{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.996437356858088, "eval_steps": 500, "global_step": 1413, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 1.8604651162790698e-07, "loss": 2.0392, "step": 1 }, { "epoch": 0.0, "learning_rate": 3.7209302325581396e-07, "loss": 1.6846, "step": 2 }, { "epoch": 0.01, "learning_rate": 5.581395348837209e-07, "loss": 1.6097, "step": 3 }, { "epoch": 0.01, "learning_rate": 7.441860465116279e-07, "loss": 2.3086, "step": 4 }, { "epoch": 0.01, "learning_rate": 9.302325581395349e-07, "loss": 1.6364, "step": 5 }, { "epoch": 0.01, "learning_rate": 1.1162790697674417e-06, "loss": 1.7009, "step": 6 }, { "epoch": 0.01, "learning_rate": 1.302325581395349e-06, "loss": 2.0812, "step": 7 }, { "epoch": 0.02, "learning_rate": 1.4883720930232558e-06, "loss": 1.9181, "step": 8 }, { "epoch": 0.02, "learning_rate": 1.6744186046511629e-06, "loss": 1.3402, "step": 9 }, { "epoch": 0.02, "learning_rate": 1.8604651162790697e-06, "loss": 1.2286, "step": 10 }, { "epoch": 0.02, "learning_rate": 2.0465116279069768e-06, "loss": 1.1485, "step": 11 }, { "epoch": 0.03, "learning_rate": 2.2325581395348834e-06, "loss": 0.9198, "step": 12 }, { "epoch": 0.03, "learning_rate": 2.4186046511627905e-06, "loss": 0.8345, "step": 13 }, { "epoch": 0.03, "learning_rate": 2.604651162790698e-06, "loss": 1.0269, "step": 14 }, { "epoch": 0.03, "learning_rate": 2.7906976744186046e-06, "loss": 0.7902, "step": 15 }, { "epoch": 0.03, "learning_rate": 2.9767441860465116e-06, "loss": 0.7482, "step": 16 }, { "epoch": 0.04, "learning_rate": 3.1627906976744183e-06, "loss": 0.7846, "step": 17 }, { "epoch": 0.04, "learning_rate": 3.3488372093023258e-06, "loss": 0.735, "step": 18 }, { "epoch": 0.04, "learning_rate": 3.5348837209302324e-06, "loss": 0.6928, "step": 19 }, { "epoch": 0.04, "learning_rate": 3.7209302325581394e-06, "loss": 0.6898, "step": 20 }, { "epoch": 0.04, "learning_rate": 3.906976744186046e-06, "loss": 0.6526, "step": 21 }, { "epoch": 0.05, "learning_rate": 4.0930232558139536e-06, "loss": 0.6669, "step": 22 }, { "epoch": 0.05, "learning_rate": 4.27906976744186e-06, "loss": 0.6992, "step": 23 }, { "epoch": 0.05, "learning_rate": 4.465116279069767e-06, "loss": 0.7552, "step": 24 }, { "epoch": 0.05, "learning_rate": 4.651162790697674e-06, "loss": 0.7492, "step": 25 }, { "epoch": 0.06, "learning_rate": 4.837209302325581e-06, "loss": 0.6134, "step": 26 }, { "epoch": 0.06, "learning_rate": 5.023255813953488e-06, "loss": 0.6963, "step": 27 }, { "epoch": 0.06, "learning_rate": 5.209302325581396e-06, "loss": 0.5131, "step": 28 }, { "epoch": 0.06, "learning_rate": 5.395348837209302e-06, "loss": 0.6743, "step": 29 }, { "epoch": 0.06, "learning_rate": 5.581395348837209e-06, "loss": 0.6523, "step": 30 }, { "epoch": 0.07, "learning_rate": 5.767441860465116e-06, "loss": 0.5206, "step": 31 }, { "epoch": 0.07, "learning_rate": 5.953488372093023e-06, "loss": 0.6574, "step": 32 }, { "epoch": 0.07, "learning_rate": 6.13953488372093e-06, "loss": 0.6243, "step": 33 }, { "epoch": 0.07, "learning_rate": 6.3255813953488365e-06, "loss": 0.5946, "step": 34 }, { "epoch": 0.07, "learning_rate": 6.511627906976744e-06, "loss": 0.6132, "step": 35 }, { "epoch": 0.08, "learning_rate": 6.6976744186046515e-06, "loss": 0.5163, "step": 36 }, { "epoch": 0.08, "learning_rate": 6.883720930232557e-06, "loss": 0.6358, "step": 37 }, { "epoch": 0.08, "learning_rate": 7.069767441860465e-06, "loss": 0.6571, "step": 38 }, { "epoch": 0.08, "learning_rate": 7.255813953488371e-06, "loss": 0.5816, "step": 39 }, { "epoch": 0.08, "learning_rate": 7.441860465116279e-06, "loss": 0.5938, "step": 40 }, { "epoch": 0.09, "learning_rate": 7.6279069767441855e-06, "loss": 0.6899, "step": 41 }, { "epoch": 0.09, "learning_rate": 7.813953488372092e-06, "loss": 0.6033, "step": 42 }, { "epoch": 0.09, "learning_rate": 8e-06, "loss": 0.5794, "step": 43 }, { "epoch": 0.09, "learning_rate": 7.999989483083726e-06, "loss": 0.5525, "step": 44 }, { "epoch": 0.1, "learning_rate": 7.999957932390211e-06, "loss": 0.5775, "step": 45 }, { "epoch": 0.1, "learning_rate": 7.99990534808536e-06, "loss": 0.547, "step": 46 }, { "epoch": 0.1, "learning_rate": 7.999831730445688e-06, "loss": 0.5855, "step": 47 }, { "epoch": 0.1, "learning_rate": 7.999737079858309e-06, "loss": 0.6557, "step": 48 }, { "epoch": 0.1, "learning_rate": 7.999621396820937e-06, "loss": 0.6552, "step": 49 }, { "epoch": 0.11, "learning_rate": 7.99948468194189e-06, "loss": 0.6311, "step": 50 }, { "epoch": 0.11, "learning_rate": 7.999326935940076e-06, "loss": 0.5301, "step": 51 }, { "epoch": 0.11, "learning_rate": 7.999148159644996e-06, "loss": 0.557, "step": 52 }, { "epoch": 0.11, "learning_rate": 7.998948353996736e-06, "loss": 0.5448, "step": 53 }, { "epoch": 0.11, "learning_rate": 7.998727520045967e-06, "loss": 0.6503, "step": 54 }, { "epoch": 0.12, "learning_rate": 7.998485658953935e-06, "loss": 0.6246, "step": 55 }, { "epoch": 0.12, "learning_rate": 7.998222771992458e-06, "loss": 0.5755, "step": 56 }, { "epoch": 0.12, "learning_rate": 7.997938860543913e-06, "loss": 0.6239, "step": 57 }, { "epoch": 0.12, "learning_rate": 7.997633926101238e-06, "loss": 0.5797, "step": 58 }, { "epoch": 0.13, "learning_rate": 7.997307970267918e-06, "loss": 0.5273, "step": 59 }, { "epoch": 0.13, "learning_rate": 7.996960994757979e-06, "loss": 0.4711, "step": 60 }, { "epoch": 0.13, "learning_rate": 7.996593001395974e-06, "loss": 0.5911, "step": 61 }, { "epoch": 0.13, "learning_rate": 7.996203992116987e-06, "loss": 0.6178, "step": 62 }, { "epoch": 0.13, "learning_rate": 7.9957939689666e-06, "loss": 0.5103, "step": 63 }, { "epoch": 0.14, "learning_rate": 7.995362934100906e-06, "loss": 0.6371, "step": 64 }, { "epoch": 0.14, "learning_rate": 7.994910889786486e-06, "loss": 0.5945, "step": 65 }, { "epoch": 0.14, "learning_rate": 7.99443783840039e-06, "loss": 0.5246, "step": 66 }, { "epoch": 0.14, "learning_rate": 7.993943782430143e-06, "loss": 0.5202, "step": 67 }, { "epoch": 0.14, "learning_rate": 7.993428724473718e-06, "loss": 0.5669, "step": 68 }, { "epoch": 0.15, "learning_rate": 7.992892667239526e-06, "loss": 0.5739, "step": 69 }, { "epoch": 0.15, "learning_rate": 7.992335613546396e-06, "loss": 0.636, "step": 70 }, { "epoch": 0.15, "learning_rate": 7.99175756632358e-06, "loss": 0.5692, "step": 71 }, { "epoch": 0.15, "learning_rate": 7.991158528610708e-06, "loss": 0.6142, "step": 72 }, { "epoch": 0.15, "learning_rate": 7.9905385035578e-06, "loss": 0.5496, "step": 73 }, { "epoch": 0.16, "learning_rate": 7.989897494425228e-06, "loss": 0.5533, "step": 74 }, { "epoch": 0.16, "learning_rate": 7.989235504583714e-06, "loss": 0.5174, "step": 75 }, { "epoch": 0.16, "learning_rate": 7.988552537514302e-06, "loss": 0.5859, "step": 76 }, { "epoch": 0.16, "learning_rate": 7.987848596808347e-06, "loss": 0.56, "step": 77 }, { "epoch": 0.17, "learning_rate": 7.98712368616749e-06, "loss": 0.6045, "step": 78 }, { "epoch": 0.17, "learning_rate": 7.986377809403648e-06, "loss": 0.5238, "step": 79 }, { "epoch": 0.17, "learning_rate": 7.985610970438977e-06, "loss": 0.5774, "step": 80 }, { "epoch": 0.17, "learning_rate": 7.984823173305872e-06, "loss": 0.5689, "step": 81 }, { "epoch": 0.17, "learning_rate": 7.984014422146926e-06, "loss": 0.6355, "step": 82 }, { "epoch": 0.18, "learning_rate": 7.98318472121493e-06, "loss": 0.509, "step": 83 }, { "epoch": 0.18, "learning_rate": 7.982334074872826e-06, "loss": 0.5356, "step": 84 }, { "epoch": 0.18, "learning_rate": 7.981462487593704e-06, "loss": 0.5086, "step": 85 }, { "epoch": 0.18, "learning_rate": 7.98056996396077e-06, "loss": 0.5245, "step": 86 }, { "epoch": 0.18, "learning_rate": 7.97965650866732e-06, "loss": 0.4611, "step": 87 }, { "epoch": 0.19, "learning_rate": 7.978722126516724e-06, "loss": 0.5607, "step": 88 }, { "epoch": 0.19, "learning_rate": 7.97776682242239e-06, "loss": 0.5196, "step": 89 }, { "epoch": 0.19, "learning_rate": 7.976790601407744e-06, "loss": 0.5956, "step": 90 }, { "epoch": 0.19, "learning_rate": 7.975793468606202e-06, "loss": 0.5261, "step": 91 }, { "epoch": 0.2, "learning_rate": 7.974775429261146e-06, "loss": 0.4927, "step": 92 }, { "epoch": 0.2, "learning_rate": 7.973736488725894e-06, "loss": 0.6336, "step": 93 }, { "epoch": 0.2, "learning_rate": 7.972676652463672e-06, "loss": 0.4601, "step": 94 }, { "epoch": 0.2, "learning_rate": 7.971595926047584e-06, "loss": 0.518, "step": 95 }, { "epoch": 0.2, "learning_rate": 7.970494315160581e-06, "loss": 0.6252, "step": 96 }, { "epoch": 0.21, "learning_rate": 7.969371825595446e-06, "loss": 0.6422, "step": 97 }, { "epoch": 0.21, "learning_rate": 7.968228463254734e-06, "loss": 0.5604, "step": 98 }, { "epoch": 0.21, "learning_rate": 7.967064234150774e-06, "loss": 0.5668, "step": 99 }, { "epoch": 0.21, "learning_rate": 7.965879144405614e-06, "loss": 0.5038, "step": 100 }, { "epoch": 0.21, "learning_rate": 7.964673200251e-06, "loss": 0.5135, "step": 101 }, { "epoch": 0.22, "learning_rate": 7.963446408028337e-06, "loss": 0.5891, "step": 102 }, { "epoch": 0.22, "learning_rate": 7.962198774188664e-06, "loss": 0.5601, "step": 103 }, { "epoch": 0.22, "learning_rate": 7.960930305292606e-06, "loss": 0.5299, "step": 104 }, { "epoch": 0.22, "learning_rate": 7.959641008010358e-06, "loss": 0.5386, "step": 105 }, { "epoch": 0.22, "learning_rate": 7.958330889121633e-06, "loss": 0.4753, "step": 106 }, { "epoch": 0.23, "learning_rate": 7.956999955515639e-06, "loss": 0.5309, "step": 107 }, { "epoch": 0.23, "learning_rate": 7.955648214191032e-06, "loss": 0.4613, "step": 108 }, { "epoch": 0.23, "learning_rate": 7.954275672255889e-06, "loss": 0.5896, "step": 109 }, { "epoch": 0.23, "learning_rate": 7.952882336927664e-06, "loss": 0.5575, "step": 110 }, { "epoch": 0.24, "learning_rate": 7.951468215533152e-06, "loss": 0.5446, "step": 111 }, { "epoch": 0.24, "learning_rate": 7.950033315508452e-06, "loss": 0.5002, "step": 112 }, { "epoch": 0.24, "learning_rate": 7.948577644398923e-06, "loss": 0.5286, "step": 113 }, { "epoch": 0.24, "learning_rate": 7.947101209859155e-06, "loss": 0.5512, "step": 114 }, { "epoch": 0.24, "learning_rate": 7.945604019652914e-06, "loss": 0.4671, "step": 115 }, { "epoch": 0.25, "learning_rate": 7.944086081653113e-06, "loss": 0.4763, "step": 116 }, { "epoch": 0.25, "learning_rate": 7.942547403841764e-06, "loss": 0.4876, "step": 117 }, { "epoch": 0.25, "learning_rate": 7.940987994309944e-06, "loss": 0.5406, "step": 118 }, { "epoch": 0.25, "learning_rate": 7.939407861257737e-06, "loss": 0.5201, "step": 119 }, { "epoch": 0.25, "learning_rate": 7.937807012994212e-06, "loss": 0.5437, "step": 120 }, { "epoch": 0.26, "learning_rate": 7.936185457937358e-06, "loss": 0.5829, "step": 121 }, { "epoch": 0.26, "learning_rate": 7.934543204614057e-06, "loss": 0.5079, "step": 122 }, { "epoch": 0.26, "learning_rate": 7.93288026166003e-06, "loss": 0.5478, "step": 123 }, { "epoch": 0.26, "learning_rate": 7.931196637819789e-06, "loss": 0.4746, "step": 124 }, { "epoch": 0.27, "learning_rate": 7.929492341946603e-06, "loss": 0.5347, "step": 125 }, { "epoch": 0.27, "learning_rate": 7.92776738300244e-06, "loss": 0.4957, "step": 126 }, { "epoch": 0.27, "learning_rate": 7.926021770057926e-06, "loss": 0.5816, "step": 127 }, { "epoch": 0.27, "learning_rate": 7.92425551229229e-06, "loss": 0.4931, "step": 128 }, { "epoch": 0.27, "learning_rate": 7.922468618993326e-06, "loss": 0.491, "step": 129 }, { "epoch": 0.28, "learning_rate": 7.920661099557337e-06, "loss": 0.5166, "step": 130 }, { "epoch": 0.28, "learning_rate": 7.91883296348909e-06, "loss": 0.5181, "step": 131 }, { "epoch": 0.28, "learning_rate": 7.916984220401761e-06, "loss": 0.5518, "step": 132 }, { "epoch": 0.28, "learning_rate": 7.915114880016888e-06, "loss": 0.5376, "step": 133 }, { "epoch": 0.28, "learning_rate": 7.91322495216432e-06, "loss": 0.4974, "step": 134 }, { "epoch": 0.29, "learning_rate": 7.911314446782161e-06, "loss": 0.5021, "step": 135 }, { "epoch": 0.29, "learning_rate": 7.909383373916727e-06, "loss": 0.5164, "step": 136 }, { "epoch": 0.29, "learning_rate": 7.907431743722481e-06, "loss": 0.5514, "step": 137 }, { "epoch": 0.29, "learning_rate": 7.905459566461991e-06, "loss": 0.6097, "step": 138 }, { "epoch": 0.29, "learning_rate": 7.903466852505868e-06, "loss": 0.6404, "step": 139 }, { "epoch": 0.3, "learning_rate": 7.901453612332712e-06, "loss": 0.5212, "step": 140 }, { "epoch": 0.3, "learning_rate": 7.899419856529065e-06, "loss": 0.4706, "step": 141 }, { "epoch": 0.3, "learning_rate": 7.897365595789349e-06, "loss": 0.5085, "step": 142 }, { "epoch": 0.3, "learning_rate": 7.895290840915802e-06, "loss": 0.4753, "step": 143 }, { "epoch": 0.31, "learning_rate": 7.893195602818441e-06, "loss": 0.452, "step": 144 }, { "epoch": 0.31, "learning_rate": 7.891079892514985e-06, "loss": 0.5328, "step": 145 }, { "epoch": 0.31, "learning_rate": 7.88894372113081e-06, "loss": 0.4966, "step": 146 }, { "epoch": 0.31, "learning_rate": 7.886787099898881e-06, "loss": 0.499, "step": 147 }, { "epoch": 0.31, "learning_rate": 7.884610040159704e-06, "loss": 0.5076, "step": 148 }, { "epoch": 0.32, "learning_rate": 7.882412553361251e-06, "loss": 0.4399, "step": 149 }, { "epoch": 0.32, "learning_rate": 7.880194651058922e-06, "loss": 0.5146, "step": 150 }, { "epoch": 0.32, "learning_rate": 7.877956344915458e-06, "loss": 0.5713, "step": 151 }, { "epoch": 0.32, "learning_rate": 7.875697646700899e-06, "loss": 0.5859, "step": 152 }, { "epoch": 0.32, "learning_rate": 7.873418568292516e-06, "loss": 0.47, "step": 153 }, { "epoch": 0.33, "learning_rate": 7.871119121674747e-06, "loss": 0.5046, "step": 154 }, { "epoch": 0.33, "learning_rate": 7.868799318939135e-06, "loss": 0.4822, "step": 155 }, { "epoch": 0.33, "learning_rate": 7.866459172284266e-06, "loss": 0.5664, "step": 156 }, { "epoch": 0.33, "learning_rate": 7.864098694015706e-06, "loss": 0.4816, "step": 157 }, { "epoch": 0.34, "learning_rate": 7.861717896545927e-06, "loss": 0.5024, "step": 158 }, { "epoch": 0.34, "learning_rate": 7.859316792394255e-06, "loss": 0.5695, "step": 159 }, { "epoch": 0.34, "learning_rate": 7.856895394186795e-06, "loss": 0.5718, "step": 160 }, { "epoch": 0.34, "learning_rate": 7.854453714656367e-06, "loss": 0.4732, "step": 161 }, { "epoch": 0.34, "learning_rate": 7.851991766642444e-06, "loss": 0.5216, "step": 162 }, { "epoch": 0.35, "learning_rate": 7.849509563091072e-06, "loss": 0.476, "step": 163 }, { "epoch": 0.35, "learning_rate": 7.847007117054819e-06, "loss": 0.5058, "step": 164 }, { "epoch": 0.35, "learning_rate": 7.844484441692688e-06, "loss": 0.5806, "step": 165 }, { "epoch": 0.35, "learning_rate": 7.841941550270068e-06, "loss": 0.4735, "step": 166 }, { "epoch": 0.35, "learning_rate": 7.839378456158641e-06, "loss": 0.5271, "step": 167 }, { "epoch": 0.36, "learning_rate": 7.836795172836333e-06, "loss": 0.4618, "step": 168 }, { "epoch": 0.36, "learning_rate": 7.83419171388723e-06, "loss": 0.5463, "step": 169 }, { "epoch": 0.36, "learning_rate": 7.831568093001514e-06, "loss": 0.5609, "step": 170 }, { "epoch": 0.36, "learning_rate": 7.828924323975384e-06, "loss": 0.4121, "step": 171 }, { "epoch": 0.36, "learning_rate": 7.82626042071099e-06, "loss": 0.5599, "step": 172 }, { "epoch": 0.37, "learning_rate": 7.823576397216353e-06, "loss": 0.5507, "step": 173 }, { "epoch": 0.37, "learning_rate": 7.8208722676053e-06, "loss": 0.5429, "step": 174 }, { "epoch": 0.37, "learning_rate": 7.818148046097385e-06, "loss": 0.4892, "step": 175 }, { "epoch": 0.37, "learning_rate": 7.815403747017809e-06, "loss": 0.5723, "step": 176 }, { "epoch": 0.38, "learning_rate": 7.812639384797356e-06, "loss": 0.497, "step": 177 }, { "epoch": 0.38, "learning_rate": 7.80985497397231e-06, "loss": 0.4353, "step": 178 }, { "epoch": 