{ "best_metric": null, "best_model_checkpoint": null, "epoch": 10.0, "eval_steps": 500, "global_step": 6170, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 2.1505376344086024e-07, "loss": 1.0621, "step": 1 }, { "epoch": 0.0, "learning_rate": 4.301075268817205e-07, "loss": 0.8972, "step": 2 }, { "epoch": 0.0, "learning_rate": 6.451612903225807e-07, "loss": 1.0901, "step": 3 }, { "epoch": 0.01, "learning_rate": 8.60215053763441e-07, "loss": 0.9241, "step": 4 }, { "epoch": 0.01, "learning_rate": 1.0752688172043011e-06, "loss": 0.8526, "step": 5 }, { "epoch": 0.01, "learning_rate": 1.2903225806451614e-06, "loss": 0.936, "step": 6 }, { "epoch": 0.01, "learning_rate": 1.5053763440860217e-06, "loss": 0.8458, "step": 7 }, { "epoch": 0.01, "learning_rate": 1.720430107526882e-06, "loss": 1.0463, "step": 8 }, { "epoch": 0.01, "learning_rate": 1.935483870967742e-06, "loss": 0.8966, "step": 9 }, { "epoch": 0.02, "learning_rate": 2.1505376344086023e-06, "loss": 0.8319, "step": 10 }, { "epoch": 0.02, "learning_rate": 2.3655913978494625e-06, "loss": 0.8795, "step": 11 }, { "epoch": 0.02, "learning_rate": 2.580645161290323e-06, "loss": 1.0134, "step": 12 }, { "epoch": 0.02, "learning_rate": 2.7956989247311827e-06, "loss": 0.9341, "step": 13 }, { "epoch": 0.02, "learning_rate": 3.0107526881720433e-06, "loss": 1.0993, "step": 14 }, { "epoch": 0.02, "learning_rate": 3.225806451612903e-06, "loss": 0.7748, "step": 15 }, { "epoch": 0.03, "learning_rate": 3.440860215053764e-06, "loss": 0.8637, "step": 16 }, { "epoch": 0.03, "learning_rate": 3.655913978494624e-06, "loss": 1.1364, "step": 17 }, { "epoch": 0.03, "learning_rate": 3.870967741935484e-06, "loss": 0.8004, "step": 18 }, { "epoch": 0.03, "learning_rate": 4.086021505376344e-06, "loss": 1.0285, "step": 19 }, { "epoch": 0.03, "learning_rate": 4.3010752688172045e-06, "loss": 0.9821, "step": 20 }, { "epoch": 0.03, "learning_rate": 4.516129032258065e-06, "loss": 0.9096, "step": 21 }, { "epoch": 0.04, "learning_rate": 4.731182795698925e-06, "loss": 0.9445, "step": 22 }, { "epoch": 0.04, "learning_rate": 4.946236559139785e-06, "loss": 1.0446, "step": 23 }, { "epoch": 0.04, "learning_rate": 5.161290322580646e-06, "loss": 0.8575, "step": 24 }, { "epoch": 0.04, "learning_rate": 5.376344086021506e-06, "loss": 1.0841, "step": 25 }, { "epoch": 0.04, "learning_rate": 5.591397849462365e-06, "loss": 0.8858, "step": 26 }, { "epoch": 0.04, "learning_rate": 5.806451612903226e-06, "loss": 0.8906, "step": 27 }, { "epoch": 0.05, "learning_rate": 6.021505376344087e-06, "loss": 0.9767, "step": 28 }, { "epoch": 0.05, "learning_rate": 6.236559139784947e-06, "loss": 0.9643, "step": 29 }, { "epoch": 0.05, "learning_rate": 6.451612903225806e-06, "loss": 0.9092, "step": 30 }, { "epoch": 0.05, "learning_rate": 6.666666666666667e-06, "loss": 1.0521, "step": 31 }, { "epoch": 0.05, "learning_rate": 6.881720430107528e-06, "loss": 0.9098, "step": 32 }, { "epoch": 0.05, "learning_rate": 7.096774193548388e-06, "loss": 0.9272, "step": 33 }, { "epoch": 0.06, "learning_rate": 7.311827956989248e-06, "loss": 0.8742, "step": 34 }, { "epoch": 0.06, "learning_rate": 7.526881720430108e-06, "loss": 1.1277, "step": 35 }, { "epoch": 0.06, "learning_rate": 7.741935483870968e-06, "loss": 0.7706, "step": 36 }, { "epoch": 0.06, "learning_rate": 7.956989247311828e-06, "loss": 0.8616, "step": 37 }, { "epoch": 0.06, "learning_rate": 8.172043010752689e-06, "loss": 0.9557, "step": 38 }, { "epoch": 0.06, "learning_rate": 8.387096774193549e-06, "loss": 0.9309, "step": 39 }, { "epoch": 0.06, "learning_rate": 8.602150537634409e-06, "loss": 0.8642, "step": 40 }, { "epoch": 0.07, "learning_rate": 8.81720430107527e-06, "loss": 0.9252, "step": 41 }, { "epoch": 0.07, "learning_rate": 9.03225806451613e-06, "loss": 0.8501, "step": 42 }, { "epoch": 0.07, "learning_rate": 9.24731182795699e-06, "loss": 0.8667, "step": 43 }, { "epoch": 0.07, "learning_rate": 9.46236559139785e-06, "loss": 0.7737, "step": 44 }, { "epoch": 0.07, "learning_rate": 9.67741935483871e-06, "loss": 0.7438, "step": 45 }, { "epoch": 0.07, "learning_rate": 9.89247311827957e-06, "loss": 0.7747, "step": 46 }, { "epoch": 0.08, "learning_rate": 1.0107526881720431e-05, "loss": 0.7795, "step": 47 }, { "epoch": 0.08, "learning_rate": 1.0322580645161291e-05, "loss": 0.8639, "step": 48 }, { "epoch": 0.08, "learning_rate": 1.0537634408602151e-05, "loss": 0.9908, "step": 49 }, { "epoch": 0.08, "learning_rate": 1.0752688172043012e-05, "loss": 0.827, "step": 50 }, { "epoch": 0.08, "learning_rate": 1.096774193548387e-05, "loss": 0.9554, "step": 51 }, { "epoch": 0.08, "learning_rate": 1.118279569892473e-05, "loss": 0.8337, "step": 52 }, { "epoch": 0.09, "learning_rate": 1.1397849462365593e-05, "loss": 0.7188, "step": 53 }, { "epoch": 0.09, "learning_rate": 1.1612903225806453e-05, "loss": 0.7529, "step": 54 }, { "epoch": 0.09, "learning_rate": 1.1827956989247313e-05, "loss": 0.6377, "step": 55 }, { "epoch": 0.09, "learning_rate": 1.2043010752688173e-05, "loss": 0.975, "step": 56 }, { "epoch": 0.09, "learning_rate": 1.2258064516129034e-05, "loss": 0.6961, "step": 57 }, { "epoch": 0.09, "learning_rate": 1.2473118279569894e-05, "loss": 0.7193, "step": 58 }, { "epoch": 0.1, "learning_rate": 1.2688172043010754e-05, "loss": 0.7281, "step": 59 }, { "epoch": 0.1, "learning_rate": 1.2903225806451613e-05, "loss": 0.7532, "step": 60 }, { "epoch": 0.1, "learning_rate": 1.3118279569892473e-05, "loss": 0.8043, "step": 61 }, { "epoch": 0.1, "learning_rate": 1.3333333333333333e-05, "loss": 0.681, "step": 62 }, { "epoch": 0.1, "learning_rate": 1.3548387096774194e-05, "loss": 0.7393, "step": 63 }, { "epoch": 0.1, "learning_rate": 1.3763440860215056e-05, "loss": 0.7802, "step": 64 }, { "epoch": 0.11, "learning_rate": 1.3978494623655916e-05, "loss": 0.6006, "step": 65 }, { "epoch": 0.11, "learning_rate": 1.4193548387096776e-05, "loss": 0.7925, "step": 66 }, { "epoch": 0.11, "learning_rate": 1.4408602150537636e-05, "loss": 0.5941, "step": 67 }, { "epoch": 0.11, "learning_rate": 1.4623655913978497e-05, "loss": 0.5565, "step": 68 }, { "epoch": 0.11, "learning_rate": 1.4838709677419357e-05, "loss": 0.621, "step": 69 }, { "epoch": 0.11, "learning_rate": 1.5053763440860215e-05, "loss": 0.5699, "step": 70 }, { "epoch": 0.12, "learning_rate": 1.5268817204301076e-05, "loss": 0.6912, "step": 71 }, { "epoch": 0.12, "learning_rate": 1.5483870967741936e-05, "loss": 0.7375, "step": 72 }, { "epoch": 0.12, "learning_rate": 1.5698924731182796e-05, "loss": 0.6683, "step": 73 }, { "epoch": 0.12, "learning_rate": 1.5913978494623657e-05, "loss": 0.6561, "step": 74 }, { "epoch": 0.12, "learning_rate": 1.6129032258064517e-05, "loss": 0.6, "step": 75 }, { "epoch": 0.12, "learning_rate": 1.6344086021505377e-05, "loss": 0.6177, "step": 76 }, { "epoch": 0.12, "learning_rate": 1.6559139784946237e-05, "loss": 0.5427, "step": 77 }, { "epoch": 0.13, "learning_rate": 1.6774193548387098e-05, "loss": 0.4793, "step": 78 }, { "epoch": 0.13, "learning_rate": 1.6989247311827958e-05, "loss": 0.6888, "step": 79 }, { "epoch": 0.13, "learning_rate": 1.7204301075268818e-05, "loss": 0.5594, "step": 80 }, { "epoch": 0.13, "learning_rate": 1.741935483870968e-05, "loss": 0.5696, "step": 81 }, { "epoch": 0.13, "learning_rate": 1.763440860215054e-05, "loss": 0.5298, "step": 82 }, { "epoch": 0.13, "learning_rate": 1.78494623655914e-05, "loss": 0.4511, "step": 83 }, { "epoch": 0.14, "learning_rate": 1.806451612903226e-05, "loss": 0.5594, "step": 84 }, { "epoch": 0.14, "learning_rate": 1.827956989247312e-05, "loss": 0.516, "step": 85 }, { "epoch": 0.14, "learning_rate": 1.849462365591398e-05, "loss": 0.4901, "step": 86 }, { "epoch": 0.14, "learning_rate": 1.870967741935484e-05, "loss": 0.3579, "step": 87 }, { "epoch": 0.14, "learning_rate": 1.89247311827957e-05, "loss": 0.5488, "step": 88 }, { "epoch": 0.14, "learning_rate": 1.913978494623656e-05, "loss": 0.4912, "step": 89 }, { "epoch": 0.15, "learning_rate": 1.935483870967742e-05, "loss": 0.4181, "step": 90 }, { "epoch": 0.15, "learning_rate": 1.956989247311828e-05, "loss": 0.4605, "step": 91 }, { "epoch": 0.15, "learning_rate": 1.978494623655914e-05, "loss": 0.4121, "step": 92 }, { "epoch": 0.15, "learning_rate": 2e-05, "loss": 0.525, "step": 93 }, { "epoch": 0.15, "learning_rate": 2.0215053763440862e-05, "loss": 0.4879, "step": 94 }, { "epoch": 0.15, "learning_rate": 2.0430107526881722e-05, "loss": 0.503, "step": 95 }, { "epoch": 0.16, "learning_rate": 2.0645161290322582e-05, "loss": 0.3593, "step": 96 }, { "epoch": 0.16, "learning_rate": 2.0860215053763443e-05, "loss": 0.4076, "step": 97 }, { "epoch": 0.16, "learning_rate": 2.1075268817204303e-05, "loss": 0.4526, "step": 98 }, { "epoch": 0.16, "learning_rate": 2.1290322580645163e-05, "loss": 0.4707, "step": 99 }, { "epoch": 0.16, "learning_rate": 2.1505376344086024e-05, "loss": 0.4515, "step": 100 }, { "epoch": 0.16, "learning_rate": 2.172043010752688e-05, "loss": 0.3818, "step": 101 }, { "epoch": 0.17, "learning_rate": 2.193548387096774e-05, "loss": 0.4323, "step": 102 }, { "epoch": 0.17, "learning_rate": 2.21505376344086e-05, "loss": 0.5323, "step": 103 }, { "epoch": 0.17, "learning_rate": 2.236559139784946e-05, "loss": 0.4282, "step": 104 }, { "epoch": 0.17, "learning_rate": 2.2580645161290328e-05, "loss": 0.3948, "step": 105 }, { "epoch": 0.17, "learning_rate": 2.2795698924731185e-05, "loss": 0.3642, "step": 106 }, { "epoch": 0.17, "learning_rate": 2.3010752688172045e-05, "loss": 0.411, "step": 107 }, { "epoch": 0.18, "learning_rate": 2.3225806451612906e-05, "loss": 0.542, "step": 108 }, { "epoch": 0.18, "learning_rate": 2.3440860215053766e-05, "loss": 0.5743, "step": 109 }, { "epoch": 0.18, "learning_rate": 2.3655913978494626e-05, "loss": 0.4697, "step": 110 }, { "epoch": 0.18, "learning_rate": 2.3870967741935486e-05, "loss": 0.2843, "step": 111 }, { "epoch": 0.18, "learning_rate": 2.4086021505376347e-05, "loss": 0.6511, "step": 112 }, { "epoch": 0.18, "learning_rate": 2.4301075268817207e-05, "loss": 0.5094, "step": 113 }, { "epoch": 0.18, "learning_rate": 2.4516129032258067e-05, "loss": 0.4962, "step": 114 }, { "epoch": 0.19, "learning_rate": 2.4731182795698928e-05, "loss": 0.4049, "step": 115 }, { "epoch": 0.19, "learning_rate": 2.4946236559139788e-05, "loss": 0.4751, "step": 116 }, { "epoch": 0.19, "learning_rate": 2.5161290322580648e-05, "loss": 0.3049, "step": 117 }, { "epoch": 0.19, "learning_rate": 2.537634408602151e-05, "loss": 0.3986, "step": 118 }, { "epoch": 0.19, "learning_rate": 2.559139784946237e-05, "loss": 0.4498, "step": 119 }, { "epoch": 0.19, "learning_rate": 2.5806451612903226e-05, "loss": 0.5182, "step": 120 }, { "epoch": 0.2, "learning_rate": 2.6021505376344086e-05, "loss": 0.4625, "step": 121 }, { "epoch": 0.2, "learning_rate": 2.6236559139784946e-05, "loss": 0.3401, "step": 122 }, { "epoch": 0.2, "learning_rate": 2.6451612903225806e-05, "loss": 0.5425, "step": 123 }, { "epoch": 0.2, "learning_rate": 2.6666666666666667e-05, "loss": 0.4276, "step": 124 }, { "epoch": 0.2, "learning_rate": 2.6881720430107527e-05, "loss": 0.3928, "step": 125 }, { "epoch": 0.2, "learning_rate": 2.7096774193548387e-05, "loss": 0.3693, "step": 126 }, { "epoch": 0.21, "learning_rate": 2.7311827956989247e-05, "loss": 0.3715, "step": 127 }, { "epoch": 0.21, "learning_rate": 2.752688172043011e-05, "loss": 0.4745, "step": 128 }, { "epoch": 0.21, "learning_rate": 2.774193548387097e-05, "loss": 0.3067, "step": 129 }, { "epoch": 0.21, "learning_rate": 2.795698924731183e-05, "loss": 0.4463, "step": 130 }, { "epoch": 0.21, "learning_rate": 2.8172043010752692e-05, "loss": 0.4669, "step": 131 }, { "epoch": 0.21, "learning_rate": 2.8387096774193552e-05, "loss": 0.4197, "step": 132 }, { "epoch": 0.22, "learning_rate": 2.8602150537634412e-05, "loss": 0.3471, "step": 133 }, { "epoch": 0.22, "learning_rate": 2.8817204301075273e-05, "loss": 0.2908, "step": 134 }, { "epoch": 0.22, "learning_rate": 2.9032258064516133e-05, "loss": 0.4127, "step": 135 }, { "epoch": 0.22, "learning_rate": 2.9247311827956993e-05, "loss": 0.4012, "step": 136 }, { "epoch": 0.22, "learning_rate": 2.9462365591397853e-05, "loss": 0.4027, "step": 137 }, { "epoch": 0.22, "learning_rate": 2.9677419354838714e-05, "loss": 0.4027, "step": 138 }, { "epoch": 0.23, "learning_rate": 2.9892473118279574e-05, "loss": 0.3629, "step": 139 }, { "epoch": 0.23, "learning_rate": 3.010752688172043e-05, "loss": 0.4829, "step": 140 }, { "epoch": 0.23, "learning_rate": 3.032258064516129e-05, "loss": 0.3413, "step": 141 }, { "epoch": 0.23, "learning_rate": 3.053763440860215e-05, "loss": 0.4558, "step": 142 }, { "epoch": 0.23, "learning_rate": 3.075268817204301e-05, "loss": 0.3402, "step": 143 }, { "epoch": 0.23, "learning_rate": 3.096774193548387e-05, "loss": 0.4753, "step": 144 }, { "epoch": 0.24, "learning_rate": 3.118279569892473e-05, "loss": 0.4989, "step": 145 }, { "epoch": 0.24, "learning_rate": 3.139784946236559e-05, "loss": 0.4822, "step": 146 }, { "epoch": 0.24, "learning_rate": 3.161290322580645e-05, "loss": 0.3282, "step": 147 }, { "epoch": 0.24, "learning_rate": 3.182795698924731e-05, "loss": 0.3056, "step": 148 }, { "epoch": 0.24, "learning_rate": 3.204301075268817e-05, "loss": 0.3184, "step": 149 }, { "epoch": 0.24, "learning_rate": 3.2258064516129034e-05, "loss": 0.4174, "step": 150 }, { "epoch": 0.24, "learning_rate": 3.2473118279569894e-05, "loss": 0.3653, "step": 151 }, { "epoch": 0.25, "learning_rate": 3.2688172043010754e-05, "loss": 0.4751, "step": 152 }, { "epoch": 0.25, "learning_rate": 3.2903225806451614e-05, "loss": 0.3685, "step": 153 }, { "epoch": 0.25, "learning_rate": 3.3118279569892475e-05, "loss": 0.2924, "step": 154 }, { "epoch": 0.25, "learning_rate": 3.3333333333333335e-05, "loss": 0.3684, "step": 155 }, { "epoch": 0.25, "learning_rate": 3.3548387096774195e-05, "loss": 0.4301, "step": 156 }, { "epoch": 0.25, "learning_rate": 3.3763440860215055e-05, "loss": 0.4983, "step": 157 }, { "epoch": 0.26, "learning_rate": 3.3978494623655916e-05, "loss": 0.3636, "step": 158 }, { "epoch": 0.26, "learning_rate": 3.4193548387096776e-05, "loss": 0.3687, "step": 159 }, { "epoch": 0.26, "learning_rate": 3.4408602150537636e-05, "loss": 0.3472, "step": 160 }, { "epoch": 0.26, "learning_rate": 3.4623655913978497e-05, "loss": 0.4539, "step": 161 }, { "epoch": 0.26, "learning_rate": 3.483870967741936e-05, "loss": 0.3627, "step": 162 }, { "epoch": 0.26, "learning_rate": 3.505376344086022e-05, "loss": 0.2852, "step": 163 }, { "epoch": 0.27, "learning_rate": 3.526881720430108e-05, "loss": 0.4188, "step": 164 }, { "epoch": 0.27, "learning_rate": 3.548387096774194e-05, "loss": 0.3719, "step": 165 }, { "epoch": 0.27, "learning_rate": 3.56989247311828e-05, "loss": 0.5377, "step": 166 }, { "epoch": 0.27, "learning_rate": 3.591397849462366e-05, "loss": 0.3597, "step": 167 }, { "epoch": 0.27, "learning_rate": 3.612903225806452e-05, "loss": 0.4433, "step": 168 }, { "epoch": 0.27, "learning_rate": 3.634408602150538e-05, "loss": 0.3789, "step": 169 }, { "epoch": 0.28, "learning_rate": 3.655913978494624e-05, "loss": 0.3546, "step": 170 }, { "epoch": 0.28, "learning_rate": 3.67741935483871e-05, "loss": 0.3547, "step": 171 }, { "epoch": 0.28, "learning_rate": 3.698924731182796e-05, "loss": 0.4064, "step": 172 }, { "epoch": 0.28, "learning_rate": 3.720430107526882e-05, "loss": 0.4175, "step": 173 }, { "epoch": 0.28, "learning_rate": 3.741935483870968e-05, "loss": 0.4955, "step": 174 }, { "epoch": 0.28, "learning_rate": 3.763440860215054e-05, "loss": 0.4112, "step": 175 }, { "epoch": 0.29, "learning_rate": 3.78494623655914e-05, "loss": 0.4142, "step": 176 }, { "epoch": 0.29, "learning_rate": 3.806451612903226e-05, "loss": 0.344, "step": 177 }, { "epoch": 0.29, "learning_rate": 3.827956989247312e-05, "loss": 0.3419, "step": 178 }, { "epoch": 0.29, "learning_rate": 3.849462365591398e-05, "loss": 0.3962, "step": 179 }, { "epoch": 0.29, "learning_rate": 3.870967741935484e-05, "loss": 0.3779, "step": 180 }, { "epoch": 0.29, "learning_rate": 3.89247311827957e-05, "loss": 0.373, "step": 181 }, { "epoch": 0.29, "learning_rate": 3.913978494623656e-05, "loss": 0.3787, "step": 182 }, { "epoch": 0.3, "learning_rate": 3.935483870967742e-05, "loss": 0.3989, "step": 183 }, { "epoch": 0.3, "learning_rate": 3.956989247311828e-05, "loss": 0.2785, "step": 184 }, { "epoch": 0.3, "learning_rate": 3.978494623655914e-05, "loss": 0.2957, "step": 185 }, { "epoch": 0.3, "learning_rate": 4e-05, "loss": 0.3883, "step": 186 }, { "epoch": 0.3, "learning_rate": 3.999999724376296e-05, "loss": 0.3884, "step": 187 }, { "epoch": 0.3, "learning_rate": 3.9999988975052576e-05, "loss": 0.3579, "step": 188 }, { "epoch": 0.31, "learning_rate": 3.9999975193871145e-05, "loss": 0.4541, "step": 189 }, { "epoch": 0.31, "learning_rate": 3.9999955900222456e-05, "loss": 0.3559, "step": 190 }, { "epoch": 0.31, "learning_rate": 3.999993109411183e-05, "loss": 0.4308, "step": 191 }, { "epoch": 0.31, "learning_rate": 3.999990077554611e-05, "loss": 0.3869, "step": 192 }, { "epoch": 0.31, "learning_rate": 3.999986494453364e-05, "loss": 0.5156, "step": 193 }, { "epoch": 0.31, "learning_rate": 3.9999823601084306e-05, "loss": 0.3499, "step": 194 }, { "epoch": 0.32, "learning_rate": 3.99997767452095e-05, "loss": 0.419, "step": 195 }, { "epoch": 0.32, "learning_rate": 3.999972437692213e-05, "loss": 0.3778, "step": 196 }, { "epoch": 0.32, "learning_rate": 3.999966649623664e-05, "loss": 0.3656, "step": 197 }, { "epoch": 0.32, "learning_rate": 3.999960310316898e-05, "loss": 0.3598, "step": 198 }, { "epoch": 0.32, "learning_rate": 3.999953419773662e-05, "loss": 0.31, "step": 199 }, { "epoch": 0.32, "learning_rate": 3.999945977995855e-05, "loss": 0.389, "step": 200 }, { "epoch": 0.33, "learning_rate": 3.999937984985529e-05, "loss": 0.4009, "step": 201 }, { "epoch": 0.33, "learning_rate": 3.999929440744887e-05, "loss": 0.4953, "step": 202 }, { "epoch": 0.33, "learning_rate": 3.999920345276283e-05, "loss": 0.4235, "step": 203 }, { "epoch": 0.33, "learning_rate": 3.9999106985822255e-05, "loss": 0.384, "step": 204 }, { "epoch": 0.33, "learning_rate": 3.999900500665371e-05, "loss": 0.3639, "step": 205 }, { "epoch": 0.33, "learning_rate": 3.9998897515285323e-05, "loss": 0.4425, "step": 206 }, { "epoch": 0.34, "learning_rate": 3.999878451174671e-05, "loss": 0.4033, "step": 207 }, { "epoch": 0.34, "learning_rate": 3.999866599606903e-05, "loss": 0.4741, "step": 208 }, { "epoch": 0.34, "learning_rate": 3.999854196828493e-05, "loss": 0.3423, "step": 209 }, { "epoch": 0.34, "learning_rate": 3.9998412428428613e-05, "loss": 0.42, "step": 210 }, { "epoch": 0.34, "learning_rate": 3.999827737653578e-05, "loss": 0.4133, "step": 211 }, { "epoch": 0.34, "learning_rate": 3.9998136812643644e-05, "loss": 0.3348, "step": 212 }, { "epoch": 0.35, "learning_rate": 3.999799073679096e-05, "loss": 0.3934, "step": 213 }, { "epoch": 0.35, "learning_rate": 3.999783914901798e-05, "loss": 0.4112, "step": 214 }, { "epoch": 0.35, "learning_rate": 3.9997682049366485e-05, "loss": 0.2863, "step": 215 }, { "epoch": 0.35, "learning_rate": 3.999751943787979e-05, "loss": 0.4174, "step": 216 }, { "epoch": 0.35, "learning_rate": 3.99973513146027e-05, "loss": 0.37, "step": 217 }, { "epoch": 0.35, "learning_rate": 3.9997177679581555e-05, "loss": 0.4872, "step": 218 }, { "epoch": 0.35, "learning_rate": 3.999699853286422e-05, "loss": 0.4023, "step": 219 }, { "epoch": 0.36, "learning_rate": 3.999681387450007e-05, "loss": 0.3799, "step": 220 }, { "epoch": 0.36, "learning_rate": 3.9996623704539995e-05, "loss": 0.3077, "step": 221 }, { "epoch": 0.36, "learning_rate": 3.9996428023036415e-05, "loss": 0.2926, "step": 222 }, { "epoch": 0.36, "learning_rate": 3.999622683004327e-05, "loss": 0.3323, "step": 223 }, { "epoch": 0.36, "learning_rate": 3.9996020125616005e-05, "loss": 0.448, "step": 224 }, { "epoch": 0.36, "learning_rate": 3.9995807909811594e-05, "loss": 0.4418, "step": 225 }, { "epoch": 0.37, "learning_rate": 3.999559018268853e-05, "loss": 0.4574, "step": 226 }, { "epoch": 0.37, "learning_rate": 3.999536694430682e-05, "loss": 0.2433, "step": 227 }, { "epoch": 0.37, "learning_rate": 3.9995138194728006e-05, "loss": 0.4125, "step": 228 }, { "epoch": 0.37, "learning_rate": 3.999490393401512e-05, "loss": 0.429, "step": 229 }, { "epoch": 0.37, "learning_rate": 3.999466416223275e-05, "loss": 0.2954, "step": 230 }, { "epoch": 0.37, "learning_rate": 3.999441887944696e-05, "loss": 0.4206, "step": 231 }, { "epoch": 0.38, "learning_rate": 3.9994168085725375e-05, "loss": 0.4191, "step": 232 }, { "epoch": 0.38, "learning_rate": 3.999391178113711e-05, "loss": 0.4855, "step": 233 }, { "epoch": 0.38, "learning_rate": 3.9993649965752804e-05, "loss": 0.4385, "step": 234 }, { "epoch": 0.38, "learning_rate": 3.999338263964463e-05, "loss": 0.4419, "step": 235 }, { "epoch": 0.38, "learning_rate": 3.999310980288627e-05, "loss": 0.3091, "step": 236 }, { "epoch": 0.38, "learning_rate": 3.999283145555291e-05, "loss": 0.3331, "step": 237 }, { "epoch": 0.39, "learning_rate": 3.9992547597721283e-05, "loss": 0.3554, "step": 238 }, { "epoch": 0.39, "learning_rate": 3.9992258229469626e-05, "loss": 0.3082, "step": 239 }, { "epoch": 0.39, "learning_rate": 3.9991963350877684e-05, "loss": 0.3481, "step": 240 }, { "epoch": 0.39, "learning_rate": 3.999166296202675e-05, "loss": 0.4176, "step": 241 }, { "epoch": 0.39, "learning_rate": 3.99913570629996e-05, "loss": 0.3463, "step": 242 }, { "epoch": 0.39, "learning_rate": 3.999104565388056e-05, "loss": 0.343, "step": 243 }, { "epoch": 0.4, "learning_rate": 3.999072873475546e-05, "loss": 0.3479, "step": 244 }, { "epoch": 0.4, "learning_rate": 3.9990406305711645e-05, "loss": 0.3924, "step": 245 }, { "epoch": 0.4, "learning_rate": 3.999007836683799e-05, "loss": 0.2858, "step": 246 }, { "epoch": 0.4, "learning_rate": 3.998974491822488e-05, "loss": 0.3633, "step": 247 }, { "epoch": 0.4, "learning_rate": 3.998940595996422e-05, "loss": 0.3026, "step": 248 }, { "epoch": 0.4, "learning_rate": 3.998906149214944e-05, "loss": 0.3922, "step": 249 }, { "epoch": 0.41, "learning_rate": 3.998871151487548e-05, "loss": 0.3877, "step": 250 }, { "epoch": 0.41, "learning_rate": 3.9988356028238796e-05, "loss": 0.4298, "step": 251 }, { "epoch": 0.41, "learning_rate": 3.998799503233738e-05, "loss": 0.3368, "step": 252 }, { "epoch": 0.41, "learning_rate": 3.998762852727072e-05, "loss": 0.2863, "step": 253 }, { "epoch": 0.41, "learning_rate": 3.998725651313984e-05, "loss": 0.3264, "step": 254 }, { "epoch": 0.41, "learning_rate": 3.998687899004727e-05, "loss": 0.3739, "step": 255 }, { "epoch": 0.41, "learning_rate": 3.998649595809708e-05, "loss": 0.257, "step": 256 }, { "epoch": 0.42, "learning_rate": 3.998610741739483e-05, "loss": 0.3744, "step": 257 }, { "epoch": 0.42, "learning_rate": 3.998571336804761e-05, "loss": 0.3697, "step": 258 }, { "epoch": 0.42, "learning_rate": 3.998531381016402e-05, "loss": 0.3731, "step": 259 }, { "epoch": 0.42, "learning_rate": 3.9984908743854216e-05, "loss": 0.3865, "step": 260 }, { "epoch": 0.42, "learning_rate": 3.998449816922983e-05, "loss": 0.3865, "step": 261 }, { "epoch": 0.42, "learning_rate": 3.9984082086404015e-05, "loss": 0.4572, "step": 262 }, { "epoch": 0.43, "learning_rate": 3.9983660495491464e-05, "loss": 0.2616, "step": 263 }, { "epoch": 0.43, "learning_rate": 3.9983233396608375e-05, "loss": 0.2741, "step": 264 }, { "epoch": 0.43, "learning_rate": 3.9982800789872466e-05, "loss": 0.3781, "step": 265 }, { "epoch": 0.43, "learning_rate": 3.998236267540298e-05, "loss": 0.3474, "step": 266 }, { "epoch": 0.43, "learning_rate": 3.9981919053320666e-05, "loss": 0.4531, "step": 267 }, { "epoch": 0.43, "learning_rate": 3.998146992374779e-05, "loss": 0.3476, "step": 268 }, { "epoch": 0.44, "learning_rate": 3.998101528680816e-05, "loss": 0.2615, "step": 269 }, { "epoch": 0.44, "learning_rate": 3.9980555142627065e-05, "loss": 0.4293, "step": 270 }, { "epoch": 0.44, "learning_rate": 3.9980089491331344e-05, "loss": 0.3541, "step": 271 }, { "epoch": 0.44, "learning_rate": 3.9979618333049345e-05, "loss": 0.3604, "step": 272 }, { "epoch": 0.44, "learning_rate": 3.997914166791092e-05, "loss": 0.4744, "step": 273 }, { "epoch": 0.44, "learning_rate": 3.9978659496047456e-05, "loss": 0.2782, "step": 274 }, { "epoch": 0.45, "learning_rate": 3.997817181759185e-05, "loss": 0.3068, "step": 275 }, { "epoch": 0.45, "learning_rate": 3.99776786326785e-05, "loss": 0.4382, "step": 276 }, { "epoch": 0.45, "learning_rate": 3.997717994144338e-05, "loss": 0.3189, "step": 277 }, { "epoch": 0.45, "learning_rate": 3.99766757440239e-05, "loss": 0.3556, "step": 278 }, { "epoch": 0.45, "learning_rate": 3.9976166040559053e-05, "loss": 0.2674, "step": 279 }, { "epoch": 0.45, "learning_rate": 3.997565083118931e-05, "loss": 0.3097, "step": 280 }, { "epoch": 0.46, "learning_rate": 3.997513011605669e-05, "loss": 0.2423, "step": 281 }, { "epoch": 0.46, "learning_rate": 3.997460389530471e-05, "loss": 0.4076, "step": 282 }, { "epoch": 0.46, "learning_rate": 3.997407216907839e-05, "loss": 0.4966, "step": 283 }, { "epoch": 0.46, "learning_rate": 3.997353493752432e-05, "loss": 0.3497, "step": 284 }, { "epoch": 0.46, "learning_rate": 3.997299220079055e-05, "loss": 0.321, "step": 285 }, { "epoch": 0.46, "learning_rate": 3.997244395902668e-05, "loss": 0.3787, "step": 286 }, { "epoch": 0.47, "learning_rate": 3.997189021238382e-05, "loss": 0.343, "step": 287 }, { "epoch": 0.47, "learning_rate": 3.997133096101458e-05, "loss": 0.3467, "step": 288 }, { "epoch": 0.47, "learning_rate": 3.997076620507312e-05, "loss": 0.3208, "step": 289 }, { "epoch": 0.47, "learning_rate": 3.9970195944715096e-05, "loss": 0.3539, "step": 290 }, { "epoch": 0.47, "learning_rate": 3.996962018009768e-05, "loss": 0.4606, "step": 291 }, { "epoch": 0.47, "learning_rate": 3.9969038911379574e-05, "loss": 0.3344, "step": 292 }, { "epoch": 0.47, "learning_rate": 3.996845213872099e-05, "loss": 0.4104, "step": 293 }, { "epoch": 0.48, "learning_rate": 3.996785986228364e-05, "loss": 0.4371, "step": 294 }, { "epoch": 0.48, "learning_rate": 3.9967262082230794e-05, "loss": 0.3972, "step": 295 }, { "epoch": 0.48, "learning_rate": 3.99666587987272e-05, "loss": 0.3405, "step": 296 }, { "epoch": 0.48, "learning_rate": 3.996605001193913e-05, "loss": 0.3089, "step": 297 }, { "epoch": 0.48, "learning_rate": 3.9965435722034395e-05, "loss": 0.3569, "step": 298 }, { "epoch": 0.48, "learning_rate": 3.9964815929182304e-05, "loss": 0.3581, "step": 299 }, { "epoch": 0.49, "learning_rate": 3.996419063355368e-05, "loss": 0.4202, "step": 300 }, { "epoch": 0.49, "learning_rate": 3.996355983532087e-05, "loss": 0.3041, "step": 301 }, { "epoch": 0.49, "learning_rate": 3.996292353465775e-05, "loss": 0.4019, "step": 302 }, { "epoch": 0.49, "learning_rate": 3.996228173173969e-05, "loss": 0.2409, "step": 303 }, { "epoch": 0.49, "learning_rate": 3.996163442674359e-05, "loss": 0.3419, "step": 304 }, { "epoch": 0.49, "learning_rate": 3.9960981619847856e-05, "loss": 0.321, "step": 305 }, { "epoch": 0.5, "learning_rate": 3.996032331123242e-05, "loss": 0.4629, "step": 306 }, { "epoch": 0.5, "learning_rate": 3.995965950107872e-05, "loss": 0.3657, "step": 307 }, { "epoch": 0.5, "learning_rate": 3.9958990189569735e-05, "loss": 0.5202, "step": 308 }, { "epoch": 0.5, "learning_rate": 3.995831537688993e-05, "loss": 0.4219, "step": 309 }, { "epoch": 0.5, "learning_rate": 3.9957635063225305e-05, "loss": 0.3766, "step": 310 }, { "epoch": 0.5, "learning_rate": 3.995694924876336e-05, "loss": 0.2759, "step": 311 }, { "epoch": 0.51, "learning_rate": 3.9956257933693144e-05, "loss": 0.374, "step": 312 }, { "epoch": 0.51, "learning_rate": 3.995556111820517e-05, "loss": 0.4295, "step": 313 }, { "epoch": 0.51, "learning_rate": 3.995485880249153e-05, "loss": 0.3173, "step": 314 }, { "epoch": 0.51, "learning_rate": 3.9954150986745775e-05, "loss": 0.4559, "step": 315 }, { "epoch": 0.51, "learning_rate": 3.9953437671163e-05, "loss": 0.3532, "step": 316 }, { "epoch": 0.51, "learning_rate": 3.9952718855939814e-05, "loss": 0.407, "step": 317 }, { "epoch": 0.52, "learning_rate": 3.9951994541274345e-05, "loss": 0.2983, "step": 318 }, { "epoch": 0.52, "learning_rate": 3.995126472736622e-05, "loss": 0.4578, "step": 319 }, { "epoch": 0.52, "learning_rate": 3.9950529414416605e-05, "loss": 0.4305, "step": 320 }, { "epoch": 0.52, "learning_rate": 3.994978860262816e-05, "loss": 0.3519, "step": 321 }, { "epoch": 0.52, "learning_rate": 3.994904229220507e-05, "loss": 0.3599, "step": 322 }, { "epoch": 0.52, "learning_rate": 3.9948290483353054e-05, "loss": 0.3785, "step": 323 }, { "epoch": 0.53, "learning_rate": 3.99475331762793e-05, "loss": 0.3852, "step": 324 }, { "epoch": 0.53, "learning_rate": 3.994677037119256e-05, "loss": 0.2715, "step": 325 }, { "epoch": 0.53, "learning_rate": 3.9946002068303076e-05, "loss": 0.2635, "step": 326 }, { "epoch": 0.53, "learning_rate": 3.9945228267822604e-05, "loss": 0.3767, "step": 327 }, { "epoch": 0.53, "learning_rate": 3.994444896996443e-05, "loss": 0.2938, "step": 328 }, { "epoch": 0.53, "learning_rate": 3.9943664174943356e-05, "loss": 0.278, "step": 329 }, { "epoch": 0.53, "learning_rate": 3.9942873882975665e-05, "loss": 0.3325, "step": 330 }, { "epoch": 0.54, "learning_rate": 3.99420780942792e-05, "loss": 0.2839, "step": 331 }, { "epoch": 0.54, "learning_rate": 3.9941276809073285e-05, "loss": 0.365, "step": 332 }, { "epoch": 0.54, "learning_rate": 3.994047002757879e-05, "loss": 0.3689, "step": 333 }, { "epoch": 0.54, "learning_rate": 3.993965775001807e-05, "loss": 0.273, "step": 334 }, { "epoch": 0.54, "learning_rate": 3.993883997661501e-05, "loss": 0.3326, "step": 335 }, { "epoch": 0.54, "learning_rate": 3.993801670759502e-05, "loss": 0.317, "step": 336 }, { "epoch": 0.55, "learning_rate": 3.9937187943184996e-05, "loss": 0.4371, "step": 337 }, { "epoch": 0.55, "learning_rate": 3.9936353683613374e-05, "loss": 0.3921, "step": 338 }, { "epoch": 0.55, "learning_rate": 3.993551392911009e-05, "loss": 0.302, "step": 339 }, { "epoch": 0.55, "learning_rate": 3.9934668679906606e-05, "loss": 0.2809, "step": 340 }, { "epoch": 0.55, "learning_rate": 3.993381793623589e-05, "loss": 0.3393, "step": 341 }, { "epoch": 0.55, "learning_rate": 3.993296169833242e-05, "loss": 0.3966, "step": 342 }, { "epoch": 0.56, "learning_rate": 3.993209996643221e-05, "loss": 0.3407, "step": 343 }, { "epoch": 0.56, "learning_rate": 3.993123274077277e-05, "loss": 0.2956, "step": 344 }, { "epoch": 0.56, "learning_rate": 3.993036002159311e-05, "loss": 0.448, "step": 345 }, { "epoch": 0.56, "learning_rate": 3.9929481809133806e-05, "loss": 0.4277, "step": 346 }, { "epoch": 0.56, "learning_rate": 3.9928598103636884e-05, "loss": 0.4245, "step": 347 }, { "epoch": 0.56, "learning_rate": 3.992770890534592e-05, "loss": 0.4114, "step": 348 }, { "epoch": 0.57, "learning_rate": 3.992681421450601e-05, "loss": 0.3528, "step": 349 }, { "epoch": 0.57, "learning_rate": 3.992591403136375e-05, "loss": 0.3025, "step": 350 }, { "epoch": 0.57, "learning_rate": 3.992500835616724e-05, "loss": 0.325, "step": 351 }, { "epoch": 0.57, "learning_rate": 3.992409718916611e-05, "loss": 0.4984, "step": 352 }, { "epoch": 0.57, "learning_rate": 3.992318053061151e-05, "loss": 0.2945, "step": 353 }, { "epoch": 0.57, "learning_rate": 3.9922258380756076e-05, "loss": 0.3904, "step": 354 }, { "epoch": 0.58, "learning_rate": 3.992133073985399e-05, "loss": 0.4449, "step": 355 }, { "epoch": 0.58, "learning_rate": 3.9920397608160925e-05, "loss": 0.3244, "step": 356 }, { "epoch": 0.58, "learning_rate": 3.9919458985934067e-05, "loss": 0.3344, "step": 357 }, { "epoch": 0.58, "learning_rate": 3.991851487343213e-05, "loss": 0.3537, "step": 358 }, { "epoch": 0.58, "learning_rate": 3.991756527091534e-05, "loss": 0.3184, "step": 359 }, { "epoch": 0.58, "learning_rate": 3.991661017864542e-05, "loss": 0.3639, "step": 360 }, { "epoch": 0.59, "learning_rate": 3.991564959688562e-05, "loss": 0.3565, "step": 361 }, { "epoch": 0.59, "learning_rate": 3.991468352590069e-05, "loss": 0.3393, "step": 362 }, { "epoch": 0.59, "learning_rate": 3.991371196595692e-05, "loss": 0.4489, "step": 363 }, { "epoch": 0.59, "learning_rate": 3.991273491732209e-05, "loss": 0.405, "step": 364 }, { "epoch": 0.59, "learning_rate": 3.991175238026548e-05, "loss": 0.3494, "step": 365 }, { "epoch": 0.59, "learning_rate": 3.991076435505792e-05, "loss": 0.2723, "step": 366 }, { "epoch": 0.59, "learning_rate": 3.990977084197173e-05, "loss": 0.4302, "step": 367 }, { "epoch": 0.6, "learning_rate": 3.9908771841280733e-05, "loss": 0.4417, "step": 368 }, { "epoch": 0.6, "learning_rate": 3.990776735326029e-05, "loss": 0.3441, "step": 369 }, { "epoch": 0.6, "learning_rate": 3.9906757378187266e-05, "loss": 0.3178, "step": 370 }, { "epoch": 0.6, "learning_rate": 3.990574191634002e-05, "loss": 0.4452, "step": 371 }, { "epoch": 0.6, "learning_rate": 3.9904720967998447e-05, "loss": 0.3529, "step": 372 }, { "epoch": 0.6, "learning_rate": 3.990369453344394e-05, "loss": 0.3367, "step": 373 }, { "epoch": 0.61, "learning_rate": 3.9902662612959407e-05, "loss": 0.3794, "step": 374 }, { "epoch": 0.61, "learning_rate": 3.990162520682928e-05, "loss": 0.3904, "step": 375 }, { "epoch": 0.61, "learning_rate": 3.990058231533948e-05, "loss": 0.3457, "step": 376 }, { "epoch": 0.61, "learning_rate": 3.989953393877747e-05, "loss": 0.2847, "step": 377 }, { "epoch": 0.61, "learning_rate": 3.9898480077432184e-05, "loss": 0.3599, "step": 378 }, { "epoch": 0.61, "learning_rate": 3.98974207315941e-05, "loss": 0.3723, "step": 379 }, { "epoch": 0.62, "learning_rate": 3.989635590155521e-05, "loss": 0.3001, "step": 380 }, { "epoch": 0.62, "learning_rate": 3.989528558760899e-05, "loss": 0.4105, "step": 381 }, { "epoch": 0.62, "learning_rate": 3.9894209790050466e-05, "loss": 0.4839, "step": 382 }, { "epoch": 0.62, "learning_rate": 3.9893128509176125e-05, "loss": 0.3939, "step": 383 }, { "epoch": 0.62, "learning_rate": 3.989204174528402e-05, "loss": 0.3524, "step": 384 }, { "epoch": 0.62, "learning_rate": 3.989094949867367e-05, "loss": 0.3909, "step": 385 }, { "epoch": 0.63, "learning_rate": 3.9889851769646125e-05, "loss": 0.325, "step": 386 }, { "epoch": 0.63, "learning_rate": 3.988874855850396e-05, "loss": 0.2442, "step": 387 }, { "epoch": 0.63, "learning_rate": 3.9887639865551236e-05, "loss": 0.3026, "step": 388 }, { "epoch": 0.63, "learning_rate": 3.988652569109353e-05, "loss": 0.3241, "step": 389 }, { "epoch": 0.63, "learning_rate": 3.9885406035437953e-05, "loss": 0.4059, "step": 390 }, { "epoch": 0.63, "learning_rate": 3.988428089889309e-05, "loss": 0.3828, "step": 391 }, { "epoch": 0.64, "learning_rate": 3.9883150281769055e-05, "loss": 0.4267, "step": 392 }, { "epoch": 0.64, "learning_rate": 3.988201418437749e-05, "loss": 0.3307, "step": 393 }, { "epoch": 0.64, "learning_rate": 3.988087260703152e-05, "loss": 0.3664, "step": 394 }, { "epoch": 0.64, "learning_rate": 3.9879725550045786e-05, "loss": 0.3905, "step": 395 }, { "epoch": 0.64, "learning_rate": 3.9878573013736456e-05, "loss": 0.3471, "step": 396 }, { "epoch": 0.64, "learning_rate": 3.987741499842118e-05, "loss": 0.3833, "step": 397 }, { "epoch": 0.65, "learning_rate": 3.9876251504419154e-05, "loss": 0.3789, "step": 398 }, { "epoch": 0.65, "learning_rate": 3.9875082532051045e-05, "loss": 0.2823, "step": 399 }, { "epoch": 0.65, "learning_rate": 3.987390808163906e-05, "loss": 0.3488, "step": 400 }, { "epoch": 0.65, "learning_rate": 3.987272815350691e-05, "loss": 0.314, "step": 401 }, { "epoch": 0.65, "learning_rate": 3.987154274797981e-05, "loss": 0.3077, "step": 402 }, { "epoch": 0.65, "learning_rate": 3.9870351865384475e-05, "loss": 0.3097, "step": 403 }, { "epoch": 0.65, "learning_rate": 3.9869155506049146e-05, "loss": 0.3101, "step": 404 }, { "epoch": 0.66, "learning_rate": 3.986795367030357e-05, "loss": 0.356, "step": 405 }, { "epoch": 0.66, "learning_rate": 3.9866746358479e-05, "loss": 0.2775, "step": 406 }, { "epoch": 0.66, "learning_rate": 3.98655335709082e-05, "loss": 0.3925, "step": 407 }, { "epoch": 0.66, "learning_rate": 3.986431530792545e-05, "loss": 0.3274, "step": 408 }, { "epoch": 0.66, "learning_rate": 3.986309156986652e-05, "loss": 0.2424, "step": 409 }, { "epoch": 0.66, "learning_rate": 3.9861862357068705e-05, "loss": 0.3038, "step": 410 }, { "epoch": 0.67, "learning_rate": 3.9860627669870805e-05, "loss": 0.3521, "step": 411 }, { "epoch": 0.67, "learning_rate": 3.985938750861313e-05, "loss": 0.4103, "step": 412 }, { "epoch": 0.67, "learning_rate": 3.98581418736375e-05, "loss": 0.3318, "step": 413 }, { "epoch": 0.67, "learning_rate": 3.985689076528725e-05, "loss": 0.3583, "step": 414 }, { "epoch": 0.67, "learning_rate": 3.9855634183907195e-05, "loss": 0.4534, "step": 415 }, { "epoch": 0.67, "learning_rate": 3.9854372129843685e-05, "loss": 0.4027, "step": 416 }, { "epoch": 0.68, "learning_rate": 3.985310460344458e-05, "loss": 0.3073, "step": 417 }, { "epoch": 0.68, "learning_rate": 3.9851831605059244e-05, "loss": 0.4138, "step": 418 }, { "epoch": 0.68, "learning_rate": 3.985055313503853e-05, "loss": 0.3734, "step": 419 }, { "epoch": 0.68, "learning_rate": 3.9849269193734826e-05, "loss": 0.3491, "step": 420 }, { "epoch": 0.68, "learning_rate": 3.9847979781502004e-05, "loss": 0.3936, "step": 421 }, { "epoch": 0.68, "learning_rate": 3.9846684898695474e-05, "loss": 0.3073, "step": 422 }, { "epoch": 0.69, "learning_rate": 3.984538454567213e-05, "loss": 0.3222, "step": 423 }, { "epoch": 0.69, "learning_rate": 3.984407872279037e-05, "loss": 0.3103, "step": 424 }, { "epoch": 0.69, "learning_rate": 3.984276743041012e-05, "loss": 0.3117, "step": 425 }, { "epoch": 0.69, "learning_rate": 3.984145066889281e-05, "loss": 0.333, "step": 426 }, { "epoch": 0.69, "learning_rate": 3.984012843860135e-05, "loss": 0.3864, "step": 427 }, { "epoch": 0.69, "learning_rate": 3.98388007399002e-05, "loss": 0.4073, "step": 428 }, { "epoch": 0.7, "learning_rate": 3.983746757315529e-05, "loss": 0.3109, "step": 429 }, { "epoch": 0.7, "learning_rate": 3.9836128938734075e-05, "loss": 0.3776, "step": 430 }, { "epoch": 0.7, "learning_rate": 3.983478483700552e-05, "loss": 0.3299, "step": 431 }, { "epoch": 0.7, "learning_rate": 3.9833435268340085e-05, "loss": 0.3547, "step": 432 }, { "epoch": 0.7, "learning_rate": 3.983208023310975e-05, "loss": 0.351, "step": 433 }, { "epoch": 0.7, "learning_rate": 3.983071973168799e-05, "loss": 0.2776, "step": 434 }, { "epoch": 0.71, "learning_rate": 3.982935376444979e-05, "loss": 0.2897, "step": 435 }, { "epoch": 0.71, "learning_rate": 3.982798233177165e-05, "loss": 0.2587, "step": 436 }, { "epoch": 0.71, "learning_rate": 3.982660543403156e-05, "loss": 0.3473, "step": 437 }, { "epoch": 0.71, "learning_rate": 3.982522307160903e-05, "loss": 0.3352, "step": 438 }, { "epoch": 0.71, "learning_rate": 3.982383524488508e-05, "loss": 0.3391, "step": 439 }, { "epoch": 0.71, "learning_rate": 3.982244195424221e-05, "loss": 0.3912, "step": 440 }, { "epoch": 0.71, "learning_rate": 3.982104320006446e-05, "loss": 0.3365, "step": 441 }, { "epoch": 0.72, "learning_rate": 3.9819638982737354e-05, "loss": 0.3023, "step": 442 }, { "epoch": 0.72, "learning_rate": 3.9818229302647925e-05, "loss": 0.3573, "step": 443 }, { "epoch": 0.72, "learning_rate": 3.981681416018472e-05, "loss": 0.3133, "step": 444 }, { "epoch": 0.72, "learning_rate": 3.9815393555737774e-05, "loss": 0.4022, "step": 445 }, { "epoch": 0.72, "learning_rate": 3.981396748969866e-05, "loss": 0.2704, "step": 446 }, { "epoch": 0.72, "learning_rate": 3.981253596246041e-05, "loss": 0.4931, "step": 447 }, { "epoch": 0.73, "learning_rate": 3.981109897441761e-05, "loss": 0.3847, "step": 448 }, { "epoch": 0.73, "learning_rate": 3.9809656525966314e-05, "loss": 0.3812, "step": 449 }, { "epoch": 0.73, "learning_rate": 3.9808208617504106e-05, "loss": 0.2979, "step": 450 }, { "epoch": 0.73, "learning_rate": 3.980675524943006e-05, "loss": 0.3908, "step": 451 }, { "epoch": 0.73, "learning_rate": 3.980529642214474e-05, "loss": 0.4425, "step": 452 }, { "epoch": 0.73, "learning_rate": 3.9803832136050263e-05, "loss": 0.3183, "step": 453 }, { "epoch": 0.74, "learning_rate": 3.9802362391550195e-05, "loss": 0.2972, "step": 454 }, { "epoch": 0.74, "learning_rate": 3.9800887189049654e-05, "loss": 0.3034, "step": 455 }, { "epoch": 0.74, "learning_rate": 3.979940652895523e-05, "loss": 0.3832, "step": 456 }, { "epoch": 0.74, "learning_rate": 3.979792041167502e-05, "loss": 0.3694, "step": 457 }, { "epoch": 0.74, "learning_rate": 3.979642883761866e-05, "loss": 0.2532, "step": 458 }, { "epoch": 0.74, "learning_rate": 3.979493180719724e-05, "loss": 0.3213, "step": 459 }, { "epoch": 0.75, "learning_rate": 3.9793429320823375e-05, "loss": 0.4074, "step": 460 }, { "epoch": 0.75, "learning_rate": 3.9791921378911195e-05, "loss": 0.2653, "step": 461 }, { "epoch": 0.75, "learning_rate": 3.979040798187633e-05, "loss": 0.3079, "step": 462 }, { "epoch": 0.75, "learning_rate": 3.97888891301359e-05, "loss": 0.3023, "step": 463 }, { "epoch": 0.75, "learning_rate": 3.978736482410853e-05, "loss": 0.3821, "step": 464 }, { "epoch": 0.75, "learning_rate": 3.9785835064214364e-05, "loss": 0.3163, "step": 465 }, { "epoch": 0.76, "learning_rate": 3.978429985087504e-05, "loss": 0.5302, "step": 466 }, { "epoch": 0.76, "learning_rate": 3.97827591845137e-05, "loss": 0.3534, "step": 467 }, { "epoch": 0.76, "learning_rate": 3.978121306555499e-05, "loss": 0.3354, "step": 468 }, { "epoch": 0.76, "learning_rate": 3.977966149442505e-05, "loss": 0.3436, "step": 469 }, { "epoch": 0.76, "learning_rate": 3.977810447155154e-05, "loss": 0.2776, "step": 470 }, { "epoch": 0.76, "learning_rate": 3.9776541997363596e-05, "loss": 0.3451, "step": 471 }, { "epoch": 0.76, "learning_rate": 3.9774974072291884e-05, "loss": 0.218, "step": 472 }, { "epoch": 0.77, "learning_rate": 3.977340069676856e-05, "loss": 0.338, "step": 473 }, { "epoch": 0.77, "learning_rate": 3.977182187122728e-05, "loss": 0.3449, "step": 474 }, { "epoch": 0.77, "learning_rate": 3.977023759610321e-05, "loss": 0.4429, "step": 475 }, { "epoch": 0.77, "learning_rate": 3.976864787183302e-05, "loss": 0.3272, "step": 476 }, { "epoch": 0.77, "learning_rate": 3.9767052698854856e-05, "loss": 0.3646, "step": 477 }, { "epoch": 0.77, "learning_rate": 3.9765452077608404e-05, "loss": 0.3414, "step": 478 }, { "epoch": 0.78, "learning_rate": 3.976384600853483e-05, "loss": 0.3833, "step": 479 }, { "epoch": 0.78, "learning_rate": 3.97622344920768e-05, "loss": 0.3906, "step": 480 }, { "epoch": 0.78, "learning_rate": 3.976061752867849e-05, "loss": 0.2799, "step": 481 }, { "epoch": 0.78, "learning_rate": 3.9758995118785566e-05, "loss": 0.354, "step": 482 }, { "epoch": 0.78, "learning_rate": 3.975736726284521e-05, "loss": 0.4916, "step": 483 }, { "epoch": 0.78, "learning_rate": 3.97557339613061e-05, "loss": 0.3265, "step": 484 }, { "epoch": 0.79, "learning_rate": 3.97540952146184e-05, "loss": 0.3633, "step": 485 }, { "epoch": 0.79, "learning_rate": 3.9752451023233804e-05, "loss": 0.3647, "step": 486 }, { "epoch": 0.79, "learning_rate": 3.975080138760548e-05, "loss": 0.2965, "step": 487 }, { "epoch": 0.79, "learning_rate": 3.974914630818811e-05, "loss": 0.3682, "step": 488 }, { "epoch": 0.79, "learning_rate": 3.974748578543787e-05, "loss": 0.36, "step": 489 }, { "epoch": 0.79, "learning_rate": 3.974581981981243e-05, "loss": 0.3383, "step": 490 }, { "epoch": 0.8, "learning_rate": 3.9744148411770996e-05, "loss": 0.2896, "step": 491 }, { "epoch": 0.8, "learning_rate": 3.974247156177423e-05, "loss": 0.3514, "step": 492 }, { "epoch": 0.8, "learning_rate": 3.974078927028431e-05, "loss": 0.3345, "step": 493 }, { "epoch": 0.8, "learning_rate": 3.973910153776492e-05, "loss": 0.2769, "step": 494 }, { "epoch": 0.8, "learning_rate": 3.973740836468124e-05, "loss": 0.2952, "step": 495 }, { "epoch": 0.8, "learning_rate": 3.973570975149994e-05, "loss": 0.4583, "step": 496 }, { "epoch": 0.81, "learning_rate": 3.973400569868921e-05, "loss": 0.2472, "step": 497 }, { "epoch": 0.81, "learning_rate": 3.9732296206718724e-05, "loss": 0.4846, "step": 498 }, { "epoch": 0.81, "learning_rate": 3.9730581276059655e-05, "loss": 0.3125, "step": 499 }, { "epoch": 0.81, "learning_rate": 3.972886090718468e-05, "loss": 0.2835, "step": 500 }, { "epoch": 0.81, "learning_rate": 3.9727135100567975e-05, "loss": 0.3516, "step": 501 }, { "epoch": 0.81, "learning_rate": 3.972540385668522e-05, "loss": 0.3061, "step": 502 }, { "epoch": 0.82, "learning_rate": 3.972366717601357e-05, "loss": 0.471, "step": 503 }, { "epoch": 0.82, "learning_rate": 3.97219250590317e-05, "loss": 0.3053, "step": 504 }, { "epoch": 0.82, "learning_rate": 3.972017750621979e-05, "loss": 0.308, "step": 505 }, { "epoch": 0.82, "learning_rate": 3.97184245180595e-05, "loss": 0.3384, "step": 506 }, { "epoch": 0.82, "learning_rate": 3.9716666095034e-05, "loss": 0.3061, "step": 507 }, { "epoch": 0.82, "learning_rate": 3.9714902237627945e-05, "loss": 0.3747, "step": 508 }, { "epoch": 0.82, "learning_rate": 3.9713132946327494e-05, "loss": 0.2518, "step": 509 }, { "epoch": 0.83, "learning_rate": 3.9711358221620315e-05, "loss": 0.2832, "step": 510 }, { "epoch": 0.83, "learning_rate": 3.970957806399556e-05, "loss": 0.3085, "step": 511 }, { "epoch": 0.83, "learning_rate": 3.970779247394388e-05, "loss": 0.2857, "step": 512 }, { "epoch": 0.83, "learning_rate": 3.970600145195743e-05, "loss": 0.2647, "step": 513 }, { "epoch": 0.83, "learning_rate": 3.970420499852986e-05, "loss": 0.2894, "step": 514 }, { "epoch": 0.83, "learning_rate": 3.970240311415631e-05, "loss": 0.3935, "step": 515 }, { "epoch": 0.84, "learning_rate": 3.970059579933342e-05, "loss": 0.3001, "step": 516 }, { "epoch": 0.84, "learning_rate": 3.969878305455934e-05, "loss": 0.2747, "step": 517 }, { "epoch": 0.84, "learning_rate": 3.969696488033369e-05, "loss": 0.355, "step": 518 }, { "epoch": 0.84, "learning_rate": 3.9695141277157614e-05, "loss": 0.365, "step": 519 }, { "epoch": 0.84, "learning_rate": 3.969331224553374e-05, "loss": 0.335, "step": 520 }, { "epoch": 0.84, "learning_rate": 3.969147778596618e-05, "loss": 0.2552, "step": 521 }, { "epoch": 0.85, "learning_rate": 3.968963789896057e-05, "loss": 0.3182, "step": 522 }, { "epoch": 0.85, "learning_rate": 3.968779258502402e-05, "loss": 0.3763, "step": 523 }, { "epoch": 0.85, "learning_rate": 3.968594184466514e-05, "loss": 0.2809, "step": 524 }, { "epoch": 0.85, "learning_rate": 3.968408567839404e-05, "loss": 0.3015, "step": 525 }, { "epoch": 0.85, "learning_rate": 3.968222408672232e-05, "loss": 0.4353, "step": 526 }, { "epoch": 0.85, "learning_rate": 3.9680357070163096e-05, "loss": 0.3543, "step": 527 }, { "epoch": 0.86, "learning_rate": 3.967848462923093e-05, "loss": 0.3402, "step": 528 }, { "epoch": 0.86, "learning_rate": 3.9676606764441945e-05, "loss": 0.4031, "step": 529 }, { "epoch": 0.86, "learning_rate": 3.96747234763137e-05, "loss": 0.3738, "step": 530 }, { "epoch": 0.86, "learning_rate": 3.967283476536529e-05, "loss": 0.331, "step": 531 }, { "epoch": 0.86, "learning_rate": 3.967094063211727e-05, "loss": 0.4383, "step": 532 }, { "epoch": 0.86, "learning_rate": 3.966904107709173e-05, "loss": 0.4244, "step": 533 }, { "epoch": 0.87, "learning_rate": 3.966713610081222e-05, "loss": 0.2539, "step": 534 }, { "epoch": 0.87, "learning_rate": 3.96652257038038e-05, "loss": 0.322, "step": 535 }, { "epoch": 0.87, "learning_rate": 3.966330988659301e-05, "loss": 0.4401, "step": 536 }, { "epoch": 0.87, "learning_rate": 3.9661388649707915e-05, "loss": 0.227, "step": 537 }, { "epoch": 0.87, "learning_rate": 3.965946199367804e-05, "loss": 0.3552, "step": 538 }, { "epoch": 0.87, "learning_rate": 3.965752991903442e-05, "loss": 0.3951, "step": 539 }, { "epoch": 0.88, "learning_rate": 3.965559242630958e-05, "loss": 0.3117, "step": 540 }, { "epoch": 0.88, "learning_rate": 3.9653649516037533e-05, "loss": 0.2564, "step": 541 }, { "epoch": 0.88, "learning_rate": 3.9651701188753806e-05, "loss": 0.3529, "step": 542 }, { "epoch": 0.88, "learning_rate": 3.964974744499539e-05, "loss": 0.2632, "step": 543 }, { "epoch": 0.88, "learning_rate": 3.964778828530079e-05, "loss": 0.2987, "step": 544 }, { "epoch": 0.88, "learning_rate": 3.9645823710209996e-05, "loss": 0.3849, "step": 545 }, { "epoch": 0.88, "learning_rate": 3.964385372026449e-05, "loss": 0.2876, "step": 546 }, { "epoch": 0.89, "learning_rate": 3.964187831600725e-05, "loss": 0.3099, "step": 547 }, { "epoch": 0.89, "learning_rate": 3.963989749798274e-05, "loss": 0.3342, "step": 548 }, { "epoch": 0.89, "learning_rate": 3.963791126673693e-05, "loss": 0.3814, "step": 549 }, { "epoch": 0.89, "learning_rate": 3.963591962281726e-05, "loss": 0.2129, "step": 550 }, { "epoch": 0.89, "learning_rate": 3.963392256677268e-05, "loss": 0.3063, "step": 551 }, { "epoch": 0.89, "learning_rate": 3.9631920099153627e-05, "loss": 0.3275, "step": 552 }, { "epoch": 0.9, "learning_rate": 3.9629912220512035e-05, "loss": 0.3301, "step": 553 }, { "epoch": 0.9, "learning_rate": 3.9627898931401307e-05, "loss": 0.2843, "step": 554 }, { "epoch": 0.9, "learning_rate": 3.962588023237636e-05, "loss": 0.2044, "step": 555 }, { "epoch": 0.9, "learning_rate": 3.96238561239936e-05, "loss": 0.4478, "step": 556 }, { "epoch": 0.9, "learning_rate": 3.962182660681092e-05, "loss": 0.3301, "step": 557 }, { "epoch": 0.9, "learning_rate": 3.961979168138769e-05, "loss": 0.3114, "step": 558 }, { "epoch": 0.91, "learning_rate": 3.961775134828481e-05, "loss": 0.356, "step": 559 }, { "epoch": 0.91, "learning_rate": 3.961570560806461e-05, "loss": 0.3044, "step": 560 }, { "epoch": 0.91, "learning_rate": 3.9613654461290976e-05, "loss": 0.3584, "step": 561 }, { "epoch": 0.91, "learning_rate": 3.9611597908529224e-05, "loss": 0.3525, "step": 562 }, { "epoch": 0.91, "learning_rate": 3.960953595034621e-05, "loss": 0.412, "step": 563 }, { "epoch": 0.91, "learning_rate": 3.960746858731026e-05, "loss": 0.3863, "step": 564 }, { "epoch": 0.92, "learning_rate": 3.960539581999117e-05, "loss": 0.313, "step": 565 }, { "epoch": 0.92, "learning_rate": 3.960331764896025e-05, "loss": 0.3198, "step": 566 }, { "epoch": 0.92, "learning_rate": 3.96012340747903e-05, "loss": 0.4035, "step": 567 }, { "epoch": 0.92, "learning_rate": 3.9599145098055605e-05, "loss": 0.3244, "step": 568 }, { "epoch": 0.92, "learning_rate": 3.9597050719331926e-05, "loss": 0.3654, "step": 569 }, { "epoch": 0.92, "learning_rate": 3.9594950939196535e-05, "loss": 0.4022, "step": 570 }, { "epoch": 0.93, "learning_rate": 3.9592845758228164e-05, "loss": 0.3283, "step": 571 }, { "epoch": 0.93, "learning_rate": 3.9590735177007066e-05, "loss": 0.3205, "step": 572 }, { "epoch": 0.93, "learning_rate": 3.958861919611496e-05, "loss": 0.4195, "step": 573 }, { "epoch": 0.93, "learning_rate": 3.958649781613507e-05, "loss": 0.2981, "step": 574 }, { "epoch": 0.93, "learning_rate": 3.958437103765209e-05, "loss": 0.3577, "step": 575 }, { "epoch": 0.93, "learning_rate": 3.958223886125221e-05, "loss": 0.255, "step": 576 }, { "epoch": 0.94, "learning_rate": 3.9580101287523105e-05, "loss": 0.2822, "step": 577 }, { "epoch": 0.94, "learning_rate": 3.957795831705396e-05, "loss": 0.2478, "step": 578 }, { "epoch": 0.94, "learning_rate": 3.95758099504354e-05, "loss": 0.3021, "step": 579 }, { "epoch": 0.94, "learning_rate": 3.957365618825959e-05, "loss": 0.2695, "step": 580 }, { "epoch": 0.94, "learning_rate": 3.9571497031120144e-05, "loss": 0.3595, "step": 581 }, { "epoch": 0.94, "learning_rate": 3.956933247961218e-05, "loss": 0.4289, "step": 582 }, { "epoch": 0.94, "learning_rate": 3.956716253433231e-05, "loss": 0.3896, "step": 583 }, { "epoch": 0.95, "learning_rate": 3.956498719587861e-05, "loss": 0.3192, "step": 584 }, { "epoch": 0.95, "learning_rate": 3.9562806464850655e-05, "loss": 0.313, "step": 585 }, { "epoch": 0.95, "learning_rate": 3.9560620341849504e-05, "loss": 0.3324, "step": 586 }, { "epoch": 0.95, "learning_rate": 3.955842882747772e-05, "loss": 0.3404, "step": 587 }, { "epoch": 0.95, "learning_rate": 3.9556231922339323e-05, "loss": 0.3061, "step": 588 }, { "epoch": 0.95, "learning_rate": 3.9554029627039836e-05, "loss": 0.3605, "step": 589 }, { "epoch": 0.96, "learning_rate": 3.9551821942186264e-05, "loss": 0.303, "step": 590 }, { "epoch": 0.96, "learning_rate": 3.9549608868387095e-05, "loss": 0.253, "step": 591 }, { "epoch": 0.96, "learning_rate": 3.954739040625231e-05, "loss": 0.3756, "step": 592 }, { "epoch": 0.96, "learning_rate": 3.9545166556393353e-05, "loss": 0.3583, "step": 593 }, { "epoch": 0.96, "learning_rate": 3.954293731942319e-05, "loss": 0.3135, "step": 594 }, { "epoch": 0.96, "learning_rate": 3.954070269595625e-05, "loss": 0.3093, "step": 595 }, { "epoch": 0.97, "learning_rate": 3.9538462686608434e-05, "loss": 0.3218, "step": 596 }, { "epoch": 0.97, "learning_rate": 3.953621729199715e-05, "loss": 0.2573, "step": 597 }, { "epoch": 0.97, "learning_rate": 3.953396651274129e-05, "loss": 0.4206, "step": 598 }, { "epoch": 0.97, "learning_rate": 3.953171034946121e-05, "loss": 0.3169, "step": 599 }, { "epoch": 0.97, "learning_rate": 3.952944880277876e-05, "loss": 0.4831, "step": 600 }, { "epoch": 0.97, "learning_rate": 3.952718187331729e-05, "loss": 0.258, "step": 601 }, { "epoch": 0.98, "learning_rate": 3.9524909561701615e-05, "loss": 0.2702, "step": 602 }, { "epoch": 0.98, "learning_rate": 3.9522631868558024e-05, "loss": 0.304, "step": 603 }, { "epoch": 0.98, "learning_rate": 3.9520348794514316e-05, "loss": 0.273, "step": 604 }, { "epoch": 0.98, "learning_rate": 3.951806034019976e-05, "loss": 0.3529, "step": 605 }, { "epoch": 0.98, "learning_rate": 3.95157665062451e-05, "loss": 0.2941, "step": 606 }, { "epoch": 0.98, "learning_rate": 3.9513467293282587e-05, "loss": 0.3075, "step": 607 }, { "epoch": 0.99, "learning_rate": 3.9511162701945925e-05, "loss": 0.3035, "step": 608 }, { "epoch": 0.99, "learning_rate": 3.950885273287032e-05, "loss": 0.3347, "step": 609 }, { "epoch": 0.99, "learning_rate": 3.9506537386692455e-05, "loss": 0.4221, "step": 610 }, { "epoch": 0.99, "learning_rate": 3.950421666405048e-05, "loss": 0.2794, "step": 611 }, { "epoch": 0.99, "learning_rate": 3.950189056558406e-05, "loss": 0.3275, "step": 612 }, { "epoch": 0.99, "learning_rate": 3.949955909193431e-05, "loss": 0.3192, "step": 613 }, { "epoch": 1.0, "learning_rate": 3.949722224374385e-05, "loss": 0.3289, "step": 614 }, { "epoch": 1.0, "learning_rate": 3.949488002165677e-05, "loss": 0.2897, "step": 615 }, { "epoch": 1.0, "learning_rate": 3.9492532426318624e-05, "loss": 0.3383, "step": 616 }, { "epoch": 1.0, "learning_rate": 3.9490179458376487e-05, "loss": 0.3042, "step": 617 }, { "epoch": 1.0, "learning_rate": 3.9487821118478885e-05, "loss": 0.3457, "step": 618 }, { "epoch": 1.0, "learning_rate": 3.948545740727583e-05, "loss": 0.1989, "step": 619 }, { "epoch": 1.0, "learning_rate": 3.948308832541882e-05, "loss": 0.3618, "step": 620 }, { "epoch": 1.01, "learning_rate": 3.9480713873560825e-05, "loss": 0.3467, "step": 621 }, { "epoch": 1.01, "learning_rate": 3.94783340523563e-05, "loss": 0.2891, "step": 622 }, { "epoch": 1.01, "learning_rate": 3.947594886246119e-05, "loss": 0.3024, "step": 623 }, { "epoch": 1.01, "learning_rate": 3.94735583045329e-05, "loss": 0.3593, "step": 624 }, { "epoch": 1.01, "learning_rate": 3.947116237923034e-05, "loss": 0.2633, "step": 625 }, { "epoch": 1.01, "learning_rate": 3.9468761087213864e-05, "loss": 0.2452, "step": 626 }, { "epoch": 1.02, "learning_rate": 3.9466354429145326e-05, "loss": 0.2697, "step": 627 }, { "epoch": 1.02, "learning_rate": 3.946394240568807e-05, "loss": 0.3144, "step": 628 }, { "epoch": 1.02, "learning_rate": 3.946152501750691e-05, "loss": 0.3706, "step": 629 }, { "epoch": 1.02, "learning_rate": 3.9459102265268115e-05, "loss": 0.2793, "step": 630 }, { "epoch": 1.02, "learning_rate": 3.945667414963947e-05, "loss": 0.3319, "step": 631 }, { "epoch": 1.02, "learning_rate": 3.945424067129022e-05, "loss": 0.3672, "step": 632 }, { "epoch": 1.03, "learning_rate": 3.945180183089108e-05, "loss": 0.2918, "step": 633 }, { "epoch": 1.03, "learning_rate": 3.944935762911426e-05, "loss": 0.2461, "step": 634 }, { "epoch": 1.03, "learning_rate": 3.944690806663344e-05, "loss": 0.3863, "step": 635 }, { "epoch": 1.03, "learning_rate": 3.944445314412377e-05, "loss": 0.379, "step": 636 }, { "epoch": 1.03, "learning_rate": 3.944199286226189e-05, "loss": 0.2804, "step": 637 }, { "epoch": 1.03, "learning_rate": 3.943952722172592e-05, "loss": 0.3288, "step": 638 }, { "epoch": 1.04, "learning_rate": 3.943705622319544e-05, "loss": 0.3106, "step": 639 }, { "epoch": 1.04, "learning_rate": 3.943457986735151e-05, "loss": 0.3411, "step": 640 }, { "epoch": 1.04, "learning_rate": 3.943209815487669e-05, "loss": 0.281, "step": 641 }, { "epoch": 1.04, "learning_rate": 3.9429611086454975e-05, "loss": 0.4077, "step": 642 }, { "epoch": 1.04, "learning_rate": 3.942711866277188e-05, "loss": 0.3932, "step": 643 }, { "epoch": 1.04, "learning_rate": 3.9424620884514375e-05, "loss": 0.2987, "step": 644 }, { "epoch": 1.05, "learning_rate": 3.942211775237089e-05, "loss": 0.3272, "step": 645 }, { "epoch": 1.05, "learning_rate": 3.941960926703137e-05, "loss": 0.3489, "step": 646 }, { "epoch": 1.05, "learning_rate": 3.9417095429187195e-05, "loss": 0.2949, "step": 647 }, { "epoch": 1.05, "learning_rate": 3.941457623953125e-05, "loss": 0.3456, "step": 648 }, { "epoch": 1.05, "learning_rate": 3.9412051698757866e-05, "loss": 0.2515, "step": 649 }, { "epoch": 1.05, "learning_rate": 3.940952180756289e-05, "loss": 0.3199, "step": 650 }, { "epoch": 1.06, "learning_rate": 3.940698656664361e-05, "loss": 0.3759, "step": 651 }, { "epoch": 1.06, "learning_rate": 3.940444597669879e-05, "loss": 0.3305, "step": 652 }, { "epoch": 1.06, "learning_rate": 3.940190003842869e-05, "loss": 0.3386, "step": 653 }, { "epoch": 1.06, "learning_rate": 3.939934875253502e-05, "loss": 0.3073, "step": 654 }, { "epoch": 1.06, "learning_rate": 3.939679211972098e-05, "loss": 0.2952, "step": 655 }, { "epoch": 1.06, "learning_rate": 3.939423014069124e-05, "loss": 0.4121, "step": 656 }, { "epoch": 1.06, "learning_rate": 3.9391662816151936e-05, "loss": 0.23, "step": 657 }, { "epoch": 1.07, "learning_rate": 3.9389090146810696e-05, "loss": 0.2813, "step": 658 }, { "epoch": 1.07, "learning_rate": 3.93865121333766e-05, "loss": 0.2599, "step": 659 }, { "epoch": 1.07, "learning_rate": 3.93839287765602e-05, "loss": 0.3128, "step": 660 }, { "epoch": 1.07, "learning_rate": 3.938134007707355e-05, "loss": 0.2842, "step": 661 }, { "epoch": 1.07, "learning_rate": 3.937874603563015e-05, "loss": 0.3198, "step": 662 }, { "epoch": 1.07, "learning_rate": 3.937614665294497e-05, "loss": 0.2255, "step": 663 }, { "epoch": 1.08, "learning_rate": 3.937354192973448e-05, "loss": 0.341, "step": 664 }, { "epoch": 1.08, "learning_rate": 3.937093186671658e-05, "loss": 0.3711, "step": 665 }, { "epoch": 1.08, "learning_rate": 3.936831646461068e-05, "loss": 0.2224, "step": 666 }, { "epoch": 1.08, "learning_rate": 3.936569572413764e-05, "loss": 0.356, "step": 667 }, { "epoch": 1.08, "learning_rate": 3.936306964601981e-05, "loss": 0.3183, "step": 668 }, { "epoch": 1.08, "learning_rate": 3.936043823098098e-05, "loss": 0.352, "step": 669 }, { "epoch": 1.09, "learning_rate": 3.935780147974646e-05, "loss": 0.3313, "step": 670 }, { "epoch": 1.09, "learning_rate": 3.9355159393042966e-05, "loss": 0.2517, "step": 671 }, { "epoch": 1.09, "learning_rate": 3.935251197159875e-05, "loss": 0.2353, "step": 672 }, { "epoch": 1.09, "learning_rate": 3.934985921614348e-05, "loss": 0.3362, "step": 673 }, { "epoch": 1.09, "learning_rate": 3.9347201127408335e-05, "loss": 0.2518, "step": 674 }, { "epoch": 1.09, "learning_rate": 3.934453770612594e-05, "loss": 0.3564, "step": 675 }, { "epoch": 1.1, "learning_rate": 3.9341868953030395e-05, "loss": 0.3084, "step": 676 }, { "epoch": 1.1, "learning_rate": 3.933919486885728e-05, "loss": 0.3275, "step": 677 }, { "epoch": 1.1, "learning_rate": 3.9336515454343634e-05, "loss": 0.3963, "step": 678 }, { "epoch": 1.1, "learning_rate": 3.933383071022795e-05, "loss": 0.2426, "step": 679 }, { "epoch": 1.1, "learning_rate": 3.933114063725024e-05, "loss": 0.338, "step": 680 }, { "epoch": 1.1, "learning_rate": 3.9328445236151916e-05, "loss": 0.2875, "step": 681 }, { "epoch": 1.11, "learning_rate": 3.932574450767592e-05, "loss": 0.3066, "step": 682 }, { "epoch": 1.11, "learning_rate": 3.9323038452566634e-05, "loss": 0.316, "step": 683 }, { "epoch": 1.11, "learning_rate": 3.93203270715699e-05, "loss": 0.2542, "step": 684 }, { "epoch": 1.11, "learning_rate": 3.931761036543304e-05, "loss": 0.3527, "step": 685 }, { "epoch": 1.11, "learning_rate": 3.9314888334904846e-05, "loss": 0.2728, "step": 686 }, { "epoch": 1.11, "learning_rate": 3.9312160980735584e-05, "loss": 0.3283, "step": 687 }, { "epoch": 1.12, "learning_rate": 3.930942830367697e-05, "loss": 0.2924, "step": 688 }, { "epoch": 1.12, "learning_rate": 3.930669030448218e-05, "loss": 0.2226, "step": 689 }, { "epoch": 1.12, "learning_rate": 3.930394698390589e-05, "loss": 0.3196, "step": 690 }, { "epoch": 1.12, "learning_rate": 3.930119834270422e-05, "loss": 0.2546, "step": 691 }, { "epoch": 1.12, "learning_rate": 3.9298444381634764e-05, "loss": 0.3494, "step": 692 }, { "epoch": 1.12, "learning_rate": 3.9295685101456566e-05, "loss": 0.411, "step": 693 }, { "epoch": 1.12, "learning_rate": 3.929292050293016e-05, "loss": 0.3163, "step": 694 }, { "epoch": 1.13, "learning_rate": 3.9290150586817536e-05, "loss": 0.3368, "step": 695 }, { "epoch": 1.13, "learning_rate": 3.928737535388214e-05, "loss": 0.2647, "step": 696 }, { "epoch": 1.13, "learning_rate": 3.92845948048889e-05, "loss": 0.3024, "step": 697 }, { "epoch": 1.13, "learning_rate": 3.92818089406042e-05, "loss": 0.3561, "step": 698 }, { "epoch": 1.13, "learning_rate": 3.927901776179588e-05, "loss": 0.3843, "step": 699 }, { "epoch": 1.13, "learning_rate": 3.927622126923327e-05, "loss": 0.2906, "step": 700 }, { "epoch": 1.14, "learning_rate": 3.9273419463687134e-05, "loss": 0.2756, "step": 701 }, { "epoch": 1.14, "learning_rate": 3.927061234592974e-05, "loss": 0.2932, "step": 702 }, { "epoch": 1.14, "learning_rate": 3.926779991673477e-05, "loss": 0.3079, "step": 703 }, { "epoch": 1.14, "learning_rate": 3.926498217687741e-05, "loss": 0.3071, "step": 704 }, { "epoch": 1.14, "learning_rate": 3.92621591271343e-05, "loss": 0.339, "step": 705 }, { "epoch": 1.14, "learning_rate": 3.9259330768283516e-05, "loss": 0.3833, "step": 706 }, { "epoch": 1.15, "learning_rate": 3.925649710110465e-05, "loss": 0.2782, "step": 707 }, { "epoch": 1.15, "learning_rate": 3.925365812637871e-05, "loss": 0.2596, "step": 708 }, { "epoch": 1.15, "learning_rate": 3.9250813844888195e-05, "loss": 0.2893, "step": 709 }, { "epoch": 1.15, "learning_rate": 3.924796425741705e-05, "loss": 0.3054, "step": 710 }, { "epoch": 1.15, "learning_rate": 3.924510936475069e-05, "loss": 0.3189, "step": 711 }, { "epoch": 1.15, "learning_rate": 3.924224916767599e-05, "loss": 0.3019, "step": 712 }, { "epoch": 1.16, "learning_rate": 3.923938366698129e-05, "loss": 0.412, "step": 713 }, { "epoch": 1.16, "learning_rate": 3.923651286345638e-05, "loss": 0.2829, "step": 714 }, { "epoch": 1.16, "learning_rate": 3.923363675789254e-05, "loss": 0.3286, "step": 715 }, { "epoch": 1.16, "learning_rate": 3.9230755351082486e-05, "loss": 0.274, "step": 716 }, { "epoch": 1.16, "learning_rate": 3.9227868643820395e-05, "loss": 0.2682, "step": 717 }, { "epoch": 1.16, "learning_rate": 3.922497663690192e-05, "loss": 0.2571, "step": 718 }, { "epoch": 1.17, "learning_rate": 3.922207933112416e-05, "loss": 0.3702, "step": 719 }, { "epoch": 1.17, "learning_rate": 3.921917672728569e-05, "loss": 0.4044, "step": 720 }, { "epoch": 1.17, "learning_rate": 3.921626882618652e-05, "loss": 0.3106, "step": 721 }, { "epoch": 1.17, "learning_rate": 3.921335562862816e-05, "loss": 0.2511, "step": 722 }, { "epoch": 1.17, "learning_rate": 3.921043713541353e-05, "loss": 0.3045, "step": 723 }, { "epoch": 1.17, "learning_rate": 3.920751334734706e-05, "loss": 0.3647, "step": 724 }, { "epoch": 1.18, "learning_rate": 3.92045842652346e-05, "loss": 0.3126, "step": 725 }, { "epoch": 1.18, "learning_rate": 3.9201649889883485e-05, "loss": 0.3647, "step": 726 }, { "epoch": 1.18, "learning_rate": 3.919871022210249e-05, "loss": 0.3372, "step": 727 }, { "epoch": 1.18, "learning_rate": 3.919576526270186e-05, "loss": 0.4023, "step": 728 }, { "epoch": 1.18, "learning_rate": 3.919281501249329e-05, "loss": 0.2735, "step": 729 }, { "epoch": 1.18, "learning_rate": 3.9189859472289956e-05, "loss": 0.3883, "step": 730 }, { "epoch": 1.18, "learning_rate": 3.9186898642906454e-05, "loss": 0.3007, "step": 731 }, { "epoch": 1.19, "learning_rate": 3.9183932525158866e-05, "loss": 0.3125, "step": 732 }, { "epoch": 1.19, "learning_rate": 3.918096111986473e-05, "loss": 0.2662, "step": 733 }, { "epoch": 1.19, "learning_rate": 3.917798442784303e-05, "loss": 0.2943, "step": 734 }, { "epoch": 1.19, "learning_rate": 3.9175002449914224e-05, "loss": 0.3391, "step": 735 }, { "epoch": 1.19, "learning_rate": 3.9172015186900196e-05, "loss": 0.3372, "step": 736 }, { "epoch": 1.19, "learning_rate": 3.9169022639624324e-05, "loss": 0.2908, "step": 737 }, { "epoch": 1.2, "learning_rate": 3.916602480891141e-05, "loss": 0.2558, "step": 738 }, { "epoch": 1.2, "learning_rate": 3.916302169558775e-05, "loss": 0.3064, "step": 739 }, { "epoch": 1.2, "learning_rate": 3.916001330048104e-05, "loss": 0.3545, "step": 740 }, { "epoch": 1.2, "learning_rate": 3.91569996244205e-05, "loss": 0.3085, "step": 741 }, { "epoch": 1.2, "learning_rate": 3.9153980668236744e-05, "loss": 0.3725, "step": 742 }, { "epoch": 1.2, "learning_rate": 3.9150956432761884e-05, "loss": 0.2215, "step": 743 }, { "epoch": 1.21, "learning_rate": 3.914792691882946e-05, "loss": 0.2816, "step": 744 }, { "epoch": 1.21, "learning_rate": 3.914489212727449e-05, "loss": 0.4138, "step": 745 }, { "epoch": 1.21, "learning_rate": 3.914185205893342e-05, "loss": 0.3294, "step": 746 }, { "epoch": 1.21, "learning_rate": 3.913880671464418e-05, "loss": 0.2323, "step": 747 }, { "epoch": 1.21, "learning_rate": 3.913575609524613e-05, "loss": 0.3003, "step": 748 }, { "epoch": 1.21, "learning_rate": 3.9132700201580085e-05, "loss": 0.452, "step": 749 }, { "epoch": 1.22, "learning_rate": 3.912963903448834e-05, "loss": 0.3962, "step": 750 }, { "epoch": 1.22, "learning_rate": 3.912657259481462e-05, "loss": 0.3542, "step": 751 }, { "epoch": 1.22, "learning_rate": 3.91235008834041e-05, "loss": 0.2359, "step": 752 }, { "epoch": 1.22, "learning_rate": 3.912042390110342e-05, "loss": 0.2615, "step": 753 }, { "epoch": 1.22, "learning_rate": 3.911734164876067e-05, "loss": 0.2974, "step": 754 }, { "epoch": 1.22, "learning_rate": 3.911425412722539e-05, "loss": 0.3835, "step": 755 }, { "epoch": 1.23, "learning_rate": 3.911116133734859e-05, "loss": 0.2998, "step": 756 }, { "epoch": 1.23, "learning_rate": 3.9108063279982686e-05, "loss": 0.2873, "step": 757 }, { "epoch": 1.23, "learning_rate": 3.9104959955981605e-05, "loss": 0.3603, "step": 758 }, { "epoch": 1.23, "learning_rate": 3.910185136620068e-05, "loss": 0.269, "step": 759 }, { "epoch": 1.23, "learning_rate": 3.9098737511496715e-05, "loss": 0.213, "step": 760 }, { "epoch": 1.23, "learning_rate": 3.9095618392727966e-05, "loss": 0.2864, "step": 761 }, { "epoch": 1.24, "learning_rate": 3.909249401075413e-05, "loss": 0.3281, "step": 762 }, { "epoch": 1.24, "learning_rate": 3.908936436643637e-05, "loss": 0.2959, "step": 763 }, { "epoch": 1.24, "learning_rate": 3.908622946063728e-05, "loss": 0.3788, "step": 764 }, { "epoch": 1.24, "learning_rate": 3.908308929422092e-05, "loss": 0.2688, "step": 765 }, { "epoch": 1.24, "learning_rate": 3.907994386805279e-05, "loss": 0.308, "step": 766 }, { "epoch": 1.24, "learning_rate": 3.9076793182999855e-05, "loss": 0.2795, "step": 767 }, { "epoch": 1.24, "learning_rate": 3.907363723993051e-05, "loss": 0.3346, "step": 768 }, { "epoch": 1.25, "learning_rate": 3.90704760397146e-05, "loss": 0.3992, "step": 769 }, { "epoch": 1.25, "learning_rate": 3.906730958322345e-05, "loss": 0.4125, "step": 770 }, { "epoch": 1.25, "learning_rate": 3.906413787132978e-05, "loss": 0.2514, "step": 771 }, { "epoch": 1.25, "learning_rate": 3.906096090490781e-05, "loss": 0.3216, "step": 772 }, { "epoch": 1.25, "learning_rate": 3.905777868483319e-05, "loss": 0.2968, "step": 773 }, { "epoch": 1.25, "learning_rate": 3.9054591211983e-05, "loss": 0.2535, "step": 774 }, { "epoch": 1.26, "learning_rate": 3.905139848723579e-05, "loss": 0.2837, "step": 775 }, { "epoch": 1.26, "learning_rate": 3.904820051147155e-05, "loss": 0.2852, "step": 776 }, { "epoch": 1.26, "learning_rate": 3.904499728557172e-05, "loss": 0.2753, "step": 777 }, { "epoch": 1.26, "learning_rate": 3.9041788810419186e-05, "loss": 0.2635, "step": 778 }, { "epoch": 1.26, "learning_rate": 3.9038575086898276e-05, "loss": 0.3716, "step": 779 }, { "epoch": 1.26, "learning_rate": 3.903535611589477e-05, "loss": 0.24, "step": 780 }, { "epoch": 