[ { "current_steps": 0, "loss": 0.6046, "learning_rate": 1e-08, "epoch": 0.008928571428571428 }, { "current_steps": 1, "loss": 0.6431, "learning_rate": 2e-08, "epoch": 0.017857142857142856 }, { "current_steps": 2, "loss": 0.6447, "learning_rate": 3e-08, "epoch": 0.026785714285714284 }, { "current_steps": 3, "loss": 0.7972, "learning_rate": 4e-08, "epoch": 0.03571428571428571 }, { "current_steps": 4, "loss": 0.6911, "learning_rate": 5e-08, "epoch": 0.044642857142857144 }, { "current_steps": 5, "loss": 0.8546, "learning_rate": 6e-08, "epoch": 0.05357142857142857 }, { "current_steps": 6, "loss": 0.7624, "learning_rate": 6e-08, "epoch": 0.0625 }, { "current_steps": 7, "loss": 0.6565, "learning_rate": 7e-08, "epoch": 0.07142857142857142 }, { "current_steps": 8, "loss": 0.6789, "learning_rate": 8e-08, "epoch": 0.08035714285714286 }, { "current_steps": 9, "loss": 0.8562, "learning_rate": 8e-08, "epoch": 0.08928571428571429 }, { "current_steps": 10, "loss": 0.8084, "learning_rate": 9e-08, "epoch": 0.09821428571428571 }, { "current_steps": 11, "loss": 0.7024, "learning_rate": 1e-07, "epoch": 0.10714285714285714 }, { "current_steps": 12, "loss": 0.7454, "learning_rate": 1.0999999999999999e-07, "epoch": 0.11607142857142858 }, { "current_steps": 13, "loss": 0.5896, "learning_rate": 1.2e-07, "epoch": 0.125 }, { "current_steps": 14, "loss": 1.1716, "learning_rate": 1.3e-07, "epoch": 0.13392857142857142 }, { "current_steps": 15, "loss": 0.8561, "learning_rate": 1.4e-07, "epoch": 0.14285714285714285 }, { "current_steps": 16, "loss": 0.9048, "learning_rate": 1.5e-07, "epoch": 0.15178571428571427 }, { "current_steps": 17, "loss": 0.6079, "learning_rate": 1.6e-07, "epoch": 0.16071428571428573 }, { "current_steps": 18, "loss": 0.9004, "learning_rate": 1.7000000000000001e-07, "epoch": 0.16964285714285715 }, { "current_steps": 19, "loss": 0.5512, "learning_rate": 1.8e-07, "epoch": 0.17857142857142858 }, { "current_steps": 20, "loss": 0.7782, "learning_rate": 1.8999999999999998e-07, "epoch": 0.1875 }, { "current_steps": 21, "loss": 0.7905, "learning_rate": 2e-07, "epoch": 0.19642857142857142 }, { "current_steps": 22, "loss": 0.6049, "learning_rate": 2.0999999999999997e-07, "epoch": 0.20535714285714285 }, { "current_steps": 23, "loss": 0.685, "learning_rate": 2.1999999999999998e-07, "epoch": 0.21428571428571427 }, { "current_steps": 24, "loss": 0.8171, "learning_rate": 2.3e-07, "epoch": 0.22321428571428573 }, { "current_steps": 25, "loss": 0.8018, "learning_rate": 2.4e-07, "epoch": 0.23214285714285715 }, { "current_steps": 26, "loss": 0.4959, "learning_rate": 2.5e-07, "epoch": 0.24107142857142858 }, { "current_steps": 27, "loss": 0.6348, "learning_rate": 2.6e-07, "epoch": 0.25 }, { "current_steps": 28, "loss": 0.8005, "learning_rate": 2.7e-07, "epoch": 0.25892857142857145 }, { "current_steps": 29, "loss": 0.6777, "learning_rate": 2.8e-07, "epoch": 0.26785714285714285 }, { "current_steps": 30, "loss": 0.9042, "learning_rate": 2.9e-07, "epoch": 0.2767857142857143 }, { "current_steps": 31, "loss": 0.6491, "learning_rate": 3e-07, "epoch": 0.2857142857142857 }, { "current_steps": 32, "loss": 1.0966, "learning_rate": 3.1e-07, "epoch": 0.29464285714285715 }, { "current_steps": 33, "loss": 0.7451, "learning_rate": 3.2e-07, "epoch": 0.30357142857142855 }, { "current_steps": 34, "loss": 1.1446, "learning_rate": 3.2e-07, "epoch": 0.3125 }, { "current_steps": 35, "loss": 0.7644, "learning_rate": 3.3e-07, "epoch": 0.32142857142857145 }, { "current_steps": 36, "loss": 0.7742, "learning_rate": 3.4000000000000003e-07, "epoch": 0.33035714285714285 }, { "current_steps": 37, "loss": 0.8247, "learning_rate": 3.5e-07, "epoch": 0.3392857142857143 }, { "current_steps": 38, "loss": 0.8667, "learning_rate": 3.6e-07, "epoch": 0.3482142857142857 }, { "current_steps": 39, "loss": 0.8309, "learning_rate": 3.7e-07, "epoch": 0.35714285714285715 }, { "current_steps": 40, "loss": 0.5913, "learning_rate": 3.7999999999999996e-07, "epoch": 0.36607142857142855 }, { "current_steps": 41, "loss": 0.5562, "learning_rate": 3.8999999999999997e-07, "epoch": 0.375 }, { "current_steps": 42, "loss": 1.6276, "learning_rate": 4e-07, "epoch": 0.38392857142857145 }, { "current_steps": 43, "loss": 0.682, "learning_rate": 4.0999999999999994e-07, "epoch": 0.39285714285714285 }, { "current_steps": 44, "loss": 0.8022, "learning_rate": 4.1999999999999995e-07, "epoch": 0.4017857142857143 }, { "current_steps": 45, "loss": 0.6702, "learning_rate": 4.2999999999999996e-07, "epoch": 0.4107142857142857 }, { "current_steps": 46, "loss": 0.6993, "learning_rate": 4.3999999999999997e-07, "epoch": 0.41964285714285715 }, { "current_steps": 47, "loss": 0.9685, "learning_rate": 4.5e-07, "epoch": 0.42857142857142855 }, { "current_steps": 48, "loss": 0.6637, "learning_rate": 4.6e-07, "epoch": 0.4375 }, { "current_steps": 49, "loss": 0.908, "learning_rate": 4.6999999999999995e-07, "epoch": 0.44642857142857145 }, { "current_steps": 50, "loss": 0.8683, "learning_rate": 4.8e-07, "epoch": 0.45535714285714285 }, { "current_steps": 51, "loss": 0.9243, "learning_rate": 4.9e-07, "epoch": 0.4642857142857143 }, { "current_steps": 52, "loss": 0.7933, "learning_rate": 5e-07, "epoch": 0.4732142857142857 }, { "current_steps": 53, "loss": 0.5856, "learning_rate": 5.1e-07, "epoch": 0.48214285714285715 }, { "current_steps": 54, "loss": 0.7097, "learning_rate": 5.2e-07, "epoch": 0.49107142857142855 }, { "current_steps": 55, "loss": 0.6476, "learning_rate": 5.3e-07, "epoch": 0.5 }, { "current_steps": 56, "loss": 0.8212, "learning_rate": 5.4e-07, "epoch": 0.5089285714285714 }, { "current_steps": 57, "loss": 0.7932, "learning_rate": 5.5e-07, "epoch": 0.5178571428571429 }, { "current_steps": 58, "loss": 0.8155, "learning_rate": 5.6e-07, "epoch": 0.5267857142857143 }, { "current_steps": 59, "loss": 0.5644, "learning_rate": 5.699999999999999e-07, "epoch": 0.5357142857142857 }, { "current_steps": 60, "loss": 0.8935, "learning_rate": 5.8e-07, "epoch": 0.5446428571428571 }, { "current_steps": 61, "loss": 0.6935, "learning_rate": 5.9e-07, "epoch": 0.5535714285714286 }, { "current_steps": 62, "loss": 0.6186, "learning_rate": 6e-07, "epoch": 0.5625 }, { "current_steps": 63, "loss": 0.7528, "learning_rate": 6.1e-07, "epoch": 0.5714285714285714 }, { "current_steps": 64, "loss": 0.7043, "learning_rate": 6.2e-07, "epoch": 0.5803571428571429 }, { "current_steps": 65, "loss": 0.5926, "learning_rate": 6.3e-07, "epoch": 0.5892857142857143 }, { "current_steps": 66, "loss": 0.7927, "learning_rate": 6.4e-07, "epoch": 0.5982142857142857 }, { "current_steps": 67, "loss": 0.5625, "learning_rate": 6.5e-07, "epoch": 0.6071428571428571 }, { "current_steps": 68, "loss": 0.707, "learning_rate": 6.6e-07, "epoch": 0.6160714285714286 }, { "current_steps": 69, "loss": 0.7023, "learning_rate": 6.7e-07, "epoch": 0.625 }, { "current_steps": 70, "loss": 0.586, "learning_rate": 6.800000000000001e-07, "epoch": 0.6339285714285714 }, { "current_steps": 71, "loss": 0.5741, "learning_rate": 6.9e-07, "epoch": 0.6428571428571429 }, { "current_steps": 72, "loss": 1.086, "learning_rate": 7e-07, "epoch": 0.6517857142857143 }, { "current_steps": 73, "loss": 0.6381, "learning_rate": 7.1e-07, "epoch": 0.6607142857142857 }, { "current_steps": 74, "loss": 0.7509, "learning_rate": 7.2e-07, "epoch": 0.6696428571428571 }, { "current_steps": 75, "loss": 0.8276, "learning_rate": 7.3e-07, "epoch": 0.6785714285714286 }, { "current_steps": 76, "loss": 0.7623, "learning_rate": 7.4e-07, "epoch": 