626371651948839e-05, "loss": 0.0279, "step": 1617 }, { "epoch": 5.58, "learning_rate": 1.161718645885784e-05, "loss": 0.0313, "step": 1618 }, { "epoch": 5.58, "learning_rate": 1.1607999864527718e-05, "loss": 0.0346, "step": 1619 }, { "epoch": 5.59, "learning_rate": 1.159881187691835e-05, "loss": 0.0345, "step": 1620 }, { "epoch": 5.59, "learning_rate": 1.1589622503990828e-05, "loss": 0.0186, "step": 1621 }, { "epoch": 5.59, "learning_rate": 1.1580431753707441e-05, "loss": 0.0223, "step": 1622 }, { "epoch": 5.6, "learning_rate": 1.157123963403168e-05, "loss": 0.0347, "step": 1623 }, { "epoch": 5.6, "learning_rate": 1.1562046152928205e-05, "loss": 0.0326, "step": 1624 }, { "epoch": 5.6, "learning_rate": 1.1552851318362876e-05, "loss": 0.0282, "step": 1625 }, { "epoch": 5.61, "learning_rate": 1.1543655138302714e-05, "loss": 0.0285, "step": 1626 }, { "epoch": 5.61, "learning_rate": 1.1534457620715905e-05, "loss": 0.0327, "step": 1627 }, { "epoch": 5.61, "learning_rate": 1.1525258773571797e-05, "loss": 0.0187, "step": 1628 }, { "epoch": 5.62, "learning_rate": 1.1516058604840891e-05, "loss": 0.0274, "step": 1629 }, { "epoch": 5.62, "learning_rate": 1.1506857122494832e-05, "loss": 0.0328, "step": 1630 }, { "epoch": 5.62, "learning_rate": 1.1497654334506405e-05, "loss": 0.041, "step": 1631 }, { "epoch": 5.63, "learning_rate": 1.1488450248849523e-05, "loss": 0.0214, "step": 1632 }, { "epoch": 5.63, "learning_rate": 1.1479244873499224e-05, "loss": 0.0318, "step": 1633 }, { "epoch": 5.63, "learning_rate": 1.1470038216431667e-05, "loss": 0.029, "step": 1634 }, { "epoch": 5.64, "learning_rate": 1.1460830285624119e-05, "loss": 0.0408, "step": 1635 }, { "epoch": 5.64, "learning_rate": 1.1451621089054945e-05, "loss": 0.0416, "step": 1636 }, { "epoch": 5.64, "learning_rate": 1.144241063470362e-05, "loss": 0.0174, "step": 1637 }, { "epoch": 5.65, "learning_rate": 1.1433198930550694e-05, "loss": 0.0446, "step": 1638 }, { "epoch": 5.65, "learning_rate": 1.1423985984577813e-05, "loss": 0.0217, "step": 1639 }, { "epoch": 5.66, "learning_rate": 1.141477180476769e-05, "loss": 0.0291, "step": 1640 }, { "epoch": 5.66, "learning_rate": 1.140555639910411e-05, "loss": 0.037, "step": 1641 }, { "epoch": 5.66, "learning_rate": 1.1396339775571923e-05, "loss": 0.0415, "step": 1642 }, { "epoch": 5.67, "learning_rate": 1.138712194215703e-05, "loss": 0.0242, "step": 1643 }, { "epoch": 5.67, "learning_rate": 1.137790290684638e-05, "loss": 0.0364, "step": 1644 }, { "epoch": 5.67, "learning_rate": 1.1368682677627971e-05, "loss": 0.0324, "step": 1645 }, { "epoch": 5.68, "learning_rate": 1.1359461262490823e-05, "loss": 0.0378, "step": 1646 }, { "epoch": 5.68, "learning_rate": 1.1350238669424993e-05, "loss": 0.0356, "step": 1647 }, { "epoch": 5.68, "learning_rate": 1.1341014906421556e-05, "loss": 0.0334, "step": 1648 }, { "epoch": 5.69, "learning_rate": 1.1331789981472603e-05, "loss": 0.0331, "step": 1649 }, { "epoch": 5.69, "learning_rate": 1.1322563902571227e-05, "loss": 0.0412, "step": 1650 }, { "epoch": 5.69, "learning_rate": 1.1313336677711521e-05, "loss": 0.035, "step": 1651 }, { "epoch": 5.7, "learning_rate": 1.1304108314888578e-05, "loss": 0.0227, "step": 1652 }, { "epoch": 5.7, "learning_rate": 1.129487882209847e-05, "loss": 0.0426, "step": 1653 }, { "epoch": 5.7, "learning_rate": 1.1285648207338252e-05, "loss": 0.0371, "step": 1654 }, { "epoch": 5.71, "learning_rate": 1.127641647860595e-05, "loss": 0.0357, "step": 1655 }, { "epoch": 5.71, "learning_rate": 1.1267183643900548e-05, "loss": 0.0416, "step": 1656 }, { "epoch": 5.71, "learning_rate": 1.1257949711222002e-05, "loss": 0.0374, "step": 1657 }, { "epoch": 5.72, "learning_rate": 1.1248714688571212e-05, "loss": 0.0387, "step": 1658 }, { "epoch": 5.72, "learning_rate": 1.1239478583950019e-05, "loss": 0.0453, "step": 1659 }, { "epoch": 5.72, "learning_rate": 1.1230241405361209e-05, "loss": 0.0467, "step": 1660 }, { "epoch": 5.73, "learning_rate": 1.1221003160808493e-05, "loss": 0.0203, "step": 1661 }, { "epoch": 5.73, "learning_rate": 1.1211763858296507e-05, "loss": 0.0199, "step": 1662 }, { "epoch": 5.73, "learning_rate": 1.1202523505830806e-05, "loss": 0.0408, "step": 1663 }, { "epoch": 5.74, "learning_rate": 1.119328211141785e-05, "loss": 0.0251, "step": 1664 }, { "epoch": 5.74, "learning_rate": 1.1184039683065014e-05, "loss": 0.0373, "step": 1665 }, { "epoch": 5.74, "learning_rate": 1.1174796228780544e-05, "loss": 0.035, "step": 1666 }, { "epoch": 5.75, "learning_rate": 1.1165551756573602e-05, "loss": 0.0397, "step": 1667 }, { "epoch": 5.75, "learning_rate": 1.1156306274454218e-05, "loss": 0.0283, "step": 1668 }, { "epoch": 5.76, "learning_rate": 1.1147059790433296e-05, "loss": 0.0347, "step": 1669 }, { "epoch": 5.76, "learning_rate": 1.1137812312522618e-05, "loss": 0.0237, "step": 1670 }, { "epoch": 5.76, "learning_rate": 1.1128563848734817e-05, "loss": 0.0343, "step": 1671 }, { "epoch": 5.77, "learning_rate": 1.1119314407083384e-05, "loss": 0.0202, "step": 1672 }, { "epoch": 5.77, "learning_rate": 1.1110063995582661e-05, "loss": 0.0465, "step": 1673 }, { "epoch": 5.77, "learning_rate": 1.1100812622247823e-05, "loss": 0.0276, "step": 1674 }, { "epoch": 5.78, "learning_rate": 1.109156029509488e-05, "loss": 0.0282, "step": 1675 }, { "epoch": 5.78, "learning_rate": 1.1082307022140677e-05, "loss": 0.0308, "step": 1676 }, { "epoch": 5.78, "learning_rate": 1.1073052811402867e-05, "loss": 0.0279, "step": 1677 }, { "epoch": 5.79, "learning_rate": 1.1063797670899923e-05, "loss": 0.0297, "step": 1678 }, { "epoch": 5.79, "learning_rate": 1.1054541608651121e-05, "loss": 0.0262, "step": 1679 }, { "epoch": 5.79, "learning_rate": 1.1045284632676535e-05, "loss": 0.0434, "step": 1680 }, { "epoch": 5.8, "learning_rate": 1.1036026750997033e-05, "loss": 0.0235, "step": 1681 }, { "epoch": 5.8, "learning_rate": 1.1026767971634268e-05, "loss": 0.0243, "step": 1682 }, { "epoch": 5.8, "learning_rate": 1.1017508302610665e-05, "loss": 0.0236, "step": 1683 }, { "epoch": 5.81, "learning_rate": 1.1008247751949426e-05, "loss": 0.0371, "step": 1684 }, { "epoch": 5.81, "learning_rate": 1.0998986327674515e-05, "loss": 0.0368, "step": 1685 }, { "epoch": 5.81, "learning_rate": 1.0989724037810651e-05, "loss": 0.0596, "step": 1686 }, { "epoch": 5.82, "learning_rate": 1.0980460890383309e-05, "loss": 0.0201, "step": 1687 }, { "epoch": 5.82, "learning_rate": 1.09711968934187e-05, "loss": 0.031, "step": 1688 }, { "epoch": 5.82, "learning_rate": 1.0961932054943778e-05, "loss": 0.0317, "step": 1689 }, { "epoch": 5.83, "learning_rate": 1.0952666382986216e-05, "loss": 0.0473, "step": 1690 }, { "epoch": 5.83, "learning_rate": 1.0943399885574422e-05, "loss": 0.0293, "step": 1691 }, { "epoch": 5.83, "learning_rate": 1.0934132570737508e-05, "loss": 0.0464, "step": 1692 }, { "epoch": 5.84, "learning_rate": 1.0924864446505301e-05, "loss": 0.0302, "step": 1693 }, { "epoch": 5.84, "learning_rate": 1.0915595520908326e-05, "loss": 0.033, "step": 1694 }, { "epoch": 5.84, "learning_rate": 1.0906325801977804e-05, "loss": 0.0276, "step": 1695 }, { "epoch": 5.85, "learning_rate": 1.0897055297745645e-05, "loss": 0.0339, "step": 1696 }, { "epoch": 5.85, "learning_rate": 1.0887784016244434e-05, "loss": 0.0398, "step": 1697 }, { "epoch": 5.86, "learning_rate": 1.0878511965507435e-05, "loss": 0.0478, "step": 1698 }, { "epoch": 5.86, "learning_rate": 1.0869239153568575e-05, "loss": 0.0347, "step": 1699 }, { "epoch": 5.86, "learning_rate": 1.0859965588462442e-05, "loss": 0.0239, "step": 1700 }, { "epoch": 5.87, "learning_rate": 1.0850691278224282e-05, "loss": 0.0247, "step": 1701 }, { "epoch": 5.87, "learning_rate": 1.0841416230889977e-05, "loss": 0.033, "step": 1702 }, { "epoch": 5.87, "learning_rate": 1.0832140454496047e-05, "loss": 0.03, "step": 1703 }, { "epoch": 5.88, "learning_rate": 1.0822863957079657e-05, "loss": 0.0355, "step": 1704 }, { "epoch": 5.88, "learning_rate": 1.0813586746678584e-05, "loss": 0.0174, "step": 1705 }, { "epoch": 5.88, "learning_rate": 1.0804308831331228e-05, "loss": 0.0212, "step": 1706 }, { "epoch": 5.89, "learning_rate": 1.07950302190766e-05, "loss": 0.0171, "step": 1707 }, { "epoch": 5.89, "learning_rate": 1.078575091795431e-05, "loss": 0.0372, "step": 1708 }, { "epoch": 5.89, "learning_rate": 1.0776470936004572e-05, "loss": 0.0333, "step": 1709 }, { "epoch": 5.9, "learning_rate": 1.0767190281268187e-05, "loss": 0.0271, "step": 1710 }, { "epoch": 5.9, "learning_rate": 1.0757908961786536e-05, "loss": 0.038, "step": 1711 }, { "epoch": 5.9, "learning_rate": 1.0748626985601583e-05, "loss": 0.0261, "step": 1712 }, { "epoch": 5.91, "learning_rate": 1.0739344360755853e-05, "loss": 0.016, "step": 1713 }, { "epoch": 5.91, "learning_rate": 1.0730061095292434e-05, "loss": 0.0308, "step": 1714 }, { "epoch": 5.91, "learning_rate": 1.0720777197254974e-05, "loss": 0.0202, "step": 1715 }, { "epoch": 5.92, "learning_rate": 1.071149267468767e-05, "loss": 0.0312, "step": 1716 }, { "epoch": 5.92, "learning_rate": 1.0702207535635253e-05, "loss": 0.043, "step": 1717 }, { "epoch": 5.92, "learning_rate": 1.0692921788142993e-05, "loss": 0.033, "step": 1718 }, { "epoch": 5.93, "learning_rate": 1.0683635440256689e-05, "loss": 0.0413, "step": 1719 }, { "epoch": 5.93, "learning_rate": 1.0674348500022653e-05, "loss": 0.0316, "step": 1720 }, { "epoch": 5.93, "learning_rate": 1.0665060975487716e-05, "loss": 0.0254, "step": 1721 }, { "epoch": 5.94, "learning_rate": 1.0655772874699217e-05, "loss": 0.0377, "step": 1722 }, { "epoch": 5.94, "learning_rate": 1.0646484205704987e-05, "loss": 0.0357, "step": 1723 }, { "epoch": 5.94, "learning_rate": 1.0637194976553356e-05, "loss": 0.0277, "step": 1724 }, { "epoch": 5.95, "learning_rate": 1.0627905195293135e-05, "loss": 0.0254, "step": 1725 }, { "epoch": 5.95, "learning_rate": 1.061861486997362e-05, "loss": 0.0419, "step": 1726 }, { "epoch": 5.96, "learning_rate": 1.0609324008644568e-05, "loss": 0.0256, "step": 1727 }, { "epoch": 5.96, "learning_rate": 1.0600032619356208e-05, "loss": 0.0211, "step": 1728 }, { "epoch": 5.96, "learning_rate": 1.059074071015923e-05, "loss": 0.0395, "step": 1729 }, { "epoch": 5.97, "learning_rate": 1.0581448289104759e-05, "loss": 0.03, "step": 1730 }, { "epoch": 5.97, "learning_rate": 1.0572155364244383e-05, "loss": 0.0337, "step": 1731 }, { "epoch": 5.97, "learning_rate": 1.0562861943630111e-05, "loss": 0.0286, "step": 1732 }, { "epoch": 5.98, "learning_rate": 1.0553568035314392e-05, "loss": 0.0325, "step": 1733 }, { "epoch": 5.98, "learning_rate": 1.0544273647350091e-05, "loss": 0.026, "step": 1734 }, { "epoch": 5.98, "learning_rate": 1.0534978787790494e-05, "loss": 0.0353, "step": 1735 }, { "epoch": 5.99, "learning_rate": 1.0525683464689287e-05, "loss": 0.0303, "step": 1736 }, { "epoch": 5.99, "learning_rate": 1.0516387686100566e-05, "loss": 0.0375, "step": 1737 }, { "epoch": 5.99, "learning_rate": 1.050709146007882e-05, "loss": 0.0294, "step": 1738 }, { "epoch": 6.0, "learning_rate": 1.0497794794678923e-05, "loss": 0.0324, "step": 1739 }, { "epoch": 6.0, "learning_rate": 1.0488497697956134e-05, "loss": 0.0263, "step": 1740 }, { "epoch": 6.0, "learning_rate": 1.047920017796608e-05, "loss": 0.015, "step": 1741 }, { "epoch": 6.01, "learning_rate": 1.0469902242764757e-05, "loss": 0.0186, "step": 1742 }, { "epoch": 6.01, "learning_rate": 1.0460603900408523e-05, "loss": 0.0207, "step": 1743 }, { "epoch": 6.01, "learning_rate": 1.0451305158954087e-05, "loss": 0.0084, "step": 1744 }, { "epoch": 6.02, "learning_rate": 1.0442006026458506e-05, "loss": 0.0216, "step": 1745 }, { "epoch": 6.02, "learning_rate": 1.0432706510979172e-05, "loss": 0.0257, "step": 1746 }, { "epoch": 6.02, "learning_rate": 1.042340662057381e-05, "loss": 0.0094, "step": 1747 }, { "epoch": 6.03, "learning_rate": 1.0414106363300472e-05, "loss": 0.0105, "step": 1748 }, { "epoch": 6.03, "learning_rate": 1.0404805747217525e-05, "loss": 0.022, "step": 1749 }, { "epoch": 6.03, "learning_rate": 1.0395504780383653e-05, "loss": 0.0153, "step": 1750 }, { "epoch": 6.04, "learning_rate": 1.0386203470857832e-05, "loss": 0.0091, "step": 1751 }, { "epoch": 6.04, "learning_rate": 1.0376901826699349e-05, "loss": 0.015, "step": 1752 }, { "epoch": 6.04, "learning_rate": 1.0367599855967767e-05, "loss": 0.0135, "step": 1753 }, { "epoch": 6.05, "learning_rate": 1.0358297566722945e-05, "loss": 0.0142, "step": 1754 }, { "epoch": 6.05, "learning_rate": 1.0348994967025012e-05, "loss": 0.02, "step": 1755 }, { "epoch": 6.06, "learning_rate": 1.0339692064934364e-05, "loss": 0.0195, "step": 1756 }, { "epoch": 6.06, "learning_rate": 1.033038886851166e-05, "loss": 0.0075, "step": 1757 }, { "epoch": 6.06, "learning_rate": 1.0321085385817818e-05, "loss": 0.01, "step": 1758 }, { "epoch": 6.07, "learning_rate": 1.0311781624914e-05, "loss": 0.0162, "step": 1759 }, { "epoch": 6.07, "learning_rate": 1.0302477593861608e-05, "loss": 0.0116, "step": 1760 }, { "epoch": 6.07, "learning_rate": 1.0293173300722286e-05, "loss": 0.0078, "step": 1761 }, { "epoch": 6.08, "learning_rate": 1.0283868753557894e-05, "loss": 0.0168, "step": 1762 }, { "epoch": 6.08, "learning_rate": 1.0274563960430518e-05, "loss": 0.0078, "step": 1763 }, { "epoch": 6.08, "learning_rate": 1.026525892940246e-05, "loss": 0.0327, "step": 1764 }, { "epoch": 6.09, "learning_rate": 1.0255953668536223e-05, "loss": 0.0079, "step": 1765 }, { "epoch": 6.09, "learning_rate": 1.0246648185894512e-05, "loss": 0.0183, "step": 1766 }, { "epoch": 6.09, "learning_rate": 1.0237342489540221e-05, "loss": 0.024, "step": 1767 }, { "epoch": 6.1, "learning_rate": 1.0228036587536431e-05, "loss": 0.0095, "step": 1768 }, { "epoch": 6.1, "learning_rate": 1.0218730487946407e-05, "loss": 0.0109, "step": 1769 }, { "epoch": 6.1, "learning_rate": 1.0209424198833571e-05, "loss": 0.0142, "step": 1770 }, { "epoch": 6.11, "learning_rate": 1.0200117728261522e-05, "loss": 0.0222, "step": 1771 }, { "epoch": 6.11, "learning_rate": 1.0190811084294014e-05, "loss": 0.0094, "step": 1772 }, { "epoch": 6.11, "learning_rate": 1.0181504274994949e-05, "loss": 0.0116, "step": 1773 }, { "epoch": 6.12, "learning_rate": 1.0172197308428368e-05, "loss": 0.022, "step": 1774 }, { "epoch": 6.12, "learning_rate": 1.0162890192658459e-05, "loss": 0.0144, "step": 1775 }, { "epoch": 6.12, "learning_rate": 1.0153582935749531e-05, "loss": 0.0164, "step": 1776 }, { "epoch": 6.13, "learning_rate": 1.0144275545766014e-05, "loss": 0.012, "step": 1777 }, { "epoch": 6.13, "learning_rate": 1.013496803077246e-05, "loss": 0.0129, "step": 1778 }, { "epoch": 6.13, "learning_rate": 1.0125660398833528e-05, "loss": 0.0108, "step": 1779 }, { "epoch": 6.14, "learning_rate": 1.0116352658013973e-05, "loss": 0.0064, "step": 1780 }, { "epoch": 6.14, "learning_rate": 1.0107044816378646e-05, "loss": 0.0113, "step": 1781 }, { "epoch": 6.14, "learning_rate": 1.0097736881992492e-05, "loss": 0.0095, "step": 1782 }, { "epoch": 6.15, "learning_rate": 1.0088428862920529e-05, "loss": 0.0391, "step": 1783 }, { "epoch": 6.15, "learning_rate": 1.007912076722785e-05, "loss": 0.0076, "step": 1784 }, { "epoch": 6.16, "learning_rate": 1.0069812602979617e-05, "loss": 0.0158, "step": 1785 }, { "epoch": 6.16, "learning_rate": 1.0060504378241049e-05, "loss": 0.0163, "step": 1786 }, { "epoch": 6.16, "learning_rate": 1.0051196101077416e-05, "loss": 0.0287, "step": 1787 }, { "epoch": 6.17, "learning_rate": 1.0041887779554041e-05, "loss": 0.0167, "step": 1788 }, { "epoch": 6.17, "learning_rate": 1.0032579421736275e-05, "loss": 0.0144, "step": 1789 }, { "epoch": 6.17, "learning_rate": 1.0023271035689506e-05, "loss": 0.0121, "step": 1790 }, { "epoch": 6.18, "learning_rate": 1.0013962629479145e-05, "loss": 0.0097, "step": 1791 }, { "epoch": 6.18, "learning_rate": 1.0004654211170623e-05, "loss": 0.021, "step": 1792 }, { "epoch": 6.18, "learning_rate": 9.995345788829382e-06, "loss": 0.0379, "step": 1793 }, { "epoch": 6.19, "learning_rate": 9.986037370520856e-06, "loss": 0.0138, "step": 1794 }, { "epoch": 6.19, "learning_rate": 9.976728964310499e-06, "loss": 0.0218, "step": 1795 }, { "epoch": 6.19, "learning_rate": 9.967420578263728e-06, "loss": 0.0144, "step": 1796 }, { "epoch": 6.2, "learning_rate": 9.958112220445964e-06, "loss": 0.0186, "step": 1797 }, { "epoch": 6.2, "learning_rate": 9.948803898922586e-06, "loss": 0.0114, "step": 1798 }, { "epoch": 6.2, "learning_rate": 9.939495621758956e-06, "loss": 0.0195, "step": 1799 }, { "epoch": 6.21, "learning_rate": 9.930187397020385e-06, "loss": 0.0088, "step": 1800 }, { "epoch": 6.21, "learning_rate": 9.920879232772155e-06, "loss": 0.013, "step": 1801 }, { "epoch": 6.21, "learning_rate": 9.911571137079474e-06, "loss": 0.0143, "step": 1802 }, { "epoch": 6.22, "learning_rate": 9.902263118007513e-06, "loss": 0.0159, "step": 1803 }, { "epoch": 6.22, "learning_rate": 9.892955183621356e-06, "loss": 0.0172, "step": 1804 }, { "epoch": 6.22, "learning_rate": 9.883647341986032e-06, "loss": 0.0111, "step": 1805 }, { "epoch": 6.23, "learning_rate": 9.874339601166474e-06, "loss": 0.0101, "step": 1806 }, { "epoch": 6.23, "learning_rate": 9.865031969227543e-06, "loss": 0.0166, "step": 1807 }, { "epoch": 6.23, "learning_rate": 9.85572445423399e-06, "loss": 0.015, "step": 1808 }, { "epoch": 6.24, "learning_rate": 9.84641706425047e-06, "loss": 0.0113, "step": 1809 }, { "epoch": 6.24, "learning_rate": 9.837109807341543e-06, "loss": 0.0342, "step": 1810 }, { "epoch": 6.24, "learning_rate": 9.82780269157163e-06, "loss": 0.006, "step": 1811 }, { "epoch": 6.25, "learning_rate": 9.818495725005053e-06, "loss": 0.0138, "step": 1812 }, { "epoch": 6.25, "learning_rate": 9.809188915705986e-06, "loss": 0.0126, "step": 1813 }, { "epoch": 6.26, "learning_rate": 9.79988227173848e-06, "loss": 0.0159, "step": 1814 }, { "epoch": 6.26, "learning_rate": 9.790575801166432e-06, "loss": 0.0175, "step": 1815 }, { "epoch": 6.26, "learning_rate": 9.781269512053598e-06, "loss": 0.0181, "step": 1816 }, { "epoch": 6.27, "learning_rate": 9.77196341246357e-06, "loss": 0.0186, "step": 1817 }, { "epoch": 6.27, "learning_rate": 9.762657510459784e-06, "loss": 0.006, "step": 1818 }, { "epoch": 6.27, "learning_rate": 9.75335181410549e-06, "loss": 0.0075, "step": 1819 }, { "epoch": 6.28, "learning_rate": 9.74404633146378e-06, "loss": 0.0236, "step": 1820 }, { "epoch": 6.28, "learning_rate": 9.73474107059754e-06, "loss": 0.0317, "step": 1821 }, { "epoch": 6.28, "learning_rate": 9.725436039569485e-06, "loss": 0.0254, "step": 1822 }, { "epoch": 6.29, "learning_rate": 9.716131246442108e-06, "loss": 0.011, "step": 1823 }, { "epoch": 6.29, "learning_rate": 9.706826699277719e-06, "loss": 0.0158, "step": 1824 }, { "epoch": 6.29, "learning_rate": 9.697522406138395e-06, "loss": 0.0262, "step": 1825 }, { "epoch": 6.3, "learning_rate": 9.688218375086005e-06, "loss": 0.0078, "step": 1826 }, { "epoch": 6.3, "learning_rate": 9.678914614182185e-06, "loss": 0.0121, "step": 1827 }, { "epoch": 6.3, "learning_rate": 9.669611131488346e-06, "loss": 0.02, "step": 1828 }, { "epoch": 6.31, "learning_rate": 9.660307935065641e-06, "loss": 0.0201, "step": 1829 }, { "epoch": 6.31, "learning_rate": 9.651005032974994e-06, "loss": 0.0145, "step": 1830 }, { "epoch": 6.31, "learning_rate": 9.641702433277056e-06, "loss": 0.0058, "step": 1831 }, { "epoch": 6.32, "learning_rate": 9.632400144032236e-06, "loss": 0.0101, "step": 1832 }, { "epoch": 6.32, "learning_rate": 9.623098173300655e-06, "loss": 0.0181, "step": 1833 }, { "epoch": 6.32, "learning_rate": 9.613796529142172e-06, "loss": 0.0095, "step": 1834 }, { "epoch": 6.33, "learning_rate": 9.60449521961635e-06, "loss": 0.0152, "step": 1835 }, { "epoch": 6.33, "learning_rate": 9.595194252782476e-06, "loss": 0.0105, "step": 1836 }, { "epoch": 6.33, "learning_rate": 9.585893636699532e-06, "loss": 0.0087, "step": 1837 }, { "epoch": 6.34, "learning_rate": 9.576593379426196e-06, "loss": 0.011, "step": 1838 }, { "epoch": 6.34, "learning_rate": 9.567293489020831e-06, "loss": 0.0136, "step": 1839 }, { "epoch": 6.34, "learning_rate": 9.557993973541494e-06, "loss": 0.014, "step": 1840 }, { "epoch": 6.35, "learning_rate": 9.548694841045914e-06, "loss": 0.0103, "step": 1841 }, { "epoch": 6.35, "learning_rate": 9.539396099591477e-06, "loss": 0.0116, "step": 1842 }, { "epoch": 6.36, "learning_rate": 9.530097757235246e-06, "loss": 0.0196, "step": 1843 }, { "epoch": 6.36, "learning_rate": 9.520799822033923e-06, "loss": 0.0305, "step": 1844 }, { "epoch": 6.36, "learning_rate": 9.511502302043867e-06, "loss": 0.0097, "step": 1845 }, { "epoch": 6.37, "learning_rate": 9.502205205321078e-06, "loss": 0.0145, "step": 1846 }, { "epoch": 6.37, "learning_rate": 9.492908539921183e-06, "loss": 0.0148, "step": 1847 }, { "epoch": 6.37, "learning_rate": 9.483612313899436e-06, "loss": 0.0098, "step": 1848 }, { "epoch": 6.38, "learning_rate": 9.474316535310717e-06, "loss": 0.0117, "step": 1849 }, { "epoch": 6.38, "learning_rate": 9.465021212209508e-06, "loss": 0.0128, "step": 1850 }, { "epoch": 6.38, "learning_rate": 9.45572635264991e-06, "loss": 0.0081, "step": 1851 }, { "epoch": 6.39, "learning_rate": 9.446431964685606e-06, "loss": 0.0107, "step": 1852 }, { "epoch": 6.39, "learning_rate": 9.43713805636989e-06, "loss": 0.0074, "step": 1853 }, { "epoch": 6.39, "learning_rate": 9.42784463575562e-06, "loss": 0.0078, "step": 1854 }, { "epoch": 6.4, "learning_rate": 9.418551710895243e-06, "loss": 0.0168, "step": 1855 }, { "epoch": 6.4, "learning_rate": 9.409259289840774e-06, "loss": 0.0099, "step": 1856 }, { "epoch": 6.4, "learning_rate": 9.399967380643795e-06, "loss": 0.0196, "step": 1857 }, { "epoch": 6.41, "learning_rate": 9.390675991355435e-06, "loss": 0.0106, "step": 1858 }, { "epoch": 6.41, "learning_rate": 9.381385130026386e-06, "loss": 0.0093, "step": 1859 }, { "epoch": 6.41, "learning_rate": 9.372094804706867e-06, "loss": 0.0127, "step": 1860 }, { "epoch": 6.42, "learning_rate": 9.36280502344665e-06, "loss": 0.0134, "step": 1861 }, { "epoch": 6.42, "learning_rate": 9.353515794295016e-06, "loss": 0.0121, "step": 1862 }, { "epoch": 6.42, "learning_rate": 9.344227125300788e-06, "loss": 0.0081, "step": 1863 }, { "epoch": 6.43, "learning_rate": 9.334939024512288e-06, "loss": 0.013, "step": 1864 }, { "epoch": 6.43, "learning_rate": 9.32565149997735e-06, "loss": 0.0135, "step": 1865 }, { "epoch": 6.43, "learning_rate": 9.316364559743315e-06, "loss": 0.0073, "step": 1866 }, { "epoch": 6.44, "learning_rate": 9.30707821185701e-06, "loss": 0.0121, "step": 1867 }, { "epoch": 6.44, "learning_rate": 9.297792464364748e-06, "loss": 0.012, "step": 1868 }, { "epoch": 6.44, "learning_rate": 9.288507325312334e-06, "loss": 0.0303, "step": 1869 }, { "epoch": 6.45, "learning_rate": 9.279222802745028e-06, "loss": 0.008, "step": 1870 }, { "epoch": 6.45, "learning_rate": 9.269938904707568e-06, "loss": 0.016, "step": 1871 }, { "epoch": 6.46, "learning_rate": 9.260655639244152e-06, "loss": 0.0177, "step": 1872 }, { "epoch": 6.46, "learning_rate": 9.251373014398419e-06, "loss": 0.0172, "step": 1873 }, { "epoch": 6.46, "learning_rate": 9.242091038213466e-06, "loss": 0.0047, "step": 1874 }, { "epoch": 6.47, "learning_rate": 9.232809718731815e-06, "loss": 0.0173, "step": 1875 }, { "epoch": 6.47, "learning_rate": 9.223529063995431e-06, "loss": 0.0194, "step": 1876 }, { "epoch": 6.47, "learning_rate": 9.214249082045691e-06, "loss": 0.0178, "step": 1877 }, { "epoch": 6.48, "learning_rate": 9.204969780923404e-06, "loss": 0.0174, "step": 1878 }, { "epoch": 6.48, "learning_rate": 9.195691168668774e-06, "loss": 0.0115, "step": 1879 }, { "epoch": 6.48, "learning_rate": 9.18641325332142e-06, "loss": 0.013, "step": 1880 }, { "epoch": 6.49, "learning_rate": 9.177136042920344e-06, "loss": 0.0122, "step": 1881 }, { "epoch": 6.49, "learning_rate": 9.167859545503955e-06, "loss": 0.0233, "step": 1882 }, { "epoch": 6.49, "learning_rate": 9.158583769110028e-06, "loss": 0.0128, "step": 1883 }, { "epoch": 6.5, "learning_rate": 9.14930872177572e-06, "loss": 0.01, "step": 1884 }, { "epoch": 6.5, "learning_rate": 9.140034411537558e-06, "loss": 0.0158, "step": 1885 }, { "epoch": 6.5, "learning_rate": 9.13076084643143e-06, "loss": 0.0186, "step": 1886 }, { "epoch": 6.51, "learning_rate": 9.121488034492569e-06, "loss": 0.0086, "step": 1887 }, { "epoch": 6.51, "learning_rate": 9.112215983755573e-06, "loss": 0.0131, "step": 1888 }, { "epoch": 6.51, "learning_rate": 9.10294470225436e-06, "loss": 0.0162, "step": 1889 }, { "epoch": 6.52, "learning_rate": 9.093674198022201e-06, "loss": 0.0171, "step": 1890 }, { "epoch": 6.52, "learning_rate": 9.084404479091676e-06, "loss": 0.0163, "step": 1891 }, { "epoch": 6.52, "learning_rate": 9.075135553494704e-06, "loss": 0.0223, "step": 1892 }, { "epoch": 6.53, "learning_rate": 9.065867429262497e-06, "loss": 0.027, "step": 1893 }, { "epoch": 6.53, "learning_rate": 9.056600114425582e-06, "loss": 0.0093, "step": 1894 }, { "epoch": 6.53, "learning_rate": 9.047333617013786e-06, "loss": 0.0258, "step": 1895 }, { "epoch": 6.54, "learning_rate": 9.038067945056229e-06, "loss": 0.0133, "step": 1896 }, { "epoch": 6.54, "learning_rate": 9.0288031065813e-06, "loss": 0.0104, "step": 1897 }, { "epoch": 6.54, "learning_rate": 9.019539109616694e-06, "loss": 0.0132, "step": 1898 }, { "epoch": 6.55, "learning_rate": 9.01027596218935e-06, "loss": 0.0173, "step": 1899 }, { "epoch": 6.55, "learning_rate": 9.001013672325491e-06, "loss": 0.0139, "step": 1900 }, { "epoch": 6.56, "learning_rate": 8.991752248050578e-06, "loss": 0.013, "step": 1901 }, { "epoch": 6.56, "learning_rate": 8.982491697389339e-06, "loss": 0.0094, "step": 1902 }, { "epoch": 6.56, "learning_rate": 8.973232028365737e-06, "loss": 0.0255, "step": 1903 }, { "epoch": 6.57, "learning_rate": 8.963973249002967e-06, "loss": 0.0039, "step": 1904 }, { "epoch": 6.57, "learning_rate": 8.954715367323468e-06, "loss": 0.0102, "step": 1905 }, { "epoch": 6.57, "learning_rate": 8.94545839134888e-06, "loss": 0.0115, "step": 1906 }, { "epoch": 6.58, "learning_rate": 8.93620232910008e-06, "loss": 0.0109, "step": 1907 }, { "epoch": 6.58, "learning_rate": 8.926947188597133e-06, "loss": 0.0089, "step": 1908 }, { "epoch": 6.58, "learning_rate": 8.917692977859326e-06, "loss": 0.0222, "step": 1909 }, { "epoch": 6.59, "learning_rate": 8.90843970490512e-06, "loss": 0.0152, "step": 1910 }, { "epoch": 6.59, "learning_rate": 8.89918737775218e-06, "loss": 0.0126, "step": 1911 }, { "epoch": 6.59, "learning_rate": 8.88993600441734e-06, "loss": 0.0144, "step": 1912 }, { "epoch": 6.6, "learning_rate": 8.880685592916617e-06, "loss": 0.0171, "step": 1913 }, { "epoch": 6.6, "learning_rate": 8.871436151265183e-06, "loss": 0.0041, "step": 1914 }, { "epoch": 6.6, "learning_rate": 8.862187687477386e-06, "loss": 0.0186, "step": 1915 }, { "epoch": 6.61, "learning_rate": 8.852940209566704e-06, "loss": 0.0223, "step": 1916 }, { "epoch": 6.61, "learning_rate": 8.843693725545787e-06, "loss": 0.019, "step": 1917 }, { "epoch": 6.61, "learning_rate": 8.8344482434264e-06, "loss": 0.0112, "step": 1918 }, { "epoch": 6.62, "learning_rate": 8.82520377121946e-06, "loss": 0.0146, "step": 1919 }, { "epoch": 6.62, "learning_rate": 8.815960316934991e-06, "loss": 0.0112, "step": 1920 }, { "epoch": 6.62, "learning_rate": 8.806717888582151e-06, "loss": 0.0104, "step": 1921 }, { "epoch": 6.63, "learning_rate": 8.797476494169197e-06, "loss": 0.0192, "step": 1922 }, { "epoch": 6.63, "learning_rate": 8.788236141703498e-06, "loss": 0.0112, "step": 1923 }, { "epoch": 6.63, "learning_rate": 8.77899683919151e-06, "loss": 0.0085, "step": 1924 }, { "epoch": 6.64, "learning_rate": 8.769758594638796e-06, "loss": 0.0129, "step": 1925 }, { "epoch": 6.64, "learning_rate": 8.760521416049983e-06, "loss": 0.0113, "step": 1926 }, { "epoch": 6.64, "learning_rate": 8.751285311428793e-06, "loss": 0.0159, "step": 1927 }, { "epoch": 6.65, "learning_rate": 8.742050288778e-06, "loss": 0.0118, "step": 1928 }, { "epoch": 6.65, "learning_rate": 8.732816356099455e-06, "loss": 0.0061, "step": 1929 }, { "epoch": 6.66, "learning_rate": 8.723583521394054e-06, "loss": 0.0077, "step": 1930 }, { "epoch": 6.66, "learning_rate": 8.714351792661752e-06, "loss": 0.0125, "step": 1931 }, { "epoch": 6.66, "learning_rate": 8.705121177901532e-06, "loss": 0.0164, "step": 1932 }, { "epoch": 6.67, "learning_rate": 8.695891685111423e-06, "loss": 0.0087, "step": 1933 }, { "epoch": 6.67, "learning_rate": 8.686663322288482e-06, "loss": 0.0153, "step": 1934 }, { "epoch": 6.67, "learning_rate": 8.677436097428775e-06, "loss": 0.0222, "step": 1935 }, { "epoch": 6.68, "learning_rate": 8.668210018527399e-06, "loss": 0.0143, "step": 1936 }, { "epoch": 6.68, "learning_rate": 8.658985093578444e-06, "loss": 0.0113, "step": 1937 }, { "epoch": 6.68, "learning_rate": 8.649761330575009e-06, "loss": 0.0217, "step": 1938 }, { "epoch": 6.69, "learning_rate": 8.64053873750918e-06, "loss": 0.0146, "step": 1939 }, { "epoch": 6.69, "learning_rate": 8.631317322372032e-06, "loss": 0.0064, "step": 1940 }, { "epoch": 6.69, "learning_rate": 8.62209709315362e-06, "loss": 0.0175, "step": 1941 }, { "epoch": 6.7, "learning_rate": 8.612878057842974e-06, "loss": 0.0176, "step": 1942 }, { "epoch": 6.7, "learning_rate": 8.603660224428077e-06, "loss": 0.0151, "step": 1943 }, { "epoch": 6.7, "learning_rate": 8.594443600895892e-06, "loss": 0.0069, "step": 1944 }, { "epoch": 6.71, "learning_rate": 8.585228195232311e-06, "loss": 0.0073, "step": 1945 }, { "epoch": 6.71, "learning_rate": 8.57601401542219e-06, "loss": 0.0208, "step": 1946 }, { "epoch": 6.71, "learning_rate": 8.566801069449307e-06, "loss": 0.0096, "step": 1947 }, { "epoch": 6.72, "learning_rate": 8.557589365296385e-06, "loss": 0.0121, "step": 1948 }, { "epoch": 6.72, "learning_rate": 8.548378910945058e-06, "loss": 0.0237, "step": 1949 }, { "epoch": 6.72, "learning_rate": 8.539169714375885e-06, "loss": 0.0237, "step": 1950 }, { "epoch": 6.73, "learning_rate": 8.529961783568334e-06, "loss": 0.0087, "step": 1951 }, { "epoch": 6.73, "learning_rate": 8.52075512650078e-06, "loss": 0.0051, "step": 1952 }, { "epoch": 6.73, "learning_rate": 8.511549751150478e-06, "loss": 0.0171, "step": 1953 }, { "epoch": 6.74, "learning_rate": 8.502345665493598e-06, "loss": 0.0217, "step": 1954 }, { "epoch": 6.74, "learning_rate": 8.49314287750517e-06, "loss": 0.0198, "step": 1955 }, { "epoch": 6.74, "learning_rate": 8.483941395159114e-06, "loss": 0.0125, "step": 1956 }, { "epoch": 6.75, "learning_rate": 8.474741226428206e-06, "loss": 0.01, "step": 1957 }, { "epoch": 6.75, "learning_rate": 8.4655423792841e-06, "loss": 0.0096, "step": 1958 }, { "epoch": 6.76, "learning_rate": 8.45634486169729e-06, "loss": 0.0112, "step": 1959 }, { "epoch": 6.76, "learning_rate": 8.447148681637127e-06, "loss": 0.0256, "step": 1960 }, { "epoch": 6.76, "learning_rate": 8.437953847071797e-06, "loss": 0.0081, "step": 1961 }, { "epoch": 6.77, "learning_rate": 8.428760365968327e-06, "loss": 0.0229, "step": 1962 }, { "epoch": 6.77, "learning_rate": 8.41956824629256e-06, "loss": 0.0241, "step": 1963 }, { "epoch": 6.77, "learning_rate": 8.410377496009172e-06, "loss": 0.0145, "step": 1964 }, { "epoch": 6.78, "learning_rate": 8.401188123081653e-06, "loss": 0.012, "step": 1965 }, { "epoch": 6.78, "learning_rate": 8.392000135472283e-06, "loss": 0.0133, "step": 1966 }, { "epoch": 6.78, "learning_rate": 8.382813541142161e-06, "loss": 0.0182, "step": 1967 }, { "epoch": 6.79, "learning_rate": 8.373628348051165e-06, "loss": 0.0212, "step": 1968 }, { "epoch": 6.79, "learning_rate": 8.364444564157966e-06, "loss": 0.0166, "step": 1969 }, { "epoch": 6.79, "learning_rate": 8.355262197420011e-06, "loss": 0.0063, "step": 1970 }, { "epoch": 6.8, "learning_rate": 8.346081255793524e-06, "loss": 0.0221, "step": 1971 }, { "epoch": 6.8, "learning_rate": 8.336901747233483e-06, "loss": 0.0097, "step": 1972 }, { "epoch": 6.8, "learning_rate": 8.327723679693643e-06, "loss": 0.0155, "step": 1973 }, { "epoch": 6.81, "learning_rate": 8.318547061126485e-06, "loss": 0.0086, "step": 1974 }, { "epoch": 6.81, "learning_rate": 8.309371899483261e-06, "loss": 0.0138, "step": 1975 }, { "epoch": 6.81, "learning_rate": 8.300198202713938e-06, "loss": 0.0074, "step": 1976 }, { "epoch": 6.82, "learning_rate": 8.291025978767236e-06, "loss": 0.0095, "step": 1977 }, { "epoch": 6.82, "learning_rate": 8.281855235590574e-06, "loss": 0.0133, "step": 1978 }, { "epoch": 6.82, "learning_rate": 8.27268598113011e-06, "loss": 0.0173, "step": 1979 }, { "epoch": 6.83, "learning_rate": 8.263518223330698e-06, "loss": 0.022, "step": 1980 }, { "epoch": 6.83, "learning_rate": 8.254351970135902e-06, "loss": 0.0176, "step": 1981 }, { "epoch": 6.83, "learning_rate": 8.24518722948798e-06, "loss": 0.0094, "step": 1982 }, { "epoch": 6.84, "learning_rate": 8.236024009327879e-06, "loss": 0.0118, "step": 1983 }, { "epoch": 6.84, "learning_rate": 8.226862317595227e-06, "loss": 0.0202, "step": 1984 }, { "epoch": 6.84, "learning_rate": 8.217702162228337e-06, "loss": 0.0091, "step": 1985 }, { "epoch": 6.85, "learning_rate": 8.208543551164178e-06, "loss": 0.0176, "step": 1986 }, { "epoch": 6.85, "learning_rate": 8.19938649233839e-06, "loss": 0.005, "step": 1987 }, { "epoch": 6.86, "learning_rate": 8.19023099368526e-06, "loss": 0.0193, "step": 1988 }, { "epoch": 6.86, "learning_rate": 8.181077063137733e-06, "loss": 0.0121, "step": 1989 }, { "epoch": 6.86, "learning_rate": 8.171924708627387e-06, "loss": 0.0189, "step": 1990 }, { "epoch": 6.87, "learning_rate": 8.162773938084443e-06, "loss": 0.0174, "step": 1991 }, { "epoch": 6.87, "learning_rate": 8.153624759437733e-06, "loss": 0.0117, "step": 1992 }, { "epoch": 6.87, "learning_rate": 8.144477180614731e-06, "loss": 0.0104, "step": 1993 }, { "epoch": 6.88, "learning_rate": 8.135331209541509e-06, "loss": 0.0131, "step": 1994 }, { "epoch": 6.88, "learning_rate": 8.126186854142752e-06, "loss": 0.0246, "step": 1995 }, { "epoch": 6.88, "learning_rate": 8.117044122341752e-06, "loss": 0.0173, "step": 1996 }, { "epoch": 6.89, "learning_rate": 8.107903022060377e-06, "loss": 0.0138, "step": 1997 }, { "epoch": 6.89, "learning_rate": 8.098763561219101e-06, "loss": 0.012, "step": 1998 }, { "epoch": 6.89, "learning_rate": 8.089625747736955e-06, "loss": 0.0118, "step": 1999 }, { "epoch": 6.9, "learning_rate": 8.080489589531567e-06, "loss": 0.0176, "step": 2000 }, { "epoch": 6.9, "learning_rate": 8.07135509451911e-06, "loss": 0.0116, "step": 2001 }, { "epoch": 6.9, "learning_rate": 8.062222270614332e-06, "loss": 0.0215, "step": 2002 }, { "epoch": 6.91, "learning_rate": 8.05309112573052e-06, "loss": 0.0091, "step": 2003 }, { "epoch": 6.91, "learning_rate": 8.04396166777952e-06, "loss": 0.0163, "step": 2004 }, { "epoch": 6.91, "learning_rate": 8.034833904671698e-06, "loss": 0.0185, "step": 2005 }, { "epoch": 6.92, "learning_rate": 8.025707844315973e-06, "loss": 0.0208, "step": 2006 }, { "epoch": 6.92, "learning_rate": 8.016583494619769e-06, "loss": 0.011, "step": 2007 }, { "epoch": 6.92, "learning_rate": 8.007460863489042e-06, "loss": 0.0291, "step": 2008 }, { "epoch": 6.93, "learning_rate": 7.998339958828246e-06, "loss": 0.0116, "step": 2009 }, { "epoch": 6.93, "learning_rate": 7.989220788540356e-06, "loss": 0.01, "step": 2010 }, { "epoch": 6.93, "learning_rate": 7.980103360526824e-06, "loss": 0.014, "step": 2011 }, { "epoch": 6.94, "learning_rate": 7.970987682687615e-06, "loss": 0.0262, "step": 2012 }, { "epoch": 6.94, "learning_rate": 7.961873762921153e-06, "loss": 0.0095, "step": 2013 }, { "epoch": 6.94, "learning_rate": 7.952761609124362e-06, "loss": 0.0165, "step": 2014 }, { "epoch": 6.95, "learning_rate": 7.943651229192615e-06, "loss": 0.0156, "step": 2015 }, { "epoch": 6.95, "learning_rate": 7.934542631019767e-06, "loss": 0.0293, "step": 2016 }, { "epoch": 6.96, "learning_rate": 7.925435822498116e-06, "loss": 0.0222, "step": 2017 }, { "epoch": 6.96, "learning_rate": 7.91633081151841e-06, "loss": 0.0123, "step": 2018 }, { "epoch": 6.96, "learning_rate": 7.907227605969849e-06, "loss": 0.0102, "step": 2019 }, { "epoch": 6.97, "learning_rate": 7.898126213740063e-06, "loss": 0.0261, "step": 2020 }, { "epoch": 6.97, "learning_rate": 7.889026642715102e-06, "loss": 0.0132, "step": 2021 }, { "epoch": 6.97, "learning_rate": 7.879928900779457e-06, "loss": 0.0093, "step": 2022 }, { "epoch": 6.98, "learning_rate": 7.870832995816014e-06, "loss": 0.0167, "step": 2023 }, { "epoch": 6.98, "learning_rate": 7.861738935706084e-06, "loss": 0.0099, "step": 2024 }, { "epoch": 6.98, "learning_rate": 7.852646728329368e-06, "loss": 0.0139, "step": 2025 }, { "epoch": 6.99, "learning_rate": 7.84355638156397e-06, "loss": 0.0151, "step": 2026 }, { "epoch": 6.99, "learning_rate": 7.834467903286376e-06, "loss": 0.0116, "step": 2027 }, { "epoch": 6.99, "learning_rate": 7.825381301371452e-06, "loss": 0.0205, "step": 2028 }, { "epoch": 7.0, "learning_rate": 7.81629658369245e-06, "loss": 0.0064, "step": 2029 }, { "epoch": 7.0, "learning_rate": 7.807213758120965e-06, "loss": 0.0058, "step": 2030 }, { "epoch": 7.0, "learning_rate": 7.798132832526986e-06, "loss": 0.0051, "step": 2031 }, { "epoch": 7.01, "learning_rate": 7.789053814778825e-06, "loss": 0.0073, "step": 2032 }, { "epoch": 7.01, "learning_rate": 7.779976712743159e-06, "loss": 0.0109, "step": 2033 }, { "epoch": 7.01, "learning_rate": 7.770901534284996e-06, "loss": 0.0058, "step": 2034 }, { "epoch": 7.02, "learning_rate": 7.761828287267688e-06, "loss": 0.0033, "step": 2035 }, { "epoch": 7.02, "learning_rate": 7.7527569795529e-06, "loss": 0.0112, "step": 2036 }, { "epoch": 7.02, "learning_rate": 7.743687619000625e-06, "loss": 0.0048, "step": 2037 }, { "epoch": 7.03, "learning_rate": 7.734620213469166e-06, "loss": 0.013, "step": 2038 }, { "epoch": 7.03, "learning_rate": 7.725554770815137e-06, "loss": 0.0063, "step": 2039 }, { "epoch": 7.03, "learning_rate": 7.716491298893443e-06, "loss": 0.0157, "step": 2040 }, { "epoch": 7.04, "learning_rate": 7.707429805557289e-06, "loss": 0.0057, "step": 2041 }, { "epoch": 7.04, "learning_rate": 7.69837029865816e-06, "loss": 0.0082, "step": 2042 }, { "epoch": 7.04, "learning_rate": 7.689312786045823e-06, "loss": 0.0051, "step": 2043 }, { "epoch": 7.05, "learning_rate": 7.680257275568314e-06, "loss": 0.0031, "step": 2044 }, { "epoch": 7.05, "learning_rate": 7.671203775071942e-06, "loss": 0.0084, "step": 2045 }, { "epoch": 7.06, "learning_rate": 7.662152292401265e-06, "loss": 0.0209, "step": 2046 }, { "epoch": 7.06, "learning_rate": 7.653102835399097e-06, "loss": 0.0105, "step": 2047 }, { "epoch": 7.06, "learning_rate": 7.644055411906493e-06, "loss": 0.005, "step": 2048 }, { "epoch": 7.07, "learning_rate": 7.635010029762755e-06, "loss": 0.003, "step": 2049 }, { "epoch": 7.07, "learning_rate": 7.625966696805406e-06, "loss": 0.0076, "step": 2050 }, { "epoch": 7.07, "learning_rate": 7.616925420870203e-06, "loss": 0.0052, "step": 2051 }, { "epoch": 7.08, "learning_rate": 7.6078862097911075e-06, "loss": 0.0041, "step": 2052 }, { "epoch": 7.08, "learning_rate": 7.59884907140031e-06, "loss": 0.0098, "step": 2053 }, { "epoch": 7.08, "learning_rate": 7.5898140135281865e-06, "loss": 0.0063, "step": 2054 }, { "epoch": 7.09, "learning_rate": 7.580781044003324e-06, "loss": 0.0146, "step": 2055 }, { "epoch": 7.09, "learning_rate": 7.571750170652494e-06, "loss": 0.0067, "step": 2056 }, { "epoch": 7.09, "learning_rate": 7.562721401300649e-06, "loss": 0.0048, "step": 2057 }, { "epoch": 7.1, "learning_rate": 7.553694743770928e-06, "loss": 0.0024, "step": 2058 }, { "epoch": 7.1, "learning_rate": 7.544670205884629e-06, "loss": 0.003, "step": 2059 }, { "epoch": 7.1, "learning_rate": 7.535647795461224e-06, "loss": 0.0078, "step": 2060 }, { "epoch": 7.11, "learning_rate": 7.526627520318329e-06, "loss": 0.003, "step": 2061 }, { "epoch": 7.11, "learning_rate": 7.517609388271727e-06, "loss": 0.005, "step": 2062 }, { "epoch": 7.11, "learning_rate": 7.508593407135325e-06, "loss": 0.0071, "step": 2063 }, { "epoch": 7.12, "learning_rate": 7.49957958472118e-06, "loss": 0.007, "step": 2064 }, { "epoch": 7.12, "learning_rate": 7.490567928839472e-06, "loss": 0.0072, "step": 2065 }, { "epoch": 7.12, "learning_rate": 7.481558447298509e-06, "loss": 0.0049, "step": 2066 }, { "epoch": 7.13, "learning_rate": 7.472551147904708e-06, "loss": 0.006, "step": 2067 }, { "epoch": 7.13, "learning_rate": 7.463546038462602e-06, "loss": 0.0055, "step": 2068 }, { "epoch": 7.13, "learning_rate": 7.45454312677482e-06, "loss": 0.0173, "step": 2069 }, { "epoch": 7.14, "learning_rate": 7.445542420642097e-06, "loss": 0.0028, "step": 2070 }, { "epoch": 7.14, "learning_rate": 7.43654392786324e-06, "loss": 0.0044, "step": 2071 }, { "epoch": 7.14, "learning_rate": 7.4275476562351614e-06, "loss": 0.0113, "step": 2072 }, { "epoch": 7.15, "learning_rate": 7.418553613552824e-06, "loss": 0.0082, "step": 2073 }, { "epoch": 7.15, "learning_rate": 7.409561807609278e-06, "loss": 0.0043, "step": 2074 }, { "epoch": 7.16, "learning_rate": 7.400572246195628e-06, "loss": 0.0016, "step": 2075 }, { "epoch": 7.16, "learning_rate": 7.391584937101034e-06, "loss": 0.0047, "step": 2076 }, { "epoch": 7.16, "learning_rate": 7.382599888112703e-06, "loss": 0.0028, "step": 2077 }, { "epoch": 7.17, "learning_rate": 7.373617107015889e-06, "loss": 0.003, "step": 2078 }, { "epoch": 7.17, "learning_rate": 7.364636601593875e-06, "loss": 0.0051, "step": 2079 }, { "epoch": 7.17, "learning_rate": 7.355658379627981e-06, "loss": 0.0069, "step": 2080 }, { "epoch": 7.18, "learning_rate": 7.346682448897533e-06, "loss": 0.0043, "step": 2081 }, { "epoch": 7.18, "learning_rate": 7.33770881717989e-06, "loss": 0.0022, "step": 2082 }, { "epoch": 7.18, "learning_rate": 7.328737492250403e-06, "loss": 0.0019, "step": 2083 }, { "epoch": 7.19, "learning_rate": 7.319768481882439e-06, "loss": 0.0022, "step": 2084 }, { "epoch": 7.19, "learning_rate": 7.310801793847344e-06, "loss": 0.0024, "step": 2085 }, { "epoch": 7.19, "learning_rate": 7.3018374359144674e-06, "loss": 