1.27, "learning_rate": 3.903213189829589e-05, "loss": 0.3407, "step": 781 }, { "epoch": 1.27, "learning_rate": 3.9028902434990315e-05, "loss": 0.3467, "step": 782 }, { "epoch": 1.27, "learning_rate": 3.9025667726868155e-05, "loss": 0.3148, "step": 783 }, { "epoch": 1.27, "learning_rate": 3.902242777482097e-05, "loss": 0.3413, "step": 784 }, { "epoch": 1.27, "learning_rate": 3.901918257974177e-05, "loss": 0.291, "step": 785 }, { "epoch": 1.27, "learning_rate": 3.901593214252502e-05, "loss": 0.329, "step": 786 }, { "epoch": 1.28, "learning_rate": 3.901267646406659e-05, "loss": 0.341, "step": 787 }, { "epoch": 1.28, "learning_rate": 3.900941554526385e-05, "loss": 0.3268, "step": 788 }, { "epoch": 1.28, "learning_rate": 3.900614938701557e-05, "loss": 0.291, "step": 789 }, { "epoch": 1.28, "learning_rate": 3.9002877990221986e-05, "loss": 0.2347, "step": 790 }, { "epoch": 1.28, "learning_rate": 3.899960135578477e-05, "loss": 0.3846, "step": 791 }, { "epoch": 1.28, "learning_rate": 3.899631948460704e-05, "loss": 0.3219, "step": 792 }, { "epoch": 1.29, "learning_rate": 3.8993032377593375e-05, "loss": 0.3286, "step": 793 }, { "epoch": 1.29, "learning_rate": 3.898974003564975e-05, "loss": 0.3049, "step": 794 }, { "epoch": 1.29, "learning_rate": 3.8986442459683633e-05, "loss": 0.3393, "step": 795 }, { "epoch": 1.29, "learning_rate": 3.89831396506039e-05, "loss": 0.2641, "step": 796 }, { "epoch": 1.29, "learning_rate": 3.89798316093209e-05, "loss": 0.5101, "step": 797 }, { "epoch": 1.29, "learning_rate": 3.8976518336746396e-05, "loss": 0.2689, "step": 798 }, { "epoch": 1.29, "learning_rate": 3.897319983379361e-05, "loss": 0.4142, "step": 799 }, { "epoch": 1.3, "learning_rate": 3.896987610137719e-05, "loss": 0.2983, "step": 800 }, { "epoch": 1.3, "learning_rate": 3.896654714041325e-05, "loss": 0.3151, "step": 801 }, { "epoch": 1.3, "learning_rate": 3.896321295181932e-05, "loss": 0.4756, "step": 802 }, { "epoch": 1.3, "learning_rate": 3.895987353651439e-05, "loss": 0.3165, "step": 803 }, { "epoch": 1.3, "learning_rate": 3.8956528895418866e-05, "loss": 0.2522, "step": 804 }, { "epoch": 1.3, "learning_rate": 3.895317902945463e-05, "loss": 0.2844, "step": 805 }, { "epoch": 1.31, "learning_rate": 3.894982393954498e-05, "loss": 0.3698, "step": 806 }, { "epoch": 1.31, "learning_rate": 3.894646362661465e-05, "loss": 0.2484, "step": 807 }, { "epoch": 1.31, "learning_rate": 3.894309809158982e-05, "loss": 0.3186, "step": 808 }, { "epoch": 1.31, "learning_rate": 3.893972733539812e-05, "loss": 0.2889, "step": 809 }, { "epoch": 1.31, "learning_rate": 3.893635135896861e-05, "loss": 0.3712, "step": 810 }, { "epoch": 1.31, "learning_rate": 3.893297016323178e-05, "loss": 0.2796, "step": 811 }, { "epoch": 1.32, "learning_rate": 3.892958374911958e-05, "loss": 0.2354, "step": 812 }, { "epoch": 1.32, "learning_rate": 3.892619211756538e-05, "loss": 0.3984, "step": 813 }, { "epoch": 1.32, "learning_rate": 3.8922795269503996e-05, "loss": 0.3537, "step": 814 }, { "epoch": 1.32, "learning_rate": 3.8919393205871676e-05, "loss": 0.3079, "step": 815 }, { "epoch": 1.32, "learning_rate": 3.8915985927606106e-05, "loss": 0.3127, "step": 816 }, { "epoch": 1.32, "learning_rate": 3.891257343564643e-05, "loss": 0.4592, "step": 817 }, { "epoch": 1.33, "learning_rate": 3.89091557309332e-05, "loss": 0.3066, "step": 818 }, { "epoch": 1.33, "learning_rate": 3.8905732814408406e-05, "loss": 0.3265, "step": 819 }, { "epoch": 1.33, "learning_rate": 3.89023046870155e-05, "loss": 0.3039, "step": 820 }, { "epoch": 1.33, "learning_rate": 3.889887134969935e-05, "loss": 0.2572, "step": 821 }, { "epoch": 1.33, "learning_rate": 3.8895432803406266e-05, "loss": 0.4013, "step": 822 }, { "epoch": 1.33, "learning_rate": 3.889198904908399e-05, "loss": 0.3456, "step": 823 }, { "epoch": 1.34, "learning_rate": 3.888854008768171e-05, "loss": 0.3483, "step": 824 }, { "epoch": 1.34, "learning_rate": 3.888508592015003e-05, "loss": 0.2486, "step": 825 }, { "epoch": 1.34, "learning_rate": 3.888162654744101e-05, "loss": 0.3142, "step": 826 }, { "epoch": 1.34, "learning_rate": 3.8878161970508135e-05, "loss": 0.1872, "step": 827 }, { "epoch": 1.34, "learning_rate": 3.8874692190306315e-05, "loss": 0.3551, "step": 828 }, { "epoch": 1.34, "learning_rate": 3.8871217207791915e-05, "loss": 0.2612, "step": 829 }, { "epoch": 1.35, "learning_rate": 3.886773702392271e-05, "loss": 0.3243, "step": 830 }, { "epoch": 1.35, "learning_rate": 3.886425163965794e-05, "loss": 0.2466, "step": 831 }, { "epoch": 1.35, "learning_rate": 3.886076105595825e-05, "loss": 0.2835, "step": 832 }, { "epoch": 1.35, "learning_rate": 3.8857265273785717e-05, "loss": 0.3465, "step": 833 }, { "epoch": 1.35, "learning_rate": 3.885376429410387e-05, "loss": 0.3252, "step": 834 }, { "epoch": 1.35, "learning_rate": 3.885025811787767e-05, "loss": 0.3942, "step": 835 }, { "epoch": 1.35, "learning_rate": 3.8846746746073485e-05, "loss": 0.3161, "step": 836 }, { "epoch": 1.36, "learning_rate": 3.884323017965915e-05, "loss": 0.4374, "step": 837 }, { "epoch": 1.36, "learning_rate": 3.88397084196039e-05, "loss": 0.3101, "step": 838 }, { "epoch": 1.36, "learning_rate": 3.883618146687842e-05, "loss": 0.2564, "step": 839 }, { "epoch": 1.36, "learning_rate": 3.883264932245484e-05, "loss": 0.2422, "step": 840 }, { "epoch": 1.36, "learning_rate": 3.8829111987306666e-05, "loss": 0.2576, "step": 841 }, { "epoch": 1.36, "learning_rate": 3.88255694624089e-05, "loss": 0.2937, "step": 842 }, { "epoch": 1.37, "learning_rate": 3.882202174873794e-05, "loss": 0.2559, "step": 843 }, { "epoch": 1.37, "learning_rate": 3.8818468847271614e-05, "loss": 0.3303, "step": 844 }, { "epoch": 1.37, "learning_rate": 3.8814910758989186e-05, "loss": 0.3006, "step": 845 }, { "epoch": 1.37, "learning_rate": 3.8811347484871353e-05, "loss": 0.257, "step": 846 }, { "epoch": 1.37, "learning_rate": 3.880777902590024e-05, "loss": 0.3424, "step": 847 }, { "epoch": 1.37, "learning_rate": 3.88042053830594e-05, "loss": 0.3338, "step": 848 }, { "epoch": 1.38, "learning_rate": 3.88006265573338e-05, "loss": 0.3418, "step": 849 }, { "epoch": 1.38, "learning_rate": 3.879704254970987e-05, "loss": 0.2949, "step": 850 }, { "epoch": 1.38, "learning_rate": 3.879345336117544e-05, "loss": 0.3267, "step": 851 }, { "epoch": 1.38, "learning_rate": 3.8789858992719766e-05, "loss": 0.2331, "step": 852 }, { "epoch": 1.38, "learning_rate": 3.878625944533355e-05, "loss": 0.3046, "step": 853 }, { "epoch": 1.38, "learning_rate": 3.87826547200089e-05, "loss": 0.2881, "step": 854 }, { "epoch": 1.39, "learning_rate": 3.877904481773937e-05, "loss": 0.2509, "step": 855 }, { "epoch": 1.39, "learning_rate": 3.877542973951996e-05, "loss": 0.324, "step": 856 }, { "epoch": 1.39, "learning_rate": 3.877180948634704e-05, "loss": 0.282, "step": 857 }, { "epoch": 1.39, "learning_rate": 3.876818405921844e-05, "loss": 0.3147, "step": 858 }, { "epoch": 1.39, "learning_rate": 3.8764553459133426e-05, "loss": 0.2618, "step": 859 }, { "epoch": 1.39, "learning_rate": 3.876091768709267e-05, "loss": 0.351, "step": 860 }, { "epoch": 1.4, "learning_rate": 3.875727674409828e-05, "loss": 0.3117, "step": 861 }, { "epoch": 1.4, "learning_rate": 3.875363063115379e-05, "loss": 0.4653, "step": 862 }, { "epoch": 1.4, "learning_rate": 3.8749979349264145e-05, "loss": 0.3469, "step": 863 }, { "epoch": 1.4, "learning_rate": 3.874632289943573e-05, "loss": 0.3459, "step": 864 }, { "epoch": 1.4, "learning_rate": 3.874266128267635e-05, "loss": 0.2668, "step": 865 }, { "epoch": 1.4, "learning_rate": 3.873899449999524e-05, "loss": 0.3017, "step": 866 }, { "epoch": 1.41, "learning_rate": 3.873532255240304e-05, "loss": 0.2801, "step": 867 }, { "epoch": 1.41, "learning_rate": 3.873164544091183e-05, "loss": 0.3198, "step": 868 }, { "epoch": 1.41, "learning_rate": 3.872796316653511e-05, "loss": 0.2705, "step": 869 }, { "epoch": 1.41, "learning_rate": 3.87242757302878e-05, "loss": 0.3438, "step": 870 }, { "epoch": 1.41, "learning_rate": 3.872058313318626e-05, "loss": 0.3438, "step": 871 }, { "epoch": 1.41, "learning_rate": 3.871688537624823e-05, "loss": 0.2868, "step": 872 }, { "epoch": 1.41, "learning_rate": 3.871318246049292e-05, "loss": 0.2685, "step": 873 }, { "epoch": 1.42, "learning_rate": 3.870947438694093e-05, "loss": 0.2513, "step": 874 }, { "epoch": 1.42, "learning_rate": 3.87057611566143e-05, "loss": 0.263, "step": 875 }, { "epoch": 1.42, "learning_rate": 3.870204277053649e-05, "loss": 0.2646, "step": 876 }, { "epoch": 1.42, "learning_rate": 3.869831922973236e-05, "loss": 0.268, "step": 877 }, { "epoch": 1.42, "learning_rate": 3.869459053522821e-05, "loss": 0.3254, "step": 878 }, { "epoch": 1.42, "learning_rate": 3.869085668805177e-05, "loss": 0.342, "step": 879 }, { "epoch": 1.43, "learning_rate": 3.8687117689232164e-05, "loss": 0.3258, "step": 880 }, { "epoch": 1.43, "learning_rate": 3.868337353979995e-05, "loss": 0.3219, "step": 881 }, { "epoch": 1.43, "learning_rate": 3.8679624240787113e-05, "loss": 0.2216, "step": 882 }, { "epoch": 1.43, "learning_rate": 3.867586979322703e-05, "loss": 0.3035, "step": 883 }, { "epoch": 1.43, "learning_rate": 3.8672110198154535e-05, "loss": 0.2658, "step": 884 }, { "epoch": 1.43, "learning_rate": 3.8668345456605857e-05, "loss": 0.3358, "step": 885 }, { "epoch": 1.44, "learning_rate": 3.866457556961864e-05, "loss": 0.3866, "step": 886 }, { "epoch": 1.44, "learning_rate": 3.866080053823197e-05, "loss": 0.2779, "step": 887 }, { "epoch": 1.44, "learning_rate": 3.8657020363486314e-05, "loss": 0.3609, "step": 888 }, { "epoch": 1.44, "learning_rate": 3.865323504642359e-05, "loss": 0.2385, "step": 889 }, { "epoch": 1.44, "learning_rate": 3.864944458808712e-05, "loss": 0.4559, "step": 890 }, { "epoch": 1.44, "learning_rate": 3.864564898952164e-05, "loss": 0.3438, "step": 891 }, { "epoch": 1.45, "learning_rate": 3.864184825177332e-05, "loss": 0.3701, "step": 892 }, { "epoch": 1.45, "learning_rate": 3.863804237588972e-05, "loss": 0.3772, "step": 893 }, { "epoch": 1.45, "learning_rate": 3.8634231362919826e-05, "loss": 0.2877, "step": 894 }, { "epoch": 1.45, "learning_rate": 3.863041521391406e-05, "loss": 0.3317, "step": 895 }, { "epoch": 1.45, "learning_rate": 3.862659392992423e-05, "loss": 0.2807, "step": 896 }, { "epoch": 1.45, "learning_rate": 3.8622767512003575e-05, "loss": 0.3732, "step": 897 }, { "epoch": 1.46, "learning_rate": 3.861893596120676e-05, "loss": 0.2705, "step": 898 }, { "epoch": 1.46, "learning_rate": 3.861509927858983e-05, "loss": 0.2534, "step": 899 }, { "epoch": 1.46, "learning_rate": 3.861125746521028e-05, "loss": 0.3454, "step": 900 }, { "epoch": 1.46, "learning_rate": 3.860741052212699e-05, "loss": 0.2992, "step": 901 }, { "epoch": 1.46, "learning_rate": 3.8603558450400286e-05, "loss": 0.2926, "step": 902 }, { "epoch": 1.46, "learning_rate": 3.8599701251091884e-05, "loss": 0.3505, "step": 903 }, { "epoch": 1.47, "learning_rate": 3.8595838925264915e-05, "loss": 0.3188, "step": 904 }, { "epoch": 1.47, "learning_rate": 3.8591971473983936e-05, "loss": 0.2946, "step": 905 }, { "epoch": 1.47, "learning_rate": 3.8588098898314895e-05, "loss": 0.1945, "step": 906 }, { "epoch": 1.47, "learning_rate": 3.858422119932518e-05, "loss": 0.3504, "step": 907 }, { "epoch": 1.47, "learning_rate": 3.858033837808357e-05, "loss": 0.3443, "step": 908 }, { "epoch": 1.47, "learning_rate": 3.8576450435660265e-05, "loss": 0.2745, "step": 909 }, { "epoch": 1.47, "learning_rate": 3.857255737312687e-05, "loss": 0.2731, "step": 910 }, { "epoch": 1.48, "learning_rate": 3.856865919155641e-05, "loss": 0.2413, "step": 911 }, { "epoch": 1.48, "learning_rate": 3.85647558920233e-05, "loss": 0.3528, "step": 912 }, { "epoch": 1.48, "learning_rate": 3.856084747560342e-05, "loss": 0.3092, "step": 913 }, { "epoch": 1.48, "learning_rate": 3.855693394337398e-05, "loss": 0.2341, "step": 914 }, { "epoch": 1.48, "learning_rate": 3.855301529641367e-05, "loss": 0.2425, "step": 915 }, { "epoch": 1.48, "learning_rate": 3.8549091535802544e-05, "loss": 0.3281, "step": 916 }, { "epoch": 1.49, "learning_rate": 3.85451626626221e-05, "loss": 0.4711, "step": 917 }, { "epoch": 1.49, "learning_rate": 3.8541228677955216e-05, "loss": 0.3296, "step": 918 }, { "epoch": 1.49, "learning_rate": 3.8537289582886195e-05, "loss": 0.3424, "step": 919 }, { "epoch": 1.49, "learning_rate": 3.853334537850074e-05, "loss": 0.305, "step": 920 }, { "epoch": 1.49, "learning_rate": 3.852939606588598e-05, "loss": 0.3486, "step": 921 }, { "epoch": 1.49, "learning_rate": 3.8525441646130435e-05, "loss": 0.3831, "step": 922 }, { "epoch": 1.5, "learning_rate": 3.852148212032403e-05, "loss": 0.3076, "step": 923 }, { "epoch": 1.5, "learning_rate": 3.851751748955811e-05, "loss": 0.245, "step": 924 }, { "epoch": 1.5, "learning_rate": 3.8513547754925424e-05, "loss": 0.3329, "step": 925 }, { "epoch": 1.5, "learning_rate": 3.8509572917520113e-05, "loss": 0.3338, "step": 926 }, { "epoch": 1.5, "learning_rate": 3.850559297843775e-05, "loss": 0.337, "step": 927 }, { "epoch": 1.5, "learning_rate": 3.8501607938775286e-05, "loss": 0.2636, "step": 928 }, { "epoch": 1.51, "learning_rate": 3.84976177996311e-05, "loss": 0.347, "step": 929 }, { "epoch": 1.51, "learning_rate": 3.8493622562104976e-05, "loss": 0.3428, "step": 930 }, { "epoch": 1.51, "learning_rate": 3.8489622227298085e-05, "loss": 0.3219, "step": 931 }, { "epoch": 1.51, "learning_rate": 3.848561679631302e-05, "loss": 0.3306, "step": 932 }, { "epoch": 1.51, "learning_rate": 3.8481606270253774e-05, "loss": 0.2808, "step": 933 }, { "epoch": 1.51, "learning_rate": 3.8477590650225735e-05, "loss": 0.2811, "step": 934 }, { "epoch": 1.52, "learning_rate": 3.847356993733572e-05, "loss": 0.2801, "step": 935 }, { "epoch": 1.52, "learning_rate": 3.846954413269191e-05, "loss": 0.3224, "step": 936 }, { "epoch": 1.52, "learning_rate": 3.846551323740393e-05, "loss": 0.3046, "step": 937 }, { "epoch": 1.52, "learning_rate": 3.846147725258278e-05, "loss": 0.2243, "step": 938 }, { "epoch": 1.52, "learning_rate": 3.845743617934088e-05, "loss": 0.3143, "step": 939 }, { "epoch": 1.52, "learning_rate": 3.845339001879204e-05, "loss": 0.2854, "step": 940 }, { "epoch": 1.53, "learning_rate": 3.8449338772051485e-05, "loss": 0.2275, "step": 941 }, { "epoch": 1.53, "learning_rate": 3.844528244023583e-05, "loss": 0.2549, "step": 942 }, { "epoch": 1.53, "learning_rate": 3.844122102446309e-05, "loss": 0.3096, "step": 943 }, { "epoch": 1.53, "learning_rate": 3.8437154525852697e-05, "loss": 0.2567, "step": 944 }, { "epoch": 1.53, "learning_rate": 3.843308294552547e-05, "loss": 0.3381, "step": 945 }, { "epoch": 1.53, "learning_rate": 3.842900628460364e-05, "loss": 0.302, "step": 946 }, { "epoch": 1.53, "learning_rate": 3.842492454421081e-05, "loss": 0.2638, "step": 947 }, { "epoch": 1.54, "learning_rate": 3.842083772547204e-05, "loss": 0.3072, "step": 948 }, { "epoch": 1.54, "learning_rate": 3.841674582951372e-05, "loss": 0.2034, "step": 949 }, { "epoch": 1.54, "learning_rate": 3.8412648857463694e-05, "loss": 0.2969, "step": 950 }, { "epoch": 1.54, "learning_rate": 3.8408546810451176e-05, "loss": 0.3215, "step": 951 }, { "epoch": 1.54, "learning_rate": 3.840443968960679e-05, "loss": 0.3311, "step": 952 }, { "epoch": 1.54, "learning_rate": 3.8400327496062555e-05, "loss": 0.2643, "step": 953 }, { "epoch": 1.55, "learning_rate": 3.839621023095189e-05, "loss": 0.372, "step": 954 }, { "epoch": 1.55, "learning_rate": 3.8392087895409614e-05, "loss": 0.2381, "step": 955 }, { "epoch": 1.55, "learning_rate": 3.8387960490571935e-05, "loss": 0.2418, "step": 956 }, { "epoch": 1.55, "learning_rate": 3.838382801757646e-05, "loss": 0.3641, "step": 957 }, { "epoch": 1.55, "learning_rate": 3.837969047756221e-05, "loss": 0.3023, "step": 958 }, { "epoch": 1.55, "learning_rate": 3.837554787166958e-05, "loss": 0.203, "step": 959 }, { "epoch": 1.56, "learning_rate": 3.837140020104036e-05, "loss": 0.2902, "step": 960 }, { "epoch": 1.56, "learning_rate": 3.836724746681776e-05, "loss": 0.2839, "step": 961 }, { "epoch": 1.56, "learning_rate": 3.836308967014638e-05, "loss": 0.3274, "step": 962 }, { "epoch": 1.56, "learning_rate": 3.8358926812172196e-05, "loss": 0.3548, "step": 963 }, { "epoch": 1.56, "learning_rate": 3.835475889404259e-05, "loss": 0.2874, "step": 964 }, { "epoch": 1.56, "learning_rate": 3.835058591690633e-05, "loss": 0.3609, "step": 965 }, { "epoch": 1.57, "learning_rate": 3.834640788191361e-05, "loss": 0.3309, "step": 966 }, { "epoch": 1.57, "learning_rate": 3.8342224790215975e-05, "loss": 0.3577, "step": 967 }, { "epoch": 1.57, "learning_rate": 3.8338036642966396e-05, "loss": 0.2769, "step": 968 }, { "epoch": 1.57, "learning_rate": 3.833384344131922e-05, "loss": 0.2796, "step": 969 }, { "epoch": 1.57, "learning_rate": 3.83296451864302e-05, "loss": 0.2687, "step": 970 }, { "epoch": 1.57, "learning_rate": 3.832544187945647e-05, "loss": 0.3277, "step": 971 }, { "epoch": 1.58, "learning_rate": 3.832123352155656e-05, "loss": 0.264, "step": 972 }, { "epoch": 1.58, "learning_rate": 3.831702011389039e-05, "loss": 0.2929, "step": 973 }, { "epoch": 1.58, "learning_rate": 3.8312801657619277e-05, "loss": 0.323, "step": 974 }, { "epoch": 1.58, "learning_rate": 3.8308578153905935e-05, "loss": 0.2529, "step": 975 }, { "epoch": 1.58, "learning_rate": 3.830434960391445e-05, "loss": 0.3479, "step": 976 }, { "epoch": 1.58, "learning_rate": 3.830011600881032e-05, "loss": 0.2764, "step": 977 }, { "epoch": 1.59, "learning_rate": 3.8295877369760426e-05, "loss": 0.3672, "step": 978 }, { "epoch": 1.59, "learning_rate": 3.829163368793302e-05, "loss": 0.3104, "step": 979 }, { "epoch": 1.59, "learning_rate": 3.828738496449779e-05, "loss": 0.2521, "step": 980 }, { "epoch": 1.59, "learning_rate": 3.8283131200625755e-05, "loss": 0.3592, "step": 981 }, { "epoch": 1.59, "learning_rate": 3.827887239748937e-05, "loss": 0.2764, "step": 982 }, { "epoch": 1.59, "learning_rate": 3.827460855626246e-05, "loss": 0.2913, "step": 983 }, { "epoch": 1.59, "learning_rate": 3.827033967812024e-05, "loss": 0.3031, "step": 984 }, { "epoch": 1.6, "learning_rate": 3.826606576423931e-05, "loss": 0.2306, "step": 985 }, { "epoch": 1.6, "learning_rate": 3.826178681579767e-05, "loss": 0.3528, "step": 986 }, { "epoch": 1.6, "learning_rate": 3.8257502833974684e-05, "loss": 0.3433, "step": 987 }, { "epoch": 1.6, "learning_rate": 3.825321381995114e-05, "loss": 0.3376, "step": 988 }, { "epoch": 1.6, "learning_rate": 3.824891977490918e-05, "loss": 0.3137, "step": 989 }, { "epoch": 1.6, "learning_rate": 3.824462070003235e-05, "loss": 0.2543, "step": 990 }, { "epoch": 1.61, "learning_rate": 3.8240316596505576e-05, "loss": 0.3041, "step": 991 }, { "epoch": 1.61, "learning_rate": 3.8236007465515156e-05, "loss": 0.269, "step": 992 }, { "epoch": 1.61, "learning_rate": 3.8231693308248804e-05, "loss": 0.2694, "step": 993 }, { "epoch": 1.61, "learning_rate": 3.822737412589561e-05, "loss": 0.3414, "step": 994 }, { "epoch": 1.61, "learning_rate": 3.822304991964603e-05, "loss": 0.3064, "step": 995 }, { "epoch": 1.61, "learning_rate": 3.821872069069192e-05, "loss": 0.298, "step": 996 }, { "epoch": 1.62, "learning_rate": 3.821438644022652e-05, "loss": 0.3826, "step": 997 }, { "epoch": 1.62, "learning_rate": 3.821004716944445e-05, "loss": 0.243, "step": 998 }, { "epoch": 1.62, "learning_rate": 3.820570287954172e-05, "loss": 0.2712, "step": 999 }, { "epoch": 1.62, "learning_rate": 3.8201353571715724e-05, "loss": 0.2695, "step": 1000 }, { "epoch": 1.62, "learning_rate": 3.819699924716522e-05, "loss": 0.2582, "step": 1001 }, { "epoch": 1.62, "learning_rate": 3.819263990709037e-05, "loss": 0.4175, "step": 1002 }, { "epoch": 1.63, "learning_rate": 3.818827555269272e-05, "loss": 0.2546, "step": 1003 }, { "epoch": 1.63, "learning_rate": 3.8183906185175174e-05, "loss": 0.3002, "step": 1004 }, { "epoch": 1.63, "learning_rate": 3.8179531805742043e-05, "loss": 0.2289, "step": 1005 }, { "epoch": 1.63, "learning_rate": 3.817515241559901e-05, "loss": 0.2786, "step": 1006 }, { "epoch": 1.63, "learning_rate": 3.817076801595313e-05, "loss": 0.2607, "step": 1007 }, { "epoch": 1.63, "learning_rate": 3.8166378608012854e-05, "loss": 0.2646, "step": 1008 }, { "epoch": 1.64, "learning_rate": 3.8161984192988015e-05, "loss": 0.3114, "step": 1009 }, { "epoch": 1.64, "learning_rate": 3.81575847720898e-05, "loss": 0.289, "step": 1010 }, { "epoch": 1.64, "learning_rate": 3.815318034653081e-05, "loss": 0.3076, "step": 1011 }, { "epoch": 1.64, "learning_rate": 3.8148770917525e-05, "loss": 0.3547, "step": 1012 }, { "epoch": 1.64, "learning_rate": 3.814435648628772e-05, "loss": 0.2811, "step": 1013 }, { "epoch": 1.64, "learning_rate": 3.8139937054035686e-05, "loss": 0.3338, "step": 1014 }, { "epoch": 1.65, "learning_rate": 3.8135512621986993e-05, "loss": 0.3739, "step": 1015 }, { "epoch": 1.65, "learning_rate": 3.813108319136113e-05, "loss": 0.4335, "step": 1016 }, { "epoch": 1.65, "learning_rate": 3.812664876337895e-05, "loss": 0.3793, "step": 1017 }, { "epoch": 1.65, "learning_rate": 3.8122209339262686e-05, "loss": 0.2581, "step": 1018 }, { "epoch": 1.65, "learning_rate": 3.8117764920235945e-05, "loss": 0.3188, "step": 1019 }, { "epoch": 1.65, "learning_rate": 3.811331550752372e-05, "loss": 0.3395, "step": 1020 }, { "epoch": 1.65, "learning_rate": 3.8108861102352375e-05, "loss": 0.3294, "step": 1021 }, { "epoch": 1.66, "learning_rate": 3.810440170594964e-05, "loss": 0.3378, "step": 1022 }, { "epoch": 1.66, "learning_rate": 3.809993731954464e-05, "loss": 0.2822, "step": 1023 }, { "epoch": 1.66, "learning_rate": 3.809546794436787e-05, "loss": 0.2903, "step": 1024 }, { "epoch": 1.66, "learning_rate": 3.809099358165118e-05, "loss": 0.351, "step": 1025 }, { "epoch": 1.66, "learning_rate": 3.808651423262782e-05, "loss": 0.2724, "step": 1026 }, { "epoch": 1.66, "learning_rate": 3.8082029898532406e-05, "loss": 0.2236, "step": 1027 }, { "epoch": 1.67, "learning_rate": 3.807754058060092e-05, "loss": 0.1383, "step": 1028 }, { "epoch": 1.67, "learning_rate": 3.807304628007074e-05, "loss": 0.3444, "step": 1029 }, { "epoch": 1.67, "learning_rate": 3.806854699818058e-05, "loss": 0.2652, "step": 1030 }, { "epoch": 1.67, "learning_rate": 3.806404273617056e-05, "loss": 0.2661, "step": 1031 }, { "epoch": 1.67, "learning_rate": 3.805953349528216e-05, "loss": 0.2572, "step": 1032 }, { "epoch": 1.67, "learning_rate": 3.8055019276758243e-05, "loss": 0.3238, "step": 1033 }, { "epoch": 1.68, "learning_rate": 3.805050008184302e-05, "loss": 0.2433, "step": 1034 }, { "epoch": 1.68, "learning_rate": 3.804597591178209e-05, "loss": 0.2532, "step": 1035 }, { "epoch": 1.68, "learning_rate": 3.804144676782243e-05, "loss": 0.308, "step": 1036 }, { "epoch": 1.68, "learning_rate": 3.803691265121238e-05, "loss": 0.2702, "step": 1037 }, { "epoch": 1.68, "learning_rate": 3.8032373563201644e-05, "loss": 0.2732, "step": 1038 }, { "epoch": 1.68, "learning_rate": 3.8027829505041296e-05, "loss": 0.2287, "step": 1039 }, { "epoch": 1.69, "learning_rate": 3.80232804779838e-05, "loss": 0.3048, "step": 1040 }, { "epoch": 1.69, "learning_rate": 3.801872648328297e-05, "loss": 0.2684, "step": 1041 }, { "epoch": 1.69, "learning_rate": 3.8014167522193985e-05, "loss": 0.357, "step": 1042 }, { "epoch": 1.69, "learning_rate": 3.800960359597342e-05, "loss": 0.3467, "step": 1043 }, { "epoch": 1.69, "learning_rate": 3.80050347058792e-05, "loss": 0.2465, "step": 1044 }, { "epoch": 1.69, "learning_rate": 3.80004608531706e-05, "loss": 0.4265, "step": 1045 }, { "epoch": 1.7, "learning_rate": 3.79958820391083e-05, "loss": 0.4031, "step": 1046 }, { "epoch": 1.7, "learning_rate": 3.799129826495433e-05, "loss": 0.3035, "step": 1047 }, { "epoch": 1.7, "learning_rate": 3.7986709531972074e-05, "loss": 0.2987, "step": 1048 }, { "epoch": 1.7, "learning_rate": 3.7982115841426305e-05, "loss": 0.2964, "step": 1049 }, { "epoch": 1.7, "learning_rate": 3.797751719458315e-05, "loss": 0.3108, "step": 1050 }, { "epoch": 1.7, "learning_rate": 3.797291359271011e-05, "loss": 0.3355, "step": 1051 }, { "epoch": 1.71, "learning_rate": 3.7968305037076035e-05, "loss": 0.347, "step": 1052 }, { "epoch": 1.71, "learning_rate": 3.796369152895117e-05, "loss": 0.317, "step": 1053 }, { "epoch": 1.71, "learning_rate": 3.7959073069607094e-05, "loss": 0.2701, "step": 1054 }, { "epoch": 1.71, "learning_rate": 3.795444966031676e-05, "loss": 0.2786, "step": 1055 }, { "epoch": 1.71, "learning_rate": 3.794982130235451e-05, "loss": 0.2706, "step": 1056 }, { "epoch": 1.71, "learning_rate": 3.7945187996996005e-05, "loss": 0.3984, "step": 1057 }, { "epoch": 1.71, "learning_rate": 3.7940549745518306e-05, "loss": 0.3318, "step": 1058 }, { "epoch": 1.72, "learning_rate": 3.7935906549199826e-05, "loss": 0.2724, "step": 1059 }, { "epoch": 1.72, "learning_rate": 3.7931258409320336e-05, "loss": 0.2902, "step": 1060 }, { "epoch": 1.72, "learning_rate": 3.792660532716098e-05, "loss": 0.2756, "step": 1061 }, { "epoch": 1.72, "learning_rate": 3.792194730400424e-05, "loss": 0.34, "step": 1062 }, { "epoch": 1.72, "learning_rate": 3.7917284341133995e-05, "loss": 0.2221, "step": 1063 }, { "epoch": 1.72, "learning_rate": 3.7912616439835475e-05, "loss": 0.3438, "step": 1064 }, { "epoch": 1.73, "learning_rate": 3.790794360139524e-05, "loss": 0.2458, "step": 1065 }, { "epoch": 1.73, "learning_rate": 3.790326582710125e-05, "loss": 0.2137, "step": 1066 }, { "epoch": 1.73, "learning_rate": 3.789858311824281e-05, "loss": 0.4089, "step": 1067 }, { "epoch": 1.73, "learning_rate": 3.789389547611058e-05, "loss": 0.2743, "step": 1068 }, { "epoch": 1.73, "learning_rate": 3.788920290199659e-05, "loss": 0.2579, "step": 1069 }, { "epoch": 1.73, "learning_rate": 3.788450539719423e-05, "loss": 0.2798, "step": 1070 }, { "epoch": 1.74, "learning_rate": 3.787980296299823e-05, "loss": 0.3623, "step": 1071 }, { "epoch": 1.74, "learning_rate": 3.7875095600704706e-05, "loss": 0.2631, "step": 1072 }, { "epoch": 1.74, "learning_rate": 3.7870383311611105e-05, "loss": 0.2766, "step": 1073 }, { "epoch": 1.74, "learning_rate": 3.786566609701626e-05, "loss": 0.369, "step": 1074 }, { "epoch": 1.74, "learning_rate": 3.786094395822033e-05, "loss": 0.2808, "step": 1075 }, { "epoch": 1.74, "learning_rate": 3.785621689652487e-05, "loss": 0.3198, "step": 1076 }, { "epoch": 1.75, "learning_rate": 3.785148491323275e-05, "loss": 0.3337, "step": 1077 }, { "epoch": 1.75, "learning_rate": 3.784674800964823e-05, "loss": 0.362, "step": 1078 }, { "epoch": 1.75, "learning_rate": 3.784200618707691e-05, "loss": 0.3166, "step": 1079 }, { "epoch": 1.75, "learning_rate": 3.783725944682574e-05, "loss": 0.3458, "step": 1080 }, { "epoch": 1.75, "learning_rate": 3.783250779020305e-05, "loss": 0.2347, "step": 1081 }, { "epoch": 1.75, "learning_rate": 3.782775121851849e-05, "loss": 0.2594, "step": 1082 }, { "epoch": 1.76, "learning_rate": 3.78229897330831e-05, "loss": 0.226, "step": 1083 }, { "epoch": 1.76, "learning_rate": 3.7818223335209256e-05, "loss": 0.2699, "step": 1084 }, { "epoch": 1.76, "learning_rate": 3.7813452026210684e-05, "loss": 0.4082, "step": 1085 }, { "epoch": 1.76, "learning_rate": 3.780867580740247e-05, "loss": 0.3494, "step": 1086 }, { "epoch": 1.76, "learning_rate": 3.780389468010106e-05, "loss": 0.2463, "step": 1087 }, { "epoch": 1.76, "learning_rate": 3.779910864562424e-05, "loss": 0.2813, "step": 1088 }, { "epoch": 1.76, "learning_rate": 3.779431770529115e-05, "loss": 0.261, "step": 1089 }, { "epoch": 1.77, "learning_rate": 3.77895218604223e-05, "loss": 0.2419, "step": 1090 }, { "epoch": 1.77, "learning_rate": 3.778472111233953e-05, "loss": 0.2424, "step": 1091 }, { "epoch": 1.77, "learning_rate": 3.777991546236604e-05, "loss": 0.3357, "step": 1092 }, { "epoch": 1.77, "learning_rate": 3.777510491182638e-05, "loss": 0.4025, "step": 1093 }, { "epoch": 1.77, "learning_rate": 3.777028946204647e-05, "loss": 0.2845, "step": 1094 }, { "epoch": 1.77, "learning_rate": 3.776546911435353e-05, "loss": 0.2943, "step": 1095 }, { "epoch": 1.78, "learning_rate": 3.7760643870076184e-05, "loss": 0.3063, "step": 1096 }, { "epoch": 1.78, "learning_rate": 3.775581373054438e-05, "loss": 0.2302, "step": 1097 }, { "epoch": 1.78, "learning_rate": 3.775097869708941e-05, "loss": 0.3009, "step": 1098 }, { "epoch": 1.78, "learning_rate": 3.774613877104394e-05, "loss": 0.2819, "step": 1099 }, { "epoch": 1.78, "learning_rate": 3.774129395374195e-05, "loss": 0.2901, "step": 1100 }, { "epoch": 1.78, "learning_rate": 3.773644424651881e-05, "loss": 0.3314, "step": 1101 }, { "epoch": 1.79, "learning_rate": 3.773158965071119e-05, "loss": 0.315, "step": 1102 }, { "epoch": 1.79, "learning_rate": 3.7726730167657136e-05, "loss": 0.3446, "step": 1103 }, { "epoch": 1.79, "learning_rate": 3.7721865798696056e-05, "loss": 0.323, "step": 1104 }, { "epoch": 1.79, "learning_rate": 3.771699654516867e-05, "loss": 0.2416, "step": 1105 }, { "epoch": 1.79, "learning_rate": 3.7712122408417055e-05, "loss": 0.2504, "step": 1106 }, { "epoch": 1.79, "learning_rate": 3.770724338978465e-05, "loss": 0.2514, "step": 1107 }, { "epoch": 1.8, "learning_rate": 3.770235949061621e-05, "loss": 0.3012, "step": 1108 }, { "epoch": 1.8, "learning_rate": 3.7697470712257877e-05, "loss": 0.3521, "step": 1109 }, { "epoch": 1.8, "learning_rate": 3.769257705605711e-05, "loss": 0.3185, "step": 1110 }, { "epoch": 1.8, "learning_rate": 3.7687678523362706e-05, "loss": 0.3032, "step": 1111 }, { "epoch": 1.8, "learning_rate": 3.768277511552482e-05, "loss": 0.3082, "step": 1112 }, { "epoch": 1.8, "learning_rate": 3.767786683389495e-05, "loss": 0.2805, "step": 1113 }, { "epoch": 1.81, "learning_rate": 3.7672953679825934e-05, "loss": 0.3086, "step": 1114 }, { "epoch": 1.81, "learning_rate": 3.7668035654671956e-05, "loss": 0.339, "step": 1115 }, { "epoch": 1.81, "learning_rate": 3.7663112759788535e-05, "loss": 0.3613, "step": 1116 }, { "epoch": 1.81, "learning_rate": 3.7658184996532535e-05, "loss": 0.2599, "step": 1117 }, { "epoch": 1.81, "learning_rate": 3.765325236626217e-05, "loss": 0.251, "step": 1118 }, { "epoch": 1.81, "learning_rate": 3.7648314870337e-05, "loss": 0.3051, "step": 1119 }, { "epoch": 1.82, "learning_rate": 3.76433725101179e-05, "loss": 0.3346, "step": 1120 }, { "epoch": 1.82, "learning_rate": 3.76384252869671e-05, "loss": 0.2946, "step": 1121 }, { "epoch": 1.82, "learning_rate": 3.763347320224819e-05, "loss": 0.317, "step": 1122 }, { "epoch": 1.82, "learning_rate": 3.7628516257326066e-05, "loss": 0.3467, "step": 1123 }, { "epoch": 1.82, "learning_rate": 3.762355445356698e-05, "loss": 0.3645, "step": 1124 }, { "epoch": 1.82, "learning_rate": 3.761858779233853e-05, "loss": 0.3227, "step": 1125 }, { "epoch": 1.82, "learning_rate": 3.761361627500964e-05, "loss": 0.2412, "step": 1126 }, { "epoch": 1.83, "learning_rate": 3.760863990295059e-05, "loss": 0.2693, "step": 1127 }, { "epoch": 1.83, "learning_rate": 3.760365867753297e-05, "loss": 0.3413, "step": 1128 }, { "epoch": 1.83, "learning_rate": 3.759867260012973e-05, "loss": 0.2969, "step": 1129 }, { "epoch": 1.83, "learning_rate": 3.7593681672115155e-05, "loss": 0.3238, "step": 1130 }, { "epoch": 1.83, "learning_rate": 3.7588685894864864e-05, "loss": 0.3022, "step": 1131 }, { "epoch": 1.83, "learning_rate": 3.75836852697558e-05, "loss": 0.224, "step": 1132 }, { "epoch": 1.84, "learning_rate": 3.757867979816626e-05, "loss": 0.3421, "step": 1133 }, { "epoch": 1.84, "learning_rate": 3.757366948147587e-05, "loss": 0.333, "step": 1134 }, { "epoch": 1.84, "learning_rate": 3.75686543210656e-05, "loss": 0.2932, "step": 1135 }, { "epoch": 1.84, "learning_rate": 3.7563634318317747e-05, "loss": 0.3211, "step": 1136 }, { "epoch": 1.84, "learning_rate": 3.7558609474615926e-05, "loss": 0.2703, "step": 1137 }, { "epoch": 1.84, "learning_rate": 3.755357979134511e-05, "loss": 0.3347, "step": 1138 }, { "epoch": 1.85, "learning_rate": 3.754854526989162e-05, "loss": 0.2398, "step": 1139 }, { "epoch": 1.85, "learning_rate": 3.754350591164306e-05, "loss": 0.2449, "step": 1140 }, { "epoch": 1.85, "learning_rate": 3.7538461717988406e-05, "loss": 0.3987, "step": 1141 }, { "epoch": 1.85, "learning_rate": 3.753341269031797e-05, "loss": 0.3693, "step": 1142 }, { "epoch": 1.85, "learning_rate": 3.752835883002336e-05, "loss": 0.2947, "step": 1143 }, { "epoch": 1.85, "learning_rate": 3.752330013849757e-05, "loss": 0.33, "step": 1144 }, { "epoch": 1.86, "learning_rate": 3.751823661713487e-05, "loss": 0.4075, "step": 1145 }, { "epoch": 1.86, "learning_rate": 3.7513168267330894e-05, "loss": 0.2628, "step": 1146 }, { "epoch": 1.86, "learning_rate": 3.75080950904826e-05, "loss": 0.2458, "step": 1147 }, { "epoch": 1.86, "learning_rate": 3.750301708798828e-05, "loss": 0.259, "step": 1148 }, { "epoch": 1.86, "learning_rate": 3.749793426124755e-05, "loss": 0.3137, "step": 1149 }, { "epoch": 1.86, "learning_rate": 3.749284661166135e-05, "loss": 0.3414, "step": 1150 }, { "epoch": 1.87, "learning_rate": 3.748775414063197e-05, "loss": 0.237, "step": 1151 }, { "epoch": 1.87, "learning_rate": 3.748265684956301e-05, "loss": 0.3404, "step": 1152 }, { "epoch": 1.87, "learning_rate": 3.7477554739859396e-05, "loss": 0.2449, "step": 1153 }, { "epoch": 1.87, "learning_rate": 3.7472447812927395e-05, "loss": 0.2606, "step": 1154 }, { "epoch": 1.87, "learning_rate": 3.7467336070174604e-05, "loss": 0.2347, "step": 1155 }, { "epoch": 1.87, "learning_rate": 3.746221951300993e-05, "loss": 0.2974, "step": 1156 }, { "epoch": 1.88, "learning_rate": 3.745709814284363e-05, "loss": 0.342, "step": 1157 }, { "epoch": 1.88, "learning_rate": 3.745197196108726e-05, "loss": 0.2859, "step": 1158 }, { "epoch": 1.88, "learning_rate": 3.744684096915373e-05, "loss": 0.4378, "step": 1159 }, { "epoch": 1.88, "learning_rate": 3.744170516845726e-05, "loss": 0.2292, "step": 1160 }, { "epoch": 1.88, "learning_rate": 3.74365645604134e-05, "loss": 0.3572, "step": 1161 }, { "epoch": 1.88, "learning_rate": 3.7431419146439014e-05, "loss": 0.2269, "step": 1162 }, { "epoch": 1.88, "learning_rate": 3.742626892795231e-05, "loss": 0.271, "step": 1163 }, { "epoch": 1.89, "learning_rate": 3.7421113906372805e-05, "loss": 0.2574, "step": 1164 }, { "epoch": 1.89, "learning_rate": 3.7415954083121345e-05, "loss": 0.2636, "step": 1165 }, { "epoch": 1.89, "learning_rate": 3.74107894596201e-05, "loss": 0.3705, "step": 1166 }, { "epoch": 1.89, "learning_rate": 3.740562003729257e-05, "loss": 0.3841, "step": 1167 }, { "epoch": 1.89, "learning_rate": 3.740044581756356e-05, "loss": 0.274, "step": 1168 }, { "epoch": 1.89, "learning_rate": 3.7395266801859214e-05, "loss": 0.333, "step": 1169 }, { "epoch": 1.9, "learning_rate": 3.739008299160698e-05, "loss": 0.3274, "step": 1170 }, { "epoch": 1.9, "learning_rate": 3.738489438823566e-05, "loss": 0.3166, "step": 1171 }, { "epoch": 1.9, "learning_rate": 3.737970099317535e-05, "loss": 0.4067, "step": 1172 }, { "epoch": 1.9, "learning_rate": 3.737450280785745e-05, "loss": 0.2614, "step": 1173 }, { "epoch": 1.9, "learning_rate": 3.736929983371473e-05, "loss": 0.2878, "step": 1174 }, { "epoch": 1.9, "learning_rate": 3.736409207218124e-05, "loss": 0.2579, "step": 1175 }, { "epoch": 1.91, "learning_rate": 3.735887952469237e-05, "loss": 0.3272, "step": 1176 }, { "epoch": 1.91, "learning_rate": 3.7353662192684814e-05, "loss": 0.2426, "step": 1177 }, { "epoch": 1.91, "learning_rate": 3.73484400775966e-05, "loss": 0.2509, "step": 1178 }, { "epoch": 1.91, "learning_rate": 3.7343213180867054e-05, "loss": 0.362, "step": 1179 }, { "epoch": 1.91, "learning_rate": 3.7337981503936847e-05, "loss": 0.2824, "step": 1180 }, { "epoch": 1.91, "learning_rate": 3.733274504824795e-05, "loss": 0.31, "step": 1181 }, { "epoch": 1.92, "learning_rate": 3.7327503815243644e-05, "loss": 0.3657, "step": 1182 }, { "epoch": 1.92, "learning_rate": 3.732225780636856e-05, "loss": 0.3474, "step": 1183 }, { "epoch": 1.92, "learning_rate": 3.731700702306859e-05, "loss": 0.2727, "step": 1184 }, { "epoch": 1.92, "learning_rate": 3.7311751466791e-05, "loss": 0.2978, "step": 1185 }, { "epoch": 1.92, "learning_rate": 3.730649113898433e-05, "loss": 0.2124, "step": 1186 }, { "epoch": 1.92, "learning_rate": 3.7301226041098465e-05, "loss": 0.2638, "step": 1187 }, { "epoch": 1.93, "learning_rate": 3.7295956174584586e-05, "loss": 0.2359, "step": 1188 }, { "epoch": 1.93, "learning_rate": 3.729068154089519e-05, "loss": 0.2931, "step": 1189 }, { "epoch": 1.93, "learning_rate": 3.7285402141484093e-05, "loss": 0.2694, "step": 1190 }, { "epoch": 1.93, "learning_rate": 3.728011797780642e-05, "loss": 0.2908, "step": 1191 }, { "epoch": 1.93, "learning_rate": 3.727482905131861e-05, "loss": 0.2522, "step": 1192 }, { "epoch": 1.93, "learning_rate": 3.726953536347843e-05, "loss": 0.3582, "step": 1193 }, { "epoch": 1.94, "learning_rate": 3.7264236915744924e-05, "loss": 0.3645, "step": 1194 }, { "epoch": 1.94, "learning_rate": 3.725893370957849e-05, "loss": 0.2672, "step": 1195 }, { "epoch": 1.94, "learning_rate": 3.7253625746440805e-05, "loss": 0.2576, "step": 1196 }, { "epoch": 1.94, "learning_rate": 3.724831302779488e-05, "loss": 0.2682, "step": 1197 }, { "epoch": 1.94, "learning_rate": 3.7242995555105016e-05, "loss": 0.2851, "step": 1198 }, { "epoch": 1.94, "learning_rate": 3.723767332983684e-05, "loss": 0.321, "step": 1199 }, { "epoch": 1.94, "learning_rate": 3.723234635345728e-05, "loss": 0.2469, "step": 1200 }, { "epoch": 1.95, "learning_rate": 3.722701462743458e-05, "loss": 0.2357, "step": 1201 }, { "epoch": 1.95, "learning_rate": 3.722167815323829e-05, "loss": 0.2743, "step": 1202 }, { "epoch": 1.95, "learning_rate": 3.7216336932339265e-05, "loss": 0.2914, "step": 1203 }, { "epoch": 1.95, "learning_rate": 3.7210990966209676e-05, "loss": 0.3073, "step": 1204 }, { "epoch": 1.95, "learning_rate": 3.7205640256322996e-05, "loss": 0.3119, "step": 1205 }, { "epoch": 1.95, "learning_rate": 3.720028480415401e-05, "loss": 0.4123, "step": 1206 }, { "epoch": 1.96, "learning_rate": 3.719492461117881e-05, "loss": 0.3017, "step": 1207 }, { "epoch": 1.96, "learning_rate": 3.7189559678874784e-05, "loss": 0.2347, "step": 1208 }, { "epoch": 1.96, "learning_rate": 3.718419000872063e-05, "loss": 0.2644, "step": 1209 }, { "epoch": 1.96, "learning_rate": 3.7178815602196385e-05, "loss": 0.2851, "step": 1210 }, { "epoch": 1.96, "learning_rate": 3.717343646078333e-05, "loss": 0.2723, "step": 1211 }, { "epoch": 1.96, "learning_rate": 3.7168052585964094e-05, "loss": 0.2522, "step": 1212 }, { "epoch": 1.97, "learning_rate": 3.716266397922261e-05, "loss": 0.3276, "step": 1213 }, { "epoch": 1.97, "learning_rate": 3.715727064204409e-05, "loss": 0.27, "step": 1214 }, { "epoch": 1.97, "learning_rate": 3.7151872575915085e-05, "loss": 0.2876, "step": 1215 }, { "epoch": 1.97, "learning_rate": 3.714646978232342e-05, "loss": 0.3891, "step": 1216 }, { "epoch": 1.97, "learning_rate": 3.7141062262758225e-05, "loss": 0.3353, "step": 1217 }, { "epoch": 1.97, "learning_rate": 3.713565001870995e-05, "loss": 0.2927, "step": 1218 }, { "epoch": 1.98, "learning_rate": 3.713023305167034e-05, "loss": 0.3802, "step": 1219 }, { "epoch": 1.98, "learning_rate": 3.7124811363132434e-05, "loss": 0.2566, "step": 1220 }, { "epoch": 1.98, "learning_rate": 3.711938495459058e-05, "loss": 0.3646, "step": 1221 }, { "epoch": 1.98, "learning_rate": 3.7113953827540424e-05, "loss": 0.5228, "step": 1222 }, { "epoch": 1.98, "learning_rate": 3.710851798347891e-05, "loss": 0.4314, "step": 1223 }, { "epoch": 1.98, "learning_rate": 3.710307742390429e-05, "loss": 0.2381, "step": 1224 }, { "epoch": 1.99, "learning_rate": 3.709763215031611e-05, "loss": 0.2953, "step": 1225 }, { "epoch": 1.99, "learning_rate": 3.709218216421522e-05, "loss": 0.3176, "step": 1226 }, { "epoch": 1.99, "learning_rate": 3.708672746710376e-05, "loss": 0.2845, "step": 1227 }, { "epoch": 1.99, "learning_rate": 3.708126806048517e-05, "loss": 0.2471, "step": 1228 }, { "epoch": 1.99, "learning_rate": 3.7075803945864206e-05, "loss": 0.2699, "step": 1229 }, { "epoch": 1.99, "learning_rate": 3.70703351247469e-05, "loss": 0.3738, "step": 1230 }, { "epoch": 2.0, "learning_rate": 3.706486159864058e-05, "loss": 0.265, "step": 1231 }, { "epoch": 2.0, "learning_rate": 3.705938336905389e-05, "loss": 0.3603, "step": 1232 }, { "epoch": 2.0, "learning_rate": 3.705390043749676e-05, "loss": 0.3057, "step": 1233 }, { "epoch": 2.0, "learning_rate": 3.704841280548041e-05, "loss": 0.2867, "step": 1234 }, { "epoch": 2.0, "learning_rate": 3.704292047451737e-05, "loss": 0.301, "step": 1235 }, { "epoch": 2.0, "learning_rate": 3.7037423446121454e-05, "loss": 0.2677, "step": 1236 }, { "epoch": 2.0, "learning_rate": 3.7031921721807763e-05, "loss": 0.2598, "step": 1237 }, { "epoch": 2.01, "learning_rate": 3.702641530309271e-05, "loss": 0.2914, "step": 1238 }, { "epoch": 2.01, "learning_rate": 3.7020904191494e-05, "loss": 0.2526, "step": 1239 }, { "epoch": 2.01, "learning_rate": 3.701538838853062e-05, "loss": 0.284, "step": 1240 }, { "epoch": 2.01, "learning_rate": 3.700986789572286e-05, "loss": 0.2814, "step": 1241 }, { "epoch": 2.01, "learning_rate": 3.700434271459229e-05, "loss": 0.221, "step": 1242 }, { "epoch": 2.01, "learning_rate": 3.6998812846661786e-05, "loss": 0.2301, "step": 1243 }, { "epoch": 2.02, "learning_rate": 3.699327829345551e-05, "loss": 0.3365, "step": 1244 }, { "epoch": 2.02, "learning_rate": 3.6987739056498925e-05, "loss": 0.2187, "step": 1245 }, { "epoch": 2.02, "learning_rate": 3.698219513731876e-05, "loss": 0.3298, "step": 1246 }, { "epoch": 2.02, "learning_rate": 3.697664653744306e-05, "loss": 0.2541, "step": 1247 }, { "epoch": 2.02, "learning_rate": 3.697109325840115e-05, "loss": 0.3659, "step": 1248 }, { "epoch": 2.02, "learning_rate": 3.696553530172365e-05, "loss": 0.3238, "step": 1249 }, { "epoch": 2.03, "learning_rate": 3.6959972668942456e-05, "loss": 0.3354, "step": 1250 }, { "epoch": 2.03, "learning_rate": 3.695440536159077e-05, "loss": 0.2831, "step": 1251 }, { "epoch": 2.03, "learning_rate": 3.694883338120306e-05, "loss": 0.2769, "step": 1252 }, { "epoch": 2.03, "learning_rate": 3.694325672931511e-05, "loss": 0.2446, "step": 1253 }, { "epoch": 2.03, "learning_rate": 3.693767540746397e-05, "loss": 0.2953, "step": 1254 }, { "epoch": 2.03, "learning_rate": 3.693208941718799e-05, "loss": 0.1836, "step": 1255 }, { "epoch": 2.04, "learning_rate": 3.692649876002679e-05, "loss": 0.2373, "step": 1256 }, { "epoch": 2.04, "learning_rate": 3.6920903437521305e-05, "loss": 0.267, "step": 1257 }, { "epoch": 2.04, "learning_rate": 3.691530345121372e-05, "loss": 0.2787, "step": 1258 }, { "epoch": 2.04, "learning_rate": 3.690969880264754e-05, "loss": 0.3202, "step": 1259 }, { "epoch": 2.04, "learning_rate": 3.6904089493367535e-05, "loss": 0.2765, "step": 1260 }, { "epoch": 2.04, "learning_rate": 3.689847552491975e-05, "loss": 0.2667, "step": 1261 }, { "epoch": 2.05, "learning_rate": 3.689285689885154e-05, "loss": 0.2665, "step": 1262 }, { "epoch": 2.05, "learning_rate": 3.688723361671154e-05, "loss": 0.2832, "step": 1263 }, { "epoch": 2.05, "learning_rate": 3.688160568004965e-05, "loss": 0.2807, "step": 1264 }, { "epoch": 2.05, "learning_rate": 3.687597309041705e-05, "loss": 0.3685, "step": 1265 }, { "epoch": 2.05, "learning_rate": 3.687033584936624e-05, "loss": 0.2635, "step": 1266 }, { "epoch": 2.05, "learning_rate": 3.6864693958450964e-05, "loss": 0.287, "step": 1267 }, { "epoch": 2.06, "learning_rate": 3.6859047419226254e-05, "loss": 0.3182, "step": 1268 }, { "epoch": 2.06, "learning_rate": 3.685339623324844e-05, "loss": 0.2459, "step": 1269 }, { "epoch": 2.06, "learning_rate": 3.684774040207512e-05, "loss": 0.246, "step": 1270 }, { "epoch": 2.06, "learning_rate": 3.684207992726519e-05, "loss": 0.2439, "step": 1271 }, { "epoch": 2.06, "learning_rate": 3.683641481037878e-05, "loss": 0.2232, "step": 1272 }, { "epoch": 2.06, "learning_rate": 3.683074505297736e-05, "loss": 0.2796, "step": 1273 }, { "epoch": 2.06, "learning_rate": 3.6825070656623626e-05, "loss": 0.2327, "step": 1274 }, { "epoch": 2.07, "learning_rate": 3.681939162288159e-05, "loss": 0.357, "step": 1275 }, { "epoch": 2.07, "learning_rate": 3.681370795331653e-05, "loss": 0.2784, "step": 1276 }, { "epoch": 2.07, "learning_rate": 3.6808019649494994e-05, "loss": 0.1787, "step": 1277 }, { "epoch": 2.07, "learning_rate": 3.6802326712984816e-05, "loss": 0.2082, "step": 1278 }, { "epoch": 2.07, "learning_rate": 3.67966291453551e-05, "loss": 0.2153, "step": 1279 }, { "epoch": 2.07, "learning_rate": 3.679092694817624e-05, "loss": 0.2552, "step": 1280 }, { "epoch": 2.08, "learning_rate": 3.678522012301988e-05, "loss": 0.2985, "step": 1281 }, { "epoch": 2.08, "learning_rate": 3.677950867145898e-05, "loss": 0.2962, "step": 1282 }, { "epoch": 2.08, "learning_rate": 3.677379259506773e-05, "loss": 0.2653, "step": 1283 }, { "epoch": 2.08, "learning_rate": 3.676807189542163e-05, "loss": 0.2505, "step": 1284 }, { "epoch": 2.08, "learning_rate": 3.676234657409743e-05, "loss": 0.2258, "step": 1285 }, { "epoch": 2.08, "learning_rate": 3.675661663267317e-05, "loss": 0.231, "step": 1286 }, { "epoch": 2.09, "learning_rate": 3.675088207272816e-05, "loss": 0.2511, "step": 1287 }, { "epoch": 2.09, "learning_rate": 3.674514289584297e-05, "loss": 0.2912, "step": 1288 }, { "epoch": 2.09, "learning_rate": 3.673939910359947e-05, "loss": 0.1975, "step": 1289 }, { "epoch": 2.09, "learning_rate": 3.6733650697580774e-05, "loss": 0.3195, "step": 1290 }, { "epoch": 2.09, "learning_rate": 3.6727897679371276e-05, "loss": 0.2735, "step": 1291 }, { "epoch": 2.09, "learning_rate": 3.6722140050556654e-05, "loss": 0.2324, "step": 1292 }, { "epoch": 2.1, "learning_rate": 3.671637781272384e-05, "loss": 0.3311, "step": 1293 }, { "epoch": 2.1, "learning_rate": 3.6710610967461044e-05, "loss": 0.2763, "step": 1294 }, { "epoch": 2.1, "learning_rate": 3.670483951635775e-05, "loss": 0.3091, "step": 1295 }, { "epoch": 2.1, "learning_rate": 3.66990634610047e-05, "loss": 0.3216, "step": 1296 }, { "epoch": 2.1, "learning_rate": 3.669328280299392e-05, "loss": 0.2103, "step": 1297 }, { "epoch": 2.1, "learning_rate": 3.668749754391869e-05, "loss": 0.205, "step": 1298 }, { "epoch": 2.11, "learning_rate": 3.668170768537357e-05, "loss": 0.212, "step": 1299 }, { "epoch": 2.11, "learning_rate": 3.6675913228954376e-05, "loss": 0.2343, "step": 1300 }, { "epoch": 2.11, "learning_rate": 3.6670114176258196e-05, "loss": 0.3186, "step": 1301 }, { "epoch": 2.11, "learning_rate": 3.6664310528883396e-05, "loss": 0.3075, "step": 1302 }, { "epoch": 2.11, "learning_rate": 3.665850228842959e-05, "loss": 0.3161, "step": 1303 }, { "epoch": 2.11, "learning_rate": 3.665268945649767e-05, "loss": 0.2888, "step": 1304 }, { "epoch": 2.12, "learning_rate": 3.664687203468979e-05, "loss": 0.2684, "step": 1305 }, { "epoch": 2.12, "learning_rate": 3.664105002460937e-05, "loss": 0.2192, "step": 1306 }, { "epoch": 2.12, "learning_rate": 3.6635223427861096e-05, "loss": 0.2308, "step": 1307 }, { "epoch": 2.12, "learning_rate": 3.662939224605091e-05, "loss": 0.3276, "step": 1308 }, { "epoch": 2.12, "learning_rate": 3.6623556480786024e-05, "loss": 0.2211, "step": 1309 }, { "epoch": 2.12, "learning_rate": 3.661771613367493e-05, "loss": 0.2591, "step": 1310 }, { "epoch": 2.12, "learning_rate": 3.661187120632734e-05, "loss": 0.2143, "step": 1311 }, { "epoch": 2.13, "learning_rate": 3.660602170035427e-05, "loss": 0.2154, "step": 1312 }, { "epoch": 2.13, "learning_rate": 3.660016761736799e-05, "loss": 0.251, "step": 1313 }, { "epoch": 2.13, "learning_rate": 3.6594308958982004e-05, "loss": 0.3008, "step": 1314 }, { "epoch": 2.13, "learning_rate": 3.658844572681111e-05, "loss": 0.2187, "step": 1315 }, { "epoch": 2.13, "learning_rate": 3.658257792247135e-05, "loss": 0.2337, "step": 1316 }, { "epoch": 2.13, "learning_rate": 3.657670554758003e-05, "loss": 0.3523, "step": 1317 }, { "epoch": 2.14, "learning_rate": 3.657082860375572e-05, "loss": 0.251, "step": 1318 }, { "epoch": 2.14, "learning_rate": 3.656494709261824e-05, "loss": 0.3254, "step": 1319 }, { "epoch": 2.14, "learning_rate": 3.655906101578868e-05, "loss": 0.3076, "step": 1320 }, { "epoch": 2.14, "learning_rate": 3.6553170374889375e-05, "loss": 0.278, "step": 1321 }, { "epoch": 2.14, "learning_rate": 3.6547275171543924e-05, "loss": 0.2762, "step": 1322 }, { "epoch": 2.14, "learning_rate": 3.6541375407377196e-05, "loss": 0.2935, "step": 1323 }, { "epoch": 2.15, "learning_rate": 3.65354710840153e-05, "loss": 0.2499, "step": 1324 }, { "epoch": 2.15, "learning_rate": 3.6529562203085595e-05, "loss": 0.225, "step": 1325 }, { "epoch": 2.15, "learning_rate": 3.652364876621673e-05, "loss": 0.3057, "step": 1326 }, { "epoch": 2.15, "learning_rate": 3.6517730775038575e-05, "loss": 0.202, "step": 1327 }, { "epoch": 2.15, "learning_rate": 3.6511808231182275e-05, "loss": 0.1745, "step": 1328 }, { "epoch": 2.15, "learning_rate": 3.6505881136280215e-05, "loss": 0.3159, "step": 1329 }, { "epoch": 2.16, "learning_rate": 3.6499949491966046e-05, "loss": 0.242, "step": 1330 }, { "epoch": 2.16, "learning_rate": 3.649401329987468e-05, "loss": 0.3227, "step": 1331 }, { "epoch": 2.16, "learning_rate": 3.648807256164226e-05, "loss": 0.2761, "step": 1332 }, { "epoch": 2.16, "learning_rate": 3.64821272789062e-05, "loss": 0.2789, "step": 1333 }, { "epoch": 2.16, "learning_rate": 3.6476177453305164e-05, "loss": 0.1947, "step": 1334 }, { "epoch": 2.16, "learning_rate": 3.647022308647905e-05, "loss": 0.2488, "step": 1335 }, { "epoch": 2.17, "learning_rate": 3.6464264180069044e-05, "loss": 0.2687, "step": 1336 }, { "epoch": 2.17, "learning_rate": 3.645830073571755e-05, "loss": 0.3061, "step": 1337 }, { "epoch": 2.17, "learning_rate": 3.6452332755068226e-05, "loss": 0.1773, "step": 1338 }, { "epoch": 2.17, "learning_rate": 3.6446360239766006e-05, "loss": 0.2401, "step": 1339 }, { "epoch": 2.17, "learning_rate": 3.644038319145705e-05, "loss": 0.2878, "step": 1340 }, { "epoch": 2.17, "learning_rate": 3.6434401611788764e-05, "loss": 0.2503, "step": 1341 }, { "epoch": 2.18, "learning_rate": 3.642841550240983e-05, "loss": 0.2435, "step": 1342 }, { "epoch": 2.18, "learning_rate": 3.6422424864970155e-05, "loss": 0.262, "step": 1343 }, { "epoch": 2.18, "learning_rate": 3.641642970112091e-05, "loss": 0.1812, "step": 1344 }, { "epoch": 2.18, "learning_rate": 3.641043001251447e-05, "loss": 0.2754, "step": 1345 }, { "epoch": 2.18, "learning_rate": 3.6404425800804533e-05, "loss": 0.1693, "step": 1346 }, { "epoch": 2.18, "learning_rate": 3.639841706764598e-05, "loss": 0.3507, "step": 1347 }, { "epoch": 2.18, "learning_rate": 3.639240381469497e-05, "loss": 0.2736, "step": 1348 }, { "epoch": 2.19, "learning_rate": 3.638638604360889e-05, "loss": 0.2219, "step": 1349 }, { "epoch": 2.19, "learning_rate": 3.638036375604638e-05, "loss": 0.3179, "step": 1350 }, { "epoch": 2.19, "learning_rate": 3.637433695366733e-05, "loss": 0.2329, "step": 1351 }, { "epoch": 2.19, "learning_rate": 3.636830563813287e-05, "loss": 0.2178, "step": 1352 }, { "epoch": 2.19, "learning_rate": 3.636226981110538e-05, "loss": 0.3047, "step": 1353 }, { "epoch": 2.19, "learning_rate": 3.635622947424845e-05, "loss": 0.2537, "step": 1354 }, { "epoch": 2.2, "learning_rate": 3.6350184629226976e-05, "loss": 0.2965, "step": 1355 }, { "epoch": 2.2, "learning_rate": 3.6344135277707035e-05, "loss": 0.2659, "step": 1356 }, { "epoch": 2.2, "learning_rate": 3.633808142135598e-05, "loss": 0.2682, "step": 1357 }, { "epoch": 2.2, "learning_rate": 3.63320230618424e-05, "loss": 0.2763, "step": 1358 }, { "epoch": 2.2, "learning_rate": 3.632596020083612e-05, "loss": 0.2098, "step": 1359 }, { "epoch": 2.2, "learning_rate": 3.631989284000821e-05, "loss": 0.2987, "step": 1360 }, { "epoch": 2.21, "learning_rate": 3.631382098103097e-05, "loss": 0.239, "step": 1361 }, { "epoch": 2.21, "learning_rate": 3.630774462557796e-05, "loss": 0.2356, "step": 1362 }, { "epoch": 2.21, "learning_rate": 3.630166377532396e-05, "loss": 0.239, "step": 1363 }, { "epoch": 2.21, "learning_rate": 3.6295578431945e-05, "loss": 0.2478, "step": 1364 }, { "epoch": 2.21, "learning_rate": 3.628948859711834e-05, "loss": 0.2575, "step": 1365 }, { "epoch": 2.21, "learning_rate": 3.628339427252249e-05, "loss": 0.2668, "step": 1366 }, { "epoch": 2.22, "learning_rate": 3.6277295459837184e-05, "loss": 0.4018, "step": 1367 }, { "epoch": 2.22, "learning_rate": 3.627119216074341e-05, "loss": 0.2242, "step": 1368 }, { "epoch": 2.22, "learning_rate": 3.626508437692337e-05, "loss": 0.2858, "step": 1369 }, { "epoch": 2.22, "learning_rate": 3.625897211006051e-05, "loss": 0.2992, "step": 1370 }, { "epoch": 2.22, "learning_rate": 3.6252855361839536e-05, "loss": 0.2632, "step": 1371 }, { "epoch": 2.22, "learning_rate": 3.6246734133946354e-05, "loss": 0.274, "step": 1372 }, { "epoch": 2.23, "learning_rate": 3.6240608428068126e-05, "loss": 0.2601, "step": 1373 }, { "epoch": 2.23, "learning_rate": 3.623447824589323e-05, "loss": 0.3861, "step": 1374 }, { "epoch": 2.23, "learning_rate": 3.62283435891113e-05, "loss": 0.2473, "step": 1375 }, { "epoch": 2.23, "learning_rate": 3.6222204459413186e-05, "loss": 0.2638, "step": 1376 }, { "epoch": 2.23, "learning_rate": 3.621606085849099e-05, "loss": 0.233, "step": 1377 }, { "epoch": 2.23, "learning_rate": 3.620991278803802e-05, "loss": 0.2536, "step": 1378 }, { "epoch": 2.24, "learning_rate": 3.6203760249748835e-05, "loss": 0.2736, "step": 1379 }, { "epoch": 2.24, "learning_rate": 3.619760324531923e-05, "loss": 0.2399, "step": 1380 }, { "epoch": 2.24, "learning_rate": 3.619144177644621e-05, "loss": 0.249, "step": 1381 }, { "epoch": 2.24, "learning_rate": 3.618527584482801e-05, "loss": 0.3104, "step": 1382 }, { "epoch": 2.24, "learning_rate": 3.617910545216414e-05, "loss": 0.2916, "step": 1383 }, { "epoch": 2.24, "learning_rate": 3.6172930600155284e-05, "loss": 0.3014, "step": 1384 }, { "epoch": 2.24, "learning_rate": 3.616675129050337e-05, "loss": 0.3786, "step": 1385 }, { "epoch": 2.25, "learning_rate": 3.6160567524911586e-05, "loss": 0.3414, "step": 1386 }, { "epoch": 2.25, "learning_rate": 3.61543793050843e-05, "loss": 0.1949, "step": 1387 }, { "epoch": 2.25, "learning_rate": 3.6148186632727156e-05, "loss": 0.338, "step": 1388 }, { "epoch": 2.25, "learning_rate": 3.614198950954699e-05, "loss": 0.2257, "step": 1389 }, { "epoch": 2.25, "learning_rate": 3.6135787937251875e-05, "loss": 0.3084, "step": 1390 }, { "epoch": 2.25, "learning_rate": 3.6129581917551105e-05, "loss": 0.2755, "step": 1391 }, { "epoch": 2.26, "learning_rate": 3.612337145215522e-05, "loss": 0.2684, "step": 1392 }, { "epoch": 2.26, "learning_rate": 3.611715654277596e-05, "loss": 0.2954, "step": 1393 }, { "epoch": 2.26, "learning_rate": 3.6110937191126305e-05, "loss": 0.2951, "step": 1394 }, { "epoch": 2.26, "learning_rate": 3.610471339892046e-05, "loss": 0.2478, "step": 1395 }, { "epoch": 2.26, "learning_rate": 3.6098485167873845e-05, "loss": 0.2674, "step": 1396 }, { "epoch": 2.26, "learning_rate": 3.609225249970311e-05, "loss": 0.302, "step": 1397 }, { "epoch": 2.27, "learning_rate": 3.6086015396126126e-05, "loss": 0.218, "step": 1398 }, { "epoch": 2.27, "learning_rate": 3.6079773858861985e-05, "loss": 0.2866, "step": 1399 }, { "epoch": 2.27, "learning_rate": 3.6073527889631e-05, "loss": 0.2452, "step": 1400 }, { "epoch": 2.27, "learning_rate": 3.6067277490154714e-05, "loss": 0.1999, "step": 1401 }, { "epoch": 2.27, "learning_rate": 3.606102266215589e-05, "loss": 0.3266, "step": 1402 }, { "epoch": 2.27, "learning_rate": 3.605476340735849e-05, "loss": 0.2619, "step": 1403 }, { "epoch": 2.28, "learning_rate": 3.6048499727487734e-05, "loss": 0.2776, "step": 1404 }, { "epoch": 2.28, "learning_rate": 3.604223162427002e-05, "loss": 0.2724, "step": 1405 }, { "epoch": 2.28, "learning_rate": 3.6035959099433e-05, "loss": 0.3884, "step": 1406 }, { "epoch": 2.28, "learning_rate": 3.602968215470553e-05, "loss": 0.2408, "step": 1407 }, { "epoch": 2.28, "learning_rate": 3.602340079181767e-05, "loss": 0.26, "step": 1408 }, { "epoch": 2.28, "learning_rate": 3.601711501250073e-05, "loss": 0.2797, "step": 1409 }, { "epoch": 2.29, "learning_rate": 3.601082481848721e-05, "loss": 0.2764, "step": 1410 }, { "epoch": 2.29, "learning_rate": 3.600453021151085e-05, "loss": 0.2203, "step": 1411 }, { "epoch": 2.29, "learning_rate": 3.599823119330657e-05, "loss": 0.3044, "step": 1412 }, { "epoch": 2.29, "learning_rate": 3.599192776561054e-05, "loss": 0.1858, "step": 1413 }, { "epoch": 2.29, "learning_rate": 3.5985619930160146e-05, "loss": 0.3081, "step": 1414 }, { "epoch": 2.29, "learning_rate": 3.597930768869396e-05, "loss": 0.2332, "step": 1415 }, { "epoch": 2.29, "learning_rate": 3.597299104295179e-05, "loss": 0.2931, "step": 1416 }, { "epoch": 2.3, "learning_rate": 3.5966669994674664e-05, "loss": 0.2476, "step": 1417 }, { "epoch": 2.3, "learning_rate": 3.5960344545604796e-05, "loss": 0.2382, "step": 1418 }, { "epoch": 2.3, "learning_rate": 3.5954014697485635e-05, "loss": 0.3468, "step": 1419 }, { "epoch": 2.3, "learning_rate": 3.594768045206184e-05, "loss": 0.2657, "step": 1420 }, { "epoch": 2.3, "learning_rate": 3.594134181107929e-05, "loss": 0.2675, "step": 1421 }, { "epoch": 2.3, "learning_rate": 3.5934998776285044e-05, "loss": 0.2332, "step": 1422 }, { "epoch": 2.31, "learning_rate": 3.59286513494274e-05, "loss": 0.3123, "step": 1423 }, { "epoch": 2.31, "learning_rate": 3.592229953225587e-05, "loss": 0.3188, "step": 1424 }, { "epoch": 2.31, "learning_rate": 3.591594332652115e-05, "loss": 0.2692, "step": 1425 }, { "epoch": 2.31, "learning_rate": 3.5909582733975174e-05, "loss": 0.216, "step": 1426 }, { "epoch": 2.31, "learning_rate": 3.5903217756371066e-05, "loss": 0.2405, "step": 1427 }, { "epoch": 2.31, "learning_rate": 3.589684839546316e-05, "loss": 0.2748, "step": 1428 }, { "epoch": 2.32, "learning_rate": 3.589047465300701e-05, "loss": 0.2486, "step": 1429 }, { "epoch": 2.32, "learning_rate": 3.588409653075937e-05, "loss": 0.2591, "step": 1430 }, { "epoch": 2.32, "learning_rate": 3.587771403047819e-05, "loss": 0.3112, "step": 1431 }, { "epoch": 2.32, "learning_rate": 3.587132715392266e-05, "loss": 0.3248, "step": 1432 }, { "epoch": 2.32, "learning_rate": 3.586493590285314e-05, "loss": 0.2257, "step": 1433 }, { "epoch": 2.32, "learning_rate": 3.585854027903121e-05, "loss": 0.2938, "step": 1434 }, { "epoch": 2.33, "learning_rate": 3.585214028421966e-05, "loss": 0.2939, "step": 1435 }, { "epoch": 2.33, "learning_rate": 3.584573592018248e-05, "loss": 0.2813, "step": 1436 }, { "epoch": 2.33, "learning_rate": 3.583932718868486e-05, "loss": 0.1722, "step": 1437 }, { "epoch": 2.33, "learning_rate": 3.58329140914932e-05, "loss": 0.2915, "step": 1438 }, { "epoch": 2.33, "learning_rate": 3.5826496630375115e-05, "loss": 0.2765, "step": 1439 }, { "epoch": 2.33, "learning_rate": 3.582007480709939e-05, "loss": 0.2763, "step": 1440 }, { "epoch": 2.34, "learning_rate": 3.581364862343604e-05, "loss": 0.2819, "step": 1441 }, { "epoch": 2.34, "learning_rate": 3.580721808115627e-05, "loss": 0.2842, "step": 1442 }, { "epoch": 2.34, "learning_rate": 3.5800783182032494e-05, "loss": 0.3083, "step": 1443 }, { "epoch": 2.34, "learning_rate": 3.579434392783832e-05, "loss": 0.2124, "step": 1444 }, { "epoch": 2.34, "learning_rate": 3.578790032034856e-05, "loss": 0.299, "step": 1445 }, { "epoch": 2.34, "learning_rate": 3.578145236133923e-05, "loss": 0.2766, "step": 1446 }, { "epoch": 2.35, "learning_rate": 3.5775000052587535e-05, "loss": 0.2004, "step": 1447 }, { "epoch": 2.35, "learning_rate": 3.5768543395871886e-05, "loss": 0.2234, "step": 1448 }, { "epoch": 2.35, "learning_rate": 3.576208239297189e-05, "loss": 0.2666, "step": 1449 }, { "epoch": 2.35, "learning_rate": 3.575561704566835e-05, "loss": 0.257, "step": 1450 }, { "epoch": 2.35, "learning_rate": 3.5749147355743275e-05, "loss": 0.231, "step": 1451 }, { "epoch": 2.35, "learning_rate": 3.5742673324979856e-05, "loss": 0.2716, "step": 1452 }, { "epoch": 2.35, "learning_rate": 3.5736194955162506e-05, "loss": 0.3119, "step": 1453 }, { "epoch": 2.36, "learning_rate": 3.572971224807679e-05, "loss": 0.2895, "step": 1454 }, { "epoch": 2.36, "learning_rate": 3.5723225205509524e-05, "loss": 0.2605, "step": 1455 }, { "epoch": 2.36, "learning_rate": 3.571673382924867e-05, "loss": 0.2993, "step": 1456 }, { "epoch": 2.36, "learning_rate": 3.571023812108342e-05, "loss": 0.2269, "step": 1457 }, { "epoch": 2.36, "learning_rate": 3.570373808280414e-05, "loss": 0.3115, "step": 1458 }, { "epoch": 2.36, "learning_rate": 3.5697233716202384e-05, "loss": 0.2182, "step": 1459 }, { "epoch": 2.37, "learning_rate": 3.569072502307093e-05, "loss": 0.3751, "step": 1460 }, { "epoch": 2.37, "learning_rate": 3.568421200520371e-05, "loss": 0.3255, "step": 1461 }, { "epoch": 2.37, "learning_rate": 3.567769466439588e-05, "loss": 0.287, "step": 1462 }, { "epoch": 2.37, "learning_rate": 3.567117300244376e-05, "loss": 0.2586, "step": 1463 }, { "epoch": 2.37, "learning_rate": 3.566464702114488e-05, "loss": 0.2658, "step": 1464 }, { "epoch": 2.37, "learning_rate": 3.565811672229796e-05, "loss": 0.3187, "step": 1465 }, { "epoch": 2.38, "learning_rate": 3.56515821077029e-05, "loss": 0.3297, "step": 1466 }, { "epoch": 2.38, "learning_rate": 3.5645043179160797e-05, "loss": 0.2482, "step": 1467 }, { "epoch": 2.38, "learning_rate": 3.563849993847394e-05, "loss": 0.2434, "step": 1468 }, { "epoch": 2.38, "learning_rate": 3.5631952387445795e-05, "loss": 0.285, "step": 1469 }, { "epoch": 2.38, "learning_rate": 3.5625400527881015e-05, "loss": 0.2416, "step": 1470 }, { "epoch": 2.38, "learning_rate": 3.561884436158546e-05, "loss": 0.2426, "step": 1471 }, { "epoch": 2.39, "learning_rate": 3.5612283890366155e-05, "loss": 0.2455, "step": 1472 }, { "epoch": 2.39, "learning_rate": 3.560571911603133e-05, "loss": 0.3009, "step": 1473 }, { "epoch": 2.39, "learning_rate": 3.559915004039039e-05, "loss": 0.2787, "step": 1474 }, { "epoch": 2.39, "learning_rate": 3.5592576665253934e-05, "loss": 0.2205, "step": 1475 }, { "epoch": 2.39, "learning_rate": 3.5585998992433724e-05, "loss": 0.2574, "step": 1476 }, { "epoch": 2.39, "learning_rate": 3.557941702374273e-05, "loss": 0.294, "step": 1477 }, { "epoch": 2.4, "learning_rate": 3.55728307609951e-05, "loss": 0.3513, "step": 1478 }, { "epoch": 2.4, "learning_rate": 3.556624020600618e-05, "loss": 0.3088, "step": 1479 }, { "epoch": 2.4, "learning_rate": 3.555964536059245e-05, "loss": 0.3909, "step": 1480 }, { "epoch": 2.4, "learning_rate": 3.555304622657163e-05, "loss": 0.36, "step": 1481 }, { "epoch": 2.4, "learning_rate": 3.554644280576259e-05, "loss": 0.2818, "step": 1482 }, { "epoch": 2.4, "learning_rate": 3.553983509998539e-05, "loss": 0.2778, "step": 1483 }, { "epoch": 2.41, "learning_rate": 3.5533223111061276e-05, "loss": 0.3747, "step": 1484 }, { "epoch": 2.41, "learning_rate": 3.552660684081266e-05, "loss": 0.2981, "step": 1485 }, { "epoch": 2.41, "learning_rate": 3.551998629106314e-05, "loss": 0.291, "step": 1486 }, { "epoch": 2.41, "learning_rate": 3.551336146363751e-05, "loss": 0.2509, "step": 1487 }, { "epoch": 2.41, "learning_rate": 3.550673236036172e-05, "loss": 0.3253, "step": 1488 }, { "epoch": 2.41, "learning_rate": 3.550009898306291e-05, "loss": 0.3547, "step": 1489 }, { "epoch": 2.41, "learning_rate": 3.5493461333569396e-05, "loss": 0.3332, "step": 1490 }, { "epoch": 2.42, "learning_rate": 3.548681941371068e-05, "loss": 0.2657, "step": 1491 }, { "epoch": 2.42, "learning_rate": 3.548017322531741e-05, "loss": 0.2446, "step": 1492 }, { "epoch": 2.42, "learning_rate": 3.547352277022146e-05, "loss": 0.2656, "step": 1493 }, { "epoch": 2.42, "learning_rate": 3.546686805025584e-05, "loss": 0.3305, "step": 1494 }, { "epoch": 2.42, "learning_rate": 3.546020906725474e-05, "loss": 0.3099, "step": 1495 }, { "epoch": 2.42, "learning_rate": 3.545354582305355e-05, "loss": 0.2686, "step": 1496 }, { "epoch": 2.43, "learning_rate": 3.5446878319488814e-05, "loss": 0.2735, "step": 1497 }, { "epoch": 2.43, "learning_rate": 3.544020655839824e-05, "loss": 0.253, "step": 1498 }, { "epoch": 2.43, "learning_rate": 3.543353054162074e-05, "loss": 0.2871, "step": 1499 }, { "epoch": 2.43, "learning_rate": 3.542685027099638e-05, "loss": 0.3531, "step": 1500 }, { "epoch": 2.43, "learning_rate": 3.542016574836639e-05, "loss": 0.2867, "step": 1501 }, { "epoch": 2.43, "learning_rate": 3.54134769755732e-05, "loss": 0.2824, "step": 1502 }, { "epoch": 2.44, "learning_rate": 3.540678395446039e-05, "loss": 0.2611, "step": 1503 }, { "epoch": 2.44, "learning_rate": 3.54000866868727e-05, "loss": 0.2452, "step": 1504 }, { "epoch": 2.44, "learning_rate": 3.5393385174656064e-05, "loss": 0.2444, "step": 1505 }, { "epoch": 2.44, "learning_rate": 3.538667941965758e-05, "loss": 0.2248, "step": 1506 }, { "epoch": 2.44, "learning_rate": 3.537996942372551e-05, "loss": 0.2186, "step": 1507 }, { "epoch": 2.44, "learning_rate": 3.5373255188709304e-05, "loss": 0.3174, "step": 1508 }, { "epoch": 2.45, "learning_rate": 3.5366536716459545e-05, "loss": 0.3004, "step": 1509 }, { "epoch": 2.45, "learning_rate": 3.5359814008828006e-05, "loss": 0.3186, "step": 1510 }, { "epoch": 2.45, "learning_rate": 3.535308706766763e-05, "loss": 0.2146, "step": 1511 }, { "epoch": 2.45, "learning_rate": 3.5346355894832515e-05, "loss": 0.2805, "step": 1512 }, { "epoch": 2.45, "learning_rate": 3.5339620492177944e-05, "loss": 0.2136, "step": 1513 }, { "epoch": 2.45, "learning_rate": 3.533288086156034e-05, "loss": 0.3, "step": 1514 }, { "epoch": 2.46, "learning_rate": 3.532613700483731e-05, "loss": 0.2874, "step": 1515 }, { "epoch": 2.46, "learning_rate": 3.5319388923867624e-05, "loss": 0.2169, "step": 1516 }, { "epoch": 2.46, "learning_rate": 3.531263662051121e-05, "loss": 0.2751, "step": 1517 }, { "epoch": 2.46, "learning_rate": 3.530588009662916e-05, "loss": 0.2415, "step": 1518 }, { "epoch": 2.46, "learning_rate": 3.529911935408374e-05, "loss": 0.2831, "step": 1519 }, { "epoch": 2.46, "learning_rate": 3.529235439473836e-05, "loss": 0.2165, "step": 1520 }, { "epoch": 2.47, "learning_rate": 3.5285585220457616e-05, "loss": 0.3332, "step": 1521 }, { "epoch": 2.47, "learning_rate": 3.5278811833107246e-05, "loss": 0.2227, "step": 1522 }, { "epoch": 2.47, "learning_rate": 3.5272034234554153e-05, "loss": 0.2672, "step": 1523 }, { "epoch": 2.47, "learning_rate": 3.526525242666641e-05, "loss": 0.3059, "step": 1524 }, { "epoch": 2.47, "learning_rate": 3.525846641131324e-05, "loss": 0.3046, "step": 1525 }, { "epoch": 2.47, "learning_rate": 3.525167619036503e-05, "loss": 0.2956, "step": 1526 }, { "epoch": 2.47, "learning_rate": 3.524488176569333e-05, "loss": 0.323, "step": 1527 }, { "epoch": 2.48, "learning_rate": 3.523808313917084e-05, "loss": 0.2802, "step": 1528 }, { "epoch": 2.48, "learning_rate": 3.5231280312671426e-05, "loss": 0.2799, "step": 1529 }, { "epoch": 2.48, "learning_rate": 3.52244732880701e-05, "loss": 0.2997, "step": 1530 }, { "epoch": 2.48, "learning_rate": 3.521766206724305e-05, "loss": 0.2698, "step": 1531 }, { "epoch": 2.48, "learning_rate": 3.521084665206761e-05, "loss": 0.3086, "step": 1532 }, { "epoch": 2.48, "learning_rate": 3.5204027044422254e-05, "loss": 0.2605, "step": 1533 }, { "epoch": 2.49, "learning_rate": 3.5197203246186654e-05, "loss": 0.2136, "step": 1534 }, { "epoch": 2.49, "learning_rate": 3.519037525924158e-05, "loss": 0.2652, "step": 1535 }, { "epoch": 2.49, "learning_rate": 3.518354308546901e-05, "loss": 0.3514, "step": 1536 }, { "epoch": 2.49, "learning_rate": 3.517670672675205e-05, "loss": 0.2669, "step": 1537 }, { "epoch": 2.49, "learning_rate": 3.516986618497496e-05, "loss": 0.3272, "step": 1538 }, { "epoch": 2.49, "learning_rate": 3.516302146202314e-05, "loss": 0.2457, "step": 1539 }, { "epoch": 2.5, "learning_rate": 3.5156172559783174e-05, "loss": 0.2217, "step": 1540 }, { "epoch": 2.5, "learning_rate": 3.5149319480142785e-05, "loss": 0.3444, "step": 1541 }, { "epoch": 2.5, "learning_rate": 3.514246222499084e-05, "loss": 0.2617, "step": 1542 }, { "epoch": 2.5, "learning_rate": 3.5135600796217357e-05, "loss": 0.2664, "step": 1543 }, { "epoch": 2.5, "learning_rate": 3.512873519571351e-05, "loss": 0.3366, "step": 1544 }, { "epoch": 2.5, "learning_rate": 3.512186542537162e-05, "loss": 0.2592, "step": 1545 }, { "epoch": 2.51, "learning_rate": 3.511499148708517e-05, "loss": 0.2344, "step": 1546 }, { "epoch": 2.51, "learning_rate": 3.510811338274876e-05, "loss": 0.2508, "step": 1547 }, { "epoch": 2.51, "learning_rate": 3.510123111425818e-05, "loss": 0.2676, "step": 1548 }, { "epoch": 2.51, "learning_rate": 3.509434468351033e-05, "loss": 0.3064, "step": 1549 }, { "epoch": 2.51, "learning_rate": 3.5087454092403285e-05, "loss": 0.2635, "step": 1550 }, { "epoch": 2.51, "learning_rate": 3.5080559342836245e-05, "loss": 0.2922, "step": 1551 }, { "epoch": 2.52, "learning_rate": 3.5073660436709574e-05, "loss": 0.2594, "step": 1552 }, { "epoch": 2.52, "learning_rate": 3.5066757375924765e-05, "loss": 0.2339, "step": 1553 }, { "epoch": 2.52, "learning_rate": 3.505985016238448e-05, "loss": 0.3301, "step": 1554 }, { "epoch": 2.52, "learning_rate": 3.50529387979925e-05, "loss": 