0.6875 }, { "current_steps": 77, "loss": 0.9499, "learning_rate": 7.5e-07, "epoch": 0.6964285714285714 }, { "current_steps": 78, "loss": 0.8563, "learning_rate": 7.599999999999999e-07, "epoch": 0.7053571428571429 }, { "current_steps": 79, "loss": 0.6512, "learning_rate": 7.699999999999999e-07, "epoch": 0.7142857142857143 }, { "current_steps": 80, "loss": 0.843, "learning_rate": 7.799999999999999e-07, "epoch": 0.7232142857142857 }, { "current_steps": 81, "loss": 0.7272, "learning_rate": 7.9e-07, "epoch": 0.7321428571428571 }, { "current_steps": 82, "loss": 0.5161, "learning_rate": 8e-07, "epoch": 0.7410714285714286 }, { "current_steps": 83, "loss": 0.8293, "learning_rate": 8.1e-07, "epoch": 0.75 }, { "current_steps": 84, "loss": 0.8704, "learning_rate": 8.199999999999999e-07, "epoch": 0.7589285714285714 }, { "current_steps": 85, "loss": 0.7255, "learning_rate": 8.299999999999999e-07, "epoch": 0.7678571428571429 }, { "current_steps": 86, "loss": 0.6252, "learning_rate": 8.399999999999999e-07, "epoch": 0.7767857142857143 }, { "current_steps": 87, "loss": 0.8116, "learning_rate": 8.499999999999999e-07, "epoch": 0.7857142857142857 }, { "current_steps": 88, "loss": 0.7703, "learning_rate": 8.599999999999999e-07, "epoch": 0.7946428571428571 }, { "current_steps": 89, "loss": 0.6496, "learning_rate": 8.699999999999999e-07, "epoch": 0.8035714285714286 }, { "current_steps": 90, "loss": 0.8585, "learning_rate": 8.799999999999999e-07, "epoch": 0.8125 }, { "current_steps": 91, "loss": 0.905, "learning_rate": 8.9e-07, "epoch": 0.8214285714285714 }, { "current_steps": 92, "loss": 0.9139, "learning_rate": 9e-07, "epoch": 0.8303571428571429 }, { "current_steps": 93, "loss": 0.9925, "learning_rate": 9.1e-07, "epoch": 0.8392857142857143 }, { "current_steps": 94, "loss": 0.7344, "learning_rate": 9.2e-07, "epoch": 0.8482142857142857 }, { "current_steps": 95, "loss": 0.7477, "learning_rate": 9.3e-07, "epoch": 0.8571428571428571 }, { "current_steps": 96, "loss": 0.671, "learning_rate": 9.399999999999999e-07, "epoch": 0.8660714285714286 }, { "current_steps": 97, "loss": 0.9654, "learning_rate": 9.499999999999999e-07, "epoch": 0.875 }, { "current_steps": 98, "loss": 0.6788, "learning_rate": 9.6e-07, "epoch": 0.8839285714285714 }, { "current_steps": 99, "loss": 0.764, "learning_rate": 9.7e-07, "epoch": 0.8928571428571429 }, { "current_steps": 100, "loss": 0.7536, "learning_rate": 9.8e-07, "epoch": 0.9017857142857143 }, { "current_steps": 101, "loss": 0.6409, "learning_rate": 9.9e-07, "epoch": 0.9107142857142857 }, { "current_steps": 102, "loss": 0.904, "learning_rate": 1e-06, "epoch": 0.9196428571428571 }, { "current_steps": 103, "loss": 0.7079, "learning_rate": 9.978260869565217e-07, "epoch": 0.9285714285714286 }, { "current_steps": 104, "loss": 0.748, "learning_rate": 9.956521739130434e-07, "epoch": 0.9375 }, { "current_steps": 105, "loss": 0.7228, "learning_rate": 9.934782608695653e-07, "epoch": 0.9464285714285714 }, { "current_steps": 106, "loss": 0.722, "learning_rate": 9.91304347826087e-07, "epoch": 0.9553571428571429 }, { "current_steps": 107, "loss": 0.8011, "learning_rate": 9.891304347826085e-07, "epoch": 0.9642857142857143 }, { "current_steps": 108, "loss": 0.8125, "learning_rate": 9.869565217391304e-07, "epoch": 0.9732142857142857 }, { "current_steps": 109, "loss": 0.8091, "learning_rate": 9.847826086956522e-07, "epoch": 0.9821428571428571 }, { "current_steps": 110, "loss": 0.9399, "learning_rate": 9.826086956521739e-07, "epoch": 0.9910714285714286 }, { "current_steps": 111, "loss": 1.0917, "learning_rate": 9.804347826086956e-07, "epoch": 1.0 }, { "current_steps": 112, "loss": 0.9014, "learning_rate": 9.782608695652173e-07, "epoch": 1.0089285714285714 }, { "current_steps": 113, "loss": 0.873, "learning_rate": 9.782608695652173e-07, "epoch": 1.0178571428571428 }, { "current_steps": 114, "loss": 0.7153, "learning_rate": 9.76086956521739e-07, "epoch": 1.0267857142857142 }, { "current_steps": 115, "loss": 0.8828, "learning_rate": 9.73913043478261e-07, "epoch": 1.0357142857142858 }, { "current_steps": 116, "loss": 1.0329, "learning_rate": 9.717391304347827e-07, "epoch": 1.0446428571428572 }, { "current_steps": 117, "loss": 1.057, "learning_rate": 9.695652173913042e-07, "epoch": 1.0535714285714286 }, { "current_steps": 118, "loss": 0.8047, "learning_rate": 9.67391304347826e-07, "epoch": 1.0625 }, { "current_steps": 119, "loss": 0.7098, "learning_rate": 9.652173913043478e-07, "epoch": 1.0714285714285714 }, { "current_steps": 120, "loss": 1.094, "learning_rate": 9.630434782608695e-07, "epoch": 1.0803571428571428 }, { "current_steps": 121, "loss": 0.7521, "learning_rate": 9.608695652173912e-07, "epoch": 1.0892857142857142 }, { "current_steps": 122, "loss": 0.9738, "learning_rate": 9.58695652173913e-07, "epoch": 1.0982142857142858 }, { "current_steps": 123, "loss": 0.5577, "learning_rate": 9.565217391304349e-07, "epoch": 1.1071428571428572 }, { "current_steps": 124, "loss": 1.046, "learning_rate": 9.543478260869566e-07, "epoch": 1.1160714285714286 }, { "current_steps": 125, "loss": 0.597, "learning_rate": 9.521739130434783e-07, "epoch": 1.125 }, { "current_steps": 126, "loss": 0.7996, "learning_rate": 9.499999999999999e-07, "epoch": 1.1339285714285714 }, { "current_steps": 127, "loss": 0.9885, "learning_rate": 9.478260869565216e-07, "epoch": 1.1428571428571428 }, { "current_steps": 128, "loss": 0.6274, "learning_rate": 9.456521739130434e-07, "epoch": 1.1517857142857142 }, { "current_steps": 129, "loss": 0.8557, "learning_rate": 9.434782608695652e-07, "epoch": 1.1607142857142858 }, { "current_steps": 130, "loss": 0.702, "learning_rate": 9.41304347826087e-07, "epoch": 1.1696428571428572 }, { "current_steps": 131, "loss": 0.6905, "learning_rate": 9.391304347826087e-07, "epoch": 1.1785714285714286 }, { "current_steps": 132, "loss": 0.5707, "learning_rate": 9.369565217391304e-07, "epoch": 1.1875 }, { "current_steps": 133, "loss": 0.6121, "learning_rate": 9.347826086956522e-07, "epoch": 1.1964285714285714 }, { "current_steps": 134, "loss": 0.8348, "learning_rate": 9.326086956521738e-07, "epoch": 1.2053571428571428 }, { "current_steps": 135, "loss": 0.8768, "learning_rate": 9.304347826086955e-07, "epoch": 1.2142857142857142 }, { "current_steps": 136, "loss": 0.5648, "learning_rate": 9.282608695652174e-07, "epoch": 1.2232142857142858 }, { "current_steps": 137, "loss": 0.6316, "learning_rate": 9.260869565217391e-07, "epoch": 1.2321428571428572 }, { "current_steps": 138, "loss": 1.1728, "learning_rate": 9.239130434782608e-07, "epoch": 1.2410714285714286 }, { "current_steps": 139, "loss": 0.7299, "learning_rate": 9.217391304347826e-07, "epoch": 1.25 }, { "current_steps": 140, "loss": 0.6284, "learning_rate": 9.195652173913043e-07, "epoch": 1.2589285714285714 }, { "current_steps": 141, "loss": 0.6366, "learning_rate": 9.17391304347826e-07, "epoch": 1.2678571428571428 }, { "current_steps": 142, "loss": 0.7357, "learning_rate": 9.152173913043479e-07, "epoch": 1.2767857142857144 }, { "current_steps": 143, "loss": 0.8618, "learning_rate": 9.130434782608695e-07, "epoch": 1.2857142857142856 }, { "current_steps": 144, "loss": 0.6803, "learning_rate": 9.108695652173912e-07, "epoch": 1.2946428571428572 }, { "current_steps": 145, "loss": 0.8093, "learning_rate": 9.08695652173913e-07, "epoch": 1.3035714285714286 }, { "current_steps": 146, "loss": 0.6808, "learning_rate": 9.065217391304347e-07, "epoch": 1.3125 }, { "current_steps": 147, "loss": 0.7173, "learning_rate": 