0.0059, "step": 2086 }, { "epoch": 7.2, "learning_rate": 7.292875415851123e-06, "loss": 0.008, "step": 2087 }, { "epoch": 7.2, "learning_rate": 7.283915741422611e-06, "loss": 0.0036, "step": 2088 }, { "epoch": 7.2, "learning_rate": 7.274958420392204e-06, "loss": 0.0116, "step": 2089 }, { "epoch": 7.21, "learning_rate": 7.266003460521116e-06, "loss": 0.0061, "step": 2090 }, { "epoch": 7.21, "learning_rate": 7.257050869568536e-06, "loss": 0.0095, "step": 2091 }, { "epoch": 7.21, "learning_rate": 7.248100655291583e-06, "loss": 0.0269, "step": 2092 }, { "epoch": 7.22, "learning_rate": 7.2391528254453305e-06, "loss": 0.0039, "step": 2093 }, { "epoch": 7.22, "learning_rate": 7.2302073877827775e-06, "loss": 0.0026, "step": 2094 }, { "epoch": 7.22, "learning_rate": 7.221264350054855e-06, "loss": 0.0026, "step": 2095 }, { "epoch": 7.23, "learning_rate": 7.212323720010406e-06, "loss": 0.013, "step": 2096 }, { "epoch": 7.23, "learning_rate": 7.203385505396203e-06, "loss": 0.0052, "step": 2097 }, { "epoch": 7.23, "learning_rate": 7.194449713956908e-06, "loss": 0.0022, "step": 2098 }, { "epoch": 7.24, "learning_rate": 7.1855163534351e-06, "loss": 0.0069, "step": 2099 }, { "epoch": 7.24, "learning_rate": 7.176585431571235e-06, "loss": 0.0068, "step": 2100 }, { "epoch": 7.24, "learning_rate": 7.167656956103673e-06, "loss": 0.0044, "step": 2101 }, { "epoch": 7.25, "learning_rate": 7.158730934768639e-06, "loss": 0.0095, "step": 2102 }, { "epoch": 7.25, "learning_rate": 7.149807375300239e-06, "loss": 0.008, "step": 2103 }, { "epoch": 7.26, "learning_rate": 7.140886285430448e-06, "loss": 0.004, "step": 2104 }, { "epoch": 7.26, "learning_rate": 7.131967672889101e-06, "loss": 0.0121, "step": 2105 }, { "epoch": 7.26, "learning_rate": 7.123051545403874e-06, "loss": 0.0086, "step": 2106 }, { "epoch": 7.27, "learning_rate": 7.11413791070031e-06, "loss": 0.0019, "step": 2107 }, { "epoch": 7.27, "learning_rate": 7.105226776501772e-06, "loss": 0.0073, "step": 2108 }, { "epoch": 7.27, "learning_rate": 7.096318150529476e-06, "loss": 0.0056, "step": 2109 }, { "epoch": 7.28, "learning_rate": 7.087412040502446e-06, "loss": 0.001, "step": 2110 }, { "epoch": 7.28, "learning_rate": 7.078508454137543e-06, "loss": 0.0062, "step": 2111 }, { "epoch": 7.28, "learning_rate": 7.069607399149427e-06, "loss": 0.0061, "step": 2112 }, { "epoch": 7.29, "learning_rate": 7.060708883250573e-06, "loss": 0.0072, "step": 2113 }, { "epoch": 7.29, "learning_rate": 7.051812914151254e-06, "loss": 0.0042, "step": 2114 }, { "epoch": 7.29, "learning_rate": 7.042919499559538e-06, "loss": 0.006, "step": 2115 }, { "epoch": 7.3, "learning_rate": 7.034028647181268e-06, "loss": 0.0034, "step": 2116 }, { "epoch": 7.3, "learning_rate": 7.02514036472009e-06, "loss": 0.0054, "step": 2117 }, { "epoch": 7.3, "learning_rate": 7.016254659877398e-06, "loss": 0.0064, "step": 2118 }, { "epoch": 7.31, "learning_rate": 7.007371540352371e-06, "loss": 0.0042, "step": 2119 }, { "epoch": 7.31, "learning_rate": 6.9984910138419434e-06, "loss": 0.0124, "step": 2120 }, { "epoch": 7.31, "learning_rate": 6.9896130880407965e-06, "loss": 0.0015, "step": 2121 }, { "epoch": 7.32, "learning_rate": 6.9807377706413635e-06, "loss": 0.0022, "step": 2122 }, { "epoch": 7.32, "learning_rate": 6.971865069333814e-06, "loss": 0.0026, "step": 2123 }, { "epoch": 7.32, "learning_rate": 6.962994991806059e-06, "loss": 0.0112, "step": 2124 }, { "epoch": 7.33, "learning_rate": 6.9541275457437215e-06, "loss": 0.002, "step": 2125 }, { "epoch": 7.33, "learning_rate": 6.945262738830164e-06, "loss": 0.0019, "step": 2126 }, { "epoch": 7.33, "learning_rate": 6.9364005787464406e-06, "loss": 0.0027, "step": 2127 }, { "epoch": 7.34, "learning_rate": 6.927541073171333e-06, "loss": 0.0047, "step": 2128 }, { "epoch": 7.34, "learning_rate": 6.918684229781305e-06, "loss": 0.0039, "step": 2129 }, { "epoch": 7.34, "learning_rate": 6.909830056250527e-06, "loss": 0.0133, "step": 2130 }, { "epoch": 7.35, "learning_rate": 6.900978560250846e-06, "loss": 0.0052, "step": 2131 }, { "epoch": 7.35, "learning_rate": 6.892129749451799e-06, "loss": 0.003, "step": 2132 }, { "epoch": 7.36, "learning_rate": 6.883283631520582e-06, "loss": 0.0134, "step": 2133 }, { "epoch": 7.36, "learning_rate": 6.874440214122077e-06, "loss": 0.007, "step": 2134 }, { "epoch": 7.36, "learning_rate": 6.865599504918805e-06, "loss": 0.0019, "step": 2135 }, { "epoch": 7.37, "learning_rate": 6.856761511570963e-06, "loss": 0.0037, "step": 2136 }, { "epoch": 7.37, "learning_rate": 6.847926241736371e-06, "loss": 0.0053, "step": 2137 }, { "epoch": 7.37, "learning_rate": 6.839093703070512e-06, "loss": 0.0114, "step": 2138 }, { "epoch": 7.38, "learning_rate": 6.830263903226483e-06, "loss": 0.0064, "step": 2139 }, { "epoch": 7.38, "learning_rate": 6.821436849855023e-06, "loss": 0.0057, "step": 2140 }, { "epoch": 7.38, "learning_rate": 6.812612550604481e-06, "loss": 0.0039, "step": 2141 }, { "epoch": 7.39, "learning_rate": 6.803791013120822e-06, "loss": 0.0071, "step": 2142 }, { "epoch": 7.39, "learning_rate": 6.794972245047623e-06, "loss": 0.0035, "step": 2143 }, { "epoch": 7.39, "learning_rate": 6.786156254026059e-06, "loss": 0.01, "step": 2144 }, { "epoch": 7.4, "learning_rate": 6.777343047694891e-06, "loss": 0.0055, "step": 2145 }, { "epoch": 7.4, "learning_rate": 6.768532633690481e-06, "loss": 0.0048, "step": 2146 }, { "epoch": 7.4, "learning_rate": 6.759725019646758e-06, "loss": 0.0044, "step": 2147 }, { "epoch": 7.41, "learning_rate": 6.750920213195238e-06, "loss": 0.0044, "step": 2148 }, { "epoch": 7.41, "learning_rate": 6.742118221964991e-06, "loss": 0.0065, "step": 2149 }, { "epoch": 7.41, "learning_rate": 6.733319053582659e-06, "loss": 0.0044, "step": 2150 }, { "epoch": 7.42, "learning_rate": 6.7245227156724324e-06, "loss": 0.0041, "step": 2151 }, { "epoch": 7.42, "learning_rate": 6.715729215856048e-06, "loss": 0.0048, "step": 2152 }, { "epoch": 7.42, "learning_rate": 6.706938561752788e-06, "loss": 0.0069, "step": 2153 }, { "epoch": 7.43, "learning_rate": 6.698150760979463e-06, "loss": 0.0096, "step": 2154 }, { "epoch": 7.43, "learning_rate": 6.689365821150421e-06, "loss": 0.0029, "step": 2155 }, { "epoch": 7.43, "learning_rate": 6.680583749877516e-06, "loss": 0.0022, "step": 2156 }, { "epoch": 7.44, "learning_rate": 6.671804554770135e-06, "loss": 0.004, "step": 2157 }, { "epoch": 7.44, "learning_rate": 6.6630282434351535e-06, "loss": 0.0057, "step": 2158 }, { "epoch": 7.44, "learning_rate": 6.654254823476967e-06, "loss": 0.0043, "step": 2159 }, { "epoch": 7.45, "learning_rate": 6.645484302497452e-06, "loss": 0.0056, "step": 2160 }, { "epoch": 7.45, "learning_rate": 6.636716688095978e-06, "loss": 0.0047, "step": 2161 }, { "epoch": 7.46, "learning_rate": 6.627951987869392e-06, "loss": 0.0102, "step": 2162 }, { "epoch": 7.46, "learning_rate": 6.6191902094120295e-06, "loss": 0.0066, "step": 2163 }, { "epoch": 7.46, "learning_rate": 6.6104313603156745e-06, "loss": 0.0036, "step": 2164 }, { "epoch": 7.47, "learning_rate": 6.601675448169591e-06, "loss": 0.0148, "step": 2165 }, { "epoch": 7.47, "learning_rate": 6.5929224805604845e-06, "loss": 0.0116, "step": 2166 }, { "epoch": 7.47, "learning_rate": 6.58417246507252e-06, "loss": 0.0059, "step": 2167 }, { "epoch": 7.48, "learning_rate": 6.575425409287292e-06, "loss": 0.0021, "step": 2168 }, { "epoch": 7.48, "learning_rate": 6.566681320783849e-06, "loss": 0.0104, "step": 2169 }, { "epoch": 7.48, "learning_rate": 6.5579402071386485e-06, "loss": 0.0105, "step": 2170 }, { "epoch": 7.49, "learning_rate": 6.549202075925583e-06, "loss": 0.0024, "step": 2171 }, { "epoch": 7.49, "learning_rate": 6.540466934715953e-06, "loss": 0.0064, "step": 2172 }, { "epoch": 7.49, "learning_rate": 6.531734791078481e-06, "loss": 0.0081, "step": 2173 }, { "epoch": 7.5, "learning_rate": 6.523005652579273e-06, "loss": 0.0052, "step": 2174 }, { "epoch": 7.5, "learning_rate": 6.5142795267818505e-06, "loss": 0.0022, "step": 2175 }, { "epoch": 7.5, "learning_rate": 6.5055564212471085e-06, "loss": 0.0026, "step": 2176 }, { "epoch": 7.51, "learning_rate": 6.4968363435333415e-06, "loss": 0.0112, "step": 2177 }, { "epoch": 7.51, "learning_rate": 6.488119301196201e-06, "loss": 0.0075, "step": 2178 }, { "epoch": 7.51, "learning_rate": 6.479405301788728e-06, "loss": 0.0052, "step": 2179 }, { "epoch": 7.52, "learning_rate": 6.4706943528613135e-06, "loss": 0.0018, "step": 2180 }, { "epoch": 7.52, "learning_rate": 6.461986461961706e-06, "loss": 0.0032, "step": 2181 }, { "epoch": 7.52, "learning_rate": 6.453281636635016e-06, "loss": 0.0036, "step": 2182 }, { "epoch": 7.53, "learning_rate": 6.444579884423682e-06, "loss": 0.0063, "step": 2183 }, { "epoch": 7.53, "learning_rate": 6.435881212867494e-06, "loss": 0.0039, "step": 2184 }, { "epoch": 7.53, "learning_rate": 6.427185629503561e-06, "loss": 0.0043, "step": 2185 }, { "epoch": 7.54, "learning_rate": 6.418493141866324e-06, "loss": 0.005, "step": 2186 }, { "epoch": 7.54, "learning_rate": 6.409803757487539e-06, "loss": 0.0026, "step": 2187 }, { "epoch": 7.54, "learning_rate": 6.4011174838962706e-06, "loss": 0.0049, "step": 2188 }, { "epoch": 7.55, "learning_rate": 6.392434328618895e-06, "loss": 0.003, "step": 2189 }, { "epoch": 7.55, "learning_rate": 6.383754299179079e-06, "loss": 0.0027, "step": 2190 }, { "epoch": 7.56, "learning_rate": 6.375077403097781e-06, "loss": 0.0017, "step": 2191 }, { "epoch": 7.56, "learning_rate": 6.3664036478932555e-06, "loss": 0.0103, "step": 2192 }, { "epoch": 7.56, "learning_rate": 6.357733041081018e-06, "loss": 0.0055, "step": 2193 }, { "epoch": 7.57, "learning_rate": 6.349065590173875e-06, "loss": 0.0056, "step": 2194 }, { "epoch": 7.57, "learning_rate": 6.340401302681879e-06, "loss": 0.0136, "step": 2195 }, { "epoch": 7.57, "learning_rate": 6.33174018611236e-06, "loss": 0.01, "step": 2196 }, { "epoch": 7.58, "learning_rate": 6.323082247969889e-06, "loss": 0.0017, "step": 2197 }, { "epoch": 7.58, "learning_rate": 6.314427495756283e-06, "loss": 0.0032, "step": 2198 }, { "epoch": 7.58, "learning_rate": 6.305775936970606e-06, "loss": 0.0218, "step": 2199 }, { "epoch": 7.59, "learning_rate": 6.29712757910915e-06, "loss": 0.0039, "step": 2200 }, { "epoch": 7.59, "learning_rate": 6.288482429665429e-06, "loss": 0.0117, "step": 2201 }, { "epoch": 7.59, "learning_rate": 6.27984049613019e-06, "loss": 0.0033, "step": 2202 }, { "epoch": 7.6, "learning_rate": 6.271201785991374e-06, "loss": 0.0041, "step": 2203 }, { "epoch": 7.6, "learning_rate": 6.262566306734154e-06, "loss": 0.0074, "step": 2204 }, { "epoch": 7.6, "learning_rate": 6.25393406584088e-06, "loss": 0.0033, "step": 2205 }, { "epoch": 7.61, "learning_rate": 6.245305070791114e-06, "loss": 0.0091, "step": 2206 }, { "epoch": 7.61, "learning_rate": 6.23667932906159e-06, "loss": 0.0032, "step": 2207 }, { "epoch": 7.61, "learning_rate": 6.228056848126236e-06, "loss": 0.0068, "step": 2208 }, { "epoch": 7.62, "learning_rate": 6.219437635456147e-06, "loss": 0.0035, "step": 2209 }, { "epoch": 7.62, "learning_rate": 6.210821698519592e-06, "loss": 0.0073, "step": 2210 }, { "epoch": 7.62, "learning_rate": 6.202209044781991e-06, "loss": 0.0086, "step": 2211 }, { "epoch": 7.63, "learning_rate": 6.193599681705931e-06, "loss": 0.0021, "step": 2212 }, { "epoch": 7.63, "learning_rate": 6.1849936167511495e-06, "loss": 0.0035, "step": 2213 }, { "epoch": 7.63, "learning_rate": 6.176390857374508e-06, "loss": 0.011, "step": 2214 }, { "epoch": 7.64, "learning_rate": 6.167791411030027e-06, "loss": 0.0023, "step": 2215 }, { "epoch": 7.64, "learning_rate": 6.15919528516884e-06, "loss": 0.008, "step": 2216 }, { "epoch": 7.64, "learning_rate": 6.150602487239207e-06, "loss": 0.0108, "step": 2217 }, { "epoch": 7.65, "learning_rate": 6.142013024686509e-06, "loss": 0.0059, "step": 2218 }, { "epoch": 7.65, "learning_rate": 6.1334269049532346e-06, "loss": 0.0086, "step": 2219 }, { "epoch": 7.66, "learning_rate": 6.124844135478971e-06, "loss": 0.0075, "step": 2220 }, { "epoch": 7.66, "learning_rate": 6.1162647237004135e-06, "loss": 0.0058, "step": 2221 }, { "epoch": 7.66, "learning_rate": 6.107688677051333e-06, "loss": 0.0072, "step": 2222 }, { "epoch": 7.67, "learning_rate": 6.099116002962604e-06, "loss": 0.0054, "step": 2223 }, { "epoch": 7.67, "learning_rate": 6.090546708862158e-06, "loss": 0.0069, "step": 2224 }, { "epoch": 7.67, "learning_rate": 6.081980802175016e-06, "loss": 0.0058, "step": 2225 }, { "epoch": 7.68, "learning_rate": 6.073418290323251e-06, "loss": 0.0089, "step": 2226 }, { "epoch": 7.68, "learning_rate": 6.0648591807259995e-06, "loss": 0.005, "step": 2227 }, { "epoch": 7.68, "learning_rate": 6.056303480799449e-06, "loss": 0.0059, "step": 2228 }, { "epoch": 7.69, "learning_rate": 6.047751197956838e-06, "loss": 0.0072, "step": 2229 }, { "epoch": 7.69, "learning_rate": 6.039202339608432e-06, "loss": 0.0035, "step": 2230 }, { "epoch": 7.69, "learning_rate": 6.030656913161546e-06, "loss": 0.0052, "step": 2231 }, { "epoch": 7.7, "learning_rate": 6.022114926020504e-06, "loss": 0.0041, "step": 2232 }, { "epoch": 7.7, "learning_rate": 6.013576385586665e-06, "loss": 0.0039, "step": 2233 }, { "epoch": 7.7, "learning_rate": 6.0050412992583875e-06, "loss": 0.0087, "step": 2234 }, { "epoch": 7.71, "learning_rate": 5.996509674431053e-06, "loss": 0.0058, "step": 2235 }, { "epoch": 7.71, "learning_rate": 5.987981518497028e-06, "loss": 0.0043, "step": 2236 }, { "epoch": 7.71, "learning_rate": 5.979456838845683e-06, "loss": 0.0064, "step": 2237 }, { "epoch": 7.72, "learning_rate": 5.970935642863375e-06, "loss": 0.0032, "step": 2238 }, { "epoch": 7.72, "learning_rate": 5.962417937933442e-06, "loss": 0.003, "step": 2239 }, { "epoch": 7.72, "learning_rate": 5.953903731436191e-06, "loss": 0.0061, "step": 2240 }, { "epoch": 7.73, "learning_rate": 5.94539303074891e-06, "loss": 0.0063, "step": 2241 }, { "epoch": 7.73, "learning_rate": 5.936885843245836e-06, "loss": 0.0054, "step": 2242 }, { "epoch": 7.73, "learning_rate": 5.928382176298173e-06, "loss": 0.0045, "step": 2243 }, { "epoch": 7.74, "learning_rate": 5.9198820372740726e-06, "loss": 0.0056, "step": 2244 }, { "epoch": 7.74, "learning_rate": 5.911385433538621e-06, "loss": 0.0159, "step": 2245 }, { "epoch": 7.74, "learning_rate": 5.902892372453853e-06, "loss": 0.0043, "step": 2246 }, { "epoch": 7.75, "learning_rate": 5.894402861378721e-06, "loss": 0.003, "step": 2247 }, { "epoch": 7.75, "learning_rate": 5.885916907669114e-06, "loss": 0.0078, "step": 2248 }, { "epoch": 7.76, "learning_rate": 5.8774345186778295e-06, "loss": 0.0046, "step": 2249 }, { "epoch": 7.76, "learning_rate": 5.868955701754584e-06, "loss": 0.0054, "step": 2250 }, { "epoch": 7.76, "learning_rate": 5.86048046424599e-06, "loss": 0.0068, "step": 2251 }, { "epoch": 7.77, "learning_rate": 5.852008813495569e-06, "loss": 0.006, "step": 2252 }, { "epoch": 7.77, "learning_rate": 5.843540756843722e-06, "loss": 0.0032, "step": 2253 }, { "epoch": 7.77, "learning_rate": 5.835076301627752e-06, "loss": 0.0095, "step": 2254 }, { "epoch": 7.78, "learning_rate": 5.8266154551818225e-06, "loss": 0.0056, "step": 2255 }, { "epoch": 7.78, "learning_rate": 5.818158224836987e-06, "loss": 0.0113, "step": 2256 }, { "epoch": 7.78, "learning_rate": 5.809704617921155e-06, "loss": 0.0033, "step": 2257 }, { "epoch": 7.79, "learning_rate": 5.801254641759103e-06, "loss": 0.0114, "step": 2258 }, { "epoch": 7.79, "learning_rate": 5.792808303672454e-06, "loss": 0.0038, "step": 2259 }, { "epoch": 7.79, "learning_rate": 5.784365610979692e-06, "loss": 0.0064, "step": 2260 }, { "epoch": 7.8, "learning_rate": 5.775926570996122e-06, "loss": 0.0059, "step": 2261 }, { "epoch": 7.8, "learning_rate": 5.7674911910339094e-06, "loss": 0.0065, "step": 2262 }, { "epoch": 7.8, "learning_rate": 5.7590594784020216e-06, "loss": 0.0066, "step": 2263 }, { "epoch": 7.81, "learning_rate": 5.750631440406274e-06, "loss": 0.0059, "step": 2264 }, { "epoch": 7.81, "learning_rate": 5.742207084349274e-06, "loss": 0.0092, "step": 2265 }, { "epoch": 7.81, "learning_rate": 5.733786417530459e-06, "loss": 0.0158, "step": 2266 }, { "epoch": 7.82, "learning_rate": 5.7253694472460555e-06, "loss": 0.0023, "step": 2267 }, { "epoch": 7.82, "learning_rate": 5.716956180789098e-06, "loss": 0.005, "step": 2268 }, { "epoch": 7.82, "learning_rate": 5.708546625449405e-06, "loss": 0.0076, "step": 2269 }, { "epoch": 7.83, "learning_rate": 5.700140788513575e-06, "loss": 0.0043, "step": 2270 }, { "epoch": 7.83, "learning_rate": 5.691738677265e-06, "loss": 0.0079, "step": 2271 }, { "epoch": 7.83, "learning_rate": 5.6833402989838285e-06, "loss": 0.0022, "step": 2272 }, { "epoch": 7.84, "learning_rate": 5.674945660946977e-06, "loss": 0.0071, "step": 2273 }, { "epoch": 7.84, "learning_rate": 5.666554770428129e-06, "loss": 0.0052, "step": 2274 }, { "epoch": 7.84, "learning_rate": 5.65816763469772e-06, "loss": 0.0183, "step": 2275 }, { "epoch": 7.85, "learning_rate": 5.649784261022922e-06, "loss": 0.0033, "step": 2276 }, { "epoch": 7.85, "learning_rate": 5.641404656667661e-06, "loss": 0.0059, "step": 2277 }, { "epoch": 7.86, "learning_rate": 5.6330288288925805e-06, "loss": 0.0041, "step": 2278 }, { "epoch": 7.86, "learning_rate": 5.624656784955072e-06, "loss": 0.0022, "step": 2279 }, { "epoch": 7.86, "learning_rate": 5.616288532109225e-06, "loss": 0.0046, "step": 2280 }, { "epoch": 7.87, "learning_rate": 5.607924077605868e-06, "loss": 0.0064, "step": 2281 }, { "epoch": 7.87, "learning_rate": 5.59956342869252e-06, "loss": 0.0054, "step": 2282 }, { "epoch": 7.87, "learning_rate": 5.591206592613416e-06, "loss": 0.0041, "step": 2283 }, { "epoch": 7.88, "learning_rate": 5.582853576609471e-06, "loss": 0.0136, "step": 2284 }, { "epoch": 7.88, "learning_rate": 5.574504387918311e-06, "loss": 0.0026, "step": 2285 }, { "epoch": 7.88, "learning_rate": 5.5661590337742255e-06, "loss": 0.0047, "step": 2286 }, { "epoch": 7.89, "learning_rate": 5.5578175214081995e-06, "loss": 0.0036, "step": 2287 }, { "epoch": 7.89, "learning_rate": 5.549479858047875e-06, "loss": 0.0065, "step": 2288 }, { "epoch": 7.89, "learning_rate": 5.5411460509175605e-06, "loss": 0.0102, "step": 2289 }, { "epoch": 7.9, "learning_rate": 5.5328161072382355e-06, "loss": 0.0065, "step": 2290 }, { "epoch": 7.9, "learning_rate": 5.52449003422752e-06, "loss": 0.0083, "step": 2291 }, { "epoch": 7.9, "learning_rate": 5.516167839099679e-06, "loss": 0.0029, "step": 2292 }, { "epoch": 7.91, "learning_rate": 5.507849529065629e-06, "loss": 0.0107, "step": 2293 }, { "epoch": 7.91, "learning_rate": 5.49953511133291e-06, "loss": 0.0015, "step": 2294 }, { "epoch": 7.91, "learning_rate": 5.491224593105695e-06, "loss": 0.0074, "step": 2295 }, { "epoch": 7.92, "learning_rate": 5.4829179815847724e-06, "loss": 0.0039, "step": 2296 }, { "epoch": 7.92, "learning_rate": 5.474615283967554e-06, "loss": 0.0035, "step": 2297 }, { "epoch": 7.92, "learning_rate": 5.466316507448049e-06, "loss": 0.0025, "step": 2298 }, { "epoch": 7.93, "learning_rate": 5.458021659216884e-06, "loss": 0.0059, "step": 2299 }, { "epoch": 7.93, "learning_rate": 5.449730746461264e-06, "loss": 0.0059, "step": 2300 }, { "epoch": 7.93, "learning_rate": 5.441443776365003e-06, "loss": 0.0049, "step": 2301 }, { "epoch": 7.94, "learning_rate": 5.43316075610848e-06, "loss": 0.0039, "step": 2302 }, { "epoch": 7.94, "learning_rate": 5.424881692868669e-06, "loss": 0.0034, "step": 2303 }, { "epoch": 7.94, "learning_rate": 5.416606593819102e-06, "loss": 0.0049, "step": 2304 }, { "epoch": 7.95, "learning_rate": 5.4083354661298816e-06, "loss": 0.0061, "step": 2305 }, { "epoch": 7.95, "learning_rate": 5.400068316967675e-06, "loss": 0.0131, "step": 2306 }, { "epoch": 7.96, "learning_rate": 5.391805153495693e-06, "loss": 0.0006, "step": 2307 }, { "epoch": 7.96, "learning_rate": 5.3835459828736945e-06, "loss": 0.0026, "step": 2308 }, { "epoch": 7.96, "learning_rate": 5.3752908122579784e-06, "loss": 0.0176, "step": 2309 }, { "epoch": 7.97, "learning_rate": 5.367039648801386e-06, "loss": 0.0076, "step": 2310 }, { "epoch": 7.97, "learning_rate": 5.3587924996532736e-06, "loss": 0.0066, "step": 2311 }, { "epoch": 7.97, "learning_rate": 5.350549371959533e-06, "loss": 0.0099, "step": 2312 }, { "epoch": 7.98, "learning_rate": 5.342310272862558e-06, "loss": 0.0075, "step": 2313 }, { "epoch": 7.98, "learning_rate": 5.3340752095012636e-06, "loss": 0.0111, "step": 2314 }, { "epoch": 7.98, "learning_rate": 5.325844189011058e-06, "loss": 0.0059, "step": 2315 }, { "epoch": 7.99, "learning_rate": 5.317617218523856e-06, "loss": 0.0042, "step": 2316 }, { "epoch": 7.99, "learning_rate": 5.309394305168054e-06, "loss": 0.0012, "step": 2317 }, { "epoch": 7.99, "learning_rate": 5.30117545606854e-06, "loss": 0.0019, "step": 2318 }, { "epoch": 8.0, "learning_rate": 5.292960678346674e-06, "loss": 0.0101, "step": 2319 }, { "epoch": 8.0, "learning_rate": 5.284749979120299e-06, "loss": 0.0025, "step": 2320 }, { "epoch": 8.0, "learning_rate": 