0.38, "learning_rate": 7.807050529184378e-06, "loss": 0.5138, "step": 179 }, { "epoch": 0.38, "learning_rate": 7.804226065180613e-06, "loss": 0.6011, "step": 180 }, { "epoch": 0.38, "learning_rate": 7.801381596813346e-06, "loss": 0.4651, "step": 181 }, { "epoch": 0.39, "learning_rate": 7.79851713904009e-06, "loss": 0.3993, "step": 182 }, { "epoch": 0.39, "learning_rate": 7.795632706923479e-06, "loss": 0.4822, "step": 183 }, { "epoch": 0.39, "learning_rate": 7.792728315631177e-06, "loss": 0.5465, "step": 184 }, { "epoch": 0.39, "learning_rate": 7.789803980435803e-06, "loss": 0.4937, "step": 185 }, { "epoch": 0.39, "learning_rate": 7.786859716714854e-06, "loss": 0.5817, "step": 186 }, { "epoch": 0.4, "learning_rate": 7.783895539950617e-06, "loss": 0.5089, "step": 187 }, { "epoch": 0.4, "learning_rate": 7.78091146573009e-06, "loss": 0.5045, "step": 188 }, { "epoch": 0.4, "learning_rate": 7.777907509744903e-06, "loss": 0.6175, "step": 189 }, { "epoch": 0.4, "learning_rate": 7.774883687791232e-06, "loss": 0.5375, "step": 190 }, { "epoch": 0.41, "learning_rate": 7.77184001576972e-06, "loss": 0.4996, "step": 191 }, { "epoch": 0.41, "learning_rate": 7.76877650968539e-06, "loss": 0.4786, "step": 192 }, { "epoch": 0.41, "learning_rate": 7.765693185647557e-06, "loss": 0.5974, "step": 193 }, { "epoch": 0.41, "learning_rate": 7.762590059869751e-06, "loss": 0.4305, "step": 194 }, { "epoch": 0.41, "learning_rate": 7.759467148669631e-06, "loss": 0.4898, "step": 195 }, { "epoch": 0.42, "learning_rate": 7.756324468468896e-06, "loss": 0.4873, "step": 196 }, { "epoch": 0.42, "learning_rate": 7.753162035793197e-06, "loss": 0.4564, "step": 197 }, { "epoch": 0.42, "learning_rate": 7.749979867272054e-06, "loss": 0.519, "step": 198 }, { "epoch": 0.42, "learning_rate": 7.746777979638766e-06, "loss": 0.4762, "step": 199 }, { "epoch": 0.42, "learning_rate": 7.743556389730326e-06, "loss": 0.4299, "step": 200 }, { "epoch": 0.43, "learning_rate": 7.740315114487328e-06, "loss": 0.4618, "step": 201 }, { "epoch": 0.43, "learning_rate": 7.737054170953887e-06, "loss": 0.5635, "step": 202 }, { "epoch": 0.43, "learning_rate": 7.73377357627753e-06, "loss": 0.5106, "step": 203 }, { "epoch": 0.43, "learning_rate": 7.730473347709133e-06, "loss": 0.488, "step": 204 }, { "epoch": 0.43, "learning_rate": 7.727153502602811e-06, "loss": 0.5428, "step": 205 }, { "epoch": 0.44, "learning_rate": 7.723814058415826e-06, "loss": 0.5067, "step": 206 }, { "epoch": 0.44, "learning_rate": 7.720455032708504e-06, "loss": 0.4982, "step": 207 }, { "epoch": 0.44, "learning_rate": 7.717076443144148e-06, "loss": 0.491, "step": 208 }, { "epoch": 0.44, "learning_rate": 7.713678307488927e-06, "loss": 0.3632, "step": 209 }, { "epoch": 0.45, "learning_rate": 7.710260643611792e-06, "loss": 0.4876, "step": 210 }, { "epoch": 0.45, "learning_rate": 7.706823469484386e-06, "loss": 0.494, "step": 211 }, { "epoch": 0.45, "learning_rate": 7.703366803180947e-06, "loss": 0.4321, "step": 212 }, { "epoch": 0.45, "learning_rate": 7.699890662878213e-06, "loss": 0.4424, "step": 213 }, { "epoch": 0.45, "learning_rate": 7.696395066855317e-06, "loss": 0.506, "step": 214 }, { "epoch": 0.46, "learning_rate": 7.692880033493706e-06, "loss": 0.5065, "step": 215 }, { "epoch": 0.46, "learning_rate": 7.689345581277037e-06, "loss": 0.4266, "step": 216 }, { "epoch": 0.46, "learning_rate": 7.685791728791079e-06, "loss": 0.5454, "step": 217 }, { "epoch": 0.46, "learning_rate": 7.682218494723613e-06, "loss": 0.5058, "step": 218 }, { "epoch": 0.46, "learning_rate": 7.678625897864346e-06, "loss": 0.4914, "step": 219 }, { "epoch": 0.47, "learning_rate": 7.675013957104795e-06, "loss": 0.4479, "step": 220 }, { "epoch": 0.47, "learning_rate": 7.671382691438199e-06, "loss": 0.4883, "step": 221 }, { "epoch": 0.47, "learning_rate": 7.667732119959419e-06, "loss": 0.4656, "step": 222 }, { "epoch": 0.47, "learning_rate": 7.66406226186483e-06, "loss": 0.5097, "step": 223 }, { "epoch": 0.48, "learning_rate": 7.660373136452227e-06, "loss": 0.5149, "step": 224 }, { "epoch": 0.48, "learning_rate": 7.656664763120723e-06, "loss": 0.4258, "step": 225 }, { "epoch": 0.48, "learning_rate": 7.652937161370643e-06, "loss": 0.476, "step": 226 }, { "epoch": 0.48, "learning_rate": 7.649190350803425e-06, "loss": 0.4781, "step": 227 }, { "epoch": 0.48, "learning_rate": 7.645424351121518e-06, "loss": 0.4783, "step": 228 }, { "epoch": 0.49, "learning_rate": 7.641639182128269e-06, "loss": 0.4735, "step": 229 }, { "epoch": 0.49, "learning_rate": 7.637834863727832e-06, "loss": 0.4702, "step": 230 }, { "epoch": 0.49, "learning_rate": 7.634011415925058e-06, "loss": 0.4501, "step": 231 }, { "epoch": 0.49, "learning_rate": 7.630168858825388e-06, "loss": 0.4906, "step": 232 }, { "epoch": 0.49, "learning_rate": 7.626307212634744e-06, "loss": 0.5146, "step": 233 }, { "epoch": 0.5, "learning_rate": 7.622426497659433e-06, "loss": 0.3979, "step": 234 }, { "epoch": 0.5, "learning_rate": 7.618526734306033e-06, "loss": 0.439, "step": 235 }, { "epoch": 0.5, "learning_rate": 7.6146079430812834e-06, "loss": 0.424, "step": 236 }, { "epoch": 0.5, "learning_rate": 7.610670144591987e-06, "loss": 0.5036, "step": 237 }, { "epoch": 0.5, "learning_rate": 7.606713359544891e-06, "loss": 0.4838, "step": 238 }, { "epoch": 0.51, "learning_rate": 7.602737608746583e-06, "loss": 0.5796, "step": 239 }, { "epoch": 0.51, "learning_rate": 7.5987429131033845e-06, "loss": 0.5559, "step": 240 }, { "epoch": 0.51, "learning_rate": 7.594729293621232e-06, "loss": 0.5669, "step": 241 }, { "epoch": 0.51, "learning_rate": 7.590696771405578e-06, "loss": 0.4606, "step": 242 }, { "epoch": 0.52, "learning_rate": 7.586645367661271e-06, "loss": 0.575, "step": 243 }, { "epoch": 0.52, "learning_rate": 7.5825751036924495e-06, "loss": 0.4341, "step": 244 }, { "epoch": 0.52, "learning_rate": 7.578486000902423e-06, "loss": 0.576, "step": 245 }, { "epoch": 0.52, "learning_rate": 7.57437808079357e-06, "loss": 0.5135, "step": 246 }, { "epoch": 0.52, "learning_rate": 7.570251364967216e-06, "loss": 0.4206, "step": 247 }, { "epoch": 0.53, "learning_rate": 7.566105875123522e-06, "loss": 0.5472, "step": 248 }, { "epoch": 0.53, "learning_rate": 7.561941633061374e-06, "loss": 0.4756, "step": 249 }, { "epoch": 0.53, "learning_rate": 7.5577586606782644e-06, "loss": 0.4792, "step": 250 }, { "epoch": 0.53, "learning_rate": 7.553556979970178e-06, "loss": 0.5208, "step": 251 }, { "epoch": 0.53, "learning_rate": 7.549336613031478e-06, "loss": 0.4277, "step": 252 }, { "epoch": 0.54, "learning_rate": 7.545097582054785e-06, "loss": 0.4843, "step": 253 }, { "epoch": 0.54, "learning_rate": 7.540839909330868e-06, "loss": 0.4407, "step": 254 }, { "epoch": 0.54, "learning_rate": 7.536563617248522e-06, "loss": 0.5072, "step": 255 }, { "epoch": 0.54, "learning_rate": 7.532268728294445e-06, "loss": 0.4303, "step": 256 }, { "epoch": 0.54, "learning_rate": 7.527955265053135e-06, "loss": 0.4282, "step": 257 }, { "epoch": 0.55, "learning_rate": 7.523623250206757e-06, "loss": 0.3934, "step": 258 }, { "epoch": 0.55, "learning_rate": 7.51927270653503e-06, "loss": 0.3748, "step": 259 }, { "epoch": 0.55, "learning_rate": 7.5149036569151034e-06, "loss": 0.4103, "step": 260 }, { "epoch": 0.55, "learning_rate": 7.510516124321446e-06, "loss": 0.5058, "step": 261 }, { "epoch": 0.56, "learning_rate": 7.506110131825709e-06, "loss": 0.4894, "step": 262 }, { "epoch": 0.56, "learning_rate": 7.501685702596624e-06, "loss": 0.5382, "step": 263 }, { "epoch": 0.56, "learning_rate": 7.497242859899865e-06, "loss": 0.4708, "step": 264 }, { "epoch": 0.56, "learning_rate": 7.492781627097933e-06, "loss": 0.5604, "step": 265 }, { "epoch": 0.56, "learning_rate": 7.4883020276500374e-06, "loss": 0.4747, "step": 266 }, { "epoch": 0.57, "learning_rate": 7.4838040851119605e-06, "loss": 0.4831, "step": 267 }, { "epoch": 0.57, "learning_rate": 7.479287823135949e-06, "loss": 0.4334, "step": 268 }, { "epoch": 0.57, "learning_rate": 7.474753265470573e-06, "loss": 0.4775, "step": 269 }, { "epoch": 0.57, "learning_rate": 7.470200435960617e-06, "loss": 0.4522, "step": 270 }, { "epoch": 0.57, "learning_rate": 7.465629358546944e-06, "loss": 0.5341, "step": 271 }, { "epoch": 0.58, "learning_rate": 7.461040057266372e-06, "loss": 0.4744, "step": 272 }, { "epoch": 0.58, "learning_rate": 7.45643255625155e-06, "loss": 0.5266, "step": 273 }, { "epoch": 0.58, "learning_rate": 7.4518068797308315e-06, "loss": 0.4811, "step": 274 }, { "epoch": 0.58, "learning_rate": 7.44716305202814e-06, "loss": 0.3954, "step": 275 }, { "epoch": 0.59, "learning_rate": 7.4425010975628495e-06, "loss": 0.4264, "step": 276 }, { "epoch": 0.59, "learning_rate": 7.437821040849656e-06, "loss": 0.4892, "step": 277 }, { "epoch": 0.59, "learning_rate": 7.433122906498436e-06, "loss": 0.4538, "step": 278 }, { "epoch": 0.59, "learning_rate": 7.428406719214136e-06, "loss": 0.4018, "step": 279 }, { "epoch": 0.59, "learning_rate": 7.423672503796628e-06, "loss": 0.4905, "step": 280 }, { "epoch": 0.6, "learning_rate": 7.418920285140586e-06, "loss": 0.4158, "step": 281 }, { "epoch": 0.6, "learning_rate": 7.414150088235354e-06, "loss": 0.4585, "step": 282 }, { "epoch": 0.6, "learning_rate": 7.40936193816481e-06, "loss": 0.3843, "step": 283 }, { "epoch": 0.6, "learning_rate": 7.404555860107244e-06, "loss": 0.4019, "step": 284 }, { "epoch": 0.6, "learning_rate": 7.399731879335213e-06, "loss": 0.4606, "step": 285 }, { "epoch": 0.61, "learning_rate": 7.394890021215422e-06, "loss": 0.4871, "step": 286 }, { "epoch": 0.61, "learning_rate": 7.390030311208574e-06, "loss": 0.4384, "step": 287 }, { "epoch": 0.61, "learning_rate": 7.385152774869256e-06, "loss": 0.3412, "step": 288 }, { "epoch": 0.61, "learning_rate": 7.380257437845784e-06, "loss": 0.4972, "step": 289 }, { "epoch": 0.61, "learning_rate": 7.375344325880087e-06, "loss": 0.5358, "step": 290 }, { "epoch": 0.62, "learning_rate": 7.370413464807555e-06, "loss": 0.4793, "step": 291 }, { "epoch": 0.62, "learning_rate": 7.365464880556916e-06, "loss": 0.4448, "step": 292 }, { "epoch": 0.62, "learning_rate": 7.360498599150094e-06, "loss": 0.5746, "step": 293 }, { "epoch": 0.62, "learning_rate": 7.35551464670207e-06, "loss": 0.469, "step": 294 }, { "epoch": 0.63, "learning_rate": 7.350513049420751e-06, "loss": 0.4803, "step": 295 }, { "epoch": 0.63, "learning_rate": 7.345493833606826e-06, "loss": 0.3804, "step": 296 }, { "epoch": 0.63, "learning_rate": 7.3404570256536305e-06, "loss": 0.4617, "step": 297 }, { "epoch": 0.63, "learning_rate": 7.33540265204701e-06, "loss": 0.4373, "step": 298 }, { "epoch": 0.63, "learning_rate": 7.330330739365177e-06, "loss": 0.4687, "step": 299 }, { "epoch": 0.64, "learning_rate": 7.325241314278569e-06, "loss": 0.4681, "step": 300 }, { "epoch": 0.64, "learning_rate": 7.320134403549718e-06, "loss": 0.4614, "step": 301 }, { "epoch": 0.64, "learning_rate": 7.315010034033097e-06, "loss": 0.4657, "step": 302 }, { "epoch": 0.64, "learning_rate": 7.309868232674991e-06, "loss": 0.4189, "step": 303 }, { "epoch": 0.64, "learning_rate": 7.304709026513347e-06, "loss": 0.4187, "step": 304 }, { "epoch": 0.65, "learning_rate": 7.299532442677634e-06, "loss": 0.4242, "step": 305 }, { "epoch": 0.65, "learning_rate": 7.294338508388701e-06, "loss": 0.524, "step": 306 }, { "epoch": 0.65, "learning_rate": 7.289127250958635e-06, "loss": 0.4778, "step": 307 }, { "epoch": 0.65, "learning_rate": 7.283898697790614e-06, "loss": 0.5113, "step": 308 }, { "epoch": 0.66, "learning_rate": 7.278652876378768e-06, "loss": 0.4564, "step": 309 }, { "epoch": 0.66, "learning_rate": 7.273389814308027e-06, "loss": 0.4455, "step": 310 }, { "epoch": 0.66, "learning_rate": 7.268109539253983e-06, "loss": 0.493, "step": 311 }, { "epoch": 0.66, "learning_rate": 7.262812078982742e-06, "loss": 0.4508, "step": 312 }, { "epoch": 0.66, "learning_rate": 7.257497461350777e-06, "loss": 0.4226, "step": 313 }, { "epoch": 0.67, "learning_rate": 7.252165714304782e-06, "loss": 0.4664, "step": 314 }, { "epoch": 0.67, "learning_rate": 7.246816865881525e-06, "loss": 0.4826, "step": 315 }, { "epoch": 0.67, "learning_rate": 7.241450944207703e-06, "loss": 0.4462, "step": 316 }, { "epoch": 0.67, "learning_rate": 7.2360679774997895e-06, "loss": 0.3952, "step": 317 }, { "epoch": 0.67, "learning_rate": 7.23066799406389e-06, "loss": 0.4112, "step": 318 }, { "epoch": 0.68, "learning_rate": 7.225251022295591e-06, "loss": 0.5491, "step": 319 }, { "epoch": 0.68, "learning_rate": 7.219817090679812e-06, "loss": 0.5139, "step": 320 }, { "epoch": 0.68, "learning_rate": 7.214366227790655e-06, "loss": 0.4228, "step": 321 }, { "epoch": 0.68, "learning_rate": 7.208898462291253e-06, "loss": 0.4306, "step": 322 }, { "epoch": 0.68, "learning_rate": 7.203413822933625e-06, "loss": 0.5346, "step": 323 }, { "epoch": 0.69, "learning_rate": 7.197912338558515e-06, "loss": 0.5154, "step": 324 }, { "epoch": 0.69, "learning_rate": 7.1923940380952486e-06, "loss": 0.4478, "step": 325 }, { "epoch": 0.69, "learning_rate": 7.186858950561579e-06, "loss": 0.5137, "step": 326 }, { "epoch": 0.69, "learning_rate": 7.181307105063529e-06, "loss": 0.4471, "step": 327 }, { "epoch": 0.7, "learning_rate": 7.17573853079525e-06, "loss": 0.5168, "step": 328 }, { "epoch": 0.7, "learning_rate": 7.170153257038854e-06, "loss": 0.4464, "step": 329 }, { "epoch": 0.7, "learning_rate": 7.16455131316427e-06, "loss": 0.4612, "step": 330 }, { "epoch": 0.7, "learning_rate": 7.158932728629086e-06, "loss": 0.4236, "step": 331 }, { "epoch": 0.7, "learning_rate": 7.153297532978392e-06, "loss": 0.3832, "step": 332 }, { "epoch": 0.71, "learning_rate": 7.147645755844629e-06, "loss": 0.4487, "step": 333 }, { "epoch": 0.71, "learning_rate": 7.1419774269474305e-06, "loss": 0.4025, "step": 334 }, { "epoch": 0.71, "learning_rate": 7.136292576093468e-06, "loss": 0.5025, "step": 335 }, { "epoch": 0.71, "learning_rate": 7.13059123317629e-06, "loss": 0.5122, "step": 336 }, { "epoch": 0.71, "learning_rate": 7.124873428176171e-06, "loss": 0.4852, "step": 337 }, { "epoch": 0.72, "learning_rate": 7.119139191159948e-06, "loss": 0.4314, "step": 338 }, { "epoch": 0.72, "learning_rate": 7.113388552280866e-06, "loss": 0.4837, "step": 339 }, { "epoch": 0.72, "learning_rate": 7.107621541778421e-06, "loss": 0.4836, "step": 340 }, { "epoch": 0.72, "learning_rate": 7.101838189978193e-06, "loss": 0.4527, "step": 341 }, { "epoch": 0.73, "learning_rate": 7.096038527291699e-06, "loss": 0.3796, "step": 342 }, { "epoch": 0.73, "learning_rate": 7.09022258421622e-06, "loss": 0.4869, "step": 343 }, { "epoch": 0.73, "learning_rate": 7.084390391334649e-06, "loss": 0.4134, "step": 344 }, { "epoch": 0.73, "learning_rate": 7.07854197931533e-06, "loss": 0.3975, "step": 345 }, { "epoch": 0.73, "learning_rate": 7.07267737891189e-06, "loss": 0.4144, "step": 346 }, { "epoch": 0.74, "learning_rate": 7.066796620963089e-06, "loss": 0.4882, "step": 347 }, { "epoch": 0.74, "learning_rate": 7.060899736392642e-06, "loss": 0.3924, "step": 348 }, { "epoch": 0.74, "learning_rate": 7.0549867562090715e-06, "loss": 0.4532, "step": 349 }, { "epoch": 0.74, "learning_rate": 7.049057711505536e-06, "loss": 0.4795, "step": 350 }, { "epoch": 0.74, "learning_rate": 7.043112633459671e-06, "loss": 0.4602, "step": 351 }, { "epoch": 0.75, "learning_rate": 7.037151553333417e-06, "loss": 0.3884, "step": 352 }, { "epoch": 0.75, "learning_rate": 7.031174502472867e-06, "loss": 0.384, "step": 353 }, { "epoch": 0.75, "learning_rate": 7.02518151230809e-06, "loss": 0.5014, "step": 354 }, { "epoch": 0.75, "learning_rate": 7.019172614352977e-06, "loss": 0.3907, "step": 355 }, { "epoch": 0.75, "learning_rate": 7.013147840205065e-06, "loss": 0.4334, "step": 356 }, { "epoch": 0.76, "learning_rate": 