9.043478260869564e-07, "epoch": 1.3214285714285714 }, { "current_steps": 148, "loss": 0.6964, "learning_rate": 9.021739130434782e-07, "epoch": 1.3303571428571428 }, { "current_steps": 149, "loss": 0.5458, "learning_rate": 9e-07, "epoch": 1.3392857142857144 }, { "current_steps": 150, "loss": 0.5362, "learning_rate": 8.978260869565218e-07, "epoch": 1.3482142857142856 }, { "current_steps": 151, "loss": 0.7248, "learning_rate": 8.956521739130435e-07, "epoch": 1.3571428571428572 }, { "current_steps": 152, "loss": 0.9701, "learning_rate": 8.934782608695651e-07, "epoch": 1.3660714285714286 }, { "current_steps": 153, "loss": 0.6072, "learning_rate": 8.913043478260869e-07, "epoch": 1.375 }, { "current_steps": 154, "loss": 0.8135, "learning_rate": 8.891304347826086e-07, "epoch": 1.3839285714285714 }, { "current_steps": 155, "loss": 0.6519, "learning_rate": 8.869565217391303e-07, "epoch": 1.3928571428571428 }, { "current_steps": 156, "loss": 0.7911, "learning_rate": 8.847826086956522e-07, "epoch": 1.4017857142857144 }, { "current_steps": 157, "loss": 0.7084, "learning_rate": 8.826086956521739e-07, "epoch": 1.4107142857142856 }, { "current_steps": 158, "loss": 0.6062, "learning_rate": 8.804347826086956e-07, "epoch": 1.4196428571428572 }, { "current_steps": 159, "loss": 0.5372, "learning_rate": 8.782608695652174e-07, "epoch": 1.4285714285714286 }, { "current_steps": 160, "loss": 0.7001, "learning_rate": 8.760869565217391e-07, "epoch": 1.4375 }, { "current_steps": 161, "loss": 0.628, "learning_rate": 8.739130434782607e-07, "epoch": 1.4464285714285714 }, { "current_steps": 162, "loss": 0.6766, "learning_rate": 8.717391304347826e-07, "epoch": 1.4553571428571428 }, { "current_steps": 163, "loss": 0.7406, "learning_rate": 8.695652173913043e-07, "epoch": 1.4642857142857144 }, { "current_steps": 164, "loss": 0.7032, "learning_rate": 8.67391304347826e-07, "epoch": 1.4732142857142856 }, { "current_steps": 165, "loss": 0.8338, "learning_rate": 8.652173913043478e-07, "epoch": 1.4821428571428572 }, { "current_steps": 166, "loss": 0.6067, "learning_rate": 8.630434782608695e-07, "epoch": 1.4910714285714286 }, { "current_steps": 167, "loss": 0.6988, "learning_rate": 8.608695652173913e-07, "epoch": 1.5 }, { "current_steps": 168, "loss": 0.6294, "learning_rate": 8.586956521739131e-07, "epoch": 1.5089285714285714 }, { "current_steps": 169, "loss": 0.7358, "learning_rate": 8.565217391304348e-07, "epoch": 1.5178571428571428 }, { "current_steps": 170, "loss": 0.7709, "learning_rate": 8.543478260869565e-07, "epoch": 1.5267857142857144 }, { "current_steps": 171, "loss": 0.8913, "learning_rate": 8.521739130434782e-07, "epoch": 1.5357142857142856 }, { "current_steps": 172, "loss": 0.697, "learning_rate": 8.499999999999999e-07, "epoch": 1.5446428571428572 }, { "current_steps": 173, "loss": 0.7902, "learning_rate": 8.478260869565217e-07, "epoch": 1.5535714285714286 }, { "current_steps": 174, "loss": 0.7858, "learning_rate": 8.456521739130434e-07, "epoch": 1.5625 }, { "current_steps": 175, "loss": 0.8903, "learning_rate": 8.434782608695652e-07, "epoch": 1.5714285714285714 }, { "current_steps": 176, "loss": 0.8324, "learning_rate": 8.41304347826087e-07, "epoch": 1.5803571428571428 }, { "current_steps": 177, "loss": 0.7323, "learning_rate": 8.391304347826087e-07, "epoch": 1.5892857142857144 }, { "current_steps": 178, "loss": 0.7527, "learning_rate": 8.369565217391304e-07, "epoch": 1.5982142857142856 }, { "current_steps": 179, "loss": 0.8336, "learning_rate": 8.347826086956521e-07, "epoch": 1.6071428571428572 }, { "current_steps": 180, "loss": 0.7886, "learning_rate": 8.326086956521738e-07, "epoch": 1.6160714285714286 }, { "current_steps": 181, "loss": 0.7455, "learning_rate": 8.304347826086955e-07, "epoch": 1.625 }, { "current_steps": 182, "loss": 0.7702, "learning_rate": 8.282608695652174e-07, "epoch": 1.6339285714285714 }, { "current_steps": 183, "loss": 0.6935, "learning_rate": 8.260869565217391e-07, "epoch": 1.6428571428571428 }, { "current_steps": 184, "loss": 0.6778, "learning_rate": 8.239130434782609e-07, "epoch": 1.6517857142857144 }, { "current_steps": 185, "loss": 0.7623, "learning_rate": 8.217391304347826e-07, "epoch": 1.6607142857142856 }, { "current_steps": 186, "loss": 0.8068, "learning_rate": 8.195652173913043e-07, "epoch": 1.6696428571428572 }, { "current_steps": 187, "loss": 0.6384, "learning_rate": 8.173913043478261e-07, "epoch": 1.6785714285714286 }, { "current_steps": 188, "loss": 0.9876, "learning_rate": 8.152173913043478e-07, "epoch": 1.6875 }, { "current_steps": 189, "loss": 0.5316, "learning_rate": 8.130434782608695e-07, "epoch": 1.6964285714285714 }, { "current_steps": 190, "loss": 0.6117, "learning_rate": 8.108695652173913e-07, "epoch": 1.7053571428571428 }, { "current_steps": 191, "loss": 0.5897, "learning_rate": 8.08695652173913e-07, "epoch": 1.7142857142857144 }, { "current_steps": 192, "loss": 0.7045, "learning_rate": 8.065217391304347e-07, "epoch": 1.7232142857142856 }, { "current_steps": 193, "loss": 0.7491, "learning_rate": 8.043478260869565e-07, "epoch": 1.7321428571428572 }, { "current_steps": 194, "loss": 0.8067, "learning_rate": 8.021739130434782e-07, "epoch": 1.7410714285714286 }, { "current_steps": 195, "loss": 0.9085, "learning_rate": 8e-07, "epoch": 1.75 }, { "current_steps": 196, "loss": 0.7977, "learning_rate": 7.978260869565217e-07, "epoch": 1.7589285714285714 }, { "current_steps": 197, "loss": 0.7509, "learning_rate": 7.956521739130434e-07, "epoch": 1.7678571428571428 }, { "current_steps": 198, "loss": 0.7048, "learning_rate": 7.934782608695651e-07, "epoch": 1.7767857142857144 }, { "current_steps": 199, "loss": 0.6452, "learning_rate": 7.913043478260869e-07, "epoch": 1.7857142857142856 }, { "current_steps": 200, "loss": 0.7265, "learning_rate": 7.891304347826086e-07, "epoch": 1.7946428571428572 }, { "current_steps": 201, "loss": 0.7936, "learning_rate": 7.869565217391305e-07, "epoch": 1.8035714285714286 }, { "current_steps": 202, "loss": 0.7336, "learning_rate": 7.847826086956522e-07, "epoch": 1.8125 }, { "current_steps": 203, "loss": 0.6462, "learning_rate": 7.826086956521739e-07, "epoch": 1.8214285714285714 }, { "current_steps": 204, "loss": 0.579, "learning_rate": 7.804347826086957e-07, "epoch": 1.8303571428571428 }, { "current_steps": 205, "loss": 0.6014, "learning_rate": 7.782608695652173e-07, "epoch": 1.8392857142857144 }, { "current_steps": 206, "loss": 0.684, "learning_rate": 7.76086956521739e-07, "epoch": 1.8482142857142856 }, { "current_steps": 207, "loss": 0.5932, "learning_rate": 7.739130434782608e-07, "epoch": 1.8571428571428572 }, { "current_steps": 208, "loss": 0.7736, "learning_rate": 7.717391304347826e-07, "epoch": 1.8660714285714286 }, { "current_steps": 209, "loss": 0.7601, "learning_rate": 7.695652173913043e-07, "epoch": 1.875 }, { "current_steps": 210, "loss": 0.8428, "learning_rate": 7.673913043478261e-07, "epoch": 1.8839285714285714 }, { "current_steps": 211, "loss": 0.8017, "learning_rate": 7.652173913043478e-07, "epoch": 1.8928571428571428 }, { "current_steps": 212, "loss": 0.5998, "learning_rate": 7.630434782608695e-07, "epoch": 1.9017857142857144 }, { "current_steps": 213, "loss": 0.9071, "learning_rate": 7.608695652173913e-07, "epoch": 1.9107142857142856 }, { "current_steps": 214, "loss": 0.8255, "learning_rate": 7.58695652173913e-07, "epoch": 1.9196428571428572 }, { "current_steps": 215, "loss": 0.9256, "learning_rate": 7.565217391304347e-07, "epoch": 1.9285714285714286 }, { "current_steps": 216, "loss": 0.6745, "learning_rate": 7.543478260869565e-07, "epoch": 1.9375 }, { "current_steps": 217, "loss": 0.6372, "learning_rate": 7.521739130434782e-07, "epoch": 1.9464285714285714 }, { "current_steps": 218, "loss": 0.6495, "learning_rate": 7.5e-07, "epoch": 1.9553571428571428 }, { "current_steps": 219, "loss": 0.6054, "learning_rate": 7.478260869565217e-07, "epoch": 1.9642857142857144 }, { "current_steps": 220, "loss": 0.9751, "learning_rate": 7.478260869565217e-07, "epoch": 1.9732142857142856 }, { "current_steps": 221, "loss": 0.6258, "learning_rate": 7.456521739130434e-07, "epoch": 1.9821428571428572 }, { "current_steps": 222, "loss": 0.794, "learning_rate": 7.434782608695653e-07, "epoch": 1.9910714285714286 }, { "current_steps": 223, "loss": 0.9991, "learning_rate": 7.41304347826087e-07, "epoch": 2.0 }, { "current_steps": 224, "loss": 0.8048, "learning_rate": 7.391304347826086e-07, "epoch": 2.0089285714285716 }, { "current_steps": 225, "loss": 0.8439, "learning_rate": 7.369565217391304e-07, "epoch": 2.017857142857143 }, { "current_steps": 226, "loss": 0.7546, "learning_rate": 7.347826086956521e-07, "epoch": 2.0267857142857144 }, { "current_steps": 227, "loss": 0.8195, "learning_rate": 7.326086956521738e-07, "epoch": 2.0357142857142856 }, { "current_steps": 228, "loss": 0.6988, "learning_rate": 7.304347826086957e-07, "epoch": 2.044642857142857 }, { "current_steps": 229, "loss": 0.8419, "learning_rate": 7.282608695652174e-07, "epoch": 2.0535714285714284 }, { "current_steps": 230, "loss": 0.6133, "learning_rate": 7.260869565217391e-07, "epoch": 2.0625 }, { "current_steps": 231, "loss": 0.6307, "learning_rate": 7.239130434782609e-07, "epoch": 2.0714285714285716 }, { "current_steps": 232, "loss": 0.7852, "learning_rate": 7.217391304347826e-07, "epoch": 2.080357142857143 }, { "current_steps": 233, "loss": 0.4894, "learning_rate": 7.195652173913042e-07, "epoch": 2.0892857142857144 }, { "current_steps": 234, "loss": 0.6806, "learning_rate": 7.17391304347826e-07, "epoch": 2.0982142857142856 }, { "current_steps": 235, "loss": 0.7798, "learning_rate": 7.152173913043478e-07, "epoch": 2.107142857142857 }, { "current_steps": 236, "loss": 0.934, "learning_rate": 7.130434782608695e-07, "epoch": 2.1160714285714284 }, { "current_steps": 237, "loss": 0.8044, "learning_rate": 7.108695652173913e-07, "epoch": 2.125 }, { "current_steps": 238, "loss": 0.8984, "learning_rate": 7.08695652173913e-07, "epoch": 2.1339285714285716 }, { "current_steps": 239, "loss": 0.7468, "learning_rate": 7.065217391304348e-07, "epoch": 2.142857142857143 }, { "current_steps": 240, "loss": 0.744, "learning_rate": 7.043478260869565e-07, "epoch": 2.1517857142857144 }, { "current_steps": 241, "loss": 0.5531, "learning_rate": 7.021739130434783e-07, "epoch": 2.1607142857142856 }, { "current_steps": 242, "loss": 0.8155, "learning_rate": 7e-07, "epoch": 2.169642857142857 }, { "current_steps": 243, "loss": 0.7626, "learning_rate": 6.978260869565217e-07, "epoch": 2.1785714285714284 }, { "current_steps": 244, "loss": 0.5438, "learning_rate": 6.956521739130434e-07, "epoch": 2.1875 }, { "current_steps": 245, "loss": 0.7638, "learning_rate": 6.934782608695652e-07, "epoch": 2.1964285714285716 }, { "current_steps": 246, "loss": 0.5092, "learning_rate": 6.913043478260869e-07, "epoch": 2.205357142857143 }, { "current_steps": 247, "loss": 0.7026, "learning_rate": 6.891304347826086e-07, "epoch": 2.2142857142857144 }, { "current_steps": 248, "loss": 0.727, "learning_rate": 6.869565217391305e-07, "epoch": 2.2232142857142856 }, { "current_steps": 249, "loss": 0.6229, "learning_rate": 6.847826086956522e-07, "epoch": 2.232142857142857 }, { "current_steps": 250, "loss": 0.6695, "learning_rate": 6.826086956521738e-07, "epoch": 2.2410714285714284 }, { "current_steps": 251, "loss": 0.6603, "learning_rate": 6.804347826086956e-07, "epoch": 2.25 }, { "current_steps": 252, "loss": 0.7804, "learning_rate": 6.782608695652173e-07, "epoch": 2.2589285714285716 }, { "current_steps": 253, "loss": 0.9138, "learning_rate": 6.76086956521739e-07, "epoch": 2.267857142857143 }, { "current_steps": 254, "loss": 0.7793, "learning_rate": 6.739130434782609e-07, "epoch": 2.2767857142857144 }, { "current_steps": 255, "loss": 0.7045, "learning_rate": 6.717391304347826e-07, "epoch": 2.2857142857142856 }, { "current_steps": 256, "loss": 0.8594, "learning_rate": 6.695652173913044e-07, "epoch": 2.294642857142857 }, { "current_steps": 257, "loss": 0.9529, "learning_rate": 6.673913043478261e-07, "epoch": 2.3035714285714284 }, { "current_steps": 258, "loss": 0.7477, "learning_rate": 6.652173913043478e-07, "epoch": 2.3125 }, { "current_steps": 259, "loss": 0.7676, "learning_rate": 6.630434782608695e-07, "epoch": 2.3214285714285716 }, { "current_steps": 260, "loss": 0.6468, "learning_rate": 6.608695652173912e-07, "epoch": 2.330357142857143 }, { "current_steps": 261, "loss": 0.6665, "learning_rate": 6.58695652173913e-07, "epoch": 2.3392857142857144 }, { "current_steps": 262, "loss": 0.838, "learning_rate": 6.565217391304348e-07, "epoch": 2.3482142857142856 }, { "current_steps": 263, "loss": 0.7129, "learning_rate": 6.543478260869565e-07, "epoch": 2.357142857142857 }, { "current_steps": 264, "loss": 0.8685, "learning_rate": 6.521739130434782e-07, "epoch": 2.3660714285714284 }, { "current_steps": 265, "loss": 0.7224, "learning_rate": 6.5e-07, "epoch": 2.375 }, { "current_steps": 266, "loss": 0.7037, "learning_rate": 6.478260869565217e-07, "epoch": 2.3839285714285716 }, { "current_steps": 267, "loss": 0.5596, "learning_rate": 6.456521739130435e-07, "epoch": 2.392857142857143 }, { "current_steps": 268, "loss": 0.8887, "learning_rate": 6.434782608695652e-07, "epoch": 2.4017857142857144 }, { "current_steps": 269, "loss": 0.6721, "learning_rate": 6.413043478260869e-07, "epoch": 2.4107142857142856 }, { "current_steps": 270, "loss": 0.7387, "learning_rate": 6.391304347826086e-07, "epoch": 2.419642857142857 }, { "current_steps": 271, "loss": 0.6304, "learning_rate": 6.369565217391304e-07, "epoch": 2.4285714285714284 }, { "current_steps": 272, "loss": 0.7563, "learning_rate": 6.347826086956521e-07, "epoch": 2.4375 }, { "current_steps": 273, "loss": 0.6833, "learning_rate": 6.326086956521739e-07, "epoch": 2.4464285714285716 }, { "current_steps": 274, "loss": 0.722, "learning_rate": 6.304347826086957e-07, "epoch": 2.455357142857143 }, { "current_steps": 275, "loss": 0.8583, "learning_rate": 6.282608695652174e-07, "epoch": 2.4642857142857144 }, { "current_steps": 276, "loss": 0.8988, "learning_rate": 6.260869565217392e-07, "epoch": 2.4732142857142856 }, { "current_steps": 277, "loss": 0.6269, "learning_rate": 6.239130434782608e-07, "epoch": 2.482142857142857 }, { "current_steps": 278, "loss": 0.473, "learning_rate": 6.217391304347825e-07, "epoch": 2.4910714285714284 }, { "current_steps": 279, "loss": 0.7065, "learning_rate": 6.195652173913043e-07, "epoch": 2.5 }, { "current_steps": 280, "loss": 0.7912, "learning_rate": 6.17391304347826e-07, "epoch": 2.508928571428571 }, { "current_steps": 281, "loss": 0.6589, "learning_rate": 6.152173913043478e-07, "epoch": 2.517857142857143 }, { "current_steps": 282, "loss": 0.5908, "learning_rate": 6.130434782608696e-07, "epoch": 2.5267857142857144 }, { "current_steps": 283, "loss": 0.839, "learning_rate": 6.108695652173913e-07, "epoch": 2.5357142857142856 }, { "current_steps": 284, "loss": 0.9573, "learning_rate": 6.08695652173913e-07, "epoch": 2.544642857142857 }, { "current_steps": 285, "loss": 0.8881, "learning_rate": 6.065217391304348e-07, "epoch": 2.553571428571429 }, { "current_steps": 286, "loss": 0.5213, "learning_rate": 6.043478260869564e-07, "epoch": 2.5625 }, { "current_steps": 287, "loss": 0.5668, "learning_rate": 6.021739130434782e-07, "epoch": 2.571428571428571 }, { "current_steps": 288, "loss": 0.6856, "learning_rate": 6e-07, "epoch": 2.580357142857143 }, { "current_steps": 289, "loss": 0.6793, "learning_rate": 5.978260869565217e-07, "epoch": 2.5892857142857144 }, { "current_steps": 290, "loss": 0.6176, "learning_rate": 5.956521739130435e-07, "epoch": 2.5982142857142856 }, { "current_steps": 291, "loss": 0.5633, "learning_rate": 5.934782608695652e-07, "epoch": 2.607142857142857 }, { "current_steps": 292, "loss": 0.8512, "learning_rate": 5.913043478260869e-07, "epoch": 2.616071428571429 }, { "current_steps": 293, "loss": 0.9664, "learning_rate": 5.891304347826088e-07, "epoch": 2.625 }, { "current_steps": 294, "loss": 0.6124, "learning_rate": 5.869565217391305e-07, "epoch": 2.633928571428571 }, { "current_steps": 295, "loss": 0.6244, "learning_rate": 5.847826086956521e-07, "epoch": 2.642857142857143 }, { "current_steps": 296, "loss": 0.7879, "learning_rate": 5.826086956521739e-07, "epoch": 2.6517857142857144 }, { "current_steps": 297, "loss": 0.6862, "learning_rate": 5.804347826086956e-07, "epoch": 2.6607142857142856 }, { "current_steps": 298, "loss": 0.6368, "learning_rate": 5.782608695652173e-07, "epoch": 2.669642857142857 }, { "current_steps": 299, "loss": 0.8478, "learning_rate": 5.760869565217391e-07, "epoch": 2.678571428571429 }, { "current_steps": 300, "loss": 0.6466, "learning_rate": 5.739130434782609e-07, "epoch": 2.6875 }, { "current_steps": 301, "loss": 0.7323, "learning_rate": 5.717391304347826e-07, "epoch": 2.696428571428571 }, { "current_steps": 302, "loss": 0.7611, "learning_rate": 5.695652173913044e-07, "epoch": 2.705357142857143 }, { "current_steps": 303, "loss": 0.7075, "learning_rate": 5.673913043478261e-07, "epoch": 2.7142857142857144 }, { "current_steps": 304, "loss": 0.5448, "learning_rate": 5.652173913043477e-07, "epoch": 2.7232142857142856 }, { "current_steps": 305, "loss": 0.704, "learning_rate": 5.630434782608695e-07, "epoch": 2.732142857142857 }, { "current_steps": 306, "loss": 0.8591, "learning_rate": 5.608695652173912e-07, "epoch": 2.741071428571429 }, { "current_steps": 307, "loss": 0.6702, "learning_rate": 5.58695652173913e-07, "epoch": 2.75 }, { "current_steps": 308, "loss": 0.6652, "learning_rate": 5.565217391304348e-07, "epoch": 2.758928571428571 }, { "current_steps": 309, "loss": 0.7208, "learning_rate": 5.543478260869565e-07, "epoch": 2.767857142857143 }, { "current_steps": 310, "loss": 0.7334, "learning_rate": 5.521739130434783e-07, "epoch": 2.7767857142857144 }, { "current_steps": 311, "loss": 0.865, "learning_rate": 5.5e-07, "epoch": 2.7857142857142856 }, { "current_steps": 312, "loss": 0.5955, "learning_rate": 5.478260869565216e-07, "epoch": 2.794642857142857 }, { "current_steps": 313, "loss": 0.5059, "learning_rate": 5.456521739130435e-07, "epoch": 2.803571428571429 }, { "current_steps": 314, "loss": 1.0855, "learning_rate": 5.434782608695652e-07, "epoch": 2.8125 }, { "current_steps": 315, "loss": 0.7484, "learning_rate": 5.413043478260869e-07, "epoch": 2.821428571428571 }, { "current_steps": 316, "loss": 0.8017, "learning_rate": 5.391304347826087e-07, "epoch": 2.830357142857143 }, { "current_steps": 317, "loss": 0.7272, "learning_rate": 5.369565217391304e-07, "epoch": 2.8392857142857144 }, { "current_steps": 318, "loss": 0.6897, "learning_rate": 5.347826086956521e-07, "epoch": 2.8482142857142856 }, { "current_steps": 319, "loss": 0.634, "learning_rate": 5.32608695652174e-07, "epoch": 2.857142857142857 }, { "current_steps": 320, "loss": 0.7684, "learning_rate": 5.304347826086957e-07, "epoch": 2.866071428571429 }, { "current_steps": 321, "loss": 0.5758, "learning_rate": 5.282608695652173e-07, "epoch": 2.875 }, { "current_steps": 322, "loss": 0.687, "learning_rate": 5.260869565217391e-07, "epoch": 2.883928571428571 }, { "current_steps": 323, "loss": 0.6942, "learning_rate": 5.239130434782608e-07, "epoch": 2.892857142857143 }, { "current_steps": 324, "loss": 0.7698, "learning_rate": 5.217391304347825e-07, "epoch": 2.9017857142857144 }, { "current_steps": 325, "loss": 0.815, "learning_rate": 5.195652173913043e-07, "epoch": 2.9107142857142856 }, { "current_steps": 326, "loss": 0.6837, "learning_rate": 5.173913043478261e-07, "epoch": 2.919642857142857 }, { "current_steps": 327, "loss": 0.7103, "learning_rate": 5.152173913043479e-07, "epoch": 2.928571428571429 }, { "current_steps": 328, "loss": 0.6798, "learning_rate": 5.130434782608696e-07, "epoch": 2.9375 }, { "current_steps": 329, "loss": 0.767, "learning_rate": 5.108695652173913e-07, "epoch": 2.946428571428571 }, { "current_steps": 330, "loss": 0.6161, "learning_rate": 5.08695652173913e-07, "epoch": 2.955357142857143 }, { "current_steps": 331, "loss": 0.6607, "learning_rate": 5.065217391304347e-07, "epoch": 2.9642857142857144 }, { "current_steps": 332, "loss": 0.6875, "learning_rate": 5.043478260869564e-07, "epoch": 2.9732142857142856 }, { "current_steps": 333, "loss": 0.746, "learning_rate": 5.021739130434783e-07, "epoch": 2.982142857142857 }, { "current_steps": 334, "loss": 0.6093, "learning_rate": 5e-07, "epoch": 2.991071428571429 }, { "current_steps": 335, "loss": 0.5599, "learning_rate": 4.978260869565217e-07, "epoch": 3.0 }, { "current_steps": 336, "loss": 0.5985, "learning_rate": 4.956521739130435e-07, "epoch": 3.0089285714285716 }, { "current_steps": 337, "loss": 0.6692, "learning_rate": 4.934782608695652e-07, "epoch": 3.017857142857143 }, { "current_steps": 338, "loss": 0.5887, "learning_rate": 4.913043478260869e-07, "epoch": 3.0267857142857144 }, { "current_steps": 339, "loss": 0.5831, "learning_rate": 4.891304347826087e-07, "epoch": 3.0357142857142856 }, { "current_steps": 340, "loss": 0.5424, "learning_rate": 4.869565217391305e-07, "epoch": 3.044642857142857 }, { "current_steps": 341, "loss": 1.0041, "learning_rate": 4.847826086956521e-07, "epoch": 3.0535714285714284 }, { "current_steps": 342, "loss": 0.6989, "learning_rate": 4.826086956521739e-07, "epoch": 3.0625 }, { "current_steps": 343, "loss": 0.7104, "learning_rate": 4.804347826086956e-07, "epoch": 3.0714285714285716 }, { "current_steps": 344, "loss": 0.6493, "learning_rate": 4.782608695652174e-07, "epoch": 3.080357142857143 }, { "current_steps": 345, "loss": 0.8018, "learning_rate": 4.7608695652173915e-07, "epoch": 3.0892857142857144 }, { "current_steps": 346, "loss": 0.638, "learning_rate": 4.739130434782608e-07, "epoch": 3.0982142857142856 }, { "current_steps": 347, "loss": 0.7714, "learning_rate": 4.717391304347826e-07, "epoch": 3.107142857142857 }, { "current_steps": 348, "loss": 0.7103, "learning_rate": 4.6956521739130434e-07, "epoch": 3.1160714285714284 }, { "current_steps": 349, "loss": 0.5937, "learning_rate": 4.673913043478261e-07, "epoch": 3.125 }, { "current_steps": 350, "loss": 0.7256, "learning_rate": 4.6521739130434777e-07, "epoch": 3.1339285714285716 }, { "current_steps": 351, "loss": 0.864, "learning_rate": 4.6304347826086954e-07, "epoch": 3.142857142857143 }, { "current_steps": 352, "loss": 0.7429, "learning_rate": 4.608695652173913e-07, "epoch": 3.1517857142857144 }, { "current_steps": 353, "loss": 0.6658, "learning_rate": 4.58695652173913e-07, "epoch": 3.1607142857142856 }, { "current_steps": 