0.29, "step": 1555 }, { "epoch": 2.52, "learning_rate": 3.5046023284653756e-05, "loss": 0.2508, "step": 1556 }, { "epoch": 2.52, "learning_rate": 3.503910362427434e-05, "loss": 0.3247, "step": 1557 }, { "epoch": 2.53, "learning_rate": 3.503217981876147e-05, "loss": 0.2755, "step": 1558 }, { "epoch": 2.53, "learning_rate": 3.502525187002351e-05, "loss": 0.1814, "step": 1559 }, { "epoch": 2.53, "learning_rate": 3.501831977996997e-05, "loss": 0.2609, "step": 1560 }, { "epoch": 2.53, "learning_rate": 3.501138355051149e-05, "loss": 0.3042, "step": 1561 }, { "epoch": 2.53, "learning_rate": 3.5004443183559864e-05, "loss": 0.2809, "step": 1562 }, { "epoch": 2.53, "learning_rate": 3.499749868102802e-05, "loss": 0.2749, "step": 1563 }, { "epoch": 2.53, "learning_rate": 3.499055004483004e-05, "loss": 0.2612, "step": 1564 }, { "epoch": 2.54, "learning_rate": 3.498359727688112e-05, "loss": 0.3132, "step": 1565 }, { "epoch": 2.54, "learning_rate": 3.4976640379097594e-05, "loss": 0.3013, "step": 1566 }, { "epoch": 2.54, "learning_rate": 3.496967935339698e-05, "loss": 0.2864, "step": 1567 }, { "epoch": 2.54, "learning_rate": 3.4962714201697886e-05, "loss": 0.24, "step": 1568 }, { "epoch": 2.54, "learning_rate": 3.495574492592007e-05, "loss": 0.2334, "step": 1569 }, { "epoch": 2.54, "learning_rate": 3.494877152798442e-05, "loss": 0.2208, "step": 1570 }, { "epoch": 2.55, "learning_rate": 3.4941794009813e-05, "loss": 0.3208, "step": 1571 }, { "epoch": 2.55, "learning_rate": 3.493481237332895e-05, "loss": 0.3466, "step": 1572 }, { "epoch": 2.55, "learning_rate": 3.492782662045659e-05, "loss": 0.2858, "step": 1573 }, { "epoch": 2.55, "learning_rate": 3.4920836753121366e-05, "loss": 0.2314, "step": 1574 }, { "epoch": 2.55, "learning_rate": 3.4913842773249824e-05, "loss": 0.3288, "step": 1575 }, { "epoch": 2.55, "learning_rate": 3.4906844682769694e-05, "loss": 0.2685, "step": 1576 }, { "epoch": 2.56, "learning_rate": 3.4899842483609804e-05, "loss": 0.2675, "step": 1577 }, { "epoch": 2.56, "learning_rate": 3.489283617770014e-05, "loss": 0.2411, "step": 1578 }, { "epoch": 2.56, "learning_rate": 3.4885825766971785e-05, "loss": 0.3064, "step": 1579 }, { "epoch": 2.56, "learning_rate": 3.487881125335699e-05, "loss": 0.2359, "step": 1580 }, { "epoch": 2.56, "learning_rate": 3.487179263878912e-05, "loss": 0.3138, "step": 1581 }, { "epoch": 2.56, "learning_rate": 3.486476992520267e-05, "loss": 0.2084, "step": 1582 }, { "epoch": 2.57, "learning_rate": 3.4857743114533255e-05, "loss": 0.3266, "step": 1583 }, { "epoch": 2.57, "learning_rate": 3.4850712208717654e-05, "loss": 0.2886, "step": 1584 }, { "epoch": 2.57, "learning_rate": 3.484367720969373e-05, "loss": 0.3269, "step": 1585 }, { "epoch": 2.57, "learning_rate": 3.4836638119400504e-05, "loss": 0.3387, "step": 1586 }, { "epoch": 2.57, "learning_rate": 3.4829594939778115e-05, "loss": 0.2907, "step": 1587 }, { "epoch": 2.57, "learning_rate": 3.482254767276783e-05, "loss": 0.2733, "step": 1588 }, { "epoch": 2.58, "learning_rate": 3.481549632031205e-05, "loss": 0.3115, "step": 1589 }, { "epoch": 2.58, "learning_rate": 3.480844088435428e-05, "loss": 0.3676, "step": 1590 }, { "epoch": 2.58, "learning_rate": 3.480138136683918e-05, "loss": 0.2224, "step": 1591 }, { "epoch": 2.58, "learning_rate": 3.4794317769712513e-05, "loss": 0.3262, "step": 1592 }, { "epoch": 2.58, "learning_rate": 3.4787250094921177e-05, "loss": 0.2618, "step": 1593 }, { "epoch": 2.58, "learning_rate": 3.478017834441319e-05, "loss": 0.2955, "step": 1594 }, { "epoch": 2.59, "learning_rate": 3.4773102520137684e-05, "loss": 0.3208, "step": 1595 }, { "epoch": 2.59, "learning_rate": 3.4766022624044936e-05, "loss": 0.2214, "step": 1596 }, { "epoch": 2.59, "learning_rate": 3.475893865808633e-05, "loss": 0.2191, "step": 1597 }, { "epoch": 2.59, "learning_rate": 3.475185062421438e-05, "loss": 0.254, "step": 1598 }, { "epoch": 2.59, "learning_rate": 3.4744758524382714e-05, "loss": 0.2825, "step": 1599 }, { "epoch": 2.59, "learning_rate": 3.473766236054607e-05, "loss": 0.2811, "step": 1600 }, { "epoch": 2.59, "learning_rate": 3.4730562134660334e-05, "loss": 0.1739, "step": 1601 }, { "epoch": 2.6, "learning_rate": 3.472345784868249e-05, "loss": 0.319, "step": 1602 }, { "epoch": 2.6, "learning_rate": 3.4716349504570655e-05, "loss": 0.2723, "step": 1603 }, { "epoch": 2.6, "learning_rate": 3.4709237104284044e-05, "loss": 0.2283, "step": 1604 }, { "epoch": 2.6, "learning_rate": 3.470212064978301e-05, "loss": 0.2937, "step": 1605 }, { "epoch": 2.6, "learning_rate": 3.4695000143029013e-05, "loss": 0.2681, "step": 1606 }, { "epoch": 2.6, "learning_rate": 3.4687875585984646e-05, "loss": 0.2807, "step": 1607 }, { "epoch": 2.61, "learning_rate": 3.4680746980613594e-05, "loss": 0.2642, "step": 1608 }, { "epoch": 2.61, "learning_rate": 3.467361432888067e-05, "loss": 0.2769, "step": 1609 }, { "epoch": 2.61, "learning_rate": 3.4666477632751814e-05, "loss": 0.2397, "step": 1610 }, { "epoch": 2.61, "learning_rate": 3.465933689419405e-05, "loss": 0.3273, "step": 1611 }, { "epoch": 2.61, "learning_rate": 3.465219211517555e-05, "loss": 0.225, "step": 1612 }, { "epoch": 2.61, "learning_rate": 3.4645043297665574e-05, "loss": 0.4216, "step": 1613 }, { "epoch": 2.62, "learning_rate": 3.463789044363451e-05, "loss": 0.2949, "step": 1614 }, { "epoch": 2.62, "learning_rate": 3.463073355505386e-05, "loss": 0.3819, "step": 1615 }, { "epoch": 2.62, "learning_rate": 3.4623572633896224e-05, "loss": 0.2142, "step": 1616 }, { "epoch": 2.62, "learning_rate": 3.461640768213532e-05, "loss": 0.3498, "step": 1617 }, { "epoch": 2.62, "learning_rate": 3.4609238701745985e-05, "loss": 0.2432, "step": 1618 }, { "epoch": 2.62, "learning_rate": 3.460206569470416e-05, "loss": 0.2061, "step": 1619 }, { "epoch": 2.63, "learning_rate": 3.459488866298689e-05, "loss": 0.2593, "step": 1620 }, { "epoch": 2.63, "learning_rate": 3.4587707608572336e-05, "loss": 0.2128, "step": 1621 }, { "epoch": 2.63, "learning_rate": 3.4580522533439773e-05, "loss": 0.3408, "step": 1622 }, { "epoch": 2.63, "learning_rate": 3.4573333439569564e-05, "loss": 0.2553, "step": 1623 }, { "epoch": 2.63, "learning_rate": 3.456614032894322e-05, "loss": 0.1846, "step": 1624 }, { "epoch": 2.63, "learning_rate": 3.455894320354331e-05, "loss": 0.3348, "step": 1625 }, { "epoch": 2.64, "learning_rate": 3.455174206535354e-05, "loss": 0.3141, "step": 1626 }, { "epoch": 2.64, "learning_rate": 3.4544536916358704e-05, "loss": 0.1972, "step": 1627 }, { "epoch": 2.64, "learning_rate": 3.4537327758544736e-05, "loss": 0.2547, "step": 1628 }, { "epoch": 2.64, "learning_rate": 3.453011459389862e-05, "loss": 0.4165, "step": 1629 }, { "epoch": 2.64, "learning_rate": 3.452289742440851e-05, "loss": 0.2548, "step": 1630 }, { "epoch": 2.64, "learning_rate": 3.4515676252063595e-05, "loss": 0.3518, "step": 1631 }, { "epoch": 2.65, "learning_rate": 3.450845107885423e-05, "loss": 0.1952, "step": 1632 }, { "epoch": 2.65, "learning_rate": 3.450122190677182e-05, "loss": 0.2702, "step": 1633 }, { "epoch": 2.65, "learning_rate": 3.449398873780891e-05, "loss": 0.2692, "step": 1634 }, { "epoch": 2.65, "learning_rate": 3.448675157395913e-05, "loss": 0.2851, "step": 1635 }, { "epoch": 2.65, "learning_rate": 3.447951041721721e-05, "loss": 0.2922, "step": 1636 }, { "epoch": 2.65, "learning_rate": 3.4472265269578986e-05, "loss": 0.3231, "step": 1637 }, { "epoch": 2.65, "learning_rate": 3.4465016133041405e-05, "loss": 0.2646, "step": 1638 }, { "epoch": 2.66, "learning_rate": 3.445776300960247e-05, "loss": 0.2493, "step": 1639 }, { "epoch": 2.66, "learning_rate": 3.445050590126136e-05, "loss": 0.3157, "step": 1640 }, { "epoch": 2.66, "learning_rate": 3.444324481001827e-05, "loss": 0.3226, "step": 1641 }, { "epoch": 2.66, "learning_rate": 3.4435979737874534e-05, "loss": 0.2735, "step": 1642 }, { "epoch": 2.66, "learning_rate": 3.442871068683258e-05, "loss": 0.275, "step": 1643 }, { "epoch": 2.66, "learning_rate": 3.442143765889594e-05, "loss": 0.242, "step": 1644 }, { "epoch": 2.67, "learning_rate": 3.4414160656069224e-05, "loss": 0.2454, "step": 1645 }, { "epoch": 2.67, "learning_rate": 3.440687968035815e-05, "loss": 0.3953, "step": 1646 }, { "epoch": 2.67, "learning_rate": 3.439959473376953e-05, "loss": 0.2835, "step": 1647 }, { "epoch": 2.67, "learning_rate": 3.439230581831126e-05, "loss": 0.2124, "step": 1648 }, { "epoch": 2.67, "learning_rate": 3.438501293599235e-05, "loss": 0.3186, "step": 1649 }, { "epoch": 2.67, "learning_rate": 3.4377716088822875e-05, "loss": 0.3185, "step": 1650 }, { "epoch": 2.68, "learning_rate": 3.437041527881403e-05, "loss": 0.2616, "step": 1651 }, { "epoch": 2.68, "learning_rate": 3.436311050797809e-05, "loss": 0.3445, "step": 1652 }, { "epoch": 2.68, "learning_rate": 3.435580177832842e-05, "loss": 0.2971, "step": 1653 }, { "epoch": 2.68, "learning_rate": 3.434848909187948e-05, "loss": 0.2883, "step": 1654 }, { "epoch": 2.68, "learning_rate": 3.434117245064683e-05, "loss": 0.3184, "step": 1655 }, { "epoch": 2.68, "learning_rate": 3.433385185664709e-05, "loss": 0.2432, "step": 1656 }, { "epoch": 2.69, "learning_rate": 3.432652731189801e-05, "loss": 0.2623, "step": 1657 }, { "epoch": 2.69, "learning_rate": 3.431919881841839e-05, "loss": 0.4514, "step": 1658 }, { "epoch": 2.69, "learning_rate": 3.431186637822815e-05, "loss": 0.2812, "step": 1659 }, { "epoch": 2.69, "learning_rate": 3.4304529993348276e-05, "loss": 0.2623, "step": 1660 }, { "epoch": 2.69, "learning_rate": 3.429718966580085e-05, "loss": 0.2605, "step": 1661 }, { "epoch": 2.69, "learning_rate": 3.4289845397609044e-05, "loss": 0.2811, "step": 1662 }, { "epoch": 2.7, "learning_rate": 3.428249719079711e-05, "loss": 0.3137, "step": 1663 }, { "epoch": 2.7, "learning_rate": 3.42751450473904e-05, "loss": 0.2757, "step": 1664 }, { "epoch": 2.7, "learning_rate": 3.4267788969415315e-05, "loss": 0.2124, "step": 1665 }, { "epoch": 2.7, "learning_rate": 3.426042895889938e-05, "loss": 0.2076, "step": 1666 }, { "epoch": 2.7, "learning_rate": 3.4253065017871186e-05, "loss": 0.3162, "step": 1667 }, { "epoch": 2.7, "learning_rate": 3.424569714836041e-05, "loss": 0.3089, "step": 1668 }, { "epoch": 2.71, "learning_rate": 3.4238325352397814e-05, "loss": 0.3049, "step": 1669 }, { "epoch": 2.71, "learning_rate": 3.423094963201524e-05, "loss": 0.2385, "step": 1670 }, { "epoch": 2.71, "learning_rate": 3.422356998924561e-05, "loss": 0.2591, "step": 1671 }, { "epoch": 2.71, "learning_rate": 3.4216186426122924e-05, "loss": 0.2701, "step": 1672 }, { "epoch": 2.71, "learning_rate": 3.4208798944682264e-05, "loss": 0.2961, "step": 1673 }, { "epoch": 2.71, "learning_rate": 3.4201407546959796e-05, "loss": 0.2048, "step": 1674 }, { "epoch": 2.71, "learning_rate": 3.419401223499278e-05, "loss": 0.2633, "step": 1675 }, { "epoch": 2.72, "learning_rate": 3.418661301081953e-05, "loss": 0.1984, "step": 1676 }, { "epoch": 2.72, "learning_rate": 3.4179209876479435e-05, "loss": 0.1849, "step": 1677 }, { "epoch": 2.72, "learning_rate": 3.4171802834012996e-05, "loss": 0.2746, "step": 1678 }, { "epoch": 2.72, "learning_rate": 3.416439188546175e-05, "loss": 0.2407, "step": 1679 }, { "epoch": 2.72, "learning_rate": 3.415697703286835e-05, "loss": 0.261, "step": 1680 }, { "epoch": 2.72, "learning_rate": 3.414955827827649e-05, "loss": 0.273, "step": 1681 }, { "epoch": 2.73, "learning_rate": 3.4142135623730954e-05, "loss": 0.3251, "step": 1682 }, { "epoch": 2.73, "learning_rate": 3.413470907127761e-05, "loss": 0.3158, "step": 1683 }, { "epoch": 2.73, "learning_rate": 3.412727862296339e-05, "loss": 0.2516, "step": 1684 }, { "epoch": 2.73, "learning_rate": 3.411984428083629e-05, "loss": 0.2926, "step": 1685 }, { "epoch": 2.73, "learning_rate": 3.411240604694541e-05, "loss": 0.2476, "step": 1686 }, { "epoch": 2.73, "learning_rate": 3.410496392334089e-05, "loss": 0.2439, "step": 1687 }, { "epoch": 2.74, "learning_rate": 3.409751791207397e-05, "loss": 0.2472, "step": 1688 }, { "epoch": 2.74, "learning_rate": 3.409006801519692e-05, "loss": 0.1926, "step": 1689 }, { "epoch": 2.74, "learning_rate": 3.408261423476314e-05, "loss": 0.2537, "step": 1690 }, { "epoch": 2.74, "learning_rate": 3.4075156572827045e-05, "loss": 0.2559, "step": 1691 }, { "epoch": 2.74, "learning_rate": 3.406769503144416e-05, "loss": 0.2482, "step": 1692 }, { "epoch": 2.74, "learning_rate": 3.4060229612671056e-05, "loss": 0.3485, "step": 1693 }, { "epoch": 2.75, "learning_rate": 3.405276031856537e-05, "loss": 0.2651, "step": 1694 }, { "epoch": 2.75, "learning_rate": 3.404528715118582e-05, "loss": 0.3348, "step": 1695 }, { "epoch": 2.75, "learning_rate": 3.403781011259221e-05, "loss": 0.2547, "step": 1696 }, { "epoch": 2.75, "learning_rate": 3.403032920484536e-05, "loss": 0.3395, "step": 1697 }, { "epoch": 2.75, "learning_rate": 3.402284443000721e-05, "loss": 0.3716, "step": 1698 }, { "epoch": 2.75, "learning_rate": 3.4015355790140715e-05, "loss": 0.2471, "step": 1699 }, { "epoch": 2.76, "learning_rate": 3.4007863287309946e-05, "loss": 0.3604, "step": 1700 }, { "epoch": 2.76, "learning_rate": 3.400036692358e-05, "loss": 0.2496, "step": 1701 }, { "epoch": 2.76, "learning_rate": 3.399286670101705e-05, "loss": 0.3705, "step": 1702 }, { "epoch": 2.76, "learning_rate": 3.3985362621688354e-05, "loss": 0.274, "step": 1703 }, { "epoch": 2.76, "learning_rate": 3.397785468766219e-05, "loss": 0.3233, "step": 1704 }, { "epoch": 2.76, "learning_rate": 3.397034290100794e-05, "loss": 0.2573, "step": 1705 }, { "epoch": 2.76, "learning_rate": 3.3962827263796024e-05, "loss": 0.2869, "step": 1706 }, { "epoch": 2.77, "learning_rate": 3.395530777809794e-05, "loss": 0.2928, "step": 1707 }, { "epoch": 2.77, "learning_rate": 3.394778444598621e-05, "loss": 0.305, "step": 1708 }, { "epoch": 2.77, "learning_rate": 3.394025726953447e-05, "loss": 0.3444, "step": 1709 }, { "epoch": 2.77, "learning_rate": 3.393272625081737e-05, "loss": 0.2856, "step": 1710 }, { "epoch": 2.77, "learning_rate": 3.392519139191066e-05, "loss": 0.2257, "step": 1711 }, { "epoch": 2.77, "learning_rate": 3.39176526948911e-05, "loss": 0.2085, "step": 1712 }, { "epoch": 2.78, "learning_rate": 3.3910110161836554e-05, "loss": 0.2911, "step": 1713 }, { "epoch": 2.78, "learning_rate": 3.3902563794825904e-05, "loss": 0.3102, "step": 1714 }, { "epoch": 2.78, "learning_rate": 3.3895013595939126e-05, "loss": 0.2483, "step": 1715 }, { "epoch": 2.78, "learning_rate": 3.388745956725722e-05, "loss": 0.1927, "step": 1716 }, { "epoch": 2.78, "learning_rate": 3.387990171086226e-05, "loss": 0.2557, "step": 1717 }, { "epoch": 2.78, "learning_rate": 3.3872340028837366e-05, "loss": 0.2549, "step": 1718 }, { "epoch": 2.79, "learning_rate": 3.386477452326673e-05, "loss": 0.2503, "step": 1719 }, { "epoch": 2.79, "learning_rate": 3.385720519623557e-05, "loss": 0.3299, "step": 1720 }, { "epoch": 2.79, "learning_rate": 3.3849632049830185e-05, "loss": 0.2104, "step": 1721 }, { "epoch": 2.79, "learning_rate": 3.38420550861379e-05, "loss": 0.2443, "step": 1722 }, { "epoch": 2.79, "learning_rate": 3.383447430724712e-05, "loss": 0.2125, "step": 1723 }, { "epoch": 2.79, "learning_rate": 3.3826889715247275e-05, "loss": 0.3031, "step": 1724 }, { "epoch": 2.8, "learning_rate": 3.3819301312228866e-05, "loss": 0.2028, "step": 1725 }, { "epoch": 2.8, "learning_rate": 3.3811709100283434e-05, "loss": 0.2811, "step": 1726 }, { "epoch": 2.8, "learning_rate": 3.380411308150357e-05, "loss": 0.2146, "step": 1727 }, { "epoch": 2.8, "learning_rate": 3.379651325798292e-05, "loss": 0.2387, "step": 1728 }, { "epoch": 2.8, "learning_rate": 3.3788909631816176e-05, "loss": 0.2366, "step": 1729 }, { "epoch": 2.8, "learning_rate": 3.378130220509908e-05, "loss": 0.3087, "step": 1730 }, { "epoch": 2.81, "learning_rate": 3.3773690979928416e-05, "loss": 0.2596, "step": 1731 }, { "epoch": 2.81, "learning_rate": 3.376607595840201e-05, "loss": 0.2204, "step": 1732 }, { "epoch": 2.81, "learning_rate": 3.3758457142618754e-05, "loss": 0.2831, "step": 1733 }, { "epoch": 2.81, "learning_rate": 3.375083453467857e-05, "loss": 0.2143, "step": 1734 }, { "epoch": 2.81, "learning_rate": 3.3743208136682435e-05, "loss": 0.3557, "step": 1735 }, { "epoch": 2.81, "learning_rate": 3.373557795073236e-05, "loss": 0.2714, "step": 1736 }, { "epoch": 2.82, "learning_rate": 3.37279439789314e-05, "loss": 0.2894, "step": 1737 }, { "epoch": 2.82, "learning_rate": 3.372030622338367e-05, "loss": 0.302, "step": 1738 }, { "epoch": 2.82, "learning_rate": 3.37126646861943e-05, "loss": 0.2498, "step": 1739 }, { "epoch": 2.82, "learning_rate": 3.37050193694695e-05, "loss": 0.2164, "step": 1740 }, { "epoch": 2.82, "learning_rate": 3.3697370275316484e-05, "loss": 0.365, "step": 1741 }, { "epoch": 2.82, "learning_rate": 3.368971740584353e-05, "loss": 0.2366, "step": 1742 }, { "epoch": 2.82, "learning_rate": 3.368206076315995e-05, "loss": 0.3419, "step": 1743 }, { "epoch": 2.83, "learning_rate": 3.367440034937609e-05, "loss": 0.3246, "step": 1744 }, { "epoch": 2.83, "learning_rate": 3.366673616660336e-05, "loss": 0.2191, "step": 1745 }, { "epoch": 2.83, "learning_rate": 3.3659068216954164e-05, "loss": 0.2874, "step": 1746 }, { "epoch": 2.83, "learning_rate": 3.3651396502541995e-05, "loss": 0.3182, "step": 1747 }, { "epoch": 2.83, "learning_rate": 3.364372102548135e-05, "loss": 0.2349, "step": 1748 }, { "epoch": 2.83, "learning_rate": 3.363604178788777e-05, "loss": 0.2483, "step": 1749 }, { "epoch": 2.84, "learning_rate": 3.362835879187783e-05, "loss": 0.2493, "step": 1750 }, { "epoch": 2.84, "learning_rate": 3.3620672039569156e-05, "loss": 0.3582, "step": 1751 }, { "epoch": 2.84, "learning_rate": 3.361298153308039e-05, "loss": 0.2837, "step": 1752 }, { "epoch": 2.84, "learning_rate": 3.3605287274531224e-05, "loss": 0.2724, "step": 1753 }, { "epoch": 2.84, "learning_rate": 3.3597589266042384e-05, "loss": 0.2621, "step": 1754 }, { "epoch": 2.84, "learning_rate": 3.358988750973561e-05, "loss": 0.3038, "step": 1755 }, { "epoch": 2.85, "learning_rate": 3.35821820077337e-05, "loss": 0.2577, "step": 1756 }, { "epoch": 2.85, "learning_rate": 3.357447276216046e-05, "loss": 0.2647, "step": 1757 }, { "epoch": 2.85, "learning_rate": 3.356675977514076e-05, "loss": 0.2712, "step": 1758 }, { "epoch": 2.85, "learning_rate": 3.355904304880047e-05, "loss": 0.3115, "step": 1759 }, { "epoch": 2.85, "learning_rate": 3.3551322585266494e-05, "loss": 0.2387, "step": 1760 }, { "epoch": 2.85, "learning_rate": 3.3543598386666796e-05, "loss": 0.2995, "step": 1761 }, { "epoch": 2.86, "learning_rate": 3.353587045513033e-05, "loss": 0.3901, "step": 1762 }, { "epoch": 2.86, "learning_rate": 3.3528138792787106e-05, "loss": 0.2654, "step": 1763 }, { "epoch": 2.86, "learning_rate": 3.3520403401768144e-05, "loss": 0.2749, "step": 1764 }, { "epoch": 2.86, "learning_rate": 3.3512664284205524e-05, "loss": 0.2121, "step": 1765 }, { "epoch": 2.86, "learning_rate": 3.3504921442232306e-05, "loss": 0.2341, "step": 1766 }, { "epoch": 2.86, "learning_rate": 3.349717487798261e-05, "loss": 0.2522, "step": 1767 }, { "epoch": 2.87, "learning_rate": 3.348942459359157e-05, "loss": 0.3472, "step": 1768 }, { "epoch": 2.87, "learning_rate": 3.348167059119535e-05, "loss": 0.3083, "step": 1769 }, { "epoch": 2.87, "learning_rate": 3.347391287293115e-05, "loss": 0.2376, "step": 1770 }, { "epoch": 2.87, "learning_rate": 3.346615144093716e-05, "loss": 0.2499, "step": 1771 }, { "epoch": 2.87, "learning_rate": 3.3458386297352623e-05, "loss": 0.2876, "step": 1772 }, { "epoch": 2.87, "learning_rate": 3.345061744431779e-05, "loss": 0.2755, "step": 1773 }, { "epoch": 2.88, "learning_rate": 3.344284488397395e-05, "loss": 0.2833, "step": 1774 }, { "epoch": 2.88, "learning_rate": 3.343506861846341e-05, "loss": 0.2713, "step": 1775 }, { "epoch": 2.88, "learning_rate": 3.342728864992948e-05, "loss": 0.2745, "step": 1776 }, { "epoch": 2.88, "learning_rate": 3.3419504980516515e-05, "loss": 0.3122, "step": 1777 }, { "epoch": 2.88, "learning_rate": 3.3411717612369866e-05, "loss": 0.2732, "step": 1778 }, { "epoch": 2.88, "learning_rate": 3.340392654763592e-05, "loss": 0.223, "step": 1779 }, { "epoch": 2.88, "learning_rate": 3.33961317884621e-05, "loss": 0.2976, "step": 1780 }, { "epoch": 2.89, "learning_rate": 3.338833333699679e-05, "loss": 0.2384, "step": 1781 }, { "epoch": 2.89, "learning_rate": 3.338053119538946e-05, "loss": 0.2405, "step": 1782 }, { "epoch": 2.89, "learning_rate": 3.337272536579055e-05, "loss": 0.3509, "step": 1783 }, { "epoch": 2.89, "learning_rate": 3.3364915850351525e-05, "loss": 0.2456, "step": 1784 }, { "epoch": 2.89, "learning_rate": 3.3357102651224895e-05, "loss": 0.3014, "step": 1785 }, { "epoch": 2.89, "learning_rate": 3.334928577056414e-05, "loss": 0.2402, "step": 1786 }, { "epoch": 2.9, "learning_rate": 3.334146521052379e-05, "loss": 0.2604, "step": 1787 }, { "epoch": 2.9, "learning_rate": 3.3333640973259374e-05, "loss": 0.267, "step": 1788 }, { "epoch": 2.9, "learning_rate": 3.332581306092744e-05, "loss": 0.2492, "step": 1789 }, { "epoch": 2.9, "learning_rate": 3.3317981475685534e-05, "loss": 0.3731, "step": 1790 }, { "epoch": 2.9, "learning_rate": 3.331014621969224e-05, "loss": 0.2451, "step": 1791 }, { "epoch": 2.9, "learning_rate": 3.330230729510714e-05, "loss": 0.2445, "step": 1792 }, { "epoch": 2.91, "learning_rate": 3.329446470409082e-05, "loss": 0.1904, "step": 1793 }, { "epoch": 2.91, "learning_rate": 3.328661844880489e-05, "loss": 0.3119, "step": 1794 }, { "epoch": 2.91, "learning_rate": 3.3278768531411954e-05, "loss": 0.2581, "step": 1795 }, { "epoch": 2.91, "learning_rate": 3.327091495407565e-05, "loss": 0.2382, "step": 1796 }, { "epoch": 2.91, "learning_rate": 3.3263057718960596e-05, "loss": 0.2105, "step": 1797 }, { "epoch": 2.91, "learning_rate": 3.325519682823244e-05, "loss": 0.2742, "step": 1798 }, { "epoch": 2.92, "learning_rate": 3.324733228405784e-05, "loss": 0.2878, "step": 1799 }, { "epoch": 2.92, "learning_rate": 3.323946408860443e-05, "loss": 0.2671, "step": 1800 }, { "epoch": 2.92, "learning_rate": 3.3231592244040885e-05, "loss": 0.3021, "step": 1801 }, { "epoch": 2.92, "learning_rate": 3.322371675253686e-05, "loss": 0.2234, "step": 1802 }, { "epoch": 2.92, "learning_rate": 3.321583761626305e-05, "loss": 0.3171, "step": 1803 }, { "epoch": 2.92, "learning_rate": 3.320795483739111e-05, "loss": 0.3343, "step": 1804 }, { "epoch": 2.93, "learning_rate": 3.320006841809372e-05, "loss": 0.2441, "step": 1805 }, { "epoch": 2.93, "learning_rate": 3.319217836054457e-05, "loss": 0.2706, "step": 1806 }, { "epoch": 2.93, "learning_rate": 3.318428466691836e-05, "loss": 0.2346, "step": 1807 }, { "epoch": 2.93, "learning_rate": 3.317638733939076e-05, "loss": 0.3072, "step": 1808 }, { "epoch": 2.93, "learning_rate": 3.3168486380138474e-05, "loss": 0.2937, "step": 1809 }, { "epoch": 2.93, "learning_rate": 3.3160581791339186e-05, "loss": 0.2606, "step": 1810 }, { "epoch": 2.94, "learning_rate": 3.315267357517159e-05, "loss": 0.2858, "step": 1811 }, { "epoch": 2.94, "learning_rate": 3.314476173381537e-05, "loss": 0.2265, "step": 1812 }, { "epoch": 2.94, "learning_rate": 3.313684626945123e-05, "loss": 0.2567, "step": 1813 }, { "epoch": 2.94, "learning_rate": 3.312892718426086e-05, "loss": 0.2824, "step": 1814 }, { "epoch": 2.94, "learning_rate": 3.312100448042693e-05, "loss": 0.3391, "step": 1815 }, { "epoch": 2.94, "learning_rate": 3.3113078160133144e-05, "loss": 0.2369, "step": 1816 }, { "epoch": 2.94, "learning_rate": 3.3105148225564176e-05, "loss": 0.2419, "step": 1817 }, { "epoch": 2.95, "learning_rate": 3.309721467890571e-05, "loss": 0.1779, "step": 1818 }, { "epoch": 2.95, "learning_rate": 3.30892775223444e-05, "loss": 0.2266, "step": 1819 }, { "epoch": 2.95, "learning_rate": 3.3081336758067935e-05, "loss": 0.3061, "step": 1820 }, { "epoch": 2.95, "learning_rate": 3.307339238826498e-05, "loss": 0.3045, "step": 1821 }, { "epoch": 2.95, "learning_rate": 3.306544441512518e-05, "loss": 0.2549, "step": 1822 }, { "epoch": 2.95, "learning_rate": 3.305749284083918e-05, "loss": 0.2613, "step": 1823 }, { "epoch": 2.96, "learning_rate": 3.304953766759863e-05, "loss": 0.2571, "step": 1824 }, { "epoch": 2.96, "learning_rate": 3.304157889759617e-05, "loss": 0.2894, "step": 1825 }, { "epoch": 2.96, "learning_rate": 3.3033616533025425e-05, "loss": 0.2813, "step": 1826 }, { "epoch": 2.96, "learning_rate": 3.3025650576081e-05, "loss": 0.3793, "step": 1827 }, { "epoch": 2.96, "learning_rate": 3.3017681028958514e-05, "loss": 0.1883, "step": 1828 }, { "epoch": 2.96, "learning_rate": 3.300970789385455e-05, "loss": 0.2337, "step": 1829 }, { "epoch": 2.97, "learning_rate": 3.300173117296671e-05, "loss": 0.2774, "step": 1830 }, { "epoch": 2.97, "learning_rate": 3.299375086849355e-05, "loss": 0.256, "step": 1831 }, { "epoch": 2.97, "learning_rate": 3.2985766982634634e-05, "loss": 0.2751, "step": 1832 }, { "epoch": 2.97, "learning_rate": 3.2977779517590525e-05, "loss": 0.2745, "step": 1833 }, { "epoch": 2.97, "learning_rate": 3.296978847556274e-05, "loss": 0.2465, "step": 1834 }, { "epoch": 2.97, "learning_rate": 3.296179385875381e-05, "loss": 0.2749, "step": 1835 }, { "epoch": 2.98, "learning_rate": 3.295379566936724e-05, "loss": 0.2359, "step": 1836 }, { "epoch": 2.98, "learning_rate": 3.294579390960752e-05, "loss": 0.2771, "step": 1837 }, { "epoch": 2.98, "learning_rate": 3.293778858168012e-05, "loss": 0.2957, "step": 1838 }, { "epoch": 2.98, "learning_rate": 3.29297796877915e-05, "loss": 0.2531, "step": 1839 }, { "epoch": 2.98, "learning_rate": 3.292176723014911e-05, "loss": 0.2309, "step": 1840 }, { "epoch": 2.98, "learning_rate": 3.2913751210961364e-05, "loss": 0.2908, "step": 1841 }, { "epoch": 2.99, "learning_rate": 3.290573163243766e-05, "loss": 0.2491, "step": 1842 }, { "epoch": 2.99, "learning_rate": 3.2897708496788405e-05, "loss": 0.2031, "step": 1843 }, { "epoch": 2.99, "learning_rate": 3.2889681806224946e-05, "loss": 0.3984, "step": 1844 }, { "epoch": 2.99, "learning_rate": 3.2881651562959645e-05, "loss": 0.2874, "step": 1845 }, { "epoch": 2.99, "learning_rate": 3.28736177692058e-05, "loss": 0.3023, "step": 1846 }, { "epoch": 2.99, "learning_rate": 3.286558042717775e-05, "loss": 0.279, "step": 1847 }, { "epoch": 3.0, "learning_rate": 3.285753953909075e-05, "loss": 0.2043, "step": 1848 }, { "epoch": 3.0, "learning_rate": 3.284949510716108e-05, "loss": 0.3252, "step": 1849 }, { "epoch": 3.0, "learning_rate": 3.2841447133605965e-05, "loss": 0.2402, "step": 1850 }, { "epoch": 3.0, "learning_rate": 3.2833395620643615e-05, "loss": 0.2871, "step": 1851 }, { "epoch": 3.0, "learning_rate": 3.282534057049322e-05, "loss": 0.2188, "step": 1852 }, { "epoch": 3.0, "learning_rate": 3.281728198537495e-05, "loss": 0.2356, "step": 1853 }, { "epoch": 3.0, "learning_rate": 3.280921986750993e-05, "loss": 0.2122, "step": 1854 }, { "epoch": 3.01, "learning_rate": 3.2801154219120276e-05, "loss": 0.2088, "step": 1855 }, { "epoch": 3.01, "learning_rate": 3.279308504242908e-05, "loss": 0.238, "step": 1856 }, { "epoch": 3.01, "learning_rate": 3.2785012339660386e-05, "loss": 0.3088, "step": 1857 }, { "epoch": 3.01, "learning_rate": 3.277693611303922e-05, "loss": 0.2762, "step": 1858 }, { "epoch": 3.01, "learning_rate": 3.27688563647916e-05, "loss": 0.2723, "step": 1859 }, { "epoch": 3.01, "learning_rate": 3.276077309714449e-05, "loss": 0.2262, "step": 1860 }, { "epoch": 3.02, "learning_rate": 3.275268631232582e-05, "loss": 0.2867, "step": 1861 }, { "epoch": 3.02, "learning_rate": 3.27445960125645e-05, "loss": 0.1914, "step": 1862 }, { "epoch": 3.02, "learning_rate": 3.273650220009041e-05, "loss": 0.21, "step": 1863 }, { "epoch": 3.02, "learning_rate": 3.272840487713441e-05, "loss": 0.2317, "step": 1864 }, { "epoch": 3.02, "learning_rate": 3.2720304045928305e-05, "loss": 0.2242, "step": 1865 }, { "epoch": 3.02, "learning_rate": 3.271219970870487e-05, "loss": 0.2383, "step": 1866 }, { "epoch": 3.03, "learning_rate": 3.2704091867697854e-05, "loss": 0.2807, "step": 1867 }, { "epoch": 3.03, "learning_rate": 3.269598052514198e-05, "loss": 0.2595, "step": 1868 }, { "epoch": 3.03, "learning_rate": 3.268786568327291e-05, "loss": 0.2416, "step": 1869 }, { "epoch": 3.03, "learning_rate": 3.267974734432731e-05, "loss": 0.211, "step": 1870 }, { "epoch": 3.03, "learning_rate": 3.267162551054276e-05, "loss": 0.2608, "step": 1871 }, { "epoch": 3.03, "learning_rate": 3.2663500184157854e-05, "loss": 0.2699, "step": 1872 }, { "epoch": 3.04, "learning_rate": 3.265537136741211e-05, "loss": 0.2641, "step": 1873 }, { "epoch": 3.04, "learning_rate": 3.2647239062546026e-05, "loss": 0.2986, "step": 1874 }, { "epoch": 3.04, "learning_rate": 3.263910327180107e-05, "loss": 0.2669, "step": 1875 }, { "epoch": 3.04, "learning_rate": 3.263096399741963e-05, "loss": 0.2543, "step": 1876 }, { "epoch": 3.04, "learning_rate": 3.26228212416451e-05, "loss": 0.2183, "step": 1877 }, { "epoch": 3.04, "learning_rate": 3.2614675006721826e-05, "loss": 0.1888, "step": 1878 }, { "epoch": 3.05, "learning_rate": 3.26065252948951e-05, "loss": 0.2047, "step": 1879 }, { "epoch": 3.05, "learning_rate": 3.259837210841116e-05, "loss": 0.2285, "step": 1880 }, { "epoch": 3.05, "learning_rate": 3.259021544951723e-05, "loss": 0.1938, "step": 1881 }, { "epoch": 3.05, "learning_rate": 3.258205532046147e-05, "loss": 0.184, "step": 1882 }, { "epoch": 3.05, "learning_rate": 3.2573891723493014e-05, "loss": 0.2629, "step": 1883 }, { "epoch": 3.05, "learning_rate": 3.256572466086194e-05, "loss": 0.2477, "step": 1884 }, { "epoch": 3.06, "learning_rate": 3.255755413481929e-05, "loss": 0.2182, "step": 1885 }, { "epoch": 3.06, "learning_rate": 3.254938014761704e-05, "loss": 0.183, "step": 1886 }, { "epoch": 3.06, "learning_rate": 3.254120270150815e-05, "loss": 0.2813, "step": 1887 }, { "epoch": 3.06, "learning_rate": 3.2533021798746505e-05, "loss": 0.1939, "step": 1888 }, { "epoch": 3.06, "learning_rate": 3.2524837441586965e-05, "loss": 0.1728, "step": 1889 }, { "epoch": 3.06, "learning_rate": 3.2516649632285335e-05, "loss": 0.2412, "step": 1890 }, { "epoch": 3.06, "learning_rate": 3.250845837309836e-05, "loss": 0.2042, "step": 1891 }, { "epoch": 3.07, "learning_rate": 3.250026366628375e-05, "loss": 0.2548, "step": 1892 }, { "epoch": 3.07, "learning_rate": 3.249206551410015e-05, "loss": 0.2267, "step": 1893 }, { "epoch": 3.07, "learning_rate": 3.2483863918807187e-05, "loss": 0.2791, "step": 1894 }, { "epoch": 3.07, "learning_rate": 3.24756588826654e-05, "loss": 0.2599, "step": 1895 }, { "epoch": 3.07, "learning_rate": 3.246745040793629e-05, "loss": 0.3153, "step": 1896 }, { "epoch": 3.07, "learning_rate": 3.2459238496882313e-05, "loss": 0.2192, "step": 1897 }, { "epoch": 3.08, "learning_rate": 3.245102315176687e-05, "loss": 0.2777, "step": 1898 }, { "epoch": 3.08, "learning_rate": 3.244280437485429e-05, "loss": 0.224, "step": 1899 }, { "epoch": 3.08, "learning_rate": 3.243458216840988e-05, "loss": 0.2433, "step": 1900 }, { "epoch": 3.08, "learning_rate": 3.2426356534699866e-05, "loss": 0.2532, "step": 1901 }, { "epoch": 3.08, "learning_rate": 3.241812747599143e-05, "loss": 0.1993, "step": 1902 }, { "epoch": 3.08, "learning_rate": 3.240989499455269e-05, "loss": 0.2198, "step": 1903 }, { "epoch": 3.09, "learning_rate": 3.2401659092652726e-05, "loss": 0.1993, "step": 1904 }, { "epoch": 3.09, "learning_rate": 3.239341977256153e-05, "loss": 0.2059, "step": 1905 }, { "epoch": 3.09, "learning_rate": 3.2385177036550075e-05, "loss": 0.2731, "step": 1906 }, { "epoch": 3.09, "learning_rate": 3.237693088689023e-05, "loss": 0.2703, "step": 1907 }, { "epoch": 3.09, "learning_rate": 3.236868132585485e-05, "loss": 0.2023, "step": 1908 }, { "epoch": 3.09, "learning_rate": 3.23604283557177e-05, "loss": 0.203, "step": 1909 }, { "epoch": 3.1, "learning_rate": 3.2352171978753495e-05, "loss": 0.1701, "step": 1910 }, { "epoch": 3.1, "learning_rate": 3.234391219723789e-05, "loss": 0.2028, "step": 1911 }, { "epoch": 3.1, "learning_rate": 3.233564901344748e-05, "loss": 0.2507, "step": 1912 }, { "epoch": 3.1, "learning_rate": 3.232738242965979e-05, "loss": 0.2147, "step": 1913 }, { "epoch": 3.1, "learning_rate": 3.2319112448153274e-05, "loss": 0.2188, "step": 1914 }, { "epoch": 3.1, "learning_rate": 3.231083907120736e-05, "loss": 0.2862, "step": 1915 }, { "epoch": 3.11, "learning_rate": 3.2302562301102365e-05, "loss": 0.2321, "step": 1916 }, { "epoch": 3.11, "learning_rate": 3.229428214011958e-05, "loss": 0.2389, "step": 1917 }, { "epoch": 3.11, "learning_rate": 3.228599859054121e-05, "loss": 0.254, "step": 1918 }, { "epoch": 3.11, "learning_rate": 3.227771165465039e-05, "loss": 0.3269, "step": 1919 }, { "epoch": 3.11, "learning_rate": 3.2269421334731196e-05, "loss": 0.2706, "step": 1920 }, { "epoch": 3.11, "learning_rate": 3.226112763306864e-05, "loss": 0.2173, "step": 1921 }, { "epoch": 3.12, "learning_rate": 3.2252830551948663e-05, "loss": 0.2095, "step": 1922 }, { "epoch": 3.12, "learning_rate": 3.2244530093658135e-05, "loss": 0.2373, "step": 1923 }, { "epoch": 3.12, "learning_rate": 3.223622626048487e-05, "loss": 0.2309, "step": 1924 }, { "epoch": 3.12, "learning_rate": 3.222791905471759e-05, "loss": 0.2247, "step": 1925 }, { "epoch": 3.12, "learning_rate": 3.221960847864596e-05, "loss": 0.2295, "step": 1926 }, { "epoch": 3.12, "learning_rate": 3.2211294534560567e-05, "loss": 0.2046, "step": 1927 }, { "epoch": 3.12, "learning_rate": 3.2202977224752935e-05, "loss": 0.306, "step": 1928 }, { "epoch": 3.13, "learning_rate": 3.2194656551515524e-05, "loss": 0.2449, "step": 1929 }, { "epoch": 3.13, "learning_rate": 3.218633251714169e-05, "loss": 0.2387, "step": 1930 }, { "epoch": 3.13, "learning_rate": 3.217800512392574e-05, "loss": 0.1562, "step": 1931 }, { "epoch": 3.13, "learning_rate": 3.216967437416291e-05, "loss": 0.23, "step": 1932 }, { "epoch": 3.13, "learning_rate": 3.2161340270149343e-05, "loss": 0.2914, "step": 1933 }, { "epoch": 3.13, "learning_rate": 3.215300281418212e-05, "loss": 0.2644, "step": 1934 }, { "epoch": 3.14, "learning_rate": 3.2144662008559234e-05, "loss": 0.2454, "step": 1935 }, { "epoch": 3.14, "learning_rate": 3.213631785557962e-05, "loss": 0.196, "step": 1936 }, { "epoch": 3.14, "learning_rate": 3.212797035754311e-05, "loss": 0.2487, "step": 1937 }, { "epoch": 3.14, "learning_rate": 3.211961951675048e-05, "loss": 0.2232, "step": 1938 }, { "epoch": 3.14, "learning_rate": 3.2111265335503424e-05, "loss": 0.2194, "step": 1939 }, { "epoch": 3.14, "learning_rate": 3.2102907816104555e-05, "loss": 0.2206, "step": 1940 }, { "epoch": 3.15, "learning_rate": 3.2094546960857385e-05, "loss": 0.2406, "step": 1941 }, { "epoch": 3.15, "learning_rate": 3.2086182772066386e-05, "loss": 0.2432, "step": 1942 }, { "epoch": 3.15, "learning_rate": 3.207781525203691e-05, "loss": 0.2671, "step": 1943 }, { "epoch": 3.15, "learning_rate": 3.206944440307526e-05, "loss": 0.1888, "step": 1944 }, { "epoch": 3.15, "learning_rate": 3.206107022748862e-05, "loss": 0.2643, "step": 1945 }, { "epoch": 3.15, "learning_rate": 3.205269272758513e-05, "loss": 0.2299, "step": 1946 }, { "epoch": 3.16, "learning_rate": 3.2044311905673815e-05, "loss": 0.2077, "step": 1947 }, { "epoch": 3.16, "learning_rate": 3.2035927764064644e-05, "loss": 0.2243, "step": 1948 }, { "epoch": 3.16, "learning_rate": 3.202754030506846e-05, "loss": 0.2058, "step": 1949 }, { "epoch": 3.16, "learning_rate": 3.201914953099707e-05, "loss": 0.256, "step": 1950 }, { "epoch": 3.16, "learning_rate": 3.201075544416315e-05, "loss": 0.2043, "step": 1951 }, { "epoch": 3.16, "learning_rate": 3.200235804688033e-05, "loss": 0.2542, "step": 1952 }, { "epoch": 3.17, "learning_rate": 3.199395734146311e-05, "loss": 0.3112, "step": 1953 }, { "epoch": 3.17, "learning_rate": 3.198555333022694e-05, "loss": 0.2111, "step": 1954 }, { "epoch": 3.17, "learning_rate": 3.197714601548816e-05, "loss": 0.2465, "step": 1955 }, { "epoch": 3.17, "learning_rate": 3.196873539956403e-05, "loss": 0.19, "step": 1956 }, { "epoch": 3.17, "learning_rate": 3.19603214847727e-05, "loss": 0.239, "step": 1957 }, { "epoch": 3.17, "learning_rate": 3.195190427343326e-05, "loss": 0.2657, "step": 1958 }, { "epoch": 3.18, "learning_rate": 3.194348376786568e-05, "loss": 0.2448, "step": 1959 }, { "epoch": 3.18, "learning_rate": 3.193505997039087e-05, "loss": 0.2815, "step": 1960 }, { "epoch": 3.18, "learning_rate": 3.19266328833306e-05, "loss": 0.3236, "step": 1961 }, { "epoch": 3.18, "learning_rate": 3.1918202509007605e-05, "loss": 0.2358, "step": 1962 }, { "epoch": 3.18, "learning_rate": 3.1909768849745475e-05, "loss": 0.3239, "step": 1963 }, { "epoch": 3.18, "learning_rate": 3.190133190786874e-05, "loss": 0.3131, "step": 1964 }, { "epoch": 3.18, "learning_rate": 3.1892891685702806e-05, "loss": 0.2413, "step": 1965 }, { "epoch": 3.19, "learning_rate": 3.1884448185574016e-05, "loss": 0.1742, "step": 1966 }, { "epoch": 3.19, "learning_rate": 3.1876001409809584e-05, "loss": 0.29, "step": 1967 }, { "epoch": 3.19, "learning_rate": 3.186755136073765e-05, "loss": 0.2679, "step": 1968 }, { "epoch": 3.19, "learning_rate": 3.1859098040687244e-05, "loss": 0.2237, "step": 1969 }, { "epoch": 3.19, "learning_rate": 3.1850641451988295e-05, "loss": 0.1865, "step": 1970 }, { "epoch": 3.19, "learning_rate": 3.184218159697166e-05, "loss": 0.2124, "step": 1971 }, { "epoch": 3.2, "learning_rate": 3.183371847796906e-05, "loss": 0.2257, "step": 1972 }, { "epoch": 3.2, "learning_rate": 3.1825252097313125e-05, "loss": 0.2363, "step": 1973 }, { "epoch": 3.2, "learning_rate": 3.181678245733741e-05, "loss": 0.3089, "step": 1974 }, { "epoch": 3.2, "learning_rate": 3.180830956037633e-05, "loss": 0.2693, "step": 1975 }, { "epoch": 3.2, "learning_rate": 3.179983340876523e-05, "loss": 0.2518, "step": 1976 }, { "epoch": 3.2, "learning_rate": 3.179135400484032e-05, "loss": 0.199, "step": 1977 }, { "epoch": 3.21, "learning_rate": 3.178287135093875e-05, "loss": 0.1997, "step": 1978 }, { "epoch": 3.21, "learning_rate": 3.1774385449398525e-05, "loss": 0.234, "step": 1979 }, { "epoch": 3.21, "learning_rate": 3.176589630255856e-05, "loss": 0.3123, "step": 1980 }, { "epoch": 3.21, "learning_rate": 3.175740391275867e-05, "loss": 0.263, "step": 1981 }, { "epoch": 3.21, "learning_rate": 3.174890828233956e-05, "loss": 0.2145, "step": 1982 }, { "epoch": 3.21, "learning_rate": 3.174040941364282e-05, "loss": 0.2089, "step": 1983 }, { "epoch": 3.22, "learning_rate": 3.1731907309010934e-05, "loss": 0.1728, "step": 1984 }, { "epoch": 3.22, "learning_rate": 3.1723401970787305e-05, "loss": 0.2719, "step": 1985 }, { "epoch": 3.22, "learning_rate": 3.171489340131619e-05, "loss": 0.3658, "step": 1986 }, { "epoch": 3.22, "learning_rate": 3.1706381602942765e-05, "loss": 0.2393, "step": 1987 }, { "epoch": 3.22, "learning_rate": 3.169786657801306e-05, "loss": 0.1806, "step": 1988 }, { "epoch": 3.22, "learning_rate": 3.1689348328874046e-05, "loss": 0.2691, "step": 1989 }, { "epoch": 3.23, "learning_rate": 3.1680826857873534e-05, "loss": 0.2264, "step": 1990 }, { "epoch": 3.23, "learning_rate": 3.1672302167360257e-05, "loss": 0.223, "step": 1991 }, { "epoch": 3.23, "learning_rate": 3.1663774259683804e-05, "loss": 0.2828, "step": 1992 }, { "epoch": 3.23, "learning_rate": 3.165524313719469e-05, "loss": 0.1973, "step": 1993 }, { "epoch": 3.23, "learning_rate": 3.164670880224428e-05, "loss": 0.2878, "step": 1994 }, { "epoch": 3.23, "learning_rate": 3.163817125718485e-05, "loss": 0.2751, "step": 1995 }, { "epoch": 3.24, "learning_rate": 3.162963050436954e-05, "loss": 0.1935, "step": 1996 }, { "epoch": 3.24, "learning_rate": 3.162108654615238e-05, "loss": 0.233, "step": 1997 }, { "epoch": 3.24, "learning_rate": 3.1612539384888304e-05, "loss": 0.2561, "step": 1998 }, { "epoch": 3.24, "learning_rate": 3.160398902293309e-05, "loss": 0.2337, "step": 1999 }, { "epoch": 3.24, "learning_rate": 3.159543546264345e-05, "loss": 0.2911, "step": 2000 }, { "epoch": 3.24, "learning_rate": 3.158687870637692e-05, "loss": 0.2818, "step": 2001 }, { "epoch": 3.24, "learning_rate": 3.157831875649196e-05, "loss": 0.2262, "step": 2002 }, { "epoch": 3.25, "learning_rate": 3.156975561534789e-05, "loss": 0.2614, "step": 2003 }, { "epoch": 3.25, "learning_rate": 3.156118928530491e-05, "loss": 0.2093, "step": 2004 }, { "epoch": 3.25, "learning_rate": 3.155261976872412e-05, "loss": 0.1647, "step": 2005 }, { "epoch": 3.25, "learning_rate": 3.1544047067967465e-05, "loss": 0.2686, "step": 2006 }, { "epoch": 3.25, "learning_rate": 3.153547118539779e-05, "loss": 0.2007, "step": 2007 }, { "epoch": 3.25, "learning_rate": 3.1526892123378815e-05, "loss": 0.2358, "step": 2008 }, { "epoch": 3.26, "learning_rate": 3.151830988427513e-05, "loss": 0.2625, "step": 2009 }, { "epoch": 3.26, "learning_rate": 3.15097244704522e-05, "loss": 0.3132, "step": 2010 }, { "epoch": 3.26, "learning_rate": 3.150113588427638e-05, "loss": 0.2124, "step": 2011 }, { "epoch": 3.26, "learning_rate": 3.1492544128114876e-05, "loss": 0.1875, "step": 2012 }, { "epoch": 3.26, "learning_rate": 3.148394920433579e-05, "loss": 0.2944, "step": 2013 }, { "epoch": 3.26, "learning_rate": 3.147535111530807e-05, "loss": 0.2777, "step": 2014 }, { "epoch": 3.27, "learning_rate": 3.1466749863401577e-05, "loss": 0.1332, "step": 2015 }, { "epoch": 3.27, "learning_rate": 3.145814545098699e-05, "loss": 0.2423, "step": 2016 }, { "epoch": 3.27, "learning_rate": 3.144953788043592e-05, "loss": 0.2043, "step": 2017 }, { "epoch": 3.27, "learning_rate": 3.1440927154120795e-05, "loss": 0.3006, "step": 2018 }, { "epoch": 3.27, "learning_rate": 3.143231327441495e-05, "loss": 0.232, "step": 2019 }, { "epoch": 3.27, "learning_rate": 3.142369624369256e-05, "loss": 0.2177, "step": 2020 }, { "epoch": 3.28, "learning_rate": 3.14150760643287e-05, "loss": 0.1947, "step": 2021 }, { "epoch": 3.28, "learning_rate": 3.1406452738699284e-05, "loss": 0.2972, "step": 2022 }, { "epoch": 3.28, "learning_rate": 3.1397826269181105e-05, "loss": 0.2497, "step": 2023 }, { "epoch": 3.28, "learning_rate": 3.138919665815183e-05, "loss": 0.2269, "step": 2024 }, { "epoch": 3.28, "learning_rate": 3.138056390798997e-05, "loss": 0.2305, "step": 2025 }, { "epoch": 3.28, "learning_rate": 3.137192802107493e-05, "loss": 0.2679, "step": 2026 }, { "epoch": 3.29, "learning_rate": 3.136328899978697e-05, "loss": 0.2153, "step": 2027 }, { "epoch": 3.29, "learning_rate": 3.135464684650719e-05, "loss": 0.2323, "step": 2028 }, { "epoch": 3.29, "learning_rate": 3.1346001563617584e-05, "loss": 0.2209, "step": 2029 }, { "epoch": 3.29, "learning_rate": 3.133735315350099e-05, "loss": 0.2136, "step": 2030 }, { "epoch": 3.29, "learning_rate": 3.132870161854112e-05, "loss": 0.2164, "step": 2031 }, { "epoch": 3.29, "learning_rate": 3.132004696112254e-05, "loss": 0.2704, "step": 2032 }, { "epoch": 3.29, "learning_rate": 3.131138918363069e-05, "loss": 0.3015, "step": 2033 }, { "epoch": 3.3, "learning_rate": 3.130272828845184e-05, "loss": 0.2119, "step": 2034 }, { "epoch": 3.3, "learning_rate": 3.1294064277973144e-05, "loss": 0.2769, "step": 2035 }, { "epoch": 3.3, "learning_rate": 3.128539715458263e-05, "loss": 0.2595, "step": 2036 }, { "epoch": 3.3, "learning_rate": 3.127672692066912e-05, "loss": 0.2257, "step": 2037 }, { "epoch": 3.3, "learning_rate": 3.126805357862237e-05, "loss": 0.2627, "step": 2038 }, { "epoch": 3.3, "learning_rate": 3.125937713083296e-05, "loss": 0.195, "step": 2039 }, { "epoch": 3.31, "learning_rate": 3.125069757969231e-05, "loss": 0.282, "step": 2040 }, { "epoch": 3.31, "learning_rate": 3.12420149275927e-05, "loss": 0.2523, "step": 2041 }, { "epoch": 3.31, "learning_rate": 3.12333291769273e-05, "loss": 0.2248, "step": 2042 }, { "epoch": 3.31, "learning_rate": 3.122464033009009e-05, "loss": 0.1668, "step": 2043 }, { "epoch": 3.31, "learning_rate": 3.121594838947593e-05, "loss": 0.2355, "step": 2044 }, { "epoch": 3.31, "learning_rate": 3.120725335748053e-05, "loss": 0.2288, "step": 2045 }, { "epoch": 3.32, "learning_rate": 3.1198555236500435e-05, "loss": 0.2587, "step": 2046 }, { "epoch": 3.32, "learning_rate": 3.1189854028933065e-05, "loss": 0.2125, "step": 2047 }, { "epoch": 3.32, "learning_rate": 3.118114973717667e-05, "loss": 0.2714, "step": 2048 }, { "epoch": 3.32, "learning_rate": 3.1172442363630365e-05, "loss": 0.2659, "step": 2049 }, { "epoch": 3.32, "learning_rate": 3.11637319106941e-05, "loss": 0.2848, "step": 2050 }, { "epoch": 3.32, "learning_rate": 3.11550183807687e-05, "loss": 0.2259, "step": 2051 }, { "epoch": 3.33, "learning_rate": 3.1146301776255795e-05, "loss": 0.239, "step": 2052 }, { "epoch": 3.33, "learning_rate": 3.113758209955791e-05, "loss": 0.2079, "step": 2053 }, { "epoch": 3.33, "learning_rate": 3.112885935307839e-05, "loss": 0.2573, "step": 2054 }, { "epoch": 3.33, "learning_rate": 3.1120133539221415e-05, "loss": 0.2319, "step": 2055 }, { "epoch": 3.33, "learning_rate": 3.111140466039205e-05, "loss": 0.1818, "step": 2056 }, { "epoch": 3.33, "learning_rate": 3.1102672718996165e-05, "loss": 0.2709, "step": 2057 }, { "epoch": 3.34, "learning_rate": 3.109393771744049e-05, "loss": 0.2371, "step": 2058 }, { "epoch": 3.34, "learning_rate": 3.108519965813261e-05, "loss": 0.2288, "step": 2059 }, { "epoch": 3.34, "learning_rate": 3.107645854348093e-05, "loss": 0.192, "step": 2060 }, { "epoch": 3.34, "learning_rate": 3.106771437589471e-05, "loss": 0.2137, "step": 2061 }, { "epoch": 3.34, "learning_rate": 3.1058967157784056e-05, "loss": 0.2172, "step": 2062 }, { "epoch": 3.34, "learning_rate": 3.1050216891559904e-05, "loss": 0.3201, "step": 2063 }, { "epoch": 3.35, "learning_rate": 3.1041463579634034e-05, "loss": 0.2397, "step": 2064 }, { "epoch": 3.35, "learning_rate": 3.1032707224419066e-05, "loss": 0.2083, "step": 2065 }, { "epoch": 3.35, "learning_rate": 3.102394782832846e-05, "loss": 0.2707, "step": 2066 }, { "epoch": 3.35, "learning_rate": 3.1015185393776516e-05, "loss": 0.3184, "step": 2067 }, { "epoch": 3.35, "learning_rate": 3.100641992317837e-05, "loss": 0.2412, "step": 2068 }, { "epoch": 3.35, "learning_rate": 3.0997651418949986e-05, "loss": 0.2819, "step": 2069 }, { "epoch": 3.35, "learning_rate": 3.098887988350818e-05, "loss": 0.2504, "step": 2070 }, { "epoch": 3.36, "learning_rate": 3.098010531927059e-05, "loss": 0.2141, "step": 2071 }, { "epoch": 3.36, "learning_rate": 3.0971327728655695e-05, "loss": 0.1938, "step": 2072 }, { "epoch": 3.36, "learning_rate": 3.0962547114082804e-05, "loss": 0.2948, "step": 2073 }, { "epoch": 3.36, "learning_rate": 3.095376347797207e-05, "loss": 0.2259, "step": 2074 }, { "epoch": 3.36, "learning_rate": 3.0944976822744464e-05, "loss": 0.2506, "step": 2075 }, { "epoch": 3.36, "learning_rate": 3.09361871508218e-05, "loss": 0.2546, "step": 2076 }, { "epoch": 3.37, "learning_rate": 3.092739446462672e-05, "loss": 0.2503, "step": 2077 }, { "epoch": 3.37, "learning_rate": 3.091859876658269e-05, "loss": 0.2051, "step": 2078 }, { "epoch": 3.37, "learning_rate": 3.090980005911402e-05, "loss": 0.2295, "step": 2079 }, { "epoch": 3.37, "learning_rate": 3.090099834464585e-05, "loss": 0.1972, "step": 2080 }, { "epoch": 3.37, "learning_rate": 3.089219362560413e-05, "loss": 0.1882, "step": 2081 }, { "epoch": 3.37, "learning_rate": 3.0883385904415644e-05, "loss": 0.2118, "step": 2082 }, { "epoch": 3.38, "learning_rate": 3.0874575183508024e-05, "loss": 0.2249, "step": 2083 }, { "epoch": 3.38, "learning_rate": 3.08657614653097e-05, "loss": 0.1758, "step": 2084 }, { "epoch": 3.38, "learning_rate": 3.0856944752249947e-05, "loss": 0.1807, "step": 2085 }, { "epoch": 3.38, "learning_rate": 3.0848125046758863e-05, "loss": 0.2272, "step": 2086 }, { "epoch": 3.38, "learning_rate": 3.083930235126737e-05, "loss": 0.1915, "step": 2087 }, { "epoch": 3.38, "learning_rate": 3.0830476668207206e-05, "loss": 0.2454, "step": 2088 }, { "epoch": 3.39, "learning_rate": 3.082164800001094e-05, "loss": 0.2029, "step": 2089 }, { "epoch": 3.39, "learning_rate": 3.0812816349111956e-05, "loss": 0.3271, "step": 2090 }, { "epoch": 3.39, "learning_rate": 3.0803981717944475e-05, "loss": 0.3121, "step": 2091 }, { "epoch": 3.39, "learning_rate": 3.0795144108943534e-05, "loss": 0.2392, "step": 2092 }, { "epoch": 3.39, "learning_rate": 3.0786303524544975e-05, "loss": 0.2901, "step": 2093 }, { "epoch": 3.39, "learning_rate": 3.077745996718548e-05, "loss": 0.2627, "step": 2094 }, { "epoch": 3.4, "learning_rate": 3.076861343930254e-05, "loss": 0.3132, "step": 2095 }, { "epoch": 3.4, "learning_rate": 3.075976394333448e-05, "loss": 0.2303, "step": 2096 }, { "epoch": 3.4, "learning_rate": 3.075091148172042e-05, "loss": 0.2041, "step": 2097 }, { "epoch": 3.4, "learning_rate": 3.0742056056900304e-05, "loss": 0.1898, "step": 2098 }, { "epoch": 3.4, "learning_rate": 3.07331976713149e-05, "loss": 0.1741, "step": 2099 }, { "epoch": 3.4, "learning_rate": 3.07243363274058e-05, "loss": 0.2101, "step": 2100 }, { "epoch": 3.41, "learning_rate": 3.0715472027615386e-05, "loss": 0.2168, "step": 2101 }, { "epoch": 3.41, "learning_rate": 3.070660477438688e-05, "loss": 0.2404, "step": 2102 }, { "epoch": 3.41, "learning_rate": 3.06977345701643e-05, "loss": 0.222, "step": 2103 }, { "epoch": 3.41, "learning_rate": 3.068886141739248e-05, "loss": 0.1658, "step": 2104 }, { "epoch": 3.41, "learning_rate": 3.067998531851709e-05, "loss": 0.2307, "step": 2105 }, { "epoch": 3.41, "learning_rate": 3.067110627598457e-05, "loss": 0.2054, "step": 2106 }, { "epoch": 3.41, "learning_rate": 3.066222429224221e-05, "loss": 0.2664, "step": 2107 }, { "epoch": 3.42, "learning_rate": 3.0653339369738094e-05, "loss": 0.2572, "step": 2108 }, { "epoch": 3.42, "learning_rate": 3.064445151092111e-05, "loss": 0.2691, "step": 2109 }, { "epoch": 3.42, "learning_rate": 3.063556071824097e-05, "loss": 0.2444, "step": 2110 }, { "epoch": 3.42, "learning_rate": 3.062666699414819e-05, "loss": 0.2974, "step": 2111 }, { "epoch": 3.42, "learning_rate": 3.061777034109408e-05, "loss": 0.2062, "step": 2112 }, { "epoch": 3.42, "learning_rate": 3.0608870761530774e-05, "loss": 0.2643, "step": 2113 }, { "epoch": 3.43, "learning_rate": 3.05999682579112e-05, "loss": 0.2336, "step": 2114 }, { "epoch": 3.43, "learning_rate": 3.059106283268912e-05, "loss": 0.2089, "step": 2115 }, { "epoch": 3.43, "learning_rate": 3.0582154488319055e-05, "loss": 0.2422, "step": 2116 }, { "epoch": 3.43, "learning_rate": 3.057324322725637e-05, "loss": 0.261, "step": 2117 }, { "epoch": 3.43, "learning_rate": 3.056432905195721e-05, "loss": 0.2739, "step": 2118 }, { "epoch": 3.43, "learning_rate": 3.055541196487855e-05, "loss": 0.3046, "step": 2119 }, { "epoch": 3.44, "learning_rate": 3.0546491968478144e-05, "loss": 0.2362, "step": 2120 }, { "epoch": 3.44, "learning_rate": 3.053756906521454e-05, "loss": 0.2199, "step": 2121 }, { "epoch": 3.44, "learning_rate": 3.052864325754712e-05, "loss": 0.2212, "step": 2122 }, { "epoch": 3.44, "learning_rate": 3.051971454793604e-05, "loss": 0.2229, "step": 2123 }, { "epoch": 3.44, "learning_rate": 3.051078293884226e-05, "loss": 0.2464, "step": 2124 }, { "epoch": 3.44, "learning_rate": 3.050184843272755e-05, "loss": 0.2763, "step": 2125 }, { "epoch": 3.45, "learning_rate": 3.0492911032054472e-05, "loss": 0.2656, "step": 2126 }, { "epoch": 3.45, "learning_rate": 3.048397073928638e-05, "loss": 0.2314, "step": 2127 }, { "epoch": 3.45, "learning_rate": 3.0475027556887445e-05, "loss": 0.2734, "step": 2128 }, { "epoch": 3.45, "learning_rate": 3.0466081487322596e-05, "loss": 0.2625, "step": 2129 }, { "epoch": 3.45, "learning_rate": 3.0457132533057598e-05, "loss": 0.2578, "step": 2130 }, { "epoch": 3.45, "learning_rate": 3.0448180696558994e-05, "loss": 0.2018, "step": 2131 }, { "epoch": 3.46, "learning_rate": 3.0439225980294113e-05, "loss": 0.2215, "step": 2132 }, { "epoch": 3.46, "learning_rate": 3.04302683867311e-05, "loss": 0.3176, "step": 2133 }, { "epoch": 3.46, "learning_rate": 3.0421307918338873e-05, "loss": 0.2159, "step": 2134 }, { "epoch": 3.46, "learning_rate": 3.0412344577587153e-05, "loss": 0.1994, "step": 2135 }, { "epoch": 3.46, "learning_rate": 3.0403378366946444e-05, "loss": 0.2581, "step": 2136 }, { "epoch": 3.46, "learning_rate": 3.039440928888805e-05, "loss": 0.221, "step": 2137 }, { "epoch": 3.47, "learning_rate": 3.038543734588406e-05, "loss": 0.2253, "step": 2138 }, { "epoch": 3.47, "learning_rate": 3.0376462540407358e-05, "loss": 0.2124, "step": 2139 }, { "epoch": 3.47, "learning_rate": 3.036748487493161e-05, "loss": 0.2229, "step": 2140 }, { "epoch": 3.47, "learning_rate": 3.0358504351931265e-05, "loss": 0.2173, "step": 2141 }, { "epoch": 3.47, "learning_rate": 3.0349520973881582e-05, "loss": 0.2726, "step": 2142 }, { "epoch": 3.47, "learning_rate": 3.034053474325859e-05, "loss": 0.2321, "step": 2143 }, { "epoch": 3.47, "learning_rate": 3.0331545662539094e-05, "loss": 0.1812, "step": 2144 }, { "epoch": 3.48, "learning_rate": 3.032255373420072e-05, "loss": 0.2068, "step": 2145 }, { "epoch": 3.48, "learning_rate": 3.0313558960721844e-05, "loss": 0.2574, "step": 2146 }, { "epoch": 3.48, "learning_rate": 3.030456134458163e-05, "loss": 0.194, "step": 2147 }, { "epoch": 3.48, "learning_rate": 3.029556088826005e-05, "loss": 0.2302, "step": 2148 }, { "epoch": 3.48, "learning_rate": 3.0286557594237832e-05, "loss": 0.215, "step": 2149 }, { "epoch": 3.48, "learning_rate": 3.027755146499651e-05, "loss": 0.2299, "step": 2150 }, { "epoch": 3.49, "learning_rate": 3.0268542503018374e-05, "loss": 0.2288, "step": 2151 }, { "epoch": 3.49, "learning_rate": 3.025953071078652e-05, "loss": 0.2256, "step": 2152 }, { "epoch": 3.49, "learning_rate": 3.0250516090784793e-05, "loss": 0.3315, "step": 2153 }, { "epoch": 3.49, "learning_rate": 3.0241498645497852e-05, "loss": 0.2589, "step": 2154 }, { "epoch": 3.49, "learning_rate": 3.0232478377411114e-05, "loss": 0.2522, "step": 2155 }, { "epoch": 3.49, "learning_rate": 3.0223455289010775e-05, "loss": 0.2387, "step": 2156 }, { "epoch": 3.5, "learning_rate": 3.0214429382783817e-05, "loss": 0.2311, "step": 2157 }, { "epoch": 3.5, "learning_rate": 3.0205400661218e-05, "loss": 0.2655, "step": 2158 }, { "epoch": 3.5, "learning_rate": 3.0196369126801835e-05, "loss": 0.2663, "step": 2159 }, { "epoch": 3.5, "learning_rate": 3.0187334782024637e-05, "loss": 0.318, "step": 2160 }, { "epoch": 3.5, "learning_rate": 3.0178297629376492e-05, "loss": 0.2032, "step": 2161 }, { "epoch": 3.5, "learning_rate": 3.016925767134825e-05, "loss": 0.1976, "step": 2162 }, { "epoch": 3.51, "learning_rate": 3.0160214910431525e-05, "loss": 0.2814, "step": 2163 }, { "epoch": 3.51, "learning_rate": 3.0151169349118733e-05, "loss": 0.3949, "step": 2164 }, { "epoch": 3.51, "learning_rate": 3.0142120989903047e-05, "loss": 0.2374, "step": 2165 }, { "epoch": 3.51, "learning_rate": 3.013306983527839e-05, "loss": 0.2027, "step": 2166 }, { "epoch": 3.51, "learning_rate": 3.0124015887739486e-05, "loss": 0.2769, "step": 2167 }, { "epoch": 3.51, "learning_rate": 3.0114959149781825e-05, "loss": 0.2279, "step": 2168 }, { "epoch": 3.52, "learning_rate": 3.0105899623901646e-05, "loss": 0.2276, "step": 2169 }, { "epoch": 3.52, "learning_rate": 3.009683731259598e-05, "loss": 0.2106, "step": 2170 }, { "epoch": 3.52, "learning_rate": 3.00877722183626e-05, "loss": 0.3004, "step": 2171 }, { "epoch": 3.52, "learning_rate": 3.0078704343700073e-05, "loss": 0.1992, "step": 2172 }, { "epoch": 3.52, "learning_rate": 3.006963369110772e-05, "loss": 0.2091, "step": 2173 }, { "epoch": 3.52, "learning_rate": 3.006056026308562e-05, "loss": 0.3297, "step": 2174 }, { "epoch": 3.53, "learning_rate": 3.0051484062134632e-05, "loss": 0.2701, "step": 2175 }, { "epoch": 3.53, "learning_rate": 3.004240509075637e-05, "loss": 0.3418, "step": 2176 }, { "epoch": 3.53, "learning_rate": 3.003332335145322e-05, "loss": 0.2034, "step": 2177 }, { "epoch": 3.53, "learning_rate": 3.002423884672831e-05, "loss": 0.2986, "step": 2178 }, { "epoch": 3.53, "learning_rate": 3.0015151579085553e-05, "loss": 0.1818, "step": 2179 }, { "epoch": 3.53, "learning_rate": 3.0006061551029617e-05, "loss": 0.2846, "step": 2180 }, { "epoch": 3.53, "learning_rate": 2.999696876506593e-05, "loss": 0.2903, "step": 2181 }, { "epoch": 3.54, "learning_rate": 2.9987873223700677e-05, "loss": 0.2668, "step": 2182 }, { "epoch": 3.54, "learning_rate": 2.9978774929440807e-05, "loss": 0.2685, "step": 2183 }, { "epoch": 3.54, "learning_rate": 2.9969673884794023e-05, "loss": 0.2491, "step": 2184 }, { "epoch": 3.54, "learning_rate": 2.9960570092268787e-05, "loss": 0.2343, "step": 2185 }, { "epoch": 3.54, "learning_rate": 2.9951463554374317e-05, "loss": 0.2115, "step": 2186 }, { "epoch": 3.54, "learning_rate": 2.99423542736206e-05, "loss": 0.2525, "step": 2187 }, { "epoch": 3.55, "learning_rate": 2.993324225251837e-05, "loss": 0.2534, "step": 2188 }, { "epoch": 3.55, "learning_rate": 2.992412749357911e-05, "loss": 0.1963, "step": 2189 }, { "epoch": 3.55, "learning_rate": 2.991500999931506e-05, "loss": 0.3109, "step": 2190 }, { "epoch": 3.55, "learning_rate": 2.9905889772239224e-05, "loss": 0.2116, "step": 2191 }, { "epoch": 3.55, "learning_rate": 2.9896766814865355e-05, "loss": 0.2124, "step": 2192 }, { "epoch": 3.55, "learning_rate": 2.9887641129707948e-05, "loss": 0.1688, "step": 2193 }, { "epoch": 3.56, "learning_rate": 2.9878512719282267e-05, "loss": 0.3099, "step": 2194 }, { "epoch": 3.56, "learning_rate": 2.9869381586104316e-05, "loss": 0.1872, "step": 2195 }, { "epoch": 3.56, "learning_rate": 2.986024773269085e-05, "loss": 0.2524, "step": 2196 }, { "epoch": 3.56, "learning_rate": 2.985111116155937e-05, "loss": 0.242, "step": 2197 }, { "epoch": 3.56, "learning_rate": 2.9841971875228134e-05, "loss": 0.2528, "step": 2198 }, { "epoch": 3.56, "learning_rate": 2.983282987621616e-05, "loss": 0.2119, "step": 2199 }, { "epoch": 3.57, "learning_rate": 2.9823685167043184e-05, "loss": 0.2573, "step": 2200 }, { "epoch": 3.57, "learning_rate": 2.981453775022971e-05, "loss": 0.3268, "step": 2201 }, { "epoch": 3.57, "learning_rate": 2.980538762829698e-05, "loss": 0.2059, "step": 2202 }, { "epoch": 3.57, "learning_rate": 2.979623480376699e-05, "loss": 0.2823, "step": 2203 }, { "epoch": 3.57, "learning_rate": 2.9787079279162467e-05, "loss": 0.2536, "step": 2204 }, { "epoch": 3.57, "learning_rate": 2.97779210570069e-05, "loss": 0.2784, "step": 2205 }, { "epoch": 3.58, "learning_rate": 2.976876013982451e-05, "loss": 0.2198, "step": 2206 }, { "epoch": 3.58, "learning_rate": 2.9759596530140257e-05, "loss": 0.242, "step": 2207 }, { "epoch": 3.58, "learning_rate": 2.9750430230479855e-05, "loss": 0.2789, "step": 2208 }, { "epoch": 3.58, "learning_rate": 2.9741261243369746e-05, "loss": 0.2907, "step": 2209 }, { "epoch": 3.58, "learning_rate": 2.9732089571337126e-05, "loss": 0.2702, "step": 2210 }, { "epoch": 3.58, "learning_rate": 2.9722915216909933e-05, "loss": 0.2709, "step": 2211 }, { "epoch": 3.59, "learning_rate": 2.971373818261682e-05, "loss": 0.239, "step": 2212 }, { "epoch": 3.59, "learning_rate": 2.970455847098721e-05, "loss": 0.2487, "step": 2213 }, { "epoch": 3.59, "learning_rate": 2.9695376084551237e-05, "loss": 0.2117, "step": 2214 }, { "epoch": 3.59, "learning_rate": 2.9686191025839793e-05, "loss": 0.2176, "step": 2215 }, { "epoch": 3.59, "learning_rate": 2.9677003297384495e-05, "loss": 0.2221, "step": 2216 }, { "epoch": 3.59, "learning_rate": 2.9667812901717696e-05, "loss": 0.2376, "step": 2217 }, { "epoch": 3.59, "learning_rate": 2.965861984137249e-05, "loss": 0.2653, "step": 2218 }, { "epoch": 3.6, "learning_rate": 2.964942411888271e-05, "loss": 0.2788, "step": 2219 }, { "epoch": 3.6, "learning_rate": 2.9640225736782898e-05, "loss": 0.2459, "step": 2220 }, { "epoch": 3.6, "learning_rate": 2.9631024697608353e-05, "loss": 0.2463, "step": 2221 }, { "epoch": 3.6, "learning_rate": 2.9621821003895107e-05, "loss": 0.2417, "step": 2222 }, { "epoch": 3.6, "learning_rate": 2.961261465817991e-05, "loss": 0.2635, "step": 2223 }, { "epoch": 3.6, "learning_rate": 2.960340566300025e-05, "loss": 0.2864, "step": 2224 }, { "epoch": 3.61, "learning_rate": 2.9594194020894343e-05, "loss": 0.2624, "step": 2225 }, { "epoch": 3.61, "learning_rate": 2.958497973440114e-05, "loss": 0.243, "step": 2226 }, { "epoch": 3.61, "learning_rate": 2.9575762806060315e-05, "loss": 0.2281, "step": 2227 }, { "epoch": 3.61, "learning_rate": 2.9566543238412263e-05, "loss": 0.2326, "step": 2228 }, { "epoch": 3.61, "learning_rate": 2.9557321033998127e-05, "loss": 0.199, "step": 2229 }, { "epoch": 3.61, "learning_rate": 2.9548096195359765e-05, "loss": 0.228, "step": 2230 }, { "epoch": 3.62, "learning_rate": 2.9538868725039757e-05, "loss": 0.241, "step": 2231 }, { "epoch": 3.62, "learning_rate": 2.952963862558141e-05, "loss": 0.302, "step": 2232 }, { "epoch": 3.62, "learning_rate": 2.9520405899528763e-05, "loss": 0.2511, "step": 2233 }, { "epoch": 3.62, "learning_rate": 2.9511170549426577e-05, "loss": 0.2278, "step": 2234 }, { "epoch": 3.62, "learning_rate": 2.950193257782032e-05, "loss": 0.2365, "step": 2235 }, { "epoch": 3.62, "learning_rate": 2.949269198725621e-05, "loss": 0.2103, "step": 2236 }, { "epoch": 3.63, "learning_rate": 2.948344878028117e-05, "loss": 0.2393, "step": 2237 }, { "epoch": 3.63, "learning_rate": 2.9474202959442848e-05, "loss": 0.1893, "step": 2238 }, { "epoch": 3.63, "learning_rate": 2.9464954527289594e-05, "loss": 0.2039, "step": 2239 }, { "epoch": 3.63, "learning_rate": 2.9455703486370518e-05, "loss": 0.3023, "step": 2240 }, { "epoch": 3.63, "learning_rate": 2.9446449839235413e-05, "loss": 0.2287, "step": 2241 }, { "epoch": 3.63, "learning_rate": 2.9437193588434816e-05, "loss": 0.2134, "step": 2242 }, { "epoch": 3.64, "learning_rate": 2.9427934736519962e-05, "loss": 0.2371, "step": 2243 }, { "epoch": 3.64, "learning_rate": 2.94186732860428e-05, "loss": 0.2415, "step": 2244 }, { "epoch": 3.64, "learning_rate": 2.940940923955602e-05, "loss": 0.2469, "step": 2245 }, { "epoch": 3.64, "learning_rate": 2.9400142599613005e-05, "loss": 0.1876, "step": 2246 }, { "epoch": 3.64, "learning_rate": 2.939087336876786e-05, "loss": 0.2966, "step": 2247 }, { "epoch": 3.64, "learning_rate": 2.9381601549575406e-05, "loss": 0.2821, "step": 2248 }, { "epoch": 3.65, "learning_rate": 2.9372327144591188e-05, "loss": 0.2484, "step": 2249 }, { "epoch": 3.65, "learning_rate": 2.9363050156371433e-05, "loss": 0.23, "step": 2250 }, { "epoch": 3.65, "learning_rate": 2.9353770587473112e-05, "loss": 0.1941, "step": 2251 }, { "epoch": 3.65, "learning_rate": 2.9344488440453887e-05, "loss": 0.293, "step": 2252 }, { "epoch": 3.65, "learning_rate": 2.9335203717872144e-05, "loss": 0.2879, "step": 2253 }, { "epoch": 3.65, "learning_rate": 2.932591642228696e-05, "loss": 0.1825, "step": 2254 }, { "epoch": 3.65, "learning_rate": 2.931662655625815e-05, "loss": 0.2209, "step": 2255 }, { "epoch": 3.66, "learning_rate": 2.9307334122346218e-05, "loss": 0.2056, "step": 2256 }, { "epoch": 3.66, "learning_rate": 2.9298039123112373e-05, "loss": 0.2665, "step": 2257 }, { "epoch": 3.66, "learning_rate": 2.928874156111853e-05, "loss": 0.296, "step": 2258 }, { "epoch": 3.66, "learning_rate": 2.9279441438927335e-05, "loss": 0.2906, "step": 2259 }, { "epoch": 3.66, "learning_rate": 2.9270138759102108e-05, "loss": 0.1692, "step": 2260 }, { "epoch": 3.66, "learning_rate": 2.9260833524206905e-05, "loss": 0.2055, "step": 2261 }, { "epoch": 3.67, "learning_rate": 2.9251525736806454e-05, "loss": 0.2308, "step": 2262 }, { "epoch": 3.67, "learning_rate": 2.92422153994662e-05, "loss": 0.2931, "step": 2263 }, { "epoch": 3.67, "learning_rate": 2.9232902514752305e-05, "loss": 0.2095, "step": 2264 }, { "epoch": 3.67, "learning_rate": 2.922358708523161e-05, "loss": 0.2841, "step": 2265 }, { "epoch": 3.67, "learning_rate": 2.9214269113471672e-05, "loss": 0.2134, "step": 2266 }, { "epoch": 3.67, "learning_rate": 2.9204948602040746e-05, "loss": 0.2646, "step": 2267 }, { "epoch": 3.68, "learning_rate": 2.9195625553507788e-05, "loss": 0.3003, "step": 2268 }, { "epoch": 3.68, "learning_rate": 2.9186299970442452e-05, "loss": 0.3143, "step": 2269 }, { "epoch": 3.68, "learning_rate": 2.9176971855415083e-05, "loss": 0.2066, "step": 2270 }, { "epoch": 3.68, "learning_rate": 2.9167641210996734e-05, "loss": 0.193, "step": 2271 }, { "epoch": 3.68, "learning_rate": 2.915830803975915e-05, "loss": 0.2635, "step": 2272 }, { "epoch": 3.68, "learning_rate": 2.9148972344274775e-05, "loss": 0.2885, "step": 2273 }, { "epoch": 3.69, "learning_rate": 2.9139634127116756e-05, "loss": 0.2639, "step": 2274 }, { "epoch": 3.69, "learning_rate": 2.9130293390858914e-05, "loss": 0.2668, "step": 2275 }, { "epoch": 3.69, "learning_rate": 2.912095013807579e-05, "loss": 0.179, "step": 2276 }, { "epoch": 3.69, "learning_rate": 2.9111604371342593e-05, "loss": 0.2013, "step": 2277 }, { "epoch": 3.69, "learning_rate": 2.9102256093235245e-05, "loss": 0.2476, "step": 2278 }, { "epoch": 3.69, "learning_rate": 2.909290530633035e-05, "loss": 0.1914, "step": 2279 }, { "epoch": 3.7, "learning_rate": 2.9083552013205216e-05, "loss": 0.248, "step": 2280 }, { "epoch": 3.7, "learning_rate": 2.9074196216437825e-05, "loss": 0.2167, "step": 2281 }, { "epoch": 3.7, "learning_rate": 2.906483791860685e-05, "loss": 0.2139, "step": 2282 }, { "epoch": 3.7, "learning_rate": 2.905547712229167e-05, "loss": 0.2591, "step": 2283 }, { "epoch": 3.7, "learning_rate": 2.9046113830072337e-05, "loss": 0.3188, "step": 2284 }, { "epoch": 3.7, "learning_rate": 2.9036748044529597e-05, "loss": 0.2355, "step": 2285 }, { "epoch": 3.71, "learning_rate": 2.902737976824489e-05, "loss": 0.2249, "step": 2286 }, { "epoch": 3.71, "learning_rate": 2.9018009003800322e-05, "loss": 0.1957, "step": 2287 }, { "epoch": 3.71, "learning_rate": 2.9008635753778704e-05, "loss": 0.2108, "step": 2288 }, { "epoch": 3.71, "learning_rate": 2.8999260020763525e-05, "loss": 0.2464, "step": 2289 }, { "epoch": 3.71, "learning_rate": 2.8989881807338964e-05, "loss": 0.233, "step": 2290 }, { "epoch": 3.71, "learning_rate": 2.898050111608987e-05, "loss": 0.1816, "step": 2291 }, { "epoch": 3.71, "learning_rate": 2.8971117949601794e-05, "loss": 0.1935, "step": 2292 }, { "epoch": 3.72, "learning_rate": 2.8961732310460955e-05, "loss": 0.3092, "step": 2293 }, { "epoch": 3.72, "learning_rate": 2.8952344201254253e-05, "loss": 0.2033, "step": 2294 }, { "epoch": 3.72, "learning_rate": 2.8942953624569283e-05, "loss": 0.2944, "step": 2295 }, { "epoch": 3.72, "learning_rate": 2.8933560582994296e-05, "loss": 0.2207, "step": 2296 }, { "epoch": 3.72, "learning_rate": 2.8924165079118252e-05, "loss": 0.249, "step": 2297 }, { "epoch": 3.72, "learning_rate": 2.891476711553077e-05, "loss": 0.2045, "step": 2298 }, { "epoch": 3.73, "learning_rate": 2.8905366694822146e-05, "loss": 0.2398, "step": 2299 }, { "epoch": 3.73, "learning_rate": 2.8895963819583365e-05, "loss": 0.1825, "step": 2300 }, { "epoch": 3.73, "learning_rate": 2.8886558492406077e-05, "loss": 0.3093, "step": 2301 }, { "epoch": 3.73, "learning_rate": 2.8877150715882613e-05, "loss": 0.218, "step": 2302 }, { "epoch": 3.73, "learning_rate": 2.8867740492605994e-05, "loss": 0.1889, "step": 2303 }, { "epoch": 3.73, "learning_rate": 2.8858327825169877e-05, "loss": 0.2884, "step": 2304 }, { "epoch": 3.74, "learning_rate": 2.8848912716168634e-05, "loss": 0.2652, "step": 2305 }, { "epoch": 3.74, "learning_rate": 2.8839495168197288e-05, "loss": 0.1909, "step": 2306 }, { "epoch": 3.74, "learning_rate": 2.8830075183851532e-05, "loss": 0.2359, "step": 2307 }, { "epoch": 3.74, "learning_rate": 2.8820652765727744e-05, "loss": 0.2362, "step": 2308 }, { "epoch": 3.74, "learning_rate": 2.8811227916422964e-05, "loss": 0.258, "step": 2309 }, { "epoch": 3.74, "learning_rate": 2.8801800638534906e-05, "loss": 0.2178, "step": 2310 }, { "epoch": 3.75, "learning_rate": 2.8792370934661948e-05, "loss": 0.2246, "step": 2311 }, { "epoch": 3.75, "learning_rate": 2.8782938807403134e-05, "loss": 0.2429, "step": 2312 }, { "epoch": 3.75, "learning_rate": 2.877350425935819e-05, "loss": 0.2369, "step": 2313 }, { "epoch": 3.75, "learning_rate": 2.8764067293127506e-05, "loss": 0.2221, "step": 2314 }, { "epoch": 3.75, "learning_rate": 2.8754627911312124e-05, "loss": 0.2542, "step": 2315 }, { "epoch": 3.75, "learning_rate": 2.874518611651376e-05, "loss": 0.2665, "step": 2316 }, { "epoch": 3.76, "learning_rate": 2.8735741911334812e-05, "loss": 0.2414, "step": 2317 }, { "epoch": 3.76, "learning_rate": 2.872629529837831e-05, "loss": 0.261, "step": 2318 }, { "epoch": 3.76, "learning_rate": 2.871684628024797e-05, "loss": 0.2384, "step": 2319 }, { "epoch": 3.76, "learning_rate": 2.8707394859548167e-05, "loss": 0.2091, "step": 2320 }, { "epoch": 3.76, "learning_rate": 2.869794103888393e-05, "loss": 0.2469, "step": 2321 }, { "epoch": 3.76, "learning_rate": 2.8688484820860965e-05, "loss": 0.2863, "step": 2322 }, { "epoch": 3.76, "learning_rate": 2.867902620808563e-05, "loss": 0.2228, "step": 2323 }, { "epoch": 3.77, "learning_rate": 2.8669565203164933e-05, "loss": 0.2775, "step": 2324 }, { "epoch": 3.77, "learning_rate": 2.8660101808706556e-05, "loss": 0.2328, "step": 2325 }, { "epoch": 