5.276543365503707e-06, "loss": 0.0016, "step": 2321 }, { "epoch": 8.01, "learning_rate": 5.26834084460767e-06, "loss": 0.0028, "step": 2322 }, { "epoch": 8.01, "learning_rate": 5.260142423539396e-06, "loss": 0.0016, "step": 2323 }, { "epoch": 8.01, "learning_rate": 5.251948109402556e-06, "loss": 0.0014, "step": 2324 }, { "epoch": 8.02, "learning_rate": 5.243757909297247e-06, "loss": 0.003, "step": 2325 }, { "epoch": 8.02, "learning_rate": 5.235571830320017e-06, "loss": 0.0026, "step": 2326 }, { "epoch": 8.02, "learning_rate": 5.227389879563831e-06, "loss": 0.0032, "step": 2327 }, { "epoch": 8.03, "learning_rate": 5.219212064118079e-06, "loss": 0.0018, "step": 2328 }, { "epoch": 8.03, "learning_rate": 5.211038391068577e-06, "loss": 0.0021, "step": 2329 }, { "epoch": 8.03, "learning_rate": 5.202868867497542e-06, "loss": 0.0043, "step": 2330 }, { "epoch": 8.04, "learning_rate": 5.194703500483593e-06, "loss": 0.0057, "step": 2331 }, { "epoch": 8.04, "learning_rate": 5.186542297101764e-06, "loss": 0.0023, "step": 2332 }, { "epoch": 8.04, "learning_rate": 5.1783852644234624e-06, "loss": 0.0009, "step": 2333 }, { "epoch": 8.05, "learning_rate": 5.1702324095164955e-06, "loss": 0.0042, "step": 2334 }, { "epoch": 8.05, "learning_rate": 5.162083739445038e-06, "loss": 0.0014, "step": 2335 }, { "epoch": 8.06, "learning_rate": 5.153939261269651e-06, "loss": 0.001, "step": 2336 }, { "epoch": 8.06, "learning_rate": 5.145798982047261e-06, "loss": 0.0112, "step": 2337 }, { "epoch": 8.06, "learning_rate": 5.137662908831147e-06, "loss": 0.002, "step": 2338 }, { "epoch": 8.07, "learning_rate": 5.129531048670956e-06, "loss": 0.0014, "step": 2339 }, { "epoch": 8.07, "learning_rate": 5.121403408612672e-06, "loss": 0.0017, "step": 2340 }, { "epoch": 8.07, "learning_rate": 5.113279995698636e-06, "loss": 0.0023, "step": 2341 }, { "epoch": 8.08, "learning_rate": 5.105160816967514e-06, "loss": 0.0037, "step": 2342 }, { "epoch": 8.08, "learning_rate": 5.0970458794543135e-06, "loss": 0.0044, "step": 2343 }, { "epoch": 8.08, "learning_rate": 5.088935190190355e-06, "loss": 0.0025, "step": 2344 }, { "epoch": 8.09, "learning_rate": 5.080828756203294e-06, "loss": 0.0017, "step": 2345 }, { "epoch": 8.09, "learning_rate": 5.072726584517086e-06, "loss": 0.0015, "step": 2346 }, { "epoch": 8.09, "learning_rate": 5.064628682151998e-06, "loss": 0.0028, "step": 2347 }, { "epoch": 8.1, "learning_rate": 5.056535056124592e-06, "loss": 0.0035, "step": 2348 }, { "epoch": 8.1, "learning_rate": 5.048445713447738e-06, "loss": 0.004, "step": 2349 }, { "epoch": 8.1, "learning_rate": 5.04036066113058e-06, "loss": 0.009, "step": 2350 }, { "epoch": 8.11, "learning_rate": 5.032279906178559e-06, "loss": 0.0081, "step": 2351 }, { "epoch": 8.11, "learning_rate": 5.024203455593375e-06, "loss": 0.0046, "step": 2352 }, { "epoch": 8.11, "learning_rate": 5.016131316373019e-06, "loss": 0.0022, "step": 2353 }, { "epoch": 8.12, "learning_rate": 5.008063495511724e-06, "loss": 0.0076, "step": 2354 }, { "epoch": 8.12, "learning_rate": 5.000000000000003e-06, "loss": 0.0031, "step": 2355 }, { "epoch": 8.12, "learning_rate": 4.991940836824602e-06, "loss": 0.0013, "step": 2356 }, { "epoch": 8.13, "learning_rate": 4.98388601296853e-06, "loss": 0.001, "step": 2357 }, { "epoch": 8.13, "learning_rate": 4.97583553541102e-06, "loss": 0.0019, "step": 2358 }, { "epoch": 8.13, "learning_rate": 4.967789411127556e-06, "loss": 0.0041, "step": 2359 }, { "epoch": 8.14, "learning_rate": 4.959747647089833e-06, "loss": 0.002, "step": 2360 }, { "epoch": 8.14, "learning_rate": 4.951710250265785e-06, "loss": 0.0027, "step": 2361 }, { "epoch": 8.14, "learning_rate": 4.943677227619543e-06, "loss": 0.004, "step": 2362 }, { "epoch": 8.15, "learning_rate": 4.935648586111469e-06, "loss": 0.0092, "step": 2363 }, { "epoch": 8.15, "learning_rate": 4.927624332698109e-06, "loss": 0.0025, "step": 2364 }, { "epoch": 8.16, "learning_rate": 4.919604474332223e-06, "loss": 0.0141, "step": 2365 }, { "epoch": 8.16, "learning_rate": 4.911589017962751e-06, "loss": 0.0042, "step": 2366 }, { "epoch": 8.16, "learning_rate": 4.903577970534823e-06, "loss": 0.0015, "step": 2367 }, { "epoch": 8.17, "learning_rate": 4.895571338989754e-06, "loss": 0.0074, "step": 2368 }, { "epoch": 8.17, "learning_rate": 4.887569130265023e-06, "loss": 0.0034, "step": 2369 }, { "epoch": 8.17, "learning_rate": 4.879571351294287e-06, "loss": 0.0011, "step": 2370 }, { "epoch": 8.18, "learning_rate": 4.8715780090073525e-06, "loss": 0.003, "step": 2371 }, { "epoch": 8.18, "learning_rate": 4.863589110330199e-06, "loss": 0.0007, "step": 2372 }, { "epoch": 8.18, "learning_rate": 4.855604662184935e-06, "loss": 0.0049, "step": 2373 }, { "epoch": 8.19, "learning_rate": 4.8476246714898334e-06, "loss": 0.0042, "step": 2374 }, { "epoch": 8.19, "learning_rate": 4.8396491451592855e-06, "loss": 0.0016, "step": 2375 }, { "epoch": 8.19, "learning_rate": 4.831678090103832e-06, "loss": 0.0073, "step": 2376 }, { "epoch": 8.2, "learning_rate": 4.823711513230125e-06, "loss": 0.007, "step": 2377 }, { "epoch": 8.2, "learning_rate": 4.8157494214409475e-06, "loss": 0.0066, "step": 2378 }, { "epoch": 8.2, "learning_rate": 4.807791821635186e-06, "loss": 0.0019, "step": 2379 }, { "epoch": 8.21, "learning_rate": 4.799838720707847e-06, "loss": 0.0024, "step": 2380 }, { "epoch": 8.21, "learning_rate": 4.791890125550024e-06, "loss": 0.0041, "step": 2381 }, { "epoch": 8.21, "learning_rate": 4.783946043048922e-06, "loss": 0.0011, "step": 2382 }, { "epoch": 8.22, "learning_rate": 4.776006480087827e-06, "loss": 0.0023, "step": 2383 }, { "epoch": 8.22, "learning_rate": 4.768071443546104e-06, "loss": 0.0009, "step": 2384 }, { "epoch": 8.22, "learning_rate": 4.76014094029921e-06, "loss": 0.0029, "step": 2385 }, { "epoch": 8.23, "learning_rate": 4.752214977218665e-06, "loss": 0.003, "step": 2386 }, { "epoch": 8.23, "learning_rate": 4.7442935611720505e-06, "loss": 0.0006, "step": 2387 }, { "epoch": 8.23, "learning_rate": 4.736376699023023e-06, "loss": 0.0042, "step": 2388 }, { "epoch": 8.24, "learning_rate": 4.728464397631276e-06, "loss": 0.0021, "step": 2389 }, { "epoch": 8.24, "learning_rate": 4.720556663852569e-06, "loss": 0.0022, "step": 2390 }, { "epoch": 8.24, "learning_rate": 4.712653504538684e-06, "loss": 0.0014, "step": 2391 }, { "epoch": 8.25, "learning_rate": 4.704754926537459e-06, "loss": 0.0036, "step": 2392 }, { "epoch": 8.25, "learning_rate": 4.696860936692746e-06, "loss": 0.0021, "step": 2393 }, { "epoch": 8.26, "learning_rate": 4.688971541844436e-06, "loss": 0.0035, "step": 2394 }, { "epoch": 8.26, "learning_rate": 4.681086748828424e-06, "loss": 0.0016, "step": 2395 }, { "epoch": 8.26, "learning_rate": 4.673206564476632e-06, "loss": 0.0011, "step": 2396 }, { "epoch": 8.27, "learning_rate": 4.6653309956169745e-06, "loss": 0.0029, "step": 2397 }, { "epoch": 8.27, "learning_rate": 4.6574600490733794e-06, "loss": 0.0016, "step": 2398 }, { "epoch": 8.27, "learning_rate": 4.649593731665765e-06, "loss": 0.002, "step": 2399 }, { "epoch": 8.28, "learning_rate": 4.641732050210032e-06, "loss": 0.0018, "step": 2400 }, { "epoch": 8.28, "learning_rate": 4.6338750115180774e-06, "loss": 0.002, "step": 2401 }, { "epoch": 8.28, "learning_rate": 4.6260226223977645e-06, "loss": 0.0015, "step": 2402 }, { "epoch": 8.29, "learning_rate": 4.618174889652928e-06, "loss": 0.0017, "step": 2403 }, { "epoch": 8.29, "learning_rate": 4.610331820083378e-06, "loss": 0.0041, "step": 2404 }, { "epoch": 8.29, "learning_rate": 4.6024934204848745e-06, "loss": 0.0008, "step": 2405 }, { "epoch": 8.3, "learning_rate": 4.59465969764913e-06, "loss": 0.0033, "step": 2406 }, { "epoch": 8.3, "learning_rate": 4.586830658363816e-06, "loss": 0.0017, "step": 2407 }, { "epoch": 8.3, "learning_rate": 4.579006309412533e-06, "loss": 0.0027, "step": 2408 }, { "epoch": 8.31, "learning_rate": 4.571186657574828e-06, "loss": 0.0012, "step": 2409 }, { "epoch": 8.31, "learning_rate": 4.563371709626167e-06, "loss": 0.0027, "step": 2410 }, { "epoch": 8.31, "learning_rate": 4.555561472337956e-06, "loss": 0.0022, "step": 2411 }, { "epoch": 8.32, "learning_rate": 4.5477559524775e-06, "loss": 0.0005, "step": 2412 }, { "epoch": 8.32, "learning_rate": 4.539955156808035e-06, "loss": 0.002, "step": 2413 }, { "epoch": 8.32, "learning_rate": 4.532159092088687e-06, "loss": 0.0008, "step": 2414 }, { "epoch": 8.33, "learning_rate": 4.524367765074499e-06, "loss": 0.0025, "step": 2415 }, { "epoch": 8.33, "learning_rate": 4.516581182516393e-06, "loss": 0.0063, "step": 2416 }, { "epoch": 8.33, "learning_rate": 4.508799351161196e-06, "loss": 0.0026, "step": 2417 }, { "epoch": 8.34, "learning_rate": 4.501022277751602e-06, "loss": 0.0019, "step": 2418 }, { "epoch": 8.34, "learning_rate": 4.493249969026198e-06, "loss": 0.0016, "step": 2419 }, { "epoch": 8.34, "learning_rate": 4.4854824317194266e-06, "loss": 0.0017, "step": 2420 }, { "epoch": 8.35, "learning_rate": 4.477719672561615e-06, "loss": 0.0017, "step": 2421 }, { "epoch": 8.35, "learning_rate": 4.469961698278933e-06, "loss": 0.005, "step": 2422 }, { "epoch": 8.36, "learning_rate": 4.462208515593409e-06, "loss": 0.0019, "step": 2423 }, { "epoch": 8.36, "learning_rate": 4.4544601312229295e-06, "loss": 0.0063, "step": 2424 }, { "epoch": 8.36, "learning_rate": 4.446716551881213e-06, "loss": 0.0118, "step": 2425 }, { "epoch": 8.37, "learning_rate": 4.438977784277812e-06, "loss": 0.0018, "step": 2426 }, { "epoch": 8.37, "learning_rate": 4.4312438351181246e-06, "loss": 0.0042, "step": 2427 }, { "epoch": 8.37, "learning_rate": 4.423514711103355e-06, "loss": 0.0012, "step": 2428 }, { "epoch": 8.38, "learning_rate": 4.415790418930541e-06, "loss": 0.0026, "step": 2429 }, { "epoch": 8.38, "learning_rate": 4.408070965292534e-06, "loss": 0.0005, "step": 2430 }, { "epoch": 8.38, "learning_rate": 4.4003563568779775e-06, "loss": 0.0012, "step": 2431 }, { "epoch": 8.39, "learning_rate": 4.3926466003713364e-06, "loss": 0.0089, "step": 2432 }, { "epoch": 8.39, "learning_rate": 4.384941702452856e-06, "loss": 0.0033, "step": 2433 }, { "epoch": 8.39, "learning_rate": 4.377241669798583e-06, "loss": 0.0008, "step": 2434 }, { "epoch": 8.4, "learning_rate": 4.369546509080338e-06, "loss": 0.0009, "step": 2435 }, { "epoch": 8.4, "learning_rate": 4.361856226965733e-06, "loss": 0.001, "step": 2436 }, { "epoch": 8.4, "learning_rate": 4.354170830118137e-06, "loss": 0.0027, "step": 2437 }, { "epoch": 8.41, "learning_rate": 4.346490325196704e-06, "loss": 0.0036, "step": 2438 }, { "epoch": 8.41, "learning_rate": 4.338814718856333e-06, "loss": 0.0005, "step": 2439 }, { "epoch": 8.41, "learning_rate": 4.33114401774769e-06, "loss": 0.0067, "step": 2440 }, { "epoch": 8.42, "learning_rate": 4.323478228517185e-06, "loss": 0.0023, "step": 2441 }, { "epoch": 8.42, "learning_rate": 4.315817357806974e-06, "loss": 0.0016, "step": 2442 }, { "epoch": 8.42, "learning_rate": 4.308161412254945e-06, "loss": 0.0032, "step": 2443 }, { "epoch": 8.43, "learning_rate": 4.300510398494734e-06, "loss": 0.0019, "step": 2444 }, { "epoch": 8.43, "learning_rate": 4.292864323155684e-06, "loss": 0.0014, "step": 2445 }, { "epoch": 8.43, "learning_rate": 4.285223192862879e-06, "loss": 0.002, "step": 2446 }, { "epoch": 8.44, "learning_rate": 4.277587014237098e-06, "loss": 0.0009, "step": 2447 }, { "epoch": 8.44, "learning_rate": 4.26995579389485e-06, "loss": 0.0026, "step": 2448 }, { "epoch": 8.44, "learning_rate": 4.262329538448328e-06, "loss": 0.0007, "step": 2449 }, { "epoch": 8.45, "learning_rate": 4.25470825450544e-06, "loss": 0.0078, "step": 2450 }, { "epoch": 8.45, "learning_rate": 4.247091948669775e-06, "loss": 0.0046, "step": 2451 }, { "epoch": 8.46, "learning_rate": 4.239480627540616e-06, "loss": 0.0045, "step": 2452 }, { "epoch": 8.46, "learning_rate": 4.231874297712919e-06, "loss": 0.0015, "step": 2453 }, { "epoch": 8.46, "learning_rate": 4.224272965777326e-06, "loss": 0.0025, "step": 2454 }, { "epoch": 8.47, "learning_rate": 4.216676638320135e-06, "loss": 0.0021, "step": 2455 }, { "epoch": 8.47, "learning_rate": 4.2090853219233215e-06, "loss": 0.005, "step": 2456 }, { "epoch": 8.47, "learning_rate": 4.201499023164508e-06, "loss": 0.0003, "step": 2457 }, { "epoch": 8.48, "learning_rate": 4.193917748616979e-06, "loss": 0.0032, "step": 2458 }, { "epoch": 8.48, "learning_rate": 4.1863415048496535e-06, "loss": 0.0025, "step": 2459 }, { "epoch": 8.48, "learning_rate": 4.178770298427107e-06, "loss": 0.002, "step": 2460 }, { "epoch": 8.49, "learning_rate": 4.1712041359095375e-06, "loss": 0.0027, "step": 2461 }, { "epoch": 8.49, "learning_rate": 4.163643023852775e-06, "loss": 0.0058, "step": 2462 }, { "epoch": 8.49, "learning_rate": 4.15608696880828e-06, "loss": 0.0014, "step": 2463 }, { "epoch": 8.5, "learning_rate": 4.148535977323124e-06, "loss": 0.0046, "step": 2464 }, { "epoch": 8.5, "learning_rate": 4.140990055939997e-06, "loss": 0.0035, "step": 2465 }, { "epoch": 8.5, "learning_rate": 4.133449211197188e-06, "loss": 0.0025, "step": 2466 }, { "epoch": 8.51, "learning_rate": 4.125913449628598e-06, "loss": 0.0081, "step": 2467 }, { "epoch": 8.51, "learning_rate": 4.118382777763711e-06, "loss": 0.0003, "step": 2468 }, { "epoch": 8.51, "learning_rate": 4.110857202127615e-06, "loss": 0.0032, "step": 2469 }, { "epoch": 8.52, "learning_rate": 4.103336729240967e-06, "loss": 0.0007, "step": 2470 }, { "epoch": 8.52, "learning_rate": 4.09582136562002e-06, "loss": 0.0016, "step": 2471 }, { "epoch": 8.52, "learning_rate": 4.08831111777658e-06, "loss": 0.0107, "step": 2472 }, { "epoch": 8.53, "learning_rate": 4.080805992218041e-06, "loss": 0.0018, "step": 2473 }, { "epoch": 8.53, "learning_rate": 4.073305995447341e-06, "loss": 0.0052, "step": 2474 }, { "epoch": 8.53, "learning_rate": 4.065811133962987e-06, "loss": 0.0017, "step": 2475 }, { "epoch": 8.54, "learning_rate": 4.058321414259026e-06, "loss": 0.0038, "step": 2476 }, { "epoch": 8.54, "learning_rate": 4.05083684282506e-06, "loss": 0.0025, "step": 2477 }, { "epoch": 8.54, "learning_rate": 4.04335742614622e-06, "loss": 0.0017, "step": 2478 }, { "epoch": 8.55, "learning_rate": 4.035883170703182e-06, "loss": 0.0307, "step": 2479 }, { "epoch": 8.55, "learning_rate": 4.028414082972141e-06, "loss": 0.0034, "step": 2480 }, { "epoch": 8.56, "learning_rate": 4.020950169424815e-06, "loss": 0.0027, "step": 2481 }, { "epoch": 8.56, "learning_rate": 4.01349143652844e-06, "loss": 0.0007, "step": 2482 }, { "epoch": 8.56, "learning_rate": 4.006037890745768e-06, "loss": 0.0049, "step": 2483 }, { "epoch": 8.57, "learning_rate": 3.998589538535046e-06, "loss": 0.0011, "step": 2484 }, { "epoch": 8.57, "learning_rate": 3.9911463863500365e-06, "loss": 0.0034, "step": 2485 }, { "epoch": 8.57, "learning_rate": 3.983708440639978e-06, "loss": 0.0008, "step": 2486 }, { "epoch": 8.58, "learning_rate": 3.976275707849616e-06, "loss": 0.0015, "step": 2487 }, { "epoch": 8.58, "learning_rate": 3.968848194419163e-06, "loss": 0.0024, "step": 2488 }, { "epoch": 8.58, "learning_rate": 3.96142590678432e-06, "loss": 0.0023, "step": 2489 }, { "epoch": 8.59, "learning_rate": 3.954008851376252e-06, "loss": 0.0025, "step": 2490 }, { "epoch": 8.59, "learning_rate": 3.946597034621599e-06, "loss": 0.004, "step": 2491 }, { "epoch": 8.59, "learning_rate": 3.939190462942458e-06, "loss": 0.0032, "step": 2492 }, { "epoch": 8.6, "learning_rate": 3.931789142756377e-06, "loss": 0.005, "step": 2493 }, { "epoch": 8.6, "learning_rate": 3.924393080476363e-06, "loss": 0.001, "step": 2494 }, { "epoch": 8.6, "learning_rate": 3.917002282510854e-06, "loss": 0.0029, "step": 2495 }, { "epoch": 8.61, "learning_rate": 3.9096167552637454e-06, "loss": 0.0019, "step": 2496 }, { "epoch": 8.61, "learning_rate": 3.902236505134347e-06, "loss": 0.0034, "step": 2497 }, { "epoch": 8.61, "learning_rate": 3.894861538517401e-06, "loss": 0.0024, "step": 2498 }, { "epoch": 8.62, "learning_rate": 3.887491861803085e-06, "loss": 0.0006, "step": 2499 }, { "epoch": 8.62, "learning_rate": 3.880127481376975e-06, "loss": 0.0016, "step": 2500 }, { "epoch": 8.62, "learning_rate": 3.872768403620066e-06, "loss": 0.0079, "step": 2501 }, { "epoch": 8.63, "learning_rate": 3.86541463490876e-06, "loss": 0.0019, "step": 2502 }, { "epoch": 8.63, "learning_rate": 3.858066181614855e-06, "loss": 0.0014, "step": 2503 }, { "epoch": 8.63, "learning_rate": 3.850723050105548e-06, "loss": 0.0039, "step": 2504 }, { "epoch": 8.64, "learning_rate": 3.8433852467434175e-06, "loss": 0.0011, "step": 2505 }, { "epoch": 8.64, "learning_rate": 3.836052777886437e-06, "loss": 0.0023, "step": 2506 }, { "epoch": 8.64, "learning_rate": 3.8287256498879426e-06, "loss": 0.002, "step": 2507 }, { "epoch": 8.65, "learning_rate": 3.821403869096658e-06, "loss": 0.0021, "step": 2508 }, { "epoch": 8.65, "learning_rate": 3.814087441856661e-06, "loss": 0.0028, "step": 2509 }, { "epoch": 8.66, "learning_rate": 3.8067763745074017e-06, "loss": 0.0097, "step": 2510 }, { "epoch": 8.66, "learning_rate": 3.7994706733836738e-06, "loss": 0.0025, "step": 2511 }, { "epoch": 8.66, "learning_rate": 3.7921703448156354e-06, "loss": 0.0017, "step": 2512 }, { "epoch": 8.67, "learning_rate": 3.7848753951287763e-06, "loss": 0.0018, "step": 2513 }, { "epoch": 8.67, "learning_rate": 3.7775858306439374e-06, "loss": 0.0018, "step": 2514 }, { "epoch": 8.67, "learning_rate": 3.77030165767728e-06, "loss": 0.001, "step": 2515 }, { "epoch": 8.68, "learning_rate": 3.7630228825403105e-06, "loss": 0.0003, "step": 2516 }, { "epoch": 8.68, "learning_rate": 3.7557495115398446e-06, "loss": 0.0056, "step": 2517 }, { "epoch": 8.68, "learning_rate": 3.748481550978017e-06, "loss": 0.0175, "step": 2518 }, { "epoch": 8.69, "learning_rate": 3.7412190071522837e-06, "loss": 0.0015, "step": 2519 }, { "epoch": 8.69, "learning_rate": 3.7339618863553983e-06, "loss": 0.0093, "step": 2520 }, { "epoch": 8.69, "learning_rate": 3.726710194875416e-06, "loss": 0.0027, "step": 2521 }, { "epoch": 8.7, "learning_rate": 3.7194639389956923e-06, "loss": 0.0011, "step": 2522 }, { "epoch": 8.7, "learning_rate": 3.7122231249948747e-06, "loss": 0.0006, "step": 2523 }, { "epoch": 8.7, "learning_rate": 3.7049877591468843e-06, "loss": 0.0019, "step": 2524 }, { "epoch": 8.71, "learning_rate": 3.6977578477209352e-06, "loss": 0.0063, "step": 2525 }, { "epoch": 8.71, "learning_rate": 3.6905333969815038e-06, "loss": 0.0013, "step": 2526 }, { "epoch": 8.71, "learning_rate": 3.6833144131883446e-06, "loss": 0.0047, "step": 2527 }, { "epoch": 8.72, "learning_rate": 3.6761009025964657e-06, "loss": 0.002, "step": 2528 }, { "epoch": 8.72, "learning_rate": 3.6688928714561444e-06, "loss": 0.0028, "step": 2529 }, { "epoch": 8.72, "learning_rate": 3.661690326012897e-06, "loss": 0.0017, "step": 2530 }, { "epoch": 8.73, "learning_rate": 3.654493272507499e-06, "loss": 0.0023, "step": 2531 }, { "epoch": 8.73, "learning_rate": 3.6473017171759563e-06, "loss": 0.0017, "step": 2532 }, { "epoch": 8.73, "learning_rate": 3.640115666249522e-06, "loss": 0.0026, "step": 2533 }, { "epoch": 8.74, "learning_rate": 3.6329351259546674e-06, "loss": 0.0019, "step": 2534 }, { "epoch": 8.74, "learning_rate": 3.625760102513103e-06, "loss": 0.0024, "step": 2535 }, { "epoch": 8.74, "learning_rate": 3.6185906021417484e-06, "loss": 0.0023, "step": 2536 }, { "epoch": 8.75, "learning_rate": 3.6114266310527367e-06, "loss": 0.0024, "step": 2537 }, { "epoch": 8.75, "learning_rate": 3.604268195453421e-06, "loss": 0.0009, "step": 2538 }, { "epoch": 8.76, "learning_rate": 3.5971153015463487e-06, "loss": 0.0032, "step": 2539 }, { "epoch": 8.76, "learning_rate": 3.5899679555292654e-06, "loss": 0.0029, "step": 2540 }, { "epoch": 8.76, "learning_rate": 3.582826163595119e-06, "loss": 0.0004, "step": 2541 }, { "epoch": 8.77, "learning_rate": 3.5756899319320305e-06, "loss": 0.003, "step": 2542 }, { "epoch": 8.77, "learning_rate": 3.568559266723318e-06, "loss": 0.0012, "step": 2543 }, { "epoch": 8.77, "learning_rate": 3.5614341741474633e-06, "loss": 0.0079, "step": 2544 }, { "epoch": 8.78, "learning_rate": 3.554314660378133e-06, "loss": 0.0016, "step": 2545 }, { "epoch": 8.78, "learning_rate": 3.547200731584145e-06, "loss": 0.0015, "step": 2546 }, { "epoch": 8.78, "learning_rate": 3.540092393929494e-06, "loss": 0.0021, "step": 2547 }, { "epoch": 8.79, "learning_rate": 3.5329896535733133e-06, "loss": 0.0015, "step": 2548 }, { "epoch": 8.79, "learning_rate": 3.525892516669902e-06, "loss": 0.0004, "step": 2549 }, { "epoch": 8.79, "learning_rate": 3.5188009893686916e-06, "loss": 0.0026, "step": 2550 }, { "epoch": 8.8, "learning_rate": 3.511715077814264e-06, "loss": 0.0025, "step": 2551 }, { "epoch": 8.8, "learning_rate": 3.504634788146322e-06, "loss": 0.0013, "step": 2552 }, { "epoch": 8.8, "learning_rate": 3.4975601264997094e-06, "loss": 0.0009, "step": 2553 }, { "epoch": 8.81, "learning_rate": 3.4904910990043926e-06, "loss": 0.0026, "step": 2554 }, { "epoch": 8.81, "learning_rate": 3.483427711785449e-06, "loss": 0.0019, "step": 