354, "loss": 0.647, "learning_rate": 4.5652173913043473e-07, "epoch": 3.169642857142857 }, { "current_steps": 355, "loss": 0.7772, "learning_rate": 4.543478260869565e-07, "epoch": 3.1785714285714284 }, { "current_steps": 356, "loss": 0.6939, "learning_rate": 4.521739130434782e-07, "epoch": 3.1875 }, { "current_steps": 357, "loss": 0.5744, "learning_rate": 4.5e-07, "epoch": 3.1964285714285716 }, { "current_steps": 358, "loss": 0.7193, "learning_rate": 4.4782608695652175e-07, "epoch": 3.205357142857143 }, { "current_steps": 359, "loss": 0.667, "learning_rate": 4.4565217391304346e-07, "epoch": 3.2142857142857144 }, { "current_steps": 360, "loss": 0.6671, "learning_rate": 4.434782608695652e-07, "epoch": 3.2232142857142856 }, { "current_steps": 361, "loss": 0.8531, "learning_rate": 4.4130434782608694e-07, "epoch": 3.232142857142857 }, { "current_steps": 362, "loss": 0.6706, "learning_rate": 4.391304347826087e-07, "epoch": 3.2410714285714284 }, { "current_steps": 363, "loss": 0.8786, "learning_rate": 4.3695652173913037e-07, "epoch": 3.25 }, { "current_steps": 364, "loss": 0.6281, "learning_rate": 4.3478260869565214e-07, "epoch": 3.2589285714285716 }, { "current_steps": 365, "loss": 0.8648, "learning_rate": 4.326086956521739e-07, "epoch": 3.267857142857143 }, { "current_steps": 366, "loss": 0.5872, "learning_rate": 4.3043478260869567e-07, "epoch": 3.2767857142857144 }, { "current_steps": 367, "loss": 0.5874, "learning_rate": 4.282608695652174e-07, "epoch": 3.2857142857142856 }, { "current_steps": 368, "loss": 0.7057, "learning_rate": 4.260869565217391e-07, "epoch": 3.294642857142857 }, { "current_steps": 369, "loss": 0.6076, "learning_rate": 4.2391304347826086e-07, "epoch": 3.3035714285714284 }, { "current_steps": 370, "loss": 0.7514, "learning_rate": 4.217391304347826e-07, "epoch": 3.3125 }, { "current_steps": 371, "loss": 0.689, "learning_rate": 4.1956521739130434e-07, "epoch": 3.3214285714285716 }, { "current_steps": 372, "loss": 0.7074, "learning_rate": 4.1739130434782606e-07, "epoch": 3.330357142857143 }, { "current_steps": 373, "loss": 0.6425, "learning_rate": 4.1521739130434777e-07, "epoch": 3.3392857142857144 }, { "current_steps": 374, "loss": 0.5247, "learning_rate": 4.1304347826086954e-07, "epoch": 3.3482142857142856 }, { "current_steps": 375, "loss": 0.7755, "learning_rate": 4.108695652173913e-07, "epoch": 3.357142857142857 }, { "current_steps": 376, "loss": 0.7774, "learning_rate": 4.0869565217391307e-07, "epoch": 3.3660714285714284 }, { "current_steps": 377, "loss": 0.6871, "learning_rate": 4.0652173913043473e-07, "epoch": 3.375 }, { "current_steps": 378, "loss": 0.566, "learning_rate": 4.043478260869565e-07, "epoch": 3.3839285714285716 }, { "current_steps": 379, "loss": 1.0922, "learning_rate": 4.0217391304347827e-07, "epoch": 3.392857142857143 }, { "current_steps": 380, "loss": 0.5958, "learning_rate": 4e-07, "epoch": 3.4017857142857144 }, { "current_steps": 381, "loss": 0.9182, "learning_rate": 3.978260869565217e-07, "epoch": 3.4107142857142856 }, { "current_steps": 382, "loss": 0.7356, "learning_rate": 3.9565217391304346e-07, "epoch": 3.419642857142857 }, { "current_steps": 383, "loss": 0.8677, "learning_rate": 3.9347826086956523e-07, "epoch": 3.4285714285714284 }, { "current_steps": 384, "loss": 0.6885, "learning_rate": 3.9130434782608694e-07, "epoch": 3.4375 }, { "current_steps": 385, "loss": 0.7982, "learning_rate": 3.8913043478260866e-07, "epoch": 3.4464285714285716 }, { "current_steps": 386, "loss": 0.8466, "learning_rate": 3.869565217391304e-07, "epoch": 3.455357142857143 }, { "current_steps": 387, "loss": 0.4563, "learning_rate": 3.8478260869565214e-07, "epoch": 3.4642857142857144 }, { "current_steps": 388, "loss": 0.7675, "learning_rate": 3.826086956521739e-07, "epoch": 3.4732142857142856 }, { "current_steps": 389, "loss": 0.7642, "learning_rate": 3.8043478260869567e-07, "epoch": 3.482142857142857 }, { "current_steps": 390, "loss": 0.6065, "learning_rate": 3.7826086956521733e-07, "epoch": 3.4910714285714284 }, { "current_steps": 391, "loss": 0.6121, "learning_rate": 3.760869565217391e-07, "epoch": 3.5 }, { "current_steps": 392, "loss": 0.8562, "learning_rate": 3.7391304347826087e-07, "epoch": 3.508928571428571 }, { "current_steps": 393, "loss": 0.8169, "learning_rate": 3.7173913043478263e-07, "epoch": 3.517857142857143 }, { "current_steps": 394, "loss": 0.7264, "learning_rate": 3.695652173913043e-07, "epoch": 3.5267857142857144 }, { "current_steps": 395, "loss": 0.6761, "learning_rate": 3.6739130434782606e-07, "epoch": 3.5357142857142856 }, { "current_steps": 396, "loss": 0.485, "learning_rate": 3.6521739130434783e-07, "epoch": 3.544642857142857 }, { "current_steps": 397, "loss": 0.6992, "learning_rate": 3.6304347826086954e-07, "epoch": 3.553571428571429 }, { "current_steps": 398, "loss": 0.6543, "learning_rate": 3.608695652173913e-07, "epoch": 3.5625 }, { "current_steps": 399, "loss": 0.6019, "learning_rate": 3.58695652173913e-07, "epoch": 3.571428571428571 }, { "current_steps": 400, "loss": 0.8135, "learning_rate": 3.5652173913043474e-07, "epoch": 3.580357142857143 }, { "current_steps": 401, "loss": 0.5053, "learning_rate": 3.543478260869565e-07, "epoch": 3.5892857142857144 }, { "current_steps": 402, "loss": 0.6121, "learning_rate": 3.5217391304347827e-07, "epoch": 3.5982142857142856 }, { "current_steps": 403, "loss": 0.5648, "learning_rate": 3.5e-07, "epoch": 3.607142857142857 }, { "current_steps": 404, "loss": 0.6023, "learning_rate": 3.478260869565217e-07, "epoch": 3.616071428571429 }, { "current_steps": 405, "loss": 0.7843, "learning_rate": 3.4565217391304346e-07, "epoch": 3.625 }, { "current_steps": 406, "loss": 0.6902, "learning_rate": 3.4347826086956523e-07, "epoch": 3.633928571428571 }, { "current_steps": 407, "loss": 0.6103, "learning_rate": 3.413043478260869e-07, "epoch": 3.642857142857143 }, { "current_steps": 408, "loss": 0.759, "learning_rate": 3.3913043478260866e-07, "epoch": 3.6517857142857144 }, { "current_steps": 409, "loss": 0.7823, "learning_rate": 3.369565217391304e-07, "epoch": 3.6607142857142856 }, { "current_steps": 410, "loss": 0.8021, "learning_rate": 3.347826086956522e-07, "epoch": 3.669642857142857 }, { "current_steps": 411, "loss": 0.5927, "learning_rate": 3.326086956521739e-07, "epoch": 3.678571428571429 }, { "current_steps": 412, "loss": 0.6503, "learning_rate": 3.304347826086956e-07, "epoch": 3.6875 }, { "current_steps": 413, "loss": 0.886, "learning_rate": 3.282608695652174e-07, "epoch": 3.696428571428571 }, { "current_steps": 414, "loss": 0.6331, "learning_rate": 3.260869565217391e-07, "epoch": 3.705357142857143 }, { "current_steps": 415, "loss": 0.7633, "learning_rate": 3.2391304347826087e-07, "epoch": 3.7142857142857144 }, { "current_steps": 416, "loss": 0.6538, "learning_rate": 3.217391304347826e-07, "epoch": 3.7232142857142856 }, { "current_steps": 417, "loss": 0.6156, "learning_rate": 3.195652173913043e-07, "epoch": 3.732142857142857 }, { "current_steps": 418, "loss": 0.6973, "learning_rate": 3.1739130434782606e-07, "epoch": 3.741071428571429 }, { "current_steps": 419, "loss": 0.6521, "learning_rate": 3.1521739130434783e-07, "epoch": 3.75 }, { "current_steps": 420, "loss": 0.6931, "learning_rate": 3.130434782608696e-07, "epoch": 3.758928571428571 }, { "current_steps": 421, "loss": 0.8192, "learning_rate": 3.1086956521739126e-07, "epoch": 3.767857142857143 }, { "current_steps": 422, "loss": 0.5986, "learning_rate": 3.08695652173913e-07, "epoch": 