3.77, "learning_rate": 2.8650636027318844e-05, "loss": 0.2514, "step": 2326 }, { "epoch": 3.77, "learning_rate": 2.864116786161078e-05, "loss": 0.2573, "step": 2327 }, { "epoch": 3.77, "learning_rate": 2.8631697314192012e-05, "loss": 0.2097, "step": 2328 }, { "epoch": 3.77, "learning_rate": 2.862222438767286e-05, "loss": 0.2365, "step": 2329 }, { "epoch": 3.78, "learning_rate": 2.8612749084664282e-05, "loss": 0.2605, "step": 2330 }, { "epoch": 3.78, "learning_rate": 2.8603271407777892e-05, "loss": 0.281, "step": 2331 }, { "epoch": 3.78, "learning_rate": 2.8593791359625957e-05, "loss": 0.2424, "step": 2332 }, { "epoch": 3.78, "learning_rate": 2.8584308942821422e-05, "loss": 0.3352, "step": 2333 }, { "epoch": 3.78, "learning_rate": 2.857482415997785e-05, "loss": 0.2659, "step": 2334 }, { "epoch": 3.78, "learning_rate": 2.8565337013709476e-05, "loss": 0.2638, "step": 2335 }, { "epoch": 3.79, "learning_rate": 2.855584750663118e-05, "loss": 0.3307, "step": 2336 }, { "epoch": 3.79, "learning_rate": 2.8546355641358506e-05, "loss": 0.2912, "step": 2337 }, { "epoch": 3.79, "learning_rate": 2.853686142050762e-05, "loss": 0.2254, "step": 2338 }, { "epoch": 3.79, "learning_rate": 2.852736484669537e-05, "loss": 0.1917, "step": 2339 }, { "epoch": 3.79, "learning_rate": 2.8517865922539227e-05, "loss": 0.2289, "step": 2340 }, { "epoch": 3.79, "learning_rate": 2.850836465065733e-05, "loss": 0.2509, "step": 2341 }, { "epoch": 3.8, "learning_rate": 2.8498861033668444e-05, "loss": 0.2397, "step": 2342 }, { "epoch": 3.8, "learning_rate": 2.8489355074191987e-05, "loss": 0.2859, "step": 2343 }, { "epoch": 3.8, "learning_rate": 2.8479846774848044e-05, "loss": 0.2423, "step": 2344 }, { "epoch": 3.8, "learning_rate": 2.8470336138257315e-05, "loss": 0.4032, "step": 2345 }, { "epoch": 3.8, "learning_rate": 2.8460823167041162e-05, "loss": 0.2493, "step": 2346 }, { "epoch": 3.8, "learning_rate": 2.8451307863821583e-05, "loss": 0.2288, "step": 2347 }, { "epoch": 3.81, "learning_rate": 2.8441790231221223e-05, "loss": 0.2172, "step": 2348 }, { "epoch": 3.81, "learning_rate": 2.8432270271863363e-05, "loss": 0.2356, "step": 2349 }, { "epoch": 3.81, "learning_rate": 2.842274798837193e-05, "loss": 0.2493, "step": 2350 }, { "epoch": 3.81, "learning_rate": 2.8413223383371497e-05, "loss": 0.2379, "step": 2351 }, { "epoch": 3.81, "learning_rate": 2.8403696459487272e-05, "loss": 0.2781, "step": 2352 }, { "epoch": 3.81, "learning_rate": 2.8394167219345087e-05, "loss": 0.3114, "step": 2353 }, { "epoch": 3.82, "learning_rate": 2.8384635665571444e-05, "loss": 0.2071, "step": 2354 }, { "epoch": 3.82, "learning_rate": 2.8375101800793454e-05, "loss": 0.2568, "step": 2355 }, { "epoch": 3.82, "learning_rate": 2.836556562763888e-05, "loss": 0.2763, "step": 2356 }, { "epoch": 3.82, "learning_rate": 2.8356027148736114e-05, "loss": 0.1868, "step": 2357 }, { "epoch": 3.82, "learning_rate": 2.8346486366714185e-05, "loss": 0.2586, "step": 2358 }, { "epoch": 3.82, "learning_rate": 2.8336943284202773e-05, "loss": 0.2594, "step": 2359 }, { "epoch": 3.82, "learning_rate": 2.832739790383217e-05, "loss": 0.2815, "step": 2360 }, { "epoch": 3.83, "learning_rate": 2.8317850228233297e-05, "loss": 0.2937, "step": 2361 }, { "epoch": 3.83, "learning_rate": 2.8308300260037734e-05, "loss": 0.1937, "step": 2362 }, { "epoch": 3.83, "learning_rate": 2.829874800187767e-05, "loss": 0.2066, "step": 2363 }, { "epoch": 3.83, "learning_rate": 2.8289193456385944e-05, "loss": 0.229, "step": 2364 }, { "epoch": 3.83, "learning_rate": 2.8279636626196006e-05, "loss": 0.2596, "step": 2365 }, { "epoch": 3.83, "learning_rate": 2.8270077513941953e-05, "loss": 0.2394, "step": 2366 }, { "epoch": 3.84, "learning_rate": 2.826051612225849e-05, "loss": 0.2032, "step": 2367 }, { "epoch": 3.84, "learning_rate": 2.8250952453780978e-05, "loss": 0.2464, "step": 2368 }, { "epoch": 3.84, "learning_rate": 2.824138651114538e-05, "loss": 0.2181, "step": 2369 }, { "epoch": 3.84, "learning_rate": 2.8231818296988304e-05, "loss": 0.2366, "step": 2370 }, { "epoch": 3.84, "learning_rate": 2.822224781394697e-05, "loss": 0.2486, "step": 2371 }, { "epoch": 3.84, "learning_rate": 2.8212675064659232e-05, "loss": 0.2958, "step": 2372 }, { "epoch": 3.85, "learning_rate": 2.820310005176358e-05, "loss": 0.2568, "step": 2373 }, { "epoch": 3.85, "learning_rate": 2.819352277789909e-05, "loss": 0.192, "step": 2374 }, { "epoch": 3.85, "learning_rate": 2.8183943245705502e-05, "loss": 0.2621, "step": 2375 }, { "epoch": 3.85, "learning_rate": 2.817436145782316e-05, "loss": 0.2127, "step": 2376 }, { "epoch": 3.85, "learning_rate": 2.8164777416893024e-05, "loss": 0.2594, "step": 2377 }, { "epoch": 3.85, "learning_rate": 2.8155191125556696e-05, "loss": 0.2339, "step": 2378 }, { "epoch": 3.86, "learning_rate": 2.814560258645638e-05, "loss": 0.304, "step": 2379 }, { "epoch": 3.86, "learning_rate": 2.8136011802234896e-05, "loss": 0.4004, "step": 2380 }, { "epoch": 3.86, "learning_rate": 2.8126418775535697e-05, "loss": 0.2351, "step": 2381 }, { "epoch": 3.86, "learning_rate": 2.811682350900285e-05, "loss": 0.1891, "step": 2382 }, { "epoch": 3.86, "learning_rate": 2.8107226005281046e-05, "loss": 0.279, "step": 2383 }, { "epoch": 3.86, "learning_rate": 2.8097626267015567e-05, "loss": 0.1927, "step": 2384 }, { "epoch": 3.87, "learning_rate": 2.8088024296852348e-05, "loss": 0.2376, "step": 2385 }, { "epoch": 3.87, "learning_rate": 2.80784200974379e-05, "loss": 0.2125, "step": 2386 }, { "epoch": 3.87, "learning_rate": 2.8068813671419385e-05, "loss": 0.2741, "step": 2387 }, { "epoch": 3.87, "learning_rate": 2.8059205021444548e-05, "loss": 0.2694, "step": 2388 }, { "epoch": 3.87, "learning_rate": 2.8049594150161764e-05, "loss": 0.2694, "step": 2389 }, { "epoch": 3.87, "learning_rate": 2.8039981060220028e-05, "loss": 0.2178, "step": 2390 }, { "epoch": 3.88, "learning_rate": 2.8030365754268927e-05, "loss": 0.2199, "step": 2391 }, { "epoch": 3.88, "learning_rate": 2.802074823495866e-05, "loss": 0.1897, "step": 2392 }, { "epoch": 3.88, "learning_rate": 2.8011128504940054e-05, "loss": 0.3196, "step": 2393 }, { "epoch": 3.88, "learning_rate": 2.8001506566864534e-05, "loss": 0.2779, "step": 2394 }, { "epoch": 3.88, "learning_rate": 2.7991882423384133e-05, "loss": 0.2127, "step": 2395 }, { "epoch": 3.88, "learning_rate": 2.7982256077151482e-05, "loss": 0.2139, "step": 2396 }, { "epoch": 3.88, "learning_rate": 2.797262753081985e-05, "loss": 0.2417, "step": 2397 }, { "epoch": 3.89, "learning_rate": 2.796299678704308e-05, "loss": 0.2025, "step": 2398 }, { "epoch": 3.89, "learning_rate": 2.7953363848475635e-05, "loss": 0.2857, "step": 2399 }, { "epoch": 3.89, "learning_rate": 2.7943728717772577e-05, "loss": 0.2422, "step": 2400 }, { "epoch": 3.89, "learning_rate": 2.7934091397589584e-05, "loss": 0.2573, "step": 2401 }, { "epoch": 3.89, "learning_rate": 2.7924451890582936e-05, "loss": 0.205, "step": 2402 }, { "epoch": 3.89, "learning_rate": 2.7914810199409492e-05, "loss": 0.3455, "step": 2403 }, { "epoch": 3.9, "learning_rate": 2.790516632672674e-05, "loss": 0.2759, "step": 2404 }, { "epoch": 3.9, "learning_rate": 2.789552027519276e-05, "loss": 0.2321, "step": 2405 }, { "epoch": 3.9, "learning_rate": 2.7885872047466236e-05, "loss": 0.2218, "step": 2406 }, { "epoch": 3.9, "learning_rate": 2.787622164620644e-05, "loss": 0.2729, "step": 2407 }, { "epoch": 3.9, "learning_rate": 2.7866569074073252e-05, "loss": 0.1838, "step": 2408 }, { "epoch": 3.9, "learning_rate": 2.7856914333727162e-05, "loss": 0.1928, "step": 2409 }, { "epoch": 3.91, "learning_rate": 2.7847257427829233e-05, "loss": 0.2818, "step": 2410 }, { "epoch": 3.91, "learning_rate": 2.783759835904114e-05, "loss": 0.2149, "step": 2411 }, { "epoch": 3.91, "learning_rate": 2.7827937130025147e-05, "loss": 0.1993, "step": 2412 }, { "epoch": 3.91, "learning_rate": 2.7818273743444132e-05, "loss": 0.2491, "step": 2413 }, { "epoch": 3.91, "learning_rate": 2.780860820196154e-05, "loss": 0.2911, "step": 2414 }, { "epoch": 3.91, "learning_rate": 2.779894050824143e-05, "loss": 0.3169, "step": 2415 }, { "epoch": 3.92, "learning_rate": 2.778927066494844e-05, "loss": 0.2479, "step": 2416 }, { "epoch": 3.92, "learning_rate": 2.7779598674747817e-05, "loss": 0.2555, "step": 2417 }, { "epoch": 3.92, "learning_rate": 2.7769924540305385e-05, "loss": 0.3005, "step": 2418 }, { "epoch": 3.92, "learning_rate": 2.7760248264287565e-05, "loss": 0.2622, "step": 2419 }, { "epoch": 3.92, "learning_rate": 2.775056984936137e-05, "loss": 0.3137, "step": 2420 }, { "epoch": 3.92, "learning_rate": 2.7740889298194402e-05, "loss": 0.3562, "step": 2421 }, { "epoch": 3.93, "learning_rate": 2.7731206613454853e-05, "loss": 0.2025, "step": 2422 }, { "epoch": 3.93, "learning_rate": 2.772152179781149e-05, "loss": 0.1819, "step": 2423 }, { "epoch": 3.93, "learning_rate": 2.7711834853933685e-05, "loss": 0.2351, "step": 2424 }, { "epoch": 3.93, "learning_rate": 2.770214578449139e-05, "loss": 0.2269, "step": 2425 }, { "epoch": 3.93, "learning_rate": 2.7692454592155137e-05, "loss": 0.2764, "step": 2426 }, { "epoch": 3.93, "learning_rate": 2.768276127959606e-05, "loss": 0.2217, "step": 2427 }, { "epoch": 3.94, "learning_rate": 2.7673065849485845e-05, "loss": 0.2702, "step": 2428 }, { "epoch": 3.94, "learning_rate": 2.7663368304496807e-05, "loss": 0.1955, "step": 2429 }, { "epoch": 3.94, "learning_rate": 2.7653668647301797e-05, "loss": 0.2488, "step": 2430 }, { "epoch": 3.94, "learning_rate": 2.7643966880574285e-05, "loss": 0.2799, "step": 2431 }, { "epoch": 3.94, "learning_rate": 2.7634263006988306e-05, "loss": 0.2396, "step": 2432 }, { "epoch": 3.94, "learning_rate": 2.762455702921847e-05, "loss": 0.1992, "step": 2433 }, { "epoch": 3.94, "learning_rate": 2.7614848949939986e-05, "loss": 0.1946, "step": 2434 }, { "epoch": 3.95, "learning_rate": 2.7605138771828617e-05, "loss": 0.2319, "step": 2435 }, { "epoch": 3.95, "learning_rate": 2.7595426497560734e-05, "loss": 0.2822, "step": 2436 }, { "epoch": 3.95, "learning_rate": 2.7585712129813253e-05, "loss": 0.2256, "step": 2437 }, { "epoch": 3.95, "learning_rate": 2.7575995671263695e-05, "loss": 0.2806, "step": 2438 }, { "epoch": 3.95, "learning_rate": 2.7566277124590145e-05, "loss": 0.2574, "step": 2439 }, { "epoch": 3.95, "learning_rate": 2.755655649247127e-05, "loss": 0.3981, "step": 2440 }, { "epoch": 3.96, "learning_rate": 2.754683377758629e-05, "loss": 0.2179, "step": 2441 }, { "epoch": 3.96, "learning_rate": 2.753710898261503e-05, "loss": 0.2919, "step": 2442 }, { "epoch": 3.96, "learning_rate": 2.752738211023787e-05, "loss": 0.2546, "step": 2443 }, { "epoch": 3.96, "learning_rate": 2.751765316313577e-05, "loss": 0.2316, "step": 2444 }, { "epoch": 3.96, "learning_rate": 2.7507922143990253e-05, "loss": 0.248, "step": 2445 }, { "epoch": 3.96, "learning_rate": 2.7498189055483423e-05, "loss": 0.226, "step": 2446 }, { "epoch": 3.97, "learning_rate": 2.748845390029794e-05, "loss": 0.2686, "step": 2447 }, { "epoch": 3.97, "learning_rate": 2.747871668111706e-05, "loss": 0.2492, "step": 2448 }, { "epoch": 3.97, "learning_rate": 2.746897740062458e-05, "loss": 0.2405, "step": 2449 }, { "epoch": 3.97, "learning_rate": 2.7459236061504873e-05, "loss": 0.2237, "step": 2450 }, { "epoch": 3.97, "learning_rate": 2.7449492666442897e-05, "loss": 0.239, "step": 2451 }, { "epoch": 3.97, "learning_rate": 2.7439747218124156e-05, "loss": 0.2907, "step": 2452 }, { "epoch": 3.98, "learning_rate": 2.7429999719234717e-05, "loss": 0.2233, "step": 2453 }, { "epoch": 3.98, "learning_rate": 2.7420250172461233e-05, "loss": 0.2726, "step": 2454 }, { "epoch": 3.98, "learning_rate": 2.7410498580490916e-05, "loss": 0.2094, "step": 2455 }, { "epoch": 3.98, "learning_rate": 2.7400744946011516e-05, "loss": 0.266, "step": 2456 }, { "epoch": 3.98, "learning_rate": 2.7390989271711377e-05, "loss": 0.3289, "step": 2457 }, { "epoch": 3.98, "learning_rate": 2.7381231560279405e-05, "loss": 0.2588, "step": 2458 }, { "epoch": 3.99, "learning_rate": 2.737147181440504e-05, "loss": 0.2673, "step": 2459 }, { "epoch": 3.99, "learning_rate": 2.7361710036778303e-05, "loss": 0.1966, "step": 2460 }, { "epoch": 3.99, "learning_rate": 2.735194623008977e-05, "loss": 0.2102, "step": 2461 }, { "epoch": 3.99, "learning_rate": 2.7342180397030586e-05, "loss": 0.2625, "step": 2462 }, { "epoch": 3.99, "learning_rate": 2.7332412540292446e-05, "loss": 0.2524, "step": 2463 }, { "epoch": 3.99, "learning_rate": 2.7322642662567592e-05, "loss": 0.2986, "step": 2464 }, { "epoch": 4.0, "learning_rate": 2.731287076654884e-05, "loss": 0.283, "step": 2465 }, { "epoch": 4.0, "learning_rate": 2.7303096854929553e-05, "loss": 0.2079, "step": 2466 }, { "epoch": 4.0, "learning_rate": 2.7293320930403662e-05, "loss": 0.2389, "step": 2467 }, { "epoch": 4.0, "learning_rate": 2.7283542995665632e-05, "loss": 0.2, "step": 2468 }, { "epoch": 4.0, "learning_rate": 2.72737630534105e-05, "loss": 0.1718, "step": 2469 }, { "epoch": 4.0, "learning_rate": 2.726398110633385e-05, "loss": 0.2614, "step": 2470 }, { "epoch": 4.0, "learning_rate": 2.7254197157131824e-05, "loss": 0.1862, "step": 2471 }, { "epoch": 4.01, "learning_rate": 2.7244411208501093e-05, "loss": 0.2126, "step": 2472 }, { "epoch": 4.01, "learning_rate": 2.7234623263138908e-05, "loss": 0.2252, "step": 2473 }, { "epoch": 4.01, "learning_rate": 2.7224833323743064e-05, "loss": 0.157, "step": 2474 }, { "epoch": 4.01, "learning_rate": 2.7215041393011888e-05, "loss": 0.1965, "step": 2475 }, { "epoch": 4.01, "learning_rate": 2.720524747364428e-05, "loss": 0.2196, "step": 2476 }, { "epoch": 4.01, "learning_rate": 2.7195451568339667e-05, "loss": 0.236, "step": 2477 }, { "epoch": 4.02, "learning_rate": 2.7185653679798036e-05, "loss": 0.1786, "step": 2478 }, { "epoch": 4.02, "learning_rate": 2.7175853810719916e-05, "loss": 0.1918, "step": 2479 }, { "epoch": 4.02, "learning_rate": 2.7166051963806387e-05, "loss": 0.181, "step": 2480 }, { "epoch": 4.02, "learning_rate": 2.715624814175907e-05, "loss": 0.2182, "step": 2481 }, { "epoch": 4.02, "learning_rate": 2.714644234728013e-05, "loss": 0.2078, "step": 2482 }, { "epoch": 4.02, "learning_rate": 2.7136634583072273e-05, "loss": 0.2162, "step": 2483 }, { "epoch": 4.03, "learning_rate": 2.7126824851838756e-05, "loss": 0.1652, "step": 2484 }, { "epoch": 4.03, "learning_rate": 2.7117013156283366e-05, "loss": 0.1803, "step": 2485 }, { "epoch": 4.03, "learning_rate": 2.7107199499110448e-05, "loss": 0.2613, "step": 2486 }, { "epoch": 4.03, "learning_rate": 2.7097383883024874e-05, "loss": 0.1976, "step": 2487 }, { "epoch": 4.03, "learning_rate": 2.7087566310732066e-05, "loss": 0.1632, "step": 2488 }, { "epoch": 4.03, "learning_rate": 2.7077746784937967e-05, "loss": 0.1747, "step": 2489 }, { "epoch": 4.04, "learning_rate": 2.7067925308349084e-05, "loss": 0.1787, "step": 2490 }, { "epoch": 4.04, "learning_rate": 2.705810188367244e-05, "loss": 0.2079, "step": 2491 }, { "epoch": 4.04, "learning_rate": 2.7048276513615603e-05, "loss": 0.2415, "step": 2492 }, { "epoch": 4.04, "learning_rate": 2.703844920088669e-05, "loss": 0.1659, "step": 2493 }, { "epoch": 4.04, "learning_rate": 2.7028619948194332e-05, "loss": 0.2262, "step": 2494 }, { "epoch": 4.04, "learning_rate": 2.701878875824771e-05, "loss": 0.1585, "step": 2495 }, { "epoch": 4.05, "learning_rate": 2.700895563375652e-05, "loss": 0.2733, "step": 2496 }, { "epoch": 4.05, "learning_rate": 2.699912057743102e-05, "loss": 0.2343, "step": 2497 }, { "epoch": 4.05, "learning_rate": 2.698928359198197e-05, "loss": 0.1944, "step": 2498 }, { "epoch": 4.05, "learning_rate": 2.6979444680120685e-05, "loss": 0.2328, "step": 2499 }, { "epoch": 4.05, "learning_rate": 2.6969603844559e-05, "loss": 0.1378, "step": 2500 }, { "epoch": 4.05, "learning_rate": 2.6959761088009294e-05, "loss": 0.1575, "step": 2501 }, { "epoch": 4.06, "learning_rate": 2.694991641318445e-05, "loss": 0.2783, "step": 2502 }, { "epoch": 4.06, "learning_rate": 2.6940069822797893e-05, "loss": 0.2535, "step": 2503 }, { "epoch": 4.06, "learning_rate": 2.6930221319563582e-05, "loss": 0.1947, "step": 2504 }, { "epoch": 4.06, "learning_rate": 2.6920370906195995e-05, "loss": 0.219, "step": 2505 }, { "epoch": 4.06, "learning_rate": 2.6910518585410144e-05, "loss": 0.198, "step": 2506 }, { "epoch": 4.06, "learning_rate": 2.690066435992156e-05, "loss": 0.1946, "step": 2507 }, { "epoch": 4.06, "learning_rate": 2.68908082324463e-05, "loss": 0.1763, "step": 2508 }, { "epoch": 4.07, "learning_rate": 2.6880950205700954e-05, "loss": 0.2463, "step": 2509 }, { "epoch": 4.07, "learning_rate": 2.6871090282402614e-05, "loss": 0.2112, "step": 2510 }, { "epoch": 4.07, "learning_rate": 2.6861228465268916e-05, "loss": 0.2497, "step": 2511 }, { "epoch": 4.07, "learning_rate": 2.6851364757018007e-05, "loss": 0.2262, "step": 2512 }, { "epoch": 4.07, "learning_rate": 2.684149916036857e-05, "loss": 0.2356, "step": 2513 }, { "epoch": 4.07, "learning_rate": 2.6831631678039785e-05, "loss": 0.2008, "step": 2514 }, { "epoch": 4.08, "learning_rate": 2.6821762312751368e-05, "loss": 0.2124, "step": 2515 }, { "epoch": 4.08, "learning_rate": 2.6811891067223555e-05, "loss": 0.2366, "step": 2516 }, { "epoch": 4.08, "learning_rate": 2.680201794417708e-05, "loss": 0.2266, "step": 2517 }, { "epoch": 4.08, "learning_rate": 2.6792142946333227e-05, "loss": 0.3046, "step": 2518 }, { "epoch": 4.08, "learning_rate": 2.678226607641378e-05, "loss": 0.1825, "step": 2519 }, { "epoch": 4.08, "learning_rate": 2.6772387337141027e-05, "loss": 0.2461, "step": 2520 }, { "epoch": 4.09, "learning_rate": 2.676250673123778e-05, "loss": 0.1723, "step": 2521 }, { "epoch": 4.09, "learning_rate": 2.675262426142738e-05, "loss": 0.2193, "step": 2522 }, { "epoch": 4.09, "learning_rate": 2.6742739930433662e-05, "loss": 0.2261, "step": 2523 }, { "epoch": 4.09, "learning_rate": 2.6732853740980988e-05, "loss": 0.2492, "step": 2524 }, { "epoch": 4.09, "learning_rate": 2.6722965695794224e-05, "loss": 0.2725, "step": 2525 }, { "epoch": 4.09, "learning_rate": 2.671307579759875e-05, "loss": 0.2959, "step": 2526 }, { "epoch": 4.1, "learning_rate": 2.6703184049120455e-05, "loss": 0.158, "step": 2527 }, { "epoch": 4.1, "learning_rate": 2.669329045308574e-05, "loss": 0.2757, "step": 2528 }, { "epoch": 4.1, "learning_rate": 2.6683395012221505e-05, "loss": 0.2213, "step": 2529 }, { "epoch": 4.1, "learning_rate": 2.6673497729255188e-05, "loss": 0.2283, "step": 2530 }, { "epoch": 4.1, "learning_rate": 2.6663598606914703e-05, "loss": 0.2623, "step": 2531 }, { "epoch": 4.1, "learning_rate": 2.6653697647928485e-05, "loss": 0.212, "step": 2532 }, { "epoch": 4.11, "learning_rate": 2.6643794855025466e-05, "loss": 0.1796, "step": 2533 }, { "epoch": 4.11, "learning_rate": 2.66338902309351e-05, "loss": 0.1956, "step": 2534 }, { "epoch": 4.11, "learning_rate": 2.6623983778387335e-05, "loss": 0.1834, "step": 2535 }, { "epoch": 4.11, "learning_rate": 2.6614075500112614e-05, "loss": 0.2023, "step": 2536 }, { "epoch": 4.11, "learning_rate": 2.6604165398841905e-05, "loss": 0.2631, "step": 2537 }, { "epoch": 4.11, "learning_rate": 2.6594253477306663e-05, "loss": 0.1653, "step": 2538 }, { "epoch": 4.12, "learning_rate": 2.6584339738238852e-05, "loss": 0.1757, "step": 2539 }, { "epoch": 4.12, "learning_rate": 2.6574424184370927e-05, "loss": 0.2154, "step": 2540 }, { "epoch": 4.12, "learning_rate": 2.656450681843585e-05, "loss": 0.2213, "step": 2541 }, { "epoch": 4.12, "learning_rate": 2.6554587643167088e-05, "loss": 0.1847, "step": 2542 }, { "epoch": 4.12, "learning_rate": 2.6544666661298595e-05, "loss": 0.2097, "step": 2543 }, { "epoch": 4.12, "learning_rate": 2.6534743875564838e-05, "loss": 0.1631, "step": 2544 }, { "epoch": 4.12, "learning_rate": 2.652481928870076e-05, "loss": 0.1795, "step": 2545 }, { "epoch": 4.13, "learning_rate": 2.6514892903441815e-05, "loss": 0.2177, "step": 2546 }, { "epoch": 4.13, "learning_rate": 2.6504964722523962e-05, "loss": 0.2878, "step": 2547 }, { "epoch": 4.13, "learning_rate": 2.6495034748683622e-05, "loss": 0.156, "step": 2548 }, { "epoch": 4.13, "learning_rate": 2.648510298465775e-05, "loss": 0.1847, "step": 2549 }, { "epoch": 4.13, "learning_rate": 2.6475169433183768e-05, "loss": 0.168, "step": 2550 }, { "epoch": 4.13, "learning_rate": 2.6465234096999603e-05, "loss": 0.1732, "step": 2551 }, { "epoch": 4.14, "learning_rate": 2.6455296978843657e-05, "loss": 0.2108, "step": 2552 }, { "epoch": 4.14, "learning_rate": 2.6445358081454843e-05, "loss": 0.2381, "step": 2553 }, { "epoch": 4.14, "learning_rate": 2.643541740757256e-05, "loss": 0.1762, "step": 2554 }, { "epoch": 4.14, "learning_rate": 2.6425474959936695e-05, "loss": 0.2113, "step": 2555 }, { "epoch": 4.14, "learning_rate": 2.6415530741287616e-05, "loss": 0.227, "step": 2556 }, { "epoch": 4.14, "learning_rate": 2.6405584754366184e-05, "loss": 0.2211, "step": 2557 }, { "epoch": 4.15, "learning_rate": 2.6395637001913752e-05, "loss": 0.2065, "step": 2558 }, { "epoch": 4.15, "learning_rate": 2.6385687486672156e-05, "loss": 0.2207, "step": 2559 }, { "epoch": 4.15, "learning_rate": 2.6375736211383717e-05, "loss": 0.2412, "step": 2560 }, { "epoch": 4.15, "learning_rate": 2.6365783178791248e-05, "loss": 0.152, "step": 2561 }, { "epoch": 4.15, "learning_rate": 2.6355828391638036e-05, "loss": 0.2137, "step": 2562 }, { "epoch": 4.15, "learning_rate": 2.634587185266786e-05, "loss": 0.2077, "step": 2563 }, { "epoch": 4.16, "learning_rate": 2.6335913564624965e-05, "loss": 0.2232, "step": 2564 }, { "epoch": 4.16, "learning_rate": 2.6325953530254107e-05, "loss": 0.2117, "step": 2565 }, { "epoch": 4.16, "learning_rate": 2.6315991752300503e-05, "loss": 0.218, "step": 2566 }, { "epoch": 4.16, "learning_rate": 2.630602823350985e-05, "loss": 0.1816, "step": 2567 }, { "epoch": 4.16, "learning_rate": 2.629606297662834e-05, "loss": 0.1664, "step": 2568 }, { "epoch": 4.16, "learning_rate": 2.628609598440262e-05, "loss": 0.1787, "step": 2569 }, { "epoch": 4.17, "learning_rate": 2.6276127259579848e-05, "loss": 0.1835, "step": 2570 }, { "epoch": 4.17, "learning_rate": 2.626615680490762e-05, "loss": 0.181, "step": 2571 }, { "epoch": 4.17, "learning_rate": 2.625618462313404e-05, "loss": 0.2345, "step": 2572 }, { "epoch": 4.17, "learning_rate": 2.6246210717007678e-05, "loss": 0.2395, "step": 2573 }, { "epoch": 4.17, "learning_rate": 2.623623508927758e-05, "loss": 0.1549, "step": 2574 }, { "epoch": 4.17, "learning_rate": 2.6226257742693273e-05, "loss": 0.2343, "step": 2575 }, { "epoch": 4.18, "learning_rate": 2.6216278680004726e-05, "loss": 0.2773, "step": 2576 }, { "epoch": 4.18, "learning_rate": 2.6206297903962433e-05, "loss": 0.2115, "step": 2577 }, { "epoch": 4.18, "learning_rate": 2.6196315417317314e-05, "loss": 0.2343, "step": 2578 }, { "epoch": 4.18, "learning_rate": 2.618633122282078e-05, "loss": 0.2073, "step": 2579 }, { "epoch": 4.18, "learning_rate": 2.6176345323224722e-05, "loss": 0.1899, "step": 2580 }, { "epoch": 4.18, "learning_rate": 2.6166357721281487e-05, "loss": 0.1979, "step": 2581 }, { "epoch": 4.18, "learning_rate": 2.6156368419743892e-05, "loss": 0.2497, "step": 2582 }, { "epoch": 4.19, "learning_rate": 2.6146377421365225e-05, "loss": 0.1741, "step": 2583 }, { "epoch": 4.19, "learning_rate": 2.6136384728899236e-05, "loss": 0.1796, "step": 2584 }, { "epoch": 4.19, "learning_rate": 2.6126390345100166e-05, "loss": 0.1919, "step": 2585 }, { "epoch": 4.19, "learning_rate": 2.6116394272722688e-05, "loss": 0.206, "step": 2586 }, { "epoch": 4.19, "learning_rate": 2.6106396514521965e-05, "loss": 0.2531, "step": 2587 }, { "epoch": 4.19, "learning_rate": 2.6096397073253606e-05, "loss": 0.2747, "step": 2588 }, { "epoch": 4.2, "learning_rate": 2.6086395951673708e-05, "loss": 0.175, "step": 2589 }, { "epoch": 4.2, "learning_rate": 2.6076393152538807e-05, "loss": 0.1856, "step": 2590 }, { "epoch": 4.2, "learning_rate": 2.6066388678605913e-05, "loss": 0.2262, "step": 2591 }, { "epoch": 4.2, "learning_rate": 2.6056382532632506e-05, "loss": 0.1592, "step": 2592 }, { "epoch": 4.2, "learning_rate": 2.6046374717376503e-05, "loss": 0.2174, "step": 2593 }, { "epoch": 4.2, "learning_rate": 2.6036365235596296e-05, "loss": 0.2692, "step": 2594 }, { "epoch": 4.21, "learning_rate": 2.602635409005075e-05, "loss": 0.1722, "step": 2595 }, { "epoch": 4.21, "learning_rate": 2.601634128349915e-05, "loss": 0.2599, "step": 2596 }, { "epoch": 4.21, "learning_rate": 2.600632681870129e-05, "loss": 0.1842, "step": 2597 }, { "epoch": 4.21, "learning_rate": 2.5996310698417376e-05, "loss": 0.1853, "step": 2598 }, { "epoch": 4.21, "learning_rate": 2.59862929254081e-05, "loss": 0.2554, "step": 2599 }, { "epoch": 4.21, "learning_rate": 2.5976273502434584e-05, "loss": 0.2066, "step": 2600 }, { "epoch": 4.22, "learning_rate": 2.5966252432258427e-05, "loss": 0.2016, "step": 2601 }, { "epoch": 4.22, "learning_rate": 2.595622971764167e-05, "loss": 0.171, "step": 2602 }, { "epoch": 4.22, "learning_rate": 2.5946205361346816e-05, "loss": 0.1454, "step": 2603 }, { "epoch": 4.22, "learning_rate": 2.5936179366136812e-05, "loss": 0.1987, "step": 2604 }, { "epoch": 4.22, "learning_rate": 2.5926151734775063e-05, "loss": 0.2409, "step": 2605 }, { "epoch": 4.22, "learning_rate": 2.5916122470025414e-05, "loss": 0.2144, "step": 2606 }, { "epoch": 4.23, "learning_rate": 2.5906091574652167e-05, "loss": 0.1677, "step": 2607 }, { "epoch": 4.23, "learning_rate": 2.5896059051420093e-05, "loss": 0.1794, "step": 2608 }, { "epoch": 4.23, "learning_rate": 2.588602490309437e-05, "loss": 0.2266, "step": 2609 }, { "epoch": 4.23, "learning_rate": 2.5875989132440663e-05, "loss": 0.2078, "step": 2610 }, { "epoch": 4.23, "learning_rate": 2.5865951742225063e-05, "loss": 0.3241, "step": 2611 }, { "epoch": 4.23, "learning_rate": 2.5855912735214116e-05, "loss": 0.2658, "step": 2612 }, { "epoch": 4.24, "learning_rate": 2.5845872114174803e-05, "loss": 0.2158, "step": 2613 }, { "epoch": 4.24, "learning_rate": 2.583582988187456e-05, "loss": 0.2503, "step": 2614 }, { "epoch": 4.24, "learning_rate": 2.582578604108126e-05, "loss": 0.2167, "step": 2615 }, { "epoch": 4.24, "learning_rate": 2.5815740594563244e-05, "loss": 0.2563, "step": 2616 }, { "epoch": 4.24, "learning_rate": 2.580569354508925e-05, "loss": 0.1923, "step": 2617 }, { "epoch": 4.24, "learning_rate": 2.5795644895428494e-05, "loss": 0.2239, "step": 2618 }, { "epoch": 4.24, "learning_rate": 2.578559464835063e-05, "loss": 0.3368, "step": 2619 }, { "epoch": 4.25, "learning_rate": 2.5775542806625727e-05, "loss": 0.2301, "step": 2620 }, { "epoch": 4.25, "learning_rate": 2.5765489373024317e-05, "loss": 0.1984, "step": 2621 }, { "epoch": 4.25, "learning_rate": 2.5755434350317367e-05, "loss": 0.2124, "step": 2622 }, { "epoch": 4.25, "learning_rate": 2.5745377741276286e-05, "loss": 0.1831, "step": 2623 }, { "epoch": 4.25, "learning_rate": 2.5735319548672913e-05, "loss": 0.1917, "step": 2624 }, { "epoch": 4.25, "learning_rate": 2.5725259775279506e-05, "loss": 0.2695, "step": 2625 }, { "epoch": 4.26, "learning_rate": 2.5715198423868794e-05, "loss": 0.2485, "step": 2626 }, { "epoch": 4.26, "learning_rate": 2.570513549721392e-05, "loss": 0.2565, "step": 2627 }, { "epoch": 4.26, "learning_rate": 2.5695070998088465e-05, "loss": 0.1812, "step": 2628 }, { "epoch": 4.26, "learning_rate": 2.5685004929266443e-05, "loss": 0.2314, "step": 2629 }, { "epoch": 4.26, "learning_rate": 2.5674937293522305e-05, "loss": 0.2661, "step": 2630 }, { "epoch": 4.26, "learning_rate": 2.5664868093630932e-05, "loss": 0.1998, "step": 2631 }, { "epoch": 4.27, "learning_rate": 2.5654797332367616e-05, "loss": 0.1602, "step": 2632 }, { "epoch": 4.27, "learning_rate": 2.5644725012508116e-05, "loss": 0.1667, "step": 2633 }, { "epoch": 4.27, "learning_rate": 2.5634651136828597e-05, "loss": 0.2353, "step": 2634 }, { "epoch": 4.27, "learning_rate": 2.5624575708105656e-05, "loss": 0.1734, "step": 2635 }, { "epoch": 4.27, "learning_rate": 2.5614498729116327e-05, "loss": 0.2371, "step": 2636 }, { "epoch": 4.27, "learning_rate": 2.5604420202638053e-05, "loss": 0.1531, "step": 2637 }, { "epoch": 4.28, "learning_rate": 2.559434013144872e-05, "loss": 0.1711, "step": 2638 }, { "epoch": 4.28, "learning_rate": 2.558425851832664e-05, "loss": 0.2418, "step": 2639 }, { "epoch": 4.28, "learning_rate": 2.557417536605053e-05, "loss": 0.1585, "step": 2640 }, { "epoch": 4.28, "learning_rate": 2.5564090677399564e-05, "loss": 0.1612, "step": 2641 }, { "epoch": 4.28, "learning_rate": 2.555400445515331e-05, "loss": 0.1591, "step": 2642 }, { "epoch": 4.28, "learning_rate": 2.554391670209178e-05, "loss": 0.2353, "step": 2643 }, { "epoch": 4.29, "learning_rate": 2.553382742099538e-05, "loss": 0.2493, "step": 2644 }, { "epoch": 4.29, "learning_rate": 2.5523736614644968e-05, "loss": 0.2197, "step": 2645 }, { "epoch": 4.29, "learning_rate": 2.551364428582181e-05, "loss": 0.2305, "step": 2646 }, { "epoch": 4.29, "learning_rate": 2.5503550437307584e-05, "loss": 0.3094, "step": 2647 }, { "epoch": 4.29, "learning_rate": 2.5493455071884406e-05, "loss": 0.3209, "step": 2648 }, { "epoch": 4.29, "learning_rate": 2.548335819233478e-05, "loss": 0.2181, "step": 2649 }, { "epoch": 4.29, "learning_rate": 2.5473259801441663e-05, "loss": 0.2191, "step": 2650 }, { "epoch": 4.3, "learning_rate": 2.54631599019884e-05, "loss": 0.1678, "step": 2651 }, { "epoch": 4.3, "learning_rate": 2.545305849675876e-05, "loss": 0.2461, "step": 2652 }, { "epoch": 4.3, "learning_rate": 2.544295558853694e-05, "loss": 0.1777, "step": 2653 }, { "epoch": 4.3, "learning_rate": 2.5432851180107544e-05, "loss": 0.1659, "step": 2654 }, { "epoch": 4.3, "learning_rate": 2.5422745274255576e-05, "loss": 0.2179, "step": 2655 }, { "epoch": 4.3, "learning_rate": 2.5412637873766458e-05, "loss": 0.2223, "step": 2656 }, { "epoch": 4.31, "learning_rate": 2.5402528981426043e-05, "loss": 0.2264, "step": 2657 }, { "epoch": 4.31, "learning_rate": 2.539241860002058e-05, "loss": 0.1849, "step": 2658 }, { "epoch": 4.31, "learning_rate": 2.5382306732336716e-05, "loss": 0.2165, "step": 2659 }, { "epoch": 4.31, "learning_rate": 2.537219338116154e-05, "loss": 0.1769, "step": 2660 }, { "epoch": 4.31, "learning_rate": 2.5362078549282522e-05, "loss": 0.2073, "step": 2661 }, { "epoch": 4.31, "learning_rate": 2.5351962239487548e-05, "loss": 0.2709, "step": 2662 }, { "epoch": 4.32, "learning_rate": 2.5341844454564912e-05, "loss": 0.225, "step": 2663 }, { "epoch": 4.32, "learning_rate": 2.5331725197303313e-05, "loss": 0.2478, "step": 2664 }, { "epoch": 4.32, "learning_rate": 2.5321604470491873e-05, "loss": 0.1854, "step": 2665 }, { "epoch": 4.32, "learning_rate": 2.531148227692009e-05, "loss": 0.1651, "step": 2666 }, { "epoch": 4.32, "learning_rate": 2.530135861937789e-05, "loss": 0.2382, "step": 2667 }, { "epoch": 4.32, "learning_rate": 2.5291233500655584e-05, "loss": 0.2347, "step": 2668 }, { "epoch": 4.33, "learning_rate": 2.52811069235439e-05, "loss": 0.2239, "step": 2669 }, { "epoch": 4.33, "learning_rate": 2.5270978890833955e-05, "loss": 0.215, "step": 2670 }, { "epoch": 4.33, "learning_rate": 2.5260849405317284e-05, "loss": 0.1971, "step": 2671 }, { "epoch": 4.33, "learning_rate": 2.5250718469785812e-05, "loss": 0.2763, "step": 2672 }, { "epoch": 4.33, "learning_rate": 2.5240586087031868e-05, "loss": 0.2597, "step": 2673 }, { "epoch": 4.33, "learning_rate": 2.5230452259848167e-05, "loss": 0.1908, "step": 2674 }, { "epoch": 4.34, "learning_rate": 2.522031699102784e-05, "loss": 0.1728, "step": 2675 }, { "epoch": 4.34, "learning_rate": 2.52101802833644e-05, "loss": 0.1847, "step": 2676 }, { "epoch": 4.34, "learning_rate": 2.5200042139651776e-05, "loss": 0.1994, "step": 2677 }, { "epoch": 4.34, "learning_rate": 2.5189902562684268e-05, "loss": 0.1824, "step": 2678 }, { "epoch": 4.34, "learning_rate": 2.517976155525659e-05, "loss": 0.1897, "step": 2679 }, { "epoch": 4.34, "learning_rate": 2.5169619120163847e-05, "loss": 0.1548, "step": 2680 }, { "epoch": 4.35, "learning_rate": 2.515947526020153e-05, "loss": 0.2044, "step": 2681 }, { "epoch": 4.35, "learning_rate": 2.514932997816552e-05, "loss": 0.1972, "step": 2682 }, { "epoch": 4.35, "learning_rate": 2.5139183276852107e-05, "loss": 0.2065, "step": 2683 }, { "epoch": 4.35, "learning_rate": 2.5129035159057966e-05, "loss": 0.1594, "step": 2684 }, { "epoch": 4.35, "learning_rate": 2.5118885627580155e-05, "loss": 0.1722, "step": 2685 }, { "epoch": 4.35, "learning_rate": 2.5108734685216117e-05, "loss": 0.1755, "step": 2686 }, { "epoch": 4.35, "learning_rate": 2.50985823347637e-05, "loss": 0.2497, "step": 2687 }, { "epoch": 4.36, "learning_rate": 2.5088428579021137e-05, "loss": 0.2478, "step": 2688 }, { "epoch": 4.36, "learning_rate": 2.507827342078703e-05, "loss": 0.1714, "step": 2689 }, { "epoch": 4.36, "learning_rate": 2.5068116862860397e-05, "loss": 0.2417, "step": 2690 }, { "epoch": 4.36, "learning_rate": 2.505795890804062e-05, "loss": 0.1933, "step": 2691 }, { "epoch": 4.36, "learning_rate": 2.5047799559127467e-05, "loss": 0.1644, "step": 2692 }, { "epoch": 4.36, "learning_rate": 2.50376388189211e-05, "loss": 0.2162, "step": 2693 }, { "epoch": 4.37, "learning_rate": 2.5027476690222058e-05, "loss": 0.1808, "step": 2694 }, { "epoch": 4.37, "learning_rate": 2.501731317583126e-05, "loss": 0.1981, "step": 2695 }, { "epoch": 4.37, "learning_rate": 2.5007148278550028e-05, "loss": 0.2008, "step": 2696 }, { "epoch": 4.37, "learning_rate": 2.4996982001180038e-05, "loss": 0.1655, "step": 2697 }, { "epoch": 4.37, "learning_rate": 2.498681434652335e-05, "loss": 0.2022, "step": 2698 }, { "epoch": 4.37, "learning_rate": 2.497664531738242e-05, "loss": 0.2098, "step": 2699 }, { "epoch": 4.38, "learning_rate": 2.4966474916560076e-05, "loss": 0.1676, "step": 2700 }, { "epoch": 4.38, "learning_rate": 2.495630314685951e-05, "loss": 0.2334, "step": 2701 }, { "epoch": 4.38, "learning_rate": 2.494613001108431e-05, "loss": 0.2703, "step": 2702 }, { "epoch": 4.38, "learning_rate": 2.4935955512038437e-05, "loss": 0.183, "step": 2703 }, { "epoch": 4.38, "learning_rate": 2.4925779652526224e-05, "loss": 0.2451, "step": 2704 }, { "epoch": 4.38, "learning_rate": 2.4915602435352364e-05, "loss": 0.2421, "step": 2705 }, { "epoch": 4.39, "learning_rate": 2.4905423863321953e-05, "loss": 0.2169, "step": 2706 }, { "epoch": 4.39, "learning_rate": 2.489524393924045e-05, "loss": 0.2193, "step": 2707 }, { "epoch": 4.39, "learning_rate": 2.488506266591367e-05, "loss": 0.1987, "step": 2708 }, { "epoch": 4.39, "learning_rate": 2.487488004614783e-05, "loss": 0.2366, "step": 2709 }, { "epoch": 4.39, "learning_rate": 2.4864696082749483e-05, "loss": 0.2212, "step": 2710 }, { "epoch": 4.39, "learning_rate": 2.4854510778525588e-05, "loss": 0.3116, "step": 2711 }, { "epoch": 4.4, "learning_rate": 2.484432413628344e-05, "loss": 0.1922, "step": 2712 }, { "epoch": 4.4, "learning_rate": 2.4834136158830734e-05, "loss": 0.1604, "step": 2713 }, { "epoch": 4.4, "learning_rate": 2.4823946848975503e-05, "loss": 0.2172, "step": 2714 }, { "epoch": 4.4, "learning_rate": 2.481375620952618e-05, "loss": 0.2191, "step": 2715 }, { "epoch": 4.4, "learning_rate": 2.4803564243291534e-05, "loss": 0.2158, "step": 2716 }, { "epoch": 4.4, "learning_rate": 2.4793370953080717e-05, "loss": 0.2147, "step": 2717 }, { "epoch": 4.41, "learning_rate": 2.4783176341703233e-05, "loss": 0.238, "step": 2718 }, { "epoch": 4.41, "learning_rate": 2.4772980411968975e-05, "loss": 0.1318, "step": 2719 }, { "epoch": 4.41, "learning_rate": 2.476278316668817e-05, "loss": 0.2587, "step": 2720 }, { "epoch": 4.41, "learning_rate": 2.4752584608671425e-05, "loss": 0.1966, "step": 2721 }, { "epoch": 4.41, "learning_rate": 2.4742384740729704e-05, "loss": 0.2559, "step": 2722 }, { "epoch": 4.41, "learning_rate": 2.4732183565674332e-05, "loss": 0.1877, "step": 2723 }, { "epoch": 4.41, "learning_rate": 2.472198108631699e-05, "loss": 0.2229, "step": 2724 }, { "epoch": 4.42, "learning_rate": 2.4711777305469734e-05, "loss": 0.2128, "step": 2725 }, { "epoch": 4.42, "learning_rate": 2.4701572225944962e-05, "loss": 0.1928, "step": 2726 }, { "epoch": 4.42, "learning_rate": 2.4691365850555432e-05, "loss": 0.2492, "step": 2727 }, { "epoch": 4.42, "learning_rate": 2.4681158182114268e-05, "loss": 0.2063, "step": 2728 }, { "epoch": 4.42, "learning_rate": 2.4670949223434947e-05, "loss": 0.157, "step": 2729 }, { "epoch": 4.42, "learning_rate": 2.4660738977331297e-05, "loss": 0.2949, "step": 2730 }, { "epoch": 4.43, "learning_rate": 2.4650527446617492e-05, "loss": 0.1406, "step": 2731 }, { "epoch": 4.43, "learning_rate": 2.4640314634108092e-05, "loss": 0.1503, "step": 2732 }, { "epoch": 4.43, "learning_rate": 2.4630100542617986e-05, "loss": 0.1877, "step": 2733 }, { "epoch": 4.43, "learning_rate": 2.4619885174962414e-05, "loss": 0.2654, "step": 2734 }, { "epoch": 4.43, "learning_rate": 2.4609668533956975e-05, "loss": 0.2001, "step": 2735 }, { "epoch": 4.43, "learning_rate": 2.4599450622417615e-05, "loss": 0.2119, "step": 2736 }, { "epoch": 4.44, "learning_rate": 2.458923144316063e-05, "loss": 0.2661, "step": 2737 }, { "epoch": 4.44, "learning_rate": 2.4579010999002683e-05, "loss": 0.213, "step": 2738 }, { "epoch": 4.44, "learning_rate": 2.456878929276076e-05, "loss": 0.1885, "step": 2739 }, { "epoch": 4.44, "learning_rate": 2.455856632725221e-05, "loss": 0.2306, "step": 2740 }, { "epoch": 4.44, "learning_rate": 2.4548342105294708e-05, "loss": 0.1447, "step": 2741 }, { "epoch": 4.44, "learning_rate": 2.4538116629706314e-05, "loss": 0.1655, "step": 2742 }, { "epoch": 4.45, "learning_rate": 2.45278899033054e-05, "loss": 0.1592, "step": 2743 }, { "epoch": 4.45, "learning_rate": 2.4517661928910697e-05, "loss": 0.162, "step": 2744 }, { "epoch": 4.45, "learning_rate": 2.450743270934128e-05, "loss": 0.2287, "step": 2745 }, { "epoch": 4.45, "learning_rate": 2.4497202247416557e-05, "loss": 0.2626, "step": 2746 }, { "epoch": 4.45, "learning_rate": 2.4486970545956298e-05, "loss": 0.2398, "step": 2747 }, { "epoch": 4.45, "learning_rate": 2.4476737607780584e-05, "loss": 0.2203, "step": 2748 }, { "epoch": 4.46, "learning_rate": 2.4466503435709874e-05, "loss": 0.1772, "step": 2749 }, { "epoch": 4.46, "learning_rate": 2.4456268032564935e-05, "loss": 0.2163, "step": 2750 }, { "epoch": 4.46, "learning_rate": 2.4446031401166894e-05, "loss": 0.2175, "step": 2751 }, { "epoch": 4.46, "learning_rate": 2.443579354433721e-05, "loss": 0.2646, "step": 2752 }, { "epoch": 4.46, "learning_rate": 2.4425554464897675e-05, "loss": 0.2669, "step": 2753 }, { "epoch": 4.46, "learning_rate": 2.4415314165670423e-05, "loss": 0.1498, "step": 2754 }, { "epoch": 4.47, "learning_rate": 2.4405072649477923e-05, "loss": 0.2418, "step": 2755 }, { "epoch": 4.47, "learning_rate": 2.4394829919142974e-05, "loss": 0.1935, "step": 2756 }, { "epoch": 4.47, "learning_rate": 2.4384585977488736e-05, "loss": 0.1835, "step": 2757 }, { "epoch": 4.47, "learning_rate": 2.4374340827338653e-05, "loss": 0.2036, "step": 2758 }, { "epoch": 4.47, "learning_rate": 2.4364094471516556e-05, "loss": 0.2238, "step": 2759 }, { "epoch": 4.47, "learning_rate": 2.4353846912846567e-05, "loss": 0.2561, "step": 2760 }, { "epoch": 4.47, "learning_rate": 2.434359815415317e-05, "loss": 0.2223, "step": 2761 }, { "epoch": 4.48, "learning_rate": 2.4333348198261154e-05, "loss": 0.2492, "step": 2762 }, { "epoch": 4.48, "learning_rate": 2.432309704799565e-05, "loss": 0.163, "step": 2763 }, { "epoch": 4.48, "learning_rate": 2.431284470618213e-05, "loss": 0.2302, "step": 2764 }, { "epoch": 4.48, "learning_rate": 2.430259117564638e-05, "loss": 0.2184, "step": 2765 }, { "epoch": 4.48, "learning_rate": 2.4292336459214497e-05, "loss": 0.2235, "step": 2766 }, { "epoch": 4.48, "learning_rate": 2.4282080559712942e-05, "loss": 0.1615, "step": 2767 }, { "epoch": 4.49, "learning_rate": 2.4271823479968482e-05, "loss": 0.1859, "step": 2768 }, { "epoch": 4.49, "learning_rate": 2.4261565222808204e-05, "loss": 0.1682, "step": 2769 }, { "epoch": 4.49, "learning_rate": 2.4251305791059533e-05, "loss": 0.2118, "step": 2770 }, { "epoch": 4.49, "learning_rate": 2.4241045187550215e-05, "loss": 0.1683, "step": 2771 }, { "epoch": 4.49, "learning_rate": 2.423078341510831e-05, "loss": 0.1804, "step": 2772 }, { "epoch": 4.49, "learning_rate": 2.4220520476562208e-05, "loss": 0.2103, "step": 2773 }, { "epoch": 4.5, "learning_rate": 2.421025637474061e-05, "loss": 0.214, "step": 2774 }, { "epoch": 4.5, "learning_rate": 2.419999111247256e-05, "loss": 0.197, "step": 2775 }, { "epoch": 4.5, "learning_rate": 2.4189724692587398e-05, "loss": 0.2835, "step": 2776 }, { "epoch": 4.5, "learning_rate": 2.4179457117914793e-05, "loss": 0.3362, "step": 2777 }, { "epoch": 4.5, "learning_rate": 2.4169188391284735e-05, "loss": 0.2501, "step": 2778 }, { "epoch": 4.5, "learning_rate": 2.4158918515527524e-05, "loss": 0.2047, "step": 2779 }, { "epoch": 4.51, "learning_rate": 2.4148647493473792e-05, "loss": 0.2229, "step": 2780 }, { "epoch": 4.51, "learning_rate": 2.413837532795446e-05, "loss": 0.3135, "step": 2781 }, { "epoch": 4.51, "learning_rate": 2.4128102021800794e-05, "loss": 0.1875, "step": 2782 }, { "epoch": 4.51, "learning_rate": 2.411782757784436e-05, "loss": 0.2182, "step": 2783 }, { "epoch": 4.51, "learning_rate": 2.410755199891703e-05, "loss": 0.2021, "step": 2784 }, { "epoch": 4.51, "learning_rate": 2.4097275287851e-05, "loss": 0.2569, "step": 2785 }, { "epoch": 4.52, "learning_rate": 2.408699744747877e-05, "loss": 0.2435, "step": 2786 }, { "epoch": 4.52, "learning_rate": 2.4076718480633178e-05, "loss": 0.2251, "step": 2787 }, { "epoch": 4.52, "learning_rate": 2.4066438390147324e-05, "loss": 0.2203, "step": 2788 }, { "epoch": 4.52, "learning_rate": 2.4056157178854663e-05, "loss": 0.2071, "step": 2789 }, { "epoch": 4.52, "learning_rate": 2.4045874849588932e-05, "loss": 0.1878, "step": 2790 }, { "epoch": 4.52, "learning_rate": 2.4035591405184183e-05, "loss": 0.2209, "step": 2791 }, { "epoch": 4.53, "learning_rate": 2.4025306848474782e-05, "loss": 0.1923, "step": 2792 }, { "epoch": 4.53, "learning_rate": 2.4015021182295396e-05, "loss": 0.2014, "step": 2793 }, { "epoch": 4.53, "learning_rate": 2.4004734409480996e-05, "loss": 0.2205, "step": 2794 }, { "epoch": 4.53, "learning_rate": 2.3994446532866866e-05, "loss": 0.2567, "step": 2795 }, { "epoch": 4.53, "learning_rate": 2.3984157555288582e-05, "loss": 0.1846, "step": 2796 }, { "epoch": 4.53, "learning_rate": 2.3973867479582036e-05, "loss": 0.2164, "step": 2797 }, { "epoch": 4.53, "learning_rate": 2.396357630858341e-05, "loss": 0.2261, "step": 2798 }, { "epoch": 4.54, "learning_rate": 2.39532840451292e-05, "loss": 0.1675, "step": 2799 }, { "epoch": 4.54, "learning_rate": 2.3942990692056195e-05, "loss": 0.1747, "step": 2800 }, { "epoch": 4.54, "learning_rate": 2.393269625220149e-05, "loss": 0.2508, "step": 2801 }, { "epoch": 4.54, "learning_rate": 2.392240072840247e-05, "loss": 0.3002, "step": 2802 }, { "epoch": 4.54, "learning_rate": 2.3912104123496836e-05, "loss": 0.1692, "step": 2803 }, { "epoch": 4.54, "learning_rate": 2.390180644032257e-05, "loss": 0.153, "step": 2804 }, { "epoch": 4.55, "learning_rate": 2.3891507681717953e-05, "loss": 0.1774, "step": 2805 }, { "epoch": 4.55, "learning_rate": 2.3881207850521578e-05, "loss": 0.1895, "step": 2806 }, { "epoch": 4.55, "learning_rate": 2.387090694957231e-05, "loss": 0.1868, "step": 2807 }, { "epoch": 4.55, "learning_rate": 2.386060498170934e-05, "loss": 0.2325, "step": 2808 }, { "epoch": 4.55, "learning_rate": 2.3850301949772115e-05, "loss": 0.1985, "step": 2809 }, { "epoch": 4.55, "learning_rate": 2.3839997856600405e-05, "loss": 0.1812, "step": 2810 }, { "epoch": 4.56, "learning_rate": 2.3829692705034258e-05, "loss": 0.1608, "step": 2811 }, { "epoch": 4.56, "learning_rate": 2.3819386497914016e-05, "loss": 0.234, "step": 2812 }, { "epoch": 4.56, "learning_rate": 2.3809079238080326e-05, "loss": 0.2288, "step": 2813 }, { "epoch": 4.56, "learning_rate": 2.379877092837411e-05, "loss": 0.1859, "step": 2814 }, { "epoch": 4.56, "learning_rate": 2.3788461571636567e-05, "loss": 0.2253, "step": 2815 }, { "epoch": 4.56, "learning_rate": 2.3778151170709212e-05, "loss": 0.1553, "step": 2816 }, { "epoch": 4.57, "learning_rate": 2.3767839728433833e-05, "loss": 0.187, "step": 2817 }, { "epoch": 4.57, "learning_rate": 2.3757527247652513e-05, "loss": 0.2193, "step": 2818 }, { "epoch": 4.57, "learning_rate": 2.3747213731207613e-05, "loss": 0.3004, "step": 2819 }, { "epoch": 4.57, "learning_rate": 2.373689918194179e-05, "loss": 0.1842, "step": 2820 }, { "epoch": 4.57, "learning_rate": 2.372658360269796e-05, "loss": 0.1899, "step": 2821 }, { "epoch": 4.57, "learning_rate": 2.3716266996319356e-05, "loss": 0.1983, "step": 2822 }, { "epoch": 4.58, "learning_rate": 2.3705949365649473e-05, "loss": 0.2688, "step": 2823 }, { "epoch": 4.58, "learning_rate": 2.3695630713532097e-05, "loss": 0.2332, "step": 2824 }, { "epoch": 4.58, "learning_rate": 2.3685311042811297e-05, "loss": 0.1635, "step": 2825 }, { "epoch": 4.58, "learning_rate": 2.367499035633141e-05, "loss": 0.1568, "step": 2826 }, { "epoch": 4.58, "learning_rate": 2.366466865693707e-05, "loss": 0.1922, "step": 2827 }, { "epoch": 4.58, "learning_rate": 2.3654345947473174e-05, "loss": 0.1819, "step": 2828 }, { "epoch": 4.59, "learning_rate": 2.3644022230784914e-05, "loss": 0.1882, "step": 2829 }, { "epoch": 4.59, "learning_rate": 2.3633697509717745e-05, "loss": 0.1978, "step": 2830 }, { "epoch": 4.59, "learning_rate": 2.362337178711741e-05, "loss": 0.1942, "step": 2831 }, { "epoch": 4.59, "learning_rate": 2.361304506582992e-05, "loss": 0.1908, "step": 2832 }, { "epoch": 4.59, "learning_rate": 2.360271734870156e-05, "loss": 0.3289, "step": 2833 }, { "epoch": 4.59, "learning_rate": 2.35923886385789e-05, "loss": 0.1649, "step": 2834 }, { "epoch": 4.59, "learning_rate": 2.3582058938308768e-05, "loss": 0.2075, "step": 2835 }, { "epoch": 4.6, "learning_rate": 2.357172825073829e-05, "loss": 0.1796, "step": 2836 }, { "epoch": 4.6, "learning_rate": 2.3561396578714838e-05, "loss": 0.2276, "step": 2837 }, { "epoch": 4.6, "learning_rate": 2.3551063925086072e-05, "loss": 0.1951, "step": 2838 }, { "epoch": 4.6, "learning_rate": 2.3540730292699904e-05, "loss": 0.3027, "step": 2839 }, { "epoch": 4.6, "learning_rate": 2.3530395684404533e-05, "loss": 0.2996, "step": 2840 }, { "epoch": 4.6, "learning_rate": 2.3520060103048435e-05, "loss": 0.2645, "step": 2841 }, { "epoch": 4.61, "learning_rate": 2.3509723551480325e-05, "loss": 0.1984, "step": 2842 }, { "epoch": 4.61, "learning_rate": 2.349938603254921e-05, "loss": 0.1865, "step": 2843 }, { "epoch": 4.61, "learning_rate": 2.3489047549104348e-05, "loss": 0.1776, "step": 2844 }, { "epoch": 4.61, "learning_rate": 2.3478708103995285e-05, "loss": 0.1418, "step": 2845 }, { "epoch": 4.61, "learning_rate": 2.3468367700071796e-05, "loss": 0.195, "step": 2846 }, { "epoch": 4.61, "learning_rate": 2.3458026340183952e-05, "loss": 0.2952, "step": 2847 }, { "epoch": 4.62, "learning_rate": 2.344768402718209e-05, "loss": 0.1994, "step": 2848 }, { "epoch": 4.62, "learning_rate": 2.343734076391677e-05, "loss": 0.2132, "step": 2849 }, { "epoch": 4.62, "learning_rate": 2.3426996553238865e-05, "loss": 0.291, "step": 2850 }, { "epoch": 4.62, "learning_rate": 2.341665139799947e-05, "loss": 0.2412, "step": 2851 }, { "epoch": 4.62, "learning_rate": 2.340630530104996e-05, "loss": 0.224, "step": 2852 }, { "epoch": 4.62, "learning_rate": 2.3395958265241963e-05, "loss": 0.174, "step": 2853 }, { "epoch": 4.63, "learning_rate": 2.3385610293427367e-05, "loss": 0.2101, "step": 2854 }, { "epoch": 4.63, "learning_rate": 2.3375261388458318e-05, "loss": 0.1929, "step": 2855 }, { "epoch": 4.63, "learning_rate": 2.336491155318723e-05, "loss": 0.1814, "step": 2856 }, { "epoch": 4.63, "learning_rate": 2.3354560790466748e-05, "loss": 0.2083, "step": 2857 }, { "epoch": 4.63, "learning_rate": 2.3344209103149792e-05, "loss": 0.1874, "step": 2858 }, { "epoch": 4.63, "learning_rate": 2.3333856494089538e-05, "loss": 0.1967, "step": 2859 }, { "epoch": 4.64, "learning_rate": 2.3323502966139407e-05, "loss": 0.2513, "step": 2860 }, { "epoch": 4.64, "learning_rate": 2.3313148522153074e-05, "loss": 0.2594, "step": 2861 }, { "epoch": 4.64, "learning_rate": 2.3302793164984472e-05, "loss": 0.2205, "step": 2862 }, { "epoch": 4.64, "learning_rate": 2.329243689748778e-05, "loss": 0.2931, "step": 2863 }, { "epoch": 4.64, "learning_rate": 2.3282079722517438e-05, "loss": 0.1823, "step": 2864 }, { "epoch": 4.64, "learning_rate": 2.3271721642928114e-05, "loss": 0.2575, "step": 2865 }, { "epoch": 4.65, "learning_rate": 2.3261362661574758e-05, "loss": 0.1935, "step": 2866 }, { "epoch": 4.65, "learning_rate": 2.3251002781312542e-05, "loss": 0.177, "step": 2867 }, { "epoch": 4.65, "learning_rate": 2.3240642004996895e-05, "loss": 0.1852, "step": 2868 }, { "epoch": 4.65, "learning_rate": 2.3230280335483495e-05, "loss": 0.1646, "step": 2869 }, { "epoch": 4.65, "learning_rate": 2.321991777562826e-05, "loss": 0.2714, "step": 2870 }, { "epoch": 4.65, "learning_rate": 2.320955432828736e-05, "loss": 0.2979, "step": 2871 }, { "epoch": 4.65, "learning_rate": 2.3199189996317205e-05, "loss": 0.1771, "step": 2872 }, { "epoch": 4.66, "learning_rate": 2.3188824782574454e-05, "loss": 0.2968, "step": 2873 }, { "epoch": 4.66, "learning_rate": 2.3178458689916e-05, "loss": 0.1528, "step": 2874 }, { "epoch": 4.66, "learning_rate": 2.316809172119899e-05, "loss": 0.2037, "step": 2875 }, { "epoch": 4.66, "learning_rate": 2.3157723879280806e-05, "loss": 0.2717, "step": 2876 }, { "epoch": 4.66, "learning_rate": 2.3147355167019063e-05, "loss": 0.1698, "step": 2877 }, { "epoch": 4.66, "learning_rate": 2.3136985587271627e-05, "loss": 0.1937, "step": 2878 }, { "epoch": 4.67, "learning_rate": 2.3126615142896607e-05, "loss": 0.2106, "step": 2879 }, { "epoch": 4.67, "learning_rate": 2.3116243836752334e-05, "loss": 0.2221, "step": 2880 }, { "epoch": 4.67, "learning_rate": 2.3105871671697394e-05, "loss": 0.211, "step": 2881 }, { "epoch": 4.67, "learning_rate": 2.3095498650590598e-05, "loss": 0.1967, "step": 2882 }, { "epoch": 4.67, "learning_rate": 2.3085124776290994e-05, "loss": 0.2399, "step": 2883 }, { "epoch": 4.67, "learning_rate": 2.3074750051657874e-05, "loss": 0.1997, "step": 2884 }, { "epoch": 4.68, "learning_rate": 2.3064374479550747e-05, "loss": 0.1862, "step": 2885 }, { "epoch": 4.68, "learning_rate": 2.3053998062829375e-05, "loss": 0.1536, "step": 2886 }, { "epoch": 4.68, "learning_rate": 2.3043620804353748e-05, "loss": 0.2601, "step": 2887 }, { "epoch": 4.68, "learning_rate": 2.303324270698408e-05, "loss": 0.2102, "step": 2888 }, { "epoch": 4.68, "learning_rate": 2.3022863773580813e-05, "loss": 0.1923, "step": 2889 }, { "epoch": 4.68, "learning_rate": 2.3012484007004644e-05, "loss": 0.138, "step": 2890 }, { "epoch": 4.69, "learning_rate": 2.3002103410116466e-05, "loss": 0.1832, "step": 2891 }, { "epoch": 4.69, "learning_rate": 2.2991721985777425e-05, "loss": 0.2183, "step": 2892 }, { "epoch": 4.69, "learning_rate": 2.298133973684889e-05, "loss": 0.2276, "step": 2893 }, { "epoch": 4.69, "learning_rate": 2.297095666619245e-05, "loss": 0.1953, "step": 2894 }, { "epoch": 4.69, "learning_rate": 2.2960572776669926e-05, "loss": 0.1778, "step": 2895 }, { "epoch": 4.69, "learning_rate": 2.2950188071143368e-05, "loss": 0.2091, "step": 2896 }, { "epoch": 4.7, "learning_rate": 2.2939802552475036e-05, "loss": 0.2026, "step": 2897 }, { "epoch": 4.7, "learning_rate": 2.2929416223527446e-05, "loss": 0.2137, "step": 2898 }, { "epoch": 4.7, "learning_rate": 2.2919029087163297e-05, "loss": 0.2495, "step": 2899 }, { "epoch": 4.7, "learning_rate": 2.2908641146245546e-05, "loss": 0.2322, "step": 2900 }, { "epoch": 4.7, "learning_rate": 2.2898252403637335e-05, "loss": 0.1986, "step": 2901 }, { "epoch": 4.7, "learning_rate": 2.2887862862202068e-05, "loss": 0.1692, "step": 2902 }, { "epoch": 4.71, "learning_rate": 2.2877472524803338e-05, "loss": 0.1851, "step": 2903 }, { "epoch": 4.71, "learning_rate": 2.2867081394304965e-05, "loss": 0.2154, "step": 2904 }, { "epoch": 4.71, "learning_rate": 2.2856689473571002e-05, "loss": 0.18, "step": 2905 }, { "epoch": 4.71, "learning_rate": 2.2846296765465708e-05, "loss": 0.2191, "step": 2906 }, { "epoch": 4.71, "learning_rate": 2.283590327285355e-05, "loss": 0.2395, "step": 2907 }, { "epoch": 4.71, "learning_rate": 2.2825508998599223e-05, "loss": 0.213, "step": 2908 }, { "epoch": 4.71, "learning_rate": 2.2815113945567643e-05, "loss": 0.2072, "step": 2909 }, { "epoch": 4.72, "learning_rate": 2.2804718116623926e-05, "loss": 0.2428, "step": 2910 }, { "epoch": 4.72, "learning_rate": 2.279432151463341e-05, "loss": 0.2847, "step": 2911 }, { "epoch": 4.72, "learning_rate": 2.2783924142461654e-05, "loss": 0.1972, "step": 2912 }, { "epoch": 4.72, "learning_rate": 2.277352600297441e-05, "loss": 0.2273, "step": 2913 }, { "epoch": 4.72, "learning_rate": 2.2763127099037646e-05, "loss": 0.2219, "step": 2914 }, { "epoch": 4.72, "learning_rate": 2.275272743351756e-05, "loss": 0.2012, "step": 2915 }, { "epoch": 4.73, "learning_rate": 2.274232700928054e-05, "loss": 0.2293, "step": 2916 }, { "epoch": 4.73, "learning_rate": 2.273192582919319e-05, "loss": 0.2127, "step": 2917 }, { "epoch": 4.73, "learning_rate": 2.272152389612233e-05, "loss": 0.2029, "step": 2918 }, { "epoch": 4.73, "learning_rate": 2.2711121212934963e-05, "loss": 0.1838, "step": 2919 }, { "epoch": 4.73, "learning_rate": 2.2700717782498324e-05, "loss": 0.2161, "step": 2920 }, { "epoch": 4.73, "learning_rate": 2.269031360767985e-05, "loss": 0.1695, "step": 2921 }, { "epoch": 4.74, "learning_rate": 2.2679908691347165e-05, "loss": 0.1726, "step": 2922 }, { "epoch": 4.74, "learning_rate": 2.2669503036368124e-05, "loss": 0.2274, "step": 2923 }, { "epoch": 4.74, "learning_rate": 2.2659096645610766e-05, "loss": 0.1935, "step": 2924 }, { "epoch": 4.74, "learning_rate": 2.264868952194334e-05, "loss": 0.2625, "step": 2925 }, { "epoch": 4.74, "learning_rate": 2.2638281668234295e-05, "loss": 0.1958, "step": 2926 }, { "epoch": 4.74, "learning_rate": 2.2627873087352282e-05, "loss": 0.2318, "step": 2927 }, { "epoch": 4.75, "learning_rate": 2.261746378216615e-05, "loss": 0.2042, "step": 2928 }, { "epoch": 4.75, "learning_rate": 2.2607053755544963e-05, "loss": 0.2047, "step": 2929 }, { "epoch": 4.75, "learning_rate": 2.259664301035796e-05, "loss": 0.1885, "step": 2930 }, { "epoch": 4.75, "learning_rate": 2.258623154947458e-05, "loss": 0.2251, "step": 2931 }, { "epoch": 4.75, "learning_rate": 2.257581937576449e-05, "loss": 0.2553, "step": 2932 }, { "epoch": 4.75, "learning_rate": 2.256540649209752e-05, "loss": 0.1924, "step": 2933 }, { "epoch": 4.76, "learning_rate": 2.2554992901343705e-05, "loss": 0.1975, "step": 2934 }, { "epoch": 4.76, "learning_rate": 2.2544578606373283e-05, "loss": 0.2319, "step": 2935 }, { "epoch": 4.76, "learning_rate": 2.253416361005668e-05, "loss": 0.1997, "step": 2936 }, { "epoch": 4.76, "learning_rate": 2.2523747915264512e-05, "loss": 0.2191, "step": 2937 }, { "epoch": 4.76, "learning_rate": 2.2513331524867596e-05, "loss": 0.2575, "step": 2938 }, { "epoch": 4.76, "learning_rate": 2.2502914441736934e-05, "loss": 0.1523, "step": 2939 }, { "epoch": 4.76, "learning_rate": 2.249249666874372e-05, "loss": 0.2898, "step": 2940 }, { "epoch": 4.77, "learning_rate": 2.2482078208759343e-05, "loss": 0.1815, "step": 2941 }, { "epoch": 4.77, "learning_rate": 2.2471659064655375e-05, "loss": 0.206, "step": 2942 }, { "epoch": 4.77, "learning_rate": 2.2461239239303577e-05, "loss": 0.2212, "step": 2943 }, { "epoch": 4.77, "learning_rate": 2.2450818735575905e-05, "loss": 0.2321, "step": 2944 }, { "epoch": 4.77, "learning_rate": 2.244039755634449e-05, "loss": 0.2469, "step": 2945 }, { "epoch": 4.77, "learning_rate": 2.2429975704481658e-05, "loss": 0.1901, "step": 2946 }, { "epoch": 4.78, "learning_rate": 2.241955318285992e-05, "loss": 0.2202, "step": 2947 }, { "epoch": 4.78, "learning_rate": 2.2409129994351978e-05, "loss": 0.2477, "step": 2948 }, { "epoch": 4.78, "learning_rate": 2.2398706141830696e-05, "loss": 0.199, "step": 2949 }, { "epoch": 4.78, "learning_rate": 2.2388281628169146e-05, "loss": 0.2395, "step": 2950 }, { "epoch": 4.78, "learning_rate": 2.2377856456240563e-05, "loss": 0.2305, "step": 2951 }, { "epoch": 4.78, "learning_rate": 2.2367430628918373e-05, "loss": 0.2017, "step": 2952 }, { "epoch": 4.79, "learning_rate": 2.2357004149076183e-05, "loss": 0.1642, "step": 2953 }, { "epoch": 4.79, "learning_rate": 2.234657701958778e-05, "loss": 0.2445, "step": 2954 }, { "epoch": 4.79, "learning_rate": 2.2336149243327126e-05, "loss": 0.2535, "step": 2955 }, { "epoch": 4.79, "learning_rate": 2.232572082316836e-05, "loss": 0.1974, "step": 2956 }, { "epoch": 4.79, "learning_rate": 2.2315291761985803e-05, "loss": 0.1791, "step": 2957 }, { "epoch": 4.79, "learning_rate": 2.2304862062653956e-05, "loss": 0.1434, "step": 2958 }, { "epoch": 4.8, "learning_rate": 2.2294431728047487e-05, "loss": 0.1949, "step": 2959 }, { "epoch": 4.8, "learning_rate": 2.2284000761041246e-05, "loss": 0.1854, "step": 2960 }, { "epoch": 4.8, "learning_rate": 2.227356916451026e-05, "loss": 0.1857, "step": 2961 }, { "epoch": 4.8, "learning_rate": 2.226313694132971e-05, "loss": 0.1747, "step": 2962 }, { "epoch": 4.8, "learning_rate": 2.225270409437498e-05, "loss": 0.1889, "step": 2963 }, { "epoch": 4.8, "learning_rate": 2.224227062652159e-05, "loss": 0.2163, "step": 2964 }, { "epoch": 4.81, "learning_rate": 2.2231836540645272e-05, "loss": 0.2001, "step": 2965 }, { "epoch": 4.81, "learning_rate": 2.22214018396219e-05, "loss": 0.2022, "step": 2966 }, { "epoch": 4.81, "learning_rate": 2.2210966526327522e-05, "loss": 0.1863, "step": 2967 }, { "epoch": 4.81, "learning_rate": 2.2200530603638356e-05, "loss": 0.194, "step": 2968 }, { "epoch": 4.81, "learning_rate": 2.2190094074430794e-05, "loss": 0.2718, "step": 2969 }, { "epoch": 4.81, "learning_rate": 2.2179656941581387e-05, "loss": 0.1734, "step": 2970 }, { "epoch": 4.82, "learning_rate": 2.2169219207966866e-05, "loss": 0.164, "step": 2971 }, { "epoch": 4.82, "learning_rate": 2.2158780876464107e-05, "loss": 0.2594, "step": 2972 }, { "epoch": 4.82, "learning_rate": 2.214834194995017e-05, "loss": 0.2437, "step": 2973 }, { "epoch": 4.82, "learning_rate": 2.2137902431302264e-05, "loss": 0.2184, "step": 2974 }, { "epoch": 4.82, "learning_rate": 2.2127462323397763e-05, "loss": 0.2431, "step": 2975 }, { "epoch": 4.82, "learning_rate": 2.2117021629114215e-05, "loss": 0.2641, "step": 2976 }, { "epoch": 4.82, "learning_rate": 2.210658035132933e-05, "loss": 0.1434, "step": 2977 }, { "epoch": 4.83, "learning_rate": 2.2096138492920965e-05, "loss": 0.2072, "step": 2978 }, { "epoch": 4.83, "learning_rate": 2.2085696056767142e-05, "loss": 0.2627, "step": 2979 }, { "epoch": 4.83, "learning_rate": 2.207525304574604e-05, "loss": 0.3085, "step": 2980 }, { "epoch": 4.83, "learning_rate": 2.2064809462736007e-05, "loss": 0.1946, "step": 2981 }, { "epoch": 4.83, "learning_rate": 2.2054365310615548e-05, "loss": 0.2272, "step": 2982 }, { "epoch": 4.83, "learning_rate": 2.20439205922633e-05, "loss": 0.2547, "step": 2983 }, { "epoch": 4.84, "learning_rate": 2.203347531055809e-05, "loss": 0.2626, "step": 2984 }, { "epoch": 4.84, "learning_rate": 2.2023029468378888e-05, "loss": 0.195, "step": 2985 }, { "epoch": 4.84, "learning_rate": 2.2012583068604803e-05, "loss": 0.1624, "step": 2986 }, { "epoch": 4.84, "learning_rate": 2.200213611411512e-05, "loss": 0.2159, "step": 2987 }, { "epoch": 4.84, "learning_rate": 2.1991688607789262e-05, "loss": 0.1863, "step": 2988 }, { "epoch": 4.84, "learning_rate": 2.198124055250681e-05, "loss": 0.1769, "step": 2989 }, { "epoch": 4.85, "learning_rate": 2.1970791951147505e-05, "loss": 0.1861, "step": 2990 }, { "epoch": 4.85, "learning_rate": 2.196034280659122e-05, "loss": 0.1868, "step": 2991 }, { "epoch": 4.85, "learning_rate": 2.194989312171798e-05, "loss": 0.1723, "step": 2992 }, { "epoch": 4.85, "learning_rate": 2.193944289940798e-05, "loss": 0.2307, "step": 2993 }, { "epoch": 4.85, "learning_rate": 2.1928992142541545e-05, "loss": 0.2058, "step": 2994 }, { "epoch": 4.85, "learning_rate": 2.1918540853999142e-05, "loss": 0.2137, "step": 2995 }, { "epoch": 4.86, "learning_rate": 2.1908089036661403e-05, "loss": 0.2132, "step": 2996 }, { "epoch": 4.86, "learning_rate": 2.1897636693409103e-05, "loss": 0.2738, "step": 2997 }, { "epoch": 4.86, "learning_rate": 2.1887183827123143e-05, "loss": 0.2012, "step": 2998 }, { "epoch": 4.86, "learning_rate": 2.187673044068458e-05, "loss": 0.1798, "step": 2999 }, { "epoch": 4.86, "learning_rate": 2.1866276536974628e-05, "loss": 0.2732, "step": 3000 }, { "epoch": 4.86, "learning_rate": 2.185582211887462e-05, "loss": 0.2816, "step": 3001 }, { "epoch": 4.87, "learning_rate": 2.184536718926604e-05, "loss": 0.1912, "step": 3002 }, { "epoch": 4.87, "learning_rate": 2.1834911751030524e-05, "loss": 0.1933, "step": 3003 }, { "epoch": 4.87, "learning_rate": 2.1824455807049832e-05, "loss": 0.1781, "step": 3004 }, { "epoch": 4.87, "learning_rate": 2.181399936020588e-05, "loss": 0.1916, "step": 3005 }, { "epoch": 4.87, "learning_rate": 2.180354241338069e-05, "loss": 0.2079, "step": 3006 }, { "epoch": 4.87, "learning_rate": 2.179308496945647e-05, "loss": 0.1833, "step": 3007 }, { "epoch": 4.88, "learning_rate": 2.178262703131552e-05, "loss": 0.2351, "step": 3008 }, { "epoch": 4.88, "learning_rate": 2.1772168601840308e-05, "loss": 0.1403, "step": 3009 }, { "epoch": 4.88, "learning_rate": 2.1761709683913423e-05, "loss": 0.2881, "step": 3010 }, { "epoch": 4.88, "learning_rate": 2.1751250280417585e-05, "loss": 0.2267, "step": 3011 }, { "epoch": 4.88, "learning_rate": 2.174079039423566e-05, "loss": 0.1657, "step": 3012 }, { "epoch": 4.88, "learning_rate": 2.1730330028250632e-05, "loss": 0.1979, "step": 3013 }, { "epoch": 4.88, "learning_rate": 2.1719869185345632e-05, "loss": 0.1967, "step": 3014 }, { "epoch": 4.89, "learning_rate": 2.1709407868403915e-05, "loss": 0.2016, "step": 3015 }, { "epoch": 4.89, "learning_rate": 2.1698946080308873e-05, "loss": 0.1738, "step": 3016 }, { "epoch": 4.89, "learning_rate": 2.1688483823944023e-05, "loss": 0.2054, "step": 3017 }, { "epoch": 4.89, "learning_rate": 2.1678021102192996e-05, "loss": 0.1836, "step": 3018 }, { "epoch": 4.89, "learning_rate": 2.1667557917939578e-05, "loss": 0.2164, "step": 3019 }, { "epoch": 4.89, "learning_rate": 2.1657094274067674e-05, "loss": 0.2099, "step": 3020 }, { "epoch": 4.9, "learning_rate": 2.1646630173461305e-05, "loss": 0.199, "step": 3021 }, { "epoch": 4.9, "learning_rate": 2.163616561900463e-05, "loss": 0.2004, "step": 3022 }, { "epoch": 4.9, "learning_rate": 2.162570061358192e-05, "loss": 0.209, "step": 3023 }, { "epoch": 4.9, "learning_rate": 2.1615235160077594e-05, "loss": 0.172, "step": 3024 }, { "epoch": 4.9, "learning_rate": 2.160476926137616e-05, "loss": 0.223, "step": 3025 }, { "epoch": 4.9, "learning_rate": 2.1594302920362276e-05, "loss": 0.2344, "step": 3026 }, { "epoch": 4.91, "learning_rate": 2.158383613992072e-05, "loss": 0.2115, "step": 3027 }, { "epoch": 4.91, "learning_rate": 2.1573368922936378e-05, "loss": 0.1762, "step": 3028 }, { "epoch": 4.91, "learning_rate": 2.156290127229427e-05, "loss": 0.2227, "step": 3029 }, { "epoch": 4.91, "learning_rate": 2.1552433190879512e-05, "loss": 0.2148, "step": 3030 }, { "epoch": 4.91, "learning_rate": 2.1541964681577373e-05, "loss": 0.1557, "step": 3031 }, { "epoch": 4.91, "learning_rate": 2.153149574727322e-05, "loss": 0.2446, "step": 3032 }, { "epoch": 4.92, "learning_rate": 2.1521026390852532e-05, "loss": 0.1864, "step": 3033 }, { "epoch": 4.92, "learning_rate": 2.1510556615200917e-05, "loss": 0.1835, "step": 3034 }, { "epoch": 4.92, "learning_rate": 2.150008642320409e-05, "loss": 0.163, "step": 3035 }, { "epoch": 4.92, "learning_rate": 2.1489615817747884e-05, "loss": 0.2982, "step": 3036 }, { "epoch": 4.92, "learning_rate": 2.147914480171825e-05, "loss": 0.1821, "step": 3037 }, { "epoch": 4.92, "learning_rate": 2.1468673378001242e-05, "loss": 0.143, "step": 3038 }, { "epoch": 4.93, "learning_rate": 2.1458201549483043e-05, "loss": 0.2037, "step": 3039 }, { "epoch": 4.93, "learning_rate": 2.1447729319049926e-05, "loss": 0.2049, "step": 3040 }, { "epoch": 4.93, "learning_rate": 2.1437256689588298e-05, "loss": 0.2122, "step": 3041 }, { "epoch": 4.93, "learning_rate": 2.1426783663984648e-05, "loss": 0.2829, "step": 3042 }, { "epoch": 4.93, "learning_rate": 2.1416310245125603e-05, "loss": 0.263, "step": 3043 }, { "epoch": 4.93, "learning_rate": 2.1405836435897882e-05, "loss": 0.1774, "step": 3044 }, { "epoch": 4.94, "learning_rate": 2.1395362239188312e-05, "loss": 0.1772, "step": 3045 }, { "epoch": 4.94, "learning_rate": 2.1384887657883836e-05, "loss": 0.1547, "step": 3046 }, { "epoch": 4.94, "learning_rate": 2.1374412694871497e-05, "loss": 0.2003, "step": 3047 }, { "epoch": 4.94, "learning_rate": 2.1363937353038428e-05, "loss": 0.2276, "step": 3048 }, { "epoch": 4.94, "learning_rate": 2.13534616352719e-05, "loss": 0.2101, "step": 3049 }, { "epoch": 4.94, "learning_rate": 2.1342985544459258e-05, "loss": 0.2474, "step": 3050 }, { "epoch": 4.94, "learning_rate": 2.1332509083487966e-05, "loss": 0.1872, "step": 3051 }, { "epoch": 4.95, "learning_rate": 2.1322032255245584e-05, "loss": 0.1636, "step": 3052 }, { "epoch": 4.95, "learning_rate": 2.1311555062619778e-05, "loss": 0.1735, "step": 3053 }, { "epoch": 4.95, "learning_rate": 2.1301077508498305e-05, "loss": 0.2532, "step": 3054 }, { "epoch": 4.95, "learning_rate": 2.129059959576903e-05, "loss": 0.2439, "step": 3055 }, { "epoch": 4.95, "learning_rate": 2.1280121327319908e-05, "loss": 0.2886, "step": 3056 }, { "epoch": 4.95, "learning_rate": 2.126964270603901e-05, "loss": 0.1988, "step": 3057 }, { "epoch": 4.96, "learning_rate": 2.1259163734814482e-05, "loss": 0.2248, "step": 3058 }, { "epoch": 4.96, "learning_rate": 2.1248684416534586e-05, "loss": 0.2285, "step": 3059 }, { "epoch": 4.96, "learning_rate": 2.1238204754087656e-05, "loss": 0.2159, "step": 3060 }, { "epoch": 4.96, "learning_rate": 2.122772475036215e-05, "loss": 0.284, "step": 3061 }, { "epoch": 4.96, "learning_rate": 2.1217244408246605e-05, "loss": 0.2331, "step": 3062 }, { "epoch": 4.96, "learning_rate": 2.1206763730629638e-05, "loss": 0.1997, "step": 3063 }, { "epoch": 4.97, "learning_rate": 2.1196282720399983e-05, "loss": 0.2486, "step": 3064 }, { "epoch": 4.97, "learning_rate": 2.1185801380446453e-05, "loss": 0.1935, "step": 3065 }, { "epoch": 4.97, "learning_rate": 2.117531971365796e-05, "loss": 0.2204, "step": 3066 }, { "epoch": 4.97, "learning_rate": 2.1164837722923487e-05, "loss": 0.1758, "step": 3067 }, { "epoch": 4.97, "learning_rate": 2.1154355411132122e-05, "loss": 0.2509, "step": 3068 }, { "epoch": 4.97, "learning_rate": 2.114387278117305e-05, "loss": 0.2483, "step": 3069 }, { "epoch": 4.98, "learning_rate": 2.113338983593552e-05, "loss": 0.2033, "step": 3070 }, { "epoch": 4.98, "learning_rate": 2.112290657830889e-05, "loss": 0.1651, "step": 3071 }, { "epoch": 4.98, "learning_rate": 2.1112423011182584e-05, "loss": 0.1816, "step": 3072 }, { "epoch": 4.98, "learning_rate": 2.1101939137446124e-05, "loss": 0.2174, "step": 3073 }, { "epoch": 4.98, "learning_rate": 2.109145495998912e-05, "loss": 0.2796, "step": 3074 }, { "epoch": 4.98, "learning_rate": 2.108097048170126e-05, "loss": 0.1547, "step": 3075 }, { "epoch": 4.99, "learning_rate": 2.1070485705472305e-05, "loss": 0.2211, "step": 3076 }, { "epoch": 4.99, "learning_rate": 2.1060000634192116e-05, "loss": 0.1903, "step": 3077 }, { "epoch": 4.99, "learning_rate": 2.1049515270750632e-05, "loss": 0.267, "step": 3078 }, { "epoch": 4.99, "learning_rate": 2.1039029618037853e-05, "loss": 0.3005, "step": 3079 }, { "epoch": 4.99, "learning_rate": 2.102854367894388e-05, "loss": 0.1883, "step": 3080 }, { "epoch": 4.99, "learning_rate": 2.10180574563589e-05, "loss": 0.2472, "step": 3081 }, { "epoch": 5.0, "learning_rate": 2.100757095317314e-05, "loss": 0.2067, "step": 3082 }, { "epoch": 5.0, "learning_rate": 2.099708417227695e-05, "loss": 0.1635, "step": 3083 }, { "epoch": 5.0, "learning_rate": 2.0986597116560717e-05, "loss": 0.2443, "step": 3084 }, { "epoch": 5.0, "learning_rate": 2.097610978891494e-05, "loss": 0.1749, "step": 3085 }, { "epoch": 5.0, "learning_rate": 2.0965622192230158e-05, "loss": 0.139, "step": 3086 }, { "epoch": 5.0, "learning_rate": 2.0955134329397017e-05, "loss": 0.169, "step": 3087 }, { "epoch": 5.0, "learning_rate": 2.0944646203306212e-05, "loss": 0.1582, "step": 3088 }, { "epoch": 5.01, "learning_rate": 2.0934157816848524e-05, "loss": 0.2129, "step": 3089 }, { "epoch": 5.01, "learning_rate": 2.0923669172914796e-05, "loss": 0.2076, "step": 3090 }, { "epoch": 5.01, "learning_rate": 2.0913180274395944e-05, "loss": 0.1766, "step": 3091 }, { "epoch": 5.01, "learning_rate": 2.0902691124182966e-05, "loss": 0.1817, "step": 3092 }, { "epoch": 5.01, "learning_rate": 2.0892201725166918e-05, "loss": 0.2321, "step": 3093 }, { "epoch": 