7.007107221545375e-06, "loss": 0.4261, "step": 357 }, { "epoch": 0.76, "learning_rate": 7.00105079013825e-06, "loss": 0.4448, "step": 358 }, { "epoch": 0.76, "learning_rate": 6.99497857783118e-06, "loss": 0.4571, "step": 359 }, { "epoch": 0.76, "learning_rate": 6.98889061655464e-06, "loss": 0.397, "step": 360 }, { "epoch": 0.77, "learning_rate": 6.982786938321917e-06, "loss": 0.5282, "step": 361 }, { "epoch": 0.77, "learning_rate": 6.976667575228949e-06, "loss": 0.4177, "step": 362 }, { "epoch": 0.77, "learning_rate": 6.970532559454152e-06, "loss": 0.4443, "step": 363 }, { "epoch": 0.77, "learning_rate": 6.964381923258248e-06, "loss": 0.3849, "step": 364 }, { "epoch": 0.77, "learning_rate": 6.9582156989840995e-06, "loss": 0.4263, "step": 365 }, { "epoch": 0.78, "learning_rate": 6.95203391905654e-06, "loss": 0.4899, "step": 366 }, { "epoch": 0.78, "learning_rate": 6.9458366159822e-06, "loss": 0.4577, "step": 367 }, { "epoch": 0.78, "learning_rate": 6.939623822349337e-06, "loss": 0.4412, "step": 368 }, { "epoch": 0.78, "learning_rate": 6.93339557082767e-06, "loss": 0.4228, "step": 369 }, { "epoch": 0.78, "learning_rate": 6.927151894168194e-06, "loss": 0.403, "step": 370 }, { "epoch": 0.79, "learning_rate": 6.920892825203026e-06, "loss": 0.4028, "step": 371 }, { "epoch": 0.79, "learning_rate": 6.9146183968452144e-06, "loss": 0.4651, "step": 372 }, { "epoch": 0.79, "learning_rate": 6.908328642088578e-06, "loss": 0.4636, "step": 373 }, { "epoch": 0.79, "learning_rate": 6.902023594007533e-06, "loss": 0.4928, "step": 374 }, { "epoch": 0.8, "learning_rate": 6.895703285756907e-06, "loss": 0.3784, "step": 375 }, { "epoch": 0.8, "learning_rate": 6.889367750571777e-06, "loss": 0.453, "step": 376 }, { "epoch": 0.8, "learning_rate": 6.8830170217672905e-06, "loss": 0.4229, "step": 377 }, { "epoch": 0.8, "learning_rate": 6.876651132738489e-06, "loss": 0.4435, "step": 378 }, { "epoch": 0.8, "learning_rate": 6.870270116960132e-06, "loss": 0.4433, "step": 379 }, { "epoch": 0.81, "learning_rate": 6.863874007986526e-06, "loss": 0.4006, "step": 380 }, { "epoch": 0.81, "learning_rate": 6.85746283945134e-06, "loss": 0.4228, "step": 381 }, { "epoch": 0.81, "learning_rate": 6.851036645067437e-06, "loss": 0.4261, "step": 382 }, { "epoch": 0.81, "learning_rate": 6.84459545862669e-06, "loss": 0.4391, "step": 383 }, { "epoch": 0.81, "learning_rate": 6.83813931399981e-06, "loss": 0.4812, "step": 384 }, { "epoch": 0.82, "learning_rate": 6.8316682451361615e-06, "loss": 0.3479, "step": 385 }, { "epoch": 0.82, "learning_rate": 6.82518228606359e-06, "loss": 0.5266, "step": 386 }, { "epoch": 0.82, "learning_rate": 6.818681470888239e-06, "loss": 0.4013, "step": 387 }, { "epoch": 0.82, "learning_rate": 6.8121658337943736e-06, "loss": 0.4608, "step": 388 }, { "epoch": 0.82, "learning_rate": 6.8056354090442e-06, "loss": 0.439, "step": 389 }, { "epoch": 0.83, "learning_rate": 6.79909023097768e-06, "loss": 0.4746, "step": 390 }, { "epoch": 0.83, "learning_rate": 6.7925303340123615e-06, "loss": 0.4865, "step": 391 }, { "epoch": 0.83, "learning_rate": 6.785955752643187e-06, "loss": 0.4544, "step": 392 }, { "epoch": 0.83, "learning_rate": 6.779366521442317e-06, "loss": 0.492, "step": 393 }, { "epoch": 0.84, "learning_rate": 6.772762675058949e-06, "loss": 0.4232, "step": 394 }, { "epoch": 0.84, "learning_rate": 6.7661442482191316e-06, "loss": 0.4923, "step": 395 }, { "epoch": 0.84, "learning_rate": 6.759511275725586e-06, "loss": 0.4106, "step": 396 }, { "epoch": 0.84, "learning_rate": 6.75286379245752e-06, "loss": 0.3977, "step": 397 }, { "epoch": 0.84, "learning_rate": 6.7462018333704465e-06, "loss": 0.4891, "step": 398 }, { "epoch": 0.85, "learning_rate": 6.739525433495998e-06, "loss": 0.4572, "step": 399 }, { "epoch": 0.85, "learning_rate": 6.732834627941744e-06, "loss": 0.4054, "step": 400 }, { "epoch": 0.85, "learning_rate": 6.726129451891004e-06, "loss": 0.4421, "step": 401 }, { "epoch": 0.85, "learning_rate": 6.719409940602668e-06, "loss": 0.3797, "step": 402 }, { "epoch": 0.85, "learning_rate": 6.7126761294110035e-06, "loss": 0.4286, "step": 403 }, { "epoch": 0.86, "learning_rate": 6.705928053725476e-06, "loss": 0.4313, "step": 404 }, { "epoch": 0.86, "learning_rate": 6.699165749030556e-06, "loss": 0.4527, "step": 405 }, { "epoch": 0.86, "learning_rate": 6.692389250885542e-06, "loss": 0.4512, "step": 406 }, { "epoch": 0.86, "learning_rate": 6.685598594924366e-06, "loss": 0.4658, "step": 407 }, { "epoch": 0.87, "learning_rate": 6.6787938168554075e-06, "loss": 0.4802, "step": 408 }, { "epoch": 0.87, "learning_rate": 6.671974952461307e-06, "loss": 0.5127, "step": 409 }, { "epoch": 0.87, "learning_rate": 6.665142037598778e-06, "loss": 0.546, "step": 410 }, { "epoch": 0.87, "learning_rate": 6.658295108198416e-06, "loss": 0.4744, "step": 411 }, { "epoch": 0.87, "learning_rate": 6.651434200264513e-06, "loss": 0.4198, "step": 412 }, { "epoch": 0.88, "learning_rate": 6.644559349874868e-06, "loss": 0.3673, "step": 413 }, { "epoch": 0.88, "learning_rate": 6.63767059318059e-06, "loss": 0.465, "step": 414 }, { "epoch": 0.88, "learning_rate": 6.630767966405923e-06, "loss": 0.4162, "step": 415 }, { "epoch": 0.88, "learning_rate": 6.623851505848036e-06, "loss": 0.4321, "step": 416 }, { "epoch": 0.88, "learning_rate": 6.616921247876851e-06, "loss": 0.4142, "step": 417 }, { "epoch": 0.89, "learning_rate": 6.609977228934837e-06, "loss": 0.4443, "step": 418 }, { "epoch": 0.89, "learning_rate": 6.603019485536827e-06, "loss": 0.466, "step": 419 }, { "epoch": 0.89, "learning_rate": 6.596048054269825e-06, "loss": 0.4174, "step": 420 }, { "epoch": 0.89, "learning_rate": 6.58906297179281e-06, "loss": 0.4396, "step": 421 }, { "epoch": 0.89, "learning_rate": 6.582064274836545e-06, "loss": 0.4313, "step": 422 }, { "epoch": 0.9, "learning_rate": 6.575052000203385e-06, "loss": 0.4246, "step": 423 }, { "epoch": 0.9, "learning_rate": 6.568026184767083e-06, "loss": 0.4202, "step": 424 }, { "epoch": 0.9, "learning_rate": 6.560986865472597e-06, "loss": 0.458, "step": 425 }, { "epoch": 0.9, "learning_rate": 6.553934079335889e-06, "loss": 0.5062, "step": 426 }, { "epoch": 0.91, "learning_rate": 6.546867863443741e-06, "loss": 0.4487, "step": 427 }, { "epoch": 0.91, "learning_rate": 6.539788254953555e-06, "loss": 0.5074, "step": 428 }, { "epoch": 0.91, "learning_rate": 6.532695291093156e-06, "loss": 0.3911, "step": 429 }, { "epoch": 0.91, "learning_rate": 6.525589009160597e-06, "loss": 0.4618, "step": 430 }, { "epoch": 0.91, "learning_rate": 6.518469446523962e-06, "loss": 0.3625, "step": 431 }, { "epoch": 0.92, "learning_rate": 6.511336640621175e-06, "loss": 0.4606, "step": 432 }, { "epoch": 0.92, "learning_rate": 6.504190628959797e-06, "loss": 0.3762, "step": 433 }, { "epoch": 0.92, "learning_rate": 6.497031449116832e-06, "loss": 0.4018, "step": 434 }, { "epoch": 0.92, "learning_rate": 6.489859138738526e-06, "loss": 0.4092, "step": 435 }, { "epoch": 0.92, "learning_rate": 6.482673735540172e-06, "loss": 0.3975, "step": 436 }, { "epoch": 0.93, "learning_rate": 6.475475277305915e-06, "loss": 0.4393, "step": 437 }, { "epoch": 0.93, "learning_rate": 6.468263801888545e-06, "loss": 0.4282, "step": 438 }, { "epoch": 0.93, "learning_rate": 6.461039347209302e-06, "loss": 0.4255, "step": 439 }, { "epoch": 0.93, "learning_rate": 6.453801951257681e-06, "loss": 0.513, "step": 440 }, { "epoch": 0.94, "learning_rate": 6.446551652091223e-06, "loss": 0.4321, "step": 441 }, { "epoch": 0.94, "learning_rate": 6.439288487835325e-06, "loss": 0.4872, "step": 442 }, { "epoch": 0.94, "learning_rate": 6.4320124966830304e-06, "loss": 0.485, "step": 443 }, { "epoch": 0.94, "learning_rate": 6.424723716894835e-06, "loss": 0.502, "step": 444 }, { "epoch": 0.94, "learning_rate": 6.417422186798482e-06, "loss": 0.4049, "step": 445 }, { "epoch": 0.95, "learning_rate": 6.410107944788763e-06, "loss": 0.4333, "step": 446 }, { "epoch": 0.95, "learning_rate": 6.40278102932731e-06, "loss": 0.3984, "step": 447 }, { "epoch": 0.95, "learning_rate": 6.3954414789424035e-06, "loss": 0.3831, "step": 448 }, { "epoch": 0.95, "learning_rate": 6.388089332228764e-06, "loss": 0.3706, "step": 449 }, { "epoch": 0.95, "learning_rate": 6.380724627847343e-06, "loss": 0.4587, "step": 450 }, { "epoch": 0.96, "learning_rate": 6.373347404525134e-06, "loss": 0.4058, "step": 451 }, { "epoch": 0.96, "learning_rate": 6.365957701054954e-06, "loss": 0.5062, "step": 452 }, { "epoch": 0.96, "learning_rate": 6.358555556295251e-06, "loss": 0.3817, "step": 453 }, { "epoch": 0.96, "learning_rate": 6.351141009169892e-06, "loss": 0.4271, "step": 454 }, { "epoch": 0.96, "learning_rate": 6.343714098667964e-06, "loss": 0.4173, "step": 455 }, { "epoch": 0.97, "learning_rate": 6.336274863843566e-06, "loss": 0.5117, "step": 456 }, { "epoch": 0.97, "learning_rate": 6.3288233438155995e-06, "loss": 0.4135, "step": 457 }, { "epoch": 0.97, "learning_rate": 6.321359577767573e-06, "loss": 0.4454, "step": 458 }, { "epoch": 0.97, "learning_rate": 6.313883604947388e-06, "loss": 0.4789, "step": 459 }, { "epoch": 0.98, "learning_rate": 6.306395464667133e-06, "loss": 0.4406, "step": 460 }, { "epoch": 0.98, "learning_rate": 6.298895196302881e-06, "loss": 0.4257, "step": 461 }, { "epoch": 0.98, "learning_rate": 6.291382839294479e-06, "loss": 0.3963, "step": 462 }, { "epoch": 0.98, "learning_rate": 6.283858433145344e-06, "loss": 0.3931, "step": 463 }, { "epoch": 0.98, "learning_rate": 6.276322017422248e-06, "loss": 0.4213, "step": 464 }, { "epoch": 0.99, "learning_rate": 6.268773631755118e-06, "loss": 0.4193, "step": 465 }, { "epoch": 0.99, "learning_rate": 6.261213315836825e-06, "loss": 0.4106, "step": 466 }, { "epoch": 0.99, "learning_rate": 6.2536411094229715e-06, "loss": 0.4813, "step": 467 }, { "epoch": 0.99, "learning_rate": 6.246057052331691e-06, "loss": 0.5012, "step": 468 }, { "epoch": 0.99, "learning_rate": 6.23846118444343e-06, "loss": 0.4133, "step": 469 }, { "epoch": 1.0, "learning_rate": 6.230853545700739e-06, "loss": 0.5327, "step": 470 }, { "epoch": 1.0, "learning_rate": 6.22323417610807e-06, "loss": 0.4831, "step": 471 }, { "epoch": 1.0, "learning_rate": 6.21560311573156e-06, "loss": 0.4026, "step": 472 }, { "epoch": 1.0, "learning_rate": 6.207960404698817e-06, "loss": 0.3656, "step": 473 }, { "epoch": 1.01, "learning_rate": 6.20030608319872e-06, "loss": 0.4121, "step": 474 }, { "epoch": 1.01, "learning_rate": 6.192640191481197e-06, "loss": 0.3757, "step": 475 }, { "epoch": 1.01, "learning_rate": 6.1849627698570195e-06, "loss": 0.4363, "step": 476 }, { "epoch": 1.01, "learning_rate": 6.177273858697587e-06, "loss": 0.4333, "step": 477 }, { "epoch": 1.01, "learning_rate": 6.169573498434717e-06, "loss": 0.4304, "step": 478 }, { "epoch": 1.02, "learning_rate": 6.1618617295604315e-06, "loss": 0.4233, "step": 479 }, { "epoch": 1.02, "learning_rate": 6.1541385926267446e-06, "loss": 0.3771, "step": 480 }, { "epoch": 1.02, "learning_rate": 6.146404128245448e-06, "loss": 0.4304, "step": 481 }, { "epoch": 1.02, "learning_rate": 6.1386583770878994e-06, "loss": 0.4226, "step": 482 }, { "epoch": 1.02, "learning_rate": 6.130901379884807e-06, "loss": 0.4151, "step": 483 }, { "epoch": 1.03, "learning_rate": 6.123133177426016e-06, "loss": 0.4144, "step": 484 }, { "epoch": 1.03, "learning_rate": 6.115353810560293e-06, "loss": 0.3793, "step": 485 }, { "epoch": 1.03, "learning_rate": 6.107563320195114e-06, "loss": 0.3304, "step": 486 }, { "epoch": 1.03, "learning_rate": 6.099761747296446e-06, "loss": 0.3824, "step": 487 }, { "epoch": 1.03, "learning_rate": 6.091949132888533e-06, "loss": 0.4095, "step": 488 }, { "epoch": 1.04, "learning_rate": 6.084125518053681e-06, "loss": 0.3464, "step": 489 }, { "epoch": 1.04, "learning_rate": 6.0762909439320425e-06, "loss": 0.3443, "step": 490 }, { "epoch": 1.04, "learning_rate": 6.068445451721396e-06, "loss": 0.4684, "step": 491 }, { "epoch": 1.04, "learning_rate": 6.060589082676933e-06, "loss": 0.3989, "step": 492 }, { "epoch": 1.05, "learning_rate": 6.052721878111044e-06, "loss": 0.4601, "step": 493 }, { "epoch": 1.05, "learning_rate": 6.0448438793930925e-06, "loss": 0.3757, "step": 494 }, { "epoch": 1.05, "learning_rate": 6.036955127949206e-06, "loss": 0.3606, "step": 495 }, { "epoch": 1.05, "learning_rate": 6.029055665262053e-06, "loss": 0.298, "step": 496 }, { "epoch": 1.05, "learning_rate": 6.021145532870628e-06, "loss": 0.4146, "step": 497 }, { "epoch": 1.06, "learning_rate": 6.013224772370031e-06, "loss": 0.4418, "step": 498 }, { "epoch": 1.06, "learning_rate": 6.005293425411251e-06, "loss": 0.3674, "step": 499 }, { "epoch": 1.06, "learning_rate": 5.997351533700939e-06, "loss": 0.3945, "step": 500 }, { "epoch": 1.06, "learning_rate": 5.989399139001206e-06, "loss": 0.4051, "step": 501 }, { "epoch": 1.06, "learning_rate": 5.981436283129383e-06, "loss": 0.4457, "step": 502 }, { "epoch": 1.07, "learning_rate": 5.973463007957816e-06, "loss": 0.3127, "step": 503 }, { "epoch": 1.07, "learning_rate": 5.965479355413637e-06, "loss": 0.3909, "step": 504 }, { "epoch": 1.07, "learning_rate": 5.957485367478551e-06, "loss": 0.3843, "step": 505 }, { "epoch": 1.07, "learning_rate": 5.949481086188607e-06, "loss": 0.4235, "step": 506 }, { "epoch": 1.08, "learning_rate": 5.941466553633983e-06, "loss": 0.3598, "step": 507 }, { "epoch": 1.08, "learning_rate": 5.933441811958763e-06, "loss": 0.3937, "step": 508 }, { "epoch": 1.08, "learning_rate": 5.925406903360716e-06, "loss": 0.4074, "step": 509 }, { "epoch": 1.08, "learning_rate": 5.917361870091073e-06, "loss": 0.351, "step": 510 }, { "epoch": 1.08, "learning_rate": 5.909306754454304e-06, "loss": 0.463, "step": 511 }, { "epoch": 1.09, "learning_rate": 5.9012415988078965e-06, "loss": 0.3958, "step": 512 }, { "epoch": 1.09, "learning_rate": 5.893166445562133e-06, "loss": 0.4059, "step": 513 }, { "epoch": 1.09, "learning_rate": 5.885081337179873e-06, "loss": 0.4071, "step": 514 }, { "epoch": 1.09, "learning_rate": 5.876986316176316e-06, "loss": 0.3505, "step": 515 }, { "epoch": 1.09, "learning_rate": 5.868881425118795e-06, "loss": 0.3885, "step": 516 }, { "epoch": 1.1, "learning_rate": 5.860766706626536e-06, "loss": 0.2975, "step": 517 }, { "epoch": 1.1, "learning_rate": 5.8526422033704486e-06, "loss": 0.3606, "step": 518 }, { "epoch": 1.1, "learning_rate": 5.844507958072895e-06, "loss": 0.4259, "step": 519 }, { "epoch": 1.1, "learning_rate": 5.8363640135074595e-06, "loss": 0.3555, "step": 520 }, { "epoch": 1.1, "learning_rate": 5.828210412498737e-06, "loss": 0.3902, "step": 521 }, { "epoch": 1.11, "learning_rate": 5.8200471979220955e-06, "loss": 0.3933, "step": 522 }, { "epoch": 1.11, "learning_rate": 5.811874412703457e-06, "loss": 0.3749, "step": 523 }, { "epoch": 1.11, "learning_rate": 5.803692099819072e-06, "loss": 0.3806, "step": 524 }, { "epoch": 1.11, "learning_rate": 5.795500302295289e-06, "loss": 0.4314, "step": 525 }, { "epoch": 1.12, "learning_rate": 5.7872990632083304e-06, "loss": 0.3964, "step": 526 }, { "epoch": 1.12, "learning_rate": 5.779088425684073e-06, "loss": 0.4215, "step": 527 }, { "epoch": 1.12, "learning_rate": 5.770868432897808e-06, "loss": 0.3749, "step": 528 }, { "epoch": 1.12, "learning_rate": 5.762639128074024e-06, "loss": 0.3758, "step": 529 }, { "epoch": 1.12, "learning_rate": 5.754400554486174e-06, "loss": 0.3959, "step": 530 }, { "epoch": 1.13, "learning_rate": 5.746152755456455e-06, "loss": 0.3748, "step": 531 }, { "epoch": 1.13, "learning_rate": 5.737895774355571e-06, "loss": 0.3739, "step": 532 }, { "epoch": 1.13, "learning_rate": 5.729629654602513e-06, "loss": 0.3878, "step": 533 }, { "epoch": 1.13, "learning_rate": 5.721354439664324e-06, "loss": 0.3574, "step": 534 }, { "epoch": 1.13, "learning_rate": 5.713070173055875e-06, "loss": 