2555 }, { "epoch": 8.81, "learning_rate": 3.476369970963072e-06, "loss": 0.0021, "step": 2556 }, { "epoch": 8.82, "learning_rate": 3.4693178826525587e-06, "loss": 0.0007, "step": 2557 }, { "epoch": 8.82, "learning_rate": 3.462271452964321e-06, "loss": 0.0004, "step": 2558 }, { "epoch": 8.82, "learning_rate": 3.455230688003852e-06, "loss": 0.0014, "step": 2559 }, { "epoch": 8.83, "learning_rate": 3.4481955938717514e-06, "loss": 0.0045, "step": 2560 }, { "epoch": 8.83, "learning_rate": 3.4411661766636917e-06, "loss": 0.0025, "step": 2561 }, { "epoch": 8.83, "learning_rate": 3.4341424424704373e-06, "loss": 0.0018, "step": 2562 }, { "epoch": 8.84, "learning_rate": 3.42712439737782e-06, "loss": 0.0012, "step": 2563 }, { "epoch": 8.84, "learning_rate": 3.4201120474667506e-06, "loss": 0.0016, "step": 2564 }, { "epoch": 8.84, "learning_rate": 3.4131053988131947e-06, "loss": 0.0016, "step": 2565 }, { "epoch": 8.85, "learning_rate": 3.406104457488192e-06, "loss": 0.0042, "step": 2566 }, { "epoch": 8.85, "learning_rate": 3.399109229557821e-06, "loss": 0.0009, "step": 2567 }, { "epoch": 8.86, "learning_rate": 3.3921197210832235e-06, "loss": 0.0048, "step": 2568 }, { "epoch": 8.86, "learning_rate": 3.3851359381205753e-06, "loss": 0.001, "step": 2569 }, { "epoch": 8.86, "learning_rate": 3.3781578867211016e-06, "loss": 0.0023, "step": 2570 }, { "epoch": 8.87, "learning_rate": 3.3711855729310482e-06, "loss": 0.0013, "step": 2571 }, { "epoch": 8.87, "learning_rate": 3.364219002791703e-06, "loss": 0.0017, "step": 2572 }, { "epoch": 8.87, "learning_rate": 3.3572581823393656e-06, "loss": 0.0037, "step": 2573 }, { "epoch": 8.88, "learning_rate": 3.3503031176053657e-06, "loss": 0.0033, "step": 2574 }, { "epoch": 8.88, "learning_rate": 3.343353814616036e-06, "loss": 0.0021, "step": 2575 }, { "epoch": 8.88, "learning_rate": 3.336410279392719e-06, "loss": 0.0009, "step": 2576 }, { "epoch": 8.89, "learning_rate": 3.3294725179517573e-06, "loss": 0.0012, "step": 2577 }, { "epoch": 8.89, "learning_rate": 3.3225405363045016e-06, "loss": 0.0011, "step": 2578 }, { "epoch": 8.89, "learning_rate": 3.315614340457279e-06, "loss": 0.0044, "step": 2579 }, { "epoch": 8.9, "learning_rate": 3.308693936411421e-06, "loss": 0.0077, "step": 2580 }, { "epoch": 8.9, "learning_rate": 3.3017793301632216e-06, "loss": 0.0015, "step": 2581 }, { "epoch": 8.9, "learning_rate": 3.2948705277039694e-06, "loss": 0.0015, "step": 2582 }, { "epoch": 8.91, "learning_rate": 3.287967535019908e-06, "loss": 0.0028, "step": 2583 }, { "epoch": 8.91, "learning_rate": 3.2810703580922576e-06, "loss": 0.0005, "step": 2584 }, { "epoch": 8.91, "learning_rate": 3.2741790028972e-06, "loss": 0.0111, "step": 2585 }, { "epoch": 8.92, "learning_rate": 3.2672934754058615e-06, "loss": 0.0015, "step": 2586 }, { "epoch": 8.92, "learning_rate": 3.260413781584334e-06, "loss": 0.0016, "step": 2587 }, { "epoch": 8.92, "learning_rate": 3.2535399273936407e-06, "loss": 0.01, "step": 2588 }, { "epoch": 8.93, "learning_rate": 3.2466719187897555e-06, "loss": 0.0004, "step": 2589 }, { "epoch": 8.93, "learning_rate": 3.239809761723579e-06, "loss": 0.0028, "step": 2590 }, { "epoch": 8.93, "learning_rate": 3.232953462140952e-06, "loss": 0.0048, "step": 2591 }, { "epoch": 8.94, "learning_rate": 3.2261030259826287e-06, "loss": 0.0042, "step": 2592 }, { "epoch": 8.94, "learning_rate": 3.2192584591842856e-06, "loss": 0.0015, "step": 2593 }, { "epoch": 8.94, "learning_rate": 3.2124197676765224e-06, "loss": 0.0019, "step": 2594 }, { "epoch": 8.95, "learning_rate": 3.2055869573848374e-06, "loss": 0.0042, "step": 2595 }, { "epoch": 8.95, "learning_rate": 3.1987600342296356e-06, "loss": 0.0014, "step": 2596 }, { "epoch": 8.96, "learning_rate": 3.1919390041262256e-06, "loss": 0.0022, "step": 2597 }, { "epoch": 8.96, "learning_rate": 3.1851238729848033e-06, "loss": 0.0004, "step": 2598 }, { "epoch": 8.96, "learning_rate": 3.178314646710463e-06, "loss": 0.0036, "step": 2599 }, { "epoch": 8.97, "learning_rate": 3.1715113312031674e-06, "loss": 0.0008, "step": 2600 }, { "epoch": 8.97, "learning_rate": 3.164713932357776e-06, "loss": 0.0035, "step": 2601 }, { "epoch": 8.97, "learning_rate": 3.1579224560640044e-06, "loss": 0.0027, "step": 2602 }, { "epoch": 8.98, "learning_rate": 3.1511369082064514e-06, "loss": 0.0023, "step": 2603 }, { "epoch": 8.98, "learning_rate": 3.144357294664565e-06, "loss": 0.0031, "step": 2604 }, { "epoch": 8.98, "learning_rate": 3.1375836213126653e-06, "loss": 0.0032, "step": 2605 }, { "epoch": 8.99, "learning_rate": 3.130815894019913e-06, "loss": 0.0054, "step": 2606 }, { "epoch": 8.99, "learning_rate": 3.124054118650327e-06, "loss": 0.0039, "step": 2607 }, { "epoch": 8.99, "learning_rate": 3.11729830106276e-06, "loss": 0.0031, "step": 2608 }, { "epoch": 9.0, "learning_rate": 3.1105484471109103e-06, "loss": 0.0053, "step": 2609 }, { "epoch": 9.0, "learning_rate": 3.103804562643302e-06, "loss": 0.0017, "step": 2610 }, { "epoch": 9.0, "learning_rate": 3.0970666535032943e-06, "loss": 0.0005, "step": 2611 }, { "epoch": 9.01, "learning_rate": 3.0903347255290593e-06, "loss": 0.0055, "step": 2612 }, { "epoch": 9.01, "learning_rate": 3.0836087845536e-06, "loss": 0.0014, "step": 2613 }, { "epoch": 9.01, "learning_rate": 3.076888836404719e-06, "loss": 0.0022, "step": 2614 }, { "epoch": 9.02, "learning_rate": 3.0701748869050285e-06, "loss": 0.0008, "step": 2615 }, { "epoch": 9.02, "learning_rate": 3.063466941871952e-06, "loss": 0.0029, "step": 2616 }, { "epoch": 9.02, "learning_rate": 3.0567650071177002e-06, "loss": 0.0006, "step": 2617 }, { "epoch": 9.03, "learning_rate": 3.0500690884492836e-06, "loss": 0.0015, "step": 2618 }, { "epoch": 9.03, "learning_rate": 3.043379191668492e-06, "loss": 0.001, "step": 2619 }, { "epoch": 9.03, "learning_rate": 3.0366953225719076e-06, "loss": 0.0012, "step": 2620 }, { "epoch": 9.04, "learning_rate": 3.030017486950879e-06, "loss": 0.0004, "step": 2621 }, { "epoch": 9.04, "learning_rate": 3.023345690591537e-06, "loss": 0.0018, "step": 2622 }, { "epoch": 9.04, "learning_rate": 3.016679939274768e-06, "loss": 0.0011, "step": 2623 }, { "epoch": 9.05, "learning_rate": 3.0100202387762357e-06, "loss": 0.0012, "step": 2624 }, { "epoch": 9.05, "learning_rate": 3.003366594866345e-06, "loss": 0.0012, "step": 2625 }, { "epoch": 9.06, "learning_rate": 2.9967190133102676e-06, "loss": 0.0068, "step": 2626 }, { "epoch": 9.06, "learning_rate": 2.990077499867907e-06, "loss": 0.0016, "step": 2627 }, { "epoch": 9.06, "learning_rate": 2.983442060293926e-06, "loss": 0.0009, "step": 2628 }, { "epoch": 9.07, "learning_rate": 2.9768127003377077e-06, "loss": 0.0005, "step": 2629 }, { "epoch": 9.07, "learning_rate": 2.970189425743383e-06, "loss": 0.001, "step": 2630 }, { "epoch": 9.07, "learning_rate": 2.963572242249799e-06, "loss": 0.0009, "step": 2631 }, { "epoch": 9.08, "learning_rate": 2.956961155590525e-06, "loss": 0.0011, "step": 2632 }, { "epoch": 9.08, "learning_rate": 2.9503561714938576e-06, "loss": 0.0009, "step": 2633 }, { "epoch": 9.08, "learning_rate": 2.9437572956827965e-06, "loss": 0.0018, "step": 2634 }, { "epoch": 9.09, "learning_rate": 2.9371645338750477e-06, "loss": 0.0005, "step": 2635 }, { "epoch": 9.09, "learning_rate": 2.9305778917830306e-06, "loss": 0.0021, "step": 2636 }, { "epoch": 9.09, "learning_rate": 2.9239973751138495e-06, "loss": 0.0014, "step": 2637 }, { "epoch": 9.1, "learning_rate": 2.917422989569311e-06, "loss": 0.0014, "step": 2638 }, { "epoch": 9.1, "learning_rate": 2.910854740845899e-06, "loss": 0.0014, "step": 2639 }, { "epoch": 9.1, "learning_rate": 2.9042926346347932e-06, "loss": 0.0004, "step": 2640 }, { "epoch": 9.11, "learning_rate": 2.8977366766218372e-06, "loss": 0.0003, "step": 2641 }, { "epoch": 9.11, "learning_rate": 2.8911868724875604e-06, "loss": 0.0009, "step": 2642 }, { "epoch": 9.11, "learning_rate": 2.884643227907147e-06, "loss": 0.0025, "step": 2643 }, { "epoch": 9.12, "learning_rate": 2.878105748550455e-06, "loss": 0.0012, "step": 2644 }, { "epoch": 9.12, "learning_rate": 2.8715744400819976e-06, "loss": 0.0032, "step": 2645 }, { "epoch": 9.12, "learning_rate": 2.8650493081609344e-06, "loss": 0.0021, "step": 2646 }, { "epoch": 9.13, "learning_rate": 2.8585303584410852e-06, "loss": 0.0013, "step": 2647 }, { "epoch": 9.13, "learning_rate": 2.852017596570901e-06, "loss": 0.0022, "step": 2648 }, { "epoch": 9.13, "learning_rate": 2.8455110281934804e-06, "loss": 0.0003, "step": 2649 }, { "epoch": 9.14, "learning_rate": 2.8390106589465514e-06, "loss": 0.0019, "step": 2650 }, { "epoch": 9.14, "learning_rate": 2.832516494462467e-06, "loss": 0.0005, "step": 2651 }, { "epoch": 9.14, "learning_rate": 2.8260285403682153e-06, "loss": 0.0003, "step": 2652 }, { "epoch": 9.15, "learning_rate": 2.8195468022853912e-06, "loss": 0.0013, "step": 2653 }, { "epoch": 9.15, "learning_rate": 2.8130712858302068e-06, "loss": 0.0007, "step": 2654 }, { "epoch": 9.16, "learning_rate": 2.8066019966134907e-06, "loss": 0.0009, "step": 2655 }, { "epoch": 9.16, "learning_rate": 2.8001389402406644e-06, "loss": 0.0019, "step": 2656 }, { "epoch": 9.16, "learning_rate": 2.7936821223117617e-06, "loss": 0.001, "step": 2657 }, { "epoch": 9.17, "learning_rate": 2.7872315484213954e-06, "loss": 0.0016, "step": 2658 }, { "epoch": 9.17, "learning_rate": 2.780787224158785e-06, "loss": 0.0009, "step": 2659 }, { "epoch": 9.17, "learning_rate": 2.7743491551077197e-06, "loss": 0.0023, "step": 2660 }, { "epoch": 9.18, "learning_rate": 2.7679173468465813e-06, "loss": 0.002, "step": 2661 }, { "epoch": 9.18, "learning_rate": 2.7614918049483166e-06, "loss": 0.0013, "step": 2662 }, { "epoch": 9.18, "learning_rate": 2.755072534980451e-06, "loss": 0.0005, "step": 2663 }, { "epoch": 9.19, "learning_rate": 2.7486595425050667e-06, "loss": 0.0015, "step": 2664 }, { "epoch": 9.19, "learning_rate": 2.742252833078818e-06, "loss": 0.0018, "step": 2665 }, { "epoch": 9.19, "learning_rate": 2.735852412252903e-06, "loss": 0.001, "step": 2666 }, { "epoch": 9.2, "learning_rate": 2.7294582855730835e-06, "loss": 0.001, "step": 2667 }, { "epoch": 9.2, "learning_rate": 2.723070458579653e-06, "loss": 0.0005, "step": 2668 }, { "epoch": 9.2, "learning_rate": 2.7166889368074624e-06, "loss": 0.0024, "step": 2669 }, { "epoch": 9.21, "learning_rate": 2.7103137257858867e-06, "loss": 0.0014, "step": 2670 }, { "epoch": 9.21, "learning_rate": 2.703944831038836e-06, "loss": 0.0006, "step": 2671 }, { "epoch": 9.21, "learning_rate": 2.6975822580847546e-06, "loss": 0.001, "step": 2672 }, { "epoch": 9.22, "learning_rate": 2.6912260124366007e-06, "loss": 0.0008, "step": 2673 }, { "epoch": 9.22, "learning_rate": 2.684876099601851e-06, "loss": 0.0006, "step": 2674 }, { "epoch": 9.22, "learning_rate": 2.678532525082498e-06, "loss": 0.0012, "step": 2675 }, { "epoch": 9.23, "learning_rate": 2.672195294375045e-06, "loss": 0.0009, "step": 2676 }, { "epoch": 9.23, "learning_rate": 2.6658644129704904e-06, "loss": 0.0004, "step": 2677 }, { "epoch": 9.23, "learning_rate": 2.6595398863543407e-06, "loss": 0.0015, "step": 2678 }, { "epoch": 9.24, "learning_rate": 2.6532217200065856e-06, "loss": 0.001, "step": 2679 }, { "epoch": 9.24, "learning_rate": 2.6469099194017144e-06, "loss": 0.0017, "step": 2680 }, { "epoch": 9.24, "learning_rate": 2.640604490008691e-06, "loss": 0.001, "step": 2681 }, { "epoch": 9.25, "learning_rate": 2.634305437290968e-06, "loss": 0.0012, "step": 2682 }, { "epoch": 9.25, "learning_rate": 2.628012766706465e-06, "loss": 0.001, "step": 2683 }, { "epoch": 9.26, "learning_rate": 2.6217264837075773e-06, "loss": 0.0004, "step": 2684 }, { "epoch": 9.26, "learning_rate": 2.615446593741161e-06, "loss": 0.0015, "step": 2685 }, { "epoch": 9.26, "learning_rate": 2.609173102248539e-06, "loss": 0.002, "step": 2686 }, { "epoch": 9.27, "learning_rate": 2.6029060146654804e-06, "loss": 0.0008, "step": 2687 }, { "epoch": 9.27, "learning_rate": 2.596645336422219e-06, "loss": 0.0002, "step": 2688 }, { "epoch": 9.27, "learning_rate": 2.590391072943423e-06, "loss": 0.0013, "step": 2689 }, { "epoch": 9.28, "learning_rate": 2.584143229648207e-06, "loss": 0.002, "step": 2690 }, { "epoch": 9.28, "learning_rate": 2.577901811950121e-06, "loss": 0.0007, "step": 2691 }, { "epoch": 9.28, "learning_rate": 2.5716668252571542e-06, "loss": 0.0017, "step": 2692 }, { "epoch": 9.29, "learning_rate": 2.565438274971712e-06, "loss": 0.0017, "step": 2693 }, { "epoch": 9.29, "learning_rate": 2.5592161664906366e-06, "loss": 0.0017, "step": 2694 }, { "epoch": 9.29, "learning_rate": 2.5530005052051742e-06, "loss": 0.0019, "step": 2695 }, { "epoch": 9.3, "learning_rate": 2.546791296500999e-06, "loss": 0.0005, "step": 2696 }, { "epoch": 9.3, "learning_rate": 2.5405885457581793e-06, "loss": 0.0008, "step": 2697 }, { "epoch": 9.3, "learning_rate": 2.5343922583512026e-06, "loss": 0.0102, "step": 2698 }, { "epoch": 9.31, "learning_rate": 2.5282024396489435e-06, "loss": 0.0033, "step": 2699 }, { "epoch": 9.31, "learning_rate": 2.522019095014683e-06, "loss": 0.0009, "step": 2700 }, { "epoch": 9.31, "learning_rate": 2.5158422298060805e-06, "loss": 0.003, "step": 2701 }, { "epoch": 9.32, "learning_rate": 2.509671849375194e-06, "loss": 0.0013, "step": 2702 }, { "epoch": 9.32, "learning_rate": 2.5035079590684496e-06, "loss": 0.0017, "step": 2703 }, { "epoch": 9.32, "learning_rate": 2.4973505642266625e-06, "loss": 0.0006, "step": 2704 }, { "epoch": 9.33, "learning_rate": 2.4911996701850083e-06, "loss": 0.0029, "step": 2705 }, { "epoch": 9.33, "learning_rate": 2.48505528227304e-06, "loss": 0.0006, "step": 2706 }, { "epoch": 9.33, "learning_rate": 2.478917405814665e-06, "loss": 0.0007, "step": 2707 }, { "epoch": 9.34, "learning_rate": 2.472786046128156e-06, "loss": 0.0017, "step": 2708 }, { "epoch": 9.34, "learning_rate": 2.4666612085261344e-06, "loss": 0.005, "step": 2709 }, { "epoch": 9.34, "learning_rate": 2.4605428983155667e-06, "loss": 0.0008, "step": 2710 }, { "epoch": 9.35, "learning_rate": 2.4544311207977754e-06, "loss": 0.0004, "step": 2711 }, { "epoch": 9.35, "learning_rate": 2.4483258812684096e-06, "loss": 0.0003, "step": 2712 }, { "epoch": 9.36, "learning_rate": 2.442227185017465e-06, "loss": 0.0014, "step": 2713 }, { "epoch": 9.36, "learning_rate": 2.4361350373292567e-06, "loss": 0.0023, "step": 2714 }, { "epoch": 9.36, "learning_rate": 2.4300494434824373e-06, "loss": 0.0014, "step": 2715 }, { "epoch": 9.37, "learning_rate": 2.4239704087499683e-06, "loss": 0.0004, "step": 2716 }, { "epoch": 9.37, "learning_rate": 2.4178979383991407e-06, "loss": 0.0007, "step": 2717 }, { "epoch": 9.37, "learning_rate": 2.411832037691545e-06, "loss": 0.0027, "step": 2718 }, { "epoch": 9.38, "learning_rate": 2.405772711883092e-06, "loss": 0.0014, "step": 2719 }, { "epoch": 9.38, "learning_rate": 2.3997199662239825e-06, "loss": 0.0005, "step": 2720 }, { "epoch": 9.38, "learning_rate": 2.3936738059587284e-06, "loss": 0.0013, "step": 2721 }, { "epoch": 9.39, "learning_rate": 2.387634236326125e-06, "loss": 0.0008, "step": 2722 }, { "epoch": 9.39, "learning_rate": 2.3816012625592657e-06, "loss": 0.0007, "step": 2723 }, { "epoch": 9.39, "learning_rate": 2.37557488988552e-06, "loss": 0.0003, "step": 2724 }, { "epoch": 9.4, "learning_rate": 2.3695551235265492e-06, "loss": 0.0011, "step": 2725 }, { "epoch": 9.4, "learning_rate": 2.3635419686982763e-06, "loss": 0.0016, "step": 2726 }, { "epoch": 9.4, "learning_rate": 2.35753543061091e-06, "loss": 0.0059, "step": 2727 }, { "epoch": 9.41, "learning_rate": 2.3515355144689155e-06, "loss": 0.0006, "step": 2728 }, { "epoch": 9.41, "learning_rate": 2.3455422254710236e-06, "loss": 0.0009, "step": 2729 }, { "epoch": 9.41, "learning_rate": 2.339555568810221e-06, "loss": 0.0021, "step": 2730 }, { "epoch": 9.42, "learning_rate": 2.3335755496737543e-06, "loss": 0.0003, "step": 2731 }, { "epoch": 9.42, "learning_rate": 2.3276021732431096e-06, "loss": 0.0022, "step": 2732 }, { "epoch": 9.42, "learning_rate": 2.321635444694028e-06, "loss": 0.001, "step": 2733 }, { "epoch": 9.43, "learning_rate": 2.3156753691964774e-06, "loss": 0.0023, "step": 2734 }, { "epoch": 9.43, "learning_rate": 2.309721951914675e-06, "loss": 0.0026, "step": 2735 }, { "epoch": 9.43, "learning_rate": 2.3037751980070557e-06, "loss": 0.0002, "step": 2736 }, { "epoch": 9.44, "learning_rate": 2.29783511262629e-06, "loss": 0.0007, "step": 2737 }, { "epoch": 9.44, "learning_rate": 2.2919017009192703e-06, "loss": 0.0015, "step": 2738 }, { "epoch": 9.44, "learning_rate": 2.2859749680270983e-06, "loss": 0.0011, "step": 2739 }, { "epoch": 9.45, "learning_rate": 2.2800549190850997e-06, "loss": 0.0023, "step": 2740 }, { "epoch": 9.45, "learning_rate": 2.274141559222797e-06, "loss": 0.0011, "step": 2741 }, { "epoch": 9.46, "learning_rate": 2.2682348935639274e-06, "loss": 0.0015, "step": 2742 }, { "epoch": 9.46, "learning_rate": 2.2623349272264205e-06, "loss": 0.0006, "step": 2743 }, { "epoch": 9.46, "learning_rate": 2.2564416653224074e-06, "loss": 0.0014, "step": 2744 }, { "epoch": 9.47, "learning_rate": 2.2505551129582047e-06, "loss": 0.0006, "step": 2745 }, { "epoch": 9.47, "learning_rate": 2.244675275234315e-06, "loss": 0.0012, "step": 2746 }, { "epoch": 9.47, "learning_rate": 2.23880215724543e-06, "loss": 0.0009, "step": 2747 }, { "epoch": 9.48, "learning_rate": 2.2329357640804118e-06, "loss": 0.0021, "step": 2748 }, { "epoch": 9.48, "learning_rate": 2.2270761008222953e-06, "loss": 0.0006, "step": 2749 }, { "epoch": 9.48, "learning_rate": 2.2212231725482914e-06, "loss": 0.0009, "step": 2750 }, { "epoch": 9.49, "learning_rate": 2.215376984329767e-06, "loss": 0.0012, "step": 2751 }, { "epoch": 9.49, "learning_rate": 2.2095375412322563e-06, "loss": 0.0007, "step": 2752 }, { "epoch": 9.49, "learning_rate": 2.2037048483154422e-06, "loss": 0.0018, "step": 2753 }, { "epoch": 9.5, "learning_rate": 2.1978789106331666e-06, "loss": 0.0003, "step": 2754 }, { "epoch": 9.5, "learning_rate": 2.192059733233408e-06, "loss": 0.0006, "step": 2755 }, { "epoch": 9.5, "learning_rate": 2.186247321158299e-06, "loss": 0.0045, "step": 2756 }, { "epoch": 9.51, "learning_rate": 2.1804416794441e-06, "loss": 0.0017, "step": 2757 }, { "epoch": 9.51, "learning_rate": 2.1746428131212126e-06, "loss": 0.0016, "step": 2758 }, { "epoch": 9.51, "learning_rate": 2.168850727214161e-06, "loss": 0.001, "step": 2759 }, { "epoch": 9.52, "learning_rate": 2.163065426741603e-06, "loss": 0.0035, "step": 2760 }, { "epoch": 9.52, "learning_rate": 2.157286916716307e-06, "loss": 0.0007, "step": 2761 }, { "epoch": 9.52, "learning_rate": 2.151515202145168e-06, "loss": 0.0018, "step": 2762 }, { "epoch": 9.53, "learning_rate": 2.1457502880291815e-06, "loss": 0.0003, "step": 2763 }, { "epoch": 9.53, "learning_rate": 2.1399921793634626e-06, "loss": 0.0012, "step": 2764 }, { "epoch": 9.53, "learning_rate": 2.1342408811372217e-06, "loss": 0.001, "step": 2765 }, { "epoch": 9.54, "learning_rate": 2.128496398333768e-06, "loss": 0.0026, "step": 2766 }, { "epoch": 9.54, "learning_rate": 2.1227587359305137e-06, "loss": 0.0011, "step": 2767 }, { "epoch": 9.54, "learning_rate": 2.117027898898948e-06, "loss": 0.0021, "step": 2768 }, { "epoch": 9.55, "learning_rate": 2.1113038922046603e-06, "loss": 0.0015, "step": 2769 }, { "epoch": 9.55, "learning_rate": 2.10558672080731e-06, "loss": 0.0003, "step": 2770 }, { "epoch": 9.56, "learning_rate": 2.099876389660643e-06, "loss": 0.001, "step": 2771 }, { "epoch": 9.56, "learning_rate": 2.09417290371247e-06, "loss": 0.0035, "step": 2772 }, { "epoch": 9.56, "learning_rate": 2.088476267904681e-06, "loss": 0.0014, "step": 2773 }, { "epoch": 9.57, "learning_rate": 2.0827864871732174e-06, "loss": 0.0004, "step": 2774 }, { "epoch": 9.57, "learning_rate": 2.0771035664480944e-06, "loss": 0.0017, "step": 2775 }, { "epoch": 9.57, "learning_rate": 2.0714275106533697e-06, "loss": 0.0009, "step": 2776 }, { "epoch": 9.58, "learning_rate": 2.0657583247071677e-06, "loss": 0.0008, "step": 2777 }, { "epoch": 9.58, "learning_rate": 2.0600960135216463e-06, "loss": 0.0008, "step": 2778 }, { "epoch": 9.58, "learning_rate": 2.0544405820030165e-06, "loss": 0.0021, "step": 2779 }, { "epoch": 9.59, "learning_rate": 2.048792035051521e-06, "loss": 0.0003, "step": 2780 }, { "epoch": 9.59, "learning_rate": 2.0431503775614457e-06, "loss": 0.0005, "step": 2781 }, { "epoch": 9.59, "learning_rate": 2.0375156144210974e-06, "loss": 0.0026, "step": 2782 }, { "epoch": 9.6, "learning_rate": 2.0318877505128177e-06, "loss": 0.0006, "step": 2783 }, { "epoch": 9.6, "learning_rate": 2.026266790712965e-06, "loss": 0.003, "step": 2784 }, { "epoch": 9.6, "learning_rate": 2.020652739891914e-06, "loss": 0.0003, "step": 2785 }, { "epoch": 9.61, "learning_rate": 2.015045602914062e-06, "loss": 0.0009, "step": 2786 }, { "epoch": 9.61, "learning_rate": 2.009445384637805e-06, "loss": 0.0003, "step": 2787 }, { "epoch": 9.61, "learning_rate": 2.003852089915548e-06, "loss": 0.0005, "step": 2788 }, { "epoch": 9.62, "learning_rate": 