5.01, "learning_rate": 2.088171208023892e-05, "loss": 0.198, "step": 3094 }, { "epoch": 5.02, "learning_rate": 2.0871222192290182e-05, "loss": 0.1578, "step": 3095 }, { "epoch": 5.02, "learning_rate": 2.0860732064211947e-05, "loss": 0.1431, "step": 3096 }, { "epoch": 5.02, "learning_rate": 2.0850241698895556e-05, "loss": 0.1881, "step": 3097 }, { "epoch": 5.02, "learning_rate": 2.0839751099232392e-05, "loss": 0.1578, "step": 3098 }, { "epoch": 5.02, "learning_rate": 2.0829260268113925e-05, "loss": 0.2114, "step": 3099 }, { "epoch": 5.02, "learning_rate": 2.081876920843167e-05, "loss": 0.1819, "step": 3100 }, { "epoch": 5.03, "learning_rate": 2.0808277923077206e-05, "loss": 0.173, "step": 3101 }, { "epoch": 5.03, "learning_rate": 2.0797786414942197e-05, "loss": 0.1774, "step": 3102 }, { "epoch": 5.03, "learning_rate": 2.0787294686918337e-05, "loss": 0.1386, "step": 3103 }, { "epoch": 5.03, "learning_rate": 2.0776802741897395e-05, "loss": 0.1391, "step": 3104 }, { "epoch": 5.03, "learning_rate": 2.0766310582771206e-05, "loss": 0.2495, "step": 3105 }, { "epoch": 5.03, "learning_rate": 2.0755818212431653e-05, "loss": 0.1842, "step": 3106 }, { "epoch": 5.04, "learning_rate": 2.0745325633770693e-05, "loss": 0.2916, "step": 3107 }, { "epoch": 5.04, "learning_rate": 2.0734832849680316e-05, "loss": 0.1919, "step": 3108 }, { "epoch": 5.04, "learning_rate": 2.0724339863052584e-05, "loss": 0.2079, "step": 3109 }, { "epoch": 5.04, "learning_rate": 2.0713846676779613e-05, "loss": 0.2068, "step": 3110 }, { "epoch": 5.04, "learning_rate": 2.0703353293753578e-05, "loss": 0.1731, "step": 3111 }, { "epoch": 5.04, "learning_rate": 2.069285971686671e-05, "loss": 0.1417, "step": 3112 }, { "epoch": 5.05, "learning_rate": 2.068236594901127e-05, "loss": 0.2054, "step": 3113 }, { "epoch": 5.05, "learning_rate": 2.0671871993079606e-05, "loss": 0.1304, "step": 3114 }, { "epoch": 5.05, "learning_rate": 2.0661377851964087e-05, "loss": 0.1352, "step": 3115 }, { "epoch": 5.05, "learning_rate": 2.065088352855716e-05, "loss": 0.1518, "step": 3116 }, { "epoch": 5.05, "learning_rate": 2.0640389025751306e-05, "loss": 0.1688, "step": 3117 }, { "epoch": 5.05, "learning_rate": 2.062989434643905e-05, "loss": 0.1844, "step": 3118 }, { "epoch": 5.06, "learning_rate": 2.0619399493512988e-05, "loss": 0.1753, "step": 3119 }, { "epoch": 5.06, "learning_rate": 2.0608904469865736e-05, "loss": 0.1619, "step": 3120 }, { "epoch": 5.06, "learning_rate": 2.0598409278389986e-05, "loss": 0.1543, "step": 3121 }, { "epoch": 5.06, "learning_rate": 2.0587913921978445e-05, "loss": 0.1388, "step": 3122 }, { "epoch": 5.06, "learning_rate": 2.0577418403523897e-05, "loss": 0.1235, "step": 3123 }, { "epoch": 5.06, "learning_rate": 2.0566922725919147e-05, "loss": 0.1717, "step": 3124 }, { "epoch": 5.06, "learning_rate": 2.0556426892057054e-05, "loss": 0.1919, "step": 3125 }, { "epoch": 5.07, "learning_rate": 2.054593090483052e-05, "loss": 0.2055, "step": 3126 }, { "epoch": 5.07, "learning_rate": 2.0535434767132495e-05, "loss": 0.2074, "step": 3127 }, { "epoch": 5.07, "learning_rate": 2.0524938481855944e-05, "loss": 0.1945, "step": 3128 }, { "epoch": 5.07, "learning_rate": 2.051444205189391e-05, "loss": 0.1967, "step": 3129 }, { "epoch": 5.07, "learning_rate": 2.050394548013945e-05, "loss": 0.1727, "step": 3130 }, { "epoch": 5.07, "learning_rate": 2.0493448769485672e-05, "loss": 0.1904, "step": 3131 }, { "epoch": 5.08, "learning_rate": 2.0482951922825712e-05, "loss": 0.2071, "step": 3132 }, { "epoch": 5.08, "learning_rate": 2.0472454943052763e-05, "loss": 0.1643, "step": 3133 }, { "epoch": 5.08, "learning_rate": 2.0461957833060025e-05, "loss": 0.1646, "step": 3134 }, { "epoch": 5.08, "learning_rate": 2.045146059574076e-05, "loss": 0.1745, "step": 3135 }, { "epoch": 5.08, "learning_rate": 2.044096323398825e-05, "loss": 0.1478, "step": 3136 }, { "epoch": 5.08, "learning_rate": 2.0430465750695822e-05, "loss": 0.1491, "step": 3137 }, { "epoch": 5.09, "learning_rate": 2.041996814875683e-05, "loss": 0.1879, "step": 3138 }, { "epoch": 5.09, "learning_rate": 2.040947043106466e-05, "loss": 0.2424, "step": 3139 }, { "epoch": 5.09, "learning_rate": 2.0398972600512735e-05, "loss": 0.1842, "step": 3140 }, { "epoch": 5.09, "learning_rate": 2.0388474659994498e-05, "loss": 0.1816, "step": 3141 }, { "epoch": 5.09, "learning_rate": 2.0377976612403443e-05, "loss": 0.167, "step": 3142 }, { "epoch": 5.09, "learning_rate": 2.0367478460633072e-05, "loss": 0.2141, "step": 3143 }, { "epoch": 5.1, "learning_rate": 2.0356980207576923e-05, "loss": 0.208, "step": 3144 }, { "epoch": 5.1, "learning_rate": 2.034648185612857e-05, "loss": 0.1557, "step": 3145 }, { "epoch": 5.1, "learning_rate": 2.0335983409181606e-05, "loss": 0.1202, "step": 3146 }, { "epoch": 5.1, "learning_rate": 2.0325484869629645e-05, "loss": 0.1598, "step": 3147 }, { "epoch": 5.1, "learning_rate": 2.0314986240366337e-05, "loss": 0.1697, "step": 3148 }, { "epoch": 5.1, "learning_rate": 2.030448752428536e-05, "loss": 0.2163, "step": 3149 }, { "epoch": 5.11, "learning_rate": 2.0293988724280404e-05, "loss": 0.1783, "step": 3150 }, { "epoch": 5.11, "learning_rate": 2.0283489843245182e-05, "loss": 0.2213, "step": 3151 }, { "epoch": 5.11, "learning_rate": 2.0272990884073444e-05, "loss": 0.2173, "step": 3152 }, { "epoch": 5.11, "learning_rate": 2.0262491849658942e-05, "loss": 0.1791, "step": 3153 }, { "epoch": 5.11, "learning_rate": 2.025199274289547e-05, "loss": 0.2093, "step": 3154 }, { "epoch": 5.11, "learning_rate": 2.024149356667682e-05, "loss": 0.1286, "step": 3155 }, { "epoch": 5.12, "learning_rate": 2.0230994323896817e-05, "loss": 0.1804, "step": 3156 }, { "epoch": 5.12, "learning_rate": 2.0220495017449306e-05, "loss": 0.147, "step": 3157 }, { "epoch": 5.12, "learning_rate": 2.0209995650228146e-05, "loss": 0.1689, "step": 3158 }, { "epoch": 5.12, "learning_rate": 2.0199496225127196e-05, "loss": 0.126, "step": 3159 }, { "epoch": 5.12, "learning_rate": 2.0188996745040367e-05, "loss": 0.209, "step": 3160 }, { "epoch": 5.12, "learning_rate": 2.017849721286155e-05, "loss": 0.1539, "step": 3161 }, { "epoch": 5.12, "learning_rate": 2.016799763148467e-05, "loss": 0.1671, "step": 3162 }, { "epoch": 5.13, "learning_rate": 2.0157498003803665e-05, "loss": 0.1743, "step": 3163 }, { "epoch": 5.13, "learning_rate": 2.014699833271247e-05, "loss": 0.2318, "step": 3164 }, { "epoch": 5.13, "learning_rate": 2.013649862110506e-05, "loss": 0.1374, "step": 3165 }, { "epoch": 5.13, "learning_rate": 2.0125998871875385e-05, "loss": 0.1595, "step": 3166 }, { "epoch": 5.13, "learning_rate": 2.0115499087917434e-05, "loss": 0.1801, "step": 3167 }, { "epoch": 5.13, "learning_rate": 2.0104999272125196e-05, "loss": 0.1648, "step": 3168 }, { "epoch": 5.14, "learning_rate": 2.009449942739268e-05, "loss": 0.2613, "step": 3169 }, { "epoch": 5.14, "learning_rate": 2.0083999556613874e-05, "loss": 0.1943, "step": 3170 }, { "epoch": 5.14, "learning_rate": 2.0073499662682797e-05, "loss": 0.1684, "step": 3171 }, { "epoch": 5.14, "learning_rate": 2.0062999748493476e-05, "loss": 0.1767, "step": 3172 }, { "epoch": 5.14, "learning_rate": 2.005249981693993e-05, "loss": 0.193, "step": 3173 }, { "epoch": 5.14, "learning_rate": 2.0041999870916186e-05, "loss": 0.1523, "step": 3174 }, { "epoch": 5.15, "learning_rate": 2.0031499913316284e-05, "loss": 0.1937, "step": 3175 }, { "epoch": 5.15, "learning_rate": 2.0020999947034258e-05, "loss": 0.2013, "step": 3176 }, { "epoch": 5.15, "learning_rate": 2.0010499974964153e-05, "loss": 0.1646, "step": 3177 }, { "epoch": 5.15, "learning_rate": 2e-05, "loss": 0.1913, "step": 3178 }, { "epoch": 5.15, "learning_rate": 1.9989500025035853e-05, "loss": 0.1395, "step": 3179 }, { "epoch": 5.15, "learning_rate": 1.9979000052965742e-05, "loss": 0.1818, "step": 3180 }, { "epoch": 5.16, "learning_rate": 1.996850008668372e-05, "loss": 0.236, "step": 3181 }, { "epoch": 5.16, "learning_rate": 1.995800012908382e-05, "loss": 0.1848, "step": 3182 }, { "epoch": 5.16, "learning_rate": 1.9947500183060078e-05, "loss": 0.1587, "step": 3183 }, { "epoch": 5.16, "learning_rate": 1.9937000251506534e-05, "loss": 0.1648, "step": 3184 }, { "epoch": 5.16, "learning_rate": 1.9926500337317203e-05, "loss": 0.1405, "step": 3185 }, { "epoch": 5.16, "learning_rate": 1.9916000443386132e-05, "loss": 0.199, "step": 3186 }, { "epoch": 5.17, "learning_rate": 1.9905500572607328e-05, "loss": 0.1414, "step": 3187 }, { "epoch": 5.17, "learning_rate": 1.9895000727874804e-05, "loss": 0.1619, "step": 3188 }, { "epoch": 5.17, "learning_rate": 1.9884500912082573e-05, "loss": 0.1931, "step": 3189 }, { "epoch": 5.17, "learning_rate": 1.987400112812463e-05, "loss": 0.2846, "step": 3190 }, { "epoch": 5.17, "learning_rate": 1.9863501378894947e-05, "loss": 0.1762, "step": 3191 }, { "epoch": 5.17, "learning_rate": 1.9853001667287535e-05, "loss": 0.1885, "step": 3192 }, { "epoch": 5.18, "learning_rate": 1.9842501996196338e-05, "loss": 0.1356, "step": 3193 }, { "epoch": 5.18, "learning_rate": 1.9832002368515336e-05, "loss": 0.1733, "step": 3194 }, { "epoch": 5.18, "learning_rate": 1.9821502787138457e-05, "loss": 0.1736, "step": 3195 }, { "epoch": 5.18, "learning_rate": 1.9811003254959637e-05, "loss": 0.187, "step": 3196 }, { "epoch": 5.18, "learning_rate": 1.9800503774872807e-05, "loss": 0.2282, "step": 3197 }, { "epoch": 5.18, "learning_rate": 1.9790004349771864e-05, "loss": 0.1391, "step": 3198 }, { "epoch": 5.18, "learning_rate": 1.9779504982550697e-05, "loss": 0.1806, "step": 3199 }, { "epoch": 5.19, "learning_rate": 1.976900567610319e-05, "loss": 0.2889, "step": 3200 }, { "epoch": 5.19, "learning_rate": 1.975850643332319e-05, "loss": 0.1556, "step": 3201 }, { "epoch": 5.19, "learning_rate": 1.974800725710454e-05, "loss": 0.1369, "step": 3202 }, { "epoch": 5.19, "learning_rate": 1.9737508150341064e-05, "loss": 0.1494, "step": 3203 }, { "epoch": 5.19, "learning_rate": 1.972700911592656e-05, "loss": 0.192, "step": 3204 }, { "epoch": 5.19, "learning_rate": 1.971651015675482e-05, "loss": 0.1646, "step": 3205 }, { "epoch": 5.2, "learning_rate": 1.9706011275719603e-05, "loss": 0.1796, "step": 3206 }, { "epoch": 5.2, "learning_rate": 1.9695512475714643e-05, "loss": 0.1568, "step": 3207 }, { "epoch": 5.2, "learning_rate": 1.9685013759633666e-05, "loss": 0.1441, "step": 3208 }, { "epoch": 5.2, "learning_rate": 1.9674515130370365e-05, "loss": 0.2174, "step": 3209 }, { "epoch": 5.2, "learning_rate": 1.96640165908184e-05, "loss": 0.1809, "step": 3210 }, { "epoch": 5.2, "learning_rate": 1.9653518143871436e-05, "loss": 0.2147, "step": 3211 }, { "epoch": 5.21, "learning_rate": 1.964301979242308e-05, "loss": 0.1678, "step": 3212 }, { "epoch": 5.21, "learning_rate": 1.9632521539366935e-05, "loss": 0.1359, "step": 3213 }, { "epoch": 5.21, "learning_rate": 1.9622023387596563e-05, "loss": 0.1638, "step": 3214 }, { "epoch": 5.21, "learning_rate": 1.96115253400055e-05, "loss": 0.1575, "step": 3215 }, { "epoch": 5.21, "learning_rate": 1.9601027399487272e-05, "loss": 0.1665, "step": 3216 }, { "epoch": 5.21, "learning_rate": 1.9590529568935345e-05, "loss": 0.1633, "step": 3217 }, { "epoch": 5.22, "learning_rate": 1.9580031851243176e-05, "loss": 0.1211, "step": 3218 }, { "epoch": 5.22, "learning_rate": 1.9569534249304184e-05, "loss": 0.1296, "step": 3219 }, { "epoch": 5.22, "learning_rate": 1.9559036766011758e-05, "loss": 0.1467, "step": 3220 }, { "epoch": 5.22, "learning_rate": 1.9548539404259245e-05, "loss": 0.1731, "step": 3221 }, { "epoch": 5.22, "learning_rate": 1.9538042166939982e-05, "loss": 0.1965, "step": 3222 }, { "epoch": 5.22, "learning_rate": 1.9527545056947243e-05, "loss": 0.1936, "step": 3223 }, { "epoch": 5.23, "learning_rate": 1.951704807717429e-05, "loss": 0.1902, "step": 3224 }, { "epoch": 5.23, "learning_rate": 1.9506551230514338e-05, "loss": 0.1865, "step": 3225 }, { "epoch": 5.23, "learning_rate": 1.949605451986055e-05, "loss": 0.1662, "step": 3226 }, { "epoch": 5.23, "learning_rate": 1.9485557948106097e-05, "loss": 0.1792, "step": 3227 }, { "epoch": 5.23, "learning_rate": 1.9475061518144066e-05, "loss": 0.1687, "step": 3228 }, { "epoch": 5.23, "learning_rate": 1.9464565232867512e-05, "loss": 0.1934, "step": 3229 }, { "epoch": 5.24, "learning_rate": 1.9454069095169484e-05, "loss": 0.2017, "step": 3230 }, { "epoch": 5.24, "learning_rate": 1.944357310794295e-05, "loss": 0.202, "step": 3231 }, { "epoch": 5.24, "learning_rate": 1.943307727408086e-05, "loss": 0.1999, "step": 3232 }, { "epoch": 5.24, "learning_rate": 1.9422581596476113e-05, "loss": 0.1865, "step": 3233 }, { "epoch": 5.24, "learning_rate": 1.941208607802156e-05, "loss": 0.1545, "step": 3234 }, { "epoch": 5.24, "learning_rate": 1.940159072161002e-05, "loss": 0.181, "step": 3235 }, { "epoch": 5.24, "learning_rate": 1.939109553013427e-05, "loss": 0.1532, "step": 3236 }, { "epoch": 5.25, "learning_rate": 1.938060050648702e-05, "loss": 0.1252, "step": 3237 }, { "epoch": 5.25, "learning_rate": 1.9370105653560956e-05, "loss": 0.1552, "step": 3238 }, { "epoch": 5.25, "learning_rate": 1.9359610974248698e-05, "loss": 0.2119, "step": 3239 }, { "epoch": 5.25, "learning_rate": 1.9349116471442842e-05, "loss": 0.1928, "step": 3240 }, { "epoch": 5.25, "learning_rate": 1.9338622148035916e-05, "loss": 0.163, "step": 3241 }, { "epoch": 5.25, "learning_rate": 1.93281280069204e-05, "loss": 0.1453, "step": 3242 }, { "epoch": 5.26, "learning_rate": 1.931763405098874e-05, "loss": 0.1748, "step": 3243 }, { "epoch": 5.26, "learning_rate": 1.9307140283133305e-05, "loss": 0.1774, "step": 3244 }, { "epoch": 5.26, "learning_rate": 1.9296646706246425e-05, "loss": 0.1685, "step": 3245 }, { "epoch": 5.26, "learning_rate": 1.9286153323220393e-05, "loss": 0.1482, "step": 3246 }, { "epoch": 5.26, "learning_rate": 1.927566013694743e-05, "loss": 0.18, "step": 3247 }, { "epoch": 5.26, "learning_rate": 1.926516715031969e-05, "loss": 0.1778, "step": 3248 }, { "epoch": 5.27, "learning_rate": 1.9254674366229317e-05, "loss": 0.1683, "step": 3249 }, { "epoch": 5.27, "learning_rate": 1.9244181787568347e-05, "loss": 0.1706, "step": 3250 }, { "epoch": 5.27, "learning_rate": 1.92336894172288e-05, "loss": 0.2196, "step": 3251 }, { "epoch": 5.27, "learning_rate": 1.9223197258102612e-05, "loss": 0.2021, "step": 3252 }, { "epoch": 5.27, "learning_rate": 1.9212705313081667e-05, "loss": 0.1451, "step": 3253 }, { "epoch": 5.27, "learning_rate": 1.920221358505781e-05, "loss": 0.1878, "step": 3254 }, { "epoch": 5.28, "learning_rate": 1.9191722076922797e-05, "loss": 0.1451, "step": 3255 }, { "epoch": 5.28, "learning_rate": 1.9181230791568336e-05, "loss": 0.1589, "step": 3256 }, { "epoch": 5.28, "learning_rate": 1.9170739731886085e-05, "loss": 0.2056, "step": 3257 }, { "epoch": 5.28, "learning_rate": 1.9160248900767607e-05, "loss": 0.1332, "step": 3258 }, { "epoch": 5.28, "learning_rate": 1.914975830110445e-05, "loss": 0.1294, "step": 3259 }, { "epoch": 5.28, "learning_rate": 1.913926793578806e-05, "loss": 0.1537, "step": 3260 }, { "epoch": 5.29, "learning_rate": 1.9128777807709825e-05, "loss": 0.1955, "step": 3261 }, { "epoch": 5.29, "learning_rate": 1.9118287919761084e-05, "loss": 0.145, "step": 3262 }, { "epoch": 5.29, "learning_rate": 1.9107798274833092e-05, "loss": 0.159, "step": 3263 }, { "epoch": 5.29, "learning_rate": 1.9097308875817037e-05, "loss": 0.1417, "step": 3264 }, { "epoch": 5.29, "learning_rate": 1.908681972560406e-05, "loss": 0.2309, "step": 3265 }, { "epoch": 5.29, "learning_rate": 1.9076330827085214e-05, "loss": 0.1887, "step": 3266 }, { "epoch": 5.29, "learning_rate": 1.9065842183151482e-05, "loss": 0.1434, "step": 3267 }, { "epoch": 5.3, "learning_rate": 1.9055353796693795e-05, "loss": 0.1705, "step": 3268 }, { "epoch": 5.3, "learning_rate": 1.9044865670602983e-05, "loss": 0.1719, "step": 3269 }, { "epoch": 5.3, "learning_rate": 1.9034377807769845e-05, "loss": 0.1306, "step": 3270 }, { "epoch": 5.3, "learning_rate": 1.902389021108507e-05, "loss": 0.1489, "step": 3271 }, { "epoch": 5.3, "learning_rate": 1.9013402883439286e-05, "loss": 0.1351, "step": 3272 }, { "epoch": 5.3, "learning_rate": 1.9002915827723058e-05, "loss": 0.2302, "step": 3273 }, { "epoch": 5.31, "learning_rate": 1.8992429046826865e-05, "loss": 0.1912, "step": 3274 }, { "epoch": 5.31, "learning_rate": 1.898194254364111e-05, "loss": 0.1111, "step": 3275 }, { "epoch": 5.31, "learning_rate": 1.897145632105612e-05, "loss": 0.1483, "step": 3276 }, { "epoch": 5.31, "learning_rate": 1.8960970381962147e-05, "loss": 0.1463, "step": 3277 }, { "epoch": 5.31, "learning_rate": 1.8950484729249374e-05, "loss": 0.1873, "step": 3278 }, { "epoch": 5.31, "learning_rate": 1.8939999365807887e-05, "loss": 0.1792, "step": 3279 }, { "epoch": 5.32, "learning_rate": 1.8929514294527698e-05, "loss": 0.1453, "step": 3280 }, { "epoch": 5.32, "learning_rate": 1.8919029518298748e-05, "loss": 0.2352, "step": 3281 }, { "epoch": 5.32, "learning_rate": 1.8908545040010885e-05, "loss": 0.209, "step": 3282 }, { "epoch": 5.32, "learning_rate": 1.889806086255388e-05, "loss": 0.172, "step": 3283 }, { "epoch": 5.32, "learning_rate": 1.8887576988817423e-05, "loss": 0.2103, "step": 3284 }, { "epoch": 5.32, "learning_rate": 1.887709342169112e-05, "loss": 0.1262, "step": 3285 }, { "epoch": 5.33, "learning_rate": 1.8866610164064485e-05, "loss": 0.1953, "step": 3286 }, { "epoch": 5.33, "learning_rate": 1.8856127218826958e-05, "loss": 0.1539, "step": 3287 }, { "epoch": 5.33, "learning_rate": 1.8845644588867878e-05, "loss": 0.1878, "step": 3288 }, { "epoch": 5.33, "learning_rate": 1.883516227707652e-05, "loss": 0.1277, "step": 3289 }, { "epoch": 5.33, "learning_rate": 1.882468028634205e-05, "loss": 0.1818, "step": 3290 }, { "epoch": 5.33, "learning_rate": 1.881419861955355e-05, "loss": 0.181, "step": 3291 }, { "epoch": 5.34, "learning_rate": 1.8803717279600023e-05, "loss": 0.1662, "step": 3292 }, { "epoch": 5.34, "learning_rate": 1.8793236269370375e-05, "loss": 0.1822, "step": 3293 }, { "epoch": 5.34, "learning_rate": 1.8782755591753405e-05, "loss": 0.1372, "step": 3294 }, { "epoch": 5.34, "learning_rate": 1.8772275249637853e-05, "loss": 0.1934, "step": 3295 }, { "epoch": 5.34, "learning_rate": 1.8761795245912344e-05, "loss": 0.1504, "step": 3296 }, { "epoch": 5.34, "learning_rate": 1.875131558346542e-05, "loss": 0.1428, "step": 3297 }, { "epoch": 5.35, "learning_rate": 1.874083626518552e-05, "loss": 0.1921, "step": 3298 }, { "epoch": 5.35, "learning_rate": 1.8730357293960994e-05, "loss": 0.2687, "step": 3299 }, { "epoch": 5.35, "learning_rate": 1.8719878672680095e-05, "loss": 0.186, "step": 3300 }, { "epoch": 5.35, "learning_rate": 1.870940040423098e-05, "loss": 0.1885, "step": 3301 }, { "epoch": 5.35, "learning_rate": 1.8698922491501698e-05, "loss": 0.2655, "step": 3302 }, { "epoch": 5.35, "learning_rate": 1.8688444937380225e-05, "loss": 0.2076, "step": 3303 }, { "epoch": 5.35, "learning_rate": 1.867796774475442e-05, "loss": 0.1693, "step": 3304 }, { "epoch": 5.36, "learning_rate": 1.8667490916512037e-05, "loss": 0.1747, "step": 3305 }, { "epoch": 5.36, "learning_rate": 1.865701445554075e-05, "loss": 0.1872, "step": 3306 }, { "epoch": 5.36, "learning_rate": 1.8646538364728104e-05, "loss": 0.1413, "step": 3307 }, { "epoch": 5.36, "learning_rate": 1.863606264696158e-05, "loss": 0.2184, "step": 3308 }, { "epoch": 5.36, "learning_rate": 1.8625587305128516e-05, "loss": 0.1831, "step": 3309 }, { "epoch": 5.36, "learning_rate": 1.861511234211617e-05, "loss": 0.1968, "step": 3310 }, { "epoch": 5.37, "learning_rate": 1.8604637760811694e-05, "loss": 0.1616, "step": 3311 }, { "epoch": 5.37, "learning_rate": 1.8594163564102128e-05, "loss": 0.1798, "step": 3312 }, { "epoch": 5.37, "learning_rate": 1.85836897548744e-05, "loss": 0.1613, "step": 3313 }, { "epoch": 5.37, "learning_rate": 1.8573216336015355e-05, "loss": 0.1903, "step": 3314 }, { "epoch": 5.37, "learning_rate": 1.856274331041171e-05, "loss": 0.1367, "step": 3315 }, { "epoch": 5.37, "learning_rate": 1.8552270680950078e-05, "loss": 0.1648, "step": 3316 }, { "epoch": 5.38, "learning_rate": 1.8541798450516967e-05, "loss": 0.1578, "step": 3317 }, { "epoch": 5.38, "learning_rate": 1.8531326621998758e-05, "loss": 0.1765, "step": 3318 }, { "epoch": 5.38, "learning_rate": 1.8520855198281757e-05, "loss": 0.1371, "step": 3319 }, { "epoch": 5.38, "learning_rate": 1.8510384182252126e-05, "loss": 0.1425, "step": 3320 }, { "epoch": 5.38, "learning_rate": 1.8499913576795913e-05, "loss": 0.1583, "step": 3321 }, { "epoch": 5.38, "learning_rate": 1.848944338479909e-05, "loss": 0.1777, "step": 3322 }, { "epoch": 5.39, "learning_rate": 1.847897360914747e-05, "loss": 0.1894, "step": 3323 }, { "epoch": 5.39, "learning_rate": 1.8468504252726787e-05, "loss": 0.2735, "step": 3324 }, { "epoch": 5.39, "learning_rate": 1.845803531842263e-05, "loss": 0.1365, "step": 3325 }, { "epoch": 5.39, "learning_rate": 1.8447566809120487e-05, "loss": 0.1465, "step": 3326 }, { "epoch": 5.39, "learning_rate": 1.843709872770574e-05, "loss": 0.1861, "step": 3327 }, { "epoch": 5.39, "learning_rate": 1.842663107706363e-05, "loss": 0.1774, "step": 3328 }, { "epoch": 5.4, "learning_rate": 1.8416163860079285e-05, "loss": 0.1371, "step": 3329 }, { "epoch": 5.4, "learning_rate": 1.840569707963773e-05, "loss": 0.161, "step": 3330 }, { "epoch": 5.4, "learning_rate": 1.839523073862385e-05, "loss": 0.1904, "step": 3331 }, { "epoch": 5.4, "learning_rate": 1.8384764839922416e-05, "loss": 0.1563, "step": 3332 }, { "epoch": 5.4, "learning_rate": 1.8374299386418082e-05, "loss": 0.18, "step": 3333 }, { "epoch": 5.4, "learning_rate": 1.8363834380995377e-05, "loss": 0.1728, "step": 3334 }, { "epoch": 5.41, "learning_rate": 1.8353369826538702e-05, "loss": 0.1471, "step": 3335 }, { "epoch": 5.41, "learning_rate": 1.8342905725932336e-05, "loss": 0.1813, "step": 3336 }, { "epoch": 5.41, "learning_rate": 1.8332442082060422e-05, "loss": 0.1425, "step": 3337 }, { "epoch": 5.41, "learning_rate": 1.8321978897807007e-05, "loss": 0.1362, "step": 3338 }, { "epoch": 5.41, "learning_rate": 1.831151617605599e-05, "loss": 0.1391, "step": 3339 }, { "epoch": 5.41, "learning_rate": 1.8301053919691133e-05, "loss": 0.1947, "step": 3340 }, { "epoch": 5.41, "learning_rate": 1.829059213159609e-05, "loss": 0.1856, "step": 3341 }, { "epoch": 5.42, "learning_rate": 1.828013081465437e-05, "loss": 0.1323, "step": 3342 }, { "epoch": 5.42, "learning_rate": 1.8269669971749374e-05, "loss": 0.2172, "step": 3343 }, { "epoch": 5.42, "learning_rate": 1.825920960576435e-05, "loss": 0.1242, "step": 3344 }, { "epoch": 5.42, "learning_rate": 1.8248749719582418e-05, "loss": 0.1944, "step": 3345 }, { "epoch": 5.42, "learning_rate": 1.8238290316086584e-05, "loss": 0.1685, "step": 3346 }, { "epoch": 5.42, "learning_rate": 1.82278313981597e-05, "loss": 0.1414, "step": 3347 }, { "epoch": 5.43, "learning_rate": 1.8217372968684483e-05, "loss": 0.1675, "step": 3348 }, { "epoch": 5.43, "learning_rate": 1.8206915030543538e-05, "loss": 0.146, "step": 3349 }, { "epoch": 5.43, "learning_rate": 1.8196457586619315e-05, "loss": 0.1518, "step": 3350 }, { "epoch": 5.43, "learning_rate": 1.8186000639794128e-05, "loss": 0.2818, "step": 3351 }, { "epoch": 5.43, "learning_rate": 1.817554419295017e-05, "loss": 0.1559, "step": 3352 }, { "epoch": 5.43, "learning_rate": 1.816508824896948e-05, "loss": 0.1739, "step": 3353 }, { "epoch": 5.44, "learning_rate": 1.815463281073396e-05, "loss": 0.1642, "step": 3354 }, { "epoch": 5.44, "learning_rate": 1.8144177881125392e-05, "loss": 0.1915, "step": 3355 }, { "epoch": 5.44, "learning_rate": 1.8133723463025375e-05, "loss": 0.1713, "step": 3356 }, { "epoch": 5.44, "learning_rate": 1.8123269559315423e-05, "loss": 0.1672, "step": 3357 }, { "epoch": 5.44, "learning_rate": 1.8112816172876867e-05, "loss": 0.1976, "step": 3358 }, { "epoch": 5.44, "learning_rate": 1.8102363306590907e-05, "loss": 0.1725, "step": 3359 }, { "epoch": 5.45, "learning_rate": 1.8091910963338604e-05, "loss": 0.162, "step": 3360 }, { "epoch": 5.45, "learning_rate": 1.808145914600086e-05, "loss": 0.204, "step": 3361 }, { "epoch": 5.45, "learning_rate": 1.8071007857458465e-05, "loss": 0.1915, "step": 3362 }, { "epoch": 5.45, "learning_rate": 1.806055710059203e-05, "loss": 0.2352, "step": 3363 }, { "epoch": 5.45, "learning_rate": 1.805010687828202e-05, "loss": 0.1884, "step": 3364 }, { "epoch": 5.45, "learning_rate": 1.8039657193408788e-05, "loss": 0.1703, "step": 3365 }, { "epoch": 5.46, "learning_rate": 1.8029208048852505e-05, "loss": 0.1503, "step": 3366 }, { "epoch": 5.46, "learning_rate": 1.801875944749319e-05, "loss": 0.1212, "step": 3367 }, { "epoch": 5.46, "learning_rate": 1.8008311392210744e-05, "loss": 0.2022, "step": 3368 }, { "epoch": 5.46, "learning_rate": 1.799786388588489e-05, "loss": 0.2183, "step": 3369 }, { "epoch": 5.46, "learning_rate": 1.79874169313952e-05, "loss": 0.1622, "step": 3370 }, { "epoch": 5.46, "learning_rate": 1.797697053162112e-05, "loss": 0.1559, "step": 3371 }, { "epoch": 5.47, "learning_rate": 1.7966524689441912e-05, "loss": 0.1468, "step": 3372 }, { "epoch": 5.47, "learning_rate": 1.7956079407736705e-05, "loss": 0.1813, "step": 3373 }, { "epoch": 5.47, "learning_rate": 1.7945634689384465e-05, "loss": 0.1756, "step": 3374 }, { "epoch": 5.47, "learning_rate": 1.7935190537263993e-05, "loss": 0.2492, "step": 3375 }, { "epoch": 5.47, "learning_rate": 1.7924746954253966e-05, "loss": 0.1552, "step": 3376 }, { "epoch": 5.47, "learning_rate": 1.7914303943232868e-05, "loss": 0.1927, "step": 3377 }, { "epoch": 5.47, "learning_rate": 1.7903861507079042e-05, "loss": 0.1581, "step": 3378 }, { "epoch": 5.48, "learning_rate": 1.7893419648670678e-05, "loss": 0.1882, "step": 3379 }, { "epoch": 5.48, "learning_rate": 1.7882978370885785e-05, "loss": 0.1628, "step": 3380 }, { "epoch": 5.48, "learning_rate": 1.787253767660224e-05, "loss": 0.1647, "step": 3381 }, { "epoch": 5.48, "learning_rate": 1.786209756869775e-05, "loss": 0.17, "step": 3382 }, { "epoch": 5.48, "learning_rate": 1.7851658050049837e-05, "loss": 0.1537, "step": 3383 }, { "epoch": 5.48, "learning_rate": 1.78412191235359e-05, "loss": 0.1207, "step": 3384 }, { "epoch": 5.49, "learning_rate": 1.7830780792033144e-05, "loss": 0.1622, "step": 3385 }, { "epoch": 5.49, "learning_rate": 1.7820343058418613e-05, "loss": 0.2571, "step": 3386 }, { "epoch": 5.49, "learning_rate": 1.780990592556921e-05, "loss": 0.2453, "step": 3387 }, { "epoch": 5.49, "learning_rate": 1.7799469396361654e-05, "loss": 0.1544, "step": 3388 }, { "epoch": 5.49, "learning_rate": 1.7789033473672485e-05, "loss": 0.2871, "step": 3389 }, { "epoch": 5.49, "learning_rate": 1.7778598160378107e-05, "loss": 0.1718, "step": 3390 }, { "epoch": 5.5, "learning_rate": 1.776816345935473e-05, "loss": 0.1835, "step": 3391 }, { "epoch": 5.5, "learning_rate": 1.7757729373478413e-05, "loss": 0.1999, "step": 3392 }, { "epoch": 5.5, "learning_rate": 1.7747295905625033e-05, "loss": 0.1703, "step": 3393 }, { "epoch": 5.5, "learning_rate": 1.773686305867029e-05, "loss": 0.1611, "step": 3394 }, { "epoch": 5.5, "learning_rate": 1.7726430835489747e-05, "loss": 0.1193, "step": 3395 }, { "epoch": 5.5, "learning_rate": 1.771599923895876e-05, "loss": 0.1582, "step": 3396 }, { "epoch": 5.51, "learning_rate": 1.7705568271952516e-05, "loss": 0.1528, "step": 3397 }, { "epoch": 5.51, "learning_rate": 1.769513793734605e-05, "loss": 0.219, "step": 3398 }, { "epoch": 5.51, "learning_rate": 1.76847082380142e-05, "loss": 0.168, "step": 3399 }, { "epoch": 5.51, "learning_rate": 1.7674279176831647e-05, "loss": 0.1888, "step": 3400 }, { "epoch": 5.51, "learning_rate": 1.7663850756672884e-05, "loss": 0.236, "step": 3401 }, { "epoch": 5.51, "learning_rate": 1.7653422980412227e-05, "loss": 0.1576, "step": 3402 }, { "epoch": 5.52, "learning_rate": 1.7642995850923827e-05, "loss": 0.1829, "step": 3403 }, { "epoch": 5.52, "learning_rate": 1.7632569371081637e-05, "loss": 0.1637, "step": 3404 }, { "epoch": 5.52, "learning_rate": 1.762214354375944e-05, "loss": 0.17, "step": 3405 }, { "epoch": 5.52, "learning_rate": 1.761171837183086e-05, "loss": 0.1657, "step": 3406 }, { "epoch": 5.52, "learning_rate": 1.760129385816931e-05, "loss": 0.1639, "step": 3407 }, { "epoch": 5.52, "learning_rate": 1.759087000564803e-05, "loss": 0.1417, "step": 3408 }, { "epoch": 5.53, "learning_rate": 1.7580446817140085e-05, "loss": 0.2845, "step": 3409 }, { "epoch": 5.53, "learning_rate": 1.7570024295518345e-05, "loss": 0.1549, "step": 3410 }, { "epoch": 5.53, "learning_rate": 1.7559602443655518e-05, "loss": 0.1972, "step": 3411 }, { "epoch": 5.53, "learning_rate": 1.7549181264424105e-05, "loss": 0.2625, "step": 3412 }, { "epoch": 5.53, "learning_rate": 1.7538760760696423e-05, "loss": 0.1683, "step": 3413 }, { "epoch": 5.53, "learning_rate": 1.752834093534463e-05, "loss": 0.1095, "step": 3414 }, { "epoch": 5.53, "learning_rate": 1.7517921791240664e-05, "loss": 0.196, "step": 3415 }, { "epoch": 5.54, "learning_rate": 1.7507503331256283e-05, "loss": 0.2242, "step": 3416 }, { "epoch": 5.54, "learning_rate": 1.7497085558263072e-05, "loss": 0.1601, "step": 3417 }, { "epoch": 5.54, "learning_rate": 1.7486668475132404e-05, "loss": 0.1633, "step": 3418 }, { "epoch": 5.54, "learning_rate": 1.747625208473549e-05, "loss": 0.159, "step": 3419 }, { "epoch": 5.54, "learning_rate": 1.7465836389943327e-05, "loss": 0.1819, "step": 3420 }, { "epoch": 5.54, "learning_rate": 1.745542139362672e-05, "loss": 0.1827, "step": 3421 }, { "epoch": 5.55, "learning_rate": 1.74450070986563e-05, "loss": 0.2198, "step": 3422 }, { "epoch": 5.55, "learning_rate": 1.7434593507902492e-05, "loss": 0.1639, "step": 3423 }, { "epoch": 5.55, "learning_rate": 1.7424180624235513e-05, "loss": 0.1823, "step": 3424 }, { "epoch": 5.55, "learning_rate": 1.7413768450525422e-05, "loss": 0.1397, "step": 3425 }, { "epoch": 5.55, "learning_rate": 1.740335698964205e-05, "loss": 0.2413, "step": 3426 }, { "epoch": 5.55, "learning_rate": 1.7392946244455043e-05, "loss": 0.1681, "step": 3427 }, { "epoch": 5.56, "learning_rate": 1.7382536217833855e-05, "loss": 0.1954, "step": 3428 }, { "epoch": 5.56, "learning_rate": 1.737212691264772e-05, "loss": 0.1424, "step": 3429 }, { "epoch": 5.56, "learning_rate": 1.736171833176571e-05, "loss": 0.1511, "step": 3430 }, { "epoch": 5.56, "learning_rate": 1.7351310478056666e-05, "loss": 0.1944, "step": 3431 }, { "epoch": 5.56, "learning_rate": 1.7340903354389237e-05, "loss": 0.19, "step": 3432 }, { "epoch": 5.56, "learning_rate": 1.7330496963631883e-05, "loss": 0.1912, "step": 3433 }, { "epoch": 5.57, "learning_rate": 1.7320091308652842e-05, "loss": 0.1301, "step": 3434 }, { "epoch": 5.57, "learning_rate": 1.730968639232016e-05, "loss": 0.1582, "step": 3435 }, { "epoch": 5.57, "learning_rate": 1.7299282217501682e-05, "loss": 0.187, "step": 3436 }, { "epoch": 5.57, "learning_rate": 1.7288878787065037e-05, "loss": 0.2038, "step": 3437 }, { "epoch": 5.57, "learning_rate": 1.7278476103877676e-05, "loss": 0.1931, "step": 3438 }, { "epoch": 5.57, "learning_rate": 1.7268074170806813e-05, "loss": 0.1556, "step": 3439 }, { "epoch": 5.58, "learning_rate": 1.7257672990719462e-05, "loss": 0.1687, "step": 3440 }, { "epoch": 5.58, "learning_rate": 1.7247272566482445e-05, "loss": 0.1882, "step": 3441 }, { "epoch": 5.58, "learning_rate": 1.7236872900962364e-05, "loss": 0.2286, "step": 3442 }, { "epoch": 5.58, "learning_rate": 1.7226473997025597e-05, "loss": 0.179, "step": 3443 }, { "epoch": 5.58, "learning_rate": 1.7216075857538352e-05, "loss": 0.2551, "step": 3444 }, { "epoch": 5.58, "learning_rate": 1.720567848536659e-05, "loss": 0.157, "step": 3445 }, { "epoch": 5.59, "learning_rate": 1.7195281883376078e-05, "loss": 0.2765, "step": 3446 }, { "epoch": 5.59, "learning_rate": 1.7184886054432367e-05, "loss": 0.1756, "step": 3447 }, { "epoch": 5.59, "learning_rate": 1.7174491001400777e-05, "loss": 0.1689, "step": 3448 }, { "epoch": 5.59, "learning_rate": 1.7164096727146455e-05, "loss": 0.1908, "step": 3449 }, { "epoch": 5.59, "learning_rate": 1.7153703234534302e-05, "loss": 0.1506, "step": 3450 }, { "epoch": 5.59, "learning_rate": 1.7143310526429e-05, "loss": 0.1844, "step": 3451 }, { "epoch": 5.59, "learning_rate": 1.7132918605695042e-05, "loss": 0.283, "step": 3452 }, { "epoch": 5.6, "learning_rate": 1.7122527475196676e-05, "loss": 0.2161, "step": 3453 }, { "epoch": 5.6, "learning_rate": 1.711213713779794e-05, "loss": 0.1601, "step": 3454 }, { "epoch": 5.6, "learning_rate": 1.710174759636267e-05, "loss": 0.1431, "step": 3455 }, { "epoch": 5.6, "learning_rate": 1.7091358853754464e-05, "loss": 0.1595, "step": 3456 }, { "epoch": 5.6, "learning_rate": 1.7080970912836707e-05, "loss": 0.149, "step": 3457 }, { "epoch": 5.6, "learning_rate": 1.7070583776472564e-05, "loss": 0.1616, "step": 3458 }, { "epoch": 5.61, "learning_rate": 1.7060197447524963e-05, "loss": 0.144, "step": 3459 }, { "epoch": 5.61, "learning_rate": 1.7049811928856642e-05, "loss": 0.1535, "step": 3460 }, { "epoch": 5.61, "learning_rate": 1.703942722333008e-05, "loss": 0.1785, "step": 3461 }, { "epoch": 5.61, "learning_rate": 1.7029043333807556e-05, "loss": 0.2036, "step": 3462 }, { "epoch": 5.61, "learning_rate": 1.7018660263151118e-05, "loss": 0.1717, "step": 3463 }, { "epoch": 5.61, "learning_rate": 1.700827801422258e-05, "loss": 0.2348, "step": 3464 }, { "epoch": 5.62, "learning_rate": 1.699789658988354e-05, "loss": 0.1809, "step": 3465 }, { "epoch": 5.62, "learning_rate": 1.6987515992995366e-05, "loss": 0.2172, "step": 3466 }, { "epoch": 5.62, "learning_rate": 1.6977136226419187e-05, "loss": 0.2129, "step": 3467 }, { "epoch": 5.62, "learning_rate": 1.6966757293015924e-05, "loss": 0.1676, "step": 3468 }, { "epoch": 5.62, "learning_rate": 1.695637919564626e-05, "loss": 0.1346, "step": 3469 }, { "epoch": 5.62, "learning_rate": 1.6946001937170625e-05, "loss": 0.2257, "step": 3470 }, { "epoch": 5.63, "learning_rate": 1.693562552044926e-05, "loss": 0.1355, "step": 3471 }, { "epoch": 5.63, "learning_rate": 1.692524994834214e-05, "loss": 0.1824, "step": 3472 }, { "epoch": 5.63, "learning_rate": 1.691487522370901e-05, "loss": 0.1834, "step": 3473 }, { "epoch": 5.63, "learning_rate": 1.690450134940941e-05, "loss": 0.1678, "step": 3474 }, { "epoch": 5.63, "learning_rate": 1.689412832830261e-05, "loss": 0.2721, "step": 3475 }, { "epoch": 5.63, "learning_rate": 1.688375616324767e-05, "loss": 0.1707, "step": 3476 }, { "epoch": 5.64, "learning_rate": 1.6873384857103403e-05, "loss": 0.1666, "step": 3477 }, { "epoch": 5.64, "learning_rate": 1.6863014412728377e-05, "loss": 0.1657, "step": 3478 }, { "epoch": 5.64, "learning_rate": 1.6852644832980947e-05, "loss": 0.2309, "step": 3479 }, { "epoch": 5.64, "learning_rate": 1.6842276120719204e-05, "loss": 0.1629, "step": 3480 }, { "epoch": 5.64, "learning_rate": 1.6831908278801016e-05, "loss": 0.1618, "step": 3481 }, { "epoch": 5.64, "learning_rate": 1.6821541310084007e-05, "loss": 0.2259, "step": 3482 }, { "epoch": 5.65, "learning_rate": 1.681117521742555e-05, "loss": 0.1766, "step": 3483 }, { "epoch": 5.65, "learning_rate": 1.68008100036828e-05, "loss": 0.1389, "step": 3484 }, { "epoch": 5.65, "learning_rate": 1.679044567171265e-05, "loss": 0.1969, "step": 3485 }, { "epoch": 5.65, "learning_rate": 1.678008222437174e-05, "loss": 0.1878, "step": 3486 }, { "epoch": 5.65, "learning_rate": 1.676971966451651e-05, "loss": 0.1767, "step": 3487 }, { "epoch": 5.65, "learning_rate": 1.675935799500311e-05, "loss": 0.2167, "step": 3488 }, { "epoch": 5.65, "learning_rate": 1.674899721868746e-05, "loss": 0.1647, "step": 3489 }, { "epoch": 5.66, "learning_rate": 1.673863733842525e-05, "loss": 0.1377, "step": 3490 }, { "epoch": 5.66, "learning_rate": 1.6728278357071896e-05, "loss": 0.1968, "step": 3491 }, { "epoch": 5.66, "learning_rate": 1.6717920277482572e-05, "loss": 0.2025, "step": 3492 }, { "epoch": 5.66, "learning_rate": 1.6707563102512228e-05, "loss": 0.1887, "step": 3493 }, { "epoch": 5.66, "learning_rate": 1.6697206835015535e-05, "loss": 0.2606, "step": 3494 }, { "epoch": 5.66, "learning_rate": 1.6686851477846936e-05, "loss": 0.1809, "step": 3495 }, { "epoch": 5.67, "learning_rate": 1.6676497033860607e-05, "loss": 0.173, "step": 3496 }, { "epoch": 5.67, "learning_rate": 1.6666143505910466e-05, "loss": 0.1523, "step": 3497 }, { "epoch": 5.67, "learning_rate": 1.665579089685021e-05, "loss": 0.193, "step": 3498 }, { "epoch": 5.67, "learning_rate": 1.664543920953326e-05, "loss": 0.1683, "step": 3499 }, { "epoch": 5.67, "learning_rate": 1.6635088446812776e-05, "loss": 0.1719, "step": 3500 }, { "epoch": 5.67, "learning_rate": 1.6624738611541685e-05, "loss": 0.1435, "step": 3501 }, { "epoch": 5.68, "learning_rate": 1.6614389706572633e-05, "loss": 0.2238, "step": 3502 }, { "epoch": 5.68, "learning_rate": 1.6604041734758043e-05, "loss": 0.1834, "step": 3503 }, { "epoch": 5.68, "learning_rate": 1.6593694698950047e-05, "loss": 0.2031, "step": 3504 }, { "epoch": 5.68, "learning_rate": 1.658334860200053e-05, "loss": 0.1638, "step": 3505 }, { "epoch": 5.68, "learning_rate": 1.657300344676114e-05, "loss": 0.1548, "step": 3506 }, { "epoch": 5.68, "learning_rate": 1.6562659236083235e-05, "loss": 0.1963, "step": 3507 }, { "epoch": 5.69, "learning_rate": 1.6552315972817918e-05, "loss": 0.1526, "step": 3508 }, { "epoch": 5.69, "learning_rate": 1.654197365981605e-05, "loss": 0.1358, "step": 3509 }, { "epoch": 5.69, "learning_rate": 1.6531632299928207e-05, "loss": 0.2022, "step": 3510 }, { "epoch": 5.69, "learning_rate": 1.6521291896004722e-05, "loss": 0.1791, "step": 3511 }, { "epoch": 5.69, "learning_rate": 1.6510952450895655e-05, "loss": 0.1524, "step": 3512 }, { "epoch": 5.69, "learning_rate": 1.6500613967450795e-05, "loss": 0.1965, "step": 3513 }, { "epoch": 5.7, "learning_rate": 1.649027644851968e-05, "loss": 0.1997, "step": 3514 }, { "epoch": 5.7, "learning_rate": 1.6479939896951575e-05, "loss": 0.1836, "step": 3515 }, { "epoch": 5.7, "learning_rate": 1.6469604315595464e-05, "loss": 0.1629, "step": 3516 }, { "epoch": 5.7, "learning_rate": 1.6459269707300103e-05, "loss": 0.2177, "step": 3517 }, { "epoch": 5.7, "learning_rate": 1.6448936074913938e-05, "loss": 0.191, "step": 3518 }, { "epoch": 5.7, "learning_rate": 1.6438603421285166e-05, "loss": 0.1712, "step": 3519 }, { "epoch": 5.71, "learning_rate": 1.6428271749261714e-05, "loss": 0.1814, "step": 3520 }, { "epoch": 5.71, "learning_rate": 1.641794106169123e-05, "loss": 0.2078, "step": 3521 }, { "epoch": 5.71, "learning_rate": 1.6407611361421107e-05, "loss": 0.1827, "step": 3522 }, { "epoch": 5.71, "learning_rate": 1.639728265129845e-05, "loss": 0.224, "step": 3523 }, { "epoch": 5.71, "learning_rate": 1.638695493417009e-05, "loss": 0.1692, "step": 3524 }, { "epoch": 5.71, "learning_rate": 1.63766282128826e-05, "loss": 0.1909, "step": 3525 }, { "epoch": 5.71, "learning_rate": 1.6366302490282265e-05, "loss": 0.1672, "step": 3526 }, { "epoch": 5.72, "learning_rate": 1.635597776921509e-05, "loss": 0.1648, "step": 3527 }, { "epoch": 5.72, "learning_rate": 1.6345654052526833e-05, "loss": 0.1734, "step": 3528 }, { "epoch": 5.72, "learning_rate": 1.6335331343062934e-05, "loss": 0.1715, "step": 3529 }, { "epoch": 5.72, "learning_rate": 1.6325009643668592e-05, "loss": 0.2155, "step": 3530 }, { "epoch": 5.72, "learning_rate": 1.631468895718871e-05, "loss": 0.1781, "step": 3531 }, { "epoch": 5.72, "learning_rate": 1.6304369286467906e-05, "loss": 0.1965, "step": 3532 }, { "epoch": 5.73, "learning_rate": 1.6294050634350533e-05, "loss": 0.1791, "step": 3533 }, { "epoch": 5.73, "learning_rate": 1.6283733003680655e-05, "loss": 0.1647, "step": 3534 }, { "epoch": 5.73, "learning_rate": 1.6273416397302043e-05, "loss": 0.1627, "step": 3535 }, { "epoch": 5.73, "learning_rate": 1.626310081805822e-05, "loss": 0.2009, "step": 3536 }, { "epoch": 5.73, "learning_rate": 1.625278626879239e-05, "loss": 0.2384, "step": 3537 }, { "epoch": 5.73, "learning_rate": 1.624247275234749e-05, "loss": 0.1072, "step": 3538 }, { "epoch": 5.74, "learning_rate": 1.6232160271566174e-05, "loss": 0.1854, "step": 3539 }, { "epoch": 5.74, "learning_rate": 1.622184882929079e-05, "loss": 0.1559, "step": 3540 }, { "epoch": 5.74, "learning_rate": 1.621153842836344e-05, "loss": 0.2336, "step": 3541 }, { "epoch": 5.74, "learning_rate": 1.6201229071625905e-05, "loss": 0.0989, "step": 3542 }, { "epoch": 5.74, "learning_rate": 1.6190920761919678e-05, "loss": 0.162, "step": 3543 }, { "epoch": 5.74, "learning_rate": 1.6180613502085987e-05, "loss": 0.1741, "step": 3544 }, { "epoch": 5.75, "learning_rate": 1.6170307294965752e-05, "loss": 0.1872, "step": 3545 }, { "epoch": 5.75, "learning_rate": 1.61600021433996e-05, "loss": 0.1676, "step": 3546 }, { "epoch": 5.75, "learning_rate": 1.6149698050227892e-05, "loss": 0.1671, "step": 3547 }, { "epoch": 5.75, "learning_rate": 1.6139395018290666e-05, "loss": 0.1665, "step": 3548 }, { "epoch": 5.75, "learning_rate": 1.6129093050427692e-05, "loss": 0.1723, "step": 3549 }, { "epoch": 5.75, "learning_rate": 1.6118792149478432e-05, "loss": 0.2048, "step": 3550 }, { "epoch": 5.76, "learning_rate": 1.6108492318282047e-05, "loss": 0.2127, "step": 3551 }, { "epoch": 5.76, "learning_rate": 1.609819355967744e-05, "loss": 0.2326, "step": 3552 }, { "epoch": 5.76, "learning_rate": 1.6087895876503174e-05, "loss": 0.192, "step": 3553 }, { "epoch": 5.76, "learning_rate": 1.607759927159753e-05, "loss": 0.1715, "step": 3554 }, { "epoch": 5.76, "learning_rate": 1.6067303747798514e-05, "loss": 0.2007, "step": 3555 }, { "epoch": 5.76, "learning_rate": 1.6057009307943812e-05, "loss": 0.1639, "step": 3556 }, { "epoch": 5.76, "learning_rate": 1.6046715954870807e-05, "loss": 0.2485, "step": 3557 }, { "epoch": 5.77, "learning_rate": 1.6036423691416597e-05, "loss": 0.2259, "step": 3558 }, { "epoch": 5.77, "learning_rate": 1.6026132520417968e-05, "loss": 0.1459, "step": 3559 }, { "epoch": 5.77, "learning_rate": 1.601584244471142e-05, "loss": 0.1804, "step": 3560 }, { "epoch": 5.77, "learning_rate": 1.600555346713314e-05, "loss": 0.1654, "step": 3561 }, { "epoch": 5.77, "learning_rate": 1.5995265590519007e-05, "loss": 0.156, "step": 3562 }, { "epoch": 5.77, "learning_rate": 1.598497881770461e-05, "loss": 0.1666, "step": 3563 }, { "epoch": 5.78, "learning_rate": 1.5974693151525228e-05, "loss": 0.1476, "step": 3564 }, { "epoch": 5.78, "learning_rate": 1.596440859481582e-05, "loss": 0.1758, "step": 3565 }, { "epoch": 5.78, "learning_rate": 1.5954125150411078e-05, "loss": 0.1309, "step": 3566 }, { "epoch": 5.78, "learning_rate": 1.5943842821145343e-05, "loss": 0.1909, "step": 3567 }, { "epoch": 5.78, "learning_rate": 1.5933561609852683e-05, "loss": 0.1693, "step": 3568 }, { "epoch": 5.78, "learning_rate": 1.5923281519366832e-05, "loss": 0.236, "step": 3569 }, { "epoch": 5.79, "learning_rate": 1.5913002552521225e-05, "loss": 0.2195, "step": 3570 }, { "epoch": 5.79, "learning_rate": 1.5902724712149007e-05, "loss": 0.177, "step": 3571 }, { "epoch": 5.79, "learning_rate": 1.5892448001082978e-05, "loss": 0.1373, "step": 3572 }, { "epoch": 5.79, "learning_rate": 1.588217242215565e-05, "loss": 0.2445, "step": 3573 }, { "epoch": 5.79, "learning_rate": 1.5871897978199213e-05, "loss": 0.1395, "step": 3574 }, { "epoch": 5.79, "learning_rate": 1.586162467204555e-05, "loss": 0.2542, "step": 3575 }, { "epoch": 5.8, "learning_rate": 1.5851352506526215e-05, "loss": 0.2349, "step": 3576 }, { "epoch": 5.8, "learning_rate": 1.584108148447248e-05, "loss": 0.165, "step": 3577 }, { "epoch": 5.8, "learning_rate": 1.5830811608715265e-05, "loss": 0.2, "step": 3578 }, { "epoch": 5.8, "learning_rate": 1.582054288208521e-05, "loss": 0.1657, "step": 3579 }, { "epoch": 5.8, "learning_rate": 1.581027530741261e-05, "loss": 0.1789, "step": 3580 }, { "epoch": 5.8, "learning_rate": 1.5800008887527444e-05, "loss": 0.1798, "step": 3581 }, { "epoch": 5.81, "learning_rate": 1.5789743625259396e-05, "loss": 0.1586, "step": 3582 }, { "epoch": 5.81, "learning_rate": 1.5779479523437802e-05, "loss": 0.1666, "step": 3583 }, { "epoch": 5.81, "learning_rate": 1.5769216584891695e-05, "loss": 0.1885, "step": 3584 }, { "epoch": 5.81, "learning_rate": 1.5758954812449788e-05, "loss": 0.2529, "step": 3585 }, { "epoch": 5.81, "learning_rate": 1.5748694208940467e-05, "loss": 0.1955, "step": 3586 }, { "epoch": 5.81, "learning_rate": 1.57384347771918e-05, "loss": 0.148, "step": 3587 }, { "epoch": 5.82, "learning_rate": 1.5728176520031528e-05, "loss": 0.1635, "step": 3588 }, { "epoch": 5.82, "learning_rate": 1.571791944028706e-05, "loss": 0.1925, "step": 3589 }, { "epoch": 5.82, "learning_rate": 1.570766354078551e-05, "loss": 0.2029, "step": 3590 }, { "epoch": 5.82, "learning_rate": 1.5697408824353635e-05, "loss": 0.1724, "step": 3591 }, { "epoch": 5.82, "learning_rate": 1.5687155293817875e-05, "loss": 0.1592, "step": 3592 }, { "epoch": 5.82, "learning_rate": 1.5676902952004352e-05, "loss": 0.3001, "step": 3593 }, { "epoch": 5.82, "learning_rate": 1.5666651801738856e-05, "loss": 0.1972, "step": 3594 }, { "epoch": 5.83, "learning_rate": 1.5656401845846834e-05, "loss": 0.1472, "step": 3595 }, { "epoch": 5.83, "learning_rate": 1.5646153087153437e-05, "loss": 0.2088, "step": 3596 }, { "epoch": 5.83, "learning_rate": 1.5635905528483447e-05, "loss": 0.2221, "step": 3597 }, { "epoch": 5.83, "learning_rate": 1.562565917266135e-05, "loss": 0.303, "step": 3598 }, { "epoch": 5.83, "learning_rate": 1.5615414022511277e-05, "loss": 0.1766, "step": 3599 }, { "epoch": 5.83, "learning_rate": 1.5605170080857025e-05, "loss": 0.1756, "step": 3600 }, { "epoch": 5.84, "learning_rate": 1.5594927350522084e-05, "loss": 0.1825, "step": 3601 }, { "epoch": 5.84, "learning_rate": 1.558468583432959e-05, "loss": 0.1751, "step": 3602 }, { "epoch": 5.84, "learning_rate": 1.557444553510233e-05, "loss": 0.191, "step": 3603 }, { "epoch": 5.84, "learning_rate": 1.5564206455662796e-05, "loss": 0.253, "step": 3604 }, { "epoch": 5.84, "learning_rate": 1.555396859883311e-05, "loss": 0.1721, "step": 3605 }, { "epoch": 5.84, "learning_rate": 1.554373196743507e-05, "loss": 0.1818, "step": 3606 }, { "epoch": 5.85, "learning_rate": 1.5533496564290136e-05, "loss": 0.1723, "step": 3607 }, { "epoch": 5.85, "learning_rate": 1.552326239221942e-05, "loss": 0.1954, "step": 3608 }, { "epoch": 5.85, "learning_rate": 1.5513029454043712e-05, "loss": 0.1924, "step": 3609 }, { "epoch": 5.85, "learning_rate": 1.550279775258345e-05, "loss": 0.1913, "step": 3610 }, { "epoch": 5.85, "learning_rate": 1.5492567290658727e-05, "loss": 0.2014, "step": 3611 }, { "epoch": 5.85, "learning_rate": 1.548233807108931e-05, "loss": 0.1921, "step": 3612 }, { "epoch": 5.86, "learning_rate": 1.5472110096694602e-05, "loss": 0.1743, "step": 3613 }, { "epoch": 5.86, "learning_rate": 1.5461883370293692e-05, "loss": 0.1932, "step": 3614 }, { "epoch": 5.86, "learning_rate": 1.54516578947053e-05, "loss": 0.1787, "step": 3615 }, { "epoch": 5.86, "learning_rate": 1.54414336727478e-05, "loss": 0.1485, "step": 3616 }, { "epoch": 5.86, "learning_rate": 1.543121070723925e-05, "loss": 0.1795, "step": 3617 }, { "epoch": 5.86, "learning_rate": 1.5420989000997324e-05, "loss": 0.1504, "step": 3618 }, { "epoch": 5.87, "learning_rate": 1.541076855683937e-05, "loss": 0.1809, "step": 3619 }, { "epoch": 5.87, "learning_rate": 1.5400549377582392e-05, "loss": 0.1936, "step": 3620 }, { "epoch": 5.87, "learning_rate": 1.5390331466043035e-05, "loss": 0.1616, "step": 3621 }, { "epoch": 5.87, "learning_rate": 1.538011482503759e-05, "loss": 0.1573, "step": 3622 }, { "epoch": 5.87, "learning_rate": 1.5369899457382017e-05, "loss": 0.1944, "step": 3623 }, { "epoch": 5.87, "learning_rate": 1.5359685365891908e-05, "loss": 0.1722, "step": 3624 }, { "epoch": 5.88, "learning_rate": 1.534947255338251e-05, "loss": 0.2245, "step": 3625 }, { "epoch": 5.88, "learning_rate": 1.5339261022668717e-05, "loss": 0.161, "step": 3626 }, { "epoch": 5.88, "learning_rate": 1.5329050776565056e-05, "loss": 0.1328, "step": 3627 }, { "epoch": 5.88, "learning_rate": 1.5318841817885736e-05, "loss": 0.1931, "step": 3628 }, { "epoch": 5.88, "learning_rate": 1.5308634149444575e-05, "loss": 0.1782, "step": 3629 }, { "epoch": 5.88, "learning_rate": 1.5298427774055045e-05, "loss": 0.2015, "step": 3630 }, { "epoch": 5.88, "learning_rate": 1.5288222694530273e-05, "loss": 0.1842, "step": 3631 }, { "epoch": 5.89, "learning_rate": 1.527801891368301e-05, "loss": 0.168, "step": 3632 }, { "epoch": 5.89, "learning_rate": 1.526781643432567e-05, "loss": 0.156, "step": 3633 }, { "epoch": 5.89, "learning_rate": 1.5257615259270302e-05, "loss": 0.1631, "step": 3634 }, { "epoch": 5.89, "learning_rate": 1.524741539132858e-05, "loss": 0.1532, "step": 3635 }, { "epoch": 5.89, "learning_rate": 1.5237216833311836e-05, "loss": 0.1833, "step": 3636 }, { "epoch": 5.89, "learning_rate": 1.5227019588031035e-05, "loss": 0.1738, "step": 3637 }, { "epoch": 5.9, "learning_rate": 1.5216823658296767e-05, "loss": 0.234, "step": 3638 }, { "epoch": 5.9, "learning_rate": 1.5206629046919292e-05, "loss": 0.1979, "step": 3639 }, { "epoch": 5.9, "learning_rate": 1.5196435756708474e-05, "loss": 0.1487, "step": 3640 }, { "epoch": 5.9, "learning_rate": 1.5186243790473826e-05, "loss": 0.1471, "step": 3641 }, { "epoch": 5.9, "learning_rate": 1.51760531510245e-05, "loss": 0.1654, "step": 3642 }, { "epoch": 5.9, "learning_rate": 1.516586384116927e-05, "loss": 0.2204, "step": 3643 }, { "epoch": 5.91, "learning_rate": 1.5155675863716563e-05, "loss": 0.1513, "step": 3644 }, { "epoch": 5.91, "learning_rate": 1.5145489221474424e-05, "loss": 0.2207, "step": 3645 }, { "epoch": 5.91, "learning_rate": 1.5135303917250517e-05, "loss": 0.1873, "step": 3646 }, { "epoch": 5.91, "learning_rate": 1.5125119953852176e-05, "loss": 0.2148, "step": 3647 }, { "epoch": 5.91, "learning_rate": 1.5114937334086333e-05, "loss": 0.1716, "step": 3648 }, { "epoch": 5.91, "learning_rate": 1.5104756060759555e-05, "loss": 0.1498, "step": 3649 }, { "epoch": 5.92, "learning_rate": 1.5094576136678052e-05, "loss": 0.1939, "step": 3650 }, { "epoch": 5.92, "learning_rate": 1.5084397564647637e-05, "loss": 0.1313, "step": 3651 }, { "epoch": 5.92, "learning_rate": 1.5074220347473784e-05, "loss": 0.2015, "step": 3652 }, { "epoch": 5.92, "learning_rate": 1.5064044487961566e-05, "loss": 0.1691, "step": 3653 }, { "epoch": 5.92, "learning_rate": 1.5053869988915691e-05, "loss": 0.1719, "step": 3654 }, { "epoch": 5.92, "learning_rate": 1.5043696853140494e-05, "loss": 0.2119, "step": 3655 }, { "epoch": 5.93, "learning_rate": 1.5033525083439934e-05, "loss": 0.2242, "step": 3656 }, { "epoch": 5.93, "learning_rate": 1.5023354682617579e-05, "loss": 0.1758, "step": 3657 }, { "epoch": 5.93, "learning_rate": 1.5013185653476653e-05, "loss": 0.27, "step": 3658 }, { "epoch": 5.93, "learning_rate": 1.500301799881997e-05, "loss": 0.1493, "step": 3659 }, { "epoch": 5.93, "learning_rate": 1.4992851721449975e-05, "loss": 0.1641, "step": 3660 }, { "epoch": 5.93, "learning_rate": 1.4982686824168741e-05, "loss": 0.1873, "step": 3661 }, { "epoch": 5.94, "learning_rate": 1.4972523309777947e-05, "loss": 0.2553, "step": 3662 }, { "epoch": 5.94, "learning_rate": 1.4962361181078908e-05, "loss": 0.1637, "step": 3663 }, { "epoch": 5.94, "learning_rate": 1.4952200440872542e-05, "loss": 0.2015, "step": 3664 }, { "epoch": 5.94, "learning_rate": 1.494204109195939e-05, "loss": 0.1835, "step": 3665 }, { "epoch": 5.94, "learning_rate": 1.4931883137139612e-05, "loss": 0.2112, "step": 3666 }, { "epoch": 5.94, "learning_rate": 1.4921726579212979e-05, "loss": 0.2031, "step": 3667 }, { "epoch": 5.94, "learning_rate": 1.4911571420978872e-05, "loss": 0.1691, "step": 3668 }, { "epoch": 5.95, "learning_rate": 1.4901417665236308e-05, "loss": 0.1387, "step": 3669 }, { "epoch": 5.95, "learning_rate": 1.4891265314783888e-05, "loss": 0.1732, "step": 3670 }, { "epoch": 5.95, "learning_rate": 1.4881114372419854e-05, "loss": 0.2515, "step": 3671 }, { "epoch": 5.95, "learning_rate": 1.4870964840942042e-05, "loss": 0.2183, "step": 3672 }, { "epoch": 5.95, "learning_rate": 1.4860816723147898e-05, "loss": 0.1701, "step": 3673 }, { "epoch": 5.95, "learning_rate": 1.4850670021834488e-05, "loss": 0.1748, "step": 3674 }, { "epoch": 5.96, "learning_rate": 1.4840524739798485e-05, "loss": 0.1578, "step": 3675 }, { "epoch": 5.96, "learning_rate": 1.483038087983616e-05, "loss": 0.2137, "step": 3676 }, { "epoch": 5.96, "learning_rate": 1.4820238444743416e-05, "loss": 0.178, "step": 3677 }, { "epoch": 5.96, "learning_rate": 1.481009743731574e-05, "loss": 0.1631, "step": 3678 }, { "epoch": 5.96, "learning_rate": 1.4799957860348234e-05, "loss": 0.2123, "step": 3679 }, { "epoch": 5.96, "learning_rate": 1.4789819716635605e-05, "loss": 0.1463, "step": 3680 }, { "epoch": 5.97, "learning_rate": 1.4779683008972163e-05, "loss": 0.1681, "step": 3681 }, { "epoch": 5.97, "learning_rate": 1.4769547740151838e-05, "loss": 0.1599, "step": 3682 }, { "epoch": 5.97, "learning_rate": 1.4759413912968138e-05, "loss": 0.1893, "step": 3683 }, { "epoch": 5.97, "learning_rate": 1.474928153021419e-05, "loss": 0.2049, "step": 3684 }, { "epoch": 5.97, "learning_rate": 1.473915059468272e-05, "loss": 0.2578, "step": 3685 }, { "epoch": 5.97, "learning_rate": 1.4729021109166053e-05, "loss": 0.1552, "step": 3686 }, { "epoch": 5.98, "learning_rate": 1.4718893076456109e-05, "loss": 0.162, "step": 3687 }, { "epoch": 5.98, "learning_rate": 1.4708766499344424e-05, "loss": 0.1515, "step": 3688 }, { "epoch": 5.98, "learning_rate": 1.4698641380622116e-05, "loss": 0.1694, "step": 3689 }, { "epoch": 5.98, "learning_rate": 1.4688517723079914e-05, "loss": 0.1718, "step": 3690 }, { "epoch": 5.98, "learning_rate": 1.4678395529508133e-05, "loss": 0.222, "step": 3691 }, { "epoch": 5.98, "learning_rate": 1.4668274802696685e-05, "loss": 0.1663, "step": 3692 }, { "epoch": 5.99, "learning_rate": 1.4658155545435096e-05, "loss": 0.1645, "step": 3693 }, { "epoch": 5.99, "learning_rate": 1.4648037760512464e-05, "loss": 0.186, "step": 3694 }, { "epoch": 5.99, "learning_rate": 1.4637921450717483e-05, "loss": 0.1422, "step": 3695 }, { "epoch": 5.99, "learning_rate": 1.4627806618838465e-05, "loss": 0.203, "step": 3696 }, { "epoch": 5.99, "learning_rate": 1.4617693267663282e-05, "loss": 0.1453, "step": 3697 }, { "epoch": 5.99, "learning_rate": 1.4607581399979427e-05, "loss": 0.158, "step": 3698 }, { "epoch": 6.0, "learning_rate": 1.4597471018573963e-05, "loss": 0.1868, "step": 3699 }, { "epoch": 6.0, "learning_rate": 1.4587362126233542e-05, "loss": 0.1864, "step": 3700 }, { "epoch": 6.0, "learning_rate": 1.4577254725744432e-05, "loss": 0.2335, "step": 3701 }, { "epoch": 6.0, "learning_rate": 1.4567148819892464e-05, "loss": 0.1287, "step": 3702 }, { "epoch": 6.0, "learning_rate": 1.4557044411463061e-05, "loss": 0.1187, "step": 3703 }, { "epoch": 6.0, "learning_rate": 1.4546941503241243e-05, "loss": 0.136, "step": 3704 }, { "epoch": 6.0, "learning_rate": 1.4536840098011613e-05, "loss": 0.119, "step": 3705 }, { "epoch": 6.01, "learning_rate": 1.4526740198558345e-05, "loss": 0.1945, "step": 3706 }, { "epoch": 6.01, "learning_rate": 1.4516641807665224e-05, "loss": 0.1579, "step": 3707 }, { "epoch": 6.01, "learning_rate": 1.4506544928115602e-05, "loss": 0.2012, "step": 3708 }, { "epoch": 6.01, "learning_rate": 1.4496449562692421e-05, "loss": 0.136, "step": 3709 }, { "epoch": 6.01, "learning_rate": 1.44863557141782e-05, "loss": 0.12, "step": 3710 }, { "epoch": 6.01, "learning_rate": 1.4476263385355033e-05, "loss": 0.1361, "step": 3711 }, { "epoch": 6.02, "learning_rate": 1.4466172579004627e-05, "loss": 0.1346, "step": 3712 }, { "epoch": 6.02, "learning_rate": 1.4456083297908232e-05, "loss": 0.1691, "step": 3713 }, { "epoch": 6.02, "learning_rate": 1.4445995544846694e-05, "loss": 0.1858, "step": 3714 }, { "epoch": 6.02, "learning_rate": 1.4435909322600443e-05, "loss": 0.1981, "step": 3715 }, { "epoch": 6.02, "learning_rate": 1.4425824633949467e-05, "loss": 0.108, "step": 3716 }, { "epoch": 6.02, "learning_rate": 1.4415741481673368e-05, "loss": 0.1684, "step": 3717 }, { "epoch": 6.03, "learning_rate": 1.4405659868551287e-05, "loss": 0.154, "step": 3718 }, { "epoch": 6.03, "learning_rate": 1.4395579797361952e-05, "loss": 0.1496, "step": 3719 }, { "epoch": 6.03, "learning_rate": 1.4385501270883682e-05, "loss": 0.1745, "step": 3720 }, { "epoch": 6.03, "learning_rate": 1.4375424291894349e-05, "loss": 0.12, "step": 3721 }, { "epoch": 6.03, "learning_rate": 1.4365348863171406e-05, "loss": 0.1659, "step": 3722 }, { "epoch": 6.03, "learning_rate": 1.4355274987491891e-05, "loss": 0.1239, "step": 3723 }, { "epoch": 6.04, "learning_rate": 1.4345202667632392e-05, "loss": 0.1353, "step": 3724 }, { "epoch": 6.04, "learning_rate": 1.4335131906369078e-05, "loss": 0.1374, "step": 3725 }, { "epoch": 6.04, "learning_rate": 1.43250627064777e-05, "loss": 0.1301, "step": 3726 }, { "epoch": 6.04, "learning_rate": 1.4314995070733557e-05, "loss": 0.1577, "step": 3727 }, { "epoch": 6.04, "learning_rate": 1.4304929001911538e-05, "loss": 0.1239, "step": 3728 }, { "epoch": 6.04, "learning_rate": 1.4294864502786085e-05, "loss": 0.1383, "step": 3729 }, { "epoch": 6.05, "learning_rate": 1.428480157613121e-05, "loss": 0.2498, "step": 3730 }, { "epoch": 6.05, "learning_rate": 1.4274740224720497e-05, "loss": 0.114, "step": 3731 }, { "epoch": 6.05, "learning_rate": 1.4264680451327099e-05, "loss": 0.1831, "step": 3732 }, { "epoch": 6.05, "learning_rate": 1.4254622258723718e-05, "loss": 0.1818, "step": 3733 }, { "epoch": 6.05, "learning_rate": 1.4244565649682636e-05, "loss": 0.1408, "step": 3734 }, { "epoch": 6.05, "learning_rate": 1.4234510626975686e-05, "loss": 0.1714, "step": 3735 }, { "epoch": 6.06, "learning_rate": 1.4224457193374281e-05, "loss": 0.1116, "step": 3736 }, { "epoch": 6.06, "learning_rate": 1.4214405351649383e-05, "loss": 0.1654, "step": 3737 }, { "epoch": 6.06, "learning_rate": 1.4204355104571506e-05, "loss": 0.1549, "step": 3738 }, { "epoch": 6.06, "learning_rate": 1.4194306454910757e-05, "loss": 0.1161, "step": 3739 }, { "epoch": 6.06, "learning_rate": 1.4184259405436769e-05, "loss": 0.1283, "step": 3740 }, { "epoch": 6.06, "learning_rate": 1.4174213958918737e-05, "loss": 0.1361, "step": 3741 }, { "epoch": 6.06, "learning_rate": 1.4164170118125448e-05, "loss": 0.1321, "step": 3742 }, { "epoch": 6.07, "learning_rate": 1.4154127885825209e-05, "loss": 0.1059, "step": 3743 }, { "epoch": 6.07, "learning_rate": 1.414408726478589e-05, "loss": 0.1916, "step": 3744 }, { "epoch": 6.07, "learning_rate": 1.4134048257774942e-05, "loss": 0.2215, "step": 3745 }, { "epoch": 6.07, "learning_rate": 1.4124010867559339e-05, "loss": 0.1224, "step": 3746 }, { "epoch": 6.07, "learning_rate": 1.4113975096905632e-05, "loss": 0.1869, "step": 3747 }, { "epoch": 6.07, "learning_rate": 1.4103940948579917e-05, "loss": 0.1069, "step": 3748 }, { "epoch": 6.08, "learning_rate": 1.4093908425347831e-05, "loss": 0.1373, "step": 3749 }, { "epoch": 6.08, "learning_rate": 1.4083877529974594e-05, "loss": 0.186, "step": 3750 }, { "epoch": 6.08, "learning_rate": 1.4073848265224947e-05, "loss": 0.19, "step": 3751 }, { "epoch": 6.08, "learning_rate": 1.4063820633863191e-05, "loss": 0.129, "step": 3752 }, { "epoch": 6.08, "learning_rate": 1.405379463865319e-05, "loss": 0.1587, "step": 3753 }, { "epoch": 6.08, "learning_rate": 1.4043770282358332e-05, "loss": 0.1544, "step": 3754 }, { "epoch": 6.09, "learning_rate": 1.4033747567741576e-05, "loss": 0.1868, "step": 3755 }, { "epoch": 6.09, "learning_rate": 1.4023726497565422e-05, "loss": 0.2063, "step": 3756 }, { "epoch": 6.09, "learning_rate": 1.4013707074591907e-05, "loss": 0.1265, "step": 3757 }, { "epoch": 6.09, "learning_rate": 1.4003689301582628e-05, "loss": 0.1494, "step": 3758 }, { "epoch": 6.09, "learning_rate": 1.399367318129872e-05, "loss": 0.1401, "step": 3759 }, { "epoch": 6.09, "learning_rate": 1.398365871650085e-05, "loss": 0.1191, "step": 3760 }, { "epoch": 6.1, "learning_rate": 1.3973645909949261e-05, "loss": 0.1491, "step": 3761 }, { "epoch": 6.1, "learning_rate": 1.3963634764403714e-05, "loss": 0.1737, "step": 3762 }, { "epoch": 6.1, "learning_rate": 1.3953625282623505e-05, "loss": 0.1917, "step": 3763 }, { "epoch": 6.1, "learning_rate": 1.3943617467367503e-05, "loss": 0.1476, "step": 3764 }, { "epoch": 6.1, "learning_rate": 1.3933611321394089e-05, "loss": 0.1137, "step": 3765 }, { "epoch": 6.1, "learning_rate": 1.39236068474612e-05, "loss": 0.1932, "step": 3766 }, { "epoch": 6.11, "learning_rate": 1.3913604048326299e-05, "loss": 0.1422, "step": 3767 }, { "epoch": 6.11, "learning_rate": 1.3903602926746394e-05, "loss": 0.1546, "step": 3768 }, { "epoch": 6.11, "learning_rate": 1.389360348547804e-05, "loss": 0.1925, "step": 3769 }, { "epoch": 6.11, "learning_rate": 1.3883605727277319e-05, "loss": 0.1255, "step": 3770 }, { "epoch": 6.11, "learning_rate": 1.3873609654899837e-05, "loss": 0.1287, "step": 3771 }, { "epoch": 6.11, "learning_rate": 1.3863615271100767e-05, "loss": 0.1554, "step": 3772 }, { "epoch": 6.12, "learning_rate": 1.385362257863478e-05, "loss": 0.1456, "step": 3773 }, { "epoch": 6.12, "learning_rate": 1.3843631580256114e-05, "loss": 0.13, "step": 3774 }, { "epoch": 6.12, "learning_rate": 1.383364227871852e-05, "loss": 0.1572, "step": 3775 }, { "epoch": 6.12, "learning_rate": 1.382365467677528e-05, "loss": 0.1142, "step": 3776 }, { "epoch": 6.12, "learning_rate": 1.3813668777179223e-05, "loss": 0.1266, "step": 3777 }, { "epoch": 6.12, "learning_rate": 1.3803684582682697e-05, "loss": 0.1252, "step": 3778 }, { "epoch": 6.12, "learning_rate": 1.3793702096037573e-05, "loss": 0.1289, "step": 3779 }, { "epoch": 6.13, "learning_rate": 1.3783721319995275e-05, "loss": 0.1458, "step": 3780 }, { "epoch": 6.13, "learning_rate": 1.3773742257306739e-05, "loss": 0.169, "step": 3781 }, { "epoch": 6.13, "learning_rate": 1.3763764910722422e-05, "loss": 0.1879, "step": 3782 }, { "epoch": 6.13, "learning_rate": 1.3753789282992327e-05, "loss": 0.1497, "step": 3783 }, { "epoch": 6.13, "learning_rate": 1.3743815376865963e-05, "loss": 0.1532, "step": 3784 }, { "epoch": 6.13, "learning_rate": 1.3733843195092389e-05, "loss": 0.1222, "step": 3785 }, { "epoch": 6.14, "learning_rate": 1.3723872740420165e-05, "loss": 0.1462, "step": 3786 }, { "epoch": 6.14, "learning_rate": 1.3713904015597378e-05, "loss": 0.1263, "step": 3787 }, { "epoch": 6.14, "learning_rate": 1.3703937023371667e-05, "loss": 0.1424, "step": 3788 }, { "epoch": 6.14, "learning_rate": 1.3693971766490157e-05, "loss": 0.1632, "step": 3789 }, { "epoch": 6.14, "learning_rate": 1.3684008247699505e-05, "loss": 0.1355, "step": 3790 }, { "epoch": 6.14, "learning_rate": 1.3674046469745901e-05, "loss": 0.1586, "step": 3791 }, { "epoch": 6.15, "learning_rate": 1.3664086435375037e-05, "loss": 0.1252, "step": 3792 }, { "epoch": 6.15, "learning_rate": 1.3654128147332149e-05, "loss": 0.1257, "step": 3793 }, { "epoch": 6.15, "learning_rate": 1.364417160836197e-05, "loss": 0.1213, "step": 3794 }, { "epoch": 6.15, "learning_rate": 1.3634216821208757e-05, "loss": 0.1367, "step": 3795 }, { "epoch": 6.15, "learning_rate": 1.3624263788616285e-05, "loss": 0.1598, "step": 3796 }, { "epoch": 6.15, "learning_rate": 1.3614312513327852e-05, "loss": 0.1572, "step": 3797 }, { "epoch": 6.16, "learning_rate": 1.3604362998086251e-05, "loss": 0.1291, "step": 3798 }, { "epoch": 6.16, "learning_rate": 1.3594415245633823e-05, "loss": 0.1372, "step": 3799 }, { "epoch": 6.16, "learning_rate": 1.3584469258712389e-05, "loss": 0.1539, "step": 3800 }, { "epoch": 6.16, "learning_rate": 1.3574525040063312e-05, "loss": 0.1159, "step": 3801 }, { "epoch": 6.16, "learning_rate": 1.3564582592427445e-05, "loss": 0.1354, "step": 3802 }, { "epoch": 6.16, "learning_rate": 1.3554641918545155e-05, "loss": 0.1417, "step": 3803 }, { "epoch": 6.17, "learning_rate": 1.354470302115635e-05, "loss": 0.1698, "step": 3804 }, { "epoch": 6.17, "learning_rate": 1.353476590300041e-05, "loss": 0.1343, "step": 3805 }, { "epoch": 6.17, "learning_rate": 1.3524830566816239e-05, "loss": 0.1285, "step": 3806 }, { "epoch": 6.17, "learning_rate": 1.3514897015342257e-05, "loss": 0.1416, "step": 3807 }, { "epoch": 6.17, "learning_rate": 1.3504965251316386e-05, "loss": 0.1234, "step": 3808 }, { "epoch": 6.17, "learning_rate": 1.3495035277476048e-05, "loss": 0.1185, "step": 3809 }, { "epoch": 6.18, "learning_rate": 1.348510709655819e-05, "loss": 0.1167, "step": 3810 }, { "epoch": 6.18, "learning_rate": 1.3475180711299243e-05, "loss": 0.1862, "step": 3811 }, { "epoch": 6.18, "learning_rate": 1.3465256124435167e-05, "loss": 0.1105, "step": 3812 }, { "epoch": 6.18, "learning_rate": 1.3455333338701408e-05, "loss": 0.1583, "step": 3813 }, { "epoch": 6.18, "learning_rate": 1.3445412356832917e-05, "loss": 0.1789, "step": 3814 }, { "epoch": 6.18, "learning_rate": 1.3435493181564155e-05, "loss": 0.1472, "step": 3815 }, { "epoch": 6.18, "learning_rate": 1.3425575815629084e-05, "loss": 0.1333, "step": 3816 }, { "epoch": 6.19, "learning_rate": 1.3415660261761151e-05, "loss": 0.1084, "step": 3817 }, { "epoch": 6.19, "learning_rate": 1.3405746522693339e-05, "loss": 0.1908, "step": 3818 }, { "epoch": 6.19, "learning_rate": 1.3395834601158098e-05, "loss": 0.1226, "step": 3819 }, { "epoch": 6.19, "learning_rate": 1.338592449988739e-05, "loss": 0.1434, "step": 3820 }, { "epoch": 6.19, "learning_rate": 1.3376016221612678e-05, "loss": 0.154, "step": 3821 }, { "epoch": 6.19, "learning_rate": 1.3366109769064903e-05, "loss": 0.1594, "step": 3822 }, { "epoch": 6.2, "learning_rate": 1.3356205144974539e-05, "loss": 0.1397, "step": 3823 }, { "epoch": 6.2, "learning_rate": 1.3346302352071525e-05, "loss": 0.1449, "step": 3824 }, { "epoch": 6.2, "learning_rate": 1.3336401393085303e-05, "loss": 0.1298, "step": 3825 }, { "epoch": 6.2, "learning_rate": 1.3326502270744819e-05, "loss": 0.154, "step": 3826 }, { "epoch": 6.2, "learning_rate": 1.3316604987778501e-05, "loss": 0.1444, "step": 3827 }, { "epoch": 6.2, "learning_rate": 1.330670954691427e-05, "loss": 0.1808, "step": 3828 }, { "epoch": 6.21, "learning_rate": 1.3296815950879553e-05, "loss": 0.138, "step": 3829 }, { "epoch": 6.21, "learning_rate": 1.3286924202401257e-05, "loss": 0.1308, "step": 3830 }, { "epoch": 6.21, "learning_rate": 1.3277034304205782e-05, "loss": 0.1325, "step": 3831 }, { "epoch": 6.21, "learning_rate": 1.3267146259019019e-05, "loss": 0.1493, "step": 3832 }, { "epoch": 6.21, "learning_rate": 1.325726006956634e-05, "loss": 0.1442, "step": 3833 }, { "epoch": 6.21, "learning_rate": 1.3247375738572628e-05, "loss": 0.1789, "step": 3834 }, { "epoch": 6.22, "learning_rate": 1.3237493268762228e-05, "loss": 0.1109, "step": 3835 }, { "epoch": 6.22, "learning_rate": 1.3227612662858982e-05, "loss": 0.1645, "step": 3836 }, { "epoch": 6.22, "learning_rate": 1.3217733923586229e-05, "loss": 0.1258, "step": 3837 }, { "epoch": 6.22, "learning_rate": 1.3207857053666773e-05, "loss": 0.1499, "step": 3838 }, { "epoch": 6.22, "learning_rate": 1.3197982055822922e-05, "loss": 0.1522, "step": 3839 }, { "epoch": 6.22, "learning_rate": 1.3188108932776458e-05, "loss": 0.142, "step": 3840 }, { "epoch": 6.23, "learning_rate": 1.3178237687248632e-05, "loss": 0.1529, "step": 3841 }, { "epoch": 6.23, "learning_rate": 1.3168368321960218e-05, "loss": 0.1544, "step": 3842 }, { "epoch": 6.23, "learning_rate": 1.3158500839631439e-05, "loss": 0.1687, "step": 3843 }, { "epoch": 6.23, "learning_rate": 1.3148635242981994e-05, "loss": 0.153, "step": 3844 }, { "epoch": 6.23, "learning_rate": 1.3138771534731093e-05, "loss": 0.156, "step": 3845 }, { "epoch": 6.23, "learning_rate": 1.3128909717597397e-05, "loss": 0.1291, "step": 3846 }, { "epoch": 6.24, "learning_rate": 1.3119049794299053e-05, "loss": 0.1435, "step": 3847 }, { "epoch": 6.24, "learning_rate": 1.3109191767553701e-05, "loss": 0.1549, "step": 3848 }, { "epoch": 6.24, "learning_rate": 1.3099335640078442e-05, "loss": 0.1511, "step": 3849 }, { "epoch": 6.24, "learning_rate": 1.308948141458986e-05, "loss": 0.1309, "step": 3850 }, { "epoch": 6.24, "learning_rate": 1.3079629093804012e-05, "loss": 0.1418, "step": 3851 }, { "epoch": 6.24, "learning_rate": 1.3069778680436423e-05, "loss": 0.1683, "step": 3852 }, { "epoch": 6.24, "learning_rate": 1.3059930177202115e-05, "loss": 0.1568, "step": 3853 }, { "epoch": 6.25, "learning_rate": 1.305008358681556e-05, "loss": 0.178, "step": 3854 }, { "epoch": 6.25, "learning_rate": 1.3040238911990713e-05, "loss": 0.2111, "step": 3855 }, { "epoch": 6.25, "learning_rate": 1.3030396155441004e-05, "loss": 0.2102, "step": 3856 }, { "epoch": 6.25, "learning_rate": 1.3020555319879315e-05, "loss": 0.1316, "step": 3857 }, { "epoch": 6.25, "learning_rate": 1.3010716408018037e-05, "loss": 0.1605, "step": 3858 }, { "epoch": 6.25, "learning_rate": 1.3000879422568993e-05, "loss": 0.1596, "step": 3859 }, { "epoch": 6.26, "learning_rate": 1.2991044366243482e-05, "loss": 0.2158, "step": 3860 }, { "epoch": 6.26, "learning_rate": 1.2981211241752299e-05, "loss": 0.1575, "step": 3861 }, { "epoch": 6.26, "learning_rate": 