3.7767857142857144 }, { "current_steps": 423, "loss": 0.9986, "learning_rate": 3.065217391304348e-07, "epoch": 3.7857142857142856 }, { "current_steps": 424, "loss": 0.7645, "learning_rate": 3.043478260869565e-07, "epoch": 3.794642857142857 }, { "current_steps": 425, "loss": 0.6489, "learning_rate": 3.021739130434782e-07, "epoch": 3.803571428571429 }, { "current_steps": 426, "loss": 0.5974, "learning_rate": 3e-07, "epoch": 3.8125 }, { "current_steps": 427, "loss": 0.7392, "learning_rate": 2.9782608695652175e-07, "epoch": 3.821428571428571 }, { "current_steps": 428, "loss": 0.7813, "learning_rate": 2.9565217391304347e-07, "epoch": 3.830357142857143 }, { "current_steps": 429, "loss": 0.7818, "learning_rate": 2.9347826086956523e-07, "epoch": 3.8392857142857144 }, { "current_steps": 430, "loss": 1.0693, "learning_rate": 2.9130434782608695e-07, "epoch": 3.8482142857142856 }, { "current_steps": 431, "loss": 0.6324, "learning_rate": 2.8913043478260866e-07, "epoch": 3.857142857142857 }, { "current_steps": 432, "loss": 0.5228, "learning_rate": 2.8695652173913043e-07, "epoch": 3.866071428571429 }, { "current_steps": 433, "loss": 0.6631, "learning_rate": 2.847826086956522e-07, "epoch": 3.875 }, { "current_steps": 434, "loss": 0.6685, "learning_rate": 2.8260869565217386e-07, "epoch": 3.883928571428571 }, { "current_steps": 435, "loss": 0.6566, "learning_rate": 2.804347826086956e-07, "epoch": 3.892857142857143 }, { "current_steps": 436, "loss": 0.6169, "learning_rate": 2.782608695652174e-07, "epoch": 3.9017857142857144 }, { "current_steps": 437, "loss": 0.5012, "learning_rate": 2.7608695652173916e-07, "epoch": 3.9107142857142856 }, { "current_steps": 438, "loss": 0.637, "learning_rate": 2.739130434782608e-07, "epoch": 3.919642857142857 }, { "current_steps": 439, "loss": 0.7777, "learning_rate": 2.717391304347826e-07, "epoch": 3.928571428571429 }, { "current_steps": 440, "loss": 0.6963, "learning_rate": 2.6956521739130435e-07, "epoch": 3.9375 }, { "current_steps": 441, "loss": 0.5398, "learning_rate": 2.6739130434782607e-07, "epoch": 3.946428571428571 }, { "current_steps": 442, "loss": 1.0029, "learning_rate": 2.6521739130434783e-07, "epoch": 3.955357142857143 }, { "current_steps": 443, "loss": 0.8166, "learning_rate": 2.6304347826086955e-07, "epoch": 3.9642857142857144 }, { "current_steps": 444, "loss": 0.8981, "learning_rate": 2.6086956521739126e-07, "epoch": 3.9732142857142856 }, { "current_steps": 445, "loss": 0.536, "learning_rate": 2.5869565217391303e-07, "epoch": 3.982142857142857 }, { "current_steps": 446, "loss": 0.7719, "learning_rate": 2.565217391304348e-07, "epoch": 3.991071428571429 }, { "current_steps": 447, "loss": 3.9574, "learning_rate": 2.565217391304348e-07, "epoch": 4.0 }, { "current_steps": 448, "loss": 0.6567, "learning_rate": 2.543478260869565e-07, "epoch": 4.008928571428571 }, { "current_steps": 449, "loss": 0.8622, "learning_rate": 2.521739130434782e-07, "epoch": 4.017857142857143 }, { "current_steps": 450, "loss": 0.5737, "learning_rate": 2.5e-07, "epoch": 4.026785714285714 }, { "current_steps": 451, "loss": 0.736, "learning_rate": 2.4782608695652176e-07, "epoch": 4.035714285714286 }, { "current_steps": 452, "loss": 0.8457, "learning_rate": 2.4565217391304347e-07, "epoch": 4.044642857142857 }, { "current_steps": 453, "loss": 0.7416, "learning_rate": 2.4347826086956524e-07, "epoch": 4.053571428571429 }, { "current_steps": 454, "loss": 1.0355, "learning_rate": 2.4130434782608695e-07, "epoch": 4.0625 }, { "current_steps": 455, "loss": 0.7162, "learning_rate": 2.391304347826087e-07, "epoch": 4.071428571428571 }, { "current_steps": 456, "loss": 0.8163, "learning_rate": 2.369565217391304e-07, "epoch": 4.080357142857143 }, { "current_steps": 457, "loss": 0.5188, "learning_rate": 2.3478260869565217e-07, "epoch": 4.089285714285714 }, { "current_steps": 458, "loss": 0.9544, "learning_rate": 2.3260869565217389e-07, "epoch": 4.098214285714286 }, { "current_steps": 459, "loss": 0.6205, "learning_rate": 2.3043478260869565e-07, "epoch": 4.107142857142857 }, { "current_steps": 460, "loss": 0.6643, "learning_rate": 2.2826086956521737e-07, "epoch": 4.116071428571429 }, { "current_steps": 461, "loss": 0.6465, "learning_rate": 2.260869565217391e-07, "epoch": 4.125 }, { "current_steps": 462, "loss": 0.6697, "learning_rate": 2.2391304347826087e-07, "epoch": 4.133928571428571 }, { "current_steps": 463, "loss": 0.7041, "learning_rate": 2.217391304347826e-07, "epoch": 4.142857142857143 }, { "current_steps": 464, "loss": 0.802, "learning_rate": 2.1956521739130435e-07, "epoch": 4.151785714285714 }, { "current_steps": 465, "loss": 0.623, "learning_rate": 2.1739130434782607e-07, "epoch": 4.160714285714286 }, { "current_steps": 466, "loss": 0.6071, "learning_rate": 2.1521739130434783e-07, "epoch": 4.169642857142857 }, { "current_steps": 467, "loss": 0.718, "learning_rate": 2.1304347826086955e-07, "epoch": 4.178571428571429 }, { "current_steps": 468, "loss": 0.6337, "learning_rate": 2.108695652173913e-07, "epoch": 4.1875 }, { "current_steps": 469, "loss": 0.5689, "learning_rate": 2.0869565217391303e-07, "epoch": 4.196428571428571 }, { "current_steps": 470, "loss": 0.62, "learning_rate": 2.0652173913043477e-07, "epoch": 4.205357142857143 }, { "current_steps": 471, "loss": 1.0191, "learning_rate": 2.0434782608695654e-07, "epoch": 4.214285714285714 }, { "current_steps": 472, "loss": 0.6678, "learning_rate": 2.0217391304347825e-07, "epoch": 4.223214285714286 }, { "current_steps": 473, "loss": 0.6296, "learning_rate": 2e-07, "epoch": 4.232142857142857 }, { "current_steps": 474, "loss": 0.884, "learning_rate": 1.9782608695652173e-07, "epoch": 4.241071428571429 }, { "current_steps": 475, "loss": 0.7207, "learning_rate": 1.9565217391304347e-07, "epoch": 4.25 }, { "current_steps": 476, "loss": 0.6856, "learning_rate": 1.934782608695652e-07, "epoch": 4.258928571428571 }, { "current_steps": 477, "loss": 0.6314, "learning_rate": 1.9130434782608695e-07, "epoch": 4.267857142857143 }, { "current_steps": 478, "loss": 0.5759, "learning_rate": 1.8913043478260867e-07, "epoch": 4.276785714285714 }, { "current_steps": 479, "loss": 0.6925, "learning_rate": 1.8695652173913043e-07, "epoch": 4.285714285714286 }, { "current_steps": 480, "loss": 0.6237, "learning_rate": 1.8478260869565215e-07, "epoch": 4.294642857142857 }, { "current_steps": 481, "loss": 0.6666, "learning_rate": 1.8260869565217391e-07, "epoch": 4.303571428571429 }, { "current_steps": 482, "loss": 0.709, "learning_rate": 1.8043478260869565e-07, "epoch": 4.3125 }, { "current_steps": 483, "loss": 0.8078, "learning_rate": 1.7826086956521737e-07, "epoch": 4.321428571428571 }, { "current_steps": 484, "loss": 0.7355, "learning_rate": 1.7608695652173914e-07, "epoch": 4.330357142857143 }, { "current_steps": 485, "loss": 0.8901, "learning_rate": 1.7391304347826085e-07, "epoch": 4.339285714285714 }, { "current_steps": 486, "loss": 0.565, "learning_rate": 1.7173913043478262e-07, "epoch": 4.348214285714286 }, { "current_steps": 487, "loss": 0.6396, "learning_rate": 1.6956521739130433e-07, "epoch": 4.357142857142857 }, { "current_steps": 488, "loss": 0.531, "learning_rate": 1.673913043478261e-07, "epoch": 4.366071428571429 }, { "current_steps": 489, "loss": 0.5726, "learning_rate": 1.652173913043478e-07, "epoch": 4.375 }, { "current_steps": 490, "loss": 0.602, "learning_rate": 1.6304347826086955e-07, "epoch": 4.383928571428571 }, { "current_steps": 491, "loss": 0.7032, "learning_rate": 1.608695652173913e-07, "epoch": 