0.4608, "step": 535 }, { "epoch": 1.14, "learning_rate": 5.704776898339638e-06, "loss": 0.4358, "step": 536 }, { "epoch": 1.14, "learning_rate": 5.696474659125449e-06, "loss": 0.4242, "step": 537 }, { "epoch": 1.14, "learning_rate": 5.688163499070285e-06, "loss": 0.3961, "step": 538 }, { "epoch": 1.14, "learning_rate": 5.679843461878035e-06, "loss": 0.3815, "step": 539 }, { "epoch": 1.15, "learning_rate": 5.6715145912992634e-06, "loss": 0.3388, "step": 540 }, { "epoch": 1.15, "learning_rate": 5.66317693113099e-06, "loss": 0.4109, "step": 541 }, { "epoch": 1.15, "learning_rate": 5.654830525216452e-06, "loss": 0.3314, "step": 542 }, { "epoch": 1.15, "learning_rate": 5.646475417444872e-06, "loss": 0.3877, "step": 543 }, { "epoch": 1.15, "learning_rate": 5.638111651751237e-06, "loss": 0.4004, "step": 544 }, { "epoch": 1.16, "learning_rate": 5.62973927211606e-06, "loss": 0.401, "step": 545 }, { "epoch": 1.16, "learning_rate": 5.621358322565147e-06, "loss": 0.3832, "step": 546 }, { "epoch": 1.16, "learning_rate": 5.612968847169371e-06, "loss": 0.3816, "step": 547 }, { "epoch": 1.16, "learning_rate": 5.604570890044436e-06, "loss": 0.384, "step": 548 }, { "epoch": 1.16, "learning_rate": 5.596164495350648e-06, "loss": 0.4038, "step": 549 }, { "epoch": 1.17, "learning_rate": 5.5877497072926845e-06, "loss": 0.4314, "step": 550 }, { "epoch": 1.17, "learning_rate": 5.5793265701193534e-06, "loss": 0.3462, "step": 551 }, { "epoch": 1.17, "learning_rate": 5.570895128123369e-06, "loss": 0.3897, "step": 552 }, { "epoch": 1.17, "learning_rate": 5.562455425641117e-06, "loss": 0.3536, "step": 553 }, { "epoch": 1.17, "learning_rate": 5.554007507052419e-06, "loss": 0.3527, "step": 554 }, { "epoch": 1.18, "learning_rate": 5.545551416780303e-06, "loss": 0.3505, "step": 555 }, { "epoch": 1.18, "learning_rate": 5.537087199290763e-06, "loss": 0.3339, "step": 556 }, { "epoch": 1.18, "learning_rate": 5.528614899092534e-06, "loss": 0.4514, "step": 557 }, { "epoch": 1.18, "learning_rate": 5.520134560736851e-06, "loss": 0.3611, "step": 558 }, { "epoch": 1.19, "learning_rate": 5.511646228817219e-06, "loss": 0.4345, "step": 559 }, { "epoch": 1.19, "learning_rate": 5.503149947969175e-06, "loss": 0.3351, "step": 560 }, { "epoch": 1.19, "learning_rate": 5.4946457628700575e-06, "loss": 0.3718, "step": 561 }, { "epoch": 1.19, "learning_rate": 5.486133718238768e-06, "loss": 0.3347, "step": 562 }, { "epoch": 1.19, "learning_rate": 5.477613858835535e-06, "loss": 0.3693, "step": 563 }, { "epoch": 1.2, "learning_rate": 5.4690862294616836e-06, "loss": 0.3756, "step": 564 }, { "epoch": 1.2, "learning_rate": 5.460550874959397e-06, "loss": 0.3475, "step": 565 }, { "epoch": 1.2, "learning_rate": 5.452007840211478e-06, "loss": 0.3827, "step": 566 }, { "epoch": 1.2, "learning_rate": 5.4434571701411164e-06, "loss": 0.3568, "step": 567 }, { "epoch": 1.2, "learning_rate": 5.4348989097116555e-06, "loss": 0.3652, "step": 568 }, { "epoch": 1.21, "learning_rate": 5.426333103926346e-06, "loss": 0.4602, "step": 569 }, { "epoch": 1.21, "learning_rate": 5.417759797828122e-06, "loss": 0.2827, "step": 570 }, { "epoch": 1.21, "learning_rate": 5.409179036499354e-06, "loss": 0.3609, "step": 571 }, { "epoch": 1.21, "learning_rate": 5.400590865061616e-06, "loss": 0.3534, "step": 572 }, { "epoch": 1.22, "learning_rate": 5.391995328675447e-06, "loss": 0.3434, "step": 573 }, { "epoch": 1.22, "learning_rate": 5.383392472540118e-06, "loss": 0.4009, "step": 574 }, { "epoch": 1.22, "learning_rate": 5.374782341893383e-06, "loss": 0.359, "step": 575 }, { "epoch": 1.22, "learning_rate": 5.366164982011259e-06, "loss": 0.3613, "step": 576 }, { "epoch": 1.22, "learning_rate": 5.357540438207769e-06, "loss": 0.4756, "step": 577 }, { "epoch": 1.23, "learning_rate": 5.348908755834716e-06, "loss": 0.3476, "step": 578 }, { "epoch": 1.23, "learning_rate": 5.34026998028144e-06, "loss": 0.3277, "step": 579 }, { "epoch": 1.23, "learning_rate": 5.3316241569745824e-06, "loss": 0.3651, "step": 580 }, { "epoch": 1.23, "learning_rate": 5.322971331377841e-06, "loss": 0.3432, "step": 581 }, { "epoch": 1.23, "learning_rate": 5.314311548991738e-06, "loss": 0.4095, "step": 582 }, { "epoch": 1.24, "learning_rate": 5.305644855353377e-06, "loss": 0.397, "step": 583 }, { "epoch": 1.24, "learning_rate": 5.296971296036203e-06, "loss": 0.3919, "step": 584 }, { "epoch": 1.24, "learning_rate": 5.288290916649765e-06, "loss": 0.3526, "step": 585 }, { "epoch": 1.24, "learning_rate": 5.279603762839474e-06, "loss": 0.3367, "step": 586 }, { "epoch": 1.24, "learning_rate": 5.270909880286365e-06, "loss": 0.4198, "step": 587 }, { "epoch": 1.25, "learning_rate": 5.262209314706856e-06, "loss": 0.3373, "step": 588 }, { "epoch": 1.25, "learning_rate": 5.253502111852505e-06, "loss": 0.3915, "step": 589 }, { "epoch": 1.25, "learning_rate": 5.244788317509775e-06, "loss": 0.4185, "step": 590 }, { "epoch": 1.25, "learning_rate": 5.236067977499789e-06, "loss": 0.3949, "step": 591 }, { "epoch": 1.26, "learning_rate": 5.227341137678091e-06, "loss": 0.4002, "step": 592 }, { "epoch": 1.26, "learning_rate": 5.2186078439344e-06, "loss": 0.3976, "step": 593 }, { "epoch": 1.26, "learning_rate": 5.209868142192378e-06, "loss": 0.3462, "step": 594 }, { "epoch": 1.26, "learning_rate": 5.201122078409378e-06, "loss": 0.3877, "step": 595 }, { "epoch": 1.26, "learning_rate": 5.192369698576213e-06, "loss": 0.3644, "step": 596 }, { "epoch": 1.27, "learning_rate": 5.183611048716906e-06, "loss": 0.4436, "step": 597 }, { "epoch": 1.27, "learning_rate": 5.174846174888447e-06, "loss": 0.4494, "step": 598 }, { "epoch": 1.27, "learning_rate": 5.166075123180562e-06, "loss": 0.3041, "step": 599 }, { "epoch": 1.27, "learning_rate": 5.15729793971546e-06, "loss": 0.3415, "step": 600 }, { "epoch": 1.27, "learning_rate": 5.148514670647587e-06, "loss": 0.3146, "step": 601 }, { "epoch": 1.28, "learning_rate": 5.1397253621634015e-06, "loss": 0.3698, "step": 602 }, { "epoch": 1.28, "learning_rate": 5.130930060481113e-06, "loss": 0.4309, "step": 603 }, { "epoch": 1.28, "learning_rate": 5.122128811850443e-06, "loss": 0.4139, "step": 604 }, { "epoch": 1.28, "learning_rate": 5.113321662552395e-06, "loss": 0.3479, "step": 605 }, { "epoch": 1.29, "learning_rate": 5.104508658898992e-06, "loss": 0.3506, "step": 606 }, { "epoch": 1.29, "learning_rate": 5.0956898472330445e-06, "loss": 0.3617, "step": 607 }, { "epoch": 1.29, "learning_rate": 5.0868652739279035e-06, "loss": 0.3378, "step": 608 }, { "epoch": 1.29, "learning_rate": 5.078034985387221e-06, "loss": 0.3692, "step": 609 }, { "epoch": 1.29, "learning_rate": 5.069199028044699e-06, "loss": 0.4453, "step": 610 }, { "epoch": 1.3, "learning_rate": 5.060357448363848e-06, "loss": 0.3917, "step": 611 }, { "epoch": 1.3, "learning_rate": 5.051510292837744e-06, "loss": 0.3321, "step": 612 }, { "epoch": 1.3, "learning_rate": 5.0426576079887865e-06, "loss": 0.4098, "step": 613 }, { "epoch": 1.3, "learning_rate": 5.033799440368446e-06, "loss": 0.3092, "step": 614 }, { "epoch": 1.3, "learning_rate": 5.024935836557028e-06, "loss": 0.3629, "step": 615 }, { "epoch": 1.31, "learning_rate": 5.016066843163419e-06, "loss": 0.354, "step": 616 }, { "epoch": 1.31, "learning_rate": 5.007192506824853e-06, "loss": 0.4121, "step": 617 }, { "epoch": 1.31, "learning_rate": 4.998312874206655e-06, "loss": 0.3791, "step": 618 }, { "epoch": 1.31, "learning_rate": 4.989427992002e-06, "loss": 0.4082, "step": 619 }, { "epoch": 1.31, "learning_rate": 4.980537906931671e-06, "loss": 0.418, "step": 620 }, { "epoch": 1.32, "learning_rate": 4.971642665743806e-06, "loss": 0.4362, "step": 621 }, { "epoch": 1.32, "learning_rate": 4.962742315213659e-06, "loss": 0.3922, "step": 622 }, { "epoch": 1.32, "learning_rate": 4.953836902143354e-06, "loss": 0.2981, "step": 623 }, { "epoch": 1.32, "learning_rate": 4.944926473361628e-06, "loss": 0.3489, "step": 624 }, { "epoch": 1.33, "learning_rate": 4.936011075723599e-06, "loss": 0.3961, "step": 625 }, { "epoch": 1.33, "learning_rate": 4.927090756110516e-06, "loss": 0.3934, "step": 626 }, { "epoch": 1.33, "learning_rate": 4.918165561429502e-06, "loss": 0.4478, "step": 627 }, { "epoch": 1.33, "learning_rate": 4.909235538613321e-06, "loss": 0.4854, "step": 628 }, { "epoch": 1.33, "learning_rate": 4.9003007346201245e-06, "loss": 0.3177, "step": 629 }, { "epoch": 1.34, "learning_rate": 4.891361196433204e-06, "loss": 0.2589, "step": 630 }, { "epoch": 1.34, "learning_rate": 4.882416971060748e-06, "loss": 0.3758, "step": 631 }, { "epoch": 1.34, "learning_rate": 4.8734681055355915e-06, "loss": 0.3793, "step": 632 }, { "epoch": 1.34, "learning_rate": 4.864514646914967e-06, "loss": 0.3236, "step": 633 }, { "epoch": 1.34, "learning_rate": 4.855556642280264e-06, "loss": 0.3848, "step": 634 }, { "epoch": 1.35, "learning_rate": 4.8465941387367755e-06, "loss": 0.4049, "step": 635 }, { "epoch": 1.35, "learning_rate": 4.837627183413449e-06, "loss": 0.3364, "step": 636 }, { "epoch": 1.35, "learning_rate": 4.828655823462645e-06, "loss": 0.3589, "step": 637 }, { "epoch": 1.35, "learning_rate": 4.819680106059883e-06, "loss": 0.3804, "step": 638 }, { "epoch": 1.36, "learning_rate": 4.8107000784035985e-06, "loss": 0.3914, "step": 639 }, { "epoch": 1.36, "learning_rate": 4.8017157877148915e-06, "loss": 0.2931, "step": 640 }, { "epoch": 1.36, "learning_rate": 4.792727281237277e-06, "loss": 0.3607, "step": 641 }, { "epoch": 1.36, "learning_rate": 4.783734606236439e-06, "loss": 0.2696, "step": 642 }, { "epoch": 1.36, "learning_rate": 4.774737809999986e-06, "loss": 0.3975, "step": 643 }, { "epoch": 1.37, "learning_rate": 4.765736939837192e-06, "loss": 0.3786, "step": 644 }, { "epoch": 1.37, "learning_rate": 4.756732043078756e-06, "loss": 0.3759, "step": 645 }, { "epoch": 1.37, "learning_rate": 4.7477231670765525e-06, "loss": 0.3361, "step": 646 }, { "epoch": 1.37, "learning_rate": 4.738710359203374e-06, "loss": 0.3457, "step": 647 }, { "epoch": 1.37, "learning_rate": 4.729693666852698e-06, "loss": 0.371, "step": 648 }, { "epoch": 1.38, "learning_rate": 4.720673137438425e-06, "loss": 0.3394, "step": 649 }, { "epoch": 1.38, "learning_rate": 4.711648818394626e-06, "loss": 0.3223, "step": 650 }, { "epoch": 1.38, "learning_rate": 4.702620757175308e-06, "loss": 0.3103, "step": 651 }, { "epoch": 1.38, "learning_rate": 4.693589001254154e-06, "loss": 0.3741, "step": 652 }, { "epoch": 1.38, "learning_rate": 4.684553598124272e-06, "loss": 0.3386, "step": 653 }, { "epoch": 1.39, "learning_rate": 4.675514595297952e-06, "loss": 0.3359, "step": 654 }, { "epoch": 1.39, "learning_rate": 4.666472040306414e-06, "loss": 0.4346, "step": 655 }, { "epoch": 1.39, "learning_rate": 4.65742598069955e-06, "loss": 0.4029, "step": 656 }, { "epoch": 1.39, "learning_rate": 4.648376464045691e-06, "loss": 0.4228, "step": 657 }, { "epoch": 1.4, "learning_rate": 4.639323537931338e-06, "loss": 0.4007, "step": 658 }, { "epoch": 1.4, "learning_rate": 4.630267249960926e-06, "loss": 0.4058, "step": 659 }, { "epoch": 1.4, "learning_rate": 4.621207647756565e-06, "loss": 0.3582, "step": 660 }, { "epoch": 1.4, "learning_rate": 4.612144778957794e-06, "loss": 0.372, "step": 661 }, { "epoch": 1.4, "learning_rate": 4.60307869122133e-06, "loss": 0.4415, "step": 662 }, { "epoch": 1.41, "learning_rate": 4.5940094322208154e-06, "loss": 0.2884, "step": 663 }, { "epoch": 1.41, "learning_rate": 4.584937049646567e-06, "loss": 0.3424, "step": 664 }, { "epoch": 1.41, "learning_rate": 4.575861591205333e-06, "loss": 0.3819, "step": 665 }, { "epoch": 1.41, "learning_rate": 4.566783104620028e-06, "loss": 0.3278, "step": 666 }, { "epoch": 1.41, "learning_rate": 4.557701637629496e-06, "loss": 0.2786, "step": 667 }, { "epoch": 1.42, "learning_rate": 4.548617237988248e-06, "loss": 0.3874, "step": 668 }, { "epoch": 1.42, "learning_rate": 4.539529953466223e-06, "loss": 0.3782, "step": 669 }, { "epoch": 1.42, "learning_rate": 4.530439831848524e-06, "loss": 0.4174, "step": 670 }, { "epoch": 1.42, "learning_rate": 4.5213469209351745e-06, "loss": 0.3274, "step": 671 }, { "epoch": 1.43, "learning_rate": 4.512251268540868e-06, "loss": 0.3762, "step": 672 }, { "epoch": 1.43, "learning_rate": 4.50315292249471e-06, "loss": 0.4249, "step": 673 }, { "epoch": 1.43, "learning_rate": 4.494051930639972e-06, "loss": 0.4217, "step": 674 }, { "epoch": 1.43, "learning_rate": 4.484948340833841e-06, "loss": 0.2993, "step": 675 }, { "epoch": 1.43, "learning_rate": 4.47584220094716e-06, "loss": 0.3597, "step": 676 }, { "epoch": 1.44, "learning_rate": 4.466733558864185e-06, "loss": 0.2738, "step": 677 }, { "epoch": 1.44, "learning_rate": 4.457622462482333e-06, "loss": 0.3443, "step": 678 }, { "epoch": 1.44, "learning_rate": 4.4485089597119175e-06, "loss": 0.3809, "step": 679 }, { "epoch": 1.44, "learning_rate": 4.439393098475914e-06, "loss": 0.3003, "step": 680 }, { "epoch": 1.44, "learning_rate": 4.430274926709698e-06, "loss": 0.3801, "step": 681 }, { "epoch": 1.45, "learning_rate": 4.421154492360791e-06, "loss": 0.3748, "step": 682 }, { "epoch": 1.45, "learning_rate": 4.412031843388617e-06, "loss": 0.2902, "step": 683 }, { "epoch": 1.45, "learning_rate": 4.402907027764245e-06, "loss": 0.3584, "step": 684 }, { "epoch": 1.45, "learning_rate": 4.393780093470134e-06, "loss": 0.418, "step": 685 }, { "epoch": 1.45, "learning_rate": 4.384651088499886e-06, "loss": 0.3436, "step": 686 }, { "epoch": 1.46, "learning_rate": 4.375520060857993e-06, "loss": 0.3171, "step": 687 }, { "epoch": 1.46, "learning_rate": 4.366387058559579e-06, "loss": 0.4112, "step": 688 }, { "epoch": 1.46, "learning_rate": 4.357252129630158e-06, "loss": 0.3329, "step": 689 }, { "epoch": 1.46, "learning_rate": 4.348115322105368e-06, "loss": 0.3829, "step": 690 }, { "epoch": 1.47, "learning_rate": 4.33897668403073e-06, "loss": 0.3473, "step": 691 }, { "epoch": 1.47, "learning_rate": 4.32983626346139e-06, "loss": 0.3749, "step": 692 }, { "epoch": 1.47, "learning_rate": 4.320694108461867e-06, "loss": 0.3507, "step": 693 }, { "epoch": 1.47, "learning_rate": 4.3115502671058e-06, "loss": 0.3414, "step": 694 }, { "epoch": 1.47, "learning_rate": 4.3024047874756964e-06, "loss": 0.3379, "step": 695 }, { "epoch": 1.48, "learning_rate": 4.293257717662677e-06, "loss": 0.2809, "step": 696 }, { "epoch": 1.48, "learning_rate": 4.284109105766226e-06, "loss": 0.3585, "step": 697 }, { "epoch": 1.48, "learning_rate": 4.274958999893936e-06, "loss": 0.4589, "step": 698 }, { "epoch": 1.48, "learning_rate": 4.265807448161257e-06, "loss": 0.4205, "step": 699 }, { "epoch": 1.48, "learning_rate": 4.2566544986912375e-06, "loss": 0.3545, "step": 700 }, { "epoch": 1.49, "learning_rate": 4.2475001996142835e-06, "loss": 0.3821, "step": 701 }, { "epoch": 1.49, "learning_rate": 4.238344599067889e-06, "loss": 0.3258, "step": 702 }, { "epoch": 1.49, "learning_rate": 4.229187745196399e-06, "loss": 0.3117, "step": 703 }, { "epoch": 1.49, "learning_rate": 4.220029686150747e-06, "loss": 0.4029, "step": 704 }, { "epoch": 1.5, "learning_rate": 4.2108704700881994e-06, "loss": 0.3934, "step": 705 }, { "epoch": 1.5, "learning_rate": 4.2017101451721135e-06, "loss": 0.3817, "step": 706 }, { "epoch": 1.5, "learning_rate": 4.192548759571674e-06, "loss": 0.3913, "step": 707 }, { "epoch": 1.5, "learning_rate": 4.183386361461642e-06, "loss": 0.3775, "step": 708 }, { "epoch": 1.5, "learning_rate": 4.174222999022106e-06, "loss": 0.331, "step": 709 }, { "epoch": 1.51, "learning_rate": 4.165058720438224e-06, "loss": 0.3255, "step": 710 }, { "epoch": 1.51, "learning_rate": 4.155893573899969e-06, "loss": 0.3321, "step": 711 }, { "epoch": 1.51, "learning_rate": 4.146727607601883e-06, "loss": 0.3433, "step": 712 }, { "epoch": 1.51, "learning_rate": 4.137560869742815e-06, "loss": 