1.2971380051805673e-05, "loss": 0.1474, "step": 3862 }, { "epoch": 6.26, "learning_rate": 1.2961550799113311e-05, "loss": 0.1291, "step": 3863 }, { "epoch": 6.26, "learning_rate": 1.29517234863844e-05, "loss": 0.1552, "step": 3864 }, { "epoch": 6.26, "learning_rate": 1.2941898116327571e-05, "loss": 0.1399, "step": 3865 }, { "epoch": 6.27, "learning_rate": 1.2932074691650925e-05, "loss": 0.1885, "step": 3866 }, { "epoch": 6.27, "learning_rate": 1.292225321506204e-05, "loss": 0.1915, "step": 3867 }, { "epoch": 6.27, "learning_rate": 1.2912433689267942e-05, "loss": 0.1211, "step": 3868 }, { "epoch": 6.27, "learning_rate": 1.2902616116975133e-05, "loss": 0.1414, "step": 3869 }, { "epoch": 6.27, "learning_rate": 1.289280050088956e-05, "loss": 0.1486, "step": 3870 }, { "epoch": 6.27, "learning_rate": 1.2882986843716636e-05, "loss": 0.17, "step": 3871 }, { "epoch": 6.28, "learning_rate": 1.2873175148161252e-05, "loss": 0.1594, "step": 3872 }, { "epoch": 6.28, "learning_rate": 1.2863365416927735e-05, "loss": 0.1436, "step": 3873 }, { "epoch": 6.28, "learning_rate": 1.2853557652719877e-05, "loss": 0.1394, "step": 3874 }, { "epoch": 6.28, "learning_rate": 1.2843751858240938e-05, "loss": 0.2058, "step": 3875 }, { "epoch": 6.28, "learning_rate": 1.2833948036193613e-05, "loss": 0.135, "step": 3876 }, { "epoch": 6.28, "learning_rate": 1.2824146189280087e-05, "loss": 0.1182, "step": 3877 }, { "epoch": 6.29, "learning_rate": 1.281434632020197e-05, "loss": 0.1263, "step": 3878 }, { "epoch": 6.29, "learning_rate": 1.2804548431660337e-05, "loss": 0.2043, "step": 3879 }, { "epoch": 6.29, "learning_rate": 1.2794752526355727e-05, "loss": 0.1568, "step": 3880 }, { "epoch": 6.29, "learning_rate": 1.2784958606988119e-05, "loss": 0.1457, "step": 3881 }, { "epoch": 6.29, "learning_rate": 1.2775166676256942e-05, "loss": 0.2033, "step": 3882 }, { "epoch": 6.29, "learning_rate": 1.2765376736861097e-05, "loss": 0.1344, "step": 3883 }, { "epoch": 6.29, "learning_rate": 1.275558879149891e-05, "loss": 0.1498, "step": 3884 }, { "epoch": 6.3, "learning_rate": 1.2745802842868184e-05, "loss": 0.1333, "step": 3885 }, { "epoch": 6.3, "learning_rate": 1.2736018893666154e-05, "loss": 0.157, "step": 3886 }, { "epoch": 6.3, "learning_rate": 1.2726236946589504e-05, "loss": 0.1196, "step": 3887 }, { "epoch": 6.3, "learning_rate": 1.2716457004334373e-05, "loss": 0.1821, "step": 3888 }, { "epoch": 6.3, "learning_rate": 1.2706679069596348e-05, "loss": 0.1831, "step": 3889 }, { "epoch": 6.3, "learning_rate": 1.2696903145070447e-05, "loss": 0.1371, "step": 3890 }, { "epoch": 6.31, "learning_rate": 1.2687129233451168e-05, "loss": 0.1826, "step": 3891 }, { "epoch": 6.31, "learning_rate": 1.267735733743242e-05, "loss": 0.1384, "step": 3892 }, { "epoch": 6.31, "learning_rate": 1.2667587459707562e-05, "loss": 0.1567, "step": 3893 }, { "epoch": 6.31, "learning_rate": 1.265781960296942e-05, "loss": 0.1629, "step": 3894 }, { "epoch": 6.31, "learning_rate": 1.264805376991023e-05, "loss": 0.1663, "step": 3895 }, { "epoch": 6.31, "learning_rate": 1.2638289963221704e-05, "loss": 0.133, "step": 3896 }, { "epoch": 6.32, "learning_rate": 1.262852818559497e-05, "loss": 0.1586, "step": 3897 }, { "epoch": 6.32, "learning_rate": 1.2618768439720603e-05, "loss": 0.1393, "step": 3898 }, { "epoch": 6.32, "learning_rate": 1.2609010728288626e-05, "loss": 0.1325, "step": 3899 }, { "epoch": 6.32, "learning_rate": 1.2599255053988494e-05, "loss": 0.1243, "step": 3900 }, { "epoch": 6.32, "learning_rate": 1.2589501419509094e-05, "loss": 0.222, "step": 3901 }, { "epoch": 6.32, "learning_rate": 1.257974982753877e-05, "loss": 0.1821, "step": 3902 }, { "epoch": 6.33, "learning_rate": 1.2570000280765283e-05, "loss": 0.1328, "step": 3903 }, { "epoch": 6.33, "learning_rate": 1.256025278187585e-05, "loss": 0.1147, "step": 3904 }, { "epoch": 6.33, "learning_rate": 1.2550507333557108e-05, "loss": 0.1091, "step": 3905 }, { "epoch": 6.33, "learning_rate": 1.2540763938495127e-05, "loss": 0.1272, "step": 3906 }, { "epoch": 6.33, "learning_rate": 1.2531022599375429e-05, "loss": 0.1755, "step": 3907 }, { "epoch": 6.33, "learning_rate": 1.2521283318882951e-05, "loss": 0.1797, "step": 3908 }, { "epoch": 6.34, "learning_rate": 1.251154609970206e-05, "loss": 0.161, "step": 3909 }, { "epoch": 6.34, "learning_rate": 1.2501810944516585e-05, "loss": 0.1711, "step": 3910 }, { "epoch": 6.34, "learning_rate": 1.2492077856009754e-05, "loss": 0.1053, "step": 3911 }, { "epoch": 6.34, "learning_rate": 1.2482346836864237e-05, "loss": 0.1613, "step": 3912 }, { "epoch": 6.34, "learning_rate": 1.2472617889762135e-05, "loss": 0.167, "step": 3913 }, { "epoch": 6.34, "learning_rate": 1.2462891017384971e-05, "loss": 0.1442, "step": 3914 }, { "epoch": 6.35, "learning_rate": 1.2453166222413713e-05, "loss": 0.174, "step": 3915 }, { "epoch": 6.35, "learning_rate": 1.2443443507528741e-05, "loss": 0.1432, "step": 3916 }, { "epoch": 6.35, "learning_rate": 1.2433722875409857e-05, "loss": 0.1338, "step": 3917 }, { "epoch": 6.35, "learning_rate": 1.2424004328736312e-05, "loss": 0.1397, "step": 3918 }, { "epoch": 6.35, "learning_rate": 1.2414287870186756e-05, "loss": 0.2019, "step": 3919 }, { "epoch": 6.35, "learning_rate": 1.2404573502439274e-05, "loss": 0.1277, "step": 3920 }, { "epoch": 6.35, "learning_rate": 1.2394861228171386e-05, "loss": 0.1631, "step": 3921 }, { "epoch": 6.36, "learning_rate": 1.238515105006002e-05, "loss": 0.1409, "step": 3922 }, { "epoch": 6.36, "learning_rate": 1.2375442970781535e-05, "loss": 0.2253, "step": 3923 }, { "epoch": 6.36, "learning_rate": 1.2365736993011702e-05, "loss": 0.1144, "step": 3924 }, { "epoch": 6.36, "learning_rate": 1.2356033119425717e-05, "loss": 0.1311, "step": 3925 }, { "epoch": 6.36, "learning_rate": 1.2346331352698206e-05, "loss": 0.1258, "step": 3926 }, { "epoch": 6.36, "learning_rate": 1.2336631695503205e-05, "loss": 0.1672, "step": 3927 }, { "epoch": 6.37, "learning_rate": 1.2326934150514153e-05, "loss": 0.2188, "step": 3928 }, { "epoch": 6.37, "learning_rate": 1.2317238720403948e-05, "loss": 0.1544, "step": 3929 }, { "epoch": 6.37, "learning_rate": 1.2307545407844868e-05, "loss": 0.13, "step": 3930 }, { "epoch": 6.37, "learning_rate": 1.2297854215508616e-05, "loss": 0.1662, "step": 3931 }, { "epoch": 6.37, "learning_rate": 1.2288165146066322e-05, "loss": 0.1451, "step": 3932 }, { "epoch": 6.37, "learning_rate": 1.2278478202188514e-05, "loss": 0.1535, "step": 3933 }, { "epoch": 6.38, "learning_rate": 1.2268793386545152e-05, "loss": 0.1351, "step": 3934 }, { "epoch": 6.38, "learning_rate": 1.2259110701805601e-05, "loss": 0.2008, "step": 3935 }, { "epoch": 6.38, "learning_rate": 1.2249430150638632e-05, "loss": 0.1475, "step": 3936 }, { "epoch": 6.38, "learning_rate": 1.223975173571244e-05, "loss": 0.1502, "step": 3937 }, { "epoch": 6.38, "learning_rate": 1.2230075459694626e-05, "loss": 0.1324, "step": 3938 }, { "epoch": 6.38, "learning_rate": 1.2220401325252187e-05, "loss": 0.1399, "step": 3939 }, { "epoch": 6.39, "learning_rate": 1.2210729335051567e-05, "loss": 0.1628, "step": 3940 }, { "epoch": 6.39, "learning_rate": 1.2201059491758578e-05, "loss": 0.1591, "step": 3941 }, { "epoch": 6.39, "learning_rate": 1.2191391798038468e-05, "loss": 0.1387, "step": 3942 }, { "epoch": 6.39, "learning_rate": 1.2181726256555877e-05, "loss": 0.1086, "step": 3943 }, { "epoch": 6.39, "learning_rate": 1.2172062869974853e-05, "loss": 0.1341, "step": 3944 }, { "epoch": 6.39, "learning_rate": 1.2162401640958867e-05, "loss": 0.1335, "step": 3945 }, { "epoch": 6.4, "learning_rate": 1.2152742572170774e-05, "loss": 0.1408, "step": 3946 }, { "epoch": 6.4, "learning_rate": 1.2143085666272845e-05, "loss": 0.1549, "step": 3947 }, { "epoch": 6.4, "learning_rate": 1.2133430925926753e-05, "loss": 0.147, "step": 3948 }, { "epoch": 6.4, "learning_rate": 1.2123778353793572e-05, "loss": 0.1307, "step": 3949 }, { "epoch": 6.4, "learning_rate": 1.2114127952533773e-05, "loss": 0.1417, "step": 3950 }, { "epoch": 6.4, "learning_rate": 1.2104479724807245e-05, "loss": 0.1981, "step": 3951 }, { "epoch": 6.41, "learning_rate": 1.209483367327326e-05, "loss": 0.1134, "step": 3952 }, { "epoch": 6.41, "learning_rate": 1.2085189800590511e-05, "loss": 0.1455, "step": 3953 }, { "epoch": 6.41, "learning_rate": 1.2075548109417073e-05, "loss": 0.1396, "step": 3954 }, { "epoch": 6.41, "learning_rate": 1.2065908602410414e-05, "loss": 0.1397, "step": 3955 }, { "epoch": 6.41, "learning_rate": 1.2056271282227428e-05, "loss": 0.1334, "step": 3956 }, { "epoch": 6.41, "learning_rate": 1.2046636151524376e-05, "loss": 0.1564, "step": 3957 }, { "epoch": 6.41, "learning_rate": 1.2037003212956924e-05, "loss": 0.1492, "step": 3958 }, { "epoch": 6.42, "learning_rate": 1.2027372469180155e-05, "loss": 0.1436, "step": 3959 }, { "epoch": 6.42, "learning_rate": 1.2017743922848518e-05, "loss": 0.1293, "step": 3960 }, { "epoch": 6.42, "learning_rate": 1.2008117576615876e-05, "loss": 0.1308, "step": 3961 }, { "epoch": 6.42, "learning_rate": 1.1998493433135474e-05, "loss": 0.1358, "step": 3962 }, { "epoch": 6.42, "learning_rate": 1.1988871495059946e-05, "loss": 0.1915, "step": 3963 }, { "epoch": 6.42, "learning_rate": 1.1979251765041342e-05, "loss": 0.1288, "step": 3964 }, { "epoch": 6.43, "learning_rate": 1.1969634245731081e-05, "loss": 0.1411, "step": 3965 }, { "epoch": 6.43, "learning_rate": 1.1960018939779977e-05, "loss": 0.1611, "step": 3966 }, { "epoch": 6.43, "learning_rate": 1.1950405849838238e-05, "loss": 0.1731, "step": 3967 }, { "epoch": 6.43, "learning_rate": 1.194079497855546e-05, "loss": 0.1441, "step": 3968 }, { "epoch": 6.43, "learning_rate": 1.1931186328580621e-05, "loss": 0.1405, "step": 3969 }, { "epoch": 6.43, "learning_rate": 1.1921579902562103e-05, "loss": 0.1339, "step": 3970 }, { "epoch": 6.44, "learning_rate": 1.1911975703147657e-05, "loss": 0.1314, "step": 3971 }, { "epoch": 6.44, "learning_rate": 1.1902373732984436e-05, "loss": 0.1456, "step": 3972 }, { "epoch": 6.44, "learning_rate": 1.1892773994718963e-05, "loss": 0.1549, "step": 3973 }, { "epoch": 6.44, "learning_rate": 1.188317649099715e-05, "loss": 0.174, "step": 3974 }, { "epoch": 6.44, "learning_rate": 1.1873581224464308e-05, "loss": 0.1686, "step": 3975 }, { "epoch": 6.44, "learning_rate": 1.1863988197765114e-05, "loss": 0.1817, "step": 3976 }, { "epoch": 6.45, "learning_rate": 1.1854397413543626e-05, "loss": 0.2009, "step": 3977 }, { "epoch": 6.45, "learning_rate": 1.1844808874443307e-05, "loss": 0.1493, "step": 3978 }, { "epoch": 6.45, "learning_rate": 1.1835222583106978e-05, "loss": 0.1645, "step": 3979 }, { "epoch": 6.45, "learning_rate": 1.1825638542176848e-05, "loss": 0.1109, "step": 3980 }, { "epoch": 6.45, "learning_rate": 1.1816056754294505e-05, "loss": 0.1096, "step": 3981 }, { "epoch": 6.45, "learning_rate": 1.1806477222100912e-05, "loss": 0.1605, "step": 3982 }, { "epoch": 6.46, "learning_rate": 1.179689994823643e-05, "loss": 0.1468, "step": 3983 }, { "epoch": 6.46, "learning_rate": 1.1787324935340769e-05, "loss": 0.1226, "step": 3984 }, { "epoch": 6.46, "learning_rate": 1.1777752186053033e-05, "loss": 0.1469, "step": 3985 }, { "epoch": 6.46, "learning_rate": 1.1768181703011703e-05, "loss": 0.1426, "step": 3986 }, { "epoch": 6.46, "learning_rate": 1.175861348885462e-05, "loss": 0.1415, "step": 3987 }, { "epoch": 6.46, "learning_rate": 1.1749047546219026e-05, "loss": 0.161, "step": 3988 }, { "epoch": 6.47, "learning_rate": 1.1739483877741515e-05, "loss": 0.1416, "step": 3989 }, { "epoch": 6.47, "learning_rate": 1.1729922486058057e-05, "loss": 0.1563, "step": 3990 }, { "epoch": 6.47, "learning_rate": 1.1720363373804e-05, "loss": 0.1649, "step": 3991 }, { "epoch": 6.47, "learning_rate": 1.1710806543614066e-05, "loss": 0.159, "step": 3992 }, { "epoch": 6.47, "learning_rate": 1.1701251998122331e-05, "loss": 0.1554, "step": 3993 }, { "epoch": 6.47, "learning_rate": 1.1691699739962275e-05, "loss": 0.1878, "step": 3994 }, { "epoch": 6.47, "learning_rate": 1.1682149771766713e-05, "loss": 0.1584, "step": 3995 }, { "epoch": 6.48, "learning_rate": 1.1672602096167843e-05, "loss": 0.1786, "step": 3996 }, { "epoch": 6.48, "learning_rate": 1.1663056715797233e-05, "loss": 0.2119, "step": 3997 }, { "epoch": 6.48, "learning_rate": 1.1653513633285813e-05, "loss": 0.1176, "step": 3998 }, { "epoch": 6.48, "learning_rate": 1.1643972851263895e-05, "loss": 0.1564, "step": 3999 }, { "epoch": 6.48, "learning_rate": 1.163443437236113e-05, "loss": 0.1403, "step": 4000 }, { "epoch": 6.48, "learning_rate": 1.162489819920655e-05, "loss": 0.1935, "step": 4001 }, { "epoch": 6.49, "learning_rate": 1.1615364334428562e-05, "loss": 0.1685, "step": 4002 }, { "epoch": 6.49, "learning_rate": 1.1605832780654918e-05, "loss": 0.1207, "step": 4003 }, { "epoch": 6.49, "learning_rate": 1.1596303540512733e-05, "loss": 0.1629, "step": 4004 }, { "epoch": 6.49, "learning_rate": 1.1586776616628503e-05, "loss": 0.1356, "step": 4005 }, { "epoch": 6.49, "learning_rate": 1.1577252011628072e-05, "loss": 0.1928, "step": 4006 }, { "epoch": 6.49, "learning_rate": 1.1567729728136646e-05, "loss": 0.1276, "step": 4007 }, { "epoch": 6.5, "learning_rate": 1.155820976877879e-05, "loss": 0.1281, "step": 4008 }, { "epoch": 6.5, "learning_rate": 1.1548692136178424e-05, "loss": 0.1471, "step": 4009 }, { "epoch": 6.5, "learning_rate": 1.1539176832958845e-05, "loss": 0.1602, "step": 4010 }, { "epoch": 6.5, "learning_rate": 1.1529663861742692e-05, "loss": 0.1025, "step": 4011 }, { "epoch": 6.5, "learning_rate": 1.152015322515196e-05, "loss": 0.2284, "step": 4012 }, { "epoch": 6.5, "learning_rate": 1.1510644925808014e-05, "loss": 0.1279, "step": 4013 }, { "epoch": 6.51, "learning_rate": 1.150113896633157e-05, "loss": 0.1399, "step": 4014 }, { "epoch": 6.51, "learning_rate": 1.1491635349342674e-05, "loss": 0.1789, "step": 4015 }, { "epoch": 6.51, "learning_rate": 1.1482134077460776e-05, "loss": 0.1244, "step": 4016 }, { "epoch": 6.51, "learning_rate": 1.1472635153304634e-05, "loss": 0.1313, "step": 4017 }, { "epoch": 6.51, "learning_rate": 1.1463138579492386e-05, "loss": 0.1241, "step": 4018 }, { "epoch": 6.51, "learning_rate": 1.1453644358641509e-05, "loss": 0.1285, "step": 4019 }, { "epoch": 6.52, "learning_rate": 1.1444152493368823e-05, "loss": 0.1646, "step": 4020 }, { "epoch": 6.52, "learning_rate": 1.1434662986290532e-05, "loss": 0.1459, "step": 4021 }, { "epoch": 6.52, "learning_rate": 1.1425175840022163e-05, "loss": 0.2336, "step": 4022 }, { "epoch": 6.52, "learning_rate": 1.1415691057178583e-05, "loss": 0.126, "step": 4023 }, { "epoch": 6.52, "learning_rate": 1.1406208640374047e-05, "loss": 0.178, "step": 4024 }, { "epoch": 6.52, "learning_rate": 1.1396728592222113e-05, "loss": 0.1422, "step": 4025 }, { "epoch": 6.53, "learning_rate": 1.1387250915335724e-05, "loss": 0.1765, "step": 4026 }, { "epoch": 6.53, "learning_rate": 1.1377775612327144e-05, "loss": 0.1616, "step": 4027 }, { "epoch": 6.53, "learning_rate": 1.1368302685807984e-05, "loss": 0.1441, "step": 4028 }, { "epoch": 6.53, "learning_rate": 1.1358832138389223e-05, "loss": 0.1643, "step": 4029 }, { "epoch": 6.53, "learning_rate": 1.134936397268116e-05, "loss": 0.2038, "step": 4030 }, { "epoch": 6.53, "learning_rate": 1.1339898191293446e-05, "loss": 0.1214, "step": 4031 }, { "epoch": 6.53, "learning_rate": 1.1330434796835075e-05, "loss": 0.1205, "step": 4032 }, { "epoch": 6.54, "learning_rate": 1.1320973791914382e-05, "loss": 0.1649, "step": 4033 }, { "epoch": 6.54, "learning_rate": 1.1311515179139038e-05, "loss": 0.2191, "step": 4034 }, { "epoch": 6.54, "learning_rate": 1.1302058961116078e-05, "loss": 0.1289, "step": 4035 }, { "epoch": 6.54, "learning_rate": 1.1292605140451838e-05, "loss": 0.1244, "step": 4036 }, { "epoch": 6.54, "learning_rate": 1.1283153719752036e-05, "loss": 0.1321, "step": 4037 }, { "epoch": 6.54, "learning_rate": 1.1273704701621698e-05, "loss": 0.1374, "step": 4038 }, { "epoch": 6.55, "learning_rate": 1.126425808866519e-05, "loss": 0.1774, "step": 4039 }, { "epoch": 6.55, "learning_rate": 1.1254813883486238e-05, "loss": 0.2217, "step": 4040 }, { "epoch": 6.55, "learning_rate": 1.1245372088687881e-05, "loss": 0.1318, "step": 4041 }, { "epoch": 6.55, "learning_rate": 1.12359327068725e-05, "loss": 0.1358, "step": 4042 }, { "epoch": 6.55, "learning_rate": 1.1226495740641816e-05, "loss": 0.1438, "step": 4043 }, { "epoch": 6.55, "learning_rate": 1.1217061192596869e-05, "loss": 0.1444, "step": 4044 }, { "epoch": 6.56, "learning_rate": 1.1207629065338063e-05, "loss": 0.1466, "step": 4045 }, { "epoch": 6.56, "learning_rate": 1.1198199361465104e-05, "loss": 0.1739, "step": 4046 }, { "epoch": 6.56, "learning_rate": 1.118877208357704e-05, "loss": 0.1117, "step": 4047 }, { "epoch": 6.56, "learning_rate": 1.1179347234272263e-05, "loss": 0.1441, "step": 4048 }, { "epoch": 6.56, "learning_rate": 1.1169924816148475e-05, "loss": 0.1416, "step": 4049 }, { "epoch": 6.56, "learning_rate": 1.1160504831802714e-05, "loss": 0.1392, "step": 4050 }, { "epoch": 6.57, "learning_rate": 1.1151087283831367e-05, "loss": 0.1779, "step": 4051 }, { "epoch": 6.57, "learning_rate": 1.1141672174830127e-05, "loss": 0.1231, "step": 4052 }, { "epoch": 6.57, "learning_rate": 1.1132259507394009e-05, "loss": 0.0944, "step": 4053 }, { "epoch": 6.57, "learning_rate": 1.1122849284117385e-05, "loss": 0.1553, "step": 4054 }, { "epoch": 6.57, "learning_rate": 1.111344150759393e-05, "loss": 0.1874, "step": 4055 }, { "epoch": 6.57, "learning_rate": 1.1104036180416645e-05, "loss": 0.1332, "step": 4056 }, { "epoch": 6.58, "learning_rate": 1.1094633305177864e-05, "loss": 0.1615, "step": 4057 }, { "epoch": 6.58, "learning_rate": 1.1085232884469236e-05, "loss": 0.1328, "step": 4058 }, { "epoch": 6.58, "learning_rate": 1.1075834920881753e-05, "loss": 0.1721, "step": 4059 }, { "epoch": 6.58, "learning_rate": 1.106643941700571e-05, "loss": 0.1894, "step": 4060 }, { "epoch": 6.58, "learning_rate": 1.1057046375430725e-05, "loss": 0.1421, "step": 4061 }, { "epoch": 6.58, "learning_rate": 1.1047655798745752e-05, "loss": 0.13, "step": 4062 }, { "epoch": 6.59, "learning_rate": 1.1038267689539047e-05, "loss": 0.1268, "step": 4063 }, { "epoch": 6.59, "learning_rate": 1.1028882050398209e-05, "loss": 0.1839, "step": 4064 }, { "epoch": 6.59, "learning_rate": 1.101949888391013e-05, "loss": 0.1108, "step": 4065 }, { "epoch": 6.59, "learning_rate": 1.1010118192661036e-05, "loss": 0.122, "step": 4066 }, { "epoch": 6.59, "learning_rate": 1.1000739979236477e-05, "loss": 0.1567, "step": 4067 }, { "epoch": 6.59, "learning_rate": 1.0991364246221301e-05, "loss": 0.1229, "step": 4068 }, { "epoch": 6.59, "learning_rate": 1.0981990996199688e-05, "loss": 0.1325, "step": 4069 }, { "epoch": 6.6, "learning_rate": 1.0972620231755125e-05, "loss": 0.161, "step": 4070 }, { "epoch": 6.6, "learning_rate": 1.0963251955470407e-05, "loss": 0.171, "step": 4071 }, { "epoch": 6.6, "learning_rate": 1.095388616992767e-05, "loss": 0.1576, "step": 4072 }, { "epoch": 6.6, "learning_rate": 1.0944522877708339e-05, "loss": 0.1174, "step": 4073 }, { "epoch": 6.6, "learning_rate": 1.0935162081393154e-05, "loss": 0.1382, "step": 4074 }, { "epoch": 6.6, "learning_rate": 1.0925803783562183e-05, "loss": 0.139, "step": 4075 }, { "epoch": 6.61, "learning_rate": 1.091644798679479e-05, "loss": 0.1531, "step": 4076 }, { "epoch": 6.61, "learning_rate": 1.0907094693669646e-05, "loss": 0.1697, "step": 4077 }, { "epoch": 6.61, "learning_rate": 1.0897743906764757e-05, "loss": 0.1267, "step": 4078 }, { "epoch": 6.61, "learning_rate": 1.0888395628657413e-05, "loss": 0.1931, "step": 4079 }, { "epoch": 6.61, "learning_rate": 1.087904986192422e-05, "loss": 0.1414, "step": 4080 }, { "epoch": 6.61, "learning_rate": 1.0869706609141093e-05, "loss": 0.1453, "step": 4081 }, { "epoch": 6.62, "learning_rate": 1.0860365872883247e-05, "loss": 0.178, "step": 4082 }, { "epoch": 6.62, "learning_rate": 1.0851027655725229e-05, "loss": 0.1721, "step": 4083 }, { "epoch": 6.62, "learning_rate": 1.084169196024086e-05, "loss": 0.1233, "step": 4084 }, { "epoch": 6.62, "learning_rate": 1.083235878900327e-05, "loss": 0.1406, "step": 4085 }, { "epoch": 6.62, "learning_rate": 1.0823028144584924e-05, "loss": 0.1764, "step": 4086 }, { "epoch": 6.62, "learning_rate": 1.081370002955756e-05, "loss": 0.1633, "step": 4087 }, { "epoch": 6.63, "learning_rate": 1.0804374446492212e-05, "loss": 0.1353, "step": 4088 }, { "epoch": 6.63, "learning_rate": 1.0795051397959257e-05, "loss": 0.1414, "step": 4089 }, { "epoch": 6.63, "learning_rate": 1.0785730886528328e-05, "loss": 0.1374, "step": 4090 }, { "epoch": 6.63, "learning_rate": 1.0776412914768395e-05, "loss": 0.1399, "step": 4091 }, { "epoch": 6.63, "learning_rate": 1.0767097485247704e-05, "loss": 0.1758, "step": 4092 }, { "epoch": 6.63, "learning_rate": 1.0757784600533807e-05, "loss": 0.133, "step": 4093 }, { "epoch": 6.64, "learning_rate": 1.074847426319356e-05, "loss": 0.1378, "step": 4094 }, { "epoch": 6.64, "learning_rate": 1.0739166475793108e-05, "loss": 0.1183, "step": 4095 }, { "epoch": 6.64, "learning_rate": 1.0729861240897892e-05, "loss": 0.1706, "step": 4096 }, { "epoch": 6.64, "learning_rate": 1.0720558561072671e-05, "loss": 0.1902, "step": 4097 }, { "epoch": 6.64, "learning_rate": 1.0711258438881477e-05, "loss": 0.1125, "step": 4098 }, { "epoch": 6.64, "learning_rate": 1.0701960876887636e-05, "loss": 0.1442, "step": 4099 }, { "epoch": 6.65, "learning_rate": 1.0692665877653789e-05, "loss": 0.1198, "step": 4100 }, { "epoch": 6.65, "learning_rate": 1.0683373443741846e-05, "loss": 0.1514, "step": 4101 }, { "epoch": 6.65, "learning_rate": 1.0674083577713037e-05, "loss": 0.1576, "step": 4102 }, { "epoch": 6.65, "learning_rate": 1.0664796282127863e-05, "loss": 0.1225, "step": 4103 }, { "epoch": 6.65, "learning_rate": 1.0655511559546121e-05, "loss": 0.1245, "step": 4104 }, { "epoch": 6.65, "learning_rate": 1.0646229412526896e-05, "loss": 0.1164, "step": 4105 }, { "epoch": 6.65, "learning_rate": 1.0636949843628578e-05, "loss": 0.1544, "step": 4106 }, { "epoch": 6.66, "learning_rate": 1.0627672855408819e-05, "loss": 0.1744, "step": 4107 }, { "epoch": 6.66, "learning_rate": 1.0618398450424599e-05, "loss": 0.1532, "step": 4108 }, { "epoch": 6.66, "learning_rate": 1.0609126631232143e-05, "loss": 0.1566, "step": 4109 }, { "epoch": 6.66, "learning_rate": 1.0599857400387003e-05, "loss": 0.1448, "step": 4110 }, { "epoch": 6.66, "learning_rate": 1.059059076044399e-05, "loss": 0.1549, "step": 4111 }, { "epoch": 6.66, "learning_rate": 1.0581326713957203e-05, "loss": 0.1414, "step": 4112 }, { "epoch": 6.67, "learning_rate": 1.0572065263480046e-05, "loss": 0.1336, "step": 4113 }, { "epoch": 6.67, "learning_rate": 1.0562806411565192e-05, "loss": 0.1692, "step": 4114 }, { "epoch": 6.67, "learning_rate": 1.0553550160764583e-05, "loss": 0.1626, "step": 4115 }, { "epoch": 6.67, "learning_rate": 1.0544296513629484e-05, "loss": 0.1315, "step": 4116 }, { "epoch": 6.67, "learning_rate": 1.053504547271041e-05, "loss": 0.1428, "step": 4117 }, { "epoch": 6.67, "learning_rate": 1.0525797040557166e-05, "loss": 0.1214, "step": 4118 }, { "epoch": 6.68, "learning_rate": 1.051655121971884e-05, "loss": 0.1818, "step": 4119 }, { "epoch": 6.68, "learning_rate": 1.050730801274379e-05, "loss": 0.2012, "step": 4120 }, { "epoch": 6.68, "learning_rate": 1.0498067422179683e-05, "loss": 0.108, "step": 4121 }, { "epoch": 6.68, "learning_rate": 1.0488829450573435e-05, "loss": 0.1425, "step": 4122 }, { "epoch": 6.68, "learning_rate": 1.0479594100471237e-05, "loss": 0.1447, "step": 4123 }, { "epoch": 6.68, "learning_rate": 1.0470361374418592e-05, "loss": 0.1555, "step": 4124 }, { "epoch": 6.69, "learning_rate": 1.046113127496025e-05, "loss": 0.1493, "step": 4125 }, { "epoch": 6.69, "learning_rate": 1.0451903804640236e-05, "loss": 0.167, "step": 4126 }, { "epoch": 6.69, "learning_rate": 1.0442678966001873e-05, "loss": 0.1827, "step": 4127 }, { "epoch": 6.69, "learning_rate": 1.0433456761587742e-05, "loss": 0.154, "step": 4128 }, { "epoch": 6.69, "learning_rate": 1.0424237193939696e-05, "loss": 0.1598, "step": 4129 }, { "epoch": 6.69, "learning_rate": 1.0415020265598872e-05, "loss": 0.1586, "step": 4130 }, { "epoch": 6.7, "learning_rate": 1.0405805979105658e-05, "loss": 0.2403, "step": 4131 }, { "epoch": 6.7, "learning_rate": 1.0396594336999758e-05, "loss": 0.1537, "step": 4132 }, { "epoch": 6.7, "learning_rate": 1.0387385341820097e-05, "loss": 0.1403, "step": 4133 }, { "epoch": 6.7, "learning_rate": 1.0378178996104898e-05, "loss": 0.1114, "step": 4134 }, { "epoch": 6.7, "learning_rate": 1.036897530239165e-05, "loss": 0.1623, "step": 4135 }, { "epoch": 6.7, "learning_rate": 1.0359774263217112e-05, "loss": 0.1442, "step": 4136 }, { "epoch": 6.71, "learning_rate": 1.0350575881117298e-05, "loss": 0.1766, "step": 4137 }, { "epoch": 6.71, "learning_rate": 1.0341380158627512e-05, "loss": 0.1286, "step": 4138 }, { "epoch": 6.71, "learning_rate": 1.0332187098282302e-05, "loss": 0.1939, "step": 4139 }, { "epoch": 6.71, "learning_rate": 1.0322996702615509e-05, "loss": 0.2757, "step": 4140 }, { "epoch": 6.71, "learning_rate": 1.031380897416021e-05, "loss": 0.1721, "step": 4141 }, { "epoch": 6.71, "learning_rate": 1.030462391544877e-05, "loss": 0.1729, "step": 4142 }, { "epoch": 6.71, "learning_rate": 1.0295441529012801e-05, "loss": 0.1519, "step": 4143 }, { "epoch": 6.72, "learning_rate": 1.028626181738319e-05, "loss": 0.1441, "step": 4144 }, { "epoch": 6.72, "learning_rate": 1.0277084783090074e-05, "loss": 0.1885, "step": 4145 }, { "epoch": 6.72, "learning_rate": 1.0267910428662878e-05, "loss": 0.2076, "step": 4146 }, { "epoch": 6.72, "learning_rate": 1.0258738756630255e-05, "loss": 0.1528, "step": 4147 }, { "epoch": 6.72, "learning_rate": 1.0249569769520154e-05, "loss": 0.1634, "step": 4148 }, { "epoch": 6.72, "learning_rate": 1.0240403469859753e-05, "loss": 0.2114, "step": 4149 }, { "epoch": 6.73, "learning_rate": 1.0231239860175495e-05, "loss": 0.1199, "step": 4150 }, { "epoch": 6.73, "learning_rate": 1.0222078942993101e-05, "loss": 0.2068, "step": 4151 }, { "epoch": 6.73, "learning_rate": 1.0212920720837535e-05, "loss": 0.1256, "step": 4152 }, { "epoch": 6.73, "learning_rate": 1.020376519623302e-05, "loss": 0.2102, "step": 4153 }, { "epoch": 6.73, "learning_rate": 1.019461237170303e-05, "loss": 0.1785, "step": 4154 }, { "epoch": 6.73, "learning_rate": 1.0185462249770301e-05, "loss": 0.1679, "step": 4155 }, { "epoch": 6.74, "learning_rate": 1.0176314832956824e-05, "loss": 0.171, "step": 4156 }, { "epoch": 6.74, "learning_rate": 1.016717012378385e-05, "loss": 0.15, "step": 4157 }, { "epoch": 6.74, "learning_rate": 1.0158028124771863e-05, "loss": 0.1388, "step": 4158 }, { "epoch": 6.74, "learning_rate": 1.0148888838440636e-05, "loss": 0.1163, "step": 4159 }, { "epoch": 6.74, "learning_rate": 1.0139752267309162e-05, "loss": 0.1346, "step": 4160 }, { "epoch": 6.74, "learning_rate": 1.0130618413895687e-05, "loss": 0.1509, "step": 4161 }, { "epoch": 6.75, "learning_rate": 1.0121487280717734e-05, "loss": 0.1358, "step": 4162 }, { "epoch": 6.75, "learning_rate": 1.0112358870292054e-05, "loss": 0.1314, "step": 4163 }, { "epoch": 6.75, "learning_rate": 1.0103233185134647e-05, "loss": 0.1581, "step": 4164 }, { "epoch": 6.75, "learning_rate": 1.0094110227760776e-05, "loss": 0.1154, "step": 4165 }, { "epoch": 6.75, "learning_rate": 1.0084990000684947e-05, "loss": 0.1853, "step": 4166 }, { "epoch": 6.75, "learning_rate": 1.00758725064209e-05, "loss": 0.1142, "step": 4167 }, { "epoch": 6.76, "learning_rate": 1.006675774748164e-05, "loss": 0.1242, "step": 4168 }, { "epoch": 6.76, "learning_rate": 1.00576457263794e-05, "loss": 0.1528, "step": 4169 }, { "epoch": 6.76, "learning_rate": 1.0048536445625688e-05, "loss": 0.1638, "step": 4170 }, { "epoch": 6.76, "learning_rate": 1.0039429907731227e-05, "loss": 0.1772, "step": 4171 }, { "epoch": 6.76, "learning_rate": 1.0030326115205983e-05, "loss": 0.1459, "step": 4172 }, { "epoch": 6.76, "learning_rate": 1.00212250705592e-05, "loss": 0.1388, "step": 4173 }, { "epoch": 6.76, "learning_rate": 1.001212677629932e-05, "loss": 0.1786, "step": 4174 }, { "epoch": 6.77, "learning_rate": 1.0003031234934068e-05, "loss": 0.1719, "step": 4175 }, { "epoch": 6.77, "learning_rate": 9.993938448970385e-06, "loss": 0.1419, "step": 4176 }, { "epoch": 6.77, "learning_rate": 9.98484842091445e-06, "loss": 0.1755, "step": 4177 }, { "epoch": 6.77, "learning_rate": 9.9757611532717e-06, "loss": 0.1841, "step": 4178 }, { "epoch": 6.77, "learning_rate": 9.966676648546793e-06, "loss": 0.1203, "step": 4179 }, { "epoch": 6.77, "learning_rate": 9.957594909243632e-06, "loss": 0.1802, "step": 4180 }, { "epoch": 6.78, "learning_rate": 9.948515937865375e-06, "loss": 0.1255, "step": 4181 }, { "epoch": 6.78, "learning_rate": 9.939439736914388e-06, "loss": 0.1731, "step": 4182 }, { "epoch": 6.78, "learning_rate": 9.930366308892288e-06, "loss": 0.1835, "step": 4183 }, { "epoch": 6.78, "learning_rate": 9.921295656299934e-06, "loss": 0.1338, "step": 4184 }, { "epoch": 6.78, "learning_rate": 9.912227781637403e-06, "loss": 0.1148, "step": 4185 }, { "epoch": 6.78, "learning_rate": 9.903162687404028e-06, "loss": 0.1262, "step": 4186 }, { "epoch": 6.79, "learning_rate": 9.89410037609836e-06, "loss": 0.1317, "step": 4187 }, { "epoch": 6.79, "learning_rate": 9.885040850218178e-06, "loss": 0.1258, "step": 4188 }, { "epoch": 6.79, "learning_rate": 9.875984112260513e-06, "loss": 0.1648, "step": 4189 }, { "epoch": 6.79, "learning_rate": 9.866930164721615e-06, "loss": 0.1582, "step": 4190 }, { "epoch": 6.79, "learning_rate": 9.857879010096965e-06, "loss": 0.1542, "step": 4191 }, { "epoch": 6.79, "learning_rate": 9.848830650881272e-06, "loss": 0.186, "step": 4192 }, { "epoch": 6.8, "learning_rate": 9.839785089568475e-06, "loss": 0.1196, "step": 4193 }, { "epoch": 6.8, "learning_rate": 9.830742328651759e-06, "loss": 0.1365, "step": 4194 }, { "epoch": 6.8, "learning_rate": 9.821702370623513e-06, "loss": 0.1522, "step": 4195 }, { "epoch": 6.8, "learning_rate": 9.812665217975363e-06, "loss": 0.1674, "step": 4196 }, { "epoch": 6.8, "learning_rate": 9.80363087319817e-06, "loss": 0.1535, "step": 4197 }, { "epoch": 6.8, "learning_rate": 9.794599338782011e-06, "loss": 0.1699, "step": 4198 }, { "epoch": 6.81, "learning_rate": 9.785570617216183e-06, "loss": 0.1757, "step": 4199 }, { "epoch": 6.81, "learning_rate": 9.776544710989226e-06, "loss": 0.119, "step": 4200 }, { "epoch": 6.81, "learning_rate": 9.767521622588891e-06, "loss": 0.1454, "step": 4201 }, { "epoch": 6.81, "learning_rate": 9.758501354502154e-06, "loss": 0.1644, "step": 4202 }, { "epoch": 6.81, "learning_rate": 9.749483909215215e-06, "loss": 0.1411, "step": 4203 }, { "epoch": 6.81, "learning_rate": 9.740469289213487e-06, "loss": 0.1389, "step": 4204 }, { "epoch": 6.82, "learning_rate": 9.731457496981629e-06, "loss": 0.2119, "step": 4205 }, { "epoch": 6.82, "learning_rate": 9.722448535003497e-06, "loss": 0.1752, "step": 4206 }, { "epoch": 6.82, "learning_rate": 9.713442405762166e-06, "loss": 0.107, "step": 4207 }, { "epoch": 6.82, "learning_rate": 9.704439111739954e-06, "loss": 0.1364, "step": 4208 }, { "epoch": 6.82, "learning_rate": 9.695438655418376e-06, "loss": 0.1195, "step": 4209 }, { "epoch": 6.82, "learning_rate": 9.686441039278163e-06, "loss": 0.1185, "step": 4210 }, { "epoch": 6.82, "learning_rate": 9.677446265799283e-06, "loss": 0.1874, "step": 4211 }, { "epoch": 6.83, "learning_rate": 9.668454337460903e-06, "loss": 0.1401, "step": 4212 }, { "epoch": 6.83, "learning_rate": 9.659465256741414e-06, "loss": 0.1089, "step": 4213 }, { "epoch": 6.83, "learning_rate": 9.650479026118423e-06, "loss": 0.1337, "step": 4214 }, { "epoch": 6.83, "learning_rate": 9.641495648068739e-06, "loss": 0.1748, "step": 4215 }, { "epoch": 6.83, "learning_rate": 9.632515125068402e-06, "loss": 0.1699, "step": 4216 }, { "epoch": 6.83, "learning_rate": 9.623537459592654e-06, "loss": 0.1516, "step": 4217 }, { "epoch": 6.84, "learning_rate": 9.614562654115944e-06, "loss": 0.1663, "step": 4218 }, { "epoch": 6.84, "learning_rate": 9.605590711111956e-06, "loss": 0.1065, "step": 4219 }, { "epoch": 6.84, "learning_rate": 9.596621633053564e-06, "loss": 0.1279, "step": 4220 }, { "epoch": 6.84, "learning_rate": 9.587655422412852e-06, "loss": 0.1463, "step": 4221 }, { "epoch": 6.84, "learning_rate": 9.578692081661132e-06, "loss": 0.1464, "step": 4222 }, { "epoch": 6.84, "learning_rate": 9.569731613268898e-06, "loss": 0.1196, "step": 4223 }, { "epoch": 6.85, "learning_rate": 9.560774019705887e-06, "loss": 0.1455, "step": 4224 }, { "epoch": 6.85, "learning_rate": 9.551819303441014e-06, "loss": 0.1308, "step": 4225 }, { "epoch": 6.85, "learning_rate": 9.542867466942409e-06, "loss": 0.1298, "step": 4226 }, { "epoch": 6.85, "learning_rate": 9.533918512677414e-06, "loss": 0.1608, "step": 4227 }, { "epoch": 6.85, "learning_rate": 9.524972443112572e-06, "loss": 0.1759, "step": 4228 }, { "epoch": 6.85, "learning_rate": 9.516029260713622e-06, "loss": 0.1632, "step": 4229 }, { "epoch": 6.86, "learning_rate": 9.507088967945535e-06, "loss": 0.1782, "step": 4230 }, { "epoch": 6.86, "learning_rate": 9.498151567272452e-06, "loss": 0.1087, "step": 4231 }, { "epoch": 6.86, "learning_rate": 9.489217061157744e-06, "loss": 0.1823, "step": 4232 }, { "epoch": 6.86, "learning_rate": 9.48028545206397e-06, "loss": 0.1893, "step": 4233 }, { "epoch": 6.86, "learning_rate": 9.471356742452881e-06, "loss": 0.156, "step": 4234 }, { "epoch": 6.86, "learning_rate": 9.462430934785462e-06, "loss": 0.1597, "step": 4235 }, { "epoch": 6.87, "learning_rate": 9.453508031521866e-06, "loss": 0.1103, "step": 4236 }, { "epoch": 6.87, "learning_rate": 9.444588035121449e-06, "loss": 0.1649, "step": 4237 }, { "epoch": 6.87, "learning_rate": 9.435670948042788e-06, "loss": 0.1395, "step": 4238 }, { "epoch": 6.87, "learning_rate": 9.426756772743637e-06, "loss": 0.1754, "step": 4239 }, { "epoch": 6.87, "learning_rate": 9.417845511680956e-06, "loss": 0.1034, "step": 4240 }, { "epoch": 6.87, "learning_rate": 9.408937167310896e-06, "loss": 0.141, "step": 4241 }, { "epoch": 6.88, "learning_rate": 9.400031742088802e-06, "loss": 0.1581, "step": 4242 }, { "epoch": 6.88, "learning_rate": 9.391129238469236e-06, "loss": 0.1545, "step": 4243 }, { "epoch": 6.88, "learning_rate": 9.382229658905933e-06, "loss": 0.2033, "step": 4244 }, { "epoch": 6.88, "learning_rate": 9.373333005851816e-06, "loss": 0.1833, "step": 4245 }, { "epoch": 6.88, "learning_rate": 9.364439281759033e-06, "loss": 0.1381, "step": 4246 }, { "epoch": 6.88, "learning_rate": 9.355548489078894e-06, "loss": 0.106, "step": 4247 }, { "epoch": 6.88, "learning_rate": 9.346660630261907e-06, "loss": 0.1349, "step": 4248 }, { "epoch": 6.89, "learning_rate": 9.337775707757792e-06, "loss": 0.0912, "step": 4249 }, { "epoch": 6.89, "learning_rate": 9.328893724015436e-06, "loss": 0.1222, "step": 4250 }, { "epoch": 6.89, "learning_rate": 9.320014681482923e-06, "loss": 0.135, "step": 4251 }, { "epoch": 6.89, "learning_rate": 9.311138582607529e-06, "loss": 0.1254, "step": 4252 }, { "epoch": 6.89, "learning_rate": 9.302265429835709e-06, "loss": 0.1195, "step": 4253 }, { "epoch": 6.89, "learning_rate": 9.29339522561313e-06, "loss": 0.1965, "step": 4254 }, { "epoch": 6.9, "learning_rate": 9.284527972384622e-06, "loss": 0.1461, "step": 4255 }, { "epoch": 6.9, "learning_rate": 9.275663672594207e-06, "loss": 0.132, "step": 4256 }, { "epoch": 6.9, "learning_rate": 9.266802328685102e-06, "loss": 0.127, "step": 4257 }, { "epoch": 6.9, "learning_rate": 9.257943943099698e-06, "loss": 0.1178, "step": 4258 }, { "epoch": 6.9, "learning_rate": 9.249088518279585e-06, "loss": 0.1523, "step": 4259 }, { "epoch": 6.9, "learning_rate": 9.240236056665524e-06, "loss": 0.1208, "step": 4260 }, { "epoch": 6.91, "learning_rate": 9.231386560697455e-06, "loss": 0.1213, "step": 4261 }, { "epoch": 6.91, "learning_rate": 9.222540032814522e-06, "loss": 0.1177, "step": 4262 }, { "epoch": 6.91, "learning_rate": 9.21369647545503e-06, "loss": 0.1365, "step": 4263 }, { "epoch": 6.91, "learning_rate": 9.204855891056478e-06, "loss": 0.1262, "step": 4264 }, { "epoch": 6.91, "learning_rate": 9.196018282055535e-06, "loss": 0.1406, "step": 4265 }, { "epoch": 6.91, "learning_rate": 9.187183650888056e-06, "loss": 0.131, "step": 4266 }, { "epoch": 6.92, "learning_rate": 9.17835199998907e-06, "loss": 0.1179, "step": 4267 }, { "epoch": 6.92, "learning_rate": 9.169523331792804e-06, "loss": 0.189, "step": 4268 }, { "epoch": 6.92, "learning_rate": 9.160697648732633e-06, "loss": 0.1855, "step": 4269 }, { "epoch": 6.92, "learning_rate": 9.151874953241138e-06, "loss": 0.1462, "step": 4270 }, { "epoch": 6.92, "learning_rate": 9.143055247750057e-06, "loss": 0.1648, "step": 4271 }, { "epoch": 6.92, "learning_rate": 9.1342385346903e-06, "loss": 0.1428, "step": 4272 }, { "epoch": 6.93, "learning_rate": 9.125424816491981e-06, "loss": 0.1708, "step": 4273 }, { "epoch": 6.93, "learning_rate": 9.116614095584361e-06, "loss": 0.2131, "step": 4274 }, { "epoch": 6.93, "learning_rate": 9.107806374395882e-06, "loss": 0.1604, "step": 4275 }, { "epoch": 6.93, "learning_rate": 9.09900165535416e-06, "loss": 0.1108, "step": 4276 }, { "epoch": 6.93, "learning_rate": 9.09019994088598e-06, "loss": 0.152, "step": 4277 }, { "epoch": 6.93, "learning_rate": 9.081401233417315e-06, "loss": 0.1843, "step": 4278 }, { "epoch": 6.94, "learning_rate": 9.07260553537329e-06, "loss": 0.1758, "step": 4279 }, { "epoch": 6.94, "learning_rate": 9.063812849178205e-06, "loss": 0.1096, "step": 4280 }, { "epoch": 6.94, "learning_rate": 9.055023177255542e-06, "loss": 0.1562, "step": 4281 }, { "epoch": 6.94, "learning_rate": 9.046236522027939e-06, "loss": 0.1639, "step": 4282 }, { "epoch": 6.94, "learning_rate": 9.037452885917197e-06, "loss": 0.1404, "step": 4283 }, { "epoch": 6.94, "learning_rate": 9.02867227134431e-06, "loss": 0.1484, "step": 4284 }, { "epoch": 6.94, "learning_rate": 9.019894680729417e-06, "loss": 0.1665, "step": 4285 }, { "epoch": 6.95, "learning_rate": 9.01112011649182e-06, "loss": 0.1304, "step": 4286 }, { "epoch": 6.95, "learning_rate": 9.002348581050016e-06, "loss": 0.1368, "step": 4287 }, { "epoch": 6.95, "learning_rate": 8.993580076821635e-06, "loss": 0.1472, "step": 4288 }, { "epoch": 6.95, "learning_rate": 8.98481460622349e-06, "loss": 0.1556, "step": 4289 }, { "epoch": 6.95, "learning_rate": 8.97605217167155e-06, "loss": 0.1896, "step": 4290 }, { "epoch": 6.95, "learning_rate": 8.96729277558094e-06, "loss": 0.2217, "step": 4291 }, { "epoch": 6.96, "learning_rate": 8.958536420365978e-06, "loss": 0.2246, "step": 4292 }, { "epoch": 6.96, "learning_rate": 8.949783108440111e-06, "loss": 0.1652, "step": 4293 }, { "epoch": 6.96, "learning_rate": 8.941032842215951e-06, "loss": 0.1691, "step": 4294 }, { "epoch": 6.96, "learning_rate": 8.932285624105298e-06, "loss": 0.1135, "step": 4295 }, { "epoch": 6.96, "learning_rate": 8.923541456519075e-06, "loss": 0.1697, "step": 4296 }, { "epoch": 6.96, "learning_rate": 8.914800341867398e-06, "loss": 0.2016, "step": 4297 }, { "epoch": 6.97, "learning_rate": 8.906062282559516e-06, "loss": 0.1728, "step": 4298 }, { "epoch": 6.97, "learning_rate": 8.897327281003838e-06, "loss": 0.1199, "step": 4299 }, { "epoch": 6.97, "learning_rate": 8.888595339607961e-06, "loss": 0.1124, "step": 4300 }, { "epoch": 6.97, "learning_rate": 8.879866460778595e-06, "loss": 0.133, "step": 4301 }, { "epoch": 6.97, "learning_rate": 8.871140646921622e-06, "loss": 0.186, "step": 4302 }, { "epoch": 6.97, "learning_rate": 8.862417900442098e-06, "loss": 0.2452, "step": 4303 }, { "epoch": 6.98, "learning_rate": 8.853698223744213e-06, "loss": 0.1537, "step": 4304 }, { "epoch": 6.98, "learning_rate": 8.84498161923131e-06, "loss": 0.1269, "step": 4305 }, { "epoch": 6.98, "learning_rate": 8.836268089305904e-06, "loss": 0.1724, "step": 4306 }, { "epoch": 6.98, "learning_rate": 8.827557636369638e-06, "loss": 0.1464, "step": 4307 }, { "epoch": 6.98, "learning_rate": 8.818850262823335e-06, "loss": 0.1348, "step": 4308 }, { "epoch": 6.98, "learning_rate": 8.810145971066943e-06, "loss": 0.1291, "step": 4309 }, { "epoch": 6.99, "learning_rate": 8.801444763499565e-06, "loss": 0.2629, "step": 4310 }, { "epoch": 6.99, "learning_rate": 8.792746642519474e-06, "loss": 0.1617, "step": 4311 }, { "epoch": 6.99, "learning_rate": 8.784051610524074e-06, "loss": 0.137, "step": 4312 }, { "epoch": 6.99, "learning_rate": 8.775359669909917e-06, "loss": 0.137, "step": 4313 }, { "epoch": 6.99, "learning_rate": 8.766670823072714e-06, "loss": 0.1372, "step": 4314 }, { "epoch": 6.99, "learning_rate": 8.757985072407304e-06, "loss": 0.1293, "step": 4315 }, { "epoch": 7.0, "learning_rate": 8.749302420307704e-06, "loss": 0.1198, "step": 4316 }, { "epoch": 7.0, "learning_rate": 8.74062286916705e-06, "loss": 0.2316, "step": 4317 }, { "epoch": 7.0, "learning_rate": 8.731946421377627e-06, "loss": 0.1424, "step": 4318 }, { "epoch": 7.0, "learning_rate": 8.723273079330881e-06, "loss": 0.1189, "step": 4319 }, { "epoch": 7.0, "learning_rate": 8.714602845417384e-06, "loss": 0.1072, "step": 4320 }, { "epoch": 7.0, "learning_rate": 8.70593572202685e-06, "loss": 0.1218, "step": 4321 }, { "epoch": 7.0, "learning_rate": 8.697271711548163e-06, "loss": 0.1042, "step": 4322 }, { "epoch": 7.01, "learning_rate": 8.688610816369319e-06, "loss": 0.0914, "step": 4323 }, { "epoch": 7.01, "learning_rate": 8.679953038877455e-06, "loss": 0.0845, "step": 4324 }, { "epoch": 7.01, "learning_rate": 8.671298381458881e-06, "loss": 0.1214, "step": 4325 }, { "epoch": 7.01, "learning_rate": 8.662646846499017e-06, "loss": 0.1129, "step": 4326 }, { "epoch": 7.01, "learning_rate": 8.653998436382426e-06, "loss": 0.154, "step": 4327 }, { "epoch": 7.01, "learning_rate": 8.64535315349282e-06, "loss": 0.093, "step": 4328 }, { "epoch": 7.02, "learning_rate": 8.636711000213039e-06, "loss": 0.1096, "step": 4329 }, { "epoch": 7.02, "learning_rate": 8.62807197892507e-06, "loss": 0.1172, "step": 4330 }, { "epoch": 7.02, "learning_rate": 8.619436092010034e-06, "loss": 0.1407, "step": 4331 }, { "epoch": 7.02, "learning_rate": 8.610803341848175e-06, "loss": 0.1099, "step": 4332 }, { "epoch": 7.02, "learning_rate": 8.602173730818899e-06, "loss": 0.2274, "step": 4333 }, { "epoch": 7.02, "learning_rate": 8.593547261300716e-06, "loss": 0.1943, "step": 4334 }, { "epoch": 7.03, "learning_rate": 8.5849239356713e-06, "loss": 0.1146, "step": 4335 }, { "epoch": 7.03, "learning_rate": 8.576303756307437e-06, "loss": 0.1332, "step": 4336 }, { "epoch": 7.03, "learning_rate": 8.567686725585056e-06, "loss": 0.1462, "step": 4337 }, { "epoch": 7.03, "learning_rate": 8.559072845879211e-06, "loss": 0.1129, "step": 4338 }, { "epoch": 7.03, "learning_rate": 8.55046211956409e-06, "loss": 0.0872, "step": 4339 }, { "epoch": 7.03, "learning_rate": 8.541854549013008e-06, "loss": 0.151, "step": 4340 }, { "epoch": 7.04, "learning_rate": 8.533250136598435e-06, "loss": 0.1072, "step": 4341 }, { "epoch": 7.04, "learning_rate": 8.524648884691935e-06, "loss": 0.1214, "step": 4342 }, { "epoch": 7.04, "learning_rate": 8.516050795664217e-06, "loss": 0.1524, "step": 4343 }, { "epoch": 7.04, "learning_rate": 8.507455871885126e-06, "loss": 0.1155, "step": 4344 }, { "epoch": 7.04, "learning_rate": 8.498864115723617e-06, "loss": 0.0963, "step": 4345 }, { "epoch": 7.04, "learning_rate": 8.490275529547798e-06, "loss": 0.0986, "step": 4346 }, { "epoch": 7.05, "learning_rate": 8.481690115724872e-06, "loss": 0.1325, "step": 4347 }, { "epoch": 7.05, "learning_rate": 8.473107876621183e-06, "loss": 0.176, "step": 4348 }, { "epoch": 7.05, "learning_rate": 8.46452881460221e-06, "loss": 0.1579, "step": 4349 }, { "epoch": 7.05, "learning_rate": 8.455952932032541e-06, "loss": 0.1238, "step": 4350 }, { "epoch": 7.05, "learning_rate": 8.447380231275889e-06, "loss": 0.2072, "step": 4351 }, { "epoch": 7.05, "learning_rate": 8.438810714695097e-06, "loss": 0.1095, "step": 4352 }, { "epoch": 7.06, "learning_rate": 8.430244384652115e-06, "loss": 0.1205, "step": 4353 }, { "epoch": 7.06, "learning_rate": 8.421681243508048e-06, "loss": 0.1225, "step": 4354 }, { "epoch": 7.06, "learning_rate": 8.41312129362309e-06, "loss": 0.1083, "step": 4355 }, { "epoch": 7.06, "learning_rate": 8.404564537356557e-06, "loss": 0.1129, "step": 4356 }, { "epoch": 7.06, "learning_rate": 8.39601097706691e-06, "loss": 0.093, "step": 4357 }, { "epoch": 7.06, "learning_rate": 8.387460615111707e-06, "loss": 0.1709, "step": 4358 }, { "epoch": 7.06, "learning_rate": 8.378913453847622e-06, "loss": 0.1071, "step": 4359 }, { "epoch": 7.07, "learning_rate": 8.370369495630469e-06, "loss": 0.1455, "step": 4360 }, { "epoch": 7.07, "learning_rate": 8.361828742815157e-06, "loss": 0.1484, "step": 4361 }, { "epoch": 7.07, "learning_rate": 8.353291197755724e-06, "loss": 0.1251, "step": 4362 }, { "epoch": 7.07, "learning_rate": 8.344756862805319e-06, "loss": 0.1553, "step": 4363 }, { "epoch": 7.07, "learning_rate": 8.336225740316195e-06, "loss": 0.143, "step": 4364 }, { "epoch": 7.07, "learning_rate": 8.327697832639752e-06, "loss": 0.0983, "step": 4365 }, { "epoch": 7.08, "learning_rate": 8.319173142126473e-06, "loss": 0.0945, "step": 4366 }, { "epoch": 7.08, "learning_rate": 8.310651671125958e-06, "loss": 0.1163, "step": 4367 }, { "epoch": 7.08, "learning_rate": 8.30213342198694e-06, "loss": 0.1459, "step": 4368 }, { "epoch": 7.08, "learning_rate": 8.293618397057245e-06, "loss": 0.1281, "step": 4369 }, { "epoch": 7.08, "learning_rate": 8.28510659868381e-06, "loss": 0.1216, "step": 4370 }, { "epoch": 7.08, "learning_rate": 8.276598029212698e-06, "loss": 0.1514, "step": 4371 }, { "epoch": 7.09, "learning_rate": 8.268092690989063e-06, "loss": 0.1039, "step": 4372 }, { "epoch": 7.09, "learning_rate": 8.259590586357186e-06, "loss": 0.1634, "step": 4373 }, { "epoch": 7.09, "learning_rate": 8.251091717660449e-06, "loss": 0.1275, "step": 4374 }, { "epoch": 7.09, "learning_rate": 8.242596087241336e-06, "loss": 0.1022, "step": 4375 }, { "epoch": 7.09, "learning_rate": 8.234103697441446e-06, "loss": 0.1545, "step": 4376 }, { "epoch": 7.09, "learning_rate": 8.225614550601483e-06, "loss": 0.0865, "step": 4377 }, { "epoch": 7.1, "learning_rate": 8.217128649061252e-06, "loss": 0.0781, "step": 4378 }, { "epoch": 7.1, "learning_rate": 8.208645995159678e-06, "loss": 0.1142, "step": 4379 }, { "epoch": 7.1, "learning_rate": 8.200166591234772e-06, "loss": 0.1149, "step": 4380 }, { "epoch": 7.1, "learning_rate": 8.191690439623672e-06, "loss": 0.1466, "step": 4381 }, { "epoch": 7.1, "learning_rate": 8.183217542662596e-06, "loss": 0.1406, "step": 4382 }, { "epoch": 7.1, "learning_rate": 8.174747902686871e-06, "loss": 0.094, "step": 4383 }, { "epoch": 7.11, "learning_rate": 8.166281522030945e-06, "loss": 0.1025, "step": 4384 }, { "epoch": 7.11, "learning_rate": 8.157818403028343e-06, "loss": 0.1283, "step": 4385 }, { "epoch": 7.11, "learning_rate": 8.149358548011706e-06, "loss": 0.1657, "step": 4386 }, { "epoch": 7.11, "learning_rate": 8.140901959312768e-06, "loss": 0.091, "step": 4387 }, { "epoch": 7.11, "learning_rate": 8.132448639262362e-06, "loss": 0.1113, "step": 4388 }, { "epoch": 7.11, "learning_rate": 8.123998590190423e-06, "loss": 0.132, "step": 4389 }, { "epoch": 7.12, "learning_rate": 8.115551814425995e-06, "loss": 0.1951, "step": 4390 }, { "epoch": 7.12, "learning_rate": 8.107108314297194e-06, "loss": 0.1376, "step": 4391 }, { "epoch": 7.12, "learning_rate": 8.098668092131267e-06, "loss": 0.2173, "step": 4392 }, { "epoch": 7.12, "learning_rate": 8.09023115025453e-06, "loss": 0.1593, "step": 4393 }, { "epoch": 7.12, "learning_rate": 8.081797490992398e-06, "loss": 0.1622, "step": 4394 }, { "epoch": 7.12, "learning_rate": 8.0733671166694e-06, "loss": 0.1218, "step": 4395 }, { "epoch": 7.12, "learning_rate": 8.06494002960914e-06, "loss": 0.1348, "step": 4396 }, { "epoch": 7.13, "learning_rate": 8.05651623213432e-06, "loss": 0.141, "step": 4397 }, { "epoch": 7.13, "learning_rate": 8.048095726566746e-06, "loss": 0.1407, "step": 4398 }, { "epoch": 7.13, "learning_rate": 8.039678515227304e-06, "loss": 0.1574, "step": 4399 }, { "epoch": 7.13, "learning_rate": 8.031264600435981e-06, "loss": 0.1346, "step": 4400 }, { "epoch": 7.13, "learning_rate": 8.022853984511847e-06, "loss": 0.1201, "step": 4401 }, { "epoch": 7.13, "learning_rate": 8.014446669773061e-06, "loss": 0.1235, "step": 4402 }, { "epoch": 7.14, "learning_rate": 8.006042658536894e-06, "loss": 0.1245, "step": 4403 }, { "epoch": 7.14, "learning_rate": 7.997641953119682e-06, "loss": 0.1977, "step": 4404 }, { "epoch": 7.14, "learning_rate": 7.989244555836852e-06, "loss": 0.1228, "step": 4405 }, { "epoch": 7.14, "learning_rate": 7.980850469002939e-06, "loss": 0.1001, "step": 4406 }, { "epoch": 7.14, "learning_rate": 7.972459694931547e-06, "loss": 0.1393, "step": 4407 }, { "epoch": 7.14, "learning_rate": 7.964072235935363e-06, "loss": 0.2237, "step": 4408 }, { "epoch": 7.15, "learning_rate": 7.955688094326187e-06, "loss": 0.1427, "step": 4409 }, { "epoch": 7.15, "learning_rate": 7.947307272414874e-06, "loss": 0.1381, "step": 4410 }, { "epoch": 7.15, "learning_rate": 7.938929772511385e-06, "loss": 0.1385, "step": 4411 }, { "epoch": 7.15, "learning_rate": 7.930555596924752e-06, "loss": 0.1091, "step": 4412 }, { "epoch": 7.15, "learning_rate": 7.92218474796309e-06, "loss": 0.1135, "step": 4413 }, { "epoch": 7.15, "learning_rate": 7.91381722793362e-06, "loss": 0.1138, "step": 4414 }, { "epoch": 7.16, "learning_rate": 7.905453039142621e-06, "loss": 0.1227, "step": 4415 }, { "epoch": 7.16, "learning_rate": 7.897092183895451e-06, "loss": 0.0939, "step": 4416 }, { "epoch": 7.16, "learning_rate": 7.88873466449658e-06, "loss": 0.1137, "step": 4417 }, { "epoch": 7.16, "learning_rate": 7.880380483249519e-06, "loss": 0.1513, "step": 4418 }, { "epoch": 7.16, "learning_rate": 7.872029642456895e-06, "loss": 0.218, "step": 4419 }, { "epoch": 7.16, "learning_rate": 7.863682144420393e-06, "loss": 0.1066, "step": 4420 }, { "epoch": 7.17, "learning_rate": 7.855337991440767e-06, "loss": 0.1568, "step": 4421 }, { "epoch": 7.17, "learning_rate": 7.846997185817886e-06, "loss": 0.1656, "step": 4422 }, { "epoch": 7.17, "learning_rate": 7.838659729850662e-06, "loss": 0.1489, "step": 4423 }, { "epoch": 7.17, "learning_rate": 7.830325625837097e-06, "loss": 0.1165, "step": 4424 }, { "epoch": 7.17, "learning_rate": 7.821994876074264e-06, "loss": 0.1216, "step": 4425 }, { "epoch": 7.17, "learning_rate": 7.81366748285832e-06, "loss": 0.0883, "step": 4426 }, { "epoch": 7.18, "learning_rate": 7.805343448484481e-06, "loss": 0.1054, "step": 4427 }, { "epoch": 7.18, "learning_rate": 7.797022775247068e-06, "loss": 0.1, "step": 4428 }, { "epoch": 7.18, "learning_rate": 7.788705465439435e-06, "loss": 0.133, "step": 4429 }, { "epoch": 7.18, "learning_rate": 7.780391521354047e-06, "loss": 0.0917, "step": 4430 }, { "epoch": 7.18, "learning_rate": 7.772080945282418e-06, "loss": 0.0948, "step": 4431 }, { "epoch": 7.18, "learning_rate": 7.76377373951513e-06, "loss": 0.1258, "step": 4432 }, { "epoch": 7.18, "learning_rate": 7.755469906341863e-06, "loss": 0.0894, "step": 4433 }, { "epoch": 7.19, "learning_rate": 7.747169448051341e-06, "loss": 0.1073, "step": 4434 }, { "epoch": 7.19, "learning_rate": 7.738872366931369e-06, "loss": 0.1192, "step": 4435 }, { "epoch": 7.19, "learning_rate": 7.730578665268815e-06, "loss": 0.1638, "step": 4436 }, { "epoch": 7.19, "learning_rate": 7.722288345349618e-06, "loss": 0.1281, "step": 4437 }, { "epoch": 7.19, "learning_rate": 7.714001409458798e-06, "loss": 0.1975, "step": 4438 }, { "epoch": 7.19, "learning_rate": 7.705717859880424e-06, "loss": 0.1698, "step": 4439 }, { "epoch": 7.2, "learning_rate": 7.697437698897632e-06, "loss": 0.1468, "step": 4440 }, { "epoch": 7.2, "learning_rate": 7.689160928792645e-06, "loss": 0.1353, "step": 4441 }, { "epoch": 7.2, "learning_rate": 7.68088755184673e-06, "loss": 0.1223, "step": 4442 }, { "epoch": 7.2, "learning_rate": 7.672617570340218e-06, "loss": 0.1517, "step": 4443 }, { "epoch": 7.2, "learning_rate": 7.664350986552527e-06, "loss": 0.1192, "step": 4444 }, { "epoch": 7.2, "learning_rate": 7.656087802762107e-06, "loss": 0.1265, "step": 4445 }, { "epoch": 7.21, "learning_rate": 7.647828021246503e-06, "loss": 0.1516, "step": 4446 }, { "epoch": 7.21, "learning_rate": 7.639571644282302e-06, "loss": 0.1552, "step": 4447 }, { "epoch": 7.21, "learning_rate": 7.631318674145154e-06, "loss": 0.1245, "step": 4448 }, { "epoch": 7.21, "learning_rate": 7.6230691131097755e-06, "loss": 0.153, "step": 4449 }, { "epoch": 7.21, "learning_rate": 7.6148229634499396e-06, "loss": 0.0966, "step": 4450 }, { "epoch": 7.21, "learning_rate": 7.606580227438471e-06, "loss": 0.185, "step": 4451 }, { "epoch": 7.22, "learning_rate": 7.5983409073472835e-06, "loss": 0.1559, "step": 4452 }, { "epoch": 7.22, "learning_rate": 7.590105005447317e-06, "loss": 0.1049, "step": 4453 }, { "epoch": 7.22, "learning_rate": 7.581872524008574e-06, "loss": 0.1852, "step": 4454 }, { "epoch": 7.22, "learning_rate": 7.5736434653001404e-06, "loss": 0.112, "step": 4455 }, { "epoch": 7.22, "learning_rate": 7.565417831590121e-06, "loss": 0.1174, "step": 4456 }, { "epoch": 7.22, "learning_rate": 7.55719562514571e-06, "loss": 0.1192, "step": 4457 }, { "epoch": 7.23, "learning_rate": 7.548976848233138e-06, "loss": 0.1599, "step": 4458 }, { "epoch": 7.23, "learning_rate": 7.540761503117693e-06, "loss": 0.149, "step": 4459 }, { "epoch": 7.23, "learning_rate": 7.532549592063718e-06, "loss": 0.1471, "step": 4460 }, { "epoch": 7.23, "learning_rate": 7.524341117334613e-06, "loss": 0.1267, "step": 4461 }, { "epoch": 7.23, "learning_rate": 7.516136081192819e-06, "loss": 0.1265, "step": 4462 }, { "epoch": 7.23, "learning_rate": 7.507934485899855e-06, "loss": 0.1174, "step": 4463 }, { "epoch": 7.24, "learning_rate": 7.499736333716257e-06, "loss": 0.1204, "step": 4464 }, { "epoch": 7.24, "learning_rate": 7.491541626901648e-06, "loss": 0.1322, "step": 4465 }, { "epoch": 7.24, "learning_rate": 7.4833503677146725e-06, "loss": 0.13, "step": 4466 }, { "epoch": 7.24, "learning_rate": 7.4751625584130335e-06, "loss": 0.1275, "step": 4467 }, { "epoch": 7.24, "learning_rate": 7.4669782012534965e-06, "loss": 0.1602, "step": 4468 }, { "epoch": 7.24, "learning_rate": 7.458797298491856e-06, "loss": 0.1277, "step": 4469 }, { "epoch": 7.24, "learning_rate": 7.450619852382959e-06, "loss": 0.1277, "step": 4470 }, { "epoch": 7.25, "learning_rate": 7.442445865180714e-06, "loss": 0.1194, "step": 4471 }, { "epoch": 7.25, "learning_rate": 7.434275339138062e-06, "loss": 0.097, "step": 4472 }, { "epoch": 7.25, "learning_rate": 7.4261082765069915e-06, "loss": 0.1667, "step": 4473 }, { "epoch": 7.25, "learning_rate": 7.41794467953854e-06, "loss": 0.1882, "step": 4474 }, { "epoch": 7.25, "learning_rate": 7.409784550482779e-06, "loss": 0.1142, "step": 4475 }, { "epoch": 7.25, "learning_rate": 7.40162789158885e-06, "loss": 0.1065, "step": 4476 }, { "epoch": 7.26, "learning_rate": 7.393474705104915e-06, "loss": 0.1044, "step": 4477 }, { "epoch": 7.26, "learning_rate": 7.3853249932781755e-06, "loss": 0.1157, "step": 4478 }, { "epoch": 7.26, "learning_rate": 7.377178758354901e-06, "loss": 0.1336, "step": 4479 }, { "epoch": 7.26, "learning_rate": 7.3690360025803785e-06, "loss": 0.0784, "step": 4480 }, { "epoch": 7.26, "learning_rate": 7.360896728198941e-06, "loss": 0.1123, "step": 4481 }, { "epoch": 7.26, "learning_rate": 7.352760937453975e-06, "loss": 0.1092, "step": 4482 }, { "epoch": 7.27, "learning_rate": 7.3446286325878955e-06, "loss": 0.1178, "step": 4483 }, { "epoch": 7.27, "learning_rate": 7.336499815842153e-06, "loss": 0.1541, "step": 4484 }, { "epoch": 7.27, "learning_rate": 7.328374489457246e-06, "loss": 0.099, "step": 4485 }, { "epoch": 7.27, "learning_rate": 7.320252655672697e-06, "loss": 0.1186, "step": 4486 }, { "epoch": 7.27, "learning_rate": 7.312134316727093e-06, "loss": 0.1177, "step": 4487 }, { "epoch": 7.27, "learning_rate": 7.3040194748580325e-06, "loss": 0.1051, "step": 4488 }, { "epoch": 7.28, "learning_rate": 7.2959081323021495e-06, "loss": 0.0951, "step": 4489 }, { "epoch": 7.28, "learning_rate": 7.2878002912951395e-06, "loss": 0.1363, "step": 4490 }, { "epoch": 7.28, "learning_rate": 7.279695954071706e-06, "loss": 0.1273, "step": 4491 }, { "epoch": 7.28, "learning_rate": 7.271595122865591e-06, "loss": 0.1038, "step": 4492 }, { "epoch": 7.28, "learning_rate": 7.263497799909589e-06, "loss": 0.0971, "step": 4493 }, { "epoch": 7.28, "learning_rate": 7.2554039874355005e-06, "loss": 0.1696, "step": 4494 }, { "epoch": 7.29, "learning_rate": 7.247313687674184e-06, "loss": 0.1106, "step": 4495 }, { "epoch": 7.29, "learning_rate": 7.239226902855514e-06, "loss": 0.1315, "step": 4496 }, { "epoch": 7.29, "learning_rate": 7.2311436352084e-06, "loss": 0.1089, "step": 4497 }, { "epoch": 7.29, "learning_rate": 7.223063886960779e-06, "loss": 0.1276, "step": 4498 }, { "epoch": 7.29, "learning_rate": 7.214987660339623e-06, "loss": 0.1092, "step": 4499 }, { "epoch": 7.29, "learning_rate": 7.206914957570925e-06, "loss": 0.1246, "step": 4500 }, { "epoch": 7.29, "learning_rate": 7.198845780879726e-06, "loss": 0.1326, "step": 4501 }, { "epoch": 7.3, "learning_rate": 7.190780132490071e-06, "loss": 0.1915, "step": 4502 }, { "epoch": 7.3, "learning_rate": 7.182718014625054e-06, "loss": 0.1128, "step": 4503 }, { "epoch": 7.3, "learning_rate": 7.1746594295067826e-06, "loss": 0.1253, "step": 4504 }, { "epoch": 7.3, "learning_rate": 7.166604379356386e-06, "loss": 0.1214, "step": 4505 }, { "epoch": 7.3, "learning_rate": 7.1585528663940375e-06, "loss": 0.1694, "step": 4506 }, { "epoch": 7.3, "learning_rate": 7.150504892838921e-06, "loss": 0.1913, "step": 4507 }, { "epoch": 7.31, "learning_rate": 7.142460460909251e-06, "loss": 0.1083, "step": 4508 }, { "epoch": 7.31, "learning_rate": 7.134419572822257e-06, "loss": 0.1308, "step": 4509 }, { "epoch": 7.31, "learning_rate": 7.1263822307942045e-06, "loss": 0.1305, "step": 4510 }, { "epoch": 7.31, "learning_rate": 7.118348437040367e-06, "loss": 0.0924, "step": 4511 }, { "epoch": 7.31, "learning_rate": 7.110318193775061e-06, "loss": 0.1369, "step": 4512 }, { "epoch": 7.31, "learning_rate": 7.102291503211598e-06, "loss": 0.1349, "step": 4513 }, { "epoch": 7.32, "learning_rate": 7.09426836756234e-06, "loss": 0.1339, "step": 4514 }, { "epoch": 7.32, "learning_rate": 7.086248789038643e-06, "loss": 0.108, "step": 4515 }, { "epoch": 7.32, "learning_rate": 7.078232769850892e-06, "loss": 0.1083, "step": 4516 }, { "epoch": 7.32, "learning_rate": 7.0702203122085e-06, "loss": 0.1296, "step": 4517 }, { "epoch": 7.32, "learning_rate": 7.062211418319884e-06, "loss": 0.1468, "step": 4518 }, { "epoch": 7.32, "learning_rate": 7.054206090392481e-06, "loss": 0.1447, "step": 4519 }, { "epoch": 7.33, "learning_rate": 7.046204330632762e-06, "loss": 0.1297, "step": 4520 }, { "epoch": 7.33, "learning_rate": 7.0382061412461935e-06, "loss": 0.1613, "step": 4521 }, { "epoch": 7.33, "learning_rate": 7.030211524437267e-06, "loss": 0.1501, "step": 4522 }, { "epoch": 7.33, "learning_rate": 7.022220482409488e-06, "loss": 0.1503, "step": 4523 }, { "epoch": 7.33, "learning_rate": 7.014233017365368e-06, "loss": 0.1925, "step": 4524 }, { "epoch": 7.33, "learning_rate": 7.006249131506462e-06, "loss": 0.1507, "step": 4525 }, { "epoch": 7.34, "learning_rate": 6.998268827033303e-06, "loss": 0.1948, "step": 4526 }, { "epoch": 7.34, "learning_rate": 6.990292106145453e-06, "loss": 0.1341, "step": 4527 }, { "epoch": 7.34, "learning_rate": 6.982318971041495e-06, "loss": 0.1551, "step": 4528 }, { "epoch": 7.34, "learning_rate": 6.974349423919007e-06, "loss": 0.0983, "step": 4529 }, { "epoch": 7.34, "learning_rate": 6.966383466974578e-06, "loss": 0.1594, "step": 4530 }, { "epoch": 7.34, "learning_rate": 6.9584211024038296e-06, "loss": 0.1434, "step": 4531 }, { "epoch": 7.35, "learning_rate": 6.950462332401371e-06, "loss": 0.1065, "step": 4532 }, { "epoch": 7.35, "learning_rate": 6.942507159160827e-06, "loss": 0.1598, "step": 4533 }, { "epoch": 7.35, "learning_rate": 6.934555584874834e-06, "loss": 0.1197, "step": 4534 }, { "epoch": 7.35, "learning_rate": 6.926607611735025e-06, "loss": 0.1052, "step": 4535 }, { "epoch": 7.35, "learning_rate": 6.918663241932067e-06, "loss": 0.1151, "step": 4536 }, { "epoch": 7.35, "learning_rate": 6.910722477655607e-06, "loss": 0.1166, "step": 4537 }, { "epoch": 7.35, "learning_rate": 6.902785321094301e-06, "loss": 0.1268, "step": 4538 }, { "epoch": 7.36, "learning_rate": 6.894851774435831e-06, "loss": 0.0891, "step": 4539 }, { "epoch": 7.36, "learning_rate": 6.886921839866858e-06, "loss": 0.0888, "step": 4540 }, { "epoch": 7.36, "learning_rate": 6.878995519573073e-06, "loss": 0.1428, "step": 4541 }, { "epoch": 7.36, "learning_rate": 6.87107281573915e-06, "loss": 0.0857, "step": 4542 }, { "epoch": 7.36, "learning_rate": 6.863153730548771e-06, "loss": 0.147, "step": 4543 }, { "epoch": 7.36, "learning_rate": 6.855238266184634e-06, "loss": 0.1611, "step": 4544 }, { "epoch": 7.37, "learning_rate": 6.84732642482842e-06, "loss": 0.1185, "step": 4545 }, { "epoch": 7.37, "learning_rate": 6.839418208660824e-06, "loss": 0.1296, "step": 4546 }, { "epoch": 7.37, "learning_rate": 6.831513619861536e-06, "loss": 0.1221, "step": 4547 }, { "epoch": 7.37, "learning_rate": 6.823612660609242e-06, "loss": 0.1193, "step": 4548 }, { "epoch": 7.37, "learning_rate": 6.815715333081645e-06, "loss": 0.115, "step": 4549 }, { "epoch": 7.37, "learning_rate": 6.807821639455432e-06, "loss": 0.1134, "step": 4550 }, { "epoch": 7.38, "learning_rate": 6.799931581906285e-06, "loss": 0.0827, "step": 4551 }, { "epoch": 7.38, "learning_rate": 6.7920451626089e-06, "loss": 0.0931, "step": 4552 }, { "epoch": 7.38, "learning_rate": 6.784162383736961e-06, "loss": 0.1035, "step": 4553 }, { "epoch": 7.38, "learning_rate": 6.776283247463135e-06, "loss": 0.0947, "step": 4554 }, { "epoch": 7.38, "learning_rate": 6.768407755959119e-06, "loss": 0.098, "step": 4555 }, { "epoch": 7.38, "learning_rate": 6.760535911395574e-06, "loss": 0.1192, "step": 4556 }, { "epoch": 7.39, "learning_rate": 6.75266771594216e-06, "loss": 0.1098, "step": 4557 }, { "epoch": 7.39, "learning_rate": 6.744803171767556e-06, "loss": 0.1155, "step": 4558 }, { "epoch": 7.39, "learning_rate": 6.736942281039405e-06, "loss": 0.141, "step": 4559 }, { "epoch": 7.39, "learning_rate": 6.729085045924357e-06, "loss": 0.1477, "step": 4560 }, { "epoch": 7.39, "learning_rate": 6.721231468588054e-06, "loss": 0.0958, "step": 4561 }, { "epoch": 7.39, "learning_rate": 6.71338155119512e-06, "loss": 0.0906, "step": 4562 }, { "epoch": 7.4, "learning_rate": 6.705535295909189e-06, "loss": 0.117, "step": 4563 }, { "epoch": 7.4, "learning_rate": 6.697692704892871e-06, "loss": 0.1269, "step": 4564 }, { "epoch": 7.4, "learning_rate": 6.689853780307762e-06, "loss": 0.1088, "step": 4565 }, { "epoch": 7.4, "learning_rate": 6.682018524314471e-06, "loss": 0.094, "step": 4566 }, { "epoch": 7.4, "learning_rate": 6.674186939072567e-06, "loss": 0.1173, "step": 4567 }, { "epoch": 7.4, "learning_rate": 6.66635902674063e-06, "loss": 0.1034, "step": 4568 }, { "epoch": 7.41, "learning_rate": 6.658534789476216e-06, "loss": 0.1882, "step": 4569 }, { "epoch": 7.41, "learning_rate": 6.650714229435867e-06, "loss": 0.1132, "step": 4570 }, { "epoch": 7.41, "learning_rate": 6.642897348775117e-06, "loss": 0.1398, "step": 4571 }, { "epoch": 7.41, "learning_rate": 6.635084149648481e-06, "loss": 0.1244, "step": 4572 }, { "epoch": 7.41, "learning_rate": 6.627274634209457e-06, "loss": 0.1334, "step": 4573 }, { "epoch": 7.41, "learning_rate": 6.619468804610547e-06, "loss": 0.117, "step": 4574 }, { "epoch": 7.41, "learning_rate": 6.611666663003213e-06, "loss": 0.1888, "step": 4575 }, { "epoch": 7.42, "learning_rate": 6.603868211537907e-06, "loss": 0.1366, "step": 4576 }, { "epoch": 7.42, "learning_rate": 6.596073452364078e-06, "loss": 0.112, "step": 4577 }, { "epoch": 7.42, "learning_rate": 6.588282387630134e-06, "loss": 0.1289, "step": 4578 }, { "epoch": 7.42, "learning_rate": 6.58049501948349e-06, "loss": 0.0965, "step": 4579 }, { "epoch": 7.42, "learning_rate": 6.5727113500705245e-06, "loss": 0.1309, "step": 4580 }, { "epoch": 7.42, "learning_rate": 6.56493138153659e-06, "loss": 0.1105, "step": 4581 }, { "epoch": 7.43, "learning_rate": 6.557155116026048e-06, "loss": 0.1231, "step": 4582 }, { "epoch": 7.43, "learning_rate": 6.549382555682213e-06, "loss": 0.1438, "step": 4583 }, { "epoch": 7.43, "learning_rate": 6.5416137026473866e-06, "loss": 0.1439, "step": 4584 }, { "epoch": 7.43, "learning_rate": 6.533848559062852e-06, "loss": 0.1106, "step": 4585 }, { "epoch": 7.43, "learning_rate": 6.526087127068857e-06, "loss": 0.1331, "step": 4586 }, { "epoch": 7.43, "learning_rate": 6.518329408804649e-06, "loss": 0.1363, "step": 4587 }, { "epoch": 7.44, "learning_rate": 6.510575406408432e-06, "loss": 0.1225, "step": 4588 }, { "epoch": 7.44, "learning_rate": 6.502825122017391e-06, "loss": 0.1272, "step": 4589 }, { "epoch": 7.44, "learning_rate": 6.495078557767698e-06, "loss": 0.1097, "step": 4590 }, { "epoch": 7.44, "learning_rate": 6.487335715794483e-06, "loss": 0.1059, "step": 4591 }, { "epoch": 7.44, "learning_rate": 6.47959659823185e-06, "loss": 0.114, "step": 4592 }, { "epoch": 7.44, "learning_rate": 6.471861207212897e-06, "loss": 0.0976, "step": 4593 }, { "epoch": 7.45, "learning_rate": 6.464129544869675e-06, "loss": 0.1309, "step": 4594 }, { "epoch": 7.45, "learning_rate": 6.456401613333214e-06, "loss": 0.1638, "step": 4595 }, { "epoch": 7.45, "learning_rate": 6.448677414733513e-06, "loss": 0.1426, "step": 4596 }, { "epoch": 7.45, "learning_rate": 6.44095695119954e-06, "loss": 0.0986, "step": 4597 }, { "epoch": 7.45, "learning_rate": 6.433240224859247e-06, "loss": 0.1073, "step": 4598 }, { "epoch": 7.45, "learning_rate": 6.425527237839544e-06, "loss": 0.1182, "step": 4599 }, { "epoch": 7.46, "learning_rate": 6.417817992266306e-06, "loss": 0.15, "step": 4600 }, { "epoch": 7.46, "learning_rate": 6.4101124902643954e-06, "loss": 0.1096, "step": 4601 }, { "epoch": 7.46, "learning_rate": 6.402410733957627e-06, "loss": 0.1013, "step": 4602 }, { "epoch": 7.46, "learning_rate": 6.394712725468777e-06, "loss": 0.0993, "step": 4603 }, { "epoch": 7.46, "learning_rate": 6.387018466919617e-06, "loss": 0.0981, "step": 4604 }, { "epoch": 7.46, "learning_rate": 6.37932796043085e-06, "loss": 0.1132, "step": 4605 }, { "epoch": 7.47, "learning_rate": 6.3716412081221766e-06, "loss": 0.1201, "step": 4606 }, { "epoch": 7.47, "learning_rate": 6.36395821211224e-06, "loss": 0.1051, "step": 4607 }, { "epoch": 7.47, "learning_rate": 6.356278974518659e-06, "loss": 0.159, "step": 4608 }, { "epoch": 7.47, "learning_rate": 6.34860349745801e-06, "loss": 0.1285, "step": 4609 }, { "epoch": 7.47, "learning_rate": 6.340931783045841e-06, "loss": 0.0988, "step": 4610 }, { "epoch": 7.47, "learning_rate": 6.333263833396646e-06, "loss": 0.1305, "step": 4611 }, { "epoch": 7.47, "learning_rate": 6.32559965062391e-06, "loss": 0.1304, "step": 4612 }, { "epoch": 7.48, "learning_rate": 6.317939236840058e-06, "loss": 0.1138, "step": 4613 }, { "epoch": 7.48, "learning_rate": 6.310282594156474e-06, "loss": 0.1155, "step": 4614 }, { "epoch": 7.48, "learning_rate": 6.302629724683522e-06, "loss": 0.1365, "step": 4615 }, { "epoch": 7.48, "learning_rate": 6.294980630530503e-06, "loss": 0.1313, "step": 4616 }, { "epoch": 7.48, "learning_rate": 6.2873353138057e-06, "loss": 0.1427, "step": 4617 }, { "epoch": 7.48, "learning_rate": 6.279693776616338e-06, "loss": 0.1232, "step": 4618 }, { "epoch": 7.49, "learning_rate": 6.272056021068606e-06, "loss": 0.1031, "step": 4619 }, { "epoch": 7.49, "learning_rate": 6.264422049267651e-06, "loss": 0.1359, "step": 4620 }, { "epoch": 7.49, "learning_rate": 6.256791863317575e-06, "loss": 0.1022, "step": 4621 }, { "epoch": 7.49, "learning_rate": 6.249165465321432e-06, "loss": 0.1335, "step": 4622 }, { "epoch": 7.49, "learning_rate": 6.241542857381251e-06, "loss": 0.107, "step": 4623 }, { "epoch": 7.49, "learning_rate": 6.233924041597992e-06, "loss": 0.1153, "step": 4624 }, { "epoch": 7.5, "learning_rate": 6.226309020071592e-06, "loss": 0.138, "step": 4625 }, { "epoch": 7.5, "learning_rate": 6.218697794900928e-06, "loss": 0.1054, "step": 4626 }, { "epoch": 7.5, "learning_rate": 6.211090368183825e-06, "loss": 0.1868, "step": 4627 }, { "epoch": 7.5, "learning_rate": 6.203486742017082e-06, "loss": 0.1418, "step": 4628 }, { "epoch": 7.5, "learning_rate": 6.195886918496436e-06, "loss": 0.0957, "step": 4629 }, { "epoch": 7.5, "learning_rate": 6.188290899716569e-06, "loss": 0.0933, "step": 4630 }, { "epoch": 7.51, "learning_rate": 6.180698687771139e-06, "loss": 0.1039, "step": 4631 }, { "epoch": 7.51, "learning_rate": 6.17311028475273e-06, "loss": 0.1537, "step": 4632 }, { "epoch": 7.51, "learning_rate": 6.165525692752887e-06, "loss": 0.1503, "step": 