1.9982657235937018e-06, "loss": 0.0003, "step": 2789 }, { "epoch": 9.62, "learning_rate": 1.9926862905126663e-06, "loss": 0.0014, "step": 2790 }, { "epoch": 9.62, "learning_rate": 1.987113795506841e-06, "loss": 0.002, "step": 2791 }, { "epoch": 9.63, "learning_rate": 1.9815482434046062e-06, "loss": 0.0018, "step": 2792 }, { "epoch": 9.63, "learning_rate": 1.9759896390283362e-06, "loss": 0.0016, "step": 2793 }, { "epoch": 9.63, "learning_rate": 1.9704379871943746e-06, "loss": 0.0013, "step": 2794 }, { "epoch": 9.64, "learning_rate": 1.964893292713049e-06, "loss": 0.0053, "step": 2795 }, { "epoch": 9.64, "learning_rate": 1.959355560388654e-06, "loss": 0.0021, "step": 2796 }, { "epoch": 9.64, "learning_rate": 1.9538247950194556e-06, "loss": 0.0018, "step": 2797 }, { "epoch": 9.65, "learning_rate": 1.9483010013976766e-06, "loss": 0.0003, "step": 2798 }, { "epoch": 9.65, "learning_rate": 1.9427841843095063e-06, "loss": 0.0016, "step": 2799 }, { "epoch": 9.66, "learning_rate": 1.9372743485350887e-06, "loss": 0.0015, "step": 2800 }, { "epoch": 9.66, "learning_rate": 1.93177149884851e-06, "loss": 0.0027, "step": 2801 }, { "epoch": 9.66, "learning_rate": 1.9262756400178163e-06, "loss": 0.0002, "step": 2802 }, { "epoch": 9.67, "learning_rate": 1.920786776804986e-06, "loss": 0.0021, "step": 2803 }, { "epoch": 9.67, "learning_rate": 1.9153049139659386e-06, "loss": 0.0012, "step": 2804 }, { "epoch": 9.67, "learning_rate": 1.9098300562505266e-06, "loss": 0.0019, "step": 2805 }, { "epoch": 9.68, "learning_rate": 1.9043622084025404e-06, "loss": 0.0009, "step": 2806 }, { "epoch": 9.68, "learning_rate": 1.8989013751596864e-06, "loss": 0.0003, "step": 2807 }, { "epoch": 9.68, "learning_rate": 1.8934475612536019e-06, "loss": 0.0022, "step": 2808 }, { "epoch": 9.69, "learning_rate": 1.8880007714098347e-06, "loss": 0.0009, "step": 2809 }, { "epoch": 9.69, "learning_rate": 1.8825610103478531e-06, "loss": 0.002, "step": 2810 }, { "epoch": 9.69, "learning_rate": 1.8771282827810278e-06, "loss": 0.0016, "step": 2811 }, { "epoch": 9.7, "learning_rate": 1.8717025934166445e-06, "loss": 0.0019, "step": 2812 }, { "epoch": 9.7, "learning_rate": 1.8662839469558803e-06, "loss": 0.0017, "step": 2813 }, { "epoch": 9.7, "learning_rate": 1.8608723480938207e-06, "loss": 0.0017, "step": 2814 }, { "epoch": 9.71, "learning_rate": 1.8554678015194316e-06, "loss": 0.0006, "step": 2815 }, { "epoch": 9.71, "learning_rate": 1.8500703119155838e-06, "loss": 0.0015, "step": 2816 }, { "epoch": 9.71, "learning_rate": 1.8446798839590186e-06, "loss": 0.0003, "step": 2817 }, { "epoch": 9.72, "learning_rate": 1.8392965223203707e-06, "loss": 0.0006, "step": 2818 }, { "epoch": 9.72, "learning_rate": 1.8339202316641413e-06, "loss": 0.0004, "step": 2819 }, { "epoch": 9.72, "learning_rate": 1.8285510166487154e-06, "loss": 0.001, "step": 2820 }, { "epoch": 9.73, "learning_rate": 1.8231888819263377e-06, "loss": 0.0006, "step": 2821 }, { "epoch": 9.73, "learning_rate": 1.8178338321431266e-06, "loss": 0.0016, "step": 2822 }, { "epoch": 9.73, "learning_rate": 1.812485871939056e-06, "loss": 0.001, "step": 2823 }, { "epoch": 9.74, "learning_rate": 1.8071450059479579e-06, "loss": 0.0008, "step": 2824 }, { "epoch": 9.74, "learning_rate": 1.8018112387975139e-06, "loss": 0.001, "step": 2825 }, { "epoch": 9.74, "learning_rate": 1.7964845751092663e-06, "loss": 0.0015, "step": 2826 }, { "epoch": 9.75, "learning_rate": 1.7911650194985875e-06, "loss": 0.0025, "step": 2827 }, { "epoch": 9.75, "learning_rate": 1.7858525765747047e-06, "loss": 0.0007, "step": 2828 }, { "epoch": 9.76, "learning_rate": 1.7805472509406695e-06, "loss": 0.0009, "step": 2829 }, { "epoch": 9.76, "learning_rate": 1.7752490471933769e-06, "loss": 0.002, "step": 2830 }, { "epoch": 9.76, "learning_rate": 1.7699579699235491e-06, "loss": 0.0005, "step": 2831 }, { "epoch": 9.77, "learning_rate": 1.7646740237157256e-06, "loss": 0.0027, "step": 2832 }, { "epoch": 9.77, "learning_rate": 1.7593972131482773e-06, "loss": 0.0012, "step": 2833 }, { "epoch": 9.77, "learning_rate": 1.7541275427933847e-06, "loss": 0.0007, "step": 2834 }, { "epoch": 9.78, "learning_rate": 1.7488650172170496e-06, "loss": 0.0013, "step": 2835 }, { "epoch": 9.78, "learning_rate": 1.7436096409790703e-06, "loss": 0.0015, "step": 2836 }, { "epoch": 9.78, "learning_rate": 1.7383614186330667e-06, "loss": 0.0004, "step": 2837 }, { "epoch": 9.79, "learning_rate": 1.7331203547264452e-06, "loss": 0.0011, "step": 2838 }, { "epoch": 9.79, "learning_rate": 1.7278864538004204e-06, "loss": 0.0003, "step": 2839 }, { "epoch": 9.79, "learning_rate": 1.7226597203899941e-06, "loss": 0.0007, "step": 2840 }, { "epoch": 9.8, "learning_rate": 1.7174401590239587e-06, "loss": 0.0015, "step": 2841 }, { "epoch": 9.8, "learning_rate": 1.712227774224896e-06, "loss": 0.0003, "step": 2842 }, { "epoch": 9.8, "learning_rate": 1.707022570509166e-06, "loss": 0.0015, "step": 2843 }, { "epoch": 9.81, "learning_rate": 1.7018245523869038e-06, "loss": 0.0009, "step": 2844 }, { "epoch": 9.81, "learning_rate": 1.6966337243620267e-06, "loss": 0.0009, "step": 2845 }, { "epoch": 9.81, "learning_rate": 1.691450090932213e-06, "loss": 0.001, "step": 2846 }, { "epoch": 9.82, "learning_rate": 1.686273656588917e-06, "loss": 0.0017, "step": 2847 }, { "epoch": 9.82, "learning_rate": 1.6811044258173425e-06, "loss": 0.0019, "step": 2848 }, { "epoch": 9.82, "learning_rate": 1.6759424030964666e-06, "loss": 0.0025, "step": 2849 }, { "epoch": 9.83, "learning_rate": 1.6707875928990059e-06, "loss": 0.0021, "step": 2850 }, { "epoch": 9.83, "learning_rate": 1.6656399996914397e-06, "loss": 0.0011, "step": 2851 }, { "epoch": 9.83, "learning_rate": 1.6604996279339847e-06, "loss": 0.0022, "step": 2852 }, { "epoch": 9.84, "learning_rate": 1.6553664820806102e-06, "loss": 0.0013, "step": 2853 }, { "epoch": 9.84, "learning_rate": 1.6502405665790134e-06, "loss": 0.0004, "step": 2854 }, { "epoch": 9.84, "learning_rate": 1.6451218858706374e-06, "loss": 0.0012, "step": 2855 }, { "epoch": 9.85, "learning_rate": 1.6400104443906463e-06, "loss": 0.0013, "step": 2856 }, { "epoch": 9.85, "learning_rate": 1.634906246567941e-06, "loss": 0.0012, "step": 2857 }, { "epoch": 9.86, "learning_rate": 1.629809296825139e-06, "loss": 0.0011, "step": 2858 }, { "epoch": 9.86, "learning_rate": 1.6247195995785836e-06, "loss": 0.0009, "step": 2859 }, { "epoch": 9.86, "learning_rate": 1.6196371592383264e-06, "loss": 0.0003, "step": 2860 }, { "epoch": 9.87, "learning_rate": 1.6145619802081413e-06, "loss": 0.0013, "step": 2861 }, { "epoch": 9.87, "learning_rate": 1.6094940668855008e-06, "loss": 0.0019, "step": 2862 }, { "epoch": 9.87, "learning_rate": 1.6044334236615845e-06, "loss": 0.0011, "step": 2863 }, { "epoch": 9.88, "learning_rate": 1.599380054921279e-06, "loss": 0.0016, "step": 2864 }, { "epoch": 9.88, "learning_rate": 1.5943339650431578e-06, "loss": 0.0011, "step": 2865 }, { "epoch": 9.88, "learning_rate": 1.5892951583994965e-06, "loss": 0.0008, "step": 2866 }, { "epoch": 9.89, "learning_rate": 1.5842636393562537e-06, "loss": 0.0007, "step": 2867 }, { "epoch": 9.89, "learning_rate": 1.579239412273078e-06, "loss": 0.0005, "step": 2868 }, { "epoch": 9.89, "learning_rate": 1.5742224815032947e-06, "loss": 0.001, "step": 2869 }, { "epoch": 9.9, "learning_rate": 1.5692128513939142e-06, "loss": 0.0014, "step": 2870 }, { "epoch": 9.9, "learning_rate": 1.5642105262856122e-06, "loss": 0.0008, "step": 2871 }, { "epoch": 9.9, "learning_rate": 1.5592155105127448e-06, "loss": 0.0013, "step": 2872 }, { "epoch": 9.91, "learning_rate": 1.5542278084033236e-06, "loss": 0.0014, "step": 2873 }, { "epoch": 9.91, "learning_rate": 1.5492474242790368e-06, "loss": 0.0008, "step": 2874 }, { "epoch": 9.91, "learning_rate": 1.544274362455216e-06, "loss": 0.0042, "step": 2875 }, { "epoch": 9.92, "learning_rate": 1.539308627240864e-06, "loss": 0.0012, "step": 2876 }, { "epoch": 9.92, "learning_rate": 1.5343502229386209e-06, "loss": 0.0003, "step": 2877 }, { "epoch": 9.92, "learning_rate": 1.5293991538447882e-06, "loss": 0.0013, "step": 2878 }, { "epoch": 9.93, "learning_rate": 1.5244554242493026e-06, "loss": 0.0013, "step": 2879 }, { "epoch": 9.93, "learning_rate": 1.5195190384357405e-06, "loss": 0.0023, "step": 2880 }, { "epoch": 9.93, "learning_rate": 1.514590000681324e-06, "loss": 0.0014, "step": 2881 }, { "epoch": 9.94, "learning_rate": 1.5096683152569003e-06, "loss": 0.0015, "step": 2882 }, { "epoch": 9.94, "learning_rate": 1.5047539864269477e-06, "loss": 0.0009, "step": 2883 }, { "epoch": 9.94, "learning_rate": 1.4998470184495739e-06, "loss": 0.0011, "step": 2884 }, { "epoch": 9.95, "learning_rate": 1.494947415576502e-06, "loss": 0.002, "step": 2885 }, { "epoch": 9.95, "learning_rate": 1.490055182053083e-06, "loss": 0.0015, "step": 2886 }, { "epoch": 9.96, "learning_rate": 1.4851703221182724e-06, "loss": 0.0019, "step": 2887 }, { "epoch": 9.96, "learning_rate": 1.4802928400046457e-06, "loss": 0.0022, "step": 2888 }, { "epoch": 9.96, "learning_rate": 1.4754227399383758e-06, "loss": 0.0013, "step": 2889 }, { "epoch": 9.97, "learning_rate": 1.4705600261392505e-06, "loss": 0.0014, "step": 2890 }, { "epoch": 9.97, "learning_rate": 1.4657047028206484e-06, "loss": 0.0017, "step": 2891 }, { "epoch": 9.97, "learning_rate": 1.4608567741895496e-06, "loss": 0.0006, "step": 2892 }, { "epoch": 9.98, "learning_rate": 1.4560162444465276e-06, "loss": 0.0006, "step": 2893 }, { "epoch": 9.98, "learning_rate": 1.4511831177857383e-06, "loss": 0.0004, "step": 2894 }, { "epoch": 9.98, "learning_rate": 1.446357398394934e-06, "loss": 0.0007, "step": 2895 }, { "epoch": 9.99, "learning_rate": 1.441539090455436e-06, "loss": 0.001, "step": 2896 }, { "epoch": 9.99, "learning_rate": 1.4367281981421554e-06, "loss": 0.0008, "step": 2897 }, { "epoch": 9.99, "learning_rate": 1.4319247256235713e-06, "loss": 0.001, "step": 2898 }, { "epoch": 10.0, "learning_rate": 1.4271286770617354e-06, "loss": 0.0009, "step": 2899 }, { "epoch": 10.0, "learning_rate": 1.4223400566122635e-06, "loss": 0.0009, "step": 2900 }, { "epoch": 10.0, "learning_rate": 1.4175588684243447e-06, "loss": 0.0004, "step": 2901 }, { "epoch": 10.01, "learning_rate": 1.4127851166407146e-06, "loss": 0.0008, "step": 2902 }, { "epoch": 10.01, "learning_rate": 1.4080188053976807e-06, "loss": 0.0002, "step": 2903 }, { "epoch": 10.01, "learning_rate": 1.40325993882509e-06, "loss": 0.0006, "step": 2904 }, { "epoch": 10.02, "learning_rate": 1.3985085210463479e-06, "loss": 0.0006, "step": 2905 }, { "epoch": 10.02, "learning_rate": 1.3937645561783985e-06, "loss": 0.0009, "step": 2906 }, { "epoch": 10.02, "learning_rate": 1.3890280483317375e-06, "loss": 0.0006, "step": 2907 }, { "epoch": 10.03, "learning_rate": 1.3842990016103886e-06, "loss": 0.0004, "step": 2908 }, { "epoch": 10.03, "learning_rate": 1.3795774201119216e-06, "loss": 0.001, "step": 2909 }, { "epoch": 10.03, "learning_rate": 1.3748633079274254e-06, "loss": 0.0004, "step": 2910 }, { "epoch": 10.04, "learning_rate": 1.3701566691415302e-06, "loss": 0.0002, "step": 2911 }, { "epoch": 10.04, "learning_rate": 1.3654575078323795e-06, "loss": 0.0003, "step": 2912 }, { "epoch": 10.04, "learning_rate": 1.3607658280716474e-06, "loss": 0.0013, "step": 2913 }, { "epoch": 10.05, "learning_rate": 1.3560816339245163e-06, "loss": 0.0003, "step": 2914 }, { "epoch": 10.05, "learning_rate": 1.3514049294496911e-06, "loss": 0.001, "step": 2915 }, { "epoch": 10.06, "learning_rate": 1.3467357186993802e-06, "loss": 0.0008, "step": 2916 }, { "epoch": 10.06, "learning_rate": 1.3420740057193038e-06, "loss": 0.0002, "step": 2917 }, { "epoch": 10.06, "learning_rate": 1.3374197945486833e-06, "loss": 0.0007, "step": 2918 }, { "epoch": 10.07, "learning_rate": 1.3327730892202384e-06, "loss": 0.0007, "step": 2919 }, { "epoch": 10.07, "learning_rate": 1.3281338937601895e-06, "loss": 0.0009, "step": 2920 }, { "epoch": 10.07, "learning_rate": 1.3235022121882468e-06, "loss": 0.0006, "step": 2921 }, { "epoch": 10.08, "learning_rate": 1.3188780485176089e-06, "loss": 0.001, "step": 2922 }, { "epoch": 10.08, "learning_rate": 1.314261406754964e-06, "loss": 0.0027, "step": 2923 }, { "epoch": 10.08, "learning_rate": 1.3096522909004827e-06, "loss": 0.0004, "step": 2924 }, { "epoch": 10.09, "learning_rate": 1.30505070494781e-06, "loss": 0.0014, "step": 2925 }, { "epoch": 10.09, "learning_rate": 1.3004566528840724e-06, "loss": 0.0004, "step": 2926 }, { "epoch": 10.09, "learning_rate": 1.295870138689862e-06, "loss": 0.0008, "step": 2927 }, { "epoch": 10.1, "learning_rate": 1.2912911663392468e-06, "loss": 0.0017, "step": 2928 }, { "epoch": 10.1, "learning_rate": 1.2867197397997533e-06, "loss": 0.0003, "step": 2929 }, { "epoch": 10.1, "learning_rate": 1.282155863032377e-06, "loss": 0.0022, "step": 2930 }, { "epoch": 10.11, "learning_rate": 1.277599539991563e-06, "loss": 0.0005, "step": 2931 }, { "epoch": 10.11, "learning_rate": 1.2730507746252197e-06, "loss": 0.0003, "step": 2932 }, { "epoch": 10.11, "learning_rate": 1.2685095708747009e-06, "loss": 0.0007, "step": 2933 }, { "epoch": 10.12, "learning_rate": 1.2639759326748136e-06, "loss": 0.0002, "step": 2934 }, { "epoch": 10.12, "learning_rate": 1.2594498639538032e-06, "loss": 0.0021, "step": 2935 }, { "epoch": 10.12, "learning_rate": 1.2549313686333641e-06, "loss": 0.0006, "step": 2936 }, { "epoch": 10.13, "learning_rate": 1.2504204506286244e-06, "loss": 0.0002, "step": 2937 }, { "epoch": 10.13, "learning_rate": 1.245917113848144e-06, "loss": 0.0004, "step": 2938 }, { "epoch": 10.13, "learning_rate": 1.2414213621939154e-06, "loss": 0.0012, "step": 2939 }, { "epoch": 10.14, "learning_rate": 1.2369331995613664e-06, "loss": 0.0009, "step": 2940 }, { "epoch": 10.14, "learning_rate": 1.2324526298393358e-06, "loss": 0.0005, "step": 2941 }, { "epoch": 10.14, "learning_rate": 1.2279796569100978e-06, "loss": 0.0003, "step": 2942 }, { "epoch": 10.15, "learning_rate": 1.223514284649331e-06, "loss": 0.0007, "step": 2943 }, { "epoch": 10.15, "learning_rate": 1.2190565169261381e-06, "loss": 0.0009, "step": 2944 }, { "epoch": 10.16, "learning_rate": 1.2146063576030265e-06, "loss": 0.0005, "step": 2945 }, { "epoch": 10.16, "learning_rate": 1.210163810535917e-06, "loss": 0.0008, "step": 2946 }, { "epoch": 10.16, "learning_rate": 1.2057288795741261e-06, "loss": 0.0009, "step": 2947 }, { "epoch": 10.17, "learning_rate": 1.2013015685603813e-06, "loss": 0.0004, "step": 2948 }, { "epoch": 10.17, "learning_rate": 1.196881881330798e-06, "loss": 0.0011, "step": 2949 }, { "epoch": 10.17, "learning_rate": 1.1924698217148955e-06, "loss": 0.0009, "step": 2950 }, { "epoch": 10.18, "learning_rate": 1.1880653935355745e-06, "loss": 0.0004, "step": 2951 }, { "epoch": 10.18, "learning_rate": 1.1836686006091313e-06, "loss": 0.0002, "step": 2952 }, { "epoch": 10.18, "learning_rate": 1.1792794467452406e-06, "loss": 0.0006, "step": 2953 }, { "epoch": 10.19, "learning_rate": 1.1748979357469626e-06, "loss": 0.0003, "step": 2954 }, { "epoch": 10.19, "learning_rate": 1.1705240714107301e-06, "loss": 0.001, "step": 2955 }, { "epoch": 10.19, "learning_rate": 1.1661578575263578e-06, "loss": 0.0002, "step": 2956 }, { "epoch": 10.2, "learning_rate": 1.1617992978770242e-06, "loss": 0.0007, "step": 2957 }, { "epoch": 10.2, "learning_rate": 1.1574483962392768e-06, "loss": 0.0007, "step": 2958 }, { "epoch": 10.2, "learning_rate": 1.1531051563830343e-06, "loss": 0.0011, "step": 2959 }, { "epoch": 10.21, "learning_rate": 1.1487695820715672e-06, "loss": 0.0011, "step": 2960 }, { "epoch": 10.21, "learning_rate": 1.1444416770615118e-06, "loss": 0.0004, "step": 2961 }, { "epoch": 10.21, "learning_rate": 1.1401214451028542e-06, "loss": 0.0014, "step": 2962 }, { "epoch": 10.22, "learning_rate": 1.1358088899389353e-06, "loss": 0.0013, "step": 2963 }, { "epoch": 10.22, "learning_rate": 1.1315040153064416e-06, "loss": 0.0004, "step": 2964 }, { "epoch": 10.22, "learning_rate": 1.1272068249354085e-06, "loss": 0.0006, "step": 2965 }, { "epoch": 10.23, "learning_rate": 1.1229173225492073e-06, "loss": 0.0006, "step": 2966 }, { "epoch": 10.23, "learning_rate": 1.1186355118645552e-06, "loss": 0.0005, "step": 2967 }, { "epoch": 10.23, "learning_rate": 1.114361396591498e-06, "loss": 0.0004, "step": 2968 }, { "epoch": 10.24, "learning_rate": 1.1100949804334183e-06, "loss": 0.0008, "step": 2969 }, { "epoch": 10.24, "learning_rate": 1.1058362670870248e-06, "loss": 0.0002, "step": 2970 }, { "epoch": 10.24, "learning_rate": 1.1015852602423548e-06, "loss": 0.0013, "step": 2971 }, { "epoch": 10.25, "learning_rate": 1.0973419635827643e-06, "loss": 0.0009, "step": 2972 }, { "epoch": 10.25, "learning_rate": 1.093106380784934e-06, "loss": 0.0003, "step": 2973 }, { "epoch": 10.26, "learning_rate": 1.0888785155188542e-06, "loss": 0.0007, "step": 2974 }, { "epoch": 10.26, "learning_rate": 1.0846583714478355e-06, "loss": 0.0004, "step": 2975 }, { "epoch": 10.26, "learning_rate": 1.0804459522284927e-06, "loss": 0.0004, "step": 2976 }, { "epoch": 10.27, "learning_rate": 1.0762412615107499e-06, "loss": 0.0005, "step": 2977 }, { "epoch": 10.27, "learning_rate": 1.0720443029378303e-06, "loss": 0.0002, "step": 2978 }, { "epoch": 10.27, "learning_rate": 1.0678550801462662e-06, "loss": 0.0013, "step": 2979 }, { "epoch": 10.28, "learning_rate": 1.0636735967658785e-06, "loss": 0.0006, "step": 2980 }, { "epoch": 10.28, "learning_rate": 1.059499856419789e-06, "loss": 0.0007, "step": 2981 }, { "epoch": 10.28, "learning_rate": 1.0553338627244026e-06, "loss": 0.0004, "step": 2982 }, { "epoch": 10.29, "learning_rate": 1.0511756192894207e-06, "loss": 0.0008, "step": 2983 }, { "epoch": 10.29, "learning_rate": 1.0470251297178213e-06, "loss": 0.0011, "step": 2984 }, { "epoch": 10.29, "learning_rate": 1.042882397605871e-06, "loss": 0.0007, "step": 2985 }, { "epoch": 10.3, "learning_rate": 1.0387474265431118e-06, "loss": 0.0016, "step": 2986 }, { "epoch": 10.3, "learning_rate": 1.0346202201123567e-06, "loss": 0.0024, "step": 2987 }, { "epoch": 10.3, "learning_rate": 1.0305007818897006e-06, "loss": 0.0008, "step": 2988 }, { "epoch": 10.31, "learning_rate": 1.026389115444497e-06, "loss": 0.0002, "step": 2989 }, { "epoch": 10.31, "learning_rate": 1.0222852243393732e-06, "loss": 0.0007, "step": 2990 }, { "epoch": 10.31, "learning_rate": 1.0181891121302145e-06, "loss": 0.0006, "step": 2991 }, { "epoch": 10.32, "learning_rate": 1.014100782366171e-06, "loss": 0.0015, "step": 2992 }, { "epoch": 10.32, "learning_rate": 1.010020238589644e-06, "loss": 0.0054, "step": 2993 }, { "epoch": 10.32, "learning_rate": 1.0059474843362893e-06, "loss": 0.0008, "step": 2994 }, { "epoch": 10.33, "learning_rate": 1.0018825231350203e-06, "loss": 0.0014, "step": 2995 }, { "epoch": 10.33, "learning_rate": 9.9782535850799e-07, "loss": 0.0016, "step": 2996 }, { "epoch": 10.33, "learning_rate": 9.93775993970597e-07, "loss": 0.0015, "step": 2997 }, { "epoch": 10.34, "learning_rate": 9.897344330314862e-07, "loss": 0.0011, "step": 2998 }, { "epoch": 10.34, "learning_rate": 9.85700679192536e-07, "loss": 0.0006, "step": 2999 }, { "epoch": 10.34, "learning_rate": 9.816747359488632e-07, "loss": 0.0012, "step": 3000 }, { "epoch": 10.35, "learning_rate": 9.776566067888137e-07, "loss": 0.0006, "step": 3001 }, { "epoch": 10.35, "learning_rate": 9.736462951939695e-07, "loss": 0.001, "step": 3002 }, { "epoch": 10.36, "learning_rate": 9.696438046391288e-07, "loss": 0.0005, "step": 3003 }, { "epoch": 10.36, "learning_rate": 9.656491385923217e-07, "loss": 0.0013, "step": 3004 }, { "epoch": 10.36, "learning_rate": 9.616623005147952e-07, "loss": 0.0004, "step": 3005 }, { "epoch": 10.37, "learning_rate": 9.576832938610137e-07, "loss": 0.0014, "step": 3006 }, { "epoch": 10.37, "learning_rate": 9.537121220786561e-07, "loss": 0.0018, "step": 3007 }, { "epoch": 10.37, "learning_rate": 9.497487886086132e-07, "loss": 0.0004, "step": 3008 }, { "epoch": 10.38, "learning_rate": 9.457932968849826e-07, "loss": 0.0009, "step": 3009 }, { "epoch": 10.38, "learning_rate": 9.418456503350714e-07, "loss": 0.0007, "step": 3010 }, { "epoch": 10.38, "learning_rate": 9.379058523793816e-07, "loss": 0.001, "step": 3011 }, { "epoch": 10.39, "learning_rate": 9.339739064316233e-07, "loss": 0.0006, "step": 3012 }, { "epoch": 10.39, "learning_rate": 9.30049815898697e-07, "loss": 0.0002, "step": 3013 }, { "epoch": 10.39, "learning_rate": 9.261335841806973e-07, "loss": 0.0005, "step": 3014 }, { "epoch": 10.4, "learning_rate": 9.222252146709143e-07, "loss": 0.0005, "step": 3015 }, { "epoch": 10.4, "learning_rate": 9.183247107558191e-07, "loss": 0.0006, "step": 3016 }, { "epoch": 10.4, "learning_rate": 9.144320758150727e-07, "loss": 0.0016, "step": 3017 }, { "epoch": 10.41, "learning_rate": 9.105473132215126e-07, "loss": 0.0008, "step": 3018 }, { "epoch": 10.41, "learning_rate": 9.066704263411641e-07, "loss": 0.001, "step": 3019 }, { "epoch": 10.41, "learning_rate": 9.028014185332168e-07, "loss": 0.001, "step": 3020 }, { "epoch": 10.42, "learning_rate": 