0.3257, "step": 713 }, { "epoch": 1.51, "learning_rate": 4.128393408525673e-06, "loss": 0.3376, "step": 714 }, { "epoch": 1.52, "learning_rate": 4.119225272157166e-06, "loss": 0.3852, "step": 715 }, { "epoch": 1.52, "learning_rate": 4.110056508847557e-06, "loss": 0.3837, "step": 716 }, { "epoch": 1.52, "learning_rate": 4.100887166810404e-06, "loss": 0.3367, "step": 717 }, { "epoch": 1.52, "learning_rate": 4.091717294262307e-06, "loss": 0.3386, "step": 718 }, { "epoch": 1.52, "learning_rate": 4.082546939422658e-06, "loss": 0.3543, "step": 719 }, { "epoch": 1.53, "learning_rate": 4.073376150513383e-06, "loss": 0.3475, "step": 720 }, { "epoch": 1.53, "learning_rate": 4.064204975758693e-06, "loss": 0.376, "step": 721 }, { "epoch": 1.53, "learning_rate": 4.0550334633848275e-06, "loss": 0.3645, "step": 722 }, { "epoch": 1.53, "learning_rate": 4.0458616616197954e-06, "loss": 0.3692, "step": 723 }, { "epoch": 1.54, "learning_rate": 4.036689618693138e-06, "loss": 0.3123, "step": 724 }, { "epoch": 1.54, "learning_rate": 4.027517382835656e-06, "loss": 0.3389, "step": 725 }, { "epoch": 1.54, "learning_rate": 4.018345002279168e-06, "loss": 0.3324, "step": 726 }, { "epoch": 1.54, "learning_rate": 4.009172525256254e-06, "loss": 0.3923, "step": 727 }, { "epoch": 1.54, "learning_rate": 4e-06, "loss": 0.3363, "step": 728 }, { "epoch": 1.55, "learning_rate": 3.990827474743746e-06, "loss": 0.3559, "step": 729 }, { "epoch": 1.55, "learning_rate": 3.9816549977208314e-06, "loss": 0.378, "step": 730 }, { "epoch": 1.55, "learning_rate": 3.9724826171643435e-06, "loss": 0.3215, "step": 731 }, { "epoch": 1.55, "learning_rate": 3.963310381306862e-06, "loss": 0.3831, "step": 732 }, { "epoch": 1.55, "learning_rate": 3.954138338380203e-06, "loss": 0.4419, "step": 733 }, { "epoch": 1.56, "learning_rate": 3.944966536615173e-06, "loss": 0.3942, "step": 734 }, { "epoch": 1.56, "learning_rate": 3.935795024241306e-06, "loss": 0.3829, "step": 735 }, { "epoch": 1.56, "learning_rate": 3.926623849486618e-06, "loss": 0.4076, "step": 736 }, { "epoch": 1.56, "learning_rate": 3.9174530605773425e-06, "loss": 0.3441, "step": 737 }, { "epoch": 1.57, "learning_rate": 3.9082827057376935e-06, "loss": 0.4521, "step": 738 }, { "epoch": 1.57, "learning_rate": 3.899112833189598e-06, "loss": 0.3162, "step": 739 }, { "epoch": 1.57, "learning_rate": 3.889943491152442e-06, "loss": 0.3672, "step": 740 }, { "epoch": 1.57, "learning_rate": 3.880774727842834e-06, "loss": 0.3228, "step": 741 }, { "epoch": 1.57, "learning_rate": 3.8716065914743285e-06, "loss": 0.3278, "step": 742 }, { "epoch": 1.58, "learning_rate": 3.862439130257184e-06, "loss": 0.3315, "step": 743 }, { "epoch": 1.58, "learning_rate": 3.853272392398117e-06, "loss": 0.3457, "step": 744 }, { "epoch": 1.58, "learning_rate": 3.844106426100031e-06, "loss": 0.3062, "step": 745 }, { "epoch": 1.58, "learning_rate": 3.834941279561775e-06, "loss": 0.4032, "step": 746 }, { "epoch": 1.58, "learning_rate": 3.825777000977894e-06, "loss": 0.334, "step": 747 }, { "epoch": 1.59, "learning_rate": 3.816613638538359e-06, "loss": 0.4068, "step": 748 }, { "epoch": 1.59, "learning_rate": 3.807451240428327e-06, "loss": 0.3049, "step": 749 }, { "epoch": 1.59, "learning_rate": 3.7982898548278866e-06, "loss": 0.3583, "step": 750 }, { "epoch": 1.59, "learning_rate": 3.789129529911801e-06, "loss": 0.3458, "step": 751 }, { "epoch": 1.59, "learning_rate": 3.7799703138492543e-06, "loss": 0.3246, "step": 752 }, { "epoch": 1.6, "learning_rate": 3.7708122548036006e-06, "loss": 0.3503, "step": 753 }, { "epoch": 1.6, "learning_rate": 3.7616554009321105e-06, "loss": 0.3589, "step": 754 }, { "epoch": 1.6, "learning_rate": 3.7524998003857174e-06, "loss": 0.3894, "step": 755 }, { "epoch": 1.6, "learning_rate": 3.7433455013087617e-06, "loss": 0.3699, "step": 756 }, { "epoch": 1.61, "learning_rate": 3.7341925518387434e-06, "loss": 0.3611, "step": 757 }, { "epoch": 1.61, "learning_rate": 3.7250410001060638e-06, "loss": 0.3684, "step": 758 }, { "epoch": 1.61, "learning_rate": 3.715890894233774e-06, "loss": 0.3784, "step": 759 }, { "epoch": 1.61, "learning_rate": 3.7067422823373235e-06, "loss": 0.3689, "step": 760 }, { "epoch": 1.61, "learning_rate": 3.6975952125243045e-06, "loss": 0.3894, "step": 761 }, { "epoch": 1.62, "learning_rate": 3.688449732894201e-06, "loss": 0.4219, "step": 762 }, { "epoch": 1.62, "learning_rate": 3.6793058915381323e-06, "loss": 0.4097, "step": 763 }, { "epoch": 1.62, "learning_rate": 3.6701637365386094e-06, "loss": 0.3849, "step": 764 }, { "epoch": 1.62, "learning_rate": 3.6610233159692706e-06, "loss": 0.3241, "step": 765 }, { "epoch": 1.62, "learning_rate": 3.6518846778946315e-06, "loss": 0.3849, "step": 766 }, { "epoch": 1.63, "learning_rate": 3.6427478703698418e-06, "loss": 0.424, "step": 767 }, { "epoch": 1.63, "learning_rate": 3.6336129414404208e-06, "loss": 0.3193, "step": 768 }, { "epoch": 1.63, "learning_rate": 3.6244799391420067e-06, "loss": 0.4062, "step": 769 }, { "epoch": 1.63, "learning_rate": 3.6153489115001145e-06, "loss": 0.337, "step": 770 }, { "epoch": 1.63, "learning_rate": 3.606219906529867e-06, "loss": 0.3086, "step": 771 }, { "epoch": 1.64, "learning_rate": 3.5970929722357544e-06, "loss": 0.3668, "step": 772 }, { "epoch": 1.64, "learning_rate": 3.5879681566113828e-06, "loss": 0.3461, "step": 773 }, { "epoch": 1.64, "learning_rate": 3.5788455076392096e-06, "loss": 0.3184, "step": 774 }, { "epoch": 1.64, "learning_rate": 3.5697250732903033e-06, "loss": 0.3858, "step": 775 }, { "epoch": 1.65, "learning_rate": 3.5606069015240857e-06, "loss": 0.4107, "step": 776 }, { "epoch": 1.65, "learning_rate": 3.5514910402880826e-06, "loss": 0.3741, "step": 777 }, { "epoch": 1.65, "learning_rate": 3.542377537517668e-06, "loss": 0.3861, "step": 778 }, { "epoch": 1.65, "learning_rate": 3.533266441135814e-06, "loss": 0.2995, "step": 779 }, { "epoch": 1.65, "learning_rate": 3.5241577990528404e-06, "loss": 0.409, "step": 780 }, { "epoch": 1.66, "learning_rate": 3.5150516591661604e-06, "loss": 0.4122, "step": 781 }, { "epoch": 1.66, "learning_rate": 3.505948069360028e-06, "loss": 0.3995, "step": 782 }, { "epoch": 1.66, "learning_rate": 3.496847077505291e-06, "loss": 0.3397, "step": 783 }, { "epoch": 1.66, "learning_rate": 3.487748731459133e-06, "loss": 0.3801, "step": 784 }, { "epoch": 1.66, "learning_rate": 3.478653079064825e-06, "loss": 0.3558, "step": 785 }, { "epoch": 1.67, "learning_rate": 3.4695601681514763e-06, "loss": 0.3934, "step": 786 }, { "epoch": 1.67, "learning_rate": 3.460470046533777e-06, "loss": 0.3421, "step": 787 }, { "epoch": 1.67, "learning_rate": 3.4513827620117526e-06, "loss": 0.3771, "step": 788 }, { "epoch": 1.67, "learning_rate": 3.4422983623705043e-06, "loss": 0.3369, "step": 789 }, { "epoch": 1.68, "learning_rate": 3.4332168953799718e-06, "loss": 0.3816, "step": 790 }, { "epoch": 1.68, "learning_rate": 3.4241384087946685e-06, "loss": 0.3522, "step": 791 }, { "epoch": 1.68, "learning_rate": 3.4150629503534315e-06, "loss": 0.331, "step": 792 }, { "epoch": 1.68, "learning_rate": 3.405990567779185e-06, "loss": 0.368, "step": 793 }, { "epoch": 1.68, "learning_rate": 3.396921308778671e-06, "loss": 0.3653, "step": 794 }, { "epoch": 1.69, "learning_rate": 3.387855221042205e-06, "loss": 0.3658, "step": 795 }, { "epoch": 1.69, "learning_rate": 3.3787923522434355e-06, "loss": 0.3568, "step": 796 }, { "epoch": 1.69, "learning_rate": 3.3697327500390746e-06, "loss": 0.3296, "step": 797 }, { "epoch": 1.69, "learning_rate": 3.3606764620686607e-06, "loss": 0.3389, "step": 798 }, { "epoch": 1.69, "learning_rate": 3.3516235359543094e-06, "loss": 0.3488, "step": 799 }, { "epoch": 1.7, "learning_rate": 3.34257401930045e-06, "loss": 0.4002, "step": 800 }, { "epoch": 1.7, "learning_rate": 3.3335279596935877e-06, "loss": 0.3457, "step": 801 }, { "epoch": 1.7, "learning_rate": 3.3244854047020473e-06, "loss": 0.3322, "step": 802 }, { "epoch": 1.7, "learning_rate": 3.3154464018757276e-06, "loss": 0.3996, "step": 803 }, { "epoch": 1.7, "learning_rate": 3.3064109987458465e-06, "loss": 0.3192, "step": 804 }, { "epoch": 1.71, "learning_rate": 3.297379242824691e-06, "loss": 0.3602, "step": 805 }, { "epoch": 1.71, "learning_rate": 3.2883511816053736e-06, "loss": 0.4305, "step": 806 }, { "epoch": 1.71, "learning_rate": 3.279326862561576e-06, "loss": 0.323, "step": 807 }, { "epoch": 1.71, "learning_rate": 3.2703063331473006e-06, "loss": 0.3759, "step": 808 }, { "epoch": 1.72, "learning_rate": 3.2612896407966253e-06, "loss": 0.3099, "step": 809 }, { "epoch": 1.72, "learning_rate": 3.2522768329234493e-06, "loss": 0.3237, "step": 810 }, { "epoch": 1.72, "learning_rate": 3.2432679569212438e-06, "loss": 0.3985, "step": 811 }, { "epoch": 1.72, "learning_rate": 3.234263060162808e-06, "loss": 0.3395, "step": 812 }, { "epoch": 1.72, "learning_rate": 3.225262190000014e-06, "loss": 0.314, "step": 813 }, { "epoch": 1.73, "learning_rate": 3.2162653937635614e-06, "loss": 0.3553, "step": 814 }, { "epoch": 1.73, "learning_rate": 3.2072727187627236e-06, "loss": 0.3595, "step": 815 }, { "epoch": 1.73, "learning_rate": 3.1982842122851086e-06, "loss": 0.3612, "step": 816 }, { "epoch": 1.73, "learning_rate": 3.189299921596402e-06, "loss": 0.3879, "step": 817 }, { "epoch": 1.73, "learning_rate": 3.1803198939401163e-06, "loss": 0.3802, "step": 818 }, { "epoch": 1.74, "learning_rate": 3.171344176537355e-06, "loss": 0.3881, "step": 819 }, { "epoch": 1.74, "learning_rate": 3.1623728165865513e-06, "loss": 0.3807, "step": 820 }, { "epoch": 1.74, "learning_rate": 3.153405861263224e-06, "loss": 0.3748, "step": 821 }, { "epoch": 1.74, "learning_rate": 3.1444433577197353e-06, "loss": 0.3725, "step": 822 }, { "epoch": 1.75, "learning_rate": 3.1354853530850332e-06, "loss": 0.3475, "step": 823 }, { "epoch": 1.75, "learning_rate": 3.126531894464408e-06, "loss": 0.3698, "step": 824 }, { "epoch": 1.75, "learning_rate": 3.1175830289392523e-06, "loss": 0.2918, "step": 825 }, { "epoch": 1.75, "learning_rate": 3.1086388035667964e-06, "loss": 0.3248, "step": 826 }, { "epoch": 1.75, "learning_rate": 3.099699265379877e-06, "loss": 0.3625, "step": 827 }, { "epoch": 1.76, "learning_rate": 3.090764461386679e-06, "loss": 0.3704, "step": 828 }, { "epoch": 1.76, "learning_rate": 3.0818344385704984e-06, "loss": 0.337, "step": 829 }, { "epoch": 1.76, "learning_rate": 3.0729092438894846e-06, "loss": 0.3518, "step": 830 }, { "epoch": 1.76, "learning_rate": 3.0639889242763994e-06, "loss": 0.3978, "step": 831 }, { "epoch": 1.76, "learning_rate": 3.0550735266383724e-06, "loss": 0.339, "step": 832 }, { "epoch": 1.77, "learning_rate": 3.0461630978566472e-06, "loss": 0.3159, "step": 833 }, { "epoch": 1.77, "learning_rate": 3.0372576847863404e-06, "loss": 0.3974, "step": 834 }, { "epoch": 1.77, "learning_rate": 3.028357334256195e-06, "loss": 0.3294, "step": 835 }, { "epoch": 1.77, "learning_rate": 3.0194620930683307e-06, "loss": 0.387, "step": 836 }, { "epoch": 1.77, "learning_rate": 3.0105720079980003e-06, "loss": 0.3634, "step": 837 }, { "epoch": 1.78, "learning_rate": 3.0016871257933452e-06, "loss": 0.3874, "step": 838 }, { "epoch": 1.78, "learning_rate": 2.992807493175147e-06, "loss": 0.3841, "step": 839 }, { "epoch": 1.78, "learning_rate": 2.9839331568365818e-06, "loss": 0.3103, "step": 840 }, { "epoch": 1.78, "learning_rate": 2.9750641634429726e-06, "loss": 0.2763, "step": 841 }, { "epoch": 1.79, "learning_rate": 2.9662005596315542e-06, "loss": 0.3447, "step": 842 }, { "epoch": 1.79, "learning_rate": 2.9573423920112152e-06, "loss": 0.3586, "step": 843 }, { "epoch": 1.79, "learning_rate": 2.9484897071622554e-06, "loss": 0.3354, "step": 844 }, { "epoch": 1.79, "learning_rate": 2.9396425516361523e-06, "loss": 0.3302, "step": 845 }, { "epoch": 1.79, "learning_rate": 2.9308009719553026e-06, "loss": 0.3501, "step": 846 }, { "epoch": 1.8, "learning_rate": 2.9219650146127776e-06, "loss": 0.3618, "step": 847 }, { "epoch": 1.8, "learning_rate": 2.913134726072096e-06, "loss": 0.3726, "step": 848 }, { "epoch": 1.8, "learning_rate": 2.9043101527669564e-06, "loss": 0.3413, "step": 849 }, { "epoch": 1.8, "learning_rate": 2.8954913411010077e-06, "loss": 0.3583, "step": 850 }, { "epoch": 1.8, "learning_rate": 2.8866783374476047e-06, "loss": 0.348, "step": 851 }, { "epoch": 1.81, "learning_rate": 2.877871188149556e-06, "loss": 0.3331, "step": 852 }, { "epoch": 1.81, "learning_rate": 2.869069939518887e-06, "loss": 0.3623, "step": 853 }, { "epoch": 1.81, "learning_rate": 2.860274637836598e-06, "loss": 0.34, "step": 854 }, { "epoch": 1.81, "learning_rate": 2.8514853293524125e-06, "loss": 0.3579, "step": 855 }, { "epoch": 1.82, "learning_rate": 2.842702060284542e-06, "loss": 0.3761, "step": 856 }, { "epoch": 1.82, "learning_rate": 2.833924876819437e-06, "loss": 0.3117, "step": 857 }, { "epoch": 1.82, "learning_rate": 2.8251538251115527e-06, "loss": 0.2625, "step": 858 }, { "epoch": 1.82, "learning_rate": 2.816388951283095e-06, "loss": 0.3593, "step": 859 }, { "epoch": 1.82, "learning_rate": 2.807630301423787e-06, "loss": 0.3543, "step": 860 }, { "epoch": 1.83, "learning_rate": 2.798877921590622e-06, "loss": 0.3238, "step": 861 }, { "epoch": 1.83, "learning_rate": 2.790131857807623e-06, "loss": 0.3292, "step": 862 }, { "epoch": 1.83, "learning_rate": 2.7813921560656e-06, "loss": 0.3375, "step": 863 }, { "epoch": 1.83, "learning_rate": 2.7726588623219096e-06, "loss": 0.3944, "step": 864 }, { "epoch": 1.83, "learning_rate": 2.7639320225002105e-06, "loss": 0.3362, "step": 865 }, { "epoch": 1.84, "learning_rate": 2.7552116824902243e-06, "loss": 0.3563, "step": 866 }, { "epoch": 1.84, "learning_rate": 2.7464978881474945e-06, "loss": 0.3778, "step": 867 }, { "epoch": 1.84, "learning_rate": 2.737790685293145e-06, "loss": 0.4274, "step": 868 }, { "epoch": 1.84, "learning_rate": 2.729090119713636e-06, "loss": 0.2822, "step": 869 }, { "epoch": 1.84, "learning_rate": 2.720396237160526e-06, "loss": 0.3054, "step": 870 }, { "epoch": 1.85, "learning_rate": 2.711709083350235e-06, "loss": 0.3469, "step": 871 }, { "epoch": 1.85, "learning_rate": 2.7030287039637975e-06, "loss": 0.3622, "step": 872 }, { "epoch": 1.85, "learning_rate": 2.694355144646622e-06, "loss": 0.3853, "step": 873 }, { "epoch": 1.85, "learning_rate": 2.685688451008262e-06, "loss": 0.3527, "step": 874 }, { "epoch": 1.86, "learning_rate": 2.6770286686221594e-06, "loss": 0.3539, "step": 875 }, { "epoch": 1.86, "learning_rate": 2.6683758430254172e-06, "loss": 0.3335, "step": 876 }, { "epoch": 1.86, "learning_rate": 2.65973001971856e-06, "loss": 0.2477, "step": 877 }, { "epoch": 1.86, "learning_rate": 2.6510912441652853e-06, "loss": 0.3791, "step": 878 }, { "epoch": 1.86, "learning_rate": 2.6424595617922306e-06, "loss": 0.3376, "step": 879 }, { "epoch": 1.87, "learning_rate": 2.6338350179887415e-06, "loss": 0.3444, "step": 880 }, { "epoch": 1.87, "learning_rate": 2.6252176581066166e-06, "loss": 0.2822, "step": 881 }, { "epoch": 1.87, "learning_rate": 2.6166075274598838e-06, "loss": 0.377, "step": 882 }, { "epoch": 1.87, "learning_rate": 2.6080046713245525e-06, "loss": 0.2903, "step": 883 }, { "epoch": 1.87, "learning_rate": 2.5994091349383845e-06, "loss": 0.3673, "step": 884 }, { "epoch": 1.88, "learning_rate": 2.590820963500646e-06, "loss": 0.4123, "step": 885 }, { "epoch": 1.88, "learning_rate": 2.582240202171877e-06, "loss": 0.2797, "step": 886 }, { "epoch": 1.88, "learning_rate": 2.5736668960736535e-06, "loss": 0.3671, "step": 887 }, { "epoch": 1.88, "learning_rate": 2.5651010902883454e-06, "loss": 0.341, "step": 888 }, { "epoch": 1.89, "learning_rate": 2.556542829858883e-06, "loss": 0.3077, "step": 889 }, { "epoch": 1.89, "learning_rate": 2.5479921597885225e-06, "loss": 0.3148, "step": 890 }, { "epoch": 1.89, "learning_rate": 2.539449125040603e-06, "loss": 0.3172, "step": 891 }, { "epoch": 1.89, "learning_rate": 2.5309137705383152e-06, "loss": 0.2691, "step": 892 }, { "epoch": 1.89, "learning_rate": 2.5223861411644644e-06, "loss": 0.3207, "step": 893 }, { "epoch": 1.9, "learning_rate": 2.513866281761232e-06, "loss": 0.2953, "step": 894 }, { "epoch": 1.9, "learning_rate": 2.5053542371299426e-06, "loss": 0.3313, "step": 895 }, { "epoch": 1.9, "learning_rate": 2.4968500520308242e-06, "loss": 0.3013, "step": 896 }, { "epoch": 1.9, "learning_rate": 2.4883537711827807e-06, "loss": 0.3486, "step": 897 }, { "epoch": 1.9, "learning_rate": 2.47986543926315e-06, "loss": 0.3292, "step": 898 }, { "epoch": 1.91, "learning_rate": 2.471385100907466e-06, "loss": 0.3666, "step": 899 }, { "epoch": 1.91, "learning_rate": 2.4629128007092376e-06, "loss": 0.3048, "step": 900 }, { "epoch": 1.91, "learning_rate": 2.4544485832196982e-06, "loss": 0.343, "step": 901 }, { "epoch": 1.91, "learning_rate": 2.44599249294758e-06, "loss": 0.2941, "step": 902 }, { "epoch": 1.91, "learning_rate": 2.437544574358883e-06, "loss": 0.3552, "step": 903 }, { "epoch": 1.92, "learning_rate": 2.429104871876632e-06, "loss": 0.3379, "step": 904 }, { "epoch": 1.92, "learning_rate": 2.4206734298806462e-06, "loss": 0.3651, "step": 905 }, { "epoch": 1.92, "learning_rate": 2.4122502927073164e-06, "loss": 0.3023, "step": 906 }, { "epoch": 1.92, "learning_rate": 2.4038355046493513e-06, "loss": 0.3447, "step": 907 }, { "epoch": 1.93, "learning_rate": 2.395429109955565e-06, "loss": 0.354, "step": 908 }, { "epoch": 1.93, "learning_rate": 2.38703115283063e-06, "loss": 0.3267, "step": 909 }, { "epoch": 1.93, "learning_rate": 2.3786416774348534e-06, "loss": 0.3248, "step": 910 }, { "epoch": 1.93, "learning_rate": 2.3702607278839406e-06, "loss": 0.3363, "step": 911 }, { "epoch": 1.93, "learning_rate": 2.361888348248762e-06, "loss": 0.275, "step": 912 }, { "epoch": 1.94, "learning_rate": 2.353524582555128e-06, "loss": 0.3155, "step": 913 }, { "epoch": 1.94, "learning_rate": 2.3451694747835495e-06, "loss": 0.3706, "step": 914 }, { "epoch": 1.94, "learning_rate": 2.3368230688690097e-06, "loss": 0.3516, "step": 915 }, { "epoch": 1.94, "learning_rate": 2.328485408700737e-06, "loss": 0.2699, "step": 916 }, { "epoch": 1.94, "learning_rate": 2.3201565381219655e-06, "loss": 0.3673, "step": 917 }, { "epoch": 1.95, "learning_rate": 2.3118365009297143e-06, "loss": 0.2994, "step": 918 }, { "epoch": 1.95, "learning_rate": 2.303525340874552e-06, "loss": 0.3673, "step": 919 }, { "epoch": 1.95, "learning_rate": 2.2952231016603616e-06, "loss": 0.323, "step": 920 }, { "epoch": 1.95, "learning_rate": 2.2869298269441254e-06, "loss": 0.3356, "step": 921 }, { "epoch": 1.96, "learning_rate": 2.2786455603356772e-06, "loss": 0.3326, "step": 922 }, { "epoch": 1.96, "learning_rate": 2.270370345397488e-06, "loss": 0.2808, "step": 923 }, { "epoch": 1.96, "learning_rate": 2.26210422564443e-06, "loss": 0.3464, "step": 924 }, { "epoch": 1.96, "learning_rate": 2.253847244543546e-06, "loss": 0.324, "step": 925 }, { "epoch": 1.96, "learning_rate": 2.2455994455138256e-06, "loss": 0.3269, "step": 926 }, { "epoch": 1.97, "learning_rate": 2.2373608719259773e-06, "loss": 0.3471, "step": 927 }, { "epoch": 1.97, "learning_rate": 2.229131567102192e-06, "loss": 0.3528, "step": 928 }, { "epoch": 1.97, "learning_rate": 2.2209115743159264e-06, "loss": 0.3703, "step": 929 }, { "epoch": 1.97, "learning_rate": 2.2127009367916688e-06, "loss": 0.3721, "step": 930 }, { "epoch": 1.97, "learning_rate": 2.204499697704712e-06, "loss": 0.2902, "step": 931 }, { "epoch": 1.98, "learning_rate": 2.196307900180928e-06, "loss": 0.3199, "step": 932 }, { "epoch": 1.98, "learning_rate": 2.1881255872965433e-06, "loss": 0.3533, "step": 933 }, { "epoch": 1.98, "learning_rate": 2.1799528020779063e-06, "loss": 0.3212, "step": 934 }, { "epoch": 1.98, "learning_rate": 2.171789587501263e-06, "loss": 0.3083, "step": 935 }, { "epoch": 1.98, "learning_rate": 2.163635986492541e-06, "loss": 0.324, "step": 936 }, { "epoch": 1.99, "learning_rate": 2.1554920419271074e-06, "loss": 0.3425, "step": 937 }, { "epoch": 1.99, "learning_rate": 2.1473577966295502e-06, "loss": 0.3464, "step": 938 }, { "epoch": 1.99, "learning_rate": 2.1392332933734646e-06, "loss": 0.3359, "step": 939 }, { "epoch": 1.99, "learning_rate": 2.1311185748812074e-06, "loss": 0.2975, "step": 940 }, { "epoch": 2.0, "learning_rate": 2.1230136838236824e-06, "loss": 0.2978, "step": 941 }, { "epoch": 2.0, "learning_rate": 2.114918662820127e-06, "loss": 0.3034, "step": 942 }, { "epoch": 2.0, "learning_rate": 2.106833554437867e-06, "loss": 0.3515, "step": 943 }, { "epoch": 2.0, "learning_rate": 2.0987584011921027e-06, "loss": 0.2545, "step": 944 }, { "epoch": 2.0, "learning_rate": 2.0906932455456964e-06, "loss": 0.2313, "step": 945 }, { "epoch": 2.01, "learning_rate": 2.0826381299089277e-06, "loss": 0.3029, "step": 946 }, { "epoch": 2.01, "learning_rate": 2.0745930966392837e-06, "loss": 0.245, "step": 947 }, { "epoch": 2.01, "learning_rate": 2.0665581880412363e-06, "loss": 0.2897, "step": 948 }, { "epoch": 2.01, "learning_rate": 2.0585334463660185e-06, "loss": 0.3204, "step": 949 }, { "epoch": 2.01, "learning_rate": 2.050518913811394e-06, "loss": 0.249, "step": 950 }, { "epoch": 2.02, "learning_rate": 2.0425146325214492e-06, "loss": 0.3227, "step": 951 }, { "epoch": 2.02, "learning_rate": 2.034520644586363e-06, "loss": 0.3016, "step": 952 }, { "epoch": 2.02, "learning_rate": 2.0265369920421834e-06, "loss": 0.261, "step": 953 }, { "epoch": 2.02, "learning_rate": 2.0185637168706157e-06, "loss": 0.2601, "step": 954 }, { "epoch": 2.03, "learning_rate": 2.010600860998794e-06, "loss": 0.2129, "step": 955 }, { "epoch": 2.03, "learning_rate": 2.0026484662990593e-06, "loss": 0.262, "step": 956 }, { "epoch": 2.03, "learning_rate": 1.994706574588749e-06, "loss": 0.2696, "step": 957 }, { "epoch": 2.03, "learning_rate": 1.9867752276299683e-06, "loss": 0.2329, "step": 958 }, { "epoch": 2.03, "learning_rate": 1.9788544671293706e-06, "loss": 0.2549, "step": 959 }, { "epoch": 2.04, "learning_rate": 1.9709443347379467e-06, "loss": 0.2301, "step": 960 }, { "epoch": 2.04, "learning_rate": 1.9630448720507943e-06, "loss": 0.2762, "step": 961 }, { "epoch": 2.04, "learning_rate": 1.9551561206069067e-06, "loss": 0.2556, "step": 962 }, { "epoch": 2.04, "learning_rate": 1.9472781218889565e-06, "loss": 0.2915, "step": 963 }, { "epoch": 2.04, "learning_rate": 1.9394109173230665e-06, "loss": 0.3008, "step": 964 }, { "epoch": 2.05, "learning_rate": 1.931554548278604e-06, "loss": 0.2627, "step": 965 }, { "epoch": 2.05, "learning_rate": 1.923709056067958e-06, "loss": 0.258, "step": 966 }, { "epoch": 2.05, "learning_rate": 1.9158744819463186e-06, "loss": 0.2374, "step": 967 }, { "epoch": 2.05, "learning_rate": 1.9080508671114676e-06, "loss": 0.2401, "step": 968 }, { "epoch": 2.05, "learning_rate": 1.9002382527035543e-06, "loss": 0.271, "step": 969 }, { "epoch": 2.06, "learning_rate": 1.8924366798048857e-06, "loss": 0.2209, "step": 970 }, { "epoch": 2.06, "learning_rate": 1.8846461894397074e-06, "loss": 0.2643, "step": 971 }, { "epoch": 2.06, "learning_rate": 1.8768668225739842e-06, "loss": 0.25, "step": 972 }, { "epoch": 2.06, "learning_rate": 1.8690986201151938e-06, "loss": 0.2718, "step": 973 }, { "epoch": 2.07, "learning_rate": 1.8613416229121008e-06, "loss": 0.2762, "step": 974 }, { "epoch": 2.07, "learning_rate": 1.8535958717545519e-06, "loss": 0.3023, "step": 975 }, { "epoch": 2.07, "learning_rate": 1.8458614073732566e-06, "loss": 0.2677, "step": 976 }, { "epoch": 2.07, "learning_rate": 1.8381382704395692e-06, "loss": 0.2729, "step": 977 }, { "epoch": 2.07, "learning_rate": 1.830426501565283e-06, "loss": 0.3024, "step": 978 }, { "epoch": 2.08, "learning_rate": 1.822726141302414e-06, "loss": 0.2886, "step": 979 }, { "epoch": 2.08, "learning_rate": 1.8150372301429804e-06, "loss": 0.2886, "step": 980 }, { "epoch": 2.08, "learning_rate": 1.807359808518802e-06, "loss": 0.2741, "step": 981 }, { "epoch": 2.08, "learning_rate": 1.79969391680128e-06, "loss": 0.3323, "step": 982 }, { "epoch": 2.08, "learning_rate": 1.7920395953011828e-06, "loss": 0.2436, "step": 983 }, { "epoch": 2.09, "learning_rate": 1.7843968842684397e-06, "loss": 0.2593, "step": 984 }, { "epoch": 2.09, "learning_rate": 1.7767658238919298e-06, "loss": 0.2693, "step": 985 }, { "epoch": 2.09, "learning_rate": 1.7691464542992617e-06, "loss": 0.233, "step": 986 }, { "epoch": 2.09, "learning_rate": 1.7615388155565695e-06, "loss": 0.2326, "step": 987 }, { "epoch": 2.1, "learning_rate": 1.7539429476683085e-06, "loss": 0.2966, "step": 988 }, { "epoch": 2.1, "learning_rate": 1.7463588905770288e-06, "loss": 0.2695, "step": 989 }, { "epoch": 2.1, "learning_rate": 1.7387866841631747e-06, "loss": 0.2722, "step": 990 }, { "epoch": 2.1, "learning_rate": 1.7312263682448825e-06, "loss": 0.2418, "step": 991 }, { "epoch": 2.1, "learning_rate": 1.7236779825777536e-06, "loss": 0.263, "step": 992 }, { "epoch": 2.11, "learning_rate": 1.7161415668546556e-06, "loss": 0.3395, "step": 993 }, { "epoch": 2.11, "learning_rate": 1.7086171607055202e-06, "loss": 0.2792, "step": 994 }, { "epoch": 2.11, "learning_rate": 1.7011048036971198e-06, "loss": 0.2759, "step": 995 }, { "epoch": 2.11, "learning_rate": 1.6936045353328662e-06, "loss": 0.2552, "step": 996 }, { "epoch": 2.11, "learning_rate": 1.6861163950526125e-06, "loss": 0.2908, "step": 997 }, { "epoch": 2.12, "learning_rate": 1.6786404222324277e-06, "loss": 0.2961, "step": 998 }, { "epoch": 2.12, "learning_rate": 1.671176656184401e-06, "loss": 0.2575, "step": 999 }, { "epoch": 2.12, "learning_rate": 1.6637251361564345e-06, "loss": 0.2916, "step": 1000 }, { "epoch": 2.12, "learning_rate": 1.656285901332036e-06, "loss": 0.2425, "step": 1001 }, { "epoch": 2.12, "learning_rate": 1.6488589908301079e-06, "loss": 0.3184, "step": 1002 }, { "epoch": 2.13, "learning_rate": 1.6414444437047488e-06, "loss": 0.2707, "step": 1003 }, { "epoch": 2.13, "learning_rate": 1.6340422989450464e-06, "loss": 0.2639, "step": 1004 }, { "epoch": 2.13, "learning_rate": 1.6266525954748663e-06, "loss": 0.2402, "step": 1005 }, { "epoch": 2.13, "learning_rate": 1.6192753721526558e-06, "loss": 0.2914, "step": 1006 }, { "epoch": 2.14, "learning_rate": 1.6119106677712364e-06, "loss": 0.2728, "step": 1007 }, { "epoch": 2.14, "learning_rate": 1.6045585210575951e-06, "loss": 0.2182, "step": 1008 }, { "epoch": 2.14, "learning_rate": 1.5972189706726891e-06, "loss": 0.3468, "step": 1009 }, { "epoch": 2.14, "learning_rate": 1.589892055211238e-06, "loss": 0.2267, "step": 1010 }, { "epoch": 2.14, "learning_rate": 1.5825778132015174e-06, "loss": 0.2971, "step": 1011 }, { "epoch": 2.15, "learning_rate": 1.5752762831051655e-06, "loss": 0.2602, "step": 1012 }, { "epoch": 2.15, "learning_rate": 1.5679875033169698e-06, "loss": 0.254, "step": 1013 }, { "epoch": 2.15, "learning_rate": 1.560711512164675e-06, "loss": 0.2387, "step": 1014 }, { "epoch": 2.15, "learning_rate": 1.5534483479087772e-06, "loss": 0.26, "step": 1015 }, { "epoch": 2.15, "learning_rate": 1.5461980487423194e-06, "loss": 0.2452, "step": 1016 }, { "epoch": 2.16, "learning_rate": 1.5389606527906974e-06, "loss": 0.351, "step": 1017 }, { "epoch": 2.16, "learning_rate": 1.5317361981114557e-06, "loss": 0.2857, "step": 1018 }, { "epoch": 2.16, "learning_rate": 1.5245247226940845e-06, "loss": 0.2604, "step": 1019 }, { "epoch": 2.16, "learning_rate": 1.517326264459828e-06, "loss": 0.2795, "step": 1020 }, { "epoch": 2.17, "learning_rate": 1.5101408612614747e-06, "loss": 0.2843, "step": 1021 }, { "epoch": 2.17, "learning_rate": 1.5029685508831683e-06, "loss": 0.2592, "step": 1022 }, { "epoch": 2.17, "learning_rate": 1.4958093710402033e-06, "loss": 0.2407, "step": 1023 }, { "epoch": 2.17, "learning_rate": 1.4886633593788251e-06, "loss": 0.2696, "step": 1024 }, { "epoch": 2.17, "learning_rate": 1.4815305534760394e-06, "loss": 0.2416, "step": 1025 }, { "epoch": 2.18, "learning_rate": 1.4744109908394044e-06, "loss": 0.3104, "step": 1026 }, { "epoch": 2.18, "learning_rate": 1.4673047089068437e-06, "loss": 0.2491, "step": 1027 }, { "epoch": 2.18, "learning_rate": 1.460211745046445e-06, "loss": 0.2733, "step": 1028 }, { "epoch": 2.18, "learning_rate": 1.4531321365562588e-06, "loss": 0.2954, "step": 1029 }, { "epoch": 2.18, "learning_rate": 1.4460659206641116e-06, "loss": 0.2703, "step": 1030 }, { "epoch": 2.19, "learning_rate": 1.4390131345274048e-06, "loss": 0.2942, "step": 1031 }, { "epoch": 2.19, "learning_rate": 1.431973815232917e-06, "loss": 0.3826, "step": 1032 }, { "epoch": 2.19, "learning_rate": 1.4249479997966142e-06, "loss": 0.2039, "step": 1033 }, { "epoch": 2.19, "learning_rate": 1.4179357251634554e-06, "loss": 0.2487, "step": 1034 }, { "epoch": 2.19, "learning_rate": 1.41093702820719e-06, "loss": 0.2395, "step": 1035 }, { "epoch": 2.2, "learning_rate": 1.4039519457301738e-06, "loss": 0.28, "step": 1036 }, { "epoch": 2.2, "learning_rate": 1.3969805144631726e-06, "loss": 0.3089, "step": 1037 }, { "epoch": 2.2, "learning_rate": 1.3900227710651647e-06, "loss": 0.2551, "step": 1038 }, { "epoch": 2.2, "learning_rate": 1.3830787521231488e-06, "loss": 0.2607, "step": 1039 }, { "epoch": 2.21, "learning_rate": 1.3761484941519638e-06, "loss": 0.2322, "step": 1040 }, { "epoch": 2.21, "learning_rate": 1.3692320335940784e-06, "loss": 0.2388, "step": 1041 }, { "epoch": 2.21, "learning_rate": 1.3623294068194083e-06, "loss": 0.27, "step": 1042 }, { "epoch": 2.21, "learning_rate": 1.355440650125133e-06, "loss": 0.2368, "step": 1043 }, { "epoch": 2.21, "learning_rate": 1.3485657997354878e-06, "loss": 0.2532, "step": 1044 }, { "epoch": 2.22, "learning_rate": 1.3417048918015836e-06, "loss": 0.2646, "step": 1045 }, { "epoch": 2.22, "learning_rate": 1.3348579624012227e-06, "loss": 0.2736, "step": 1046 }, { "epoch": 2.22, "learning_rate": 1.3280250475386936e-06, "loss": 0.2414, "step": 1047 }, { "epoch": 2.22, "learning_rate": 1.321206183144591e-06, "loss": 0.2816, "step": 1048 }, { "epoch": 2.22, "learning_rate": 1.314401405075633e-06, "loss": 0.2208, "step": 1049 }, { "epoch": 2.23, "learning_rate": 1.307610749114458e-06, "loss": 0.3263, "step": 1050 }, { "epoch": 2.23, "learning_rate": 1.3008342509694439e-06, "loss": 0.2282, "step": 1051 }, { "epoch": 2.23, "learning_rate": 1.2940719462745246e-06, "loss": 0.255, "step": 1052 }, { "epoch": 2.23, "learning_rate": 1.2873238705889966e-06, "loss": 0.2878, "step": 1053 }, { "epoch": 2.24, "learning_rate": 1.280590059397332e-06, "loss": 0.2875, "step": 1054 }, { "epoch": 2.24, "learning_rate": 1.273870548108995e-06, "loss": 0.3157, "step": 1055 }, { "epoch": 2.24, "learning_rate": 1.2671653720582573e-06, "loss": 0.2602, "step": 1056 }, { "epoch": 2.24, "learning_rate": 1.2604745665040023e-06, "loss": 0.2217, "step": 1057 }, { "epoch": 2.24, "learning_rate": 1.2537981666295533e-06, "loss": 0.274, "step": 1058 }, { "epoch": 2.25, "learning_rate": 1.2471362075424802e-06, "loss": 0.2466, "step": 1059 }, { "epoch": 2.25, "learning_rate": 1.2404887242744137e-06, "loss": 0.2716, "step": 1060 }, { "epoch": 2.25, "learning_rate": 1.2338557517808674e-06, "loss": 0.2755, "step": 1061 }, { "epoch": 2.25, "learning_rate": 1.227237324941051e-06, "loss": 0.2414, "step": 1062 }, { "epoch": 2.25, "learning_rate": 1.2206334785576822e-06, "loss": 0.2685, "step": 1063 }, { "epoch": 2.26, "learning_rate": 1.2140442473568135e-06, "loss": 0.2686, "step": 1064 }, { "epoch": 2.26, "learning_rate": 1.2074696659876384e-06, "loss": 0.2292, "step": 1065 }, { "epoch": 2.26, "learning_rate": 1.2009097690223193e-06, "loss": 0.2626, "step": 1066 }, { "epoch": 