4633 }, { "epoch": 7.51, "learning_rate": 6.1579449138621065e-06, "loss": 0.1413, "step": 4634 }, { "epoch": 7.51, "learning_rate": 6.1503679501698195e-06, "loss": 0.0998, "step": 4635 }, { "epoch": 7.51, "learning_rate": 6.1427948037644334e-06, "loss": 0.1238, "step": 4636 }, { "epoch": 7.52, "learning_rate": 6.135225476733278e-06, "loss": 0.1555, "step": 4637 }, { "epoch": 7.52, "learning_rate": 6.127659971162634e-06, "loss": 0.1072, "step": 4638 }, { "epoch": 7.52, "learning_rate": 6.120098289137748e-06, "loss": 0.107, "step": 4639 }, { "epoch": 7.52, "learning_rate": 6.112540432742791e-06, "loss": 0.1191, "step": 4640 }, { "epoch": 7.52, "learning_rate": 6.10498640406088e-06, "loss": 0.1208, "step": 4641 }, { "epoch": 7.52, "learning_rate": 6.0974362051740985e-06, "loss": 0.1106, "step": 4642 }, { "epoch": 7.53, "learning_rate": 6.089889838163454e-06, "loss": 0.1429, "step": 4643 }, { "epoch": 7.53, "learning_rate": 6.082347305108904e-06, "loss": 0.1517, "step": 4644 }, { "epoch": 7.53, "learning_rate": 6.074808608089349e-06, "loss": 0.1394, "step": 4645 }, { "epoch": 7.53, "learning_rate": 6.067273749182627e-06, "loss": 0.0981, "step": 4646 }, { "epoch": 7.53, "learning_rate": 6.0597427304655365e-06, "loss": 0.0997, "step": 4647 }, { "epoch": 7.53, "learning_rate": 6.052215554013796e-06, "loss": 0.123, "step": 4648 }, { "epoch": 7.53, "learning_rate": 6.044692221902071e-06, "loss": 0.1284, "step": 4649 }, { "epoch": 7.54, "learning_rate": 6.03717273620398e-06, "loss": 0.108, "step": 4650 }, { "epoch": 7.54, "learning_rate": 6.029657098992061e-06, "loss": 0.1062, "step": 4651 }, { "epoch": 7.54, "learning_rate": 6.022145312337812e-06, "loss": 0.1331, "step": 4652 }, { "epoch": 7.54, "learning_rate": 6.014637378311656e-06, "loss": 0.12, "step": 4653 }, { "epoch": 7.54, "learning_rate": 6.00713329898295e-06, "loss": 0.1153, "step": 4654 }, { "epoch": 7.54, "learning_rate": 5.999633076420006e-06, "loss": 0.1112, "step": 4655 }, { "epoch": 7.55, "learning_rate": 5.992136712690062e-06, "loss": 0.1135, "step": 4656 }, { "epoch": 7.55, "learning_rate": 5.9846442098592895e-06, "loss": 0.109, "step": 4657 }, { "epoch": 7.55, "learning_rate": 5.977155569992803e-06, "loss": 0.1725, "step": 4658 }, { "epoch": 7.55, "learning_rate": 5.969670795154645e-06, "loss": 0.1152, "step": 4659 }, { "epoch": 7.55, "learning_rate": 5.962189887407797e-06, "loss": 0.0968, "step": 4660 }, { "epoch": 7.55, "learning_rate": 5.954712848814179e-06, "loss": 0.1009, "step": 4661 }, { "epoch": 7.56, "learning_rate": 5.947239681434634e-06, "loss": 0.1056, "step": 4662 }, { "epoch": 7.56, "learning_rate": 5.939770387328953e-06, "loss": 0.1131, "step": 4663 }, { "epoch": 7.56, "learning_rate": 5.932304968555846e-06, "loss": 0.1209, "step": 4664 }, { "epoch": 7.56, "learning_rate": 5.924843427172953e-06, "loss": 0.1261, "step": 4665 }, { "epoch": 7.56, "learning_rate": 5.9173857652368645e-06, "loss": 0.1284, "step": 4666 }, { "epoch": 7.56, "learning_rate": 5.909931984803081e-06, "loss": 0.1105, "step": 4667 }, { "epoch": 7.57, "learning_rate": 5.902482087926042e-06, "loss": 0.1354, "step": 4668 }, { "epoch": 7.57, "learning_rate": 5.895036076659116e-06, "loss": 0.1402, "step": 4669 }, { "epoch": 7.57, "learning_rate": 5.8875939530545936e-06, "loss": 0.1323, "step": 4670 }, { "epoch": 7.57, "learning_rate": 5.880155719163714e-06, "loss": 0.1653, "step": 4671 }, { "epoch": 7.57, "learning_rate": 5.872721377036621e-06, "loss": 0.1298, "step": 4672 }, { "epoch": 7.57, "learning_rate": 5.8652909287223934e-06, "loss": 0.1249, "step": 4673 }, { "epoch": 7.58, "learning_rate": 5.857864376269051e-06, "loss": 0.121, "step": 4674 }, { "epoch": 7.58, "learning_rate": 5.8504417217235186e-06, "loss": 0.1094, "step": 4675 }, { "epoch": 7.58, "learning_rate": 5.843022967131653e-06, "loss": 0.0958, "step": 4676 }, { "epoch": 7.58, "learning_rate": 5.835608114538249e-06, "loss": 0.1123, "step": 4677 }, { "epoch": 7.58, "learning_rate": 5.82819716598701e-06, "loss": 0.1186, "step": 4678 }, { "epoch": 7.58, "learning_rate": 5.820790123520564e-06, "loss": 0.12, "step": 4679 }, { "epoch": 7.59, "learning_rate": 5.813386989180476e-06, "loss": 0.1166, "step": 4680 }, { "epoch": 7.59, "learning_rate": 5.805987765007224e-06, "loss": 0.1515, "step": 4681 }, { "epoch": 7.59, "learning_rate": 5.7985924530402064e-06, "loss": 0.1322, "step": 4682 }, { "epoch": 7.59, "learning_rate": 5.791201055317748e-06, "loss": 0.1032, "step": 4683 }, { "epoch": 7.59, "learning_rate": 5.783813573877086e-06, "loss": 0.1266, "step": 4684 }, { "epoch": 7.59, "learning_rate": 5.776430010754399e-06, "loss": 0.1543, "step": 4685 }, { "epoch": 7.59, "learning_rate": 5.769050367984765e-06, "loss": 0.1056, "step": 4686 }, { "epoch": 7.6, "learning_rate": 5.761674647602185e-06, "loss": 0.093, "step": 4687 }, { "epoch": 7.6, "learning_rate": 5.754302851639588e-06, "loss": 0.1159, "step": 4688 }, { "epoch": 7.6, "learning_rate": 5.746934982128811e-06, "loss": 0.1243, "step": 4689 }, { "epoch": 7.6, "learning_rate": 5.739571041100622e-06, "loss": 0.1518, "step": 4690 }, { "epoch": 7.6, "learning_rate": 5.732211030584691e-06, "loss": 0.1226, "step": 4691 }, { "epoch": 7.6, "learning_rate": 5.724854952609613e-06, "loss": 0.1554, "step": 4692 }, { "epoch": 7.61, "learning_rate": 5.717502809202895e-06, "loss": 0.1157, "step": 4693 }, { "epoch": 7.61, "learning_rate": 5.710154602390965e-06, "loss": 0.1605, "step": 4694 }, { "epoch": 7.61, "learning_rate": 5.7028103341991555e-06, "loss": 0.1792, "step": 4695 }, { "epoch": 7.61, "learning_rate": 5.695470006651736e-06, "loss": 0.1171, "step": 4696 }, { "epoch": 7.61, "learning_rate": 5.688133621771863e-06, "loss": 0.1053, "step": 4697 }, { "epoch": 7.61, "learning_rate": 5.680801181581617e-06, "loss": 0.1735, "step": 4698 }, { "epoch": 7.62, "learning_rate": 5.673472688102e-06, "loss": 0.1034, "step": 4699 }, { "epoch": 7.62, "learning_rate": 5.66614814335291e-06, "loss": 0.1795, "step": 4700 }, { "epoch": 7.62, "learning_rate": 5.658827549353176e-06, "loss": 0.1514, "step": 4701 }, { "epoch": 7.62, "learning_rate": 5.651510908120521e-06, "loss": 0.1059, "step": 4702 }, { "epoch": 7.62, "learning_rate": 5.64419822167158e-06, "loss": 0.126, "step": 4703 }, { "epoch": 7.62, "learning_rate": 5.636889492021913e-06, "loss": 0.1615, "step": 4704 }, { "epoch": 7.63, "learning_rate": 5.629584721185975e-06, "loss": 0.0961, "step": 4705 }, { "epoch": 7.63, "learning_rate": 5.622283911177133e-06, "loss": 0.1041, "step": 4706 }, { "epoch": 7.63, "learning_rate": 5.614987064007662e-06, "loss": 0.1362, "step": 4707 }, { "epoch": 7.63, "learning_rate": 5.607694181688743e-06, "loss": 0.1446, "step": 4708 }, { "epoch": 7.63, "learning_rate": 5.600405266230475e-06, "loss": 0.113, "step": 4709 }, { "epoch": 7.63, "learning_rate": 5.593120319641854e-06, "loss": 0.1254, "step": 4710 }, { "epoch": 7.64, "learning_rate": 5.585839343930777e-06, "loss": 0.0755, "step": 4711 }, { "epoch": 7.64, "learning_rate": 5.578562341104064e-06, "loss": 0.1112, "step": 4712 }, { "epoch": 7.64, "learning_rate": 5.571289313167425e-06, "loss": 0.1024, "step": 4713 }, { "epoch": 7.64, "learning_rate": 5.5640202621254714e-06, "loss": 0.1097, "step": 4714 }, { "epoch": 7.64, "learning_rate": 5.55675518998174e-06, "loss": 0.1428, "step": 4715 }, { "epoch": 7.64, "learning_rate": 5.549494098738648e-06, "loss": 0.1312, "step": 4716 }, { "epoch": 7.65, "learning_rate": 5.542236990397527e-06, "loss": 0.092, "step": 4717 }, { "epoch": 7.65, "learning_rate": 5.534983866958608e-06, "loss": 0.134, "step": 4718 }, { "epoch": 7.65, "learning_rate": 5.527734730421015e-06, "loss": 0.1014, "step": 4719 }, { "epoch": 7.65, "learning_rate": 5.520489582782798e-06, "loss": 0.1268, "step": 4720 }, { "epoch": 7.65, "learning_rate": 5.5132484260408805e-06, "loss": 0.0954, "step": 4721 }, { "epoch": 7.65, "learning_rate": 5.506011262191096e-06, "loss": 0.1334, "step": 4722 }, { "epoch": 7.65, "learning_rate": 5.498778093228188e-06, "loss": 0.1218, "step": 4723 }, { "epoch": 7.66, "learning_rate": 5.491548921145782e-06, "loss": 0.1726, "step": 4724 }, { "epoch": 7.66, "learning_rate": 5.484323747936404e-06, "loss": 0.1245, "step": 4725 }, { "epoch": 7.66, "learning_rate": 5.477102575591495e-06, "loss": 0.1195, "step": 4726 }, { "epoch": 7.66, "learning_rate": 5.469885406101372e-06, "loss": 0.1392, "step": 4727 }, { "epoch": 7.66, "learning_rate": 5.4626722414552665e-06, "loss": 0.1307, "step": 4728 }, { "epoch": 7.66, "learning_rate": 5.455463083641295e-06, "loss": 0.1293, "step": 4729 }, { "epoch": 7.67, "learning_rate": 5.448257934646468e-06, "loss": 0.1404, "step": 4730 }, { "epoch": 7.67, "learning_rate": 5.441056796456699e-06, "loss": 0.1137, "step": 4731 }, { "epoch": 7.67, "learning_rate": 5.433859671056789e-06, "loss": 0.1447, "step": 4732 }, { "epoch": 7.67, "learning_rate": 5.426666560430433e-06, "loss": 0.1375, "step": 4733 }, { "epoch": 7.67, "learning_rate": 5.419477466560237e-06, "loss": 0.1949, "step": 4734 }, { "epoch": 7.67, "learning_rate": 5.412292391427667e-06, "loss": 0.1125, "step": 4735 }, { "epoch": 7.68, "learning_rate": 5.405111337013118e-06, "loss": 0.1056, "step": 4736 }, { "epoch": 7.68, "learning_rate": 5.397934305295851e-06, "loss": 0.2057, "step": 4737 }, { "epoch": 7.68, "learning_rate": 5.390761298254019e-06, "loss": 0.2042, "step": 4738 }, { "epoch": 7.68, "learning_rate": 5.3835923178646855e-06, "loss": 0.1426, "step": 4739 }, { "epoch": 7.68, "learning_rate": 5.376427366103785e-06, "loss": 0.1131, "step": 4740 }, { "epoch": 7.68, "learning_rate": 5.369266444946149e-06, "loss": 0.118, "step": 4741 }, { "epoch": 7.69, "learning_rate": 5.362109556365496e-06, "loss": 0.1602, "step": 4742 }, { "epoch": 7.69, "learning_rate": 5.354956702334435e-06, "loss": 0.0965, "step": 4743 }, { "epoch": 7.69, "learning_rate": 5.347807884824456e-06, "loss": 0.1567, "step": 4744 }, { "epoch": 7.69, "learning_rate": 5.340663105805957e-06, "loss": 0.1515, "step": 4745 }, { "epoch": 7.69, "learning_rate": 5.333522367248189e-06, "loss": 0.1609, "step": 4746 }, { "epoch": 7.69, "learning_rate": 5.32638567111933e-06, "loss": 0.1699, "step": 4747 }, { "epoch": 7.7, "learning_rate": 5.31925301938641e-06, "loss": 0.1328, "step": 4748 }, { "epoch": 7.7, "learning_rate": 5.3121244140153535e-06, "loss": 0.1218, "step": 4749 }, { "epoch": 7.7, "learning_rate": 5.304999856970987e-06, "loss": 0.1924, "step": 4750 }, { "epoch": 7.7, "learning_rate": 5.297879350216997e-06, "loss": 0.142, "step": 4751 }, { "epoch": 7.7, "learning_rate": 5.290762895715962e-06, "loss": 0.1306, "step": 4752 }, { "epoch": 7.7, "learning_rate": 5.283650495429353e-06, "loss": 0.2471, "step": 4753 }, { "epoch": 7.71, "learning_rate": 5.276542151317514e-06, "loss": 0.0945, "step": 4754 }, { "epoch": 7.71, "learning_rate": 5.269437865339672e-06, "loss": 0.1424, "step": 4755 }, { "epoch": 7.71, "learning_rate": 5.262337639453938e-06, "loss": 0.1128, "step": 4756 }, { "epoch": 7.71, "learning_rate": 5.255241475617295e-06, "loss": 0.1038, "step": 4757 }, { "epoch": 7.71, "learning_rate": 5.248149375785623e-06, "loss": 0.1769, "step": 4758 }, { "epoch": 7.71, "learning_rate": 5.2410613419136715e-06, "loss": 0.1283, "step": 4759 }, { "epoch": 7.71, "learning_rate": 5.2339773759550635e-06, "loss": 0.1425, "step": 4760 }, { "epoch": 7.72, "learning_rate": 5.226897479862321e-06, "loss": 0.1564, "step": 4761 }, { "epoch": 7.72, "learning_rate": 5.219821655586821e-06, "loss": 0.1229, "step": 4762 }, { "epoch": 7.72, "learning_rate": 5.212749905078827e-06, "loss": 0.1655, "step": 4763 }, { "epoch": 7.72, "learning_rate": 5.20568223028749e-06, "loss": 0.1778, "step": 4764 }, { "epoch": 7.72, "learning_rate": 5.198618633160823e-06, "loss": 0.1261, "step": 4765 }, { "epoch": 7.72, "learning_rate": 5.191559115645723e-06, "loss": 0.0873, "step": 4766 }, { "epoch": 7.73, "learning_rate": 5.18450367968796e-06, "loss": 0.1084, "step": 4767 }, { "epoch": 7.73, "learning_rate": 5.177452327232173e-06, "loss": 0.136, "step": 4768 }, { "epoch": 7.73, "learning_rate": 5.17040506022189e-06, "loss": 0.121, "step": 4769 }, { "epoch": 7.73, "learning_rate": 5.163361880599505e-06, "loss": 0.1146, "step": 4770 }, { "epoch": 7.73, "learning_rate": 5.156322790306276e-06, "loss": 0.1186, "step": 4771 }, { "epoch": 7.73, "learning_rate": 5.149287791282356e-06, "loss": 0.1027, "step": 4772 }, { "epoch": 7.74, "learning_rate": 5.142256885466743e-06, "loss": 0.0951, "step": 4773 }, { "epoch": 7.74, "learning_rate": 5.1352300747973375e-06, "loss": 0.1395, "step": 4774 }, { "epoch": 7.74, "learning_rate": 5.128207361210886e-06, "loss": 0.1481, "step": 4775 }, { "epoch": 7.74, "learning_rate": 5.121188746643009e-06, "loss": 0.1362, "step": 4776 }, { "epoch": 7.74, "learning_rate": 5.114174233028217e-06, "loss": 0.1423, "step": 4777 }, { "epoch": 7.74, "learning_rate": 5.10716382229987e-06, "loss": 0.1141, "step": 4778 }, { "epoch": 7.75, "learning_rate": 5.1001575163902005e-06, "loss": 0.1154, "step": 4779 }, { "epoch": 7.75, "learning_rate": 5.093155317230316e-06, "loss": 0.1171, "step": 4780 }, { "epoch": 7.75, "learning_rate": 5.086157226750186e-06, "loss": 0.1272, "step": 4781 }, { "epoch": 7.75, "learning_rate": 5.0791632468786445e-06, "loss": 0.1067, "step": 4782 }, { "epoch": 7.75, "learning_rate": 5.072173379543413e-06, "loss": 0.1298, "step": 4783 }, { "epoch": 7.75, "learning_rate": 5.065187626671048e-06, "loss": 0.1843, "step": 4784 }, { "epoch": 7.76, "learning_rate": 5.058205990187004e-06, "loss": 0.1461, "step": 4785 }, { "epoch": 7.76, "learning_rate": 5.0512284720155794e-06, "loss": 0.1901, "step": 4786 }, { "epoch": 7.76, "learning_rate": 5.044255074079936e-06, "loss": 0.1527, "step": 4787 }, { "epoch": 7.76, "learning_rate": 5.037285798302121e-06, "loss": 0.1206, "step": 4788 }, { "epoch": 7.76, "learning_rate": 5.0303206466030244e-06, "loss": 0.118, "step": 4789 }, { "epoch": 7.76, "learning_rate": 5.023359620902408e-06, "loss": 0.1056, "step": 4790 }, { "epoch": 7.76, "learning_rate": 5.016402723118896e-06, "loss": 0.2024, "step": 4791 }, { "epoch": 7.77, "learning_rate": 5.009449955169967e-06, "loss": 0.1141, "step": 4792 }, { "epoch": 7.77, "learning_rate": 5.002501318971984e-06, "loss": 0.1406, "step": 4793 }, { "epoch": 7.77, "learning_rate": 4.9955568164401456e-06, "loss": 0.1067, "step": 4794 }, { "epoch": 7.77, "learning_rate": 4.988616449488517e-06, "loss": 0.1759, "step": 4795 }, { "epoch": 7.77, "learning_rate": 4.981680220030041e-06, "loss": 0.1386, "step": 4796 }, { "epoch": 7.77, "learning_rate": 4.974748129976496e-06, "loss": 0.1779, "step": 4797 }, { "epoch": 7.78, "learning_rate": 4.967820181238532e-06, "loss": 0.1345, "step": 4798 }, { "epoch": 7.78, "learning_rate": 4.960896375725664e-06, "loss": 0.126, "step": 4799 }, { "epoch": 7.78, "learning_rate": 4.953976715346249e-06, "loss": 0.1332, "step": 4800 }, { "epoch": 7.78, "learning_rate": 4.947061202007506e-06, "loss": 0.1792, "step": 4801 }, { "epoch": 7.78, "learning_rate": 4.940149837615527e-06, "loss": 0.1116, "step": 4802 }, { "epoch": 7.78, "learning_rate": 4.93324262407524e-06, "loss": 0.1389, "step": 4803 }, { "epoch": 7.79, "learning_rate": 4.926339563290437e-06, "loss": 0.1373, "step": 4804 }, { "epoch": 7.79, "learning_rate": 4.919440657163766e-06, "loss": 0.1434, "step": 4805 }, { "epoch": 7.79, "learning_rate": 4.912545907596722e-06, "loss": 0.171, "step": 4806 }, { "epoch": 7.79, "learning_rate": 4.905655316489674e-06, "loss": 0.1205, "step": 4807 }, { "epoch": 7.79, "learning_rate": 4.898768885741829e-06, "loss": 0.0907, "step": 4808 }, { "epoch": 7.79, "learning_rate": 4.89188661725124e-06, "loss": 0.1469, "step": 4809 }, { "epoch": 7.8, "learning_rate": 4.885008512914837e-06, "loss": 0.108, "step": 4810 }, { "epoch": 7.8, "learning_rate": 4.878134574628377e-06, "loss": 0.1272, "step": 4811 }, { "epoch": 7.8, "learning_rate": 4.87126480428649e-06, "loss": 0.1455, "step": 4812 }, { "epoch": 7.8, "learning_rate": 4.864399203782648e-06, "loss": 0.1066, "step": 4813 }, { "epoch": 7.8, "learning_rate": 4.85753777500916e-06, "loss": 0.1177, "step": 4814 }, { "epoch": 7.8, "learning_rate": 4.850680519857216e-06, "loss": 0.1091, "step": 4815 }, { "epoch": 7.81, "learning_rate": 4.843827440216827e-06, "loss": 0.1261, "step": 4816 }, { "epoch": 7.81, "learning_rate": 4.836978537976866e-06, "loss": 0.1353, "step": 4817 }, { "epoch": 7.81, "learning_rate": 4.830133815025055e-06, "loss": 0.1072, "step": 4818 }, { "epoch": 7.81, "learning_rate": 4.823293273247955e-06, "loss": 0.1662, "step": 4819 }, { "epoch": 7.81, "learning_rate": 4.816456914530991e-06, "loss": 0.104, "step": 4820 }, { "epoch": 7.81, "learning_rate": 4.809624740758423e-06, "loss": 0.1339, "step": 4821 }, { "epoch": 7.82, "learning_rate": 4.802796753813353e-06, "loss": 0.1137, "step": 4822 }, { "epoch": 7.82, "learning_rate": 4.795972955577746e-06, "loss": 0.1563, "step": 4823 }, { "epoch": 7.82, "learning_rate": 4.789153347932398e-06, "loss": 0.1512, "step": 4824 }, { "epoch": 7.82, "learning_rate": 4.782337932756948e-06, "loss": 0.1533, "step": 4825 }, { "epoch": 7.82, "learning_rate": 4.775526711929901e-06, "loss": 0.1157, "step": 4826 }, { "epoch": 7.82, "learning_rate": 4.76871968732858e-06, "loss": 0.1497, "step": 4827 }, { "epoch": 7.82, "learning_rate": 4.7619168608291655e-06, "loss": 0.1392, "step": 4828 }, { "epoch": 7.83, "learning_rate": 4.755118234306677e-06, "loss": 0.0989, "step": 4829 }, { "epoch": 7.83, "learning_rate": 4.748323809634972e-06, "loss": 0.117, "step": 4830 }, { "epoch": 7.83, "learning_rate": 4.741533588686764e-06, "loss": 0.1805, "step": 4831 }, { "epoch": 7.83, "learning_rate": 4.734747573333596e-06, "loss": 0.144, "step": 4832 }, { "epoch": 7.83, "learning_rate": 4.727965765445847e-06, "loss": 0.146, "step": 4833 }, { "epoch": 7.83, "learning_rate": 4.721188166892759e-06, "loss": 0.1698, "step": 4834 }, { "epoch": 7.84, "learning_rate": 4.714414779542389e-06, "loss": 0.2847, "step": 4835 }, { "epoch": 7.84, "learning_rate": 4.707645605261639e-06, "loss": 0.1351, "step": 4836 }, { "epoch": 7.84, "learning_rate": 4.700880645916264e-06, "loss": 0.1604, "step": 4837 }, { "epoch": 7.84, "learning_rate": 4.694119903370837e-06, "loss": 0.1322, "step": 4838 }, { "epoch": 7.84, "learning_rate": 4.687363379488792e-06, "loss": 0.1604, "step": 4839 }, { "epoch": 7.84, "learning_rate": 4.68061107613238e-06, "loss": 0.1066, "step": 4840 }, { "epoch": 7.85, "learning_rate": 4.673862995162695e-06, "loss": 0.1441, "step": 4841 }, { "epoch": 7.85, "learning_rate": 4.667119138439669e-06, "loss": 0.1442, "step": 4842 }, { "epoch": 7.85, "learning_rate": 4.6603795078220656e-06, "loss": 0.1045, "step": 4843 }, { "epoch": 7.85, "learning_rate": 4.653644105167487e-06, "loss": 0.1358, "step": 4844 }, { "epoch": 7.85, "learning_rate": 4.646912932332377e-06, "loss": 0.1215, "step": 4845 }, { "epoch": 7.85, "learning_rate": 4.640185991172002e-06, "loss": 0.128, "step": 4846 }, { "epoch": 7.86, "learning_rate": 4.63346328354046e-06, "loss": 0.1094, "step": 4847 }, { "epoch": 7.86, "learning_rate": 4.626744811290702e-06, "loss": 0.1239, "step": 4848 }, { "epoch": 7.86, "learning_rate": 4.620030576274483e-06, "loss": 0.131, "step": 4849 }, { "epoch": 7.86, "learning_rate": 4.613320580342422e-06, "loss": 0.1423, "step": 4850 }, { "epoch": 7.86, "learning_rate": 4.606614825343943e-06, "loss": 0.1088, "step": 4851 }, { "epoch": 7.86, "learning_rate": 4.599913313127311e-06, "loss": 0.1175, "step": 4852 }, { "epoch": 7.87, "learning_rate": 4.5932160455396235e-06, "loss": 0.1263, "step": 4853 }, { "epoch": 7.87, "learning_rate": 4.586523024426808e-06, "loss": 0.123, "step": 4854 }, { "epoch": 7.87, "learning_rate": 4.579834251633608e-06, "loss": 0.1588, "step": 4855 }, { "epoch": 7.87, "learning_rate": 4.573149729003625e-06, "loss": 0.2166, "step": 4856 }, { "epoch": 7.87, "learning_rate": 4.566469458379259e-06, "loss": 0.1294, "step": 4857 }, { "epoch": 7.87, "learning_rate": 4.559793441601761e-06, "loss": 0.1252, "step": 4858 }, { "epoch": 7.88, "learning_rate": 4.553121680511194e-06, "loss": 0.1211, "step": 4859 }, { "epoch": 7.88, "learning_rate": 4.546454176946451e-06, "loss": 0.0966, "step": 4860 }, { "epoch": 7.88, "learning_rate": 4.53979093274526e-06, "loss": 0.1093, "step": 4861 }, { "epoch": 7.88, "learning_rate": 4.533131949744167e-06, "loss": 0.1141, "step": 4862 }, { "epoch": 7.88, "learning_rate": 4.526477229778541e-06, "loss": 0.1471, "step": 4863 }, { "epoch": 7.88, "learning_rate": 4.519826774682588e-06, "loss": 0.112, "step": 4864 }, { "epoch": 7.88, "learning_rate": 4.513180586289328e-06, "loss": 0.1471, "step": 4865 }, { "epoch": 7.89, "learning_rate": 4.506538666430606e-06, "loss": 0.1041, "step": 4866 }, { "epoch": 7.89, "learning_rate": 4.499901016937096e-06, "loss": 0.1159, "step": 4867 }, { "epoch": 7.89, "learning_rate": 4.493267639638283e-06, "loss": 0.1006, "step": 4868 }, { "epoch": 7.89, "learning_rate": 4.486638536362495e-06, "loss": 0.0874, "step": 4869 }, { "epoch": 7.89, "learning_rate": 4.4800137089368655e-06, "loss": 0.1723, "step": 4870 }, { "epoch": 7.89, "learning_rate": 4.473393159187347e-06, "loss": 0.1437, "step": 4871 }, { "epoch": 7.9, "learning_rate": 4.466776888938731e-06, "loss": 0.1358, "step": 4872 }, { "epoch": 7.9, "learning_rate": 4.460164900014614e-06, "loss": 0.0982, "step": 4873 }, { "epoch": 7.9, "learning_rate": 4.453557194237413e-06, "loss": 0.1311, "step": 4874 }, { "epoch": 7.9, "learning_rate": 4.446953773428373e-06, "loss": 0.0988, "step": 4875 }, { "epoch": 7.9, "learning_rate": 4.4403546394075535e-06, "loss": 0.123, "step": 4876 }, { "epoch": 7.9, "learning_rate": 4.433759793993832e-06, "loss": 0.1323, "step": 4877 }, { "epoch": 7.91, "learning_rate": 4.427169239004902e-06, "loss": 0.1109, "step": 4878 }, { "epoch": 7.91, "learning_rate": 4.4205829762572724e-06, "loss": 0.1226, "step": 4879 }, { "epoch": 7.91, "learning_rate": 4.414001007566284e-06, "loss": 0.1188, "step": 4880 }, { "epoch": 7.91, "learning_rate": 4.407423334746077e-06, "loss": 0.1306, "step": 4881 }, { "epoch": 7.91, "learning_rate": 4.4008499596096095e-06, "loss": 0.1366, "step": 4882 }, { "epoch": 7.91, "learning_rate": 4.394280883968671e-06, "loss": 0.1565, "step": 4883 }, { "epoch": 7.92, "learning_rate": 4.3877161096338486e-06, "loss": 0.1774, "step": 4884 }, { "epoch": 7.92, "learning_rate": 4.381155638414545e-06, "loss": 0.1154, "step": 4885 }, { "epoch": 7.92, "learning_rate": 4.37459947211899e-06, "loss": 0.1243, "step": 4886 }, { "epoch": 7.92, "learning_rate": 4.368047612554209e-06, "loss": 0.0726, "step": 4887 }, { "epoch": 7.92, "learning_rate": 4.361500061526063e-06, "loss": 0.1585, "step": 4888 }, { "epoch": 7.92, "learning_rate": 4.3549568208392024e-06, "loss": 0.2441, "step": 4889 }, { "epoch": 7.93, "learning_rate": 4.348417892297101e-06, "loss": 0.1218, "step": 4890 }, { "epoch": 7.93, "learning_rate": 4.3418832777020456e-06, "loss": 0.1172, "step": 4891 }, { "epoch": 7.93, "learning_rate": 4.3353529788551275e-06, "loss": 0.1147, "step": 4892 }, { "epoch": 7.93, "learning_rate": 4.328826997556246e-06, "loss": 0.1135, "step": 4893 }, { "epoch": 7.93, "learning_rate": 4.3223053356041315e-06, "loss": 0.1426, "step": 4894 }, { "epoch": 7.93, "learning_rate": 4.315787994796292e-06, "loss": 0.0968, "step": 4895 }, { "epoch": 7.94, "learning_rate": 4.309274976929074e-06, "loss": 0.1673, "step": 4896 }, { "epoch": 7.94, "learning_rate": 4.302766283797617e-06, "loss": 0.0958, "step": 4897 }, { "epoch": 7.94, "learning_rate": 4.296261917195863e-06, "loss": 0.1865, "step": 4898 }, { "epoch": 7.94, "learning_rate": 4.289761878916581e-06, "loss": 0.1714, "step": 4899 }, { "epoch": 7.94, "learning_rate": 4.28326617075133e-06, "loss": 0.1685, "step": 4900 }, { "epoch": 7.94, "learning_rate": 4.276774794490484e-06, "loss": 0.1341, "step": 4901 }, { "epoch": 7.94, "learning_rate": 4.270287751923215e-06, "loss": 0.1152, "step": 4902 }, { "epoch": 7.95, "learning_rate": 4.263805044837508e-06, "loss": 0.124, "step": 4903 }, { "epoch": 7.95, "learning_rate": 4.257326675020146e-06, "loss": 0.1031, "step": 4904 }, { "epoch": 7.95, "learning_rate": 4.2508526442567314e-06, "loss": 0.1906, "step": 4905 }, { "epoch": 7.95, "learning_rate": 4.244382954331652e-06, "loss": 0.1204, "step": 4906 }, { "epoch": 7.95, "learning_rate": 4.2379176070281144e-06, "loss": 0.1507, "step": 4907 }, { "epoch": 7.95, "learning_rate": 4.2314566041281194e-06, "loss": 0.1276, "step": 4908 }, { "epoch": 7.96, "learning_rate": 4.2249999474124645e-06, "loss": 0.1324, "step": 4909 }, { "epoch": 7.96, "learning_rate": 4.218547638660773e-06, "loss": 0.141, "step": 4910 }, { "epoch": 7.96, "learning_rate": 4.212099679651442e-06, "loss": 0.1213, "step": 4911 }, { "epoch": 7.96, "learning_rate": 4.205656072161681e-06, "loss": 0.1774, "step": 4912 }, { "epoch": 7.96, "learning_rate": 4.199216817967513e-06, "loss": 0.1799, "step": 4913 }, { "epoch": 7.96, "learning_rate": 4.192781918843738e-06, "loss": 0.1019, "step": 4914 }, { "epoch": 7.97, "learning_rate": 4.186351376563973e-06, "loss": 0.2004, "step": 4915 }, { "epoch": 7.97, "learning_rate": 4.1799251929006225e-06, "loss": 0.139, "step": 4916 }, { "epoch": 7.97, "learning_rate": 4.173503369624894e-06, "loss": 0.1452, "step": 4917 }, { "epoch": 7.97, "learning_rate": 4.167085908506803e-06, "loss": 0.1634, "step": 4918 }, { "epoch": 7.97, "learning_rate": 4.1606728113151475e-06, "loss": 0.0886, "step": 4919 }, { "epoch": 7.97, "learning_rate": 4.154264079817525e-06, "loss": 0.122, "step": 4920 }, { "epoch": 7.98, "learning_rate": 4.147859715780347e-06, "loss": 0.1584, "step": 4921 }, { "epoch": 7.98, "learning_rate": 4.141459720968793e-06, "loss": 0.1354, "step": 4922 }, { "epoch": 7.98, "learning_rate": 4.1350640971468655e-06, "loss": 0.2247, "step": 4923 }, { "epoch": 7.98, "learning_rate": 4.128672846077344e-06, "loss": 0.107, "step": 4924 }, { "epoch": 7.98, "learning_rate": 4.122285969521811e-06, "loss": 0.0983, "step": 4925 }, { "epoch": 7.98, "learning_rate": 4.115903469240641e-06, "loss": 0.1778, "step": 4926 }, { "epoch": 7.99, "learning_rate": 4.109525346993e-06, "loss": 0.0955, "step": 4927 }, { "epoch": 7.99, "learning_rate": 4.103151604536845e-06, "loss": 0.1252, "step": 4928 }, { "epoch": 7.99, "learning_rate": 4.096782243628943e-06, "loss": 0.0932, "step": 4929 }, { "epoch": 7.99, "learning_rate": 4.090417266024833e-06, "loss": 0.159, "step": 4930 }, { "epoch": 7.99, "learning_rate": 4.084056673478851e-06, "loss": 0.1614, "step": 4931 }, { "epoch": 7.99, "learning_rate": 4.077700467744135e-06, "loss": 0.1011, "step": 4932 }, { "epoch": 8.0, "learning_rate": 4.071348650572597e-06, "loss": 0.1081, "step": 4933 }, { "epoch": 8.0, "learning_rate": 4.065001223714959e-06, "loss": 0.173, "step": 4934 }, { "epoch": 8.0, "learning_rate": 4.0586581889207165e-06, "loss": 0.1687, "step": 4935 }, { "epoch": 8.0, "learning_rate": 4.052319547938155e-06, "loss": 0.1019, "step": 4936 }, { "epoch": 8.0, "learning_rate": 4.045985302514366e-06, "loss": 0.1119, "step": 4937 }, { "epoch": 8.0, "learning_rate": 4.03965545439521e-06, "loss": 0.1007, "step": 4938 }, { "epoch": 8.0, "learning_rate": 4.0333300053253465e-06, "loss": 0.1193, "step": 4939 }, { "epoch": 8.01, "learning_rate": 4.027008957048215e-06, "loss": 0.1037, "step": 4940 }, { "epoch": 8.01, "learning_rate": 4.020692311306045e-06, "loss": 0.1332, "step": 4941 }, { "epoch": 8.01, "learning_rate": 4.014380069839861e-06, "loss": 0.0995, "step": 4942 }, { "epoch": 8.01, "learning_rate": 4.008072234389464e-06, "loss": 0.1056, "step": 4943 }, { "epoch": 8.01, "learning_rate": 4.0017688066934355e-06, "loss": 0.0906, "step": 4944 }, { "epoch": 8.01, "learning_rate": 3.995469788489162e-06, "loss": 0.1274, "step": 4945 }, { "epoch": 8.02, "learning_rate": 3.989175181512794e-06, "loss": 0.1249, "step": 4946 }, { "epoch": 8.02, "learning_rate": 3.982884987499274e-06, "loss": 0.1054, "step": 4947 }, { "epoch": 8.02, "learning_rate": 3.976599208182332e-06, "loss": 0.1086, "step": 4948 }, { "epoch": 8.02, "learning_rate": 3.9703178452944805e-06, "loss": 0.0902, "step": 4949 }, { "epoch": 8.02, "learning_rate": 3.9640409005670075e-06, "loss": 0.1202, "step": 4950 }, { "epoch": 8.02, "learning_rate": 3.957768375729986e-06, "loss": 0.104, "step": 4951 }, { "epoch": 8.03, "learning_rate": 3.951500272512272e-06, "loss": 0.1449, "step": 4952 }, { "epoch": 8.03, "learning_rate": 3.945236592641513e-06, "loss": 0.1298, "step": 4953 }, { "epoch": 8.03, "learning_rate": 3.9389773378441185e-06, "loss": 0.1033, "step": 4954 }, { "epoch": 8.03, "learning_rate": 3.932722509845286e-06, "loss": 0.1234, "step": 4955 }, { "epoch": 8.03, "learning_rate": 3.926472110369002e-06, "loss": 0.1243, "step": 4956 }, { "epoch": 8.03, "learning_rate": 3.920226141138024e-06, "loss": 0.1148, "step": 4957 }, { "epoch": 8.04, "learning_rate": 3.913984603873877e-06, "loss": 0.0968, "step": 4958 }, { "epoch": 8.04, "learning_rate": 3.907747500296894e-06, "loss": 0.1193, "step": 4959 }, { "epoch": 8.04, "learning_rate": 3.901514832126154e-06, "loss": 0.1167, "step": 4960 }, { "epoch": 8.04, "learning_rate": 3.895286601079542e-06, "loss": 0.099, "step": 4961 }, { "epoch": 8.04, "learning_rate": 3.889062808873698e-06, "loss": 0.1084, "step": 4962 }, { "epoch": 8.04, "learning_rate": 3.882843457224046e-06, "loss": 0.1409, "step": 4963 }, { "epoch": 8.05, "learning_rate": 3.87662854784479e-06, "loss": 0.199, "step": 4964 }, { "epoch": 8.05, "learning_rate": 3.870418082448902e-06, "loss": 0.1235, "step": 4965 }, { "epoch": 8.05, "learning_rate": 3.864212062748132e-06, "loss": 0.135, "step": 4966 }, { "epoch": 8.05, "learning_rate": 3.858010490453014e-06, "loss": 0.1176, "step": 4967 }, { "epoch": 8.05, "learning_rate": 3.851813367272847e-06, "loss": 0.1615, "step": 4968 }, { "epoch": 8.05, "learning_rate": 3.845620694915695e-06, "loss": 0.091, "step": 4969 }, { "epoch": 8.06, "learning_rate": 3.83943247508842e-06, "loss": 0.1014, "step": 4970 }, { "epoch": 8.06, "learning_rate": 3.8332487094966285e-06, "loss": 0.1115, "step": 4971 }, { "epoch": 8.06, "learning_rate": 3.8270693998447254e-06, "loss": 0.1233, "step": 4972 }, { "epoch": 8.06, "learning_rate": 3.820894547835867e-06, "loss": 0.1163, "step": 4973 }, { "epoch": 8.06, "learning_rate": 3.8147241551719915e-06, "loss": 0.1327, "step": 4974 }, { "epoch": 8.06, "learning_rate": 3.808558223553804e-06, "loss": 0.1096, "step": 4975 }, { "epoch": 8.06, "learning_rate": 3.8023967546807838e-06, "loss": 0.1007, "step": 4976 }, { "epoch": 8.07, "learning_rate": 3.7962397502511696e-06, "loss": 0.1515, "step": 4977 }, { "epoch": 8.07, "learning_rate": 3.790087211961988e-06, "loss": 0.1287, "step": 4978 }, { "epoch": 8.07, "learning_rate": 3.7839391415090167e-06, "loss": 0.1649, "step": 4979 }, { "epoch": 8.07, "learning_rate": 3.777795540586817e-06, "loss": 0.1397, "step": 4980 }, { "epoch": 8.07, "learning_rate": 3.771656410888709e-06, "loss": 0.0921, "step": 4981 }, { "epoch": 8.07, "learning_rate": 3.765521754106776e-06, "loss": 0.2096, "step": 4982 }, { "epoch": 8.08, "learning_rate": 3.759391571931883e-06, "loss": 0.0991, "step": 4983 }, { "epoch": 8.08, "learning_rate": 3.7532658660536504e-06, "loss": 0.1075, "step": 4984 }, { "epoch": 8.08, "learning_rate": 3.7471446381604628e-06, "loss": 0.0995, "step": 4985 }, { "epoch": 8.08, "learning_rate": 3.741027889939486e-06, "loss": 0.1225, "step": 4986 }, { "epoch": 8.08, "learning_rate": 3.7349156230766358e-06, "loss": 0.1004, "step": 4987 }, { "epoch": 8.08, "learning_rate": 3.7288078392565963e-06, "loss": 0.1213, "step": 4988 }, { "epoch": 8.09, "learning_rate": 3.7227045401628204e-06, "loss": 0.0839, "step": 4989 }, { "epoch": 8.09, "learning_rate": 3.7166057274775134e-06, "loss": 0.1309, "step": 4990 }, { "epoch": 8.09, "learning_rate": 3.7105114028816647e-06, "loss": 0.1189, "step": 4991 }, { "epoch": 8.09, "learning_rate": 3.70442156805501e-06, "loss": 0.1434, "step": 4992 }, { "epoch": 8.09, "learning_rate": 3.698336224676047e-06, "loss": 0.1315, "step": 4993 }, { "epoch": 8.09, "learning_rate": 3.692255374422049e-06, "loss": 0.0907, "step": 4994 }, { "epoch": 8.1, "learning_rate": 3.686179018969038e-06, "loss": 0.1936, "step": 4995 }, { "epoch": 8.1, "learning_rate": 3.680107159991797e-06, "loss": 0.1185, "step": 4996 }, { "epoch": 8.1, "learning_rate": 3.6740397991638864e-06, "loss": 0.1021, "step": 4997 }, { "epoch": 8.1, "learning_rate": 3.667976938157607e-06, "loss": 0.2686, "step": 4998 }, { "epoch": 8.1, "learning_rate": 3.6619185786440257e-06, "loss": 0.1677, "step": 4999 }, { "epoch": 8.1, "learning_rate": 3.6558647222929745e-06, "loss": 0.1723, "step": 5000 }, { "epoch": 8.11, "learning_rate": 3.649815370773031e-06, "loss": 0.115, "step": 5001 }, { "epoch": 8.11, "learning_rate": 3.643770525751551e-06, "loss": 0.1077, "step": 5002 }, { "epoch": 8.11, "learning_rate": 3.6377301888946325e-06, "loss": 0.1365, "step": 5003 }, { "epoch": 8.11, "learning_rate": 3.6316943618671306e-06, "loss": 0.19, "step": 5004 }, { "epoch": 8.11, "learning_rate": 3.6256630463326725e-06, "loss": 0.1177, "step": 5005 }, { "epoch": 8.11, "learning_rate": 3.6196362439536192e-06, "loss": 0.1326, "step": 5006 }, { "epoch": 8.12, "learning_rate": 3.613613956391113e-06, "loss": 0.1287, "step": 5007 }, { "epoch": 8.12, "learning_rate": 3.6075961853050356e-06, "loss": 0.1034, "step": 5008 }, { "epoch": 8.12, "learning_rate": 3.6015829323540173e-06, "loss": 0.1462, "step": 5009 }, { "epoch": 8.12, "learning_rate": 3.5955741991954664e-06, "loss": 0.0927, "step": 5010 }, { "epoch": 8.12, "learning_rate": 3.589569987485528e-06, "loss": 0.1207, "step": 5011 }, { "epoch": 8.12, "learning_rate": 3.583570298879102e-06, "loss": 0.0933, "step": 5012 }, { "epoch": 8.12, "learning_rate": 3.5775751350298473e-06, "loss": 0.0914, "step": 5013 }, { "epoch": 8.13, "learning_rate": 3.5715844975901747e-06, "loss": 0.0869, "step": 5014 }, { "epoch": 8.13, "learning_rate": 3.5655983882112355e-06, "loss": 0.1337, "step": 5015 }, { "epoch": 8.13, "learning_rate": 3.5596168085429585e-06, "loss": 0.1591, "step": 5016 }, { "epoch": 8.13, "learning_rate": 3.553639760233998e-06, "loss": 0.1105, "step": 5017 }, { "epoch": 8.13, "learning_rate": 3.547667244931776e-06, "loss": 0.1068, "step": 5018 }, { "epoch": 8.13, "learning_rate": 3.541699264282461e-06, "loss": 0.1037, "step": 5019 }, { "epoch": 8.14, "learning_rate": 3.535735819930959e-06, "loss": 0.1052, "step": 5020 }, { "epoch": 8.14, "learning_rate": 3.5297769135209503e-06, "loss": 0.1232, "step": 5021 }, { "epoch": 8.14, "learning_rate": 3.523822546694844e-06, "loss": 0.1108, "step": 5022 }, { "epoch": 8.14, "learning_rate": 3.5178727210938045e-06, "loss": 0.1029, "step": 5023 }, { "epoch": 8.14, "learning_rate": 3.511927438357745e-06, "loss": 0.1643, "step": 5024 }, { "epoch": 8.14, "learning_rate": 3.505986700125323e-06, "loss": 0.0946, "step": 5025 }, { "epoch": 8.15, "learning_rate": 3.5000505080339565e-06, "loss": 0.1254, "step": 5026 }, { "epoch": 8.15, "learning_rate": 3.494118863719793e-06, "loss": 0.1002, "step": 5027 }, { "epoch": 8.15, "learning_rate": 3.4881917688177325e-06, "loss": 0.0792, "step": 5028 }, { "epoch": 8.15, "learning_rate": 3.4822692249614322e-06, "loss": 0.1223, "step": 5029 }, { "epoch": 8.15, "learning_rate": 3.476351233783277e-06, "loss": 0.0901, "step": 5030 }, { "epoch": 8.15, "learning_rate": 3.4704377969144053e-06, "loss": 0.0908, "step": 5031 }, { "epoch": 8.16, "learning_rate": 3.4645289159847084e-06, "loss": 0.107, "step": 5032 }, { "epoch": 8.16, "learning_rate": 3.4586245926228103e-06, "loss": 0.0985, "step": 5033 }, { "epoch": 8.16, "learning_rate": 3.4527248284560754e-06, "loss": 0.1352, "step": 5034 }, { "epoch": 8.16, "learning_rate": 3.446829625110628e-06, "loss": 0.0868, "step": 5035 }, { "epoch": 8.16, "learning_rate": 3.440938984211324e-06, "loss": 0.0717, "step": 5036 }, { "epoch": 8.16, "learning_rate": 3.435052907381762e-06, "loss": 0.0994, "step": 5037 }, { "epoch": 8.17, "learning_rate": 3.429171396244284e-06, "loss": 0.1281, "step": 5038 }, { "epoch": 8.17, "learning_rate": 3.4232944524199696e-06, "loss": 0.1275, "step": 5039 }, { "epoch": 8.17, "learning_rate": 3.4174220775286536e-06, "loss": 0.1286, "step": 5040 }, { "epoch": 8.17, "learning_rate": 3.4115542731888974e-06, "loss": 0.1369, "step": 5041 }, { "epoch": 8.17, "learning_rate": 3.405691041018e-06, "loss": 0.1336, "step": 5042 }, { "epoch": 8.17, "learning_rate": 3.399832382632018e-06, "loss": 0.0867, "step": 5043 }, { "epoch": 8.18, "learning_rate": 3.393978299645728e-06, "loss": 0.1014, "step": 5044 }, { "epoch": 8.18, "learning_rate": 3.3881287936726627e-06, "loss": 0.1354, "step": 5045 }, { "epoch": 8.18, "learning_rate": 3.382283866325078e-06, "loss": 0.1242, "step": 5046 }, { "epoch": 8.18, "learning_rate": 3.3764435192139745e-06, "loss": 0.1256, "step": 5047 }, { "epoch": 8.18, "learning_rate": 3.3706077539490933e-06, "loss": 0.1013, "step": 5048 }, { "epoch": 8.18, "learning_rate": 3.364776572138917e-06, "loss": 0.1093, "step": 5049 }, { "epoch": 8.18, "learning_rate": 3.3589499753906375e-06, "loss": 0.1025, "step": 5050 }, { "epoch": 8.19, "learning_rate": 3.353127965310219e-06, "loss": 0.1224, "step": 5051 }, { "epoch": 8.19, "learning_rate": 3.34731054350234e-06, "loss": 0.1008, "step": 5052 }, { "epoch": 8.19, "learning_rate": 3.341497711570416e-06, "loss": 0.0866, "step": 5053 }, { "epoch": 8.19, "learning_rate": 3.335689471116612e-06, "loss": 0.1021, "step": 5054 }, { "epoch": 8.19, "learning_rate": 3.329885823741805e-06, "loss": 0.1068, "step": 5055 }, { "epoch": 8.19, "learning_rate": 3.3240867710456293e-06, "loss": 0.1098, "step": 5056 }, { "epoch": 8.2, "learning_rate": 3.3182923146264367e-06, "loss": 0.1786, "step": 5057 }, { "epoch": 8.2, "learning_rate": 3.312502456081308e-06, "loss": 0.1219, "step": 5058 }, { "epoch": 8.2, "learning_rate": 3.3067171970060796e-06, "loss": 0.1861, "step": 5059 }, { "epoch": 8.2, "learning_rate": 3.3009365389953008e-06, "loss": 0.1514, "step": 5060 }, { "epoch": 8.2, "learning_rate": 3.2951604836422544e-06, "loss": 0.0979, "step": 5061 }, { "epoch": 8.2, "learning_rate": 3.289389032538961e-06, "loss": 0.0822, "step": 5062 }, { "epoch": 8.21, "learning_rate": 3.283622187276163e-06, "loss": 0.1084, "step": 5063 }, { "epoch": 8.21, "learning_rate": 3.2778599494433517e-06, "loss": 0.1002, "step": 5064 }, { "epoch": 8.21, "learning_rate": 3.2721023206287296e-06, "loss": 0.1293, "step": 5065 }, { "epoch": 8.21, "learning_rate": 3.2663493024192316e-06, "loss": 0.0968, "step": 5066 }, { "epoch": 8.21, "learning_rate": 3.2606008964005365e-06, "loss": 0.1568, "step": 5067 }, { "epoch": 8.21, "learning_rate": 3.254857104157034e-06, "loss": 0.0714, "step": 5068 }, { "epoch": 8.22, "learning_rate": 3.2491179272718453e-06, "loss": 0.0999, "step": 5069 }, { "epoch": 8.22, "learning_rate": 3.2433833673268358e-06, "loss": 0.0963, "step": 5070 }, { "epoch": 8.22, "learning_rate": 3.237653425902576e-06, "loss": 0.117, "step": 5071 }, { "epoch": 8.22, "learning_rate": 3.2319281045783747e-06, "loss": 0.0898, "step": 5072 }, { "epoch": 8.22, "learning_rate": 3.2262074049322736e-06, "loss": 0.134, "step": 5073 }, { "epoch": 8.22, "learning_rate": 3.220491328541027e-06, "loss": 0.0983, "step": 5074 }, { "epoch": 8.23, "learning_rate": 3.214779876980121e-06, "loss": 0.1256, "step": 5075 }, { "epoch": 8.23, "learning_rate": 3.20907305182377e-06, "loss": 0.0775, "step": 5076 }, { "epoch": 8.23, "learning_rate": 3.2033708546449026e-06, "loss": 0.1089, "step": 5077 }, { "epoch": 8.23, "learning_rate": 3.1976732870151903e-06, "loss": 0.1197, "step": 5078 }, { "epoch": 8.23, "learning_rate": 3.1919803505050105e-06, "loss": 0.0946, "step": 5079 }, { "epoch": 8.23, "learning_rate": 3.186292046683472e-06, "loss": 0.0853, "step": 5080 }, { "epoch": 8.24, "learning_rate": 3.1806083771184104e-06, "loss": 0.1189, "step": 5081 }, { "epoch": 8.24, "learning_rate": 3.174929343376374e-06, "loss": 0.1034, "step": 5082 }, { "epoch": 8.24, "learning_rate": 3.1692549470226463e-06, "loss": 0.1085, "step": 5083 }, { "epoch": 8.24, "learning_rate": 3.1635851896212233e-06, "loss": 0.1794, "step": 5084 }, { "epoch": 8.24, "learning_rate": 3.1579200727348212e-06, "loss": 0.1071, "step": 5085 }, { "epoch": 8.24, "learning_rate": 3.1522595979248805e-06, "loss": 0.0895, "step": 5086 }, { "epoch": 8.24, "learning_rate": 3.146603766751566e-06, "loss": 0.107, "step": 5087 }, { "epoch": 8.25, "learning_rate": 3.1409525807737506e-06, "loss": 0.1379, "step": 5088 }, { "epoch": 8.25, "learning_rate": 3.1353060415490464e-06, "loss": 0.0774, "step": 5089 }, { "epoch": 8.25, "learning_rate": 3.1296641506337687e-06, "loss": 0.1447, "step": 5090 }, { "epoch": 8.25, "learning_rate": 3.124026909582951e-06, "loss": 0.1598, "step": 5091 }, { "epoch": 8.25, "learning_rate": 3.11839431995036e-06, "loss": 0.1097, "step": 5092 }, { "epoch": 8.25, "learning_rate": 3.112766383288459e-06, "loss": 0.1113, "step": 5093 }, { "epoch": 8.26, "learning_rate": 3.1071431011484555e-06, "loss": 0.1173, "step": 5094 }, { "epoch": 8.26, "learning_rate": 3.1015244750802532e-06, "loss": 0.0965, "step": 5095 }, { "epoch": 8.26, "learning_rate": 3.095910506632469e-06, "loss": 0.1184, "step": 5096 }, { "epoch": 8.26, "learning_rate": 3.090301197352461e-06, "loss": 0.0945, "step": 5097 }, { "epoch": 8.26, "learning_rate": 3.0846965487862813e-06, "loss": 0.099, "step": 5098 }, { "epoch": 8.26, "learning_rate": 3.0790965624787027e-06, "loss": 0.1058, "step": 5099 }, { "epoch": 8.27, "learning_rate": 3.0735012399732157e-06, "loss": 0.1053, "step": 5100 }, { "epoch": 8.27, "learning_rate": 3.067910582812017e-06, "loss": 0.0938, "step": 5101 }, { "epoch": 8.27, "learning_rate": 3.0623245925360344e-06, "loss": 0.1455, "step": 5102 }, { "epoch": 8.27, "learning_rate": 3.0567432706848964e-06, "loss": 0.1108, "step": 5103 }, { "epoch": 8.27, "learning_rate": 3.0511666187969415e-06, "loss": 0.1001, "step": 5104 }, { "epoch": 8.27, "learning_rate": 3.045594638409237e-06, "loss": 0.0814, "step": 5105 }, { "epoch": 8.28, "learning_rate": 3.040027331057547e-06, "loss": 0.151, "step": 5106 }, { "epoch": 8.28, "learning_rate": 3.0344646982763517e-06, "loss": 0.0782, "step": 5107 }, { "epoch": 8.28, "learning_rate": 3.0289067415988495e-06, "loss": 0.1276, "step": 5108 }, { "epoch": 8.28, "learning_rate": 3.0233534625569416e-06, "loss": 0.1479, "step": 5109 }, { "epoch": 8.28, "learning_rate": 3.0178048626812464e-06, "loss": 0.0973, "step": 5110 }, { "epoch": 8.28, "learning_rate": 3.0122609435010863e-06, "loss": 0.0977, "step": 5111 }, { "epoch": 8.29, "learning_rate": 3.0067217065444932e-06, "loss": 0.1157, "step": 5112 }, { "epoch": 8.29, "learning_rate": 3.0011871533382207e-06, "loss": 0.1097, "step": 5113 }, { "epoch": 8.29, "learning_rate": 2.9956572854077205e-06, "loss": 0.0901, "step": 5114 }, { "epoch": 8.29, "learning_rate": 2.990132104277148e-06, "loss": 0.1058, "step": 5115 }, { "epoch": 8.29, "learning_rate": 2.984611611469386e-06, "loss": 0.1336, "step": 5116 }, { "epoch": 8.29, "learning_rate": 2.9790958085060052e-06, "loss": 0.0978, "step": 5117 }, { "epoch": 8.29, "learning_rate": 2.97358469690729e-06, "loss": 0.1188, "step": 5118 }, { "epoch": 8.3, "learning_rate": 2.968078278192241e-06, "loss": 0.1205, "step": 5119 }, { "epoch": 8.3, "learning_rate": 2.962576553878549e-06, "loss": 0.1745, "step": 5120 }, { "epoch": 8.3, "learning_rate": 2.957079525482631e-06, "loss": 0.1738, "step": 5121 }, { "epoch": 8.3, "learning_rate": 2.9515871945195897e-06, "loss": 0.1079, "step": 5122 }, { "epoch": 8.3, "learning_rate": 2.946099562503244e-06, "loss": 0.1098, "step": 5123 }, { "epoch": 8.3, "learning_rate": 2.9406166309461136e-06, "loss": 0.2211, "step": 5124 }, { "epoch": 8.31, "learning_rate": 2.9351384013594273e-06, "loss": 0.0739, "step": 5125 }, { "epoch": 8.31, "learning_rate": 2.9296648752531085e-06, "loss": 0.086, "step": 5126 }, { "epoch": 8.31, "learning_rate": 2.9241960541357995e-06, "loss": 0.1999, "step": 5127 }, { "epoch": 8.31, "learning_rate": 2.9187319395148296e-06, "loss": 0.1022, "step": 5128 }, { "epoch": 8.31, "learning_rate": 2.9132725328962473e-06, "loss": 0.0846, "step": 5129 }, { "epoch": 8.31, "learning_rate": 2.9078178357847874e-06, "loss": 0.1416, "step": 5130 }, { "epoch": 8.32, "learning_rate": 2.9023678496838915e-06, "loss": 0.1617, "step": 5131 }, { "epoch": 8.32, "learning_rate": 2.8969225760957133e-06, "loss": 0.1402, "step": 5132 }, { "epoch": 8.32, "learning_rate": 2.8914820165210965e-06, "loss": 0.1174, "step": 5133 }, { "epoch": 8.32, "learning_rate": 2.8860461724595846e-06, "loss": 0.1119, "step": 5134 }, { "epoch": 8.32, "learning_rate": 2.8806150454094293e-06, "loss": 0.0864, "step": 5135 }, { "epoch": 8.32, "learning_rate": 2.8751886368675742e-06, "loss": 0.1213, "step": 5136 }, { "epoch": 8.33, "learning_rate": 2.8697669483296644e-06, "loss": 0.1357, "step": 5137 }, { "epoch": 8.33, "learning_rate": 2.864349981290053e-06, "loss": 0.1315, "step": 5138 }, { "epoch": 8.33, "learning_rate": 2.858937737241776e-06, "loss": 0.1014, "step": 5139 }, { "epoch": 8.33, "learning_rate": 2.8535302176765855e-06, "loss": 0.1166, "step": 5140 }, { "epoch": 8.33, "learning_rate": 2.8481274240849187e-06, "loss": 0.1641, "step": 5141 }, { "epoch": 8.33, "learning_rate": 2.8427293579559067e-06, "loss": 0.1042, "step": 5142 }, { "epoch": 8.34, "learning_rate": 2.8373360207773947e-06, "loss": 0.1529, "step": 5143 }, { "epoch": 8.34, "learning_rate": 2.8319474140359093e-06, "loss": 0.1205, "step": 5144 }, { "epoch": 8.34, "learning_rate": 2.8265635392166733e-06, "loss": 0.1089, "step": 5145 }, { "epoch": 8.34, "learning_rate": 2.8211843978036223e-06, "loss": 0.1009, "step": 5146 }, { "epoch": 8.34, "learning_rate": 2.8158099912793656e-06, "loss": 0.1006, "step": 5147 }, { "epoch": 8.34, "learning_rate": 2.810440321125223e-06, "loss": 0.0985, "step": 5148 }, { "epoch": 8.35, "learning_rate": 2.805075388821197e-06, "loss": 0.1132, "step": 5149 }, { "epoch": 8.35, "learning_rate": 2.7997151958459888e-06, "loss": 0.092, "step": 5150 }, { "epoch": 8.35, "learning_rate": 2.7943597436770043e-06, "loss": 0.1189, "step": 5151 }, { "epoch": 8.35, "learning_rate": 2.7890090337903287e-06, "loss": 0.1055, "step": 5152 }, { "epoch": 8.35, "learning_rate": 2.7836630676607358e-06, "loss": 0.1183, "step": 5153 }, { "epoch": 8.35, "learning_rate": 2.7783218467617134e-06, "loss": 0.0913, "step": 5154 }, { "epoch": 8.35, "learning_rate": 2.7729853725654244e-06, "loss": 0.1565, "step": 5155 }, { "epoch": 8.36, "learning_rate": 2.7676536465427207e-06, "loss": 0.1138, "step": 5156 }, { "epoch": 8.36, "learning_rate": 2.7623266701631646e-06, "loss": 0.0998, "step": 5157 }, { "epoch": 8.36, "learning_rate": 2.7570044448949886e-06, "loss": 0.1136, "step": 5158 }, { "epoch": 8.36, "learning_rate": 2.7516869722051256e-06, "loss": 0.1178, "step": 5159 }, { "epoch": 8.36, "learning_rate": 2.7463742535591986e-06, "loss": 0.0889, "step": 5160 }, { "epoch": 8.36, "learning_rate": 2.7410662904215147e-06, "loss": 0.0944, "step": 5161 }, { "epoch": 8.37, "learning_rate": 2.7357630842550785e-06, "loss": 0.1566, "step": 5162 }, { "epoch": 8.37, "learning_rate": 2.7304646365215813e-06, "loss": 0.1384, "step": 5163 }, { "epoch": 8.37, "learning_rate": 2.7251709486813925e-06, "loss": 0.1297, "step": 5164 }, { "epoch": 8.37, "learning_rate": 2.7198820221935875e-06, "loss": 0.1071, "step": 5165 }, { "epoch": 8.37, "learning_rate": 2.714597858515913e-06, "loss": 0.0708, "step": 5166 }, { "epoch": 8.37, "learning_rate": 2.709318459104815e-06, "loss": 0.1317, "step": 5167 }, { "epoch": 8.38, "learning_rate": 2.7040438254154187e-06, "loss": 0.1405, "step": 5168 }, { "epoch": 8.38, "learning_rate": 2.698773958901533e-06, "loss": 0.1104, "step": 5169 }, { "epoch": 8.38, "learning_rate": 2.693508861015668e-06, "loss": 0.1468, "step": 5170 }, { "epoch": 8.38, "learning_rate": 2.688248533209006e-06, "loss": 0.0869, "step": 5171 }, { "epoch": 8.38, "learning_rate": 2.6829929769314155e-06, "loss": 0.114, "step": 5172 }, { "epoch": 8.38, "learning_rate": 2.677742193631454e-06, "loss": 0.0876, "step": 5173 }, { "epoch": 8.39, "learning_rate": 2.672496184756359e-06, "loss": 0.0947, "step": 5174 }, { "epoch": 8.39, "learning_rate": 2.6672549517520564e-06, "loss": 0.1212, "step": 5175 }, { "epoch": 8.39, "learning_rate": 2.6620184960631567e-06, "loss": 0.1271, "step": 5176 }, { "epoch": 8.39, "learning_rate": 2.656786819132946e-06, "loss": 0.0995, "step": 5177 }, { "epoch": 8.39, "learning_rate": 2.651559922403406e-06, "loss": 0.1288, "step": 5178 }, { "epoch": 8.39, "learning_rate": 2.646337807315191e-06, "loss": 0.1019, "step": 5179 }, { "epoch": 8.4, "learning_rate": 2.6411204753076325e-06, "loss": 0.1143, "step": 5180 }, { "epoch": 8.4, "learning_rate": 2.6359079278187616e-06, "loss": 0.1007, "step": 5181 }, { "epoch": 8.4, "learning_rate": 2.630700166285274e-06, "loss": 0.1196, "step": 5182 }, { "epoch": 8.4, "learning_rate": 2.6254971921425545e-06, "loss": 0.137, "step": 5183 }, { "epoch": 8.4, "learning_rate": 2.6202990068246625e-06, "loss": 0.0792, "step": 5184 }, { "epoch": 8.4, "learning_rate": 2.6151056117643412e-06, "loss": 0.1142, "step": 5185 }, { "epoch": 8.41, "learning_rate": 2.609917008393019e-06, "loss": 0.0818, "step": 5186 }, { "epoch": 8.41, "learning_rate": 2.604733198140794e-06, "loss": 0.1115, "step": 5187 }, { "epoch": 8.41, "learning_rate": 2.5995541824364436e-06, "loss": 0.115, "step": 5188 }, { "epoch": 8.41, "learning_rate": 2.594379962707434e-06, "loss": 0.1381, "step": 5189 }, { "epoch": 8.41, "learning_rate": 2.589210540379903e-06, "loss": 0.1358, "step": 5190 }, { "epoch": 8.41, "learning_rate": 2.5840459168786568e-06, "loss": 0.1457, "step": 5191 }, { "epoch": 8.41, "learning_rate": 2.5788860936271998e-06, "loss": 0.1122, "step": 5192 }, { "epoch": 8.42, "learning_rate": 2.5737310720476914e-06, "loss": 0.0967, "step": 5193 }, { "epoch": 8.42, "learning_rate": 2.5685808535609867e-06, "loss": 0.087, "step": 5194 }, { "epoch": 8.42, "learning_rate": 2.5634354395866036e-06, "loss": 0.1278, "step": 5195 }, { "epoch": 8.42, "learning_rate": 2.5582948315427403e-06, "loss": 0.0997, "step": 5196 }, { "epoch": 8.42, "learning_rate": 2.5531590308462704e-06, "loss": 0.0912, "step": 5197 }, { "epoch": 8.42, "learning_rate": 2.5480280389127422e-06, "loss": 0.0983, "step": 5198 }, { "epoch": 8.43, "learning_rate": 2.5429018571563747e-06, "loss": 0.1129, "step": 5199 }, { "epoch": 8.43, "learning_rate": 2.5377804869900733e-06, "loss": 0.1091, "step": 5200 }, { "epoch": 8.43, "learning_rate": 2.532663929825405e-06, "loss": 0.2139, "step": 5201 }, { "epoch": 8.43, "learning_rate": 2.5275521870726107e-06, "loss": 0.1712, "step": 5202 }, { "epoch": 8.43, "learning_rate": 2.5224452601406134e-06, "loss": 0.1157, "step": 5203 }, { "epoch": 8.43, "learning_rate": 2.517343150436997e-06, "loss": 0.1023, "step": 5204 }, { "epoch": 8.44, "learning_rate": 2.5122458593680323e-06, "loss": 0.1089, "step": 5205 }, { "epoch": 8.44, "learning_rate": 2.50715338833865e-06, "loss": 0.0808, "step": 5206 }, { "epoch": 8.44, "learning_rate": 2.502065738752455e-06, "loss": 0.1374, "step": 5207 }, { "epoch": 8.44, "learning_rate": 2.496982912011725e-06, "loss": 0.093, "step": 5208 }, { "epoch": 8.44, "learning_rate": 2.4919049095174043e-06, "loss": 0.1088, "step": 5209 }, { "epoch": 8.44, "learning_rate": 2.4868317326691107e-06, "loss": 0.1363, "step": 5210 }, { "epoch": 8.45, "learning_rate": 2.4817633828651387e-06, "loss": 0.1122, "step": 5211 }, { "epoch": 8.45, "learning_rate": 2.4766998615024364e-06, "loss": 0.1305, "step": 5212 }, { "epoch": 8.45, "learning_rate": 2.4716411699766395e-06, "loss": 0.0823, "step": 5213 }, { "epoch": 8.45, "learning_rate": 2.466587309682038e-06, "loss": 0.0928, "step": 5214 }, { "epoch": 8.45, "learning_rate": 2.4615382820115953e-06, "loss": 0.118, "step": 5215 }, { "epoch": 8.45, "learning_rate": 2.4564940883569467e-06, "loss": 0.1437, "step": 5216 }, { "epoch": 8.46, "learning_rate": 2.451454730108389e-06, "loss": 0.0869, "step": 5217 }, { "epoch": 8.46, "learning_rate": 2.4464202086548874e-06, "loss": 0.1315, "step": 5218 }, { "epoch": 8.46, "learning_rate": 2.4413905253840776e-06, "loss": 0.1466, "step": 5219 }, { "epoch": 8.46, "learning_rate": 2.436365681682262e-06, "loss": 0.1069, "step": 5220 }, { "epoch": 8.46, "learning_rate": 2.4313456789344025e-06, "loss": 0.1066, "step": 5221 }, { "epoch": 8.46, "learning_rate": 2.4263305185241316e-06, "loss": 0.1132, "step": 5222 }, { "epoch": 8.47, "learning_rate": 2.4213202018337433e-06, "loss": 0.1073, "step": 5223 }, { "epoch": 8.47, "learning_rate": 2.416314730244207e-06, "loss": 0.1279, "step": 5224 }, { "epoch": 8.47, "learning_rate": 2.4113141051351474e-06, "loss": 0.0755, "step": 5225 }, { "epoch": 8.47, "learning_rate": 2.406318327884847e-06, "loss": 0.0853, "step": 5226 }, { "epoch": 8.47, "learning_rate": 2.40132739987027e-06, "loss": 0.1366, "step": 5227 }, { "epoch": 8.47, "learning_rate": 2.396341322467033e-06, "loss": 0.1211, "step": 5228 }, { "epoch": 8.47, "learning_rate": 2.391360097049411e-06, "loss": 0.1166, "step": 5229 }, { "epoch": 8.48, "learning_rate": 2.3863837249903577e-06, "loss": 0.1283, "step": 5230 }, { "epoch": 8.48, "learning_rate": 2.381412207661473e-06, "loss": 0.0941, "step": 5231 }, { "epoch": 8.48, "learning_rate": 2.3764455464330236e-06, "loss": 0.109, "step": 5232 }, { "epoch": 8.48, "learning_rate": 2.3714837426739436e-06, "loss": 0.0997, "step": 5233 }, { "epoch": 8.48, "learning_rate": 2.3665267977518157e-06, "loss": 0.1306, "step": 5234 }, { "epoch": 8.48, "learning_rate": 2.3615747130329013e-06, "loss": 0.0975, "step": 5235 }, { "epoch": 8.49, "learning_rate": 2.3566274898821083e-06, "loss": 0.0866, "step": 5236 }, { "epoch": 8.49, "learning_rate": 2.351685129663004e-06, "loss": 0.1408, "step": 5237 }, { "epoch": 8.49, "learning_rate": 2.346747633737829e-06, "loss": 0.1035, "step": 5238 }, { "epoch": 8.49, "learning_rate": 2.341815003467469e-06, "loss": 0.1164, "step": 5239 }, { "epoch": 8.49, "learning_rate": 2.336887240211472e-06, "loss": 0.1117, "step": 5240 }, { "epoch": 8.49, "learning_rate": 2.3319643453280504e-06, "loss": 0.162, "step": 5241 }, { "epoch": 8.5, "learning_rate": 2.3270463201740668e-06, "loss": 0.1053, "step": 5242 }, { "epoch": 8.5, "learning_rate": 2.3221331661050516e-06, "loss": 0.1141, "step": 5243 }, { "epoch": 8.5, "learning_rate": 2.317224884475182e-06, "loss": 0.1034, "step": 5244 }, { "epoch": 8.5, "learning_rate": 2.312321476637298e-06, "loss": 0.0888, "step": 5245 }, { "epoch": 8.5, "learning_rate": 2.3074229439428964e-06, "loss": 0.1393, "step": 5246 }, { "epoch": 8.5, "learning_rate": 2.302529287742126e-06, "loss": 0.1227, "step": 5247 }, { "epoch": 8.51, "learning_rate": 2.2976405093837895e-06, "loss": 0.113, "step": 5248 }, { "epoch": 8.51, "learning_rate": 2.292756610215361e-06, "loss": 0.1048, "step": 5249 }, { "epoch": 8.51, "learning_rate": 2.287877591582952e-06, "loss": 0.1359, "step": 5250 }, { "epoch": 8.51, "learning_rate": 2.283003454831341e-06, "loss": 0.11, "step": 5251 }, { "epoch": 8.51, "learning_rate": 2.278134201303952e-06, "loss": 0.0917, "step": 5252 }, { "epoch": 8.51, "learning_rate": 2.2732698323428613e-06, "loss": 0.128, "step": 5253 }, { "epoch": 8.52, "learning_rate": 2.2684103492888165e-06, "loss": 0.1226, "step": 5254 }, { "epoch": 8.52, "learning_rate": 2.263555753481199e-06, "loss": 0.1025, "step": 5255 }, { "epoch": 8.52, "learning_rate": 2.258706046258052e-06, "loss": 0.1103, "step": 5256 }, { "epoch": 8.52, "learning_rate": 2.253861228956067e-06, "loss": 0.113, "step": 5257 }, { "epoch": 8.52, "learning_rate": 2.2490213029105947e-06, "loss": 0.1064, "step": 5258 }, { "epoch": 8.52, "learning_rate": 2.244186269455628e-06, "loss": 0.1145, "step": 5259 }, { "epoch": 8.53, "learning_rate": 2.239356129923822e-06, "loss": 0.1244, "step": 5260 }, { "epoch": 8.53, "learning_rate": 2.234530885646473e-06, "loss": 0.1705, "step": 5261 }, { "epoch": 8.53, "learning_rate": 2.22971053795354e-06, "loss": 0.1288, "step": 5262 }, { "epoch": 8.53, "learning_rate": 2.2248950881736198e-06, "loss": 0.1056, "step": 5263 }, { "epoch": 8.53, "learning_rate": 2.2200845376339595e-06, "loss": 0.1023, "step": 5264 }, { "epoch": 8.53, "learning_rate": 2.2152788876604726e-06, "loss": 0.0769, "step": 5265 }, { "epoch": 8.53, "learning_rate": 2.210478139577705e-06, "loss": 0.1036, "step": 5266 }, { "epoch": 8.54, "learning_rate": 2.205682294708851e-06, "loss": 0.1212, "step": 5267 }, { "epoch": 8.54, "learning_rate": 2.2008913543757673e-06, "loss": 0.1352, "step": 5268 }, { "epoch": 8.54, "learning_rate": 2.1961053198989467e-06, "loss": 0.115, "step": 5269 }, { "epoch": 8.54, "learning_rate": 2.191324192597535e-06, "loss": 0.1018, "step": 5270 }, { "epoch": 8.54, "learning_rate": 2.1865479737893238e-06, "loss": 0.1326, "step": 5271 }, { "epoch": 8.54, "learning_rate": 2.181776664790749e-06, "loss": 0.095, "step": 5272 }, { "epoch": 8.55, "learning_rate": 2.177010266916901e-06, "loss": 0.1255, "step": 5273 }, { "epoch": 8.55, "learning_rate": 2.172248781481514e-06, "loss": 0.099, "step": 5274 }, { "epoch": 8.55, "learning_rate": 2.167492209796955e-06, "loss": 0.1049, "step": 5275 }, { "epoch": 8.55, "learning_rate": 2.1627405531742627e-06, "loss": 0.1029, "step": 5276 }, { "epoch": 8.55, "learning_rate": 2.157993812923098e-06, "loss": 0.1092, "step": 5277 }, { "epoch": 8.55, "learning_rate": 2.1532519903517723e-06, "loss": 0.0869, "step": 5278 }, { "epoch": 8.56, "learning_rate": 2.148515086767251e-06, "loss": 0.1676, "step": 5279 }, { "epoch": 8.56, "learning_rate": 2.1437831034751367e-06, "loss": 0.1057, "step": 5280 }, { "epoch": 8.56, "learning_rate": 2.1390560417796723e-06, "loss": 0.1161, "step": 5281 }, { "epoch": 8.56, "learning_rate": 2.1343339029837496e-06, "loss": 0.0806, "step": 5282 }, { "epoch": 8.56, "learning_rate": 2.129616688388898e-06, "loss": 0.0918, "step": 5283 }, { "epoch": 8.56, "learning_rate": 2.124904399295302e-06, "loss": 0.1003, "step": 5284 }, { "epoch": 8.57, "learning_rate": 2.1201970370017743e-06, "loss": 0.1157, "step": 5285 }, { "epoch": 8.57, "learning_rate": 2.1154946028057744e-06, "loss": 0.1066, "step": 5286 }, { "epoch": 8.57, "learning_rate": 2.110797098003412e-06, "loss": 0.128, "step": 5287 }, { "epoch": 8.57, "learning_rate": 2.1061045238894206e-06, "loss": 0.0994, "step": 5288 }, { "epoch": 8.57, "learning_rate": 2.1014168817571946e-06, "loss": 0.0979, "step": 5289 }, { "epoch": 8.57, "learning_rate": 2.0967341728987554e-06, "loss": 0.1155, "step": 5290 }, { "epoch": 8.58, "learning_rate": 2.0920563986047627e-06, "loss": 0.1066, "step": 5291 }, { "epoch": 8.58, "learning_rate": 2.087383560164533e-06, "loss": 0.1018, "step": 5292 }, { "epoch": 8.58, "learning_rate": 2.082715658866006e-06, "loss": 0.135, "step": 5293 }, { "epoch": 8.58, "learning_rate": 2.0780526959957627e-06, "loss": 0.116, "step": 5294 }, { "epoch": 8.58, "learning_rate": 2.0733946728390332e-06, "loss": 0.0941, "step": 5295 }, { "epoch": 8.58, "learning_rate": 2.0687415906796682e-06, "loss": 0.0891, "step": 5296 }, { "epoch": 8.59, "learning_rate": 2.0640934508001798e-06, "loss": 0.1071, "step": 5297 }, { "epoch": 8.59, "learning_rate": 2.0594502544816984e-06, "loss": 0.0932, "step": 5298 }, { "epoch": 8.59, "learning_rate": 2.0548120030039987e-06, "loss": 0.1072, "step": 5299 }, { "epoch": 8.59, "learning_rate": 2.0501786976454975e-06, "loss": 0.1527, "step": 5300 }, { "epoch": 8.59, "learning_rate": 2.04555033968324e-06, "loss": 0.0726, "step": 5301 }, { "epoch": 8.59, "learning_rate": 2.04092693039291e-06, "loss": 0.0939, "step": 5302 }, { "epoch": 8.59, "learning_rate": 2.0363084710488334e-06, "loss": 0.1655, "step": 5303 }, { "epoch": 8.6, "learning_rate": 2.031694962923965e-06, "loss": 0.0879, "step": 5304 }, { "epoch": 8.6, "learning_rate": 2.027086407289893e-06, "loss": 0.106, "step": 5305 }, { "epoch": 8.6, "learning_rate": 2.0224828054168523e-06, "loss": 0.1343, "step": 5306 }, { "epoch": 8.6, "learning_rate": 2.0178841585736998e-06, "loss": 0.1008, "step": 5307 }, { "epoch": 8.6, "learning_rate": 2.013290468027931e-06, "loss": 0.1028, "step": 5308 }, { "epoch": 8.6, "learning_rate": 2.0087017350456796e-06, "loss": 0.1277, "step": 5309 }, { "epoch": 8.61, "learning_rate": 2.0041179608917003e-06, "loss": 0.1485, "step": 5310 }, { "epoch": 8.61, "learning_rate": 1.9995391468294032e-06, "loss": 0.1183, "step": 5311 }, { "epoch": 8.61, "learning_rate": 1.99496529412081e-06, "loss": 0.1192, "step": 5312 }, { "epoch": 8.61, "learning_rate": 1.990396404026578e-06, "loss": 0.1021, "step": 5313 }, { "epoch": 8.61, "learning_rate": 1.9858324778060133e-06, "loss": 0.0923, "step": 5314 }, { "epoch": 8.61, "learning_rate": 1.981273516717033e-06, "loss": 0.102, "step": 5315 }, { "epoch": 8.62, "learning_rate": 1.9767195220162037e-06, "loss": 0.1116, "step": 5316 }, { "epoch": 8.62, "learning_rate": 1.9721704949587073e-06, "loss": 0.1395, "step": 5317 }, { "epoch": 8.62, "learning_rate": 1.9676264367983643e-06, "loss": 0.1307, "step": 5318 }, { "epoch": 8.62, "learning_rate": 1.963087348787627e-06, "loss": 0.1043, "step": 5319 }, { "epoch": 8.62, "learning_rate": 1.9585532321775736e-06, "loss": 0.0895, "step": 5320 }, { "epoch": 8.62, "learning_rate": 1.954024088217912e-06, "loss": 0.1041, "step": 5321 }, { "epoch": 8.63, "learning_rate": 1.9494999181569874e-06, "loss": 0.1586, "step": 5322 }, { "epoch": 8.63, "learning_rate": 1.9449807232417674e-06, "loss": 0.1322, "step": 5323 }, { "epoch": 8.63, "learning_rate": 1.9404665047178417e-06, "loss": 0.0915, "step": 5324 }, { "epoch": 8.63, "learning_rate": 1.9359572638294446e-06, "loss": 0.1276, "step": 5325 }, { "epoch": 8.63, "learning_rate": 1.9314530018194253e-06, "loss": 0.1211, "step": 5326 }, { "epoch": 8.63, "learning_rate": 1.9269537199292674e-06, "loss": 0.1291, "step": 5327 }, { "epoch": 8.64, "learning_rate": 1.922459419399081e-06, "loss": 0.0835, "step": 5328 }, { "epoch": 8.64, "learning_rate": 1.9179701014675964e-06, "loss": 0.1148, "step": 5329 }, { "epoch": 8.64, "learning_rate": 1.913485767372181e-06, "loss": 0.1193, "step": 5330 }, { "epoch": 8.64, "learning_rate": 1.9090064183488243e-06, "loss": 0.1141, "step": 5331 }, { "epoch": 8.64, "learning_rate": 1.9045320556321357e-06, "loss": 0.1029, "step": 5332 }, { "epoch": 8.64, "learning_rate": 1.9000626804553613e-06, "loss": 0.1205, "step": 5333 }, { "epoch": 8.65, "learning_rate": 1.895598294050358e-06, "loss": 0.1084, "step": 5334 }, { "epoch": 8.65, "learning_rate": 1.8911388976476286e-06, "loss": 0.0961, "step": 5335 }, { "epoch": 8.65, "learning_rate": 1.8866844924762828e-06, "loss": 0.0917, "step": 5336 }, { "epoch": 8.65, "learning_rate": 1.8822350797640543e-06, "loss": 0.1323, "step": 5337 }, { "epoch": 8.65, "learning_rate": 1.8777906607373175e-06, "loss": 0.108, "step": 5338 }, { "epoch": 8.65, "learning_rate": 1.8733512366210527e-06, "loss": 0.1217, "step": 5339 }, { "epoch": 8.65, "learning_rate": 1.8689168086388697e-06, "loss": 0.0814, "step": 5340 }, { "epoch": 8.66, "learning_rate": 1.864487378013009e-06, "loss": 0.0973, "step": 5341 }, { "epoch": 8.66, "learning_rate": 1.8600629459643226e-06, "loss": 0.1411, "step": 5342 }, { "epoch": 8.66, "learning_rate": 1.8556435137122864e-06, "loss": 0.0745, "step": 5343 }, { "epoch": 8.66, "learning_rate": 1.8512290824750034e-06, "loss": 0.105, "step": 5344 }, { "epoch": 8.66, "learning_rate": 1.8468196534691917e-06, "loss": 0.1005, "step": 5345 }, { "epoch": 8.66, "learning_rate": 1.8424152279102015e-06, "loss": 0.103, "step": 5346 }, { "epoch": 8.67, "learning_rate": 1.8380158070119924e-06, "loss": 0.0946, "step": 5347 }, { "epoch": 8.67, "learning_rate": 1.8336213919871458e-06, "loss": 0.1232, "step": 5348 }, { "epoch": 8.67, "learning_rate": 1.8292319840468752e-06, "loss": 0.1093, "step": 5349 }, { "epoch": 8.67, "learning_rate": 1.8248475844010016e-06, "loss": 0.1073, "step": 5350 }, { "epoch": 8.67, "learning_rate": 1.8204681942579628e-06, "loss": 0.1224, "step": 5351 }, { "epoch": 8.67, "learning_rate": 1.8160938148248331e-06, "loss": 0.1322, "step": 5352 }, { "epoch": 8.68, "learning_rate": 1.811724447307286e-06, "loss": 0.1214, "step": 5353 }, { "epoch": 8.68, "learning_rate": 1.8073600929096314e-06, "loss": 0.1546, "step": 5354 }, { "epoch": 8.68, "learning_rate": 1.8030007528347848e-06, "loss": 0.1036, "step": 5355 }, { "epoch": 8.68, "learning_rate": 1.798646428284283e-06, "loss": 0.1103, "step": 5356 }, { "epoch": 8.68, "learning_rate": 1.7942971204582815e-06, "loss": 0.1003, "step": 5357 }, { "epoch": 8.68, "learning_rate": 1.7899528305555547e-06, "loss": 0.1188, "step": 5358 }, { "epoch": 8.69, "learning_rate": 1.7856135597734847e-06, "loss": 0.0888, "step": 5359 }, { "epoch": 8.69, "learning_rate": 1.781279309308086e-06, "loss": 0.0863, "step": 5360 }, { "epoch": 8.69, "learning_rate": 1.7769500803539785e-06, "loss": 0.1917, "step": 5361 }, { "epoch": 8.69, "learning_rate": 1.7726258741043945e-06, "loss": 0.1192, "step": 5362 }, { "epoch": 8.69, "learning_rate": 1.768306691751196e-06, "loss": 0.0853, "step": 5363 }, { "epoch": 8.69, "learning_rate": 1.7639925344848442e-06, "loss": 0.1028, "step": 5364 }, { "epoch": 8.7, "learning_rate": 1.759683403494432e-06, "loss": 0.1045, "step": 5365 }, { "epoch": 8.7, "learning_rate": 1.7553792999676523e-06, "loss": 0.1167, "step": 5366 }, { "epoch": 8.7, "learning_rate": 1.751080225090822e-06, "loss": 0.1352, "step": 5367 }, { "epoch": 8.7, "learning_rate": 1.7467861800488628e-06, "loss": 0.1286, "step": 5368 }, { "epoch": 8.7, "learning_rate": 1.7424971660253188e-06, "loss": 0.127, "step": 5369 }, { "epoch": 8.7, "learning_rate": 1.7382131842023374e-06, "loss": 0.1271, "step": 5370 }, { "epoch": 8.71, "learning_rate": 1.733934235760697e-06, "loss": 0.1019, "step": 5371 }, { "epoch": 8.71, "learning_rate": 1.729660321879767e-06, "loss": 0.1283, "step": 5372 }, { "epoch": 8.71, "learning_rate": 1.7253914437375453e-06, "loss": 0.1054, "step": 5373 }, { "epoch": 8.71, "learning_rate": 1.721127602510635e-06, "loss": 0.1343, "step": 5374 }, { "epoch": 8.71, "learning_rate": 1.7168687993742495e-06, "loss": 0.1084, "step": 5375 }, { "epoch": 8.71, "learning_rate": 1.7126150355022187e-06, "loss": 0.1088, "step": 5376 }, { "epoch": 8.71, "learning_rate": 1.7083663120669802e-06, "loss": 0.1348, "step": 5377 }, { "epoch": 8.72, "learning_rate": 1.7041226302395797e-06, "loss": 0.1338, "step": 5378 }, { "epoch": 8.72, "learning_rate": 1.6998839911896815e-06, "loss": 0.1148, "step": 5379 }, { "epoch": 8.72, "learning_rate": 1.695650396085553e-06, "loss": 0.1291, "step": 5380 }, { "epoch": 8.72, "learning_rate": 1.6914218460940724e-06, "loss": 0.0806, "step": 5381 }, { "epoch": 8.72, "learning_rate": 1.687198342380727e-06, "loss": 0.0968, "step": 5382 }, { "epoch": 8.72, "learning_rate": 1.6829798861096146e-06, "loss": 0.096, "step": 5383 }, { "epoch": 8.73, "learning_rate": 1.6787664784434477e-06, "loss": 0.1171, "step": 5384 }, { "epoch": 8.73, "learning_rate": 1.6745581205435367e-06, "loss": 0.113, "step": 5385 }, { "epoch": 8.73, "learning_rate": 1.6703548135698012e-06, "loss": 0.123, "step": 5386 }, { "epoch": 8.73, "learning_rate": 1.6661565586807782e-06, "loss": 0.1149, "step": 5387 }, { "epoch": 8.73, "learning_rate": 1.661963357033607e-06, "loss": 0.1234, "step": 5388 }, { "epoch": 8.73, "learning_rate": 1.657775209784025e-06, "loss": 0.1263, "step": 5389 }, { "epoch": 8.74, "learning_rate": 1.6535921180863956e-06, "loss": 0.0905, "step": 5390 }, { "epoch": 8.74, "learning_rate": 1.6494140830936723e-06, "loss": 0.1397, "step": 5391 }, { "epoch": 8.74, "learning_rate": 1.6452411059574203e-06, "loss": 0.0866, "step": 5392 }, { "epoch": 8.74, "learning_rate": 1.641073187827813e-06, "loss": 0.0933, "step": 5393 }, { "epoch": 8.74, "learning_rate": 1.6369103298536227e-06, "loss": 0.109, "step": 5394 }, { "epoch": 8.74, "learning_rate": 1.632752533182238e-06, "loss": 0.1288, "step": 5395 }, { "epoch": 8.75, "learning_rate": 1.6285997989596448e-06, "loss": 0.093, "step": 5396 }, { "epoch": 8.75, "learning_rate": 1.6244521283304293e-06, "loss": 0.144, "step": 5397 }, { "epoch": 8.75, "learning_rate": 1.6203095224377974e-06, "loss": 0.1035, "step": 5398 }, { "epoch": 8.75, "learning_rate": 1.61617198242354e-06, "loss": 0.1064, "step": 5399 }, { "epoch": 8.75, "learning_rate": 1.6120395094280693e-06, "loss": 0.1128, "step": 5400 }, { "epoch": 8.75, "learning_rate": 1.60791210459039e-06, "loss": 0.093, "step": 5401 }, { "epoch": 8.76, "learning_rate": 1.6037897690481075e-06, "loss": 0.0909, "step": 5402 }, { "epoch": 8.76, "learning_rate": 1.599672503937444e-06, "loss": 0.0838, "step": 5403 }, { "epoch": 8.76, "learning_rate": 1.5955603103932116e-06, "loss": 