4.392857142857143 }, { "current_steps": 492, "loss": 0.8984, "learning_rate": 1.5869565217391303e-07, "epoch": 4.401785714285714 }, { "current_steps": 493, "loss": 0.5913, "learning_rate": 1.565217391304348e-07, "epoch": 4.410714285714286 }, { "current_steps": 494, "loss": 0.6021, "learning_rate": 1.543478260869565e-07, "epoch": 4.419642857142857 }, { "current_steps": 495, "loss": 0.7554, "learning_rate": 1.5217391304347825e-07, "epoch": 4.428571428571429 }, { "current_steps": 496, "loss": 0.8683, "learning_rate": 1.5e-07, "epoch": 4.4375 }, { "current_steps": 497, "loss": 0.5465, "learning_rate": 1.4782608695652173e-07, "epoch": 4.446428571428571 }, { "current_steps": 498, "loss": 0.6903, "learning_rate": 1.4565217391304347e-07, "epoch": 4.455357142857143 }, { "current_steps": 499, "loss": 0.4821, "learning_rate": 1.4347826086956521e-07, "epoch": 4.464285714285714 }, { "current_steps": 500, "loss": 0.6731, "learning_rate": 1.4130434782608693e-07, "epoch": 4.473214285714286 }, { "current_steps": 501, "loss": 0.7423, "learning_rate": 1.391304347826087e-07, "epoch": 4.482142857142857 }, { "current_steps": 502, "loss": 0.6967, "learning_rate": 1.369565217391304e-07, "epoch": 4.491071428571429 }, { "current_steps": 503, "loss": 0.5918, "learning_rate": 1.3478260869565218e-07, "epoch": 4.5 }, { "current_steps": 504, "loss": 0.8028, "learning_rate": 1.3260869565217392e-07, "epoch": 4.508928571428571 }, { "current_steps": 505, "loss": 0.9578, "learning_rate": 1.3043478260869563e-07, "epoch": 4.517857142857143 }, { "current_steps": 506, "loss": 0.6187, "learning_rate": 1.282608695652174e-07, "epoch": 4.526785714285714 }, { "current_steps": 507, "loss": 0.6426, "learning_rate": 1.260869565217391e-07, "epoch": 4.535714285714286 }, { "current_steps": 508, "loss": 0.5835, "learning_rate": 1.2391304347826088e-07, "epoch": 4.544642857142857 }, { "current_steps": 509, "loss": 0.7218, "learning_rate": 1.2173913043478262e-07, "epoch": 4.553571428571429 }, { "current_steps": 510, "loss": 0.812, "learning_rate": 1.1956521739130436e-07, "epoch": 4.5625 }, { "current_steps": 511, "loss": 0.5526, "learning_rate": 1.1739130434782609e-07, "epoch": 4.571428571428571 }, { "current_steps": 512, "loss": 0.8554, "learning_rate": 1.1521739130434783e-07, "epoch": 4.580357142857143 }, { "current_steps": 513, "loss": 0.7209, "learning_rate": 1.1304347826086955e-07, "epoch": 4.589285714285714 }, { "current_steps": 514, "loss": 0.7154, "learning_rate": 1.108695652173913e-07, "epoch": 4.598214285714286 }, { "current_steps": 515, "loss": 0.7147, "learning_rate": 1.0869565217391303e-07, "epoch": 4.607142857142857 }, { "current_steps": 516, "loss": 0.6997, "learning_rate": 1.0652173913043477e-07, "epoch": 4.616071428571429 }, { "current_steps": 517, "loss": 0.6283, "learning_rate": 1.0434782608695651e-07, "epoch": 4.625 }, { "current_steps": 518, "loss": 0.6279, "learning_rate": 1.0217391304347827e-07, "epoch": 4.633928571428571 }, { "current_steps": 519, "loss": 0.8152, "learning_rate": 1e-07, "epoch": 4.642857142857143 }, { "current_steps": 520, "loss": 0.6155, "learning_rate": 9.782608695652174e-08, "epoch": 4.651785714285714 }, { "current_steps": 521, "loss": 0.4727, "learning_rate": 9.565217391304348e-08, "epoch": 4.660714285714286 }, { "current_steps": 522, "loss": 0.7457, "learning_rate": 9.347826086956522e-08, "epoch": 4.669642857142857 }, { "current_steps": 523, "loss": 0.9712, "learning_rate": 9.130434782608696e-08, "epoch": 4.678571428571429 }, { "current_steps": 524, "loss": 0.7759, "learning_rate": 8.913043478260868e-08, "epoch": 4.6875 }, { "current_steps": 525, "loss": 0.6597, "learning_rate": 8.695652173913042e-08, "epoch": 4.696428571428571 }, { "current_steps": 526, "loss": 0.6258, "learning_rate": 8.478260869565216e-08, "epoch": 4.705357142857143 }, { "current_steps": 527, "loss": 0.6443, "learning_rate": 8.26086956521739e-08, "epoch": 4.714285714285714 }, { "current_steps": 528, "loss": 0.5547, "learning_rate": 8.043478260869565e-08, "epoch": 4.723214285714286 }, { "current_steps": 529, "loss": 0.7149, "learning_rate": 7.82608695652174e-08, "epoch": 4.732142857142857 }, { "current_steps": 530, "loss": 0.6138, "learning_rate": 7.608695652173913e-08, "epoch": 4.741071428571429 }, { "current_steps": 531, "loss": 0.8032, "learning_rate": 7.391304347826087e-08, "epoch": 4.75 }, { "current_steps": 532, "loss": 0.7141, "learning_rate": 7.173913043478261e-08, "epoch": 4.758928571428571 }, { "current_steps": 533, "loss": 0.724, "learning_rate": 6.956521739130435e-08, "epoch": 4.767857142857143 }, { "current_steps": 534, "loss": 0.7707, "learning_rate": 6.739130434782609e-08, "epoch": 4.776785714285714 }, { "current_steps": 535, "loss": 0.6754, "learning_rate": 6.521739130434782e-08, "epoch": 4.785714285714286 }, { "current_steps": 536, "loss": 0.5861, "learning_rate": 6.304347826086956e-08, "epoch": 4.794642857142857 }, { "current_steps": 537, "loss": 0.8395, "learning_rate": 6.086956521739131e-08, "epoch": 4.803571428571429 }, { "current_steps": 538, "loss": 0.7642, "learning_rate": 5.869565217391304e-08, "epoch": 4.8125 }, { "current_steps": 539, "loss": 0.735, "learning_rate": 5.6521739130434777e-08, "epoch": 4.821428571428571 }, { "current_steps": 540, "loss": 0.6153, "learning_rate": 5.434782608695652e-08, "epoch": 4.830357142857143 }, { "current_steps": 541, "loss": 0.6299, "learning_rate": 5.217391304347826e-08, "epoch": 4.839285714285714 }, { "current_steps": 542, "loss": 1.078, "learning_rate": 5e-08, "epoch": 4.848214285714286 }, { "current_steps": 543, "loss": 0.7314, "learning_rate": 4.782608695652174e-08, "epoch": 4.857142857142857 }, { "current_steps": 544, "loss": 0.8515, "learning_rate": 4.565217391304348e-08, "epoch": 4.866071428571429 }, { "current_steps": 545, "loss": 0.5401, "learning_rate": 4.347826086956521e-08, "epoch": 4.875 }, { "current_steps": 546, "loss": 0.7315, "learning_rate": 4.130434782608695e-08, "epoch": 4.883928571428571 }, { "current_steps": 547, "loss": 0.6113, "learning_rate": 3.91304347826087e-08, "epoch": 4.892857142857143 }, { "current_steps": 548, "loss": 0.6239, "learning_rate": 3.6956521739130433e-08, "epoch": 4.901785714285714 }, { "current_steps": 549, "loss": 0.7292, "learning_rate": 3.4782608695652174e-08, "epoch": 4.910714285714286 }, { "current_steps": 550, "loss": 0.5297, "learning_rate": 3.260869565217391e-08, "epoch": 4.919642857142857 }, { "current_steps": 551, "loss": 0.6269, "learning_rate": 3.0434782608695655e-08, "epoch": 4.928571428571429 }, { "current_steps": 552, "loss": 0.6724, "learning_rate": 2.8260869565217388e-08, "epoch": 4.9375 }, { "current_steps": 553, "loss": 0.5109, "learning_rate": 2.608695652173913e-08, "epoch": 4.946428571428571 }, { "current_steps": 554, "loss": 0.9446, "learning_rate": 2.391304347826087e-08, "epoch": 4.955357142857143 }, { "current_steps": 555, "loss": 0.6897, "learning_rate": 2.1739130434782606e-08, "epoch": 4.964285714285714 }, { "current_steps": 556, "loss": 0.5511, "learning_rate": 1.956521739130435e-08, "epoch": 4.973214285714286 }, { "current_steps": 557, "loss": 0.7246, "learning_rate": 1.7391304347826087e-08, "epoch": 4.982142857142857 }, { "current_steps": 558, "loss": 0.6332, "learning_rate": 1.5217391304347827e-08, "epoch": 4.991071428571429 }, { "current_steps": 559, "loss": 1.0499, "learning_rate": 1.3043478260869564e-08, "epoch": 5.0 }, { "current_steps": 559, "loss": 1.0499, "learning_rate": 1.3043478260869564e-08, "epoch": 5.0 } ]