2.26, "learning_rate": 1.194364590955801e-06, "loss": 0.2903, "step": 1067 }, { "epoch": 2.26, "learning_rate": 1.1878341662056257e-06, "loss": 0.3413, "step": 1068 }, { "epoch": 2.27, "learning_rate": 1.1813185291117603e-06, "loss": 0.2639, "step": 1069 }, { "epoch": 2.27, "learning_rate": 1.1748177139364103e-06, "loss": 0.3068, "step": 1070 }, { "epoch": 2.27, "learning_rate": 1.1683317548638382e-06, "loss": 0.2879, "step": 1071 }, { "epoch": 2.27, "learning_rate": 1.1618606860001907e-06, "loss": 0.2407, "step": 1072 }, { "epoch": 2.28, "learning_rate": 1.1554045413733095e-06, "loss": 0.278, "step": 1073 }, { "epoch": 2.28, "learning_rate": 1.148963354932563e-06, "loss": 0.2644, "step": 1074 }, { "epoch": 2.28, "learning_rate": 1.1425371605486605e-06, "loss": 0.2428, "step": 1075 }, { "epoch": 2.28, "learning_rate": 1.1361259920134747e-06, "loss": 0.243, "step": 1076 }, { "epoch": 2.28, "learning_rate": 1.1297298830398676e-06, "loss": 0.2757, "step": 1077 }, { "epoch": 2.29, "learning_rate": 1.123348867261512e-06, "loss": 0.3367, "step": 1078 }, { "epoch": 2.29, "learning_rate": 1.1169829782327091e-06, "loss": 0.2418, "step": 1079 }, { "epoch": 2.29, "learning_rate": 1.1106322494282236e-06, "loss": 0.2531, "step": 1080 }, { "epoch": 2.29, "learning_rate": 1.1042967142430933e-06, "loss": 0.2963, "step": 1081 }, { "epoch": 2.29, "learning_rate": 1.0979764059924668e-06, "loss": 0.3322, "step": 1082 }, { "epoch": 2.3, "learning_rate": 1.0916713579114217e-06, "loss": 0.2655, "step": 1083 }, { "epoch": 2.3, "learning_rate": 1.0853816031547865e-06, "loss": 0.2628, "step": 1084 }, { "epoch": 2.3, "learning_rate": 1.0791071747969743e-06, "loss": 0.2698, "step": 1085 }, { "epoch": 2.3, "learning_rate": 1.0728481058318054e-06, "loss": 0.2356, "step": 1086 }, { "epoch": 2.31, "learning_rate": 1.0666044291723305e-06, "loss": 0.2745, "step": 1087 }, { "epoch": 2.31, "learning_rate": 1.0603761776506614e-06, "loss": 0.242, "step": 1088 }, { "epoch": 2.31, "learning_rate": 1.0541633840178006e-06, "loss": 0.2456, "step": 1089 }, { "epoch": 2.31, "learning_rate": 1.04796608094346e-06, "loss": 0.2414, "step": 1090 }, { "epoch": 2.31, "learning_rate": 1.0417843010159e-06, "loss": 0.2361, "step": 1091 }, { "epoch": 2.32, "learning_rate": 1.035618076741753e-06, "loss": 0.2595, "step": 1092 }, { "epoch": 2.32, "learning_rate": 1.029467440545849e-06, "loss": 0.2387, "step": 1093 }, { "epoch": 2.32, "learning_rate": 1.0233324247710497e-06, "loss": 0.2423, "step": 1094 }, { "epoch": 2.32, "learning_rate": 1.0172130616780834e-06, "loss": 0.2851, "step": 1095 }, { "epoch": 2.32, "learning_rate": 1.0111093834453614e-06, "loss": 0.2492, "step": 1096 }, { "epoch": 2.33, "learning_rate": 1.005021422168819e-06, "loss": 0.2438, "step": 1097 }, { "epoch": 2.33, "learning_rate": 9.989492098617493e-07, "loss": 0.3107, "step": 1098 }, { "epoch": 2.33, "learning_rate": 9.928927784546251e-07, "loss": 0.2113, "step": 1099 }, { "epoch": 2.33, "learning_rate": 9.86852159794935e-07, "loss": 0.2067, "step": 1100 }, { "epoch": 2.33, "learning_rate": 9.808273856470228e-07, "loss": 0.2174, "step": 1101 }, { "epoch": 2.34, "learning_rate": 9.748184876919103e-07, "loss": 0.2451, "step": 1102 }, { "epoch": 2.34, "learning_rate": 9.688254975271325e-07, "loss": 0.2202, "step": 1103 }, { "epoch": 2.34, "learning_rate": 9.628484466665828e-07, "loss": 0.2694, "step": 1104 }, { "epoch": 2.34, "learning_rate": 9.568873665403302e-07, "loss": 0.2604, "step": 1105 }, { "epoch": 2.35, "learning_rate": 9.509422884944634e-07, "loss": 0.2958, "step": 1106 }, { "epoch": 2.35, "learning_rate": 9.450132437909282e-07, "loss": 0.3149, "step": 1107 }, { "epoch": 2.35, "learning_rate": 9.391002636073589e-07, "loss": 0.2795, "step": 1108 }, { "epoch": 2.35, "learning_rate": 9.332033790369118e-07, "loss": 0.2955, "step": 1109 }, { "epoch": 2.35, "learning_rate": 9.273226210881087e-07, "loss": 0.2134, "step": 1110 }, { "epoch": 2.36, "learning_rate": 9.214580206846707e-07, "loss": 0.2857, "step": 1111 }, { "epoch": 2.36, "learning_rate": 9.156096086653504e-07, "loss": 0.2571, "step": 1112 }, { "epoch": 2.36, "learning_rate": 9.097774157837799e-07, "loss": 0.2651, "step": 1113 }, { "epoch": 2.36, "learning_rate": 9.039614727083012e-07, "loss": 0.206, "step": 1114 }, { "epoch": 2.36, "learning_rate": 8.98161810021806e-07, "loss": 0.2589, "step": 1115 }, { "epoch": 2.37, "learning_rate": 8.923784582215788e-07, "loss": 0.302, "step": 1116 }, { "epoch": 2.37, "learning_rate": 8.866114477191335e-07, "loss": 0.2575, "step": 1117 }, { "epoch": 2.37, "learning_rate": 8.808608088400519e-07, "loss": 0.2391, "step": 1118 }, { "epoch": 2.37, "learning_rate": 8.751265718238295e-07, "loss": 0.2552, "step": 1119 }, { "epoch": 2.38, "learning_rate": 8.694087668237094e-07, "loss": 0.2551, "step": 1120 }, { "epoch": 2.38, "learning_rate": 8.637074239065314e-07, "loss": 0.2506, "step": 1121 }, { "epoch": 2.38, "learning_rate": 8.58022573052569e-07, "loss": 0.3408, "step": 1122 }, { "epoch": 2.38, "learning_rate": 8.523542441553711e-07, "loss": 0.2347, "step": 1123 }, { "epoch": 2.38, "learning_rate": 8.46702467021609e-07, "loss": 0.2537, "step": 1124 }, { "epoch": 2.39, "learning_rate": 8.410672713709148e-07, "loss": 0.2526, "step": 1125 }, { "epoch": 2.39, "learning_rate": 8.3544868683573e-07, "loss": 0.2116, "step": 1126 }, { "epoch": 2.39, "learning_rate": 8.298467429611466e-07, "loss": 0.2855, "step": 1127 }, { "epoch": 2.39, "learning_rate": 8.242614692047505e-07, "loss": 0.2903, "step": 1128 }, { "epoch": 2.39, "learning_rate": 8.186928949364703e-07, "loss": 0.2923, "step": 1129 }, { "epoch": 2.4, "learning_rate": 8.131410494384226e-07, "loss": 0.2848, "step": 1130 }, { "epoch": 2.4, "learning_rate": 8.076059619047515e-07, "loss": 0.2321, "step": 1131 }, { "epoch": 2.4, "learning_rate": 8.020876614414858e-07, "loss": 0.2647, "step": 1132 }, { "epoch": 2.4, "learning_rate": 7.965861770663748e-07, "loss": 0.33, "step": 1133 }, { "epoch": 2.4, "learning_rate": 7.911015377087458e-07, "loss": 0.2359, "step": 1134 }, { "epoch": 2.41, "learning_rate": 7.856337722093456e-07, "loss": 0.2609, "step": 1135 }, { "epoch": 2.41, "learning_rate": 7.801829093201879e-07, "loss": 0.273, "step": 1136 }, { "epoch": 2.41, "learning_rate": 7.747489777044088e-07, "loss": 0.2832, "step": 1137 }, { "epoch": 2.41, "learning_rate": 7.693320059361106e-07, "loss": 0.2981, "step": 1138 }, { "epoch": 2.42, "learning_rate": 7.639320225002106e-07, "loss": 0.2558, "step": 1139 }, { "epoch": 2.42, "learning_rate": 7.585490557922969e-07, "loss": 0.2668, "step": 1140 }, { "epoch": 2.42, "learning_rate": 7.531831341184753e-07, "loss": 0.2426, "step": 1141 }, { "epoch": 2.42, "learning_rate": 7.478342856952186e-07, "loss": 0.247, "step": 1142 }, { "epoch": 2.42, "learning_rate": 7.42502538649223e-07, "loss": 0.2606, "step": 1143 }, { "epoch": 2.43, "learning_rate": 7.371879210172584e-07, "loss": 0.2594, "step": 1144 }, { "epoch": 2.43, "learning_rate": 7.318904607460181e-07, "loss": 0.2985, "step": 1145 }, { "epoch": 2.43, "learning_rate": 7.266101856919728e-07, "loss": 0.2841, "step": 1146 }, { "epoch": 2.43, "learning_rate": 7.213471236212325e-07, "loss": 0.2486, "step": 1147 }, { "epoch": 2.43, "learning_rate": 7.16101302209386e-07, "loss": 0.2418, "step": 1148 }, { "epoch": 2.44, "learning_rate": 7.108727490413642e-07, "loss": 0.257, "step": 1149 }, { "epoch": 2.44, "learning_rate": 7.056614916112988e-07, "loss": 0.3122, "step": 1150 }, { "epoch": 2.44, "learning_rate": 7.00467557322367e-07, "loss": 0.2438, "step": 1151 }, { "epoch": 2.44, "learning_rate": 6.952909734866525e-07, "loss": 0.298, "step": 1152 }, { "epoch": 2.45, "learning_rate": 6.901317673250089e-07, "loss": 0.2087, "step": 1153 }, { "epoch": 2.45, "learning_rate": 6.849899659669036e-07, "loss": 0.2045, "step": 1154 }, { "epoch": 2.45, "learning_rate": 6.798655964502819e-07, "loss": 0.2591, "step": 1155 }, { "epoch": 2.45, "learning_rate": 6.747586857214305e-07, "loss": 0.2495, "step": 1156 }, { "epoch": 2.45, "learning_rate": 6.696692606348238e-07, "loss": 0.2941, "step": 1157 }, { "epoch": 2.46, "learning_rate": 6.645973479529891e-07, "loss": 0.2195, "step": 1158 }, { "epoch": 2.46, "learning_rate": 6.595429743463685e-07, "loss": 0.2938, "step": 1159 }, { "epoch": 2.46, "learning_rate": 6.545061663931743e-07, "loss": 0.2302, "step": 1160 }, { "epoch": 2.46, "learning_rate": 6.494869505792491e-07, "loss": 0.3048, "step": 1161 }, { "epoch": 2.46, "learning_rate": 6.444853532979295e-07, "loss": 0.2848, "step": 1162 }, { "epoch": 2.47, "learning_rate": 6.395014008499067e-07, "loss": 0.2343, "step": 1163 }, { "epoch": 2.47, "learning_rate": 6.345351194430835e-07, "loss": 0.2778, "step": 1164 }, { "epoch": 2.47, "learning_rate": 6.295865351924448e-07, "loss": 0.3015, "step": 1165 }, { "epoch": 2.47, "learning_rate": 6.246556741199134e-07, "loss": 0.3403, "step": 1166 }, { "epoch": 2.47, "learning_rate": 6.197425621542152e-07, "loss": 0.2828, "step": 1167 }, { "epoch": 2.48, "learning_rate": 6.148472251307435e-07, "loss": 0.3331, "step": 1168 }, { "epoch": 2.48, "learning_rate": 6.099696887914252e-07, "loss": 0.2602, "step": 1169 }, { "epoch": 2.48, "learning_rate": 6.05109978784578e-07, "loss": 0.2534, "step": 1170 }, { "epoch": 2.48, "learning_rate": 6.002681206647864e-07, "loss": 0.2424, "step": 1171 }, { "epoch": 2.49, "learning_rate": 5.954441398927561e-07, "loss": 0.2194, "step": 1172 }, { "epoch": 2.49, "learning_rate": 5.906380618351892e-07, "loss": 0.2377, "step": 1173 }, { "epoch": 2.49, "learning_rate": 5.858499117646465e-07, "loss": 0.2973, "step": 1174 }, { "epoch": 2.49, "learning_rate": 5.810797148594137e-07, "loss": 0.2768, "step": 1175 }, { "epoch": 2.49, "learning_rate": 5.763274962033726e-07, "loss": 0.2742, "step": 1176 }, { "epoch": 2.5, "learning_rate": 5.715932807858648e-07, "loss": 0.2622, "step": 1177 }, { "epoch": 2.5, "learning_rate": 5.668770935015641e-07, "loss": 0.2534, "step": 1178 }, { "epoch": 2.5, "learning_rate": 5.621789591503452e-07, "loss": 0.2347, "step": 1179 }, { "epoch": 2.5, "learning_rate": 5.574989024371493e-07, "loss": 0.275, "step": 1180 }, { "epoch": 2.5, "learning_rate": 5.528369479718594e-07, "loss": 0.2419, "step": 1181 }, { "epoch": 2.51, "learning_rate": 5.481931202691688e-07, "loss": 0.2678, "step": 1182 }, { "epoch": 2.51, "learning_rate": 5.435674437484489e-07, "loss": 0.2593, "step": 1183 }, { "epoch": 2.51, "learning_rate": 5.389599427336287e-07, "loss": 0.231, "step": 1184 }, { "epoch": 2.51, "learning_rate": 5.343706414530565e-07, "loss": 0.286, "step": 1185 }, { "epoch": 2.52, "learning_rate": 5.297995640393829e-07, "loss": 0.2812, "step": 1186 }, { "epoch": 2.52, "learning_rate": 5.252467345294271e-07, "loss": 0.2351, "step": 1187 }, { "epoch": 2.52, "learning_rate": 5.207121768640519e-07, "loss": 0.2122, "step": 1188 }, { "epoch": 2.52, "learning_rate": 5.161959148880384e-07, "loss": 0.2453, "step": 1189 }, { "epoch": 2.52, "learning_rate": 5.116979723499631e-07, "loss": 0.2435, "step": 1190 }, { "epoch": 2.53, "learning_rate": 5.072183729020661e-07, "loss": 0.2444, "step": 1191 }, { "epoch": 2.53, "learning_rate": 5.027571401001349e-07, "loss": 0.2233, "step": 1192 }, { "epoch": 2.53, "learning_rate": 4.983142974033763e-07, "loss": 0.2771, "step": 1193 }, { "epoch": 2.53, "learning_rate": 4.938898681742905e-07, "loss": 0.2549, "step": 1194 }, { "epoch": 2.53, "learning_rate": 4.894838756785544e-07, "loss": 0.2315, "step": 1195 }, { "epoch": 2.54, "learning_rate": 4.85096343084896e-07, "loss": 0.2603, "step": 1196 }, { "epoch": 2.54, "learning_rate": 4.807272934649709e-07, "loss": 0.2286, "step": 1197 }, { "epoch": 2.54, "learning_rate": 4.7637674979324185e-07, "loss": 0.2874, "step": 1198 }, { "epoch": 2.54, "learning_rate": 4.7204473494686457e-07, "loss": 0.2681, "step": 1199 }, { "epoch": 2.54, "learning_rate": 4.67731271705555e-07, "loss": 0.2081, "step": 1200 }, { "epoch": 2.55, "learning_rate": 4.6343638275147824e-07, "loss": 0.2378, "step": 1201 }, { "epoch": 2.55, "learning_rate": 4.591600906691315e-07, "loss": 0.2466, "step": 1202 }, { "epoch": 2.55, "learning_rate": 4.54902417945215e-07, "loss": 0.2377, "step": 1203 }, { "epoch": 2.55, "learning_rate": 4.506633869685217e-07, "loss": 0.2226, "step": 1204 }, { "epoch": 2.56, "learning_rate": 4.464430200298217e-07, "loss": 0.3036, "step": 1205 }, { "epoch": 2.56, "learning_rate": 4.422413393217361e-07, "loss": 0.2747, "step": 1206 }, { "epoch": 2.56, "learning_rate": 4.380583669386251e-07, "loss": 0.2607, "step": 1207 }, { "epoch": 2.56, "learning_rate": 4.3389412487647804e-07, "loss": 0.2405, "step": 1208 }, { "epoch": 2.56, "learning_rate": 4.297486350327846e-07, "loss": 0.2643, "step": 1209 }, { "epoch": 2.57, "learning_rate": 4.2562191920642965e-07, "loss": 0.2251, "step": 1210 }, { "epoch": 2.57, "learning_rate": 4.2151399909757626e-07, "loss": 0.241, "step": 1211 }, { "epoch": 2.57, "learning_rate": 4.1742489630755085e-07, "loss": 0.2522, "step": 1212 }, { "epoch": 2.57, "learning_rate": 4.1335463233872805e-07, "loss": 0.2456, "step": 1213 }, { "epoch": 2.57, "learning_rate": 4.0930322859442115e-07, "loss": 0.2997, "step": 1214 }, { "epoch": 2.58, "learning_rate": 4.0527070637876814e-07, "loss": 0.2668, "step": 1215 }, { "epoch": 2.58, "learning_rate": 4.0125708689661587e-07, "loss": 0.3431, "step": 1216 }, { "epoch": 2.58, "learning_rate": 3.972623912534163e-07, "loss": 0.2467, "step": 1217 }, { "epoch": 2.58, "learning_rate": 3.932866404551092e-07, "loss": 0.2797, "step": 1218 }, { "epoch": 2.59, "learning_rate": 3.8932985540801245e-07, "loss": 0.2452, "step": 1219 }, { "epoch": 2.59, "learning_rate": 3.8539205691871547e-07, "loss": 0.3477, "step": 1220 }, { "epoch": 2.59, "learning_rate": 3.8147326569396745e-07, "loss": 0.2702, "step": 1221 }, { "epoch": 2.59, "learning_rate": 3.775735023405664e-07, "loss": 0.2576, "step": 1222 }, { "epoch": 2.59, "learning_rate": 3.736927873652558e-07, "loss": 0.2545, "step": 1223 }, { "epoch": 2.6, "learning_rate": 3.69831141174612e-07, "loss": 0.2702, "step": 1224 }, { "epoch": 2.6, "learning_rate": 3.659885840749406e-07, "loss": 0.3055, "step": 1225 }, { "epoch": 2.6, "learning_rate": 3.6216513627216736e-07, "loss": 0.2787, "step": 1226 }, { "epoch": 2.6, "learning_rate": 3.5836081787173146e-07, "loss": 0.2892, "step": 1227 }, { "epoch": 2.6, "learning_rate": 3.5457564887848257e-07, "loss": 0.2413, "step": 1228 }, { "epoch": 2.61, "learning_rate": 3.5080964919657417e-07, "loss": 0.2573, "step": 1229 }, { "epoch": 2.61, "learning_rate": 3.470628386293564e-07, "loss": 0.2438, "step": 1230 }, { "epoch": 2.61, "learning_rate": 3.4333523687927725e-07, "loss": 0.3176, "step": 1231 }, { "epoch": 2.61, "learning_rate": 3.396268635477733e-07, "loss": 0.2656, "step": 1232 }, { "epoch": 2.61, "learning_rate": 3.3593773813517066e-07, "loss": 0.1924, "step": 1233 }, { "epoch": 2.62, "learning_rate": 3.32267880040582e-07, "loss": 0.2279, "step": 1234 }, { "epoch": 2.62, "learning_rate": 3.286173085618009e-07, "loss": 0.2721, "step": 1235 }, { "epoch": 2.62, "learning_rate": 3.2498604289520603e-07, "loss": 0.2232, "step": 1236 }, { "epoch": 2.62, "learning_rate": 3.2137410213565463e-07, "loss": 0.2646, "step": 1237 }, { "epoch": 2.63, "learning_rate": 3.1778150527638657e-07, "loss": 0.2748, "step": 1238 }, { "epoch": 2.63, "learning_rate": 3.1420827120892225e-07, "loss": 0.2535, "step": 1239 }, { "epoch": 2.63, "learning_rate": 3.1065441872296293e-07, "loss": 0.2551, "step": 1240 }, { "epoch": 2.63, "learning_rate": 3.0711996650629335e-07, "loss": 0.2831, "step": 1241 }, { "epoch": 2.63, "learning_rate": 3.036049331446833e-07, "loss": 0.2774, "step": 1242 }, { "epoch": 2.64, "learning_rate": 3.0010933712178733e-07, "loss": 0.2993, "step": 1243 }, { "epoch": 2.64, "learning_rate": 2.966331968190512e-07, "loss": 0.2857, "step": 1244 }, { "epoch": 2.64, "learning_rate": 2.93176530515614e-07, "loss": 0.3196, "step": 1245 }, { "epoch": 2.64, "learning_rate": 2.897393563882091e-07, "loss": 0.2551, "step": 1246 }, { "epoch": 2.64, "learning_rate": 2.8632169251107383e-07, "loss": 0.1975, "step": 1247 }, { "epoch": 2.65, "learning_rate": 2.8292355685585144e-07, "loss": 0.2521, "step": 1248 }, { "epoch": 2.65, "learning_rate": 2.7954496729149447e-07, "loss": 0.1795, "step": 1249 }, { "epoch": 2.65, "learning_rate": 2.761859415841745e-07, "loss": 0.2473, "step": 1250 }, { "epoch": 2.65, "learning_rate": 2.728464973971896e-07, "loss": 0.321, "step": 1251 }, { "epoch": 2.66, "learning_rate": 2.695266522908657e-07, "loss": 0.2644, "step": 1252 }, { "epoch": 2.66, "learning_rate": 2.662264237224687e-07, "loss": 0.2359, "step": 1253 }, { "epoch": 2.66, "learning_rate": 2.629458290461146e-07, "loss": 0.2755, "step": 1254 }, { "epoch": 2.66, "learning_rate": 2.5968488551267166e-07, "loss": 0.2305, "step": 1255 }, { "epoch": 2.66, "learning_rate": 2.5644361026967385e-07, "loss": 0.2777, "step": 1256 }, { "epoch": 2.67, "learning_rate": 2.532220203612341e-07, "loss": 0.2899, "step": 1257 }, { "epoch": 2.67, "learning_rate": 2.5002013272794653e-07, "loss": 0.2478, "step": 1258 }, { "epoch": 2.67, "learning_rate": 2.468379642068017e-07, "loss": 0.2211, "step": 1259 }, { "epoch": 2.67, "learning_rate": 2.4367553153110274e-07, "loss": 0.2067, "step": 1260 }, { "epoch": 2.67, "learning_rate": 2.4053285133036796e-07, "loss": 0.2107, "step": 1261 }, { "epoch": 2.68, "learning_rate": 2.3740994013024873e-07, "loss": 0.2695, "step": 1262 }, { "epoch": 2.68, "learning_rate": 2.3430681435244381e-07, "loss": 0.2686, "step": 1263 }, { "epoch": 2.68, "learning_rate": 2.3122349031461062e-07, "loss": 0.2197, "step": 1264 }, { "epoch": 2.68, "learning_rate": 2.2815998423027837e-07, "loss": 0.2406, "step": 1265 }, { "epoch": 2.68, "learning_rate": 2.251163122087667e-07, "loss": 0.2692, "step": 1266 }, { "epoch": 2.69, "learning_rate": 2.2209249025509692e-07, "loss": 0.2611, "step": 1267 }, { "epoch": 2.69, "learning_rate": 2.1908853426990982e-07, "loss": 0.2462, "step": 1268 }, { "epoch": 2.69, "learning_rate": 2.161044600493831e-07, "loss": 0.3073, "step": 1269 }, { "epoch": 2.69, "learning_rate": 2.1314028328514566e-07, "loss": 0.2099, "step": 1270 }, { "epoch": 2.7, "learning_rate": 2.1019601956419674e-07, "loss": 0.2273, "step": 1271 }, { "epoch": 2.7, "learning_rate": 2.0727168436882382e-07, "loss": 0.293, "step": 1272 }, { "epoch": 2.7, "learning_rate": 2.0436729307652212e-07, "loss": 0.235, "step": 1273 }, { "epoch": 2.7, "learning_rate": 2.0148286095990996e-07, "loss": 0.2978, "step": 1274 }, { "epoch": 2.7, "learning_rate": 1.9861840318665445e-07, "loss": 0.2407, "step": 1275 }, { "epoch": 2.71, "learning_rate": 1.9577393481938586e-07, "loss": 0.2987, "step": 1276 }, { "epoch": 2.71, "learning_rate": 1.9294947081562208e-07, "loss": 0.2359, "step": 1277 }, { "epoch": 2.71, "learning_rate": 1.9014502602769e-07, "loss": 0.3236, "step": 1278 }, { "epoch": 2.71, "learning_rate": 1.8736061520264346e-07, "loss": 0.2285, "step": 1279 }, { "epoch": 2.71, "learning_rate": 1.8459625298219117e-07, "loss": 0.2466, "step": 1280 }, { "epoch": 2.72, "learning_rate": 1.8185195390261643e-07, "loss": 0.2181, "step": 1281 }, { "epoch": 2.72, "learning_rate": 1.791277323946998e-07, "loss": 0.2567, "step": 1282 }, { "epoch": 2.72, "learning_rate": 1.7642360278364765e-07, "loss": 0.2746, "step": 1283 }, { "epoch": 2.72, "learning_rate": 1.737395792890113e-07, "loss": 0.315, "step": 1284 }, { "epoch": 2.72, "learning_rate": 1.7107567602461547e-07, "loss": 0.2386, "step": 1285 }, { "epoch": 2.73, "learning_rate": 1.6843190699848565e-07, "loss": 0.2142, "step": 1286 }, { "epoch": 2.73, "learning_rate": 1.658082861127692e-07, "loss": 0.2747, "step": 1287 }, { "epoch": 2.73, "learning_rate": 1.6320482716366725e-07, "loss": 0.3016, "step": 1288 }, { "epoch": 2.73, "learning_rate": 1.6062154384135894e-07, "loss": 0.2739, "step": 1289 }, { "epoch": 2.74, "learning_rate": 1.5805844972993243e-07, "loss": 0.2921, "step": 1290 }, { "epoch": 2.74, "learning_rate": 1.555155583073109e-07, "loss": 0.3238, "step": 1291 }, { "epoch": 2.74, "learning_rate": 1.529928829451812e-07, "loss": 0.2896, "step": 1292 }, { "epoch": 2.74, "learning_rate": 1.5049043690892727e-07, "loss": 0.2519, "step": 1293 }, { "epoch": 2.74, "learning_rate": 1.4800823335755676e-07, "loss": 0.2463, "step": 1294 }, { "epoch": 2.75, "learning_rate": 1.4554628534363266e-07, "loss": 0.2411, "step": 1295 }, { "epoch": 2.75, "learning_rate": 1.4310460581320505e-07, "loss": 0.2541, "step": 1296 }, { "epoch": 2.75, "learning_rate": 1.4068320760574516e-07, "loss": 0.256, "step": 1297 }, { "epoch": 2.75, "learning_rate": 1.3828210345407265e-07, "loss": 0.2276, "step": 1298 }, { "epoch": 2.75, "learning_rate": 1.359013059842935e-07, "loss": 0.3029, "step": 1299 }, { "epoch": 2.76, "learning_rate": 1.3354082771573238e-07, "loss": 0.2583, "step": 1300 }, { "epoch": 2.76, "learning_rate": 1.3120068106086392e-07, "loss": 0.3016, "step": 1301 }, { "epoch": 2.76, "learning_rate": 1.2888087832525264e-07, "loss": 0.2739, "step": 1302 }, { "epoch": 2.76, "learning_rate": 1.265814317074838e-07, "loss": 0.2576, "step": 1303 }, { "epoch": 2.77, "learning_rate": 1.2430235329910076e-07, "loss": 0.2464, "step": 1304 }, { "epoch": 2.77, "learning_rate": 1.2204365508454185e-07, "loss": 0.238, "step": 1305 }, { "epoch": 2.77, "learning_rate": 1.1980534894107774e-07, "loss": 0.2292, "step": 1306 }, { "epoch": 2.77, "learning_rate": 1.1758744663874765e-07, "loss": 0.3191, "step": 1307 }, { "epoch": 2.77, "learning_rate": 1.1538995984029653e-07, "loss": 0.2299, "step": 1308 }, { "epoch": 2.78, "learning_rate": 1.1321290010111884e-07, "loss": 0.2536, "step": 1309 }, { "epoch": 2.78, "learning_rate": 1.110562788691909e-07, "loss": 0.2465, "step": 1310 }, { "epoch": 2.78, "learning_rate": 1.0892010748501413e-07, "loss": 0.3041, "step": 1311 }, { "epoch": 2.78, "learning_rate": 1.0680439718155865e-07, "loss": 0.213, "step": 1312 }, { "epoch": 2.78, "learning_rate": 1.0470915908419708e-07, "loss": 0.2786, "step": 1313 }, { "epoch": 2.79, "learning_rate": 1.0263440421065128e-07, "loss": 0.1773, "step": 1314 }, { "epoch": 2.79, "learning_rate": 1.0058014347093324e-07, "loss": 0.2504, "step": 1315 }, { "epoch": 2.79, "learning_rate": 9.85463876672874e-08, "loss": 0.2554, "step": 1316 }, { "epoch": 2.79, "learning_rate": 9.653314749413244e-08, "loss": 0.2249, "step": 1317 }, { "epoch": 2.79, "learning_rate": 9.4540433538008e-08, "loss": 0.2648, "step": 1318 }, { "epoch": 2.8, "learning_rate": 9.256825627751785e-08, "loss": 0.268, "step": 1319 }, { "epoch": 2.8, "learning_rate": 9.061662608327214e-08, "loss": 0.2306, "step": 1320 }, { "epoch": 2.8, "learning_rate": 8.868555321783765e-08, "loss": 0.2583, "step": 1321 }, { "epoch": 2.8, "learning_rate": 8.677504783568013e-08, "loss": 0.2736, "step": 1322 }, { "epoch": 2.81, "learning_rate": 8.488511998311132e-08, "loss": 0.225, "step": 1323 }, { "epoch": 2.81, "learning_rate": 8.301577959823802e-08, "loss": 0.292, "step": 1324 }, { "epoch": 2.81, "learning_rate": 8.116703651090916e-08, "loss": 0.3001, "step": 1325 }, { "epoch": 2.81, "learning_rate": 7.933890044266167e-08, "loss": 0.1987, "step": 1326 }, { "epoch": 2.81, "learning_rate": 7.753138100667334e-08, "loss": 0.2309, "step": 1327 }, { "epoch": 2.82, "learning_rate": 7.574448770771003e-08, "loss": 0.2266, "step": 1328 }, { "epoch": 2.82, "learning_rate": 7.39782299420737e-08, "loss": 0.208, "step": 1329 }, { "epoch": 2.82, "learning_rate": 7.2232616997558e-08, "loss": 0.2336, "step": 1330 }, { "epoch": 2.82, "learning_rate": 7.050765805339542e-08, "loss": 0.2604, "step": 1331 }, { "epoch": 2.82, "learning_rate": 6.880336218020977e-08, "loss": 0.2501, "step": 1332 }, { "epoch": 2.83, "learning_rate": 6.711973833997087e-08, "loss": 0.255, "step": 1333 }, { "epoch": 2.83, "learning_rate": 6.545679538594262e-08, "loss": 0.2789, "step": 1334 }, { "epoch": 2.83, "learning_rate": 6.38145420626417e-08, "loss": 0.2394, "step": 1335 }, { "epoch": 2.83, "learning_rate": 6.219298700578824e-08, "loss": 0.2728, "step": 1336 }, { "epoch": 2.84, "learning_rate": 6.059213874226188e-08, "loss": 0.2935, "step": 1337 }, { "epoch": 2.84, "learning_rate": 5.9012005690056484e-08, "loss": 0.2304, "step": 1338 }, { "epoch": 2.84, "learning_rate": 5.7452596158234836e-08, "loss": 0.2665, "step": 1339 }, { "epoch": 2.84, "learning_rate": 5.591391834688686e-08, "loss": 0.3066, "step": 1340 }, { "epoch": 2.84, "learning_rate": 5.439598034708614e-08, "loss": 0.294, "step": 1341 }, { "epoch": 2.85, "learning_rate": 5.289879014084464e-08, "loss": 0.2261, "step": 1342 }, { "epoch": 2.85, "learning_rate": 5.142235560107622e-08, "loss": 0.3047, "step": 1343 }, { "epoch": 2.85, "learning_rate": 4.9966684491548286e-08, "loss": 0.2357, "step": 1344 }, { "epoch": 2.85, "learning_rate": 4.853178446684758e-08, "loss": 0.2664, "step": 1345 }, { "epoch": 2.85, "learning_rate": 4.711766307233578e-08, "loss": 0.221, "step": 1346 }, { "epoch": 2.86, "learning_rate": 4.572432774411039e-08, "loss": 0.235, "step": 1347 }, { "epoch": 2.86, "learning_rate": 4.435178580896748e-08, "loss": 0.2497, "step": 1348 }, { "epoch": 2.86, "learning_rate": 4.300004448436123e-08, "loss": 0.2267, "step": 1349 }, { "epoch": 2.86, "learning_rate": 4.1669110878366664e-08, "loss": 0.2585, "step": 1350 }, { "epoch": 2.86, "learning_rate": 4.0358991989642324e-08, "loss": 0.2499, "step": 1351 }, { "epoch": 2.87, "learning_rate": 3.9069694707393855e-08, "loss": 0.2798, "step": 1352 }, { "epoch": 2.87, "learning_rate": 3.7801225811336713e-08, "loss": 0.2736, "step": 1353 }, { "epoch": 2.87, "learning_rate": 3.655359197166197e-08, "loss": 0.2375, "step": 1354 }, { "epoch": 2.87, "learning_rate": 3.532679974899943e-08, "loss": 0.2507, "step": 1355 }, { "epoch": 2.88, "learning_rate": 3.412085559438527e-08, "loss": 0.2787, "step": 1356 }, { "epoch": 2.88, "learning_rate": 3.293576584922508e-08, "loss": 0.2832, "step": 1357 }, { "epoch": 2.88, "learning_rate": 3.177153674526556e-08, "loss": 0.2679, "step": 1358 }, { "epoch": 2.88, "learning_rate": 3.062817440455534e-08, "loss": 0.272, "step": 1359 }, { "epoch": 2.88, "learning_rate": 2.9505684839417067e-08, "loss": 0.2807, "step": 1360 }, { "epoch": 2.89, "learning_rate": 2.8404073952416284e-08, "loss": 0.3096, "step": 1361 }, { "epoch": 2.89, "learning_rate": 2.73233475363277e-08, "loss": 0.2709, "step": 1362 }, { "epoch": 2.89, "learning_rate": 2.6263511274104976e-08, "loss": 0.2428, "step": 1363 }, { "epoch": 2.89, "learning_rate": 2.5224570738853202e-08, "loss": 0.2544, "step": 1364 }, { "epoch": 2.89, "learning_rate": 2.4206531393798246e-08, "loss": 0.3054, "step": 1365 }, { "epoch": 2.9, "learning_rate": 2.3209398592256125e-08, "loss": 0.2663, "step": 1366 }, { "epoch": 2.9, "learning_rate": 2.2233177577609007e-08, "loss": 0.2688, "step": 1367 }, { "epoch": 2.9, "learning_rate": 2.1277873483274145e-08, "loss": 0.2266, "step": 1368 }, { "epoch": 2.9, "learning_rate": 2.0343491332677653e-08, "loss": 0.2298, "step": 1369 }, { "epoch": 2.91, "learning_rate": 1.9430036039229213e-08, "loss": 0.2277, "step": 1370 }, { "epoch": 2.91, "learning_rate": 1.853751240629542e-08, "loss": 0.2375, "step": 1371 }, { "epoch": 2.91, "learning_rate": 1.7665925127173576e-08, "loss": 0.2523, "step": 1372 }, { "epoch": 2.91, "learning_rate": 1.681527878506994e-08, "loss": 0.2578, "step": 1373 }, { "epoch": 2.91, "learning_rate": 1.598557785307264e-08, "loss": 0.2307, "step": 1374 }, { "epoch": 2.92, "learning_rate": 1.5176826694128563e-08, "loss": 0.2681, "step": 1375 }, { "epoch": 2.92, "learning_rate": 1.4389029561022059e-08, "loss": 0.2968, "step": 1376 }, { "epoch": 2.92, "learning_rate": 1.3622190596351835e-08, "loss": 0.218, "step": 1377 }, { "epoch": 2.92, "learning_rate": 1.2876313832508312e-08, "loss": 0.2747, "step": 1378 }, { "epoch": 2.92, "learning_rate": 1.2151403191652754e-08, "loss": 0.2337, "step": 1379 }, { "epoch": 2.93, "learning_rate": 1.1447462485697723e-08, "loss": 0.2258, "step": 1380 }, { "epoch": 2.93, "learning_rate": 1.0764495416286212e-08, "loss": 0.238, "step": 1381 }, { "epoch": 2.93, "learning_rate": 1.0102505574771659e-08, "loss": 0.2424, "step": 1382 }, { "epoch": 2.93, "learning_rate": 9.461496442199735e-09, "loss": 0.2527, "step": 1383 }, { "epoch": 2.93, "learning_rate": 8.84147138929059e-09, "loss": 0.2335, "step": 1384 }, { "epoch": 2.94, "learning_rate": 8.24243367642019e-09, "loss": 0.2668, "step": 1385 }, { "epoch": 2.94, "learning_rate": 7.664386453602567e-09, "loss": 0.2323, "step": 1386 }, { "epoch": 2.94, "learning_rate": 7.107332760475149e-09, "loss": 0.3155, "step": 1387 }, { "epoch": 2.94, "learning_rate": 6.57127552628145e-09, "loss": 0.2288, "step": 1388 }, { "epoch": 2.95, "learning_rate": 6.056217569855971e-09, "loss": 0.2449, "step": 1389 }, { "epoch": 2.95, "learning_rate": 5.5621615996099825e-09, "loss": 0.2525, "step": 1390 }, { "epoch": 2.95, "learning_rate": 5.089110213515102e-09, "loss": 0.2184, "step": 1391 }, { "epoch": 2.95, "learning_rate": 4.637065899092629e-09, "loss": 0.2384, "step": 1392 }, { "epoch": 2.95, "learning_rate": 4.206031033399338e-09, "loss": 0.1903, "step": 1393 }, { "epoch": 2.96, "learning_rate": 3.7960078830132635e-09, "loss": 0.2389, "step": 1394 }, { "epoch": 2.96, "learning_rate": 3.406998604023936e-09, "loss": 0.2197, "step": 1395 }, { "epoch": 2.96, "learning_rate": 3.0390052420208313e-09, "loss": 0.2488, "step": 1396 }, { "epoch": 2.96, "learning_rate": 2.69202973208138e-09, "loss": 0.3215, "step": 1397 }, { "epoch": 2.96, "learning_rate": 2.3660738987616447e-09, "loss": 0.2713, "step": 1398 }, { "epoch": 2.97, "learning_rate": 2.061139456087435e-09, "loss": 0.2686, "step": 1399 }, { "epoch": 2.97, "learning_rate": 1.7772280075427637e-09, "loss": 0.2983, "step": 1400 }, { "epoch": 2.97, "learning_rate": 1.5143410460645157e-09, "loss": 0.2746, "step": 1401 }, { "epoch": 2.97, "learning_rate": 1.2724799540331233e-09, "loss": 0.2684, "step": 1402 }, { "epoch": 2.98, "learning_rate": 1.0516460032641283e-09, "loss": 0.2348, "step": 1403 }, { "epoch": 2.98, "learning_rate": 8.518403550046294e-10, "loss": 0.2285, "step": 1404 }, { "epoch": 2.98, "learning_rate": 6.730640599239557e-10, "loss": 0.2542, "step": 1405 }, { "epoch": 2.98, "learning_rate": 5.153180581092265e-10, "loss": 0.2855, "step": 1406 }, { "epoch": 2.98, "learning_rate": 3.7860317906224236e-10, "loss": 0.2713, "step": 1407 }, { "epoch": 2.99, "learning_rate": 2.629201416910476e-10, "loss": 0.2403, "step": 1408 }, { "epoch": 2.99, "learning_rate": 1.6826955431126221e-10, "loss": 0.3237, "step": 1409 }, { "epoch": 2.99, "learning_rate": 9.465191463853273e-11, "loss": 0.2607, "step": 1410 }, { "epoch": 2.99, "learning_rate": 4.206760978853197e-11, "loss": 0.1945, "step": 1411 }, { "epoch": 2.99, "learning_rate": 1.0516916272962362e-11, "loss": 0.2344, "step": 1412 }, { "epoch": 3.0, "learning_rate": 0.0, "loss": 0.2814, "step": 1413 }, { "epoch": 3.0, "step": 1413, "total_flos": 5.437824739505494e+21, "train_loss": 0.38383744233100026, "train_runtime": 18726.0235, "train_samples_per_second": 9.443, "train_steps_per_second": 0.075 } ], "logging_steps": 1.0, "max_steps": 1413, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 200, "total_flos": 5.437824739505494e+21, "train_batch_size": 1, "trial_name": null, "trial_params": null }