8.989402931500434e-07, "loss": 0.0004, "step": 3021 }, { "epoch": 10.42, "learning_rate": 8.950870535371803e-07, "loss": 0.0024, "step": 3022 }, { "epoch": 10.42, "learning_rate": 8.912417030333365e-07, "loss": 0.0007, "step": 3023 }, { "epoch": 10.43, "learning_rate": 8.874042449703779e-07, "loss": 0.0003, "step": 3024 }, { "epoch": 10.43, "learning_rate": 8.835746826733404e-07, "loss": 0.0011, "step": 3025 }, { "epoch": 10.43, "learning_rate": 8.797530194604109e-07, "loss": 0.0007, "step": 3026 }, { "epoch": 10.44, "learning_rate": 8.759392586429394e-07, "loss": 0.001, "step": 3027 }, { "epoch": 10.44, "learning_rate": 8.721334035254203e-07, "loss": 0.0005, "step": 3028 }, { "epoch": 10.44, "learning_rate": 8.683354574055059e-07, "loss": 0.0003, "step": 3029 }, { "epoch": 10.45, "learning_rate": 8.645454235739903e-07, "loss": 0.0003, "step": 3030 }, { "epoch": 10.45, "learning_rate": 8.607633053148156e-07, "loss": 0.001, "step": 3031 }, { "epoch": 10.46, "learning_rate": 8.569891059050628e-07, "loss": 0.0014, "step": 3032 }, { "epoch": 10.46, "learning_rate": 8.532228286149502e-07, "loss": 0.0006, "step": 3033 }, { "epoch": 10.46, "learning_rate": 8.494644767078375e-07, "loss": 0.0003, "step": 3034 }, { "epoch": 10.47, "learning_rate": 8.457140534402098e-07, "loss": 0.0006, "step": 3035 }, { "epoch": 10.47, "learning_rate": 8.419715620616875e-07, "loss": 0.0014, "step": 3036 }, { "epoch": 10.47, "learning_rate": 8.38237005815018e-07, "loss": 0.0004, "step": 3037 }, { "epoch": 10.48, "learning_rate": 8.345103879360695e-07, "loss": 0.0005, "step": 3038 }, { "epoch": 10.48, "learning_rate": 8.307917116538378e-07, "loss": 0.0012, "step": 3039 }, { "epoch": 10.48, "learning_rate": 8.270809801904301e-07, "loss": 0.0013, "step": 3040 }, { "epoch": 10.49, "learning_rate": 8.233781967610788e-07, "loss": 0.0011, "step": 3041 }, { "epoch": 10.49, "learning_rate": 8.196833645741187e-07, "loss": 0.0016, "step": 3042 }, { "epoch": 10.49, "learning_rate": 8.159964868310066e-07, "loss": 0.0004, "step": 3043 }, { "epoch": 10.5, "learning_rate": 8.123175667262972e-07, "loss": 0.0007, "step": 3044 }, { "epoch": 10.5, "learning_rate": 8.086466074476562e-07, "loss": 0.0006, "step": 3045 }, { "epoch": 10.5, "learning_rate": 8.049836121758492e-07, "loss": 0.0004, "step": 3046 }, { "epoch": 10.51, "learning_rate": 8.013285840847407e-07, "loss": 0.0004, "step": 3047 }, { "epoch": 10.51, "learning_rate": 7.976815263412963e-07, "loss": 0.001, "step": 3048 }, { "epoch": 10.51, "learning_rate": 7.940424421055681e-07, "loss": 0.0012, "step": 3049 }, { "epoch": 10.52, "learning_rate": 7.904113345307073e-07, "loss": 0.0007, "step": 3050 }, { "epoch": 10.52, "learning_rate": 7.867882067629473e-07, "loss": 0.0016, "step": 3051 }, { "epoch": 10.52, "learning_rate": 7.8317306194161e-07, "loss": 0.0007, "step": 3052 }, { "epoch": 10.53, "learning_rate": 7.795659031990988e-07, "loss": 0.0006, "step": 3053 }, { "epoch": 10.53, "learning_rate": 7.759667336609011e-07, "loss": 0.0005, "step": 3054 }, { "epoch": 10.53, "learning_rate": 7.723755564455771e-07, "loss": 0.0007, "step": 3055 }, { "epoch": 10.54, "learning_rate": 7.687923746647663e-07, "loss": 0.0006, "step": 3056 }, { "epoch": 10.54, "learning_rate": 7.652171914231777e-07, "loss": 0.0003, "step": 3057 }, { "epoch": 10.54, "learning_rate": 7.616500098185908e-07, "loss": 0.0007, "step": 3058 }, { "epoch": 10.55, "learning_rate": 7.580908329418501e-07, "loss": 0.0003, "step": 3059 }, { "epoch": 10.55, "learning_rate": 7.545396638768698e-07, "loss": 0.0006, "step": 3060 }, { "epoch": 10.56, "learning_rate": 7.509965057006163e-07, "loss": 0.0002, "step": 3061 }, { "epoch": 10.56, "learning_rate": 7.47461361483125e-07, "loss": 0.0007, "step": 3062 }, { "epoch": 10.56, "learning_rate": 7.439342342874789e-07, "loss": 0.0011, "step": 3063 }, { "epoch": 10.57, "learning_rate": 7.404151271698212e-07, "loss": 0.0006, "step": 3064 }, { "epoch": 10.57, "learning_rate": 7.369040431793406e-07, "loss": 0.0014, "step": 3065 }, { "epoch": 10.57, "learning_rate": 7.334009853582791e-07, "loss": 0.0014, "step": 3066 }, { "epoch": 10.58, "learning_rate": 7.299059567419175e-07, "loss": 0.0005, "step": 3067 }, { "epoch": 10.58, "learning_rate": 7.264189603585892e-07, "loss": 0.0008, "step": 3068 }, { "epoch": 10.58, "learning_rate": 7.22939999229657e-07, "loss": 0.0009, "step": 3069 }, { "epoch": 10.59, "learning_rate": 7.194690763695312e-07, "loss": 0.0008, "step": 3070 }, { "epoch": 10.59, "learning_rate": 7.160061947856511e-07, "loss": 0.0003, "step": 3071 }, { "epoch": 10.59, "learning_rate": 7.125513574784904e-07, "loss": 0.0005, "step": 3072 }, { "epoch": 10.6, "learning_rate": 7.091045674415498e-07, "loss": 0.0016, "step": 3073 }, { "epoch": 10.6, "learning_rate": 7.056658276613648e-07, "loss": 0.0009, "step": 3074 }, { "epoch": 10.6, "learning_rate": 7.022351411174866e-07, "loss": 0.0006, "step": 3075 }, { "epoch": 10.61, "learning_rate": 6.988125107824961e-07, "loss": 0.0005, "step": 3076 }, { "epoch": 10.61, "learning_rate": 6.953979396219879e-07, "loss": 0.0009, "step": 3077 }, { "epoch": 10.61, "learning_rate": 6.919914305945774e-07, "loss": 0.004, "step": 3078 }, { "epoch": 10.62, "learning_rate": 6.885929866518948e-07, "loss": 0.0009, "step": 3079 }, { "epoch": 10.62, "learning_rate": 6.852026107385756e-07, "loss": 0.001, "step": 3080 }, { "epoch": 10.62, "learning_rate": 6.818203057922756e-07, "loss": 0.0005, "step": 3081 }, { "epoch": 10.63, "learning_rate": 6.784460747436472e-07, "loss": 0.0004, "step": 3082 }, { "epoch": 10.63, "learning_rate": 6.750799205163528e-07, "loss": 0.001, "step": 3083 }, { "epoch": 10.63, "learning_rate": 6.717218460270536e-07, "loss": 0.0015, "step": 3084 }, { "epoch": 10.64, "learning_rate": 6.683718541854134e-07, "loss": 0.001, "step": 3085 }, { "epoch": 10.64, "learning_rate": 6.65029947894088e-07, "loss": 0.0012, "step": 3086 }, { "epoch": 10.64, "learning_rate": 6.616961300487323e-07, "loss": 0.001, "step": 3087 }, { "epoch": 10.65, "learning_rate": 6.58370403537989e-07, "loss": 0.0005, "step": 3088 }, { "epoch": 10.65, "learning_rate": 6.550527712434884e-07, "loss": 0.0005, "step": 3089 }, { "epoch": 10.66, "learning_rate": 6.517432360398556e-07, "loss": 0.001, "step": 3090 }, { "epoch": 10.66, "learning_rate": 6.484418007946925e-07, "loss": 0.0003, "step": 3091 }, { "epoch": 10.66, "learning_rate": 6.451484683685815e-07, "loss": 0.0013, "step": 3092 }, { "epoch": 10.67, "learning_rate": 6.418632416150927e-07, "loss": 0.0003, "step": 3093 }, { "epoch": 10.67, "learning_rate": 6.385861233807633e-07, "loss": 0.0003, "step": 3094 }, { "epoch": 10.67, "learning_rate": 6.353171165051109e-07, "loss": 0.0011, "step": 3095 }, { "epoch": 10.68, "learning_rate": 6.320562238206218e-07, "loss": 0.0008, "step": 3096 }, { "epoch": 10.68, "learning_rate": 6.288034481527549e-07, "loss": 0.0006, "step": 3097 }, { "epoch": 10.68, "learning_rate": 6.255587923199313e-07, "loss": 0.0002, "step": 3098 }, { "epoch": 10.69, "learning_rate": 6.223222591335409e-07, "loss": 0.0008, "step": 3099 }, { "epoch": 10.69, "learning_rate": 6.190938513979317e-07, "loss": 0.0004, "step": 3100 }, { "epoch": 10.69, "learning_rate": 6.15873571910417e-07, "loss": 0.0009, "step": 3101 }, { "epoch": 10.7, "learning_rate": 6.126614234612593e-07, "loss": 0.0003, "step": 3102 }, { "epoch": 10.7, "learning_rate": 6.094574088336835e-07, "loss": 0.0002, "step": 3103 }, { "epoch": 10.7, "learning_rate": 6.0626153080386e-07, "loss": 0.0007, "step": 3104 }, { "epoch": 10.71, "learning_rate": 6.030737921409169e-07, "loss": 0.0009, "step": 3105 }, { "epoch": 10.71, "learning_rate": 5.998941956069204e-07, "loss": 0.0008, "step": 3106 }, { "epoch": 10.71, "learning_rate": 5.967227439568913e-07, "loss": 0.0002, "step": 3107 }, { "epoch": 10.72, "learning_rate": 5.935594399387856e-07, "loss": 0.0008, "step": 3108 }, { "epoch": 10.72, "learning_rate": 5.904042862935044e-07, "loss": 0.0018, "step": 3109 }, { "epoch": 10.72, "learning_rate": 5.872572857548853e-07, "loss": 0.0006, "step": 3110 }, { "epoch": 10.73, "learning_rate": 5.841184410496992e-07, "loss": 0.0018, "step": 3111 }, { "epoch": 10.73, "learning_rate": 5.809877548976539e-07, "loss": 0.0016, "step": 3112 }, { "epoch": 10.73, "learning_rate": 5.778652300113841e-07, "loss": 0.0003, "step": 3113 }, { "epoch": 10.74, "learning_rate": 5.747508690964599e-07, "loss": 0.0013, "step": 3114 }, { "epoch": 10.74, "learning_rate": 5.716446748513682e-07, "loss": 0.001, "step": 3115 }, { "epoch": 10.74, "learning_rate": 5.685466499675296e-07, "loss": 0.0006, "step": 3116 }, { "epoch": 10.75, "learning_rate": 5.654567971292757e-07, "loss": 0.0002, "step": 3117 }, { "epoch": 10.75, "learning_rate": 5.623751190138682e-07, "loss": 0.0008, "step": 3118 }, { "epoch": 10.76, "learning_rate": 5.593016182914757e-07, "loss": 0.0005, "step": 3119 }, { "epoch": 10.76, "learning_rate": 5.562362976251901e-07, "loss": 0.001, "step": 3120 }, { "epoch": 10.76, "learning_rate": 5.531791596710079e-07, "loss": 0.001, "step": 3121 }, { "epoch": 10.77, "learning_rate": 5.501302070778414e-07, "loss": 0.0006, "step": 3122 }, { "epoch": 10.77, "learning_rate": 5.470894424875062e-07, "loss": 0.0004, "step": 3123 }, { "epoch": 10.77, "learning_rate": 5.44056868534728e-07, "loss": 0.001, "step": 3124 }, { "epoch": 10.78, "learning_rate": 5.410324878471296e-07, "loss": 0.0009, "step": 3125 }, { "epoch": 10.78, "learning_rate": 5.380163030452412e-07, "loss": 0.0012, "step": 3126 }, { "epoch": 10.78, "learning_rate": 5.350083167424869e-07, "loss": 0.0006, "step": 3127 }, { "epoch": 10.79, "learning_rate": 5.320085315451862e-07, "loss": 0.0004, "step": 3128 }, { "epoch": 10.79, "learning_rate": 5.290169500525577e-07, "loss": 0.0004, "step": 3129 }, { "epoch": 10.79, "learning_rate": 5.26033574856708e-07, "loss": 0.0002, "step": 3130 }, { "epoch": 10.8, "learning_rate": 5.230584085426327e-07, "loss": 0.0012, "step": 3131 }, { "epoch": 10.8, "learning_rate": 5.200914536882184e-07, "loss": 0.0007, "step": 3132 }, { "epoch": 10.8, "learning_rate": 5.171327128642312e-07, "loss": 0.0006, "step": 3133 }, { "epoch": 10.81, "learning_rate": 5.141821886343267e-07, "loss": 0.0004, "step": 3134 }, { "epoch": 10.81, "learning_rate": 5.112398835550348e-07, "loss": 0.0006, "step": 3135 }, { "epoch": 10.81, "learning_rate": 5.08305800175769e-07, "loss": 0.0006, "step": 3136 }, { "epoch": 10.82, "learning_rate": 5.053799410388138e-07, "loss": 0.0005, "step": 3137 }, { "epoch": 10.82, "learning_rate": 5.024623086793323e-07, "loss": 0.0008, "step": 3138 }, { "epoch": 10.82, "learning_rate": 4.995529056253556e-07, "loss": 0.0009, "step": 3139 }, { "epoch": 10.83, "learning_rate": 4.966517343977884e-07, "loss": 0.0005, "step": 3140 }, { "epoch": 10.83, "learning_rate": 4.937587975103997e-07, "loss": 0.0009, "step": 3141 }, { "epoch": 10.83, "learning_rate": 4.908740974698245e-07, "loss": 0.0005, "step": 3142 }, { "epoch": 10.84, "learning_rate": 4.879976367755612e-07, "loss": 0.0004, "step": 3143 }, { "epoch": 10.84, "learning_rate": 4.851294179199673e-07, "loss": 0.0007, "step": 3144 }, { "epoch": 10.84, "learning_rate": 4.822694433882635e-07, "loss": 0.0006, "step": 3145 }, { "epoch": 10.85, "learning_rate": 4.794177156585233e-07, "loss": 0.0008, "step": 3146 }, { "epoch": 10.85, "learning_rate": 4.765742372016735e-07, "loss": 0.0007, "step": 3147 }, { "epoch": 10.86, "learning_rate": 4.737390104814954e-07, "loss": 0.0015, "step": 3148 }, { "epoch": 10.86, "learning_rate": 4.709120379546217e-07, "loss": 0.0009, "step": 3149 }, { "epoch": 10.86, "learning_rate": 4.6809332207053083e-07, "loss": 0.0004, "step": 3150 }, { "epoch": 10.87, "learning_rate": 4.65282865271548e-07, "loss": 0.0011, "step": 3151 }, { "epoch": 10.87, "learning_rate": 4.624806699928408e-07, "loss": 0.0009, "step": 3152 }, { "epoch": 10.87, "learning_rate": 4.596867386624215e-07, "loss": 0.001, "step": 3153 }, { "epoch": 10.88, "learning_rate": 4.5690107370113814e-07, "loss": 0.0006, "step": 3154 }, { "epoch": 10.88, "learning_rate": 4.5412367752268094e-07, "loss": 0.0004, "step": 3155 }, { "epoch": 10.88, "learning_rate": 4.5135455253357053e-07, "loss": 0.0002, "step": 3156 }, { "epoch": 10.89, "learning_rate": 4.485937011331643e-07, "loss": 0.0008, "step": 3157 }, { "epoch": 10.89, "learning_rate": 4.458411257136486e-07, "loss": 0.0005, "step": 3158 }, { "epoch": 10.89, "learning_rate": 4.4309682866004124e-07, "loss": 0.0014, "step": 3159 }, { "epoch": 10.9, "learning_rate": 4.4036081235018347e-07, "loss": 0.0002, "step": 3160 }, { "epoch": 10.9, "learning_rate": 4.376330791547478e-07, "loss": 0.001, "step": 3161 }, { "epoch": 10.9, "learning_rate": 4.349136314372204e-07, "loss": 0.0008, "step": 3162 }, { "epoch": 10.91, "learning_rate": 4.322024715539197e-07, "loss": 0.0011, "step": 3163 }, { "epoch": 10.91, "learning_rate": 4.29499601853971e-07, "loss": 0.0002, "step": 3164 }, { "epoch": 10.91, "learning_rate": 4.268050246793276e-07, "loss": 0.0008, "step": 3165 }, { "epoch": 10.92, "learning_rate": 4.241187423647497e-07, "loss": 0.0006, "step": 3166 }, { "epoch": 10.92, "learning_rate": 4.2144075723781206e-07, "loss": 0.0008, "step": 3167 }, { "epoch": 10.92, "learning_rate": 4.1877107161890416e-07, "loss": 0.0006, "step": 3168 }, { "epoch": 10.93, "learning_rate": 4.1610968782122006e-07, "loss": 0.0003, "step": 3169 }, { "epoch": 10.93, "learning_rate": 4.134566081507585e-07, "loss": 0.0003, "step": 3170 }, { "epoch": 10.93, "learning_rate": 4.108118349063306e-07, "loss": 0.0003, "step": 3171 }, { "epoch": 10.94, "learning_rate": 4.081753703795444e-07, "loss": 0.001, "step": 3172 }, { "epoch": 10.94, "learning_rate": 4.05547216854808e-07, "loss": 0.001, "step": 3173 }, { "epoch": 10.94, "learning_rate": 4.0292737660933335e-07, "loss": 0.0008, "step": 3174 }, { "epoch": 10.95, "learning_rate": 4.003158519131245e-07, "loss": 0.0003, "step": 3175 }, { "epoch": 10.95, "learning_rate": 3.9771264502898366e-07, "loss": 0.0014, "step": 3176 }, { "epoch": 10.96, "learning_rate": 3.9511775821250206e-07, "loss": 0.0004, "step": 3177 }, { "epoch": 10.96, "learning_rate": 3.9253119371206684e-07, "loss": 0.0005, "step": 3178 }, { "epoch": 10.96, "learning_rate": 3.8995295376884957e-07, "loss": 0.0007, "step": 3179 }, { "epoch": 10.97, "learning_rate": 3.8738304061681107e-07, "loss": 0.0007, "step": 3180 }, { "epoch": 10.97, "learning_rate": 3.848214564826969e-07, "loss": 0.0008, "step": 3181 }, { "epoch": 10.97, "learning_rate": 3.822682035860381e-07, "loss": 0.0015, "step": 3182 }, { "epoch": 10.98, "learning_rate": 3.7972328413914074e-07, "loss": 0.0005, "step": 3183 }, { "epoch": 10.98, "learning_rate": 3.771867003470975e-07, "loss": 0.0007, "step": 3184 }, { "epoch": 10.98, "learning_rate": 3.746584544077736e-07, "loss": 0.0011, "step": 3185 }, { "epoch": 10.99, "learning_rate": 3.721385485118123e-07, "loss": 0.0017, "step": 3186 }, { "epoch": 10.99, "learning_rate": 3.6962698484262814e-07, "loss": 0.0008, "step": 3187 }, { "epoch": 10.99, "learning_rate": 3.671237655764104e-07, "loss": 0.0006, "step": 3188 }, { "epoch": 11.0, "learning_rate": 3.646288928821151e-07, "loss": 0.0005, "step": 3189 }, { "epoch": 11.0, "learning_rate": 3.6214236892146983e-07, "loss": 0.0006, "step": 3190 }, { "epoch": 11.0, "learning_rate": 3.596641958489633e-07, "loss": 0.0006, "step": 3191 }, { "epoch": 11.01, "learning_rate": 3.571943758118546e-07, "loss": 0.0004, "step": 3192 }, { "epoch": 11.01, "learning_rate": 3.547329109501585e-07, "loss": 0.0002, "step": 3193 }, { "epoch": 11.01, "learning_rate": 3.522798033966579e-07, "loss": 0.0007, "step": 3194 }, { "epoch": 11.02, "learning_rate": 3.498350552768859e-07, "loss": 0.0006, "step": 3195 }, { "epoch": 11.02, "learning_rate": 3.473986687091402e-07, "loss": 0.0004, "step": 3196 }, { "epoch": 11.02, "learning_rate": 3.449706458044666e-07, "loss": 0.0003, "step": 3197 }, { "epoch": 11.03, "learning_rate": 3.4255098866667114e-07, "loss": 0.0005, "step": 3198 }, { "epoch": 11.03, "learning_rate": 3.401396993923045e-07, "loss": 0.0003, "step": 3199 }, { "epoch": 11.03, "learning_rate": 3.377367800706732e-07, "loss": 0.0004, "step": 3200 }, { "epoch": 11.04, "learning_rate": 3.3534223278382405e-07, "loss": 0.0009, "step": 3201 }, { "epoch": 11.04, "learning_rate": 3.329560596065573e-07, "loss": 0.0009, "step": 3202 }, { "epoch": 11.04, "learning_rate": 3.3057826260641136e-07, "loss": 0.0006, "step": 3203 }, { "epoch": 11.05, "learning_rate": 3.282088438436715e-07, "loss": 0.0007, "step": 3204 }, { "epoch": 11.05, "learning_rate": 3.2584780537136206e-07, "loss": 0.0005, "step": 3205 }, { "epoch": 11.06, "learning_rate": 3.2349514923524115e-07, "loss": 0.0012, "step": 3206 }, { "epoch": 11.06, "learning_rate": 3.211508774738137e-07, "loss": 0.0012, "step": 3207 }, { "epoch": 11.06, "learning_rate": 3.188149921183115e-07, "loss": 0.0008, "step": 3208 }, { "epoch": 11.07, "learning_rate": 3.164874951927033e-07, "loss": 0.0012, "step": 3209 }, { "epoch": 11.07, "learning_rate": 3.1416838871368925e-07, "loss": 0.0009, "step": 3210 }, { "epoch": 11.07, "learning_rate": 3.1185767469069874e-07, "loss": 0.0006, "step": 3211 }, { "epoch": 11.08, "learning_rate": 3.0955535512589007e-07, "loss": 0.0004, "step": 3212 }, { "epoch": 11.08, "learning_rate": 3.072614320141487e-07, "loss": 0.0008, "step": 3213 }, { "epoch": 11.08, "learning_rate": 3.049759073430814e-07, "loss": 0.0005, "step": 3214 }, { "epoch": 11.09, "learning_rate": 3.026987830930239e-07, "loss": 0.0002, "step": 3215 }, { "epoch": 11.09, "learning_rate": 3.00430061237027e-07, "loss": 0.0004, "step": 3216 }, { "epoch": 11.09, "learning_rate": 2.9816974374086594e-07, "loss": 0.0006, "step": 3217 }, { "epoch": 11.1, "learning_rate": 2.959178325630296e-07, "loss": 0.0003, "step": 3218 }, { "epoch": 11.1, "learning_rate": 2.936743296547273e-07, "loss": 0.0003, "step": 3219 }, { "epoch": 11.1, "learning_rate": 2.9143923695987955e-07, "loss": 0.0005, "step": 3220 }, { "epoch": 11.11, "learning_rate": 2.8921255641512157e-07, "loss": 0.0007, "step": 3221 }, { "epoch": 11.11, "learning_rate": 2.8699428994980017e-07, "loss": 0.0006, "step": 3222 }, { "epoch": 11.11, "learning_rate": 2.847844394859689e-07, "loss": 0.0005, "step": 3223 }, { "epoch": 11.12, "learning_rate": 2.825830069383917e-07, "loss": 0.0004, "step": 3224 }, { "epoch": 11.12, "learning_rate": 2.8038999421453827e-07, "loss": 0.0004, "step": 3225 }, { "epoch": 11.12, "learning_rate": 2.7820540321458087e-07, "loss": 0.0004, "step": 3226 }, { "epoch": 11.13, "learning_rate": 2.760292358313976e-07, "loss": 0.0002, "step": 3227 }, { "epoch": 11.13, "learning_rate": 2.7386149395056463e-07, "loss": 0.0007, "step": 3228 }, { "epoch": 11.13, "learning_rate": 2.717021794503616e-07, "loss": 0.0007, "step": 3229 }, { "epoch": 11.14, "learning_rate": 2.6955129420176193e-07, "loss": 0.0004, "step": 3230 }, { "epoch": 11.14, "learning_rate": 2.6740884006843826e-07, "loss": 0.0008, "step": 3231 }, { "epoch": 11.14, "learning_rate": 2.6527481890675666e-07, "loss": 0.0006, "step": 3232 }, { "epoch": 11.15, "learning_rate": 2.6314923256577586e-07, "loss": 0.0002, "step": 3233 }, { "epoch": 11.15, "learning_rate": 2.6103208288724815e-07, "loss": 0.0003, "step": 3234 }, { "epoch": 11.16, "learning_rate": 2.589233717056128e-07, "loss": 0.0011, "step": 3235 }, { "epoch": 11.16, "learning_rate": 2.5682310084800154e-07, "loss": 0.0011, "step": 3236 }, { "epoch": 11.16, "learning_rate": 2.547312721342277e-07, "loss": 0.0012, "step": 3237 }, { "epoch": 11.17, "learning_rate": 2.526478873767946e-07, "loss": 0.0002, "step": 3238 }, { "epoch": 11.17, "learning_rate": 2.50572948380885e-07, "loss": 0.0002, "step": 3239 }, { "epoch": 11.17, "learning_rate": 2.4850645694436736e-07, "loss": 0.0006, "step": 3240 }, { "epoch": 11.18, "learning_rate": 2.4644841485778836e-07, "loss": 0.0009, "step": 3241 }, { "epoch": 11.18, "learning_rate": 2.4439882390437264e-07, "loss": 0.0006, "step": 3242 }, { "epoch": 11.18, "learning_rate": 2.423576858600252e-07, "loss": 0.0008, "step": 3243 }, { "epoch": 11.19, "learning_rate": 2.403250024933246e-07, "loss": 0.0004, "step": 3244 }, { "epoch": 11.19, "learning_rate": 2.3830077556552424e-07, "loss": 0.0007, "step": 3245 }, { "epoch": 11.19, "learning_rate": 2.3628500683055222e-07, "loss": 0.0003, "step": 3246 }, { "epoch": 11.2, "learning_rate": 2.3427769803500365e-07, "loss": 0.0003, "step": 3247 }, { "epoch": 11.2, "learning_rate": 2.322788509181484e-07, "loss": 0.0011, "step": 3248 }, { "epoch": 11.2, "learning_rate": 2.3028846721191878e-07, "loss": 0.0008, "step": 3249 }, { "epoch": 11.21, "learning_rate": 2.2830654864092083e-07, "loss": 0.0006, "step": 3250 }, { "epoch": 11.21, "learning_rate": 2.2633309692241978e-07, "loss": 0.0011, "step": 3251 }, { "epoch": 11.21, "learning_rate": 2.2436811376634893e-07, "loss": 0.0004, "step": 3252 }, { "epoch": 