0.1144, "step": 5404 }, { "epoch": 8.76, "learning_rate": 1.5914531895488262e-06, "loss": 0.0826, "step": 5405 }, { "epoch": 8.76, "learning_rate": 1.5873511425363108e-06, "loss": 0.1443, "step": 5406 }, { "epoch": 8.76, "learning_rate": 1.5832541704862837e-06, "loss": 0.1099, "step": 5407 }, { "epoch": 8.76, "learning_rate": 1.5791622745279656e-06, "loss": 0.1036, "step": 5408 }, { "epoch": 8.77, "learning_rate": 1.5750754557891878e-06, "loss": 0.1576, "step": 5409 }, { "epoch": 8.77, "learning_rate": 1.570993715396365e-06, "loss": 0.1421, "step": 5410 }, { "epoch": 8.77, "learning_rate": 1.5669170544745326e-06, "loss": 0.1288, "step": 5411 }, { "epoch": 8.77, "learning_rate": 1.5628454741473076e-06, "loss": 0.0815, "step": 5412 }, { "epoch": 8.77, "learning_rate": 1.558778975536912e-06, "loss": 0.1161, "step": 5413 }, { "epoch": 8.77, "learning_rate": 1.5547175597641762e-06, "loss": 0.1457, "step": 5414 }, { "epoch": 8.78, "learning_rate": 1.55066122794852e-06, "loss": 0.1112, "step": 5415 }, { "epoch": 8.78, "learning_rate": 1.5466099812079627e-06, "loss": 0.0895, "step": 5416 }, { "epoch": 8.78, "learning_rate": 1.5425638206591264e-06, "loss": 0.1087, "step": 5417 }, { "epoch": 8.78, "learning_rate": 1.5385227474172215e-06, "loss": 0.0924, "step": 5418 }, { "epoch": 8.78, "learning_rate": 1.5344867625960746e-06, "loss": 0.0904, "step": 5419 }, { "epoch": 8.78, "learning_rate": 1.5304558673080937e-06, "loss": 0.1216, "step": 5420 }, { "epoch": 8.79, "learning_rate": 1.526430062664286e-06, "loss": 0.1301, "step": 5421 }, { "epoch": 8.79, "learning_rate": 1.5224093497742654e-06, "loss": 0.0718, "step": 5422 }, { "epoch": 8.79, "learning_rate": 1.5183937297462326e-06, "loss": 0.1148, "step": 5423 }, { "epoch": 8.79, "learning_rate": 1.514383203686982e-06, "loss": 0.0855, "step": 5424 }, { "epoch": 8.79, "learning_rate": 1.5103777727019186e-06, "loss": 0.1028, "step": 5425 }, { "epoch": 8.79, "learning_rate": 1.5063774378950325e-06, "loss": 0.1388, "step": 5426 }, { "epoch": 8.8, "learning_rate": 1.5023822003689036e-06, "loss": 0.1181, "step": 5427 }, { "epoch": 8.8, "learning_rate": 1.4983920612247227e-06, "loss": 0.1349, "step": 5428 }, { "epoch": 8.8, "learning_rate": 1.494407021562263e-06, "loss": 0.1299, "step": 5429 }, { "epoch": 8.8, "learning_rate": 1.490427082479895e-06, "loss": 0.109, "step": 5430 }, { "epoch": 8.8, "learning_rate": 1.4864522450745878e-06, "loss": 0.1023, "step": 5431 }, { "epoch": 8.8, "learning_rate": 1.4824825104418938e-06, "loss": 0.1107, "step": 5432 }, { "epoch": 8.81, "learning_rate": 1.4785178796759737e-06, "loss": 0.0816, "step": 5433 }, { "epoch": 8.81, "learning_rate": 1.4745583538695685e-06, "loss": 0.0698, "step": 5434 }, { "epoch": 8.81, "learning_rate": 1.4706039341140187e-06, "loss": 0.1151, "step": 5435 }, { "epoch": 8.81, "learning_rate": 1.4666546214992593e-06, "loss": 0.1329, "step": 5436 }, { "epoch": 8.81, "learning_rate": 1.4627104171138084e-06, "loss": 0.0837, "step": 5437 }, { "epoch": 8.81, "learning_rate": 1.4587713220447897e-06, "loss": 0.1336, "step": 5438 }, { "epoch": 8.82, "learning_rate": 1.4548373373779078e-06, "loss": 0.0937, "step": 5439 }, { "epoch": 8.82, "learning_rate": 1.4509084641974603e-06, "loss": 0.0861, "step": 5440 }, { "epoch": 8.82, "learning_rate": 1.4469847035863382e-06, "loss": 0.1445, "step": 5441 }, { "epoch": 8.82, "learning_rate": 1.4430660566260256e-06, "loss": 0.0903, "step": 5442 }, { "epoch": 8.82, "learning_rate": 1.4391525243965898e-06, "loss": 0.1643, "step": 5443 }, { "epoch": 8.82, "learning_rate": 1.4352441079766987e-06, "loss": 0.1194, "step": 5444 }, { "epoch": 8.82, "learning_rate": 1.4313408084435998e-06, "loss": 0.1561, "step": 5445 }, { "epoch": 8.83, "learning_rate": 1.4274426268731367e-06, "loss": 0.1134, "step": 5446 }, { "epoch": 8.83, "learning_rate": 1.4235495643397435e-06, "loss": 0.0962, "step": 5447 }, { "epoch": 8.83, "learning_rate": 1.4196616219164328e-06, "loss": 0.0842, "step": 5448 }, { "epoch": 8.83, "learning_rate": 1.415778800674823e-06, "loss": 0.1414, "step": 5449 }, { "epoch": 8.83, "learning_rate": 1.411901101685107e-06, "loss": 0.1023, "step": 5450 }, { "epoch": 8.83, "learning_rate": 1.4080285260160697e-06, "loss": 0.112, "step": 5451 }, { "epoch": 8.84, "learning_rate": 1.4041610747350887e-06, "loss": 0.1143, "step": 5452 }, { "epoch": 8.84, "learning_rate": 1.400298748908122e-06, "loss": 0.0918, "step": 5453 }, { "epoch": 8.84, "learning_rate": 1.3964415495997185e-06, "loss": 0.1348, "step": 5454 }, { "epoch": 8.84, "learning_rate": 1.3925894778730143e-06, "loss": 0.0966, "step": 5455 }, { "epoch": 8.84, "learning_rate": 1.3887425347897287e-06, "loss": 0.1081, "step": 5456 }, { "epoch": 8.84, "learning_rate": 1.3849007214101762e-06, "loss": 0.1027, "step": 5457 }, { "epoch": 8.85, "learning_rate": 1.3810640387932472e-06, "loss": 0.1127, "step": 5458 }, { "epoch": 8.85, "learning_rate": 1.3772324879964228e-06, "loss": 0.1277, "step": 5459 }, { "epoch": 8.85, "learning_rate": 1.3734060700757712e-06, "loss": 0.1233, "step": 5460 }, { "epoch": 8.85, "learning_rate": 1.3695847860859447e-06, "loss": 0.0935, "step": 5461 }, { "epoch": 8.85, "learning_rate": 1.3657686370801737e-06, "loss": 0.1196, "step": 5462 }, { "epoch": 8.85, "learning_rate": 1.361957624110286e-06, "loss": 0.109, "step": 5463 }, { "epoch": 8.86, "learning_rate": 1.358151748226686e-06, "loss": 0.1184, "step": 5464 }, { "epoch": 8.86, "learning_rate": 1.3543510104783609e-06, "loss": 0.1164, "step": 5465 }, { "epoch": 8.86, "learning_rate": 1.3505554119128861e-06, "loss": 0.1538, "step": 5466 }, { "epoch": 8.86, "learning_rate": 1.346764953576416e-06, "loss": 0.1285, "step": 5467 }, { "epoch": 8.86, "learning_rate": 1.3429796365136926e-06, "loss": 0.1058, "step": 5468 }, { "epoch": 8.86, "learning_rate": 1.3391994617680394e-06, "loss": 0.0979, "step": 5469 }, { "epoch": 8.87, "learning_rate": 1.3354244303813601e-06, "loss": 0.1938, "step": 5470 }, { "epoch": 8.87, "learning_rate": 1.3316545433941452e-06, "loss": 0.1986, "step": 5471 }, { "epoch": 8.87, "learning_rate": 1.3278898018454655e-06, "loss": 0.1259, "step": 5472 }, { "epoch": 8.87, "learning_rate": 1.3241302067729689e-06, "loss": 0.1054, "step": 5473 }, { "epoch": 8.87, "learning_rate": 1.320375759212893e-06, "loss": 0.1489, "step": 5474 }, { "epoch": 8.87, "learning_rate": 1.31662646020005e-06, "loss": 0.0814, "step": 5475 }, { "epoch": 8.88, "learning_rate": 1.3128823107678379e-06, "loss": 0.1125, "step": 5476 }, { "epoch": 8.88, "learning_rate": 1.3091433119482332e-06, "loss": 0.1591, "step": 5477 }, { "epoch": 8.88, "learning_rate": 1.3054094647717896e-06, "loss": 0.1022, "step": 5478 }, { "epoch": 8.88, "learning_rate": 1.301680770267646e-06, "loss": 0.0947, "step": 5479 }, { "epoch": 8.88, "learning_rate": 1.29795722946352e-06, "loss": 0.1227, "step": 5480 }, { "epoch": 8.88, "learning_rate": 1.2942388433857022e-06, "loss": 0.0951, "step": 5481 }, { "epoch": 8.88, "learning_rate": 1.2905256130590749e-06, "loss": 0.1685, "step": 5482 }, { "epoch": 8.89, "learning_rate": 1.286817539507086e-06, "loss": 0.1174, "step": 5483 }, { "epoch": 8.89, "learning_rate": 1.2831146237517755e-06, "loss": 0.1462, "step": 5484 }, { "epoch": 8.89, "learning_rate": 1.2794168668137496e-06, "loss": 0.1319, "step": 5485 }, { "epoch": 8.89, "learning_rate": 1.2757242697121997e-06, "loss": 0.0931, "step": 5486 }, { "epoch": 8.89, "learning_rate": 1.2720368334648936e-06, "loss": 0.1006, "step": 5487 }, { "epoch": 8.89, "learning_rate": 1.268354559088174e-06, "loss": 0.1246, "step": 5488 }, { "epoch": 8.9, "learning_rate": 1.264677447596967e-06, "loss": 0.1567, "step": 5489 }, { "epoch": 8.9, "learning_rate": 1.2610055000047683e-06, "loss": 0.1066, "step": 5490 }, { "epoch": 8.9, "learning_rate": 1.257338717323653e-06, "loss": 0.1059, "step": 5491 }, { "epoch": 8.9, "learning_rate": 1.2536771005642723e-06, "loss": 0.0809, "step": 5492 }, { "epoch": 8.9, "learning_rate": 1.2500206507358614e-06, "loss": 0.1284, "step": 5493 }, { "epoch": 8.9, "learning_rate": 1.2463693688462163e-06, "loss": 0.1143, "step": 5494 }, { "epoch": 8.91, "learning_rate": 1.2427232559017233e-06, "loss": 0.1401, "step": 5495 }, { "epoch": 8.91, "learning_rate": 1.2390823129073338e-06, "loss": 0.1022, "step": 5496 }, { "epoch": 8.91, "learning_rate": 1.2354465408665783e-06, "loss": 0.1094, "step": 5497 }, { "epoch": 8.91, "learning_rate": 1.2318159407815645e-06, "loss": 0.1294, "step": 5498 }, { "epoch": 8.91, "learning_rate": 1.2281905136529715e-06, "loss": 0.1087, "step": 5499 }, { "epoch": 8.91, "learning_rate": 1.2245702604800468e-06, "loss": 0.1561, "step": 5500 }, { "epoch": 8.92, "learning_rate": 1.2209551822606258e-06, "loss": 0.1019, "step": 5501 }, { "epoch": 8.92, "learning_rate": 1.2173452799911046e-06, "loss": 0.0846, "step": 5502 }, { "epoch": 8.92, "learning_rate": 1.2137405546664627e-06, "loss": 0.0929, "step": 5503 }, { "epoch": 8.92, "learning_rate": 1.2101410072802432e-06, "loss": 0.0933, "step": 5504 }, { "epoch": 8.92, "learning_rate": 1.206546638824566e-06, "loss": 0.0969, "step": 5505 }, { "epoch": 8.92, "learning_rate": 1.2029574502901297e-06, "loss": 0.1004, "step": 5506 }, { "epoch": 8.93, "learning_rate": 1.1993734426661985e-06, "loss": 0.1163, "step": 5507 }, { "epoch": 8.93, "learning_rate": 1.1957946169406021e-06, "loss": 0.1156, "step": 5508 }, { "epoch": 8.93, "learning_rate": 1.1922209740997604e-06, "loss": 0.1021, "step": 5509 }, { "epoch": 8.93, "learning_rate": 1.1886525151286477e-06, "loss": 0.1315, "step": 5510 }, { "epoch": 8.93, "learning_rate": 1.1850892410108172e-06, "loss": 0.1123, "step": 5511 }, { "epoch": 8.93, "learning_rate": 1.1815311527283924e-06, "loss": 0.0931, "step": 5512 }, { "epoch": 8.94, "learning_rate": 1.1779782512620686e-06, "loss": 0.1455, "step": 5513 }, { "epoch": 8.94, "learning_rate": 1.1744305375911048e-06, "loss": 0.0919, "step": 5514 }, { "epoch": 8.94, "learning_rate": 1.170888012693341e-06, "loss": 0.1087, "step": 5515 }, { "epoch": 8.94, "learning_rate": 1.1673506775451715e-06, "loss": 0.1031, "step": 5516 }, { "epoch": 8.94, "learning_rate": 1.1638185331215812e-06, "loss": 0.1291, "step": 5517 }, { "epoch": 8.94, "learning_rate": 1.1602915803961068e-06, "loss": 0.095, "step": 5518 }, { "epoch": 8.94, "learning_rate": 1.1567698203408574e-06, "loss": 0.1398, "step": 5519 }, { "epoch": 8.95, "learning_rate": 1.1532532539265185e-06, "loss": 0.1562, "step": 5520 }, { "epoch": 8.95, "learning_rate": 1.1497418821223373e-06, "loss": 0.1776, "step": 5521 }, { "epoch": 8.95, "learning_rate": 1.1462357058961327e-06, "loss": 0.105, "step": 5522 }, { "epoch": 8.95, "learning_rate": 1.1427347262142897e-06, "loss": 0.086, "step": 5523 }, { "epoch": 8.95, "learning_rate": 1.1392389440417584e-06, "loss": 0.0874, "step": 5524 }, { "epoch": 8.95, "learning_rate": 1.1357483603420616e-06, "loss": 0.1309, "step": 5525 }, { "epoch": 8.96, "learning_rate": 1.1322629760772874e-06, "loss": 0.1425, "step": 5526 }, { "epoch": 8.96, "learning_rate": 1.1287827922080897e-06, "loss": 0.1113, "step": 5527 }, { "epoch": 8.96, "learning_rate": 1.1253078096936898e-06, "loss": 0.1076, "step": 5528 }, { "epoch": 8.96, "learning_rate": 1.1218380294918729e-06, "loss": 0.1444, "step": 5529 }, { "epoch": 8.96, "learning_rate": 1.1183734525589939e-06, "loss": 0.0846, "step": 5530 }, { "epoch": 8.96, "learning_rate": 1.1149140798499758e-06, "loss": 0.0844, "step": 5531 }, { "epoch": 8.97, "learning_rate": 1.1114599123182956e-06, "loss": 0.1481, "step": 5532 }, { "epoch": 8.97, "learning_rate": 1.1080109509160142e-06, "loss": 0.1448, "step": 5533 }, { "epoch": 8.97, "learning_rate": 1.1045671965937421e-06, "loss": 0.1326, "step": 5534 }, { "epoch": 8.97, "learning_rate": 1.1011286503006557e-06, "loss": 0.1029, "step": 5535 }, { "epoch": 8.97, "learning_rate": 1.0976953129845058e-06, "loss": 0.0955, "step": 5536 }, { "epoch": 8.97, "learning_rate": 1.0942671855916e-06, "loss": 0.1166, "step": 5537 }, { "epoch": 8.98, "learning_rate": 1.090844269066813e-06, "loss": 0.1676, "step": 5538 }, { "epoch": 8.98, "learning_rate": 1.0874265643535776e-06, "loss": 0.1832, "step": 5539 }, { "epoch": 8.98, "learning_rate": 1.084014072393893e-06, "loss": 0.1224, "step": 5540 }, { "epoch": 8.98, "learning_rate": 1.0806067941283295e-06, "loss": 0.1276, "step": 5541 }, { "epoch": 8.98, "learning_rate": 1.0772047304960109e-06, "loss": 0.1254, "step": 5542 }, { "epoch": 8.98, "learning_rate": 1.0738078824346232e-06, "loss": 0.1087, "step": 5543 }, { "epoch": 8.99, "learning_rate": 1.0704162508804239e-06, "loss": 0.1365, "step": 5544 }, { "epoch": 8.99, "learning_rate": 1.067029836768223e-06, "loss": 0.0864, "step": 5545 }, { "epoch": 8.99, "learning_rate": 1.0636486410313961e-06, "loss": 0.1054, "step": 5546 }, { "epoch": 8.99, "learning_rate": 1.0602726646018868e-06, "loss": 0.1024, "step": 5547 }, { "epoch": 8.99, "learning_rate": 1.0569019084101883e-06, "loss": 0.1131, "step": 5548 }, { "epoch": 8.99, "learning_rate": 1.0535363733853598e-06, "loss": 0.1103, "step": 5549 }, { "epoch": 9.0, "learning_rate": 1.0501760604550281e-06, "loss": 0.1301, "step": 5550 }, { "epoch": 9.0, "learning_rate": 1.0468209705453725e-06, "loss": 0.1177, "step": 5551 }, { "epoch": 9.0, "learning_rate": 1.0434711045811352e-06, "loss": 0.0992, "step": 5552 }, { "epoch": 9.0, "learning_rate": 1.04012646348562e-06, "loss": 0.1036, "step": 5553 }, { "epoch": 9.0, "learning_rate": 1.036787048180683e-06, "loss": 0.0824, "step": 5554 }, { "epoch": 9.0, "learning_rate": 1.0334528595867543e-06, "loss": 0.0926, "step": 5555 }, { "epoch": 9.0, "learning_rate": 1.0301238986228146e-06, "loss": 0.1056, "step": 5556 }, { "epoch": 9.01, "learning_rate": 1.0268001662063965e-06, "loss": 0.1108, "step": 5557 }, { "epoch": 9.01, "learning_rate": 1.0234816632536094e-06, "loss": 0.0945, "step": 5558 }, { "epoch": 9.01, "learning_rate": 1.0201683906791016e-06, "loss": 0.087, "step": 5559 }, { "epoch": 9.01, "learning_rate": 1.0168603493961004e-06, "loss": 0.1226, "step": 5560 }, { "epoch": 9.01, "learning_rate": 1.0135575403163722e-06, "loss": 0.0811, "step": 5561 }, { "epoch": 9.01, "learning_rate": 1.0102599643502508e-06, "loss": 0.116, "step": 5562 }, { "epoch": 9.02, "learning_rate": 1.0069676224066316e-06, "loss": 0.1121, "step": 5563 }, { "epoch": 9.02, "learning_rate": 1.0036805153929574e-06, "loss": 0.1006, "step": 5564 }, { "epoch": 9.02, "learning_rate": 1.0003986442152325e-06, "loss": 0.1563, "step": 5565 }, { "epoch": 9.02, "learning_rate": 9.9712200977802e-07, "loss": 0.1168, "step": 5566 }, { "epoch": 9.02, "learning_rate": 9.93850612984435e-07, "loss": 0.1103, "step": 5567 }, { "epoch": 9.02, "learning_rate": 9.905844547361566e-07, "loss": 0.1061, "step": 5568 }, { "epoch": 9.03, "learning_rate": 9.873235359334131e-07, "loss": 0.0993, "step": 5569 }, { "epoch": 9.03, "learning_rate": 9.840678574749886e-07, "loss": 0.1284, "step": 5570 }, { "epoch": 9.03, "learning_rate": 9.80817420258231e-07, "loss": 0.144, "step": 5571 }, { "epoch": 9.03, "learning_rate": 9.775722251790354e-07, "loss": 0.0869, "step": 5572 }, { "epoch": 9.03, "learning_rate": 9.743322731318504e-07, "loss": 0.1646, "step": 5573 }, { "epoch": 9.03, "learning_rate": 9.710975650096889e-07, "loss": 0.0809, "step": 5574 }, { "epoch": 9.04, "learning_rate": 9.678681017041125e-07, "loss": 0.0777, "step": 5575 }, { "epoch": 9.04, "learning_rate": 9.646438841052364e-07, "loss": 0.143, "step": 5576 }, { "epoch": 9.04, "learning_rate": 9.614249131017317e-07, "loss": 0.1704, "step": 5577 }, { "epoch": 9.04, "learning_rate": 9.582111895808198e-07, "loss": 0.0935, "step": 5578 }, { "epoch": 9.04, "learning_rate": 9.550027144282836e-07, "loss": 0.0822, "step": 5579 }, { "epoch": 9.04, "learning_rate": 9.517994885284554e-07, "loss": 0.101, "step": 5580 }, { "epoch": 9.05, "learning_rate": 9.486015127642157e-07, "loss": 0.0905, "step": 5581 }, { "epoch": 9.05, "learning_rate": 9.45408788017006e-07, "loss": 0.1125, "step": 5582 }, { "epoch": 9.05, "learning_rate": 9.42221315166818e-07, "loss": 0.0905, "step": 5583 }, { "epoch": 9.05, "learning_rate": 9.39039095092189e-07, "loss": 0.1322, "step": 5584 }, { "epoch": 9.05, "learning_rate": 9.358621286702219e-07, "loss": 0.1042, "step": 5585 }, { "epoch": 9.05, "learning_rate": 9.32690416776556e-07, "loss": 0.1165, "step": 5586 }, { "epoch": 9.06, "learning_rate": 9.295239602853989e-07, "loss": 0.0978, "step": 5587 }, { "epoch": 9.06, "learning_rate": 9.263627600694947e-07, "loss": 0.1728, "step": 5588 }, { "epoch": 9.06, "learning_rate": 9.232068170001485e-07, "loss": 0.0813, "step": 5589 }, { "epoch": 9.06, "learning_rate": 9.20056131947209e-07, "loss": 0.1353, "step": 5590 }, { "epoch": 9.06, "learning_rate": 9.169107057790838e-07, "loss": 0.1437, "step": 5591 }, { "epoch": 9.06, "learning_rate": 9.137705393627239e-07, "loss": 0.0838, "step": 5592 }, { "epoch": 9.06, "learning_rate": 9.106356335636368e-07, "loss": 0.12, "step": 5593 }, { "epoch": 9.07, "learning_rate": 9.075059892458738e-07, "loss": 0.1083, "step": 5594 }, { "epoch": 9.07, "learning_rate": 9.043816072720379e-07, "loss": 0.1489, "step": 5595 }, { "epoch": 9.07, "learning_rate": 9.012624885032894e-07, "loss": 0.074, "step": 5596 }, { "epoch": 9.07, "learning_rate": 8.98148633799325e-07, "loss": 0.0859, "step": 5597 }, { "epoch": 9.07, "learning_rate": 8.950400440184004e-07, "loss": 0.1168, "step": 5598 }, { "epoch": 9.07, "learning_rate": 8.919367200173146e-07, "loss": 0.0781, "step": 5599 }, { "epoch": 9.08, "learning_rate": 8.88838662651419e-07, "loss": 0.1752, "step": 5600 }, { "epoch": 9.08, "learning_rate": 8.857458727746105e-07, "loss": 0.1391, "step": 5601 }, { "epoch": 9.08, "learning_rate": 8.826583512393361e-07, "loss": 0.0924, "step": 5602 }, { "epoch": 9.08, "learning_rate": 8.79576098896584e-07, "loss": 0.1131, "step": 5603 }, { "epoch": 9.08, "learning_rate": 8.764991165959059e-07, "loss": 0.0729, "step": 5604 }, { "epoch": 9.08, "learning_rate": 8.734274051853853e-07, "loss": 0.1275, "step": 5605 }, { "epoch": 9.09, "learning_rate": 8.703609655116608e-07, "loss": 0.1246, "step": 5606 }, { "epoch": 9.09, "learning_rate": 8.672997984199139e-07, "loss": 0.0878, "step": 5607 }, { "epoch": 9.09, "learning_rate": 8.642439047538742e-07, "loss": 0.112, "step": 5608 }, { "epoch": 9.09, "learning_rate": 8.611932853558236e-07, "loss": 0.0988, "step": 5609 }, { "epoch": 9.09, "learning_rate": 8.581479410665805e-07, "loss": 0.0916, "step": 5610 }, { "epoch": 9.09, "learning_rate": 8.551078727255113e-07, "loss": 0.1312, "step": 5611 }, { "epoch": 9.1, "learning_rate": 8.520730811705391e-07, "loss": 0.0902, "step": 5612 }, { "epoch": 9.1, "learning_rate": 8.490435672381192e-07, "loss": 0.0809, "step": 5613 }, { "epoch": 9.1, "learning_rate": 8.46019331763257e-07, "loss": 0.0719, "step": 5614 }, { "epoch": 9.1, "learning_rate": 8.430003755795057e-07, "loss": 0.084, "step": 5615 }, { "epoch": 9.1, "learning_rate": 8.399866995189576e-07, "loss": 0.1229, "step": 5616 }, { "epoch": 9.1, "learning_rate": 8.369783044122593e-07, "loss": 0.1335, "step": 5617 }, { "epoch": 9.11, "learning_rate": 8.339751910885918e-07, "loss": 0.0708, "step": 5618 }, { "epoch": 9.11, "learning_rate": 8.309773603756799e-07, "loss": 0.091, "step": 5619 }, { "epoch": 9.11, "learning_rate": 8.27984813099807e-07, "loss": 0.0827, "step": 5620 }, { "epoch": 9.11, "learning_rate": 8.249975500857843e-07, "loss": 0.084, "step": 5621 }, { "epoch": 9.11, "learning_rate": 8.220155721569689e-07, "loss": 0.1088, "step": 5622 }, { "epoch": 9.11, "learning_rate": 8.190388801352722e-07, "loss": 0.0684, "step": 5623 }, { "epoch": 9.12, "learning_rate": 8.160674748411379e-07, "loss": 0.0892, "step": 5624 }, { "epoch": 9.12, "learning_rate": 8.131013570935531e-07, "loss": 0.0949, "step": 5625 }, { "epoch": 9.12, "learning_rate": 8.101405277100549e-07, "loss": 0.1073, "step": 5626 }, { "epoch": 9.12, "learning_rate": 8.071849875067106e-07, "loss": 0.0931, "step": 5627 }, { "epoch": 9.12, "learning_rate": 8.042347372981463e-07, "loss": 0.0987, "step": 5628 }, { "epoch": 9.12, "learning_rate": 8.012897778975159e-07, "loss": 0.1215, "step": 5629 }, { "epoch": 9.12, "learning_rate": 7.983501101165169e-07, "loss": 0.0742, "step": 5630 }, { "epoch": 9.13, "learning_rate": 7.95415734765399e-07, "loss": 0.1163, "step": 5631 }, { "epoch": 9.13, "learning_rate": 7.924866526529418e-07, "loss": 0.103, "step": 5632 }, { "epoch": 9.13, "learning_rate": 7.895628645864684e-07, "loss": 0.1277, "step": 5633 }, { "epoch": 9.13, "learning_rate": 7.866443713718453e-07, "loss": 0.1294, "step": 5634 }, { "epoch": 9.13, "learning_rate": 7.837311738134779e-07, "loss": 0.1361, "step": 5635 }, { "epoch": 9.13, "learning_rate": 7.80823272714315e-07, "loss": 0.0929, "step": 5636 }, { "epoch": 9.14, "learning_rate": 7.779206688758422e-07, "loss": 0.1202, "step": 5637 }, { "epoch": 9.14, "learning_rate": 7.750233630980841e-07, "loss": 0.0917, "step": 5638 }, { "epoch": 9.14, "learning_rate": 7.721313561796085e-07, "loss": 0.0958, "step": 5639 }, { "epoch": 9.14, "learning_rate": 7.692446489175198e-07, "loss": 0.125, "step": 5640 }, { "epoch": 9.14, "learning_rate": 7.663632421074596e-07, "loss": 0.1139, "step": 5641 }, { "epoch": 9.14, "learning_rate": 7.634871365436192e-07, "loss": 0.0783, "step": 5642 }, { "epoch": 9.15, "learning_rate": 7.606163330187155e-07, "loss": 0.0891, "step": 5643 }, { "epoch": 9.15, "learning_rate": 7.577508323240157e-07, "loss": 0.0945, "step": 5644 }, { "epoch": 9.15, "learning_rate": 7.548906352493168e-07, "loss": 0.1183, "step": 5645 }, { "epoch": 9.15, "learning_rate": 7.520357425829528e-07, "loss": 0.1036, "step": 5646 }, { "epoch": 9.15, "learning_rate": 7.491861551118073e-07, "loss": 0.1034, "step": 5647 }, { "epoch": 9.15, "learning_rate": 7.463418736212902e-07, "loss": 0.0845, "step": 5648 }, { "epoch": 9.16, "learning_rate": 7.435028988953541e-07, "loss": 0.0793, "step": 5649 }, { "epoch": 9.16, "learning_rate": 7.406692317164865e-07, "loss": 0.0682, "step": 5650 }, { "epoch": 9.16, "learning_rate": 7.378408728657116e-07, "loss": 0.0977, "step": 5651 }, { "epoch": 9.16, "learning_rate": 7.350178231225946e-07, "loss": 0.0745, "step": 5652 }, { "epoch": 9.16, "learning_rate": 7.322000832652354e-07, "loss": 0.1379, "step": 5653 }, { "epoch": 9.16, "learning_rate": 7.29387654070266e-07, "loss": 0.0719, "step": 5654 }, { "epoch": 9.17, "learning_rate": 7.265805363128642e-07, "loss": 0.0817, "step": 5655 }, { "epoch": 9.17, "learning_rate": 7.237787307667355e-07, "loss": 0.0957, "step": 5656 }, { "epoch": 9.17, "learning_rate": 7.20982238204122e-07, "loss": 0.1451, "step": 5657 }, { "epoch": 9.17, "learning_rate": 7.181910593958075e-07, "loss": 0.0932, "step": 5658 }, { "epoch": 9.17, "learning_rate": 7.154051951111052e-07, "loss": 0.0933, "step": 5659 }, { "epoch": 9.17, "learning_rate": 7.126246461178609e-07, "loss": 0.1336, "step": 5660 }, { "epoch": 9.18, "learning_rate": 7.098494131824684e-07, "loss": 0.1355, "step": 5661 }, { "epoch": 9.18, "learning_rate": 7.070794970698425e-07, "loss": 0.1044, "step": 5662 }, { "epoch": 9.18, "learning_rate": 7.043148985434389e-07, "loss": 0.1236, "step": 5663 }, { "epoch": 9.18, "learning_rate": 7.015556183652439e-07, "loss": 0.1108, "step": 5664 }, { "epoch": 9.18, "learning_rate": 6.988016572957823e-07, "loss": 0.1143, "step": 5665 }, { "epoch": 9.18, "learning_rate": 6.960530160941136e-07, "loss": 0.1225, "step": 5666 }, { "epoch": 9.18, "learning_rate": 6.933096955178253e-07, "loss": 0.1361, "step": 5667 }, { "epoch": 9.19, "learning_rate": 6.905716963230414e-07, "loss": 0.1146, "step": 5668 }, { "epoch": 9.19, "learning_rate": 6.878390192644202e-07, "loss": 0.0972, "step": 5669 }, { "epoch": 9.19, "learning_rate": 6.851116650951528e-07, "loss": 0.1054, "step": 5670 }, { "epoch": 9.19, "learning_rate": 6.823896345669645e-07, "loss": 0.141, "step": 5671 }, { "epoch": 9.19, "learning_rate": 6.796729284301085e-07, "loss": 0.097, "step": 5672 }, { "epoch": 9.19, "learning_rate": 6.769615474333747e-07, "loss": 0.1358, "step": 5673 }, { "epoch": 9.2, "learning_rate": 6.742554923240829e-07, "loss": 0.1285, "step": 5674 }, { "epoch": 9.2, "learning_rate": 6.715547638480879e-07, "loss": 0.0863, "step": 5675 }, { "epoch": 9.2, "learning_rate": 6.688593627497697e-07, "loss": 0.1045, "step": 5676 }, { "epoch": 9.2, "learning_rate": 6.661692897720517e-07, "loss": 0.1425, "step": 5677 }, { "epoch": 9.2, "learning_rate": 6.634845456563766e-07, "loss": 0.0818, "step": 5678 }, { "epoch": 9.2, "learning_rate": 6.608051311427254e-07, "loss": 0.089, "step": 5679 }, { "epoch": 9.21, "learning_rate": 6.581310469696078e-07, "loss": 0.0869, "step": 5680 }, { "epoch": 9.21, "learning_rate": 6.554622938740651e-07, "loss": 0.1874, "step": 5681 }, { "epoch": 9.21, "learning_rate": 6.527988725916712e-07, "loss": 0.1194, "step": 5682 }, { "epoch": 9.21, "learning_rate": 6.501407838565255e-07, "loss": 0.0925, "step": 5683 }, { "epoch": 9.21, "learning_rate": 6.474880284012574e-07, "loss": 0.0979, "step": 5684 }, { "epoch": 9.21, "learning_rate": 6.448406069570356e-07, "loss": 0.1051, "step": 5685 }, { "epoch": 9.22, "learning_rate": 6.421985202535497e-07, "loss": 0.1513, "step": 5686 }, { "epoch": 9.22, "learning_rate": 6.395617690190193e-07, "loss": 0.0957, "step": 5687 }, { "epoch": 9.22, "learning_rate": 6.369303539801986e-07, "loss": 0.1253, "step": 5688 }, { "epoch": 9.22, "learning_rate": 6.34304275862363e-07, "loss": 0.11, "step": 5689 }, { "epoch": 9.22, "learning_rate": 6.31683535389327e-07, "loss": 0.0952, "step": 5690 }, { "epoch": 9.22, "learning_rate": 6.290681332834281e-07, "loss": 0.0878, "step": 5691 }, { "epoch": 9.23, "learning_rate": 6.264580702655299e-07, "loss": 0.0826, "step": 5692 }, { "epoch": 9.23, "learning_rate": 6.238533470550301e-07, "loss": 0.1007, "step": 5693 }, { "epoch": 9.23, "learning_rate": 6.212539643698546e-07, "loss": 0.0808, "step": 5694 }, { "epoch": 9.23, "learning_rate": 6.186599229264478e-07, "loss": 0.1081, "step": 5695 }, { "epoch": 9.23, "learning_rate": 6.160712234397981e-07, "loss": 0.0925, "step": 5696 }, { "epoch": 9.23, "learning_rate": 6.134878666234056e-07, "loss": 0.1592, "step": 5697 }, { "epoch": 9.24, "learning_rate": 6.109098531893076e-07, "loss": 0.1078, "step": 5698 }, { "epoch": 9.24, "learning_rate": 6.083371838480645e-07, "loss": 0.1418, "step": 5699 }, { "epoch": 9.24, "learning_rate": 6.057698593087646e-07, "loss": 0.0839, "step": 5700 }, { "epoch": 9.24, "learning_rate": 6.032078802790242e-07, "loss": 0.0992, "step": 5701 }, { "epoch": 9.24, "learning_rate": 6.006512474649873e-07, "loss": 0.1174, "step": 5702 }, { "epoch": 9.24, "learning_rate": 5.980999615713167e-07, "loss": 0.1107, "step": 5703 }, { "epoch": 9.24, "learning_rate": 5.955540233012147e-07, "loss": 0.0844, "step": 5704 }, { "epoch": 9.25, "learning_rate": 5.930134333563975e-07, "loss": 0.1082, "step": 5705 }, { "epoch": 9.25, "learning_rate": 5.904781924371117e-07, "loss": 0.1355, "step": 5706 }, { "epoch": 9.25, "learning_rate": 5.879483012421339e-07, "loss": 0.1287, "step": 5707 }, { "epoch": 9.25, "learning_rate": 5.854237604687574e-07, "loss": 0.0856, "step": 5708 }, { "epoch": 9.25, "learning_rate": 5.829045708128079e-07, "loss": 0.1706, "step": 5709 }, { "epoch": 9.25, "learning_rate": 5.803907329686342e-07, "loss": 0.1253, "step": 5710 }, { "epoch": 9.26, "learning_rate": 5.77882247629109e-07, "loss": 0.091, "step": 5711 }, { "epoch": 9.26, "learning_rate": 5.753791154856303e-07, "loss": 0.0845, "step": 5712 }, { "epoch": 9.26, "learning_rate": 5.728813372281217e-07, "loss": 0.0796, "step": 5713 }, { "epoch": 9.26, "learning_rate": 5.703889135450258e-07, "loss": 0.1593, "step": 5714 }, { "epoch": 9.26, "learning_rate": 5.679018451233175e-07, "loss": 0.1123, "step": 5715 }, { "epoch": 9.26, "learning_rate": 5.65420132648491e-07, "loss": 0.1125, "step": 5716 }, { "epoch": 9.27, "learning_rate": 5.629437768045654e-07, "loss": 0.0912, "step": 5717 }, { "epoch": 9.27, "learning_rate": 5.604727782740838e-07, "loss": 0.094, "step": 5718 }, { "epoch": 9.27, "learning_rate": 5.58007137738108e-07, "loss": 0.108, "step": 5719 }, { "epoch": 9.27, "learning_rate": 5.555468558762322e-07, "loss": 0.1167, "step": 5720 }, { "epoch": 9.27, "learning_rate": 5.530919333665674e-07, "loss": 0.1031, "step": 5721 }, { "epoch": 9.27, "learning_rate": 5.506423708857456e-07, "loss": 0.0926, "step": 5722 }, { "epoch": 9.28, "learning_rate": 5.481981691089267e-07, "loss": 0.0924, "step": 5723 }, { "epoch": 9.28, "learning_rate": 5.457593287097896e-07, "loss": 0.1172, "step": 5724 }, { "epoch": 9.28, "learning_rate": 5.433258503605343e-07, "loss": 0.1211, "step": 5725 }, { "epoch": 9.28, "learning_rate": 5.408977347318889e-07, "loss": 0.1123, "step": 5726 }, { "epoch": 9.28, "learning_rate": 5.384749824930979e-07, "loss": 0.1143, "step": 5727 }, { "epoch": 9.28, "learning_rate": 5.360575943119317e-07, "loss": 0.1048, "step": 5728 }, { "epoch": 9.29, "learning_rate": 5.336455708546773e-07, "loss": 0.1064, "step": 5729 }, { "epoch": 9.29, "learning_rate": 5.312389127861428e-07, "loss": 0.0928, "step": 5730 }, { "epoch": 9.29, "learning_rate": 5.288376207696666e-07, "loss": 0.1486, "step": 5731 }, { "epoch": 9.29, "learning_rate": 5.26441695467097e-07, "loss": 0.1171, "step": 5732 }, { "epoch": 9.29, "learning_rate": 5.240511375388102e-07, "loss": 0.1072, "step": 5733 }, { "epoch": 9.29, "learning_rate": 5.216659476436991e-07, "loss": 0.0908, "step": 5734 }, { "epoch": 9.29, "learning_rate": 5.192861264391802e-07, "loss": 0.085, "step": 5735 }, { "epoch": 9.3, "learning_rate": 5.169116745811864e-07, "loss": 0.1108, "step": 5736 }, { "epoch": 9.3, "learning_rate": 5.145425927241765e-07, "loss": 0.0883, "step": 5737 }, { "epoch": 9.3, "learning_rate": 5.121788815211193e-07, "loss": 0.108, "step": 5738 }, { "epoch": 9.3, "learning_rate": 5.098205416235158e-07, "loss": 0.1147, "step": 5739 }, { "epoch": 9.3, "learning_rate": 5.074675736813772e-07, "loss": 0.0848, "step": 5740 }, { "epoch": 9.3, "learning_rate": 5.051199783432381e-07, "loss": 0.1203, "step": 5741 }, { "epoch": 9.31, "learning_rate": 5.027777562561542e-07, "loss": 0.1057, "step": 5742 }, { "epoch": 9.31, "learning_rate": 5.004409080656914e-07, "loss": 0.1128, "step": 5743 }, { "epoch": 9.31, "learning_rate": 4.981094344159454e-07, "loss": 0.0687, "step": 5744 }, { "epoch": 9.31, "learning_rate": 4.957833359495246e-07, "loss": 0.1319, "step": 5745 }, { "epoch": 9.31, "learning_rate": 4.93462613307556e-07, "loss": 0.0981, "step": 5746 }, { "epoch": 9.31, "learning_rate": 4.911472671296857e-07, "loss": 0.1019, "step": 5747 }, { "epoch": 9.32, "learning_rate": 4.88837298054079e-07, "loss": 0.1028, "step": 5748 }, { "epoch": 9.32, "learning_rate": 4.865327067174153e-07, "loss": 0.1611, "step": 5749 }, { "epoch": 9.32, "learning_rate": 4.842334937548976e-07, "loss": 0.0982, "step": 5750 }, { "epoch": 9.32, "learning_rate": 4.819396598002457e-07, "loss": 0.1151, "step": 5751 }, { "epoch": 9.32, "learning_rate": 4.796512054856872e-07, "loss": 0.1023, "step": 5752 }, { "epoch": 9.32, "learning_rate": 4.77368131441982e-07, "loss": 0.0881, "step": 5753 }, { "epoch": 9.33, "learning_rate": 4.750904382983934e-07, "loss": 0.0827, "step": 5754 }, { "epoch": 9.33, "learning_rate": 4.728181266827125e-07, "loss": 0.1302, "step": 5755 }, { "epoch": 9.33, "learning_rate": 4.7055119722123843e-07, "loss": 0.1159, "step": 5756 }, { "epoch": 9.33, "learning_rate": 4.682896505387935e-07, "loss": 0.1108, "step": 5757 }, { "epoch": 9.33, "learning_rate": 4.6603348725871244e-07, "loss": 0.1095, "step": 5758 }, { "epoch": 9.33, "learning_rate": 4.6378270800284896e-07, "loss": 0.1265, "step": 5759 }, { "epoch": 9.34, "learning_rate": 4.61537313391569e-07, "loss": 0.1086, "step": 5760 }, { "epoch": 9.34, "learning_rate": 4.592973040437554e-07, "loss": 0.0832, "step": 5761 }, { "epoch": 9.34, "learning_rate": 4.570626805768119e-07, "loss": 0.1298, "step": 5762 }, { "epoch": 9.34, "learning_rate": 4.5483344360664817e-07, "loss": 0.074, "step": 5763 }, { "epoch": 9.34, "learning_rate": 4.526095937476993e-07, "loss": 0.1032, "step": 5764 }, { "epoch": 9.34, "learning_rate": 4.503911316129106e-07, "loss": 0.0971, "step": 5765 }, { "epoch": 9.35, "learning_rate": 4.4817805781374177e-07, "loss": 0.0951, "step": 5766 }, { "epoch": 9.35, "learning_rate": 4.459703729601672e-07, "loss": 0.0993, "step": 5767 }, { "epoch": 9.35, "learning_rate": 4.437680776606801e-07, "loss": 0.0725, "step": 5768 }, { "epoch": 9.35, "learning_rate": 4.4157117252228154e-07, "loss": 0.1042, "step": 5769 }, { "epoch": 9.35, "learning_rate": 4.393796581504961e-07, "loss": 0.1073, "step": 5770 }, { "epoch": 9.35, "learning_rate": 4.371935351493517e-07, "loss": 0.0831, "step": 5771 }, { "epoch": 9.35, "learning_rate": 4.3501280412139966e-07, "loss": 0.0868, "step": 5772 }, { "epoch": 9.36, "learning_rate": 4.328374656676948e-07, "loss": 0.2, "step": 5773 }, { "epoch": 9.36, "learning_rate": 4.306675203878219e-07, "loss": 0.0803, "step": 5774 }, { "epoch": 9.36, "learning_rate": 4.285029688798603e-07, "loss": 0.0843, "step": 5775 }, { "epoch": 9.36, "learning_rate": 4.2634381174041506e-07, "loss": 0.0829, "step": 5776 }, { "epoch": 9.36, "learning_rate": 4.241900495646034e-07, "loss": 0.1227, "step": 5777 }, { "epoch": 9.36, "learning_rate": 4.220416829460505e-07, "loss": 0.1068, "step": 5778 }, { "epoch": 9.37, "learning_rate": 4.198987124768938e-07, "loss": 0.1212, "step": 5779 }, { "epoch": 9.37, "learning_rate": 4.177611387477964e-07, "loss": 0.1017, "step": 5780 }, { "epoch": 9.37, "learning_rate": 4.1562896234791594e-07, "loss": 0.108, "step": 5781 }, { "epoch": 9.37, "learning_rate": 4.1350218386493115e-07, "loss": 0.0927, "step": 5782 }, { "epoch": 9.37, "learning_rate": 4.1138080388503754e-07, "loss": 0.089, "step": 5783 }, { "epoch": 9.37, "learning_rate": 4.0926482299293635e-07, "loss": 0.0874, "step": 5784 }, { "epoch": 9.38, "learning_rate": 4.0715424177183884e-07, "loss": 0.1327, "step": 5785 }, { "epoch": 9.38, "learning_rate": 4.050490608034729e-07, "loss": 0.1575, "step": 5786 }, { "epoch": 9.38, "learning_rate": 4.0294928066807683e-07, "loss": 0.1909, "step": 5787 }, { "epoch": 9.38, "learning_rate": 4.008549019443986e-07, "loss": 0.0992, "step": 5788 }, { "epoch": 9.38, "learning_rate": 3.987659252097009e-07, "loss": 0.115, "step": 5789 }, { "epoch": 9.38, "learning_rate": 3.966823510397522e-07, "loss": 0.1359, "step": 5790 }, { "epoch": 9.39, "learning_rate": 3.946041800088374e-07, "loss": 0.094, "step": 5791 }, { "epoch": 9.39, "learning_rate": 3.925314126897495e-07, "loss": 0.1104, "step": 5792 }, { "epoch": 9.39, "learning_rate": 3.9046404965379147e-07, "loss": 0.1234, "step": 5793 }, { "epoch": 9.39, "learning_rate": 3.8840209147077866e-07, "loss": 0.0754, "step": 5794 }, { "epoch": 9.39, "learning_rate": 3.8634553870903204e-07, "loss": 0.1252, "step": 5795 }, { "epoch": 9.39, "learning_rate": 3.842943919353914e-07, "loss": 0.1436, "step": 5796 }, { "epoch": 9.4, "learning_rate": 3.822486517152002e-07, "loss": 0.0973, "step": 5797 }, { "epoch": 9.4, "learning_rate": 3.8020831861230733e-07, "loss": 0.1113, "step": 5798 }, { "epoch": 9.4, "learning_rate": 3.781733931890852e-07, "loss": 0.1144, "step": 5799 }, { "epoch": 9.4, "learning_rate": 3.761438760064029e-07, "loss": 0.0878, "step": 5800 }, { "epoch": 9.4, "learning_rate": 3.741197676236419e-07, "loss": 0.0884, "step": 5801 }, { "epoch": 9.4, "learning_rate": 3.721010685987003e-07, "loss": 0.0939, "step": 5802 }, { "epoch": 9.41, "learning_rate": 3.7008777948797313e-07, "loss": 0.104, "step": 5803 }, { "epoch": 9.41, "learning_rate": 3.680799008463742e-07, "loss": 0.0796, "step": 5804 }, { "epoch": 9.41, "learning_rate": 3.6607743322732317e-07, "loss": 0.1218, "step": 5805 }, { "epoch": 9.41, "learning_rate": 3.640803771827428e-07, "loss": 0.0877, "step": 5806 }, { "epoch": 9.41, "learning_rate": 3.6208873326307514e-07, "loss": 0.1132, "step": 5807 }, { "epoch": 9.41, "learning_rate": 3.60102502017261e-07, "loss": 0.1054, "step": 5808 }, { "epoch": 9.41, "learning_rate": 3.581216839927537e-07, "loss": 0.156, "step": 5809 }, { "epoch": 9.42, "learning_rate": 3.561462797355142e-07, "loss": 0.1188, "step": 5810 }, { "epoch": 9.42, "learning_rate": 3.54176289790007e-07, "loss": 0.0907, "step": 5811 }, { "epoch": 9.42, "learning_rate": 3.5221171469921323e-07, "loss": 0.089, "step": 5812 }, { "epoch": 9.42, "learning_rate": 3.5025255500461544e-07, "loss": 0.1177, "step": 5813 }, { "epoch": 9.42, "learning_rate": 3.4829881124619933e-07, "loss": 0.1375, "step": 5814 }, { "epoch": 9.42, "learning_rate": 3.4635048396246986e-07, "loss": 0.1155, "step": 5815 }, { "epoch": 9.43, "learning_rate": 3.4440757369042845e-07, "loss": 0.0904, "step": 5816 }, { "epoch": 9.43, "learning_rate": 3.424700809655845e-07, "loss": 0.1184, "step": 5817 }, { "epoch": 9.43, "learning_rate": 3.4053800632196434e-07, "loss": 0.116, "step": 5818 }, { "epoch": 9.43, "learning_rate": 3.3861135029208847e-07, "loss": 0.1073, "step": 5819 }, { "epoch": 9.43, "learning_rate": 3.3669011340699e-07, "loss": 0.132, "step": 5820 }, { "epoch": 9.43, "learning_rate": 3.347742961962075e-07, "loss": 0.1155, "step": 5821 }, { "epoch": 9.44, "learning_rate": 3.328638991877853e-07, "loss": 0.0686, "step": 5822 }, { "epoch": 9.44, "learning_rate": 3.309589229082755e-07, "loss": 0.1022, "step": 5823 }, { "epoch": 9.44, "learning_rate": 3.2905936788273363e-07, "loss": 0.2179, "step": 5824 }, { "epoch": 9.44, "learning_rate": 3.2716523463471875e-07, "loss": 0.1083, "step": 5825 }, { "epoch": 9.44, "learning_rate": 3.2527652368630426e-07, "loss": 0.0918, "step": 5826 }, { "epoch": 9.44, "learning_rate": 3.233932355580627e-07, "loss": 0.0908, "step": 5827 }, { "epoch": 9.45, "learning_rate": 3.215153707690699e-07, "loss": 0.106, "step": 5828 }, { "epoch": 9.45, "learning_rate": 3.196429298369119e-07, "loss": 0.0746, "step": 5829 }, { "epoch": 9.45, "learning_rate": 3.177759132776781e-07, "loss": 0.1069, "step": 5830 }, { "epoch": 9.45, "learning_rate": 3.1591432160596126e-07, "loss": 0.1119, "step": 5831 }, { "epoch": 9.45, "learning_rate": 3.1405815533486206e-07, "loss": 0.1355, "step": 5832 }, { "epoch": 9.45, "learning_rate": 3.122074149759846e-07, "loss": 0.1048, "step": 5833 }, { "epoch": 9.46, "learning_rate": 3.10362101039432e-07, "loss": 0.1357, "step": 5834 }, { "epoch": 9.46, "learning_rate": 3.0852221403382176e-07, "loss": 0.0719, "step": 5835 }, { "epoch": 9.46, "learning_rate": 3.066877544662661e-07, "loss": 0.1579, "step": 5836 }, { "epoch": 9.46, "learning_rate": 3.0485872284238937e-07, "loss": 0.1431, "step": 5837 }, { "epoch": 9.46, "learning_rate": 3.030351196663128e-07, "loss": 0.0958, "step": 5838 }, { "epoch": 9.46, "learning_rate": 3.012169454406655e-07, "loss": 0.1548, "step": 5839 }, { "epoch": 9.47, "learning_rate": 2.9940420066658204e-07, "loss": 0.075, "step": 5840 }, { "epoch": 9.47, "learning_rate": 2.9759688584369394e-07, "loss": 0.1506, "step": 5841 }, { "epoch": 9.47, "learning_rate": 2.9579500147014496e-07, "loss": 0.1124, "step": 5842 }, { "epoch": 9.47, "learning_rate": 2.939985480425711e-07, "loss": 0.1399, "step": 5843 }, { "epoch": 9.47, "learning_rate": 2.9220752605612077e-07, "loss": 0.116, "step": 5844 }, { "epoch": 9.47, "learning_rate": 2.9042193600444355e-07, "loss": 0.0838, "step": 5845 }, { "epoch": 9.47, "learning_rate": 2.88641778379688e-07, "loss": 0.0822, "step": 5846 }, { "epoch": 9.48, "learning_rate": 2.8686705367250824e-07, "loss": 0.0987, "step": 5847 }, { "epoch": 9.48, "learning_rate": 2.850977623720619e-07, "loss": 0.0821, "step": 5848 }, { "epoch": 9.48, "learning_rate": 2.8333390496600334e-07, "loss": 0.0905, "step": 5849 }, { "epoch": 9.48, "learning_rate": 2.815754819404992e-07, "loss": 0.1093, "step": 5850 }, { "epoch": 9.48, "learning_rate": 2.798224937802085e-07, "loss": 0.1059, "step": 5851 }, { "epoch": 9.48, "learning_rate": 2.7807494096829813e-07, "loss": 0.1018, "step": 5852 }, { "epoch": 9.49, "learning_rate": 2.763328239864338e-07, "loss": 0.1444, "step": 5853 }, { "epoch": 9.49, "learning_rate": 2.74596143314787e-07, "loss": 0.1186, "step": 5854 }, { "epoch": 9.49, "learning_rate": 2.7286489943202376e-07, "loss": 0.0809, "step": 5855 }, { "epoch": 9.49, "learning_rate": 2.7113909281532016e-07, "loss": 0.1266, "step": 5856 }, { "epoch": 9.49, "learning_rate": 2.694187239403467e-07, "loss": 0.1509, "step": 5857 }, { "epoch": 9.49, "learning_rate": 2.6770379328127983e-07, "loss": 0.1257, "step": 5858 }, { "epoch": 9.5, "learning_rate": 2.6599430131079243e-07, "loss": 0.0899, "step": 5859 }, { "epoch": 9.5, "learning_rate": 2.6429024850006315e-07, "loss": 0.0816, "step": 5860 }, { "epoch": 9.5, "learning_rate": 2.6259163531876965e-07, "loss": 0.0908, "step": 5861 }, { "epoch": 9.5, "learning_rate": 2.6089846223508853e-07, "loss": 0.1081, "step": 5862 }, { "epoch": 9.5, "learning_rate": 2.5921072971569763e-07, "loss": 0.1078, "step": 5863 }, { "epoch": 9.5, "learning_rate": 2.575284382257781e-07, "loss": 0.0972, "step": 5864 }, { "epoch": 9.51, "learning_rate": 2.55851588229008e-07, "loss": 0.0988, "step": 5865 }, { "epoch": 9.51, "learning_rate": 2.5418018018756876e-07, "loss": 0.1191, "step": 5866 }, { "epoch": 9.51, "learning_rate": 2.525142145621384e-07, "loss": 0.1026, "step": 5867 }, { "epoch": 9.51, "learning_rate": 2.508536918118942e-07, "loss": 0.1135, "step": 5868 }, { "epoch": 9.51, "learning_rate": 2.4919861239452336e-07, "loss": 0.1011, "step": 5869 }, { "epoch": 9.51, "learning_rate": 2.4754897676619647e-07, "loss": 0.1058, "step": 5870 }, { "epoch": 9.52, "learning_rate": 2.4590478538159876e-07, "loss": 0.1095, "step": 5871 }, { "epoch": 9.52, "learning_rate": 2.442660386939033e-07, "loss": 0.091, "step": 5872 }, { "epoch": 9.52, "learning_rate": 2.4263273715479095e-07, "loss": 0.1297, "step": 5873 }, { "epoch": 9.52, "learning_rate": 2.41004881214435e-07, "loss": 0.0884, "step": 5874 }, { "epoch": 9.52, "learning_rate": 2.3938247132151426e-07, "loss": 0.1022, "step": 5875 }, { "epoch": 9.52, "learning_rate": 2.3776550792319997e-07, "loss": 0.1087, "step": 5876 }, { "epoch": 9.53, "learning_rate": 2.3615399146517115e-07, "loss": 0.0859, "step": 5877 }, { "epoch": 9.53, "learning_rate": 2.3454792239159474e-07, "loss": 0.1136, "step": 5878 }, { "epoch": 9.53, "learning_rate": 2.329473011451433e-07, "loss": 0.0888, "step": 5879 }, { "epoch": 9.53, "learning_rate": 2.3135212816698615e-07, "loss": 0.0835, "step": 5880 }, { "epoch": 9.53, "learning_rate": 2.297624038967916e-07, "loss": 0.112, "step": 5881 }, { "epoch": 9.53, "learning_rate": 2.2817812877272471e-07, "loss": 0.1091, "step": 5882 }, { "epoch": 9.53, "learning_rate": 2.265993032314473e-07, "loss": 0.1238, "step": 5883 }, { "epoch": 9.54, "learning_rate": 2.250259277081246e-07, "loss": 0.0993, "step": 5884 }, { "epoch": 9.54, "learning_rate": 2.2345800263641193e-07, "loss": 0.0816, "step": 5885 }, { "epoch": 9.54, "learning_rate": 2.2189552844847027e-07, "loss": 0.1331, "step": 5886 }, { "epoch": 9.54, "learning_rate": 2.2033850557495072e-07, "loss": 0.1375, "step": 5887 }, { "epoch": 9.54, "learning_rate": 2.187869344450122e-07, "loss": 0.1149, "step": 5888 }, { "epoch": 9.54, "learning_rate": 2.1724081548629927e-07, "loss": 0.0765, "step": 5889 }, { "epoch": 9.55, "learning_rate": 2.1570014912495773e-07, "loss": 0.0969, "step": 5890 }, { "epoch": 9.55, "learning_rate": 2.1416493578563678e-07, "loss": 0.0842, "step": 5891 }, { "epoch": 9.55, "learning_rate": 2.1263517589147353e-07, "loss": 0.099, "step": 5892 }, { "epoch": 9.55, "learning_rate": 2.1111086986410843e-07, "loss": 0.0895, "step": 5893 }, { "epoch": 9.55, "learning_rate": 2.0959201812367658e-07, "loss": 0.0715, "step": 5894 }, { "epoch": 9.55, "learning_rate": 2.080786210888075e-07, "loss": 0.169, "step": 5895 }, { "epoch": 9.56, "learning_rate": 2.0657067917662977e-07, "loss": 0.1351, "step": 5896 }, { "epoch": 9.56, "learning_rate": 2.050681928027709e-07, "loss": 0.1512, "step": 5897 }, { "epoch": 9.56, "learning_rate": 2.0357116238134633e-07, "loss": 0.1166, "step": 5898 }, { "epoch": 9.56, "learning_rate": 2.020795883249771e-07, "loss": 0.1058, "step": 5899 }, { "epoch": 9.56, "learning_rate": 2.0059347104477434e-07, "loss": 0.0884, "step": 5900 }, { "epoch": 9.56, "learning_rate": 1.9911281095034817e-07, "loss": 0.1508, "step": 5901 }, { "epoch": 9.57, "learning_rate": 1.976376084498055e-07, "loss": 0.1044, "step": 5902 }, { "epoch": 9.57, "learning_rate": 1.961678639497455e-07, "loss": 0.0596, "step": 5903 }, { "epoch": 9.57, "learning_rate": 1.9470357785526195e-07, "loss": 0.0857, "step": 5904 }, { "epoch": 9.57, "learning_rate": 1.9324475056994973e-07, "loss": 0.133, "step": 5905 }, { "epoch": 9.57, "learning_rate": 1.9179138249589836e-07, "loss": 0.0859, "step": 5906 }, { "epoch": 9.57, "learning_rate": 1.9034347403368515e-07, "loss": 0.0904, "step": 5907 }, { "epoch": 9.58, "learning_rate": 1.8890102558239089e-07, "loss": 0.1077, "step": 5908 }, { "epoch": 9.58, "learning_rate": 1.8746403753958865e-07, "loss": 0.1096, "step": 5909 }, { "epoch": 9.58, "learning_rate": 1.8603251030134606e-07, "loss": 0.079, "step": 5910 }, { "epoch": 9.58, "learning_rate": 1.846064442622275e-07, "loss": 0.0957, "step": 5911 }, { "epoch": 9.58, "learning_rate": 1.8318583981528748e-07, "loss": 0.0872, "step": 5912 }, { "epoch": 9.58, "learning_rate": 1.8177069735208164e-07, "loss": 0.1077, "step": 5913 }, { "epoch": 9.59, "learning_rate": 1.8036101726265133e-07, "loss": 0.0972, "step": 5914 }, { "epoch": 9.59, "learning_rate": 1.789567999355457e-07, "loss": 0.0848, "step": 5915 }, { "epoch": 9.59, "learning_rate": 1.77558045757793e-07, "loss": 0.1005, "step": 5916 }, { "epoch": 9.59, "learning_rate": 1.7616475511492705e-07, "loss": 0.1151, "step": 5917 }, { "epoch": 9.59, "learning_rate": 1.747769283909717e-07, "loss": 0.1325, "step": 5918 }, { "epoch": 9.59, "learning_rate": 1.733945659684455e-07, "loss": 0.1504, "step": 5919 }, { "epoch": 9.59, "learning_rate": 1.7201766822835697e-07, "loss": 0.1224, "step": 5920 }, { "epoch": 9.6, "learning_rate": 1.7064623555021363e-07, "loss": 0.1208, "step": 5921 }, { "epoch": 9.6, "learning_rate": 1.692802683120154e-07, "loss": 0.1351, "step": 5922 }, { "epoch": 9.6, "learning_rate": 1.6791976689025435e-07, "loss": 0.1123, "step": 5923 }, { "epoch": 9.6, "learning_rate": 1.6656473165991727e-07, "loss": 0.0877, "step": 5924 }, { "epoch": 9.6, "learning_rate": 1.6521516299448314e-07, "loss": 0.077, "step": 5925 }, { "epoch": 9.6, "learning_rate": 1.6387106126592778e-07, "loss": 0.0892, "step": 5926 }, { "epoch": 9.61, "learning_rate": 1.6253242684471483e-07, "loss": 0.104, "step": 5927 }, { "epoch": 9.61, "learning_rate": 1.6119926009980468e-07, "loss": 0.0996, "step": 5928 }, { "epoch": 9.61, "learning_rate": 1.5987156139865011e-07, "loss": 0.111, "step": 5929 }, { "epoch": 9.61, "learning_rate": 1.5854933110719616e-07, "loss": 0.1239, "step": 5930 }, { "epoch": 9.61, "learning_rate": 1.57232569589878e-07, "loss": 0.1302, "step": 5931 }, { "epoch": 9.61, "learning_rate": 1.559212772096319e-07, "loss": 0.097, "step": 5932 }, { "epoch": 9.62, "learning_rate": 1.546154543278755e-07, "loss": 0.1102, "step": 5933 }, { "epoch": 9.62, "learning_rate": 1.5331510130452752e-07, "loss": 0.0955, "step": 5934 }, { "epoch": 9.62, "learning_rate": 1.5202021849799685e-07, "loss": 0.1148, "step": 5935 }, { "epoch": 9.62, "learning_rate": 1.5073080626518022e-07, "loss": 0.1477, "step": 5936 }, { "epoch": 9.62, "learning_rate": 1.494468649614733e-07, "loss": 0.1611, "step": 5937 }, { "epoch": 9.62, "learning_rate": 1.4816839494076197e-07, "loss": 0.0827, "step": 5938 }, { "epoch": 9.63, "learning_rate": 1.4689539655541764e-07, "loss": 0.1474, "step": 5939 }, { "epoch": 9.63, "learning_rate": 1.4562787015631518e-07, "loss": 0.1275, "step": 5940 }, { "epoch": 9.63, "learning_rate": 1.4436581609281075e-07, "loss": 0.1674, "step": 5941 }, { "epoch": 9.63, "learning_rate": 1.4310923471275717e-07, "loss": 0.0882, "step": 5942 }, { "epoch": 9.63, "learning_rate": 1.4185812636249961e-07, "loss": 0.0863, "step": 5943 }, { "epoch": 9.63, "learning_rate": 1.4061249138687115e-07, "loss": 0.1117, "step": 5944 }, { "epoch": 9.64, "learning_rate": 1.3937233012919938e-07, "loss": 0.1344, "step": 5945 }, { "epoch": 9.64, "learning_rate": 1.3813764293130194e-07, "loss": 0.1309, "step": 5946 }, { "epoch": 9.64, "learning_rate": 1.3690843013348664e-07, "loss": 0.0743, "step": 5947 }, { "epoch": 9.64, "learning_rate": 1.3568469207455582e-07, "loss": 0.1863, "step": 5948 }, { "epoch": 9.64, "learning_rate": 1.3446642909180186e-07, "loss": 0.1178, "step": 5949 }, { "epoch": 9.64, "learning_rate": 1.3325364152100063e-07, "loss": 0.0752, "step": 5950 }, { "epoch": 9.65, "learning_rate": 1.3204632969643138e-07, "loss": 0.0958, "step": 5951 }, { "epoch": 9.65, "learning_rate": 1.3084449395085686e-07, "loss": 0.0761, "step": 5952 }, { "epoch": 9.65, "learning_rate": 1.296481346155276e-07, "loss": 0.1216, "step": 5953 }, { "epoch": 9.65, "learning_rate": 1.2845725202019322e-07, "loss": 0.0891, "step": 5954 }, { "epoch": 9.65, "learning_rate": 1.2727184649308887e-07, "loss": 0.1437, "step": 5955 }, { "epoch": 9.65, "learning_rate": 1.2609191836093771e-07, "loss": 0.1206, "step": 5956 }, { "epoch": 9.65, "learning_rate": 1.2491746794895733e-07, "loss": 0.0875, "step": 5957 }, { "epoch": 9.66, "learning_rate": 1.23748495580851e-07, "loss": 0.1956, "step": 5958 }, { "epoch": 9.66, "learning_rate": 1.2258500157882104e-07, "loss": 0.0982, "step": 5959 }, { "epoch": 9.66, "learning_rate": 1.2142698626355088e-07, "loss": 0.1254, "step": 5960 }, { "epoch": 9.66, "learning_rate": 1.2027444995421633e-07, "loss": 0.1189, "step": 5961 }, { "epoch": 9.66, "learning_rate": 1.1912739296848552e-07, "loss": 0.0913, "step": 5962 }, { "epoch": 9.66, "learning_rate": 1.1798581562251221e-07, "loss": 0.1104, "step": 5963 }, { "epoch": 9.67, "learning_rate": 1.1684971823094471e-07, "loss": 0.1204, "step": 5964 }, { "epoch": 9.67, "learning_rate": 1.1571910110691697e-07, "loss": 0.1143, "step": 5965 }, { "epoch": 9.67, "learning_rate": 1.1459396456205307e-07, "loss": 0.1202, "step": 5966 }, { "epoch": 9.67, "learning_rate": 1.1347430890646937e-07, "loss": 0.1205, "step": 5967 }, { "epoch": 9.67, "learning_rate": 1.1236013444877014e-07, "loss": 0.1488, "step": 5968 }, { "epoch": 9.67, "learning_rate": 1.1125144149604305e-07, "loss": 0.102, "step": 5969 }, { "epoch": 9.68, "learning_rate": 1.10148230353877e-07, "loss": 0.1092, "step": 5970 }, { "epoch": 9.68, "learning_rate": 1.0905050132633766e-07, "loss": 0.0787, "step": 5971 }, { "epoch": 9.68, "learning_rate": 1.0795825471598742e-07, "loss": 0.1087, "step": 5972 }, { "epoch": 9.68, "learning_rate": 1.068714908238766e-07, "loss": 0.0868, "step": 5973 }, { "epoch": 9.68, "learning_rate": 1.0579020994954114e-07, "loss": 0.0954, "step": 5974 }, { "epoch": 9.68, "learning_rate": 1.0471441239100933e-07, "loss": 0.1029, "step": 5975 }, { "epoch": 9.69, "learning_rate": 1.0364409844479506e-07, "loss": 0.1207, "step": 5976 }, { "epoch": 9.69, "learning_rate": 1.0257926840590016e-07, "loss": 0.1053, "step": 5977 }, { "epoch": 9.69, "learning_rate": 1.0151992256782317e-07, "loss": 0.1124, "step": 5978 }, { "epoch": 9.69, "learning_rate": 1.0046606122253943e-07, "loss": 0.1021, "step": 5979 }, { "epoch": 9.69, "learning_rate": 9.941768466052105e-08, "loss": 0.1321, "step": 5980 }, { "epoch": 9.69, "learning_rate": 9.837479317072351e-08, "loss": 0.0936, "step": 5981 }, { "epoch": 9.7, "learning_rate": 9.733738704059247e-08, "loss": 0.0711, "step": 5982 }, { "epoch": 9.7, "learning_rate": 9.630546655606365e-08, "loss": 0.0835, "step": 5983 }, { "epoch": 9.7, "learning_rate": 9.52790320015562e-08, "loss": 0.0953, "step": 5984 }, { "epoch": 9.7, "learning_rate": 9.425808365998157e-08, "loss": 0.1053, "step": 5985 }, { "epoch": 9.7, "learning_rate": 9.324262181273691e-08, "loss": 0.069, "step": 5986 }, { "epoch": 9.7, "learning_rate": 9.223264673970944e-08, "loss": 0.1552, "step": 5987 }, { "epoch": 9.71, "learning_rate": 9.12281587192676e-08, "loss": 0.076, "step": 5988 }, { "epoch": 9.71, "learning_rate": 9.02291580282788e-08, "loss": 0.1009, "step": 5989 }, { "epoch": 9.71, "learning_rate": 8.923564494208281e-08, "loss": 0.0936, "step": 5990 }, { "epoch": 9.71, "learning_rate": 8.824761973452278e-08, "loss": 0.0836, "step": 5991 }, { "epoch": 9.71, "learning_rate": 8.726508267791866e-08, "loss": 0.1714, "step": 5992 }, { "epoch": 9.71, "learning_rate": 8.628803404308272e-08, "loss": 0.1114, "step": 5993 }, { "epoch": 9.71, "learning_rate": 8.531647409931065e-08, "loss": 0.1054, "step": 5994 }, { "epoch": 9.72, "learning_rate": 8.435040311438824e-08, "loss": 0.1251, "step": 5995 }, { "epoch": 9.72, "learning_rate": 8.338982135458473e-08, "loss": 0.0817, "step": 5996 }, { "epoch": 9.72, "learning_rate": 8.243472908466387e-08, "loss": 0.1508, "step": 5997 }, { "epoch": 9.72, "learning_rate": 8.148512656787066e-08, "loss": 0.126, "step": 5998 }, { "epoch": 9.72, "learning_rate": 8.054101406593574e-08, "loss": 0.0815, "step": 5999 }, { "epoch": 9.72, "learning_rate": 7.960239183908202e-08, "loss": 0.0911, "step": 6000 }, { "epoch": 9.73, "learning_rate": 7.866926014601373e-08, "loss": 0.0917, "step": 6001 }, { "epoch": 9.73, "learning_rate": 7.77416192439251e-08, "loss": 0.0879, "step": 6002 }, { "epoch": 9.73, "learning_rate": 7.681946938849383e-08, "loss": 0.1001, "step": 6003 }, { "epoch": 9.73, "learning_rate": 7.590281083388995e-08, "loss": 0.085, "step": 6004 }, { "epoch": 9.73, "learning_rate": 7.499164383276469e-08, "loss": 0.1254, "step": 6005 }, { "epoch": 9.73, "learning_rate": 7.408596863625717e-08, "loss": 0.1162, "step": 6006 }, { "epoch": 9.74, "learning_rate": 7.318578549398991e-08, "loss": 0.1292, "step": 6007 }, { "epoch": 9.74, "learning_rate": 7.229109465408001e-08, "loss": 0.1298, "step": 6008 }, { "epoch": 9.74, "learning_rate": 7.140189636312134e-08, "loss": 0.119, "step": 6009 }, { "epoch": 9.74, "learning_rate": 7.051819086620004e-08, "loss": 0.1059, "step": 6010 }, { "epoch": 9.74, "learning_rate": 6.963997840688797e-08, "loss": 0.1058, "step": 6011 }, { "epoch": 9.74, "learning_rate": 6.876725922723814e-08, "loss": 0.1584, "step": 6012 }, { "epoch": 9.75, "learning_rate": 6.790003356779373e-08, "loss": 0.0853, "step": 6013 }, { "epoch": 9.75, "learning_rate": 6.703830166758129e-08, "loss": 0.0963, "step": 6014 }, { "epoch": 9.75, "learning_rate": 6.618206376411751e-08, "loss": 0.0795, "step": 6015 }, { "epoch": 9.75, "learning_rate": 6.533132009340026e-08, "loss": 0.0878, "step": 6016 }, { "epoch": 9.75, "learning_rate": 6.448607088991532e-08, "loss": 0.1054, "step": 6017 }, { "epoch": 9.75, "learning_rate": 6.364631638663188e-08, "loss": 0.0758, "step": 6018 }, { "epoch": 9.76, "learning_rate": 6.281205681500701e-08, "loss": 0.0894, "step": 6019 }, { "epoch": 9.76, "learning_rate": 6.198329240498347e-08, "loss": 0.0936, "step": 6020 }, { "epoch": 9.76, "learning_rate": 6.116002338498738e-08, "loss": 0.1107, "step": 6021 }, { "epoch": 9.76, "learning_rate": 6.034224998193061e-08, "loss": 0.0924, "step": 6022 }, { "epoch": 9.76, "learning_rate": 5.952997242121283e-08, "loss": 0.1159, "step": 6023 }, { "epoch": 9.76, "learning_rate": 5.872319092671497e-08, "loss": 0.1174, "step": 6024 }, { "epoch": 9.76, "learning_rate": 5.79219057208058e-08, "loss": 0.111, "step": 6025 }, { "epoch": 9.77, "learning_rate": 5.712611702433757e-08, "loss": 0.1201, "step": 6026 }, { "epoch": 9.77, "learning_rate": 5.633582505665036e-08, "loss": 0.0907, "step": 6027 }, { "epoch": 9.77, "learning_rate": 5.555103003556772e-08, "loss": 0.083, "step": 6028 }, { "epoch": 9.77, "learning_rate": 5.477173217739662e-08, "loss": 0.1205, "step": 6029 }, { "epoch": 9.77, "learning_rate": 5.399793169692968e-08, "loss": 0.1121, "step": 6030 }, { "epoch": 9.77, "learning_rate": 5.322962880744298e-08, "loss": 0.1368, "step": 6031 }, { "epoch": 9.78, "learning_rate": 5.2466823720702664e-08, "loss": 0.1105, "step": 6032 }, { "epoch": 9.78, "learning_rate": 5.1709516646953894e-08, "loss": 0.086, "step": 6033 }, { "epoch": 9.78, "learning_rate": 5.09577077949297e-08, "loss": 0.0964, "step": 6034 }, { "epoch": 9.78, "learning_rate": 5.021139737184433e-08, "loss": 0.1333, "step": 6035 }, { "epoch": 9.78, "learning_rate": 4.94705855833999e-08, "loss": 0.1113, "step": 6036 }, { "epoch": 9.78, "learning_rate": 4.8735272633781974e-08, "loss": 0.1215, "step": 6037 }, { "epoch": 9.79, "learning_rate": 4.800545872566176e-08, "loss": 0.0997, "step": 6038 }, { "epoch": 9.79, "learning_rate": 4.7281144060189464e-08, "loss": 0.1596, "step": 6039 }, { "epoch": 9.79, "learning_rate": 4.6562328837005396e-08, "loss": 0.1282, "step": 6040 }, { "epoch": 9.79, "learning_rate": 4.584901325423108e-08, "loss": 0.0767, "step": 6041 }, { "epoch": 9.79, "learning_rate": 4.51411975084759e-08, "loss": 0.1671, "step": 6042 }, { "epoch": 9.79, "learning_rate": 4.4438881794828246e-08, "loss": 0.09, "step": 6043 }, { "epoch": 9.8, "learning_rate": 4.374206630686217e-08, "loss": 0.088, "step": 6044 }, { "epoch": 9.8, "learning_rate": 4.30507512366396e-08, "loss": 0.1511, "step": 6045 }, { "epoch": 9.8, "learning_rate": 4.236493677470144e-08, "loss": 0.1008, "step": 6046 }, { "epoch": 9.8, "learning_rate": 4.168462311007426e-08, "loss": 0.1521, "step": 6047 }, { "epoch": 9.8, "learning_rate": 4.1009810430270304e-08, "loss": 0.0769, "step": 6048 }, { "epoch": 9.8, "learning_rate": 4.0340498921283e-08, "loss": 0.0492, "step": 6049 }, { "epoch": 9.81, "learning_rate": 3.967668876758701e-08, "loss": 0.074, "step": 6050 }, { "epoch": 9.81, "learning_rate": 3.9018380152149313e-08, "loss": 0.1416, "step": 6051 }, { "epoch": 9.81, "learning_rate": 3.8365573256413655e-08, "loss": 0.0735, "step": 6052 }, { "epoch": 9.81, "learning_rate": 3.7718268260309444e-08, "loss": 0.0884, "step": 6053 }, { "epoch": 9.81, "learning_rate": 3.7076465342247295e-08, "loss": 0.0955, "step": 6054 }, { "epoch": 9.81, "learning_rate": 3.64401646791257e-08, "loss": 0.107, "step": 6055 }, { "epoch": 9.82, "learning_rate": 3.580936644632216e-08, "loss": 0.1029, "step": 6056 }, { "epoch": 9.82, "learning_rate": 3.5184070817699814e-08, "loss": 0.1043, "step": 6057 }, { "epoch": 9.82, "learning_rate": 3.4564277965607465e-08, "loss": 0.0846, "step": 6058 }, { "epoch": 9.82, "learning_rate": 3.394998806087291e-08, "loss": 0.0769, "step": 6059 }, { "epoch": 9.82, "learning_rate": 3.334120127280738e-08, "loss": 0.1045, "step": 6060 }, { "epoch": 9.82, "learning_rate": 3.2737917769209984e-08, "loss": 0.094, "step": 6061 }, { "epoch": 9.82, "learning_rate": 3.214013771635882e-08, "loss": 0.1288, "step": 6062 }, { "epoch": 9.83, "learning_rate": 3.1547861279015436e-08, "loss": 0.1078, "step": 6063 }, { "epoch": 9.83, "learning_rate": 3.0961088620427014e-08, "loss": 0.0908, "step": 6064 }, { "epoch": 9.83, "learning_rate": 3.037981990231975e-08, "loss": 0.1178, "step": 6065 }, { "epoch": 9.83, "learning_rate": 2.9804055284907705e-08, "loss": 0.1032, "step": 6066 }, { "epoch": 9.83, "learning_rate": 2.923379492688172e-08, "loss": 0.1283, "step": 6067 }, { "epoch": 9.83, "learning_rate": 2.8669038985422724e-08, "loss": 0.1249, "step": 6068 }, { "epoch": 9.84, "learning_rate": 2.8109787616188434e-08, "loss": 0.1114, "step": 6069 }, { "epoch": 9.84, "learning_rate": 2.7556040973322206e-08, "loss": 0.1202, "step": 6070 }, { "epoch": 9.84, "learning_rate": 2.7007799209450848e-08, "loss": 0.1901, "step": 6071 }, { "epoch": 9.84, "learning_rate": 2.646506247568237e-08, "loss": 0.145, "step": 6072 }, { "epoch": 9.84, "learning_rate": 2.5927830921606e-08, "loss": 0.114, "step": 6073 }, { "epoch": 9.84, "learning_rate": 2.539610469529885e-08, "loss": 0.0912, "step": 6074 }, { "epoch": 9.85, "learning_rate": 2.4869883943314798e-08, "loss": 0.1045, "step": 6075 }, { "epoch": 9.85, "learning_rate": 2.434916881069338e-08, "loss": 0.0801, "step": 6076 }, { "epoch": 9.85, "learning_rate": 2.3833959440955344e-08, "loss": 0.1201, "step": 6077 }, { "epoch": 9.85, "learning_rate": 2.3324255976104883e-08, "loss": 0.11, "step": 6078 }, { "epoch": 9.85, "learning_rate": 2.282005855662961e-08, "loss": 0.085, "step": 6079 }, { "epoch": 9.85, "learning_rate": 2.2321367321498366e-08, "loss": 0.098, "step": 6080 }, { "epoch": 9.86, "learning_rate": 2.1828182408161203e-08, "loss": 0.1119, "step": 6081 }, { "epoch": 9.86, "learning_rate": 2.1340503952551606e-08, "loss": 0.1168, "step": 6082 }, { "epoch": 9.86, "learning_rate": 2.0858332089084275e-08, "loss": 0.1716, "step": 6083 }, { "epoch": 9.86, "learning_rate": 2.0381666950659573e-08, "loss": 0.1126, "step": 6084 }, { "epoch": 9.86, "learning_rate": 1.991050866865685e-08, "loss": 0.0744, "step": 6085 }, { "epoch": 9.86, "learning_rate": 1.9444857372936666e-08, "loss": 0.1152, "step": 6086 }, { "epoch": 9.87, "learning_rate": 1.898471319184747e-08, "loss": 0.1334, "step": 6087 }, { "epoch": 9.87, "learning_rate": 1.8530076252212258e-08, "loss": 0.1264, "step": 6088 }, { "epoch": 9.87, "learning_rate": 1.8080946679339685e-08, "loss": 0.1007, "step": 6089 }, { "epoch": 9.87, "learning_rate": 1.763732459702405e-08, "loss": 0.1287, "step": 6090 }, { "epoch": 9.87, "learning_rate": 1.719921012753423e-08, "loss": 0.0915, "step": 6091 }, { "epoch": 9.87, "learning_rate": 1.6766603391626947e-08, "loss": 0.1126, "step": 6092 }, { "epoch": 9.88, "learning_rate": 1.6339504508540162e-08, "loss": 0.1142, "step": 6093 }, { "epoch": 9.88, "learning_rate": 1.59179135959886e-08, "loss": 0.1372, "step": 6094 }, { "epoch": 9.88, "learning_rate": 1.5501830770177083e-08, "loss": 0.1493, "step": 6095 }, { "epoch": 9.88, "learning_rate": 1.5091256145784993e-08, "loss": 0.1033, "step": 6096 }, { "epoch": 9.88, "learning_rate": 1.468618983597514e-08, "loss": 0.0965, "step": 6097 }, { "epoch": 9.88, "learning_rate": 1.4286631952398212e-08, "loss": 0.1058, "step": 6098 }, { "epoch": 9.88, "learning_rate": 1.389258260517723e-08, "loss": 0.0988, "step": 6099 }, { "epoch": 9.89, "learning_rate": 1.3504041902925314e-08, "loss": 0.1555, "step": 6100 }, { "epoch": 9.89, "learning_rate": 1.3121009952730136e-08, "loss": 0.1017, "step": 6101 }, { "epoch": 9.89, "learning_rate": 1.2743486860165022e-08, "loss": 0.0883, "step": 6102 }, { "epoch": 9.89, "learning_rate": 1.2371472729286737e-08, "loss": 0.0802, "step": 6103 }, { "epoch": 9.89, "learning_rate": 1.2004967662628819e-08, "loss": 0.113, "step": 6104 }, { "epoch": 9.89, "learning_rate": 1.164397176121046e-08, "loss": 0.0864, "step": 6105 }, { "epoch": 9.9, "learning_rate": 1.1288485124529847e-08, "loss": 0.0925, "step": 6106 }, { "epoch": 9.9, "learning_rate": 1.0938507850566383e-08, "loss": 0.1332, "step": 6107 }, { "epoch": 9.9, "learning_rate": 1.0594040035782903e-08, "loss": 0.0603, "step": 6108 }, { "epoch": 9.9, "learning_rate": 1.0255081775123466e-08, "loss": 0.0762, "step": 6109 }, { "epoch": 9.9, "learning_rate": 9.921633162011113e-09, "loss": 0.0868, "step": 6110 }, { "epoch": 9.9, "learning_rate": 9.59369428835677e-09, "loss": 0.0953, "step": 6111 }, { "epoch": 9.91, "learning_rate": 9.271265244541472e-09, "loss": 0.0908, "step": 6112 }, { "epoch": 9.91, "learning_rate": 8.954346119440794e-09, "loss": 0.1182, "step": 6113 }, { "epoch": 9.91, "learning_rate": 8.64293700040264e-09, "loss": 0.1081, "step": 6114 }, { "epoch": 9.91, "learning_rate": 8.337037973256135e-09, "loss": 0.0817, "step": 6115 }, { "epoch": 9.91, "learning_rate": 8.036649122318274e-09, "loss": 0.1738, "step": 6116 }, { "epoch": 9.91, "learning_rate": 7.74177053038061e-09, "loss": 0.111, "step": 6117 }, { "epoch": 9.92, "learning_rate": 7.45240227872035e-09, "loss": 0.1181, "step": 6118 }, { "epoch": 9.92, "learning_rate": 7.168544447093695e-09, "loss": 0.126, "step": 6119 }, { "epoch": 9.92, "learning_rate": 6.890197113738062e-09, "loss": 0.0876, "step": 6120 }, { "epoch": 9.92, "learning_rate": 6.617360355372082e-09, "loss": 0.1707, "step": 6121 }, { "epoch": 9.92, "learning_rate": 6.350034247197823e-09, "loss": 0.1355, "step": 6122 }, { "epoch": 9.92, "learning_rate": 6.0882188628963446e-09, "loss": 0.1138, "step": 6123 }, { "epoch": 9.93, "learning_rate": 5.831914274629924e-09, "loss": 0.1776, "step": 6124 }, { "epoch": 9.93, "learning_rate": 5.581120553039832e-09, "loss": 0.1115, "step": 6125 }, { "epoch": 9.93, "learning_rate": 5.335837767255214e-09, "loss": 0.0902, "step": 6126 }, { "epoch": 9.93, "learning_rate": 5.096065984877552e-09, "loss": 0.1773, "step": 6127 }, { "epoch": 9.93, "learning_rate": 4.861805271996201e-09, "loss": 0.1144, "step": 6128 }, { "epoch": 9.93, "learning_rate": 4.633055693179511e-09, "loss": 0.133, "step": 6129 }, { "epoch": 9.94, "learning_rate": 4.409817311474829e-09, "loss": 0.1142, "step": 6130 }, { "epoch": 9.94, "learning_rate": 4.1920901884107135e-09, "loss": 0.0915, "step": 6131 }, { "epoch": 9.94, "learning_rate": 3.97987438399916e-09, "loss": 0.1004, "step": 6132 }, { "epoch": 9.94, "learning_rate": 3.7731699567333806e-09, "loss": 0.1071, "step": 6133 }, { "epoch": 9.94, "learning_rate": 3.5719769635855773e-09, "loss": 0.1664, "step": 6134 }, { "epoch": 9.94, "learning_rate": 3.376295460006951e-09, "loss": 0.1301, "step": 6135 }, { "epoch": 9.94, "learning_rate": 3.186125499934356e-09, "loss": 0.1123, "step": 6136 }, { "epoch": 9.95, "learning_rate": 3.001467135781422e-09, "loss": 0.0959, "step": 6137 }, { "epoch": 9.95, "learning_rate": 2.8223204184452123e-09, "loss": 0.1027, "step": 6138 }, { "epoch": 9.95, "learning_rate": 2.648685397304007e-09, "loss": 0.1266, "step": 6139 }, { "epoch": 9.95, "learning_rate": 2.4805621202128595e-09, "loss": 0.092, "step": 6140 }, { "epoch": 9.95, "learning_rate": 2.3179506335146982e-09, "loss": 0.1955, "step": 6141 }, { "epoch": 9.95, "learning_rate": 2.160850982024787e-09, "loss": 0.1346, "step": 6142 }, { "epoch": 9.96, "learning_rate": 2.009263209046264e-09, "loss": 0.1508, "step": 6143 }, { "epoch": 9.96, "learning_rate": 1.863187356359042e-09, "loss": 0.1267, "step": 6144 }, { "epoch": 9.96, "learning_rate": 1.722623464224249e-09, "loss": 0.1228, "step": 6145 }, { "epoch": 9.96, "learning_rate": 1.587571571386448e-09, "loss": 0.0885, "step": 6146 }, { "epoch": 9.96, "learning_rate": 1.458031715069197e-09, "loss": 0.0828, "step": 6147 }, { "epoch": 9.96, "learning_rate": 1.3340039309750475e-09, "loss": 0.1202, "step": 6148 }, { "epoch": 9.97, "learning_rate": 1.2154882532922073e-09, "loss": 0.1419, "step": 6149 }, { "epoch": 9.97, "learning_rate": 1.102484714681218e-09, "loss": 0.1266, "step": 6150 }, { "epoch": 9.97, "learning_rate": 9.949933462949368e-10, "loss": 0.127, "step": 6151 }, { "epoch": 9.97, "learning_rate": 8.930141777541146e-10, "loss": 0.1236, "step": 6152 }, { "epoch": 9.97, "learning_rate": 7.965472371718186e-10, "loss": 0.1488, "step": 6153 }, { "epoch": 9.97, "learning_rate": 7.055925511334493e-10, "loss": 0.1461, "step": 6154 }, { "epoch": 9.98, "learning_rate": 6.201501447078428e-10, "loss": 0.0814, "step": 6155 }, { "epoch": 9.98, "learning_rate": 5.402200414494907e-10, "loss": 0.0984, "step": 6156 }, { "epoch": 9.98, "learning_rate": 4.658022633829973e-10, "loss": 0.1536, "step": 6157 }, { "epoch": 9.98, "learning_rate": 3.9689683102306364e-10, "loss": 0.1526, "step": 6158 }, { "epoch": 9.98, "learning_rate": 3.335037633633853e-10, "loss": 0.15, "step": 6159 }, { "epoch": 9.98, "learning_rate": 2.756230778722113e-10, "loss": 0.0954, "step": 6160 }, { "epoch": 9.99, "learning_rate": 2.23254790505667e-10, "loss": 0.1311, "step": 6161 }, { "epoch": 9.99, "learning_rate": 1.7639891569665167e-10, "loss": 0.0915, "step": 6162 }, { "epoch": 9.99, "learning_rate": 1.3505546636150003e-10, "loss": 0.136, "step": 6163 }, { "epoch": 9.99, "learning_rate": 9.92244538933207e-11, "loss": 0.1038, "step": 6164 }, { "epoch": 9.99, "learning_rate": 6.890588816865773e-11, "loss": 0.0924, "step": 6165 }, { "epoch": 9.99, "learning_rate": 4.409977754527006e-11, "loss": 0.0751, "step": 6166 }, { "epoch": 10.0, "learning_rate": 2.4806128857690627e-11, "loss": 0.1151, "step": 6167 }, { "epoch": 10.0, "learning_rate": 1.102494742388771e-11, "loss": 0.0828, "step": 6168 }, { "epoch": 10.0, "learning_rate": 2.7562370452649535e-12, "loss": 0.1454, "step": 6169 }, { "epoch": 10.0, "learning_rate": 0.0, "loss": 0.1724, "step": 6170 }, { "epoch": 10.0, "step": 6170, "total_flos": 5.557199237139573e+21, "train_loss": 0.21487315905490223, "train_runtime": 7541.8834, "train_samples_per_second": 9.808, "train_steps_per_second": 0.818 } ], "logging_steps": 1.0, "max_steps": 6170, "num_input_tokens_seen": 0, "num_train_epochs": 10, "save_steps": 500, "total_flos": 5.557199237139573e+21, "train_batch_size": 2, "trial_name": null, "trial_params": null }