11.22, "learning_rate": 2.2241160087529857e-07, "loss": 0.0004, "step": 3253 }, { "epoch": 11.22, "learning_rate": 2.2046355994452596e-07, "loss": 0.0003, "step": 3254 }, { "epoch": 11.22, "learning_rate": 2.1852399266194312e-07, "loss": 0.0017, "step": 3255 }, { "epoch": 11.23, "learning_rate": 2.1659290070812356e-07, "loss": 0.0011, "step": 3256 }, { "epoch": 11.23, "learning_rate": 2.1467028575629322e-07, "loss": 0.0003, "step": 3257 }, { "epoch": 11.23, "learning_rate": 2.1275614947233624e-07, "loss": 0.0003, "step": 3258 }, { "epoch": 11.24, "learning_rate": 2.1085049351478814e-07, "loss": 0.0009, "step": 3259 }, { "epoch": 11.24, "learning_rate": 2.089533195348392e-07, "loss": 0.0005, "step": 3260 }, { "epoch": 11.24, "learning_rate": 2.0706462917632676e-07, "loss": 0.0003, "step": 3261 }, { "epoch": 11.25, "learning_rate": 2.0518442407573946e-07, "loss": 0.0014, "step": 3262 }, { "epoch": 11.25, "learning_rate": 2.0331270586221308e-07, "loss": 0.0008, "step": 3263 }, { "epoch": 11.26, "learning_rate": 2.014494761575314e-07, "loss": 0.0003, "step": 3264 }, { "epoch": 11.26, "learning_rate": 1.9959473657612193e-07, "loss": 0.0007, "step": 3265 }, { "epoch": 11.26, "learning_rate": 1.977484887250547e-07, "loss": 0.0002, "step": 3266 }, { "epoch": 11.27, "learning_rate": 1.9591073420404338e-07, "loss": 0.0003, "step": 3267 }, { "epoch": 11.27, "learning_rate": 1.9408147460544203e-07, "loss": 0.0003, "step": 3268 }, { "epoch": 11.27, "learning_rate": 1.9226071151424608e-07, "loss": 0.0018, "step": 3269 }, { "epoch": 11.28, "learning_rate": 1.9044844650808468e-07, "loss": 0.0006, "step": 3270 }, { "epoch": 11.28, "learning_rate": 1.8864468115722733e-07, "loss": 0.0002, "step": 3271 }, { "epoch": 11.28, "learning_rate": 1.8684941702457604e-07, "loss": 0.0005, "step": 3272 }, { "epoch": 11.29, "learning_rate": 1.8506265566567095e-07, "loss": 0.0006, "step": 3273 }, { "epoch": 11.29, "learning_rate": 1.832843986286803e-07, "loss": 0.0004, "step": 3274 }, { "epoch": 11.29, "learning_rate": 1.8151464745440828e-07, "loss": 0.0004, "step": 3275 }, { "epoch": 11.3, "learning_rate": 1.7975340367628269e-07, "loss": 0.0008, "step": 3276 }, { "epoch": 11.3, "learning_rate": 1.7800066882036615e-07, "loss": 0.0009, "step": 3277 }, { "epoch": 11.3, "learning_rate": 1.7625644440534384e-07, "loss": 0.0002, "step": 3278 }, { "epoch": 11.31, "learning_rate": 1.7452073194253237e-07, "loss": 0.001, "step": 3279 }, { "epoch": 11.31, "learning_rate": 1.7279353293586765e-07, "loss": 0.0004, "step": 3280 }, { "epoch": 11.31, "learning_rate": 1.710748488819114e-07, "loss": 0.0002, "step": 3281 }, { "epoch": 11.32, "learning_rate": 1.6936468126984573e-07, "loss": 0.0009, "step": 3282 }, { "epoch": 11.32, "learning_rate": 1.6766303158147757e-07, "loss": 0.0008, "step": 3283 }, { "epoch": 11.32, "learning_rate": 1.659699012912286e-07, "loss": 0.0003, "step": 3284 }, { "epoch": 11.33, "learning_rate": 1.6428529186614195e-07, "loss": 0.0004, "step": 3285 }, { "epoch": 11.33, "learning_rate": 1.626092047658756e-07, "loss": 0.001, "step": 3286 }, { "epoch": 11.33, "learning_rate": 1.6094164144270453e-07, "loss": 0.0004, "step": 3287 }, { "epoch": 11.34, "learning_rate": 1.5928260334151847e-07, "loss": 0.0004, "step": 3288 }, { "epoch": 11.34, "learning_rate": 1.5763209189981864e-07, "loss": 0.0007, "step": 3289 }, { "epoch": 11.34, "learning_rate": 1.5599010854772002e-07, "loss": 0.0005, "step": 3290 }, { "epoch": 11.35, "learning_rate": 1.543566547079467e-07, "loss": 0.0018, "step": 3291 }, { "epoch": 11.35, "learning_rate": 1.5273173179583322e-07, "loss": 0.0003, "step": 3292 }, { "epoch": 11.36, "learning_rate": 1.5111534121932225e-07, "loss": 0.0005, "step": 3293 }, { "epoch": 11.36, "learning_rate": 1.4950748437896235e-07, "loss": 0.0003, "step": 3294 }, { "epoch": 11.36, "learning_rate": 1.4790816266791018e-07, "loss": 0.0005, "step": 3295 }, { "epoch": 11.37, "learning_rate": 1.463173774719262e-07, "loss": 0.0009, "step": 3296 }, { "epoch": 11.37, "learning_rate": 1.4473513016937223e-07, "loss": 0.0003, "step": 3297 }, { "epoch": 11.37, "learning_rate": 1.4316142213121386e-07, "loss": 0.0002, "step": 3298 }, { "epoch": 11.38, "learning_rate": 1.4159625472101812e-07, "loss": 0.0008, "step": 3299 }, { "epoch": 11.38, "learning_rate": 1.400396292949513e-07, "loss": 0.0002, "step": 3300 }, { "epoch": 11.38, "learning_rate": 1.3849154720177782e-07, "loss": 0.0009, "step": 3301 }, { "epoch": 11.39, "learning_rate": 1.3695200978286028e-07, "loss": 0.0005, "step": 3302 }, { "epoch": 11.39, "learning_rate": 1.3542101837215826e-07, "loss": 0.0004, "step": 3303 }, { "epoch": 11.39, "learning_rate": 1.338985742962251e-07, "loss": 0.0006, "step": 3304 }, { "epoch": 11.4, "learning_rate": 1.323846788742078e-07, "loss": 0.0003, "step": 3305 }, { "epoch": 11.4, "learning_rate": 1.308793334178493e-07, "loss": 0.0005, "step": 3306 }, { "epoch": 11.4, "learning_rate": 1.293825392314807e-07, "loss": 0.0003, "step": 3307 }, { "epoch": 11.41, "learning_rate": 1.2789429761202565e-07, "loss": 0.0004, "step": 3308 }, { "epoch": 11.41, "learning_rate": 1.26414609848996e-07, "loss": 0.0007, "step": 3309 }, { "epoch": 11.41, "learning_rate": 1.2494347722449506e-07, "loss": 0.0004, "step": 3310 }, { "epoch": 11.42, "learning_rate": 1.2348090101320766e-07, "loss": 0.0005, "step": 3311 }, { "epoch": 11.42, "learning_rate": 1.2202688248241113e-07, "loss": 0.0009, "step": 3312 }, { "epoch": 11.42, "learning_rate": 1.205814228919633e-07, "loss": 0.0009, "step": 3313 }, { "epoch": 11.43, "learning_rate": 1.1914452349430782e-07, "loss": 0.0009, "step": 3314 }, { "epoch": 11.43, "learning_rate": 1.1771618553447217e-07, "loss": 0.0009, "step": 3315 }, { "epoch": 11.43, "learning_rate": 1.16296410250063e-07, "loss": 0.0003, "step": 3316 }, { "epoch": 11.44, "learning_rate": 1.1488519887126848e-07, "loss": 0.0008, "step": 3317 }, { "epoch": 11.44, "learning_rate": 1.134825526208605e-07, "loss": 0.0004, "step": 3318 }, { "epoch": 11.44, "learning_rate": 1.1208847271418244e-07, "loss": 0.0006, "step": 3319 }, { "epoch": 11.45, "learning_rate": 1.1070296035916028e-07, "loss": 0.0005, "step": 3320 }, { "epoch": 11.45, "learning_rate": 1.0932601675629595e-07, "loss": 0.0004, "step": 3321 }, { "epoch": 11.46, "learning_rate": 1.0795764309866397e-07, "loss": 0.0011, "step": 3322 }, { "epoch": 11.46, "learning_rate": 1.0659784057191702e-07, "loss": 0.0004, "step": 3323 }, { "epoch": 11.46, "learning_rate": 1.052466103542793e-07, "loss": 0.0007, "step": 3324 }, { "epoch": 11.47, "learning_rate": 1.039039536165476e-07, "loss": 0.0015, "step": 3325 }, { "epoch": 11.47, "learning_rate": 1.0256987152208908e-07, "loss": 0.0008, "step": 3326 }, { "epoch": 11.47, "learning_rate": 1.0124436522684244e-07, "loss": 0.0012, "step": 3327 }, { "epoch": 11.48, "learning_rate": 9.992743587931674e-08, "loss": 0.0013, "step": 3328 }, { "epoch": 11.48, "learning_rate": 9.8619084620587e-08, "loss": 0.0006, "step": 3329 }, { "epoch": 11.48, "learning_rate": 9.731931258429638e-08, "loss": 0.0006, "step": 3330 }, { "epoch": 11.49, "learning_rate": 9.602812089665626e-08, "loss": 0.0002, "step": 3331 }, { "epoch": 11.49, "learning_rate": 9.474551067644167e-08, "loss": 0.0004, "step": 3332 }, { "epoch": 11.49, "learning_rate": 9.347148303499143e-08, "loss": 0.0009, "step": 3333 }, { "epoch": 11.5, "learning_rate": 9.220603907620806e-08, "loss": 0.0006, "step": 3334 }, { "epoch": 11.5, "learning_rate": 9.094917989656005e-08, "loss": 0.0006, "step": 3335 }, { "epoch": 11.5, "learning_rate": 8.970090658507291e-08, "loss": 0.0003, "step": 3336 }, { "epoch": 11.51, "learning_rate": 8.84612202233337e-08, "loss": 0.0006, "step": 3337 }, { "epoch": 11.51, "learning_rate": 8.723012188549318e-08, "loss": 0.001, "step": 3338 }, { "epoch": 11.51, "learning_rate": 8.600761263825475e-08, "loss": 0.0003, "step": 3339 }, { "epoch": 11.52, "learning_rate": 8.479369354088329e-08, "loss": 0.0002, "step": 3340 }, { "epoch": 11.52, "learning_rate": 8.358836564520189e-08, "loss": 0.0002, "step": 3341 }, { "epoch": 11.52, "learning_rate": 8.239162999558403e-08, "loss": 0.0008, "step": 3342 }, { "epoch": 11.53, "learning_rate": 8.120348762896579e-08, "loss": 0.0007, "step": 3343 }, { "epoch": 11.53, "learning_rate": 8.002393957483145e-08, "loss": 0.0008, "step": 3344 }, { "epoch": 11.53, "learning_rate": 7.885298685522235e-08, "loss": 0.0006, "step": 3345 }, { "epoch": 11.54, "learning_rate": 7.769063048472802e-08, "loss": 0.0007, "step": 3346 }, { "epoch": 11.54, "learning_rate": 7.653687147049504e-08, "loss": 0.0003, "step": 3347 }, { "epoch": 11.54, "learning_rate": 7.539171081221597e-08, "loss": 0.0005, "step": 3348 }, { "epoch": 11.55, "learning_rate": 7.425514950213708e-08, "loss": 0.0005, "step": 3349 }, { "epoch": 11.55, "learning_rate": 7.31271885250484e-08, "loss": 0.0003, "step": 3350 }, { "epoch": 11.56, "learning_rate": 7.200782885829482e-08, "loss": 0.0007, "step": 3351 }, { "epoch": 11.56, "learning_rate": 7.089707147176161e-08, "loss": 0.0006, "step": 3352 }, { "epoch": 11.56, "learning_rate": 6.979491732788557e-08, "loss": 0.0018, "step": 3353 }, { "epoch": 11.57, "learning_rate": 6.870136738164612e-08, "loss": 0.0008, "step": 3354 }, { "epoch": 11.57, "learning_rate": 6.761642258056977e-08, "loss": 0.0002, "step": 3355 }, { "epoch": 11.57, "learning_rate": 6.654008386472455e-08, "loss": 0.001, "step": 3356 }, { "epoch": 11.58, "learning_rate": 6.547235216672443e-08, "loss": 0.0002, "step": 3357 }, { "epoch": 11.58, "learning_rate": 6.44132284117216e-08, "loss": 0.0005, "step": 3358 }, { "epoch": 11.58, "learning_rate": 6.336271351741308e-08, "loss": 0.0004, "step": 3359 }, { "epoch": 11.59, "learning_rate": 6.232080839403631e-08, "loss": 0.0002, "step": 3360 }, { "epoch": 11.59, "learning_rate": 6.128751394436694e-08, "loss": 0.0003, "step": 3361 }, { "epoch": 11.59, "learning_rate": 6.02628310637221e-08, "loss": 0.0006, "step": 3362 }, { "epoch": 11.6, "learning_rate": 5.9246760639953824e-08, "loss": 0.0007, "step": 3363 }, { "epoch": 11.6, "learning_rate": 5.823930355345675e-08, "loss": 0.0008, "step": 3364 }, { "epoch": 11.6, "learning_rate": 5.724046067715705e-08, "loss": 0.0003, "step": 3365 }, { "epoch": 11.61, "learning_rate": 5.625023287652021e-08, "loss": 0.0007, "step": 3366 }, { "epoch": 11.61, "learning_rate": 5.526862100954655e-08, "loss": 0.0006, "step": 3367 }, { "epoch": 11.61, "learning_rate": 5.429562592677018e-08, "loss": 0.0005, "step": 3368 }, { "epoch": 11.62, "learning_rate": 5.3331248471258926e-08, "loss": 0.0003, "step": 3369 }, { "epoch": 11.62, "learning_rate": 5.2375489478616593e-08, "loss": 0.0005, "step": 3370 }, { "epoch": 11.62, "learning_rate": 5.142834977697408e-08, "loss": 0.0007, "step": 3371 }, { "epoch": 11.63, "learning_rate": 5.048983018699827e-08, "loss": 0.0004, "step": 3372 }, { "epoch": 11.63, "learning_rate": 4.955993152188643e-08, "loss": 0.0012, "step": 3373 }, { "epoch": 11.63, "learning_rate": 4.863865458736405e-08, "loss": 0.0006, "step": 3374 }, { "epoch": 11.64, "learning_rate": 4.772600018168816e-08, "loss": 0.0004, "step": 3375 }, { "epoch": 11.64, "learning_rate": 4.682196909564396e-08, "loss": 0.0012, "step": 3376 }, { "epoch": 11.64, "learning_rate": 4.592656211254487e-08, "loss": 0.0003, "step": 3377 }, { "epoch": 11.65, "learning_rate": 4.503978000823028e-08, "loss": 0.0002, "step": 3378 }, { "epoch": 11.65, "learning_rate": 4.416162355107001e-08, "loss": 0.0009, "step": 3379 }, { "epoch": 11.66, "learning_rate": 4.329209350195651e-08, "loss": 0.0006, "step": 3380 }, { "epoch": 11.66, "learning_rate": 4.2431190614309334e-08, "loss": 0.0013, "step": 3381 }, { "epoch": 11.66, "learning_rate": 4.1578915634072904e-08, "loss": 0.0009, "step": 3382 }, { "epoch": 11.67, "learning_rate": 4.0735269299715386e-08, "loss": 0.0006, "step": 3383 }, { "epoch": 11.67, "learning_rate": 3.990025234222872e-08, "loss": 0.0008, "step": 3384 }, { "epoch": 11.67, "learning_rate": 3.907386548512748e-08, "loss": 0.0003, "step": 3385 }, { "epoch": 11.68, "learning_rate": 3.825610944445002e-08, "loss": 0.0011, "step": 3386 }, { "epoch": 11.68, "learning_rate": 3.7446984928753984e-08, "loss": 0.0004, "step": 3387 }, { "epoch": 11.68, "learning_rate": 3.6646492639118567e-08, "loss": 0.0007, "step": 3388 }, { "epoch": 11.69, "learning_rate": 3.5854633269146735e-08, "loss": 0.0004, "step": 3389 }, { "epoch": 11.69, "learning_rate": 3.50714075049563e-08, "loss": 0.0007, "step": 3390 }, { "epoch": 11.69, "learning_rate": 3.429681602518886e-08, "loss": 0.0004, "step": 3391 }, { "epoch": 11.7, "learning_rate": 3.353085950099977e-08, "loss": 0.0006, "step": 3392 }, { "epoch": 11.7, "learning_rate": 3.2773538596068134e-08, "loss": 0.0003, "step": 3393 }, { "epoch": 11.7, "learning_rate": 3.2024853966585725e-08, "loss": 0.0002, "step": 3394 }, { "epoch": 11.71, "learning_rate": 3.1284806261264735e-08, "loss": 0.0007, "step": 3395 }, { "epoch": 11.71, "learning_rate": 3.0553396121330015e-08, "loss": 0.0003, "step": 3396 }, { "epoch": 11.71, "learning_rate": 2.9830624180526845e-08, "loss": 0.0004, "step": 3397 }, { "epoch": 11.72, "learning_rate": 2.911649106511316e-08, "loss": 0.0007, "step": 3398 }, { "epoch": 11.72, "learning_rate": 2.8410997393860663e-08, "loss": 0.0003, "step": 3399 }, { "epoch": 11.72, "learning_rate": 2.7714143778058146e-08, "loss": 0.0002, "step": 3400 }, { "epoch": 11.73, "learning_rate": 2.702593082150484e-08, "loss": 0.0004, "step": 3401 }, { "epoch": 11.73, "learning_rate": 2.6346359120514863e-08, "loss": 0.0005, "step": 3402 }, { "epoch": 11.73, "learning_rate": 2.5675429263917197e-08, "loss": 0.0014, "step": 3403 }, { "epoch": 11.74, "learning_rate": 2.5013141833046818e-08, "loss": 0.0004, "step": 3404 }, { "epoch": 11.74, "learning_rate": 2.4359497401758026e-08, "loss": 0.0005, "step": 3405 }, { "epoch": 11.74, "learning_rate": 2.371449653640889e-08, "loss": 0.0004, "step": 3406 }, { "epoch": 11.75, "learning_rate": 2.3078139795874587e-08, "loss": 0.0003, "step": 3407 }, { "epoch": 11.75, "learning_rate": 2.2450427731534052e-08, "loss": 0.0009, "step": 3408 }, { "epoch": 11.76, "learning_rate": 2.1831360887283325e-08, "loss": 0.001, "step": 3409 }, { "epoch": 11.76, "learning_rate": 2.1220939799520003e-08, "loss": 0.0015, "step": 3410 }, { "epoch": 11.76, "learning_rate": 2.061916499715544e-08, "loss": 0.0012, "step": 3411 }, { "epoch": 11.77, "learning_rate": 2.002603700160699e-08, "loss": 0.0016, "step": 3412 }, { "epoch": 11.77, "learning_rate": 1.9441556326802447e-08, "loss": 0.0003, "step": 3413 }, { "epoch": 11.77, "learning_rate": 1.886572347917337e-08, "loss": 0.0009, "step": 3414 }, { "epoch": 11.78, "learning_rate": 1.829853895766176e-08, "loss": 0.0003, "step": 3415 }, { "epoch": 11.78, "learning_rate": 1.7740003253712278e-08, "loss": 0.0004, "step": 3416 }, { "epoch": 11.78, "learning_rate": 1.7190116851280024e-08, "loss": 0.0002, "step": 3417 }, { "epoch": 11.79, "learning_rate": 1.664888022682165e-08, "loss": 0.0008, "step": 3418 }, { "epoch": 11.79, "learning_rate": 1.6116293849302024e-08, "loss": 0.0003, "step": 3419 }, { "epoch": 11.79, "learning_rate": 1.5592358180189782e-08, "loss": 0.0008, "step": 3420 }, { "epoch": 11.8, "learning_rate": 1.5077073673458453e-08, "loss": 0.0003, "step": 3421 }, { "epoch": 11.8, "learning_rate": 1.4570440775584226e-08, "loss": 0.0006, "step": 3422 }, { "epoch": 11.8, "learning_rate": 1.4072459925548176e-08, "loss": 0.0005, "step": 3423 }, { "epoch": 11.81, "learning_rate": 1.358313155483404e-08, "loss": 0.0004, "step": 3424 }, { "epoch": 11.81, "learning_rate": 1.3102456087430437e-08, "loss": 0.0015, "step": 3425 }, { "epoch": 11.81, "learning_rate": 1.2630433939825326e-08, "loss": 0.0004, "step": 3426 }, { "epoch": 11.82, "learning_rate": 1.2167065521010436e-08, "loss": 0.0015, "step": 3427 }, { "epoch": 11.82, "learning_rate": 1.1712351232480157e-08, "loss": 0.0003, "step": 3428 }, { "epoch": 11.82, "learning_rate": 1.126629146822933e-08, "loss": 0.0003, "step": 3429 }, { "epoch": 11.83, "learning_rate": 1.0828886614754342e-08, "loss": 0.0002, "step": 3430 }, { "epoch": 11.83, "learning_rate": 1.0400137051052028e-08, "loss": 0.0005, "step": 3431 }, { "epoch": 11.83, "learning_rate": 9.980043148619668e-09, "loss": 0.0004, "step": 3432 }, { "epoch": 11.84, "learning_rate": 9.568605271454978e-09, "loss": 0.0004, "step": 3433 }, { "epoch": 11.84, "learning_rate": 9.165823776055016e-09, "loss": 0.001, "step": 3434 }, { "epoch": 11.84, "learning_rate": 8.771699011416169e-09, "loss": 0.001, "step": 3435 }, { "epoch": 11.85, "learning_rate": 8.386231319037485e-09, "loss": 0.0002, "step": 3436 }, { "epoch": 11.85, "learning_rate": 8.009421032910692e-09, "loss": 0.0003, "step": 3437 }, { "epoch": 11.86, "learning_rate": 7.641268479531283e-09, "loss": 0.0002, "step": 3438 }, { "epoch": 11.86, "learning_rate": 7.28177397789187e-09, "loss": 0.0011, "step": 3439 }, { "epoch": 11.86, "learning_rate": 6.930937839481067e-09, "loss": 0.0014, "step": 3440 }, { "epoch": 11.87, "learning_rate": 6.588760368287928e-09, "loss": 0.0014, "step": 3441 }, { "epoch": 11.87, "learning_rate": 6.255241860798622e-09, "loss": 0.0007, "step": 3442 }, { "epoch": 11.87, "learning_rate": 5.930382605995322e-09, "loss": 0.0006, "step": 3443 }, { "epoch": 11.88, "learning_rate": 5.614182885357311e-09, "loss": 0.0003, "step": 3444 }, { "epoch": 11.88, "learning_rate": 5.306642972862097e-09, "loss": 0.0007, "step": 3445 }, { "epoch": 11.88, "learning_rate": 5.00776313498319e-09, "loss": 0.0002, "step": 3446 }, { "epoch": 11.89, "learning_rate": 4.717543630688992e-09, "loss": 0.0005, "step": 3447 }, { "epoch": 11.89, "learning_rate": 4.435984711446128e-09, "loss": 0.0004, "step": 3448 }, { "epoch": 11.89, "learning_rate": 4.1630866212161166e-09, "loss": 0.0002, "step": 3449 }, { "epoch": 11.9, "learning_rate": 3.898849596456477e-09, "loss": 0.0012, "step": 3450 }, { "epoch": 11.9, "learning_rate": 3.643273866119623e-09, "loss": 0.0004, "step": 3451 }, { "epoch": 11.9, "learning_rate": 3.3963596516528586e-09, "loss": 0.0015, "step": 3452 }, { "epoch": 11.91, "learning_rate": 3.1581071670006013e-09, "loss": 0.0015, "step": 3453 }, { "epoch": 11.91, "learning_rate": 2.9285166185999414e-09, "loss": 0.0012, "step": 3454 }, { "epoch": 11.91, "learning_rate": 2.7075882053828605e-09, "loss": 0.0005, "step": 3455 }, { "epoch": 11.92, "learning_rate": 2.495322118778454e-09, "loss": 0.0003, "step": 3456 }, { "epoch": 11.92, "learning_rate": 2.291718542707377e-09, "loss": 0.0006, "step": 3457 }, { "epoch": 11.92, "learning_rate": 2.0967776535851802e-09, "loss": 0.0006, "step": 3458 }, { "epoch": 11.93, "learning_rate": 1.910499620322304e-09, "loss": 0.0003, "step": 3459 }, { "epoch": 11.93, "learning_rate": 1.7328846043229707e-09, "loss": 0.0005, "step": 3460 }, { "epoch": 11.93, "learning_rate": 1.5639327594829667e-09, "loss": 0.001, "step": 3461 }, { "epoch": 11.94, "learning_rate": 1.4036442321962995e-09, "loss": 0.0003, "step": 3462 }, { "epoch": 11.94, "learning_rate": 1.2520191613452082e-09, "loss": 0.0004, "step": 3463 }, { "epoch": 11.94, "learning_rate": 1.1090576783079343e-09, "loss": 0.0002, "step": 3464 }, { "epoch": 11.95, "learning_rate": 9.74759906957612e-10, "loss": 0.0005, "step": 3465 }, { "epoch": 11.95, "learning_rate": 8.491259636578264e-10, "loss": 0.0007, "step": 3466 }, { "epoch": 11.96, "learning_rate": 7.321559572670556e-10, "loss": 0.0011, "step": 3467 }, { "epoch": 11.96, "learning_rate": 6.238499891353389e-10, "loss": 0.0014, "step": 3468 }, { "epoch": 11.96, "learning_rate": 5.242081531053877e-10, "loss": 0.0004, "step": 3469 }, { "epoch": 11.97, "learning_rate": 4.332305355159161e-10, "loss": 0.0003, "step": 3470 }, { "epoch": 11.97, "learning_rate": 3.509172151938689e-10, "loss": 0.0005, "step": 3471 }, { "epoch": 11.97, "learning_rate": 2.772682634610835e-10, "loss": 0.001, "step": 3472 }, { "epoch": 11.98, "learning_rate": 2.1228374413428955e-10, "loss": 0.0014, "step": 3473 }, { "epoch": 11.98, "learning_rate": 1.559637135173375e-10, "loss": 0.0004, "step": 3474 }, { "epoch": 11.98, "learning_rate": 1.0830822041230093e-10, "loss": 0.0003, "step": 3475 }, { "epoch": 11.99, "learning_rate": 6.931730610948429e-11, "loss": 0.0014, "step": 3476 }, { "epoch": 11.99, "learning_rate": 3.899100439408443e-11, "loss": 0.0009, "step": 3477 }, { "epoch": 11.99, "learning_rate": 1.7329341542859922e-11, "loss": 0.0005, "step": 3478 }, { "epoch": 12.0, "learning_rate": 4.332336324130993e-12, "loss": 0.0004, "step": 3479 }, { "epoch": 12.0, "learning_rate": 0.0, "loss": 0.0007, "step": 3480 }, { "epoch": 12.0, "step": 3480, "total_flos": 387889000611840.0, "train_loss": 0.22196650955858327, "train_runtime": 26294.1127, "train_samples_per_second": 33.801, "train_steps_per_second": 0.132 } ], "max_steps": 3480, "num_train_epochs": 12, "total_flos": 387889000611840.0, "trial_name": null, "trial_params": null }